diff --git a/examples/research_projects/bertabs/modeling_bertabs.py b/examples/research_projects/bertabs/modeling_bertabs.py index 2ebce46656..66f2320ebd 100644 --- a/examples/research_projects/bertabs/modeling_bertabs.py +++ b/examples/research_projects/bertabs/modeling_bertabs.py @@ -33,10 +33,6 @@ from transformers import BertConfig, BertModel, PreTrainedModel MAX_SIZE = 5000 -BERTABS_FINETUNED_MODEL_ARCHIVE_LIST = [ - "remi/bertabs-finetuned-cnndm-extractive-abstractive-summarization", -] - class BertAbsPreTrainedModel(PreTrainedModel): config_class = BertAbsConfig diff --git a/src/transformers/__init__.py b/src/transformers/__init__.py index cd5852924e..23e1d14114 100644 --- a/src/transformers/__init__.py +++ b/src/transformers/__init__.py @@ -726,7 +726,7 @@ _import_structure = { "ProphetNetTokenizer", ], "models.pvt": ["PVT_PRETRAINED_CONFIG_ARCHIVE_MAP", "PvtConfig"], - "models.pvt_v2": ["PVT_V2_PRETRAINED_CONFIG_ARCHIVE_MAP", "PvtV2Config"], + "models.pvt_v2": ["PvtV2Config"], "models.qdqbert": ["QDQBERT_PRETRAINED_CONFIG_ARCHIVE_MAP", "QDQBertConfig"], "models.qwen2": [ "QWEN2_PRETRAINED_CONFIG_ARCHIVE_MAP", @@ -3050,7 +3050,6 @@ else: ) _import_structure["models.pvt_v2"].extend( [ - "PVT_V2_PRETRAINED_MODEL_ARCHIVE_LIST", "PvtV2Backbone", "PvtV2ForImageClassification", "PvtV2Model", @@ -5602,7 +5601,7 @@ if TYPE_CHECKING: ProphetNetTokenizer, ) from .models.pvt import PVT_PRETRAINED_CONFIG_ARCHIVE_MAP, PvtConfig - from .models.pvt_v2 import PVT_V2_PRETRAINED_CONFIG_ARCHIVE_MAP, PvtV2Config + from .models.pvt_v2 import PvtV2Config from .models.qdqbert import QDQBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, QDQBertConfig from .models.qwen2 import QWEN2_PRETRAINED_CONFIG_ARCHIVE_MAP, Qwen2Config, Qwen2Tokenizer from .models.rag import RagConfig, RagRetriever, RagTokenizer @@ -7623,7 +7622,6 @@ if TYPE_CHECKING: PvtPreTrainedModel, ) from .models.pvt_v2 import ( - PVT_V2_PRETRAINED_MODEL_ARCHIVE_LIST, PvtV2Backbone, PvtV2ForImageClassification, PvtV2Model, diff --git a/src/transformers/commands/add_new_model_like.py b/src/transformers/commands/add_new_model_like.py index 3b7fcdf19f..626e837319 100644 --- a/src/transformers/commands/add_new_model_like.py +++ b/src/transformers/commands/add_new_model_like.py @@ -527,35 +527,6 @@ def duplicate_module( # Loop and treat all objects new_objects = [] for obj in objects: - # Special cases - if "PRETRAINED_CONFIG_ARCHIVE_MAP = {" in obj: - # docstyle-ignore - obj = ( - f"{new_model_patterns.model_upper_cased}_PRETRAINED_CONFIG_ARCHIVE_MAP = " - + "{" - + f""" - "{new_model_patterns.checkpoint}": "https://huggingface.co/{new_model_patterns.checkpoint}/resolve/main/config.json", -""" - + "}\n" - ) - new_objects.append(obj) - continue - elif "PRETRAINED_MODEL_ARCHIVE_LIST = [" in obj: - if obj.startswith("TF_"): - prefix = "TF_" - elif obj.startswith("FLAX_"): - prefix = "FLAX_" - else: - prefix = "" - # docstyle-ignore - obj = f"""{prefix}{new_model_patterns.model_upper_cased}_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "{new_model_patterns.checkpoint}", - # See all {new_model_patterns.model_name} models at https://huggingface.co/models?filter={new_model_patterns.model_type} -] -""" - new_objects.append(obj) - continue - special_pattern = False for pattern, attr in SPECIAL_PATTERNS.items(): if pattern in obj: @@ -785,7 +756,6 @@ def retrieve_info_for_model(model_type, frameworks: Optional[List[str]] = None): model_name = auto_module.MODEL_NAMES_MAPPING[model_type] config_class = auto_module.configuration_auto.CONFIG_MAPPING_NAMES[model_type] - archive_map = auto_module.configuration_auto.CONFIG_ARCHIVE_MAP_MAPPING_NAMES.get(model_type, None) if model_type in auto_module.tokenization_auto.TOKENIZER_MAPPING_NAMES: tokenizer_classes = auto_module.tokenization_auto.TOKENIZER_MAPPING_NAMES[model_type] tokenizer_class = tokenizer_classes[0] if tokenizer_classes[0] is not None else tokenizer_classes[1] @@ -814,19 +784,7 @@ def retrieve_info_for_model(model_type, frameworks: Optional[List[str]] = None): model_classes = retrieve_model_classes(model_type, frameworks=frameworks) - # Retrieve model upper-cased name from the constant name of the pretrained archive map. - if archive_map is None: - model_upper_cased = model_camel_cased.upper() - else: - parts = archive_map.split("_") - idx = 0 - while idx < len(parts) and parts[idx] != "PRETRAINED": - idx += 1 - if idx < len(parts): - model_upper_cased = "_".join(parts[:idx]) - else: - model_upper_cased = model_camel_cased.upper() - + model_upper_cased = model_camel_cased.upper() model_patterns = ModelPatterns( model_name, checkpoint=find_base_model_checkpoint(model_type, model_files=model_files), @@ -1135,14 +1093,6 @@ def add_model_to_auto_classes( for attr in ["model_type", "model_name"]: old_model_line = old_model_line.replace("{" + attr + "}", getattr(old_model_patterns, attr)) new_model_line = new_model_line.replace("{" + attr + "}", getattr(new_model_patterns, attr)) - if "pretrained_archive_map" in pattern: - old_model_line = old_model_line.replace( - "{pretrained_archive_map}", f"{old_model_patterns.model_upper_cased}_PRETRAINED_CONFIG_ARCHIVE_MAP" - ) - new_model_line = new_model_line.replace( - "{pretrained_archive_map}", f"{new_model_patterns.model_upper_cased}_PRETRAINED_CONFIG_ARCHIVE_MAP" - ) - new_model_line = new_model_line.replace( old_model_patterns.model_camel_cased, new_model_patterns.model_camel_cased ) diff --git a/src/transformers/convert_pytorch_checkpoint_to_tf2.py b/src/transformers/convert_pytorch_checkpoint_to_tf2.py index 12f89ff2e5..c544c8c9e1 100755 --- a/src/transformers/convert_pytorch_checkpoint_to_tf2.py +++ b/src/transformers/convert_pytorch_checkpoint_to_tf2.py @@ -19,28 +19,6 @@ import argparse import os from . import ( - ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, - BART_PRETRAINED_MODEL_ARCHIVE_LIST, - BERT_PRETRAINED_CONFIG_ARCHIVE_MAP, - CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, - CTRL_PRETRAINED_CONFIG_ARCHIVE_MAP, - DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, - DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST, - DPR_QUESTION_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST, - DPR_READER_PRETRAINED_MODEL_ARCHIVE_LIST, - ELECTRA_PRETRAINED_CONFIG_ARCHIVE_MAP, - FLAUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, - GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP, - LAYOUTLM_PRETRAINED_MODEL_ARCHIVE_LIST, - LXMERT_PRETRAINED_CONFIG_ARCHIVE_MAP, - OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP, - ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, - T5_PRETRAINED_CONFIG_ARCHIVE_MAP, - TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP, - WAV_2_VEC_2_PRETRAINED_CONFIG_ARCHIVE_MAP, - XLM_PRETRAINED_CONFIG_ARCHIVE_MAP, - XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, - XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP, AlbertConfig, BartConfig, BertConfig, @@ -140,31 +118,26 @@ MODEL_CLASSES = { TFBartForConditionalGeneration, TFBartForSequenceClassification, BartForConditionalGeneration, - BART_PRETRAINED_MODEL_ARCHIVE_LIST, ), "bert": ( BertConfig, TFBertForPreTraining, BertForPreTraining, - BERT_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad": ( BertConfig, TFBertForQuestionAnswering, BertForQuestionAnswering, - BERT_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "google-bert/bert-large-cased-whole-word-masking-finetuned-squad": ( BertConfig, TFBertForQuestionAnswering, BertForQuestionAnswering, - BERT_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "google-bert/bert-base-cased-finetuned-mrpc": ( BertConfig, TFBertForSequenceClassification, BertForSequenceClassification, - BERT_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "dpr": ( DPRConfig, @@ -174,130 +147,107 @@ MODEL_CLASSES = { DPRQuestionEncoder, DPRContextEncoder, DPRReader, - DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST, - DPR_QUESTION_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST, - DPR_READER_PRETRAINED_MODEL_ARCHIVE_LIST, ), "openai-community/gpt2": ( GPT2Config, TFGPT2LMHeadModel, GPT2LMHeadModel, - GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "xlnet": ( XLNetConfig, TFXLNetLMHeadModel, XLNetLMHeadModel, - XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "xlm": ( XLMConfig, TFXLMWithLMHeadModel, XLMWithLMHeadModel, - XLM_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "xlm-roberta": ( XLMRobertaConfig, TFXLMRobertaForMaskedLM, XLMRobertaForMaskedLM, - XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "transfo-xl": ( TransfoXLConfig, TFTransfoXLLMHeadModel, TransfoXLLMHeadModel, - TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "openai-community/openai-gpt": ( OpenAIGPTConfig, TFOpenAIGPTLMHeadModel, OpenAIGPTLMHeadModel, - OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "roberta": ( RobertaConfig, TFRobertaForCausalLM, TFRobertaForMaskedLM, RobertaForMaskedLM, - ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "layoutlm": ( LayoutLMConfig, TFLayoutLMForMaskedLM, LayoutLMForMaskedLM, - LAYOUTLM_PRETRAINED_MODEL_ARCHIVE_LIST, ), "FacebookAI/roberta-large-mnli": ( RobertaConfig, TFRobertaForSequenceClassification, RobertaForSequenceClassification, - ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "camembert": ( CamembertConfig, TFCamembertForMaskedLM, CamembertForMaskedLM, - CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "flaubert": ( FlaubertConfig, TFFlaubertWithLMHeadModel, FlaubertWithLMHeadModel, - FLAUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "distilbert": ( DistilBertConfig, TFDistilBertForMaskedLM, DistilBertForMaskedLM, - DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "distilbert-base-distilled-squad": ( DistilBertConfig, TFDistilBertForQuestionAnswering, DistilBertForQuestionAnswering, - DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "lxmert": ( LxmertConfig, TFLxmertForPreTraining, LxmertForPreTraining, - LXMERT_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "lxmert-visual-feature-encoder": ( LxmertConfig, TFLxmertVisualFeatureEncoder, LxmertVisualFeatureEncoder, - LXMERT_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "Salesforce/ctrl": ( CTRLConfig, TFCTRLLMHeadModel, CTRLLMHeadModel, - CTRL_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "albert": ( AlbertConfig, TFAlbertForPreTraining, AlbertForPreTraining, - ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "t5": ( T5Config, TFT5ForConditionalGeneration, T5ForConditionalGeneration, - T5_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "electra": ( ElectraConfig, TFElectraForPreTraining, ElectraForPreTraining, - ELECTRA_PRETRAINED_CONFIG_ARCHIVE_MAP, ), "wav2vec2": ( Wav2Vec2Config, TFWav2Vec2Model, Wav2Vec2Model, - WAV_2_VEC_2_PRETRAINED_CONFIG_ARCHIVE_MAP, ), } diff --git a/src/transformers/models/albert/configuration_albert.py b/src/transformers/models/albert/configuration_albert.py index 690be7fbbf..c5ddded483 100644 --- a/src/transformers/models/albert/configuration_albert.py +++ b/src/transformers/models/albert/configuration_albert.py @@ -19,18 +19,7 @@ from typing import Mapping from ...configuration_utils import PretrainedConfig from ...onnx import OnnxConfig - - -ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "albert/albert-base-v1": "https://huggingface.co/albert/albert-base-v1/resolve/main/config.json", - "albert/albert-large-v1": "https://huggingface.co/albert/albert-large-v1/resolve/main/config.json", - "albert/albert-xlarge-v1": "https://huggingface.co/albert/albert-xlarge-v1/resolve/main/config.json", - "albert/albert-xxlarge-v1": "https://huggingface.co/albert/albert-xxlarge-v1/resolve/main/config.json", - "albert/albert-base-v2": "https://huggingface.co/albert/albert-base-v2/resolve/main/config.json", - "albert/albert-large-v2": "https://huggingface.co/albert/albert-large-v2/resolve/main/config.json", - "albert/albert-xlarge-v2": "https://huggingface.co/albert/albert-xlarge-v2/resolve/main/config.json", - "albert/albert-xxlarge-v2": "https://huggingface.co/albert/albert-xxlarge-v2/resolve/main/config.json", -} +from ..deprecated._archive_maps import ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class AlbertConfig(PretrainedConfig): diff --git a/src/transformers/models/albert/modeling_albert.py b/src/transformers/models/albert/modeling_albert.py index 25ae832b03..87f5a9e30c 100755 --- a/src/transformers/models/albert/modeling_albert.py +++ b/src/transformers/models/albert/modeling_albert.py @@ -52,17 +52,7 @@ _CHECKPOINT_FOR_DOC = "albert/albert-base-v2" _CONFIG_FOR_DOC = "AlbertConfig" -ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "albert/albert-base-v1", - "albert/albert-large-v1", - "albert/albert-xlarge-v1", - "albert/albert-xxlarge-v1", - "albert/albert-base-v2", - "albert/albert-large-v2", - "albert/albert-xlarge-v2", - "albert/albert-xxlarge-v2", - # See all ALBERT models at https://huggingface.co/models?filter=albert -] +from ..deprecated._archive_maps import ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_albert(model, config, tf_checkpoint_path): diff --git a/src/transformers/models/albert/modeling_tf_albert.py b/src/transformers/models/albert/modeling_tf_albert.py index 1225465c52..5aa521bb73 100644 --- a/src/transformers/models/albert/modeling_tf_albert.py +++ b/src/transformers/models/albert/modeling_tf_albert.py @@ -65,17 +65,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "albert/albert-base-v2" _CONFIG_FOR_DOC = "AlbertConfig" -TF_ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "albert/albert-base-v1", - "albert/albert-large-v1", - "albert/albert-xlarge-v1", - "albert/albert-xxlarge-v1", - "albert/albert-base-v2", - "albert/albert-large-v2", - "albert/albert-xlarge-v2", - "albert/albert-xxlarge-v2", - # See all ALBERT models at https://huggingface.co/models?filter=albert -] + +from ..deprecated._archive_maps import TF_ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFAlbertPreTrainingLoss: diff --git a/src/transformers/models/albert/tokenization_albert.py b/src/transformers/models/albert/tokenization_albert.py index 7baaa0a600..786f9eeafc 100644 --- a/src/transformers/models/albert/tokenization_albert.py +++ b/src/transformers/models/albert/tokenization_albert.py @@ -29,29 +29,6 @@ from ...utils import logging logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "albert/albert-base-v1": "https://huggingface.co/albert/albert-base-v1/resolve/main/spiece.model", - "albert/albert-large-v1": "https://huggingface.co/albert/albert-large-v1/resolve/main/spiece.model", - "albert/albert-xlarge-v1": "https://huggingface.co/albert/albert-xlarge-v1/resolve/main/spiece.model", - "albert/albert-xxlarge-v1": "https://huggingface.co/albert/albert-xxlarge-v1/resolve/main/spiece.model", - "albert/albert-base-v2": "https://huggingface.co/albert/albert-base-v2/resolve/main/spiece.model", - "albert/albert-large-v2": "https://huggingface.co/albert/albert-large-v2/resolve/main/spiece.model", - "albert/albert-xlarge-v2": "https://huggingface.co/albert/albert-xlarge-v2/resolve/main/spiece.model", - "albert/albert-xxlarge-v2": "https://huggingface.co/albert/albert-xxlarge-v2/resolve/main/spiece.model", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "albert/albert-base-v1": 512, - "albert/albert-large-v1": 512, - "albert/albert-xlarge-v1": 512, - "albert/albert-xxlarge-v1": 512, - "albert/albert-base-v2": 512, - "albert/albert-large-v2": 512, - "albert/albert-xlarge-v2": 512, - "albert/albert-xxlarge-v2": 512, -} SPIECE_UNDERLINE = "▁" @@ -130,8 +107,6 @@ class AlbertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/albert/tokenization_albert_fast.py b/src/transformers/models/albert/tokenization_albert_fast.py index 91cf403d07..e0b09a7356 100644 --- a/src/transformers/models/albert/tokenization_albert_fast.py +++ b/src/transformers/models/albert/tokenization_albert_fast.py @@ -32,39 +32,6 @@ else: logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "albert/albert-base-v1": "https://huggingface.co/albert/albert-base-v1/resolve/main/spiece.model", - "albert/albert-large-v1": "https://huggingface.co/albert/albert-large-v1/resolve/main/spiece.model", - "albert/albert-xlarge-v1": "https://huggingface.co/albert/albert-xlarge-v1/resolve/main/spiece.model", - "albert/albert-xxlarge-v1": "https://huggingface.co/albert/albert-xxlarge-v1/resolve/main/spiece.model", - "albert/albert-base-v2": "https://huggingface.co/albert/albert-base-v2/resolve/main/spiece.model", - "albert/albert-large-v2": "https://huggingface.co/albert/albert-large-v2/resolve/main/spiece.model", - "albert/albert-xlarge-v2": "https://huggingface.co/albert/albert-xlarge-v2/resolve/main/spiece.model", - "albert/albert-xxlarge-v2": "https://huggingface.co/albert/albert-xxlarge-v2/resolve/main/spiece.model", - }, - "tokenizer_file": { - "albert/albert-base-v1": "https://huggingface.co/albert/albert-base-v1/resolve/main/tokenizer.json", - "albert/albert-large-v1": "https://huggingface.co/albert/albert-large-v1/resolve/main/tokenizer.json", - "albert/albert-xlarge-v1": "https://huggingface.co/albert/albert-xlarge-v1/resolve/main/tokenizer.json", - "albert/albert-xxlarge-v1": "https://huggingface.co/albert/albert-xxlarge-v1/resolve/main/tokenizer.json", - "albert/albert-base-v2": "https://huggingface.co/albert/albert-base-v2/resolve/main/tokenizer.json", - "albert/albert-large-v2": "https://huggingface.co/albert/albert-large-v2/resolve/main/tokenizer.json", - "albert/albert-xlarge-v2": "https://huggingface.co/albert/albert-xlarge-v2/resolve/main/tokenizer.json", - "albert/albert-xxlarge-v2": "https://huggingface.co/albert/albert-xxlarge-v2/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "albert/albert-base-v1": 512, - "albert/albert-large-v1": 512, - "albert/albert-xlarge-v1": 512, - "albert/albert-xxlarge-v1": 512, - "albert/albert-base-v2": 512, - "albert/albert-large-v2": 512, - "albert/albert-xlarge-v2": 512, - "albert/albert-xxlarge-v2": 512, -} SPIECE_UNDERLINE = "▁" @@ -117,8 +84,6 @@ class AlbertTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = AlbertTokenizer def __init__( diff --git a/src/transformers/models/align/configuration_align.py b/src/transformers/models/align/configuration_align.py index b7f377d481..a4b3149d97 100644 --- a/src/transformers/models/align/configuration_align.py +++ b/src/transformers/models/align/configuration_align.py @@ -27,9 +27,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -ALIGN_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "kakaobrain/align-base": "https://huggingface.co/kakaobrain/align-base/resolve/main/config.json", -} + +from ..deprecated._archive_maps import ALIGN_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class AlignTextConfig(PretrainedConfig): diff --git a/src/transformers/models/align/modeling_align.py b/src/transformers/models/align/modeling_align.py index f48fcbace1..c6789fb1f4 100644 --- a/src/transformers/models/align/modeling_align.py +++ b/src/transformers/models/align/modeling_align.py @@ -47,10 +47,7 @@ _CHECKPOINT_FOR_DOC = "kakaobrain/align-base" _CONFIG_FOR_DOC = "AlignConfig" -ALIGN_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "kakaobrain/align-base", - # See all ALIGN models at https://huggingface.co/models?filter=align -] +from ..deprecated._archive_maps import ALIGN_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 ALIGN_START_DOCSTRING = r""" diff --git a/src/transformers/models/altclip/configuration_altclip.py b/src/transformers/models/altclip/configuration_altclip.py index b9d451d2c0..590f2b526e 100755 --- a/src/transformers/models/altclip/configuration_altclip.py +++ b/src/transformers/models/altclip/configuration_altclip.py @@ -22,10 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -ALTCLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "BAAI/AltCLIP": "https://huggingface.co/BAAI/AltCLIP/resolve/main/config.json", - # See all AltCLIP models at https://huggingface.co/models?filter=altclip -} + +from ..deprecated._archive_maps import ALTCLIP_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class AltCLIPTextConfig(PretrainedConfig): diff --git a/src/transformers/models/altclip/modeling_altclip.py b/src/transformers/models/altclip/modeling_altclip.py index 2f511bace5..0d27d87de7 100755 --- a/src/transformers/models/altclip/modeling_altclip.py +++ b/src/transformers/models/altclip/modeling_altclip.py @@ -40,10 +40,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "BAAI/AltCLIP" _CONFIG_FOR_DOC = "AltCLIPConfig" -ALTCLIP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "BAAI/AltCLIP", - # See all AltCLIP models at https://huggingface.co/models?filter=altclip -] + +from ..deprecated._archive_maps import ALTCLIP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 ALTCLIP_START_DOCSTRING = r""" diff --git a/src/transformers/models/audio_spectrogram_transformer/configuration_audio_spectrogram_transformer.py b/src/transformers/models/audio_spectrogram_transformer/configuration_audio_spectrogram_transformer.py index 81a087f07f..94a7af6006 100644 --- a/src/transformers/models/audio_spectrogram_transformer/configuration_audio_spectrogram_transformer.py +++ b/src/transformers/models/audio_spectrogram_transformer/configuration_audio_spectrogram_transformer.py @@ -21,11 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -AUDIO_SPECTROGRAM_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "MIT/ast-finetuned-audioset-10-10-0.4593": ( - "https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import AUDIO_SPECTROGRAM_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ASTConfig(PretrainedConfig): diff --git a/src/transformers/models/audio_spectrogram_transformer/modeling_audio_spectrogram_transformer.py b/src/transformers/models/audio_spectrogram_transformer/modeling_audio_spectrogram_transformer.py index 3fddccdea7..5ec18e2c7f 100644 --- a/src/transformers/models/audio_spectrogram_transformer/modeling_audio_spectrogram_transformer.py +++ b/src/transformers/models/audio_spectrogram_transformer/modeling_audio_spectrogram_transformer.py @@ -45,10 +45,7 @@ _SEQ_CLASS_EXPECTED_OUTPUT = "'Speech'" _SEQ_CLASS_EXPECTED_LOSS = 0.17 -AUDIO_SPECTROGRAM_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "MIT/ast-finetuned-audioset-10-10-0.4593", - # See all Audio Spectrogram Transformer models at https://huggingface.co/models?filter=ast -] +from ..deprecated._archive_maps import AUDIO_SPECTROGRAM_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class ASTEmbeddings(nn.Module): diff --git a/src/transformers/models/auto/configuration_auto.py b/src/transformers/models/auto/configuration_auto.py index 80551b8452..40639d8d83 100755 --- a/src/transformers/models/auto/configuration_auto.py +++ b/src/transformers/models/auto/configuration_auto.py @@ -27,6 +27,10 @@ from ...utils import CONFIG_NAME, logging logger = logging.get_logger(__name__) + +from ..deprecated._archive_maps import CONFIG_ARCHIVE_MAP_MAPPING_NAMES # noqa: F401, E402 + + CONFIG_MAPPING_NAMES = OrderedDict( [ # Add configs here @@ -276,230 +280,6 @@ CONFIG_MAPPING_NAMES = OrderedDict( ] ) -CONFIG_ARCHIVE_MAP_MAPPING_NAMES = OrderedDict( - [ - # Add archive maps here) - ("albert", "ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("align", "ALIGN_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("altclip", "ALTCLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("audio-spectrogram-transformer", "AUDIO_SPECTROGRAM_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("autoformer", "AUTOFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("bark", "BARK_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("bart", "BART_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("beit", "BEIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("bert", "BERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("big_bird", "BIG_BIRD_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("bigbird_pegasus", "BIGBIRD_PEGASUS_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("biogpt", "BIOGPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("bit", "BIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("blenderbot", "BLENDERBOT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("blenderbot-small", "BLENDERBOT_SMALL_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("blip", "BLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("blip-2", "BLIP_2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("bloom", "BLOOM_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("bridgetower", "BRIDGETOWER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("bros", "BROS_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("camembert", "CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("canine", "CANINE_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("chinese_clip", "CHINESE_CLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("clap", "CLAP_PRETRAINED_MODEL_ARCHIVE_LIST"), - ("clip", "CLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("clipseg", "CLIPSEG_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("clvp", "CLVP_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("codegen", "CODEGEN_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("cohere", "COHERE_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("conditional_detr", "CONDITIONAL_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("convbert", "CONVBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("convnext", "CONVNEXT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("convnextv2", "CONVNEXTV2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("cpmant", "CPMANT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("ctrl", "CTRL_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("cvt", "CVT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("data2vec-audio", "DATA2VEC_AUDIO_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("data2vec-text", "DATA2VEC_TEXT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("data2vec-vision", "DATA2VEC_VISION_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("deberta", "DEBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("deberta-v2", "DEBERTA_V2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("deformable_detr", "DEFORMABLE_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("deit", "DEIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("depth_anything", "DEPTH_ANYTHING_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("deta", "DETA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("detr", "DETR_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("dinat", "DINAT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("dinov2", "DINOV2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("distilbert", "DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("donut-swin", "DONUT_SWIN_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("dpr", "DPR_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("dpt", "DPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("efficientformer", "EFFICIENTFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("efficientnet", "EFFICIENTNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("electra", "ELECTRA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("encodec", "ENCODEC_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("ernie", "ERNIE_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("ernie_m", "ERNIE_M_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("esm", "ESM_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("falcon", "FALCON_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("fastspeech2_conformer", "FASTSPEECH2_CONFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("flaubert", "FLAUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("flava", "FLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("fnet", "FNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("focalnet", "FOCALNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("fsmt", "FSMT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("funnel", "FUNNEL_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("fuyu", "FUYU_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("gemma", "GEMMA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("git", "GIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("glpn", "GLPN_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("gpt2", "GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("gpt_bigcode", "GPT_BIGCODE_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("gpt_neo", "GPT_NEO_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("gpt_neox", "GPT_NEOX_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("gpt_neox_japanese", "GPT_NEOX_JAPANESE_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("gptj", "GPTJ_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("gptsan-japanese", "GPTSAN_JAPANESE_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("graphormer", "GRAPHORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("groupvit", "GROUPVIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("hubert", "HUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("ibert", "IBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("idefics", "IDEFICS_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("imagegpt", "IMAGEGPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("informer", "INFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("instructblip", "INSTRUCTBLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("jukebox", "JUKEBOX_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("kosmos-2", "KOSMOS2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("layoutlm", "LAYOUTLM_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("layoutlmv2", "LAYOUTLMV2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("layoutlmv3", "LAYOUTLMV3_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("led", "LED_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("levit", "LEVIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("lilt", "LILT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("llama", "LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("llava", "LLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("llava_next", "LLAVA_NEXT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("longformer", "LONGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("longt5", "LONGT5_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("luke", "LUKE_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("lxmert", "LXMERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("m2m_100", "M2M_100_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mamba", "MAMBA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("markuplm", "MARKUPLM_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mask2former", "MASK2FORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("maskformer", "MASKFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mbart", "MBART_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mctct", "MCTCT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mega", "MEGA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("megatron-bert", "MEGATRON_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mgp-str", "MGP_STR_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mistral", "MISTRAL_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mixtral", "MIXTRAL_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mobilenet_v1", "MOBILENET_V1_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mobilenet_v2", "MOBILENET_V2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mobilevit", "MOBILEVIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mobilevitv2", "MOBILEVITV2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mpnet", "MPNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mpt", "MPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mra", "MRA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("musicgen", "MUSICGEN_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("musicgen_melody", "MUSICGEN_MELODY_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("mvp", "MVP_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("nat", "NAT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("nezha", "NEZHA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("nllb-moe", "NLLB_MOE_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("nystromformer", "NYSTROMFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("oneformer", "ONEFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("open-llama", "OPEN_LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("openai-gpt", "OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("opt", "OPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("owlv2", "OWLV2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("owlvit", "OWLVIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("patchtsmixer", "PATCHTSMIXER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("patchtst", "PATCHTST_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("pegasus", "PEGASUS_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("pegasus_x", "PEGASUS_X_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("perceiver", "PERCEIVER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("persimmon", "PERSIMMON_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("phi", "PHI_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("pix2struct", "PIX2STRUCT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("plbart", "PLBART_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("poolformer", "POOLFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("pop2piano", "POP2PIANO_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("prophetnet", "PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("pvt", "PVT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("pvt_v2", "PVT_V2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("qdqbert", "QDQBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("qwen2", "QWEN2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("realm", "REALM_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("regnet", "REGNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("rembert", "REMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("resnet", "RESNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("retribert", "RETRIBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("roberta", "ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("roberta-prelayernorm", "ROBERTA_PRELAYERNORM_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("roc_bert", "ROC_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("roformer", "ROFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("rwkv", "RWKV_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("sam", "SAM_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("seamless_m4t", "SEAMLESS_M4T_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("seamless_m4t_v2", "SEAMLESS_M4T_V2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("segformer", "SEGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("seggpt", "SEGGPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("sew", "SEW_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("sew-d", "SEW_D_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("siglip", "SIGLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("speech_to_text", "SPEECH_TO_TEXT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("speech_to_text_2", "SPEECH_TO_TEXT_2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("speecht5", "SPEECHT5_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("splinter", "SPLINTER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("squeezebert", "SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("stablelm", "STABLELM_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("starcoder2", "STARCODER2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("superpoint", "SUPERPOINT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("swiftformer", "SWIFTFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("swin", "SWIN_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("swin2sr", "SWIN2SR_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("swinv2", "SWINV2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("switch_transformers", "SWITCH_TRANSFORMERS_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("t5", "T5_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("table-transformer", "TABLE_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("tapas", "TAPAS_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("time_series_transformer", "TIME_SERIES_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("timesformer", "TIMESFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("transfo-xl", "TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("tvlt", "TVLT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("tvp", "TVP_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("udop", "UDOP_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("unispeech", "UNISPEECH_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("unispeech-sat", "UNISPEECH_SAT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("univnet", "UNIVNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("van", "VAN_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("videomae", "VIDEOMAE_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("vilt", "VILT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("vipllava", "VIPLLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("visual_bert", "VISUAL_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("vit", "VIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("vit_hybrid", "VIT_HYBRID_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("vit_mae", "VIT_MAE_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("vit_msn", "VIT_MSN_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("vitdet", "VITDET_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("vitmatte", "VITMATTE_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("vits", "VITS_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("vivit", "VIVIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("wav2vec2", "WAV_2_VEC_2_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("wav2vec2-bert", "WAV2VEC2_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("wav2vec2-conformer", "WAV2VEC2_CONFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("whisper", "WHISPER_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("xclip", "XCLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("xglm", "XGLM_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("xlm", "XLM_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("xlm-prophetnet", "XLM_PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("xlm-roberta", "XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("xlnet", "XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("xmod", "XMOD_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("yolos", "YOLOS_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ("yoso", "YOSO_PRETRAINED_CONFIG_ARCHIVE_MAP"), - ] -) - MODEL_NAMES_MAPPING = OrderedDict( [ # Add full (and cased) model names here @@ -906,11 +686,6 @@ class _LazyLoadAllMappings(OrderedDict): def _initialize(self): if self._initialized: return - warnings.warn( - "ALL_PRETRAINED_CONFIG_ARCHIVE_MAP is deprecated and will be removed in v5 of Transformers. " - "It does not contain all available model checkpoints, far from it. Checkout hf.co/models for that.", - FutureWarning, - ) for model_type, map_name in self._mapping.items(): module_name = model_type_to_module_name(model_type) @@ -945,9 +720,6 @@ class _LazyLoadAllMappings(OrderedDict): return item in self._data -ALL_PRETRAINED_CONFIG_ARCHIVE_MAP = _LazyLoadAllMappings(CONFIG_ARCHIVE_MAP_MAPPING_NAMES) - - def _get_class_name(model_class: Union[str, List[str]]): if isinstance(model_class, (list, tuple)): return " or ".join([f"[`{c}`]" for c in model_class if c is not None]) @@ -1192,3 +964,6 @@ class AutoConfig: "match!" ) CONFIG_MAPPING.register(model_type, config, exist_ok=exist_ok) + + +ALL_PRETRAINED_CONFIG_ARCHIVE_MAP = _LazyLoadAllMappings(CONFIG_ARCHIVE_MAP_MAPPING_NAMES) diff --git a/src/transformers/models/autoformer/configuration_autoformer.py b/src/transformers/models/autoformer/configuration_autoformer.py index 7604233e32..11909ac5c3 100644 --- a/src/transformers/models/autoformer/configuration_autoformer.py +++ b/src/transformers/models/autoformer/configuration_autoformer.py @@ -22,9 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -AUTOFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "huggingface/autoformer-tourism-monthly": "https://huggingface.co/huggingface/autoformer-tourism-monthly/resolve/main/config.json", -} + +from ..deprecated._archive_maps import AUTOFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class AutoformerConfig(PretrainedConfig): diff --git a/src/transformers/models/autoformer/modeling_autoformer.py b/src/transformers/models/autoformer/modeling_autoformer.py index 78dbb8a5de..8a993fad32 100644 --- a/src/transformers/models/autoformer/modeling_autoformer.py +++ b/src/transformers/models/autoformer/modeling_autoformer.py @@ -167,10 +167,7 @@ class AutoformerModelOutput(ModelOutput): static_features: Optional[torch.FloatTensor] = None -AUTOFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "huggingface/autoformer-tourism-monthly", - # See all Autoformer models at https://huggingface.co/models?filter=autoformer -] +from ..deprecated._archive_maps import AUTOFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesFeatureEmbedder with TimeSeries->Autoformer diff --git a/src/transformers/models/bark/configuration_bark.py b/src/transformers/models/bark/configuration_bark.py index 15efb11dc7..a6bf2b546a 100644 --- a/src/transformers/models/bark/configuration_bark.py +++ b/src/transformers/models/bark/configuration_bark.py @@ -25,11 +25,6 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -BARK_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "suno/bark-small": "https://huggingface.co/suno/bark-small/resolve/main/config.json", - "suno/bark": "https://huggingface.co/suno/bark/resolve/main/config.json", -} - BARK_SUBMODELCONFIG_START_DOCSTRING = """ This is the configuration class to store the configuration of a [`{model}`]. It is used to instantiate the model according to the specified arguments, defining the model architecture. Instantiating a configuration with the diff --git a/src/transformers/models/bark/modeling_bark.py b/src/transformers/models/bark/modeling_bark.py index f26b723a49..de04614075 100644 --- a/src/transformers/models/bark/modeling_bark.py +++ b/src/transformers/models/bark/modeling_bark.py @@ -63,11 +63,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "suno/bark-small" _CONFIG_FOR_DOC = "BarkConfig" -BARK_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "suno/bark-small", - "suno/bark", - # See all Bark models at https://huggingface.co/models?filter=bark -] + +from ..deprecated._archive_maps import BARK_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.llama.modeling_llama._get_unpad_data diff --git a/src/transformers/models/bart/configuration_bart.py b/src/transformers/models/bart/configuration_bart.py index 8c03be9a62..1a6214c2ee 100644 --- a/src/transformers/models/bart/configuration_bart.py +++ b/src/transformers/models/bart/configuration_bart.py @@ -26,11 +26,6 @@ from ...utils import TensorType, is_torch_available, logging logger = logging.get_logger(__name__) -BART_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/bart-large": "https://huggingface.co/facebook/bart-large/resolve/main/config.json", - # See all BART models at https://huggingface.co/models?filter=bart -} - class BartConfig(PretrainedConfig): r""" diff --git a/src/transformers/models/bart/modeling_bart.py b/src/transformers/models/bart/modeling_bart.py index 1f90b82a10..535f380cd0 100755 --- a/src/transformers/models/bart/modeling_bart.py +++ b/src/transformers/models/bart/modeling_bart.py @@ -78,10 +78,7 @@ _QA_EXPECTED_LOSS = 0.59 _QA_EXPECTED_OUTPUT = "' nice puppet'" -BART_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/bart-large", - # see all BART models at https://huggingface.co/models?filter=bart -] +from ..deprecated._archive_maps import BART_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.llama.modeling_llama._get_unpad_data diff --git a/src/transformers/models/bart/tokenization_bart.py b/src/transformers/models/bart/tokenization_bart.py index b21e81000f..5207b9c92b 100644 --- a/src/transformers/models/bart/tokenization_bart.py +++ b/src/transformers/models/bart/tokenization_bart.py @@ -30,33 +30,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt"} # See all BART models at https://huggingface.co/models?filter=bart -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/bart-base": "https://huggingface.co/facebook/bart-base/resolve/main/vocab.json", - "facebook/bart-large": "https://huggingface.co/facebook/bart-large/resolve/main/vocab.json", - "facebook/bart-large-mnli": "https://huggingface.co/facebook/bart-large-mnli/resolve/main/vocab.json", - "facebook/bart-large-cnn": "https://huggingface.co/facebook/bart-large-cnn/resolve/main/vocab.json", - "facebook/bart-large-xsum": "https://huggingface.co/facebook/bart-large-xsum/resolve/main/vocab.json", - "yjernite/bart_eli5": "https://huggingface.co/yjernite/bart_eli5/resolve/main/vocab.json", - }, - "merges_file": { - "facebook/bart-base": "https://huggingface.co/facebook/bart-base/resolve/main/merges.txt", - "facebook/bart-large": "https://huggingface.co/facebook/bart-large/resolve/main/merges.txt", - "facebook/bart-large-mnli": "https://huggingface.co/facebook/bart-large-mnli/resolve/main/merges.txt", - "facebook/bart-large-cnn": "https://huggingface.co/facebook/bart-large-cnn/resolve/main/merges.txt", - "facebook/bart-large-xsum": "https://huggingface.co/facebook/bart-large-xsum/resolve/main/merges.txt", - "yjernite/bart_eli5": "https://huggingface.co/yjernite/bart_eli5/resolve/main/merges.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/bart-base": 1024, - "facebook/bart-large": 1024, - "facebook/bart-large-mnli": 1024, - "facebook/bart-large-cnn": 1024, - "facebook/bart-large-xsum": 1024, - "yjernite/bart_eli5": 1024, -} @lru_cache() @@ -177,8 +150,6 @@ class BartTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/bart/tokenization_bart_fast.py b/src/transformers/models/bart/tokenization_bart_fast.py index 850c963683..e9fb8497c9 100644 --- a/src/transformers/models/bart/tokenization_bart_fast.py +++ b/src/transformers/models/bart/tokenization_bart_fast.py @@ -30,41 +30,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} # See all BART models at https://huggingface.co/models?filter=bart -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/bart-base": "https://huggingface.co/facebook/bart-base/resolve/main/vocab.json", - "facebook/bart-large": "https://huggingface.co/facebook/bart-large/resolve/main/vocab.json", - "facebook/bart-large-mnli": "https://huggingface.co/facebook/bart-large-mnli/resolve/main/vocab.json", - "facebook/bart-large-cnn": "https://huggingface.co/facebook/bart-large-cnn/resolve/main/vocab.json", - "facebook/bart-large-xsum": "https://huggingface.co/facebook/bart-large-xsum/resolve/main/vocab.json", - "yjernite/bart_eli5": "https://huggingface.co/yjernite/bart_eli5/resolve/main/vocab.json", - }, - "merges_file": { - "facebook/bart-base": "https://huggingface.co/facebook/bart-base/resolve/main/merges.txt", - "facebook/bart-large": "https://huggingface.co/facebook/bart-large/resolve/main/merges.txt", - "facebook/bart-large-mnli": "https://huggingface.co/facebook/bart-large-mnli/resolve/main/merges.txt", - "facebook/bart-large-cnn": "https://huggingface.co/facebook/bart-large-cnn/resolve/main/merges.txt", - "facebook/bart-large-xsum": "https://huggingface.co/facebook/bart-large-xsum/resolve/main/merges.txt", - "yjernite/bart_eli5": "https://huggingface.co/yjernite/bart_eli5/resolve/main/merges.txt", - }, - "tokenizer_file": { - "facebook/bart-base": "https://huggingface.co/facebook/bart-base/resolve/main/tokenizer.json", - "facebook/bart-large": "https://huggingface.co/facebook/bart-large/resolve/main/tokenizer.json", - "facebook/bart-large-mnli": "https://huggingface.co/facebook/bart-large-mnli/resolve/main/tokenizer.json", - "facebook/bart-large-cnn": "https://huggingface.co/facebook/bart-large-cnn/resolve/main/tokenizer.json", - "facebook/bart-large-xsum": "https://huggingface.co/facebook/bart-large-xsum/resolve/main/tokenizer.json", - "yjernite/bart_eli5": "https://huggingface.co/yjernite/bart_eli5/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/bart-base": 1024, - "facebook/bart-large": 1024, - "facebook/bart-large-mnli": 1024, - "facebook/bart-large-cnn": 1024, - "facebook/bart-large-xsum": 1024, - "yjernite/bart_eli5": 1024, -} class BartTokenizerFast(PreTrainedTokenizerFast): @@ -149,8 +114,6 @@ class BartTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = BartTokenizer diff --git a/src/transformers/models/barthez/tokenization_barthez.py b/src/transformers/models/barthez/tokenization_barthez.py index f6ea253402..d9bd67cf51 100644 --- a/src/transformers/models/barthez/tokenization_barthez.py +++ b/src/transformers/models/barthez/tokenization_barthez.py @@ -29,21 +29,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "moussaKam/mbarthez": "https://huggingface.co/moussaKam/mbarthez/resolve/main/sentencepiece.bpe.model", - "moussaKam/barthez": "https://huggingface.co/moussaKam/barthez/resolve/main/sentencepiece.bpe.model", - "moussaKam/barthez-orangesum-title": ( - "https://huggingface.co/moussaKam/barthez-orangesum-title/resolve/main/sentencepiece.bpe.model" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "moussaKam/mbarthez": 1024, - "moussaKam/barthez": 1024, - "moussaKam/barthez-orangesum-title": 1024, -} SPIECE_UNDERLINE = "▁" @@ -119,8 +104,6 @@ class BarthezTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/barthez/tokenization_barthez_fast.py b/src/transformers/models/barthez/tokenization_barthez_fast.py index fb4a114b43..e988b0d518 100644 --- a/src/transformers/models/barthez/tokenization_barthez_fast.py +++ b/src/transformers/models/barthez/tokenization_barthez_fast.py @@ -33,28 +33,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "moussaKam/mbarthez": "https://huggingface.co/moussaKam/mbarthez/resolve/main/sentencepiece.bpe.model", - "moussaKam/barthez": "https://huggingface.co/moussaKam/barthez/resolve/main/sentencepiece.bpe.model", - "moussaKam/barthez-orangesum-title": ( - "https://huggingface.co/moussaKam/barthez-orangesum-title/resolve/main/sentencepiece.bpe.model" - ), - }, - "tokenizer_file": { - "moussaKam/mbarthez": "https://huggingface.co/moussaKam/mbarthez/resolve/main/tokenizer.json", - "moussaKam/barthez": "https://huggingface.co/moussaKam/barthez/resolve/main/tokenizer.json", - "moussaKam/barthez-orangesum-title": ( - "https://huggingface.co/moussaKam/barthez-orangesum-title/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "moussaKam/mbarthez": 1024, - "moussaKam/barthez": 1024, - "moussaKam/barthez-orangesum-title": 1024, -} SPIECE_UNDERLINE = "▁" @@ -111,8 +89,6 @@ class BarthezTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = BarthezTokenizer diff --git a/src/transformers/models/bartpho/tokenization_bartpho.py b/src/transformers/models/bartpho/tokenization_bartpho.py index 6b9dc266b2..d936be41c2 100644 --- a/src/transformers/models/bartpho/tokenization_bartpho.py +++ b/src/transformers/models/bartpho/tokenization_bartpho.py @@ -31,17 +31,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "monolingual_vocab_file": "dict.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "vinai/bartpho-syllable": "https://huggingface.co/vinai/bartpho-syllable/resolve/main/sentencepiece.bpe.model", - }, - "monolingual_vocab_file": { - "vinai/bartpho-syllable": "https://huggingface.co/vinai/bartpho-syllable/resolve/main/dict.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"vinai/bartpho-syllable": 1024} - class BartphoTokenizer(PreTrainedTokenizer): """ @@ -114,8 +103,6 @@ class BartphoTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/beit/configuration_beit.py b/src/transformers/models/beit/configuration_beit.py index b579eeea37..dbb1e755e9 100644 --- a/src/transformers/models/beit/configuration_beit.py +++ b/src/transformers/models/beit/configuration_beit.py @@ -26,12 +26,8 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -BEIT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/beit-base-patch16-224-pt22k": ( - "https://huggingface.co/microsoft/beit-base-patch16-224-pt22k/resolve/main/config.json" - ), - # See all BEiT models at https://huggingface.co/models?filter=beit -} + +from ..deprecated._archive_maps import BEIT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class BeitConfig(BackboneConfigMixin, PretrainedConfig): diff --git a/src/transformers/models/beit/modeling_beit.py b/src/transformers/models/beit/modeling_beit.py index da4721656c..d04717039e 100755 --- a/src/transformers/models/beit/modeling_beit.py +++ b/src/transformers/models/beit/modeling_beit.py @@ -60,10 +60,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 197, 768] _IMAGE_CLASS_CHECKPOINT = "microsoft/beit-base-patch16-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -BEIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/beit-base-patch16-224", - # See all BEiT models at https://huggingface.co/models?filter=beit -] + +from ..deprecated._archive_maps import BEIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/bert/configuration_bert.py b/src/transformers/models/bert/configuration_bert.py index 1f79260f51..e692f8284c 100644 --- a/src/transformers/models/bert/configuration_bert.py +++ b/src/transformers/models/bert/configuration_bert.py @@ -24,49 +24,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google-bert/bert-base-uncased": "https://huggingface.co/google-bert/bert-base-uncased/resolve/main/config.json", - "google-bert/bert-large-uncased": "https://huggingface.co/google-bert/bert-large-uncased/resolve/main/config.json", - "google-bert/bert-base-cased": "https://huggingface.co/google-bert/bert-base-cased/resolve/main/config.json", - "google-bert/bert-large-cased": "https://huggingface.co/google-bert/bert-large-cased/resolve/main/config.json", - "google-bert/bert-base-multilingual-uncased": "https://huggingface.co/google-bert/bert-base-multilingual-uncased/resolve/main/config.json", - "google-bert/bert-base-multilingual-cased": "https://huggingface.co/google-bert/bert-base-multilingual-cased/resolve/main/config.json", - "google-bert/bert-base-chinese": "https://huggingface.co/google-bert/bert-base-chinese/resolve/main/config.json", - "google-bert/bert-base-german-cased": "https://huggingface.co/google-bert/bert-base-german-cased/resolve/main/config.json", - "google-bert/bert-large-uncased-whole-word-masking": ( - "https://huggingface.co/google-bert/bert-large-uncased-whole-word-masking/resolve/main/config.json" - ), - "google-bert/bert-large-cased-whole-word-masking": ( - "https://huggingface.co/google-bert/bert-large-cased-whole-word-masking/resolve/main/config.json" - ), - "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad": ( - "https://huggingface.co/google-bert/bert-large-uncased-whole-word-masking-finetuned-squad/resolve/main/config.json" - ), - "google-bert/bert-large-cased-whole-word-masking-finetuned-squad": ( - "https://huggingface.co/google-bert/bert-large-cased-whole-word-masking-finetuned-squad/resolve/main/config.json" - ), - "google-bert/bert-base-cased-finetuned-mrpc": "https://huggingface.co/google-bert/bert-base-cased-finetuned-mrpc/resolve/main/config.json", - "google-bert/bert-base-german-dbmdz-cased": "https://huggingface.co/google-bert/bert-base-german-dbmdz-cased/resolve/main/config.json", - "google-bert/bert-base-german-dbmdz-uncased": "https://huggingface.co/google-bert/bert-base-german-dbmdz-uncased/resolve/main/config.json", - "cl-tohoku/bert-base-japanese": "https://huggingface.co/cl-tohoku/bert-base-japanese/resolve/main/config.json", - "cl-tohoku/bert-base-japanese-whole-word-masking": ( - "https://huggingface.co/cl-tohoku/bert-base-japanese-whole-word-masking/resolve/main/config.json" - ), - "cl-tohoku/bert-base-japanese-char": ( - "https://huggingface.co/cl-tohoku/bert-base-japanese-char/resolve/main/config.json" - ), - "cl-tohoku/bert-base-japanese-char-whole-word-masking": ( - "https://huggingface.co/cl-tohoku/bert-base-japanese-char-whole-word-masking/resolve/main/config.json" - ), - "TurkuNLP/bert-base-finnish-cased-v1": ( - "https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1/resolve/main/config.json" - ), - "TurkuNLP/bert-base-finnish-uncased-v1": ( - "https://huggingface.co/TurkuNLP/bert-base-finnish-uncased-v1/resolve/main/config.json" - ), - "wietsedv/bert-base-dutch-cased": "https://huggingface.co/wietsedv/bert-base-dutch-cased/resolve/main/config.json", - # See all BERT models at https://huggingface.co/models?filter=bert -} + +from ..deprecated._archive_maps import BERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class BertConfig(PretrainedConfig): diff --git a/src/transformers/models/bert/modeling_bert.py b/src/transformers/models/bert/modeling_bert.py index 4c068c4d4f..1b06c37578 100755 --- a/src/transformers/models/bert/modeling_bert.py +++ b/src/transformers/models/bert/modeling_bert.py @@ -77,31 +77,7 @@ _SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_1'" _SEQ_CLASS_EXPECTED_LOSS = 0.01 -BERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google-bert/bert-base-uncased", - "google-bert/bert-large-uncased", - "google-bert/bert-base-cased", - "google-bert/bert-large-cased", - "google-bert/bert-base-multilingual-uncased", - "google-bert/bert-base-multilingual-cased", - "google-bert/bert-base-chinese", - "google-bert/bert-base-german-cased", - "google-bert/bert-large-uncased-whole-word-masking", - "google-bert/bert-large-cased-whole-word-masking", - "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad", - "google-bert/bert-large-cased-whole-word-masking-finetuned-squad", - "google-bert/bert-base-cased-finetuned-mrpc", - "google-bert/bert-base-german-dbmdz-cased", - "google-bert/bert-base-german-dbmdz-uncased", - "cl-tohoku/bert-base-japanese", - "cl-tohoku/bert-base-japanese-whole-word-masking", - "cl-tohoku/bert-base-japanese-char", - "cl-tohoku/bert-base-japanese-char-whole-word-masking", - "TurkuNLP/bert-base-finnish-cased-v1", - "TurkuNLP/bert-base-finnish-uncased-v1", - "wietsedv/bert-base-dutch-cased", - # See all BERT models at https://huggingface.co/models?filter=bert -] +from ..deprecated._archive_maps import BERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_bert(model, config, tf_checkpoint_path): diff --git a/src/transformers/models/bert/modeling_tf_bert.py b/src/transformers/models/bert/modeling_tf_bert.py index cc1218bbea..9d027d8431 100644 --- a/src/transformers/models/bert/modeling_tf_bert.py +++ b/src/transformers/models/bert/modeling_tf_bert.py @@ -89,29 +89,8 @@ _CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "ydshieh/bert-base-uncased-yelp-polari _SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_1'" _SEQ_CLASS_EXPECTED_LOSS = 0.01 -TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google-bert/bert-base-uncased", - "google-bert/bert-large-uncased", - "google-bert/bert-base-cased", - "google-bert/bert-large-cased", - "google-bert/bert-base-multilingual-uncased", - "google-bert/bert-base-multilingual-cased", - "google-bert/bert-base-chinese", - "google-bert/bert-base-german-cased", - "google-bert/bert-large-uncased-whole-word-masking", - "google-bert/bert-large-cased-whole-word-masking", - "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad", - "google-bert/bert-large-cased-whole-word-masking-finetuned-squad", - "google-bert/bert-base-cased-finetuned-mrpc", - "cl-tohoku/bert-base-japanese", - "cl-tohoku/bert-base-japanese-whole-word-masking", - "cl-tohoku/bert-base-japanese-char", - "cl-tohoku/bert-base-japanese-char-whole-word-masking", - "TurkuNLP/bert-base-finnish-cased-v1", - "TurkuNLP/bert-base-finnish-uncased-v1", - "wietsedv/bert-base-dutch-cased", - # See all BERT models at https://huggingface.co/models?filter=bert -] + +from ..deprecated._archive_maps import TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFBertPreTrainingLoss: diff --git a/src/transformers/models/bert/tokenization_bert.py b/src/transformers/models/bert/tokenization_bert.py index c95e9ff0f8..f645d7c08a 100644 --- a/src/transformers/models/bert/tokenization_bert.py +++ b/src/transformers/models/bert/tokenization_bert.py @@ -28,91 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google-bert/bert-base-uncased": "https://huggingface.co/google-bert/bert-base-uncased/resolve/main/vocab.txt", - "google-bert/bert-large-uncased": "https://huggingface.co/google-bert/bert-large-uncased/resolve/main/vocab.txt", - "google-bert/bert-base-cased": "https://huggingface.co/google-bert/bert-base-cased/resolve/main/vocab.txt", - "google-bert/bert-large-cased": "https://huggingface.co/google-bert/bert-large-cased/resolve/main/vocab.txt", - "google-bert/bert-base-multilingual-uncased": ( - "https://huggingface.co/google-bert/bert-base-multilingual-uncased/resolve/main/vocab.txt" - ), - "google-bert/bert-base-multilingual-cased": "https://huggingface.co/google-bert/bert-base-multilingual-cased/resolve/main/vocab.txt", - "google-bert/bert-base-chinese": "https://huggingface.co/google-bert/bert-base-chinese/resolve/main/vocab.txt", - "google-bert/bert-base-german-cased": "https://huggingface.co/google-bert/bert-base-german-cased/resolve/main/vocab.txt", - "google-bert/bert-large-uncased-whole-word-masking": ( - "https://huggingface.co/google-bert/bert-large-uncased-whole-word-masking/resolve/main/vocab.txt" - ), - "google-bert/bert-large-cased-whole-word-masking": ( - "https://huggingface.co/google-bert/bert-large-cased-whole-word-masking/resolve/main/vocab.txt" - ), - "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad": ( - "https://huggingface.co/google-bert/bert-large-uncased-whole-word-masking-finetuned-squad/resolve/main/vocab.txt" - ), - "google-bert/bert-large-cased-whole-word-masking-finetuned-squad": ( - "https://huggingface.co/google-bert/bert-large-cased-whole-word-masking-finetuned-squad/resolve/main/vocab.txt" - ), - "google-bert/bert-base-cased-finetuned-mrpc": ( - "https://huggingface.co/google-bert/bert-base-cased-finetuned-mrpc/resolve/main/vocab.txt" - ), - "google-bert/bert-base-german-dbmdz-cased": "https://huggingface.co/google-bert/bert-base-german-dbmdz-cased/resolve/main/vocab.txt", - "google-bert/bert-base-german-dbmdz-uncased": ( - "https://huggingface.co/google-bert/bert-base-german-dbmdz-uncased/resolve/main/vocab.txt" - ), - "TurkuNLP/bert-base-finnish-cased-v1": ( - "https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1/resolve/main/vocab.txt" - ), - "TurkuNLP/bert-base-finnish-uncased-v1": ( - "https://huggingface.co/TurkuNLP/bert-base-finnish-uncased-v1/resolve/main/vocab.txt" - ), - "wietsedv/bert-base-dutch-cased": ( - "https://huggingface.co/wietsedv/bert-base-dutch-cased/resolve/main/vocab.txt" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google-bert/bert-base-uncased": 512, - "google-bert/bert-large-uncased": 512, - "google-bert/bert-base-cased": 512, - "google-bert/bert-large-cased": 512, - "google-bert/bert-base-multilingual-uncased": 512, - "google-bert/bert-base-multilingual-cased": 512, - "google-bert/bert-base-chinese": 512, - "google-bert/bert-base-german-cased": 512, - "google-bert/bert-large-uncased-whole-word-masking": 512, - "google-bert/bert-large-cased-whole-word-masking": 512, - "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad": 512, - "google-bert/bert-large-cased-whole-word-masking-finetuned-squad": 512, - "google-bert/bert-base-cased-finetuned-mrpc": 512, - "google-bert/bert-base-german-dbmdz-cased": 512, - "google-bert/bert-base-german-dbmdz-uncased": 512, - "TurkuNLP/bert-base-finnish-cased-v1": 512, - "TurkuNLP/bert-base-finnish-uncased-v1": 512, - "wietsedv/bert-base-dutch-cased": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "google-bert/bert-base-uncased": {"do_lower_case": True}, - "google-bert/bert-large-uncased": {"do_lower_case": True}, - "google-bert/bert-base-cased": {"do_lower_case": False}, - "google-bert/bert-large-cased": {"do_lower_case": False}, - "google-bert/bert-base-multilingual-uncased": {"do_lower_case": True}, - "google-bert/bert-base-multilingual-cased": {"do_lower_case": False}, - "google-bert/bert-base-chinese": {"do_lower_case": False}, - "google-bert/bert-base-german-cased": {"do_lower_case": False}, - "google-bert/bert-large-uncased-whole-word-masking": {"do_lower_case": True}, - "google-bert/bert-large-cased-whole-word-masking": {"do_lower_case": False}, - "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad": {"do_lower_case": True}, - "google-bert/bert-large-cased-whole-word-masking-finetuned-squad": {"do_lower_case": False}, - "google-bert/bert-base-cased-finetuned-mrpc": {"do_lower_case": False}, - "google-bert/bert-base-german-dbmdz-cased": {"do_lower_case": False}, - "google-bert/bert-base-german-dbmdz-uncased": {"do_lower_case": True}, - "TurkuNLP/bert-base-finnish-cased-v1": {"do_lower_case": False}, - "TurkuNLP/bert-base-finnish-uncased-v1": {"do_lower_case": True}, - "wietsedv/bert-base-dutch-cased": {"do_lower_case": False}, -} - def load_vocab(vocab_file): """Loads a vocabulary file into a dictionary.""" @@ -177,9 +92,6 @@ class BertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/bert/tokenization_bert_fast.py b/src/transformers/models/bert/tokenization_bert_fast.py index e7754b2fb5..f489777284 100644 --- a/src/transformers/models/bert/tokenization_bert_fast.py +++ b/src/transformers/models/bert/tokenization_bert_fast.py @@ -28,135 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google-bert/bert-base-uncased": "https://huggingface.co/google-bert/bert-base-uncased/resolve/main/vocab.txt", - "google-bert/bert-large-uncased": "https://huggingface.co/google-bert/bert-large-uncased/resolve/main/vocab.txt", - "google-bert/bert-base-cased": "https://huggingface.co/google-bert/bert-base-cased/resolve/main/vocab.txt", - "google-bert/bert-large-cased": "https://huggingface.co/google-bert/bert-large-cased/resolve/main/vocab.txt", - "google-bert/bert-base-multilingual-uncased": ( - "https://huggingface.co/google-bert/bert-base-multilingual-uncased/resolve/main/vocab.txt" - ), - "google-bert/bert-base-multilingual-cased": "https://huggingface.co/google-bert/bert-base-multilingual-cased/resolve/main/vocab.txt", - "google-bert/bert-base-chinese": "https://huggingface.co/google-bert/bert-base-chinese/resolve/main/vocab.txt", - "google-bert/bert-base-german-cased": "https://huggingface.co/google-bert/bert-base-german-cased/resolve/main/vocab.txt", - "google-bert/bert-large-uncased-whole-word-masking": ( - "https://huggingface.co/google-bert/bert-large-uncased-whole-word-masking/resolve/main/vocab.txt" - ), - "google-bert/bert-large-cased-whole-word-masking": ( - "https://huggingface.co/google-bert/bert-large-cased-whole-word-masking/resolve/main/vocab.txt" - ), - "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad": ( - "https://huggingface.co/google-bert/bert-large-uncased-whole-word-masking-finetuned-squad/resolve/main/vocab.txt" - ), - "google-bert/bert-large-cased-whole-word-masking-finetuned-squad": ( - "https://huggingface.co/google-bert/bert-large-cased-whole-word-masking-finetuned-squad/resolve/main/vocab.txt" - ), - "google-bert/bert-base-cased-finetuned-mrpc": ( - "https://huggingface.co/google-bert/bert-base-cased-finetuned-mrpc/resolve/main/vocab.txt" - ), - "google-bert/bert-base-german-dbmdz-cased": "https://huggingface.co/google-bert/bert-base-german-dbmdz-cased/resolve/main/vocab.txt", - "google-bert/bert-base-german-dbmdz-uncased": ( - "https://huggingface.co/google-bert/bert-base-german-dbmdz-uncased/resolve/main/vocab.txt" - ), - "TurkuNLP/bert-base-finnish-cased-v1": ( - "https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1/resolve/main/vocab.txt" - ), - "TurkuNLP/bert-base-finnish-uncased-v1": ( - "https://huggingface.co/TurkuNLP/bert-base-finnish-uncased-v1/resolve/main/vocab.txt" - ), - "wietsedv/bert-base-dutch-cased": ( - "https://huggingface.co/wietsedv/bert-base-dutch-cased/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "google-bert/bert-base-uncased": "https://huggingface.co/google-bert/bert-base-uncased/resolve/main/tokenizer.json", - "google-bert/bert-large-uncased": "https://huggingface.co/google-bert/bert-large-uncased/resolve/main/tokenizer.json", - "google-bert/bert-base-cased": "https://huggingface.co/google-bert/bert-base-cased/resolve/main/tokenizer.json", - "google-bert/bert-large-cased": "https://huggingface.co/google-bert/bert-large-cased/resolve/main/tokenizer.json", - "google-bert/bert-base-multilingual-uncased": ( - "https://huggingface.co/google-bert/bert-base-multilingual-uncased/resolve/main/tokenizer.json" - ), - "google-bert/bert-base-multilingual-cased": ( - "https://huggingface.co/google-bert/bert-base-multilingual-cased/resolve/main/tokenizer.json" - ), - "google-bert/bert-base-chinese": "https://huggingface.co/google-bert/bert-base-chinese/resolve/main/tokenizer.json", - "google-bert/bert-base-german-cased": "https://huggingface.co/google-bert/bert-base-german-cased/resolve/main/tokenizer.json", - "google-bert/bert-large-uncased-whole-word-masking": ( - "https://huggingface.co/google-bert/bert-large-uncased-whole-word-masking/resolve/main/tokenizer.json" - ), - "google-bert/bert-large-cased-whole-word-masking": ( - "https://huggingface.co/google-bert/bert-large-cased-whole-word-masking/resolve/main/tokenizer.json" - ), - "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad": ( - "https://huggingface.co/google-bert/bert-large-uncased-whole-word-masking-finetuned-squad/resolve/main/tokenizer.json" - ), - "google-bert/bert-large-cased-whole-word-masking-finetuned-squad": ( - "https://huggingface.co/google-bert/bert-large-cased-whole-word-masking-finetuned-squad/resolve/main/tokenizer.json" - ), - "google-bert/bert-base-cased-finetuned-mrpc": ( - "https://huggingface.co/google-bert/bert-base-cased-finetuned-mrpc/resolve/main/tokenizer.json" - ), - "google-bert/bert-base-german-dbmdz-cased": ( - "https://huggingface.co/google-bert/bert-base-german-dbmdz-cased/resolve/main/tokenizer.json" - ), - "google-bert/bert-base-german-dbmdz-uncased": ( - "https://huggingface.co/google-bert/bert-base-german-dbmdz-uncased/resolve/main/tokenizer.json" - ), - "TurkuNLP/bert-base-finnish-cased-v1": ( - "https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1/resolve/main/tokenizer.json" - ), - "TurkuNLP/bert-base-finnish-uncased-v1": ( - "https://huggingface.co/TurkuNLP/bert-base-finnish-uncased-v1/resolve/main/tokenizer.json" - ), - "wietsedv/bert-base-dutch-cased": ( - "https://huggingface.co/wietsedv/bert-base-dutch-cased/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google-bert/bert-base-uncased": 512, - "google-bert/bert-large-uncased": 512, - "google-bert/bert-base-cased": 512, - "google-bert/bert-large-cased": 512, - "google-bert/bert-base-multilingual-uncased": 512, - "google-bert/bert-base-multilingual-cased": 512, - "google-bert/bert-base-chinese": 512, - "google-bert/bert-base-german-cased": 512, - "google-bert/bert-large-uncased-whole-word-masking": 512, - "google-bert/bert-large-cased-whole-word-masking": 512, - "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad": 512, - "google-bert/bert-large-cased-whole-word-masking-finetuned-squad": 512, - "google-bert/bert-base-cased-finetuned-mrpc": 512, - "google-bert/bert-base-german-dbmdz-cased": 512, - "google-bert/bert-base-german-dbmdz-uncased": 512, - "TurkuNLP/bert-base-finnish-cased-v1": 512, - "TurkuNLP/bert-base-finnish-uncased-v1": 512, - "wietsedv/bert-base-dutch-cased": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "google-bert/bert-base-uncased": {"do_lower_case": True}, - "google-bert/bert-large-uncased": {"do_lower_case": True}, - "google-bert/bert-base-cased": {"do_lower_case": False}, - "google-bert/bert-large-cased": {"do_lower_case": False}, - "google-bert/bert-base-multilingual-uncased": {"do_lower_case": True}, - "google-bert/bert-base-multilingual-cased": {"do_lower_case": False}, - "google-bert/bert-base-chinese": {"do_lower_case": False}, - "google-bert/bert-base-german-cased": {"do_lower_case": False}, - "google-bert/bert-large-uncased-whole-word-masking": {"do_lower_case": True}, - "google-bert/bert-large-cased-whole-word-masking": {"do_lower_case": False}, - "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad": {"do_lower_case": True}, - "google-bert/bert-large-cased-whole-word-masking-finetuned-squad": {"do_lower_case": False}, - "google-bert/bert-base-cased-finetuned-mrpc": {"do_lower_case": False}, - "google-bert/bert-base-german-dbmdz-cased": {"do_lower_case": False}, - "google-bert/bert-base-german-dbmdz-uncased": {"do_lower_case": True}, - "TurkuNLP/bert-base-finnish-cased-v1": {"do_lower_case": False}, - "TurkuNLP/bert-base-finnish-uncased-v1": {"do_lower_case": True}, - "wietsedv/bert-base-dutch-cased": {"do_lower_case": False}, -} - class BertTokenizerFast(PreTrainedTokenizerFast): r""" @@ -199,9 +70,6 @@ class BertTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = BertTokenizer def __init__( diff --git a/src/transformers/models/bert_generation/tokenization_bert_generation.py b/src/transformers/models/bert_generation/tokenization_bert_generation.py index 3b6298fcbd..772eb123c3 100644 --- a/src/transformers/models/bert_generation/tokenization_bert_generation.py +++ b/src/transformers/models/bert_generation/tokenization_bert_generation.py @@ -29,16 +29,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "bert_for_seq_generation": ( - "https://huggingface.co/google/bert_for_seq_generation_L-24_bbc_encoder/resolve/main/spiece.model" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"bert_for_seq_generation": 512} - class BertGenerationTokenizer(PreTrainedTokenizer): """ @@ -82,8 +72,6 @@ class BertGenerationTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES prefix_tokens: List[int] = [] model_input_names = ["input_ids", "attention_mask"] diff --git a/src/transformers/models/bert_japanese/tokenization_bert_japanese.py b/src/transformers/models/bert_japanese/tokenization_bert_japanese.py index b2d1ac1958..fe5cd06f7f 100644 --- a/src/transformers/models/bert_japanese/tokenization_bert_japanese.py +++ b/src/transformers/models/bert_japanese/tokenization_bert_japanese.py @@ -36,51 +36,6 @@ VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "spm_file": "spiece.model"} SPIECE_UNDERLINE = "▁" -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "cl-tohoku/bert-base-japanese": "https://huggingface.co/cl-tohoku/bert-base-japanese/resolve/main/vocab.txt", - "cl-tohoku/bert-base-japanese-whole-word-masking": ( - "https://huggingface.co/cl-tohoku/bert-base-japanese-whole-word-masking/resolve/main/vocab.txt" - ), - "cl-tohoku/bert-base-japanese-char": ( - "https://huggingface.co/cl-tohoku/bert-base-japanese-char/resolve/main/vocab.txt" - ), - "cl-tohoku/bert-base-japanese-char-whole-word-masking": ( - "https://huggingface.co/cl-tohoku/bert-base-japanese-char-whole-word-masking/resolve/main/vocab.txt" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "cl-tohoku/bert-base-japanese": 512, - "cl-tohoku/bert-base-japanese-whole-word-masking": 512, - "cl-tohoku/bert-base-japanese-char": 512, - "cl-tohoku/bert-base-japanese-char-whole-word-masking": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "cl-tohoku/bert-base-japanese": { - "do_lower_case": False, - "word_tokenizer_type": "mecab", - "subword_tokenizer_type": "wordpiece", - }, - "cl-tohoku/bert-base-japanese-whole-word-masking": { - "do_lower_case": False, - "word_tokenizer_type": "mecab", - "subword_tokenizer_type": "wordpiece", - }, - "cl-tohoku/bert-base-japanese-char": { - "do_lower_case": False, - "word_tokenizer_type": "mecab", - "subword_tokenizer_type": "character", - }, - "cl-tohoku/bert-base-japanese-char-whole-word-masking": { - "do_lower_case": False, - "word_tokenizer_type": "mecab", - "subword_tokenizer_type": "character", - }, -} - # Copied from transformers.models.bert.tokenization_bert.load_vocab def load_vocab(vocab_file): @@ -136,9 +91,6 @@ class BertJapaneseTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/bertweet/tokenization_bertweet.py b/src/transformers/models/bertweet/tokenization_bertweet.py index 74bc040c25..7f14ed61da 100644 --- a/src/transformers/models/bertweet/tokenization_bertweet.py +++ b/src/transformers/models/bertweet/tokenization_bertweet.py @@ -35,19 +35,6 @@ VOCAB_FILES_NAMES = { "merges_file": "bpe.codes", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "vinai/bertweet-base": "https://huggingface.co/vinai/bertweet-base/resolve/main/vocab.txt", - }, - "merges_file": { - "vinai/bertweet-base": "https://huggingface.co/vinai/bertweet-base/resolve/main/bpe.codes", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "vinai/bertweet-base": 128, -} - def get_pairs(word): """ @@ -117,8 +104,6 @@ class BertweetTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/big_bird/configuration_big_bird.py b/src/transformers/models/big_bird/configuration_big_bird.py index 9802e75853..f803d56839 100644 --- a/src/transformers/models/big_bird/configuration_big_bird.py +++ b/src/transformers/models/big_bird/configuration_big_bird.py @@ -23,12 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -BIG_BIRD_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/bigbird-roberta-base": "https://huggingface.co/google/bigbird-roberta-base/resolve/main/config.json", - "google/bigbird-roberta-large": "https://huggingface.co/google/bigbird-roberta-large/resolve/main/config.json", - "google/bigbird-base-trivia-itc": "https://huggingface.co/google/bigbird-base-trivia-itc/resolve/main/config.json", - # See all BigBird models at https://huggingface.co/models?filter=big_bird -} + +from ..deprecated._archive_maps import BIG_BIRD_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class BigBirdConfig(PretrainedConfig): diff --git a/src/transformers/models/big_bird/modeling_big_bird.py b/src/transformers/models/big_bird/modeling_big_bird.py index 008985f760..510c980795 100755 --- a/src/transformers/models/big_bird/modeling_big_bird.py +++ b/src/transformers/models/big_bird/modeling_big_bird.py @@ -54,12 +54,9 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "google/bigbird-roberta-base" _CONFIG_FOR_DOC = "BigBirdConfig" -BIG_BIRD_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/bigbird-roberta-base", - "google/bigbird-roberta-large", - "google/bigbird-base-trivia-itc", - # See all BigBird models at https://huggingface.co/models?filter=big_bird -] + +from ..deprecated._archive_maps import BIG_BIRD_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + _TRIVIA_QA_MAPPING = { "big_bird_attention": "attention/self", diff --git a/src/transformers/models/big_bird/tokenization_big_bird.py b/src/transformers/models/big_bird/tokenization_big_bird.py index e7c43a86a6..58dc57ef6d 100644 --- a/src/transformers/models/big_bird/tokenization_big_bird.py +++ b/src/transformers/models/big_bird/tokenization_big_bird.py @@ -30,24 +30,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/bigbird-roberta-base": "https://huggingface.co/google/bigbird-roberta-base/resolve/main/spiece.model", - "google/bigbird-roberta-large": ( - "https://huggingface.co/google/bigbird-roberta-large/resolve/main/spiece.model" - ), - "google/bigbird-base-trivia-itc": ( - "https://huggingface.co/google/bigbird-base-trivia-itc/resolve/main/spiece.model" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/bigbird-roberta-base": 4096, - "google/bigbird-roberta-large": 4096, - "google/bigbird-base-trivia-itc": 4096, -} - class BigBirdTokenizer(PreTrainedTokenizer): """ @@ -97,8 +79,6 @@ class BigBirdTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] prefix_tokens: List[int] = [] diff --git a/src/transformers/models/big_bird/tokenization_big_bird_fast.py b/src/transformers/models/big_bird/tokenization_big_bird_fast.py index 24fc33d805..fa37cd4ac7 100644 --- a/src/transformers/models/big_bird/tokenization_big_bird_fast.py +++ b/src/transformers/models/big_bird/tokenization_big_bird_fast.py @@ -32,35 +32,6 @@ else: logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/bigbird-roberta-base": "https://huggingface.co/google/bigbird-roberta-base/resolve/main/spiece.model", - "google/bigbird-roberta-large": ( - "https://huggingface.co/google/bigbird-roberta-large/resolve/main/spiece.model" - ), - "google/bigbird-base-trivia-itc": ( - "https://huggingface.co/google/bigbird-base-trivia-itc/resolve/main/spiece.model" - ), - }, - "tokenizer_file": { - "google/bigbird-roberta-base": ( - "https://huggingface.co/google/bigbird-roberta-base/resolve/main/tokenizer.json" - ), - "google/bigbird-roberta-large": ( - "https://huggingface.co/google/bigbird-roberta-large/resolve/main/tokenizer.json" - ), - "google/bigbird-base-trivia-itc": ( - "https://huggingface.co/google/bigbird-base-trivia-itc/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/bigbird-roberta-base": 4096, - "google/bigbird-roberta-large": 4096, - "google/bigbird-base-trivia-itc": 4096, -} - SPIECE_UNDERLINE = "▁" @@ -107,8 +78,6 @@ class BigBirdTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = BigBirdTokenizer model_input_names = ["input_ids", "attention_mask"] prefix_tokens: List[int] = [] diff --git a/src/transformers/models/bigbird_pegasus/configuration_bigbird_pegasus.py b/src/transformers/models/bigbird_pegasus/configuration_bigbird_pegasus.py index 1c78803c4b..5cdcbca775 100644 --- a/src/transformers/models/bigbird_pegasus/configuration_bigbird_pegasus.py +++ b/src/transformers/models/bigbird_pegasus/configuration_bigbird_pegasus.py @@ -26,18 +26,8 @@ from ...utils import TensorType, is_torch_available, logging logger = logging.get_logger(__name__) -BIGBIRD_PEGASUS_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/bigbird-pegasus-large-arxiv": ( - "https://huggingface.co/google/bigbird-pegasus-large-arxiv/resolve/main/config.json" - ), - "google/bigbird-pegasus-large-pubmed": ( - "https://huggingface.co/google/bigbird-pegasus-large-pubmed/resolve/main/config.json" - ), - "google/bigbird-pegasus-large-bigpatent": ( - "https://huggingface.co/google/bigbird-pegasus-large-bigpatent/resolve/main/config.json" - ), - # See all BigBirdPegasus models at https://huggingface.co/models?filter=bigbird_pegasus -} + +from ..deprecated._archive_maps import BIGBIRD_PEGASUS_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class BigBirdPegasusConfig(PretrainedConfig): diff --git a/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py b/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py index baf0814343..b863beb75e 100755 --- a/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py +++ b/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py @@ -54,12 +54,7 @@ _CONFIG_FOR_DOC = "BigBirdPegasusConfig" _EXPECTED_OUTPUT_SHAPE = [1, 7, 1024] -BIGBIRD_PEGASUS_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/bigbird-pegasus-large-arxiv", - "google/bigbird-pegasus-large-pubmed", - "google/bigbird-pegasus-large-bigpatent", - # See all BigBirdPegasus models at https://huggingface.co/models?filter=bigbird_pegasus -] +from ..deprecated._archive_maps import BIGBIRD_PEGASUS_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def shift_tokens_right(input_ids: torch.Tensor, pad_token_id: int, decoder_start_token_id: int): diff --git a/src/transformers/models/biogpt/configuration_biogpt.py b/src/transformers/models/biogpt/configuration_biogpt.py index 1fb2933f28..1b4155c0ae 100644 --- a/src/transformers/models/biogpt/configuration_biogpt.py +++ b/src/transformers/models/biogpt/configuration_biogpt.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -BIOGPT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/biogpt": "https://huggingface.co/microsoft/biogpt/resolve/main/config.json", - # See all BioGPT models at https://huggingface.co/models?filter=biogpt -} + +from ..deprecated._archive_maps import BIOGPT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class BioGptConfig(PretrainedConfig): diff --git a/src/transformers/models/biogpt/modeling_biogpt.py b/src/transformers/models/biogpt/modeling_biogpt.py index d98f0886df..30df3e0847 100755 --- a/src/transformers/models/biogpt/modeling_biogpt.py +++ b/src/transformers/models/biogpt/modeling_biogpt.py @@ -47,11 +47,7 @@ _CHECKPOINT_FOR_DOC = "microsoft/biogpt" _CONFIG_FOR_DOC = "BioGptConfig" -BIOGPT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/biogpt", - "microsoft/BioGPT-Large", - # See all BioGPT models at https://huggingface.co/models?filter=biogpt -] +from ..deprecated._archive_maps import BIOGPT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.opt.modeling_opt.OPTLearnedPositionalEmbedding with OPT->BioGpt diff --git a/src/transformers/models/biogpt/tokenization_biogpt.py b/src/transformers/models/biogpt/tokenization_biogpt.py index 093991ecb3..e16742ec5a 100644 --- a/src/transformers/models/biogpt/tokenization_biogpt.py +++ b/src/transformers/models/biogpt/tokenization_biogpt.py @@ -28,17 +28,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/biogpt": "https://huggingface.co/microsoft/biogpt/resolve/main/vocab.json", - }, - "merges_file": {"microsoft/biogpt": "https://huggingface.co/microsoft/biogpt/resolve/main/merges.txt"}, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/biogpt": 1024, -} - def get_pairs(word): """ @@ -97,8 +86,6 @@ class BioGptTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/bit/configuration_bit.py b/src/transformers/models/bit/configuration_bit.py index d11a8e3818..2ec6307421 100644 --- a/src/transformers/models/bit/configuration_bit.py +++ b/src/transformers/models/bit/configuration_bit.py @@ -21,9 +21,8 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -BIT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/bit-50": "https://huggingface.co/google/bit-50/resolve/main/config.json", -} + +from ..deprecated._archive_maps import BIT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class BitConfig(BackboneConfigMixin, PretrainedConfig): diff --git a/src/transformers/models/bit/modeling_bit.py b/src/transformers/models/bit/modeling_bit.py index 49bc75b5f0..27141a9009 100644 --- a/src/transformers/models/bit/modeling_bit.py +++ b/src/transformers/models/bit/modeling_bit.py @@ -56,10 +56,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 2048, 7, 7] _IMAGE_CLASS_CHECKPOINT = "google/bit-50" _IMAGE_CLASS_EXPECTED_OUTPUT = "tiger cat" -BIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/bit-50", - # See all BiT models at https://huggingface.co/models?filter=bit -] + +from ..deprecated._archive_maps import BIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def get_padding_value(padding=None, kernel_size=7, stride=1, dilation=1) -> Tuple[Tuple, bool]: diff --git a/src/transformers/models/blenderbot/configuration_blenderbot.py b/src/transformers/models/blenderbot/configuration_blenderbot.py index 4f55a96bf6..0060871059 100644 --- a/src/transformers/models/blenderbot/configuration_blenderbot.py +++ b/src/transformers/models/blenderbot/configuration_blenderbot.py @@ -27,10 +27,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -BLENDERBOT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/blenderbot-3B": "https://huggingface.co/facebook/blenderbot-3B/resolve/main/config.json", - # See all Blenderbot models at https://huggingface.co/models?filter=blenderbot -} + +from ..deprecated._archive_maps import BLENDERBOT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class BlenderbotConfig(PretrainedConfig): diff --git a/src/transformers/models/blenderbot/modeling_blenderbot.py b/src/transformers/models/blenderbot/modeling_blenderbot.py index 28b81387c1..5fa17abcdd 100755 --- a/src/transformers/models/blenderbot/modeling_blenderbot.py +++ b/src/transformers/models/blenderbot/modeling_blenderbot.py @@ -53,10 +53,7 @@ _CONFIG_FOR_DOC = "BlenderbotConfig" _CHECKPOINT_FOR_DOC = "facebook/blenderbot-400M-distill" -BLENDERBOT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/blenderbot-3B", - # See all Blenderbot models at https://huggingface.co/models?filter=blenderbot -] +from ..deprecated._archive_maps import BLENDERBOT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.bart.modeling_bart.shift_tokens_right diff --git a/src/transformers/models/blenderbot/tokenization_blenderbot.py b/src/transformers/models/blenderbot/tokenization_blenderbot.py index 29386c1233..b812f84b7d 100644 --- a/src/transformers/models/blenderbot/tokenization_blenderbot.py +++ b/src/transformers/models/blenderbot/tokenization_blenderbot.py @@ -34,16 +34,6 @@ VOCAB_FILES_NAMES = { "tokenizer_config_file": "tokenizer_config.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": {"facebook/blenderbot-3B": "https://huggingface.co/facebook/blenderbot-3B/resolve/main/vocab.json"}, - "merges_file": {"facebook/blenderbot-3B": "https://huggingface.co/facebook/blenderbot-3B/resolve/main/merges.txt"}, - "tokenizer_config_file": { - "facebook/blenderbot-3B": "https://huggingface.co/facebook/blenderbot-3B/resolve/main/tokenizer_config.json" - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"facebook/blenderbot-3B": 128} - @lru_cache() # Copied from transformers.models.roberta.tokenization_roberta.bytes_to_unicode @@ -166,8 +156,6 @@ class BlenderbotTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] # Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer.__init__ with Roberta->Blenderbot, RoBERTa->Blenderbot diff --git a/src/transformers/models/blenderbot/tokenization_blenderbot_fast.py b/src/transformers/models/blenderbot/tokenization_blenderbot_fast.py index 6245025b50..879173282d 100644 --- a/src/transformers/models/blenderbot/tokenization_blenderbot_fast.py +++ b/src/transformers/models/blenderbot/tokenization_blenderbot_fast.py @@ -33,16 +33,6 @@ VOCAB_FILES_NAMES = { "tokenizer_config_file": "tokenizer_config.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": {"facebook/blenderbot-3B": "https://huggingface.co/facebook/blenderbot-3B/resolve/main/vocab.json"}, - "merges_file": {"facebook/blenderbot-3B": "https://huggingface.co/facebook/blenderbot-3B/resolve/main/merges.txt"}, - "tokenizer_config_file": { - "facebook/blenderbot-3B": "https://huggingface.co/facebook/blenderbot-3B/resolve/main/tokenizer_config.json" - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"facebook/blenderbot-3B": 128} - class BlenderbotTokenizerFast(PreTrainedTokenizerFast): """ @@ -126,8 +116,6 @@ class BlenderbotTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = BlenderbotTokenizer diff --git a/src/transformers/models/blenderbot_small/configuration_blenderbot_small.py b/src/transformers/models/blenderbot_small/configuration_blenderbot_small.py index b41330656d..8b54bd3760 100644 --- a/src/transformers/models/blenderbot_small/configuration_blenderbot_small.py +++ b/src/transformers/models/blenderbot_small/configuration_blenderbot_small.py @@ -27,10 +27,7 @@ from ...utils import logging logger = logging.get_logger(__name__) -BLENDERBOT_SMALL_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/blenderbot_small-90M": "https://huggingface.co/facebook/blenderbot_small-90M/resolve/main/config.json", - # See all BlenderbotSmall models at https://huggingface.co/models?filter=blenderbot_small -} +from ..deprecated._archive_maps import BLENDERBOT_SMALL_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class BlenderbotSmallConfig(PretrainedConfig): diff --git a/src/transformers/models/blenderbot_small/modeling_blenderbot_small.py b/src/transformers/models/blenderbot_small/modeling_blenderbot_small.py index f9a9508e59..da07669a4e 100755 --- a/src/transformers/models/blenderbot_small/modeling_blenderbot_small.py +++ b/src/transformers/models/blenderbot_small/modeling_blenderbot_small.py @@ -49,10 +49,7 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "BlenderbotSmallConfig" -BLENDERBOT_SMALL_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/blenderbot_small-90M", - # See all BlenderbotSmall models at https://huggingface.co/models?filter=blenderbot_small -] +from ..deprecated._archive_maps import BLENDERBOT_SMALL_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.bart.modeling_bart.shift_tokens_right diff --git a/src/transformers/models/blenderbot_small/tokenization_blenderbot_small.py b/src/transformers/models/blenderbot_small/tokenization_blenderbot_small.py index 240495d738..820868c8cb 100644 --- a/src/transformers/models/blenderbot_small/tokenization_blenderbot_small.py +++ b/src/transformers/models/blenderbot_small/tokenization_blenderbot_small.py @@ -33,22 +33,6 @@ VOCAB_FILES_NAMES = { "tokenizer_config_file": "tokenizer_config.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/blenderbot_small-90M": "https://huggingface.co/facebook/blenderbot_small-90M/resolve/main/vocab.json" - }, - "merges_file": { - "facebook/blenderbot_small-90M": "https://huggingface.co/facebook/blenderbot_small-90M/resolve/main/merges.txt" - }, - "tokenizer_config_file": { - "facebook/blenderbot_small-90M": ( - "https://huggingface.co/facebook/blenderbot_small-90M/resolve/main/tokenizer_config.json" - ) - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"facebook/blenderbot_small-90M": 512} - def get_pairs(word): """ @@ -92,8 +76,6 @@ class BlenderbotSmallTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/blenderbot_small/tokenization_blenderbot_small_fast.py b/src/transformers/models/blenderbot_small/tokenization_blenderbot_small_fast.py index 4bf0017b5f..a0c61505b1 100644 --- a/src/transformers/models/blenderbot_small/tokenization_blenderbot_small_fast.py +++ b/src/transformers/models/blenderbot_small/tokenization_blenderbot_small_fast.py @@ -30,24 +30,6 @@ VOCAB_FILES_NAMES = { "tokenizer_config_file": "tokenizer_config.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/blenderbot_small-90M": "https://huggingface.co/facebook/blenderbot_small-90M/resolve/main/vocab.json" - }, - "merges_file": { - "facebook/blenderbot_small-90M": "https://huggingface.co/facebook/blenderbot_small-90M/resolve/main/merges.txt" - }, - "tokenizer_config_file": { - "facebook/blenderbot_small-90M": ( - "https://huggingface.co/facebook/blenderbot_small-90M/resolve/main/tokenizer_config.json" - ) - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/blenderbot_small-90M": 512, -} - class BlenderbotSmallTokenizerFast(PreTrainedTokenizerFast): """ @@ -59,8 +41,6 @@ class BlenderbotSmallTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = BlenderbotSmallTokenizer def __init__( diff --git a/src/transformers/models/blip/configuration_blip.py b/src/transformers/models/blip/configuration_blip.py index 42e35958ce..2a76660c0f 100644 --- a/src/transformers/models/blip/configuration_blip.py +++ b/src/transformers/models/blip/configuration_blip.py @@ -23,24 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -BLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "Salesforce/blip-vqa-base": "https://huggingface.co/Salesforce/blip-vqa-base/resolve/main/config.json", - "Salesforce/blip-vqa-capfit-large": ( - "https://huggingface.co/Salesforce/blip-vqa-base-capfit/resolve/main/config.json" - ), - "Salesforce/blip-image-captioning-base": ( - "https://huggingface.co/Salesforce/blip-image-captioning-base/resolve/main/config.json" - ), - "Salesforce/blip-image-captioning-large": ( - "https://huggingface.co/Salesforce/blip-image-captioning-large/resolve/main/config.json" - ), - "Salesforce/blip-itm-base-coco": "https://huggingface.co/Salesforce/blip-itm-base-coco/resolve/main/config.json", - "Salesforce/blip-itm-large-coco": "https://huggingface.co/Salesforce/blip-itm-large-coco/resolve/main/config.json", - "Salesforce/blip-itm-base-flikr": "https://huggingface.co/Salesforce/blip-itm-base-flikr/resolve/main/config.json", - "Salesforce/blip-itm-large-flikr": ( - "https://huggingface.co/Salesforce/blip-itm-large-flikr/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import BLIP_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class BlipTextConfig(PretrainedConfig): diff --git a/src/transformers/models/blip/modeling_blip.py b/src/transformers/models/blip/modeling_blip.py index 1dc79efb65..39506478f1 100644 --- a/src/transformers/models/blip/modeling_blip.py +++ b/src/transformers/models/blip/modeling_blip.py @@ -41,17 +41,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "Salesforce/blip-vqa-base" -BLIP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Salesforce/blip-vqa-base", - "Salesforce/blip-vqa-capfilt-large", - "Salesforce/blip-image-captioning-base", - "Salesforce/blip-image-captioning-large", - "Salesforce/blip-itm-base-coco", - "Salesforce/blip-itm-large-coco", - "Salesforce/blip-itm-base-flickr", - "Salesforce/blip-itm-large-flickr", - # See all BLIP models at https://huggingface.co/models?filter=blip -] + +from ..deprecated._archive_maps import BLIP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.clip.modeling_clip.contrastive_loss diff --git a/src/transformers/models/blip/modeling_tf_blip.py b/src/transformers/models/blip/modeling_tf_blip.py index 5952aa145c..37098467a7 100644 --- a/src/transformers/models/blip/modeling_tf_blip.py +++ b/src/transformers/models/blip/modeling_tf_blip.py @@ -48,17 +48,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "Salesforce/blip-vqa-base" -TF_BLIP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Salesforce/blip-vqa-base", - "Salesforce/blip-vqa-capfilt-large", - "Salesforce/blip-image-captioning-base", - "Salesforce/blip-image-captioning-large", - "Salesforce/blip-itm-base-coco", - "Salesforce/blip-itm-large-coco", - "Salesforce/blip-itm-base-flickr", - "Salesforce/blip-itm-large-flickr", - # See all BLIP models at https://huggingface.co/models?filter=blip -] + +from ..deprecated._archive_maps import TF_BLIP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.clip.modeling_tf_clip.contrastive_loss diff --git a/src/transformers/models/blip_2/configuration_blip_2.py b/src/transformers/models/blip_2/configuration_blip_2.py index 85749888a5..f5645f5dee 100644 --- a/src/transformers/models/blip_2/configuration_blip_2.py +++ b/src/transformers/models/blip_2/configuration_blip_2.py @@ -25,9 +25,8 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -BLIP_2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "salesforce/blip2-opt-2.7b": "https://huggingface.co/salesforce/blip2-opt-2.7b/resolve/main/config.json", -} + +from ..deprecated._archive_maps import BLIP_2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Blip2VisionConfig(PretrainedConfig): diff --git a/src/transformers/models/blip_2/modeling_blip_2.py b/src/transformers/models/blip_2/modeling_blip_2.py index c776df1bc0..935e041eb8 100644 --- a/src/transformers/models/blip_2/modeling_blip_2.py +++ b/src/transformers/models/blip_2/modeling_blip_2.py @@ -47,10 +47,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "Salesforce/blip2-opt-2.7b" -BLIP_2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Salesforce/blip2-opt-2.7b", - # See all BLIP-2 models at https://huggingface.co/models?filter=blip -] + +from ..deprecated._archive_maps import BLIP_2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/bloom/configuration_bloom.py b/src/transformers/models/bloom/configuration_bloom.py index 17395625e0..e04877485e 100644 --- a/src/transformers/models/bloom/configuration_bloom.py +++ b/src/transformers/models/bloom/configuration_bloom.py @@ -29,14 +29,8 @@ from ...utils import is_torch_available, logging logger = logging.get_logger(__name__) -BLOOM_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "bigscience/bloom": "https://huggingface.co/bigscience/bloom/resolve/main/config.json", - "bigscience/bloom-560m": "https://huggingface.co/bigscience/bloom-560m/blob/main/config.json", - "bigscience/bloom-1b1": "https://huggingface.co/bigscience/bloom-1b1/blob/main/config.json", - "bigscience/bloom-1b7": "https://huggingface.co/bigscience/bloom-1b7/blob/main/config.json", - "bigscience/bloom-3b": "https://huggingface.co/bigscience/bloom-3b/blob/main/config.json", - "bigscience/bloom-7b1": "https://huggingface.co/bigscience/bloom-7b1/blob/main/config.json", -} + +from ..deprecated._archive_maps import BLOOM_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class BloomConfig(PretrainedConfig): diff --git a/src/transformers/models/bloom/modeling_bloom.py b/src/transformers/models/bloom/modeling_bloom.py index 14700d6f12..05b18f5938 100644 --- a/src/transformers/models/bloom/modeling_bloom.py +++ b/src/transformers/models/bloom/modeling_bloom.py @@ -43,15 +43,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "bigscience/bloom-560m" _CONFIG_FOR_DOC = "BloomConfig" -BLOOM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "bigscience/bigscience-small-testing", - "bigscience/bloom-560m", - "bigscience/bloom-1b1", - "bigscience/bloom-1b7", - "bigscience/bloom-3b", - "bigscience/bloom-7b1", - "bigscience/bloom", -] + +from ..deprecated._archive_maps import BLOOM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def build_alibi_tensor(attention_mask: torch.Tensor, num_heads: int, dtype: torch.dtype) -> torch.Tensor: diff --git a/src/transformers/models/bloom/tokenization_bloom_fast.py b/src/transformers/models/bloom/tokenization_bloom_fast.py index c0189e08b3..3a0972d87a 100644 --- a/src/transformers/models/bloom/tokenization_bloom_fast.py +++ b/src/transformers/models/bloom/tokenization_bloom_fast.py @@ -27,18 +27,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "tokenizer_file": { - "bigscience/tokenizer": "https://huggingface.co/bigscience/tokenizer/blob/main/tokenizer.json", - "bigscience/bloom-560m": "https://huggingface.co/bigscience/bloom-560m/blob/main/tokenizer.json", - "bigscience/bloom-1b1": "https://huggingface.co/bigscience/bloom-1b1/blob/main/tokenizer.json", - "bigscience/bloom-1b7": "https://huggingface.co/bigscience/bloom-1b7/blob/main/tokenizer.json", - "bigscience/bloom-3b": "https://huggingface.co/bigscience/bloom-3b/blob/main/tokenizer.json", - "bigscience/bloom-7b1": "https://huggingface.co/bigscience/bloom-7b1/blob/main/tokenizer.json", - "bigscience/bloom": "https://huggingface.co/bigscience/bloom/blob/main/tokenizer.json", - }, -} - class BloomTokenizerFast(PreTrainedTokenizerFast): """ @@ -94,7 +82,6 @@ class BloomTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = None # No `max_model_input_sizes` as BLOOM uses ALiBi positional embeddings diff --git a/src/transformers/models/bridgetower/configuration_bridgetower.py b/src/transformers/models/bridgetower/configuration_bridgetower.py index c12c1600e9..2d3340ad62 100644 --- a/src/transformers/models/bridgetower/configuration_bridgetower.py +++ b/src/transformers/models/bridgetower/configuration_bridgetower.py @@ -23,12 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -BRIDGETOWER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "BridgeTower/bridgetower-base": "https://huggingface.co/BridgeTower/bridgetower-base/blob/main/config.json", - "BridgeTower/bridgetower-base-itm-mlm": ( - "https://huggingface.co/BridgeTower/bridgetower-base-itm-mlm/blob/main/config.json" - ), -} + +from ..deprecated._archive_maps import BRIDGETOWER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class BridgeTowerVisionConfig(PretrainedConfig): diff --git a/src/transformers/models/bridgetower/modeling_bridgetower.py b/src/transformers/models/bridgetower/modeling_bridgetower.py index f5822070db..bcace39b29 100644 --- a/src/transformers/models/bridgetower/modeling_bridgetower.py +++ b/src/transformers/models/bridgetower/modeling_bridgetower.py @@ -44,11 +44,8 @@ _CONFIG_FOR_DOC = "BridgeTowerConfig" _CHECKPOINT_FOR_DOC = "BridgeTower/bridgetower-base" _TOKENIZER_FOR_DOC = "RobertaTokenizer" -BRIDGETOWER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "BridgeTower/bridgetower-base", - "BridgeTower/bridgetower-base-itm-mlm", - # See all bridgetower models at https://huggingface.co/BridgeTower -] + +from ..deprecated._archive_maps import BRIDGETOWER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 BRIDGETOWER_START_DOCSTRING = r""" diff --git a/src/transformers/models/bros/configuration_bros.py b/src/transformers/models/bros/configuration_bros.py index 4384810a55..547bbf39ad 100644 --- a/src/transformers/models/bros/configuration_bros.py +++ b/src/transformers/models/bros/configuration_bros.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -BROS_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "jinho8345/bros-base-uncased": "https://huggingface.co/jinho8345/bros-base-uncased/blob/main/config.json", - "jinho8345/bros-large-uncased": "https://huggingface.co/jinho8345/bros-large-uncased/blob/main/config.json", -} + +from ..deprecated._archive_maps import BROS_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class BrosConfig(PretrainedConfig): diff --git a/src/transformers/models/bros/modeling_bros.py b/src/transformers/models/bros/modeling_bros.py index d3a17b23c9..32f0338f0e 100755 --- a/src/transformers/models/bros/modeling_bros.py +++ b/src/transformers/models/bros/modeling_bros.py @@ -47,11 +47,9 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "jinho8345/bros-base-uncased" _CONFIG_FOR_DOC = "BrosConfig" -BROS_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "jinho8345/bros-base-uncased", - "jinho8345/bros-large-uncased", - # See all Bros models at https://huggingface.co/models?filter=bros -] + +from ..deprecated._archive_maps import BROS_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + BROS_START_DOCSTRING = r""" This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. diff --git a/src/transformers/models/camembert/configuration_camembert.py b/src/transformers/models/camembert/configuration_camembert.py index d904c35ad7..d29ca067db 100644 --- a/src/transformers/models/camembert/configuration_camembert.py +++ b/src/transformers/models/camembert/configuration_camembert.py @@ -25,15 +25,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "almanach/camembert-base": "https://huggingface.co/almanach/camembert-base/resolve/main/config.json", - "umberto-commoncrawl-cased-v1": ( - "https://huggingface.co/Musixmatch/umberto-commoncrawl-cased-v1/resolve/main/config.json" - ), - "umberto-wikipedia-uncased-v1": ( - "https://huggingface.co/Musixmatch/umberto-wikipedia-uncased-v1/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class CamembertConfig(PretrainedConfig): diff --git a/src/transformers/models/camembert/modeling_camembert.py b/src/transformers/models/camembert/modeling_camembert.py index cd0b329b6a..26250896b2 100644 --- a/src/transformers/models/camembert/modeling_camembert.py +++ b/src/transformers/models/camembert/modeling_camembert.py @@ -51,12 +51,9 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "almanach/camembert-base" _CONFIG_FOR_DOC = "CamembertConfig" -CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "almanach/camembert-base", - "Musixmatch/umberto-commoncrawl-cased-v1", - "Musixmatch/umberto-wikipedia-uncased-v1", - # See all CamemBERT models at https://huggingface.co/models?filter=camembert -] + +from ..deprecated._archive_maps import CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + CAMEMBERT_START_DOCSTRING = r""" diff --git a/src/transformers/models/camembert/modeling_tf_camembert.py b/src/transformers/models/camembert/modeling_tf_camembert.py index e3e3fca4ce..9ec998593d 100644 --- a/src/transformers/models/camembert/modeling_tf_camembert.py +++ b/src/transformers/models/camembert/modeling_tf_camembert.py @@ -65,9 +65,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "almanach/camembert-base" _CONFIG_FOR_DOC = "CamembertConfig" -TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - # See all CamemBERT models at https://huggingface.co/models?filter=camembert -] + +from ..deprecated._archive_maps import TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 CAMEMBERT_START_DOCSTRING = r""" diff --git a/src/transformers/models/camembert/tokenization_camembert.py b/src/transformers/models/camembert/tokenization_camembert.py index 0949db02fb..51d70b198b 100644 --- a/src/transformers/models/camembert/tokenization_camembert.py +++ b/src/transformers/models/camembert/tokenization_camembert.py @@ -29,15 +29,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "almanach/camembert-base": "https://huggingface.co/almanach/camembert-base/resolve/main/sentencepiece.bpe.model", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "almanach/camembert-base": 512, -} SPIECE_UNDERLINE = "▁" @@ -113,8 +104,6 @@ class CamembertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/camembert/tokenization_camembert_fast.py b/src/transformers/models/camembert/tokenization_camembert_fast.py index 627971eb51..d1f0db688a 100644 --- a/src/transformers/models/camembert/tokenization_camembert_fast.py +++ b/src/transformers/models/camembert/tokenization_camembert_fast.py @@ -34,18 +34,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "almanach/camembert-base": "https://huggingface.co/almanach/camembert-base/resolve/main/sentencepiece.bpe.model", - }, - "tokenizer_file": { - "almanach/camembert-base": "https://huggingface.co/almanach/camembert-base/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "almanach/camembert-base": 512, -} SPIECE_UNDERLINE = "▁" @@ -103,8 +91,6 @@ class CamembertTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = CamembertTokenizer diff --git a/src/transformers/models/canine/configuration_canine.py b/src/transformers/models/canine/configuration_canine.py index f1e1bb4158..c5a77a5c4b 100644 --- a/src/transformers/models/canine/configuration_canine.py +++ b/src/transformers/models/canine/configuration_canine.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -CANINE_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/canine-s": "https://huggingface.co/google/canine-s/resolve/main/config.json", - # See all CANINE models at https://huggingface.co/models?filter=canine -} + +from ..deprecated._archive_maps import CANINE_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class CanineConfig(PretrainedConfig): diff --git a/src/transformers/models/canine/modeling_canine.py b/src/transformers/models/canine/modeling_canine.py index 378a577525..023287153a 100644 --- a/src/transformers/models/canine/modeling_canine.py +++ b/src/transformers/models/canine/modeling_canine.py @@ -52,11 +52,9 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "google/canine-s" _CONFIG_FOR_DOC = "CanineConfig" -CANINE_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/canine-s", - "google/canine-r", - # See all CANINE models at https://huggingface.co/models?filter=canine -] + +from ..deprecated._archive_maps import CANINE_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + # Support up to 16 hash functions. _PRIMES = [31, 43, 59, 61, 73, 97, 103, 113, 137, 149, 157, 173, 181, 193, 211, 223] diff --git a/src/transformers/models/canine/tokenization_canine.py b/src/transformers/models/canine/tokenization_canine.py index 25932ae75d..024507f778 100644 --- a/src/transformers/models/canine/tokenization_canine.py +++ b/src/transformers/models/canine/tokenization_canine.py @@ -23,10 +23,6 @@ from ...utils import logging logger = logging.get_logger(__name__) -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "nielsr/canine-s": 2048, -} - # Unicode defines 1,114,112 total “codepoints” UNICODE_VOCAB_SIZE = 1114112 @@ -73,8 +69,6 @@ class CanineTokenizer(PreTrainedTokenizer): The maximum sentence length the model accepts. """ - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - def __init__( self, bos_token=chr(CLS), diff --git a/src/transformers/models/chinese_clip/configuration_chinese_clip.py b/src/transformers/models/chinese_clip/configuration_chinese_clip.py index 53b6d49b3f..349833d1f2 100644 --- a/src/transformers/models/chinese_clip/configuration_chinese_clip.py +++ b/src/transformers/models/chinese_clip/configuration_chinese_clip.py @@ -30,11 +30,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -CHINESE_CLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "OFA-Sys/chinese-clip-vit-base-patch16": ( - "https://huggingface.co/OFA-Sys/chinese-clip-vit-base-patch16/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import CHINESE_CLIP_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ChineseCLIPTextConfig(PretrainedConfig): diff --git a/src/transformers/models/chinese_clip/modeling_chinese_clip.py b/src/transformers/models/chinese_clip/modeling_chinese_clip.py index a16fb081b1..d8e97c20b2 100644 --- a/src/transformers/models/chinese_clip/modeling_chinese_clip.py +++ b/src/transformers/models/chinese_clip/modeling_chinese_clip.py @@ -48,10 +48,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "OFA-Sys/chinese-clip-vit-base-patch16" _CONFIG_FOR_DOC = "ChineseCLIPConfig" -CHINESE_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "OFA-Sys/chinese-clip-vit-base-patch16", - # See all Chinese-CLIP models at https://huggingface.co/models?filter=chinese_clip -] + +from ..deprecated._archive_maps import CHINESE_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # https://sachinruk.github.io/blog/pytorch/pytorch%20lightning/loss%20function/gpu/2021/03/07/CLIP.html diff --git a/src/transformers/models/clap/configuration_clap.py b/src/transformers/models/clap/configuration_clap.py index 1a02d84609..0a36402249 100644 --- a/src/transformers/models/clap/configuration_clap.py +++ b/src/transformers/models/clap/configuration_clap.py @@ -23,11 +23,6 @@ from ...utils import logging logger = logging.get_logger(__name__) -CLAP_PRETRAINED_MODEL_ARCHIVE_LIST = { - "laion/clap-htsat-fused": "https://huggingface.co/laion/clap-htsat-fused/resolve/main/config.json", - "laion/clap-htsat-unfused": "https://huggingface.co/laion/clap-htsat-unfused/resolve/main/config.json", -} - class ClapTextConfig(PretrainedConfig): r""" diff --git a/src/transformers/models/clap/modeling_clap.py b/src/transformers/models/clap/modeling_clap.py index 6310b9675f..b2c0df4866 100644 --- a/src/transformers/models/clap/modeling_clap.py +++ b/src/transformers/models/clap/modeling_clap.py @@ -44,11 +44,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "laion/clap-htsat-fused" -CLAP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "laion/clap-htsat-fused", - "laion/clap-htsat-unfused", - # See all clap models at https://huggingface.co/models?filter=clap -] + +from ..deprecated._archive_maps import CLAP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Adapted from: https://github.com/LAION-AI/CLAP/blob/6ad05a971ba0622f6acee8c41993e0d02bbed639/src/open_clip/utils.py#L191 diff --git a/src/transformers/models/clip/configuration_clip.py b/src/transformers/models/clip/configuration_clip.py index 8c3e30ee05..a48cb73a97 100644 --- a/src/transformers/models/clip/configuration_clip.py +++ b/src/transformers/models/clip/configuration_clip.py @@ -30,10 +30,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -CLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "openai/clip-vit-base-patch32": "https://huggingface.co/openai/clip-vit-base-patch32/resolve/main/config.json", - # See all CLIP models at https://huggingface.co/models?filter=clip -} + +from ..deprecated._archive_maps import CLIP_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class CLIPTextConfig(PretrainedConfig): diff --git a/src/transformers/models/clip/modeling_clip.py b/src/transformers/models/clip/modeling_clip.py index 06ee5f6e32..a4ce51625e 100644 --- a/src/transformers/models/clip/modeling_clip.py +++ b/src/transformers/models/clip/modeling_clip.py @@ -48,10 +48,8 @@ _CHECKPOINT_FOR_DOC = "openai/clip-vit-base-patch32" _IMAGE_CLASS_CHECKPOINT = "openai/clip-vit-base-patch32" _IMAGE_CLASS_EXPECTED_OUTPUT = "LABEL_0" -CLIP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "openai/clip-vit-base-patch32", - # See all CLIP models at https://huggingface.co/models?filter=clip -] + +from ..deprecated._archive_maps import CLIP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # contrastive loss function, adapted from diff --git a/src/transformers/models/clip/modeling_tf_clip.py b/src/transformers/models/clip/modeling_tf_clip.py index d8dd7f0bd8..c7e8ba7f5c 100644 --- a/src/transformers/models/clip/modeling_tf_clip.py +++ b/src/transformers/models/clip/modeling_tf_clip.py @@ -51,10 +51,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "openai/clip-vit-base-patch32" -TF_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "openai/clip-vit-base-patch32", - # See all CLIP models at https://huggingface.co/models?filter=clip -] + +from ..deprecated._archive_maps import TF_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 LARGE_NEGATIVE = -1e8 diff --git a/src/transformers/models/clip/tokenization_clip.py b/src/transformers/models/clip/tokenization_clip.py index f62ef65c5e..7b4ad88b80 100644 --- a/src/transformers/models/clip/tokenization_clip.py +++ b/src/transformers/models/clip/tokenization_clip.py @@ -33,24 +33,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "openai/clip-vit-base-patch32": "https://huggingface.co/openai/clip-vit-base-patch32/resolve/main/vocab.json", - }, - "merges_file": { - "openai/clip-vit-base-patch32": "https://huggingface.co/openai/clip-vit-base-patch32/resolve/main/merges.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "openai/clip-vit-base-patch32": 77, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "openai/clip-vit-base-patch32": {}, -} - @lru_cache() def bytes_to_unicode(): @@ -296,8 +278,6 @@ class CLIPTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/clip/tokenization_clip_fast.py b/src/transformers/models/clip/tokenization_clip_fast.py index 3b092b0f8d..6198958a03 100644 --- a/src/transformers/models/clip/tokenization_clip_fast.py +++ b/src/transformers/models/clip/tokenization_clip_fast.py @@ -28,24 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "openai/clip-vit-base-patch32": "https://huggingface.co/openai/clip-vit-base-patch32/resolve/main/vocab.json", - }, - "merges_file": { - "openai/clip-vit-base-patch32": "https://huggingface.co/openai/clip-vit-base-patch32/resolve/main/merges.txt", - }, - "tokenizer_file": { - "openai/clip-vit-base-patch32": ( - "https://huggingface.co/openai/clip-vit-base-patch32/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "openai/clip-vit-base-patch32": 77, -} - class CLIPTokenizerFast(PreTrainedTokenizerFast): """ @@ -74,8 +56,6 @@ class CLIPTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = CLIPTokenizer diff --git a/src/transformers/models/clipseg/configuration_clipseg.py b/src/transformers/models/clipseg/configuration_clipseg.py index 555d226e10..07ba08f475 100644 --- a/src/transformers/models/clipseg/configuration_clipseg.py +++ b/src/transformers/models/clipseg/configuration_clipseg.py @@ -23,9 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -CLIPSEG_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "CIDAS/clipseg-rd64": "https://huggingface.co/CIDAS/clipseg-rd64/resolve/main/config.json", -} + +from ..deprecated._archive_maps import CLIPSEG_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class CLIPSegTextConfig(PretrainedConfig): diff --git a/src/transformers/models/clipseg/modeling_clipseg.py b/src/transformers/models/clipseg/modeling_clipseg.py index b250e09ad2..06e4c83e7e 100644 --- a/src/transformers/models/clipseg/modeling_clipseg.py +++ b/src/transformers/models/clipseg/modeling_clipseg.py @@ -42,10 +42,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "CIDAS/clipseg-rd64-refined" -CLIPSEG_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "CIDAS/clipseg-rd64-refined", - # See all CLIPSeg models at https://huggingface.co/models?filter=clipseg -] + +from ..deprecated._archive_maps import CLIPSEG_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # contrastive loss function, adapted from diff --git a/src/transformers/models/clvp/configuration_clvp.py b/src/transformers/models/clvp/configuration_clvp.py index 3d20b5c16d..00906e7d7f 100644 --- a/src/transformers/models/clvp/configuration_clvp.py +++ b/src/transformers/models/clvp/configuration_clvp.py @@ -28,9 +28,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -CLVP_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "susnato/clvp_dev": "https://huggingface.co/susnato/clvp_dev/resolve/main/config.json", -} + +from ..deprecated._archive_maps import CLVP_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ClvpEncoderConfig(PretrainedConfig): diff --git a/src/transformers/models/clvp/modeling_clvp.py b/src/transformers/models/clvp/modeling_clvp.py index b660f54e5d..654989dcbd 100644 --- a/src/transformers/models/clvp/modeling_clvp.py +++ b/src/transformers/models/clvp/modeling_clvp.py @@ -55,10 +55,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "susnato/clvp_dev" -CLVP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "susnato/clvp_dev", - # See all Clvp models at https://huggingface.co/models?filter=clvp -] + +from ..deprecated._archive_maps import CLVP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.clip.modeling_clip.contrastive_loss diff --git a/src/transformers/models/clvp/tokenization_clvp.py b/src/transformers/models/clvp/tokenization_clvp.py index f09245f94b..d77564f718 100644 --- a/src/transformers/models/clvp/tokenization_clvp.py +++ b/src/transformers/models/clvp/tokenization_clvp.py @@ -33,19 +33,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "clvp_dev": "https://huggingface.co/susnato/clvp_dev/blob/main/vocab.json", - }, - "merges_file": { - "clvp_dev": "https://huggingface.co/susnato/clvp_dev/blob/main/merges.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "clvp_dev": 1024, -} - @lru_cache() # Copied from transformers.models.gpt2.tokenization_gpt2.bytes_to_unicode @@ -145,8 +132,6 @@ class ClvpTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = [ "input_ids", "attention_mask", diff --git a/src/transformers/models/code_llama/tokenization_code_llama.py b/src/transformers/models/code_llama/tokenization_code_llama.py index db280bbc15..fa1433e107 100644 --- a/src/transformers/models/code_llama/tokenization_code_llama.py +++ b/src/transformers/models/code_llama/tokenization_code_llama.py @@ -30,17 +30,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "hf-internal-testing/llama-code-tokenizer": "https://huggingface.co/hf-internal-testing/llama-tokenizer/resolve/main/tokenizer.model", - }, - "tokenizer_file": { - "hf-internal-testing/llama-code-tokenizer": "https://huggingface.co/hf-internal-testing/llama-tokenizer/resolve/main/tokenizer_config.json", - }, -} -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "hf-internal-testing/llama-code-tokenizer": 2048, -} SPIECE_UNDERLINE = "▁" B_INST, E_INST = "[INST]", "[/INST]" @@ -123,8 +112,6 @@ class CodeLlamaTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/codegen/configuration_codegen.py b/src/transformers/models/codegen/configuration_codegen.py index 73c019870f..e16dd1fadc 100644 --- a/src/transformers/models/codegen/configuration_codegen.py +++ b/src/transformers/models/codegen/configuration_codegen.py @@ -25,20 +25,7 @@ from ...utils import logging logger = logging.get_logger(__name__) -CODEGEN_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "Salesforce/codegen-350M-nl": "https://huggingface.co/Salesforce/codegen-350M-nl/resolve/main/config.json", - "Salesforce/codegen-350M-multi": "https://huggingface.co/Salesforce/codegen-350M-multi/resolve/main/config.json", - "Salesforce/codegen-350M-mono": "https://huggingface.co/Salesforce/codegen-350M-mono/resolve/main/config.json", - "Salesforce/codegen-2B-nl": "https://huggingface.co/Salesforce/codegen-2B-nl/resolve/main/config.json", - "Salesforce/codegen-2B-multi": "https://huggingface.co/Salesforce/codegen-2B-multi/resolve/main/config.json", - "Salesforce/codegen-2B-mono": "https://huggingface.co/Salesforce/codegen-2B-mono/resolve/main/config.json", - "Salesforce/codegen-6B-nl": "https://huggingface.co/Salesforce/codegen-6B-nl/resolve/main/config.json", - "Salesforce/codegen-6B-multi": "https://huggingface.co/Salesforce/codegen-6B-multi/resolve/main/config.json", - "Salesforce/codegen-6B-mono": "https://huggingface.co/Salesforce/codegen-6B-mono/resolve/main/config.json", - "Salesforce/codegen-16B-nl": "https://huggingface.co/Salesforce/codegen-16B-nl/resolve/main/config.json", - "Salesforce/codegen-16B-multi": "https://huggingface.co/Salesforce/codegen-16B-multi/resolve/main/config.json", - "Salesforce/codegen-16B-mono": "https://huggingface.co/Salesforce/codegen-16B-mono/resolve/main/config.json", -} +from ..deprecated._archive_maps import CODEGEN_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class CodeGenConfig(PretrainedConfig): diff --git a/src/transformers/models/codegen/modeling_codegen.py b/src/transformers/models/codegen/modeling_codegen.py index f37ceccaac..41f23900c2 100644 --- a/src/transformers/models/codegen/modeling_codegen.py +++ b/src/transformers/models/codegen/modeling_codegen.py @@ -34,21 +34,7 @@ _CHECKPOINT_FOR_DOC = "Salesforce/codegen-2B-mono" _CONFIG_FOR_DOC = "CodeGenConfig" -CODEGEN_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Salesforce/codegen-350M-nl", - "Salesforce/codegen-350M-multi", - "Salesforce/codegen-350M-mono", - "Salesforce/codegen-2B-nl", - "Salesforce/codegen-2B-multi", - "Salesforce/codegen-2B-mono", - "Salesforce/codegen-6B-nl", - "Salesforce/codegen-6B-multi", - "Salesforce/codegen-6B-mono", - "Salesforce/codegen-16B-nl", - "Salesforce/codegen-16B-multi", - "Salesforce/codegen-16B-mono", - # See all CodeGen models at https://huggingface.co/models?filter=codegen -] +from ..deprecated._archive_maps import CODEGEN_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.gptj.modeling_gptj.create_sinusoidal_positions diff --git a/src/transformers/models/codegen/tokenization_codegen.py b/src/transformers/models/codegen/tokenization_codegen.py index c79a6d46e4..abf64e1892 100644 --- a/src/transformers/models/codegen/tokenization_codegen.py +++ b/src/transformers/models/codegen/tokenization_codegen.py @@ -42,19 +42,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "Salesforce/codegen-350M-mono": "https://huggingface.co/Salesforce/codegen-350M-mono/resolve/main/vocab.json", - }, - "merges_file": { - "Salesforce/codegen-350M-mono": "https://huggingface.co/Salesforce/codegen-350M-mono/resolve/main/merges.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "Salesforce/codegen-350M-mono": 2048, -} - @lru_cache() def bytes_to_unicode(): @@ -150,8 +137,6 @@ class CodeGenTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/codegen/tokenization_codegen_fast.py b/src/transformers/models/codegen/tokenization_codegen_fast.py index 3c2661db39..fb9f0442e0 100644 --- a/src/transformers/models/codegen/tokenization_codegen_fast.py +++ b/src/transformers/models/codegen/tokenization_codegen_fast.py @@ -41,24 +41,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "Salesforce/codegen-350M-mono": "https://huggingface.co/Salesforce/codegen-350M-mono/resolve/main/vocab.json", - }, - "merges_file": { - "Salesforce/codegen-350M-mono": "https://huggingface.co/Salesforce/codegen-350M-mono/resolve/main/merges.txt", - }, - "tokenizer_file": { - "Salesforce/codegen-350M-mono": ( - "https://huggingface.co/Salesforce/codegen-350M-mono/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "Salesforce/codegen-350M-mono": 2048, -} - class CodeGenTokenizerFast(PreTrainedTokenizerFast): """ @@ -112,8 +94,6 @@ class CodeGenTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = CodeGenTokenizer diff --git a/src/transformers/models/conditional_detr/configuration_conditional_detr.py b/src/transformers/models/conditional_detr/configuration_conditional_detr.py index 7a6cd43638..945e5edb32 100644 --- a/src/transformers/models/conditional_detr/configuration_conditional_detr.py +++ b/src/transformers/models/conditional_detr/configuration_conditional_detr.py @@ -26,11 +26,8 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -CONDITIONAL_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/conditional-detr-resnet-50": ( - "https://huggingface.co/microsoft/conditional-detr-resnet-50/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import CONDITIONAL_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ConditionalDetrConfig(PretrainedConfig): diff --git a/src/transformers/models/conditional_detr/modeling_conditional_detr.py b/src/transformers/models/conditional_detr/modeling_conditional_detr.py index b6ea7cdf4c..d8ff371fad 100644 --- a/src/transformers/models/conditional_detr/modeling_conditional_detr.py +++ b/src/transformers/models/conditional_detr/modeling_conditional_detr.py @@ -60,10 +60,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "ConditionalDetrConfig" _CHECKPOINT_FOR_DOC = "microsoft/conditional-detr-resnet-50" -CONDITIONAL_DETR_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/conditional-detr-resnet-50", - # See all Conditional DETR models at https://huggingface.co/models?filter=conditional_detr -] + +from ..deprecated._archive_maps import CONDITIONAL_DETR_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/convbert/configuration_convbert.py b/src/transformers/models/convbert/configuration_convbert.py index 6201979666..d309ca396b 100644 --- a/src/transformers/models/convbert/configuration_convbert.py +++ b/src/transformers/models/convbert/configuration_convbert.py @@ -24,14 +24,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -CONVBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "YituTech/conv-bert-base": "https://huggingface.co/YituTech/conv-bert-base/resolve/main/config.json", - "YituTech/conv-bert-medium-small": ( - "https://huggingface.co/YituTech/conv-bert-medium-small/resolve/main/config.json" - ), - "YituTech/conv-bert-small": "https://huggingface.co/YituTech/conv-bert-small/resolve/main/config.json", - # See all ConvBERT models at https://huggingface.co/models?filter=convbert -} + +from ..deprecated._archive_maps import CONVBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ConvBertConfig(PretrainedConfig): diff --git a/src/transformers/models/convbert/modeling_convbert.py b/src/transformers/models/convbert/modeling_convbert.py index 032b9d0ce1..d88add4e13 100755 --- a/src/transformers/models/convbert/modeling_convbert.py +++ b/src/transformers/models/convbert/modeling_convbert.py @@ -45,12 +45,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "YituTech/conv-bert-base" _CONFIG_FOR_DOC = "ConvBertConfig" -CONVBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "YituTech/conv-bert-base", - "YituTech/conv-bert-medium-small", - "YituTech/conv-bert-small", - # See all ConvBERT models at https://huggingface.co/models?filter=convbert -] + +from ..deprecated._archive_maps import CONVBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_convbert(model, config, tf_checkpoint_path): diff --git a/src/transformers/models/convbert/modeling_tf_convbert.py b/src/transformers/models/convbert/modeling_tf_convbert.py index e6855c68e2..7206b3558a 100644 --- a/src/transformers/models/convbert/modeling_tf_convbert.py +++ b/src/transformers/models/convbert/modeling_tf_convbert.py @@ -60,12 +60,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "YituTech/conv-bert-base" _CONFIG_FOR_DOC = "ConvBertConfig" -TF_CONVBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "YituTech/conv-bert-base", - "YituTech/conv-bert-medium-small", - "YituTech/conv-bert-small", - # See all ConvBERT models at https://huggingface.co/models?filter=convbert -] + +from ..deprecated._archive_maps import TF_CONVBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.albert.modeling_tf_albert.TFAlbertEmbeddings with Albert->ConvBert diff --git a/src/transformers/models/convbert/tokenization_convbert.py b/src/transformers/models/convbert/tokenization_convbert.py index 8c359886cf..c0fe2c0183 100644 --- a/src/transformers/models/convbert/tokenization_convbert.py +++ b/src/transformers/models/convbert/tokenization_convbert.py @@ -26,29 +26,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "YituTech/conv-bert-base": "https://huggingface.co/YituTech/conv-bert-base/resolve/main/vocab.txt", - "YituTech/conv-bert-medium-small": ( - "https://huggingface.co/YituTech/conv-bert-medium-small/resolve/main/vocab.txt" - ), - "YituTech/conv-bert-small": "https://huggingface.co/YituTech/conv-bert-small/resolve/main/vocab.txt", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "YituTech/conv-bert-base": 512, - "YituTech/conv-bert-medium-small": 512, - "YituTech/conv-bert-small": 512, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "YituTech/conv-bert-base": {"do_lower_case": True}, - "YituTech/conv-bert-medium-small": {"do_lower_case": True}, - "YituTech/conv-bert-small": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert.load_vocab def load_vocab(vocab_file): @@ -116,9 +93,6 @@ class ConvBertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/convbert/tokenization_convbert_fast.py b/src/transformers/models/convbert/tokenization_convbert_fast.py index 14909876de..65bedb73fe 100644 --- a/src/transformers/models/convbert/tokenization_convbert_fast.py +++ b/src/transformers/models/convbert/tokenization_convbert_fast.py @@ -27,29 +27,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "YituTech/conv-bert-base": "https://huggingface.co/YituTech/conv-bert-base/resolve/main/vocab.txt", - "YituTech/conv-bert-medium-small": ( - "https://huggingface.co/YituTech/conv-bert-medium-small/resolve/main/vocab.txt" - ), - "YituTech/conv-bert-small": "https://huggingface.co/YituTech/conv-bert-small/resolve/main/vocab.txt", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "YituTech/conv-bert-base": 512, - "YituTech/conv-bert-medium-small": 512, - "YituTech/conv-bert-small": 512, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "YituTech/conv-bert-base": {"do_lower_case": True}, - "YituTech/conv-bert-medium-small": {"do_lower_case": True}, - "YituTech/conv-bert-small": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert_fast.BertTokenizerFast with bert-base-cased->YituTech/conv-bert-base, Bert->ConvBert, BERT->ConvBERT class ConvBertTokenizerFast(PreTrainedTokenizerFast): @@ -93,9 +70,6 @@ class ConvBertTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = ConvBertTokenizer def __init__( diff --git a/src/transformers/models/convnext/configuration_convnext.py b/src/transformers/models/convnext/configuration_convnext.py index 48647bd122..f84c31079e 100644 --- a/src/transformers/models/convnext/configuration_convnext.py +++ b/src/transformers/models/convnext/configuration_convnext.py @@ -27,10 +27,8 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -CONVNEXT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/convnext-tiny-224": "https://huggingface.co/facebook/convnext-tiny-224/resolve/main/config.json", - # See all ConvNeXT models at https://huggingface.co/models?filter=convnext -} + +from ..deprecated._archive_maps import CONVNEXT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ConvNextConfig(BackboneConfigMixin, PretrainedConfig): diff --git a/src/transformers/models/convnext/modeling_convnext.py b/src/transformers/models/convnext/modeling_convnext.py index a952e5d816..147d2ac22d 100755 --- a/src/transformers/models/convnext/modeling_convnext.py +++ b/src/transformers/models/convnext/modeling_convnext.py @@ -54,10 +54,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 768, 7, 7] _IMAGE_CLASS_CHECKPOINT = "facebook/convnext-tiny-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -CONVNEXT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/convnext-tiny-224", - # See all ConvNext models at https://huggingface.co/models?filter=convnext -] + +from ..deprecated._archive_maps import CONVNEXT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.beit.modeling_beit.drop_path diff --git a/src/transformers/models/convnextv2/configuration_convnextv2.py b/src/transformers/models/convnextv2/configuration_convnextv2.py index 3d7d1fa739..ccee03eef6 100644 --- a/src/transformers/models/convnextv2/configuration_convnextv2.py +++ b/src/transformers/models/convnextv2/configuration_convnextv2.py @@ -22,9 +22,8 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -CONVNEXTV2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/convnextv2-tiny-1k-224": "https://huggingface.co/facebook/convnextv2-tiny-1k-224/resolve/main/config.json", -} + +from ..deprecated._archive_maps import CONVNEXTV2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ConvNextV2Config(BackboneConfigMixin, PretrainedConfig): diff --git a/src/transformers/models/convnextv2/modeling_convnextv2.py b/src/transformers/models/convnextv2/modeling_convnextv2.py index 8d166200d1..7439f21297 100644 --- a/src/transformers/models/convnextv2/modeling_convnextv2.py +++ b/src/transformers/models/convnextv2/modeling_convnextv2.py @@ -54,10 +54,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 768, 7, 7] _IMAGE_CLASS_CHECKPOINT = "facebook/convnextv2-tiny-1k-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -CONVNEXTV2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/convnextv2-tiny-1k-224", - # See all ConvNextV2 models at https://huggingface.co/models?filter=convnextv2 -] + +from ..deprecated._archive_maps import CONVNEXTV2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.beit.modeling_beit.drop_path diff --git a/src/transformers/models/convnextv2/modeling_tf_convnextv2.py b/src/transformers/models/convnextv2/modeling_tf_convnextv2.py index d4bef6f161..0debe6fd0c 100644 --- a/src/transformers/models/convnextv2/modeling_tf_convnextv2.py +++ b/src/transformers/models/convnextv2/modeling_tf_convnextv2.py @@ -61,11 +61,6 @@ _EXPECTED_OUTPUT_SHAPE = [1, 768, 7, 7] _IMAGE_CLASS_CHECKPOINT = "facebook/convnextv2-tiny-1k-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -CONVNEXTV2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/convnextv2-tiny-1k-224", - # See all ConvNextV2 models at https://huggingface.co/models?filter=convnextv2 -] - # Copied from transformers.models.convnext.modeling_tf_convnext.TFConvNextDropPath with ConvNext->ConvNextV2 class TFConvNextV2DropPath(keras.layers.Layer): diff --git a/src/transformers/models/cpm/tokenization_cpm.py b/src/transformers/models/cpm/tokenization_cpm.py index 67281b3cf1..ac454898b5 100644 --- a/src/transformers/models/cpm/tokenization_cpm.py +++ b/src/transformers/models/cpm/tokenization_cpm.py @@ -28,18 +28,11 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "TsinghuaAI/CPM-Generate": "https://huggingface.co/TsinghuaAI/CPM-Generate/resolve/main/spiece.model", - } -} - class CpmTokenizer(PreTrainedTokenizer): """Runs pre-tokenization with Jieba segmentation tool. It is used in CPM models.""" vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP def __init__( self, diff --git a/src/transformers/models/cpm/tokenization_cpm_fast.py b/src/transformers/models/cpm/tokenization_cpm_fast.py index 8e8f927e81..9b7b6da118 100644 --- a/src/transformers/models/cpm/tokenization_cpm_fast.py +++ b/src/transformers/models/cpm/tokenization_cpm_fast.py @@ -25,15 +25,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "TsinghuaAI/CPM-Generate": "https://huggingface.co/TsinghuaAI/CPM-Generate/resolve/main/spiece.model", - }, - "tokenizer_file": { - "TsinghuaAI/CPM-Generate": "https://huggingface.co/TsinghuaAI/CPM-Generate/resolve/main/tokenizer.json", - }, -} - class CpmTokenizerFast(PreTrainedTokenizerFast): """Runs pre-tokenization with Jieba segmentation tool. It is used in CPM models.""" diff --git a/src/transformers/models/cpmant/configuration_cpmant.py b/src/transformers/models/cpmant/configuration_cpmant.py index 0ad5208566..62bbce8ada 100644 --- a/src/transformers/models/cpmant/configuration_cpmant.py +++ b/src/transformers/models/cpmant/configuration_cpmant.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -CPMANT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "openbmb/cpm-ant-10b": "https://huggingface.co/openbmb/cpm-ant-10b/blob/main/config.json" - # See all CPMAnt models at https://huggingface.co/models?filter=cpmant -} + +from ..deprecated._archive_maps import CPMANT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class CpmAntConfig(PretrainedConfig): diff --git a/src/transformers/models/cpmant/modeling_cpmant.py b/src/transformers/models/cpmant/modeling_cpmant.py index 405d892c70..63bb467e64 100755 --- a/src/transformers/models/cpmant/modeling_cpmant.py +++ b/src/transformers/models/cpmant/modeling_cpmant.py @@ -36,10 +36,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "openbmb/cpm-ant-10b" _CONFIG_FOR_DOC = "CpmAntConfig" -CPMANT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "openbmb/cpm-ant-10b", - # See all CPMAnt models at https://huggingface.co/models?filter=cpmant -] + +from ..deprecated._archive_maps import CPMANT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class CpmAntLayerNorm(nn.Module): diff --git a/src/transformers/models/cpmant/tokenization_cpmant.py b/src/transformers/models/cpmant/tokenization_cpmant.py index c10f48e2de..a5e66c7679 100644 --- a/src/transformers/models/cpmant/tokenization_cpmant.py +++ b/src/transformers/models/cpmant/tokenization_cpmant.py @@ -31,16 +31,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "openbmb/cpm-ant-10b": "https://huggingface.co/openbmb/cpm-ant-10b/blob/main/vocab.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "openbmb/cpm-ant-10b": 1024, -} - def load_vocab(vocab_file): """Loads a vocabulary file into a dictionary.""" @@ -111,8 +101,6 @@ class CpmAntTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] add_prefix_space = False diff --git a/src/transformers/models/ctrl/configuration_ctrl.py b/src/transformers/models/ctrl/configuration_ctrl.py index 553e919b4a..0c5a68bf6f 100644 --- a/src/transformers/models/ctrl/configuration_ctrl.py +++ b/src/transformers/models/ctrl/configuration_ctrl.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -CTRL_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "Salesforce/ctrl": "https://huggingface.co/Salesforce/ctrl/resolve/main/config.json" -} + +from ..deprecated._archive_maps import CTRL_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class CTRLConfig(PretrainedConfig): diff --git a/src/transformers/models/ctrl/modeling_ctrl.py b/src/transformers/models/ctrl/modeling_ctrl.py index 3814f897d5..250ec8fc92 100644 --- a/src/transformers/models/ctrl/modeling_ctrl.py +++ b/src/transformers/models/ctrl/modeling_ctrl.py @@ -33,10 +33,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "CTRLConfig" -CTRL_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Salesforce/ctrl" - # See all CTRL models at https://huggingface.co/models?filter=ctrl -] + +from ..deprecated._archive_maps import CTRL_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def angle_defn(pos, i, d_model_size): diff --git a/src/transformers/models/ctrl/modeling_tf_ctrl.py b/src/transformers/models/ctrl/modeling_tf_ctrl.py index 19a6a84fc7..6569b9e7d7 100644 --- a/src/transformers/models/ctrl/modeling_tf_ctrl.py +++ b/src/transformers/models/ctrl/modeling_tf_ctrl.py @@ -43,10 +43,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "Salesforce/ctrl" _CONFIG_FOR_DOC = "CTRLConfig" -TF_CTRL_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Salesforce/ctrl" - # See all CTRL models at https://huggingface.co/models?filter=Salesforce/ctrl -] + +from ..deprecated._archive_maps import TF_CTRL_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def angle_defn(pos, i, d_model_size): diff --git a/src/transformers/models/ctrl/tokenization_ctrl.py b/src/transformers/models/ctrl/tokenization_ctrl.py index 3aac022897..fdae22d2c3 100644 --- a/src/transformers/models/ctrl/tokenization_ctrl.py +++ b/src/transformers/models/ctrl/tokenization_ctrl.py @@ -32,14 +32,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": {"Salesforce/ctrl": "https://raw.githubusercontent.com/salesforce/ctrl/master/ctrl-vocab.json"}, - "merges_file": {"Salesforce/ctrl": "https://raw.githubusercontent.com/salesforce/ctrl/master/ctrl-merges.txt"}, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "Salesforce/ctrl": 256, -} CONTROL_CODES = { "Pregnancy": 168629, @@ -134,8 +126,6 @@ class CTRLTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES control_codes = CONTROL_CODES def __init__(self, vocab_file, merges_file, unk_token="", **kwargs): diff --git a/src/transformers/models/cvt/configuration_cvt.py b/src/transformers/models/cvt/configuration_cvt.py index f1d96fc17e..412387af5e 100644 --- a/src/transformers/models/cvt/configuration_cvt.py +++ b/src/transformers/models/cvt/configuration_cvt.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -CVT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/cvt-13": "https://huggingface.co/microsoft/cvt-13/resolve/main/config.json", - # See all Cvt models at https://huggingface.co/models?filter=cvt -} + +from ..deprecated._archive_maps import CVT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class CvtConfig(PretrainedConfig): diff --git a/src/transformers/models/cvt/modeling_cvt.py b/src/transformers/models/cvt/modeling_cvt.py index ef7e3671e6..25cf3963cb 100644 --- a/src/transformers/models/cvt/modeling_cvt.py +++ b/src/transformers/models/cvt/modeling_cvt.py @@ -45,15 +45,7 @@ _IMAGE_CLASS_CHECKPOINT = "microsoft/cvt-13" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -CVT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/cvt-13", - "microsoft/cvt-13-384", - "microsoft/cvt-13-384-22k", - "microsoft/cvt-21", - "microsoft/cvt-21-384", - "microsoft/cvt-21-384-22k", - # See all Cvt models at https://huggingface.co/models?filter=cvt -] +from ..deprecated._archive_maps import CVT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/cvt/modeling_tf_cvt.py b/src/transformers/models/cvt/modeling_tf_cvt.py index c69973bdc8..5664412eff 100644 --- a/src/transformers/models/cvt/modeling_tf_cvt.py +++ b/src/transformers/models/cvt/modeling_tf_cvt.py @@ -49,15 +49,8 @@ logger = logging.get_logger(__name__) # General docstring _CONFIG_FOR_DOC = "CvtConfig" -TF_CVT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/cvt-13", - "microsoft/cvt-13-384", - "microsoft/cvt-13-384-22k", - "microsoft/cvt-21", - "microsoft/cvt-21-384", - "microsoft/cvt-21-384-22k", - # See all Cvt models at https://huggingface.co/models?filter=cvt -] + +from ..deprecated._archive_maps import TF_CVT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/data2vec/configuration_data2vec_audio.py b/src/transformers/models/data2vec/configuration_data2vec_audio.py index e37def379f..32d505f157 100644 --- a/src/transformers/models/data2vec/configuration_data2vec_audio.py +++ b/src/transformers/models/data2vec/configuration_data2vec_audio.py @@ -22,11 +22,6 @@ from ...utils import logging logger = logging.get_logger(__name__) -DATA2VEC_AUDIO_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/data2vec-base-960h": "https://huggingface.co/facebook/data2vec-audio-base-960h/resolve/main/config.json", - # See all Data2VecAudio models at https://huggingface.co/models?filter=data2vec-audio -} - class Data2VecAudioConfig(PretrainedConfig): r""" diff --git a/src/transformers/models/data2vec/configuration_data2vec_text.py b/src/transformers/models/data2vec/configuration_data2vec_text.py index 01a81e95b4..cd52db2d32 100644 --- a/src/transformers/models/data2vec/configuration_data2vec_text.py +++ b/src/transformers/models/data2vec/configuration_data2vec_text.py @@ -23,9 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -DATA2VEC_TEXT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/data2vec-text-base": "https://huggingface.co/data2vec/resolve/main/config.json", -} + +from ..deprecated._archive_maps import DATA2VEC_TEXT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Data2VecTextConfig(PretrainedConfig): diff --git a/src/transformers/models/data2vec/configuration_data2vec_vision.py b/src/transformers/models/data2vec/configuration_data2vec_vision.py index 5d8e4a252a..9a9de9c4be 100644 --- a/src/transformers/models/data2vec/configuration_data2vec_vision.py +++ b/src/transformers/models/data2vec/configuration_data2vec_vision.py @@ -25,11 +25,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -DATA2VEC_VISION_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/data2vec-vision-base-ft": ( - "https://huggingface.co/facebook/data2vec-vision-base-ft/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import DATA2VEC_VISION_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Data2VecVisionConfig(PretrainedConfig): diff --git a/src/transformers/models/data2vec/modeling_data2vec_audio.py b/src/transformers/models/data2vec/modeling_data2vec_audio.py index b3dde2438a..b5300cca08 100755 --- a/src/transformers/models/data2vec/modeling_data2vec_audio.py +++ b/src/transformers/models/data2vec/modeling_data2vec_audio.py @@ -62,13 +62,7 @@ _CTC_EXPECTED_OUTPUT = "'MISTER QUILTER IS THE APOSTLE OF THE MIDDLE CLASSES AND _CTC_EXPECTED_LOSS = 66.95 -DATA2VEC_AUDIO_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/data2vec-audio-base", - "facebook/data2vec-audio-base-10m", - "facebook/data2vec-audio-base-100h", - "facebook/data2vec-audio-base-960h", - # See all Data2VecAudio models at https://huggingface.co/models?filter=data2vec-audio -] +from ..deprecated._archive_maps import DATA2VEC_AUDIO_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.wav2vec2.modeling_wav2vec2._compute_mask_indices diff --git a/src/transformers/models/data2vec/modeling_data2vec_text.py b/src/transformers/models/data2vec/modeling_data2vec_text.py index 567cc7b5c3..7dcc53e2cc 100644 --- a/src/transformers/models/data2vec/modeling_data2vec_text.py +++ b/src/transformers/models/data2vec/modeling_data2vec_text.py @@ -55,10 +55,7 @@ _CHECKPOINT_FOR_DOC = "facebook/data2vec-text-base" _CONFIG_FOR_DOC = "Data2VecTextConfig" -DATA2VEC_TEXT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/data2vec-text-base", - # See all data2vec models at https://huggingface.co/models?filter=data2vec-text -] +from ..deprecated._archive_maps import DATA2VEC_TEXT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.roberta.modeling_roberta.RobertaEmbeddings with Roberta->Data2VecText diff --git a/src/transformers/models/data2vec/modeling_data2vec_vision.py b/src/transformers/models/data2vec/modeling_data2vec_vision.py index 77c9363fa2..44088d498f 100644 --- a/src/transformers/models/data2vec/modeling_data2vec_vision.py +++ b/src/transformers/models/data2vec/modeling_data2vec_vision.py @@ -57,10 +57,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 197, 768] _IMAGE_CLASS_CHECKPOINT = "facebook/data2vec-vision-base-ft1k" _IMAGE_CLASS_EXPECTED_OUTPUT = "remote control, remote" -DATA2VEC_VISION_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/data2vec-vision-base-ft1k", - # See all Data2VecVision models at https://huggingface.co/models?filter=data2vec-vision -] + +from ..deprecated._archive_maps import DATA2VEC_VISION_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/data2vec/modeling_tf_data2vec_vision.py b/src/transformers/models/data2vec/modeling_tf_data2vec_vision.py index bc8ff9cfc9..e65a61fae5 100644 --- a/src/transformers/models/data2vec/modeling_tf_data2vec_vision.py +++ b/src/transformers/models/data2vec/modeling_tf_data2vec_vision.py @@ -65,11 +65,6 @@ _EXPECTED_OUTPUT_SHAPE = [1, 197, 768] _IMAGE_CLASS_CHECKPOINT = "facebook/data2vec-vision-base-ft1k" _IMAGE_CLASS_EXPECTED_OUTPUT = "remote control, remote" -TF_DATA2VEC_VISION_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/data2vec-vision-base-ft1k", - # See all Data2VecVision models at https://huggingface.co/models?filter=data2vec-vision -] - @dataclass class TFData2VecVisionModelOutputWithPooling(TFBaseModelOutputWithPooling): diff --git a/src/transformers/models/deberta/configuration_deberta.py b/src/transformers/models/deberta/configuration_deberta.py index f6db66f0d8..5907f0869d 100644 --- a/src/transformers/models/deberta/configuration_deberta.py +++ b/src/transformers/models/deberta/configuration_deberta.py @@ -27,14 +27,8 @@ if TYPE_CHECKING: logger = logging.get_logger(__name__) -DEBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/deberta-base": "https://huggingface.co/microsoft/deberta-base/resolve/main/config.json", - "microsoft/deberta-large": "https://huggingface.co/microsoft/deberta-large/resolve/main/config.json", - "microsoft/deberta-xlarge": "https://huggingface.co/microsoft/deberta-xlarge/resolve/main/config.json", - "microsoft/deberta-base-mnli": "https://huggingface.co/microsoft/deberta-base-mnli/resolve/main/config.json", - "microsoft/deberta-large-mnli": "https://huggingface.co/microsoft/deberta-large-mnli/resolve/main/config.json", - "microsoft/deberta-xlarge-mnli": "https://huggingface.co/microsoft/deberta-xlarge-mnli/resolve/main/config.json", -} + +from ..deprecated._archive_maps import DEBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DebertaConfig(PretrainedConfig): diff --git a/src/transformers/models/deberta/modeling_deberta.py b/src/transformers/models/deberta/modeling_deberta.py index b5136bcb88..42dae5c808 100644 --- a/src/transformers/models/deberta/modeling_deberta.py +++ b/src/transformers/models/deberta/modeling_deberta.py @@ -53,14 +53,7 @@ _QA_TARGET_START_INDEX = 12 _QA_TARGET_END_INDEX = 14 -DEBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/deberta-base", - "microsoft/deberta-large", - "microsoft/deberta-xlarge", - "microsoft/deberta-base-mnli", - "microsoft/deberta-large-mnli", - "microsoft/deberta-xlarge-mnli", -] +from ..deprecated._archive_maps import DEBERTA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class ContextPooler(nn.Module): diff --git a/src/transformers/models/deberta/modeling_tf_deberta.py b/src/transformers/models/deberta/modeling_tf_deberta.py index 2a2a586c35..3cef6a50c8 100644 --- a/src/transformers/models/deberta/modeling_tf_deberta.py +++ b/src/transformers/models/deberta/modeling_tf_deberta.py @@ -53,10 +53,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "DebertaConfig" _CHECKPOINT_FOR_DOC = "kamalkraj/deberta-base" -TF_DEBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "kamalkraj/deberta-base", - # See all DeBERTa models at https://huggingface.co/models?filter=DeBERTa -] + +from ..deprecated._archive_maps import TF_DEBERTA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFDebertaContextPooler(keras.layers.Layer): diff --git a/src/transformers/models/deberta/tokenization_deberta.py b/src/transformers/models/deberta/tokenization_deberta.py index 6a48b188d6..b846a78915 100644 --- a/src/transformers/models/deberta/tokenization_deberta.py +++ b/src/transformers/models/deberta/tokenization_deberta.py @@ -28,43 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/deberta-base": "https://huggingface.co/microsoft/deberta-base/resolve/main/vocab.json", - "microsoft/deberta-large": "https://huggingface.co/microsoft/deberta-large/resolve/main/vocab.json", - "microsoft/deberta-xlarge": "https://huggingface.co/microsoft/deberta-xlarge/resolve/main/vocab.json", - "microsoft/deberta-base-mnli": "https://huggingface.co/microsoft/deberta-base-mnli/resolve/main/vocab.json", - "microsoft/deberta-large-mnli": "https://huggingface.co/microsoft/deberta-large-mnli/resolve/main/vocab.json", - "microsoft/deberta-xlarge-mnli": ( - "https://huggingface.co/microsoft/deberta-xlarge-mnli/resolve/main/vocab.json" - ), - }, - "merges_file": { - "microsoft/deberta-base": "https://huggingface.co/microsoft/deberta-base/resolve/main/merges.txt", - "microsoft/deberta-large": "https://huggingface.co/microsoft/deberta-large/resolve/main/merges.txt", - "microsoft/deberta-xlarge": "https://huggingface.co/microsoft/deberta-xlarge/resolve/main/merges.txt", - "microsoft/deberta-base-mnli": "https://huggingface.co/microsoft/deberta-base-mnli/resolve/main/merges.txt", - "microsoft/deberta-large-mnli": "https://huggingface.co/microsoft/deberta-large-mnli/resolve/main/merges.txt", - "microsoft/deberta-xlarge-mnli": ( - "https://huggingface.co/microsoft/deberta-xlarge-mnli/resolve/main/merges.txt" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/deberta-base": 512, - "microsoft/deberta-large": 512, - "microsoft/deberta-xlarge": 512, - "microsoft/deberta-base-mnli": 512, - "microsoft/deberta-large-mnli": 512, - "microsoft/deberta-xlarge-mnli": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/deberta-base": {"do_lower_case": False}, - "microsoft/deberta-large": {"do_lower_case": False}, -} - # Copied from transformers.models.gpt2.tokenization_gpt2.bytes_to_unicode def bytes_to_unicode(): @@ -172,8 +135,6 @@ class DebertaTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask", "token_type_ids"] def __init__( diff --git a/src/transformers/models/deberta/tokenization_deberta_fast.py b/src/transformers/models/deberta/tokenization_deberta_fast.py index 6d157fdf3c..07226443d3 100644 --- a/src/transformers/models/deberta/tokenization_deberta_fast.py +++ b/src/transformers/models/deberta/tokenization_deberta_fast.py @@ -29,43 +29,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/deberta-base": "https://huggingface.co/microsoft/deberta-base/resolve/main/vocab.json", - "microsoft/deberta-large": "https://huggingface.co/microsoft/deberta-large/resolve/main/vocab.json", - "microsoft/deberta-xlarge": "https://huggingface.co/microsoft/deberta-xlarge/resolve/main/vocab.json", - "microsoft/deberta-base-mnli": "https://huggingface.co/microsoft/deberta-base-mnli/resolve/main/vocab.json", - "microsoft/deberta-large-mnli": "https://huggingface.co/microsoft/deberta-large-mnli/resolve/main/vocab.json", - "microsoft/deberta-xlarge-mnli": ( - "https://huggingface.co/microsoft/deberta-xlarge-mnli/resolve/main/vocab.json" - ), - }, - "merges_file": { - "microsoft/deberta-base": "https://huggingface.co/microsoft/deberta-base/resolve/main/merges.txt", - "microsoft/deberta-large": "https://huggingface.co/microsoft/deberta-large/resolve/main/merges.txt", - "microsoft/deberta-xlarge": "https://huggingface.co/microsoft/deberta-xlarge/resolve/main/merges.txt", - "microsoft/deberta-base-mnli": "https://huggingface.co/microsoft/deberta-base-mnli/resolve/main/merges.txt", - "microsoft/deberta-large-mnli": "https://huggingface.co/microsoft/deberta-large-mnli/resolve/main/merges.txt", - "microsoft/deberta-xlarge-mnli": ( - "https://huggingface.co/microsoft/deberta-xlarge-mnli/resolve/main/merges.txt" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/deberta-base": 512, - "microsoft/deberta-large": 512, - "microsoft/deberta-xlarge": 512, - "microsoft/deberta-base-mnli": 512, - "microsoft/deberta-large-mnli": 512, - "microsoft/deberta-xlarge-mnli": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/deberta-base": {"do_lower_case": False}, - "microsoft/deberta-large": {"do_lower_case": False}, -} - class DebertaTokenizerFast(PreTrainedTokenizerFast): """ @@ -133,8 +96,6 @@ class DebertaTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask", "token_type_ids"] slow_tokenizer_class = DebertaTokenizer diff --git a/src/transformers/models/deberta_v2/configuration_deberta_v2.py b/src/transformers/models/deberta_v2/configuration_deberta_v2.py index 68f2112754..520222a34a 100644 --- a/src/transformers/models/deberta_v2/configuration_deberta_v2.py +++ b/src/transformers/models/deberta_v2/configuration_deberta_v2.py @@ -27,16 +27,8 @@ if TYPE_CHECKING: logger = logging.get_logger(__name__) -DEBERTA_V2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/deberta-v2-xlarge": "https://huggingface.co/microsoft/deberta-v2-xlarge/resolve/main/config.json", - "microsoft/deberta-v2-xxlarge": "https://huggingface.co/microsoft/deberta-v2-xxlarge/resolve/main/config.json", - "microsoft/deberta-v2-xlarge-mnli": ( - "https://huggingface.co/microsoft/deberta-v2-xlarge-mnli/resolve/main/config.json" - ), - "microsoft/deberta-v2-xxlarge-mnli": ( - "https://huggingface.co/microsoft/deberta-v2-xxlarge-mnli/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import DEBERTA_V2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DebertaV2Config(PretrainedConfig): diff --git a/src/transformers/models/deberta_v2/modeling_deberta_v2.py b/src/transformers/models/deberta_v2/modeling_deberta_v2.py index a8f0643692..dfe18b0d49 100644 --- a/src/transformers/models/deberta_v2/modeling_deberta_v2.py +++ b/src/transformers/models/deberta_v2/modeling_deberta_v2.py @@ -44,12 +44,8 @@ _CHECKPOINT_FOR_DOC = "microsoft/deberta-v2-xlarge" _QA_TARGET_START_INDEX = 2 _QA_TARGET_END_INDEX = 9 -DEBERTA_V2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/deberta-v2-xlarge", - "microsoft/deberta-v2-xxlarge", - "microsoft/deberta-v2-xlarge-mnli", - "microsoft/deberta-v2-xxlarge-mnli", -] + +from ..deprecated._archive_maps import DEBERTA_V2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.deberta.modeling_deberta.ContextPooler diff --git a/src/transformers/models/deberta_v2/modeling_tf_deberta_v2.py b/src/transformers/models/deberta_v2/modeling_tf_deberta_v2.py index 05b222ec8a..546e7f1a8d 100644 --- a/src/transformers/models/deberta_v2/modeling_tf_deberta_v2.py +++ b/src/transformers/models/deberta_v2/modeling_tf_deberta_v2.py @@ -52,10 +52,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "DebertaV2Config" _CHECKPOINT_FOR_DOC = "kamalkraj/deberta-v2-xlarge" -TF_DEBERTA_V2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "kamalkraj/deberta-v2-xlarge", - # See all DeBERTa models at https://huggingface.co/models?filter=deberta-v2 -] + +from ..deprecated._archive_maps import TF_DEBERTA_V2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.deberta.modeling_tf_deberta.TFDebertaContextPooler with Deberta->DebertaV2 diff --git a/src/transformers/models/deberta_v2/tokenization_deberta_v2.py b/src/transformers/models/deberta_v2/tokenization_deberta_v2.py index 0cf8807ca6..a921039454 100644 --- a/src/transformers/models/deberta_v2/tokenization_deberta_v2.py +++ b/src/transformers/models/deberta_v2/tokenization_deberta_v2.py @@ -26,32 +26,6 @@ from ...utils import logging logger = logging.get_logger(__name__) -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/deberta-v2-xlarge": "https://huggingface.co/microsoft/deberta-v2-xlarge/resolve/main/spm.model", - "microsoft/deberta-v2-xxlarge": "https://huggingface.co/microsoft/deberta-v2-xxlarge/resolve/main/spm.model", - "microsoft/deberta-v2-xlarge-mnli": ( - "https://huggingface.co/microsoft/deberta-v2-xlarge-mnli/resolve/main/spm.model" - ), - "microsoft/deberta-v2-xxlarge-mnli": ( - "https://huggingface.co/microsoft/deberta-v2-xxlarge-mnli/resolve/main/spm.model" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/deberta-v2-xlarge": 512, - "microsoft/deberta-v2-xxlarge": 512, - "microsoft/deberta-v2-xlarge-mnli": 512, - "microsoft/deberta-v2-xxlarge-mnli": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/deberta-v2-xlarge": {"do_lower_case": False}, - "microsoft/deberta-v2-xxlarge": {"do_lower_case": False}, - "microsoft/deberta-v2-xlarge-mnli": {"do_lower_case": False}, - "microsoft/deberta-v2-xxlarge-mnli": {"do_lower_case": False}, -} VOCAB_FILES_NAMES = {"vocab_file": "spm.model"} @@ -106,9 +80,6 @@ class DebertaV2Tokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/deberta_v2/tokenization_deberta_v2_fast.py b/src/transformers/models/deberta_v2/tokenization_deberta_v2_fast.py index dab376ce95..cb92a61edf 100644 --- a/src/transformers/models/deberta_v2/tokenization_deberta_v2_fast.py +++ b/src/transformers/models/deberta_v2/tokenization_deberta_v2_fast.py @@ -32,33 +32,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spm.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/deberta-v2-xlarge": "https://huggingface.co/microsoft/deberta-v2-xlarge/resolve/main/spm.model", - "microsoft/deberta-v2-xxlarge": "https://huggingface.co/microsoft/deberta-v2-xxlarge/resolve/main/spm.model", - "microsoft/deberta-v2-xlarge-mnli": ( - "https://huggingface.co/microsoft/deberta-v2-xlarge-mnli/resolve/main/spm.model" - ), - "microsoft/deberta-v2-xxlarge-mnli": ( - "https://huggingface.co/microsoft/deberta-v2-xxlarge-mnli/resolve/main/spm.model" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/deberta-v2-xlarge": 512, - "microsoft/deberta-v2-xxlarge": 512, - "microsoft/deberta-v2-xlarge-mnli": 512, - "microsoft/deberta-v2-xxlarge-mnli": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/deberta-v2-xlarge": {"do_lower_case": False}, - "microsoft/deberta-v2-xxlarge": {"do_lower_case": False}, - "microsoft/deberta-v2-xlarge-mnli": {"do_lower_case": False}, - "microsoft/deberta-v2-xxlarge-mnli": {"do_lower_case": False}, -} - class DebertaV2TokenizerFast(PreTrainedTokenizerFast): r""" @@ -110,9 +83,6 @@ class DebertaV2TokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = DebertaV2Tokenizer def __init__( diff --git a/src/transformers/models/decision_transformer/configuration_decision_transformer.py b/src/transformers/models/decision_transformer/configuration_decision_transformer.py index 88ff005469..d2c1914bee 100644 --- a/src/transformers/models/decision_transformer/configuration_decision_transformer.py +++ b/src/transformers/models/decision_transformer/configuration_decision_transformer.py @@ -20,12 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -DECISION_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "edbeeching/decision-transformer-gym-hopper-medium": ( - "https://huggingface.co/edbeeching/decision-transformer-gym-hopper-medium/resolve/main/config.json" - ), - # See all DecisionTransformer models at https://huggingface.co/models?filter=decision_transformer -} + +from ..deprecated._archive_maps import DECISION_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DecisionTransformerConfig(PretrainedConfig): diff --git a/src/transformers/models/decision_transformer/modeling_decision_transformer.py b/src/transformers/models/decision_transformer/modeling_decision_transformer.py index fdfb5b37d2..9dd9d95c38 100755 --- a/src/transformers/models/decision_transformer/modeling_decision_transformer.py +++ b/src/transformers/models/decision_transformer/modeling_decision_transformer.py @@ -43,10 +43,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "edbeeching/decision-transformer-gym-hopper-medium" _CONFIG_FOR_DOC = "DecisionTransformerConfig" -DECISION_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "edbeeching/decision-transformer-gym-hopper-medium", - # See all DecisionTransformer models at https://huggingface.co/models?filter=decision_transformer -] + +from ..deprecated._archive_maps import DECISION_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.gpt2.modeling_gpt2.load_tf_weights_in_gpt2 diff --git a/src/transformers/models/deformable_detr/configuration_deformable_detr.py b/src/transformers/models/deformable_detr/configuration_deformable_detr.py index eb3b3807ab..6d32f6220d 100644 --- a/src/transformers/models/deformable_detr/configuration_deformable_detr.py +++ b/src/transformers/models/deformable_detr/configuration_deformable_detr.py @@ -21,10 +21,8 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -DEFORMABLE_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "SenseTime/deformable-detr": "https://huggingface.co/sensetime/deformable-detr/resolve/main/config.json", - # See all Deformable DETR models at https://huggingface.co/models?filter=deformable-detr -} + +from ..deprecated._archive_maps import DEFORMABLE_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DeformableDetrConfig(PretrainedConfig): diff --git a/src/transformers/models/deformable_detr/modeling_deformable_detr.py b/src/transformers/models/deformable_detr/modeling_deformable_detr.py index 4c122832ff..1e2296d177 100755 --- a/src/transformers/models/deformable_detr/modeling_deformable_detr.py +++ b/src/transformers/models/deformable_detr/modeling_deformable_detr.py @@ -152,10 +152,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "DeformableDetrConfig" _CHECKPOINT_FOR_DOC = "sensetime/deformable-detr" -DEFORMABLE_DETR_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "sensetime/deformable-detr", - # See all Deformable DETR models at https://huggingface.co/models?filter=deformable-detr -] + +from ..deprecated._archive_maps import DEFORMABLE_DETR_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/deit/configuration_deit.py b/src/transformers/models/deit/configuration_deit.py index 20b874ff54..394c6ff937 100644 --- a/src/transformers/models/deit/configuration_deit.py +++ b/src/transformers/models/deit/configuration_deit.py @@ -26,12 +26,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -DEIT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/deit-base-distilled-patch16-224": ( - "https://huggingface.co/facebook/deit-base-patch16-224/resolve/main/config.json" - ), - # See all DeiT models at https://huggingface.co/models?filter=deit -} + +from ..deprecated._archive_maps import DEIT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DeiTConfig(PretrainedConfig): diff --git a/src/transformers/models/deit/modeling_deit.py b/src/transformers/models/deit/modeling_deit.py index b8bd9d6ce6..d8f904b938 100644 --- a/src/transformers/models/deit/modeling_deit.py +++ b/src/transformers/models/deit/modeling_deit.py @@ -59,10 +59,7 @@ _IMAGE_CLASS_CHECKPOINT = "facebook/deit-base-distilled-patch16-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -DEIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/deit-base-distilled-patch16-224", - # See all DeiT models at https://huggingface.co/models?filter=deit -] +from ..deprecated._archive_maps import DEIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class DeiTEmbeddings(nn.Module): diff --git a/src/transformers/models/deit/modeling_tf_deit.py b/src/transformers/models/deit/modeling_tf_deit.py index c6215c63b8..aec5f6df95 100644 --- a/src/transformers/models/deit/modeling_tf_deit.py +++ b/src/transformers/models/deit/modeling_tf_deit.py @@ -65,10 +65,7 @@ _IMAGE_CLASS_CHECKPOINT = "facebook/deit-base-distilled-patch16-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -TF_DEIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/deit-base-distilled-patch16-224", - # See all DeiT models at https://huggingface.co/models?filter=deit -] +from ..deprecated._archive_maps import TF_DEIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/deprecated/_archive_maps.py b/src/transformers/models/deprecated/_archive_maps.py new file mode 100644 index 0000000000..f7b0679a3e --- /dev/null +++ b/src/transformers/models/deprecated/_archive_maps.py @@ -0,0 +1,2759 @@ +# coding=utf-8 +# Copyright 2024 The HuggingFace Inc. team. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +from collections import OrderedDict + +from ...utils import logging + + +logger = logging.get_logger(__name__) + + +class DeprecatedDict(dict): + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + + def __getitem__(self, item): + logger.warning( + "Archive maps are deprecated and will be removed in version v4.40.0 as they are no longer relevant. " + "If looking to get all checkpoints for a given architecture, we recommend using `huggingface_hub` " + "with the list_models method." + ) + return self[item] + + +class DeprecatedList(list): + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + + def __getitem__(self, item): + logger.warning_once( + "Archive maps are deprecated and will be removed in version v4.40.0 as they are no longer relevant. " + "If looking to get all checkpoints for a given architecture, we recommend using `huggingface_hub` " + "with the `list_models` method." + ) + return super().__getitem__(item) + + +ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "albert/albert-base-v1": "https://huggingface.co/albert/albert-base-v1/resolve/main/config.json", + "albert/albert-large-v1": "https://huggingface.co/albert/albert-large-v1/resolve/main/config.json", + "albert/albert-xlarge-v1": "https://huggingface.co/albert/albert-xlarge-v1/resolve/main/config.json", + "albert/albert-xxlarge-v1": "https://huggingface.co/albert/albert-xxlarge-v1/resolve/main/config.json", + "albert/albert-base-v2": "https://huggingface.co/albert/albert-base-v2/resolve/main/config.json", + "albert/albert-large-v2": "https://huggingface.co/albert/albert-large-v2/resolve/main/config.json", + "albert/albert-xlarge-v2": "https://huggingface.co/albert/albert-xlarge-v2/resolve/main/config.json", + "albert/albert-xxlarge-v2": "https://huggingface.co/albert/albert-xxlarge-v2/resolve/main/config.json", + } +) + +ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "albert/albert-base-v1", + "albert/albert-large-v1", + "albert/albert-xlarge-v1", + "albert/albert-xxlarge-v1", + "albert/albert-base-v2", + "albert/albert-large-v2", + "albert/albert-xlarge-v2", + "albert/albert-xxlarge-v2", + ] +) + +TF_ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "albert/albert-base-v1", + "albert/albert-large-v1", + "albert/albert-xlarge-v1", + "albert/albert-xxlarge-v1", + "albert/albert-base-v2", + "albert/albert-large-v2", + "albert/albert-xlarge-v2", + "albert/albert-xxlarge-v2", + ] +) + +ALIGN_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"kakaobrain/align-base": "https://huggingface.co/kakaobrain/align-base/resolve/main/config.json"} +) + +ALIGN_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["kakaobrain/align-base"]) + +ALTCLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"BAAI/AltCLIP": "https://huggingface.co/BAAI/AltCLIP/resolve/main/config.json"} +) + +ALTCLIP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["BAAI/AltCLIP"]) + +AUDIO_SPECTROGRAM_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "MIT/ast-finetuned-audioset-10-10-0.4593": "https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593/resolve/main/config.json" + } +) + +AUDIO_SPECTROGRAM_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["MIT/ast-finetuned-audioset-10-10-0.4593"] +) + +AUTOFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "huggingface/autoformer-tourism-monthly": "https://huggingface.co/huggingface/autoformer-tourism-monthly/resolve/main/config.json" + } +) + +AUTOFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["huggingface/autoformer-tourism-monthly"]) + +BARK_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["suno/bark-small", "suno/bark"]) + +BART_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/bart-large"]) + +BEIT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/beit-base-patch16-224-pt22k": "https://huggingface.co/microsoft/beit-base-patch16-224-pt22k/resolve/main/config.json" + } +) + +BEIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/beit-base-patch16-224"]) + +BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google-bert/bert-base-uncased": "https://huggingface.co/google-bert/bert-base-uncased/resolve/main/config.json", + "google-bert/bert-large-uncased": "https://huggingface.co/google-bert/bert-large-uncased/resolve/main/config.json", + "google-bert/bert-base-cased": "https://huggingface.co/google-bert/bert-base-cased/resolve/main/config.json", + "google-bert/bert-large-cased": "https://huggingface.co/google-bert/bert-large-cased/resolve/main/config.json", + "google-bert/bert-base-multilingual-uncased": "https://huggingface.co/google-bert/bert-base-multilingual-uncased/resolve/main/config.json", + "google-bert/bert-base-multilingual-cased": "https://huggingface.co/google-bert/bert-base-multilingual-cased/resolve/main/config.json", + "google-bert/bert-base-chinese": "https://huggingface.co/google-bert/bert-base-chinese/resolve/main/config.json", + "google-bert/bert-base-german-cased": "https://huggingface.co/google-bert/bert-base-german-cased/resolve/main/config.json", + "google-bert/bert-large-uncased-whole-word-masking": "https://huggingface.co/google-bert/bert-large-uncased-whole-word-masking/resolve/main/config.json", + "google-bert/bert-large-cased-whole-word-masking": "https://huggingface.co/google-bert/bert-large-cased-whole-word-masking/resolve/main/config.json", + "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad": "https://huggingface.co/google-bert/bert-large-uncased-whole-word-masking-finetuned-squad/resolve/main/config.json", + "google-bert/bert-large-cased-whole-word-masking-finetuned-squad": "https://huggingface.co/google-bert/bert-large-cased-whole-word-masking-finetuned-squad/resolve/main/config.json", + "google-bert/bert-base-cased-finetuned-mrpc": "https://huggingface.co/google-bert/bert-base-cased-finetuned-mrpc/resolve/main/config.json", + "google-bert/bert-base-german-dbmdz-cased": "https://huggingface.co/google-bert/bert-base-german-dbmdz-cased/resolve/main/config.json", + "google-bert/bert-base-german-dbmdz-uncased": "https://huggingface.co/google-bert/bert-base-german-dbmdz-uncased/resolve/main/config.json", + "cl-tohoku/bert-base-japanese": "https://huggingface.co/cl-tohoku/bert-base-japanese/resolve/main/config.json", + "cl-tohoku/bert-base-japanese-whole-word-masking": "https://huggingface.co/cl-tohoku/bert-base-japanese-whole-word-masking/resolve/main/config.json", + "cl-tohoku/bert-base-japanese-char": "https://huggingface.co/cl-tohoku/bert-base-japanese-char/resolve/main/config.json", + "cl-tohoku/bert-base-japanese-char-whole-word-masking": "https://huggingface.co/cl-tohoku/bert-base-japanese-char-whole-word-masking/resolve/main/config.json", + "TurkuNLP/bert-base-finnish-cased-v1": "https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1/resolve/main/config.json", + "TurkuNLP/bert-base-finnish-uncased-v1": "https://huggingface.co/TurkuNLP/bert-base-finnish-uncased-v1/resolve/main/config.json", + "wietsedv/bert-base-dutch-cased": "https://huggingface.co/wietsedv/bert-base-dutch-cased/resolve/main/config.json", + } +) + +BERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "google-bert/bert-base-uncased", + "google-bert/bert-large-uncased", + "google-bert/bert-base-cased", + "google-bert/bert-large-cased", + "google-bert/bert-base-multilingual-uncased", + "google-bert/bert-base-multilingual-cased", + "google-bert/bert-base-chinese", + "google-bert/bert-base-german-cased", + "google-bert/bert-large-uncased-whole-word-masking", + "google-bert/bert-large-cased-whole-word-masking", + "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad", + "google-bert/bert-large-cased-whole-word-masking-finetuned-squad", + "google-bert/bert-base-cased-finetuned-mrpc", + "google-bert/bert-base-german-dbmdz-cased", + "google-bert/bert-base-german-dbmdz-uncased", + "cl-tohoku/bert-base-japanese", + "cl-tohoku/bert-base-japanese-whole-word-masking", + "cl-tohoku/bert-base-japanese-char", + "cl-tohoku/bert-base-japanese-char-whole-word-masking", + "TurkuNLP/bert-base-finnish-cased-v1", + "TurkuNLP/bert-base-finnish-uncased-v1", + "wietsedv/bert-base-dutch-cased", + ] +) + +TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "google-bert/bert-base-uncased", + "google-bert/bert-large-uncased", + "google-bert/bert-base-cased", + "google-bert/bert-large-cased", + "google-bert/bert-base-multilingual-uncased", + "google-bert/bert-base-multilingual-cased", + "google-bert/bert-base-chinese", + "google-bert/bert-base-german-cased", + "google-bert/bert-large-uncased-whole-word-masking", + "google-bert/bert-large-cased-whole-word-masking", + "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad", + "google-bert/bert-large-cased-whole-word-masking-finetuned-squad", + "google-bert/bert-base-cased-finetuned-mrpc", + "cl-tohoku/bert-base-japanese", + "cl-tohoku/bert-base-japanese-whole-word-masking", + "cl-tohoku/bert-base-japanese-char", + "cl-tohoku/bert-base-japanese-char-whole-word-masking", + "TurkuNLP/bert-base-finnish-cased-v1", + "TurkuNLP/bert-base-finnish-uncased-v1", + "wietsedv/bert-base-dutch-cased", + ] +) + +BIG_BIRD_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/bigbird-roberta-base": "https://huggingface.co/google/bigbird-roberta-base/resolve/main/config.json", + "google/bigbird-roberta-large": "https://huggingface.co/google/bigbird-roberta-large/resolve/main/config.json", + "google/bigbird-base-trivia-itc": "https://huggingface.co/google/bigbird-base-trivia-itc/resolve/main/config.json", + } +) + +BIG_BIRD_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["google/bigbird-roberta-base", "google/bigbird-roberta-large", "google/bigbird-base-trivia-itc"] +) + +BIGBIRD_PEGASUS_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/bigbird-pegasus-large-arxiv": "https://huggingface.co/google/bigbird-pegasus-large-arxiv/resolve/main/config.json", + "google/bigbird-pegasus-large-pubmed": "https://huggingface.co/google/bigbird-pegasus-large-pubmed/resolve/main/config.json", + "google/bigbird-pegasus-large-bigpatent": "https://huggingface.co/google/bigbird-pegasus-large-bigpatent/resolve/main/config.json", + } +) + +BIGBIRD_PEGASUS_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "google/bigbird-pegasus-large-arxiv", + "google/bigbird-pegasus-large-pubmed", + "google/bigbird-pegasus-large-bigpatent", + ] +) + +BIOGPT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"microsoft/biogpt": "https://huggingface.co/microsoft/biogpt/resolve/main/config.json"} +) + +BIOGPT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/biogpt", "microsoft/BioGPT-Large"]) + +BIT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"google/bit-50": "https://huggingface.co/google/bit-50/resolve/main/config.json"} +) + +BIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/bit-50"]) + +BLENDERBOT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/blenderbot-3B": "https://huggingface.co/facebook/blenderbot-3B/resolve/main/config.json"} +) + +BLENDERBOT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/blenderbot-3B"]) + +BLENDERBOT_SMALL_PRETRAINED_CONFIG_ARCHIVE_MAP = { + "facebook/blenderbot_small-90M": "https://huggingface.co/facebook/blenderbot_small-90M/resolve/main/config.json", + # See all BlenderbotSmall models at https://huggingface.co/models?filter=blenderbot_small +} + +BLENDERBOT_SMALL_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/blenderbot_small-90M"]) + +BLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "Salesforce/blip-vqa-base": "https://huggingface.co/Salesforce/blip-vqa-base/resolve/main/config.json", + "Salesforce/blip-vqa-capfit-large": "https://huggingface.co/Salesforce/blip-vqa-base-capfit/resolve/main/config.json", + "Salesforce/blip-image-captioning-base": "https://huggingface.co/Salesforce/blip-image-captioning-base/resolve/main/config.json", + "Salesforce/blip-image-captioning-large": "https://huggingface.co/Salesforce/blip-image-captioning-large/resolve/main/config.json", + "Salesforce/blip-itm-base-coco": "https://huggingface.co/Salesforce/blip-itm-base-coco/resolve/main/config.json", + "Salesforce/blip-itm-large-coco": "https://huggingface.co/Salesforce/blip-itm-large-coco/resolve/main/config.json", + "Salesforce/blip-itm-base-flikr": "https://huggingface.co/Salesforce/blip-itm-base-flikr/resolve/main/config.json", + "Salesforce/blip-itm-large-flikr": "https://huggingface.co/Salesforce/blip-itm-large-flikr/resolve/main/config.json", + } +) + +BLIP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "Salesforce/blip-vqa-base", + "Salesforce/blip-vqa-capfilt-large", + "Salesforce/blip-image-captioning-base", + "Salesforce/blip-image-captioning-large", + "Salesforce/blip-itm-base-coco", + "Salesforce/blip-itm-large-coco", + "Salesforce/blip-itm-base-flickr", + "Salesforce/blip-itm-large-flickr", + ] +) + +TF_BLIP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "Salesforce/blip-vqa-base", + "Salesforce/blip-vqa-capfilt-large", + "Salesforce/blip-image-captioning-base", + "Salesforce/blip-image-captioning-large", + "Salesforce/blip-itm-base-coco", + "Salesforce/blip-itm-large-coco", + "Salesforce/blip-itm-base-flickr", + "Salesforce/blip-itm-large-flickr", + ] +) + +BLIP_2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"salesforce/blip2-opt-2.7b": "https://huggingface.co/salesforce/blip2-opt-2.7b/resolve/main/config.json"} +) + +BLIP_2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["Salesforce/blip2-opt-2.7b"]) + +BLOOM_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "bigscience/bloom": "https://huggingface.co/bigscience/bloom/resolve/main/config.json", + "bigscience/bloom-560m": "https://huggingface.co/bigscience/bloom-560m/blob/main/config.json", + "bigscience/bloom-1b1": "https://huggingface.co/bigscience/bloom-1b1/blob/main/config.json", + "bigscience/bloom-1b7": "https://huggingface.co/bigscience/bloom-1b7/blob/main/config.json", + "bigscience/bloom-3b": "https://huggingface.co/bigscience/bloom-3b/blob/main/config.json", + "bigscience/bloom-7b1": "https://huggingface.co/bigscience/bloom-7b1/blob/main/config.json", + } +) + +BLOOM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "bigscience/bigscience-small-testing", + "bigscience/bloom-560m", + "bigscience/bloom-1b1", + "bigscience/bloom-1b7", + "bigscience/bloom-3b", + "bigscience/bloom-7b1", + "bigscience/bloom", + ] +) + +BRIDGETOWER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "BridgeTower/bridgetower-base": "https://huggingface.co/BridgeTower/bridgetower-base/blob/main/config.json", + "BridgeTower/bridgetower-base-itm-mlm": "https://huggingface.co/BridgeTower/bridgetower-base-itm-mlm/blob/main/config.json", + } +) + +BRIDGETOWER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["BridgeTower/bridgetower-base", "BridgeTower/bridgetower-base-itm-mlm"] +) + +BROS_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "jinho8345/bros-base-uncased": "https://huggingface.co/jinho8345/bros-base-uncased/blob/main/config.json", + "jinho8345/bros-large-uncased": "https://huggingface.co/jinho8345/bros-large-uncased/blob/main/config.json", + } +) + +BROS_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["jinho8345/bros-base-uncased", "jinho8345/bros-large-uncased"]) + +CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "almanach/camembert-base": "https://huggingface.co/almanach/camembert-base/resolve/main/config.json", + "umberto-commoncrawl-cased-v1": "https://huggingface.co/Musixmatch/umberto-commoncrawl-cased-v1/resolve/main/config.json", + "umberto-wikipedia-uncased-v1": "https://huggingface.co/Musixmatch/umberto-wikipedia-uncased-v1/resolve/main/config.json", + } +) + +CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["almanach/camembert-base", "Musixmatch/umberto-commoncrawl-cased-v1", "Musixmatch/umberto-wikipedia-uncased-v1"] +) + +TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList([]) + +CANINE_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"google/canine-s": "https://huggingface.co/google/canine-s/resolve/main/config.json"} +) + +CANINE_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/canine-s", "google/canine-r"]) + +CHINESE_CLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "OFA-Sys/chinese-clip-vit-base-patch16": "https://huggingface.co/OFA-Sys/chinese-clip-vit-base-patch16/resolve/main/config.json" + } +) + +CHINESE_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["OFA-Sys/chinese-clip-vit-base-patch16"]) + +CLAP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["laion/clap-htsat-fused", "laion/clap-htsat-unfused"]) + +CLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"openai/clip-vit-base-patch32": "https://huggingface.co/openai/clip-vit-base-patch32/resolve/main/config.json"} +) + +CLIP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["openai/clip-vit-base-patch32"]) + +TF_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["openai/clip-vit-base-patch32"]) + +CLIPSEG_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"CIDAS/clipseg-rd64": "https://huggingface.co/CIDAS/clipseg-rd64/resolve/main/config.json"} +) + +CLIPSEG_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["CIDAS/clipseg-rd64-refined"]) + +CLVP_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"susnato/clvp_dev": "https://huggingface.co/susnato/clvp_dev/resolve/main/config.json"} +) + +CLVP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["susnato/clvp_dev"]) + +CODEGEN_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "Salesforce/codegen-350M-nl": "https://huggingface.co/Salesforce/codegen-350M-nl/resolve/main/config.json", + "Salesforce/codegen-350M-multi": "https://huggingface.co/Salesforce/codegen-350M-multi/resolve/main/config.json", + "Salesforce/codegen-350M-mono": "https://huggingface.co/Salesforce/codegen-350M-mono/resolve/main/config.json", + "Salesforce/codegen-2B-nl": "https://huggingface.co/Salesforce/codegen-2B-nl/resolve/main/config.json", + "Salesforce/codegen-2B-multi": "https://huggingface.co/Salesforce/codegen-2B-multi/resolve/main/config.json", + "Salesforce/codegen-2B-mono": "https://huggingface.co/Salesforce/codegen-2B-mono/resolve/main/config.json", + "Salesforce/codegen-6B-nl": "https://huggingface.co/Salesforce/codegen-6B-nl/resolve/main/config.json", + "Salesforce/codegen-6B-multi": "https://huggingface.co/Salesforce/codegen-6B-multi/resolve/main/config.json", + "Salesforce/codegen-6B-mono": "https://huggingface.co/Salesforce/codegen-6B-mono/resolve/main/config.json", + "Salesforce/codegen-16B-nl": "https://huggingface.co/Salesforce/codegen-16B-nl/resolve/main/config.json", + "Salesforce/codegen-16B-multi": "https://huggingface.co/Salesforce/codegen-16B-multi/resolve/main/config.json", + "Salesforce/codegen-16B-mono": "https://huggingface.co/Salesforce/codegen-16B-mono/resolve/main/config.json", + } +) + +CODEGEN_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "Salesforce/codegen-350M-nl", + "Salesforce/codegen-350M-multi", + "Salesforce/codegen-350M-mono", + "Salesforce/codegen-2B-nl", + "Salesforce/codegen-2B-multi", + "Salesforce/codegen-2B-mono", + "Salesforce/codegen-6B-nl", + "Salesforce/codegen-6B-multi", + "Salesforce/codegen-6B-mono", + "Salesforce/codegen-16B-nl", + "Salesforce/codegen-16B-multi", + "Salesforce/codegen-16B-mono", + ] +) + +CONDITIONAL_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/conditional-detr-resnet-50": "https://huggingface.co/microsoft/conditional-detr-resnet-50/resolve/main/config.json" + } +) + +CONDITIONAL_DETR_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/conditional-detr-resnet-50"]) + +CONVBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "YituTech/conv-bert-base": "https://huggingface.co/YituTech/conv-bert-base/resolve/main/config.json", + "YituTech/conv-bert-medium-small": "https://huggingface.co/YituTech/conv-bert-medium-small/resolve/main/config.json", + "YituTech/conv-bert-small": "https://huggingface.co/YituTech/conv-bert-small/resolve/main/config.json", + } +) + +CONVBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["YituTech/conv-bert-base", "YituTech/conv-bert-medium-small", "YituTech/conv-bert-small"] +) + +TF_CONVBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["YituTech/conv-bert-base", "YituTech/conv-bert-medium-small", "YituTech/conv-bert-small"] +) + +CONVNEXT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/convnext-tiny-224": "https://huggingface.co/facebook/convnext-tiny-224/resolve/main/config.json"} +) + +CONVNEXT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/convnext-tiny-224"]) + +CONVNEXTV2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/convnextv2-tiny-1k-224": "https://huggingface.co/facebook/convnextv2-tiny-1k-224/resolve/main/config.json" + } +) + +CONVNEXTV2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/convnextv2-tiny-1k-224"]) + +CPMANT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"openbmb/cpm-ant-10b": "https://huggingface.co/openbmb/cpm-ant-10b/blob/main/config.json"} +) + +CPMANT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["openbmb/cpm-ant-10b"]) + +CTRL_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"Salesforce/ctrl": "https://huggingface.co/Salesforce/ctrl/resolve/main/config.json"} +) + +CTRL_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["Salesforce/ctrl"]) + +TF_CTRL_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["Salesforce/ctrl"]) + +CVT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"microsoft/cvt-13": "https://huggingface.co/microsoft/cvt-13/resolve/main/config.json"} +) + +CVT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "microsoft/cvt-13", + "microsoft/cvt-13-384", + "microsoft/cvt-13-384-22k", + "microsoft/cvt-21", + "microsoft/cvt-21-384", + "microsoft/cvt-21-384-22k", + ] +) + +TF_CVT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "microsoft/cvt-13", + "microsoft/cvt-13-384", + "microsoft/cvt-13-384-22k", + "microsoft/cvt-21", + "microsoft/cvt-21-384", + "microsoft/cvt-21-384-22k", + ] +) + +DATA2VEC_TEXT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/data2vec-text-base": "https://huggingface.co/data2vec/resolve/main/config.json"} +) + +DATA2VEC_VISION_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/data2vec-vision-base-ft": "https://huggingface.co/facebook/data2vec-vision-base-ft/resolve/main/config.json" + } +) + +DATA2VEC_AUDIO_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "facebook/data2vec-audio-base", + "facebook/data2vec-audio-base-10m", + "facebook/data2vec-audio-base-100h", + "facebook/data2vec-audio-base-960h", + ] +) + +DATA2VEC_TEXT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/data2vec-text-base"]) + +DATA2VEC_VISION_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/data2vec-vision-base-ft1k"]) + +DEBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/deberta-base": "https://huggingface.co/microsoft/deberta-base/resolve/main/config.json", + "microsoft/deberta-large": "https://huggingface.co/microsoft/deberta-large/resolve/main/config.json", + "microsoft/deberta-xlarge": "https://huggingface.co/microsoft/deberta-xlarge/resolve/main/config.json", + "microsoft/deberta-base-mnli": "https://huggingface.co/microsoft/deberta-base-mnli/resolve/main/config.json", + "microsoft/deberta-large-mnli": "https://huggingface.co/microsoft/deberta-large-mnli/resolve/main/config.json", + "microsoft/deberta-xlarge-mnli": "https://huggingface.co/microsoft/deberta-xlarge-mnli/resolve/main/config.json", + } +) + +DEBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "microsoft/deberta-base", + "microsoft/deberta-large", + "microsoft/deberta-xlarge", + "microsoft/deberta-base-mnli", + "microsoft/deberta-large-mnli", + "microsoft/deberta-xlarge-mnli", + ] +) + +TF_DEBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["kamalkraj/deberta-base"]) + +DEBERTA_V2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/deberta-v2-xlarge": "https://huggingface.co/microsoft/deberta-v2-xlarge/resolve/main/config.json", + "microsoft/deberta-v2-xxlarge": "https://huggingface.co/microsoft/deberta-v2-xxlarge/resolve/main/config.json", + "microsoft/deberta-v2-xlarge-mnli": "https://huggingface.co/microsoft/deberta-v2-xlarge-mnli/resolve/main/config.json", + "microsoft/deberta-v2-xxlarge-mnli": "https://huggingface.co/microsoft/deberta-v2-xxlarge-mnli/resolve/main/config.json", + } +) + +DEBERTA_V2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "microsoft/deberta-v2-xlarge", + "microsoft/deberta-v2-xxlarge", + "microsoft/deberta-v2-xlarge-mnli", + "microsoft/deberta-v2-xxlarge-mnli", + ] +) + +TF_DEBERTA_V2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["kamalkraj/deberta-v2-xlarge"]) + +DECISION_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "edbeeching/decision-transformer-gym-hopper-medium": "https://huggingface.co/edbeeching/decision-transformer-gym-hopper-medium/resolve/main/config.json" + } +) + +DECISION_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["edbeeching/decision-transformer-gym-hopper-medium"] +) + +DEFORMABLE_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"SenseTime/deformable-detr": "https://huggingface.co/sensetime/deformable-detr/resolve/main/config.json"} +) + +DEFORMABLE_DETR_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["sensetime/deformable-detr"]) + +DEIT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/deit-base-distilled-patch16-224": "https://huggingface.co/facebook/deit-base-patch16-224/resolve/main/config.json" + } +) + +DEIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/deit-base-distilled-patch16-224"]) + +TF_DEIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/deit-base-distilled-patch16-224"]) + +MCTCT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"speechbrain/m-ctc-t-large": "https://huggingface.co/speechbrain/m-ctc-t-large/resolve/main/config.json"} +) + +MCTCT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["speechbrain/m-ctc-t-large"]) + +OPEN_LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"s-JoL/Open-Llama-V1": "https://huggingface.co/s-JoL/Open-Llama-V1/blob/main/config.json"} +) + +RETRIBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "yjernite/retribert-base-uncased": "https://huggingface.co/yjernite/retribert-base-uncased/resolve/main/config.json" + } +) + +RETRIBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["yjernite/retribert-base-uncased"]) + +TRAJECTORY_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "CarlCochet/trajectory-transformer-halfcheetah-medium-v2": "https://huggingface.co/CarlCochet/trajectory-transformer-halfcheetah-medium-v2/resolve/main/config.json" + } +) + +TRAJECTORY_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["CarlCochet/trajectory-transformer-halfcheetah-medium-v2"] +) + +TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"transfo-xl/transfo-xl-wt103": "https://huggingface.co/transfo-xl/transfo-xl-wt103/resolve/main/config.json"} +) + +TRANSFO_XL_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["transfo-xl/transfo-xl-wt103"]) + +TF_TRANSFO_XL_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["transfo-xl/transfo-xl-wt103"]) + +VAN_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "Visual-Attention-Network/van-base": "https://huggingface.co/Visual-Attention-Network/van-base/blob/main/config.json" + } +) + +VAN_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["Visual-Attention-Network/van-base"]) + +DEPTH_ANYTHING_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "LiheYoung/depth-anything-small-hf": "https://huggingface.co/LiheYoung/depth-anything-small-hf/resolve/main/config.json" + } +) + +DEPTH_ANYTHING_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["LiheYoung/depth-anything-small-hf"]) + +DETA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"ut/deta": "https://huggingface.co/ut/deta/resolve/main/config.json"} +) + +DETA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["jozhang97/deta-swin-large-o365"]) + +DETR_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/detr-resnet-50": "https://huggingface.co/facebook/detr-resnet-50/resolve/main/config.json"} +) + +DETR_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/detr-resnet-50"]) + +DINAT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"shi-labs/dinat-mini-in1k-224": "https://huggingface.co/shi-labs/dinat-mini-in1k-224/resolve/main/config.json"} +) + +DINAT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["shi-labs/dinat-mini-in1k-224"]) + +DINOV2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/dinov2-base": "https://huggingface.co/facebook/dinov2-base/resolve/main/config.json"} +) + +DINOV2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/dinov2-base"]) + +DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "distilbert-base-uncased": "https://huggingface.co/distilbert-base-uncased/resolve/main/config.json", + "distilbert-base-uncased-distilled-squad": "https://huggingface.co/distilbert-base-uncased-distilled-squad/resolve/main/config.json", + "distilbert-base-cased": "https://huggingface.co/distilbert-base-cased/resolve/main/config.json", + "distilbert-base-cased-distilled-squad": "https://huggingface.co/distilbert-base-cased-distilled-squad/resolve/main/config.json", + "distilbert-base-german-cased": "https://huggingface.co/distilbert-base-german-cased/resolve/main/config.json", + "distilbert-base-multilingual-cased": "https://huggingface.co/distilbert-base-multilingual-cased/resolve/main/config.json", + "distilbert-base-uncased-finetuned-sst-2-english": "https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english/resolve/main/config.json", + } +) + +DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "distilbert-base-uncased", + "distilbert-base-uncased-distilled-squad", + "distilbert-base-cased", + "distilbert-base-cased-distilled-squad", + "distilbert-base-german-cased", + "distilbert-base-multilingual-cased", + "distilbert-base-uncased-finetuned-sst-2-english", + ] +) + +TF_DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "distilbert-base-uncased", + "distilbert-base-uncased-distilled-squad", + "distilbert-base-cased", + "distilbert-base-cased-distilled-squad", + "distilbert-base-multilingual-cased", + "distilbert-base-uncased-finetuned-sst-2-english", + ] +) + +DONUT_SWIN_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"naver-clova-ix/donut-base": "https://huggingface.co/naver-clova-ix/donut-base/resolve/main/config.json"} +) + +DONUT_SWIN_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["naver-clova-ix/donut-base"]) + +DPR_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/dpr-ctx_encoder-single-nq-base": "https://huggingface.co/facebook/dpr-ctx_encoder-single-nq-base/resolve/main/config.json", + "facebook/dpr-question_encoder-single-nq-base": "https://huggingface.co/facebook/dpr-question_encoder-single-nq-base/resolve/main/config.json", + "facebook/dpr-reader-single-nq-base": "https://huggingface.co/facebook/dpr-reader-single-nq-base/resolve/main/config.json", + "facebook/dpr-ctx_encoder-multiset-base": "https://huggingface.co/facebook/dpr-ctx_encoder-multiset-base/resolve/main/config.json", + "facebook/dpr-question_encoder-multiset-base": "https://huggingface.co/facebook/dpr-question_encoder-multiset-base/resolve/main/config.json", + "facebook/dpr-reader-multiset-base": "https://huggingface.co/facebook/dpr-reader-multiset-base/resolve/main/config.json", + } +) + +DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["facebook/dpr-ctx_encoder-single-nq-base", "facebook/dpr-ctx_encoder-multiset-base"] +) + +DPR_QUESTION_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["facebook/dpr-question_encoder-single-nq-base", "facebook/dpr-question_encoder-multiset-base"] +) + +DPR_READER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["facebook/dpr-reader-single-nq-base", "facebook/dpr-reader-multiset-base"] +) + +TF_DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["facebook/dpr-ctx_encoder-single-nq-base", "facebook/dpr-ctx_encoder-multiset-base"] +) + +TF_DPR_QUESTION_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["facebook/dpr-question_encoder-single-nq-base", "facebook/dpr-question_encoder-multiset-base"] +) + +TF_DPR_READER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["facebook/dpr-reader-single-nq-base", "facebook/dpr-reader-multiset-base"] +) + +DPT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"Intel/dpt-large": "https://huggingface.co/Intel/dpt-large/resolve/main/config.json"} +) + +DPT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["Intel/dpt-large", "Intel/dpt-hybrid-midas"]) + +EFFICIENTFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "snap-research/efficientformer-l1-300": "https://huggingface.co/snap-research/efficientformer-l1-300/resolve/main/config.json" + } +) + +EFFICIENTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["snap-research/efficientformer-l1-300"]) + +TF_EFFICIENTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["snap-research/efficientformer-l1-300"]) + +EFFICIENTNET_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"google/efficientnet-b7": "https://huggingface.co/google/efficientnet-b7/resolve/main/config.json"} +) + +EFFICIENTNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/efficientnet-b7"]) + +ELECTRA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/electra-small-generator": "https://huggingface.co/google/electra-small-generator/resolve/main/config.json", + "google/electra-base-generator": "https://huggingface.co/google/electra-base-generator/resolve/main/config.json", + "google/electra-large-generator": "https://huggingface.co/google/electra-large-generator/resolve/main/config.json", + "google/electra-small-discriminator": "https://huggingface.co/google/electra-small-discriminator/resolve/main/config.json", + "google/electra-base-discriminator": "https://huggingface.co/google/electra-base-discriminator/resolve/main/config.json", + "google/electra-large-discriminator": "https://huggingface.co/google/electra-large-discriminator/resolve/main/config.json", + } +) + +ELECTRA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "google/electra-small-generator", + "google/electra-base-generator", + "google/electra-large-generator", + "google/electra-small-discriminator", + "google/electra-base-discriminator", + "google/electra-large-discriminator", + ] +) + +TF_ELECTRA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "google/electra-small-generator", + "google/electra-base-generator", + "google/electra-large-generator", + "google/electra-small-discriminator", + "google/electra-base-discriminator", + "google/electra-large-discriminator", + ] +) + +ENCODEC_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/encodec_24khz": "https://huggingface.co/facebook/encodec_24khz/resolve/main/config.json", + "facebook/encodec_48khz": "https://huggingface.co/facebook/encodec_48khz/resolve/main/config.json", + } +) + +ENCODEC_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/encodec_24khz", "facebook/encodec_48khz"]) + +ERNIE_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "nghuyong/ernie-1.0-base-zh": "https://huggingface.co/nghuyong/ernie-1.0-base-zh/resolve/main/config.json", + "nghuyong/ernie-2.0-base-en": "https://huggingface.co/nghuyong/ernie-2.0-base-en/resolve/main/config.json", + "nghuyong/ernie-2.0-large-en": "https://huggingface.co/nghuyong/ernie-2.0-large-en/resolve/main/config.json", + "nghuyong/ernie-3.0-base-zh": "https://huggingface.co/nghuyong/ernie-3.0-base-zh/resolve/main/config.json", + "nghuyong/ernie-3.0-medium-zh": "https://huggingface.co/nghuyong/ernie-3.0-medium-zh/resolve/main/config.json", + "nghuyong/ernie-3.0-mini-zh": "https://huggingface.co/nghuyong/ernie-3.0-mini-zh/resolve/main/config.json", + "nghuyong/ernie-3.0-micro-zh": "https://huggingface.co/nghuyong/ernie-3.0-micro-zh/resolve/main/config.json", + "nghuyong/ernie-3.0-nano-zh": "https://huggingface.co/nghuyong/ernie-3.0-nano-zh/resolve/main/config.json", + "nghuyong/ernie-gram-zh": "https://huggingface.co/nghuyong/ernie-gram-zh/resolve/main/config.json", + "nghuyong/ernie-health-zh": "https://huggingface.co/nghuyong/ernie-health-zh/resolve/main/config.json", + } +) + +ERNIE_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "nghuyong/ernie-1.0-base-zh", + "nghuyong/ernie-2.0-base-en", + "nghuyong/ernie-2.0-large-en", + "nghuyong/ernie-3.0-base-zh", + "nghuyong/ernie-3.0-medium-zh", + "nghuyong/ernie-3.0-mini-zh", + "nghuyong/ernie-3.0-micro-zh", + "nghuyong/ernie-3.0-nano-zh", + "nghuyong/ernie-gram-zh", + "nghuyong/ernie-health-zh", + ] +) + +ERNIE_M_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "susnato/ernie-m-base_pytorch": "https://huggingface.co/susnato/ernie-m-base_pytorch/blob/main/config.json", + "susnato/ernie-m-large_pytorch": "https://huggingface.co/susnato/ernie-m-large_pytorch/blob/main/config.json", + } +) + +ERNIE_M_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["susnato/ernie-m-base_pytorch", "susnato/ernie-m-large_pytorch"] +) + +ESM_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/esm-1b": "https://huggingface.co/facebook/esm-1b/resolve/main/config.json"} +) + +ESM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/esm2_t6_8M_UR50D", "facebook/esm2_t12_35M_UR50D"]) + +FALCON_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "tiiuae/falcon-40b": "https://huggingface.co/tiiuae/falcon-40b/resolve/main/config.json", + "tiiuae/falcon-7b": "https://huggingface.co/tiiuae/falcon-7b/resolve/main/config.json", + } +) + +FALCON_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "tiiuae/falcon-40b", + "tiiuae/falcon-40b-instruct", + "tiiuae/falcon-7b", + "tiiuae/falcon-7b-instruct", + "tiiuae/falcon-rw-7b", + "tiiuae/falcon-rw-1b", + ] +) + +FASTSPEECH2_CONFORMER_HIFIGAN_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "espnet/fastspeech2_conformer_hifigan": "https://huggingface.co/espnet/fastspeech2_conformer_hifigan/raw/main/config.json" + } +) + +FASTSPEECH2_CONFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"espnet/fastspeech2_conformer": "https://huggingface.co/espnet/fastspeech2_conformer/raw/main/config.json"} +) + +FASTSPEECH2_CONFORMER_WITH_HIFIGAN_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "espnet/fastspeech2_conformer_with_hifigan": "https://huggingface.co/espnet/fastspeech2_conformer_with_hifigan/raw/main/config.json" + } +) + +FASTSPEECH2_CONFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["espnet/fastspeech2_conformer"]) + +FLAUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "flaubert/flaubert_small_cased": "https://huggingface.co/flaubert/flaubert_small_cased/resolve/main/config.json", + "flaubert/flaubert_base_uncased": "https://huggingface.co/flaubert/flaubert_base_uncased/resolve/main/config.json", + "flaubert/flaubert_base_cased": "https://huggingface.co/flaubert/flaubert_base_cased/resolve/main/config.json", + "flaubert/flaubert_large_cased": "https://huggingface.co/flaubert/flaubert_large_cased/resolve/main/config.json", + } +) + +FLAUBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "flaubert/flaubert_small_cased", + "flaubert/flaubert_base_uncased", + "flaubert/flaubert_base_cased", + "flaubert/flaubert_large_cased", + ] +) + +TF_FLAUBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList([]) + +FLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/flava-full": "https://huggingface.co/facebook/flava-full/resolve/main/config.json"} +) + +FLAVA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/flava-full"]) + +FNET_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/fnet-base": "https://huggingface.co/google/fnet-base/resolve/main/config.json", + "google/fnet-large": "https://huggingface.co/google/fnet-large/resolve/main/config.json", + } +) + +FNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/fnet-base", "google/fnet-large"]) + +FOCALNET_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"microsoft/focalnet-tiny": "https://huggingface.co/microsoft/focalnet-tiny/resolve/main/config.json"} +) + +FOCALNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/focalnet-tiny"]) + +FSMT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict({}) + +FUNNEL_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "funnel-transformer/small": "https://huggingface.co/funnel-transformer/small/resolve/main/config.json", + "funnel-transformer/small-base": "https://huggingface.co/funnel-transformer/small-base/resolve/main/config.json", + "funnel-transformer/medium": "https://huggingface.co/funnel-transformer/medium/resolve/main/config.json", + "funnel-transformer/medium-base": "https://huggingface.co/funnel-transformer/medium-base/resolve/main/config.json", + "funnel-transformer/intermediate": "https://huggingface.co/funnel-transformer/intermediate/resolve/main/config.json", + "funnel-transformer/intermediate-base": "https://huggingface.co/funnel-transformer/intermediate-base/resolve/main/config.json", + "funnel-transformer/large": "https://huggingface.co/funnel-transformer/large/resolve/main/config.json", + "funnel-transformer/large-base": "https://huggingface.co/funnel-transformer/large-base/resolve/main/config.json", + "funnel-transformer/xlarge": "https://huggingface.co/funnel-transformer/xlarge/resolve/main/config.json", + "funnel-transformer/xlarge-base": "https://huggingface.co/funnel-transformer/xlarge-base/resolve/main/config.json", + } +) + +FUNNEL_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "funnel-transformer/small", + "funnel-transformer/small-base", + "funnel-transformer/medium", + "funnel-transformer/medium-base", + "funnel-transformer/intermediate", + "funnel-transformer/intermediate-base", + "funnel-transformer/large", + "funnel-transformer/large-base", + "funnel-transformer/xlarge-base", + "funnel-transformer/xlarge", + ] +) + +TF_FUNNEL_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "funnel-transformer/small", + "funnel-transformer/small-base", + "funnel-transformer/medium", + "funnel-transformer/medium-base", + "funnel-transformer/intermediate", + "funnel-transformer/intermediate-base", + "funnel-transformer/large", + "funnel-transformer/large-base", + "funnel-transformer/xlarge-base", + "funnel-transformer/xlarge", + ] +) + +FUYU_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"adept/fuyu-8b": "https://huggingface.co/adept/fuyu-8b/resolve/main/config.json"} +) + +GEMMA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict({}) + +GIT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"microsoft/git-base": "https://huggingface.co/microsoft/git-base/resolve/main/config.json"} +) + +GIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/git-base"]) + +GLPN_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"vinvino02/glpn-kitti": "https://huggingface.co/vinvino02/glpn-kitti/resolve/main/config.json"} +) + +GLPN_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["vinvino02/glpn-kitti"]) + +GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "openai-community/gpt2": "https://huggingface.co/openai-community/gpt2/resolve/main/config.json", + "openai-community/gpt2-medium": "https://huggingface.co/openai-community/gpt2-medium/resolve/main/config.json", + "openai-community/gpt2-large": "https://huggingface.co/openai-community/gpt2-large/resolve/main/config.json", + "openai-community/gpt2-xl": "https://huggingface.co/openai-community/gpt2-xl/resolve/main/config.json", + "distilbert/distilgpt2": "https://huggingface.co/distilbert/distilgpt2/resolve/main/config.json", + } +) + +GPT2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "openai-community/gpt2", + "openai-community/gpt2-medium", + "openai-community/gpt2-large", + "openai-community/gpt2-xl", + "distilbert/distilgpt2", + ] +) + +TF_GPT2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "openai-community/gpt2", + "openai-community/gpt2-medium", + "openai-community/gpt2-large", + "openai-community/gpt2-xl", + "distilbert/distilgpt2", + ] +) + +GPT_BIGCODE_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "bigcode/gpt_bigcode-santacoder": "https://huggingface.co/bigcode/gpt_bigcode-santacoder/resolve/main/config.json" + } +) + +GPT_BIGCODE_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["bigcode/gpt_bigcode-santacoder"]) + +GPT_NEO_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"EleutherAI/gpt-neo-1.3B": "https://huggingface.co/EleutherAI/gpt-neo-1.3B/resolve/main/config.json"} +) + +GPT_NEO_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["EleutherAI/gpt-neo-1.3B"]) + +GPT_NEOX_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"EleutherAI/gpt-neox-20b": "https://huggingface.co/EleutherAI/gpt-neox-20b/resolve/main/config.json"} +) + +GPT_NEOX_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["EleutherAI/gpt-neox-20b"]) + +GPT_NEOX_JAPANESE_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"abeja/gpt-neox-japanese-2.7b": "https://huggingface.co/abeja/gpt-neox-japanese-2.7b/resolve/main/config.json"} +) + +GPT_NEOX_JAPANESE_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["https://huggingface.co/abeja/gpt-neox-japanese-2.7b/resolve/main/config.json"] +) + +GPTJ_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"EleutherAI/gpt-j-6B": "https://huggingface.co/EleutherAI/gpt-j-6B/resolve/main/config.json"} +) + +GPTJ_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["EleutherAI/gpt-j-6B"]) + +GPTSAN_JAPANESE_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "tanreinama/GPTSAN-2.8B-spout_is_uniform": "https://huggingface.co/tanreinama/GPTSAN-2.8B-spout_is_uniform/resolve/main/config.json" + } +) + +GPTSAN_JAPANESE_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["Tanrei/GPTSAN-japanese"]) + +GRAPHORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"graphormer-base": "https://huggingface.co/clefourrier/graphormer-base-pcqm4mv2/resolve/main/config.json"} +) + +GRAPHORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["clefourrier/graphormer-base-pcqm4mv1", "clefourrier/graphormer-base-pcqm4mv2"] +) + +GROUPVIT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"nvidia/groupvit-gcc-yfcc": "https://huggingface.co/nvidia/groupvit-gcc-yfcc/resolve/main/config.json"} +) + +GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["nvidia/groupvit-gcc-yfcc"]) + +TF_GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["nvidia/groupvit-gcc-yfcc"]) + +HUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/hubert-base-ls960": "https://huggingface.co/facebook/hubert-base-ls960/resolve/main/config.json"} +) + +HUBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/hubert-base-ls960"]) + +TF_HUBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/hubert-base-ls960"]) + +IBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "kssteven/ibert-roberta-base": "https://huggingface.co/kssteven/ibert-roberta-base/resolve/main/config.json", + "kssteven/ibert-roberta-large": "https://huggingface.co/kssteven/ibert-roberta-large/resolve/main/config.json", + "kssteven/ibert-roberta-large-mnli": "https://huggingface.co/kssteven/ibert-roberta-large-mnli/resolve/main/config.json", + } +) + +IBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["kssteven/ibert-roberta-base", "kssteven/ibert-roberta-large", "kssteven/ibert-roberta-large-mnli"] +) + +IDEFICS_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "HuggingFaceM4/idefics-9b": "https://huggingface.co/HuggingFaceM4/idefics-9b/blob/main/config.json", + "HuggingFaceM4/idefics-80b": "https://huggingface.co/HuggingFaceM4/idefics-80b/blob/main/config.json", + } +) + +IDEFICS_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["HuggingFaceM4/idefics-9b", "HuggingFaceM4/idefics-80b"]) + +IMAGEGPT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"openai/imagegpt-small": "", "openai/imagegpt-medium": "", "openai/imagegpt-large": ""} +) + +IMAGEGPT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["openai/imagegpt-small", "openai/imagegpt-medium", "openai/imagegpt-large"] +) + +INFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "huggingface/informer-tourism-monthly": "https://huggingface.co/huggingface/informer-tourism-monthly/resolve/main/config.json" + } +) + +INFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["huggingface/informer-tourism-monthly"]) + +INSTRUCTBLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "Salesforce/instruct-blip-flan-t5": "https://huggingface.co/Salesforce/instruct-blip-flan-t5/resolve/main/config.json" + } +) + +INSTRUCTBLIP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["Salesforce/instructblip-flan-t5-xl"]) + +JUKEBOX_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "openai/jukebox-5b-lyrics": "https://huggingface.co/openai/jukebox-5b-lyrics/blob/main/config.json", + "openai/jukebox-1b-lyrics": "https://huggingface.co/openai/jukebox-1b-lyrics/blob/main/config.json", + } +) + +JUKEBOX_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["openai/jukebox-1b-lyrics", "openai/jukebox-5b-lyrics"]) + +KOSMOS2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/kosmos-2-patch14-224": "https://huggingface.co/microsoft/kosmos-2-patch14-224/resolve/main/config.json" + } +) + +KOSMOS2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/kosmos-2-patch14-224"]) + +LAYOUTLM_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/layoutlm-base-uncased": "https://huggingface.co/microsoft/layoutlm-base-uncased/resolve/main/config.json", + "microsoft/layoutlm-large-uncased": "https://huggingface.co/microsoft/layoutlm-large-uncased/resolve/main/config.json", + } +) + +LAYOUTLM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["layoutlm-base-uncased", "layoutlm-large-uncased"]) + +TF_LAYOUTLM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["microsoft/layoutlm-base-uncased", "microsoft/layoutlm-large-uncased"] +) + +LAYOUTLMV2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "layoutlmv2-base-uncased": "https://huggingface.co/microsoft/layoutlmv2-base-uncased/resolve/main/config.json", + "layoutlmv2-large-uncased": "https://huggingface.co/microsoft/layoutlmv2-large-uncased/resolve/main/config.json", + } +) + +LAYOUTLMV2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["microsoft/layoutlmv2-base-uncased", "microsoft/layoutlmv2-large-uncased"] +) + +LAYOUTLMV3_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"microsoft/layoutlmv3-base": "https://huggingface.co/microsoft/layoutlmv3-base/resolve/main/config.json"} +) + +LAYOUTLMV3_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/layoutlmv3-base", "microsoft/layoutlmv3-large"]) + +TF_LAYOUTLMV3_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["microsoft/layoutlmv3-base", "microsoft/layoutlmv3-large"] +) + +LED_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"allenai/led-base-16384": "https://huggingface.co/allenai/led-base-16384/resolve/main/config.json"} +) + +LED_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["allenai/led-base-16384"]) + +LEVIT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/levit-128S": "https://huggingface.co/facebook/levit-128S/resolve/main/config.json"} +) + +LEVIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/levit-128S"]) + +LILT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "SCUT-DLVCLab/lilt-roberta-en-base": "https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base/resolve/main/config.json" + } +) + +LILT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["SCUT-DLVCLab/lilt-roberta-en-base"]) + +LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict({}) + +LLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"llava-hf/llava-v1.5-7b": "https://huggingface.co/llava-hf/llava-v1.5-7b/resolve/main/config.json"} +) + +LLAVA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["llava-hf/llava-1.5-7b-hf", "llava-hf/llava-1.5-13b-hf", "llava-hf/bakLlava-v1-hf"] +) + +LONGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "allenai/longformer-base-4096": "https://huggingface.co/allenai/longformer-base-4096/resolve/main/config.json", + "allenai/longformer-large-4096": "https://huggingface.co/allenai/longformer-large-4096/resolve/main/config.json", + "allenai/longformer-large-4096-finetuned-triviaqa": "https://huggingface.co/allenai/longformer-large-4096-finetuned-triviaqa/resolve/main/config.json", + "allenai/longformer-base-4096-extra.pos.embd.only": "https://huggingface.co/allenai/longformer-base-4096-extra.pos.embd.only/resolve/main/config.json", + "allenai/longformer-large-4096-extra.pos.embd.only": "https://huggingface.co/allenai/longformer-large-4096-extra.pos.embd.only/resolve/main/config.json", + } +) + +LONGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "allenai/longformer-base-4096", + "allenai/longformer-large-4096", + "allenai/longformer-large-4096-finetuned-triviaqa", + "allenai/longformer-base-4096-extra.pos.embd.only", + "allenai/longformer-large-4096-extra.pos.embd.only", + ] +) + +TF_LONGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "allenai/longformer-base-4096", + "allenai/longformer-large-4096", + "allenai/longformer-large-4096-finetuned-triviaqa", + "allenai/longformer-base-4096-extra.pos.embd.only", + "allenai/longformer-large-4096-extra.pos.embd.only", + ] +) + +LONGT5_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/long-t5-local-base": "https://huggingface.co/google/long-t5-local-base/blob/main/config.json", + "google/long-t5-local-large": "https://huggingface.co/google/long-t5-local-large/blob/main/config.json", + "google/long-t5-tglobal-base": "https://huggingface.co/google/long-t5-tglobal-base/blob/main/config.json", + "google/long-t5-tglobal-large": "https://huggingface.co/google/long-t5-tglobal-large/blob/main/config.json", + } +) + +LONGT5_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "google/long-t5-local-base", + "google/long-t5-local-large", + "google/long-t5-tglobal-base", + "google/long-t5-tglobal-large", + ] +) + +LUKE_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "studio-ousia/luke-base": "https://huggingface.co/studio-ousia/luke-base/resolve/main/config.json", + "studio-ousia/luke-large": "https://huggingface.co/studio-ousia/luke-large/resolve/main/config.json", + } +) + +LUKE_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["studio-ousia/luke-base", "studio-ousia/luke-large"]) + +LXMERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"unc-nlp/lxmert-base-uncased": "https://huggingface.co/unc-nlp/lxmert-base-uncased/resolve/main/config.json"} +) + +TF_LXMERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["unc-nlp/lxmert-base-uncased"]) + +M2M_100_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/m2m100_418M": "https://huggingface.co/facebook/m2m100_418M/resolve/main/config.json"} +) + +M2M_100_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/m2m100_418M"]) + +MAMBA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"state-spaces/mamba-2.8b": "https://huggingface.co/state-spaces/mamba-2.8b/resolve/main/config.json"} +) + +MAMBA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList([]) + +MARKUPLM_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/markuplm-base": "https://huggingface.co/microsoft/markuplm-base/resolve/main/config.json", + "microsoft/markuplm-large": "https://huggingface.co/microsoft/markuplm-large/resolve/main/config.json", + } +) + +MARKUPLM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/markuplm-base", "microsoft/markuplm-large"]) + +MASK2FORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/mask2former-swin-small-coco-instance": "https://huggingface.co/facebook/mask2former-swin-small-coco-instance/blob/main/config.json" + } +) + +MASK2FORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/mask2former-swin-small-coco-instance"]) + +MASKFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/maskformer-swin-base-ade": "https://huggingface.co/facebook/maskformer-swin-base-ade/blob/main/config.json" + } +) + +MASKFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/maskformer-swin-base-ade"]) + +MEGA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"mnaylor/mega-base-wikitext": "https://huggingface.co/mnaylor/mega-base-wikitext/resolve/main/config.json"} +) + +MEGA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["mnaylor/mega-base-wikitext"]) + +MEGATRON_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict({}) + +MEGATRON_BERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["nvidia/megatron-bert-cased-345m"]) + +MGP_STR_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"alibaba-damo/mgp-str-base": "https://huggingface.co/alibaba-damo/mgp-str-base/resolve/main/config.json"} +) + +MGP_STR_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["alibaba-damo/mgp-str-base"]) + +MISTRAL_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "mistralai/Mistral-7B-v0.1": "https://huggingface.co/mistralai/Mistral-7B-v0.1/resolve/main/config.json", + "mistralai/Mistral-7B-Instruct-v0.1": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1/resolve/main/config.json", + } +) + +MIXTRAL_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"mistral-ai/Mixtral-8x7B": "https://huggingface.co/mistral-ai/Mixtral-8x7B/resolve/main/config.json"} +) + +MOBILEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"google/mobilebert-uncased": "https://huggingface.co/google/mobilebert-uncased/resolve/main/config.json"} +) + +MOBILEBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/mobilebert-uncased"]) + +TF_MOBILEBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/mobilebert-uncased"]) + +MOBILENET_V1_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/mobilenet_v1_1.0_224": "https://huggingface.co/google/mobilenet_v1_1.0_224/resolve/main/config.json", + "google/mobilenet_v1_0.75_192": "https://huggingface.co/google/mobilenet_v1_0.75_192/resolve/main/config.json", + } +) + +MOBILENET_V1_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["google/mobilenet_v1_1.0_224", "google/mobilenet_v1_0.75_192"] +) + +MOBILENET_V2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/mobilenet_v2_1.4_224": "https://huggingface.co/google/mobilenet_v2_1.4_224/resolve/main/config.json", + "google/mobilenet_v2_1.0_224": "https://huggingface.co/google/mobilenet_v2_1.0_224/resolve/main/config.json", + "google/mobilenet_v2_0.75_160": "https://huggingface.co/google/mobilenet_v2_0.75_160/resolve/main/config.json", + "google/mobilenet_v2_0.35_96": "https://huggingface.co/google/mobilenet_v2_0.35_96/resolve/main/config.json", + } +) + +MOBILENET_V2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "google/mobilenet_v2_1.4_224", + "google/mobilenet_v2_1.0_224", + "google/mobilenet_v2_0.37_160", + "google/mobilenet_v2_0.35_96", + ] +) + +MOBILEVIT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "apple/mobilevit-small": "https://huggingface.co/apple/mobilevit-small/resolve/main/config.json", + "apple/mobilevit-x-small": "https://huggingface.co/apple/mobilevit-x-small/resolve/main/config.json", + "apple/mobilevit-xx-small": "https://huggingface.co/apple/mobilevit-xx-small/resolve/main/config.json", + "apple/deeplabv3-mobilevit-small": "https://huggingface.co/apple/deeplabv3-mobilevit-small/resolve/main/config.json", + "apple/deeplabv3-mobilevit-x-small": "https://huggingface.co/apple/deeplabv3-mobilevit-x-small/resolve/main/config.json", + "apple/deeplabv3-mobilevit-xx-small": "https://huggingface.co/apple/deeplabv3-mobilevit-xx-small/resolve/main/config.json", + } +) + +MOBILEVIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "apple/mobilevit-small", + "apple/mobilevit-x-small", + "apple/mobilevit-xx-small", + "apple/deeplabv3-mobilevit-small", + "apple/deeplabv3-mobilevit-x-small", + "apple/deeplabv3-mobilevit-xx-small", + ] +) + +TF_MOBILEVIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "apple/mobilevit-small", + "apple/mobilevit-x-small", + "apple/mobilevit-xx-small", + "apple/deeplabv3-mobilevit-small", + "apple/deeplabv3-mobilevit-x-small", + "apple/deeplabv3-mobilevit-xx-small", + ] +) + +MOBILEVITV2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"apple/mobilevitv2-1.0": "https://huggingface.co/apple/mobilevitv2-1.0/resolve/main/config.json"} +) + +MOBILEVITV2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["apple/mobilevitv2-1.0-imagenet1k-256"]) + +MPNET_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"microsoft/mpnet-base": "https://huggingface.co/microsoft/mpnet-base/resolve/main/config.json"} +) + +MPNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/mpnet-base"]) + +TF_MPNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/mpnet-base"]) + +MPT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"mosaicml/mpt-7b": "https://huggingface.co/mosaicml/mpt-7b/resolve/main/config.json"} +) + +MPT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "mosaicml/mpt-7b", + "mosaicml/mpt-7b-storywriter", + "mosaicml/mpt-7b-instruct", + "mosaicml/mpt-7b-8k", + "mosaicml/mpt-7b-8k-instruct", + "mosaicml/mpt-7b-8k-chat", + "mosaicml/mpt-30b", + "mosaicml/mpt-30b-instruct", + "mosaicml/mpt-30b-chat", + ] +) + +MRA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"uw-madison/mra-base-512-4": "https://huggingface.co/uw-madison/mra-base-512-4/resolve/main/config.json"} +) + +MRA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["uw-madison/mra-base-512-4"]) + +MUSICGEN_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/musicgen-small": "https://huggingface.co/facebook/musicgen-small/resolve/main/config.json"} +) + +MUSICGEN_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/musicgen-small"]) + +MVP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "RUCAIBox/mvp", + "RUCAIBox/mvp-data-to-text", + "RUCAIBox/mvp-open-dialog", + "RUCAIBox/mvp-question-answering", + "RUCAIBox/mvp-question-generation", + "RUCAIBox/mvp-story", + "RUCAIBox/mvp-summarization", + "RUCAIBox/mvp-task-dialog", + "RUCAIBox/mtl-data-to-text", + "RUCAIBox/mtl-multi-task", + "RUCAIBox/mtl-open-dialog", + "RUCAIBox/mtl-question-answering", + "RUCAIBox/mtl-question-generation", + "RUCAIBox/mtl-story", + "RUCAIBox/mtl-summarization", + ] +) + +NAT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"shi-labs/nat-mini-in1k-224": "https://huggingface.co/shi-labs/nat-mini-in1k-224/resolve/main/config.json"} +) + +NAT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["shi-labs/nat-mini-in1k-224"]) + +NEZHA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"sijunhe/nezha-cn-base": "https://huggingface.co/sijunhe/nezha-cn-base/resolve/main/config.json"} +) + +NEZHA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["sijunhe/nezha-cn-base", "sijunhe/nezha-cn-large", "sijunhe/nezha-base-wwm", "sijunhe/nezha-large-wwm"] +) + +NLLB_MOE_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/nllb-moe-54B": "https://huggingface.co/facebook/nllb-moe-54b/resolve/main/config.json"} +) + +NLLB_MOE_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/nllb-moe-54b"]) + +NYSTROMFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"uw-madison/nystromformer-512": "https://huggingface.co/uw-madison/nystromformer-512/resolve/main/config.json"} +) + +NYSTROMFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["uw-madison/nystromformer-512"]) + +ONEFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "shi-labs/oneformer_ade20k_swin_tiny": "https://huggingface.co/shi-labs/oneformer_ade20k_swin_tiny/blob/main/config.json" + } +) + +ONEFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["shi-labs/oneformer_ade20k_swin_tiny"]) + +OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"openai-community/openai-gpt": "https://huggingface.co/openai-community/openai-gpt/resolve/main/config.json"} +) + +OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["openai-community/openai-gpt"]) + +TF_OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["openai-community/openai-gpt"]) + +OPT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "facebook/opt-125m", + "facebook/opt-350m", + "facebook/opt-1.3b", + "facebook/opt-2.7b", + "facebook/opt-6.7b", + "facebook/opt-13b", + "facebook/opt-30b", + ] +) + +OWLV2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"google/owlv2-base-patch16": "https://huggingface.co/google/owlv2-base-patch16/resolve/main/config.json"} +) + +OWLV2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/owlv2-base-patch16-ensemble"]) + +OWLVIT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/owlvit-base-patch32": "https://huggingface.co/google/owlvit-base-patch32/resolve/main/config.json", + "google/owlvit-base-patch16": "https://huggingface.co/google/owlvit-base-patch16/resolve/main/config.json", + "google/owlvit-large-patch14": "https://huggingface.co/google/owlvit-large-patch14/resolve/main/config.json", + } +) + +OWLVIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["google/owlvit-base-patch32", "google/owlvit-base-patch16", "google/owlvit-large-patch14"] +) + +PATCHTSMIXER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "ibm/patchtsmixer-etth1-pretrain": "https://huggingface.co/ibm/patchtsmixer-etth1-pretrain/resolve/main/config.json" + } +) + +PATCHTSMIXER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["ibm/patchtsmixer-etth1-pretrain"]) + +PATCHTST_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"ibm/patchtst-base": "https://huggingface.co/ibm/patchtst-base/resolve/main/config.json"} +) + +PATCHTST_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["ibm/patchtst-etth1-pretrain"]) + +PEGASUS_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"google/pegasus-large": "https://huggingface.co/google/pegasus-large/resolve/main/config.json"} +) + +PEGASUS_X_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/pegasus-x-base": "https://huggingface.co/google/pegasus-x-base/resolve/main/config.json", + "google/pegasus-x-large": "https://huggingface.co/google/pegasus-x-large/resolve/main/config.json", + } +) + +PEGASUS_X_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/pegasus-x-base", "google/pegasus-x-large"]) + +PERCEIVER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"deepmind/language-perceiver": "https://huggingface.co/deepmind/language-perceiver/resolve/main/config.json"} +) + +PERCEIVER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["deepmind/language-perceiver"]) + +PERSIMMON_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"adept/persimmon-8b-base": "https://huggingface.co/adept/persimmon-8b-base/resolve/main/config.json"} +) + +PHI_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/phi-1": "https://huggingface.co/microsoft/phi-1/resolve/main/config.json", + "microsoft/phi-1_5": "https://huggingface.co/microsoft/phi-1_5/resolve/main/config.json", + "microsoft/phi-2": "https://huggingface.co/microsoft/phi-2/resolve/main/config.json", + } +) + +PHI_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/phi-1", "microsoft/phi-1_5", "microsoft/phi-2"]) + +PIX2STRUCT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/pix2struct-textcaps-base": "https://huggingface.co/google/pix2struct-textcaps-base/resolve/main/config.json" + } +) + +PIX2STRUCT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "google/pix2struct-textcaps-base", + "google/pix2struct-textcaps-large", + "google/pix2struct-base", + "google/pix2struct-large", + "google/pix2struct-ai2d-base", + "google/pix2struct-ai2d-large", + "google/pix2struct-widget-captioning-base", + "google/pix2struct-widget-captioning-large", + "google/pix2struct-screen2words-base", + "google/pix2struct-screen2words-large", + "google/pix2struct-docvqa-base", + "google/pix2struct-docvqa-large", + "google/pix2struct-ocrvqa-base", + "google/pix2struct-ocrvqa-large", + "google/pix2struct-chartqa-base", + "google/pix2struct-inforgraphics-vqa-base", + "google/pix2struct-inforgraphics-vqa-large", + ] +) + +PLBART_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"uclanlp/plbart-base": "https://huggingface.co/uclanlp/plbart-base/resolve/main/config.json"} +) + +PLBART_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["uclanlp/plbart-base", "uclanlp/plbart-cs-java", "uclanlp/plbart-multi_task-all"] +) + +POOLFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"sail/poolformer_s12": "https://huggingface.co/sail/poolformer_s12/resolve/main/config.json"} +) + +POOLFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["sail/poolformer_s12"]) + +POP2PIANO_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"sweetcocoa/pop2piano": "https://huggingface.co/sweetcocoa/pop2piano/blob/main/config.json"} +) + +POP2PIANO_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["sweetcocoa/pop2piano"]) + +PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/prophetnet-large-uncased": "https://huggingface.co/microsoft/prophetnet-large-uncased/resolve/main/config.json" + } +) + +PROPHETNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/prophetnet-large-uncased"]) + +PVT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict({"pvt-tiny-224": "https://huggingface.co/Zetatech/pvt-tiny-224"}) + +PVT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["Zetatech/pvt-tiny-224"]) + +QDQBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"google-bert/bert-base-uncased": "https://huggingface.co/google-bert/bert-base-uncased/resolve/main/config.json"} +) + +QDQBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google-bert/bert-base-uncased"]) + +QWEN2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"Qwen/Qwen2-7B-beta": "https://huggingface.co/Qwen/Qwen2-7B-beta/resolve/main/config.json"} +) + +REALM_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/realm-cc-news-pretrained-embedder": "https://huggingface.co/google/realm-cc-news-pretrained-embedder/resolve/main/config.json", + "google/realm-cc-news-pretrained-encoder": "https://huggingface.co/google/realm-cc-news-pretrained-encoder/resolve/main/config.json", + "google/realm-cc-news-pretrained-scorer": "https://huggingface.co/google/realm-cc-news-pretrained-scorer/resolve/main/config.json", + "google/realm-cc-news-pretrained-openqa": "https://huggingface.co/google/realm-cc-news-pretrained-openqa/aresolve/main/config.json", + "google/realm-orqa-nq-openqa": "https://huggingface.co/google/realm-orqa-nq-openqa/resolve/main/config.json", + "google/realm-orqa-nq-reader": "https://huggingface.co/google/realm-orqa-nq-reader/resolve/main/config.json", + "google/realm-orqa-wq-openqa": "https://huggingface.co/google/realm-orqa-wq-openqa/resolve/main/config.json", + "google/realm-orqa-wq-reader": "https://huggingface.co/google/realm-orqa-wq-reader/resolve/main/config.json", + } +) + +REALM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "google/realm-cc-news-pretrained-embedder", + "google/realm-cc-news-pretrained-encoder", + "google/realm-cc-news-pretrained-scorer", + "google/realm-cc-news-pretrained-openqa", + "google/realm-orqa-nq-openqa", + "google/realm-orqa-nq-reader", + "google/realm-orqa-wq-openqa", + "google/realm-orqa-wq-reader", + ] +) + +REFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/reformer-crime-and-punishment": "https://huggingface.co/google/reformer-crime-and-punishment/resolve/main/config.json", + "google/reformer-enwik8": "https://huggingface.co/google/reformer-enwik8/resolve/main/config.json", + } +) + +REFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["google/reformer-crime-and-punishment", "google/reformer-enwik8"] +) + +REGNET_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/regnet-y-040": "https://huggingface.co/facebook/regnet-y-040/blob/main/config.json"} +) + +REGNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/regnet-y-040"]) + +TF_REGNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/regnet-y-040"]) + +REMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"google/rembert": "https://huggingface.co/google/rembert/resolve/main/config.json"} +) + +REMBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/rembert"]) + +TF_REMBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/rembert"]) + +RESNET_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"microsoft/resnet-50": "https://huggingface.co/microsoft/resnet-50/blob/main/config.json"} +) + +RESNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/resnet-50"]) + +TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/resnet-50"]) + +ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "FacebookAI/roberta-base": "https://huggingface.co/FacebookAI/roberta-base/resolve/main/config.json", + "FacebookAI/roberta-large": "https://huggingface.co/FacebookAI/roberta-large/resolve/main/config.json", + "FacebookAI/roberta-large-mnli": "https://huggingface.co/FacebookAI/roberta-large-mnli/resolve/main/config.json", + "distilbert/distilroberta-base": "https://huggingface.co/distilbert/distilroberta-base/resolve/main/config.json", + "openai-community/roberta-base-openai-detector": "https://huggingface.co/openai-community/roberta-base-openai-detector/resolve/main/config.json", + "openai-community/roberta-large-openai-detector": "https://huggingface.co/openai-community/roberta-large-openai-detector/resolve/main/config.json", + } +) + +ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "FacebookAI/roberta-base", + "FacebookAI/roberta-large", + "FacebookAI/roberta-large-mnli", + "distilbert/distilroberta-base", + "openai-community/roberta-base-openai-detector", + "openai-community/roberta-large-openai-detector", + ] +) + +TF_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "FacebookAI/roberta-base", + "FacebookAI/roberta-large", + "FacebookAI/roberta-large-mnli", + "distilbert/distilroberta-base", + ] +) + +ROBERTA_PRELAYERNORM_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "andreasmadsen/efficient_mlm_m0.40": "https://huggingface.co/andreasmadsen/efficient_mlm_m0.40/resolve/main/config.json" + } +) + +ROBERTA_PRELAYERNORM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "andreasmadsen/efficient_mlm_m0.15", + "andreasmadsen/efficient_mlm_m0.20", + "andreasmadsen/efficient_mlm_m0.30", + "andreasmadsen/efficient_mlm_m0.40", + "andreasmadsen/efficient_mlm_m0.50", + "andreasmadsen/efficient_mlm_m0.60", + "andreasmadsen/efficient_mlm_m0.70", + "andreasmadsen/efficient_mlm_m0.80", + ] +) + +TF_ROBERTA_PRELAYERNORM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "andreasmadsen/efficient_mlm_m0.15", + "andreasmadsen/efficient_mlm_m0.20", + "andreasmadsen/efficient_mlm_m0.30", + "andreasmadsen/efficient_mlm_m0.40", + "andreasmadsen/efficient_mlm_m0.50", + "andreasmadsen/efficient_mlm_m0.60", + "andreasmadsen/efficient_mlm_m0.70", + "andreasmadsen/efficient_mlm_m0.80", + ] +) + +ROC_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"weiweishi/roc-bert-base-zh": "https://huggingface.co/weiweishi/roc-bert-base-zh/resolve/main/config.json"} +) + +ROC_BERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["weiweishi/roc-bert-base-zh"]) + +ROFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "junnyu/roformer_chinese_small": "https://huggingface.co/junnyu/roformer_chinese_small/resolve/main/config.json", + "junnyu/roformer_chinese_base": "https://huggingface.co/junnyu/roformer_chinese_base/resolve/main/config.json", + "junnyu/roformer_chinese_char_small": "https://huggingface.co/junnyu/roformer_chinese_char_small/resolve/main/config.json", + "junnyu/roformer_chinese_char_base": "https://huggingface.co/junnyu/roformer_chinese_char_base/resolve/main/config.json", + "junnyu/roformer_small_discriminator": "https://huggingface.co/junnyu/roformer_small_discriminator/resolve/main/config.json", + "junnyu/roformer_small_generator": "https://huggingface.co/junnyu/roformer_small_generator/resolve/main/config.json", + } +) + +ROFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "junnyu/roformer_chinese_small", + "junnyu/roformer_chinese_base", + "junnyu/roformer_chinese_char_small", + "junnyu/roformer_chinese_char_base", + "junnyu/roformer_small_discriminator", + "junnyu/roformer_small_generator", + ] +) + +TF_ROFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "junnyu/roformer_chinese_small", + "junnyu/roformer_chinese_base", + "junnyu/roformer_chinese_char_small", + "junnyu/roformer_chinese_char_base", + "junnyu/roformer_small_discriminator", + "junnyu/roformer_small_generator", + ] +) + +RWKV_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "RWKV/rwkv-4-169m-pile": "https://huggingface.co/RWKV/rwkv-4-169m-pile/resolve/main/config.json", + "RWKV/rwkv-4-430m-pile": "https://huggingface.co/RWKV/rwkv-4-430m-pile/resolve/main/config.json", + "RWKV/rwkv-4-1b5-pile": "https://huggingface.co/RWKV/rwkv-4-1b5-pile/resolve/main/config.json", + "RWKV/rwkv-4-3b-pile": "https://huggingface.co/RWKV/rwkv-4-3b-pile/resolve/main/config.json", + "RWKV/rwkv-4-7b-pile": "https://huggingface.co/RWKV/rwkv-4-7b-pile/resolve/main/config.json", + "RWKV/rwkv-4-14b-pile": "https://huggingface.co/RWKV/rwkv-4-14b-pile/resolve/main/config.json", + "RWKV/rwkv-raven-1b5": "https://huggingface.co/RWKV/rwkv-raven-1b5/resolve/main/config.json", + "RWKV/rwkv-raven-3b": "https://huggingface.co/RWKV/rwkv-raven-3b/resolve/main/config.json", + "RWKV/rwkv-raven-7b": "https://huggingface.co/RWKV/rwkv-raven-7b/resolve/main/config.json", + "RWKV/rwkv-raven-14b": "https://huggingface.co/RWKV/rwkv-raven-14b/resolve/main/config.json", + } +) + +RWKV_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "RWKV/rwkv-4-169m-pile", + "RWKV/rwkv-4-430m-pile", + "RWKV/rwkv-4-1b5-pile", + "RWKV/rwkv-4-3b-pile", + "RWKV/rwkv-4-7b-pile", + "RWKV/rwkv-4-14b-pile", + "RWKV/rwkv-raven-1b5", + "RWKV/rwkv-raven-3b", + "RWKV/rwkv-raven-7b", + "RWKV/rwkv-raven-14b", + ] +) + +SAM_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/sam-vit-huge": "https://huggingface.co/facebook/sam-vit-huge/resolve/main/config.json", + "facebook/sam-vit-large": "https://huggingface.co/facebook/sam-vit-large/resolve/main/config.json", + "facebook/sam-vit-base": "https://huggingface.co/facebook/sam-vit-base/resolve/main/config.json", + } +) + +SAM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["facebook/sam-vit-huge", "facebook/sam-vit-large", "facebook/sam-vit-base"] +) + +TF_SAM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["facebook/sam-vit-huge", "facebook/sam-vit-large", "facebook/sam-vit-base"] +) + +SEAMLESS_M4T_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/hf-seamless-m4t-medium": "https://huggingface.co/facebook/hf-seamless-m4t-medium/resolve/main/config.json" + } +) + +SEAMLESS_M4T_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/hf-seamless-m4t-medium"]) + +SEAMLESS_M4T_V2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"": "https://huggingface.co//resolve/main/config.json"} +) + +SEAMLESS_M4T_V2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/seamless-m4t-v2-large"]) + +SEGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "nvidia/segformer-b0-finetuned-ade-512-512": "https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512/resolve/main/config.json" + } +) + +SEGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["nvidia/segformer-b0-finetuned-ade-512-512"]) + +TF_SEGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["nvidia/segformer-b0-finetuned-ade-512-512"]) + +SEGGPT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"BAAI/seggpt-vit-large": "https://huggingface.co/BAAI/seggpt-vit-large/resolve/main/config.json"} +) + +SEGGPT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["BAAI/seggpt-vit-large"]) + +SEW_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"asapp/sew-tiny-100k": "https://huggingface.co/asapp/sew-tiny-100k/resolve/main/config.json"} +) + +SEW_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["asapp/sew-tiny-100k", "asapp/sew-small-100k", "asapp/sew-mid-100k"] +) + +SEW_D_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"asapp/sew-d-tiny-100k": "https://huggingface.co/asapp/sew-d-tiny-100k/resolve/main/config.json"} +) + +SEW_D_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "asapp/sew-d-tiny-100k", + "asapp/sew-d-small-100k", + "asapp/sew-d-mid-100k", + "asapp/sew-d-mid-k127-100k", + "asapp/sew-d-base-100k", + "asapp/sew-d-base-plus-100k", + "asapp/sew-d-mid-400k", + "asapp/sew-d-mid-k127-400k", + "asapp/sew-d-base-plus-400k", + ] +) + +SIGLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/siglip-base-patch16-224": "https://huggingface.co/google/siglip-base-patch16-224/resolve/main/config.json" + } +) + +SIGLIP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/siglip-base-patch16-224"]) + +SPEECH_TO_TEXT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/s2t-small-librispeech-asr": "https://huggingface.co/facebook/s2t-small-librispeech-asr/resolve/main/config.json" + } +) + +SPEECH_TO_TEXT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/s2t-small-librispeech-asr"]) + +TF_SPEECH_TO_TEXT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/s2t-small-librispeech-asr"]) + +SPEECH_TO_TEXT_2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/s2t-wav2vec2-large-en-de": "https://huggingface.co/facebook/s2t-wav2vec2-large-en-de/resolve/main/config.json" + } +) + +SPEECHT5_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/speecht5_asr": "https://huggingface.co/microsoft/speecht5_asr/resolve/main/config.json", + "microsoft/speecht5_tts": "https://huggingface.co/microsoft/speecht5_tts/resolve/main/config.json", + "microsoft/speecht5_vc": "https://huggingface.co/microsoft/speecht5_vc/resolve/main/config.json", + } +) + +SPEECHT5_PRETRAINED_HIFIGAN_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"microsoft/speecht5_hifigan": "https://huggingface.co/microsoft/speecht5_hifigan/resolve/main/config.json"} +) + +SPEECHT5_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["microsoft/speecht5_asr", "microsoft/speecht5_tts", "microsoft/speecht5_vc"] +) + +SPLINTER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "tau/splinter-base": "https://huggingface.co/tau/splinter-base/resolve/main/config.json", + "tau/splinter-base-qass": "https://huggingface.co/tau/splinter-base-qass/resolve/main/config.json", + "tau/splinter-large": "https://huggingface.co/tau/splinter-large/resolve/main/config.json", + "tau/splinter-large-qass": "https://huggingface.co/tau/splinter-large-qass/resolve/main/config.json", + } +) + +SPLINTER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["tau/splinter-base", "tau/splinter-base-qass", "tau/splinter-large", "tau/splinter-large-qass"] +) + +SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "squeezebert/squeezebert-uncased": "https://huggingface.co/squeezebert/squeezebert-uncased/resolve/main/config.json", + "squeezebert/squeezebert-mnli": "https://huggingface.co/squeezebert/squeezebert-mnli/resolve/main/config.json", + "squeezebert/squeezebert-mnli-headless": "https://huggingface.co/squeezebert/squeezebert-mnli-headless/resolve/main/config.json", + } +) + +SQUEEZEBERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["squeezebert/squeezebert-uncased", "squeezebert/squeezebert-mnli", "squeezebert/squeezebert-mnli-headless"] +) + +STABLELM_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"stabilityai/stablelm-3b-4e1t": "https://huggingface.co/stabilityai/stablelm-3b-4e1t/resolve/main/config.json"} +) + +STARCODER2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict({}) + +SWIFTFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"MBZUAI/swiftformer-xs": "https://huggingface.co/MBZUAI/swiftformer-xs/resolve/main/config.json"} +) + +SWIFTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["MBZUAI/swiftformer-xs"]) + +SWIN_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/swin-tiny-patch4-window7-224": "https://huggingface.co/microsoft/swin-tiny-patch4-window7-224/resolve/main/config.json" + } +) + +SWIN_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/swin-tiny-patch4-window7-224"]) + +TF_SWIN_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/swin-tiny-patch4-window7-224"]) + +SWIN2SR_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "caidas/swin2sr-classicalsr-x2-64": "https://huggingface.co/caidas/swin2sr-classicalsr-x2-64/resolve/main/config.json" + } +) + +SWIN2SR_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["caidas/swin2SR-classical-sr-x2-64"]) + +SWINV2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/swinv2-tiny-patch4-window8-256": "https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256/resolve/main/config.json" + } +) + +SWINV2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/swinv2-tiny-patch4-window8-256"]) + +SWITCH_TRANSFORMERS_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"google/switch-base-8": "https://huggingface.co/google/switch-base-8/blob/main/config.json"} +) + +SWITCH_TRANSFORMERS_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "google/switch-base-8", + "google/switch-base-16", + "google/switch-base-32", + "google/switch-base-64", + "google/switch-base-128", + "google/switch-base-256", + "google/switch-large-128", + "google/switch-xxl-128", + "google/switch-c-2048", + ] +) + +T5_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google-t5/t5-small": "https://huggingface.co/google-t5/t5-small/resolve/main/config.json", + "google-t5/t5-base": "https://huggingface.co/google-t5/t5-base/resolve/main/config.json", + "google-t5/t5-large": "https://huggingface.co/google-t5/t5-large/resolve/main/config.json", + "google-t5/t5-3b": "https://huggingface.co/google-t5/t5-3b/resolve/main/config.json", + "google-t5/t5-11b": "https://huggingface.co/google-t5/t5-11b/resolve/main/config.json", + } +) + +T5_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["google-t5/t5-small", "google-t5/t5-base", "google-t5/t5-large", "google-t5/t5-3b", "google-t5/t5-11b"] +) + +TF_T5_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["google-t5/t5-small", "google-t5/t5-base", "google-t5/t5-large", "google-t5/t5-3b", "google-t5/t5-11b"] +) + +TABLE_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/table-transformer-detection": "https://huggingface.co/microsoft/table-transformer-detection/resolve/main/config.json" + } +) + +TABLE_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/table-transformer-detection"]) + +TAPAS_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/tapas-base-finetuned-sqa": "https://huggingface.co/google/tapas-base-finetuned-sqa/resolve/main/config.json", + "google/tapas-base-finetuned-wtq": "https://huggingface.co/google/tapas-base-finetuned-wtq/resolve/main/config.json", + "google/tapas-base-finetuned-wikisql-supervised": "https://huggingface.co/google/tapas-base-finetuned-wikisql-supervised/resolve/main/config.json", + "google/tapas-base-finetuned-tabfact": "https://huggingface.co/google/tapas-base-finetuned-tabfact/resolve/main/config.json", + } +) + +TAPAS_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "google/tapas-large", + "google/tapas-large-finetuned-sqa", + "google/tapas-large-finetuned-wtq", + "google/tapas-large-finetuned-wikisql-supervised", + "google/tapas-large-finetuned-tabfact", + "google/tapas-base", + "google/tapas-base-finetuned-sqa", + "google/tapas-base-finetuned-wtq", + "google/tapas-base-finetuned-wikisql-supervised", + "google/tapas-base-finetuned-tabfact", + "google/tapas-small", + "google/tapas-small-finetuned-sqa", + "google/tapas-small-finetuned-wtq", + "google/tapas-small-finetuned-wikisql-supervised", + "google/tapas-small-finetuned-tabfact", + "google/tapas-mini", + "google/tapas-mini-finetuned-sqa", + "google/tapas-mini-finetuned-wtq", + "google/tapas-mini-finetuned-wikisql-supervised", + "google/tapas-mini-finetuned-tabfact", + "google/tapas-tiny", + "google/tapas-tiny-finetuned-sqa", + "google/tapas-tiny-finetuned-wtq", + "google/tapas-tiny-finetuned-wikisql-supervised", + "google/tapas-tiny-finetuned-tabfact", + ] +) + +TF_TAPAS_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "google/tapas-large", + "google/tapas-large-finetuned-sqa", + "google/tapas-large-finetuned-wtq", + "google/tapas-large-finetuned-wikisql-supervised", + "google/tapas-large-finetuned-tabfact", + "google/tapas-base", + "google/tapas-base-finetuned-sqa", + "google/tapas-base-finetuned-wtq", + "google/tapas-base-finetuned-wikisql-supervised", + "google/tapas-base-finetuned-tabfact", + "google/tapas-small", + "google/tapas-small-finetuned-sqa", + "google/tapas-small-finetuned-wtq", + "google/tapas-small-finetuned-wikisql-supervised", + "google/tapas-small-finetuned-tabfact", + "google/tapas-mini", + "google/tapas-mini-finetuned-sqa", + "google/tapas-mini-finetuned-wtq", + "google/tapas-mini-finetuned-wikisql-supervised", + "google/tapas-mini-finetuned-tabfact", + "google/tapas-tiny", + "google/tapas-tiny-finetuned-sqa", + "google/tapas-tiny-finetuned-wtq", + "google/tapas-tiny-finetuned-wikisql-supervised", + "google/tapas-tiny-finetuned-tabfact", + ] +) + +TIME_SERIES_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "huggingface/time-series-transformer-tourism-monthly": "https://huggingface.co/huggingface/time-series-transformer-tourism-monthly/resolve/main/config.json" + } +) + +TIME_SERIES_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["huggingface/time-series-transformer-tourism-monthly"] +) + +TIMESFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/timesformer": "https://huggingface.co/facebook/timesformer/resolve/main/config.json"} +) + +TIMESFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/timesformer-base-finetuned-k400"]) + +TROCR_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/trocr-base-handwritten": "https://huggingface.co/microsoft/trocr-base-handwritten/resolve/main/config.json" + } +) + +TROCR_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/trocr-base-handwritten"]) + +TVLT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"ZinengTang/tvlt-base": "https://huggingface.co/ZinengTang/tvlt-base/blob/main/config.json"} +) + +TVLT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["ZinengTang/tvlt-base"]) + +TVP_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"Intel/tvp-base": "https://huggingface.co/Intel/tvp-base/resolve/main/config.json"} +) + +TVP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["Intel/tvp-base", "Intel/tvp-base-ANet"]) + +UDOP_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"microsoft/udop-large": "https://huggingface.co/microsoft/udop-large/resolve/main/config.json"} +) + +UDOP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/udop-large"]) + +UNISPEECH_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/unispeech-large-1500h-cv": "https://huggingface.co/microsoft/unispeech-large-1500h-cv/resolve/main/config.json" + } +) + +UNISPEECH_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["microsoft/unispeech-large-1500h-cv", "microsoft/unispeech-large-multi-lingual-1500h-cv"] +) + +UNISPEECH_SAT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/unispeech-sat-base-100h-libri-ft": "https://huggingface.co/microsoft/unispeech-sat-base-100h-libri-ft/resolve/main/config.json" + } +) + +UNISPEECH_SAT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList([]) + +UNIVNET_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"dg845/univnet-dev": "https://huggingface.co/dg845/univnet-dev/resolve/main/config.json"} +) + +UNIVNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["dg845/univnet-dev"]) + +VIDEOMAE_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"MCG-NJU/videomae-base": "https://huggingface.co/MCG-NJU/videomae-base/resolve/main/config.json"} +) + +VIDEOMAE_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["MCG-NJU/videomae-base"]) + +VILT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"dandelin/vilt-b32-mlm": "https://huggingface.co/dandelin/vilt-b32-mlm/blob/main/config.json"} +) + +VILT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["dandelin/vilt-b32-mlm"]) + +VIPLLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"ybelkada/vip-llava-7b-hf": "https://huggingface.co/llava-hf/vip-llava-7b-hf/resolve/main/config.json"} +) + +VIPLLAVA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["llava-hf/vip-llava-7b-hf"]) + +VISUAL_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "uclanlp/visualbert-vqa": "https://huggingface.co/uclanlp/visualbert-vqa/resolve/main/config.json", + "uclanlp/visualbert-vqa-pre": "https://huggingface.co/uclanlp/visualbert-vqa-pre/resolve/main/config.json", + "uclanlp/visualbert-vqa-coco-pre": "https://huggingface.co/uclanlp/visualbert-vqa-coco-pre/resolve/main/config.json", + "uclanlp/visualbert-vcr": "https://huggingface.co/uclanlp/visualbert-vcr/resolve/main/config.json", + "uclanlp/visualbert-vcr-pre": "https://huggingface.co/uclanlp/visualbert-vcr-pre/resolve/main/config.json", + "uclanlp/visualbert-vcr-coco-pre": "https://huggingface.co/uclanlp/visualbert-vcr-coco-pre/resolve/main/config.json", + "uclanlp/visualbert-nlvr2": "https://huggingface.co/uclanlp/visualbert-nlvr2/resolve/main/config.json", + "uclanlp/visualbert-nlvr2-pre": "https://huggingface.co/uclanlp/visualbert-nlvr2-pre/resolve/main/config.json", + "uclanlp/visualbert-nlvr2-coco-pre": "https://huggingface.co/uclanlp/visualbert-nlvr2-coco-pre/resolve/main/config.json", + } +) + +VISUAL_BERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "uclanlp/visualbert-vqa", + "uclanlp/visualbert-vqa-pre", + "uclanlp/visualbert-vqa-coco-pre", + "uclanlp/visualbert-vcr", + "uclanlp/visualbert-vcr-pre", + "uclanlp/visualbert-vcr-coco-pre", + "uclanlp/visualbert-nlvr2", + "uclanlp/visualbert-nlvr2-pre", + "uclanlp/visualbert-nlvr2-coco-pre", + ] +) + +VIT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"google/vit-base-patch16-224": "https://huggingface.co/vit-base-patch16-224/resolve/main/config.json"} +) + +VIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/vit-base-patch16-224"]) + +VIT_HYBRID_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"google/vit-hybrid-base-bit-384": "https://huggingface.co/vit-hybrid-base-bit-384/resolve/main/config.json"} +) + +VIT_HYBRID_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/vit-hybrid-base-bit-384"]) + +VIT_MAE_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/vit-mae-base": "https://huggingface.co/facebook/vit-mae-base/resolve/main/config.json"} +) + +VIT_MAE_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/vit-mae-base"]) + +VIT_MSN_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"sayakpaul/vit-msn-base": "https://huggingface.co/sayakpaul/vit-msn-base/resolve/main/config.json"} +) + +VIT_MSN_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/vit-msn-small"]) + +VITDET_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/vit-det-base": "https://huggingface.co/facebook/vit-det-base/resolve/main/config.json"} +) + +VITDET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/vit-det-base"]) + +VITMATTE_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "hustvl/vitmatte-small-composition-1k": "https://huggingface.co/hustvl/vitmatte-small-composition-1k/resolve/main/config.json" + } +) + +VITMATTE_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["hustvl/vitmatte-small-composition-1k"]) + +VITS_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/mms-tts-eng": "https://huggingface.co/facebook/mms-tts-eng/resolve/main/config.json"} +) + +VITS_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/mms-tts-eng"]) + +VIVIT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "google/vivit-b-16x2-kinetics400": "https://huggingface.co/google/vivit-b-16x2-kinetics400/resolve/main/config.json" + } +) + +VIVIT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["google/vivit-b-16x2-kinetics400"]) + +WAV_2_VEC_2_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/wav2vec2-base-960h": "https://huggingface.co/facebook/wav2vec2-base-960h/resolve/main/config.json"} +) + +WAV_2_VEC_2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "facebook/wav2vec2-base-960h", + "facebook/wav2vec2-large-960h", + "facebook/wav2vec2-large-960h-lv60", + "facebook/wav2vec2-large-960h-lv60-self", + ] +) + +TF_WAV_2_VEC_2_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "facebook/wav2vec2-base-960h", + "facebook/wav2vec2-large-960h", + "facebook/wav2vec2-large-960h-lv60", + "facebook/wav2vec2-large-960h-lv60-self", + ] +) + +WAV2VEC2_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/w2v-bert-2.0": "https://huggingface.co/facebook/w2v-bert-2.0/resolve/main/config.json"} +) + +WAV2VEC2_BERT_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/w2v-bert-2.0"]) + +WAV2VEC2_CONFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/wav2vec2-conformer-rel-pos-large": "https://huggingface.co/facebook/wav2vec2-conformer-rel-pos-large/resolve/main/config.json" + } +) + +WAV2VEC2_CONFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/wav2vec2-conformer-rel-pos-large"]) + +WAVLM_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"microsoft/wavlm-base": "https://huggingface.co/microsoft/wavlm-base/resolve/main/config.json"} +) + +WAVLM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["microsoft/wavlm-base", "microsoft/wavlm-base-plus", "microsoft/wavlm-large"] +) + +WHISPER_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"openai/whisper-base": "https://huggingface.co/openai/whisper-base/resolve/main/config.json"} +) + +WHISPER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["openai/whisper-base"]) + +TF_WHISPER_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["openai/whisper-base"]) + +XCLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"microsoft/xclip-base-patch32": "https://huggingface.co/microsoft/xclip-base-patch32/resolve/main/config.json"} +) + +XCLIP_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/xclip-base-patch32"]) + +XGLM_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"facebook/xglm-564M": "https://huggingface.co/facebook/xglm-564M/resolve/main/config.json"} +) + +XGLM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/xglm-564M"]) + +TF_XGLM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/xglm-564M"]) + +XLM_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "FacebookAI/xlm-mlm-en-2048": "https://huggingface.co/FacebookAI/xlm-mlm-en-2048/resolve/main/config.json", + "FacebookAI/xlm-mlm-ende-1024": "https://huggingface.co/FacebookAI/xlm-mlm-ende-1024/resolve/main/config.json", + "FacebookAI/xlm-mlm-enfr-1024": "https://huggingface.co/FacebookAI/xlm-mlm-enfr-1024/resolve/main/config.json", + "FacebookAI/xlm-mlm-enro-1024": "https://huggingface.co/FacebookAI/xlm-mlm-enro-1024/resolve/main/config.json", + "FacebookAI/xlm-mlm-tlm-xnli15-1024": "https://huggingface.co/FacebookAI/xlm-mlm-tlm-xnli15-1024/resolve/main/config.json", + "FacebookAI/xlm-mlm-xnli15-1024": "https://huggingface.co/FacebookAI/xlm-mlm-xnli15-1024/resolve/main/config.json", + "FacebookAI/xlm-clm-enfr-1024": "https://huggingface.co/FacebookAI/xlm-clm-enfr-1024/resolve/main/config.json", + "FacebookAI/xlm-clm-ende-1024": "https://huggingface.co/FacebookAI/xlm-clm-ende-1024/resolve/main/config.json", + "FacebookAI/xlm-mlm-17-1280": "https://huggingface.co/FacebookAI/xlm-mlm-17-1280/resolve/main/config.json", + "FacebookAI/xlm-mlm-100-1280": "https://huggingface.co/FacebookAI/xlm-mlm-100-1280/resolve/main/config.json", + } +) + +XLM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "FacebookAI/xlm-mlm-en-2048", + "FacebookAI/xlm-mlm-ende-1024", + "FacebookAI/xlm-mlm-enfr-1024", + "FacebookAI/xlm-mlm-enro-1024", + "FacebookAI/xlm-mlm-tlm-xnli15-1024", + "FacebookAI/xlm-mlm-xnli15-1024", + "FacebookAI/xlm-clm-enfr-1024", + "FacebookAI/xlm-clm-ende-1024", + "FacebookAI/xlm-mlm-17-1280", + "FacebookAI/xlm-mlm-100-1280", + ] +) + +TF_XLM_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "FacebookAI/xlm-mlm-en-2048", + "FacebookAI/xlm-mlm-ende-1024", + "FacebookAI/xlm-mlm-enfr-1024", + "FacebookAI/xlm-mlm-enro-1024", + "FacebookAI/xlm-mlm-tlm-xnli15-1024", + "FacebookAI/xlm-mlm-xnli15-1024", + "FacebookAI/xlm-clm-enfr-1024", + "FacebookAI/xlm-clm-ende-1024", + "FacebookAI/xlm-mlm-17-1280", + "FacebookAI/xlm-mlm-100-1280", + ] +) + +XLM_PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "microsoft/xprophetnet-large-wiki100-cased": "https://huggingface.co/microsoft/xprophetnet-large-wiki100-cased/resolve/main/config.json" + } +) + +XLM_PROPHETNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["microsoft/xprophetnet-large-wiki100-cased"]) + +XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "FacebookAI/xlm-roberta-base": "https://huggingface.co/FacebookAI/xlm-roberta-base/resolve/main/config.json", + "FacebookAI/xlm-roberta-large": "https://huggingface.co/FacebookAI/xlm-roberta-large/resolve/main/config.json", + "FacebookAI/xlm-roberta-large-finetuned-conll02-dutch": "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll02-dutch/resolve/main/config.json", + "FacebookAI/xlm-roberta-large-finetuned-conll02-spanish": "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll02-spanish/resolve/main/config.json", + "FacebookAI/xlm-roberta-large-finetuned-conll03-english": "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-english/resolve/main/config.json", + "FacebookAI/xlm-roberta-large-finetuned-conll03-german": "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-german/resolve/main/config.json", + } +) + +XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "FacebookAI/xlm-roberta-base", + "FacebookAI/xlm-roberta-large", + "FacebookAI/xlm-roberta-large-finetuned-conll02-dutch", + "FacebookAI/xlm-roberta-large-finetuned-conll02-spanish", + "FacebookAI/xlm-roberta-large-finetuned-conll03-english", + "FacebookAI/xlm-roberta-large-finetuned-conll03-german", + ] +) + +TF_XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "FacebookAI/xlm-roberta-base", + "FacebookAI/xlm-roberta-large", + "joeddav/xlm-roberta-large-xnli", + "cardiffnlp/twitter-xlm-roberta-base-sentiment", + ] +) + +FLAX_XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + ["FacebookAI/xlm-roberta-base", "FacebookAI/xlm-roberta-large"] +) + +XLM_ROBERTA_XL_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/xlm-roberta-xl": "https://huggingface.co/facebook/xlm-roberta-xl/resolve/main/config.json", + "facebook/xlm-roberta-xxl": "https://huggingface.co/facebook/xlm-roberta-xxl/resolve/main/config.json", + } +) + +XLM_ROBERTA_XL_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["facebook/xlm-roberta-xl", "facebook/xlm-roberta-xxl"]) + +XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "xlnet/xlnet-base-cased": "https://huggingface.co/xlnet/xlnet-base-cased/resolve/main/config.json", + "xlnet/xlnet-large-cased": "https://huggingface.co/xlnet/xlnet-large-cased/resolve/main/config.json", + } +) + +XLNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["xlnet/xlnet-base-cased", "xlnet/xlnet-large-cased"]) + +TF_XLNET_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["xlnet/xlnet-base-cased", "xlnet/xlnet-large-cased"]) + +XMOD_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + { + "facebook/xmod-base": "https://huggingface.co/facebook/xmod-base/resolve/main/config.json", + "facebook/xmod-large-prenorm": "https://huggingface.co/facebook/xmod-large-prenorm/resolve/main/config.json", + "facebook/xmod-base-13-125k": "https://huggingface.co/facebook/xmod-base-13-125k/resolve/main/config.json", + "facebook/xmod-base-30-125k": "https://huggingface.co/facebook/xmod-base-30-125k/resolve/main/config.json", + "facebook/xmod-base-30-195k": "https://huggingface.co/facebook/xmod-base-30-195k/resolve/main/config.json", + "facebook/xmod-base-60-125k": "https://huggingface.co/facebook/xmod-base-60-125k/resolve/main/config.json", + "facebook/xmod-base-60-265k": "https://huggingface.co/facebook/xmod-base-60-265k/resolve/main/config.json", + "facebook/xmod-base-75-125k": "https://huggingface.co/facebook/xmod-base-75-125k/resolve/main/config.json", + "facebook/xmod-base-75-269k": "https://huggingface.co/facebook/xmod-base-75-269k/resolve/main/config.json", + } +) + +XMOD_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList( + [ + "facebook/xmod-base", + "facebook/xmod-large-prenorm", + "facebook/xmod-base-13-125k", + "facebook/xmod-base-30-125k", + "facebook/xmod-base-30-195k", + "facebook/xmod-base-60-125k", + "facebook/xmod-base-60-265k", + "facebook/xmod-base-75-125k", + "facebook/xmod-base-75-269k", + ] +) + +YOLOS_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"hustvl/yolos-small": "https://huggingface.co/hustvl/yolos-small/resolve/main/config.json"} +) + +YOLOS_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["hustvl/yolos-small"]) + +YOSO_PRETRAINED_CONFIG_ARCHIVE_MAP = DeprecatedDict( + {"uw-madison/yoso-4096": "https://huggingface.co/uw-madison/yoso-4096/resolve/main/config.json"} +) + +YOSO_PRETRAINED_MODEL_ARCHIVE_LIST = DeprecatedList(["uw-madison/yoso-4096"]) + + +CONFIG_ARCHIVE_MAP_MAPPING_NAMES = OrderedDict( + [ + # Add archive maps here) + ("albert", "ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("align", "ALIGN_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("altclip", "ALTCLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("audio-spectrogram-transformer", "AUDIO_SPECTROGRAM_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("autoformer", "AUTOFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("bark", "BARK_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("bart", "BART_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("beit", "BEIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("bert", "BERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("big_bird", "BIG_BIRD_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("bigbird_pegasus", "BIGBIRD_PEGASUS_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("biogpt", "BIOGPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("bit", "BIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("blenderbot", "BLENDERBOT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("blenderbot-small", "BLENDERBOT_SMALL_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("blip", "BLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("blip-2", "BLIP_2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("bloom", "BLOOM_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("bridgetower", "BRIDGETOWER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("bros", "BROS_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("camembert", "CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("canine", "CANINE_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("chinese_clip", "CHINESE_CLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("clap", "CLAP_PRETRAINED_MODEL_ARCHIVE_LIST"), + ("clip", "CLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("clipseg", "CLIPSEG_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("clvp", "CLVP_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("codegen", "CODEGEN_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("conditional_detr", "CONDITIONAL_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("convbert", "CONVBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("convnext", "CONVNEXT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("convnextv2", "CONVNEXTV2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("cpmant", "CPMANT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("ctrl", "CTRL_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("cvt", "CVT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("data2vec-audio", "DATA2VEC_AUDIO_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("data2vec-text", "DATA2VEC_TEXT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("data2vec-vision", "DATA2VEC_VISION_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("deberta", "DEBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("deberta-v2", "DEBERTA_V2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("deformable_detr", "DEFORMABLE_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("deit", "DEIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("depth_anything", "DEPTH_ANYTHING_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("deta", "DETA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("detr", "DETR_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("dinat", "DINAT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("dinov2", "DINOV2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("distilbert", "DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("donut-swin", "DONUT_SWIN_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("dpr", "DPR_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("dpt", "DPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("efficientformer", "EFFICIENTFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("efficientnet", "EFFICIENTNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("electra", "ELECTRA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("encodec", "ENCODEC_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("ernie", "ERNIE_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("ernie_m", "ERNIE_M_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("esm", "ESM_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("falcon", "FALCON_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("fastspeech2_conformer", "FASTSPEECH2_CONFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("flaubert", "FLAUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("flava", "FLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("fnet", "FNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("focalnet", "FOCALNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("fsmt", "FSMT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("funnel", "FUNNEL_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("fuyu", "FUYU_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("gemma", "GEMMA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("git", "GIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("glpn", "GLPN_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("gpt2", "GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("gpt_bigcode", "GPT_BIGCODE_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("gpt_neo", "GPT_NEO_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("gpt_neox", "GPT_NEOX_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("gpt_neox_japanese", "GPT_NEOX_JAPANESE_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("gptj", "GPTJ_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("gptsan-japanese", "GPTSAN_JAPANESE_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("graphormer", "GRAPHORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("groupvit", "GROUPVIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("hubert", "HUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("ibert", "IBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("idefics", "IDEFICS_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("imagegpt", "IMAGEGPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("informer", "INFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("instructblip", "INSTRUCTBLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("jukebox", "JUKEBOX_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("kosmos-2", "KOSMOS2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("layoutlm", "LAYOUTLM_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("layoutlmv2", "LAYOUTLMV2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("layoutlmv3", "LAYOUTLMV3_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("led", "LED_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("levit", "LEVIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("lilt", "LILT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("llama", "LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("llava", "LLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("longformer", "LONGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("longt5", "LONGT5_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("luke", "LUKE_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("lxmert", "LXMERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("m2m_100", "M2M_100_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mamba", "MAMBA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("markuplm", "MARKUPLM_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mask2former", "MASK2FORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("maskformer", "MASKFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mbart", "MBART_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mctct", "MCTCT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mega", "MEGA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("megatron-bert", "MEGATRON_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mgp-str", "MGP_STR_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mistral", "MISTRAL_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mixtral", "MIXTRAL_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mobilenet_v1", "MOBILENET_V1_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mobilenet_v2", "MOBILENET_V2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mobilevit", "MOBILEVIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mobilevitv2", "MOBILEVITV2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mpnet", "MPNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mpt", "MPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mra", "MRA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("musicgen", "MUSICGEN_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("mvp", "MVP_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("nat", "NAT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("nezha", "NEZHA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("nllb-moe", "NLLB_MOE_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("nystromformer", "NYSTROMFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("oneformer", "ONEFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("open-llama", "OPEN_LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("openai-gpt", "OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("opt", "OPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("owlv2", "OWLV2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("owlvit", "OWLVIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("patchtsmixer", "PATCHTSMIXER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("patchtst", "PATCHTST_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("pegasus", "PEGASUS_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("pegasus_x", "PEGASUS_X_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("perceiver", "PERCEIVER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("persimmon", "PERSIMMON_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("phi", "PHI_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("pix2struct", "PIX2STRUCT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("plbart", "PLBART_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("poolformer", "POOLFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("pop2piano", "POP2PIANO_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("prophetnet", "PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("pvt", "PVT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("qdqbert", "QDQBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("qwen2", "QWEN2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("realm", "REALM_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("regnet", "REGNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("rembert", "REMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("resnet", "RESNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("retribert", "RETRIBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("roberta", "ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("roberta-prelayernorm", "ROBERTA_PRELAYERNORM_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("roc_bert", "ROC_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("roformer", "ROFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("rwkv", "RWKV_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("sam", "SAM_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("seamless_m4t", "SEAMLESS_M4T_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("seamless_m4t_v2", "SEAMLESS_M4T_V2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("segformer", "SEGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("seggpt", "SEGGPT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("sew", "SEW_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("sew-d", "SEW_D_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("siglip", "SIGLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("speech_to_text", "SPEECH_TO_TEXT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("speech_to_text_2", "SPEECH_TO_TEXT_2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("speecht5", "SPEECHT5_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("splinter", "SPLINTER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("squeezebert", "SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("stablelm", "STABLELM_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("starcoder2", "STARCODER2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("swiftformer", "SWIFTFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("swin", "SWIN_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("swin2sr", "SWIN2SR_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("swinv2", "SWINV2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("switch_transformers", "SWITCH_TRANSFORMERS_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("t5", "T5_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("table-transformer", "TABLE_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("tapas", "TAPAS_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("time_series_transformer", "TIME_SERIES_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("timesformer", "TIMESFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("transfo-xl", "TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("tvlt", "TVLT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("tvp", "TVP_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("udop", "UDOP_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("unispeech", "UNISPEECH_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("unispeech-sat", "UNISPEECH_SAT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("univnet", "UNIVNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("van", "VAN_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("videomae", "VIDEOMAE_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("vilt", "VILT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("vipllava", "VIPLLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("visual_bert", "VISUAL_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("vit", "VIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("vit_hybrid", "VIT_HYBRID_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("vit_mae", "VIT_MAE_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("vit_msn", "VIT_MSN_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("vitdet", "VITDET_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("vitmatte", "VITMATTE_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("vits", "VITS_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("vivit", "VIVIT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("wav2vec2", "WAV_2_VEC_2_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("wav2vec2-bert", "WAV2VEC2_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("wav2vec2-conformer", "WAV2VEC2_CONFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("whisper", "WHISPER_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("xclip", "XCLIP_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("xglm", "XGLM_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("xlm", "XLM_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("xlm-prophetnet", "XLM_PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("xlm-roberta", "XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("xlnet", "XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("xmod", "XMOD_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("yolos", "YOLOS_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ("yoso", "YOSO_PRETRAINED_CONFIG_ARCHIVE_MAP"), + ] +) diff --git a/src/transformers/models/deprecated/mctct/configuration_mctct.py b/src/transformers/models/deprecated/mctct/configuration_mctct.py index 9d4eab0d3f..6546b18eab 100644 --- a/src/transformers/models/deprecated/mctct/configuration_mctct.py +++ b/src/transformers/models/deprecated/mctct/configuration_mctct.py @@ -20,10 +20,8 @@ from ....utils import logging logger = logging.get_logger(__name__) -MCTCT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "speechbrain/m-ctc-t-large": "https://huggingface.co/speechbrain/m-ctc-t-large/resolve/main/config.json", - # See all M-CTC-T models at https://huggingface.co/models?filter=mctct -} + +from .._archive_maps import MCTCT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MCTCTConfig(PretrainedConfig): diff --git a/src/transformers/models/deprecated/mctct/modeling_mctct.py b/src/transformers/models/deprecated/mctct/modeling_mctct.py index cb3186c9dd..2d9ef6cf72 100755 --- a/src/transformers/models/deprecated/mctct/modeling_mctct.py +++ b/src/transformers/models/deprecated/mctct/modeling_mctct.py @@ -52,10 +52,7 @@ _CTC_EXPECTED_OUTPUT = '"Mr. Quilter is the apostle of the middle classes, and w _CTC_EXPECTED_LOSS = 1885.65 -MCTCT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "speechbrain/m-ctc-t-large", - # See all M-CTC-T models at https://huggingface.co/models?filter=mctct -] +from .._archive_maps import MCTCT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class MCTCTConv1dSubsampler(nn.Module): diff --git a/src/transformers/models/deprecated/open_llama/configuration_open_llama.py b/src/transformers/models/deprecated/open_llama/configuration_open_llama.py index 5786abac85..6b6fc04a46 100644 --- a/src/transformers/models/deprecated/open_llama/configuration_open_llama.py +++ b/src/transformers/models/deprecated/open_llama/configuration_open_llama.py @@ -25,9 +25,8 @@ from ....utils import logging logger = logging.get_logger(__name__) -OPEN_LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "s-JoL/Open-Llama-V1": "https://huggingface.co/s-JoL/Open-Llama-V1/blob/main/config.json", -} + +from .._archive_maps import OPEN_LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class OpenLlamaConfig(PretrainedConfig): diff --git a/src/transformers/models/deprecated/retribert/configuration_retribert.py b/src/transformers/models/deprecated/retribert/configuration_retribert.py index 3861b9c90f..c188c7347a 100644 --- a/src/transformers/models/deprecated/retribert/configuration_retribert.py +++ b/src/transformers/models/deprecated/retribert/configuration_retribert.py @@ -20,12 +20,7 @@ from ....utils import logging logger = logging.get_logger(__name__) -# TODO: upload to AWS -RETRIBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "yjernite/retribert-base-uncased": ( - "https://huggingface.co/yjernite/retribert-base-uncased/resolve/main/config.json" - ), -} +from .._archive_maps import RETRIBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class RetriBertConfig(PretrainedConfig): diff --git a/src/transformers/models/deprecated/retribert/modeling_retribert.py b/src/transformers/models/deprecated/retribert/modeling_retribert.py index 00d47bce51..7dba8a276e 100644 --- a/src/transformers/models/deprecated/retribert/modeling_retribert.py +++ b/src/transformers/models/deprecated/retribert/modeling_retribert.py @@ -32,10 +32,8 @@ from .configuration_retribert import RetriBertConfig logger = logging.get_logger(__name__) -RETRIBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "yjernite/retribert-base-uncased", - # See all RetriBert models at https://huggingface.co/models?filter=retribert -] + +from .._archive_maps import RETRIBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # INTERFACE FOR ENCODER AND TASK SPECIFIC MODEL # diff --git a/src/transformers/models/deprecated/retribert/tokenization_retribert.py b/src/transformers/models/deprecated/retribert/tokenization_retribert.py index d0904e3c93..c991f39722 100644 --- a/src/transformers/models/deprecated/retribert/tokenization_retribert.py +++ b/src/transformers/models/deprecated/retribert/tokenization_retribert.py @@ -27,23 +27,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "yjernite/retribert-base-uncased": ( - "https://huggingface.co/yjernite/retribert-base-uncased/resolve/main/vocab.txt" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "yjernite/retribert-base-uncased": 512, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "yjernite/retribert-base-uncased": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert.load_vocab def load_vocab(vocab_file): @@ -111,9 +94,6 @@ class RetriBertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION model_input_names = ["input_ids", "attention_mask"] # Copied from transformers.models.bert.tokenization_bert.BertTokenizer.__init__ diff --git a/src/transformers/models/deprecated/retribert/tokenization_retribert_fast.py b/src/transformers/models/deprecated/retribert/tokenization_retribert_fast.py index 07f7964b9f..97fbfc07d3 100644 --- a/src/transformers/models/deprecated/retribert/tokenization_retribert_fast.py +++ b/src/transformers/models/deprecated/retribert/tokenization_retribert_fast.py @@ -28,28 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "yjernite/retribert-base-uncased": ( - "https://huggingface.co/yjernite/retribert-base-uncased/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "yjernite/retribert-base-uncased": ( - "https://huggingface.co/yjernite/retribert-base-uncased/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "yjernite/retribert-base-uncased": 512, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "yjernite/retribert-base-uncased": {"do_lower_case": True}, -} - class RetriBertTokenizerFast(PreTrainedTokenizerFast): r""" @@ -95,9 +73,6 @@ class RetriBertTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION slow_tokenizer_class = RetriBertTokenizer model_input_names = ["input_ids", "attention_mask"] diff --git a/src/transformers/models/deprecated/tapex/tokenization_tapex.py b/src/transformers/models/deprecated/tapex/tokenization_tapex.py index a5ee093c56..cd3d353b52 100644 --- a/src/transformers/models/deprecated/tapex/tokenization_tapex.py +++ b/src/transformers/models/deprecated/tapex/tokenization_tapex.py @@ -36,23 +36,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/tapex-base": "https://huggingface.co/microsoft/tapex-base/resolve/main/vocab.json", - }, - "merges_file": { - "microsoft/tapex-base": "https://huggingface.co/microsoft/tapex-base/resolve/main/merges.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/tapex-base": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/tapex-base": {"do_lower_case": True}, -} - class TapexTruncationStrategy(ExplicitEnum): """ @@ -264,9 +247,6 @@ class TapexTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/deprecated/trajectory_transformer/configuration_trajectory_transformer.py b/src/transformers/models/deprecated/trajectory_transformer/configuration_trajectory_transformer.py index cfad075c6a..eccb71fcc4 100644 --- a/src/transformers/models/deprecated/trajectory_transformer/configuration_trajectory_transformer.py +++ b/src/transformers/models/deprecated/trajectory_transformer/configuration_trajectory_transformer.py @@ -20,12 +20,8 @@ from ....utils import logging logger = logging.get_logger(__name__) -TRAJECTORY_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "CarlCochet/trajectory-transformer-halfcheetah-medium-v2": ( - "https://huggingface.co/CarlCochet/trajectory-transformer-halfcheetah-medium-v2/resolve/main/config.json" - ), - # See all TrajectoryTransformer models at https://huggingface.co/models?filter=trajectory_transformer -} + +from .._archive_maps import TRAJECTORY_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class TrajectoryTransformerConfig(PretrainedConfig): diff --git a/src/transformers/models/deprecated/trajectory_transformer/modeling_trajectory_transformer.py b/src/transformers/models/deprecated/trajectory_transformer/modeling_trajectory_transformer.py index 40c08e4d1d..5c98aa45dc 100644 --- a/src/transformers/models/deprecated/trajectory_transformer/modeling_trajectory_transformer.py +++ b/src/transformers/models/deprecated/trajectory_transformer/modeling_trajectory_transformer.py @@ -41,10 +41,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "CarlCochet/trajectory-transformer-halfcheetah-medium-v2" _CONFIG_FOR_DOC = "TrajectoryTransformerConfig" -TRAJECTORY_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "CarlCochet/trajectory-transformer-halfcheetah-medium-v2", - # See all TrajectoryTransformer models at https://huggingface.co/models?filter=trajectory_transformer -] + +from .._archive_maps import TRAJECTORY_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_trajectory_transformer(model, config, tf_checkpoint_path): diff --git a/src/transformers/models/deprecated/transfo_xl/configuration_transfo_xl.py b/src/transformers/models/deprecated/transfo_xl/configuration_transfo_xl.py index f7d5f2f87f..50bf94ae7e 100644 --- a/src/transformers/models/deprecated/transfo_xl/configuration_transfo_xl.py +++ b/src/transformers/models/deprecated/transfo_xl/configuration_transfo_xl.py @@ -21,9 +21,8 @@ from ....utils import logging logger = logging.get_logger(__name__) -TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "transfo-xl/transfo-xl-wt103": "https://huggingface.co/transfo-xl/transfo-xl-wt103/resolve/main/config.json", -} + +from .._archive_maps import TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class TransfoXLConfig(PretrainedConfig): diff --git a/src/transformers/models/deprecated/transfo_xl/modeling_tf_transfo_xl.py b/src/transformers/models/deprecated/transfo_xl/modeling_tf_transfo_xl.py index ab2725df0c..27200a5d63 100644 --- a/src/transformers/models/deprecated/transfo_xl/modeling_tf_transfo_xl.py +++ b/src/transformers/models/deprecated/transfo_xl/modeling_tf_transfo_xl.py @@ -51,10 +51,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "transfo-xl/transfo-xl-wt103" _CONFIG_FOR_DOC = "TransfoXLConfig" -TF_TRANSFO_XL_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "transfo-xl/transfo-xl-wt103", - # See all Transformer XL models at https://huggingface.co/models?filter=transfo-xl -] + +from .._archive_maps import TF_TRANSFO_XL_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFPositionalEmbedding(keras.layers.Layer): diff --git a/src/transformers/models/deprecated/transfo_xl/modeling_transfo_xl.py b/src/transformers/models/deprecated/transfo_xl/modeling_transfo_xl.py index 1b8f222f50..897a3899c7 100644 --- a/src/transformers/models/deprecated/transfo_xl/modeling_transfo_xl.py +++ b/src/transformers/models/deprecated/transfo_xl/modeling_transfo_xl.py @@ -42,10 +42,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "transfo-xl/transfo-xl-wt103" _CONFIG_FOR_DOC = "TransfoXLConfig" -TRANSFO_XL_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "transfo-xl/transfo-xl-wt103", - # See all Transformer XL models at https://huggingface.co/models?filter=transfo-xl -] + +from .._archive_maps import TRANSFO_XL_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def build_tf_to_pytorch_map(model, config): diff --git a/src/transformers/models/deprecated/transfo_xl/tokenization_transfo_xl.py b/src/transformers/models/deprecated/transfo_xl/tokenization_transfo_xl.py index 12d360076f..7290a7a83b 100644 --- a/src/transformers/models/deprecated/transfo_xl/tokenization_transfo_xl.py +++ b/src/transformers/models/deprecated/transfo_xl/tokenization_transfo_xl.py @@ -55,15 +55,6 @@ VOCAB_FILES_NAMES = { "vocab_file": "vocab.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "pretrained_vocab_file": { - "transfo-xl/transfo-xl-wt103": "https://huggingface.co/transfo-xl/transfo-xl-wt103/resolve/main/vocab.pkl", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "transfo-xl/transfo-xl-wt103": None, -} PRETRAINED_CORPUS_ARCHIVE_MAP = { "transfo-xl/transfo-xl-wt103": "https://huggingface.co/transfo-xl/transfo-xl-wt103/resolve/main/corpus.bin", @@ -162,8 +153,6 @@ class TransfoXLTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids"] def __init__( diff --git a/src/transformers/models/deprecated/van/configuration_van.py b/src/transformers/models/deprecated/van/configuration_van.py index 85f228193c..f58d021569 100644 --- a/src/transformers/models/deprecated/van/configuration_van.py +++ b/src/transformers/models/deprecated/van/configuration_van.py @@ -20,11 +20,8 @@ from ....utils import logging logger = logging.get_logger(__name__) -VAN_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "Visual-Attention-Network/van-base": ( - "https://huggingface.co/Visual-Attention-Network/van-base/blob/main/config.json" - ), -} + +from .._archive_maps import VAN_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class VanConfig(PretrainedConfig): diff --git a/src/transformers/models/deprecated/van/modeling_van.py b/src/transformers/models/deprecated/van/modeling_van.py index e0f88467e1..6fa2b73482 100644 --- a/src/transformers/models/deprecated/van/modeling_van.py +++ b/src/transformers/models/deprecated/van/modeling_van.py @@ -47,10 +47,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 512, 7, 7] _IMAGE_CLASS_CHECKPOINT = "Visual-Attention-Network/van-base" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -VAN_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Visual-Attention-Network/van-base", - # See all VAN models at https://huggingface.co/models?filter=van -] + +from .._archive_maps import VAN_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.convnext.modeling_convnext.drop_path diff --git a/src/transformers/models/depth_anything/configuration_depth_anything.py b/src/transformers/models/depth_anything/configuration_depth_anything.py index 7fa7745c32..3d58a3874e 100644 --- a/src/transformers/models/depth_anything/configuration_depth_anything.py +++ b/src/transformers/models/depth_anything/configuration_depth_anything.py @@ -23,9 +23,8 @@ from ..auto.configuration_auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -DEPTH_ANYTHING_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "LiheYoung/depth-anything-small-hf": "https://huggingface.co/LiheYoung/depth-anything-small-hf/resolve/main/config.json", -} + +from ..deprecated._archive_maps import DEPTH_ANYTHING_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DepthAnythingConfig(PretrainedConfig): diff --git a/src/transformers/models/depth_anything/modeling_depth_anything.py b/src/transformers/models/depth_anything/modeling_depth_anything.py index 6497759f17..788b0d9113 100644 --- a/src/transformers/models/depth_anything/modeling_depth_anything.py +++ b/src/transformers/models/depth_anything/modeling_depth_anything.py @@ -38,10 +38,8 @@ logger = logging.get_logger(__name__) # General docstring _CONFIG_FOR_DOC = "DepthAnythingConfig" -DEPTH_ANYTHING_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "LiheYoung/depth-anything-small-hf", - # See all Depth Anything models at https://huggingface.co/models?filter=depth_anything -] + +from ..deprecated._archive_maps import DEPTH_ANYTHING_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 DEPTH_ANYTHING_START_DOCSTRING = r""" diff --git a/src/transformers/models/deta/configuration_deta.py b/src/transformers/models/deta/configuration_deta.py index d5a3709b91..1604bc56e6 100644 --- a/src/transformers/models/deta/configuration_deta.py +++ b/src/transformers/models/deta/configuration_deta.py @@ -22,9 +22,8 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -DETA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "ut/deta": "https://huggingface.co/ut/deta/resolve/main/config.json", -} + +from ..deprecated._archive_maps import DETA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DetaConfig(PretrainedConfig): diff --git a/src/transformers/models/deta/modeling_deta.py b/src/transformers/models/deta/modeling_deta.py index 0c2dfdf3b0..35d9b67d2f 100644 --- a/src/transformers/models/deta/modeling_deta.py +++ b/src/transformers/models/deta/modeling_deta.py @@ -151,10 +151,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "DetaConfig" _CHECKPOINT_FOR_DOC = "jozhang97/deta-swin-large-o365" -DETA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "jozhang97/deta-swin-large-o365", - # See all DETA models at https://huggingface.co/models?filter=deta -] + +from ..deprecated._archive_maps import DETA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/detr/configuration_detr.py b/src/transformers/models/detr/configuration_detr.py index f13c1ef09a..9b9b5afacd 100644 --- a/src/transformers/models/detr/configuration_detr.py +++ b/src/transformers/models/detr/configuration_detr.py @@ -27,10 +27,8 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -DETR_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/detr-resnet-50": "https://huggingface.co/facebook/detr-resnet-50/resolve/main/config.json", - # See all DETR models at https://huggingface.co/models?filter=detr -} + +from ..deprecated._archive_maps import DETR_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DetrConfig(PretrainedConfig): diff --git a/src/transformers/models/detr/modeling_detr.py b/src/transformers/models/detr/modeling_detr.py index 1e548b61d3..d7fcdfc5bc 100644 --- a/src/transformers/models/detr/modeling_detr.py +++ b/src/transformers/models/detr/modeling_detr.py @@ -60,10 +60,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "DetrConfig" _CHECKPOINT_FOR_DOC = "facebook/detr-resnet-50" -DETR_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/detr-resnet-50", - # See all DETR models at https://huggingface.co/models?filter=detr -] + +from ..deprecated._archive_maps import DETR_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/dinat/configuration_dinat.py b/src/transformers/models/dinat/configuration_dinat.py index 83c3227f66..4bd38c7385 100644 --- a/src/transformers/models/dinat/configuration_dinat.py +++ b/src/transformers/models/dinat/configuration_dinat.py @@ -21,10 +21,8 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -DINAT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "shi-labs/dinat-mini-in1k-224": "https://huggingface.co/shi-labs/dinat-mini-in1k-224/resolve/main/config.json", - # See all Dinat models at https://huggingface.co/models?filter=dinat -} + +from ..deprecated._archive_maps import DINAT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DinatConfig(BackboneConfigMixin, PretrainedConfig): diff --git a/src/transformers/models/dinat/modeling_dinat.py b/src/transformers/models/dinat/modeling_dinat.py index 71470efece..72bf6d1170 100644 --- a/src/transformers/models/dinat/modeling_dinat.py +++ b/src/transformers/models/dinat/modeling_dinat.py @@ -68,10 +68,8 @@ _IMAGE_CLASS_CHECKPOINT = "shi-labs/dinat-mini-in1k-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -DINAT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "shi-labs/dinat-mini-in1k-224", - # See all Dinat models at https://huggingface.co/models?filter=dinat -] +from ..deprecated._archive_maps import DINAT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + # drop_path and DinatDropPath are from the timm library. diff --git a/src/transformers/models/dinov2/configuration_dinov2.py b/src/transformers/models/dinov2/configuration_dinov2.py index 037f889ebf..b5fe872a70 100644 --- a/src/transformers/models/dinov2/configuration_dinov2.py +++ b/src/transformers/models/dinov2/configuration_dinov2.py @@ -27,9 +27,8 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -DINOV2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/dinov2-base": "https://huggingface.co/facebook/dinov2-base/resolve/main/config.json", -} + +from ..deprecated._archive_maps import DINOV2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Dinov2Config(BackboneConfigMixin, PretrainedConfig): diff --git a/src/transformers/models/dinov2/modeling_dinov2.py b/src/transformers/models/dinov2/modeling_dinov2.py index accdf0a9b2..c25022f6ec 100644 --- a/src/transformers/models/dinov2/modeling_dinov2.py +++ b/src/transformers/models/dinov2/modeling_dinov2.py @@ -58,10 +58,7 @@ _IMAGE_CLASS_CHECKPOINT = "facebook/dinov2-small-imagenet1k-1-layer" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -DINOV2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/dinov2-base", - # See all DINOv2 models at https://huggingface.co/models?filter=dinov2 -] +from ..deprecated._archive_maps import DINOV2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class Dinov2Embeddings(nn.Module): diff --git a/src/transformers/models/distilbert/configuration_distilbert.py b/src/transformers/models/distilbert/configuration_distilbert.py index 97b5b7c869..5f6b004dc0 100644 --- a/src/transformers/models/distilbert/configuration_distilbert.py +++ b/src/transformers/models/distilbert/configuration_distilbert.py @@ -23,23 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "distilbert-base-uncased": "https://huggingface.co/distilbert-base-uncased/resolve/main/config.json", - "distilbert-base-uncased-distilled-squad": ( - "https://huggingface.co/distilbert-base-uncased-distilled-squad/resolve/main/config.json" - ), - "distilbert-base-cased": "https://huggingface.co/distilbert-base-cased/resolve/main/config.json", - "distilbert-base-cased-distilled-squad": ( - "https://huggingface.co/distilbert-base-cased-distilled-squad/resolve/main/config.json" - ), - "distilbert-base-german-cased": "https://huggingface.co/distilbert-base-german-cased/resolve/main/config.json", - "distilbert-base-multilingual-cased": ( - "https://huggingface.co/distilbert-base-multilingual-cased/resolve/main/config.json" - ), - "distilbert-base-uncased-finetuned-sst-2-english": ( - "https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DistilBertConfig(PretrainedConfig): diff --git a/src/transformers/models/distilbert/modeling_distilbert.py b/src/transformers/models/distilbert/modeling_distilbert.py index 023b4dc13a..d33ffc8844 100755 --- a/src/transformers/models/distilbert/modeling_distilbert.py +++ b/src/transformers/models/distilbert/modeling_distilbert.py @@ -62,16 +62,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "distilbert-base-uncased" _CONFIG_FOR_DOC = "DistilBertConfig" -DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "distilbert-base-uncased", - "distilbert-base-uncased-distilled-squad", - "distilbert-base-cased", - "distilbert-base-cased-distilled-squad", - "distilbert-base-german-cased", - "distilbert-base-multilingual-cased", - "distilbert-base-uncased-finetuned-sst-2-english", - # See all DistilBERT models at https://huggingface.co/models?filter=distilbert -] + +from ..deprecated._archive_maps import DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # UTILS AND BUILDING BLOCKS OF THE ARCHITECTURE # diff --git a/src/transformers/models/distilbert/modeling_tf_distilbert.py b/src/transformers/models/distilbert/modeling_tf_distilbert.py index 39fd470597..c41deac3f2 100644 --- a/src/transformers/models/distilbert/modeling_tf_distilbert.py +++ b/src/transformers/models/distilbert/modeling_tf_distilbert.py @@ -62,15 +62,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "distilbert-base-uncased" _CONFIG_FOR_DOC = "DistilBertConfig" -TF_DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "distilbert-base-uncased", - "distilbert-base-uncased-distilled-squad", - "distilbert-base-cased", - "distilbert-base-cased-distilled-squad", - "distilbert-base-multilingual-cased", - "distilbert-base-uncased-finetuned-sst-2-english", - # See all DistilBERT models at https://huggingface.co/models?filter=distilbert -] + +from ..deprecated._archive_maps import TF_DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFEmbeddings(keras.layers.Layer): diff --git a/src/transformers/models/distilbert/tokenization_distilbert.py b/src/transformers/models/distilbert/tokenization_distilbert.py index 014c41d124..ff8854ba3d 100644 --- a/src/transformers/models/distilbert/tokenization_distilbert.py +++ b/src/transformers/models/distilbert/tokenization_distilbert.py @@ -27,42 +27,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "distilbert-base-uncased": "https://huggingface.co/distilbert-base-uncased/resolve/main/vocab.txt", - "distilbert-base-uncased-distilled-squad": ( - "https://huggingface.co/distilbert-base-uncased-distilled-squad/resolve/main/vocab.txt" - ), - "distilbert-base-cased": "https://huggingface.co/distilbert-base-cased/resolve/main/vocab.txt", - "distilbert-base-cased-distilled-squad": ( - "https://huggingface.co/distilbert-base-cased-distilled-squad/resolve/main/vocab.txt" - ), - "distilbert-base-german-cased": "https://huggingface.co/distilbert-base-german-cased/resolve/main/vocab.txt", - "distilbert-base-multilingual-cased": ( - "https://huggingface.co/distilbert-base-multilingual-cased/resolve/main/vocab.txt" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "distilbert-base-uncased": 512, - "distilbert-base-uncased-distilled-squad": 512, - "distilbert-base-cased": 512, - "distilbert-base-cased-distilled-squad": 512, - "distilbert-base-german-cased": 512, - "distilbert-base-multilingual-cased": 512, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "distilbert-base-uncased": {"do_lower_case": True}, - "distilbert-base-uncased-distilled-squad": {"do_lower_case": True}, - "distilbert-base-cased": {"do_lower_case": False}, - "distilbert-base-cased-distilled-squad": {"do_lower_case": False}, - "distilbert-base-german-cased": {"do_lower_case": False}, - "distilbert-base-multilingual-cased": {"do_lower_case": False}, -} - # Copied from transformers.models.bert.tokenization_bert.load_vocab def load_vocab(vocab_file): @@ -129,9 +93,6 @@ class DistilBertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/distilbert/tokenization_distilbert_fast.py b/src/transformers/models/distilbert/tokenization_distilbert_fast.py index adb90f857d..f1d69a27d6 100644 --- a/src/transformers/models/distilbert/tokenization_distilbert_fast.py +++ b/src/transformers/models/distilbert/tokenization_distilbert_fast.py @@ -28,58 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "distilbert-base-uncased": "https://huggingface.co/distilbert-base-uncased/resolve/main/vocab.txt", - "distilbert-base-uncased-distilled-squad": ( - "https://huggingface.co/distilbert-base-uncased-distilled-squad/resolve/main/vocab.txt" - ), - "distilbert-base-cased": "https://huggingface.co/distilbert-base-cased/resolve/main/vocab.txt", - "distilbert-base-cased-distilled-squad": ( - "https://huggingface.co/distilbert-base-cased-distilled-squad/resolve/main/vocab.txt" - ), - "distilbert-base-german-cased": "https://huggingface.co/distilbert-base-german-cased/resolve/main/vocab.txt", - "distilbert-base-multilingual-cased": ( - "https://huggingface.co/distilbert-base-multilingual-cased/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "distilbert-base-uncased": "https://huggingface.co/distilbert-base-uncased/resolve/main/tokenizer.json", - "distilbert-base-uncased-distilled-squad": ( - "https://huggingface.co/distilbert-base-uncased-distilled-squad/resolve/main/tokenizer.json" - ), - "distilbert-base-cased": "https://huggingface.co/distilbert-base-cased/resolve/main/tokenizer.json", - "distilbert-base-cased-distilled-squad": ( - "https://huggingface.co/distilbert-base-cased-distilled-squad/resolve/main/tokenizer.json" - ), - "distilbert-base-german-cased": ( - "https://huggingface.co/distilbert-base-german-cased/resolve/main/tokenizer.json" - ), - "distilbert-base-multilingual-cased": ( - "https://huggingface.co/distilbert-base-multilingual-cased/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "distilbert-base-uncased": 512, - "distilbert-base-uncased-distilled-squad": 512, - "distilbert-base-cased": 512, - "distilbert-base-cased-distilled-squad": 512, - "distilbert-base-german-cased": 512, - "distilbert-base-multilingual-cased": 512, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "distilbert-base-uncased": {"do_lower_case": True}, - "distilbert-base-uncased-distilled-squad": {"do_lower_case": True}, - "distilbert-base-cased": {"do_lower_case": False}, - "distilbert-base-cased-distilled-squad": {"do_lower_case": False}, - "distilbert-base-german-cased": {"do_lower_case": False}, - "distilbert-base-multilingual-cased": {"do_lower_case": False}, -} - class DistilBertTokenizerFast(PreTrainedTokenizerFast): r""" @@ -122,9 +70,6 @@ class DistilBertTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = DistilBertTokenizer diff --git a/src/transformers/models/donut/configuration_donut_swin.py b/src/transformers/models/donut/configuration_donut_swin.py index 9de3181b55..e57ddb255a 100644 --- a/src/transformers/models/donut/configuration_donut_swin.py +++ b/src/transformers/models/donut/configuration_donut_swin.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -DONUT_SWIN_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "naver-clova-ix/donut-base": "https://huggingface.co/naver-clova-ix/donut-base/resolve/main/config.json", - # See all Donut models at https://huggingface.co/models?filter=donut-swin -} + +from ..deprecated._archive_maps import DONUT_SWIN_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DonutSwinConfig(PretrainedConfig): diff --git a/src/transformers/models/donut/modeling_donut_swin.py b/src/transformers/models/donut/modeling_donut_swin.py index ed79b8ef8e..b2aa8d61b1 100644 --- a/src/transformers/models/donut/modeling_donut_swin.py +++ b/src/transformers/models/donut/modeling_donut_swin.py @@ -48,10 +48,8 @@ _CONFIG_FOR_DOC = "DonutSwinConfig" _CHECKPOINT_FOR_DOC = "https://huggingface.co/naver-clova-ix/donut-base" _EXPECTED_OUTPUT_SHAPE = [1, 49, 768] -DONUT_SWIN_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "naver-clova-ix/donut-base", - # See all Donut Swin models at https://huggingface.co/models?filter=donut -] + +from ..deprecated._archive_maps import DONUT_SWIN_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/dpr/configuration_dpr.py b/src/transformers/models/dpr/configuration_dpr.py index 3b6785c6b5..74ac90a4be 100644 --- a/src/transformers/models/dpr/configuration_dpr.py +++ b/src/transformers/models/dpr/configuration_dpr.py @@ -20,26 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -DPR_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/dpr-ctx_encoder-single-nq-base": ( - "https://huggingface.co/facebook/dpr-ctx_encoder-single-nq-base/resolve/main/config.json" - ), - "facebook/dpr-question_encoder-single-nq-base": ( - "https://huggingface.co/facebook/dpr-question_encoder-single-nq-base/resolve/main/config.json" - ), - "facebook/dpr-reader-single-nq-base": ( - "https://huggingface.co/facebook/dpr-reader-single-nq-base/resolve/main/config.json" - ), - "facebook/dpr-ctx_encoder-multiset-base": ( - "https://huggingface.co/facebook/dpr-ctx_encoder-multiset-base/resolve/main/config.json" - ), - "facebook/dpr-question_encoder-multiset-base": ( - "https://huggingface.co/facebook/dpr-question_encoder-multiset-base/resolve/main/config.json" - ), - "facebook/dpr-reader-multiset-base": ( - "https://huggingface.co/facebook/dpr-reader-multiset-base/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import DPR_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DPRConfig(PretrainedConfig): diff --git a/src/transformers/models/dpr/modeling_dpr.py b/src/transformers/models/dpr/modeling_dpr.py index 1071a42d81..0a45ec7520 100644 --- a/src/transformers/models/dpr/modeling_dpr.py +++ b/src/transformers/models/dpr/modeling_dpr.py @@ -39,18 +39,12 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "DPRConfig" _CHECKPOINT_FOR_DOC = "facebook/dpr-ctx_encoder-single-nq-base" -DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/dpr-ctx_encoder-single-nq-base", - "facebook/dpr-ctx_encoder-multiset-base", -] -DPR_QUESTION_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/dpr-question_encoder-single-nq-base", - "facebook/dpr-question_encoder-multiset-base", -] -DPR_READER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/dpr-reader-single-nq-base", - "facebook/dpr-reader-multiset-base", -] + +from ..deprecated._archive_maps import ( # noqa: F401, E402 + DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST, # noqa: F401, E402 + DPR_QUESTION_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST, # noqa: F401, E402 + DPR_READER_PRETRAINED_MODEL_ARCHIVE_LIST, # noqa: F401, E402 +) ########## diff --git a/src/transformers/models/dpr/modeling_tf_dpr.py b/src/transformers/models/dpr/modeling_tf_dpr.py index 0a6aa47640..e8cb1464f7 100644 --- a/src/transformers/models/dpr/modeling_tf_dpr.py +++ b/src/transformers/models/dpr/modeling_tf_dpr.py @@ -39,18 +39,12 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "DPRConfig" -TF_DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/dpr-ctx_encoder-single-nq-base", - "facebook/dpr-ctx_encoder-multiset-base", -] -TF_DPR_QUESTION_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/dpr-question_encoder-single-nq-base", - "facebook/dpr-question_encoder-multiset-base", -] -TF_DPR_READER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/dpr-reader-single-nq-base", - "facebook/dpr-reader-multiset-base", -] + +from ..deprecated._archive_maps import ( # noqa: F401, E402 + TF_DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST, # noqa: F401, E402 + TF_DPR_QUESTION_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST, # noqa: F401, E402 + TF_DPR_READER_PRETRAINED_MODEL_ARCHIVE_LIST, # noqa: F401, E402 +) ########## diff --git a/src/transformers/models/dpr/tokenization_dpr.py b/src/transformers/models/dpr/tokenization_dpr.py index b2ae84addc..1362047ce2 100644 --- a/src/transformers/models/dpr/tokenization_dpr.py +++ b/src/transformers/models/dpr/tokenization_dpr.py @@ -27,88 +27,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -CONTEXT_ENCODER_PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/dpr-ctx_encoder-single-nq-base": ( - "https://huggingface.co/facebook/dpr-ctx_encoder-single-nq-base/resolve/main/vocab.txt" - ), - "facebook/dpr-ctx_encoder-multiset-base": ( - "https://huggingface.co/facebook/dpr-ctx_encoder-multiset-base/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "facebook/dpr-ctx_encoder-single-nq-base": ( - "https://huggingface.co/facebook/dpr-ctx_encoder-single-nq-base/resolve/main/tokenizer.json" - ), - "facebook/dpr-ctx_encoder-multiset-base": ( - "https://huggingface.co/facebook/dpr-ctx_encoder-multiset-base/resolve/main/tokenizer.json" - ), - }, -} -QUESTION_ENCODER_PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/dpr-question_encoder-single-nq-base": ( - "https://huggingface.co/facebook/dpr-question_encoder-single-nq-base/resolve/main/vocab.txt" - ), - "facebook/dpr-question_encoder-multiset-base": ( - "https://huggingface.co/facebook/dpr-question_encoder-multiset-base/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "facebook/dpr-question_encoder-single-nq-base": ( - "https://huggingface.co/facebook/dpr-question_encoder-single-nq-base/resolve/main/tokenizer.json" - ), - "facebook/dpr-question_encoder-multiset-base": ( - "https://huggingface.co/facebook/dpr-question_encoder-multiset-base/resolve/main/tokenizer.json" - ), - }, -} -READER_PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/dpr-reader-single-nq-base": ( - "https://huggingface.co/facebook/dpr-reader-single-nq-base/resolve/main/vocab.txt" - ), - "facebook/dpr-reader-multiset-base": ( - "https://huggingface.co/facebook/dpr-reader-multiset-base/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "facebook/dpr-reader-single-nq-base": ( - "https://huggingface.co/facebook/dpr-reader-single-nq-base/resolve/main/tokenizer.json" - ), - "facebook/dpr-reader-multiset-base": ( - "https://huggingface.co/facebook/dpr-reader-multiset-base/resolve/main/tokenizer.json" - ), - }, -} - -CONTEXT_ENCODER_PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/dpr-ctx_encoder-single-nq-base": 512, - "facebook/dpr-ctx_encoder-multiset-base": 512, -} -QUESTION_ENCODER_PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/dpr-question_encoder-single-nq-base": 512, - "facebook/dpr-question_encoder-multiset-base": 512, -} -READER_PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/dpr-reader-single-nq-base": 512, - "facebook/dpr-reader-multiset-base": 512, -} - - -CONTEXT_ENCODER_PRETRAINED_INIT_CONFIGURATION = { - "facebook/dpr-ctx_encoder-single-nq-base": {"do_lower_case": True}, - "facebook/dpr-ctx_encoder-multiset-base": {"do_lower_case": True}, -} -QUESTION_ENCODER_PRETRAINED_INIT_CONFIGURATION = { - "facebook/dpr-question_encoder-single-nq-base": {"do_lower_case": True}, - "facebook/dpr-question_encoder-multiset-base": {"do_lower_case": True}, -} -READER_PRETRAINED_INIT_CONFIGURATION = { - "facebook/dpr-reader-single-nq-base": {"do_lower_case": True}, - "facebook/dpr-reader-multiset-base": {"do_lower_case": True}, -} - class DPRContextEncoderTokenizer(BertTokenizer): r""" @@ -121,9 +39,6 @@ class DPRContextEncoderTokenizer(BertTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = CONTEXT_ENCODER_PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = CONTEXT_ENCODER_PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = CONTEXT_ENCODER_PRETRAINED_INIT_CONFIGURATION class DPRQuestionEncoderTokenizer(BertTokenizer): @@ -137,9 +52,6 @@ class DPRQuestionEncoderTokenizer(BertTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = QUESTION_ENCODER_PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = QUESTION_ENCODER_PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = QUESTION_ENCODER_PRETRAINED_INIT_CONFIGURATION DPRSpanPrediction = collections.namedtuple( @@ -404,7 +316,4 @@ class DPRReaderTokenizer(CustomDPRReaderTokenizerMixin, BertTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = READER_PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = READER_PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = READER_PRETRAINED_INIT_CONFIGURATION model_input_names = ["input_ids", "attention_mask"] diff --git a/src/transformers/models/dpr/tokenization_dpr_fast.py b/src/transformers/models/dpr/tokenization_dpr_fast.py index 784ed1344c..730f200a68 100644 --- a/src/transformers/models/dpr/tokenization_dpr_fast.py +++ b/src/transformers/models/dpr/tokenization_dpr_fast.py @@ -28,88 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -CONTEXT_ENCODER_PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/dpr-ctx_encoder-single-nq-base": ( - "https://huggingface.co/facebook/dpr-ctx_encoder-single-nq-base/resolve/main/vocab.txt" - ), - "facebook/dpr-ctx_encoder-multiset-base": ( - "https://huggingface.co/facebook/dpr-ctx_encoder-multiset-base/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "facebook/dpr-ctx_encoder-single-nq-base": ( - "https://huggingface.co/facebook/dpr-ctx_encoder-single-nq-base/resolve/main/tokenizer.json" - ), - "facebook/dpr-ctx_encoder-multiset-base": ( - "https://huggingface.co/facebook/dpr-ctx_encoder-multiset-base/resolve/main/tokenizer.json" - ), - }, -} -QUESTION_ENCODER_PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/dpr-question_encoder-single-nq-base": ( - "https://huggingface.co/facebook/dpr-question_encoder-single-nq-base/resolve/main/vocab.txt" - ), - "facebook/dpr-question_encoder-multiset-base": ( - "https://huggingface.co/facebook/dpr-question_encoder-multiset-base/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "facebook/dpr-question_encoder-single-nq-base": ( - "https://huggingface.co/facebook/dpr-question_encoder-single-nq-base/resolve/main/tokenizer.json" - ), - "facebook/dpr-question_encoder-multiset-base": ( - "https://huggingface.co/facebook/dpr-question_encoder-multiset-base/resolve/main/tokenizer.json" - ), - }, -} -READER_PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/dpr-reader-single-nq-base": ( - "https://huggingface.co/facebook/dpr-reader-single-nq-base/resolve/main/vocab.txt" - ), - "facebook/dpr-reader-multiset-base": ( - "https://huggingface.co/facebook/dpr-reader-multiset-base/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "facebook/dpr-reader-single-nq-base": ( - "https://huggingface.co/facebook/dpr-reader-single-nq-base/resolve/main/tokenizer.json" - ), - "facebook/dpr-reader-multiset-base": ( - "https://huggingface.co/facebook/dpr-reader-multiset-base/resolve/main/tokenizer.json" - ), - }, -} - -CONTEXT_ENCODER_PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/dpr-ctx_encoder-single-nq-base": 512, - "facebook/dpr-ctx_encoder-multiset-base": 512, -} -QUESTION_ENCODER_PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/dpr-question_encoder-single-nq-base": 512, - "facebook/dpr-question_encoder-multiset-base": 512, -} -READER_PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/dpr-reader-single-nq-base": 512, - "facebook/dpr-reader-multiset-base": 512, -} - - -CONTEXT_ENCODER_PRETRAINED_INIT_CONFIGURATION = { - "facebook/dpr-ctx_encoder-single-nq-base": {"do_lower_case": True}, - "facebook/dpr-ctx_encoder-multiset-base": {"do_lower_case": True}, -} -QUESTION_ENCODER_PRETRAINED_INIT_CONFIGURATION = { - "facebook/dpr-question_encoder-single-nq-base": {"do_lower_case": True}, - "facebook/dpr-question_encoder-multiset-base": {"do_lower_case": True}, -} -READER_PRETRAINED_INIT_CONFIGURATION = { - "facebook/dpr-reader-single-nq-base": {"do_lower_case": True}, - "facebook/dpr-reader-multiset-base": {"do_lower_case": True}, -} - class DPRContextEncoderTokenizerFast(BertTokenizerFast): r""" @@ -122,9 +40,6 @@ class DPRContextEncoderTokenizerFast(BertTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = CONTEXT_ENCODER_PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = CONTEXT_ENCODER_PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = CONTEXT_ENCODER_PRETRAINED_INIT_CONFIGURATION slow_tokenizer_class = DPRContextEncoderTokenizer @@ -139,9 +54,6 @@ class DPRQuestionEncoderTokenizerFast(BertTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = QUESTION_ENCODER_PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = QUESTION_ENCODER_PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = QUESTION_ENCODER_PRETRAINED_INIT_CONFIGURATION slow_tokenizer_class = DPRQuestionEncoderTokenizer @@ -403,8 +315,5 @@ class DPRReaderTokenizerFast(CustomDPRReaderTokenizerMixin, BertTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = READER_PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = READER_PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = READER_PRETRAINED_INIT_CONFIGURATION model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = DPRReaderTokenizer diff --git a/src/transformers/models/dpt/configuration_dpt.py b/src/transformers/models/dpt/configuration_dpt.py index 97b9e2e9a8..9bdc8d1ef0 100644 --- a/src/transformers/models/dpt/configuration_dpt.py +++ b/src/transformers/models/dpt/configuration_dpt.py @@ -24,10 +24,8 @@ from ..bit import BitConfig logger = logging.get_logger(__name__) -DPT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "Intel/dpt-large": "https://huggingface.co/Intel/dpt-large/resolve/main/config.json", - # See all DPT models at https://huggingface.co/models?filter=dpt -} + +from ..deprecated._archive_maps import DPT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DPTConfig(PretrainedConfig): diff --git a/src/transformers/models/dpt/modeling_dpt.py b/src/transformers/models/dpt/modeling_dpt.py index e986e71d48..aad3330279 100755 --- a/src/transformers/models/dpt/modeling_dpt.py +++ b/src/transformers/models/dpt/modeling_dpt.py @@ -55,11 +55,7 @@ _CHECKPOINT_FOR_DOC = "Intel/dpt-large" _EXPECTED_OUTPUT_SHAPE = [1, 577, 1024] -DPT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Intel/dpt-large", - "Intel/dpt-hybrid-midas", - # See all DPT models at https://huggingface.co/models?filter=dpt -] +from ..deprecated._archive_maps import DPT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/efficientformer/configuration_efficientformer.py b/src/transformers/models/efficientformer/configuration_efficientformer.py index fecb90a886..1641c90711 100644 --- a/src/transformers/models/efficientformer/configuration_efficientformer.py +++ b/src/transformers/models/efficientformer/configuration_efficientformer.py @@ -22,11 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -EFFICIENTFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "snap-research/efficientformer-l1-300": ( - "https://huggingface.co/snap-research/efficientformer-l1-300/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import EFFICIENTFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class EfficientFormerConfig(PretrainedConfig): diff --git a/src/transformers/models/efficientformer/modeling_efficientformer.py b/src/transformers/models/efficientformer/modeling_efficientformer.py index 5f03a5ab74..70075cff55 100644 --- a/src/transformers/models/efficientformer/modeling_efficientformer.py +++ b/src/transformers/models/efficientformer/modeling_efficientformer.py @@ -50,10 +50,7 @@ _IMAGE_CLASS_CHECKPOINT = "snap-research/efficientformer-l1-300" _IMAGE_CLASS_EXPECTED_OUTPUT = "Egyptian cat" -EFFICIENTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "snap-research/efficientformer-l1-300", - # See all EfficientFormer models at https://huggingface.co/models?filter=efficientformer -] +from ..deprecated._archive_maps import EFFICIENTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class EfficientFormerPatchEmbeddings(nn.Module): diff --git a/src/transformers/models/efficientformer/modeling_tf_efficientformer.py b/src/transformers/models/efficientformer/modeling_tf_efficientformer.py index 113eafb88d..77b62999e7 100644 --- a/src/transformers/models/efficientformer/modeling_tf_efficientformer.py +++ b/src/transformers/models/efficientformer/modeling_tf_efficientformer.py @@ -59,10 +59,7 @@ _IMAGE_CLASS_CHECKPOINT = "snap-research/efficientformer-l1-300" _IMAGE_CLASS_EXPECTED_OUTPUT = "LABEL_281" -TF_EFFICIENTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "snap-research/efficientformer-l1-300", - # See all EfficientFormer models at https://huggingface.co/models?filter=efficientformer -] +from ..deprecated._archive_maps import TF_EFFICIENTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFEfficientFormerPatchEmbeddings(keras.layers.Layer): diff --git a/src/transformers/models/efficientnet/configuration_efficientnet.py b/src/transformers/models/efficientnet/configuration_efficientnet.py index 49e50a45e1..77106c70d7 100644 --- a/src/transformers/models/efficientnet/configuration_efficientnet.py +++ b/src/transformers/models/efficientnet/configuration_efficientnet.py @@ -26,9 +26,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -EFFICIENTNET_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/efficientnet-b7": "https://huggingface.co/google/efficientnet-b7/resolve/main/config.json", -} + +from ..deprecated._archive_maps import EFFICIENTNET_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class EfficientNetConfig(PretrainedConfig): diff --git a/src/transformers/models/efficientnet/modeling_efficientnet.py b/src/transformers/models/efficientnet/modeling_efficientnet.py index 2513f9b2fd..5b7ff534ee 100644 --- a/src/transformers/models/efficientnet/modeling_efficientnet.py +++ b/src/transformers/models/efficientnet/modeling_efficientnet.py @@ -52,10 +52,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 768, 7, 7] _IMAGE_CLASS_CHECKPOINT = "google/efficientnet-b7" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -EFFICIENTNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/efficientnet-b7", - # See all EfficientNet models at https://huggingface.co/models?filter=efficientnet -] + +from ..deprecated._archive_maps import EFFICIENTNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 EFFICIENTNET_START_DOCSTRING = r""" diff --git a/src/transformers/models/electra/configuration_electra.py b/src/transformers/models/electra/configuration_electra.py index d45f629302..b6d1368a9d 100644 --- a/src/transformers/models/electra/configuration_electra.py +++ b/src/transformers/models/electra/configuration_electra.py @@ -25,20 +25,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -ELECTRA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/electra-small-generator": "https://huggingface.co/google/electra-small-generator/resolve/main/config.json", - "google/electra-base-generator": "https://huggingface.co/google/electra-base-generator/resolve/main/config.json", - "google/electra-large-generator": "https://huggingface.co/google/electra-large-generator/resolve/main/config.json", - "google/electra-small-discriminator": ( - "https://huggingface.co/google/electra-small-discriminator/resolve/main/config.json" - ), - "google/electra-base-discriminator": ( - "https://huggingface.co/google/electra-base-discriminator/resolve/main/config.json" - ), - "google/electra-large-discriminator": ( - "https://huggingface.co/google/electra-large-discriminator/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import ELECTRA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ElectraConfig(PretrainedConfig): diff --git a/src/transformers/models/electra/modeling_electra.py b/src/transformers/models/electra/modeling_electra.py index 3aaa614100..2138aa97c6 100644 --- a/src/transformers/models/electra/modeling_electra.py +++ b/src/transformers/models/electra/modeling_electra.py @@ -53,15 +53,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "google/electra-small-discriminator" _CONFIG_FOR_DOC = "ElectraConfig" -ELECTRA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/electra-small-generator", - "google/electra-base-generator", - "google/electra-large-generator", - "google/electra-small-discriminator", - "google/electra-base-discriminator", - "google/electra-large-discriminator", - # See all ELECTRA models at https://huggingface.co/models?filter=electra -] + +from ..deprecated._archive_maps import ELECTRA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_electra(model, config, tf_checkpoint_path, discriminator_or_generator="discriminator"): diff --git a/src/transformers/models/electra/modeling_tf_electra.py b/src/transformers/models/electra/modeling_tf_electra.py index b0c8b4fa28..ba60cd8f5d 100644 --- a/src/transformers/models/electra/modeling_tf_electra.py +++ b/src/transformers/models/electra/modeling_tf_electra.py @@ -65,15 +65,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "google/electra-small-discriminator" _CONFIG_FOR_DOC = "ElectraConfig" -TF_ELECTRA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/electra-small-generator", - "google/electra-base-generator", - "google/electra-large-generator", - "google/electra-small-discriminator", - "google/electra-base-discriminator", - "google/electra-large-discriminator", - # See all ELECTRA models at https://huggingface.co/models?filter=electra -] + +from ..deprecated._archive_maps import TF_ELECTRA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.bert.modeling_tf_bert.TFBertSelfAttention with Bert->Electra diff --git a/src/transformers/models/electra/tokenization_electra.py b/src/transformers/models/electra/tokenization_electra.py index 6ea9a600a6..ceb3e75602 100644 --- a/src/transformers/models/electra/tokenization_electra.py +++ b/src/transformers/models/electra/tokenization_electra.py @@ -26,46 +26,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/electra-small-generator": ( - "https://huggingface.co/google/electra-small-generator/resolve/main/vocab.txt" - ), - "google/electra-base-generator": "https://huggingface.co/google/electra-base-generator/resolve/main/vocab.txt", - "google/electra-large-generator": ( - "https://huggingface.co/google/electra-large-generator/resolve/main/vocab.txt" - ), - "google/electra-small-discriminator": ( - "https://huggingface.co/google/electra-small-discriminator/resolve/main/vocab.txt" - ), - "google/electra-base-discriminator": ( - "https://huggingface.co/google/electra-base-discriminator/resolve/main/vocab.txt" - ), - "google/electra-large-discriminator": ( - "https://huggingface.co/google/electra-large-discriminator/resolve/main/vocab.txt" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/electra-small-generator": 512, - "google/electra-base-generator": 512, - "google/electra-large-generator": 512, - "google/electra-small-discriminator": 512, - "google/electra-base-discriminator": 512, - "google/electra-large-discriminator": 512, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "google/electra-small-generator": {"do_lower_case": True}, - "google/electra-base-generator": {"do_lower_case": True}, - "google/electra-large-generator": {"do_lower_case": True}, - "google/electra-small-discriminator": {"do_lower_case": True}, - "google/electra-base-discriminator": {"do_lower_case": True}, - "google/electra-large-discriminator": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert.load_vocab def load_vocab(vocab_file): @@ -133,9 +93,6 @@ class ElectraTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/electra/tokenization_electra_fast.py b/src/transformers/models/electra/tokenization_electra_fast.py index e76082de17..7b9d6a36cb 100644 --- a/src/transformers/models/electra/tokenization_electra_fast.py +++ b/src/transformers/models/electra/tokenization_electra_fast.py @@ -24,65 +24,6 @@ from .tokenization_electra import ElectraTokenizer VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/electra-small-generator": ( - "https://huggingface.co/google/electra-small-generator/resolve/main/vocab.txt" - ), - "google/electra-base-generator": "https://huggingface.co/google/electra-base-generator/resolve/main/vocab.txt", - "google/electra-large-generator": ( - "https://huggingface.co/google/electra-large-generator/resolve/main/vocab.txt" - ), - "google/electra-small-discriminator": ( - "https://huggingface.co/google/electra-small-discriminator/resolve/main/vocab.txt" - ), - "google/electra-base-discriminator": ( - "https://huggingface.co/google/electra-base-discriminator/resolve/main/vocab.txt" - ), - "google/electra-large-discriminator": ( - "https://huggingface.co/google/electra-large-discriminator/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "google/electra-small-generator": ( - "https://huggingface.co/google/electra-small-generator/resolve/main/tokenizer.json" - ), - "google/electra-base-generator": ( - "https://huggingface.co/google/electra-base-generator/resolve/main/tokenizer.json" - ), - "google/electra-large-generator": ( - "https://huggingface.co/google/electra-large-generator/resolve/main/tokenizer.json" - ), - "google/electra-small-discriminator": ( - "https://huggingface.co/google/electra-small-discriminator/resolve/main/tokenizer.json" - ), - "google/electra-base-discriminator": ( - "https://huggingface.co/google/electra-base-discriminator/resolve/main/tokenizer.json" - ), - "google/electra-large-discriminator": ( - "https://huggingface.co/google/electra-large-discriminator/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/electra-small-generator": 512, - "google/electra-base-generator": 512, - "google/electra-large-generator": 512, - "google/electra-small-discriminator": 512, - "google/electra-base-discriminator": 512, - "google/electra-large-discriminator": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "google/electra-small-generator": {"do_lower_case": True}, - "google/electra-base-generator": {"do_lower_case": True}, - "google/electra-large-generator": {"do_lower_case": True}, - "google/electra-small-discriminator": {"do_lower_case": True}, - "google/electra-base-discriminator": {"do_lower_case": True}, - "google/electra-large-discriminator": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert_fast.BertTokenizerFast with Bert->Electra , BERT->ELECTRA class ElectraTokenizerFast(PreTrainedTokenizerFast): @@ -126,9 +67,6 @@ class ElectraTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = ElectraTokenizer def __init__( diff --git a/src/transformers/models/encodec/configuration_encodec.py b/src/transformers/models/encodec/configuration_encodec.py index af493c325b..4e18bb178a 100644 --- a/src/transformers/models/encodec/configuration_encodec.py +++ b/src/transformers/models/encodec/configuration_encodec.py @@ -26,10 +26,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -ENCODEC_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/encodec_24khz": "https://huggingface.co/facebook/encodec_24khz/resolve/main/config.json", - "facebook/encodec_48khz": "https://huggingface.co/facebook/encodec_48khz/resolve/main/config.json", -} + +from ..deprecated._archive_maps import ENCODEC_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class EncodecConfig(PretrainedConfig): diff --git a/src/transformers/models/encodec/modeling_encodec.py b/src/transformers/models/encodec/modeling_encodec.py index bf7503efb4..bd56661b19 100644 --- a/src/transformers/models/encodec/modeling_encodec.py +++ b/src/transformers/models/encodec/modeling_encodec.py @@ -40,11 +40,7 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "EncodecConfig" -ENCODEC_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/encodec_24khz", - "facebook/encodec_48khz", - # See all EnCodec models at https://huggingface.co/models?filter=encodec -] +from ..deprecated._archive_maps import ENCODEC_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/ernie/configuration_ernie.py b/src/transformers/models/ernie/configuration_ernie.py index 7278a74ece..81ed035963 100644 --- a/src/transformers/models/ernie/configuration_ernie.py +++ b/src/transformers/models/ernie/configuration_ernie.py @@ -24,18 +24,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -ERNIE_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "nghuyong/ernie-1.0-base-zh": "https://huggingface.co/nghuyong/ernie-1.0-base-zh/resolve/main/config.json", - "nghuyong/ernie-2.0-base-en": "https://huggingface.co/nghuyong/ernie-2.0-base-en/resolve/main/config.json", - "nghuyong/ernie-2.0-large-en": "https://huggingface.co/nghuyong/ernie-2.0-large-en/resolve/main/config.json", - "nghuyong/ernie-3.0-base-zh": "https://huggingface.co/nghuyong/ernie-3.0-base-zh/resolve/main/config.json", - "nghuyong/ernie-3.0-medium-zh": "https://huggingface.co/nghuyong/ernie-3.0-medium-zh/resolve/main/config.json", - "nghuyong/ernie-3.0-mini-zh": "https://huggingface.co/nghuyong/ernie-3.0-mini-zh/resolve/main/config.json", - "nghuyong/ernie-3.0-micro-zh": "https://huggingface.co/nghuyong/ernie-3.0-micro-zh/resolve/main/config.json", - "nghuyong/ernie-3.0-nano-zh": "https://huggingface.co/nghuyong/ernie-3.0-nano-zh/resolve/main/config.json", - "nghuyong/ernie-gram-zh": "https://huggingface.co/nghuyong/ernie-gram-zh/resolve/main/config.json", - "nghuyong/ernie-health-zh": "https://huggingface.co/nghuyong/ernie-health-zh/resolve/main/config.json", -} + +from ..deprecated._archive_maps import ERNIE_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ErnieConfig(PretrainedConfig): diff --git a/src/transformers/models/ernie/modeling_ernie.py b/src/transformers/models/ernie/modeling_ernie.py index 291ab6c54d..a65f453205 100644 --- a/src/transformers/models/ernie/modeling_ernie.py +++ b/src/transformers/models/ernie/modeling_ernie.py @@ -56,19 +56,7 @@ _CHECKPOINT_FOR_DOC = "nghuyong/ernie-1.0-base-zh" _CONFIG_FOR_DOC = "ErnieConfig" -ERNIE_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "nghuyong/ernie-1.0-base-zh", - "nghuyong/ernie-2.0-base-en", - "nghuyong/ernie-2.0-large-en", - "nghuyong/ernie-3.0-base-zh", - "nghuyong/ernie-3.0-medium-zh", - "nghuyong/ernie-3.0-mini-zh", - "nghuyong/ernie-3.0-micro-zh", - "nghuyong/ernie-3.0-nano-zh", - "nghuyong/ernie-gram-zh", - "nghuyong/ernie-health-zh", - # See all ERNIE models at https://huggingface.co/models?filter=ernie -] +from ..deprecated._archive_maps import ERNIE_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class ErnieEmbeddings(nn.Module): diff --git a/src/transformers/models/ernie_m/configuration_ernie_m.py b/src/transformers/models/ernie_m/configuration_ernie_m.py index 85917dc828..96451c9d9c 100644 --- a/src/transformers/models/ernie_m/configuration_ernie_m.py +++ b/src/transformers/models/ernie_m/configuration_ernie_m.py @@ -20,12 +20,7 @@ from __future__ import annotations from typing import Dict from ...configuration_utils import PretrainedConfig - - -ERNIE_M_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "susnato/ernie-m-base_pytorch": "https://huggingface.co/susnato/ernie-m-base_pytorch/blob/main/config.json", - "susnato/ernie-m-large_pytorch": "https://huggingface.co/susnato/ernie-m-large_pytorch/blob/main/config.json", -} +from ..deprecated._archive_maps import ERNIE_M_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ErnieMConfig(PretrainedConfig): diff --git a/src/transformers/models/ernie_m/modeling_ernie_m.py b/src/transformers/models/ernie_m/modeling_ernie_m.py index c1be3cfba1..ac56e120a0 100755 --- a/src/transformers/models/ernie_m/modeling_ernie_m.py +++ b/src/transformers/models/ernie_m/modeling_ernie_m.py @@ -44,11 +44,8 @@ _CHECKPOINT_FOR_DOC = "susnato/ernie-m-base_pytorch" _CONFIG_FOR_DOC = "ErnieMConfig" _TOKENIZER_FOR_DOC = "ErnieMTokenizer" -ERNIE_M_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "susnato/ernie-m-base_pytorch", - "susnato/ernie-m-large_pytorch", - # See all ErnieM models at https://huggingface.co/models?filter=ernie_m -] + +from ..deprecated._archive_maps import ERNIE_M_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Adapted from paddlenlp.transformers.ernie_m.modeling.ErnieEmbeddings diff --git a/src/transformers/models/ernie_m/tokenization_ernie_m.py b/src/transformers/models/ernie_m/tokenization_ernie_m.py index b1b8cc8450..0bd7edea1c 100644 --- a/src/transformers/models/ernie_m/tokenization_ernie_m.py +++ b/src/transformers/models/ernie_m/tokenization_ernie_m.py @@ -36,27 +36,6 @@ RESOURCE_FILES_NAMES = { "vocab_file": "vocab.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "ernie-m-base": "https://huggingface.co/susnato/ernie-m-base_pytorch/blob/main/vocab.txt", - "ernie-m-large": "https://huggingface.co/susnato/ernie-m-base_pytorch/blob/main/vocab.txt", - }, - "sentencepiece_model_file": { - "ernie-m-base": "https://huggingface.co/susnato/ernie-m-base_pytorch/blob/main/sentencepiece.bpe.model", - "ernie-m-large": "https://huggingface.co/susnato/ernie-m-base_pytorch/blob/main/sentencepiece.bpe.model", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "ernie-m-base": 514, - "ernie-m-large": 514, -} - -PRETRAINED_INIT_CONFIGURATION = { - "ernie-m-base": {"do_lower_case": False}, - "ernie-m-large": {"do_lower_case": False}, -} - # Adapted from paddlenlp.transformers.ernie_m.tokenizer.ErnieMTokenizer class ErnieMTokenizer(PreTrainedTokenizer): @@ -89,9 +68,6 @@ class ErnieMTokenizer(PreTrainedTokenizer): model_input_names: List[str] = ["input_ids"] vocab_files_names = VOCAB_FILES_NAMES - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP resource_files_names = RESOURCE_FILES_NAMES def __init__( diff --git a/src/transformers/models/esm/configuration_esm.py b/src/transformers/models/esm/configuration_esm.py index 75f8609ab0..31d309cb04 100644 --- a/src/transformers/models/esm/configuration_esm.py +++ b/src/transformers/models/esm/configuration_esm.py @@ -24,10 +24,8 @@ from ...utils import logging logger = logging.get_logger(__name__) # TODO Update this -ESM_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/esm-1b": "https://huggingface.co/facebook/esm-1b/resolve/main/config.json", - # See all ESM models at https://huggingface.co/models?filter=esm -} + +from ..deprecated._archive_maps import ESM_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class EsmConfig(PretrainedConfig): diff --git a/src/transformers/models/esm/modeling_esm.py b/src/transformers/models/esm/modeling_esm.py index 2349ce5800..a97ea58d7b 100755 --- a/src/transformers/models/esm/modeling_esm.py +++ b/src/transformers/models/esm/modeling_esm.py @@ -40,12 +40,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "facebook/esm2_t6_8M_UR50D" _CONFIG_FOR_DOC = "EsmConfig" -ESM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/esm2_t6_8M_UR50D", - "facebook/esm2_t12_35M_UR50D", - # This is not a complete list of all ESM models! - # See all ESM models at https://huggingface.co/models?filter=esm -] + +from ..deprecated._archive_maps import ESM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def rotate_half(x): diff --git a/src/transformers/models/esm/modeling_tf_esm.py b/src/transformers/models/esm/modeling_tf_esm.py index 2c780b4bdd..2688c207b0 100644 --- a/src/transformers/models/esm/modeling_tf_esm.py +++ b/src/transformers/models/esm/modeling_tf_esm.py @@ -52,13 +52,6 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "facebook/esm2_t6_8M_UR50D" _CONFIG_FOR_DOC = "EsmConfig" -TF_ESM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/esm2_t6_8M_UR50D", - "facebook/esm2_t12_35M_UR50D", - # This is not a complete list of all ESM models! - # See all ESM models at https://huggingface.co/models?filter=esm -] - def rotate_half(x): x1, x2 = tf.split(x, 2, axis=-1) diff --git a/src/transformers/models/esm/tokenization_esm.py b/src/transformers/models/esm/tokenization_esm.py index 478527c0ec..27a889c87e 100644 --- a/src/transformers/models/esm/tokenization_esm.py +++ b/src/transformers/models/esm/tokenization_esm.py @@ -24,18 +24,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/esm2_t6_8M_UR50D": "https://huggingface.co/facebook/esm2_t6_8M_UR50D/resolve/main/vocab.txt", - "facebook/esm2_t12_35M_UR50D": "https://huggingface.co/facebook/esm2_t12_35M_UR50D/resolve/main/vocab.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/esm2_t6_8M_UR50D": 1024, - "facebook/esm2_t12_35M_UR50D": 1024, -} - def load_vocab_file(vocab_file): with open(vocab_file, "r") as f: @@ -49,8 +37,6 @@ class EsmTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/falcon/configuration_falcon.py b/src/transformers/models/falcon/configuration_falcon.py index fe0a450a24..16d9dec47c 100644 --- a/src/transformers/models/falcon/configuration_falcon.py +++ b/src/transformers/models/falcon/configuration_falcon.py @@ -19,10 +19,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -FALCON_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "tiiuae/falcon-40b": "https://huggingface.co/tiiuae/falcon-40b/resolve/main/config.json", - "tiiuae/falcon-7b": "https://huggingface.co/tiiuae/falcon-7b/resolve/main/config.json", -} + +from ..deprecated._archive_maps import FALCON_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class FalconConfig(PretrainedConfig): diff --git a/src/transformers/models/falcon/modeling_falcon.py b/src/transformers/models/falcon/modeling_falcon.py index d2c9125ddc..f1cff3f181 100644 --- a/src/transformers/models/falcon/modeling_falcon.py +++ b/src/transformers/models/falcon/modeling_falcon.py @@ -58,14 +58,9 @@ if is_flash_attn_2_available(): logger = logging.get_logger(__name__) -FALCON_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "tiiuae/falcon-40b", - "tiiuae/falcon-40b-instruct", - "tiiuae/falcon-7b", - "tiiuae/falcon-7b-instruct", - "tiiuae/falcon-rw-7b", - "tiiuae/falcon-rw-1b", -] +from ..deprecated._archive_maps import FALCON_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + + _CHECKPOINT_FOR_DOC = "Rocketknight1/falcon-rw-1b" _CONFIG_FOR_DOC = "FalconConfig" diff --git a/src/transformers/models/fastspeech2_conformer/configuration_fastspeech2_conformer.py b/src/transformers/models/fastspeech2_conformer/configuration_fastspeech2_conformer.py index 46dc10adb2..adb038ad1b 100644 --- a/src/transformers/models/fastspeech2_conformer/configuration_fastspeech2_conformer.py +++ b/src/transformers/models/fastspeech2_conformer/configuration_fastspeech2_conformer.py @@ -23,17 +23,11 @@ from ...utils import logging logger = logging.get_logger(__name__) -FASTSPEECH2_CONFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "espnet/fastspeech2_conformer": "https://huggingface.co/espnet/fastspeech2_conformer/raw/main/config.json", -} - -FASTSPEECH2_CONFORMER_HIFIGAN_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "espnet/fastspeech2_conformer_hifigan": "https://huggingface.co/espnet/fastspeech2_conformer_hifigan/raw/main/config.json", -} - -FASTSPEECH2_CONFORMER_WITH_HIFIGAN_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "espnet/fastspeech2_conformer_with_hifigan": "https://huggingface.co/espnet/fastspeech2_conformer_with_hifigan/raw/main/config.json", -} +from ..deprecated._archive_maps import ( # noqa: F401, E402 + FASTSPEECH2_CONFORMER_HIFIGAN_PRETRAINED_CONFIG_ARCHIVE_MAP, # noqa: F401, E402 + FASTSPEECH2_CONFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP, # noqa: F401, E402 + FASTSPEECH2_CONFORMER_WITH_HIFIGAN_PRETRAINED_CONFIG_ARCHIVE_MAP, # noqa: F401, E402 +) class FastSpeech2ConformerConfig(PretrainedConfig): diff --git a/src/transformers/models/fastspeech2_conformer/modeling_fastspeech2_conformer.py b/src/transformers/models/fastspeech2_conformer/modeling_fastspeech2_conformer.py index cc57747c59..c46ef2a836 100644 --- a/src/transformers/models/fastspeech2_conformer/modeling_fastspeech2_conformer.py +++ b/src/transformers/models/fastspeech2_conformer/modeling_fastspeech2_conformer.py @@ -33,10 +33,8 @@ from .configuration_fastspeech2_conformer import ( logger = logging.get_logger(__name__) -FASTSPEECH2_CONFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "espnet/fastspeech2_conformer", - # See all FastSpeech2Conformer models at https://huggingface.co/models?filter=fastspeech2_conformer -] + +from ..deprecated._archive_maps import FASTSPEECH2_CONFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/fastspeech2_conformer/tokenization_fastspeech2_conformer.py b/src/transformers/models/fastspeech2_conformer/tokenization_fastspeech2_conformer.py index c4fd208cef..bc52006ad6 100644 --- a/src/transformers/models/fastspeech2_conformer/tokenization_fastspeech2_conformer.py +++ b/src/transformers/models/fastspeech2_conformer/tokenization_fastspeech2_conformer.py @@ -27,18 +27,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "espnet/fastspeech2_conformer": "https://huggingface.co/espnet/fastspeech2_conformer/raw/main/vocab.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - # Set to somewhat arbitrary large number as the model input - # isn't constrained by the relative positional encoding - "espnet/fastspeech2_conformer": 4096, -} - class FastSpeech2ConformerTokenizer(PreTrainedTokenizer): """ @@ -61,9 +49,7 @@ class FastSpeech2ConformerTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP model_input_names = ["input_ids", "attention_mask"] - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/flaubert/configuration_flaubert.py b/src/transformers/models/flaubert/configuration_flaubert.py index ba6d79891f..fb4ef2992c 100644 --- a/src/transformers/models/flaubert/configuration_flaubert.py +++ b/src/transformers/models/flaubert/configuration_flaubert.py @@ -23,12 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -FLAUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "flaubert/flaubert_small_cased": "https://huggingface.co/flaubert/flaubert_small_cased/resolve/main/config.json", - "flaubert/flaubert_base_uncased": "https://huggingface.co/flaubert/flaubert_base_uncased/resolve/main/config.json", - "flaubert/flaubert_base_cased": "https://huggingface.co/flaubert/flaubert_base_cased/resolve/main/config.json", - "flaubert/flaubert_large_cased": "https://huggingface.co/flaubert/flaubert_large_cased/resolve/main/config.json", -} + +from ..deprecated._archive_maps import FLAUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class FlaubertConfig(PretrainedConfig): diff --git a/src/transformers/models/flaubert/modeling_flaubert.py b/src/transformers/models/flaubert/modeling_flaubert.py index 4786fc6d57..4077d1b7b0 100644 --- a/src/transformers/models/flaubert/modeling_flaubert.py +++ b/src/transformers/models/flaubert/modeling_flaubert.py @@ -51,13 +51,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "flaubert/flaubert_base_cased" _CONFIG_FOR_DOC = "FlaubertConfig" -FLAUBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "flaubert/flaubert_small_cased", - "flaubert/flaubert_base_uncased", - "flaubert/flaubert_base_cased", - "flaubert/flaubert_large_cased", - # See all Flaubert models at https://huggingface.co/models?filter=flaubert -] + +from ..deprecated._archive_maps import FLAUBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.xlm.modeling_xlm.create_sinusoidal_embeddings diff --git a/src/transformers/models/flaubert/modeling_tf_flaubert.py b/src/transformers/models/flaubert/modeling_tf_flaubert.py index 23f66e56a9..08e573daa9 100644 --- a/src/transformers/models/flaubert/modeling_tf_flaubert.py +++ b/src/transformers/models/flaubert/modeling_tf_flaubert.py @@ -67,9 +67,9 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "flaubert/flaubert_base_cased" _CONFIG_FOR_DOC = "FlaubertConfig" -TF_FLAUBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - # See all Flaubert models at https://huggingface.co/models?filter=flaubert -] + +from ..deprecated._archive_maps import TF_FLAUBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + FLAUBERT_START_DOCSTRING = r""" diff --git a/src/transformers/models/flaubert/tokenization_flaubert.py b/src/transformers/models/flaubert/tokenization_flaubert.py index b1b34cc0f7..20f9926422 100644 --- a/src/transformers/models/flaubert/tokenization_flaubert.py +++ b/src/transformers/models/flaubert/tokenization_flaubert.py @@ -32,47 +32,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "flaubert/flaubert_small_cased": ( - "https://huggingface.co/flaubert/flaubert_small_cased/resolve/main/vocab.json" - ), - "flaubert/flaubert_base_uncased": ( - "https://huggingface.co/flaubert/flaubert_base_uncased/resolve/main/vocab.json" - ), - "flaubert/flaubert_base_cased": "https://huggingface.co/flaubert/flaubert_base_cased/resolve/main/vocab.json", - "flaubert/flaubert_large_cased": ( - "https://huggingface.co/flaubert/flaubert_large_cased/resolve/main/vocab.json" - ), - }, - "merges_file": { - "flaubert/flaubert_small_cased": ( - "https://huggingface.co/flaubert/flaubert_small_cased/resolve/main/merges.txt" - ), - "flaubert/flaubert_base_uncased": ( - "https://huggingface.co/flaubert/flaubert_base_uncased/resolve/main/merges.txt" - ), - "flaubert/flaubert_base_cased": "https://huggingface.co/flaubert/flaubert_base_cased/resolve/main/merges.txt", - "flaubert/flaubert_large_cased": ( - "https://huggingface.co/flaubert/flaubert_large_cased/resolve/main/merges.txt" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "flaubert/flaubert_small_cased": 512, - "flaubert/flaubert_base_uncased": 512, - "flaubert/flaubert_base_cased": 512, - "flaubert/flaubert_large_cased": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "flaubert/flaubert_small_cased": {"do_lowercase": False}, - "flaubert/flaubert_base_uncased": {"do_lowercase": True}, - "flaubert/flaubert_base_cased": {"do_lowercase": False}, - "flaubert/flaubert_large_cased": {"do_lowercase": False}, -} - def convert_to_unicode(text): """ @@ -216,9 +175,6 @@ class FlaubertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/flava/configuration_flava.py b/src/transformers/models/flava/configuration_flava.py index 6ea4403e0f..2c8642bfd2 100644 --- a/src/transformers/models/flava/configuration_flava.py +++ b/src/transformers/models/flava/configuration_flava.py @@ -23,9 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -FLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/flava-full": "https://huggingface.co/facebook/flava-full/resolve/main/config.json", -} + +from ..deprecated._archive_maps import FLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class FlavaImageConfig(PretrainedConfig): diff --git a/src/transformers/models/flava/modeling_flava.py b/src/transformers/models/flava/modeling_flava.py index 0e5cfe1b68..19f19d4c9d 100644 --- a/src/transformers/models/flava/modeling_flava.py +++ b/src/transformers/models/flava/modeling_flava.py @@ -55,10 +55,9 @@ _CONFIG_CLASS_FOR_TEXT_MODEL_DOC = "FlavaTextConfig" _CONFIG_CLASS_FOR_MULTIMODAL_MODEL_DOC = "FlavaMultimodalConfig" _EXPECTED_IMAGE_OUTPUT_SHAPE = [1, 197, 768] -FLAVA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/flava-full", - # See all flava models at https://huggingface.co/models?filter=flava -] +from ..deprecated._archive_maps import FLAVA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + + FLAVA_CODEBOOK_PRETRAINED_MODEL_ARCHIVE_LIST = ["facebook/flava-image-codebook"] LOGIT_SCALE_CLAMP_MIN = 0 LOGIT_SCALE_CLAMP_MAX = 4.6052 diff --git a/src/transformers/models/fnet/configuration_fnet.py b/src/transformers/models/fnet/configuration_fnet.py index 993feb676d..4678cae92e 100644 --- a/src/transformers/models/fnet/configuration_fnet.py +++ b/src/transformers/models/fnet/configuration_fnet.py @@ -20,11 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -FNET_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/fnet-base": "https://huggingface.co/google/fnet-base/resolve/main/config.json", - "google/fnet-large": "https://huggingface.co/google/fnet-large/resolve/main/config.json", - # See all FNet models at https://huggingface.co/models?filter=fnet -} + +from ..deprecated._archive_maps import FNET_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class FNetConfig(PretrainedConfig): diff --git a/src/transformers/models/fnet/modeling_fnet.py b/src/transformers/models/fnet/modeling_fnet.py index dac75178d5..5724faee56 100755 --- a/src/transformers/models/fnet/modeling_fnet.py +++ b/src/transformers/models/fnet/modeling_fnet.py @@ -59,11 +59,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "google/fnet-base" _CONFIG_FOR_DOC = "FNetConfig" -FNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/fnet-base", - "google/fnet-large", - # See all FNet models at https://huggingface.co/models?filter=fnet -] + +from ..deprecated._archive_maps import FNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Adapted from https://github.com/google-research/google-research/blob/master/f_net/fourier.py diff --git a/src/transformers/models/fnet/tokenization_fnet.py b/src/transformers/models/fnet/tokenization_fnet.py index 919d60531a..a38114eb6d 100644 --- a/src/transformers/models/fnet/tokenization_fnet.py +++ b/src/transformers/models/fnet/tokenization_fnet.py @@ -28,17 +28,6 @@ from ...utils import logging logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/fnet-base": "https://huggingface.co/google/fnet-base/resolve/main/spiece.model", - "google/fnet-large": "https://huggingface.co/google/fnet-large/resolve/main/spiece.model", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/fnet-base": 512, - "google/fnet-large": 512, -} SPIECE_UNDERLINE = "▁" @@ -96,8 +85,6 @@ class FNetTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "token_type_ids"] def __init__( diff --git a/src/transformers/models/fnet/tokenization_fnet_fast.py b/src/transformers/models/fnet/tokenization_fnet_fast.py index 2179751e55..f279ad9ca7 100644 --- a/src/transformers/models/fnet/tokenization_fnet_fast.py +++ b/src/transformers/models/fnet/tokenization_fnet_fast.py @@ -32,21 +32,6 @@ else: logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/fnet-base": "https://huggingface.co/google/fnet-base/resolve/main/spiece.model", - "google/fnet-large": "https://huggingface.co/google/fnet-large/resolve/main/spiece.model", - }, - "tokenizer_file": { - "google/fnet-base": "https://huggingface.co/google/fnet-base/resolve/main/tokenizer.json", - "google/fnet-large": "https://huggingface.co/google/fnet-large/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/fnet-base": 512, - "google/fnet-large": 512, -} SPIECE_UNDERLINE = "▁" @@ -87,8 +72,6 @@ class FNetTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "token_type_ids"] slow_tokenizer_class = FNetTokenizer diff --git a/src/transformers/models/focalnet/configuration_focalnet.py b/src/transformers/models/focalnet/configuration_focalnet.py index c1d4e2e86c..7f590b9c2c 100644 --- a/src/transformers/models/focalnet/configuration_focalnet.py +++ b/src/transformers/models/focalnet/configuration_focalnet.py @@ -21,9 +21,8 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -FOCALNET_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/focalnet-tiny": "https://huggingface.co/microsoft/focalnet-tiny/resolve/main/config.json", -} + +from ..deprecated._archive_maps import FOCALNET_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class FocalNetConfig(BackboneConfigMixin, PretrainedConfig): diff --git a/src/transformers/models/focalnet/modeling_focalnet.py b/src/transformers/models/focalnet/modeling_focalnet.py index b0033c8559..a452f4171d 100644 --- a/src/transformers/models/focalnet/modeling_focalnet.py +++ b/src/transformers/models/focalnet/modeling_focalnet.py @@ -54,10 +54,7 @@ _IMAGE_CLASS_CHECKPOINT = "microsoft/focalnet-tiny" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -FOCALNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/focalnet-tiny", - # See all FocalNet models at https://huggingface.co/models?filter=focalnet -] +from ..deprecated._archive_maps import FOCALNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/fsmt/configuration_fsmt.py b/src/transformers/models/fsmt/configuration_fsmt.py index 493e6b6bf5..68abe47c01 100644 --- a/src/transformers/models/fsmt/configuration_fsmt.py +++ b/src/transformers/models/fsmt/configuration_fsmt.py @@ -21,7 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -FSMT_PRETRAINED_CONFIG_ARCHIVE_MAP = {} + +from ..deprecated._archive_maps import FSMT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class DecoderConfig(PretrainedConfig): diff --git a/src/transformers/models/fsmt/tokenization_fsmt.py b/src/transformers/models/fsmt/tokenization_fsmt.py index a631f07476..8b0be1f8be 100644 --- a/src/transformers/models/fsmt/tokenization_fsmt.py +++ b/src/transformers/models/fsmt/tokenization_fsmt.py @@ -33,26 +33,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "src_vocab_file": { - "stas/tiny-wmt19-en-de": "https://huggingface.co/stas/tiny-wmt19-en-de/resolve/main/vocab-src.json" - }, - "tgt_vocab_file": { - "stas/tiny-wmt19-en-de": "https://huggingface.co/stas/tiny-wmt19-en-de/resolve/main/vocab-tgt.json" - }, - "merges_file": {"stas/tiny-wmt19-en-de": "https://huggingface.co/stas/tiny-wmt19-en-de/resolve/main/merges.txt"}, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"stas/tiny-wmt19-en-de": 1024} -PRETRAINED_INIT_CONFIGURATION = { - "stas/tiny-wmt19-en-de": { - "langs": ["en", "de"], - "model_max_length": 1024, - "special_tokens_map_file": None, - "full_tokenizer_file": None, - } -} - def get_pairs(word): """ @@ -179,9 +159,6 @@ class FSMTTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/funnel/configuration_funnel.py b/src/transformers/models/funnel/configuration_funnel.py index 228216163b..0b49c22fb4 100644 --- a/src/transformers/models/funnel/configuration_funnel.py +++ b/src/transformers/models/funnel/configuration_funnel.py @@ -20,22 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -FUNNEL_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "funnel-transformer/small": "https://huggingface.co/funnel-transformer/small/resolve/main/config.json", - "funnel-transformer/small-base": "https://huggingface.co/funnel-transformer/small-base/resolve/main/config.json", - "funnel-transformer/medium": "https://huggingface.co/funnel-transformer/medium/resolve/main/config.json", - "funnel-transformer/medium-base": "https://huggingface.co/funnel-transformer/medium-base/resolve/main/config.json", - "funnel-transformer/intermediate": ( - "https://huggingface.co/funnel-transformer/intermediate/resolve/main/config.json" - ), - "funnel-transformer/intermediate-base": ( - "https://huggingface.co/funnel-transformer/intermediate-base/resolve/main/config.json" - ), - "funnel-transformer/large": "https://huggingface.co/funnel-transformer/large/resolve/main/config.json", - "funnel-transformer/large-base": "https://huggingface.co/funnel-transformer/large-base/resolve/main/config.json", - "funnel-transformer/xlarge": "https://huggingface.co/funnel-transformer/xlarge/resolve/main/config.json", - "funnel-transformer/xlarge-base": "https://huggingface.co/funnel-transformer/xlarge-base/resolve/main/config.json", -} + +from ..deprecated._archive_maps import FUNNEL_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class FunnelConfig(PretrainedConfig): diff --git a/src/transformers/models/funnel/modeling_funnel.py b/src/transformers/models/funnel/modeling_funnel.py index 50f8df3743..ce0c778948 100644 --- a/src/transformers/models/funnel/modeling_funnel.py +++ b/src/transformers/models/funnel/modeling_funnel.py @@ -49,18 +49,9 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "FunnelConfig" _CHECKPOINT_FOR_DOC = "funnel-transformer/small" -FUNNEL_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "funnel-transformer/small", # B4-4-4H768 - "funnel-transformer/small-base", # B4-4-4H768, no decoder - "funnel-transformer/medium", # B6-3x2-3x2H768 - "funnel-transformer/medium-base", # B6-3x2-3x2H768, no decoder - "funnel-transformer/intermediate", # B6-6-6H768 - "funnel-transformer/intermediate-base", # B6-6-6H768, no decoder - "funnel-transformer/large", # B8-8-8H1024 - "funnel-transformer/large-base", # B8-8-8H1024, no decoder - "funnel-transformer/xlarge-base", # B10-10-10H1024 - "funnel-transformer/xlarge", # B10-10-10H1024, no decoder -] + +from ..deprecated._archive_maps import FUNNEL_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + INF = 1e6 diff --git a/src/transformers/models/funnel/modeling_tf_funnel.py b/src/transformers/models/funnel/modeling_tf_funnel.py index 4e4a544523..b50b96df1c 100644 --- a/src/transformers/models/funnel/modeling_tf_funnel.py +++ b/src/transformers/models/funnel/modeling_tf_funnel.py @@ -62,18 +62,9 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "FunnelConfig" -TF_FUNNEL_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "funnel-transformer/small", # B4-4-4H768 - "funnel-transformer/small-base", # B4-4-4H768, no decoder - "funnel-transformer/medium", # B6-3x2-3x2H768 - "funnel-transformer/medium-base", # B6-3x2-3x2H768, no decoder - "funnel-transformer/intermediate", # B6-6-6H768 - "funnel-transformer/intermediate-base", # B6-6-6H768, no decoder - "funnel-transformer/large", # B8-8-8H1024 - "funnel-transformer/large-base", # B8-8-8H1024, no decoder - "funnel-transformer/xlarge-base", # B10-10-10H1024 - "funnel-transformer/xlarge", # B10-10-10H1024, no decoder -] + +from ..deprecated._archive_maps import TF_FUNNEL_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + INF = 1e6 diff --git a/src/transformers/models/funnel/tokenization_funnel.py b/src/transformers/models/funnel/tokenization_funnel.py index 9b0d3c1b6c..a1580deccf 100644 --- a/src/transformers/models/funnel/tokenization_funnel.py +++ b/src/transformers/models/funnel/tokenization_funnel.py @@ -40,31 +40,6 @@ _model_names = [ "xlarge-base", ] -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "funnel-transformer/small": "https://huggingface.co/funnel-transformer/small/resolve/main/vocab.txt", - "funnel-transformer/small-base": "https://huggingface.co/funnel-transformer/small-base/resolve/main/vocab.txt", - "funnel-transformer/medium": "https://huggingface.co/funnel-transformer/medium/resolve/main/vocab.txt", - "funnel-transformer/medium-base": ( - "https://huggingface.co/funnel-transformer/medium-base/resolve/main/vocab.txt" - ), - "funnel-transformer/intermediate": ( - "https://huggingface.co/funnel-transformer/intermediate/resolve/main/vocab.txt" - ), - "funnel-transformer/intermediate-base": ( - "https://huggingface.co/funnel-transformer/intermediate-base/resolve/main/vocab.txt" - ), - "funnel-transformer/large": "https://huggingface.co/funnel-transformer/large/resolve/main/vocab.txt", - "funnel-transformer/large-base": "https://huggingface.co/funnel-transformer/large-base/resolve/main/vocab.txt", - "funnel-transformer/xlarge": "https://huggingface.co/funnel-transformer/xlarge/resolve/main/vocab.txt", - "funnel-transformer/xlarge-base": ( - "https://huggingface.co/funnel-transformer/xlarge-base/resolve/main/vocab.txt" - ), - } -} -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {f"funnel-transformer/{name}": 512 for name in _model_names} -PRETRAINED_INIT_CONFIGURATION = {f"funnel-transformer/{name}": {"do_lower_case": True} for name in _model_names} - # Copied from transformers.models.bert.tokenization_bert.load_vocab def load_vocab(vocab_file): @@ -135,9 +110,6 @@ class FunnelTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES cls_token_type_id: int = 2 def __init__( diff --git a/src/transformers/models/funnel/tokenization_funnel_fast.py b/src/transformers/models/funnel/tokenization_funnel_fast.py index 17946eb74b..9ff2a3bfef 100644 --- a/src/transformers/models/funnel/tokenization_funnel_fast.py +++ b/src/transformers/models/funnel/tokenization_funnel_fast.py @@ -41,55 +41,6 @@ _model_names = [ "xlarge-base", ] -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "funnel-transformer/small": "https://huggingface.co/funnel-transformer/small/resolve/main/vocab.txt", - "funnel-transformer/small-base": "https://huggingface.co/funnel-transformer/small-base/resolve/main/vocab.txt", - "funnel-transformer/medium": "https://huggingface.co/funnel-transformer/medium/resolve/main/vocab.txt", - "funnel-transformer/medium-base": ( - "https://huggingface.co/funnel-transformer/medium-base/resolve/main/vocab.txt" - ), - "funnel-transformer/intermediate": ( - "https://huggingface.co/funnel-transformer/intermediate/resolve/main/vocab.txt" - ), - "funnel-transformer/intermediate-base": ( - "https://huggingface.co/funnel-transformer/intermediate-base/resolve/main/vocab.txt" - ), - "funnel-transformer/large": "https://huggingface.co/funnel-transformer/large/resolve/main/vocab.txt", - "funnel-transformer/large-base": "https://huggingface.co/funnel-transformer/large-base/resolve/main/vocab.txt", - "funnel-transformer/xlarge": "https://huggingface.co/funnel-transformer/xlarge/resolve/main/vocab.txt", - "funnel-transformer/xlarge-base": ( - "https://huggingface.co/funnel-transformer/xlarge-base/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "funnel-transformer/small": "https://huggingface.co/funnel-transformer/small/resolve/main/tokenizer.json", - "funnel-transformer/small-base": ( - "https://huggingface.co/funnel-transformer/small-base/resolve/main/tokenizer.json" - ), - "funnel-transformer/medium": "https://huggingface.co/funnel-transformer/medium/resolve/main/tokenizer.json", - "funnel-transformer/medium-base": ( - "https://huggingface.co/funnel-transformer/medium-base/resolve/main/tokenizer.json" - ), - "funnel-transformer/intermediate": ( - "https://huggingface.co/funnel-transformer/intermediate/resolve/main/tokenizer.json" - ), - "funnel-transformer/intermediate-base": ( - "https://huggingface.co/funnel-transformer/intermediate-base/resolve/main/tokenizer.json" - ), - "funnel-transformer/large": "https://huggingface.co/funnel-transformer/large/resolve/main/tokenizer.json", - "funnel-transformer/large-base": ( - "https://huggingface.co/funnel-transformer/large-base/resolve/main/tokenizer.json" - ), - "funnel-transformer/xlarge": "https://huggingface.co/funnel-transformer/xlarge/resolve/main/tokenizer.json", - "funnel-transformer/xlarge-base": ( - "https://huggingface.co/funnel-transformer/xlarge-base/resolve/main/tokenizer.json" - ), - }, -} -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {f"funnel-transformer/{name}": 512 for name in _model_names} -PRETRAINED_INIT_CONFIGURATION = {f"funnel-transformer/{name}": {"do_lower_case": True} for name in _model_names} - class FunnelTokenizerFast(PreTrainedTokenizerFast): r""" @@ -136,10 +87,7 @@ class FunnelTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION slow_tokenizer_class = FunnelTokenizer - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES cls_token_type_id: int = 2 def __init__( diff --git a/src/transformers/models/fuyu/configuration_fuyu.py b/src/transformers/models/fuyu/configuration_fuyu.py index 9376ccb5ef..4f1e5da021 100644 --- a/src/transformers/models/fuyu/configuration_fuyu.py +++ b/src/transformers/models/fuyu/configuration_fuyu.py @@ -21,9 +21,8 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -FUYU_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "adept/fuyu-8b": "https://huggingface.co/adept/fuyu-8b/resolve/main/config.json", -} + +from ..deprecated._archive_maps import FUYU_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class FuyuConfig(PretrainedConfig): diff --git a/src/transformers/models/gemma/configuration_gemma.py b/src/transformers/models/gemma/configuration_gemma.py index cf7be344e8..87e5a2c669 100644 --- a/src/transformers/models/gemma/configuration_gemma.py +++ b/src/transformers/models/gemma/configuration_gemma.py @@ -20,7 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -GEMMA_PRETRAINED_CONFIG_ARCHIVE_MAP = {} + +from ..deprecated._archive_maps import GEMMA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class GemmaConfig(PretrainedConfig): diff --git a/src/transformers/models/git/configuration_git.py b/src/transformers/models/git/configuration_git.py index bfc2b4bf74..0c28bbabff 100644 --- a/src/transformers/models/git/configuration_git.py +++ b/src/transformers/models/git/configuration_git.py @@ -22,9 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -GIT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/git-base": "https://huggingface.co/microsoft/git-base/resolve/main/config.json", -} + +from ..deprecated._archive_maps import GIT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class GitVisionConfig(PretrainedConfig): diff --git a/src/transformers/models/git/modeling_git.py b/src/transformers/models/git/modeling_git.py index c4baed9e0b..c8953d4984 100644 --- a/src/transformers/models/git/modeling_git.py +++ b/src/transformers/models/git/modeling_git.py @@ -45,10 +45,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "microsoft/git-base" _CONFIG_FOR_DOC = "GitConfig" -GIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/git-base", - # See all GIT models at https://huggingface.co/models?filter=git -] + +from ..deprecated._archive_maps import GIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/glpn/configuration_glpn.py b/src/transformers/models/glpn/configuration_glpn.py index 5408ee94a8..c334119216 100644 --- a/src/transformers/models/glpn/configuration_glpn.py +++ b/src/transformers/models/glpn/configuration_glpn.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -GLPN_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "vinvino02/glpn-kitti": "https://huggingface.co/vinvino02/glpn-kitti/resolve/main/config.json", - # See all GLPN models at https://huggingface.co/models?filter=glpn -} + +from ..deprecated._archive_maps import GLPN_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class GLPNConfig(PretrainedConfig): diff --git a/src/transformers/models/glpn/modeling_glpn.py b/src/transformers/models/glpn/modeling_glpn.py index d2ddef5c41..e5d30b6272 100755 --- a/src/transformers/models/glpn/modeling_glpn.py +++ b/src/transformers/models/glpn/modeling_glpn.py @@ -46,10 +46,8 @@ _CONFIG_FOR_DOC = "GLPNConfig" _CHECKPOINT_FOR_DOC = "vinvino02/glpn-kitti" _EXPECTED_OUTPUT_SHAPE = [1, 512, 15, 20] -GLPN_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "vinvino02/glpn-kitti", - # See all GLPN models at https://huggingface.co/models?filter=glpn -] + +from ..deprecated._archive_maps import GLPN_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.beit.modeling_beit.drop_path diff --git a/src/transformers/models/gpt2/configuration_gpt2.py b/src/transformers/models/gpt2/configuration_gpt2.py index 395e2b4873..45495c0012 100644 --- a/src/transformers/models/gpt2/configuration_gpt2.py +++ b/src/transformers/models/gpt2/configuration_gpt2.py @@ -25,13 +25,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "openai-community/gpt2": "https://huggingface.co/openai-community/gpt2/resolve/main/config.json", - "openai-community/gpt2-medium": "https://huggingface.co/openai-community/gpt2-medium/resolve/main/config.json", - "openai-community/gpt2-large": "https://huggingface.co/openai-community/gpt2-large/resolve/main/config.json", - "openai-community/gpt2-xl": "https://huggingface.co/openai-community/gpt2-xl/resolve/main/config.json", - "distilbert/distilgpt2": "https://huggingface.co/distilbert/distilgpt2/resolve/main/config.json", -} + +from ..deprecated._archive_maps import GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class GPT2Config(PretrainedConfig): diff --git a/src/transformers/models/gpt2/modeling_gpt2.py b/src/transformers/models/gpt2/modeling_gpt2.py index e1b357cefb..9511baafca 100644 --- a/src/transformers/models/gpt2/modeling_gpt2.py +++ b/src/transformers/models/gpt2/modeling_gpt2.py @@ -54,14 +54,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "openai-community/gpt2" _CONFIG_FOR_DOC = "GPT2Config" -GPT2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "openai-community/gpt2", - "openai-community/gpt2-medium", - "openai-community/gpt2-large", - "openai-community/gpt2-xl", - "distilbert/distilgpt2", - # See all GPT-2 models at https://huggingface.co/models?filter=gpt2 -] + +from ..deprecated._archive_maps import GPT2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_gpt2(model, config, gpt2_checkpoint_path): diff --git a/src/transformers/models/gpt2/modeling_tf_gpt2.py b/src/transformers/models/gpt2/modeling_tf_gpt2.py index 2c17593e26..26a4e7a398 100644 --- a/src/transformers/models/gpt2/modeling_tf_gpt2.py +++ b/src/transformers/models/gpt2/modeling_tf_gpt2.py @@ -58,14 +58,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "openai-community/gpt2" _CONFIG_FOR_DOC = "GPT2Config" -TF_GPT2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "openai-community/gpt2", - "openai-community/gpt2-medium", - "openai-community/gpt2-large", - "openai-community/gpt2-xl", - "distilbert/distilgpt2", - # See all GPT-2 models at https://huggingface.co/models?filter=openai-community/gpt2 -] + +from ..deprecated._archive_maps import TF_GPT2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFAttention(keras.layers.Layer): diff --git a/src/transformers/models/gpt2/tokenization_gpt2.py b/src/transformers/models/gpt2/tokenization_gpt2.py index 801e997344..36f3ca8fad 100644 --- a/src/transformers/models/gpt2/tokenization_gpt2.py +++ b/src/transformers/models/gpt2/tokenization_gpt2.py @@ -33,31 +33,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "openai-community/gpt2": "https://huggingface.co/openai-community/gpt2/resolve/main/vocab.json", - "openai-community/gpt2-medium": "https://huggingface.co/openai-community/gpt2-medium/resolve/main/vocab.json", - "openai-community/gpt2-large": "https://huggingface.co/openai-community/gpt2-large/resolve/main/vocab.json", - "openai-community/gpt2-xl": "https://huggingface.co/openai-community/gpt2-xl/resolve/main/vocab.json", - "distilbert/distilgpt2": "https://huggingface.co/distilbert/distilgpt2/resolve/main/vocab.json", - }, - "merges_file": { - "openai-community/gpt2": "https://huggingface.co/openai-community/gpt2/resolve/main/merges.txt", - "openai-community/gpt2-medium": "https://huggingface.co/openai-community/gpt2-medium/resolve/main/merges.txt", - "openai-community/gpt2-large": "https://huggingface.co/openai-community/gpt2-large/resolve/main/merges.txt", - "openai-community/gpt2-xl": "https://huggingface.co/openai-community/gpt2-xl/resolve/main/merges.txt", - "distilbert/distilgpt2": "https://huggingface.co/distilbert/distilgpt2/resolve/main/merges.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "openai-community/gpt2": 1024, - "openai-community/gpt2-medium": 1024, - "openai-community/gpt2-large": 1024, - "openai-community/gpt2-xl": 1024, - "distilbert/distilgpt2": 1024, -} - @lru_cache() def bytes_to_unicode(): @@ -154,8 +129,6 @@ class GPT2Tokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/gpt2/tokenization_gpt2_fast.py b/src/transformers/models/gpt2/tokenization_gpt2_fast.py index c4e49d23d1..fb3a5d4a0c 100644 --- a/src/transformers/models/gpt2/tokenization_gpt2_fast.py +++ b/src/transformers/models/gpt2/tokenization_gpt2_fast.py @@ -30,38 +30,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "openai-community/gpt2": "https://huggingface.co/openai-community/gpt2/resolve/main/vocab.json", - "openai-community/gpt2-medium": "https://huggingface.co/openai-community/gpt2-medium/resolve/main/vocab.json", - "openai-community/gpt2-large": "https://huggingface.co/openai-community/gpt2-large/resolve/main/vocab.json", - "openai-community/gpt2-xl": "https://huggingface.co/openai-community/gpt2-xl/resolve/main/vocab.json", - "distilbert/distilgpt2": "https://huggingface.co/distilbert/distilgpt2/resolve/main/vocab.json", - }, - "merges_file": { - "openai-community/gpt2": "https://huggingface.co/openai-community/gpt2/resolve/main/merges.txt", - "openai-community/gpt2-medium": "https://huggingface.co/openai-community/gpt2-medium/resolve/main/merges.txt", - "openai-community/gpt2-large": "https://huggingface.co/openai-community/gpt2-large/resolve/main/merges.txt", - "openai-community/gpt2-xl": "https://huggingface.co/openai-community/gpt2-xl/resolve/main/merges.txt", - "distilbert/distilgpt2": "https://huggingface.co/distilbert/distilgpt2/resolve/main/merges.txt", - }, - "tokenizer_file": { - "openai-community/gpt2": "https://huggingface.co/openai-community/gpt2/resolve/main/tokenizer.json", - "openai-community/gpt2-medium": "https://huggingface.co/openai-community/gpt2-medium/resolve/main/tokenizer.json", - "openai-community/gpt2-large": "https://huggingface.co/openai-community/gpt2-large/resolve/main/tokenizer.json", - "openai-community/gpt2-xl": "https://huggingface.co/openai-community/gpt2-xl/resolve/main/tokenizer.json", - "distilbert/distilgpt2": "https://huggingface.co/distilbert/distilgpt2/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "openai-community/gpt2": 1024, - "openai-community/gpt2-medium": 1024, - "openai-community/gpt2-large": 1024, - "openai-community/gpt2-xl": 1024, - "distilbert/distilgpt2": 1024, -} - class GPT2TokenizerFast(PreTrainedTokenizerFast): """ @@ -115,8 +83,6 @@ class GPT2TokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = GPT2Tokenizer diff --git a/src/transformers/models/gpt_bigcode/configuration_gpt_bigcode.py b/src/transformers/models/gpt_bigcode/configuration_gpt_bigcode.py index 9cbaf3e184..ef5e02ffdc 100644 --- a/src/transformers/models/gpt_bigcode/configuration_gpt_bigcode.py +++ b/src/transformers/models/gpt_bigcode/configuration_gpt_bigcode.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -GPT_BIGCODE_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "bigcode/gpt_bigcode-santacoder": "https://huggingface.co/bigcode/gpt_bigcode-santacoder/resolve/main/config.json", -} + +from ..deprecated._archive_maps import GPT_BIGCODE_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class GPTBigCodeConfig(PretrainedConfig): diff --git a/src/transformers/models/gpt_bigcode/modeling_gpt_bigcode.py b/src/transformers/models/gpt_bigcode/modeling_gpt_bigcode.py index 25938342c2..4e3b849848 100644 --- a/src/transformers/models/gpt_bigcode/modeling_gpt_bigcode.py +++ b/src/transformers/models/gpt_bigcode/modeling_gpt_bigcode.py @@ -52,10 +52,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "bigcode/gpt_bigcode-santacoder" _CONFIG_FOR_DOC = "GPTBigCodeConfig" -GPT_BIGCODE_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "bigcode/gpt_bigcode-santacoder", - # See all GPTBigCode models at https://huggingface.co/models?filter=gpt_bigcode -] + +from ..deprecated._archive_maps import GPT_BIGCODE_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Fused kernels diff --git a/src/transformers/models/gpt_neo/configuration_gpt_neo.py b/src/transformers/models/gpt_neo/configuration_gpt_neo.py index 842614b280..411b392180 100644 --- a/src/transformers/models/gpt_neo/configuration_gpt_neo.py +++ b/src/transformers/models/gpt_neo/configuration_gpt_neo.py @@ -25,10 +25,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -GPT_NEO_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "EleutherAI/gpt-neo-1.3B": "https://huggingface.co/EleutherAI/gpt-neo-1.3B/resolve/main/config.json", - # See all GPTNeo models at https://huggingface.co/models?filter=gpt_neo -} + +from ..deprecated._archive_maps import GPT_NEO_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class GPTNeoConfig(PretrainedConfig): diff --git a/src/transformers/models/gpt_neo/modeling_gpt_neo.py b/src/transformers/models/gpt_neo/modeling_gpt_neo.py index 5e1ca2f191..2fbf4677ca 100755 --- a/src/transformers/models/gpt_neo/modeling_gpt_neo.py +++ b/src/transformers/models/gpt_neo/modeling_gpt_neo.py @@ -67,10 +67,9 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "GPTNeoConfig" -GPT_NEO_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "EleutherAI/gpt-neo-1.3B", - # See all GPTNeo models at https://huggingface.co/models?filter=gpt_neo -] + +from ..deprecated._archive_maps import GPT_NEO_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + _CHECKPOINT_FOR_DOC = "EleutherAI/gpt-neo-1.3B" diff --git a/src/transformers/models/gpt_neox/configuration_gpt_neox.py b/src/transformers/models/gpt_neox/configuration_gpt_neox.py index 99fbb2f7be..a9d20f7a63 100644 --- a/src/transformers/models/gpt_neox/configuration_gpt_neox.py +++ b/src/transformers/models/gpt_neox/configuration_gpt_neox.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -GPT_NEOX_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "EleutherAI/gpt-neox-20b": "https://huggingface.co/EleutherAI/gpt-neox-20b/resolve/main/config.json", - # See all GPTNeoX models at https://huggingface.co/models?filter=gpt_neox -} + +from ..deprecated._archive_maps import GPT_NEOX_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class GPTNeoXConfig(PretrainedConfig): diff --git a/src/transformers/models/gpt_neox/modeling_gpt_neox.py b/src/transformers/models/gpt_neox/modeling_gpt_neox.py index 2ab552f118..83c99202ac 100755 --- a/src/transformers/models/gpt_neox/modeling_gpt_neox.py +++ b/src/transformers/models/gpt_neox/modeling_gpt_neox.py @@ -52,10 +52,8 @@ _CHECKPOINT_FOR_DOC = "trl-internal-testing/tiny-random-GPTNeoXForCausalLM" _REAL_CHECKPOINT_FOR_DOC = "EleutherAI/gpt-neox-20b" _CONFIG_FOR_DOC = "GPTNeoXConfig" -GPT_NEOX_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "EleutherAI/gpt-neox-20b", - # See all GPTNeoX models at https://huggingface.co/models?filter=gpt_neox -] + +from ..deprecated._archive_maps import GPT_NEOX_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.llama.modeling_llama._get_unpad_data diff --git a/src/transformers/models/gpt_neox/tokenization_gpt_neox_fast.py b/src/transformers/models/gpt_neox/tokenization_gpt_neox_fast.py index 16ed6b1e75..dceb512e8f 100644 --- a/src/transformers/models/gpt_neox/tokenization_gpt_neox_fast.py +++ b/src/transformers/models/gpt_neox/tokenization_gpt_neox_fast.py @@ -26,16 +26,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "tokenizer_file": { - "EleutherAI/gpt-neox-20b": "https://huggingface.co/EleutherAI/gpt-neox-20b/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "gpt-neox-20b": 2048, -} - class GPTNeoXTokenizerFast(PreTrainedTokenizerFast): """ @@ -91,8 +81,6 @@ class GPTNeoXTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/gpt_neox_japanese/configuration_gpt_neox_japanese.py b/src/transformers/models/gpt_neox_japanese/configuration_gpt_neox_japanese.py index ddf3d4dec8..8ee73257b6 100644 --- a/src/transformers/models/gpt_neox_japanese/configuration_gpt_neox_japanese.py +++ b/src/transformers/models/gpt_neox_japanese/configuration_gpt_neox_japanese.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -GPT_NEOX_JAPANESE_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "abeja/gpt-neox-japanese-2.7b": "https://huggingface.co/abeja/gpt-neox-japanese-2.7b/resolve/main/config.json", -} + +from ..deprecated._archive_maps import GPT_NEOX_JAPANESE_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class GPTNeoXJapaneseConfig(PretrainedConfig): diff --git a/src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py b/src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py index 4ac7c4d4e0..9fdff2c838 100755 --- a/src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py +++ b/src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py @@ -34,10 +34,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "abeja/gpt-neox-japanese-2.7b" _CONFIG_FOR_DOC = "GPTNeoXJapaneseConfig" -GPT_NEOX_JAPANESE_PRETRAINED_MODEL_ARCHIVE_LIST = { - "https://huggingface.co/abeja/gpt-neox-japanese-2.7b/resolve/main/config.json", - # See all GPTNeoXJapanese models at https://huggingface.co/models?filter=gpt_neox_japanese -} + +from ..deprecated._archive_maps import GPT_NEOX_JAPANESE_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class GPTNeoXJapanesePreTrainedModel(PreTrainedModel): diff --git a/src/transformers/models/gpt_neox_japanese/tokenization_gpt_neox_japanese.py b/src/transformers/models/gpt_neox_japanese/tokenization_gpt_neox_japanese.py index fae50aa8ff..fd0fe796dc 100644 --- a/src/transformers/models/gpt_neox_japanese/tokenization_gpt_neox_japanese.py +++ b/src/transformers/models/gpt_neox_japanese/tokenization_gpt_neox_japanese.py @@ -29,19 +29,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "emoji_file": "emoji.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "abeja/gpt-neox-japanese-2.7b": "https://huggingface.co/abeja/gpt-neox-japanese-2.7b/resolve/main/vocab.txt", - }, - "emoji_file": { - "abeja/gpt-neox-japanese-2.7b": "https://huggingface.co/abeja/gpt-neox-japanese-2.7b/resolve/main/emoji.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "abeja/gpt-neox-japanese-2.7b": 2048, -} - def load_vocab_and_emoji(vocab_file, emoji_file): """Loads a vocabulary file and emoji file into a dictionary.""" @@ -112,8 +99,6 @@ class GPTNeoXJapaneseTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/gpt_sw3/tokenization_gpt_sw3.py b/src/transformers/models/gpt_sw3/tokenization_gpt_sw3.py index d740c13d35..7bb2e51f04 100644 --- a/src/transformers/models/gpt_sw3/tokenization_gpt_sw3.py +++ b/src/transformers/models/gpt_sw3/tokenization_gpt_sw3.py @@ -19,28 +19,6 @@ if is_torch_available(): logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "AI-Sweden-Models/gpt-sw3-126m": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-126m/resolve/main/spiece.model", - "AI-Sweden-Models/gpt-sw3-356m": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-356m/resolve/main/spiece.model", - "AI-Sweden-Models/gpt-sw3-1.3b": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-1.3b/resolve/main/spiece.model", - "AI-Sweden-Models/gpt-sw3-6.7b": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b/resolve/main/spiece.model", - "AI-Sweden-Models/gpt-sw3-6.7b-v2": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b-v2/resolve/main/spiece.model", - "AI-Sweden-Models/gpt-sw3-20b": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-20b/resolve/main/spiece.model", - "AI-Sweden-Models/gpt-sw3-40b": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-20b/resolve/main/spiece.model", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "AI-Sweden-Models/gpt-sw3-126m": 2048, - "AI-Sweden-Models/gpt-sw3-356m": 2048, - "AI-Sweden-Models/gpt-sw3-1.3b": 2048, - "AI-Sweden-Models/gpt-sw3-6.7b": 2048, - "AI-Sweden-Models/gpt-sw3-6.7b-v2": 2048, - "AI-Sweden-Models/gpt-sw3-20b": 2048, - "AI-Sweden-Models/gpt-sw3-40b": 2048, -} - class GPTSw3Tokenizer(PreTrainedTokenizer): """ @@ -105,8 +83,6 @@ class GPTSw3Tokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/gptj/configuration_gptj.py b/src/transformers/models/gptj/configuration_gptj.py index 47b1224279..56d6042764 100644 --- a/src/transformers/models/gptj/configuration_gptj.py +++ b/src/transformers/models/gptj/configuration_gptj.py @@ -24,10 +24,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -GPTJ_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "EleutherAI/gpt-j-6B": "https://huggingface.co/EleutherAI/gpt-j-6B/resolve/main/config.json", - # See all GPT-J models at https://huggingface.co/models?filter=gpt_j -} + +from ..deprecated._archive_maps import GPTJ_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class GPTJConfig(PretrainedConfig): diff --git a/src/transformers/models/gptj/modeling_gptj.py b/src/transformers/models/gptj/modeling_gptj.py index 144dbba055..3c6ddac4ec 100644 --- a/src/transformers/models/gptj/modeling_gptj.py +++ b/src/transformers/models/gptj/modeling_gptj.py @@ -57,10 +57,7 @@ _REAL_CHECKPOINT_FOR_DOC = "EleutherAI/gpt-j-6B" _CONFIG_FOR_DOC = "GPTJConfig" -GPTJ_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "EleutherAI/gpt-j-6B", - # See all GPT-J models at https://huggingface.co/models?filter=gptj -] +from ..deprecated._archive_maps import GPTJ_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.llama.modeling_llama._get_unpad_data diff --git a/src/transformers/models/gptj/modeling_tf_gptj.py b/src/transformers/models/gptj/modeling_tf_gptj.py index d948fc63c0..5c315b5b66 100644 --- a/src/transformers/models/gptj/modeling_tf_gptj.py +++ b/src/transformers/models/gptj/modeling_tf_gptj.py @@ -55,11 +55,6 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "EleutherAI/gpt-j-6B" _CONFIG_FOR_DOC = "GPTJConfig" -GPTJ_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "EleutherAI/gpt-j-6B", - # See all GPT-J models at https://huggingface.co/models?filter=gptj -] - def create_sinusoidal_positions(num_pos: int, dim: int) -> tf.Tensor: inv_freq = tf.cast(1.0 / (10000 ** (tf.range(0, dim, 2) / dim)), tf.float32) diff --git a/src/transformers/models/gptsan_japanese/configuration_gptsan_japanese.py b/src/transformers/models/gptsan_japanese/configuration_gptsan_japanese.py index c25e4b0e1e..e0a17d1c11 100644 --- a/src/transformers/models/gptsan_japanese/configuration_gptsan_japanese.py +++ b/src/transformers/models/gptsan_japanese/configuration_gptsan_japanese.py @@ -19,11 +19,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -GPTSAN_JAPANESE_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "tanreinama/GPTSAN-2.8B-spout_is_uniform": ( - "https://huggingface.co/tanreinama/GPTSAN-2.8B-spout_is_uniform/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import GPTSAN_JAPANESE_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class GPTSanJapaneseConfig(PretrainedConfig): diff --git a/src/transformers/models/gptsan_japanese/modeling_gptsan_japanese.py b/src/transformers/models/gptsan_japanese/modeling_gptsan_japanese.py index d9b7003050..59252bc567 100644 --- a/src/transformers/models/gptsan_japanese/modeling_gptsan_japanese.py +++ b/src/transformers/models/gptsan_japanese/modeling_gptsan_japanese.py @@ -44,10 +44,8 @@ _CHECKPOINT_FOR_DOC = "Tanrei/GPTSAN-japanese" # This dict contains ids and associated url # for the pretrained weights provided with the models #################################################### -GPTSAN_JAPANESE_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Tanrei/GPTSAN-japanese", - # See all GPTSAN-japanese models at https://huggingface.co/models?filter=gptsan-japanese -] + +from ..deprecated._archive_maps import GPTSAN_JAPANESE_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.switch_transformers.modeling_switch_transformers.router_z_loss_func diff --git a/src/transformers/models/gptsan_japanese/tokenization_gptsan_japanese.py b/src/transformers/models/gptsan_japanese/tokenization_gptsan_japanese.py index df3f94dc1e..2a2b465d8c 100644 --- a/src/transformers/models/gptsan_japanese/tokenization_gptsan_japanese.py +++ b/src/transformers/models/gptsan_japanese/tokenization_gptsan_japanese.py @@ -37,19 +37,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "emoji_file": "emoji.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "Tanrei/GPTSAN-japanese": "https://huggingface.co/Tanrei/GPTSAN-japanese/blob/main/vocab.txt", - }, - "emoji_file": { - "Tanrei/GPTSAN-japanese": "https://huggingface.co/Tanrei/GPTSAN-japanese/blob/main/emoji.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "Tanrei/GPTSAN-japanese": 1280, -} - def load_vocab_and_emoji(vocab_file, emoji_file): """Loads a vocabulary file and emoji file into a dictionary.""" @@ -150,8 +137,6 @@ class GPTSanJapaneseTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask", "token_type_ids"] def __init__( diff --git a/src/transformers/models/graphormer/configuration_graphormer.py b/src/transformers/models/graphormer/configuration_graphormer.py index 9d49fbea29..8d1f135984 100644 --- a/src/transformers/models/graphormer/configuration_graphormer.py +++ b/src/transformers/models/graphormer/configuration_graphormer.py @@ -20,11 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -GRAPHORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - # pcqm4mv1 now deprecated - "graphormer-base": "https://huggingface.co/clefourrier/graphormer-base-pcqm4mv2/resolve/main/config.json", - # See all Graphormer models at https://huggingface.co/models?filter=graphormer -} + +from ..deprecated._archive_maps import GRAPHORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class GraphormerConfig(PretrainedConfig): diff --git a/src/transformers/models/graphormer/modeling_graphormer.py b/src/transformers/models/graphormer/modeling_graphormer.py index ec56d8eda0..8b484fe1e4 100755 --- a/src/transformers/models/graphormer/modeling_graphormer.py +++ b/src/transformers/models/graphormer/modeling_graphormer.py @@ -37,11 +37,7 @@ _CHECKPOINT_FOR_DOC = "graphormer-base-pcqm4mv1" _CONFIG_FOR_DOC = "GraphormerConfig" -GRAPHORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "clefourrier/graphormer-base-pcqm4mv1", - "clefourrier/graphormer-base-pcqm4mv2", - # See all Graphormer models at https://huggingface.co/models?filter=graphormer -] +from ..deprecated._archive_maps import GRAPHORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def quant_noise(module: nn.Module, p: float, block_size: int): diff --git a/src/transformers/models/groupvit/configuration_groupvit.py b/src/transformers/models/groupvit/configuration_groupvit.py index bfec885244..3c46c277f3 100644 --- a/src/transformers/models/groupvit/configuration_groupvit.py +++ b/src/transformers/models/groupvit/configuration_groupvit.py @@ -30,9 +30,8 @@ if TYPE_CHECKING: logger = logging.get_logger(__name__) -GROUPVIT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "nvidia/groupvit-gcc-yfcc": "https://huggingface.co/nvidia/groupvit-gcc-yfcc/resolve/main/config.json", -} + +from ..deprecated._archive_maps import GROUPVIT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class GroupViTTextConfig(PretrainedConfig): diff --git a/src/transformers/models/groupvit/modeling_groupvit.py b/src/transformers/models/groupvit/modeling_groupvit.py index c99c96ec87..ec383b0fcf 100644 --- a/src/transformers/models/groupvit/modeling_groupvit.py +++ b/src/transformers/models/groupvit/modeling_groupvit.py @@ -43,10 +43,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "nvidia/groupvit-gcc-yfcc" -GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "nvidia/groupvit-gcc-yfcc", - # See all GroupViT models at https://huggingface.co/models?filter=groupvit -] + +from ..deprecated._archive_maps import GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # contrastive loss function, adapted from diff --git a/src/transformers/models/groupvit/modeling_tf_groupvit.py b/src/transformers/models/groupvit/modeling_tf_groupvit.py index d04f9afb7d..31c76083e0 100644 --- a/src/transformers/models/groupvit/modeling_tf_groupvit.py +++ b/src/transformers/models/groupvit/modeling_tf_groupvit.py @@ -66,10 +66,8 @@ if is_tensorflow_probability_available(): _CHECKPOINT_FOR_DOC = "nvidia/groupvit-gcc-yfcc" -TF_GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "nvidia/groupvit-gcc-yfcc", - # See all GroupViT models at https://huggingface.co/models?filter=groupvit -] + +from ..deprecated._archive_maps import TF_GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 LARGE_NEGATIVE = -1e8 diff --git a/src/transformers/models/herbert/tokenization_herbert.py b/src/transformers/models/herbert/tokenization_herbert.py index 1747a59c6f..6e37922028 100644 --- a/src/transformers/models/herbert/tokenization_herbert.py +++ b/src/transformers/models/herbert/tokenization_herbert.py @@ -29,18 +29,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "allegro/herbert-base-cased": "https://huggingface.co/allegro/herbert-base-cased/resolve/main/vocab.json" - }, - "merges_file": { - "allegro/herbert-base-cased": "https://huggingface.co/allegro/herbert-base-cased/resolve/main/merges.txt" - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"allegro/herbert-base-cased": 514} -PRETRAINED_INIT_CONFIGURATION = {} - # Copied from transformers.models.xlm.tokenization_xlm.get_pairs def get_pairs(word): @@ -302,9 +290,6 @@ class HerbertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/herbert/tokenization_herbert_fast.py b/src/transformers/models/herbert/tokenization_herbert_fast.py index 67e38c1c5e..4cd5db58f1 100644 --- a/src/transformers/models/herbert/tokenization_herbert_fast.py +++ b/src/transformers/models/herbert/tokenization_herbert_fast.py @@ -24,18 +24,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "allegro/herbert-base-cased": "https://huggingface.co/allegro/herbert-base-cased/resolve/main/vocab.json" - }, - "merges_file": { - "allegro/herbert-base-cased": "https://huggingface.co/allegro/herbert-base-cased/resolve/main/merges.txt" - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"allegro/herbert-base-cased": 514} -PRETRAINED_INIT_CONFIGURATION = {} - class HerbertTokenizerFast(PreTrainedTokenizerFast): """ @@ -57,9 +45,6 @@ class HerbertTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = HerbertTokenizer def __init__( diff --git a/src/transformers/models/hubert/configuration_hubert.py b/src/transformers/models/hubert/configuration_hubert.py index 3067c6efb1..00a3244a31 100644 --- a/src/transformers/models/hubert/configuration_hubert.py +++ b/src/transformers/models/hubert/configuration_hubert.py @@ -23,10 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -HUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/hubert-base-ls960": "https://huggingface.co/facebook/hubert-base-ls960/resolve/main/config.json", - # See all Hubert models at https://huggingface.co/models?filter=hubert -} + +from ..deprecated._archive_maps import HUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class HubertConfig(PretrainedConfig): diff --git a/src/transformers/models/hubert/modeling_hubert.py b/src/transformers/models/hubert/modeling_hubert.py index a45dcb2d11..f9e223f9a3 100755 --- a/src/transformers/models/hubert/modeling_hubert.py +++ b/src/transformers/models/hubert/modeling_hubert.py @@ -58,10 +58,7 @@ _SEQ_CLASS_EXPECTED_OUTPUT = "'_unknown_'" _SEQ_CLASS_EXPECTED_LOSS = 8.53 -HUBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/hubert-base-ls960", - # See all Hubert models at https://huggingface.co/models?filter=hubert -] +from ..deprecated._archive_maps import HUBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.wav2vec2.modeling_wav2vec2._compute_mask_indices diff --git a/src/transformers/models/hubert/modeling_tf_hubert.py b/src/transformers/models/hubert/modeling_tf_hubert.py index 258763beb1..0dc696f8a7 100644 --- a/src/transformers/models/hubert/modeling_tf_hubert.py +++ b/src/transformers/models/hubert/modeling_tf_hubert.py @@ -45,10 +45,9 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "HubertConfig" -TF_HUBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/hubert-base-ls960", - # See all Hubert models at https://huggingface.co/models?filter=hubert -] + +from ..deprecated._archive_maps import TF_HUBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + LARGE_NEGATIVE = -1e8 diff --git a/src/transformers/models/ibert/configuration_ibert.py b/src/transformers/models/ibert/configuration_ibert.py index 249061ceae..94e040d417 100644 --- a/src/transformers/models/ibert/configuration_ibert.py +++ b/src/transformers/models/ibert/configuration_ibert.py @@ -25,13 +25,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -IBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "kssteven/ibert-roberta-base": "https://huggingface.co/kssteven/ibert-roberta-base/resolve/main/config.json", - "kssteven/ibert-roberta-large": "https://huggingface.co/kssteven/ibert-roberta-large/resolve/main/config.json", - "kssteven/ibert-roberta-large-mnli": ( - "https://huggingface.co/kssteven/ibert-roberta-large-mnli/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import IBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class IBertConfig(PretrainedConfig): diff --git a/src/transformers/models/ibert/modeling_ibert.py b/src/transformers/models/ibert/modeling_ibert.py index 0dcdaaf699..54c37f507e 100644 --- a/src/transformers/models/ibert/modeling_ibert.py +++ b/src/transformers/models/ibert/modeling_ibert.py @@ -47,11 +47,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "kssteven/ibert-roberta-base" _CONFIG_FOR_DOC = "IBertConfig" -IBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "kssteven/ibert-roberta-base", - "kssteven/ibert-roberta-large", - "kssteven/ibert-roberta-large-mnli", -] + +from ..deprecated._archive_maps import IBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class IBertEmbeddings(nn.Module): diff --git a/src/transformers/models/idefics/configuration_idefics.py b/src/transformers/models/idefics/configuration_idefics.py index a61c96e0a4..07a92432ae 100644 --- a/src/transformers/models/idefics/configuration_idefics.py +++ b/src/transformers/models/idefics/configuration_idefics.py @@ -25,10 +25,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -IDEFICS_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "HuggingFaceM4/idefics-9b": "https://huggingface.co/HuggingFaceM4/idefics-9b/blob/main/config.json", - "HuggingFaceM4/idefics-80b": "https://huggingface.co/HuggingFaceM4/idefics-80b/blob/main/config.json", -} + +from ..deprecated._archive_maps import IDEFICS_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class IdeficsVisionConfig(PretrainedConfig): diff --git a/src/transformers/models/idefics/modeling_idefics.py b/src/transformers/models/idefics/modeling_idefics.py index 0023fd2014..47024d24e6 100644 --- a/src/transformers/models/idefics/modeling_idefics.py +++ b/src/transformers/models/idefics/modeling_idefics.py @@ -48,11 +48,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "IdeficsConfig" -IDEFICS_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "HuggingFaceM4/idefics-9b", - "HuggingFaceM4/idefics-80b", - # See all Idefics models at https://huggingface.co/models?filter=idefics -] + +from ..deprecated._archive_maps import IDEFICS_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/imagegpt/configuration_imagegpt.py b/src/transformers/models/imagegpt/configuration_imagegpt.py index 85f44a4e34..2a8d62f9b5 100644 --- a/src/transformers/models/imagegpt/configuration_imagegpt.py +++ b/src/transformers/models/imagegpt/configuration_imagegpt.py @@ -27,11 +27,8 @@ if TYPE_CHECKING: logger = logging.get_logger(__name__) -IMAGEGPT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "openai/imagegpt-small": "", - "openai/imagegpt-medium": "", - "openai/imagegpt-large": "", -} + +from ..deprecated._archive_maps import IMAGEGPT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ImageGPTConfig(PretrainedConfig): diff --git a/src/transformers/models/imagegpt/modeling_imagegpt.py b/src/transformers/models/imagegpt/modeling_imagegpt.py index 33f7ee99c4..3b9be17246 100755 --- a/src/transformers/models/imagegpt/modeling_imagegpt.py +++ b/src/transformers/models/imagegpt/modeling_imagegpt.py @@ -42,12 +42,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "openai/imagegpt-small" _CONFIG_FOR_DOC = "ImageGPTConfig" -IMAGEGPT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "openai/imagegpt-small", - "openai/imagegpt-medium", - "openai/imagegpt-large", - # See all Image GPT models at https://huggingface.co/models?filter=imagegpt -] + +from ..deprecated._archive_maps import IMAGEGPT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_imagegpt(model, config, imagegpt_checkpoint_path): diff --git a/src/transformers/models/informer/configuration_informer.py b/src/transformers/models/informer/configuration_informer.py index dedf09bb2b..93b3f3556c 100644 --- a/src/transformers/models/informer/configuration_informer.py +++ b/src/transformers/models/informer/configuration_informer.py @@ -22,12 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -INFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "huggingface/informer-tourism-monthly": ( - "https://huggingface.co/huggingface/informer-tourism-monthly/resolve/main/config.json" - ), - # See all Informer models at https://huggingface.co/models?filter=informer -} + +from ..deprecated._archive_maps import INFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class InformerConfig(PretrainedConfig): diff --git a/src/transformers/models/informer/modeling_informer.py b/src/transformers/models/informer/modeling_informer.py index 0fe108a640..2955eb7a6a 100644 --- a/src/transformers/models/informer/modeling_informer.py +++ b/src/transformers/models/informer/modeling_informer.py @@ -40,10 +40,7 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "InformerConfig" -INFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "huggingface/informer-tourism-monthly", - # See all Informer models at https://huggingface.co/models?filter=informer -] +from ..deprecated._archive_maps import INFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesFeatureEmbedder with TimeSeries->Informer diff --git a/src/transformers/models/instructblip/configuration_instructblip.py b/src/transformers/models/instructblip/configuration_instructblip.py index 98c06d2fe8..152389d337 100644 --- a/src/transformers/models/instructblip/configuration_instructblip.py +++ b/src/transformers/models/instructblip/configuration_instructblip.py @@ -25,9 +25,8 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -INSTRUCTBLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "Salesforce/instruct-blip-flan-t5": "https://huggingface.co/Salesforce/instruct-blip-flan-t5/resolve/main/config.json", -} + +from ..deprecated._archive_maps import INSTRUCTBLIP_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class InstructBlipVisionConfig(PretrainedConfig): diff --git a/src/transformers/models/instructblip/modeling_instructblip.py b/src/transformers/models/instructblip/modeling_instructblip.py index ba78b9143d..b18d467231 100644 --- a/src/transformers/models/instructblip/modeling_instructblip.py +++ b/src/transformers/models/instructblip/modeling_instructblip.py @@ -47,10 +47,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "Salesforce/instructblip-flan-t5-xl" -INSTRUCTBLIP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Salesforce/instructblip-flan-t5-xl", - # See all InstructBLIP models at https://huggingface.co/models?filter=instructblip -] + +from ..deprecated._archive_maps import INSTRUCTBLIP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/jukebox/configuration_jukebox.py b/src/transformers/models/jukebox/configuration_jukebox.py index d4a8f0a007..4c68051310 100644 --- a/src/transformers/models/jukebox/configuration_jukebox.py +++ b/src/transformers/models/jukebox/configuration_jukebox.py @@ -23,10 +23,9 @@ from ...utils import logging logger = logging.get_logger(__name__) -JUKEBOX_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "openai/jukebox-5b-lyrics": "https://huggingface.co/openai/jukebox-5b-lyrics/blob/main/config.json", - "openai/jukebox-1b-lyrics": "https://huggingface.co/openai/jukebox-1b-lyrics/blob/main/config.json", -} + +from ..deprecated._archive_maps import JUKEBOX_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 + _LARGE_ATTENTION = [ "block_attn", diff --git a/src/transformers/models/jukebox/modeling_jukebox.py b/src/transformers/models/jukebox/modeling_jukebox.py index 236d1f4ff3..282cfdc5b4 100755 --- a/src/transformers/models/jukebox/modeling_jukebox.py +++ b/src/transformers/models/jukebox/modeling_jukebox.py @@ -33,11 +33,8 @@ from .configuration_jukebox import ATTENTION_PATTERNS, JukeboxConfig, JukeboxPri logger = logging.get_logger(__name__) -JUKEBOX_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "openai/jukebox-1b-lyrics", - "openai/jukebox-5b-lyrics", - # See all Jukebox models at https://huggingface.co/models?filter=jukebox -] + +from ..deprecated._archive_maps import JUKEBOX_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def filter_logits(logits, top_k=0, top_p=0.0, filter_value=-float("Inf")): diff --git a/src/transformers/models/jukebox/tokenization_jukebox.py b/src/transformers/models/jukebox/tokenization_jukebox.py index 0eb4b0961f..cd478d6f6b 100644 --- a/src/transformers/models/jukebox/tokenization_jukebox.py +++ b/src/transformers/models/jukebox/tokenization_jukebox.py @@ -39,22 +39,6 @@ VOCAB_FILES_NAMES = { "genres_file": "genres.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "artists_file": { - "jukebox": "https://huggingface.co/ArthurZ/jukebox/blob/main/artists.json", - }, - "genres_file": { - "jukebox": "https://huggingface.co/ArthurZ/jukebox/blob/main/genres.json", - }, - "lyrics_file": { - "jukebox": "https://huggingface.co/ArthurZ/jukebox/blob/main/lyrics.json", - }, -} - -PRETRAINED_LYRIC_TOKENS_SIZES = { - "jukebox": 512, -} - class JukeboxTokenizer(PreTrainedTokenizer): """ @@ -112,8 +96,6 @@ class JukeboxTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_lyric_input_size = PRETRAINED_LYRIC_TOKENS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/kosmos2/configuration_kosmos2.py b/src/transformers/models/kosmos2/configuration_kosmos2.py index 198016a928..ae5afd637b 100644 --- a/src/transformers/models/kosmos2/configuration_kosmos2.py +++ b/src/transformers/models/kosmos2/configuration_kosmos2.py @@ -23,12 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -KOSMOS2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/kosmos-2-patch14-224": ( - "https://huggingface.co/microsoft/kosmos-2-patch14-224/resolve/main/config.json" - ), - # See all KOSMOS-2 models at https://huggingface.co/models?filter=kosmos-2 -} + +from ..deprecated._archive_maps import KOSMOS2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Kosmos2TextConfig(PretrainedConfig): diff --git a/src/transformers/models/kosmos2/modeling_kosmos2.py b/src/transformers/models/kosmos2/modeling_kosmos2.py index 7bbbbe8d76..2e3a945c33 100644 --- a/src/transformers/models/kosmos2/modeling_kosmos2.py +++ b/src/transformers/models/kosmos2/modeling_kosmos2.py @@ -46,10 +46,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = Kosmos2Config -KOSMOS2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/kosmos-2-patch14-224", - # See all KOSMOS-2 models at https://huggingface.co/models?filter=kosmos-2 -] + +from ..deprecated._archive_maps import KOSMOS2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def _expand_mask(mask: torch.Tensor, dtype: torch.dtype, tgt_len: Optional[int] = None): diff --git a/src/transformers/models/layoutlm/configuration_layoutlm.py b/src/transformers/models/layoutlm/configuration_layoutlm.py index 77d62ded40..c7c6886fed 100644 --- a/src/transformers/models/layoutlm/configuration_layoutlm.py +++ b/src/transformers/models/layoutlm/configuration_layoutlm.py @@ -23,14 +23,8 @@ from ...utils import TensorType, is_torch_available, logging logger = logging.get_logger(__name__) -LAYOUTLM_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/layoutlm-base-uncased": ( - "https://huggingface.co/microsoft/layoutlm-base-uncased/resolve/main/config.json" - ), - "microsoft/layoutlm-large-uncased": ( - "https://huggingface.co/microsoft/layoutlm-large-uncased/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import LAYOUTLM_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class LayoutLMConfig(PretrainedConfig): diff --git a/src/transformers/models/layoutlm/modeling_layoutlm.py b/src/transformers/models/layoutlm/modeling_layoutlm.py index c2ecede73d..c570fdb124 100644 --- a/src/transformers/models/layoutlm/modeling_layoutlm.py +++ b/src/transformers/models/layoutlm/modeling_layoutlm.py @@ -43,10 +43,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "LayoutLMConfig" _CHECKPOINT_FOR_DOC = "microsoft/layoutlm-base-uncased" -LAYOUTLM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "layoutlm-base-uncased", - "layoutlm-large-uncased", -] + +from ..deprecated._archive_maps import LAYOUTLM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 LayoutLMLayerNorm = nn.LayerNorm @@ -613,7 +611,6 @@ class LayoutLMPreTrainedModel(PreTrainedModel): """ config_class = LayoutLMConfig - pretrained_model_archive_map = LAYOUTLM_PRETRAINED_MODEL_ARCHIVE_LIST base_model_prefix = "layoutlm" supports_gradient_checkpointing = True diff --git a/src/transformers/models/layoutlm/modeling_tf_layoutlm.py b/src/transformers/models/layoutlm/modeling_tf_layoutlm.py index 21e7c64069..0125fc3ed6 100644 --- a/src/transformers/models/layoutlm/modeling_tf_layoutlm.py +++ b/src/transformers/models/layoutlm/modeling_tf_layoutlm.py @@ -54,10 +54,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "LayoutLMConfig" -TF_LAYOUTLM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/layoutlm-base-uncased", - "microsoft/layoutlm-large-uncased", -] + +from ..deprecated._archive_maps import TF_LAYOUTLM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFLayoutLMEmbeddings(keras.layers.Layer): diff --git a/src/transformers/models/layoutlm/tokenization_layoutlm.py b/src/transformers/models/layoutlm/tokenization_layoutlm.py index 6105d5d77c..836b1aab88 100644 --- a/src/transformers/models/layoutlm/tokenization_layoutlm.py +++ b/src/transformers/models/layoutlm/tokenization_layoutlm.py @@ -27,27 +27,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/layoutlm-base-uncased": ( - "https://huggingface.co/microsoft/layoutlm-base-uncased/resolve/main/vocab.txt" - ), - "microsoft/layoutlm-large-uncased": ( - "https://huggingface.co/microsoft/layoutlm-large-uncased/resolve/main/vocab.txt" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/layoutlm-base-uncased": 512, - "microsoft/layoutlm-large-uncased": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/layoutlm-base-uncased": {"do_lower_case": True}, - "microsoft/layoutlm-large-uncased": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert.load_vocab def load_vocab(vocab_file): @@ -115,9 +94,6 @@ class LayoutLMTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/layoutlm/tokenization_layoutlm_fast.py b/src/transformers/models/layoutlm/tokenization_layoutlm_fast.py index c0bc1072f7..fa3d95132b 100644 --- a/src/transformers/models/layoutlm/tokenization_layoutlm_fast.py +++ b/src/transformers/models/layoutlm/tokenization_layoutlm_fast.py @@ -28,35 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/layoutlm-base-uncased": ( - "https://huggingface.co/microsoft/layoutlm-base-uncased/resolve/main/vocab.txt" - ), - "microsoft/layoutlm-large-uncased": ( - "https://huggingface.co/microsoft/layoutlm-large-uncased/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "microsoft/layoutlm-base-uncased": ( - "https://huggingface.co/microsoft/layoutlm-base-uncased/resolve/main/tokenizer.json" - ), - "microsoft/layoutlm-large-uncased": ( - "https://huggingface.co/microsoft/layoutlm-large-uncased/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/layoutlm-base-uncased": 512, - "microsoft/layoutlm-large-uncased": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/layoutlm-base-uncased": {"do_lower_case": True}, - "microsoft/layoutlm-large-uncased": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert_fast.BertTokenizerFast with Bert->LayoutLM,BERT->LayoutLM class LayoutLMTokenizerFast(PreTrainedTokenizerFast): @@ -100,9 +71,6 @@ class LayoutLMTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = LayoutLMTokenizer def __init__( diff --git a/src/transformers/models/layoutlmv2/configuration_layoutlmv2.py b/src/transformers/models/layoutlmv2/configuration_layoutlmv2.py index 839cfd18ed..4528923a5d 100644 --- a/src/transformers/models/layoutlmv2/configuration_layoutlmv2.py +++ b/src/transformers/models/layoutlmv2/configuration_layoutlmv2.py @@ -20,11 +20,9 @@ from ...utils import is_detectron2_available, logging logger = logging.get_logger(__name__) -LAYOUTLMV2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "layoutlmv2-base-uncased": "https://huggingface.co/microsoft/layoutlmv2-base-uncased/resolve/main/config.json", - "layoutlmv2-large-uncased": "https://huggingface.co/microsoft/layoutlmv2-large-uncased/resolve/main/config.json", - # See all LayoutLMv2 models at https://huggingface.co/models?filter=layoutlmv2 -} + +from ..deprecated._archive_maps import LAYOUTLMV2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 + # soft dependency if is_detectron2_available(): diff --git a/src/transformers/models/layoutlmv2/modeling_layoutlmv2.py b/src/transformers/models/layoutlmv2/modeling_layoutlmv2.py index 4a85923cb9..41939b044a 100755 --- a/src/transformers/models/layoutlmv2/modeling_layoutlmv2.py +++ b/src/transformers/models/layoutlmv2/modeling_layoutlmv2.py @@ -53,11 +53,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "microsoft/layoutlmv2-base-uncased" _CONFIG_FOR_DOC = "LayoutLMv2Config" -LAYOUTLMV2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/layoutlmv2-base-uncased", - "microsoft/layoutlmv2-large-uncased", - # See all LayoutLMv2 models at https://huggingface.co/models?filter=layoutlmv2 -] + +from ..deprecated._archive_maps import LAYOUTLMV2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class LayoutLMv2Embeddings(nn.Module): @@ -489,7 +486,6 @@ class LayoutLMv2PreTrainedModel(PreTrainedModel): """ config_class = LayoutLMv2Config - pretrained_model_archive_map = LAYOUTLMV2_PRETRAINED_MODEL_ARCHIVE_LIST base_model_prefix = "layoutlmv2" def _init_weights(self, module): diff --git a/src/transformers/models/layoutlmv2/tokenization_layoutlmv2.py b/src/transformers/models/layoutlmv2/tokenization_layoutlmv2.py index b09bd08715..c9a138391e 100644 --- a/src/transformers/models/layoutlmv2/tokenization_layoutlmv2.py +++ b/src/transformers/models/layoutlmv2/tokenization_layoutlmv2.py @@ -36,29 +36,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/layoutlmv2-base-uncased": ( - "https://huggingface.co/microsoft/layoutlmv2-base-uncased/resolve/main/vocab.txt" - ), - "microsoft/layoutlmv2-large-uncased": ( - "https://huggingface.co/microsoft/layoutlmv2-large-uncased/resolve/main/vocab.txt" - ), - } -} - - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/layoutlmv2-base-uncased": 512, - "microsoft/layoutlmv2-large-uncased": 512, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/layoutlmv2-base-uncased": {"do_lower_case": True}, - "microsoft/layoutlmv2-large-uncased": {"do_lower_case": True}, -} - LAYOUTLMV2_ENCODE_KWARGS_DOCSTRING = r""" add_special_tokens (`bool`, *optional*, defaults to `True`): @@ -218,9 +195,6 @@ class LayoutLMv2Tokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION def __init__( self, diff --git a/src/transformers/models/layoutlmv2/tokenization_layoutlmv2_fast.py b/src/transformers/models/layoutlmv2/tokenization_layoutlmv2_fast.py index bed4e133aa..aa2bf6b322 100644 --- a/src/transformers/models/layoutlmv2/tokenization_layoutlmv2_fast.py +++ b/src/transformers/models/layoutlmv2/tokenization_layoutlmv2_fast.py @@ -45,27 +45,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/layoutlmv2-base-uncased": ( - "https://huggingface.co/microsoft/layoutlmv2-base-uncased/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "microsoft/layoutlmv2-base-uncased": ( - "https://huggingface.co/microsoft/layoutlmv2-base-uncased/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/layoutlmv2-base-uncased": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/layoutlmv2-base-uncased": {"do_lower_case": True}, -} - class LayoutLMv2TokenizerFast(PreTrainedTokenizerFast): r""" @@ -114,9 +93,6 @@ class LayoutLMv2TokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = LayoutLMv2Tokenizer def __init__( diff --git a/src/transformers/models/layoutlmv3/configuration_layoutlmv3.py b/src/transformers/models/layoutlmv3/configuration_layoutlmv3.py index d7cddb6002..d6f9b6c9f1 100644 --- a/src/transformers/models/layoutlmv3/configuration_layoutlmv3.py +++ b/src/transformers/models/layoutlmv3/configuration_layoutlmv3.py @@ -32,9 +32,8 @@ if TYPE_CHECKING: logger = logging.get_logger(__name__) -LAYOUTLMV3_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/layoutlmv3-base": "https://huggingface.co/microsoft/layoutlmv3-base/resolve/main/config.json", -} + +from ..deprecated._archive_maps import LAYOUTLMV3_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class LayoutLMv3Config(PretrainedConfig): diff --git a/src/transformers/models/layoutlmv3/modeling_layoutlmv3.py b/src/transformers/models/layoutlmv3/modeling_layoutlmv3.py index 3148155a43..0db2bd775f 100644 --- a/src/transformers/models/layoutlmv3/modeling_layoutlmv3.py +++ b/src/transformers/models/layoutlmv3/modeling_layoutlmv3.py @@ -41,11 +41,9 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "LayoutLMv3Config" -LAYOUTLMV3_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/layoutlmv3-base", - "microsoft/layoutlmv3-large", - # See all LayoutLMv3 models at https://huggingface.co/models?filter=layoutlmv3 -] + +from ..deprecated._archive_maps import LAYOUTLMV3_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + LAYOUTLMV3_START_DOCSTRING = r""" This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) sub-class. Use diff --git a/src/transformers/models/layoutlmv3/modeling_tf_layoutlmv3.py b/src/transformers/models/layoutlmv3/modeling_tf_layoutlmv3.py index b52cfba54c..531eb59d87 100644 --- a/src/transformers/models/layoutlmv3/modeling_tf_layoutlmv3.py +++ b/src/transformers/models/layoutlmv3/modeling_tf_layoutlmv3.py @@ -57,11 +57,9 @@ _DUMMY_BBOX = [ [[13, 14, 15, 16], [17, 18, 19, 20], [21, 22, 23, 24]], ] -TF_LAYOUTLMV3_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/layoutlmv3-base", - "microsoft/layoutlmv3-large", - # See all LayoutLMv3 models at https://huggingface.co/models?filter=layoutlmv3 -] + +from ..deprecated._archive_maps import TF_LAYOUTLMV3_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + LARGE_NEGATIVE = -1e8 diff --git a/src/transformers/models/layoutlmv3/tokenization_layoutlmv3.py b/src/transformers/models/layoutlmv3/tokenization_layoutlmv3.py index 351e811b81..89f899f22f 100644 --- a/src/transformers/models/layoutlmv3/tokenization_layoutlmv3.py +++ b/src/transformers/models/layoutlmv3/tokenization_layoutlmv3.py @@ -40,22 +40,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/layoutlmv3-base": "https://huggingface.co/microsoft/layoutlmv3-base/raw/main/vocab.json", - "microsoft/layoutlmv3-large": "https://huggingface.co/microsoft/layoutlmv3-large/raw/main/vocab.json", - }, - "merges_file": { - "microsoft/layoutlmv3-base": "https://huggingface.co/microsoft/layoutlmv3-base/raw/main/merges.txt", - "microsoft/layoutlmv3-large": "https://huggingface.co/microsoft/layoutlmv3-large/raw/main/merges.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/layoutlmv3-base": 512, - "microsoft/layoutlmv3-large": 512, -} - LAYOUTLMV3_ENCODE_KWARGS_DOCSTRING = r""" add_special_tokens (`bool`, *optional*, defaults to `True`): @@ -270,8 +254,6 @@ class LayoutLMv3Tokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask", "bbox"] def __init__( diff --git a/src/transformers/models/layoutlmv3/tokenization_layoutlmv3_fast.py b/src/transformers/models/layoutlmv3/tokenization_layoutlmv3_fast.py index 3d7445e449..07bedf3613 100644 --- a/src/transformers/models/layoutlmv3/tokenization_layoutlmv3_fast.py +++ b/src/transformers/models/layoutlmv3/tokenization_layoutlmv3_fast.py @@ -45,22 +45,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/layoutlmv3-base": "https://huggingface.co/microsoft/layoutlmv3-base/raw/main/vocab.json", - "microsoft/layoutlmv3-large": "https://huggingface.co/microsoft/layoutlmv3-large/raw/main/vocab.json", - }, - "merges_file": { - "microsoft/layoutlmv3-base": "https://huggingface.co/microsoft/layoutlmv3-base/raw/main/merges.txt", - "microsoft/layoutlmv3-large": "https://huggingface.co/microsoft/layoutlmv3-large/raw/main/merges.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/layoutlmv3-base": 512, - "microsoft/layoutlmv3-large": 512, -} - class LayoutLMv3TokenizerFast(PreTrainedTokenizerFast): r""" @@ -131,8 +115,6 @@ class LayoutLMv3TokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = LayoutLMv3Tokenizer diff --git a/src/transformers/models/layoutxlm/tokenization_layoutxlm.py b/src/transformers/models/layoutxlm/tokenization_layoutxlm.py index 44a31f8580..bbfdf44a1e 100644 --- a/src/transformers/models/layoutxlm/tokenization_layoutxlm.py +++ b/src/transformers/models/layoutxlm/tokenization_layoutxlm.py @@ -32,8 +32,6 @@ from ...tokenization_utils_base import ( ) from ...utils import PaddingStrategy, TensorType, add_end_docstrings, logging from ..xlm_roberta.tokenization_xlm_roberta import ( - PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES, - PRETRAINED_VOCAB_FILES_MAP, SPIECE_UNDERLINE, VOCAB_FILES_NAMES, ) @@ -225,8 +223,6 @@ class LayoutXLMTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/layoutxlm/tokenization_layoutxlm_fast.py b/src/transformers/models/layoutxlm/tokenization_layoutxlm_fast.py index 31c4579d47..e899d8b22e 100644 --- a/src/transformers/models/layoutxlm/tokenization_layoutxlm_fast.py +++ b/src/transformers/models/layoutxlm/tokenization_layoutxlm_fast.py @@ -31,8 +31,6 @@ from ...tokenization_utils_base import ( from ...tokenization_utils_fast import PreTrainedTokenizerFast from ...utils import PaddingStrategy, TensorType, add_end_docstrings, is_sentencepiece_available, logging from ..xlm_roberta.tokenization_xlm_roberta_fast import ( - PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES, - PRETRAINED_VOCAB_FILES_MAP, VOCAB_FILES_NAMES, ) @@ -212,8 +210,6 @@ class LayoutXLMTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = LayoutXLMTokenizer diff --git a/src/transformers/models/led/configuration_led.py b/src/transformers/models/led/configuration_led.py index d9efc308fe..59a2793cc8 100644 --- a/src/transformers/models/led/configuration_led.py +++ b/src/transformers/models/led/configuration_led.py @@ -22,10 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -LED_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "allenai/led-base-16384": "https://huggingface.co/allenai/led-base-16384/resolve/main/config.json", - # See all LED models at https://huggingface.co/models?filter=led -} + +from ..deprecated._archive_maps import LED_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class LEDConfig(PretrainedConfig): diff --git a/src/transformers/models/led/modeling_led.py b/src/transformers/models/led/modeling_led.py index c10a8de115..b2a5f440e0 100755 --- a/src/transformers/models/led/modeling_led.py +++ b/src/transformers/models/led/modeling_led.py @@ -53,10 +53,7 @@ _CHECKPOINT_FOR_DOC = "allenai/led-base-16384" _CONFIG_FOR_DOC = "LEDConfig" -LED_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "allenai/led-base-16384", - # See all LED models at https://huggingface.co/models?filter=led -] +from ..deprecated._archive_maps import LED_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def shift_tokens_right(input_ids: torch.Tensor, pad_token_id: int, decoder_start_token_id: int): diff --git a/src/transformers/models/led/tokenization_led.py b/src/transformers/models/led/tokenization_led.py index e82739b496..aaf09e6d14 100644 --- a/src/transformers/models/led/tokenization_led.py +++ b/src/transformers/models/led/tokenization_led.py @@ -32,21 +32,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt"} # See all LED models at https://huggingface.co/models?filter=LED -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "allenai/led-base-16384": "https://huggingface.co/allenai/led-base-16384/resolve/main/vocab.json", - }, - "merges_file": { - "allenai/led-base-16384": "https://huggingface.co/allenai/led-base-16384/resolve/main/merges.txt", - }, - "tokenizer_file": { - "allenai/led-base-16384": "https://huggingface.co/allenai/led-base-16384/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "allenai/led-base-16384": 16384, -} @lru_cache() @@ -169,8 +154,6 @@ class LEDTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] # Copied from transformers.models.bart.tokenization_bart.BartTokenizer.__init__ diff --git a/src/transformers/models/led/tokenization_led_fast.py b/src/transformers/models/led/tokenization_led_fast.py index 5c80491a84..ca15eb997b 100644 --- a/src/transformers/models/led/tokenization_led_fast.py +++ b/src/transformers/models/led/tokenization_led_fast.py @@ -30,22 +30,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "allenai/led-base-16384": "https://huggingface.co/allenai/led-base-16384/resolve/main/vocab.json", - }, - "merges_file": { - "allenai/led-base-16384": "https://huggingface.co/allenai/led-base-16384/resolve/main/merges.txt", - }, - "tokenizer_file": { - "allenai/led-base-16384": "https://huggingface.co/allenai/led-base-16384/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "allenai/led-base-16384": 16384, -} - class LEDTokenizerFast(PreTrainedTokenizerFast): r""" @@ -129,8 +113,6 @@ class LEDTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = LEDTokenizer model_input_names = ["input_ids", "attention_mask"] diff --git a/src/transformers/models/levit/configuration_levit.py b/src/transformers/models/levit/configuration_levit.py index 3a9546a652..fd840f519f 100644 --- a/src/transformers/models/levit/configuration_levit.py +++ b/src/transformers/models/levit/configuration_levit.py @@ -26,10 +26,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -LEVIT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/levit-128S": "https://huggingface.co/facebook/levit-128S/resolve/main/config.json", - # See all LeViT models at https://huggingface.co/models?filter=levit -} + +from ..deprecated._archive_maps import LEVIT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class LevitConfig(PretrainedConfig): diff --git a/src/transformers/models/levit/modeling_levit.py b/src/transformers/models/levit/modeling_levit.py index 38a9ee1abc..11eda7bcc5 100644 --- a/src/transformers/models/levit/modeling_levit.py +++ b/src/transformers/models/levit/modeling_levit.py @@ -47,10 +47,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 16, 384] _IMAGE_CLASS_CHECKPOINT = "facebook/levit-128S" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -LEVIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/levit-128S", - # See all LeViT models at https://huggingface.co/models?filter=levit -] + +from ..deprecated._archive_maps import LEVIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/lilt/configuration_lilt.py b/src/transformers/models/lilt/configuration_lilt.py index 3db595e86e..f1cfa98c6c 100644 --- a/src/transformers/models/lilt/configuration_lilt.py +++ b/src/transformers/models/lilt/configuration_lilt.py @@ -20,11 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -LILT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "SCUT-DLVCLab/lilt-roberta-en-base": ( - "https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import LILT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class LiltConfig(PretrainedConfig): diff --git a/src/transformers/models/lilt/modeling_lilt.py b/src/transformers/models/lilt/modeling_lilt.py index e21f8ab2ce..adf8edcdc2 100644 --- a/src/transformers/models/lilt/modeling_lilt.py +++ b/src/transformers/models/lilt/modeling_lilt.py @@ -40,10 +40,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "LiltConfig" -LILT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "SCUT-DLVCLab/lilt-roberta-en-base", - # See all LiLT models at https://huggingface.co/models?filter=lilt -] + +from ..deprecated._archive_maps import LILT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class LiltTextEmbeddings(nn.Module): diff --git a/src/transformers/models/llama/configuration_llama.py b/src/transformers/models/llama/configuration_llama.py index b62a105309..242d24af2d 100644 --- a/src/transformers/models/llama/configuration_llama.py +++ b/src/transformers/models/llama/configuration_llama.py @@ -25,7 +25,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP = {} + +from ..deprecated._archive_maps import LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class LlamaConfig(PretrainedConfig): diff --git a/src/transformers/models/llama/tokenization_llama.py b/src/transformers/models/llama/tokenization_llama.py index 2f8997274c..2f68d6c1e9 100644 --- a/src/transformers/models/llama/tokenization_llama.py +++ b/src/transformers/models/llama/tokenization_llama.py @@ -37,17 +37,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "hf-internal-testing/llama-tokenizer": "https://huggingface.co/hf-internal-testing/llama-tokenizer/resolve/main/tokenizer.model", - }, - "tokenizer_file": { - "hf-internal-testing/llama-tokenizer": "https://huggingface.co/hf-internal-testing/llama-tokenizer/resolve/main/tokenizer_config.json", - }, -} -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "hf-internal-testing/llama-tokenizer": 2048, -} SPIECE_UNDERLINE = "▁" B_INST, E_INST = "[INST]", "[/INST]" @@ -137,8 +126,6 @@ class LlamaTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/llama/tokenization_llama_fast.py b/src/transformers/models/llama/tokenization_llama_fast.py index fee7711987..07c01be893 100644 --- a/src/transformers/models/llama/tokenization_llama_fast.py +++ b/src/transformers/models/llama/tokenization_llama_fast.py @@ -33,14 +33,6 @@ else: logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "hf-internal-testing/llama-tokenizer": "https://huggingface.co/hf-internal-testing/llama-tokenizer/resolve/main/tokenizer.model", - }, - "tokenizer_file": { - "hf-internal-testing/llama-tokenizer": "https://huggingface.co/hf-internal-testing/llama-tokenizer/resolve/main/tokenizer_config.json", - }, -} B_INST, E_INST = "[INST]", "[/INST]" B_SYS, E_SYS = "<>\n", "\n<>\n\n" @@ -105,7 +97,6 @@ class LlamaTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP slow_tokenizer_class = LlamaTokenizer padding_side = "left" model_input_names = ["input_ids", "attention_mask"] diff --git a/src/transformers/models/llava/configuration_llava.py b/src/transformers/models/llava/configuration_llava.py index 56b7974db0..8c322f41de 100644 --- a/src/transformers/models/llava/configuration_llava.py +++ b/src/transformers/models/llava/configuration_llava.py @@ -22,9 +22,8 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -LLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "llava-hf/llava-v1.5-7b": "https://huggingface.co/llava-hf/llava-v1.5-7b/resolve/main/config.json", -} + +from ..deprecated._archive_maps import LLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class LlavaConfig(PretrainedConfig): diff --git a/src/transformers/models/llava/modeling_llava.py b/src/transformers/models/llava/modeling_llava.py index d3fc58eb36..f195c1140b 100644 --- a/src/transformers/models/llava/modeling_llava.py +++ b/src/transformers/models/llava/modeling_llava.py @@ -38,12 +38,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "LlavaConfig" -LLAVA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "llava-hf/llava-1.5-7b-hf", - "llava-hf/llava-1.5-13b-hf", - "llava-hf/bakLlava-v1-hf", - # See all Llava models at https://huggingface.co/models?filter=llava -] + +from ..deprecated._archive_maps import LLAVA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/longformer/configuration_longformer.py b/src/transformers/models/longformer/configuration_longformer.py index 2935dd4aaa..7dce8a74a6 100644 --- a/src/transformers/models/longformer/configuration_longformer.py +++ b/src/transformers/models/longformer/configuration_longformer.py @@ -28,19 +28,8 @@ if TYPE_CHECKING: logger = logging.get_logger(__name__) -LONGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "allenai/longformer-base-4096": "https://huggingface.co/allenai/longformer-base-4096/resolve/main/config.json", - "allenai/longformer-large-4096": "https://huggingface.co/allenai/longformer-large-4096/resolve/main/config.json", - "allenai/longformer-large-4096-finetuned-triviaqa": ( - "https://huggingface.co/allenai/longformer-large-4096-finetuned-triviaqa/resolve/main/config.json" - ), - "allenai/longformer-base-4096-extra.pos.embd.only": ( - "https://huggingface.co/allenai/longformer-base-4096-extra.pos.embd.only/resolve/main/config.json" - ), - "allenai/longformer-large-4096-extra.pos.embd.only": ( - "https://huggingface.co/allenai/longformer-large-4096-extra.pos.embd.only/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import LONGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class LongformerConfig(PretrainedConfig): diff --git a/src/transformers/models/longformer/modeling_longformer.py b/src/transformers/models/longformer/modeling_longformer.py index aefd225869..f8c7c44ef9 100755 --- a/src/transformers/models/longformer/modeling_longformer.py +++ b/src/transformers/models/longformer/modeling_longformer.py @@ -42,14 +42,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "allenai/longformer-base-4096" _CONFIG_FOR_DOC = "LongformerConfig" -LONGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "allenai/longformer-base-4096", - "allenai/longformer-large-4096", - "allenai/longformer-large-4096-finetuned-triviaqa", - "allenai/longformer-base-4096-extra.pos.embd.only", - "allenai/longformer-large-4096-extra.pos.embd.only", - # See all Longformer models at https://huggingface.co/models?filter=longformer -] + +from ..deprecated._archive_maps import LONGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/longformer/modeling_tf_longformer.py b/src/transformers/models/longformer/modeling_tf_longformer.py index 1cbfb28695..907fbbddf1 100644 --- a/src/transformers/models/longformer/modeling_tf_longformer.py +++ b/src/transformers/models/longformer/modeling_tf_longformer.py @@ -56,14 +56,8 @@ _CONFIG_FOR_DOC = "LongformerConfig" LARGE_NEGATIVE = -1e8 -TF_LONGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "allenai/longformer-base-4096", - "allenai/longformer-large-4096", - "allenai/longformer-large-4096-finetuned-triviaqa", - "allenai/longformer-base-4096-extra.pos.embd.only", - "allenai/longformer-large-4096-extra.pos.embd.only", - # See all Longformer models at https://huggingface.co/models?filter=longformer -] + +from ..deprecated._archive_maps import TF_LONGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/longformer/tokenization_longformer.py b/src/transformers/models/longformer/tokenization_longformer.py index cf0477bac1..51728d7780 100644 --- a/src/transformers/models/longformer/tokenization_longformer.py +++ b/src/transformers/models/longformer/tokenization_longformer.py @@ -29,47 +29,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "allenai/longformer-base-4096": "https://huggingface.co/allenai/longformer-base-4096/resolve/main/vocab.json", - "allenai/longformer-large-4096": ( - "https://huggingface.co/allenai/longformer-large-4096/resolve/main/vocab.json" - ), - "allenai/longformer-large-4096-finetuned-triviaqa": ( - "https://huggingface.co/allenai/longformer-large-4096-finetuned-triviaqa/resolve/main/vocab.json" - ), - "allenai/longformer-base-4096-extra.pos.embd.only": ( - "https://huggingface.co/allenai/longformer-base-4096-extra.pos.embd.only/resolve/main/vocab.json" - ), - "allenai/longformer-large-4096-extra.pos.embd.only": ( - "https://huggingface.co/allenai/longformer-large-4096-extra.pos.embd.only/resolve/main/vocab.json" - ), - }, - "merges_file": { - "allenai/longformer-base-4096": "https://huggingface.co/allenai/longformer-base-4096/resolve/main/merges.txt", - "allenai/longformer-large-4096": ( - "https://huggingface.co/allenai/longformer-large-4096/resolve/main/merges.txt" - ), - "allenai/longformer-large-4096-finetuned-triviaqa": ( - "https://huggingface.co/allenai/longformer-large-4096-finetuned-triviaqa/resolve/main/merges.txt" - ), - "allenai/longformer-base-4096-extra.pos.embd.only": ( - "https://huggingface.co/allenai/longformer-base-4096-extra.pos.embd.only/resolve/main/merges.txt" - ), - "allenai/longformer-large-4096-extra.pos.embd.only": ( - "https://huggingface.co/allenai/longformer-large-4096-extra.pos.embd.only/resolve/main/merges.txt" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "allenai/longformer-base-4096": 4096, - "allenai/longformer-large-4096": 4096, - "allenai/longformer-large-4096-finetuned-triviaqa": 4096, - "allenai/longformer-base-4096-extra.pos.embd.only": 4096, - "allenai/longformer-large-4096-extra.pos.embd.only": 4096, -} - @lru_cache() # Copied from transformers.models.roberta.tokenization_roberta.bytes_to_unicode @@ -192,8 +151,6 @@ class LongformerTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/longformer/tokenization_longformer_fast.py b/src/transformers/models/longformer/tokenization_longformer_fast.py index e40ebff3b6..02b74818a2 100644 --- a/src/transformers/models/longformer/tokenization_longformer_fast.py +++ b/src/transformers/models/longformer/tokenization_longformer_fast.py @@ -28,64 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "allenai/longformer-base-4096": "https://huggingface.co/allenai/longformer-base-4096/resolve/main/vocab.json", - "allenai/longformer-large-4096": ( - "https://huggingface.co/allenai/longformer-large-4096/resolve/main/vocab.json" - ), - "allenai/longformer-large-4096-finetuned-triviaqa": ( - "https://huggingface.co/allenai/longformer-large-4096-finetuned-triviaqa/resolve/main/vocab.json" - ), - "allenai/longformer-base-4096-extra.pos.embd.only": ( - "https://huggingface.co/allenai/longformer-base-4096-extra.pos.embd.only/resolve/main/vocab.json" - ), - "allenai/longformer-large-4096-extra.pos.embd.only": ( - "https://huggingface.co/allenai/longformer-large-4096-extra.pos.embd.only/resolve/main/vocab.json" - ), - }, - "merges_file": { - "allenai/longformer-base-4096": "https://huggingface.co/allenai/longformer-base-4096/resolve/main/merges.txt", - "allenai/longformer-large-4096": ( - "https://huggingface.co/allenai/longformer-large-4096/resolve/main/merges.txt" - ), - "allenai/longformer-large-4096-finetuned-triviaqa": ( - "https://huggingface.co/allenai/longformer-large-4096-finetuned-triviaqa/resolve/main/merges.txt" - ), - "allenai/longformer-base-4096-extra.pos.embd.only": ( - "https://huggingface.co/allenai/longformer-base-4096-extra.pos.embd.only/resolve/main/merges.txt" - ), - "allenai/longformer-large-4096-extra.pos.embd.only": ( - "https://huggingface.co/allenai/longformer-large-4096-extra.pos.embd.only/resolve/main/merges.txt" - ), - }, - "tokenizer_file": { - "allenai/longformer-base-4096": ( - "https://huggingface.co/allenai/longformer-base-4096/resolve/main/tokenizer.json" - ), - "allenai/longformer-large-4096": ( - "https://huggingface.co/allenai/longformer-large-4096/resolve/main/tokenizer.json" - ), - "allenai/longformer-large-4096-finetuned-triviaqa": ( - "https://huggingface.co/allenai/longformer-large-4096-finetuned-triviaqa/resolve/main/tokenizer.json" - ), - "allenai/longformer-base-4096-extra.pos.embd.only": ( - "https://huggingface.co/allenai/longformer-base-4096-extra.pos.embd.only/resolve/main/tokenizer.json" - ), - "allenai/longformer-large-4096-extra.pos.embd.only": ( - "https://huggingface.co/allenai/longformer-large-4096-extra.pos.embd.only/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "allenai/longformer-base-4096": 4096, - "allenai/longformer-large-4096": 4096, - "allenai/longformer-large-4096-finetuned-triviaqa": 4096, - "allenai/longformer-base-4096-extra.pos.embd.only": 4096, - "allenai/longformer-large-4096-extra.pos.embd.only": 4096, -} - # Copied from transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast with FacebookAI/roberta-base->allenai/longformer-base-4096, RoBERTa->Longformer all-casing, Roberta->Longformer class LongformerTokenizerFast(PreTrainedTokenizerFast): @@ -170,8 +112,6 @@ class LongformerTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = LongformerTokenizer diff --git a/src/transformers/models/longt5/configuration_longt5.py b/src/transformers/models/longt5/configuration_longt5.py index 0095af0e24..f6e8284ed0 100644 --- a/src/transformers/models/longt5/configuration_longt5.py +++ b/src/transformers/models/longt5/configuration_longt5.py @@ -22,12 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -LONGT5_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/long-t5-local-base": "https://huggingface.co/google/long-t5-local-base/blob/main/config.json", - "google/long-t5-local-large": "https://huggingface.co/google/long-t5-local-large/blob/main/config.json", - "google/long-t5-tglobal-base": "https://huggingface.co/google/long-t5-tglobal-base/blob/main/config.json", - "google/long-t5-tglobal-large": "https://huggingface.co/google/long-t5-tglobal-large/blob/main/config.json", -} + +from ..deprecated._archive_maps import LONGT5_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class LongT5Config(PretrainedConfig): diff --git a/src/transformers/models/longt5/modeling_longt5.py b/src/transformers/models/longt5/modeling_longt5.py index 5189db98a1..e16e095120 100644 --- a/src/transformers/models/longt5/modeling_longt5.py +++ b/src/transformers/models/longt5/modeling_longt5.py @@ -51,12 +51,8 @@ _CONFIG_FOR_DOC = "LongT5Config" _CHECKPOINT_FOR_DOC = "google/long-t5-local-base" # TODO: Update before the merge -LONGT5_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/long-t5-local-base", - "google/long-t5-local-large", - "google/long-t5-tglobal-base", - "google/long-t5-tglobal-large", -] + +from ..deprecated._archive_maps import LONGT5_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def _pad_to_multiple(x: torch.Tensor, block_len: int, dim: int, pad_value: int = 0) -> torch.Tensor: diff --git a/src/transformers/models/luke/configuration_luke.py b/src/transformers/models/luke/configuration_luke.py index 53ab1a3528..257c9a2553 100644 --- a/src/transformers/models/luke/configuration_luke.py +++ b/src/transformers/models/luke/configuration_luke.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -LUKE_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "studio-ousia/luke-base": "https://huggingface.co/studio-ousia/luke-base/resolve/main/config.json", - "studio-ousia/luke-large": "https://huggingface.co/studio-ousia/luke-large/resolve/main/config.json", -} + +from ..deprecated._archive_maps import LUKE_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class LukeConfig(PretrainedConfig): diff --git a/src/transformers/models/luke/modeling_luke.py b/src/transformers/models/luke/modeling_luke.py index 1742283ef6..3523e739f5 100644 --- a/src/transformers/models/luke/modeling_luke.py +++ b/src/transformers/models/luke/modeling_luke.py @@ -43,11 +43,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "LukeConfig" _CHECKPOINT_FOR_DOC = "studio-ousia/luke-base" -LUKE_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "studio-ousia/luke-base", - "studio-ousia/luke-large", - # See all LUKE models at https://huggingface.co/models?filter=luke -] + +from ..deprecated._archive_maps import LUKE_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/luke/tokenization_luke.py b/src/transformers/models/luke/tokenization_luke.py index e8ad725d05..d37258f2a4 100644 --- a/src/transformers/models/luke/tokenization_luke.py +++ b/src/transformers/models/luke/tokenization_luke.py @@ -53,25 +53,6 @@ VOCAB_FILES_NAMES = { "entity_vocab_file": "entity_vocab.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "studio-ousia/luke-base": "https://huggingface.co/studio-ousia/luke-base/resolve/main/vocab.json", - "studio-ousia/luke-large": "https://huggingface.co/studio-ousia/luke-large/resolve/main/vocab.json", - }, - "merges_file": { - "studio-ousia/luke-base": "https://huggingface.co/studio-ousia/luke-base/resolve/main/merges.txt", - "studio-ousia/luke-large": "https://huggingface.co/studio-ousia/luke-large/resolve/main/merges.txt", - }, - "entity_vocab_file": { - "studio-ousia/luke-base": "https://huggingface.co/studio-ousia/luke-base/resolve/main/entity_vocab.json", - "studio-ousia/luke-large": "https://huggingface.co/studio-ousia/luke-large/resolve/main/entity_vocab.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "studio-ousia/luke-base": 512, - "studio-ousia/luke-large": 512, -} ENCODE_PLUS_ADDITIONAL_KWARGS_DOCSTRING = r""" return_token_type_ids (`bool`, *optional*): @@ -287,8 +268,6 @@ class LukeTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/lxmert/configuration_lxmert.py b/src/transformers/models/lxmert/configuration_lxmert.py index 6ced7d2aca..b79fb67908 100644 --- a/src/transformers/models/lxmert/configuration_lxmert.py +++ b/src/transformers/models/lxmert/configuration_lxmert.py @@ -21,9 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -LXMERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "unc-nlp/lxmert-base-uncased": "https://huggingface.co/unc-nlp/lxmert-base-uncased/resolve/main/config.json", -} + +from ..deprecated._archive_maps import LXMERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class LxmertConfig(PretrainedConfig): diff --git a/src/transformers/models/lxmert/modeling_lxmert.py b/src/transformers/models/lxmert/modeling_lxmert.py index 226e2e7197..6e2ae7d22e 100644 --- a/src/transformers/models/lxmert/modeling_lxmert.py +++ b/src/transformers/models/lxmert/modeling_lxmert.py @@ -43,10 +43,6 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "unc-nlp/lxmert-base-uncased" _CONFIG_FOR_DOC = "LxmertConfig" -LXMERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "unc-nlp/lxmert-base-uncased", -] - class GeLU(nn.Module): def __init__(self): diff --git a/src/transformers/models/lxmert/modeling_tf_lxmert.py b/src/transformers/models/lxmert/modeling_tf_lxmert.py index 22ce04a001..c474119603 100644 --- a/src/transformers/models/lxmert/modeling_tf_lxmert.py +++ b/src/transformers/models/lxmert/modeling_tf_lxmert.py @@ -53,9 +53,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "unc-nlp/lxmert-base-uncased" _CONFIG_FOR_DOC = "LxmertConfig" -TF_LXMERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "unc-nlp/lxmert-base-uncased", -] + +from ..deprecated._archive_maps import TF_LXMERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/lxmert/tokenization_lxmert.py b/src/transformers/models/lxmert/tokenization_lxmert.py index 1557be1add..8d2fca9328 100644 --- a/src/transformers/models/lxmert/tokenization_lxmert.py +++ b/src/transformers/models/lxmert/tokenization_lxmert.py @@ -26,20 +26,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "unc-nlp/lxmert-base-uncased": "https://huggingface.co/unc-nlp/lxmert-base-uncased/resolve/main/vocab.txt", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "unc-nlp/lxmert-base-uncased": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "unc-nlp/lxmert-base-uncased": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert.load_vocab def load_vocab(vocab_file): @@ -107,9 +93,6 @@ class LxmertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/lxmert/tokenization_lxmert_fast.py b/src/transformers/models/lxmert/tokenization_lxmert_fast.py index 7d9758a601..e31fdbcf76 100644 --- a/src/transformers/models/lxmert/tokenization_lxmert_fast.py +++ b/src/transformers/models/lxmert/tokenization_lxmert_fast.py @@ -24,25 +24,6 @@ from .tokenization_lxmert import LxmertTokenizer VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "unc-nlp/lxmert-base-uncased": "https://huggingface.co/unc-nlp/lxmert-base-uncased/resolve/main/vocab.txt", - }, - "tokenizer_file": { - "unc-nlp/lxmert-base-uncased": ( - "https://huggingface.co/unc-nlp/lxmert-base-uncased/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "unc-nlp/lxmert-base-uncased": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "unc-nlp/lxmert-base-uncased": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert_fast.BertTokenizerFast with bert-base-cased->unc-nlp/lxmert-base-uncased, BERT->Lxmert, Bert->Lxmert class LxmertTokenizerFast(PreTrainedTokenizerFast): @@ -86,9 +67,6 @@ class LxmertTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = LxmertTokenizer def __init__( diff --git a/src/transformers/models/m2m_100/configuration_m2m_100.py b/src/transformers/models/m2m_100/configuration_m2m_100.py index 1b15658c03..b211527e80 100644 --- a/src/transformers/models/m2m_100/configuration_m2m_100.py +++ b/src/transformers/models/m2m_100/configuration_m2m_100.py @@ -25,10 +25,8 @@ from ...utils import TensorType, is_torch_available, logging logger = logging.get_logger(__name__) -M2M_100_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/m2m100_418M": "https://huggingface.co/facebook/m2m100_418M/resolve/main/config.json", - # See all M2M100 models at https://huggingface.co/models?filter=m2m_100 -} + +from ..deprecated._archive_maps import M2M_100_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class M2M100Config(PretrainedConfig): diff --git a/src/transformers/models/m2m_100/modeling_m2m_100.py b/src/transformers/models/m2m_100/modeling_m2m_100.py index 1aad2bde81..9e2ff11ad8 100755 --- a/src/transformers/models/m2m_100/modeling_m2m_100.py +++ b/src/transformers/models/m2m_100/modeling_m2m_100.py @@ -49,10 +49,7 @@ _CONFIG_FOR_DOC = "M2M100Config" _CHECKPOINT_FOR_DOC = "facebook/m2m100_418M" -M2M_100_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/m2m100_418M", - # See all M2M100 models at https://huggingface.co/models?filter=m2m_100 -] +from ..deprecated._archive_maps import M2M_100_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.bart.modeling_bart.shift_tokens_right diff --git a/src/transformers/models/m2m_100/tokenization_m2m_100.py b/src/transformers/models/m2m_100/tokenization_m2m_100.py index 1346af8141..96f79ee4e7 100644 --- a/src/transformers/models/m2m_100/tokenization_m2m_100.py +++ b/src/transformers/models/m2m_100/tokenization_m2m_100.py @@ -34,24 +34,6 @@ VOCAB_FILES_NAMES = { "tokenizer_config_file": "tokenizer_config.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/m2m100_418M": "https://huggingface.co/facebook/m2m100_418M/resolve/main/vocab.json", - "facebook/m2m100_1.2B": "https://huggingface.co/facebook/m2m100_1.2B/resolve/main/vocab.json", - }, - "spm_file": { - "facebook/m2m100_418M": "https://huggingface.co/facebook/m2m100_418M/resolve/main/sentencepiece.bpe.model", - "facebook/m2m100_1.2B": "https://huggingface.co/facebook/m2m100_1.2B/resolve/main/sentencepiece.bpe.model", - }, - "tokenizer_config_file": { - "facebook/m2m100_418M": "https://huggingface.co/facebook/m2m100_418M/resolve/main/tokenizer_config.json", - "facebook/m2m100_1.2B": "https://huggingface.co/facebook/m2m100_1.2B/resolve/main/tokenizer_config.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/m2m100_418M": 1024, -} # fmt: off FAIRSEQ_LANGUAGE_CODES = { @@ -121,8 +103,6 @@ class M2M100Tokenizer(PreTrainedTokenizer): ```""" vocab_files_names = VOCAB_FILES_NAMES - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP model_input_names = ["input_ids", "attention_mask"] prefix_tokens: List[int] = [] diff --git a/src/transformers/models/mamba/configuration_mamba.py b/src/transformers/models/mamba/configuration_mamba.py index ec5e615c0b..695d9a6273 100644 --- a/src/transformers/models/mamba/configuration_mamba.py +++ b/src/transformers/models/mamba/configuration_mamba.py @@ -22,9 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MAMBA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "state-spaces/mamba-2.8b": "https://huggingface.co/state-spaces/mamba-2.8b/resolve/main/config.json", -} + +from ..deprecated._archive_maps import MAMBA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MambaConfig(PretrainedConfig): diff --git a/src/transformers/models/mamba/modeling_mamba.py b/src/transformers/models/mamba/modeling_mamba.py index a3325b3af8..0e233ae430 100644 --- a/src/transformers/models/mamba/modeling_mamba.py +++ b/src/transformers/models/mamba/modeling_mamba.py @@ -56,7 +56,8 @@ is_fast_path_available = all( _CHECKPOINT_FOR_DOC = "state-spaces/mamba-130m-hf" _CONFIG_FOR_DOC = "MambaConfig" -MAMBA_PRETRAINED_MODEL_ARCHIVE_LIST = [] # See all Mamba models at https://huggingface.co/models?filter=mamba + +from ..deprecated._archive_maps import MAMBA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class MambaCache: diff --git a/src/transformers/models/marian/configuration_marian.py b/src/transformers/models/marian/configuration_marian.py index 201788673e..5921fde981 100644 --- a/src/transformers/models/marian/configuration_marian.py +++ b/src/transformers/models/marian/configuration_marian.py @@ -25,11 +25,6 @@ from ...utils import TensorType, is_torch_available, logging logger = logging.get_logger(__name__) -MARIAN_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "Helsinki-NLP/opus-mt-en-de": "https://huggingface.co/Helsinki-NLP/opus-mt-en-de/resolve/main/config.json", - # See all Marian models at https://huggingface.co/models?filter=marian -} - class MarianConfig(PretrainedConfig): r""" diff --git a/src/transformers/models/marian/modeling_marian.py b/src/transformers/models/marian/modeling_marian.py index d52a060d47..7c39acbcd4 100755 --- a/src/transformers/models/marian/modeling_marian.py +++ b/src/transformers/models/marian/modeling_marian.py @@ -51,12 +51,6 @@ _CONFIG_FOR_DOC = "MarianConfig" _CHECKPOINT_FOR_DOC = "Helsinki-NLP/opus-mt-en-de" -MARIAN_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Helsinki-NLP/opus-mt-en-de", - # See all Marian models at https://huggingface.co/models?filter=marian -] - - # Copied from transformers.models.bart.modeling_bart.shift_tokens_right def shift_tokens_right(input_ids: torch.Tensor, pad_token_id: int, decoder_start_token_id: int): """ diff --git a/src/transformers/models/marian/tokenization_marian.py b/src/transformers/models/marian/tokenization_marian.py index ead3ddd70e..4f0d90b6f0 100644 --- a/src/transformers/models/marian/tokenization_marian.py +++ b/src/transformers/models/marian/tokenization_marian.py @@ -35,25 +35,6 @@ VOCAB_FILES_NAMES = { "tokenizer_config_file": "tokenizer_config.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "source_spm": { - "Helsinki-NLP/opus-mt-en-de": "https://huggingface.co/Helsinki-NLP/opus-mt-en-de/resolve/main/source.spm" - }, - "target_spm": { - "Helsinki-NLP/opus-mt-en-de": "https://huggingface.co/Helsinki-NLP/opus-mt-en-de/resolve/main/target.spm" - }, - "vocab": { - "Helsinki-NLP/opus-mt-en-de": "https://huggingface.co/Helsinki-NLP/opus-mt-en-de/resolve/main/vocab.json" - }, - "tokenizer_config_file": { - "Helsinki-NLP/opus-mt-en-de": ( - "https://huggingface.co/Helsinki-NLP/opus-mt-en-de/resolve/main/tokenizer_config.json" - ) - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"Helsinki-NLP/opus-mt-en-de": 512} -PRETRAINED_INIT_CONFIGURATION = {} SPIECE_UNDERLINE = "▁" @@ -120,9 +101,6 @@ class MarianTokenizer(PreTrainedTokenizer): ```""" vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] language_code_re = re.compile(">>.+<<") # type: re.Pattern diff --git a/src/transformers/models/markuplm/configuration_markuplm.py b/src/transformers/models/markuplm/configuration_markuplm.py index ff0ab96919..aeb80ae51f 100644 --- a/src/transformers/models/markuplm/configuration_markuplm.py +++ b/src/transformers/models/markuplm/configuration_markuplm.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MARKUPLM_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/markuplm-base": "https://huggingface.co/microsoft/markuplm-base/resolve/main/config.json", - "microsoft/markuplm-large": "https://huggingface.co/microsoft/markuplm-large/resolve/main/config.json", -} + +from ..deprecated._archive_maps import MARKUPLM_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MarkupLMConfig(PretrainedConfig): diff --git a/src/transformers/models/markuplm/modeling_markuplm.py b/src/transformers/models/markuplm/modeling_markuplm.py index 24ca0c4972..2058ce2795 100755 --- a/src/transformers/models/markuplm/modeling_markuplm.py +++ b/src/transformers/models/markuplm/modeling_markuplm.py @@ -52,10 +52,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "microsoft/markuplm-base" _CONFIG_FOR_DOC = "MarkupLMConfig" -MARKUPLM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/markuplm-base", - "microsoft/markuplm-large", -] + +from ..deprecated._archive_maps import MARKUPLM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class XPathEmbeddings(nn.Module): @@ -708,7 +706,6 @@ class MarkupLMPreTrainedModel(PreTrainedModel): """ config_class = MarkupLMConfig - pretrained_model_archive_map = MARKUPLM_PRETRAINED_MODEL_ARCHIVE_LIST base_model_prefix = "markuplm" # Copied from transformers.models.bert.modeling_bert.BertPreTrainedModel._init_weights with Bert->MarkupLM diff --git a/src/transformers/models/markuplm/tokenization_markuplm.py b/src/transformers/models/markuplm/tokenization_markuplm.py index 24fa4b7763..c77865abc9 100644 --- a/src/transformers/models/markuplm/tokenization_markuplm.py +++ b/src/transformers/models/markuplm/tokenization_markuplm.py @@ -39,23 +39,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/markuplm-base": "https://huggingface.co/microsoft/markuplm-base/resolve/main/vocab.json", - "microsoft/markuplm-large": "https://huggingface.co/microsoft/markuplm-large/resolve/main/vocab.json", - }, - "merges_file": { - "microsoft/markuplm-base": "https://huggingface.co/microsoft/markuplm-base/resolve/main/merges.txt", - "microsoft/markuplm-large": "https://huggingface.co/microsoft/markuplm-large/resolve/main/merges.txt", - }, -} - - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/markuplm-base": 512, - "microsoft/markuplm-large": 512, -} - MARKUPLM_ENCODE_PLUS_ADDITIONAL_KWARGS_DOCSTRING = r""" add_special_tokens (`bool`, *optional*, defaults to `True`): @@ -198,8 +181,6 @@ class MarkupLMTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/markuplm/tokenization_markuplm_fast.py b/src/transformers/models/markuplm/tokenization_markuplm_fast.py index a0933631b6..ff0e4ffeb5 100644 --- a/src/transformers/models/markuplm/tokenization_markuplm_fast.py +++ b/src/transformers/models/markuplm/tokenization_markuplm_fast.py @@ -43,23 +43,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/markuplm-base": "https://huggingface.co/microsoft/markuplm-base/resolve/main/vocab.json", - "microsoft/markuplm-large": "https://huggingface.co/microsoft/markuplm-large/resolve/main/vocab.json", - }, - "merges_file": { - "microsoft/markuplm-base": "https://huggingface.co/microsoft/markuplm-base/resolve/main/merges.txt", - "microsoft/markuplm-large": "https://huggingface.co/microsoft/markuplm-large/resolve/main/merges.txt", - }, -} - - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/markuplm-base": 512, - "microsoft/markuplm-large": 512, -} - @lru_cache() def bytes_to_unicode(): @@ -156,8 +139,6 @@ class MarkupLMTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = MarkupLMTokenizer def __init__( diff --git a/src/transformers/models/mask2former/configuration_mask2former.py b/src/transformers/models/mask2former/configuration_mask2former.py index 0b5aa9aa0c..f0d13b8e03 100644 --- a/src/transformers/models/mask2former/configuration_mask2former.py +++ b/src/transformers/models/mask2former/configuration_mask2former.py @@ -18,15 +18,9 @@ from typing import Dict, List, Optional from ...configuration_utils import PretrainedConfig from ...utils import logging from ..auto import CONFIG_MAPPING +from ..deprecated._archive_maps import MASK2FORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 -MASK2FORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/mask2former-swin-small-coco-instance": ( - "https://huggingface.co/facebook/mask2former-swin-small-coco-instance/blob/main/config.json" - ) - # See all Mask2Former models at https://huggingface.co/models?filter=mask2former -} - logger = logging.get_logger(__name__) diff --git a/src/transformers/models/mask2former/modeling_mask2former.py b/src/transformers/models/mask2former/modeling_mask2former.py index 628b50e448..3a9a743453 100644 --- a/src/transformers/models/mask2former/modeling_mask2former.py +++ b/src/transformers/models/mask2former/modeling_mask2former.py @@ -54,10 +54,8 @@ _CONFIG_FOR_DOC = "Mask2FormerConfig" _CHECKPOINT_FOR_DOC = "facebook/mask2former-swin-small-coco-instance" _IMAGE_PROCESSOR_FOR_DOC = "Mask2FormerImageProcessor" -MASK2FORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/mask2former-swin-small-coco-instance", - # See all mask2former models at https://huggingface.co/models?filter=mask2former -] + +from ..deprecated._archive_maps import MASK2FORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/maskformer/configuration_maskformer.py b/src/transformers/models/maskformer/configuration_maskformer.py index 758ac4eb20..653350ca05 100644 --- a/src/transformers/models/maskformer/configuration_maskformer.py +++ b/src/transformers/models/maskformer/configuration_maskformer.py @@ -18,17 +18,11 @@ from typing import Dict, Optional from ...configuration_utils import PretrainedConfig from ...utils import logging from ..auto import CONFIG_MAPPING +from ..deprecated._archive_maps import MASKFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 from ..detr import DetrConfig from ..swin import SwinConfig -MASKFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/maskformer-swin-base-ade": ( - "https://huggingface.co/facebook/maskformer-swin-base-ade/blob/main/config.json" - ) - # See all MaskFormer models at https://huggingface.co/models?filter=maskformer -} - logger = logging.get_logger(__name__) diff --git a/src/transformers/models/maskformer/modeling_maskformer.py b/src/transformers/models/maskformer/modeling_maskformer.py index e61146e9c4..4419a36e9f 100644 --- a/src/transformers/models/maskformer/modeling_maskformer.py +++ b/src/transformers/models/maskformer/modeling_maskformer.py @@ -57,10 +57,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "MaskFormerConfig" _CHECKPOINT_FOR_DOC = "facebook/maskformer-swin-base-ade" -MASKFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/maskformer-swin-base-ade", - # See all MaskFormer models at https://huggingface.co/models?filter=maskformer -] + +from ..deprecated._archive_maps import MASKFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/mbart/configuration_mbart.py b/src/transformers/models/mbart/configuration_mbart.py index 176ce52dbf..4823047dcf 100644 --- a/src/transformers/models/mbart/configuration_mbart.py +++ b/src/transformers/models/mbart/configuration_mbart.py @@ -25,11 +25,6 @@ from ...utils import TensorType, is_torch_available, logging logger = logging.get_logger(__name__) -MBART_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/mbart-large-cc25": "https://huggingface.co/facebook/mbart-large-cc25/resolve/main/config.json", - # See all MBART models at https://huggingface.co/models?filter=mbart -} - class MBartConfig(PretrainedConfig): r""" diff --git a/src/transformers/models/mbart/modeling_mbart.py b/src/transformers/models/mbart/modeling_mbart.py index 2f1d031d1a..fc23e2c675 100755 --- a/src/transformers/models/mbart/modeling_mbart.py +++ b/src/transformers/models/mbart/modeling_mbart.py @@ -61,11 +61,6 @@ _CONFIG_FOR_DOC = "MBartConfig" # Base model docstring _EXPECTED_OUTPUT_SHAPE = [1, 8, 1024] -MBART_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/mbart-large-cc25", - # See all MBART models at https://huggingface.co/models?filter=mbart -] - # Copied from transformers.models.llama.modeling_llama._get_unpad_data def _get_unpad_data(attention_mask): diff --git a/src/transformers/models/mbart/tokenization_mbart.py b/src/transformers/models/mbart/tokenization_mbart.py index 37f4c849ab..d9da6cb45c 100644 --- a/src/transformers/models/mbart/tokenization_mbart.py +++ b/src/transformers/models/mbart/tokenization_mbart.py @@ -29,21 +29,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/mbart-large-en-ro": ( - "https://huggingface.co/facebook/mbart-large-en-ro/resolve/main/sentencepiece.bpe.model" - ), - "facebook/mbart-large-cc25": ( - "https://huggingface.co/facebook/mbart-large-cc25/resolve/main/sentencepiece.bpe.model" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/mbart-large-en-ro": 1024, - "facebook/mbart-large-cc25": 1024, -} FAIRSEQ_LANGUAGE_CODES = ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN"] # fmt: skip @@ -70,8 +55,6 @@ class MBartTokenizer(PreTrainedTokenizer): ```""" vocab_files_names = VOCAB_FILES_NAMES - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP model_input_names = ["input_ids", "attention_mask"] prefix_tokens: List[int] = [] diff --git a/src/transformers/models/mbart/tokenization_mbart_fast.py b/src/transformers/models/mbart/tokenization_mbart_fast.py index 8638ab974e..71107bf0cd 100644 --- a/src/transformers/models/mbart/tokenization_mbart_fast.py +++ b/src/transformers/models/mbart/tokenization_mbart_fast.py @@ -35,25 +35,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/mbart-large-en-ro": ( - "https://huggingface.co/facebook/mbart-large-en-ro/resolve/main/sentencepiece.bpe.model" - ), - "facebook/mbart-large-cc25": ( - "https://huggingface.co/facebook/mbart-large-cc25/resolve/main/sentencepiece.bpe.model" - ), - }, - "tokenizer_file": { - "facebook/mbart-large-en-ro": "https://huggingface.co/facebook/mbart-large-en-ro/resolve/main/tokenizer.json", - "facebook/mbart-large-cc25": "https://huggingface.co/facebook/mbart-large-cc25/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/mbart-large-en-ro": 1024, - "facebook/mbart-large-cc25": 1024, -} FAIRSEQ_LANGUAGE_CODES = ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN"] # fmt: skip @@ -83,8 +64,6 @@ class MBartTokenizerFast(PreTrainedTokenizerFast): ```""" vocab_files_names = VOCAB_FILES_NAMES - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = MBartTokenizer diff --git a/src/transformers/models/mbart50/tokenization_mbart50.py b/src/transformers/models/mbart50/tokenization_mbart50.py index cd4e52f42e..7acc6ecbf3 100644 --- a/src/transformers/models/mbart50/tokenization_mbart50.py +++ b/src/transformers/models/mbart50/tokenization_mbart50.py @@ -29,17 +29,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/mbart-large-50-one-to-many-mmt": ( - "https://huggingface.co/facebook/mbart-large-50-one-to-many-mmt/resolve/main/sentencepiece.bpe.model" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/mbart-large-50-one-to-many-mmt": 1024, -} FAIRSEQ_LANGUAGE_CODES = ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"] # fmt: skip @@ -104,8 +93,6 @@ class MBart50Tokenizer(PreTrainedTokenizer): ```""" vocab_files_names = VOCAB_FILES_NAMES - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP model_input_names = ["input_ids", "attention_mask"] prefix_tokens: List[int] = [] diff --git a/src/transformers/models/mbart50/tokenization_mbart50_fast.py b/src/transformers/models/mbart50/tokenization_mbart50_fast.py index 701e30d916..cc4678f5f5 100644 --- a/src/transformers/models/mbart50/tokenization_mbart50_fast.py +++ b/src/transformers/models/mbart50/tokenization_mbart50_fast.py @@ -34,22 +34,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/mbart-large-50-one-to-many-mmt": ( - "https://huggingface.co/facebook/mbart-large-50-one-to-many-mmt/resolve/main/sentencepiece.bpe.model" - ), - }, - "tokenizer_file": { - "facebook/mbart-large-50-one-to-many-mmt": ( - "https://huggingface.co/facebook/mbart-large-50-one-to-many-mmt/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/mbart-large-50-one-to-many-mmt": 1024, -} FAIRSEQ_LANGUAGE_CODES = ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"] # fmt: skip @@ -100,8 +84,6 @@ class MBart50TokenizerFast(PreTrainedTokenizerFast): ```""" vocab_files_names = VOCAB_FILES_NAMES - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = MBart50Tokenizer diff --git a/src/transformers/models/mega/configuration_mega.py b/src/transformers/models/mega/configuration_mega.py index 34f858569c..993a21cf70 100644 --- a/src/transformers/models/mega/configuration_mega.py +++ b/src/transformers/models/mega/configuration_mega.py @@ -23,9 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MEGA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "mnaylor/mega-base-wikitext": "https://huggingface.co/mnaylor/mega-base-wikitext/resolve/main/config.json", -} + +from ..deprecated._archive_maps import MEGA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MegaConfig(PretrainedConfig): diff --git a/src/transformers/models/mega/modeling_mega.py b/src/transformers/models/mega/modeling_mega.py index dda31f5d94..069c717a73 100644 --- a/src/transformers/models/mega/modeling_mega.py +++ b/src/transformers/models/mega/modeling_mega.py @@ -50,10 +50,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "mnaylor/mega-base-wikitext" _CONFIG_FOR_DOC = "MegaConfig" -MEGA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "mnaylor/mega-base-wikitext", - # See all Mega models at https://huggingface.co/models?filter=mega -] + +from ..deprecated._archive_maps import MEGA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class MegaEmbeddings(nn.Module): diff --git a/src/transformers/models/megatron_bert/configuration_megatron_bert.py b/src/transformers/models/megatron_bert/configuration_megatron_bert.py index 02cdf28943..177bc146a2 100644 --- a/src/transformers/models/megatron_bert/configuration_megatron_bert.py +++ b/src/transformers/models/megatron_bert/configuration_megatron_bert.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MEGATRON_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - # See all MEGATRON_BERT models at https://huggingface.co/models?filter=bert -} + +from ..deprecated._archive_maps import MEGATRON_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MegatronBertConfig(PretrainedConfig): diff --git a/src/transformers/models/megatron_bert/modeling_megatron_bert.py b/src/transformers/models/megatron_bert/modeling_megatron_bert.py index 9111f937bc..528bcca3d9 100755 --- a/src/transformers/models/megatron_bert/modeling_megatron_bert.py +++ b/src/transformers/models/megatron_bert/modeling_megatron_bert.py @@ -57,10 +57,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "MegatronBertConfig" _CHECKPOINT_FOR_DOC = "nvidia/megatron-bert-cased-345m" -MEGATRON_BERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "nvidia/megatron-bert-cased-345m", - # See all MegatronBERT models at https://huggingface.co/models?filter=megatron_bert -] + +from ..deprecated._archive_maps import MEGATRON_BERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_megatron_bert(model, config, tf_checkpoint_path): diff --git a/src/transformers/models/mgp_str/configuration_mgp_str.py b/src/transformers/models/mgp_str/configuration_mgp_str.py index 4644b4f0cc..2d341309a8 100644 --- a/src/transformers/models/mgp_str/configuration_mgp_str.py +++ b/src/transformers/models/mgp_str/configuration_mgp_str.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MGP_STR_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "alibaba-damo/mgp-str-base": "https://huggingface.co/alibaba-damo/mgp-str-base/resolve/main/config.json", -} + +from ..deprecated._archive_maps import MGP_STR_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MgpstrConfig(PretrainedConfig): diff --git a/src/transformers/models/mgp_str/modeling_mgp_str.py b/src/transformers/models/mgp_str/modeling_mgp_str.py index 8914e59a20..e35c414d73 100644 --- a/src/transformers/models/mgp_str/modeling_mgp_str.py +++ b/src/transformers/models/mgp_str/modeling_mgp_str.py @@ -44,10 +44,8 @@ _TOKENIZER_FOR_DOC = "MgpstrTokenizer" # Base docstring _CHECKPOINT_FOR_DOC = "alibaba-damo/mgp-str-base" -MGP_STR_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "alibaba-damo/mgp-str-base", - # See all MGP-STR models at https://huggingface.co/models?filter=mgp-str -] + +from ..deprecated._archive_maps import MGP_STR_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.beit.modeling_beit.drop_path diff --git a/src/transformers/models/mgp_str/tokenization_mgp_str.py b/src/transformers/models/mgp_str/tokenization_mgp_str.py index 7fe1106115..a34ba744c1 100644 --- a/src/transformers/models/mgp_str/tokenization_mgp_str.py +++ b/src/transformers/models/mgp_str/tokenization_mgp_str.py @@ -26,14 +26,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "mgp-str": "https://huggingface.co/alibaba-damo/mgp-str-base/blob/main/vocab.json", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"mgp-str": 27} - class MgpstrTokenizer(PreTrainedTokenizer): """ @@ -58,8 +50,6 @@ class MgpstrTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__(self, vocab_file, unk_token="[GO]", bos_token="[GO]", eos_token="[s]", pad_token="[GO]", **kwargs): with open(vocab_file, encoding="utf-8") as vocab_handle: diff --git a/src/transformers/models/mistral/configuration_mistral.py b/src/transformers/models/mistral/configuration_mistral.py index a6c4634f61..83dd0e7a62 100644 --- a/src/transformers/models/mistral/configuration_mistral.py +++ b/src/transformers/models/mistral/configuration_mistral.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MISTRAL_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "mistralai/Mistral-7B-v0.1": "https://huggingface.co/mistralai/Mistral-7B-v0.1/resolve/main/config.json", - "mistralai/Mistral-7B-Instruct-v0.1": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1/resolve/main/config.json", -} + +from ..deprecated._archive_maps import MISTRAL_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MistralConfig(PretrainedConfig): diff --git a/src/transformers/models/mixtral/configuration_mixtral.py b/src/transformers/models/mixtral/configuration_mixtral.py index ac2dbed16e..93dfbbbda5 100644 --- a/src/transformers/models/mixtral/configuration_mixtral.py +++ b/src/transformers/models/mixtral/configuration_mixtral.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MIXTRAL_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "mistral-ai/Mixtral-8x7B": "https://huggingface.co/mistral-ai/Mixtral-8x7B/resolve/main/config.json", -} + +from ..deprecated._archive_maps import MIXTRAL_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MixtralConfig(PretrainedConfig): diff --git a/src/transformers/models/mluke/tokenization_mluke.py b/src/transformers/models/mluke/tokenization_mluke.py index 028de5d4f7..3ef5e64ed2 100644 --- a/src/transformers/models/mluke/tokenization_mluke.py +++ b/src/transformers/models/mluke/tokenization_mluke.py @@ -52,21 +52,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "entity_vocab_file": "entity_vocab.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "studio-ousia/mluke-base": "https://huggingface.co/studio-ousia/mluke-base/resolve/main/vocab.json", - }, - "merges_file": { - "studio-ousia/mluke-base": "https://huggingface.co/studio-ousia/mluke-base/resolve/main/merges.txt", - }, - "entity_vocab_file": { - "studio-ousia/mluke-base": "https://huggingface.co/studio-ousia/mluke-base/resolve/main/entity_vocab.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "studio-ousia/mluke-base": 512, -} ENCODE_PLUS_ADDITIONAL_KWARGS_DOCSTRING = r""" return_token_type_ids (`bool`, *optional*): @@ -230,8 +215,6 @@ class MLukeTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/mobilebert/configuration_mobilebert.py b/src/transformers/models/mobilebert/configuration_mobilebert.py index b14d25ea9e..d66dba8c02 100644 --- a/src/transformers/models/mobilebert/configuration_mobilebert.py +++ b/src/transformers/models/mobilebert/configuration_mobilebert.py @@ -23,9 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MOBILEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/mobilebert-uncased": "https://huggingface.co/google/mobilebert-uncased/resolve/main/config.json" -} + +from ..deprecated._archive_maps import MOBILEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MobileBertConfig(PretrainedConfig): @@ -104,12 +103,8 @@ class MobileBertConfig(PretrainedConfig): >>> # Accessing the model configuration >>> configuration = model.config ``` - - Attributes: pretrained_config_archive_map (Dict[str, str]): A dictionary containing all the available pre-trained - checkpoints. """ - pretrained_config_archive_map = MOBILEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP model_type = "mobilebert" def __init__( diff --git a/src/transformers/models/mobilebert/modeling_mobilebert.py b/src/transformers/models/mobilebert/modeling_mobilebert.py index 70f2ebc7bf..8dc0aafa70 100644 --- a/src/transformers/models/mobilebert/modeling_mobilebert.py +++ b/src/transformers/models/mobilebert/modeling_mobilebert.py @@ -76,7 +76,8 @@ _CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "lordtt13/emo-mobilebert" _SEQ_CLASS_EXPECTED_OUTPUT = "'others'" _SEQ_CLASS_EXPECTED_LOSS = "4.72" -MOBILEBERT_PRETRAINED_MODEL_ARCHIVE_LIST = ["google/mobilebert-uncased"] + +from ..deprecated._archive_maps import MOBILEBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_mobilebert(model, config, tf_checkpoint_path): @@ -685,7 +686,6 @@ class MobileBertPreTrainedModel(PreTrainedModel): """ config_class = MobileBertConfig - pretrained_model_archive_map = MOBILEBERT_PRETRAINED_MODEL_ARCHIVE_LIST load_tf_weights = load_tf_weights_in_mobilebert base_model_prefix = "mobilebert" diff --git a/src/transformers/models/mobilebert/modeling_tf_mobilebert.py b/src/transformers/models/mobilebert/modeling_tf_mobilebert.py index 6ccc996557..8526e636a2 100644 --- a/src/transformers/models/mobilebert/modeling_tf_mobilebert.py +++ b/src/transformers/models/mobilebert/modeling_tf_mobilebert.py @@ -84,10 +84,8 @@ _CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "vumichien/emo-mobilebert" _SEQ_CLASS_EXPECTED_OUTPUT = "'others'" _SEQ_CLASS_EXPECTED_LOSS = "4.72" -TF_MOBILEBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/mobilebert-uncased", - # See all MobileBERT models at https://huggingface.co/models?filter=mobilebert -] + +from ..deprecated._archive_maps import TF_MOBILEBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.bert.modeling_tf_bert.TFBertPreTrainingLoss diff --git a/src/transformers/models/mobilebert/tokenization_mobilebert.py b/src/transformers/models/mobilebert/tokenization_mobilebert.py index f27873e92f..ccfdcc31ff 100644 --- a/src/transformers/models/mobilebert/tokenization_mobilebert.py +++ b/src/transformers/models/mobilebert/tokenization_mobilebert.py @@ -29,15 +29,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": {"mobilebert-uncased": "https://huggingface.co/google/mobilebert-uncased/resolve/main/vocab.txt"} -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"mobilebert-uncased": 512} - - -PRETRAINED_INIT_CONFIGURATION = {} - # Copied from transformers.models.bert.tokenization_bert.load_vocab def load_vocab(vocab_file): @@ -105,9 +96,6 @@ class MobileBertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/mobilebert/tokenization_mobilebert_fast.py b/src/transformers/models/mobilebert/tokenization_mobilebert_fast.py index 2b137d2ed6..2105792409 100644 --- a/src/transformers/models/mobilebert/tokenization_mobilebert_fast.py +++ b/src/transformers/models/mobilebert/tokenization_mobilebert_fast.py @@ -29,18 +29,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": {"mobilebert-uncased": "https://huggingface.co/google/mobilebert-uncased/resolve/main/vocab.txt"}, - "tokenizer_file": { - "mobilebert-uncased": "https://huggingface.co/google/mobilebert-uncased/resolve/main/tokenizer.json" - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"mobilebert-uncased": 512} - - -PRETRAINED_INIT_CONFIGURATION = {} - # Copied from transformers.models.bert.tokenization_bert_fast.BertTokenizerFast with BERT->MobileBERT,Bert->MobileBert class MobileBertTokenizerFast(PreTrainedTokenizerFast): @@ -84,9 +72,6 @@ class MobileBertTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = MobileBertTokenizer def __init__( diff --git a/src/transformers/models/mobilenet_v1/configuration_mobilenet_v1.py b/src/transformers/models/mobilenet_v1/configuration_mobilenet_v1.py index 59f025c621..2b575cb6a1 100644 --- a/src/transformers/models/mobilenet_v1/configuration_mobilenet_v1.py +++ b/src/transformers/models/mobilenet_v1/configuration_mobilenet_v1.py @@ -26,11 +26,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MOBILENET_V1_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/mobilenet_v1_1.0_224": "https://huggingface.co/google/mobilenet_v1_1.0_224/resolve/main/config.json", - "google/mobilenet_v1_0.75_192": "https://huggingface.co/google/mobilenet_v1_0.75_192/resolve/main/config.json", - # See all MobileNetV1 models at https://huggingface.co/models?filter=mobilenet_v1 -} + +from ..deprecated._archive_maps import MOBILENET_V1_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MobileNetV1Config(PretrainedConfig): diff --git a/src/transformers/models/mobilenet_v1/modeling_mobilenet_v1.py b/src/transformers/models/mobilenet_v1/modeling_mobilenet_v1.py index 3963e60f35..adfb5c5670 100755 --- a/src/transformers/models/mobilenet_v1/modeling_mobilenet_v1.py +++ b/src/transformers/models/mobilenet_v1/modeling_mobilenet_v1.py @@ -43,11 +43,7 @@ _IMAGE_CLASS_CHECKPOINT = "google/mobilenet_v1_1.0_224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -MOBILENET_V1_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/mobilenet_v1_1.0_224", - "google/mobilenet_v1_0.75_192", - # See all MobileNetV1 models at https://huggingface.co/models?filter=mobilenet_v1 -] +from ..deprecated._archive_maps import MOBILENET_V1_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def _build_tf_to_pytorch_map(model, config, tf_weights=None): diff --git a/src/transformers/models/mobilenet_v2/configuration_mobilenet_v2.py b/src/transformers/models/mobilenet_v2/configuration_mobilenet_v2.py index 161f0e6d8f..dd9f6d17cd 100644 --- a/src/transformers/models/mobilenet_v2/configuration_mobilenet_v2.py +++ b/src/transformers/models/mobilenet_v2/configuration_mobilenet_v2.py @@ -26,13 +26,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MOBILENET_V2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/mobilenet_v2_1.4_224": "https://huggingface.co/google/mobilenet_v2_1.4_224/resolve/main/config.json", - "google/mobilenet_v2_1.0_224": "https://huggingface.co/google/mobilenet_v2_1.0_224/resolve/main/config.json", - "google/mobilenet_v2_0.75_160": "https://huggingface.co/google/mobilenet_v2_0.75_160/resolve/main/config.json", - "google/mobilenet_v2_0.35_96": "https://huggingface.co/google/mobilenet_v2_0.35_96/resolve/main/config.json", - # See all MobileNetV2 models at https://huggingface.co/models?filter=mobilenet_v2 -} + +from ..deprecated._archive_maps import MOBILENET_V2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MobileNetV2Config(PretrainedConfig): diff --git a/src/transformers/models/mobilenet_v2/modeling_mobilenet_v2.py b/src/transformers/models/mobilenet_v2/modeling_mobilenet_v2.py index b76e68f906..789da48401 100755 --- a/src/transformers/models/mobilenet_v2/modeling_mobilenet_v2.py +++ b/src/transformers/models/mobilenet_v2/modeling_mobilenet_v2.py @@ -53,13 +53,7 @@ _IMAGE_CLASS_CHECKPOINT = "google/mobilenet_v2_1.0_224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -MOBILENET_V2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/mobilenet_v2_1.4_224", - "google/mobilenet_v2_1.0_224", - "google/mobilenet_v2_0.37_160", - "google/mobilenet_v2_0.35_96", - # See all MobileNetV2 models at https://huggingface.co/models?filter=mobilenet_v2 -] +from ..deprecated._archive_maps import MOBILENET_V2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def _build_tf_to_pytorch_map(model, config, tf_weights=None): diff --git a/src/transformers/models/mobilevit/configuration_mobilevit.py b/src/transformers/models/mobilevit/configuration_mobilevit.py index 24429bbbcc..8f13112447 100644 --- a/src/transformers/models/mobilevit/configuration_mobilevit.py +++ b/src/transformers/models/mobilevit/configuration_mobilevit.py @@ -26,21 +26,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MOBILEVIT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "apple/mobilevit-small": "https://huggingface.co/apple/mobilevit-small/resolve/main/config.json", - "apple/mobilevit-x-small": "https://huggingface.co/apple/mobilevit-x-small/resolve/main/config.json", - "apple/mobilevit-xx-small": "https://huggingface.co/apple/mobilevit-xx-small/resolve/main/config.json", - "apple/deeplabv3-mobilevit-small": ( - "https://huggingface.co/apple/deeplabv3-mobilevit-small/resolve/main/config.json" - ), - "apple/deeplabv3-mobilevit-x-small": ( - "https://huggingface.co/apple/deeplabv3-mobilevit-x-small/resolve/main/config.json" - ), - "apple/deeplabv3-mobilevit-xx-small": ( - "https://huggingface.co/apple/deeplabv3-mobilevit-xx-small/resolve/main/config.json" - ), - # See all MobileViT models at https://huggingface.co/models?filter=mobilevit -} + +from ..deprecated._archive_maps import MOBILEVIT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MobileViTConfig(PretrainedConfig): diff --git a/src/transformers/models/mobilevit/modeling_mobilevit.py b/src/transformers/models/mobilevit/modeling_mobilevit.py index 1de0f6adbf..939982148c 100755 --- a/src/transformers/models/mobilevit/modeling_mobilevit.py +++ b/src/transformers/models/mobilevit/modeling_mobilevit.py @@ -59,15 +59,7 @@ _IMAGE_CLASS_CHECKPOINT = "apple/mobilevit-small" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -MOBILEVIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "apple/mobilevit-small", - "apple/mobilevit-x-small", - "apple/mobilevit-xx-small", - "apple/deeplabv3-mobilevit-small", - "apple/deeplabv3-mobilevit-x-small", - "apple/deeplabv3-mobilevit-xx-small", - # See all MobileViT models at https://huggingface.co/models?filter=mobilevit -] +from ..deprecated._archive_maps import MOBILEVIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def make_divisible(value: int, divisor: int = 8, min_value: Optional[int] = None) -> int: diff --git a/src/transformers/models/mobilevit/modeling_tf_mobilevit.py b/src/transformers/models/mobilevit/modeling_tf_mobilevit.py index 2024979936..8434c9685e 100644 --- a/src/transformers/models/mobilevit/modeling_tf_mobilevit.py +++ b/src/transformers/models/mobilevit/modeling_tf_mobilevit.py @@ -61,15 +61,7 @@ _IMAGE_CLASS_CHECKPOINT = "apple/mobilevit-small" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -TF_MOBILEVIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "apple/mobilevit-small", - "apple/mobilevit-x-small", - "apple/mobilevit-xx-small", - "apple/deeplabv3-mobilevit-small", - "apple/deeplabv3-mobilevit-x-small", - "apple/deeplabv3-mobilevit-xx-small", - # See all MobileViT models at https://huggingface.co/models?filter=mobilevit -] +from ..deprecated._archive_maps import TF_MOBILEVIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def make_divisible(value: int, divisor: int = 8, min_value: Optional[int] = None) -> int: diff --git a/src/transformers/models/mobilevitv2/configuration_mobilevitv2.py b/src/transformers/models/mobilevitv2/configuration_mobilevitv2.py index c3bc44f38e..f8f1be141b 100644 --- a/src/transformers/models/mobilevitv2/configuration_mobilevitv2.py +++ b/src/transformers/models/mobilevitv2/configuration_mobilevitv2.py @@ -26,9 +26,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MOBILEVITV2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "apple/mobilevitv2-1.0": "https://huggingface.co/apple/mobilevitv2-1.0/resolve/main/config.json", -} + +from ..deprecated._archive_maps import MOBILEVITV2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MobileViTV2Config(PretrainedConfig): diff --git a/src/transformers/models/mobilevitv2/modeling_mobilevitv2.py b/src/transformers/models/mobilevitv2/modeling_mobilevitv2.py index 842e78946e..c6c446b186 100644 --- a/src/transformers/models/mobilevitv2/modeling_mobilevitv2.py +++ b/src/transformers/models/mobilevitv2/modeling_mobilevitv2.py @@ -57,10 +57,7 @@ _IMAGE_CLASS_CHECKPOINT = "apple/mobilevitv2-1.0-imagenet1k-256" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -MOBILEVITV2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "apple/mobilevitv2-1.0-imagenet1k-256" - # See all MobileViTV2 models at https://huggingface.co/models?filter=mobilevitv2 -] +from ..deprecated._archive_maps import MOBILEVITV2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.mobilevit.modeling_mobilevit.make_divisible diff --git a/src/transformers/models/mpnet/configuration_mpnet.py b/src/transformers/models/mpnet/configuration_mpnet.py index fe492a963e..a8cb07894b 100644 --- a/src/transformers/models/mpnet/configuration_mpnet.py +++ b/src/transformers/models/mpnet/configuration_mpnet.py @@ -21,9 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MPNET_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/mpnet-base": "https://huggingface.co/microsoft/mpnet-base/resolve/main/config.json", -} + +from ..deprecated._archive_maps import MPNET_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MPNetConfig(PretrainedConfig): diff --git a/src/transformers/models/mpnet/modeling_mpnet.py b/src/transformers/models/mpnet/modeling_mpnet.py index 86194607e2..d9b9f90d39 100644 --- a/src/transformers/models/mpnet/modeling_mpnet.py +++ b/src/transformers/models/mpnet/modeling_mpnet.py @@ -45,14 +45,11 @@ _CHECKPOINT_FOR_DOC = "microsoft/mpnet-base" _CONFIG_FOR_DOC = "MPNetConfig" -MPNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/mpnet-base", -] +from ..deprecated._archive_maps import MPNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class MPNetPreTrainedModel(PreTrainedModel): config_class = MPNetConfig - pretrained_model_archive_map = MPNET_PRETRAINED_MODEL_ARCHIVE_LIST base_model_prefix = "mpnet" def _init_weights(self, module): diff --git a/src/transformers/models/mpnet/modeling_tf_mpnet.py b/src/transformers/models/mpnet/modeling_tf_mpnet.py index fe2825c76c..b57132d813 100644 --- a/src/transformers/models/mpnet/modeling_tf_mpnet.py +++ b/src/transformers/models/mpnet/modeling_tf_mpnet.py @@ -63,9 +63,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "microsoft/mpnet-base" _CONFIG_FOR_DOC = "MPNetConfig" -TF_MPNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/mpnet-base", -] + +from ..deprecated._archive_maps import TF_MPNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFMPNetPreTrainedModel(TFPreTrainedModel): diff --git a/src/transformers/models/mpnet/tokenization_mpnet.py b/src/transformers/models/mpnet/tokenization_mpnet.py index 51b8d0ff15..003575300e 100644 --- a/src/transformers/models/mpnet/tokenization_mpnet.py +++ b/src/transformers/models/mpnet/tokenization_mpnet.py @@ -28,20 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/mpnet-base": "https://huggingface.co/microsoft/mpnet-base/resolve/main/vocab.txt", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/mpnet-base": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/mpnet-base": {"do_lower_case": True}, -} - def load_vocab(vocab_file): """Loads a vocabulary file into a dictionary.""" @@ -125,9 +111,6 @@ class MPNetTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/mpnet/tokenization_mpnet_fast.py b/src/transformers/models/mpnet/tokenization_mpnet_fast.py index 1c9b1d5922..433c3028fc 100644 --- a/src/transformers/models/mpnet/tokenization_mpnet_fast.py +++ b/src/transformers/models/mpnet/tokenization_mpnet_fast.py @@ -30,23 +30,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/mpnet-base": "https://huggingface.co/microsoft/mpnet-base/resolve/main/vocab.txt", - }, - "tokenizer_file": { - "microsoft/mpnet-base": "https://huggingface.co/microsoft/mpnet-base/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/mpnet-base": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/mpnet-base": {"do_lower_case": True}, -} - class MPNetTokenizerFast(PreTrainedTokenizerFast): r""" @@ -104,9 +87,6 @@ class MPNetTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = MPNetTokenizer model_input_names = ["input_ids", "attention_mask"] diff --git a/src/transformers/models/mpt/configuration_mpt.py b/src/transformers/models/mpt/configuration_mpt.py index cc91966b6b..5c1cb4d783 100644 --- a/src/transformers/models/mpt/configuration_mpt.py +++ b/src/transformers/models/mpt/configuration_mpt.py @@ -25,9 +25,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MPT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "mosaicml/mpt-7b": "https://huggingface.co/mosaicml/mpt-7b/resolve/main/config.json", -} + +from ..deprecated._archive_maps import MPT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MptAttentionConfig(PretrainedConfig): diff --git a/src/transformers/models/mpt/modeling_mpt.py b/src/transformers/models/mpt/modeling_mpt.py index fc4af29d8c..864e9c09ca 100644 --- a/src/transformers/models/mpt/modeling_mpt.py +++ b/src/transformers/models/mpt/modeling_mpt.py @@ -42,18 +42,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "mosaicml/mpt-7b" _CONFIG_FOR_DOC = "MptConfig" -MPT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "mosaicml/mpt-7b", - "mosaicml/mpt-7b-storywriter", - "mosaicml/mpt-7b-instruct", - "mosaicml/mpt-7b-8k", - "mosaicml/mpt-7b-8k-instruct", - "mosaicml/mpt-7b-8k-chat", - "mosaicml/mpt-30b", - "mosaicml/mpt-30b-instruct", - "mosaicml/mpt-30b-chat", - # See all MPT models at https://huggingface.co/models?filter=mpt -] + +from ..deprecated._archive_maps import MPT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def build_mpt_alibi_tensor(num_heads, sequence_length, alibi_bias_max=8, device=None): diff --git a/src/transformers/models/mra/configuration_mra.py b/src/transformers/models/mra/configuration_mra.py index 5ae2f5b13b..2b3bec0416 100644 --- a/src/transformers/models/mra/configuration_mra.py +++ b/src/transformers/models/mra/configuration_mra.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -MRA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "uw-madison/mra-base-512-4": "https://huggingface.co/uw-madison/mra-base-512-4/resolve/main/config.json", -} + +from ..deprecated._archive_maps import MRA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MraConfig(PretrainedConfig): diff --git a/src/transformers/models/mra/modeling_mra.py b/src/transformers/models/mra/modeling_mra.py index 6e33753817..846578997c 100644 --- a/src/transformers/models/mra/modeling_mra.py +++ b/src/transformers/models/mra/modeling_mra.py @@ -53,10 +53,9 @@ _CHECKPOINT_FOR_DOC = "uw-madison/mra-base-512-4" _CONFIG_FOR_DOC = "MraConfig" _TOKENIZER_FOR_DOC = "AutoTokenizer" -MRA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "uw-madison/mra-base-512-4", - # See all Mra models at https://huggingface.co/models?filter=mra -] + +from ..deprecated._archive_maps import MRA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + mra_cuda_kernel = None diff --git a/src/transformers/models/mt5/modeling_mt5.py b/src/transformers/models/mt5/modeling_mt5.py index 100273a5ac..1c0351c9ea 100644 --- a/src/transformers/models/mt5/modeling_mt5.py +++ b/src/transformers/models/mt5/modeling_mt5.py @@ -59,14 +59,6 @@ _CHECKPOINT_FOR_DOC = "mt5-small" # This dict contains ids and associated url # for the pretrained weights provided with the models #################################################### -MT5_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/mt5-small", - "google/mt5-base", - "google/mt5-large", - "google/mt5-xl", - "google/mt5-xxl", - # See all mT5 models at https://huggingface.co/models?filter=mt5 -] PARALLELIZE_DOCSTRING = r""" This is an experimental feature and is a subject to change at a moment's notice. diff --git a/src/transformers/models/musicgen/configuration_musicgen.py b/src/transformers/models/musicgen/configuration_musicgen.py index c0f5662640..9d835835df 100644 --- a/src/transformers/models/musicgen/configuration_musicgen.py +++ b/src/transformers/models/musicgen/configuration_musicgen.py @@ -21,10 +21,8 @@ from ..auto.configuration_auto import AutoConfig logger = logging.get_logger(__name__) -MUSICGEN_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/musicgen-small": "https://huggingface.co/facebook/musicgen-small/resolve/main/config.json", - # See all Musicgen models at https://huggingface.co/models?filter=musicgen -} + +from ..deprecated._archive_maps import MUSICGEN_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class MusicgenDecoderConfig(PretrainedConfig): diff --git a/src/transformers/models/musicgen/modeling_musicgen.py b/src/transformers/models/musicgen/modeling_musicgen.py index bb5a5277f3..99e06f7df1 100644 --- a/src/transformers/models/musicgen/modeling_musicgen.py +++ b/src/transformers/models/musicgen/modeling_musicgen.py @@ -56,10 +56,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "MusicgenConfig" _CHECKPOINT_FOR_DOC = "facebook/musicgen-small" -MUSICGEN_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/musicgen-small", - # See all Musicgen models at https://huggingface.co/models?filter=musicgen -] + +from ..deprecated._archive_maps import MUSICGEN_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/mvp/configuration_mvp.py b/src/transformers/models/mvp/configuration_mvp.py index 9f60c79efa..00f6b14249 100644 --- a/src/transformers/models/mvp/configuration_mvp.py +++ b/src/transformers/models/mvp/configuration_mvp.py @@ -21,10 +21,6 @@ from ...utils import logging logger = logging.get_logger(__name__) -MVP_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "RUCAIBox/mvp": "https://huggingface.co/RUCAIBox/mvp/resolve/main/config.json", -} - class MvpConfig(PretrainedConfig): r""" diff --git a/src/transformers/models/mvp/modeling_mvp.py b/src/transformers/models/mvp/modeling_mvp.py index 88106a0787..fe289dc81e 100644 --- a/src/transformers/models/mvp/modeling_mvp.py +++ b/src/transformers/models/mvp/modeling_mvp.py @@ -53,24 +53,8 @@ _CONFIG_FOR_DOC = "MvpConfig" # Base model docstring _EXPECTED_OUTPUT_SHAPE = [1, 8, 1024] -MVP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "RUCAIBox/mvp", - "RUCAIBox/mvp-data-to-text", - "RUCAIBox/mvp-open-dialog", - "RUCAIBox/mvp-question-answering", - "RUCAIBox/mvp-question-generation", - "RUCAIBox/mvp-story", - "RUCAIBox/mvp-summarization", - "RUCAIBox/mvp-task-dialog", - "RUCAIBox/mtl-data-to-text", - "RUCAIBox/mtl-multi-task", - "RUCAIBox/mtl-open-dialog", - "RUCAIBox/mtl-question-answering", - "RUCAIBox/mtl-question-generation", - "RUCAIBox/mtl-story", - "RUCAIBox/mtl-summarization", - # See all MVP models at https://huggingface.co/models?filter=mvp -] + +from ..deprecated._archive_maps import MVP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.bart.modeling_bart.shift_tokens_right diff --git a/src/transformers/models/mvp/tokenization_mvp.py b/src/transformers/models/mvp/tokenization_mvp.py index d6f5e980bb..5a159320b7 100644 --- a/src/transformers/models/mvp/tokenization_mvp.py +++ b/src/transformers/models/mvp/tokenization_mvp.py @@ -30,21 +30,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt"} # See all MVP models at https://huggingface.co/models?filter=mvp -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "RUCAIBox/mvp": "https://huggingface.co/RUCAIBox/mvp/resolve/main/vocab.json", - }, - "added_tokens.json": { - "RUCAIBox/mvp": "https://huggingface.co/RUCAIBox/mvp/resolve/main/added_tokens.json", - }, - "merges_file": { - "RUCAIBox/mvp": "https://huggingface.co/RUCAIBox/mvp/resolve/main/merges.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "RUCAIBox/mvp": 1024, -} @lru_cache() @@ -165,8 +150,6 @@ class MvpTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/mvp/tokenization_mvp_fast.py b/src/transformers/models/mvp/tokenization_mvp_fast.py index a6ff13c089..5901c2bece 100644 --- a/src/transformers/models/mvp/tokenization_mvp_fast.py +++ b/src/transformers/models/mvp/tokenization_mvp_fast.py @@ -30,24 +30,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} # See all MVP models at https://huggingface.co/models?filter=mvp -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "RUCAIBox/mvp": "https://huggingface.co/RUCAIBox/mvp/resolve/main/vocab.json", - }, - "added_tokens.json": { - "RUCAIBox/mvp": "https://huggingface.co/RUCAIBox/mvp/resolve/main/added_tokens.json", - }, - "merges_file": { - "RUCAIBox/mvp": "https://huggingface.co/RUCAIBox/mvp/resolve/main/merges.txt", - }, - "tokenizer_file": { - "RUCAIBox/mvp": "https://huggingface.co/RUCAIBox/mvp/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "RUCAIBox/mvp": 1024, -} class MvpTokenizerFast(PreTrainedTokenizerFast): @@ -132,8 +114,6 @@ class MvpTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = MvpTokenizer diff --git a/src/transformers/models/nat/configuration_nat.py b/src/transformers/models/nat/configuration_nat.py index 4dff9c84da..bb3b85a80c 100644 --- a/src/transformers/models/nat/configuration_nat.py +++ b/src/transformers/models/nat/configuration_nat.py @@ -21,10 +21,8 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -NAT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "shi-labs/nat-mini-in1k-224": "https://huggingface.co/shi-labs/nat-mini-in1k-224/resolve/main/config.json", - # See all Nat models at https://huggingface.co/models?filter=nat -} + +from ..deprecated._archive_maps import NAT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class NatConfig(BackboneConfigMixin, PretrainedConfig): diff --git a/src/transformers/models/nat/modeling_nat.py b/src/transformers/models/nat/modeling_nat.py index 7384e2ac4c..2434b65161 100644 --- a/src/transformers/models/nat/modeling_nat.py +++ b/src/transformers/models/nat/modeling_nat.py @@ -68,10 +68,8 @@ _IMAGE_CLASS_CHECKPOINT = "shi-labs/nat-mini-in1k-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tiger cat" -NAT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "shi-labs/nat-mini-in1k-224", - # See all Nat models at https://huggingface.co/models?filter=nat -] +from ..deprecated._archive_maps import NAT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + # drop_path and NatDropPath are from the timm library. diff --git a/src/transformers/models/nezha/configuration_nezha.py b/src/transformers/models/nezha/configuration_nezha.py index e47f6e721f..a19c27d62a 100644 --- a/src/transformers/models/nezha/configuration_nezha.py +++ b/src/transformers/models/nezha/configuration_nezha.py @@ -1,9 +1,5 @@ from ... import PretrainedConfig - - -NEZHA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "sijunhe/nezha-cn-base": "https://huggingface.co/sijunhe/nezha-cn-base/resolve/main/config.json", -} +from ..deprecated._archive_maps import NEZHA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class NezhaConfig(PretrainedConfig): @@ -64,7 +60,6 @@ class NezhaConfig(PretrainedConfig): >>> configuration = model.config ```""" - pretrained_config_archive_map = NEZHA_PRETRAINED_CONFIG_ARCHIVE_MAP model_type = "nezha" def __init__( diff --git a/src/transformers/models/nezha/modeling_nezha.py b/src/transformers/models/nezha/modeling_nezha.py index 918a10b275..6d983bd237 100644 --- a/src/transformers/models/nezha/modeling_nezha.py +++ b/src/transformers/models/nezha/modeling_nezha.py @@ -55,13 +55,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "sijunhe/nezha-cn-base" _CONFIG_FOR_DOC = "NezhaConfig" -NEZHA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "sijunhe/nezha-cn-base", - "sijunhe/nezha-cn-large", - "sijunhe/nezha-base-wwm", - "sijunhe/nezha-large-wwm", - # See all Nezha models at https://huggingface.co/models?filter=nezha -] + +from ..deprecated._archive_maps import NEZHA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_nezha(model, config, tf_checkpoint_path): diff --git a/src/transformers/models/nllb/tokenization_nllb.py b/src/transformers/models/nllb/tokenization_nllb.py index ee2285e826..f517121157 100644 --- a/src/transformers/models/nllb/tokenization_nllb.py +++ b/src/transformers/models/nllb/tokenization_nllb.py @@ -29,17 +29,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/nllb-200-distilled-600M": ( - "https://huggingface.co/facebook/nllb-200-distilled-600M/blob/main/sentencepiece.bpe.model" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/nllb-200-distilled-600M": 1024, -} FAIRSEQ_LANGUAGE_CODES = ['ace_Arab', 'ace_Latn', 'acm_Arab', 'acq_Arab', 'aeb_Arab', 'afr_Latn', 'ajp_Arab', 'aka_Latn', 'amh_Ethi', 'apc_Arab', 'arb_Arab', 'ars_Arab', 'ary_Arab', 'arz_Arab', 'asm_Beng', 'ast_Latn', 'awa_Deva', 'ayr_Latn', 'azb_Arab', 'azj_Latn', 'bak_Cyrl', 'bam_Latn', 'ban_Latn', 'bel_Cyrl', 'bem_Latn', 'ben_Beng', 'bho_Deva', 'bjn_Arab', 'bjn_Latn', 'bod_Tibt', 'bos_Latn', 'bug_Latn', 'bul_Cyrl', 'cat_Latn', 'ceb_Latn', 'ces_Latn', 'cjk_Latn', 'ckb_Arab', 'crh_Latn', 'cym_Latn', 'dan_Latn', 'deu_Latn', 'dik_Latn', 'dyu_Latn', 'dzo_Tibt', 'ell_Grek', 'eng_Latn', 'epo_Latn', 'est_Latn', 'eus_Latn', 'ewe_Latn', 'fao_Latn', 'pes_Arab', 'fij_Latn', 'fin_Latn', 'fon_Latn', 'fra_Latn', 'fur_Latn', 'fuv_Latn', 'gla_Latn', 'gle_Latn', 'glg_Latn', 'grn_Latn', 'guj_Gujr', 'hat_Latn', 'hau_Latn', 'heb_Hebr', 'hin_Deva', 'hne_Deva', 'hrv_Latn', 'hun_Latn', 'hye_Armn', 'ibo_Latn', 'ilo_Latn', 'ind_Latn', 'isl_Latn', 'ita_Latn', 'jav_Latn', 'jpn_Jpan', 'kab_Latn', 'kac_Latn', 'kam_Latn', 'kan_Knda', 'kas_Arab', 'kas_Deva', 'kat_Geor', 'knc_Arab', 'knc_Latn', 'kaz_Cyrl', 'kbp_Latn', 'kea_Latn', 'khm_Khmr', 'kik_Latn', 'kin_Latn', 'kir_Cyrl', 'kmb_Latn', 'kon_Latn', 'kor_Hang', 'kmr_Latn', 'lao_Laoo', 'lvs_Latn', 'lij_Latn', 'lim_Latn', 'lin_Latn', 'lit_Latn', 'lmo_Latn', 'ltg_Latn', 'ltz_Latn', 'lua_Latn', 'lug_Latn', 'luo_Latn', 'lus_Latn', 'mag_Deva', 'mai_Deva', 'mal_Mlym', 'mar_Deva', 'min_Latn', 'mkd_Cyrl', 'plt_Latn', 'mlt_Latn', 'mni_Beng', 'khk_Cyrl', 'mos_Latn', 'mri_Latn', 'zsm_Latn', 'mya_Mymr', 'nld_Latn', 'nno_Latn', 'nob_Latn', 'npi_Deva', 'nso_Latn', 'nus_Latn', 'nya_Latn', 'oci_Latn', 'gaz_Latn', 'ory_Orya', 'pag_Latn', 'pan_Guru', 'pap_Latn', 'pol_Latn', 'por_Latn', 'prs_Arab', 'pbt_Arab', 'quy_Latn', 'ron_Latn', 'run_Latn', 'rus_Cyrl', 'sag_Latn', 'san_Deva', 'sat_Beng', 'scn_Latn', 'shn_Mymr', 'sin_Sinh', 'slk_Latn', 'slv_Latn', 'smo_Latn', 'sna_Latn', 'snd_Arab', 'som_Latn', 'sot_Latn', 'spa_Latn', 'als_Latn', 'srd_Latn', 'srp_Cyrl', 'ssw_Latn', 'sun_Latn', 'swe_Latn', 'swh_Latn', 'szl_Latn', 'tam_Taml', 'tat_Cyrl', 'tel_Telu', 'tgk_Cyrl', 'tgl_Latn', 'tha_Thai', 'tir_Ethi', 'taq_Latn', 'taq_Tfng', 'tpi_Latn', 'tsn_Latn', 'tso_Latn', 'tuk_Latn', 'tum_Latn', 'tur_Latn', 'twi_Latn', 'tzm_Tfng', 'uig_Arab', 'ukr_Cyrl', 'umb_Latn', 'urd_Arab', 'uzn_Latn', 'vec_Latn', 'vie_Latn', 'war_Latn', 'wol_Latn', 'xho_Latn', 'ydd_Hebr', 'yor_Latn', 'yue_Hant', 'zho_Hans', 'zho_Hant', 'zul_Latn'] # fmt: skip @@ -116,8 +105,6 @@ class NllbTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP model_input_names = ["input_ids", "attention_mask"] prefix_tokens: List[int] = [] diff --git a/src/transformers/models/nllb/tokenization_nllb_fast.py b/src/transformers/models/nllb/tokenization_nllb_fast.py index d71de82d41..2004580bf6 100644 --- a/src/transformers/models/nllb/tokenization_nllb_fast.py +++ b/src/transformers/models/nllb/tokenization_nllb_fast.py @@ -35,23 +35,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/nllb-200-distilled-600M": ( - "https://huggingface.co/facebook/nllb-200-distilled-600M/resolve/main/sentencepiece.bpe.model" - ), - }, - "tokenizer_file": { - "facebook/nllb-200-distilled-600M": ( - "https://huggingface.co/facebook/nllb-200-distilled-600M/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/nllb-large-en-ro": 1024, - "facebook/nllb-200-distilled-600M": 1024, -} FAIRSEQ_LANGUAGE_CODES = ['ace_Arab', 'ace_Latn', 'acm_Arab', 'acq_Arab', 'aeb_Arab', 'afr_Latn', 'ajp_Arab', 'aka_Latn', 'amh_Ethi', 'apc_Arab', 'arb_Arab', 'ars_Arab', 'ary_Arab', 'arz_Arab', 'asm_Beng', 'ast_Latn', 'awa_Deva', 'ayr_Latn', 'azb_Arab', 'azj_Latn', 'bak_Cyrl', 'bam_Latn', 'ban_Latn', 'bel_Cyrl', 'bem_Latn', 'ben_Beng', 'bho_Deva', 'bjn_Arab', 'bjn_Latn', 'bod_Tibt', 'bos_Latn', 'bug_Latn', 'bul_Cyrl', 'cat_Latn', 'ceb_Latn', 'ces_Latn', 'cjk_Latn', 'ckb_Arab', 'crh_Latn', 'cym_Latn', 'dan_Latn', 'deu_Latn', 'dik_Latn', 'dyu_Latn', 'dzo_Tibt', 'ell_Grek', 'eng_Latn', 'epo_Latn', 'est_Latn', 'eus_Latn', 'ewe_Latn', 'fao_Latn', 'pes_Arab', 'fij_Latn', 'fin_Latn', 'fon_Latn', 'fra_Latn', 'fur_Latn', 'fuv_Latn', 'gla_Latn', 'gle_Latn', 'glg_Latn', 'grn_Latn', 'guj_Gujr', 'hat_Latn', 'hau_Latn', 'heb_Hebr', 'hin_Deva', 'hne_Deva', 'hrv_Latn', 'hun_Latn', 'hye_Armn', 'ibo_Latn', 'ilo_Latn', 'ind_Latn', 'isl_Latn', 'ita_Latn', 'jav_Latn', 'jpn_Jpan', 'kab_Latn', 'kac_Latn', 'kam_Latn', 'kan_Knda', 'kas_Arab', 'kas_Deva', 'kat_Geor', 'knc_Arab', 'knc_Latn', 'kaz_Cyrl', 'kbp_Latn', 'kea_Latn', 'khm_Khmr', 'kik_Latn', 'kin_Latn', 'kir_Cyrl', 'kmb_Latn', 'kon_Latn', 'kor_Hang', 'kmr_Latn', 'lao_Laoo', 'lvs_Latn', 'lij_Latn', 'lim_Latn', 'lin_Latn', 'lit_Latn', 'lmo_Latn', 'ltg_Latn', 'ltz_Latn', 'lua_Latn', 'lug_Latn', 'luo_Latn', 'lus_Latn', 'mag_Deva', 'mai_Deva', 'mal_Mlym', 'mar_Deva', 'min_Latn', 'mkd_Cyrl', 'plt_Latn', 'mlt_Latn', 'mni_Beng', 'khk_Cyrl', 'mos_Latn', 'mri_Latn', 'zsm_Latn', 'mya_Mymr', 'nld_Latn', 'nno_Latn', 'nob_Latn', 'npi_Deva', 'nso_Latn', 'nus_Latn', 'nya_Latn', 'oci_Latn', 'gaz_Latn', 'ory_Orya', 'pag_Latn', 'pan_Guru', 'pap_Latn', 'pol_Latn', 'por_Latn', 'prs_Arab', 'pbt_Arab', 'quy_Latn', 'ron_Latn', 'run_Latn', 'rus_Cyrl', 'sag_Latn', 'san_Deva', 'sat_Beng', 'scn_Latn', 'shn_Mymr', 'sin_Sinh', 'slk_Latn', 'slv_Latn', 'smo_Latn', 'sna_Latn', 'snd_Arab', 'som_Latn', 'sot_Latn', 'spa_Latn', 'als_Latn', 'srd_Latn', 'srp_Cyrl', 'ssw_Latn', 'sun_Latn', 'swe_Latn', 'swh_Latn', 'szl_Latn', 'tam_Taml', 'tat_Cyrl', 'tel_Telu', 'tgk_Cyrl', 'tgl_Latn', 'tha_Thai', 'tir_Ethi', 'taq_Latn', 'taq_Tfng', 'tpi_Latn', 'tsn_Latn', 'tso_Latn', 'tuk_Latn', 'tum_Latn', 'tur_Latn', 'twi_Latn', 'tzm_Tfng', 'uig_Arab', 'ukr_Cyrl', 'umb_Latn', 'urd_Arab', 'uzn_Latn', 'vec_Latn', 'vie_Latn', 'war_Latn', 'wol_Latn', 'xho_Latn', 'ydd_Hebr', 'yor_Latn', 'yue_Hant', 'zho_Hans', 'zho_Hant', 'zul_Latn'] # fmt: skip @@ -127,8 +110,6 @@ class NllbTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = NllbTokenizer diff --git a/src/transformers/models/nllb_moe/configuration_nllb_moe.py b/src/transformers/models/nllb_moe/configuration_nllb_moe.py index 435d7caa17..48172824ff 100644 --- a/src/transformers/models/nllb_moe/configuration_nllb_moe.py +++ b/src/transformers/models/nllb_moe/configuration_nllb_moe.py @@ -19,9 +19,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -NLLB_MOE_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/nllb-moe-54B": "https://huggingface.co/facebook/nllb-moe-54b/resolve/main/config.json", -} + +from ..deprecated._archive_maps import NLLB_MOE_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class NllbMoeConfig(PretrainedConfig): diff --git a/src/transformers/models/nllb_moe/modeling_nllb_moe.py b/src/transformers/models/nllb_moe/modeling_nllb_moe.py index e02c0b0fd7..4ef66b7bd5 100644 --- a/src/transformers/models/nllb_moe/modeling_nllb_moe.py +++ b/src/transformers/models/nllb_moe/modeling_nllb_moe.py @@ -53,10 +53,8 @@ _REAL_CHECKPOINT_FOR_DOC = "facebook/nllb-moe-54b" # This dict contains ids and associated url # for the pretrained weights provided with the models #################################################### -NLLB_MOE_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/nllb-moe-54b", - # See all NLLB-MOE models at https://huggingface.co/models?filter=nllb-moe -] + +from ..deprecated._archive_maps import NLLB_MOE_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.bart.modeling_bart.shift_tokens_right diff --git a/src/transformers/models/nougat/tokenization_nougat_fast.py b/src/transformers/models/nougat/tokenization_nougat_fast.py index d02aec7575..ef6b613bba 100644 --- a/src/transformers/models/nougat/tokenization_nougat_fast.py +++ b/src/transformers/models/nougat/tokenization_nougat_fast.py @@ -49,14 +49,7 @@ INIT_TOKENIZER_DOCSTRING += """ """ -PRETRAINED_VOCAB_FILES_MAP = { - "tokenizer_file": { - "facebook/nougat-base": "https://huggingface.co/facebook/nougat-base/tokenizer/blob/main/tokenizer.json", - }, -} - VOCAB_FILES_NAMES = {"tokenizer_file": "tokenizer.json"} -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"facebook/nougat-base": 3584} def markdown_compatible(text: str) -> str: @@ -409,8 +402,6 @@ class NougatTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = None diff --git a/src/transformers/models/nystromformer/configuration_nystromformer.py b/src/transformers/models/nystromformer/configuration_nystromformer.py index e59b1ce810..af6e8d2c21 100644 --- a/src/transformers/models/nystromformer/configuration_nystromformer.py +++ b/src/transformers/models/nystromformer/configuration_nystromformer.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -NYSTROMFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "uw-madison/nystromformer-512": "https://huggingface.co/uw-madison/nystromformer-512/resolve/main/config.json", - # See all Nystromformer models at https://huggingface.co/models?filter=nystromformer -} + +from ..deprecated._archive_maps import NYSTROMFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class NystromformerConfig(PretrainedConfig): diff --git a/src/transformers/models/nystromformer/modeling_nystromformer.py b/src/transformers/models/nystromformer/modeling_nystromformer.py index 950f8d27fa..1da61bc59e 100755 --- a/src/transformers/models/nystromformer/modeling_nystromformer.py +++ b/src/transformers/models/nystromformer/modeling_nystromformer.py @@ -43,10 +43,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "uw-madison/nystromformer-512" _CONFIG_FOR_DOC = "NystromformerConfig" -NYSTROMFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "uw-madison/nystromformer-512", - # See all Nyströmformer models at https://huggingface.co/models?filter=nystromformer -] + +from ..deprecated._archive_maps import NYSTROMFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class NystromformerEmbeddings(nn.Module): diff --git a/src/transformers/models/oneformer/configuration_oneformer.py b/src/transformers/models/oneformer/configuration_oneformer.py index c4c2851947..1cbd2ab7db 100644 --- a/src/transformers/models/oneformer/configuration_oneformer.py +++ b/src/transformers/models/oneformer/configuration_oneformer.py @@ -22,12 +22,8 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -ONEFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "shi-labs/oneformer_ade20k_swin_tiny": ( - "https://huggingface.co/shi-labs/oneformer_ade20k_swin_tiny/blob/main/config.json" - ), - # See all OneFormer models at https://huggingface.co/models?filter=oneformer -} + +from ..deprecated._archive_maps import ONEFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class OneFormerConfig(PretrainedConfig): diff --git a/src/transformers/models/oneformer/modeling_oneformer.py b/src/transformers/models/oneformer/modeling_oneformer.py index 79ad21c39f..6af4226995 100644 --- a/src/transformers/models/oneformer/modeling_oneformer.py +++ b/src/transformers/models/oneformer/modeling_oneformer.py @@ -51,10 +51,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "OneFormerConfig" _CHECKPOINT_FOR_DOC = "shi-labs/oneformer_ade20k_swin_tiny" -ONEFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "shi-labs/oneformer_ade20k_swin_tiny", - # See all OneFormer models at https://huggingface.co/models?filter=oneformer -] + +from ..deprecated._archive_maps import ONEFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 if is_scipy_available(): diff --git a/src/transformers/models/openai/configuration_openai.py b/src/transformers/models/openai/configuration_openai.py index 38e646b393..422922c791 100644 --- a/src/transformers/models/openai/configuration_openai.py +++ b/src/transformers/models/openai/configuration_openai.py @@ -21,9 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "openai-community/openai-gpt": "https://huggingface.co/openai-community/openai-gpt/resolve/main/config.json" -} + +from ..deprecated._archive_maps import OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class OpenAIGPTConfig(PretrainedConfig): diff --git a/src/transformers/models/openai/modeling_openai.py b/src/transformers/models/openai/modeling_openai.py index 747118bd27..637aa90cff 100644 --- a/src/transformers/models/openai/modeling_openai.py +++ b/src/transformers/models/openai/modeling_openai.py @@ -46,10 +46,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "openai-community/openai-gpt" _CONFIG_FOR_DOC = "OpenAIGPTConfig" -OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "openai-community/openai-gpt", - # See all OpenAI GPT models at https://huggingface.co/models?filter=openai-community/openai-gpt -] + +from ..deprecated._archive_maps import OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_openai_gpt(model, config, openai_checkpoint_folder_path): diff --git a/src/transformers/models/openai/modeling_tf_openai.py b/src/transformers/models/openai/modeling_tf_openai.py index 34bc5aa522..b826936c51 100644 --- a/src/transformers/models/openai/modeling_tf_openai.py +++ b/src/transformers/models/openai/modeling_tf_openai.py @@ -55,10 +55,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "openai-community/openai-gpt" _CONFIG_FOR_DOC = "OpenAIGPTConfig" -TF_OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "openai-community/openai-gpt", - # See all OpenAI GPT models at https://huggingface.co/models?filter=openai-community/openai-gpt -] + +from ..deprecated._archive_maps import TF_OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFAttention(keras.layers.Layer): diff --git a/src/transformers/models/openai/tokenization_openai.py b/src/transformers/models/openai/tokenization_openai.py index e189b15035..4f2b279160 100644 --- a/src/transformers/models/openai/tokenization_openai.py +++ b/src/transformers/models/openai/tokenization_openai.py @@ -32,19 +32,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "openai-community/openai-gpt": "https://huggingface.co/openai-community/openai-gpt/resolve/main/vocab.json" - }, - "merges_file": { - "openai-community/openai-gpt": "https://huggingface.co/openai-community/openai-gpt/resolve/main/merges.txt" - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "openai-community/openai-gpt": 512, -} - # Copied from transformers.models.bert.tokenization_bert.whitespace_tokenize def whitespace_tokenize(text): @@ -268,8 +255,6 @@ class OpenAIGPTTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__(self, vocab_file, merges_file, unk_token="", **kwargs): diff --git a/src/transformers/models/openai/tokenization_openai_fast.py b/src/transformers/models/openai/tokenization_openai_fast.py index e1f04722ee..214db53850 100644 --- a/src/transformers/models/openai/tokenization_openai_fast.py +++ b/src/transformers/models/openai/tokenization_openai_fast.py @@ -26,22 +26,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "openai-community/openai-gpt": "https://huggingface.co/openai-community/openai-gpt/resolve/main/vocab.json" - }, - "merges_file": { - "openai-community/openai-gpt": "https://huggingface.co/openai-community/openai-gpt/resolve/main/merges.txt" - }, - "tokenizer_file": { - "openai-community/openai-gpt": "https://huggingface.co/openai-community/openai-gpt/resolve/main/tokenizer.json" - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "openai-community/openai-gpt": 512, -} - class OpenAIGPTTokenizerFast(PreTrainedTokenizerFast): """ @@ -65,8 +49,6 @@ class OpenAIGPTTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = OpenAIGPTTokenizer diff --git a/src/transformers/models/opt/configuration_opt.py b/src/transformers/models/opt/configuration_opt.py index 2918ee269a..a9802d2ef3 100644 --- a/src/transformers/models/opt/configuration_opt.py +++ b/src/transformers/models/opt/configuration_opt.py @@ -19,15 +19,6 @@ from ...utils import logging logger = logging.get_logger(__name__) -OPT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/opt-125m": "https://huggingface.co/facebook/opt-125m/blob/main/config.json", - "facebook/opt-350m": "https://huggingface.co/facebook/opt-350m/blob/main/config.json", - "facebook/opt-1.3b": "https://huggingface.co/facebook/opt-1.3b/blob/main/config.json", - "facebook/opt-2.7b": "https://huggingface.co/facebook/opt-2.7b/blob/main/config.json", - "facebook/opt-6.7b": "https://huggingface.co/facebook/opt-6.7b/blob/main/config.json", - "facebook/opt-13b": "https://huggingface.co/facebook/opt-13b/blob/main/config.json", -} - class OPTConfig(PretrainedConfig): r""" diff --git a/src/transformers/models/opt/modeling_opt.py b/src/transformers/models/opt/modeling_opt.py index a350c9019d..5e9e53a2ac 100644 --- a/src/transformers/models/opt/modeling_opt.py +++ b/src/transformers/models/opt/modeling_opt.py @@ -60,16 +60,8 @@ _CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "ArthurZ/opt-350m-dummy-sc" _SEQ_CLASS_EXPECTED_LOSS = 1.71 _SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_0'" -OPT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/opt-125m", - "facebook/opt-350m", - "facebook/opt-1.3b", - "facebook/opt-2.7b", - "facebook/opt-6.7b", - "facebook/opt-13b", - "facebook/opt-30b", - # See all OPT models at https://huggingface.co/models?filter=opt -] + +from ..deprecated._archive_maps import OPT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.llama.modeling_llama._get_unpad_data diff --git a/src/transformers/models/owlv2/configuration_owlv2.py b/src/transformers/models/owlv2/configuration_owlv2.py index fd15c0e797..fe96ff8fa4 100644 --- a/src/transformers/models/owlv2/configuration_owlv2.py +++ b/src/transformers/models/owlv2/configuration_owlv2.py @@ -27,9 +27,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -OWLV2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/owlv2-base-patch16": "https://huggingface.co/google/owlv2-base-patch16/resolve/main/config.json", -} + +from ..deprecated._archive_maps import OWLV2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 # Copied from transformers.models.owlvit.configuration_owlvit.OwlViTTextConfig with OwlViT->Owlv2, owlvit-base-patch32->owlv2-base-patch16, owlvit->owlv2, OWL-ViT->OWLv2 diff --git a/src/transformers/models/owlv2/modeling_owlv2.py b/src/transformers/models/owlv2/modeling_owlv2.py index 3506ce0fec..d99b269012 100644 --- a/src/transformers/models/owlv2/modeling_owlv2.py +++ b/src/transformers/models/owlv2/modeling_owlv2.py @@ -47,10 +47,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "google/owlv2-base-patch16-ensemble" # See all Owlv2 models at https://huggingface.co/models?filter=owlv2 -OWLV2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/owlv2-base-patch16-ensemble", - # See all OWLv2 models at https://huggingface.co/models?filter=owlv2 -] + +from ..deprecated._archive_maps import OWLV2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.clip.modeling_clip.contrastive_loss with clip->owlv2 diff --git a/src/transformers/models/owlvit/configuration_owlvit.py b/src/transformers/models/owlvit/configuration_owlvit.py index 254619cccd..d223cdf812 100644 --- a/src/transformers/models/owlvit/configuration_owlvit.py +++ b/src/transformers/models/owlvit/configuration_owlvit.py @@ -30,11 +30,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -OWLVIT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/owlvit-base-patch32": "https://huggingface.co/google/owlvit-base-patch32/resolve/main/config.json", - "google/owlvit-base-patch16": "https://huggingface.co/google/owlvit-base-patch16/resolve/main/config.json", - "google/owlvit-large-patch14": "https://huggingface.co/google/owlvit-large-patch14/resolve/main/config.json", -} + +from ..deprecated._archive_maps import OWLVIT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class OwlViTTextConfig(PretrainedConfig): diff --git a/src/transformers/models/owlvit/modeling_owlvit.py b/src/transformers/models/owlvit/modeling_owlvit.py index 64e9956430..751f9c9a52 100644 --- a/src/transformers/models/owlvit/modeling_owlvit.py +++ b/src/transformers/models/owlvit/modeling_owlvit.py @@ -47,11 +47,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "google/owlvit-base-patch32" # See all OwlViT models at https://huggingface.co/models?filter=owlvit -OWLVIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/owlvit-base-patch32", - "google/owlvit-base-patch16", - "google/owlvit-large-patch14", -] + +from ..deprecated._archive_maps import OWLVIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.clip.modeling_clip.contrastive_loss with clip->owlvit diff --git a/src/transformers/models/patchtsmixer/configuration_patchtsmixer.py b/src/transformers/models/patchtsmixer/configuration_patchtsmixer.py index 527b5a8327..2f4f1dc761 100644 --- a/src/transformers/models/patchtsmixer/configuration_patchtsmixer.py +++ b/src/transformers/models/patchtsmixer/configuration_patchtsmixer.py @@ -22,9 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -PATCHTSMIXER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "ibm/patchtsmixer-etth1-pretrain": "https://huggingface.co/ibm/patchtsmixer-etth1-pretrain/resolve/main/config.json", -} + +from ..deprecated._archive_maps import PATCHTSMIXER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class PatchTSMixerConfig(PretrainedConfig): diff --git a/src/transformers/models/patchtsmixer/modeling_patchtsmixer.py b/src/transformers/models/patchtsmixer/modeling_patchtsmixer.py index 5bccccb813..dade06dfde 100644 --- a/src/transformers/models/patchtsmixer/modeling_patchtsmixer.py +++ b/src/transformers/models/patchtsmixer/modeling_patchtsmixer.py @@ -39,10 +39,7 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "PatchTSMixerConfig" -PATCHTSMIXER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "ibm/patchtsmixer-etth1-pretrain", - # See all PatchTSMixer models at https://huggingface.co/models?filter=patchtsmixer -] +from ..deprecated._archive_maps import PATCHTSMIXER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 PATCHTSMIXER_START_DOCSTRING = r""" diff --git a/src/transformers/models/patchtst/configuration_patchtst.py b/src/transformers/models/patchtst/configuration_patchtst.py index 5cf949304e..dc95429d90 100644 --- a/src/transformers/models/patchtst/configuration_patchtst.py +++ b/src/transformers/models/patchtst/configuration_patchtst.py @@ -22,10 +22,8 @@ from transformers.utils import logging logger = logging.get_logger(__name__) -PATCHTST_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "ibm/patchtst-base": "https://huggingface.co/ibm/patchtst-base/resolve/main/config.json", - # See all PatchTST models at https://huggingface.co/ibm/models?filter=patchtst -} + +from ..deprecated._archive_maps import PATCHTST_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class PatchTSTConfig(PretrainedConfig): diff --git a/src/transformers/models/patchtst/modeling_patchtst.py b/src/transformers/models/patchtst/modeling_patchtst.py index 08ce547126..22b206726e 100755 --- a/src/transformers/models/patchtst/modeling_patchtst.py +++ b/src/transformers/models/patchtst/modeling_patchtst.py @@ -33,10 +33,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "PatchTSTConfig" -PATCHTST_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "ibm/patchtst-etth1-pretrain", - # See all PatchTST models at https://huggingface.co/models?filter=patchtst -] + +from ..deprecated._archive_maps import PATCHTST_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.bart.modeling_bart.BartAttention with Bart->PatchTST diff --git a/src/transformers/models/pegasus/configuration_pegasus.py b/src/transformers/models/pegasus/configuration_pegasus.py index 51b506c4e0..39d3865fd5 100644 --- a/src/transformers/models/pegasus/configuration_pegasus.py +++ b/src/transformers/models/pegasus/configuration_pegasus.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -PEGASUS_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/pegasus-large": "https://huggingface.co/google/pegasus-large/resolve/main/config.json", - # See all PEGASUS models at https://huggingface.co/models?filter=pegasus -} + +from ..deprecated._archive_maps import PEGASUS_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class PegasusConfig(PretrainedConfig): diff --git a/src/transformers/models/pegasus/modeling_pegasus.py b/src/transformers/models/pegasus/modeling_pegasus.py index 91fdb9c1db..069c6aa6fe 100755 --- a/src/transformers/models/pegasus/modeling_pegasus.py +++ b/src/transformers/models/pegasus/modeling_pegasus.py @@ -50,12 +50,6 @@ _CHECKPOINT_FOR_DOC = "google/pegasus-large" _CONFIG_FOR_DOC = "PegasusConfig" -PEGASUS_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/pegasus-large", - # See all PEGASUS models at https://huggingface.co/models?filter=pegasus -] - - # Copied from transformers.models.bart.modeling_bart.shift_tokens_right def shift_tokens_right(input_ids: torch.Tensor, pad_token_id: int, decoder_start_token_id: int): """ diff --git a/src/transformers/models/pegasus/tokenization_pegasus.py b/src/transformers/models/pegasus/tokenization_pegasus.py index e1c8f6933f..2763b739a9 100644 --- a/src/transformers/models/pegasus/tokenization_pegasus.py +++ b/src/transformers/models/pegasus/tokenization_pegasus.py @@ -26,14 +26,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": {"google/pegasus-xsum": "https://huggingface.co/google/pegasus-xsum/resolve/main/spiece.model"} -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/pegasus-xsum": 512, -} - logger = logging.get_logger(__name__) @@ -98,8 +90,6 @@ class PegasusTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/pegasus/tokenization_pegasus_fast.py b/src/transformers/models/pegasus/tokenization_pegasus_fast.py index 3bc1726876..f1252e959e 100644 --- a/src/transformers/models/pegasus/tokenization_pegasus_fast.py +++ b/src/transformers/models/pegasus/tokenization_pegasus_fast.py @@ -36,17 +36,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "spiece.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": {"google/pegasus-xsum": "https://huggingface.co/google/pegasus-xsum/resolve/main/spiece.model"}, - "tokenizer_file": { - "google/pegasus-xsum": "https://huggingface.co/google/pegasus-xsum/resolve/main/tokenizer.json" - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/pegasus-xsum": 512, -} - class PegasusTokenizerFast(PreTrainedTokenizerFast): r""" @@ -93,8 +82,6 @@ class PegasusTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = PegasusTokenizer model_input_names = ["input_ids", "attention_mask"] diff --git a/src/transformers/models/pegasus_x/configuration_pegasus_x.py b/src/transformers/models/pegasus_x/configuration_pegasus_x.py index be092c018a..fa1f3da6d3 100644 --- a/src/transformers/models/pegasus_x/configuration_pegasus_x.py +++ b/src/transformers/models/pegasus_x/configuration_pegasus_x.py @@ -20,11 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -PEGASUS_X_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/pegasus-x-base": "https://huggingface.co/google/pegasus-x-base/resolve/main/config.json", - "google/pegasus-x-large": "https://huggingface.co/google/pegasus-x-large/resolve/main/config.json", - # See all PEGASUS-X models at https://huggingface.co/models?filter=pegasus-x -} + +from ..deprecated._archive_maps import PEGASUS_X_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class PegasusXConfig(PretrainedConfig): diff --git a/src/transformers/models/pegasus_x/modeling_pegasus_x.py b/src/transformers/models/pegasus_x/modeling_pegasus_x.py index 4953951437..f31ccccbb1 100755 --- a/src/transformers/models/pegasus_x/modeling_pegasus_x.py +++ b/src/transformers/models/pegasus_x/modeling_pegasus_x.py @@ -49,11 +49,7 @@ _CHECKPOINT_FOR_DOC = "google/pegasus-x-base" _CONFIG_FOR_DOC = "PegasusXConfig" -PEGASUS_X_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/pegasus-x-base", - "google/pegasus-x-large", - # See all PEGASUS models at https://huggingface.co/models?filter=pegasus-x -] +from ..deprecated._archive_maps import PEGASUS_X_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclasses.dataclass diff --git a/src/transformers/models/perceiver/configuration_perceiver.py b/src/transformers/models/perceiver/configuration_perceiver.py index d741b287e5..eb9458989c 100644 --- a/src/transformers/models/perceiver/configuration_perceiver.py +++ b/src/transformers/models/perceiver/configuration_perceiver.py @@ -27,10 +27,8 @@ from ...utils import TensorType, logging logger = logging.get_logger(__name__) -PERCEIVER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "deepmind/language-perceiver": "https://huggingface.co/deepmind/language-perceiver/resolve/main/config.json", - # See all Perceiver models at https://huggingface.co/models?filter=perceiver -} + +from ..deprecated._archive_maps import PERCEIVER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class PerceiverConfig(PretrainedConfig): diff --git a/src/transformers/models/perceiver/modeling_perceiver.py b/src/transformers/models/perceiver/modeling_perceiver.py index bb7ac2bc31..5de7635355 100755 --- a/src/transformers/models/perceiver/modeling_perceiver.py +++ b/src/transformers/models/perceiver/modeling_perceiver.py @@ -51,10 +51,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "deepmind/language-perceiver" _CONFIG_FOR_DOC = "PerceiverConfig" -PERCEIVER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "deepmind/language-perceiver", - # See all Perceiver models at https://huggingface.co/models?filter=perceiver -] + +from ..deprecated._archive_maps import PERCEIVER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/persimmon/configuration_persimmon.py b/src/transformers/models/persimmon/configuration_persimmon.py index 6997e159d5..e520d91685 100644 --- a/src/transformers/models/persimmon/configuration_persimmon.py +++ b/src/transformers/models/persimmon/configuration_persimmon.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -PERSIMMON_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "adept/persimmon-8b-base": "https://huggingface.co/adept/persimmon-8b-base/resolve/main/config.json", -} + +from ..deprecated._archive_maps import PERSIMMON_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class PersimmonConfig(PretrainedConfig): diff --git a/src/transformers/models/phi/configuration_phi.py b/src/transformers/models/phi/configuration_phi.py index 1b495cc8e2..456f500b61 100644 --- a/src/transformers/models/phi/configuration_phi.py +++ b/src/transformers/models/phi/configuration_phi.py @@ -22,11 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -PHI_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/phi-1": "https://huggingface.co/microsoft/phi-1/resolve/main/config.json", - "microsoft/phi-1_5": "https://huggingface.co/microsoft/phi-1_5/resolve/main/config.json", - "microsoft/phi-2": "https://huggingface.co/microsoft/phi-2/resolve/main/config.json", -} + +from ..deprecated._archive_maps import PHI_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class PhiConfig(PretrainedConfig): diff --git a/src/transformers/models/phi/modeling_phi.py b/src/transformers/models/phi/modeling_phi.py index c3cb119f0a..13719166ed 100644 --- a/src/transformers/models/phi/modeling_phi.py +++ b/src/transformers/models/phi/modeling_phi.py @@ -62,12 +62,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "microsoft/phi-1" _CONFIG_FOR_DOC = "PhiConfig" -PHI_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/phi-1", - "microsoft/phi-1_5", - "microsoft/phi-2", - # See all Phi models at https://huggingface.co/models?filter=phi -] + +from ..deprecated._archive_maps import PHI_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.llama.modeling_llama._get_unpad_data diff --git a/src/transformers/models/phobert/tokenization_phobert.py b/src/transformers/models/phobert/tokenization_phobert.py index 1275947776..f312f49501 100644 --- a/src/transformers/models/phobert/tokenization_phobert.py +++ b/src/transformers/models/phobert/tokenization_phobert.py @@ -32,22 +32,6 @@ VOCAB_FILES_NAMES = { "merges_file": "bpe.codes", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "vinai/phobert-base": "https://huggingface.co/vinai/phobert-base/resolve/main/vocab.txt", - "vinai/phobert-large": "https://huggingface.co/vinai/phobert-large/resolve/main/vocab.txt", - }, - "merges_file": { - "vinai/phobert-base": "https://huggingface.co/vinai/phobert-base/resolve/main/bpe.codes", - "vinai/phobert-large": "https://huggingface.co/vinai/phobert-large/resolve/main/bpe.codes", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "vinai/phobert-base": 256, - "vinai/phobert-large": 256, -} - def get_pairs(word): """ @@ -115,8 +99,6 @@ class PhobertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/pix2struct/configuration_pix2struct.py b/src/transformers/models/pix2struct/configuration_pix2struct.py index 2449d496f2..12bf998d58 100644 --- a/src/transformers/models/pix2struct/configuration_pix2struct.py +++ b/src/transformers/models/pix2struct/configuration_pix2struct.py @@ -23,11 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -PIX2STRUCT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/pix2struct-textcaps-base": ( - "https://huggingface.co/google/pix2struct-textcaps-base/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import PIX2STRUCT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Pix2StructTextConfig(PretrainedConfig): diff --git a/src/transformers/models/pix2struct/modeling_pix2struct.py b/src/transformers/models/pix2struct/modeling_pix2struct.py index 42f3002ac6..e8032fcef6 100644 --- a/src/transformers/models/pix2struct/modeling_pix2struct.py +++ b/src/transformers/models/pix2struct/modeling_pix2struct.py @@ -49,26 +49,7 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "Pix2StructConfig" -PIX2STRUCT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/pix2struct-textcaps-base", - "google/pix2struct-textcaps-large", - "google/pix2struct-base", - "google/pix2struct-large", - "google/pix2struct-ai2d-base", - "google/pix2struct-ai2d-large", - "google/pix2struct-widget-captioning-base", - "google/pix2struct-widget-captioning-large", - "google/pix2struct-screen2words-base", - "google/pix2struct-screen2words-large", - "google/pix2struct-docvqa-base", - "google/pix2struct-docvqa-large", - "google/pix2struct-ocrvqa-base", - "google/pix2struct-ocrvqa-large", - "google/pix2struct-chartqa-base", - "google/pix2struct-inforgraphics-vqa-base", - "google/pix2struct-inforgraphics-vqa-large", - # See all Pix2StructVision models at https://huggingface.co/models?filter=pix2struct -] +from ..deprecated._archive_maps import PIX2STRUCT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Adapted from transformers.models.t5.modeling_t5.T5LayerNorm with T5->Pix2Struct diff --git a/src/transformers/models/plbart/configuration_plbart.py b/src/transformers/models/plbart/configuration_plbart.py index 836cf5900c..555a2fcc75 100644 --- a/src/transformers/models/plbart/configuration_plbart.py +++ b/src/transformers/models/plbart/configuration_plbart.py @@ -23,10 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -PLBART_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "uclanlp/plbart-base": "https://huggingface.co/uclanlp/plbart-base/resolve/main/config.json", - # See all PLBART models at https://huggingface.co/models?filter=plbart -} + +from ..deprecated._archive_maps import PLBART_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class PLBartConfig(PretrainedConfig): diff --git a/src/transformers/models/plbart/modeling_plbart.py b/src/transformers/models/plbart/modeling_plbart.py index 3c17eceabb..d60b7ee4b0 100644 --- a/src/transformers/models/plbart/modeling_plbart.py +++ b/src/transformers/models/plbart/modeling_plbart.py @@ -54,12 +54,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "uclanlp/plbart-base" _CONFIG_FOR_DOC = "PLBartConfig" -PLBART_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "uclanlp/plbart-base", - "uclanlp/plbart-cs-java", - "uclanlp/plbart-multi_task-all", - # See all PLBART models at https://huggingface.co/models?filter=plbart -] + +from ..deprecated._archive_maps import PLBART_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.mbart.modeling_mbart.shift_tokens_right diff --git a/src/transformers/models/plbart/tokenization_plbart.py b/src/transformers/models/plbart/tokenization_plbart.py index e50849b51d..9ab2e33f7f 100644 --- a/src/transformers/models/plbart/tokenization_plbart.py +++ b/src/transformers/models/plbart/tokenization_plbart.py @@ -29,63 +29,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "uclanlp/plbart-base": "https://huggingface.co/uclanlp/plbart-base/resolve/main/sentencepiece.bpe.model", - "uclanlp/plbart-c-cpp-defect-detection": ( - "https://huggingface.co/uclanlp/plbart-c-cpp-defect-detection/resolve/main/sentencepiece.bpe.model" - ), - "uclanlp/plbart-cs-java": "https://huggingface.co/uclanlp/plbart-cs-java/resolve/main/sentencepiece.bpe.model", - "uclanlp/plbart-en_XX-java": ( - "https://huggingface.co/uclanlp/plbart-en_XX-java/resolve/main/sentencepiece.bpe.model" - ), - "uclanlp/plbart-go-en_XX": ( - "https://huggingface.co/uclanlp/plbart-go-en_XX/resolve/main/sentencepiece.bpe.model" - ), - "uclanlp/plbart-java-clone-detection": ( - "https://huggingface.co/uclanlp/plbart-java-clone-detection/resolve/main/sentencepiece.bpe.model" - ), - "uclanlp/plbart-java-cs": "https://huggingface.co/uclanlp/plbart-java-cs/resolve/main/sentencepiece.bpe.model", - "uclanlp/plbart-java-en_XX": ( - "https://huggingface.co/uclanlp/plbart-java-en_XX/resolve/main/sentencepiece.bpe.model" - ), - "uclanlp/plbart-javascript-en_XX": ( - "https://huggingface.co/uclanlp/plbart-javascript-en_XX/resolve/main/sentencepiece.bpe.model" - ), - "uclanlp/plbart-php-en_XX": ( - "https://huggingface.co/uclanlp/plbart-php-en_XX/resolve/main/sentencepiece.bpe.model" - ), - "uclanlp/plbart-python-en_XX": ( - "https://huggingface.co/uclanlp/plbart-python-en_XX/resolve/main/sentencepiece.bpe.model" - ), - "uclanlp/plbart-refine-java-medium": ( - "https://huggingface.co/uclanlp/plbart-refine-java-medium/resolve/main/sentencepiece.bpe.model" - ), - "uclanlp/plbart-refine-java-small": ( - "https://huggingface.co/uclanlp/plbart-refine-java-small/resolve/main/sentencepiece.bpe.model" - ), - "uclanlp/plbart-ruby-en_XX": ( - "https://huggingface.co/uclanlp/plbart-ruby-en_XX/resolve/main/sentencepiece.bpe.model" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "uclanlp/plbart-base": 1024, - "uclanlp/plbart-c-cpp-defect-detection": 1024, - "uclanlp/plbart-cs-java": 1024, - "uclanlp/plbart-en_XX-java": 1024, - "uclanlp/plbart-go-en_XX": 1024, - "uclanlp/plbart-java-clone-detection": 1024, - "uclanlp/plbart-java-cs": 1024, - "uclanlp/plbart-java-en_XX": 1024, - "uclanlp/plbart-javascript-en_XX": 1024, - "uclanlp/plbart-php-en_XX": 1024, - "uclanlp/plbart-python-en_XX": 1024, - "uclanlp/plbart-refine-java-medium": 1024, - "uclanlp/plbart-refine-java-small": 1024, - "uclanlp/plbart-ruby-en_XX": 1024, -} FAIRSEQ_LANGUAGE_CODES = { "base": ["__java__", "__python__", "__en_XX__"], @@ -166,8 +109,6 @@ class PLBartTokenizer(PreTrainedTokenizer): ```""" vocab_files_names = VOCAB_FILES_NAMES - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP model_input_names = ["input_ids", "attention_mask"] prefix_tokens: List[int] = [] diff --git a/src/transformers/models/poolformer/configuration_poolformer.py b/src/transformers/models/poolformer/configuration_poolformer.py index d859cefc90..be0f18c0a3 100644 --- a/src/transformers/models/poolformer/configuration_poolformer.py +++ b/src/transformers/models/poolformer/configuration_poolformer.py @@ -25,10 +25,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -POOLFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "sail/poolformer_s12": "https://huggingface.co/sail/poolformer_s12/resolve/main/config.json", - # See all PoolFormer models at https://huggingface.co/models?filter=poolformer -} + +from ..deprecated._archive_maps import POOLFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class PoolFormerConfig(PretrainedConfig): diff --git a/src/transformers/models/poolformer/modeling_poolformer.py b/src/transformers/models/poolformer/modeling_poolformer.py index c5a8c7a0d2..80208bd1fc 100755 --- a/src/transformers/models/poolformer/modeling_poolformer.py +++ b/src/transformers/models/poolformer/modeling_poolformer.py @@ -43,10 +43,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 512, 7, 7] _IMAGE_CLASS_CHECKPOINT = "sail/poolformer_s12" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -POOLFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "sail/poolformer_s12", - # See all PoolFormer models at https://huggingface.co/models?filter=poolformer -] + +from ..deprecated._archive_maps import POOLFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.beit.modeling_beit.drop_path diff --git a/src/transformers/models/pop2piano/configuration_pop2piano.py b/src/transformers/models/pop2piano/configuration_pop2piano.py index 15bf1ac438..ff0d4f37b2 100644 --- a/src/transformers/models/pop2piano/configuration_pop2piano.py +++ b/src/transformers/models/pop2piano/configuration_pop2piano.py @@ -21,9 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -POP2PIANO_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "sweetcocoa/pop2piano": "https://huggingface.co/sweetcocoa/pop2piano/blob/main/config.json" -} + +from ..deprecated._archive_maps import POP2PIANO_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Pop2PianoConfig(PretrainedConfig): diff --git a/src/transformers/models/pop2piano/modeling_pop2piano.py b/src/transformers/models/pop2piano/modeling_pop2piano.py index d3638d25b9..e944940689 100644 --- a/src/transformers/models/pop2piano/modeling_pop2piano.py +++ b/src/transformers/models/pop2piano/modeling_pop2piano.py @@ -64,10 +64,8 @@ except Exception: _CONFIG_FOR_DOC = "Pop2PianoConfig" _CHECKPOINT_FOR_DOC = "sweetcocoa/pop2piano" -POP2PIANO_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "sweetcocoa/pop2piano", - # See all Pop2Piano models at https://huggingface.co/models?filter=pop2piano -] + +from ..deprecated._archive_maps import POP2PIANO_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 POP2PIANO_INPUTS_DOCSTRING = r""" diff --git a/src/transformers/models/pop2piano/tokenization_pop2piano.py b/src/transformers/models/pop2piano/tokenization_pop2piano.py index 0d25dcdfc7..3c5844ae7c 100644 --- a/src/transformers/models/pop2piano/tokenization_pop2piano.py +++ b/src/transformers/models/pop2piano/tokenization_pop2piano.py @@ -35,12 +35,6 @@ VOCAB_FILES_NAMES = { "vocab": "vocab.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab": { - "sweetcocoa/pop2piano": "https://huggingface.co/sweetcocoa/pop2piano/blob/main/vocab.json", - }, -} - def token_time_to_note(number, cutoff_time_idx, current_idx): current_idx += number @@ -83,7 +77,6 @@ class Pop2PianoTokenizer(PreTrainedTokenizer): model_input_names = ["token_ids", "attention_mask"] vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP def __init__( self, diff --git a/src/transformers/models/prophetnet/configuration_prophetnet.py b/src/transformers/models/prophetnet/configuration_prophetnet.py index 4072709af9..e07936a14c 100644 --- a/src/transformers/models/prophetnet/configuration_prophetnet.py +++ b/src/transformers/models/prophetnet/configuration_prophetnet.py @@ -22,11 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/prophetnet-large-uncased": ( - "https://huggingface.co/microsoft/prophetnet-large-uncased/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ProphetNetConfig(PretrainedConfig): diff --git a/src/transformers/models/prophetnet/modeling_prophetnet.py b/src/transformers/models/prophetnet/modeling_prophetnet.py index 81eb503ddb..c7d9028cda 100644 --- a/src/transformers/models/prophetnet/modeling_prophetnet.py +++ b/src/transformers/models/prophetnet/modeling_prophetnet.py @@ -43,10 +43,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "ProphenetConfig" _CHECKPOINT_FOR_DOC = "microsoft/prophetnet-large-uncased" -PROPHETNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/prophetnet-large-uncased", - # See all ProphetNet models at https://huggingface.co/models?filter=prophetnet -] + +from ..deprecated._archive_maps import PROPHETNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 PROPHETNET_START_DOCSTRING = r""" diff --git a/src/transformers/models/prophetnet/tokenization_prophetnet.py b/src/transformers/models/prophetnet/tokenization_prophetnet.py index 483188ca55..cd387520af 100644 --- a/src/transformers/models/prophetnet/tokenization_prophetnet.py +++ b/src/transformers/models/prophetnet/tokenization_prophetnet.py @@ -26,22 +26,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "prophetnet.tokenizer"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/prophetnet-large-uncased": ( - "https://huggingface.co/microsoft/prophetnet-large-uncased/resolve/main/prophetnet.tokenizer" - ), - } -} - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/prophetnet-large-uncased": {"do_lower_case": True}, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/prophetnet-large-uncased": 512, -} - # Copied from transformers.models.bert.tokenization_bert.whitespace_tokenize def whitespace_tokenize(text): @@ -327,9 +311,6 @@ class ProphetNetTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES # first name has to correspond to main model input name # to make sure `tokenizer.pad(...)` works correctly diff --git a/src/transformers/models/pvt/configuration_pvt.py b/src/transformers/models/pvt/configuration_pvt.py index ac7d5add7f..7fc99b49cf 100644 --- a/src/transformers/models/pvt/configuration_pvt.py +++ b/src/transformers/models/pvt/configuration_pvt.py @@ -28,10 +28,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -PVT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "pvt-tiny-224": "https://huggingface.co/Zetatech/pvt-tiny-224", - # See all PVT models at https://huggingface.co/models?filter=pvt -} + +from ..deprecated._archive_maps import PVT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class PvtConfig(PretrainedConfig): diff --git a/src/transformers/models/pvt/modeling_pvt.py b/src/transformers/models/pvt/modeling_pvt.py index 58ed0ae68f..b169af0cbd 100755 --- a/src/transformers/models/pvt/modeling_pvt.py +++ b/src/transformers/models/pvt/modeling_pvt.py @@ -49,10 +49,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 50, 512] _IMAGE_CLASS_CHECKPOINT = "Zetatech/pvt-tiny-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -PVT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Zetatech/pvt-tiny-224" - # See all PVT models at https://huggingface.co/models?filter=pvt -] + +from ..deprecated._archive_maps import PVT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.beit.modeling_beit.drop_path diff --git a/src/transformers/models/pvt_v2/__init__.py b/src/transformers/models/pvt_v2/__init__.py index e9297e7908..4825eda165 100644 --- a/src/transformers/models/pvt_v2/__init__.py +++ b/src/transformers/models/pvt_v2/__init__.py @@ -25,7 +25,7 @@ from ...utils import ( _import_structure = { - "configuration_pvt_v2": ["PVT_V2_PRETRAINED_CONFIG_ARCHIVE_MAP", "PvtV2Config"], + "configuration_pvt_v2": ["PvtV2Config"], } try: @@ -35,7 +35,6 @@ except OptionalDependencyNotAvailable: pass else: _import_structure["modeling_pvt_v2"] = [ - "PVT_V2_PRETRAINED_MODEL_ARCHIVE_LIST", "PvtV2ForImageClassification", "PvtV2Model", "PvtV2PreTrainedModel", @@ -44,7 +43,7 @@ else: if TYPE_CHECKING: - from .configuration_pvt_v2 import PVT_V2_PRETRAINED_CONFIG_ARCHIVE_MAP, PvtV2Config + from .configuration_pvt_v2 import PvtV2Config try: if not is_torch_available(): @@ -53,7 +52,6 @@ if TYPE_CHECKING: pass else: from .modeling_pvt_v2 import ( - PVT_V2_PRETRAINED_MODEL_ARCHIVE_LIST, PvtV2Backbone, PvtV2ForImageClassification, PvtV2Model, diff --git a/src/transformers/models/pvt_v2/configuration_pvt_v2.py b/src/transformers/models/pvt_v2/configuration_pvt_v2.py index 1ff3a50232..f6d7de299b 100644 --- a/src/transformers/models/pvt_v2/configuration_pvt_v2.py +++ b/src/transformers/models/pvt_v2/configuration_pvt_v2.py @@ -25,16 +25,6 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -PVT_V2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "pvt_v2_b0": "https://huggingface.co/OpenGVLab/pvt_v2_b0", - "pvt_v2_b1": "https://huggingface.co/OpenGVLab/pvt_v2_b1", - "pvt_v2_b2": "https://huggingface.co/OpenGVLab/pvt_v2_b2", - "pvt_v2_b2_linear": "https://huggingface.co/OpenGVLab/pvt_v2_b2_linear", - "pvt_v2_b3": "https://huggingface.co/OpenGVLab/pvt_v2_b3", - "pvt_v2_b4": "https://huggingface.co/OpenGVLab/pvt_v2_b4", - "pvt_v2_b5": "https://huggingface.co/OpenGVLab/pvt_v2_b5", -} - class PvtV2Config(BackboneConfigMixin, PretrainedConfig): r""" diff --git a/src/transformers/models/pvt_v2/modeling_pvt_v2.py b/src/transformers/models/pvt_v2/modeling_pvt_v2.py index 7df2015c1c..a2e1e7a674 100644 --- a/src/transformers/models/pvt_v2/modeling_pvt_v2.py +++ b/src/transformers/models/pvt_v2/modeling_pvt_v2.py @@ -49,17 +49,6 @@ _EXPECTED_OUTPUT_SHAPE = [1, 256, 7, 7] _IMAGE_CLASS_CHECKPOINT = "OpenGVLab/pvt_v2_b0" _IMAGE_CLASS_EXPECTED_OUTPUT = "LABEL_281" # ImageNet ID for "tabby, tabby cat" -PVT_V2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "OpenGVLab/pvt_v2_b0", - "OpenGVLab/pvt_v2_b1", - "OpenGVLab/pvt_v2_b2", - "OpenGVLab/pvt_v2_b2_linear", - "OpenGVLab/pvt_v2_b3", - "OpenGVLab/pvt_v2_b4", - "OpenGVLab/pvt_v2_b5", - # See all PVT models at https://huggingface.co/models?filter=pvt_v2 -] - # Copied from transformers.models.beit.modeling_beit.drop_path def drop_path(input: torch.Tensor, drop_prob: float = 0.0, training: bool = False) -> torch.Tensor: diff --git a/src/transformers/models/qdqbert/configuration_qdqbert.py b/src/transformers/models/qdqbert/configuration_qdqbert.py index 1efa2ef811..9a48424cc0 100644 --- a/src/transformers/models/qdqbert/configuration_qdqbert.py +++ b/src/transformers/models/qdqbert/configuration_qdqbert.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -QDQBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google-bert/bert-base-uncased": "https://huggingface.co/google-bert/bert-base-uncased/resolve/main/config.json", - # QDQBERT models can be loaded from any BERT checkpoint, available at https://huggingface.co/models?filter=bert -} + +from ..deprecated._archive_maps import QDQBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class QDQBertConfig(PretrainedConfig): diff --git a/src/transformers/models/qdqbert/modeling_qdqbert.py b/src/transformers/models/qdqbert/modeling_qdqbert.py index 8c610ecaed..c5e9af7025 100755 --- a/src/transformers/models/qdqbert/modeling_qdqbert.py +++ b/src/transformers/models/qdqbert/modeling_qdqbert.py @@ -69,10 +69,8 @@ if is_pytorch_quantization_available(): _CHECKPOINT_FOR_DOC = "google-bert/bert-base-uncased" _CONFIG_FOR_DOC = "QDQBertConfig" -QDQBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google-bert/bert-base-uncased", - # See all BERT models at https://huggingface.co/models?filter=bert -] + +from ..deprecated._archive_maps import QDQBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_qdqbert(model, tf_checkpoint_path): diff --git a/src/transformers/models/qwen2/configuration_qwen2.py b/src/transformers/models/qwen2/configuration_qwen2.py index 0bbfd1cf16..2513866d3e 100644 --- a/src/transformers/models/qwen2/configuration_qwen2.py +++ b/src/transformers/models/qwen2/configuration_qwen2.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -QWEN2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "Qwen/Qwen2-7B-beta": "https://huggingface.co/Qwen/Qwen2-7B-beta/resolve/main/config.json", -} + +from ..deprecated._archive_maps import QWEN2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Qwen2Config(PretrainedConfig): diff --git a/src/transformers/models/qwen2/modeling_qwen2.py b/src/transformers/models/qwen2/modeling_qwen2.py index bfba4a4532..7ca32c3768 100644 --- a/src/transformers/models/qwen2/modeling_qwen2.py +++ b/src/transformers/models/qwen2/modeling_qwen2.py @@ -58,11 +58,6 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "Qwen/Qwen2-7B-beta" _CONFIG_FOR_DOC = "Qwen2Config" -QWEN2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Qwen/Qwen2-7B-beta", - # See all Qwen2 models at https://huggingface.co/models?filter=qwen2 -] - # Copied from transformers.models.llama.modeling_llama._get_unpad_data def _get_unpad_data(attention_mask): diff --git a/src/transformers/models/qwen2/tokenization_qwen2.py b/src/transformers/models/qwen2/tokenization_qwen2.py index 9f8607c9ef..22cffcb608 100644 --- a/src/transformers/models/qwen2/tokenization_qwen2.py +++ b/src/transformers/models/qwen2/tokenization_qwen2.py @@ -33,10 +33,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": {"qwen/qwen-tokenizer": "https://huggingface.co/qwen/qwen-tokenizer/resolve/main/vocab.json"}, - "merges_file": {"qwen/qwen-tokenizer": "https://huggingface.co/qwen/qwen-tokenizer/resolve/main/merges.txt"}, -} MAX_MODEL_INPUT_SIZES = {"qwen/qwen-tokenizer": 32768} @@ -136,8 +132,6 @@ class Qwen2Tokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = MAX_MODEL_INPUT_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/qwen2/tokenization_qwen2_fast.py b/src/transformers/models/qwen2/tokenization_qwen2_fast.py index 467aa6d947..82e3073788 100644 --- a/src/transformers/models/qwen2/tokenization_qwen2_fast.py +++ b/src/transformers/models/qwen2/tokenization_qwen2_fast.py @@ -30,13 +30,6 @@ VOCAB_FILES_NAMES = { "tokenizer_file": "tokenizer.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": {"qwen/qwen-tokenizer": "https://huggingface.co/qwen/qwen-tokenizer/resolve/main/vocab.json"}, - "merges_file": {"qwen/qwen-tokenizer": "https://huggingface.co/qwen/qwen-tokenizer/resolve/main/merges.txt"}, - "tokenizer_file": { - "qwen/qwen-tokenizer": "https://huggingface.co/qwen/qwen-tokenizer/resolve/main/tokenizer.json" - }, -} MAX_MODEL_INPUT_SIZES = {"qwen/qwen-tokenizer": 32768} @@ -84,8 +77,6 @@ class Qwen2TokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = MAX_MODEL_INPUT_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = Qwen2Tokenizer diff --git a/src/transformers/models/realm/configuration_realm.py b/src/transformers/models/realm/configuration_realm.py index b7e25c8d15..3725c37922 100644 --- a/src/transformers/models/realm/configuration_realm.py +++ b/src/transformers/models/realm/configuration_realm.py @@ -20,25 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -REALM_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/realm-cc-news-pretrained-embedder": ( - "https://huggingface.co/google/realm-cc-news-pretrained-embedder/resolve/main/config.json" - ), - "google/realm-cc-news-pretrained-encoder": ( - "https://huggingface.co/google/realm-cc-news-pretrained-encoder/resolve/main/config.json" - ), - "google/realm-cc-news-pretrained-scorer": ( - "https://huggingface.co/google/realm-cc-news-pretrained-scorer/resolve/main/config.json" - ), - "google/realm-cc-news-pretrained-openqa": ( - "https://huggingface.co/google/realm-cc-news-pretrained-openqa/aresolve/main/config.json" - ), - "google/realm-orqa-nq-openqa": "https://huggingface.co/google/realm-orqa-nq-openqa/resolve/main/config.json", - "google/realm-orqa-nq-reader": "https://huggingface.co/google/realm-orqa-nq-reader/resolve/main/config.json", - "google/realm-orqa-wq-openqa": "https://huggingface.co/google/realm-orqa-wq-openqa/resolve/main/config.json", - "google/realm-orqa-wq-reader": "https://huggingface.co/google/realm-orqa-wq-reader/resolve/main/config.json", - # See all REALM models at https://huggingface.co/models?filter=realm -} + +from ..deprecated._archive_maps import REALM_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class RealmConfig(PretrainedConfig): diff --git a/src/transformers/models/realm/modeling_realm.py b/src/transformers/models/realm/modeling_realm.py index 1b202ffd09..86f2894289 100644 --- a/src/transformers/models/realm/modeling_realm.py +++ b/src/transformers/models/realm/modeling_realm.py @@ -42,17 +42,8 @@ _ENCODER_CHECKPOINT_FOR_DOC = "google/realm-cc-news-pretrained-encoder" _SCORER_CHECKPOINT_FOR_DOC = "google/realm-cc-news-pretrained-scorer" _CONFIG_FOR_DOC = "RealmConfig" -REALM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/realm-cc-news-pretrained-embedder", - "google/realm-cc-news-pretrained-encoder", - "google/realm-cc-news-pretrained-scorer", - "google/realm-cc-news-pretrained-openqa", - "google/realm-orqa-nq-openqa", - "google/realm-orqa-nq-reader", - "google/realm-orqa-wq-openqa", - "google/realm-orqa-wq-reader", - # See all REALM models at https://huggingface.co/models?filter=realm -] + +from ..deprecated._archive_maps import REALM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_realm(model, config, tf_checkpoint_path): diff --git a/src/transformers/models/realm/tokenization_realm.py b/src/transformers/models/realm/tokenization_realm.py index bf6b632774..c4ff7e38a3 100644 --- a/src/transformers/models/realm/tokenization_realm.py +++ b/src/transformers/models/realm/tokenization_realm.py @@ -28,49 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/realm-cc-news-pretrained-embedder": ( - "https://huggingface.co/google/realm-cc-news-pretrained-embedder/resolve/main/vocab.txt" - ), - "google/realm-cc-news-pretrained-encoder": ( - "https://huggingface.co/google/realm-cc-news-pretrained-encoder/resolve/main/vocab.txt" - ), - "google/realm-cc-news-pretrained-scorer": ( - "https://huggingface.co/google/realm-cc-news-pretrained-scorer/resolve/main/vocab.txt" - ), - "google/realm-cc-news-pretrained-openqa": ( - "https://huggingface.co/google/realm-cc-news-pretrained-openqa/aresolve/main/vocab.txt" - ), - "google/realm-orqa-nq-openqa": "https://huggingface.co/google/realm-orqa-nq-openqa/resolve/main/vocab.txt", - "google/realm-orqa-nq-reader": "https://huggingface.co/google/realm-orqa-nq-reader/resolve/main/vocab.txt", - "google/realm-orqa-wq-openqa": "https://huggingface.co/google/realm-orqa-wq-openqa/resolve/main/vocab.txt", - "google/realm-orqa-wq-reader": "https://huggingface.co/google/realm-orqa-wq-reader/resolve/main/vocab.txt", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/realm-cc-news-pretrained-embedder": 512, - "google/realm-cc-news-pretrained-encoder": 512, - "google/realm-cc-news-pretrained-scorer": 512, - "google/realm-cc-news-pretrained-openqa": 512, - "google/realm-orqa-nq-openqa": 512, - "google/realm-orqa-nq-reader": 512, - "google/realm-orqa-wq-openqa": 512, - "google/realm-orqa-wq-reader": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "google/realm-cc-news-pretrained-embedder": {"do_lower_case": True}, - "google/realm-cc-news-pretrained-encoder": {"do_lower_case": True}, - "google/realm-cc-news-pretrained-scorer": {"do_lower_case": True}, - "google/realm-cc-news-pretrained-openqa": {"do_lower_case": True}, - "google/realm-orqa-nq-openqa": {"do_lower_case": True}, - "google/realm-orqa-nq-reader": {"do_lower_case": True}, - "google/realm-orqa-wq-openqa": {"do_lower_case": True}, - "google/realm-orqa-wq-reader": {"do_lower_case": True}, -} - def load_vocab(vocab_file): """Loads a vocabulary file into a dictionary.""" @@ -138,9 +95,6 @@ class RealmTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/realm/tokenization_realm_fast.py b/src/transformers/models/realm/tokenization_realm_fast.py index 59b23f45ee..7315bf1c25 100644 --- a/src/transformers/models/realm/tokenization_realm_fast.py +++ b/src/transformers/models/realm/tokenization_realm_fast.py @@ -29,75 +29,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/realm-cc-news-pretrained-embedder": ( - "https://huggingface.co/google/realm-cc-news-pretrained-embedder/resolve/main/vocab.txt" - ), - "google/realm-cc-news-pretrained-encoder": ( - "https://huggingface.co/google/realm-cc-news-pretrained-encoder/resolve/main/vocab.txt" - ), - "google/realm-cc-news-pretrained-scorer": ( - "https://huggingface.co/google/realm-cc-news-pretrained-scorer/resolve/main/vocab.txt" - ), - "google/realm-cc-news-pretrained-openqa": ( - "https://huggingface.co/google/realm-cc-news-pretrained-openqa/aresolve/main/vocab.txt" - ), - "google/realm-orqa-nq-openqa": "https://huggingface.co/google/realm-orqa-nq-openqa/resolve/main/vocab.txt", - "google/realm-orqa-nq-reader": "https://huggingface.co/google/realm-orqa-nq-reader/resolve/main/vocab.txt", - "google/realm-orqa-wq-openqa": "https://huggingface.co/google/realm-orqa-wq-openqa/resolve/main/vocab.txt", - "google/realm-orqa-wq-reader": "https://huggingface.co/google/realm-orqa-wq-reader/resolve/main/vocab.txt", - }, - "tokenizer_file": { - "google/realm-cc-news-pretrained-embedder": ( - "https://huggingface.co/google/realm-cc-news-pretrained-embedder/resolve/main/tokenizer.jsont" - ), - "google/realm-cc-news-pretrained-encoder": ( - "https://huggingface.co/google/realm-cc-news-pretrained-encoder/resolve/main/tokenizer.json" - ), - "google/realm-cc-news-pretrained-scorer": ( - "https://huggingface.co/google/realm-cc-news-pretrained-scorer/resolve/main/tokenizer.json" - ), - "google/realm-cc-news-pretrained-openqa": ( - "https://huggingface.co/google/realm-cc-news-pretrained-openqa/aresolve/main/tokenizer.json" - ), - "google/realm-orqa-nq-openqa": ( - "https://huggingface.co/google/realm-orqa-nq-openqa/resolve/main/tokenizer.json" - ), - "google/realm-orqa-nq-reader": ( - "https://huggingface.co/google/realm-orqa-nq-reader/resolve/main/tokenizer.json" - ), - "google/realm-orqa-wq-openqa": ( - "https://huggingface.co/google/realm-orqa-wq-openqa/resolve/main/tokenizer.json" - ), - "google/realm-orqa-wq-reader": ( - "https://huggingface.co/google/realm-orqa-wq-reader/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/realm-cc-news-pretrained-embedder": 512, - "google/realm-cc-news-pretrained-encoder": 512, - "google/realm-cc-news-pretrained-scorer": 512, - "google/realm-cc-news-pretrained-openqa": 512, - "google/realm-orqa-nq-openqa": 512, - "google/realm-orqa-nq-reader": 512, - "google/realm-orqa-wq-openqa": 512, - "google/realm-orqa-wq-reader": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "google/realm-cc-news-pretrained-embedder": {"do_lower_case": True}, - "google/realm-cc-news-pretrained-encoder": {"do_lower_case": True}, - "google/realm-cc-news-pretrained-scorer": {"do_lower_case": True}, - "google/realm-cc-news-pretrained-openqa": {"do_lower_case": True}, - "google/realm-orqa-nq-openqa": {"do_lower_case": True}, - "google/realm-orqa-nq-reader": {"do_lower_case": True}, - "google/realm-orqa-wq-openqa": {"do_lower_case": True}, - "google/realm-orqa-wq-reader": {"do_lower_case": True}, -} - class RealmTokenizerFast(PreTrainedTokenizerFast): r""" @@ -143,9 +74,6 @@ class RealmTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = RealmTokenizer def __init__( diff --git a/src/transformers/models/reformer/configuration_reformer.py b/src/transformers/models/reformer/configuration_reformer.py index e01f25a5fb..35e8628ce0 100755 --- a/src/transformers/models/reformer/configuration_reformer.py +++ b/src/transformers/models/reformer/configuration_reformer.py @@ -21,12 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -REFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/reformer-crime-and-punishment": ( - "https://huggingface.co/google/reformer-crime-and-punishment/resolve/main/config.json" - ), - "google/reformer-enwik8": "https://huggingface.co/google/reformer-enwik8/resolve/main/config.json", -} + +from ..deprecated._archive_maps import REFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ReformerConfig(PretrainedConfig): diff --git a/src/transformers/models/reformer/modeling_reformer.py b/src/transformers/models/reformer/modeling_reformer.py index 7096a57d0f..e6768e897e 100755 --- a/src/transformers/models/reformer/modeling_reformer.py +++ b/src/transformers/models/reformer/modeling_reformer.py @@ -50,11 +50,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "google/reformer-crime-and-punishment" _CONFIG_FOR_DOC = "ReformerConfig" -REFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/reformer-crime-and-punishment", - "google/reformer-enwik8", - # See all Reformer models at https://huggingface.co/models?filter=reformer -] + +from ..deprecated._archive_maps import REFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Define named tuples for nn.Modules here diff --git a/src/transformers/models/reformer/tokenization_reformer.py b/src/transformers/models/reformer/tokenization_reformer.py index 364a2d42ed..efc692185b 100644 --- a/src/transformers/models/reformer/tokenization_reformer.py +++ b/src/transformers/models/reformer/tokenization_reformer.py @@ -32,18 +32,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/reformer-crime-and-punishment": ( - "https://huggingface.co/google/reformer-crime-and-punishment/resolve/main/spiece.model" - ) - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/reformer-crime-and-punishment": 524288, -} - class ReformerTokenizer(PreTrainedTokenizer): """ @@ -89,8 +77,6 @@ class ReformerTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/reformer/tokenization_reformer_fast.py b/src/transformers/models/reformer/tokenization_reformer_fast.py index eb8c86b3cd..fb0f2c8b8e 100644 --- a/src/transformers/models/reformer/tokenization_reformer_fast.py +++ b/src/transformers/models/reformer/tokenization_reformer_fast.py @@ -36,23 +36,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "spiece.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/reformer-crime-and-punishment": ( - "https://huggingface.co/google/reformer-crime-and-punishment/resolve/main/spiece.model" - ) - }, - "tokenizer_file": { - "google/reformer-crime-and-punishment": ( - "https://huggingface.co/google/reformer-crime-and-punishment/resolve/main/tokenizer.json" - ) - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/reformer-crime-and-punishment": 524288, -} - class ReformerTokenizerFast(PreTrainedTokenizerFast): """ @@ -86,8 +69,6 @@ class ReformerTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = ReformerTokenizer diff --git a/src/transformers/models/regnet/configuration_regnet.py b/src/transformers/models/regnet/configuration_regnet.py index 4969e426bc..629ac73391 100644 --- a/src/transformers/models/regnet/configuration_regnet.py +++ b/src/transformers/models/regnet/configuration_regnet.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -REGNET_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/regnet-y-040": "https://huggingface.co/facebook/regnet-y-040/blob/main/config.json", -} + +from ..deprecated._archive_maps import REGNET_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class RegNetConfig(PretrainedConfig): diff --git a/src/transformers/models/regnet/modeling_regnet.py b/src/transformers/models/regnet/modeling_regnet.py index 2295fbeeab..915e4cbae4 100644 --- a/src/transformers/models/regnet/modeling_regnet.py +++ b/src/transformers/models/regnet/modeling_regnet.py @@ -46,10 +46,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 1088, 7, 7] _IMAGE_CLASS_CHECKPOINT = "facebook/regnet-y-040" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -REGNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/regnet-y-040", - # See all regnet models at https://huggingface.co/models?filter=regnet -] + +from ..deprecated._archive_maps import REGNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class RegNetConvLayer(nn.Module): diff --git a/src/transformers/models/regnet/modeling_tf_regnet.py b/src/transformers/models/regnet/modeling_tf_regnet.py index bca515fbf3..a8c296027f 100644 --- a/src/transformers/models/regnet/modeling_tf_regnet.py +++ b/src/transformers/models/regnet/modeling_tf_regnet.py @@ -50,10 +50,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 1088, 7, 7] _IMAGE_CLASS_CHECKPOINT = "facebook/regnet-y-040" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -TF_REGNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/regnet-y-040", - # See all regnet models at https://huggingface.co/models?filter=regnet -] + +from ..deprecated._archive_maps import TF_REGNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFRegNetConvLayer(keras.layers.Layer): diff --git a/src/transformers/models/rembert/configuration_rembert.py b/src/transformers/models/rembert/configuration_rembert.py index 0b5833c1c7..fa51a79f60 100644 --- a/src/transformers/models/rembert/configuration_rembert.py +++ b/src/transformers/models/rembert/configuration_rembert.py @@ -23,10 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -REMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/rembert": "https://huggingface.co/google/rembert/resolve/main/config.json", - # See all RemBERT models at https://huggingface.co/models?filter=rembert -} + +from ..deprecated._archive_maps import REMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class RemBertConfig(PretrainedConfig): diff --git a/src/transformers/models/rembert/modeling_rembert.py b/src/transformers/models/rembert/modeling_rembert.py index b53464cdec..9c04ed10b8 100755 --- a/src/transformers/models/rembert/modeling_rembert.py +++ b/src/transformers/models/rembert/modeling_rembert.py @@ -52,10 +52,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "RemBertConfig" _CHECKPOINT_FOR_DOC = "google/rembert" -REMBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/rembert", - # See all RemBERT models at https://huggingface.co/models?filter=rembert -] + +from ..deprecated._archive_maps import REMBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def load_tf_weights_in_rembert(model, config, tf_checkpoint_path): diff --git a/src/transformers/models/rembert/modeling_tf_rembert.py b/src/transformers/models/rembert/modeling_tf_rembert.py index 58b13bc35b..94667c2537 100644 --- a/src/transformers/models/rembert/modeling_tf_rembert.py +++ b/src/transformers/models/rembert/modeling_tf_rembert.py @@ -62,10 +62,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "RemBertConfig" -TF_REMBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/rembert", - # See all RemBERT models at https://huggingface.co/models?filter=rembert -] + +from ..deprecated._archive_maps import TF_REMBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFRemBertEmbeddings(keras.layers.Layer): diff --git a/src/transformers/models/rembert/tokenization_rembert.py b/src/transformers/models/rembert/tokenization_rembert.py index 9403e91176..a2b1f9abc2 100644 --- a/src/transformers/models/rembert/tokenization_rembert.py +++ b/src/transformers/models/rembert/tokenization_rembert.py @@ -29,16 +29,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/rembert": "https://huggingface.co/google/rembert/resolve/main/sentencepiece.model", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/rembert": 256, -} - class RemBertTokenizer(PreTrainedTokenizer): """ @@ -93,8 +83,6 @@ class RemBertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/rembert/tokenization_rembert_fast.py b/src/transformers/models/rembert/tokenization_rembert_fast.py index 947cc4bc96..b7165e362a 100644 --- a/src/transformers/models/rembert/tokenization_rembert_fast.py +++ b/src/transformers/models/rembert/tokenization_rembert_fast.py @@ -32,18 +32,6 @@ else: logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/rembert": "https://huggingface.co/google/rembert/resolve/main/sentencepiece.model", - }, - "tokenizer_file": { - "google/rembert": "https://huggingface.co/google/rembert/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/rembert": 256, -} SPIECE_UNDERLINE = "▁" @@ -96,8 +84,6 @@ class RemBertTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = RemBertTokenizer def __init__( diff --git a/src/transformers/models/resnet/configuration_resnet.py b/src/transformers/models/resnet/configuration_resnet.py index 250589c1de..8e1938cb9c 100644 --- a/src/transformers/models/resnet/configuration_resnet.py +++ b/src/transformers/models/resnet/configuration_resnet.py @@ -27,9 +27,8 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -RESNET_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/resnet-50": "https://huggingface.co/microsoft/resnet-50/blob/main/config.json", -} + +from ..deprecated._archive_maps import RESNET_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ResNetConfig(BackboneConfigMixin, PretrainedConfig): diff --git a/src/transformers/models/resnet/modeling_resnet.py b/src/transformers/models/resnet/modeling_resnet.py index df460d58f0..ab2ff4814e 100644 --- a/src/transformers/models/resnet/modeling_resnet.py +++ b/src/transformers/models/resnet/modeling_resnet.py @@ -53,10 +53,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 2048, 7, 7] _IMAGE_CLASS_CHECKPOINT = "microsoft/resnet-50" _IMAGE_CLASS_EXPECTED_OUTPUT = "tiger cat" -RESNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/resnet-50", - # See all resnet models at https://huggingface.co/models?filter=resnet -] + +from ..deprecated._archive_maps import RESNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class ResNetConvLayer(nn.Module): diff --git a/src/transformers/models/resnet/modeling_tf_resnet.py b/src/transformers/models/resnet/modeling_tf_resnet.py index faf5c635ba..98e9a32d29 100644 --- a/src/transformers/models/resnet/modeling_tf_resnet.py +++ b/src/transformers/models/resnet/modeling_tf_resnet.py @@ -49,10 +49,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 2048, 7, 7] _IMAGE_CLASS_CHECKPOINT = "microsoft/resnet-50" _IMAGE_CLASS_EXPECTED_OUTPUT = "tiger cat" -TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/resnet-50", - # See all resnet models at https://huggingface.co/models?filter=resnet -] + +from ..deprecated._archive_maps import TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFResNetConvLayer(keras.layers.Layer): diff --git a/src/transformers/models/roberta/configuration_roberta.py b/src/transformers/models/roberta/configuration_roberta.py index 8cc35d6090..aa549556d9 100644 --- a/src/transformers/models/roberta/configuration_roberta.py +++ b/src/transformers/models/roberta/configuration_roberta.py @@ -24,14 +24,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "FacebookAI/roberta-base": "https://huggingface.co/FacebookAI/roberta-base/resolve/main/config.json", - "FacebookAI/roberta-large": "https://huggingface.co/FacebookAI/roberta-large/resolve/main/config.json", - "FacebookAI/roberta-large-mnli": "https://huggingface.co/FacebookAI/roberta-large-mnli/resolve/main/config.json", - "distilbert/distilroberta-base": "https://huggingface.co/distilbert/distilroberta-base/resolve/main/config.json", - "openai-community/roberta-base-openai-detector": "https://huggingface.co/openai-community/roberta-base-openai-detector/resolve/main/config.json", - "openai-community/roberta-large-openai-detector": "https://huggingface.co/openai-community/roberta-large-openai-detector/resolve/main/config.json", -} + +from ..deprecated._archive_maps import ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class RobertaConfig(PretrainedConfig): diff --git a/src/transformers/models/roberta/modeling_roberta.py b/src/transformers/models/roberta/modeling_roberta.py index f755bd9d56..e1f15722e4 100644 --- a/src/transformers/models/roberta/modeling_roberta.py +++ b/src/transformers/models/roberta/modeling_roberta.py @@ -51,15 +51,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "FacebookAI/roberta-base" _CONFIG_FOR_DOC = "RobertaConfig" -ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "FacebookAI/roberta-base", - "FacebookAI/roberta-large", - "FacebookAI/roberta-large-mnli", - "distilbert/distilroberta-base", - "openai-community/roberta-base-openai-detector", - "openai-community/roberta-large-openai-detector", - # See all RoBERTa models at https://huggingface.co/models?filter=roberta -] + +from ..deprecated._archive_maps import ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class RobertaEmbeddings(nn.Module): diff --git a/src/transformers/models/roberta/modeling_tf_roberta.py b/src/transformers/models/roberta/modeling_tf_roberta.py index 0bc5e85e80..f48bb796c1 100644 --- a/src/transformers/models/roberta/modeling_tf_roberta.py +++ b/src/transformers/models/roberta/modeling_tf_roberta.py @@ -65,13 +65,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "FacebookAI/roberta-base" _CONFIG_FOR_DOC = "RobertaConfig" -TF_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "FacebookAI/roberta-base", - "FacebookAI/roberta-large", - "FacebookAI/roberta-large-mnli", - "distilbert/distilroberta-base", - # See all RoBERTa models at https://huggingface.co/models?filter=roberta -] + +from ..deprecated._archive_maps import TF_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFRobertaEmbeddings(keras.layers.Layer): diff --git a/src/transformers/models/roberta/tokenization_roberta.py b/src/transformers/models/roberta/tokenization_roberta.py index c7dc51b972..072c44ac4d 100644 --- a/src/transformers/models/roberta/tokenization_roberta.py +++ b/src/transformers/models/roberta/tokenization_roberta.py @@ -32,38 +32,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "FacebookAI/roberta-base": "https://huggingface.co/FacebookAI/roberta-base/resolve/main/vocab.json", - "FacebookAI/roberta-large": "https://huggingface.co/FacebookAI/roberta-large/resolve/main/vocab.json", - "FacebookAI/roberta-large-mnli": "https://huggingface.co/FacebookAI/roberta-large-mnli/resolve/main/vocab.json", - "distilbert/distilroberta-base": "https://huggingface.co/distilbert/distilroberta-base/resolve/main/vocab.json", - "openai-community/roberta-base-openai-detector": "https://huggingface.co/openai-community/roberta-base-openai-detector/resolve/main/vocab.json", - "openai-community/roberta-large-openai-detector": ( - "https://huggingface.co/openai-community/roberta-large-openai-detector/resolve/main/vocab.json" - ), - }, - "merges_file": { - "FacebookAI/roberta-base": "https://huggingface.co/FacebookAI/roberta-base/resolve/main/merges.txt", - "FacebookAI/roberta-large": "https://huggingface.co/FacebookAI/roberta-large/resolve/main/merges.txt", - "FacebookAI/roberta-large-mnli": "https://huggingface.co/FacebookAI/roberta-large-mnli/resolve/main/merges.txt", - "distilbert/distilroberta-base": "https://huggingface.co/distilbert/distilroberta-base/resolve/main/merges.txt", - "openai-community/roberta-base-openai-detector": "https://huggingface.co/openai-community/roberta-base-openai-detector/resolve/main/merges.txt", - "openai-community/roberta-large-openai-detector": ( - "https://huggingface.co/openai-community/roberta-large-openai-detector/resolve/main/merges.txt" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "FacebookAI/roberta-base": 512, - "FacebookAI/roberta-large": 512, - "FacebookAI/roberta-large-mnli": 512, - "distilbert/distilroberta-base": 512, - "openai-community/roberta-base-openai-detector": 512, - "openai-community/roberta-large-openai-detector": 512, -} - @lru_cache() def bytes_to_unicode(): @@ -183,8 +151,6 @@ class RobertaTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/roberta/tokenization_roberta_fast.py b/src/transformers/models/roberta/tokenization_roberta_fast.py index 00341e870f..702af8a33e 100644 --- a/src/transformers/models/roberta/tokenization_roberta_fast.py +++ b/src/transformers/models/roberta/tokenization_roberta_fast.py @@ -28,50 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "FacebookAI/roberta-base": "https://huggingface.co/FacebookAI/roberta-base/resolve/main/vocab.json", - "FacebookAI/roberta-large": "https://huggingface.co/FacebookAI/roberta-large/resolve/main/vocab.json", - "FacebookAI/roberta-large-mnli": "https://huggingface.co/FacebookAI/roberta-large-mnli/resolve/main/vocab.json", - "distilbert/distilroberta-base": "https://huggingface.co/distilbert/distilroberta-base/resolve/main/vocab.json", - "openai-community/roberta-base-openai-detector": "https://huggingface.co/openai-community/roberta-base-openai-detector/resolve/main/vocab.json", - "openai-community/roberta-large-openai-detector": ( - "https://huggingface.co/openai-community/roberta-large-openai-detector/resolve/main/vocab.json" - ), - }, - "merges_file": { - "FacebookAI/roberta-base": "https://huggingface.co/FacebookAI/roberta-base/resolve/main/merges.txt", - "FacebookAI/roberta-large": "https://huggingface.co/FacebookAI/roberta-large/resolve/main/merges.txt", - "FacebookAI/roberta-large-mnli": "https://huggingface.co/FacebookAI/roberta-large-mnli/resolve/main/merges.txt", - "distilbert/distilroberta-base": "https://huggingface.co/distilbert/distilroberta-base/resolve/main/merges.txt", - "openai-community/roberta-base-openai-detector": "https://huggingface.co/openai-community/roberta-base-openai-detector/resolve/main/merges.txt", - "openai-community/roberta-large-openai-detector": ( - "https://huggingface.co/openai-community/roberta-large-openai-detector/resolve/main/merges.txt" - ), - }, - "tokenizer_file": { - "FacebookAI/roberta-base": "https://huggingface.co/FacebookAI/roberta-base/resolve/main/tokenizer.json", - "FacebookAI/roberta-large": "https://huggingface.co/FacebookAI/roberta-large/resolve/main/tokenizer.json", - "FacebookAI/roberta-large-mnli": "https://huggingface.co/FacebookAI/roberta-large-mnli/resolve/main/tokenizer.json", - "distilbert/distilroberta-base": "https://huggingface.co/distilbert/distilroberta-base/resolve/main/tokenizer.json", - "openai-community/roberta-base-openai-detector": ( - "https://huggingface.co/openai-community/roberta-base-openai-detector/resolve/main/tokenizer.json" - ), - "openai-community/roberta-large-openai-detector": ( - "https://huggingface.co/openai-community/roberta-large-openai-detector/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "FacebookAI/roberta-base": 512, - "FacebookAI/roberta-large": 512, - "FacebookAI/roberta-large-mnli": 512, - "distilbert/distilroberta-base": 512, - "openai-community/roberta-base-openai-detector": 512, - "openai-community/roberta-large-openai-detector": 512, -} - class RobertaTokenizerFast(PreTrainedTokenizerFast): """ @@ -155,8 +111,6 @@ class RobertaTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = RobertaTokenizer diff --git a/src/transformers/models/roberta_prelayernorm/configuration_roberta_prelayernorm.py b/src/transformers/models/roberta_prelayernorm/configuration_roberta_prelayernorm.py index f932513816..379a71abf1 100644 --- a/src/transformers/models/roberta_prelayernorm/configuration_roberta_prelayernorm.py +++ b/src/transformers/models/roberta_prelayernorm/configuration_roberta_prelayernorm.py @@ -24,11 +24,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -ROBERTA_PRELAYERNORM_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "andreasmadsen/efficient_mlm_m0.40": ( - "https://huggingface.co/andreasmadsen/efficient_mlm_m0.40/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import ROBERTA_PRELAYERNORM_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 # Copied from transformers.models.roberta.configuration_roberta.RobertaConfig with FacebookAI/roberta-base->andreasmadsen/efficient_mlm_m0.40,RoBERTa->RoBERTa-PreLayerNorm,Roberta->RobertaPreLayerNorm,roberta->roberta-prelayernorm diff --git a/src/transformers/models/roberta_prelayernorm/modeling_roberta_prelayernorm.py b/src/transformers/models/roberta_prelayernorm/modeling_roberta_prelayernorm.py index 7c37950e47..468cb1a243 100644 --- a/src/transformers/models/roberta_prelayernorm/modeling_roberta_prelayernorm.py +++ b/src/transformers/models/roberta_prelayernorm/modeling_roberta_prelayernorm.py @@ -51,17 +51,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "andreasmadsen/efficient_mlm_m0.40" _CONFIG_FOR_DOC = "RobertaPreLayerNormConfig" -ROBERTA_PRELAYERNORM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "andreasmadsen/efficient_mlm_m0.15", - "andreasmadsen/efficient_mlm_m0.20", - "andreasmadsen/efficient_mlm_m0.30", - "andreasmadsen/efficient_mlm_m0.40", - "andreasmadsen/efficient_mlm_m0.50", - "andreasmadsen/efficient_mlm_m0.60", - "andreasmadsen/efficient_mlm_m0.70", - "andreasmadsen/efficient_mlm_m0.80", - # See all RoBERTaWithPreLayerNorm models at https://huggingface.co/models?filter=roberta_with_prelayernorm -] + +from ..deprecated._archive_maps import ROBERTA_PRELAYERNORM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.roberta.modeling_roberta.RobertaEmbeddings with Roberta->RobertaPreLayerNorm diff --git a/src/transformers/models/roberta_prelayernorm/modeling_tf_roberta_prelayernorm.py b/src/transformers/models/roberta_prelayernorm/modeling_tf_roberta_prelayernorm.py index 6d111deaab..b3a0070788 100644 --- a/src/transformers/models/roberta_prelayernorm/modeling_tf_roberta_prelayernorm.py +++ b/src/transformers/models/roberta_prelayernorm/modeling_tf_roberta_prelayernorm.py @@ -65,17 +65,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "andreasmadsen/efficient_mlm_m0.40" _CONFIG_FOR_DOC = "RobertaPreLayerNormConfig" -TF_ROBERTA_PRELAYERNORM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "andreasmadsen/efficient_mlm_m0.15", - "andreasmadsen/efficient_mlm_m0.20", - "andreasmadsen/efficient_mlm_m0.30", - "andreasmadsen/efficient_mlm_m0.40", - "andreasmadsen/efficient_mlm_m0.50", - "andreasmadsen/efficient_mlm_m0.60", - "andreasmadsen/efficient_mlm_m0.70", - "andreasmadsen/efficient_mlm_m0.80", - # See all RoBERTaWithPreLayerNorm models at https://huggingface.co/models?filter=roberta_with_prelayernorm -] + +from ..deprecated._archive_maps import TF_ROBERTA_PRELAYERNORM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.roberta.modeling_tf_roberta.TFRobertaEmbeddings with Roberta->RobertaPreLayerNorm diff --git a/src/transformers/models/roc_bert/configuration_roc_bert.py b/src/transformers/models/roc_bert/configuration_roc_bert.py index 6a8dfd9e83..26f74ee4c4 100644 --- a/src/transformers/models/roc_bert/configuration_roc_bert.py +++ b/src/transformers/models/roc_bert/configuration_roc_bert.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -ROC_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "weiweishi/roc-bert-base-zh": "https://huggingface.co/weiweishi/roc-bert-base-zh/resolve/main/config.json", -} + +from ..deprecated._archive_maps import ROC_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class RoCBertConfig(PretrainedConfig): diff --git a/src/transformers/models/roc_bert/modeling_roc_bert.py b/src/transformers/models/roc_bert/modeling_roc_bert.py index f3de92fed3..51850c9af1 100644 --- a/src/transformers/models/roc_bert/modeling_roc_bert.py +++ b/src/transformers/models/roc_bert/modeling_roc_bert.py @@ -72,10 +72,8 @@ _QA_TARGET_START_INDEX = 14 _QA_TARGET_END_INDEX = 15 # Maske language modeling -ROC_BERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "weiweishi/roc-bert-base-zh", - # See all RoCBert models at https://huggingface.co/models?filter=roc_bert -] + +from ..deprecated._archive_maps import ROC_BERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.bert.modeling_bert.load_tf_weights_in_bert with bert->roc_bert diff --git a/src/transformers/models/roc_bert/tokenization_roc_bert.py b/src/transformers/models/roc_bert/tokenization_roc_bert.py index 0bbdc04e53..85e1cd1d32 100644 --- a/src/transformers/models/roc_bert/tokenization_roc_bert.py +++ b/src/transformers/models/roc_bert/tokenization_roc_bert.py @@ -47,28 +47,6 @@ VOCAB_FILES_NAMES = { "word_pronunciation_file": "word_pronunciation.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "weiweishi/roc-bert-base-zh": "https://huggingface.co/weiweishi/roc-bert-base-zh/resolve/main/vocab.txt" - }, - "word_shape_file": { - "weiweishi/roc-bert-base-zh": "https://huggingface.co/weiweishi/roc-bert-base-zh/resolve/main/word_shape.json" - }, - "word_pronunciation_file": { - "weiweishi/roc-bert-base-zh": ( - "https://huggingface.co/weiweishi/roc-bert-base-zh/resolve/main/word_pronunciation.json" - ) - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "weiweishi/roc-bert-base-zh": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "weiweishi/roc-bert-base-zh": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert.load_vocab def load_vocab(vocab_file): @@ -135,9 +113,6 @@ class RoCBertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/roformer/configuration_roformer.py b/src/transformers/models/roformer/configuration_roformer.py index 89875db770..adde64345d 100644 --- a/src/transformers/models/roformer/configuration_roformer.py +++ b/src/transformers/models/roformer/configuration_roformer.py @@ -24,23 +24,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -ROFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "junnyu/roformer_chinese_small": "https://huggingface.co/junnyu/roformer_chinese_small/resolve/main/config.json", - "junnyu/roformer_chinese_base": "https://huggingface.co/junnyu/roformer_chinese_base/resolve/main/config.json", - "junnyu/roformer_chinese_char_small": ( - "https://huggingface.co/junnyu/roformer_chinese_char_small/resolve/main/config.json" - ), - "junnyu/roformer_chinese_char_base": ( - "https://huggingface.co/junnyu/roformer_chinese_char_base/resolve/main/config.json" - ), - "junnyu/roformer_small_discriminator": ( - "https://huggingface.co/junnyu/roformer_small_discriminator/resolve/main/config.json" - ), - "junnyu/roformer_small_generator": ( - "https://huggingface.co/junnyu/roformer_small_generator/resolve/main/config.json" - ), - # See all RoFormer models at https://huggingface.co/models?filter=roformer -} + +from ..deprecated._archive_maps import ROFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class RoFormerConfig(PretrainedConfig): diff --git a/src/transformers/models/roformer/modeling_flax_roformer.py b/src/transformers/models/roformer/modeling_flax_roformer.py index 10a9bdece6..6e154b311d 100644 --- a/src/transformers/models/roformer/modeling_flax_roformer.py +++ b/src/transformers/models/roformer/modeling_flax_roformer.py @@ -43,16 +43,6 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "junnyu/roformer_chinese_base" _CONFIG_FOR_DOC = "RoFormerConfig" -FLAX_ROFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "junnyu/roformer_chinese_small", - "junnyu/roformer_chinese_base", - "junnyu/roformer_chinese_char_small", - "junnyu/roformer_chinese_char_base", - "junnyu/roformer_small_discriminator", - "junnyu/roformer_small_generator", - # See all RoFormer models at https://huggingface.co/models?filter=roformer -] - ROFORMER_START_DOCSTRING = r""" diff --git a/src/transformers/models/roformer/modeling_roformer.py b/src/transformers/models/roformer/modeling_roformer.py index 7aa9a0b12d..b2a63221a8 100644 --- a/src/transformers/models/roformer/modeling_roformer.py +++ b/src/transformers/models/roformer/modeling_roformer.py @@ -52,15 +52,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "junnyu/roformer_chinese_base" _CONFIG_FOR_DOC = "RoFormerConfig" -ROFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "junnyu/roformer_chinese_small", - "junnyu/roformer_chinese_base", - "junnyu/roformer_chinese_char_small", - "junnyu/roformer_chinese_char_base", - "junnyu/roformer_small_discriminator", - "junnyu/roformer_small_generator", - # See all RoFormer models at https://huggingface.co/models?filter=roformer -] + +from ..deprecated._archive_maps import ROFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.marian.modeling_marian.MarianSinusoidalPositionalEmbedding with Marian->RoFormer diff --git a/src/transformers/models/roformer/modeling_tf_roformer.py b/src/transformers/models/roformer/modeling_tf_roformer.py index eb52a09934..3c1ba63ce1 100644 --- a/src/transformers/models/roformer/modeling_tf_roformer.py +++ b/src/transformers/models/roformer/modeling_tf_roformer.py @@ -64,15 +64,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "junnyu/roformer_chinese_base" _CONFIG_FOR_DOC = "RoFormerConfig" -TF_ROFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "junnyu/roformer_chinese_small", - "junnyu/roformer_chinese_base", - "junnyu/roformer_chinese_char_small", - "junnyu/roformer_chinese_char_base", - "junnyu/roformer_small_discriminator", - "junnyu/roformer_small_generator", - # See all RoFormer models at https://huggingface.co/models?filter=roformer -] + +from ..deprecated._archive_maps import TF_ROFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFRoFormerSinusoidalPositionalEmbedding(keras.layers.Layer): diff --git a/src/transformers/models/roformer/tokenization_roformer.py b/src/transformers/models/roformer/tokenization_roformer.py index 27a7281600..ebaf8e56b1 100644 --- a/src/transformers/models/roformer/tokenization_roformer.py +++ b/src/transformers/models/roformer/tokenization_roformer.py @@ -27,44 +27,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "junnyu/roformer_chinese_small": "https://huggingface.co/junnyu/roformer_chinese_small/resolve/main/vocab.txt", - "junnyu/roformer_chinese_base": "https://huggingface.co/junnyu/roformer_chinese_base/resolve/main/vocab.txt", - "junnyu/roformer_chinese_char_small": ( - "https://huggingface.co/junnyu/roformer_chinese_char_small/resolve/main/vocab.txt" - ), - "junnyu/roformer_chinese_char_base": ( - "https://huggingface.co/junnyu/roformer_chinese_char_base/resolve/main/vocab.txt" - ), - "junnyu/roformer_small_discriminator": ( - "https://huggingface.co/junnyu/roformer_small_discriminator/resolve/main/vocab.txt" - ), - "junnyu/roformer_small_generator": ( - "https://huggingface.co/junnyu/roformer_small_generator/resolve/main/vocab.txt" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "junnyu/roformer_chinese_small": 1536, - "junnyu/roformer_chinese_base": 1536, - "junnyu/roformer_chinese_char_small": 512, - "junnyu/roformer_chinese_char_base": 512, - "junnyu/roformer_small_discriminator": 128, - "junnyu/roformer_small_generator": 128, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "junnyu/roformer_chinese_small": {"do_lower_case": True}, - "junnyu/roformer_chinese_base": {"do_lower_case": True}, - "junnyu/roformer_chinese_char_small": {"do_lower_case": True}, - "junnyu/roformer_chinese_char_base": {"do_lower_case": True}, - "junnyu/roformer_small_discriminator": {"do_lower_case": True}, - "junnyu/roformer_small_generator": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert.load_vocab def load_vocab(vocab_file): @@ -360,9 +322,6 @@ class RoFormerTokenizer(PreTrainedTokenizer): ```""" vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION def __init__( self, diff --git a/src/transformers/models/roformer/tokenization_roformer_fast.py b/src/transformers/models/roformer/tokenization_roformer_fast.py index bed5935e90..1f073c03a5 100644 --- a/src/transformers/models/roformer/tokenization_roformer_fast.py +++ b/src/transformers/models/roformer/tokenization_roformer_fast.py @@ -29,44 +29,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "junnyu/roformer_chinese_small": "https://huggingface.co/junnyu/roformer_chinese_small/resolve/main/vocab.txt", - "junnyu/roformer_chinese_base": "https://huggingface.co/junnyu/roformer_chinese_base/resolve/main/vocab.txt", - "junnyu/roformer_chinese_char_small": ( - "https://huggingface.co/junnyu/roformer_chinese_char_small/resolve/main/vocab.txt" - ), - "junnyu/roformer_chinese_char_base": ( - "https://huggingface.co/junnyu/roformer_chinese_char_base/resolve/main/vocab.txt" - ), - "junnyu/roformer_small_discriminator": ( - "https://huggingface.co/junnyu/roformer_small_discriminator/resolve/main/vocab.txt" - ), - "junnyu/roformer_small_generator": ( - "https://huggingface.co/junnyu/roformer_small_generator/resolve/main/vocab.txt" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "junnyu/roformer_chinese_small": 1536, - "junnyu/roformer_chinese_base": 1536, - "junnyu/roformer_chinese_char_small": 512, - "junnyu/roformer_chinese_char_base": 512, - "junnyu/roformer_small_discriminator": 128, - "junnyu/roformer_small_generator": 128, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "junnyu/roformer_chinese_small": {"do_lower_case": True}, - "junnyu/roformer_chinese_base": {"do_lower_case": True}, - "junnyu/roformer_chinese_char_small": {"do_lower_case": True}, - "junnyu/roformer_chinese_char_base": {"do_lower_case": True}, - "junnyu/roformer_small_discriminator": {"do_lower_case": True}, - "junnyu/roformer_small_generator": {"do_lower_case": True}, -} - class RoFormerTokenizerFast(PreTrainedTokenizerFast): r""" @@ -89,9 +51,6 @@ class RoFormerTokenizerFast(PreTrainedTokenizerFast): ```""" vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION slow_tokenizer_class = RoFormerTokenizer def __init__( diff --git a/src/transformers/models/rwkv/configuration_rwkv.py b/src/transformers/models/rwkv/configuration_rwkv.py index 6e82a59935..a6abfc549e 100644 --- a/src/transformers/models/rwkv/configuration_rwkv.py +++ b/src/transformers/models/rwkv/configuration_rwkv.py @@ -21,18 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -RWKV_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "RWKV/rwkv-4-169m-pile": "https://huggingface.co/RWKV/rwkv-4-169m-pile/resolve/main/config.json", - "RWKV/rwkv-4-430m-pile": "https://huggingface.co/RWKV/rwkv-4-430m-pile/resolve/main/config.json", - "RWKV/rwkv-4-1b5-pile": "https://huggingface.co/RWKV/rwkv-4-1b5-pile/resolve/main/config.json", - "RWKV/rwkv-4-3b-pile": "https://huggingface.co/RWKV/rwkv-4-3b-pile/resolve/main/config.json", - "RWKV/rwkv-4-7b-pile": "https://huggingface.co/RWKV/rwkv-4-7b-pile/resolve/main/config.json", - "RWKV/rwkv-4-14b-pile": "https://huggingface.co/RWKV/rwkv-4-14b-pile/resolve/main/config.json", - "RWKV/rwkv-raven-1b5": "https://huggingface.co/RWKV/rwkv-raven-1b5/resolve/main/config.json", - "RWKV/rwkv-raven-3b": "https://huggingface.co/RWKV/rwkv-raven-3b/resolve/main/config.json", - "RWKV/rwkv-raven-7b": "https://huggingface.co/RWKV/rwkv-raven-7b/resolve/main/config.json", - "RWKV/rwkv-raven-14b": "https://huggingface.co/RWKV/rwkv-raven-14b/resolve/main/config.json", -} + +from ..deprecated._archive_maps import RWKV_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class RwkvConfig(PretrainedConfig): diff --git a/src/transformers/models/rwkv/modeling_rwkv.py b/src/transformers/models/rwkv/modeling_rwkv.py index e6dfa46f2a..79e06d141b 100644 --- a/src/transformers/models/rwkv/modeling_rwkv.py +++ b/src/transformers/models/rwkv/modeling_rwkv.py @@ -44,19 +44,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "RWKV/rwkv-4-169m-pile" _CONFIG_FOR_DOC = "RwkvConfig" -RWKV_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "RWKV/rwkv-4-169m-pile", - "RWKV/rwkv-4-430m-pile", - "RWKV/rwkv-4-1b5-pile", - "RWKV/rwkv-4-3b-pile", - "RWKV/rwkv-4-7b-pile", - "RWKV/rwkv-4-14b-pile", - "RWKV/rwkv-raven-1b5", - "RWKV/rwkv-raven-3b", - "RWKV/rwkv-raven-7b", - "RWKV/rwkv-raven-14b", - # See all RWKV models at https://huggingface.co/models?filter=rwkv -] + +from ..deprecated._archive_maps import RWKV_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 rwkv_cuda_kernel = None diff --git a/src/transformers/models/sam/configuration_sam.py b/src/transformers/models/sam/configuration_sam.py index 2eb75e122e..5afe75eb8e 100644 --- a/src/transformers/models/sam/configuration_sam.py +++ b/src/transformers/models/sam/configuration_sam.py @@ -21,11 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SAM_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/sam-vit-huge": "https://huggingface.co/facebook/sam-vit-huge/resolve/main/config.json", - "facebook/sam-vit-large": "https://huggingface.co/facebook/sam-vit-large/resolve/main/config.json", - "facebook/sam-vit-base": "https://huggingface.co/facebook/sam-vit-base/resolve/main/config.json", -} + +from ..deprecated._archive_maps import SAM_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SamPromptEncoderConfig(PretrainedConfig): diff --git a/src/transformers/models/sam/modeling_sam.py b/src/transformers/models/sam/modeling_sam.py index 7fc9e670ce..385fb9c00a 100644 --- a/src/transformers/models/sam/modeling_sam.py +++ b/src/transformers/models/sam/modeling_sam.py @@ -37,12 +37,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "SamConfig" _CHECKPOINT_FOR_DOC = "facebook/sam-vit-huge" -SAM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/sam-vit-huge", - "facebook/sam-vit-large", - "facebook/sam-vit-base", - # See all SAM models at https://huggingface.co/models?filter=sam -] + +from ..deprecated._archive_maps import SAM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/sam/modeling_tf_sam.py b/src/transformers/models/sam/modeling_tf_sam.py index db7b9d32cd..f527337cd6 100644 --- a/src/transformers/models/sam/modeling_tf_sam.py +++ b/src/transformers/models/sam/modeling_tf_sam.py @@ -40,12 +40,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "SamConfig" _CHECKPOINT_FOR_DOC = "facebook/sam-vit-huge" -TF_SAM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/sam-vit-huge", - "facebook/sam-vit-large", - "facebook/sam-vit-base", - # See all SAM models at https://huggingface.co/models?filter=sam -] + +from ..deprecated._archive_maps import TF_SAM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/seamless_m4t/configuration_seamless_m4t.py b/src/transformers/models/seamless_m4t/configuration_seamless_m4t.py index b4407ed741..8ae61f1def 100644 --- a/src/transformers/models/seamless_m4t/configuration_seamless_m4t.py +++ b/src/transformers/models/seamless_m4t/configuration_seamless_m4t.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SEAMLESS_M4T_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/hf-seamless-m4t-medium": "https://huggingface.co/facebook/hf-seamless-m4t-medium/resolve/main/config.json", - # See all SeamlessM4T models at https://huggingface.co/models?filter=seamless_m4t -} + +from ..deprecated._archive_maps import SEAMLESS_M4T_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SeamlessM4TConfig(PretrainedConfig): diff --git a/src/transformers/models/seamless_m4t/modeling_seamless_m4t.py b/src/transformers/models/seamless_m4t/modeling_seamless_m4t.py index 6b00754930..f619dd9e79 100755 --- a/src/transformers/models/seamless_m4t/modeling_seamless_m4t.py +++ b/src/transformers/models/seamless_m4t/modeling_seamless_m4t.py @@ -50,14 +50,11 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "facebook/hf-seamless-m4t-medium" _CONFIG_FOR_DOC = "SeamlessM4TConfig" -SEAMLESS_M4T_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/hf-seamless-m4t-medium", - # See all SeamlessM4T models at https://huggingface.co/models?filter=seamless_m4t -] -SPEECHT5_PRETRAINED_HIFIGAN_CONFIG_ARCHIVE_MAP = { - "microsoft/speecht5_hifigan": "https://huggingface.co/microsoft/speecht5_hifigan/resolve/main/config.json", -} +from ..deprecated._archive_maps import ( # noqa: F401, E402 + SEAMLESS_M4T_PRETRAINED_MODEL_ARCHIVE_LIST, # noqa: F401, E402 + SPEECHT5_PRETRAINED_HIFIGAN_CONFIG_ARCHIVE_MAP, # noqa: F401, E402 +) @dataclass diff --git a/src/transformers/models/seamless_m4t/tokenization_seamless_m4t.py b/src/transformers/models/seamless_m4t/tokenization_seamless_m4t.py index 99dd1f0955..bb6beb760a 100644 --- a/src/transformers/models/seamless_m4t/tokenization_seamless_m4t.py +++ b/src/transformers/models/seamless_m4t/tokenization_seamless_m4t.py @@ -32,13 +32,6 @@ from ...utils import PaddingStrategy, logging logger = logging.get_logger(__name__) -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/hf-seamless-m4t-medium": ( - "https://huggingface.co/facebook/hf-seamless-m4t-medium/blob/main/sentencepiece.bpe.model" - ), - } -} SPIECE_UNDERLINE = "▁" @@ -46,11 +39,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model"} -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/hf-seamless-m4t-medium": 2048, -} - - class SeamlessM4TTokenizer(PreTrainedTokenizer): """ Construct a SeamlessM4T tokenizer. @@ -126,8 +114,6 @@ class SeamlessM4TTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP model_input_names = ["input_ids", "attention_mask"] prefix_tokens: List[int] = [] diff --git a/src/transformers/models/seamless_m4t/tokenization_seamless_m4t_fast.py b/src/transformers/models/seamless_m4t/tokenization_seamless_m4t_fast.py index b7bedfb38a..a236db3cb5 100644 --- a/src/transformers/models/seamless_m4t/tokenization_seamless_m4t_fast.py +++ b/src/transformers/models/seamless_m4t/tokenization_seamless_m4t_fast.py @@ -37,19 +37,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/hf-seamless-m4t-medium": "https://huggingface.co/facebook/hf-seamless-m4t-medium/resolve/main/vocab.txt", - }, - "tokenizer_file": { - "facebook/hf-seamless-m4t-medium": "https://huggingface.co/facebook/hf-seamless-m4t-medium/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/hf-seamless-m4t-medium": 2048, -} - class SeamlessM4TTokenizerFast(PreTrainedTokenizerFast): """ @@ -121,8 +108,6 @@ class SeamlessM4TTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = SeamlessM4TTokenizer model_input_names = ["input_ids", "attention_mask"] diff --git a/src/transformers/models/seamless_m4t_v2/configuration_seamless_m4t_v2.py b/src/transformers/models/seamless_m4t_v2/configuration_seamless_m4t_v2.py index 28c521f6a5..e03523d3e0 100644 --- a/src/transformers/models/seamless_m4t_v2/configuration_seamless_m4t_v2.py +++ b/src/transformers/models/seamless_m4t_v2/configuration_seamless_m4t_v2.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SEAMLESS_M4T_V2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "": "https://huggingface.co//resolve/main/config.json", -} + +from ..deprecated._archive_maps import SEAMLESS_M4T_V2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SeamlessM4Tv2Config(PretrainedConfig): diff --git a/src/transformers/models/seamless_m4t_v2/modeling_seamless_m4t_v2.py b/src/transformers/models/seamless_m4t_v2/modeling_seamless_m4t_v2.py index fd64051f6c..c7f90f6c0a 100644 --- a/src/transformers/models/seamless_m4t_v2/modeling_seamless_m4t_v2.py +++ b/src/transformers/models/seamless_m4t_v2/modeling_seamless_m4t_v2.py @@ -50,10 +50,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "" _CONFIG_FOR_DOC = "SeamlessM4Tv2Config" -SEAMLESS_M4T_V2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/seamless-m4t-v2-large", - # See all SeamlessM4T-v2 models at https://huggingface.co/models?filter=seamless_m4t_v2 -] + +from ..deprecated._archive_maps import SEAMLESS_M4T_V2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 SPEECHT5_PRETRAINED_HIFIGAN_CONFIG_ARCHIVE_MAP = { diff --git a/src/transformers/models/segformer/configuration_segformer.py b/src/transformers/models/segformer/configuration_segformer.py index ad1c205329..aba2693ba3 100644 --- a/src/transformers/models/segformer/configuration_segformer.py +++ b/src/transformers/models/segformer/configuration_segformer.py @@ -27,12 +27,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SEGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "nvidia/segformer-b0-finetuned-ade-512-512": ( - "https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512/resolve/main/config.json" - ), - # See all SegFormer models at https://huggingface.co/models?filter=segformer -} + +from ..deprecated._archive_maps import SEGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SegformerConfig(PretrainedConfig): diff --git a/src/transformers/models/segformer/modeling_segformer.py b/src/transformers/models/segformer/modeling_segformer.py index 47f42b5e0e..d1205630dd 100755 --- a/src/transformers/models/segformer/modeling_segformer.py +++ b/src/transformers/models/segformer/modeling_segformer.py @@ -51,10 +51,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 256, 16, 16] _IMAGE_CLASS_CHECKPOINT = "nvidia/mit-b0" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -SEGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "nvidia/segformer-b0-finetuned-ade-512-512", - # See all SegFormer models at https://huggingface.co/models?filter=segformer -] + +from ..deprecated._archive_maps import SEGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class SegFormerImageClassifierOutput(ImageClassifierOutput): diff --git a/src/transformers/models/segformer/modeling_tf_segformer.py b/src/transformers/models/segformer/modeling_tf_segformer.py index 75c8ee2b39..d215059ff6 100644 --- a/src/transformers/models/segformer/modeling_tf_segformer.py +++ b/src/transformers/models/segformer/modeling_tf_segformer.py @@ -55,10 +55,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 256, 16, 16] _IMAGE_CLASS_CHECKPOINT = "nvidia/mit-b0" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -TF_SEGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "nvidia/segformer-b0-finetuned-ade-512-512", - # See all SegFormer models at https://huggingface.co/models?filter=segformer -] + +from ..deprecated._archive_maps import TF_SEGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.convnext.modeling_tf_convnext.TFConvNextDropPath with ConvNext->Segformer diff --git a/src/transformers/models/seggpt/configuration_seggpt.py b/src/transformers/models/seggpt/configuration_seggpt.py index 37c81f1032..38607d775a 100644 --- a/src/transformers/models/seggpt/configuration_seggpt.py +++ b/src/transformers/models/seggpt/configuration_seggpt.py @@ -21,9 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SEGGPT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "BAAI/seggpt-vit-large": "https://huggingface.co/BAAI/seggpt-vit-large/resolve/main/config.json", -} + +from ..deprecated._archive_maps import SEGGPT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SegGptConfig(PretrainedConfig): diff --git a/src/transformers/models/seggpt/modeling_seggpt.py b/src/transformers/models/seggpt/modeling_seggpt.py index 87175fdf38..79fd309eaf 100644 --- a/src/transformers/models/seggpt/modeling_seggpt.py +++ b/src/transformers/models/seggpt/modeling_seggpt.py @@ -47,10 +47,7 @@ _CHECKPOINT_FOR_DOC = "BAAI/seggpt-vit-large" _EXPECTED_OUTPUT_SHAPE = [3, 896, 448] -SEGGPT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "BAAI/seggpt-vit-large", - # See all SegGpt models at https://huggingface.co/models?filter=seggpt -] +from ..deprecated._archive_maps import SEGGPT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/sew/configuration_sew.py b/src/transformers/models/sew/configuration_sew.py index f5db6fd2c1..b14ce441d0 100644 --- a/src/transformers/models/sew/configuration_sew.py +++ b/src/transformers/models/sew/configuration_sew.py @@ -23,10 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SEW_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "asapp/sew-tiny-100k": "https://huggingface.co/asapp/sew-tiny-100k/resolve/main/config.json", - # See all SEW models at https://huggingface.co/models?filter=sew -} + +from ..deprecated._archive_maps import SEW_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SEWConfig(PretrainedConfig): diff --git a/src/transformers/models/sew/modeling_sew.py b/src/transformers/models/sew/modeling_sew.py index a5ebb9b2bb..950a91fb6a 100644 --- a/src/transformers/models/sew/modeling_sew.py +++ b/src/transformers/models/sew/modeling_sew.py @@ -55,12 +55,8 @@ _SEQ_CLASS_CHECKPOINT = "anton-l/sew-mid-100k-ft-keyword-spotting" _SEQ_CLASS_EXPECTED_OUTPUT = "'_unknown_'" _SEQ_CLASS_EXPECTED_LOSS = 9.52 -SEW_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "asapp/sew-tiny-100k", - "asapp/sew-small-100k", - "asapp/sew-mid-100k", - # See all SEW models at https://huggingface.co/models?filter=sew -] + +from ..deprecated._archive_maps import SEW_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.wav2vec2.modeling_wav2vec2._compute_mask_indices diff --git a/src/transformers/models/sew_d/configuration_sew_d.py b/src/transformers/models/sew_d/configuration_sew_d.py index 2f08ff81f5..9e96a1f22b 100644 --- a/src/transformers/models/sew_d/configuration_sew_d.py +++ b/src/transformers/models/sew_d/configuration_sew_d.py @@ -23,10 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SEW_D_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "asapp/sew-d-tiny-100k": "https://huggingface.co/asapp/sew-d-tiny-100k/resolve/main/config.json", - # See all SEW-D models at https://huggingface.co/models?filter=sew-d -} + +from ..deprecated._archive_maps import SEW_D_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SEWDConfig(PretrainedConfig): diff --git a/src/transformers/models/sew_d/modeling_sew_d.py b/src/transformers/models/sew_d/modeling_sew_d.py index 8e890f207d..aadcf6f669 100644 --- a/src/transformers/models/sew_d/modeling_sew_d.py +++ b/src/transformers/models/sew_d/modeling_sew_d.py @@ -55,18 +55,8 @@ _SEQ_CLASS_CHECKPOINT = "anton-l/sew-d-mid-400k-ft-keyword-spotting" _SEQ_CLASS_EXPECTED_OUTPUT = "'_unknown_'" _SEQ_CLASS_EXPECTED_LOSS = 3.16 -SEW_D_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "asapp/sew-d-tiny-100k", - "asapp/sew-d-small-100k", - "asapp/sew-d-mid-100k", - "asapp/sew-d-mid-k127-100k", - "asapp/sew-d-base-100k", - "asapp/sew-d-base-plus-100k", - "asapp/sew-d-mid-400k", - "asapp/sew-d-mid-k127-400k", - "asapp/sew-d-base-plus-400k", - # See all SEW models at https://huggingface.co/models?filter=sew-d -] + +from ..deprecated._archive_maps import SEW_D_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.wav2vec2.modeling_wav2vec2._compute_mask_indices diff --git a/src/transformers/models/siglip/configuration_siglip.py b/src/transformers/models/siglip/configuration_siglip.py index 990bad7ace..872e5c3b96 100644 --- a/src/transformers/models/siglip/configuration_siglip.py +++ b/src/transformers/models/siglip/configuration_siglip.py @@ -23,9 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SIGLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/siglip-base-patch16-224": "https://huggingface.co/google/siglip-base-patch16-224/resolve/main/config.json", -} + +from ..deprecated._archive_maps import SIGLIP_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SiglipTextConfig(PretrainedConfig): diff --git a/src/transformers/models/siglip/modeling_siglip.py b/src/transformers/models/siglip/modeling_siglip.py index 07f6dd6721..6e225803b4 100644 --- a/src/transformers/models/siglip/modeling_siglip.py +++ b/src/transformers/models/siglip/modeling_siglip.py @@ -53,10 +53,7 @@ _IMAGE_CLASS_CHECKPOINT = "google/siglip-base-patch16-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "LABEL_1" -SIGLIP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/siglip-base-patch16-224", - # See all SigLIP models at https://huggingface.co/models?filter=siglip -] +from ..deprecated._archive_maps import SIGLIP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def _trunc_normal_(tensor, mean, std, a, b): diff --git a/src/transformers/models/siglip/tokenization_siglip.py b/src/transformers/models/siglip/tokenization_siglip.py index 043d1d27b8..41277320a3 100644 --- a/src/transformers/models/siglip/tokenization_siglip.py +++ b/src/transformers/models/siglip/tokenization_siglip.py @@ -37,15 +37,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google/siglip-base-patch16-224": "https://huggingface.co/google/siglip-base-patch16-224/resolve/main/spiece.model", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google/siglip-base-patch16-224": 256, -} SPIECE_UNDERLINE = "▁" @@ -92,8 +83,6 @@ class SiglipTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/speech_to_text/configuration_speech_to_text.py b/src/transformers/models/speech_to_text/configuration_speech_to_text.py index fb1a8e1b5a..67dee8dc0b 100644 --- a/src/transformers/models/speech_to_text/configuration_speech_to_text.py +++ b/src/transformers/models/speech_to_text/configuration_speech_to_text.py @@ -20,12 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SPEECH_TO_TEXT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/s2t-small-librispeech-asr": ( - "https://huggingface.co/facebook/s2t-small-librispeech-asr/resolve/main/config.json" - ), - # See all Speech2Text models at https://huggingface.co/models?filter=speech_to_text -} + +from ..deprecated._archive_maps import SPEECH_TO_TEXT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Speech2TextConfig(PretrainedConfig): diff --git a/src/transformers/models/speech_to_text/modeling_speech_to_text.py b/src/transformers/models/speech_to_text/modeling_speech_to_text.py index a5ec9e9fd3..6898cc081f 100755 --- a/src/transformers/models/speech_to_text/modeling_speech_to_text.py +++ b/src/transformers/models/speech_to_text/modeling_speech_to_text.py @@ -44,10 +44,7 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "Speech2TextConfig" -SPEECH_TO_TEXT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/s2t-small-librispeech-asr", - # See all Speech2Text models at https://huggingface.co/models?filter=speech_to_text -] +from ..deprecated._archive_maps import SPEECH_TO_TEXT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.bart.modeling_bart.shift_tokens_right diff --git a/src/transformers/models/speech_to_text/modeling_tf_speech_to_text.py b/src/transformers/models/speech_to_text/modeling_tf_speech_to_text.py index 927d8e09ba..8fd6bd21a5 100755 --- a/src/transformers/models/speech_to_text/modeling_tf_speech_to_text.py +++ b/src/transformers/models/speech_to_text/modeling_tf_speech_to_text.py @@ -56,10 +56,7 @@ _CONFIG_FOR_DOC = "Speech2TextConfig" _CHECKPOINT_FOR_DOC = "facebook/s2t-small-librispeech-asr" -TF_SPEECH_TO_TEXT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/s2t-small-librispeech-asr", - # See all Speech2Text models at https://huggingface.co/models?filter=speech_to_text -] +from ..deprecated._archive_maps import TF_SPEECH_TO_TEXT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 LARGE_NEGATIVE = -1e8 diff --git a/src/transformers/models/speech_to_text/tokenization_speech_to_text.py b/src/transformers/models/speech_to_text/tokenization_speech_to_text.py index b7104da7f1..27db0a671e 100644 --- a/src/transformers/models/speech_to_text/tokenization_speech_to_text.py +++ b/src/transformers/models/speech_to_text/tokenization_speech_to_text.py @@ -34,18 +34,6 @@ VOCAB_FILES_NAMES = { "spm_file": "sentencepiece.bpe.model", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/s2t-small-librispeech-asr": ( - "https://huggingface.co/facebook/s2t-small-librispeech-asr/resolve/main/vocab.json" - ), - }, - "spm_file": { - "facebook/s2t-small-librispeech-asr": ( - "https://huggingface.co/facebook/s2t-small-librispeech-asr/resolve/main/sentencepiece.bpe.model" - ) - }, -} MAX_MODEL_INPUT_SIZES = { "facebook/s2t-small-librispeech-asr": 1024, @@ -104,8 +92,6 @@ class Speech2TextTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = MAX_MODEL_INPUT_SIZES model_input_names = ["input_ids", "attention_mask"] prefix_tokens: List[int] = [] diff --git a/src/transformers/models/speech_to_text_2/configuration_speech_to_text_2.py b/src/transformers/models/speech_to_text_2/configuration_speech_to_text_2.py index 5dd34cb86b..cbb3be8255 100644 --- a/src/transformers/models/speech_to_text_2/configuration_speech_to_text_2.py +++ b/src/transformers/models/speech_to_text_2/configuration_speech_to_text_2.py @@ -20,12 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SPEECH_TO_TEXT_2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/s2t-wav2vec2-large-en-de": ( - "https://huggingface.co/facebook/s2t-wav2vec2-large-en-de/resolve/main/config.json" - ), - # See all Speech2Text models at https://huggingface.co/models?filter=speech2text2 -} + +from ..deprecated._archive_maps import SPEECH_TO_TEXT_2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Speech2Text2Config(PretrainedConfig): diff --git a/src/transformers/models/speech_to_text_2/modeling_speech_to_text_2.py b/src/transformers/models/speech_to_text_2/modeling_speech_to_text_2.py index 4f5885f8c8..20f8555bd9 100755 --- a/src/transformers/models/speech_to_text_2/modeling_speech_to_text_2.py +++ b/src/transformers/models/speech_to_text_2/modeling_speech_to_text_2.py @@ -37,12 +37,6 @@ _CONFIG_FOR_DOC = "Speech2Text2Config" _CHECKPOINT_FOR_DOC = "facebook/s2t-wav2vec2-large-en-de" -SPEECH_TO_TEXT_2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/s2t-wav2vec2-large-en-de", - # See all Speech2Text2 models at https://huggingface.co/models?filter=speech2text2 -] - - # Copied from transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextSinusoidalPositionalEmbedding with Speech2Text->Speech2Text2 class Speech2Text2SinusoidalPositionalEmbedding(nn.Module): """This module produces sinusoidal positional embeddings of any length.""" diff --git a/src/transformers/models/speech_to_text_2/tokenization_speech_to_text_2.py b/src/transformers/models/speech_to_text_2/tokenization_speech_to_text_2.py index 074576a6c0..8d6818356f 100644 --- a/src/transformers/models/speech_to_text_2/tokenization_speech_to_text_2.py +++ b/src/transformers/models/speech_to_text_2/tokenization_speech_to_text_2.py @@ -31,23 +31,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/s2t-wav2vec2-large-en-de": ( - "https://huggingface.co/facebook/s2t-wav2vec2-large-en-de/resolve/main/vocab.json" - ), - }, - "tokenizer_config_file": { - "facebook/s2t-wav2vec2-large-en-de": ( - "https://huggingface.co/facebook/s2t-wav2vec2-large-en-de/resolve/main/tokenizer_config.json" - ), - }, - "merges_file": { - "facebook/s2t-wav2vec2-large-en-de": ( - "https://huggingface.co/facebook/s2t-wav2vec2-large-en-de/resolve/main/merges.txt" - ), - }, -} BPE_TOKEN_MERGES = "" BPE_TOKEN_VOCAB = "@@ " @@ -67,7 +50,6 @@ def get_pairs(word): # Speech2Text2 has no max input length -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"facebook/s2t-wav2vec2-large-en-de": 1024} class Speech2Text2Tokenizer(PreTrainedTokenizer): @@ -95,8 +77,6 @@ class Speech2Text2Tokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/speecht5/configuration_speecht5.py b/src/transformers/models/speecht5/configuration_speecht5.py index c7cd7d2f62..36cb4995a8 100644 --- a/src/transformers/models/speecht5/configuration_speecht5.py +++ b/src/transformers/models/speecht5/configuration_speecht5.py @@ -23,11 +23,9 @@ from ...utils import logging logger = logging.get_logger(__name__) -SPEECHT5_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/speecht5_asr": "https://huggingface.co/microsoft/speecht5_asr/resolve/main/config.json", - "microsoft/speecht5_tts": "https://huggingface.co/microsoft/speecht5_tts/resolve/main/config.json", - "microsoft/speecht5_vc": "https://huggingface.co/microsoft/speecht5_vc/resolve/main/config.json", -} + +from ..deprecated._archive_maps import SPEECHT5_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 + SPEECHT5_PRETRAINED_HIFIGAN_CONFIG_ARCHIVE_MAP = { "microsoft/speecht5_hifigan": "https://huggingface.co/microsoft/speecht5_hifigan/resolve/main/config.json", diff --git a/src/transformers/models/speecht5/modeling_speecht5.py b/src/transformers/models/speecht5/modeling_speecht5.py index e9f9f1e171..c4b9aca6f0 100644 --- a/src/transformers/models/speecht5/modeling_speecht5.py +++ b/src/transformers/models/speecht5/modeling_speecht5.py @@ -47,12 +47,7 @@ _HIDDEN_STATES_START_POSITION = 1 _CONFIG_FOR_DOC = "SpeechT5Config" -SPEECHT5_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/speecht5_asr", - "microsoft/speecht5_tts", - "microsoft/speecht5_vc", - # See all SpeechT5 models at https://huggingface.co/models?filter=speecht5 -] +from ..deprecated._archive_maps import SPEECHT5_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.bart.modeling_bart.shift_tokens_right diff --git a/src/transformers/models/speecht5/tokenization_speecht5.py b/src/transformers/models/speecht5/tokenization_speecht5.py index 9f5ed8a5e0..41cb296f8f 100644 --- a/src/transformers/models/speecht5/tokenization_speecht5.py +++ b/src/transformers/models/speecht5/tokenization_speecht5.py @@ -30,20 +30,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spm_char.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/speecht5_asr": "https://huggingface.co/microsoft/speecht5_asr/resolve/main/spm_char.model", - "microsoft/speecht5_tts": "https://huggingface.co/microsoft/speecht5_tts/resolve/main/spm_char.model", - "microsoft/speecht5_vc": "https://huggingface.co/microsoft/speecht5_vc/resolve/main/spm_char.model", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/speecht5_asr": 1024, - "microsoft/speecht5_tts": 1024, - "microsoft/speecht5_vc": 1024, -} - class SpeechT5Tokenizer(PreTrainedTokenizer): """ @@ -89,8 +75,6 @@ class SpeechT5Tokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/splinter/configuration_splinter.py b/src/transformers/models/splinter/configuration_splinter.py index e7325f0165..5248c74c1a 100644 --- a/src/transformers/models/splinter/configuration_splinter.py +++ b/src/transformers/models/splinter/configuration_splinter.py @@ -20,13 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SPLINTER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "tau/splinter-base": "https://huggingface.co/tau/splinter-base/resolve/main/config.json", - "tau/splinter-base-qass": "https://huggingface.co/tau/splinter-base-qass/resolve/main/config.json", - "tau/splinter-large": "https://huggingface.co/tau/splinter-large/resolve/main/config.json", - "tau/splinter-large-qass": "https://huggingface.co/tau/splinter-large-qass/resolve/main/config.json", - # See all Splinter models at https://huggingface.co/models?filter=splinter -} + +from ..deprecated._archive_maps import SPLINTER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SplinterConfig(PretrainedConfig): diff --git a/src/transformers/models/splinter/modeling_splinter.py b/src/transformers/models/splinter/modeling_splinter.py index 75187c36b9..b643601d0e 100755 --- a/src/transformers/models/splinter/modeling_splinter.py +++ b/src/transformers/models/splinter/modeling_splinter.py @@ -37,13 +37,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "tau/splinter-base" _CONFIG_FOR_DOC = "SplinterConfig" -SPLINTER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "tau/splinter-base", - "tau/splinter-base-qass", - "tau/splinter-large", - "tau/splinter-large-qass", - # See all Splinter models at https://huggingface.co/models?filter=splinter -] + +from ..deprecated._archive_maps import SPLINTER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class SplinterEmbeddings(nn.Module): diff --git a/src/transformers/models/splinter/tokenization_splinter.py b/src/transformers/models/splinter/tokenization_splinter.py index 909905979b..ee82e19c6c 100644 --- a/src/transformers/models/splinter/tokenization_splinter.py +++ b/src/transformers/models/splinter/tokenization_splinter.py @@ -28,29 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "tau/splinter-base": "https://huggingface.co/tau/splinter-base/resolve/main/vocab.txt", - "tau/splinter-base-qass": "https://huggingface.co/tau/splinter-base-qass/resolve/main/vocab.txt", - "tau/splinter-large": "https://huggingface.co/tau/splinter-large/resolve/main/vocab.txt", - "tau/splinter-large-qass": "https://huggingface.co/tau/splinter-large-qass/resolve/main/vocab.txt", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "tau/splinter-base": 512, - "tau/splinter-base-qass": 512, - "tau/splinter-large": 512, - "tau/splinter-large-qass": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "tau/splinter-base": {"do_lower_case": False}, - "tau/splinter-base-qass": {"do_lower_case": False}, - "tau/splinter-large": {"do_lower_case": False}, - "tau/splinter-large-qass": {"do_lower_case": False}, -} - def load_vocab(vocab_file): """Loads a vocabulary file into a dictionary.""" @@ -117,9 +94,6 @@ class SplinterTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/splinter/tokenization_splinter_fast.py b/src/transformers/models/splinter/tokenization_splinter_fast.py index 97db72caad..0371fdf282 100644 --- a/src/transformers/models/splinter/tokenization_splinter_fast.py +++ b/src/transformers/models/splinter/tokenization_splinter_fast.py @@ -28,29 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "tau/splinter-base": "https://huggingface.co/tau/splinter-base/resolve/main/vocab.txt", - "tau/splinter-base-qass": "https://huggingface.co/tau/splinter-base-qass/resolve/main/vocab.txt", - "tau/splinter-large": "https://huggingface.co/tau/splinter-large/resolve/main/vocab.txt", - "tau/splinter-large-qass": "https://huggingface.co/tau/splinter-large-qass/resolve/main/vocab.txt", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "tau/splinter-base": 512, - "tau/splinter-base-qass": 512, - "tau/splinter-large": 512, - "tau/splinter-large-qass": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "tau/splinter-base": {"do_lower_case": False}, - "tau/splinter-base-qass": {"do_lower_case": False}, - "tau/splinter-large": {"do_lower_case": False}, - "tau/splinter-large-qass": {"do_lower_case": False}, -} - class SplinterTokenizerFast(PreTrainedTokenizerFast): r""" @@ -95,9 +72,6 @@ class SplinterTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = SplinterTokenizer def __init__( diff --git a/src/transformers/models/squeezebert/configuration_squeezebert.py b/src/transformers/models/squeezebert/configuration_squeezebert.py index 4926a73177..2e8710bb5c 100644 --- a/src/transformers/models/squeezebert/configuration_squeezebert.py +++ b/src/transformers/models/squeezebert/configuration_squeezebert.py @@ -23,15 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "squeezebert/squeezebert-uncased": ( - "https://huggingface.co/squeezebert/squeezebert-uncased/resolve/main/config.json" - ), - "squeezebert/squeezebert-mnli": "https://huggingface.co/squeezebert/squeezebert-mnli/resolve/main/config.json", - "squeezebert/squeezebert-mnli-headless": ( - "https://huggingface.co/squeezebert/squeezebert-mnli-headless/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SqueezeBertConfig(PretrainedConfig): @@ -105,12 +98,8 @@ class SqueezeBertConfig(PretrainedConfig): >>> # Accessing the model configuration >>> configuration = model.config ``` - - Attributes: pretrained_config_archive_map (Dict[str, str]): A dictionary containing all the available pre-trained - checkpoints. """ - pretrained_config_archive_map = SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP model_type = "squeezebert" def __init__( diff --git a/src/transformers/models/squeezebert/modeling_squeezebert.py b/src/transformers/models/squeezebert/modeling_squeezebert.py index 0ac1260c82..b5657f6e6f 100644 --- a/src/transformers/models/squeezebert/modeling_squeezebert.py +++ b/src/transformers/models/squeezebert/modeling_squeezebert.py @@ -42,11 +42,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "squeezebert/squeezebert-uncased" _CONFIG_FOR_DOC = "SqueezeBertConfig" -SQUEEZEBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "squeezebert/squeezebert-uncased", - "squeezebert/squeezebert-mnli", - "squeezebert/squeezebert-mnli-headless", -] + +from ..deprecated._archive_maps import SQUEEZEBERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class SqueezeBertEmbeddings(nn.Module): diff --git a/src/transformers/models/squeezebert/tokenization_squeezebert.py b/src/transformers/models/squeezebert/tokenization_squeezebert.py index c655ba8dda..30f866770d 100644 --- a/src/transformers/models/squeezebert/tokenization_squeezebert.py +++ b/src/transformers/models/squeezebert/tokenization_squeezebert.py @@ -27,31 +27,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "squeezebert/squeezebert-uncased": ( - "https://huggingface.co/squeezebert/squeezebert-uncased/resolve/main/vocab.txt" - ), - "squeezebert/squeezebert-mnli": "https://huggingface.co/squeezebert/squeezebert-mnli/resolve/main/vocab.txt", - "squeezebert/squeezebert-mnli-headless": ( - "https://huggingface.co/squeezebert/squeezebert-mnli-headless/resolve/main/vocab.txt" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "squeezebert/squeezebert-uncased": 512, - "squeezebert/squeezebert-mnli": 512, - "squeezebert/squeezebert-mnli-headless": 512, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "squeezebert/squeezebert-uncased": {"do_lower_case": True}, - "squeezebert/squeezebert-mnli": {"do_lower_case": True}, - "squeezebert/squeezebert-mnli-headless": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert.load_vocab def load_vocab(vocab_file): @@ -119,9 +94,6 @@ class SqueezeBertTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/squeezebert/tokenization_squeezebert_fast.py b/src/transformers/models/squeezebert/tokenization_squeezebert_fast.py index a06aaf615e..985fe657f0 100644 --- a/src/transformers/models/squeezebert/tokenization_squeezebert_fast.py +++ b/src/transformers/models/squeezebert/tokenization_squeezebert_fast.py @@ -28,42 +28,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "squeezebert/squeezebert-uncased": ( - "https://huggingface.co/squeezebert/squeezebert-uncased/resolve/main/vocab.txt" - ), - "squeezebert/squeezebert-mnli": "https://huggingface.co/squeezebert/squeezebert-mnli/resolve/main/vocab.txt", - "squeezebert/squeezebert-mnli-headless": ( - "https://huggingface.co/squeezebert/squeezebert-mnli-headless/resolve/main/vocab.txt" - ), - }, - "tokenizer_file": { - "squeezebert/squeezebert-uncased": ( - "https://huggingface.co/squeezebert/squeezebert-uncased/resolve/main/tokenizer.json" - ), - "squeezebert/squeezebert-mnli": ( - "https://huggingface.co/squeezebert/squeezebert-mnli/resolve/main/tokenizer.json" - ), - "squeezebert/squeezebert-mnli-headless": ( - "https://huggingface.co/squeezebert/squeezebert-mnli-headless/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "squeezebert/squeezebert-uncased": 512, - "squeezebert/squeezebert-mnli": 512, - "squeezebert/squeezebert-mnli-headless": 512, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "squeezebert/squeezebert-uncased": {"do_lower_case": True}, - "squeezebert/squeezebert-mnli": {"do_lower_case": True}, - "squeezebert/squeezebert-mnli-headless": {"do_lower_case": True}, -} - # Copied from transformers.models.bert.tokenization_bert_fast.BertTokenizerFast with Bert->SqueezeBert,BERT->SqueezeBERT class SqueezeBertTokenizerFast(PreTrainedTokenizerFast): @@ -107,9 +71,6 @@ class SqueezeBertTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = SqueezeBertTokenizer def __init__( diff --git a/src/transformers/models/stablelm/configuration_stablelm.py b/src/transformers/models/stablelm/configuration_stablelm.py index b3e7f3216c..d702ba87af 100644 --- a/src/transformers/models/stablelm/configuration_stablelm.py +++ b/src/transformers/models/stablelm/configuration_stablelm.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -STABLELM_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "stabilityai/stablelm-3b-4e1t": "https://huggingface.co/stabilityai/stablelm-3b-4e1t/resolve/main/config.json", - # See all StableLM models at https://huggingface.co/models?filter=stablelm -} + +from ..deprecated._archive_maps import STABLELM_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class StableLmConfig(PretrainedConfig): diff --git a/src/transformers/models/starcoder2/configuration_starcoder2.py b/src/transformers/models/starcoder2/configuration_starcoder2.py index d569ebb4f7..8337135442 100644 --- a/src/transformers/models/starcoder2/configuration_starcoder2.py +++ b/src/transformers/models/starcoder2/configuration_starcoder2.py @@ -20,7 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -STARCODER2_PRETRAINED_CONFIG_ARCHIVE_MAP = {} + +from ..deprecated._archive_maps import STARCODER2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Starcoder2Config(PretrainedConfig): diff --git a/src/transformers/models/swiftformer/configuration_swiftformer.py b/src/transformers/models/swiftformer/configuration_swiftformer.py index 3e06b2feab..3c7a9eebbd 100644 --- a/src/transformers/models/swiftformer/configuration_swiftformer.py +++ b/src/transformers/models/swiftformer/configuration_swiftformer.py @@ -26,9 +26,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SWIFTFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "MBZUAI/swiftformer-xs": "https://huggingface.co/MBZUAI/swiftformer-xs/resolve/main/config.json", -} + +from ..deprecated._archive_maps import SWIFTFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SwiftFormerConfig(PretrainedConfig): diff --git a/src/transformers/models/swiftformer/modeling_swiftformer.py b/src/transformers/models/swiftformer/modeling_swiftformer.py index 0c59c6b5b2..c447c0ce12 100644 --- a/src/transformers/models/swiftformer/modeling_swiftformer.py +++ b/src/transformers/models/swiftformer/modeling_swiftformer.py @@ -52,10 +52,7 @@ _IMAGE_CLASS_CHECKPOINT = "MBZUAI/swiftformer-xs" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -SWIFTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "MBZUAI/swiftformer-xs", - # See all SwiftFormer models at https://huggingface.co/models?filter=swiftformer -] +from ..deprecated._archive_maps import SWIFTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class SwiftFormerPatchEmbedding(nn.Module): diff --git a/src/transformers/models/swin/configuration_swin.py b/src/transformers/models/swin/configuration_swin.py index 20da7ac113..9bf460870f 100644 --- a/src/transformers/models/swin/configuration_swin.py +++ b/src/transformers/models/swin/configuration_swin.py @@ -27,12 +27,8 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -SWIN_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/swin-tiny-patch4-window7-224": ( - "https://huggingface.co/microsoft/swin-tiny-patch4-window7-224/resolve/main/config.json" - ), - # See all Swin models at https://huggingface.co/models?filter=swin -} + +from ..deprecated._archive_maps import SWIN_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SwinConfig(BackboneConfigMixin, PretrainedConfig): diff --git a/src/transformers/models/swin/modeling_swin.py b/src/transformers/models/swin/modeling_swin.py index a3f0643512..c841faddf0 100644 --- a/src/transformers/models/swin/modeling_swin.py +++ b/src/transformers/models/swin/modeling_swin.py @@ -56,10 +56,8 @@ _IMAGE_CLASS_CHECKPOINT = "microsoft/swin-tiny-patch4-window7-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -SWIN_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/swin-tiny-patch4-window7-224", - # See all Swin models at https://huggingface.co/models?filter=swin -] +from ..deprecated._archive_maps import SWIN_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + # drop_path, SwinPatchEmbeddings, SwinPatchMerging and SwinDropPath are from the timm library. diff --git a/src/transformers/models/swin/modeling_tf_swin.py b/src/transformers/models/swin/modeling_tf_swin.py index 6632759f68..b9a1079340 100644 --- a/src/transformers/models/swin/modeling_tf_swin.py +++ b/src/transformers/models/swin/modeling_tf_swin.py @@ -61,10 +61,8 @@ _IMAGE_CLASS_CHECKPOINT = "microsoft/swin-tiny-patch4-window7-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -TF_SWIN_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/swin-tiny-patch4-window7-224", - # See all Swin models at https://huggingface.co/models?filter=swin -] +from ..deprecated._archive_maps import TF_SWIN_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + # drop_path, TFSwinPatchEmbeddings, TFSwinPatchMerging and TFSwinDropPath are tensorflow # implementations of PyTorch functionalities in the timm library. diff --git a/src/transformers/models/swin2sr/configuration_swin2sr.py b/src/transformers/models/swin2sr/configuration_swin2sr.py index 81c6af31e2..1858be52a5 100644 --- a/src/transformers/models/swin2sr/configuration_swin2sr.py +++ b/src/transformers/models/swin2sr/configuration_swin2sr.py @@ -20,11 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SWIN2SR_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "caidas/swin2sr-classicalsr-x2-64": ( - "https://huggingface.co/caidas/swin2sr-classicalsr-x2-64/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import SWIN2SR_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Swin2SRConfig(PretrainedConfig): diff --git a/src/transformers/models/swin2sr/modeling_swin2sr.py b/src/transformers/models/swin2sr/modeling_swin2sr.py index 86dbcbaa65..1ef628a144 100644 --- a/src/transformers/models/swin2sr/modeling_swin2sr.py +++ b/src/transformers/models/swin2sr/modeling_swin2sr.py @@ -49,10 +49,7 @@ _CHECKPOINT_FOR_DOC = "caidas/swin2SR-classical-sr-x2-64" _EXPECTED_OUTPUT_SHAPE = [1, 180, 488, 648] -SWIN2SR_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "caidas/swin2SR-classical-sr-x2-64", - # See all Swin2SR models at https://huggingface.co/models?filter=swin2sr -] +from ..deprecated._archive_maps import SWIN2SR_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/swinv2/configuration_swinv2.py b/src/transformers/models/swinv2/configuration_swinv2.py index 3c839e3f94..41acd48f53 100644 --- a/src/transformers/models/swinv2/configuration_swinv2.py +++ b/src/transformers/models/swinv2/configuration_swinv2.py @@ -21,11 +21,8 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -SWINV2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/swinv2-tiny-patch4-window8-256": ( - "https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import SWINV2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Swinv2Config(BackboneConfigMixin, PretrainedConfig): diff --git a/src/transformers/models/swinv2/modeling_swinv2.py b/src/transformers/models/swinv2/modeling_swinv2.py index 5dc3dd0de8..16c68ee63f 100644 --- a/src/transformers/models/swinv2/modeling_swinv2.py +++ b/src/transformers/models/swinv2/modeling_swinv2.py @@ -56,10 +56,7 @@ _IMAGE_CLASS_CHECKPOINT = "microsoft/swinv2-tiny-patch4-window8-256" _IMAGE_CLASS_EXPECTED_OUTPUT = "Egyptian cat" -SWINV2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/swinv2-tiny-patch4-window8-256", - # See all Swinv2 models at https://huggingface.co/models?filter=swinv2 -] +from ..deprecated._archive_maps import SWINV2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # drop_path, Swinv2PatchEmbeddings, Swinv2PatchMerging and Swinv2DropPath are from https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/swin_transformer_v2.py. diff --git a/src/transformers/models/switch_transformers/configuration_switch_transformers.py b/src/transformers/models/switch_transformers/configuration_switch_transformers.py index f90874af4d..fb53100317 100644 --- a/src/transformers/models/switch_transformers/configuration_switch_transformers.py +++ b/src/transformers/models/switch_transformers/configuration_switch_transformers.py @@ -19,9 +19,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -SWITCH_TRANSFORMERS_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/switch-base-8": "https://huggingface.co/google/switch-base-8/blob/main/config.json", -} + +from ..deprecated._archive_maps import SWITCH_TRANSFORMERS_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class SwitchTransformersConfig(PretrainedConfig): diff --git a/src/transformers/models/switch_transformers/modeling_switch_transformers.py b/src/transformers/models/switch_transformers/modeling_switch_transformers.py index 416549b7b7..375d94043e 100644 --- a/src/transformers/models/switch_transformers/modeling_switch_transformers.py +++ b/src/transformers/models/switch_transformers/modeling_switch_transformers.py @@ -54,18 +54,8 @@ _CHECKPOINT_FOR_DOC = "google/switch-base-8" # This dict contains ids and associated url # for the pretrained weights provided with the models #################################################### -SWITCH_TRANSFORMERS_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/switch-base-8", - "google/switch-base-16", - "google/switch-base-32", - "google/switch-base-64", - "google/switch-base-128", - "google/switch-base-256", - "google/switch-large-128", - "google/switch-xxl-128", - "google/switch-c-2048", - # See all SwitchTransformers models at https://huggingface.co/models?filter=switch_transformers -] + +from ..deprecated._archive_maps import SWITCH_TRANSFORMERS_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def router_z_loss_func(router_logits: torch.Tensor) -> float: diff --git a/src/transformers/models/t5/configuration_t5.py b/src/transformers/models/t5/configuration_t5.py index 6a1d3c529e..2633ee630d 100644 --- a/src/transformers/models/t5/configuration_t5.py +++ b/src/transformers/models/t5/configuration_t5.py @@ -22,13 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -T5_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google-t5/t5-small": "https://huggingface.co/google-t5/t5-small/resolve/main/config.json", - "google-t5/t5-base": "https://huggingface.co/google-t5/t5-base/resolve/main/config.json", - "google-t5/t5-large": "https://huggingface.co/google-t5/t5-large/resolve/main/config.json", - "google-t5/t5-3b": "https://huggingface.co/google-t5/t5-3b/resolve/main/config.json", - "google-t5/t5-11b": "https://huggingface.co/google-t5/t5-11b/resolve/main/config.json", -} + +from ..deprecated._archive_maps import T5_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class T5Config(PretrainedConfig): diff --git a/src/transformers/models/t5/modeling_t5.py b/src/transformers/models/t5/modeling_t5.py index a3febdd1aa..9c4ceec4c2 100644 --- a/src/transformers/models/t5/modeling_t5.py +++ b/src/transformers/models/t5/modeling_t5.py @@ -59,14 +59,8 @@ _CHECKPOINT_FOR_DOC = "google-t5/t5-small" # This dict contains ids and associated url # for the pretrained weights provided with the models #################################################### -T5_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google-t5/t5-small", - "google-t5/t5-base", - "google-t5/t5-large", - "google-t5/t5-3b", - "google-t5/t5-11b", - # See all T5 models at https://huggingface.co/models?filter=t5 -] + +from ..deprecated._archive_maps import T5_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 #################################################### diff --git a/src/transformers/models/t5/modeling_tf_t5.py b/src/transformers/models/t5/modeling_tf_t5.py index c809659477..8122c6a0ac 100644 --- a/src/transformers/models/t5/modeling_tf_t5.py +++ b/src/transformers/models/t5/modeling_tf_t5.py @@ -58,14 +58,9 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "T5Config" -TF_T5_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google-t5/t5-small", - "google-t5/t5-base", - "google-t5/t5-large", - "google-t5/t5-3b", - "google-t5/t5-11b", - # See all T5 models at https://huggingface.co/models?filter=t5 -] + +from ..deprecated._archive_maps import TF_T5_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + #################################################### # TF 2.0 Models are constructed using Keras imperative API by sub-classing diff --git a/src/transformers/models/t5/tokenization_t5.py b/src/transformers/models/t5/tokenization_t5.py index fba83ae920..7292808adc 100644 --- a/src/transformers/models/t5/tokenization_t5.py +++ b/src/transformers/models/t5/tokenization_t5.py @@ -37,25 +37,8 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google-t5/t5-small": "https://huggingface.co/google-t5/t5-small/resolve/main/spiece.model", - "google-t5/t5-base": "https://huggingface.co/google-t5/t5-base/resolve/main/spiece.model", - "google-t5/t5-large": "https://huggingface.co/google-t5/t5-large/resolve/main/spiece.model", - "google-t5/t5-3b": "https://huggingface.co/google-t5/t5-3b/resolve/main/spiece.model", - "google-t5/t5-11b": "https://huggingface.co/google-t5/t5-11b/resolve/main/spiece.model", - } -} - # TODO(PVP) - this should be removed in Transformers v5 -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google-t5/t5-small": 512, - "google-t5/t5-base": 512, - "google-t5/t5-large": 512, - "google-t5/t5-3b": 512, - "google-t5/t5-11b": 512, -} SPIECE_UNDERLINE = "▁" @@ -140,8 +123,6 @@ class T5Tokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/t5/tokenization_t5_fast.py b/src/transformers/models/t5/tokenization_t5_fast.py index bf1ef13cb5..e9f2033812 100644 --- a/src/transformers/models/t5/tokenization_t5_fast.py +++ b/src/transformers/models/t5/tokenization_t5_fast.py @@ -35,32 +35,8 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "google-t5/t5-small": "https://huggingface.co/google-t5/t5-small/resolve/main/spiece.model", - "google-t5/t5-base": "https://huggingface.co/google-t5/t5-base/resolve/main/spiece.model", - "google-t5/t5-large": "https://huggingface.co/google-t5/t5-large/resolve/main/spiece.model", - "google-t5/t5-3b": "https://huggingface.co/google-t5/t5-3b/resolve/main/spiece.model", - "google-t5/t5-11b": "https://huggingface.co/google-t5/t5-11b/resolve/main/spiece.model", - }, - "tokenizer_file": { - "google-t5/t5-small": "https://huggingface.co/google-t5/t5-small/resolve/main/tokenizer.json", - "google-t5/t5-base": "https://huggingface.co/google-t5/t5-base/resolve/main/tokenizer.json", - "google-t5/t5-large": "https://huggingface.co/google-t5/t5-large/resolve/main/tokenizer.json", - "google-t5/t5-3b": "https://huggingface.co/google-t5/t5-3b/resolve/main/tokenizer.json", - "google-t5/t5-11b": "https://huggingface.co/google-t5/t5-11b/resolve/main/tokenizer.json", - }, -} - # TODO(PVP) - this should be removed in Transformers v5 -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "google-t5/t5-small": 512, - "google-t5/t5-base": 512, - "google-t5/t5-large": 512, - "google-t5/t5-3b": 512, - "google-t5/t5-11b": 512, -} class T5TokenizerFast(PreTrainedTokenizerFast): @@ -103,8 +79,6 @@ class T5TokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = T5Tokenizer diff --git a/src/transformers/models/table_transformer/configuration_table_transformer.py b/src/transformers/models/table_transformer/configuration_table_transformer.py index 12b62ee973..9a2ff6bbab 100644 --- a/src/transformers/models/table_transformer/configuration_table_transformer.py +++ b/src/transformers/models/table_transformer/configuration_table_transformer.py @@ -26,11 +26,8 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -TABLE_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/table-transformer-detection": ( - "https://huggingface.co/microsoft/table-transformer-detection/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import TABLE_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class TableTransformerConfig(PretrainedConfig): diff --git a/src/transformers/models/table_transformer/modeling_table_transformer.py b/src/transformers/models/table_transformer/modeling_table_transformer.py index 7f86b0ab53..8e577a65a5 100644 --- a/src/transformers/models/table_transformer/modeling_table_transformer.py +++ b/src/transformers/models/table_transformer/modeling_table_transformer.py @@ -60,10 +60,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "TableTransformerConfig" _CHECKPOINT_FOR_DOC = "microsoft/table-transformer-detection" -TABLE_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/table-transformer-detection", - # See all Table Transformer models at https://huggingface.co/models?filter=table-transformer -] + +from ..deprecated._archive_maps import TABLE_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/tapas/configuration_tapas.py b/src/transformers/models/tapas/configuration_tapas.py index f466ab4254..b448afd002 100644 --- a/src/transformers/models/tapas/configuration_tapas.py +++ b/src/transformers/models/tapas/configuration_tapas.py @@ -24,22 +24,7 @@ Hyperparameters are taken from run_task_main.py and hparam_utils.py of the origi from ...configuration_utils import PretrainedConfig - - -TAPAS_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/tapas-base-finetuned-sqa": ( - "https://huggingface.co/google/tapas-base-finetuned-sqa/resolve/main/config.json" - ), - "google/tapas-base-finetuned-wtq": ( - "https://huggingface.co/google/tapas-base-finetuned-wtq/resolve/main/config.json" - ), - "google/tapas-base-finetuned-wikisql-supervised": ( - "https://huggingface.co/google/tapas-base-finetuned-wikisql-supervised/resolve/main/config.json" - ), - "google/tapas-base-finetuned-tabfact": ( - "https://huggingface.co/google/tapas-base-finetuned-tabfact/resolve/main/config.json" - ), -} +from ..deprecated._archive_maps import TAPAS_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class TapasConfig(PretrainedConfig): diff --git a/src/transformers/models/tapas/modeling_tapas.py b/src/transformers/models/tapas/modeling_tapas.py index 1e7a4372bb..e2ce847926 100644 --- a/src/transformers/models/tapas/modeling_tapas.py +++ b/src/transformers/models/tapas/modeling_tapas.py @@ -56,39 +56,9 @@ if not is_torch_greater_or_equal_than_1_12: _CONFIG_FOR_DOC = "TapasConfig" _CHECKPOINT_FOR_DOC = "google/tapas-base" -TAPAS_PRETRAINED_MODEL_ARCHIVE_LIST = [ - # large models - "google/tapas-large", - "google/tapas-large-finetuned-sqa", - "google/tapas-large-finetuned-wtq", - "google/tapas-large-finetuned-wikisql-supervised", - "google/tapas-large-finetuned-tabfact", - # base models - "google/tapas-base", - "google/tapas-base-finetuned-sqa", - "google/tapas-base-finetuned-wtq", - "google/tapas-base-finetuned-wikisql-supervised", - "google/tapas-base-finetuned-tabfact", - # small models - "google/tapas-small", - "google/tapas-small-finetuned-sqa", - "google/tapas-small-finetuned-wtq", - "google/tapas-small-finetuned-wikisql-supervised", - "google/tapas-small-finetuned-tabfact", - # mini models - "google/tapas-mini", - "google/tapas-mini-finetuned-sqa", - "google/tapas-mini-finetuned-wtq", - "google/tapas-mini-finetuned-wikisql-supervised", - "google/tapas-mini-finetuned-tabfact", - # tiny models - "google/tapas-tiny", - "google/tapas-tiny-finetuned-sqa", - "google/tapas-tiny-finetuned-wtq", - "google/tapas-tiny-finetuned-wikisql-supervised", - "google/tapas-tiny-finetuned-tabfact", - # See all TAPAS models at https://huggingface.co/models?filter=tapas -] + +from ..deprecated._archive_maps import TAPAS_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + EPSILON_ZERO_DIVISION = 1e-10 CLOSE_ENOUGH_TO_LOG_ZERO = -10000.0 diff --git a/src/transformers/models/tapas/modeling_tf_tapas.py b/src/transformers/models/tapas/modeling_tf_tapas.py index 79b1a9ebfc..6b2ed5fab4 100644 --- a/src/transformers/models/tapas/modeling_tf_tapas.py +++ b/src/transformers/models/tapas/modeling_tf_tapas.py @@ -75,39 +75,9 @@ if is_tensorflow_probability_available(): _CONFIG_FOR_DOC = "TapasConfig" _CHECKPOINT_FOR_DOC = "google/tapas-base" -TF_TAPAS_PRETRAINED_MODEL_ARCHIVE_LIST = [ - # large models - "google/tapas-large", - "google/tapas-large-finetuned-sqa", - "google/tapas-large-finetuned-wtq", - "google/tapas-large-finetuned-wikisql-supervised", - "google/tapas-large-finetuned-tabfact", - # base models - "google/tapas-base", - "google/tapas-base-finetuned-sqa", - "google/tapas-base-finetuned-wtq", - "google/tapas-base-finetuned-wikisql-supervised", - "google/tapas-base-finetuned-tabfact", - # small models - "google/tapas-small", - "google/tapas-small-finetuned-sqa", - "google/tapas-small-finetuned-wtq", - "google/tapas-small-finetuned-wikisql-supervised", - "google/tapas-small-finetuned-tabfact", - # mini models - "google/tapas-mini", - "google/tapas-mini-finetuned-sqa", - "google/tapas-mini-finetuned-wtq", - "google/tapas-mini-finetuned-wikisql-supervised", - "google/tapas-mini-finetuned-tabfact", - # tiny models - "google/tapas-tiny", - "google/tapas-tiny-finetuned-sqa", - "google/tapas-tiny-finetuned-wtq", - "google/tapas-tiny-finetuned-wikisql-supervised", - "google/tapas-tiny-finetuned-tabfact", - # See all TAPAS models at https://huggingface.co/models?filter=tapas -] + +from ..deprecated._archive_maps import TF_TAPAS_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + EPSILON_ZERO_DIVISION = 1e-10 CLOSE_ENOUGH_TO_LOG_ZERO = -10000.0 diff --git a/src/transformers/models/tapas/tokenization_tapas.py b/src/transformers/models/tapas/tokenization_tapas.py index 7ec1e68f21..124d48df24 100644 --- a/src/transformers/models/tapas/tokenization_tapas.py +++ b/src/transformers/models/tapas/tokenization_tapas.py @@ -48,92 +48,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - # large models - "google/tapas-large-finetuned-sqa": ( - "https://huggingface.co/google/tapas-large-finetuned-sqa/resolve/main/vocab.txt" - ), - "google/tapas-large-finetuned-wtq": ( - "https://huggingface.co/google/tapas-large-finetuned-wtq/resolve/main/vocab.txt" - ), - "google/tapas-large-finetuned-wikisql-supervised": ( - "https://huggingface.co/google/tapas-large-finetuned-wikisql-supervised/resolve/main/vocab.txt" - ), - "google/tapas-large-finetuned-tabfact": ( - "https://huggingface.co/google/tapas-large-finetuned-tabfact/resolve/main/vocab.txt" - ), - # base models - "google/tapas-base-finetuned-sqa": ( - "https://huggingface.co/google/tapas-base-finetuned-sqa/resolve/main/vocab.txt" - ), - "google/tapas-base-finetuned-wtq": ( - "https://huggingface.co/google/tapas-base-finetuned-wtq/resolve/main/vocab.txt" - ), - "google/tapas-base-finetuned-wikisql-supervised": ( - "https://huggingface.co/google/tapas-base-finetuned-wikisql-supervised/resolve/main/vocab.txt" - ), - "google/tapas-base-finetuned-tabfact": ( - "https://huggingface.co/google/tapas-base-finetuned-tabfact/resolve/main/vocab.txt" - ), - # medium models - "google/tapas-medium-finetuned-sqa": ( - "https://huggingface.co/google/tapas-medium-finetuned-sqa/resolve/main/vocab.txt" - ), - "google/tapas-medium-finetuned-wtq": ( - "https://huggingface.co/google/tapas-medium-finetuned-wtq/resolve/main/vocab.txt" - ), - "google/tapas-medium-finetuned-wikisql-supervised": ( - "https://huggingface.co/google/tapas-medium-finetuned-wikisql-supervised/resolve/main/vocab.txt" - ), - "google/tapas-medium-finetuned-tabfact": ( - "https://huggingface.co/google/tapas-medium-finetuned-tabfact/resolve/main/vocab.txt" - ), - # small models - "google/tapas-small-finetuned-sqa": ( - "https://huggingface.co/google/tapas-small-finetuned-sqa/resolve/main/vocab.txt" - ), - "google/tapas-small-finetuned-wtq": ( - "https://huggingface.co/google/tapas-small-finetuned-wtq/resolve/main/vocab.txt" - ), - "google/tapas-small-finetuned-wikisql-supervised": ( - "https://huggingface.co/google/tapas-small-finetuned-wikisql-supervised/resolve/main/vocab.txt" - ), - "google/tapas-small-finetuned-tabfact": ( - "https://huggingface.co/google/tapas-small-finetuned-tabfact/resolve/main/vocab.txt" - ), - # tiny models - "google/tapas-tiny-finetuned-sqa": ( - "https://huggingface.co/google/tapas-tiny-finetuned-sqa/resolve/main/vocab.txt" - ), - "google/tapas-tiny-finetuned-wtq": ( - "https://huggingface.co/google/tapas-tiny-finetuned-wtq/resolve/main/vocab.txt" - ), - "google/tapas-tiny-finetuned-wikisql-supervised": ( - "https://huggingface.co/google/tapas-tiny-finetuned-wikisql-supervised/resolve/main/vocab.txt" - ), - "google/tapas-tiny-finetuned-tabfact": ( - "https://huggingface.co/google/tapas-tiny-finetuned-tabfact/resolve/main/vocab.txt" - ), - # mini models - "google/tapas-mini-finetuned-sqa": ( - "https://huggingface.co/google/tapas-mini-finetuned-sqa/resolve/main/vocab.txt" - ), - "google/tapas-mini-finetuned-wtq": ( - "https://huggingface.co/google/tapas-mini-finetuned-wtq/resolve/main/vocab.txt" - ), - "google/tapas-mini-finetuned-wikisql-supervised": ( - "https://huggingface.co/google/tapas-mini-finetuned-wikisql-supervised/resolve/main/vocab.txt" - ), - "google/tapas-mini-finetuned-tabfact": ( - "https://huggingface.co/google/tapas-mini-finetuned-tabfact/resolve/main/vocab.txt" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {name: 512 for name in PRETRAINED_VOCAB_FILES_MAP.keys()} -PRETRAINED_INIT_CONFIGURATION = {name: {"do_lower_case": True} for name in PRETRAINED_VOCAB_FILES_MAP.keys()} - class TapasTruncationStrategy(ExplicitEnum): """ @@ -315,8 +229,6 @@ class TapasTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/time_series_transformer/configuration_time_series_transformer.py b/src/transformers/models/time_series_transformer/configuration_time_series_transformer.py index a2e31ba48d..f53f3aad1e 100644 --- a/src/transformers/models/time_series_transformer/configuration_time_series_transformer.py +++ b/src/transformers/models/time_series_transformer/configuration_time_series_transformer.py @@ -22,12 +22,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -TIME_SERIES_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "huggingface/time-series-transformer-tourism-monthly": ( - "https://huggingface.co/huggingface/time-series-transformer-tourism-monthly/resolve/main/config.json" - ), - # See all TimeSeriesTransformer models at https://huggingface.co/models?filter=time_series_transformer -} + +from ..deprecated._archive_maps import TIME_SERIES_TRANSFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class TimeSeriesTransformerConfig(PretrainedConfig): diff --git a/src/transformers/models/time_series_transformer/modeling_time_series_transformer.py b/src/transformers/models/time_series_transformer/modeling_time_series_transformer.py index b6e86735c6..ab46d3a92a 100644 --- a/src/transformers/models/time_series_transformer/modeling_time_series_transformer.py +++ b/src/transformers/models/time_series_transformer/modeling_time_series_transformer.py @@ -46,10 +46,7 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "TimeSeriesTransformerConfig" -TIME_SERIES_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "huggingface/time-series-transformer-tourism-monthly", - # See all TimeSeriesTransformer models at https://huggingface.co/models?filter=time_series_transformer -] +from ..deprecated._archive_maps import TIME_SERIES_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TimeSeriesFeatureEmbedder(nn.Module): diff --git a/src/transformers/models/timesformer/configuration_timesformer.py b/src/transformers/models/timesformer/configuration_timesformer.py index e910564fb1..79a86b7b5b 100644 --- a/src/transformers/models/timesformer/configuration_timesformer.py +++ b/src/transformers/models/timesformer/configuration_timesformer.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -TIMESFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/timesformer": "https://huggingface.co/facebook/timesformer/resolve/main/config.json", -} + +from ..deprecated._archive_maps import TIMESFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class TimesformerConfig(PretrainedConfig): diff --git a/src/transformers/models/timesformer/modeling_timesformer.py b/src/transformers/models/timesformer/modeling_timesformer.py index 73ce6bf773..3374472508 100644 --- a/src/transformers/models/timesformer/modeling_timesformer.py +++ b/src/transformers/models/timesformer/modeling_timesformer.py @@ -36,10 +36,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "TimesformerConfig" _CHECKPOINT_FOR_DOC = "facebook/timesformer" -TIMESFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/timesformer-base-finetuned-k400", - # See all TimeSformer models at https://huggingface.co/models?filter=timesformer -] + +from ..deprecated._archive_maps import TIMESFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Adapted from https://github.com/facebookresearch/TimeSformer/blob/a5ef29a7b7264baff199a30b3306ac27de901133/timesformer/models/vit.py#L155 diff --git a/src/transformers/models/trocr/configuration_trocr.py b/src/transformers/models/trocr/configuration_trocr.py index 4964ab27ac..ab282db97b 100644 --- a/src/transformers/models/trocr/configuration_trocr.py +++ b/src/transformers/models/trocr/configuration_trocr.py @@ -20,12 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -TROCR_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/trocr-base-handwritten": ( - "https://huggingface.co/microsoft/trocr-base-handwritten/resolve/main/config.json" - ), - # See all TrOCR models at https://huggingface.co/models?filter=trocr -} + +from ..deprecated._archive_maps import TROCR_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class TrOCRConfig(PretrainedConfig): diff --git a/src/transformers/models/trocr/modeling_trocr.py b/src/transformers/models/trocr/modeling_trocr.py index a21f6338ba..72ead7143a 100644 --- a/src/transformers/models/trocr/modeling_trocr.py +++ b/src/transformers/models/trocr/modeling_trocr.py @@ -37,10 +37,7 @@ _CONFIG_FOR_DOC = "TrOCRConfig" _CHECKPOINT_FOR_DOC = "microsoft/trocr-base-handwritten" -TROCR_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/trocr-base-handwritten", - # See all TrOCR models at https://huggingface.co/models?filter=trocr -] +from ..deprecated._archive_maps import TROCR_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.bart.modeling_bart.BartLearnedPositionalEmbedding with Bart->TrOCR diff --git a/src/transformers/models/tvlt/configuration_tvlt.py b/src/transformers/models/tvlt/configuration_tvlt.py index 1200eb470b..063befc9d7 100644 --- a/src/transformers/models/tvlt/configuration_tvlt.py +++ b/src/transformers/models/tvlt/configuration_tvlt.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -TVLT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "ZinengTang/tvlt-base": "https://huggingface.co/ZinengTang/tvlt-base/blob/main/config.json", -} + +from ..deprecated._archive_maps import TVLT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class TvltConfig(PretrainedConfig): diff --git a/src/transformers/models/tvlt/modeling_tvlt.py b/src/transformers/models/tvlt/modeling_tvlt.py index d2fe1040a3..f841c47ea4 100644 --- a/src/transformers/models/tvlt/modeling_tvlt.py +++ b/src/transformers/models/tvlt/modeling_tvlt.py @@ -45,10 +45,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "TvltConfig" _CHECKPOINT_FOR_DOC = "ZinengTang/tvlt-base" -TVLT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "ZinengTang/tvlt-base", - # See all TVLT models at https://huggingface.co/ZinengTang/tvlt-base -] + +from ..deprecated._archive_maps import TVLT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/tvp/configuration_tvp.py b/src/transformers/models/tvp/configuration_tvp.py index f39a0ab5df..85b7ac6a41 100644 --- a/src/transformers/models/tvp/configuration_tvp.py +++ b/src/transformers/models/tvp/configuration_tvp.py @@ -24,9 +24,7 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -TVP_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "Intel/tvp-base": "https://huggingface.co/Intel/tvp-base/resolve/main/config.json", -} +from ..deprecated._archive_maps import TVP_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class TvpConfig(PretrainedConfig): diff --git a/src/transformers/models/tvp/modeling_tvp.py b/src/transformers/models/tvp/modeling_tvp.py index 159b4926af..da8e85da74 100644 --- a/src/transformers/models/tvp/modeling_tvp.py +++ b/src/transformers/models/tvp/modeling_tvp.py @@ -34,11 +34,8 @@ from .configuration_tvp import TvpConfig logger = logging.get_logger(__name__) -TVP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "Intel/tvp-base", - "Intel/tvp-base-ANet", - # See all Tvp models at https://huggingface.co/models?filter=tvp -] + +from ..deprecated._archive_maps import TVP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/udop/configuration_udop.py b/src/transformers/models/udop/configuration_udop.py index 8647a7bae2..ba124d0aa1 100644 --- a/src/transformers/models/udop/configuration_udop.py +++ b/src/transformers/models/udop/configuration_udop.py @@ -21,9 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -UDOP_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/udop-large": "https://huggingface.co/microsoft/udop-large/resolve/main/config.json", -} + +from ..deprecated._archive_maps import UDOP_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class UdopConfig(PretrainedConfig): diff --git a/src/transformers/models/udop/modeling_udop.py b/src/transformers/models/udop/modeling_udop.py index 62192eea7f..6118600b5b 100644 --- a/src/transformers/models/udop/modeling_udop.py +++ b/src/transformers/models/udop/modeling_udop.py @@ -46,10 +46,8 @@ from ...utils import ( logger = logging.getLogger(__name__) -UDOP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/udop-large", - # See all UDOP models at https://huggingface.co/models?filter=udop -] + +from ..deprecated._archive_maps import UDOP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 _CONFIG_FOR_DOC = "UdopConfig" diff --git a/src/transformers/models/umt5/configuration_umt5.py b/src/transformers/models/umt5/configuration_umt5.py index ccd2392d72..9365717c28 100644 --- a/src/transformers/models/umt5/configuration_umt5.py +++ b/src/transformers/models/umt5/configuration_umt5.py @@ -22,11 +22,6 @@ from ...utils import logging logger = logging.get_logger(__name__) -UMT5_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/umt5-small": "https://huggingface.co/google/umt5-small/resolve/main/config.json", - # See all umt5 models at https://huggingface.co/models?filter=umt5 -} - class UMT5Config(PretrainedConfig): r""" diff --git a/src/transformers/models/unispeech/configuration_unispeech.py b/src/transformers/models/unispeech/configuration_unispeech.py index d723433903..25a003ae9f 100644 --- a/src/transformers/models/unispeech/configuration_unispeech.py +++ b/src/transformers/models/unispeech/configuration_unispeech.py @@ -23,12 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -UNISPEECH_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/unispeech-large-1500h-cv": ( - "https://huggingface.co/microsoft/unispeech-large-1500h-cv/resolve/main/config.json" - ), - # See all UniSpeech models at https://huggingface.co/models?filter=unispeech -} + +from ..deprecated._archive_maps import UNISPEECH_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class UniSpeechConfig(PretrainedConfig): diff --git a/src/transformers/models/unispeech/modeling_unispeech.py b/src/transformers/models/unispeech/modeling_unispeech.py index 11965bdb50..473bc7d4ff 100755 --- a/src/transformers/models/unispeech/modeling_unispeech.py +++ b/src/transformers/models/unispeech/modeling_unispeech.py @@ -56,11 +56,8 @@ _EXPECTED_OUTPUT_SHAPE = [1, 292, 1024] _CTC_EXPECTED_OUTPUT = "'mister quilter is the apposl of the midle classes and weare glad to welcom his gosepl'" _CTC_EXPECTED_LOSS = 17.17 -UNISPEECH_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/unispeech-large-1500h-cv", - "microsoft/unispeech-large-multi-lingual-1500h-cv", - # See all UniSpeech models at https://huggingface.co/models?filter=unispeech -] + +from ..deprecated._archive_maps import UNISPEECH_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/unispeech_sat/configuration_unispeech_sat.py b/src/transformers/models/unispeech_sat/configuration_unispeech_sat.py index fea89da119..1e6e40ad48 100644 --- a/src/transformers/models/unispeech_sat/configuration_unispeech_sat.py +++ b/src/transformers/models/unispeech_sat/configuration_unispeech_sat.py @@ -23,12 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -UNISPEECH_SAT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/unispeech-sat-base-100h-libri-ft": ( - "https://huggingface.co/microsoft/unispeech-sat-base-100h-libri-ft/resolve/main/config.json" - ), - # See all UniSpeechSat models at https://huggingface.co/models?filter=unispeech_sat -} + +from ..deprecated._archive_maps import UNISPEECH_SAT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class UniSpeechSatConfig(PretrainedConfig): diff --git a/src/transformers/models/unispeech_sat/modeling_unispeech_sat.py b/src/transformers/models/unispeech_sat/modeling_unispeech_sat.py index aec02db00f..f38da0d47f 100755 --- a/src/transformers/models/unispeech_sat/modeling_unispeech_sat.py +++ b/src/transformers/models/unispeech_sat/modeling_unispeech_sat.py @@ -72,9 +72,8 @@ _FRAME_EXPECTED_OUTPUT = [0, 0] _XVECTOR_CHECKPOINT = "microsoft/unispeech-sat-base-plus-sv" _XVECTOR_EXPECTED_OUTPUT = 0.97 -UNISPEECH_SAT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - # See all UniSpeechSat models at https://huggingface.co/models?filter=unispeech_sat -] + +from ..deprecated._archive_maps import UNISPEECH_SAT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/univnet/configuration_univnet.py b/src/transformers/models/univnet/configuration_univnet.py index c9dbbb5328..933db21d5a 100644 --- a/src/transformers/models/univnet/configuration_univnet.py +++ b/src/transformers/models/univnet/configuration_univnet.py @@ -20,9 +20,7 @@ from ...utils import logging logger = logging.get_logger(__name__) -UNIVNET_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "dg845/univnet-dev": "https://huggingface.co/dg845/univnet-dev/resolve/main/config.json", -} +from ..deprecated._archive_maps import UNIVNET_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class UnivNetConfig(PretrainedConfig): diff --git a/src/transformers/models/univnet/modeling_univnet.py b/src/transformers/models/univnet/modeling_univnet.py index dc9beddec5..c2551d7265 100644 --- a/src/transformers/models/univnet/modeling_univnet.py +++ b/src/transformers/models/univnet/modeling_univnet.py @@ -32,10 +32,8 @@ _CONFIG_FOR_DOC = "UnivNetConfig" _CHECKPOINT_FOR_DOC = "dg845/univnet-dev" -UNIVNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "dg845/univnet-dev", - # See all UnivNet models at https://huggingface.co/models?filter=univnet -] + +from ..deprecated._archive_maps import UNIVNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/upernet/modeling_upernet.py b/src/transformers/models/upernet/modeling_upernet.py index b889ae4eb4..2d5b4443e3 100644 --- a/src/transformers/models/upernet/modeling_upernet.py +++ b/src/transformers/models/upernet/modeling_upernet.py @@ -27,11 +27,6 @@ from ...utils.backbone_utils import load_backbone from .configuration_upernet import UperNetConfig -UPERNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "openmmlab/upernet-convnext-tiny", - # See all UperNet models at https://huggingface.co/models?filter=upernet -] - # General docstring _CONFIG_FOR_DOC = "UperNetConfig" diff --git a/src/transformers/models/videomae/configuration_videomae.py b/src/transformers/models/videomae/configuration_videomae.py index 1645b4985d..ba3d1d8273 100644 --- a/src/transformers/models/videomae/configuration_videomae.py +++ b/src/transformers/models/videomae/configuration_videomae.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -VIDEOMAE_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "MCG-NJU/videomae-base": "https://huggingface.co/MCG-NJU/videomae-base/resolve/main/config.json", -} + +from ..deprecated._archive_maps import VIDEOMAE_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class VideoMAEConfig(PretrainedConfig): diff --git a/src/transformers/models/videomae/modeling_videomae.py b/src/transformers/models/videomae/modeling_videomae.py index aac69b6c53..6beb18bb77 100644 --- a/src/transformers/models/videomae/modeling_videomae.py +++ b/src/transformers/models/videomae/modeling_videomae.py @@ -47,10 +47,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "VideoMAEConfig" _CHECKPOINT_FOR_DOC = "MCG-NJU/videomae-base" -VIDEOMAE_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "MCG-NJU/videomae-base", - # See all VideoMAE models at https://huggingface.co/models?filter=videomae -] + +from ..deprecated._archive_maps import VIDEOMAE_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/vilt/configuration_vilt.py b/src/transformers/models/vilt/configuration_vilt.py index bd419285e9..0ad4bde694 100644 --- a/src/transformers/models/vilt/configuration_vilt.py +++ b/src/transformers/models/vilt/configuration_vilt.py @@ -20,9 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -VILT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "dandelin/vilt-b32-mlm": "https://huggingface.co/dandelin/vilt-b32-mlm/blob/main/config.json" -} + +from ..deprecated._archive_maps import VILT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ViltConfig(PretrainedConfig): diff --git a/src/transformers/models/vilt/modeling_vilt.py b/src/transformers/models/vilt/modeling_vilt.py index 9ffa9fff01..5545b881bd 100755 --- a/src/transformers/models/vilt/modeling_vilt.py +++ b/src/transformers/models/vilt/modeling_vilt.py @@ -48,10 +48,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "ViltConfig" _CHECKPOINT_FOR_DOC = "dandelin/vilt-b32-mlm" -VILT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "dandelin/vilt-b32-mlm", - # See all ViLT models at https://huggingface.co/models?filter=vilt -] + +from ..deprecated._archive_maps import VILT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/vipllava/configuration_vipllava.py b/src/transformers/models/vipllava/configuration_vipllava.py index bba02bea78..d57f417949 100644 --- a/src/transformers/models/vipllava/configuration_vipllava.py +++ b/src/transformers/models/vipllava/configuration_vipllava.py @@ -22,9 +22,8 @@ from ..auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -VIPLLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "ybelkada/vip-llava-7b-hf": "https://huggingface.co/llava-hf/vip-llava-7b-hf/resolve/main/config.json", -} + +from ..deprecated._archive_maps import VIPLLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class VipLlavaConfig(PretrainedConfig): diff --git a/src/transformers/models/vipllava/modeling_vipllava.py b/src/transformers/models/vipllava/modeling_vipllava.py index 34582a912a..dda9549a4f 100644 --- a/src/transformers/models/vipllava/modeling_vipllava.py +++ b/src/transformers/models/vipllava/modeling_vipllava.py @@ -38,10 +38,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "VipLlavaConfig" -VIPLLAVA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "llava-hf/vip-llava-7b-hf", - # See all VipLlava models at https://huggingface.co/models?filter=vipllava -] + +from ..deprecated._archive_maps import VIPLLAVA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/visual_bert/configuration_visual_bert.py b/src/transformers/models/visual_bert/configuration_visual_bert.py index 9b675ff602..2edf5466e3 100644 --- a/src/transformers/models/visual_bert/configuration_visual_bert.py +++ b/src/transformers/models/visual_bert/configuration_visual_bert.py @@ -20,24 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -VISUAL_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "uclanlp/visualbert-vqa": "https://huggingface.co/uclanlp/visualbert-vqa/resolve/main/config.json", - "uclanlp/visualbert-vqa-pre": "https://huggingface.co/uclanlp/visualbert-vqa-pre/resolve/main/config.json", - "uclanlp/visualbert-vqa-coco-pre": ( - "https://huggingface.co/uclanlp/visualbert-vqa-coco-pre/resolve/main/config.json" - ), - "uclanlp/visualbert-vcr": "https://huggingface.co/uclanlp/visualbert-vcr/resolve/main/config.json", - "uclanlp/visualbert-vcr-pre": "https://huggingface.co/uclanlp/visualbert-vcr-pre/resolve/main/config.json", - "uclanlp/visualbert-vcr-coco-pre": ( - "https://huggingface.co/uclanlp/visualbert-vcr-coco-pre/resolve/main/config.json" - ), - "uclanlp/visualbert-nlvr2": "https://huggingface.co/uclanlp/visualbert-nlvr2/resolve/main/config.json", - "uclanlp/visualbert-nlvr2-pre": "https://huggingface.co/uclanlp/visualbert-nlvr2-pre/resolve/main/config.json", - "uclanlp/visualbert-nlvr2-coco-pre": ( - "https://huggingface.co/uclanlp/visualbert-nlvr2-coco-pre/resolve/main/config.json" - ), - # See all VisualBERT models at https://huggingface.co/models?filter=visual_bert -} + +from ..deprecated._archive_maps import VISUAL_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class VisualBertConfig(PretrainedConfig): diff --git a/src/transformers/models/visual_bert/modeling_visual_bert.py b/src/transformers/models/visual_bert/modeling_visual_bert.py index 4af7696fc3..07c8b7a4b5 100755 --- a/src/transformers/models/visual_bert/modeling_visual_bert.py +++ b/src/transformers/models/visual_bert/modeling_visual_bert.py @@ -48,18 +48,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "VisualBertConfig" _CHECKPOINT_FOR_DOC = "uclanlp/visualbert-vqa-coco-pre" -VISUAL_BERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "uclanlp/visualbert-vqa", - "uclanlp/visualbert-vqa-pre", - "uclanlp/visualbert-vqa-coco-pre", - "uclanlp/visualbert-vcr", - "uclanlp/visualbert-vcr-pre", - "uclanlp/visualbert-vcr-coco-pre", - "uclanlp/visualbert-nlvr2", - "uclanlp/visualbert-nlvr2-pre", - "uclanlp/visualbert-nlvr2-coco-pre", - # See all VisualBERT models at https://huggingface.co/models?filter=visual_bert -] + +from ..deprecated._archive_maps import VISUAL_BERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class VisualBertEmbeddings(nn.Module): diff --git a/src/transformers/models/vit/configuration_vit.py b/src/transformers/models/vit/configuration_vit.py index 5eda0385c3..4b505b5d9c 100644 --- a/src/transformers/models/vit/configuration_vit.py +++ b/src/transformers/models/vit/configuration_vit.py @@ -26,10 +26,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -VIT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/vit-base-patch16-224": "https://huggingface.co/vit-base-patch16-224/resolve/main/config.json", - # See all ViT models at https://huggingface.co/models?filter=vit -} + +from ..deprecated._archive_maps import VIT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ViTConfig(PretrainedConfig): diff --git a/src/transformers/models/vit/modeling_vit.py b/src/transformers/models/vit/modeling_vit.py index 734ccf6a9e..4ccdd1deaf 100644 --- a/src/transformers/models/vit/modeling_vit.py +++ b/src/transformers/models/vit/modeling_vit.py @@ -57,10 +57,7 @@ _IMAGE_CLASS_CHECKPOINT = "google/vit-base-patch16-224" _IMAGE_CLASS_EXPECTED_OUTPUT = "Egyptian cat" -VIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/vit-base-patch16-224", - # See all ViT models at https://huggingface.co/models?filter=vit -] +from ..deprecated._archive_maps import VIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class ViTEmbeddings(nn.Module): diff --git a/src/transformers/models/vit_hybrid/configuration_vit_hybrid.py b/src/transformers/models/vit_hybrid/configuration_vit_hybrid.py index 2875e62dd4..8a8a808ec6 100644 --- a/src/transformers/models/vit_hybrid/configuration_vit_hybrid.py +++ b/src/transformers/models/vit_hybrid/configuration_vit_hybrid.py @@ -23,10 +23,8 @@ from ..bit import BitConfig logger = logging.get_logger(__name__) -VIT_HYBRID_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/vit-hybrid-base-bit-384": "https://huggingface.co/vit-hybrid-base-bit-384/resolve/main/config.json", - # See all ViT hybrid models at https://huggingface.co/models?filter=vit -} + +from ..deprecated._archive_maps import VIT_HYBRID_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ViTHybridConfig(PretrainedConfig): diff --git a/src/transformers/models/vit_hybrid/modeling_vit_hybrid.py b/src/transformers/models/vit_hybrid/modeling_vit_hybrid.py index 3dc715af51..6fe9f8d2b6 100644 --- a/src/transformers/models/vit_hybrid/modeling_vit_hybrid.py +++ b/src/transformers/models/vit_hybrid/modeling_vit_hybrid.py @@ -47,10 +47,7 @@ _IMAGE_CLASS_CHECKPOINT = "google/vit-hybrid-base-bit-384" _IMAGE_CLASS_EXPECTED_OUTPUT = "tabby, tabby cat" -VIT_HYBRID_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/vit-hybrid-base-bit-384", - # See all ViT hybrid models at https://huggingface.co/models?filter=vit-hybrid -] +from ..deprecated._archive_maps import VIT_HYBRID_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class ViTHybridEmbeddings(nn.Module): diff --git a/src/transformers/models/vit_mae/configuration_vit_mae.py b/src/transformers/models/vit_mae/configuration_vit_mae.py index 42697f382c..c5866ef40b 100644 --- a/src/transformers/models/vit_mae/configuration_vit_mae.py +++ b/src/transformers/models/vit_mae/configuration_vit_mae.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -VIT_MAE_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/vit-mae-base": "https://huggingface.co/facebook/vit-mae-base/resolve/main/config.json", - # See all ViT MAE models at https://huggingface.co/models?filter=vit-mae -} + +from ..deprecated._archive_maps import VIT_MAE_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ViTMAEConfig(PretrainedConfig): diff --git a/src/transformers/models/vit_mae/modeling_vit_mae.py b/src/transformers/models/vit_mae/modeling_vit_mae.py index 910353217f..bfbe59ea90 100755 --- a/src/transformers/models/vit_mae/modeling_vit_mae.py +++ b/src/transformers/models/vit_mae/modeling_vit_mae.py @@ -45,10 +45,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "ViTMAEConfig" _CHECKPOINT_FOR_DOC = "facebook/vit-mae-base" -VIT_MAE_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/vit-mae-base", - # See all ViTMAE models at https://huggingface.co/models?filter=vit_mae -] + +from ..deprecated._archive_maps import VIT_MAE_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/vit_msn/configuration_vit_msn.py b/src/transformers/models/vit_msn/configuration_vit_msn.py index 4ee05e3c39..2964343466 100644 --- a/src/transformers/models/vit_msn/configuration_vit_msn.py +++ b/src/transformers/models/vit_msn/configuration_vit_msn.py @@ -21,10 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -VIT_MSN_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "sayakpaul/vit-msn-base": "https://huggingface.co/sayakpaul/vit-msn-base/resolve/main/config.json", - # See all ViT MSN models at https://huggingface.co/models?filter=vit_msn -} + +from ..deprecated._archive_maps import VIT_MSN_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class ViTMSNConfig(PretrainedConfig): diff --git a/src/transformers/models/vit_msn/modeling_vit_msn.py b/src/transformers/models/vit_msn/modeling_vit_msn.py index 6b10eb9f24..45d1779b5f 100644 --- a/src/transformers/models/vit_msn/modeling_vit_msn.py +++ b/src/transformers/models/vit_msn/modeling_vit_msn.py @@ -37,10 +37,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "ViTMSNConfig" _CHECKPOINT_FOR_DOC = "facebook/vit-msn-small" -VIT_MSN_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/vit-msn-small", - # See all ViTMSN models at https://huggingface.co/models?filter=vit_msn -] + +from ..deprecated._archive_maps import VIT_MSN_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class ViTMSNEmbeddings(nn.Module): diff --git a/src/transformers/models/vitdet/configuration_vitdet.py b/src/transformers/models/vitdet/configuration_vitdet.py index 2b1f37e311..2a7973dde8 100644 --- a/src/transformers/models/vitdet/configuration_vitdet.py +++ b/src/transformers/models/vitdet/configuration_vitdet.py @@ -22,9 +22,8 @@ from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_feat logger = logging.get_logger(__name__) -VITDET_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/vit-det-base": "https://huggingface.co/facebook/vit-det-base/resolve/main/config.json", -} + +from ..deprecated._archive_maps import VITDET_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class VitDetConfig(BackboneConfigMixin, PretrainedConfig): diff --git a/src/transformers/models/vitdet/modeling_vitdet.py b/src/transformers/models/vitdet/modeling_vitdet.py index 7af69d2869..5d12b0b585 100644 --- a/src/transformers/models/vitdet/modeling_vitdet.py +++ b/src/transformers/models/vitdet/modeling_vitdet.py @@ -42,10 +42,7 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "VitDetConfig" -VITDET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/vit-det-base", - # See all ViTDet models at https://huggingface.co/models?filter=vitdet -] +from ..deprecated._archive_maps import VITDET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class VitDetEmbeddings(nn.Module): diff --git a/src/transformers/models/vitmatte/configuration_vitmatte.py b/src/transformers/models/vitmatte/configuration_vitmatte.py index 13f9942c9e..275640d1d0 100644 --- a/src/transformers/models/vitmatte/configuration_vitmatte.py +++ b/src/transformers/models/vitmatte/configuration_vitmatte.py @@ -24,9 +24,8 @@ from ..auto.configuration_auto import CONFIG_MAPPING logger = logging.get_logger(__name__) -VITMATTE_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "hustvl/vitmatte-small-composition-1k": "https://huggingface.co/hustvl/vitmatte-small-composition-1k/resolve/main/config.json", -} + +from ..deprecated._archive_maps import VITMATTE_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class VitMatteConfig(PretrainedConfig): diff --git a/src/transformers/models/vitmatte/modeling_vitmatte.py b/src/transformers/models/vitmatte/modeling_vitmatte.py index 465f5da6ad..f371c60860 100644 --- a/src/transformers/models/vitmatte/modeling_vitmatte.py +++ b/src/transformers/models/vitmatte/modeling_vitmatte.py @@ -28,15 +28,10 @@ from ...utils import ( replace_return_docstrings, ) from ...utils.backbone_utils import load_backbone +from ..deprecated._archive_maps import VITMATTE_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 from .configuration_vitmatte import VitMatteConfig -VITMATTE_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "hustvl/vitmatte-small-composition-1k", - # See all VitMatte models at https://huggingface.co/models?filter=vitmatte -] - - # General docstring _CONFIG_FOR_DOC = "VitMatteConfig" diff --git a/src/transformers/models/vits/configuration_vits.py b/src/transformers/models/vits/configuration_vits.py index 72f69e75a5..5538e53d4b 100644 --- a/src/transformers/models/vits/configuration_vits.py +++ b/src/transformers/models/vits/configuration_vits.py @@ -21,9 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -VITS_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/mms-tts-eng": "https://huggingface.co/facebook/mms-tts-eng/resolve/main/config.json", -} + +from ..deprecated._archive_maps import VITS_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class VitsConfig(PretrainedConfig): diff --git a/src/transformers/models/vits/modeling_vits.py b/src/transformers/models/vits/modeling_vits.py index 18309f3a10..df8cf9350b 100644 --- a/src/transformers/models/vits/modeling_vits.py +++ b/src/transformers/models/vits/modeling_vits.py @@ -42,11 +42,7 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "VitsConfig" -VITS_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/mms-tts-eng", - # See all VITS models at https://huggingface.co/models?filter=vits - # and all MMS models at https://huggingface.co/models?sort=trending&search=facebook%2Fmms-tts -] +from ..deprecated._archive_maps import VITS_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/vits/tokenization_vits.py b/src/transformers/models/vits/tokenization_vits.py index 0563be326c..c8b115c176 100644 --- a/src/transformers/models/vits/tokenization_vits.py +++ b/src/transformers/models/vits/tokenization_vits.py @@ -32,17 +32,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/mms-tts-eng": "https://huggingface.co/facebook/mms-tts-eng/resolve/main/vocab.json", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - # This model does not have a maximum input length. - "facebook/mms-tts-eng": 4096, -} - def has_non_roman_characters(input_string): # Find any character outside the ASCII range @@ -77,8 +66,6 @@ class VitsTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/vivit/configuration_vivit.py b/src/transformers/models/vivit/configuration_vivit.py index 0e367fcb9b..28ac13496f 100644 --- a/src/transformers/models/vivit/configuration_vivit.py +++ b/src/transformers/models/vivit/configuration_vivit.py @@ -20,12 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -VIVIT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "google/vivit-b-16x2-kinetics400": ( - "https://huggingface.co/google/vivit-b-16x2-kinetics400/resolve/main/config.json" - ), - # See all Vivit models at https://huggingface.co/models?filter=vivit -} + +from ..deprecated._archive_maps import VIVIT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class VivitConfig(PretrainedConfig): diff --git a/src/transformers/models/vivit/modeling_vivit.py b/src/transformers/models/vivit/modeling_vivit.py index a9c3f5fd65..08efb85e1f 100755 --- a/src/transformers/models/vivit/modeling_vivit.py +++ b/src/transformers/models/vivit/modeling_vivit.py @@ -36,10 +36,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "google/vivit-b-16x2-kinetics400" _CONFIG_FOR_DOC = "VivitConfig" -VIVIT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "google/vivit-b-16x2-kinetics400", - # See all Vivit models at https://huggingface.co/models?filter=vivit -] + +from ..deprecated._archive_maps import VIVIT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class VivitTubeletEmbeddings(nn.Module): diff --git a/src/transformers/models/wav2vec2/configuration_wav2vec2.py b/src/transformers/models/wav2vec2/configuration_wav2vec2.py index fadf1b6b6a..252674bb3d 100644 --- a/src/transformers/models/wav2vec2/configuration_wav2vec2.py +++ b/src/transformers/models/wav2vec2/configuration_wav2vec2.py @@ -23,10 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -WAV_2_VEC_2_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/wav2vec2-base-960h": "https://huggingface.co/facebook/wav2vec2-base-960h/resolve/main/config.json", - # See all Wav2Vec2 models at https://huggingface.co/models?filter=wav2vec2 -} + +from ..deprecated._archive_maps import WAV_2_VEC_2_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Wav2Vec2Config(PretrainedConfig): diff --git a/src/transformers/models/wav2vec2/modeling_tf_wav2vec2.py b/src/transformers/models/wav2vec2/modeling_tf_wav2vec2.py index e6a6cb4a75..a8e39b0754 100644 --- a/src/transformers/models/wav2vec2/modeling_tf_wav2vec2.py +++ b/src/transformers/models/wav2vec2/modeling_tf_wav2vec2.py @@ -52,13 +52,9 @@ _HIDDEN_STATES_START_POSITION = 2 _CHECKPOINT_FOR_DOC = "facebook/wav2vec2-base-960h" _CONFIG_FOR_DOC = "Wav2Vec2Config" -TF_WAV_2_VEC_2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/wav2vec2-base-960h", - "facebook/wav2vec2-large-960h", - "facebook/wav2vec2-large-960h-lv60", - "facebook/wav2vec2-large-960h-lv60-self", - # See all Wav2Vec2 models at https://huggingface.co/models?filter=wav2vec2 -] + +from ..deprecated._archive_maps import TF_WAV_2_VEC_2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + LARGE_NEGATIVE = -1e8 diff --git a/src/transformers/models/wav2vec2/modeling_wav2vec2.py b/src/transformers/models/wav2vec2/modeling_wav2vec2.py index 082dd18dce..d40af1739c 100755 --- a/src/transformers/models/wav2vec2/modeling_wav2vec2.py +++ b/src/transformers/models/wav2vec2/modeling_wav2vec2.py @@ -89,13 +89,7 @@ _XVECTOR_CHECKPOINT = "anton-l/wav2vec2-base-superb-sv" _XVECTOR_EXPECTED_OUTPUT = 0.98 -WAV_2_VEC_2_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/wav2vec2-base-960h", - "facebook/wav2vec2-large-960h", - "facebook/wav2vec2-large-960h-lv60", - "facebook/wav2vec2-large-960h-lv60-self", - # See all Wav2Vec2 models at https://huggingface.co/models?filter=wav2vec2 -] +from ..deprecated._archive_maps import WAV_2_VEC_2_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/wav2vec2/tokenization_wav2vec2.py b/src/transformers/models/wav2vec2/tokenization_wav2vec2.py index 00bb00fba3..42b1aa3063 100644 --- a/src/transformers/models/wav2vec2/tokenization_wav2vec2.py +++ b/src/transformers/models/wav2vec2/tokenization_wav2vec2.py @@ -16,7 +16,6 @@ import json import os -import sys import warnings from dataclasses import dataclass from itertools import groupby @@ -56,19 +55,8 @@ VOCAB_FILES_NAMES = { "tokenizer_config_file": "tokenizer_config.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/wav2vec2-base-960h": "https://huggingface.co/facebook/wav2vec2-base-960h/resolve/main/vocab.json", - }, - "tokenizer_config_file": { - "facebook/wav2vec2-base-960h": ( - "https://huggingface.co/facebook/wav2vec2-base-960h/resolve/main/tokenizer_config.json" - ), - }, -} # Wav2Vec2 has no max input length -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"facebook/wav2vec2-base-960h": sys.maxsize} WAV2VEC2_KWARGS_DOCSTRING = r""" padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`): @@ -157,8 +145,6 @@ class Wav2Vec2CTCTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/wav2vec2_bert/configuration_wav2vec2_bert.py b/src/transformers/models/wav2vec2_bert/configuration_wav2vec2_bert.py index 621aede3e3..4183c1e4c0 100644 --- a/src/transformers/models/wav2vec2_bert/configuration_wav2vec2_bert.py +++ b/src/transformers/models/wav2vec2_bert/configuration_wav2vec2_bert.py @@ -21,9 +21,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -WAV2VEC2_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/w2v-bert-2.0": "https://huggingface.co/facebook/w2v-bert-2.0/resolve/main/config.json", -} + +from ..deprecated._archive_maps import WAV2VEC2_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Wav2Vec2BertConfig(PretrainedConfig): diff --git a/src/transformers/models/wav2vec2_bert/modeling_wav2vec2_bert.py b/src/transformers/models/wav2vec2_bert/modeling_wav2vec2_bert.py index 858f270a87..6519faa931 100644 --- a/src/transformers/models/wav2vec2_bert/modeling_wav2vec2_bert.py +++ b/src/transformers/models/wav2vec2_bert/modeling_wav2vec2_bert.py @@ -64,10 +64,7 @@ _CTC_EXPECTED_OUTPUT = "'mr quilter is the apostle of the middle classes and we _CTC_EXPECTED_LOSS = 17.04 -WAV2VEC2_BERT_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/w2v-bert-2.0", - # See all Wav2Vec2-BERT models at https://huggingface.co/models?filter=wav2vec2-bert -] +from ..deprecated._archive_maps import WAV2VEC2_BERT_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2._compute_new_attention_mask diff --git a/src/transformers/models/wav2vec2_conformer/configuration_wav2vec2_conformer.py b/src/transformers/models/wav2vec2_conformer/configuration_wav2vec2_conformer.py index 9983f01bbf..1b99edcece 100644 --- a/src/transformers/models/wav2vec2_conformer/configuration_wav2vec2_conformer.py +++ b/src/transformers/models/wav2vec2_conformer/configuration_wav2vec2_conformer.py @@ -23,11 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -WAV2VEC2_CONFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/wav2vec2-conformer-rel-pos-large": ( - "https://huggingface.co/facebook/wav2vec2-conformer-rel-pos-large/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import WAV2VEC2_CONFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class Wav2Vec2ConformerConfig(PretrainedConfig): diff --git a/src/transformers/models/wav2vec2_conformer/modeling_wav2vec2_conformer.py b/src/transformers/models/wav2vec2_conformer/modeling_wav2vec2_conformer.py index 3ba2ff7bb3..8354a88a51 100644 --- a/src/transformers/models/wav2vec2_conformer/modeling_wav2vec2_conformer.py +++ b/src/transformers/models/wav2vec2_conformer/modeling_wav2vec2_conformer.py @@ -65,10 +65,7 @@ _CTC_EXPECTED_OUTPUT = "'MISTER QUILTER IS THE APOSTLE OF THE MIDDLE CLASSES AND _CTC_EXPECTED_LOSS = 64.21 -WAV2VEC2_CONFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/wav2vec2-conformer-rel-pos-large", - # See all Wav2Vec2Conformer models at https://huggingface.co/models?filter=wav2vec2-conformer -] +from ..deprecated._archive_maps import WAV2VEC2_CONFORMER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/wav2vec2_phoneme/tokenization_wav2vec2_phoneme.py b/src/transformers/models/wav2vec2_phoneme/tokenization_wav2vec2_phoneme.py index c10b679409..8809e2c2e8 100644 --- a/src/transformers/models/wav2vec2_phoneme/tokenization_wav2vec2_phoneme.py +++ b/src/transformers/models/wav2vec2_phoneme/tokenization_wav2vec2_phoneme.py @@ -16,7 +16,6 @@ import json import os -import sys from dataclasses import dataclass from itertools import groupby from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union @@ -53,21 +52,8 @@ VOCAB_FILES_NAMES = { "tokenizer_config_file": "tokenizer_config.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/wav2vec2-lv-60-espeak-cv-ft": ( - "https://huggingface.co/facebook/wav2vec2-lv-60-espeak-cv-ft/resolve/main/vocab.json" - ), - }, - "tokenizer_config_file": { - "facebook/wav2vec2-lv-60-espeak-cv-ft": ( - "https://huggingface.co/facebook/wav2vec2-lv-60-espeak-cv-ft/resolve/main/tokenizer_config.json" - ), - }, -} # Wav2Vec2Phoneme has no max input length -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"facebook/wav2vec2-lv-60-espeak-cv-ft": sys.maxsize} ListOfDict = List[Dict[str, Union[int, str]]] @@ -125,8 +111,6 @@ class Wav2Vec2PhonemeCTCTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/wavlm/configuration_wavlm.py b/src/transformers/models/wavlm/configuration_wavlm.py index 589741c520..c0f5f90fe3 100644 --- a/src/transformers/models/wavlm/configuration_wavlm.py +++ b/src/transformers/models/wavlm/configuration_wavlm.py @@ -23,10 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -WAVLM_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/wavlm-base": "https://huggingface.co/microsoft/wavlm-base/resolve/main/config.json", - # See all WavLM models at https://huggingface.co/models?filter=wavlm -} + +from ..deprecated._archive_maps import WAVLM_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class WavLMConfig(PretrainedConfig): diff --git a/src/transformers/models/wavlm/modeling_wavlm.py b/src/transformers/models/wavlm/modeling_wavlm.py index bfe0ced2b5..f46fc1ef4f 100755 --- a/src/transformers/models/wavlm/modeling_wavlm.py +++ b/src/transformers/models/wavlm/modeling_wavlm.py @@ -70,12 +70,8 @@ _FRAME_EXPECTED_OUTPUT = [0, 0] _XVECTOR_CHECKPOINT = "microsoft/wavlm-base-plus-sv" _XVECTOR_EXPECTED_OUTPUT = 0.97 -WAVLM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/wavlm-base", - "microsoft/wavlm-base-plus", - "microsoft/wavlm-large", - # See all WavLM models at https://huggingface.co/models?filter=wavlm -] + +from ..deprecated._archive_maps import WAVLM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.wav2vec2.modeling_wav2vec2._compute_mask_indices diff --git a/src/transformers/models/whisper/configuration_whisper.py b/src/transformers/models/whisper/configuration_whisper.py index 5af3242141..ec9c64df1b 100644 --- a/src/transformers/models/whisper/configuration_whisper.py +++ b/src/transformers/models/whisper/configuration_whisper.py @@ -29,9 +29,9 @@ if TYPE_CHECKING: logger = logging.get_logger(__name__) -WHISPER_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "openai/whisper-base": "https://huggingface.co/openai/whisper-base/resolve/main/config.json", -} + +from ..deprecated._archive_maps import WHISPER_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 + # fmt: off NON_SPEECH_TOKENS = [ diff --git a/src/transformers/models/whisper/modeling_tf_whisper.py b/src/transformers/models/whisper/modeling_tf_whisper.py index e5d59c00d3..4d5dda71e8 100644 --- a/src/transformers/models/whisper/modeling_tf_whisper.py +++ b/src/transformers/models/whisper/modeling_tf_whisper.py @@ -52,10 +52,8 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "WhisperConfig" -TF_WHISPER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "openai/whisper-base", - # See all Whisper models at https://huggingface.co/models?filter=whisper -] +from ..deprecated._archive_maps import TF_WHISPER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + LARGE_NEGATIVE = -1e8 diff --git a/src/transformers/models/whisper/modeling_whisper.py b/src/transformers/models/whisper/modeling_whisper.py index 45f2d9fc5c..ab8fe750a5 100644 --- a/src/transformers/models/whisper/modeling_whisper.py +++ b/src/transformers/models/whisper/modeling_whisper.py @@ -59,10 +59,7 @@ _CONFIG_FOR_DOC = "WhisperConfig" _CHECKPOINT_FOR_DOC = "openai/whisper-tiny" -WHISPER_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "openai/whisper-base", - # See all Whisper models at https://huggingface.co/models?filter=whisper -] +from ..deprecated._archive_maps import WHISPER_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.llama.modeling_llama._get_unpad_data diff --git a/src/transformers/models/whisper/tokenization_whisper.py b/src/transformers/models/whisper/tokenization_whisper.py index f853c60e26..25e80d477f 100644 --- a/src/transformers/models/whisper/tokenization_whisper.py +++ b/src/transformers/models/whisper/tokenization_whisper.py @@ -34,15 +34,6 @@ VOCAB_FILES_NAMES = { "normalizer_file": "normalizer.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "openai/whisper-base": "https://huggingface.co/openai/whisper-base/resolve/main/vocab.json", - }, - "merges_file": {"openai/whisper-base": "https://huggingface.co/openai/whisper-base/resolve/main/merges_file.txt"}, - "normalizer_file": { - "openai/whisper-base": "https://huggingface.co/openai/whisper-base/resolve/main/normalizer.json" - }, -} MAX_MODEL_INPUT_SIZES = { "openai/whisper-base": 448, @@ -257,8 +248,6 @@ class WhisperTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = MAX_MODEL_INPUT_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/whisper/tokenization_whisper_fast.py b/src/transformers/models/whisper/tokenization_whisper_fast.py index dc5a3e0dc1..0463d521d5 100644 --- a/src/transformers/models/whisper/tokenization_whisper_fast.py +++ b/src/transformers/models/whisper/tokenization_whisper_fast.py @@ -39,54 +39,6 @@ VOCAB_FILES_NAMES = { "normalizer_file": "normalizer.json", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "openai/whisper-tiny": "https://huggingface.co/openai/whisper-tiny/resolve/main/vocab.json", - "openai/whisper-base": "https://huggingface.co/openai/whisper-base/resolve/main/vocab.json", - "openai/whisper-small": "https://huggingface.co/openai/whisper-small/resolve/main/vocab.json", - "openai/whisper-medium": "https://huggingface.co/openai/whisper-medium/resolve/main/vocab.json", - "openai/whisper-large": "https://huggingface.co/openai/whisper-large/resolve/main/vocab.json", - "openai/whisper-tiny.en": "https://huggingface.co/openai/whisper-tiny.en/resolve/main/vocab.json", - "openai/whisper-base.en": "https://huggingface.co/openai/whisper-base.en/resolve/main/vocab.json", - "openai/whisper-small.en": "https://huggingface.co/openai/whisper-small.en/resolve/main/vocab.json", - "openai/whisper-medium.en": "https://huggingface.co/openai/whisper-medium.en/resolve/main/vocab.json", - }, - "merges_file": { - "openai/whisper-tiny": "https://huggingface.co/openai/whisper-tiny/resolve/main/merges.txt", - "openai/whisper-base": "https://huggingface.co/openai/whisper-base/resolve/main/merges.txt", - "openai/whisper-small": "https://huggingface.co/openai/whisper-small/resolve/main/merges.txt", - "openai/whisper-medium": "https://huggingface.co/openai/whisper-medium/resolve/main/merges.txt", - "openai/whisper-large": "https://huggingface.co/openai/whisper-large/resolve/main/merges.txt", - "openai/whisper-tiny.en": "https://huggingface.co/openai/whisper-tiny.en/resolve/main/merges.txt", - "openai/whisper-base.en": "https://huggingface.co/openai/whisper-base.en/resolve/main/merges.txt", - "openai/whisper-small.en": "https://huggingface.co/openai/whisper-small.en/resolve/main/merges.txt", - "openai/whisper-medium.en": "https://huggingface.co/openai/whisper-medium.en/resolve/main/merges.txt", - }, - "tokenizer_file": { - "openai/whisper-tiny": "https://huggingface.co/openai/whisper-tiny/resolve/main/tokenizer.json", - "openai/whisper-base": "https://huggingface.co/openai/whisper-base/resolve/main/tokenizer.json", - "openai/whisper-small": "https://huggingface.co/openai/whisper-small/resolve/main/tokenizer.json", - "openai/whisper-medium": "https://huggingface.co/openai/whisper-medium/resolve/main/tokenizer.json", - "openai/whisper-large": "https://huggingface.co/openai/whisper-large/resolve/main/tokenizer.json", - "openai/whisper-tiny.en": "https://huggingface.co/openai/whisper-tiny.en/resolve/main/tokenizer.json", - "openai/whisper-base.en": "https://huggingface.co/openai/whisper-base.en/resolve/main/tokenizer.json", - "openai/whisper-small.en": "https://huggingface.co/openai/whisper-small.en/resolve/main/tokenizer.json", - "openai/whisper-medium.en": "https://huggingface.co/openai/whisper-medium.en/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "openai/whisper-tiny": 1500, - "openai/whisper-base": 1500, - "openai/whisper-small": 1500, - "openai/whisper-medium": 1500, - "openai/whisper-large": 1500, - "openai/whisper-tiny.en": 1500, - "openai/whisper-base.en": 1500, - "openai/whisper-small.en": 1500, - "openai/whisper-medium.en": 1500, -} - class WhisperTokenizerFast(PreTrainedTokenizerFast): """ @@ -128,8 +80,6 @@ class WhisperTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = WhisperTokenizer diff --git a/src/transformers/models/x_clip/configuration_x_clip.py b/src/transformers/models/x_clip/configuration_x_clip.py index c7e23ae3ba..7795269b7e 100644 --- a/src/transformers/models/x_clip/configuration_x_clip.py +++ b/src/transformers/models/x_clip/configuration_x_clip.py @@ -23,9 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -XCLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/xclip-base-patch32": "https://huggingface.co/microsoft/xclip-base-patch32/resolve/main/config.json", -} + +from ..deprecated._archive_maps import XCLIP_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class XCLIPTextConfig(PretrainedConfig): diff --git a/src/transformers/models/x_clip/modeling_x_clip.py b/src/transformers/models/x_clip/modeling_x_clip.py index e341b9639d..c9791fdfcc 100644 --- a/src/transformers/models/x_clip/modeling_x_clip.py +++ b/src/transformers/models/x_clip/modeling_x_clip.py @@ -41,10 +41,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "microsoft/xclip-base-patch32" -XCLIP_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/xclip-base-patch32", - # See all X-CLIP models at https://huggingface.co/models?filter=x-clip -] + +from ..deprecated._archive_maps import XCLIP_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # contrastive loss function, adapted from diff --git a/src/transformers/models/xglm/configuration_xglm.py b/src/transformers/models/xglm/configuration_xglm.py index 9377bbce6f..c67c67a4b2 100644 --- a/src/transformers/models/xglm/configuration_xglm.py +++ b/src/transformers/models/xglm/configuration_xglm.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -XGLM_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/xglm-564M": "https://huggingface.co/facebook/xglm-564M/resolve/main/config.json", - # See all XGLM models at https://huggingface.co/models?filter=xglm -} + +from ..deprecated._archive_maps import XGLM_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class XGLMConfig(PretrainedConfig): diff --git a/src/transformers/models/xglm/modeling_tf_xglm.py b/src/transformers/models/xglm/modeling_tf_xglm.py index 4157cc0616..e3003fdbc5 100644 --- a/src/transformers/models/xglm/modeling_tf_xglm.py +++ b/src/transformers/models/xglm/modeling_tf_xglm.py @@ -55,10 +55,7 @@ _CHECKPOINT_FOR_DOC = "facebook/xglm-564M" _CONFIG_FOR_DOC = "XGLMConfig" -TF_XGLM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/xglm-564M", - # See all XGLM models at https://huggingface.co/models?filter=xglm -] +from ..deprecated._archive_maps import TF_XGLM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 LARGE_NEGATIVE = -1e8 diff --git a/src/transformers/models/xglm/modeling_xglm.py b/src/transformers/models/xglm/modeling_xglm.py index ee98f2090c..7ec48b6f9d 100755 --- a/src/transformers/models/xglm/modeling_xglm.py +++ b/src/transformers/models/xglm/modeling_xglm.py @@ -37,10 +37,8 @@ _CHECKPOINT_FOR_DOC = "facebook/xglm-564M" _CONFIG_FOR_DOC = "XGLMConfig" -XGLM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/xglm-564M", - # See all XGLM models at https://huggingface.co/models?filter=xglm -] +from ..deprecated._archive_maps import XGLM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + XGLM_START_DOCSTRING = r""" This model inherits from [`PreTrainedModel`]. Check the superclass documentation for the generic methods the diff --git a/src/transformers/models/xglm/tokenization_xglm.py b/src/transformers/models/xglm/tokenization_xglm.py index a8c93dc3bc..818ca163da 100644 --- a/src/transformers/models/xglm/tokenization_xglm.py +++ b/src/transformers/models/xglm/tokenization_xglm.py @@ -29,16 +29,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/xglm-564M": "https://huggingface.co/facebook/xglm-564M/resolve/main/sentencepiece.bpe.model", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/xglm-564M": 2048, -} - class XGLMTokenizer(PreTrainedTokenizer): """ @@ -105,8 +95,6 @@ class XGLMTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/xglm/tokenization_xglm_fast.py b/src/transformers/models/xglm/tokenization_xglm_fast.py index 62db9dd694..2f8b0480c8 100644 --- a/src/transformers/models/xglm/tokenization_xglm_fast.py +++ b/src/transformers/models/xglm/tokenization_xglm_fast.py @@ -32,19 +32,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "facebook/xglm-564M": "https://huggingface.co/facebook/xglm-564M/resolve/main/sentencepiece.bpe.model", - }, - "tokenizer_file": { - "facebook/xglm-564M": "https://huggingface.co/facebook/xglm-564M/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "facebook/xglm-564M": 2048, -} - class XGLMTokenizerFast(PreTrainedTokenizerFast): """ @@ -95,8 +82,6 @@ class XGLMTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = XGLMTokenizer diff --git a/src/transformers/models/xlm/configuration_xlm.py b/src/transformers/models/xlm/configuration_xlm.py index 2992a3ab32..3b1dadd565 100644 --- a/src/transformers/models/xlm/configuration_xlm.py +++ b/src/transformers/models/xlm/configuration_xlm.py @@ -23,18 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -XLM_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "FacebookAI/xlm-mlm-en-2048": "https://huggingface.co/FacebookAI/xlm-mlm-en-2048/resolve/main/config.json", - "FacebookAI/xlm-mlm-ende-1024": "https://huggingface.co/FacebookAI/xlm-mlm-ende-1024/resolve/main/config.json", - "FacebookAI/xlm-mlm-enfr-1024": "https://huggingface.co/FacebookAI/xlm-mlm-enfr-1024/resolve/main/config.json", - "FacebookAI/xlm-mlm-enro-1024": "https://huggingface.co/FacebookAI/xlm-mlm-enro-1024/resolve/main/config.json", - "FacebookAI/xlm-mlm-tlm-xnli15-1024": "https://huggingface.co/FacebookAI/xlm-mlm-tlm-xnli15-1024/resolve/main/config.json", - "FacebookAI/xlm-mlm-xnli15-1024": "https://huggingface.co/FacebookAI/xlm-mlm-xnli15-1024/resolve/main/config.json", - "FacebookAI/xlm-clm-enfr-1024": "https://huggingface.co/FacebookAI/xlm-clm-enfr-1024/resolve/main/config.json", - "FacebookAI/xlm-clm-ende-1024": "https://huggingface.co/FacebookAI/xlm-clm-ende-1024/resolve/main/config.json", - "FacebookAI/xlm-mlm-17-1280": "https://huggingface.co/FacebookAI/xlm-mlm-17-1280/resolve/main/config.json", - "FacebookAI/xlm-mlm-100-1280": "https://huggingface.co/FacebookAI/xlm-mlm-100-1280/resolve/main/config.json", -} + +from ..deprecated._archive_maps import XLM_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class XLMConfig(PretrainedConfig): diff --git a/src/transformers/models/xlm/modeling_tf_xlm.py b/src/transformers/models/xlm/modeling_tf_xlm.py index 173f1d0acd..45447a4236 100644 --- a/src/transformers/models/xlm/modeling_tf_xlm.py +++ b/src/transformers/models/xlm/modeling_tf_xlm.py @@ -66,19 +66,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "FacebookAI/xlm-mlm-en-2048" _CONFIG_FOR_DOC = "XLMConfig" -TF_XLM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "FacebookAI/xlm-mlm-en-2048", - "FacebookAI/xlm-mlm-ende-1024", - "FacebookAI/xlm-mlm-enfr-1024", - "FacebookAI/xlm-mlm-enro-1024", - "FacebookAI/xlm-mlm-tlm-xnli15-1024", - "FacebookAI/xlm-mlm-xnli15-1024", - "FacebookAI/xlm-clm-enfr-1024", - "FacebookAI/xlm-clm-ende-1024", - "FacebookAI/xlm-mlm-17-1280", - "FacebookAI/xlm-mlm-100-1280", - # See all XLM models at https://huggingface.co/models?filter=xlm -] + +from ..deprecated._archive_maps import TF_XLM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def create_sinusoidal_embeddings(n_pos, dim, out): diff --git a/src/transformers/models/xlm/modeling_xlm.py b/src/transformers/models/xlm/modeling_xlm.py index de07829974..06e621da01 100755 --- a/src/transformers/models/xlm/modeling_xlm.py +++ b/src/transformers/models/xlm/modeling_xlm.py @@ -53,19 +53,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "FacebookAI/xlm-mlm-en-2048" _CONFIG_FOR_DOC = "XLMConfig" -XLM_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "FacebookAI/xlm-mlm-en-2048", - "FacebookAI/xlm-mlm-ende-1024", - "FacebookAI/xlm-mlm-enfr-1024", - "FacebookAI/xlm-mlm-enro-1024", - "FacebookAI/xlm-mlm-tlm-xnli15-1024", - "FacebookAI/xlm-mlm-xnli15-1024", - "FacebookAI/xlm-clm-enfr-1024", - "FacebookAI/xlm-clm-ende-1024", - "FacebookAI/xlm-mlm-17-1280", - "FacebookAI/xlm-mlm-100-1280", - # See all XLM models at https://huggingface.co/models?filter=xlm -] + +from ..deprecated._archive_maps import XLM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def create_sinusoidal_embeddings(n_pos, dim, out): diff --git a/src/transformers/models/xlm/tokenization_xlm.py b/src/transformers/models/xlm/tokenization_xlm.py index a99b5cb73c..b39e4c2708 100644 --- a/src/transformers/models/xlm/tokenization_xlm.py +++ b/src/transformers/models/xlm/tokenization_xlm.py @@ -33,397 +33,6 @@ VOCAB_FILES_NAMES = { "merges_file": "merges.txt", } -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "FacebookAI/xlm-mlm-en-2048": "https://huggingface.co/FacebookAI/xlm-mlm-en-2048/resolve/main/vocab.json", - "FacebookAI/xlm-mlm-ende-1024": "https://huggingface.co/FacebookAI/xlm-mlm-ende-1024/resolve/main/vocab.json", - "FacebookAI/xlm-mlm-enfr-1024": "https://huggingface.co/FacebookAI/xlm-mlm-enfr-1024/resolve/main/vocab.json", - "FacebookAI/xlm-mlm-enro-1024": "https://huggingface.co/FacebookAI/xlm-mlm-enro-1024/resolve/main/vocab.json", - "FacebookAI/xlm-mlm-tlm-xnli15-1024": "https://huggingface.co/FacebookAI/xlm-mlm-tlm-xnli15-1024/resolve/main/vocab.json", - "FacebookAI/xlm-mlm-xnli15-1024": "https://huggingface.co/FacebookAI/xlm-mlm-xnli15-1024/resolve/main/vocab.json", - "FacebookAI/xlm-clm-enfr-1024": "https://huggingface.co/FacebookAI/xlm-clm-enfr-1024/resolve/main/vocab.json", - "FacebookAI/xlm-clm-ende-1024": "https://huggingface.co/FacebookAI/xlm-clm-ende-1024/resolve/main/vocab.json", - "FacebookAI/xlm-mlm-17-1280": "https://huggingface.co/FacebookAI/xlm-mlm-17-1280/resolve/main/vocab.json", - "FacebookAI/xlm-mlm-100-1280": "https://huggingface.co/FacebookAI/xlm-mlm-100-1280/resolve/main/vocab.json", - }, - "merges_file": { - "FacebookAI/xlm-mlm-en-2048": "https://huggingface.co/FacebookAI/xlm-mlm-en-2048/resolve/main/merges.txt", - "FacebookAI/xlm-mlm-ende-1024": "https://huggingface.co/FacebookAI/xlm-mlm-ende-1024/resolve/main/merges.txt", - "FacebookAI/xlm-mlm-enfr-1024": "https://huggingface.co/FacebookAI/xlm-mlm-enfr-1024/resolve/main/merges.txt", - "FacebookAI/xlm-mlm-enro-1024": "https://huggingface.co/FacebookAI/xlm-mlm-enro-1024/resolve/main/merges.txt", - "FacebookAI/xlm-mlm-tlm-xnli15-1024": "https://huggingface.co/FacebookAI/xlm-mlm-tlm-xnli15-1024/resolve/main/merges.txt", - "FacebookAI/xlm-mlm-xnli15-1024": "https://huggingface.co/FacebookAI/xlm-mlm-xnli15-1024/resolve/main/merges.txt", - "FacebookAI/xlm-clm-enfr-1024": "https://huggingface.co/FacebookAI/xlm-clm-enfr-1024/resolve/main/merges.txt", - "FacebookAI/xlm-clm-ende-1024": "https://huggingface.co/FacebookAI/xlm-clm-ende-1024/resolve/main/merges.txt", - "FacebookAI/xlm-mlm-17-1280": "https://huggingface.co/FacebookAI/xlm-mlm-17-1280/resolve/main/merges.txt", - "FacebookAI/xlm-mlm-100-1280": "https://huggingface.co/FacebookAI/xlm-mlm-100-1280/resolve/main/merges.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "FacebookAI/xlm-mlm-en-2048": 512, - "FacebookAI/xlm-mlm-ende-1024": 512, - "FacebookAI/xlm-mlm-enfr-1024": 512, - "FacebookAI/xlm-mlm-enro-1024": 512, - "FacebookAI/xlm-mlm-tlm-xnli15-1024": 512, - "FacebookAI/xlm-mlm-xnli15-1024": 512, - "FacebookAI/xlm-clm-enfr-1024": 512, - "FacebookAI/xlm-clm-ende-1024": 512, - "FacebookAI/xlm-mlm-17-1280": 512, - "FacebookAI/xlm-mlm-100-1280": 512, -} - -PRETRAINED_INIT_CONFIGURATION = { - "FacebookAI/xlm-mlm-en-2048": {"do_lowercase_and_remove_accent": True}, - "FacebookAI/xlm-mlm-ende-1024": { - "do_lowercase_and_remove_accent": True, - "id2lang": {0: "de", 1: "en"}, - "lang2id": {"de": 0, "en": 1}, - }, - "FacebookAI/xlm-mlm-enfr-1024": { - "do_lowercase_and_remove_accent": True, - "id2lang": {0: "en", 1: "fr"}, - "lang2id": {"en": 0, "fr": 1}, - }, - "FacebookAI/xlm-mlm-enro-1024": { - "do_lowercase_and_remove_accent": True, - "id2lang": {0: "en", 1: "ro"}, - "lang2id": {"en": 0, "ro": 1}, - }, - "FacebookAI/xlm-mlm-tlm-xnli15-1024": { - "do_lowercase_and_remove_accent": True, - "id2lang": { - 0: "ar", - 1: "bg", - 2: "de", - 3: "el", - 4: "en", - 5: "es", - 6: "fr", - 7: "hi", - 8: "ru", - 9: "sw", - 10: "th", - 11: "tr", - 12: "ur", - 13: "vi", - 14: "zh", - }, - "lang2id": { - "ar": 0, - "bg": 1, - "de": 2, - "el": 3, - "en": 4, - "es": 5, - "fr": 6, - "hi": 7, - "ru": 8, - "sw": 9, - "th": 10, - "tr": 11, - "ur": 12, - "vi": 13, - "zh": 14, - }, - }, - "FacebookAI/xlm-mlm-xnli15-1024": { - "do_lowercase_and_remove_accent": True, - "id2lang": { - 0: "ar", - 1: "bg", - 2: "de", - 3: "el", - 4: "en", - 5: "es", - 6: "fr", - 7: "hi", - 8: "ru", - 9: "sw", - 10: "th", - 11: "tr", - 12: "ur", - 13: "vi", - 14: "zh", - }, - "lang2id": { - "ar": 0, - "bg": 1, - "de": 2, - "el": 3, - "en": 4, - "es": 5, - "fr": 6, - "hi": 7, - "ru": 8, - "sw": 9, - "th": 10, - "tr": 11, - "ur": 12, - "vi": 13, - "zh": 14, - }, - }, - "FacebookAI/xlm-clm-enfr-1024": { - "do_lowercase_and_remove_accent": True, - "id2lang": {0: "en", 1: "fr"}, - "lang2id": {"en": 0, "fr": 1}, - }, - "FacebookAI/xlm-clm-ende-1024": { - "do_lowercase_and_remove_accent": True, - "id2lang": {0: "de", 1: "en"}, - "lang2id": {"de": 0, "en": 1}, - }, - "FacebookAI/xlm-mlm-17-1280": { - "do_lowercase_and_remove_accent": False, - "id2lang": { - 0: "ar", - 1: "de", - 2: "en", - 3: "es", - 4: "fr", - 5: "hi", - 6: "it", - 7: "ja", - 8: "ko", - 9: "nl", - 10: "pl", - 11: "pt", - 12: "ru", - 13: "sv", - 14: "tr", - 15: "vi", - 16: "zh", - }, - "lang2id": { - "ar": 0, - "de": 1, - "en": 2, - "es": 3, - "fr": 4, - "hi": 5, - "it": 6, - "ja": 7, - "ko": 8, - "nl": 9, - "pl": 10, - "pt": 11, - "ru": 12, - "sv": 13, - "tr": 14, - "vi": 15, - "zh": 16, - }, - }, - "FacebookAI/xlm-mlm-100-1280": { - "do_lowercase_and_remove_accent": False, - "id2lang": { - 0: "af", - 1: "als", - 2: "am", - 3: "an", - 4: "ang", - 5: "ar", - 6: "arz", - 7: "ast", - 8: "az", - 9: "bar", - 10: "be", - 11: "bg", - 12: "bn", - 13: "br", - 14: "bs", - 15: "ca", - 16: "ceb", - 17: "ckb", - 18: "cs", - 19: "cy", - 20: "da", - 21: "de", - 22: "el", - 23: "en", - 24: "eo", - 25: "es", - 26: "et", - 27: "eu", - 28: "fa", - 29: "fi", - 30: "fr", - 31: "fy", - 32: "ga", - 33: "gan", - 34: "gl", - 35: "gu", - 36: "he", - 37: "hi", - 38: "hr", - 39: "hu", - 40: "hy", - 41: "ia", - 42: "id", - 43: "is", - 44: "it", - 45: "ja", - 46: "jv", - 47: "ka", - 48: "kk", - 49: "kn", - 50: "ko", - 51: "ku", - 52: "la", - 53: "lb", - 54: "lt", - 55: "lv", - 56: "mk", - 57: "ml", - 58: "mn", - 59: "mr", - 60: "ms", - 61: "my", - 62: "nds", - 63: "ne", - 64: "nl", - 65: "nn", - 66: "no", - 67: "oc", - 68: "pl", - 69: "pt", - 70: "ro", - 71: "ru", - 72: "scn", - 73: "sco", - 74: "sh", - 75: "si", - 76: "simple", - 77: "sk", - 78: "sl", - 79: "sq", - 80: "sr", - 81: "sv", - 82: "sw", - 83: "ta", - 84: "te", - 85: "th", - 86: "tl", - 87: "tr", - 88: "tt", - 89: "uk", - 90: "ur", - 91: "uz", - 92: "vi", - 93: "war", - 94: "wuu", - 95: "yi", - 96: "zh", - 97: "zh_classical", - 98: "zh_min_nan", - 99: "zh_yue", - }, - "lang2id": { - "af": 0, - "als": 1, - "am": 2, - "an": 3, - "ang": 4, - "ar": 5, - "arz": 6, - "ast": 7, - "az": 8, - "bar": 9, - "be": 10, - "bg": 11, - "bn": 12, - "br": 13, - "bs": 14, - "ca": 15, - "ceb": 16, - "ckb": 17, - "cs": 18, - "cy": 19, - "da": 20, - "de": 21, - "el": 22, - "en": 23, - "eo": 24, - "es": 25, - "et": 26, - "eu": 27, - "fa": 28, - "fi": 29, - "fr": 30, - "fy": 31, - "ga": 32, - "gan": 33, - "gl": 34, - "gu": 35, - "he": 36, - "hi": 37, - "hr": 38, - "hu": 39, - "hy": 40, - "ia": 41, - "id": 42, - "is": 43, - "it": 44, - "ja": 45, - "jv": 46, - "ka": 47, - "kk": 48, - "kn": 49, - "ko": 50, - "ku": 51, - "la": 52, - "lb": 53, - "lt": 54, - "lv": 55, - "mk": 56, - "ml": 57, - "mn": 58, - "mr": 59, - "ms": 60, - "my": 61, - "nds": 62, - "ne": 63, - "nl": 64, - "nn": 65, - "no": 66, - "oc": 67, - "pl": 68, - "pt": 69, - "ro": 70, - "ru": 71, - "scn": 72, - "sco": 73, - "sh": 74, - "si": 75, - "simple": 76, - "sk": 77, - "sl": 78, - "sq": 79, - "sr": 80, - "sv": 81, - "sw": 82, - "ta": 83, - "te": 84, - "th": 85, - "tl": 86, - "tr": 87, - "tt": 88, - "uk": 89, - "ur": 90, - "uz": 91, - "vi": 92, - "war": 93, - "wuu": 94, - "yi": 95, - "zh": 96, - "zh_classical": 97, - "zh_min_nan": 98, - "zh_yue": 99, - }, - }, -} - def get_pairs(word): """ @@ -582,9 +191,6 @@ class XLMTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, diff --git a/src/transformers/models/xlm_prophetnet/configuration_xlm_prophetnet.py b/src/transformers/models/xlm_prophetnet/configuration_xlm_prophetnet.py index 88ca83a732..f1a903c227 100644 --- a/src/transformers/models/xlm_prophetnet/configuration_xlm_prophetnet.py +++ b/src/transformers/models/xlm_prophetnet/configuration_xlm_prophetnet.py @@ -23,11 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -XLM_PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "microsoft/xprophetnet-large-wiki100-cased": ( - "https://huggingface.co/microsoft/xprophetnet-large-wiki100-cased/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import XLM_PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class XLMProphetNetConfig(PretrainedConfig): diff --git a/src/transformers/models/xlm_prophetnet/modeling_xlm_prophetnet.py b/src/transformers/models/xlm_prophetnet/modeling_xlm_prophetnet.py index e705b95b17..53b8a1fc20 100644 --- a/src/transformers/models/xlm_prophetnet/modeling_xlm_prophetnet.py +++ b/src/transformers/models/xlm_prophetnet/modeling_xlm_prophetnet.py @@ -44,10 +44,9 @@ logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "XLMProphetNetConfig" -XLM_PROPHETNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "microsoft/xprophetnet-large-wiki100-cased", - # See all XLMProphetNet models at https://huggingface.co/models?filter=xprophetnet -] + +from ..deprecated._archive_maps import XLM_PROPHETNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + # Copied from src.transformers.models.prophetnet.modeling_prophetnet.PROPHETNET_START_DOCSTRING with ProphetNetConfig->XLMProphetNetConfig XLM_PROPHETNET_START_DOCSTRING = r""" diff --git a/src/transformers/models/xlm_prophetnet/tokenization_xlm_prophetnet.py b/src/transformers/models/xlm_prophetnet/tokenization_xlm_prophetnet.py index c024d5d16d..fa65fa5cbf 100644 --- a/src/transformers/models/xlm_prophetnet/tokenization_xlm_prophetnet.py +++ b/src/transformers/models/xlm_prophetnet/tokenization_xlm_prophetnet.py @@ -28,22 +28,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "prophetnet.tokenizer"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "microsoft/xprophetnet-large-wiki100-cased": ( - "https://huggingface.co/microsoft/xprophetnet-large-wiki100-cased/resolve/main/prophetnet.tokenizer" - ), - } -} - -PRETRAINED_INIT_CONFIGURATION = { - "microsoft/xprophetnet-large-wiki100-cased": {"do_lower_case": False}, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "microsoft/xprophetnet-large-wiki100-cased": 512, -} - def load_vocab(vocab_file): """Loads a vocabulary file into a dictionary.""" @@ -124,8 +108,6 @@ class XLMProphetNetTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/xlm_roberta/configuration_xlm_roberta.py b/src/transformers/models/xlm_roberta/configuration_xlm_roberta.py index 65c536ba43..3da0fbecd6 100644 --- a/src/transformers/models/xlm_roberta/configuration_xlm_roberta.py +++ b/src/transformers/models/xlm_roberta/configuration_xlm_roberta.py @@ -24,22 +24,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "FacebookAI/xlm-roberta-base": "https://huggingface.co/FacebookAI/xlm-roberta-base/resolve/main/config.json", - "FacebookAI/xlm-roberta-large": "https://huggingface.co/FacebookAI/xlm-roberta-large/resolve/main/config.json", - "FacebookAI/xlm-roberta-large-finetuned-conll02-dutch": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll02-dutch/resolve/main/config.json" - ), - "FacebookAI/xlm-roberta-large-finetuned-conll02-spanish": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll02-spanish/resolve/main/config.json" - ), - "FacebookAI/xlm-roberta-large-finetuned-conll03-english": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-english/resolve/main/config.json" - ), - "FacebookAI/xlm-roberta-large-finetuned-conll03-german": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-german/resolve/main/config.json" - ), -} + +from ..deprecated._archive_maps import XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class XLMRobertaConfig(PretrainedConfig): diff --git a/src/transformers/models/xlm_roberta/modeling_flax_xlm_roberta.py b/src/transformers/models/xlm_roberta/modeling_flax_xlm_roberta.py index 0017be6bd8..2caffc0b90 100644 --- a/src/transformers/models/xlm_roberta/modeling_flax_xlm_roberta.py +++ b/src/transformers/models/xlm_roberta/modeling_flax_xlm_roberta.py @@ -51,11 +51,8 @@ _CONFIG_FOR_DOC = "XLMRobertaConfig" remat = nn_partitioning.remat -FLAX_XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "FacebookAI/xlm-roberta-base", - "FacebookAI/xlm-roberta-large", - # See all XLM-RoBERTa models at https://huggingface.co/models?filter=xlm-roberta -] + +from ..deprecated._archive_maps import FLAX_XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.roberta.modeling_flax_roberta.create_position_ids_from_input_ids diff --git a/src/transformers/models/xlm_roberta/modeling_tf_xlm_roberta.py b/src/transformers/models/xlm_roberta/modeling_tf_xlm_roberta.py index dcf1b018b2..3b0efe6bd7 100644 --- a/src/transformers/models/xlm_roberta/modeling_tf_xlm_roberta.py +++ b/src/transformers/models/xlm_roberta/modeling_tf_xlm_roberta.py @@ -67,13 +67,9 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "FacebookAI/xlm-roberta-base" _CONFIG_FOR_DOC = "XLMRobertaConfig" -TF_XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "FacebookAI/xlm-roberta-base", - "FacebookAI/xlm-roberta-large", - "joeddav/xlm-roberta-large-xnli", - "cardiffnlp/twitter-xlm-roberta-base-sentiment", - # See all XLM-RoBERTa models at https://huggingface.co/models?filter=xlm-roberta -] + +from ..deprecated._archive_maps import TF_XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + XLM_ROBERTA_START_DOCSTRING = r""" diff --git a/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py b/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py index 8abd77b8c3..0d829aaee6 100644 --- a/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py +++ b/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py @@ -51,15 +51,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "FacebookAI/xlm-roberta-base" _CONFIG_FOR_DOC = "XLMRobertaConfig" -XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "FacebookAI/xlm-roberta-base", - "FacebookAI/xlm-roberta-large", - "FacebookAI/xlm-roberta-large-finetuned-conll02-dutch", - "FacebookAI/xlm-roberta-large-finetuned-conll02-spanish", - "FacebookAI/xlm-roberta-large-finetuned-conll03-english", - "FacebookAI/xlm-roberta-large-finetuned-conll03-german", - # See all XLM-RoBERTa models at https://huggingface.co/models?filter=xlm-roberta -] + +from ..deprecated._archive_maps import XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.roberta.modeling_roberta.RobertaEmbeddings with Roberta->XLMRoberta diff --git a/src/transformers/models/xlm_roberta/tokenization_xlm_roberta.py b/src/transformers/models/xlm_roberta/tokenization_xlm_roberta.py index 3f87bd9b0d..20300a19ce 100644 --- a/src/transformers/models/xlm_roberta/tokenization_xlm_roberta.py +++ b/src/transformers/models/xlm_roberta/tokenization_xlm_roberta.py @@ -31,34 +31,6 @@ SPIECE_UNDERLINE = "▁" VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "FacebookAI/xlm-roberta-base": "https://huggingface.co/FacebookAI/xlm-roberta-base/resolve/main/sentencepiece.bpe.model", - "FacebookAI/xlm-roberta-large": "https://huggingface.co/FacebookAI/xlm-roberta-large/resolve/main/sentencepiece.bpe.model", - "FacebookAI/xlm-roberta-large-finetuned-conll02-dutch": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll02-dutch/resolve/main/sentencepiece.bpe.model" - ), - "FacebookAI/xlm-roberta-large-finetuned-conll02-spanish": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll02-spanish/resolve/main/sentencepiece.bpe.model" - ), - "FacebookAI/xlm-roberta-large-finetuned-conll03-english": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-english/resolve/main/sentencepiece.bpe.model" - ), - "FacebookAI/xlm-roberta-large-finetuned-conll03-german": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-german/resolve/main/sentencepiece.bpe.model" - ), - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "FacebookAI/xlm-roberta-base": 512, - "FacebookAI/xlm-roberta-large": 512, - "FacebookAI/xlm-roberta-large-finetuned-conll02-dutch": 512, - "FacebookAI/xlm-roberta-large-finetuned-conll02-spanish": 512, - "FacebookAI/xlm-roberta-large-finetuned-conll03-english": 512, - "FacebookAI/xlm-roberta-large-finetuned-conll03-german": 512, -} - class XLMRobertaTokenizer(PreTrainedTokenizer): """ @@ -128,8 +100,6 @@ class XLMRobertaTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/src/transformers/models/xlm_roberta/tokenization_xlm_roberta_fast.py b/src/transformers/models/xlm_roberta/tokenization_xlm_roberta_fast.py index 8f2c1e02a0..f32e715154 100644 --- a/src/transformers/models/xlm_roberta/tokenization_xlm_roberta_fast.py +++ b/src/transformers/models/xlm_roberta/tokenization_xlm_roberta_fast.py @@ -34,50 +34,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "FacebookAI/xlm-roberta-base": "https://huggingface.co/FacebookAI/xlm-roberta-base/resolve/main/sentencepiece.bpe.model", - "FacebookAI/xlm-roberta-large": "https://huggingface.co/FacebookAI/xlm-roberta-large/resolve/main/sentencepiece.bpe.model", - "FacebookAI/xlm-roberta-large-finetuned-conll02-dutch": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll02-dutch/resolve/main/sentencepiece.bpe.model" - ), - "FacebookAI/xlm-roberta-large-finetuned-conll02-spanish": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll02-spanish/resolve/main/sentencepiece.bpe.model" - ), - "FacebookAI/xlm-roberta-large-finetuned-conll03-english": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-english/resolve/main/sentencepiece.bpe.model" - ), - "FacebookAI/xlm-roberta-large-finetuned-conll03-german": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-german/resolve/main/sentencepiece.bpe.model" - ), - }, - "tokenizer_file": { - "FacebookAI/xlm-roberta-base": "https://huggingface.co/FacebookAI/xlm-roberta-base/resolve/main/tokenizer.json", - "FacebookAI/xlm-roberta-large": "https://huggingface.co/FacebookAI/xlm-roberta-large/resolve/main/tokenizer.json", - "FacebookAI/xlm-roberta-large-finetuned-conll02-dutch": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll02-dutch/resolve/main/tokenizer.json" - ), - "FacebookAI/xlm-roberta-large-finetuned-conll02-spanish": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll02-spanish/resolve/main/tokenizer.json" - ), - "FacebookAI/xlm-roberta-large-finetuned-conll03-english": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-english/resolve/main/tokenizer.json" - ), - "FacebookAI/xlm-roberta-large-finetuned-conll03-german": ( - "https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-german/resolve/main/tokenizer.json" - ), - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "FacebookAI/xlm-roberta-base": 512, - "FacebookAI/xlm-roberta-large": 512, - "FacebookAI/xlm-roberta-large-finetuned-conll02-dutch": 512, - "FacebookAI/xlm-roberta-large-finetuned-conll02-spanish": 512, - "FacebookAI/xlm-roberta-large-finetuned-conll03-english": 512, - "FacebookAI/xlm-roberta-large-finetuned-conll03-german": 512, -} - class XLMRobertaTokenizerFast(PreTrainedTokenizerFast): """ @@ -131,8 +87,6 @@ class XLMRobertaTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] slow_tokenizer_class = XLMRobertaTokenizer diff --git a/src/transformers/models/xlm_roberta_xl/configuration_xlm_roberta_xl.py b/src/transformers/models/xlm_roberta_xl/configuration_xlm_roberta_xl.py index acb9c63097..23deeea743 100644 --- a/src/transformers/models/xlm_roberta_xl/configuration_xlm_roberta_xl.py +++ b/src/transformers/models/xlm_roberta_xl/configuration_xlm_roberta_xl.py @@ -24,11 +24,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -XLM_ROBERTA_XL_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/xlm-roberta-xl": "https://huggingface.co/facebook/xlm-roberta-xl/resolve/main/config.json", - "facebook/xlm-roberta-xxl": "https://huggingface.co/facebook/xlm-roberta-xxl/resolve/main/config.json", - # See all XLM-RoBERTa-XL models at https://huggingface.co/models?filter=xlm-roberta-xl -} + +from ..deprecated._archive_maps import XLM_ROBERTA_XL_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class XLMRobertaXLConfig(PretrainedConfig): diff --git a/src/transformers/models/xlm_roberta_xl/modeling_xlm_roberta_xl.py b/src/transformers/models/xlm_roberta_xl/modeling_xlm_roberta_xl.py index 2799752ca4..1c17652dfa 100644 --- a/src/transformers/models/xlm_roberta_xl/modeling_xlm_roberta_xl.py +++ b/src/transformers/models/xlm_roberta_xl/modeling_xlm_roberta_xl.py @@ -50,11 +50,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "facebook/xlm-roberta-xl" _CONFIG_FOR_DOC = "XLMRobertaXLConfig" -XLM_ROBERTA_XL_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/xlm-roberta-xl", - "facebook/xlm-roberta-xxl", - # See all RoBERTa models at https://huggingface.co/models?filter=xlm-roberta-xl -] + +from ..deprecated._archive_maps import XLM_ROBERTA_XL_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class XLMRobertaXLEmbeddings(nn.Module): diff --git a/src/transformers/models/xlnet/configuration_xlnet.py b/src/transformers/models/xlnet/configuration_xlnet.py index 8528bb0639..f81c456b61 100644 --- a/src/transformers/models/xlnet/configuration_xlnet.py +++ b/src/transformers/models/xlnet/configuration_xlnet.py @@ -23,10 +23,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "xlnet/xlnet-base-cased": "https://huggingface.co/xlnet/xlnet-base-cased/resolve/main/config.json", - "xlnet/xlnet-large-cased": "https://huggingface.co/xlnet/xlnet-large-cased/resolve/main/config.json", -} + +from ..deprecated._archive_maps import XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class XLNetConfig(PretrainedConfig): diff --git a/src/transformers/models/xlnet/modeling_tf_xlnet.py b/src/transformers/models/xlnet/modeling_tf_xlnet.py index 598af1b707..188f5e39a2 100644 --- a/src/transformers/models/xlnet/modeling_tf_xlnet.py +++ b/src/transformers/models/xlnet/modeling_tf_xlnet.py @@ -60,11 +60,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "xlnet/xlnet-base-cased" _CONFIG_FOR_DOC = "XLNetConfig" -TF_XLNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "xlnet/xlnet-base-cased", - "xlnet/xlnet-large-cased", - # See all XLNet models at https://huggingface.co/models?filter=xlnet -] + +from ..deprecated._archive_maps import TF_XLNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 class TFXLNetRelativeAttention(keras.layers.Layer): diff --git a/src/transformers/models/xlnet/modeling_xlnet.py b/src/transformers/models/xlnet/modeling_xlnet.py index 6def87ef07..78ca545751 100755 --- a/src/transformers/models/xlnet/modeling_xlnet.py +++ b/src/transformers/models/xlnet/modeling_xlnet.py @@ -43,11 +43,8 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "xlnet/xlnet-base-cased" _CONFIG_FOR_DOC = "XLNetConfig" -XLNET_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "xlnet/xlnet-base-cased", - "xlnet/xlnet-large-cased", - # See all XLNet models at https://huggingface.co/models?filter=xlnet -] + +from ..deprecated._archive_maps import XLNET_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 def build_tf_xlnet_to_pytorch_map(model, config, tf_weights=None): diff --git a/src/transformers/models/xlnet/tokenization_xlnet.py b/src/transformers/models/xlnet/tokenization_xlnet.py index 808a7ff5bf..8d87f34ba2 100644 --- a/src/transformers/models/xlnet/tokenization_xlnet.py +++ b/src/transformers/models/xlnet/tokenization_xlnet.py @@ -30,17 +30,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "xlnet/xlnet-base-cased": "https://huggingface.co/xlnet/xlnet-base-cased/resolve/main/spiece.model", - "xlnet/xlnet-large-cased": "https://huggingface.co/xlnet/xlnet-large-cased/resolve/main/spiece.model", - } -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "xlnet/xlnet-base-cased": None, - "xlnet/xlnet-large-cased": None, -} # Segments (not really needed) SEG_ID_A = 0 @@ -126,8 +115,6 @@ class XLNetTokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES padding_side = "left" def __init__( diff --git a/src/transformers/models/xlnet/tokenization_xlnet_fast.py b/src/transformers/models/xlnet/tokenization_xlnet_fast.py index c43016a1a7..d77307e7a3 100644 --- a/src/transformers/models/xlnet/tokenization_xlnet_fast.py +++ b/src/transformers/models/xlnet/tokenization_xlnet_fast.py @@ -34,21 +34,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "spiece.model", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "xlnet/xlnet-base-cased": "https://huggingface.co/xlnet/xlnet-base-cased/resolve/main/spiece.model", - "xlnet/xlnet-large-cased": "https://huggingface.co/xlnet/xlnet-large-cased/resolve/main/spiece.model", - }, - "tokenizer_file": { - "xlnet/xlnet-base-cased": "https://huggingface.co/xlnet/xlnet-base-cased/resolve/main/tokenizer.json", - "xlnet/xlnet-large-cased": "https://huggingface.co/xlnet/xlnet-large-cased/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "xlnet/xlnet-base-cased": None, - "xlnet/xlnet-large-cased": None, -} SPIECE_UNDERLINE = "▁" @@ -122,8 +107,6 @@ class XLNetTokenizerFast(PreTrainedTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES padding_side = "left" slow_tokenizer_class = XLNetTokenizer diff --git a/src/transformers/models/xmod/configuration_xmod.py b/src/transformers/models/xmod/configuration_xmod.py index abf7a3275c..21eb9ba2ea 100644 --- a/src/transformers/models/xmod/configuration_xmod.py +++ b/src/transformers/models/xmod/configuration_xmod.py @@ -24,17 +24,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -XMOD_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "facebook/xmod-base": "https://huggingface.co/facebook/xmod-base/resolve/main/config.json", - "facebook/xmod-large-prenorm": "https://huggingface.co/facebook/xmod-large-prenorm/resolve/main/config.json", - "facebook/xmod-base-13-125k": "https://huggingface.co/facebook/xmod-base-13-125k/resolve/main/config.json", - "facebook/xmod-base-30-125k": "https://huggingface.co/facebook/xmod-base-30-125k/resolve/main/config.json", - "facebook/xmod-base-30-195k": "https://huggingface.co/facebook/xmod-base-30-195k/resolve/main/config.json", - "facebook/xmod-base-60-125k": "https://huggingface.co/facebook/xmod-base-60-125k/resolve/main/config.json", - "facebook/xmod-base-60-265k": "https://huggingface.co/facebook/xmod-base-60-265k/resolve/main/config.json", - "facebook/xmod-base-75-125k": "https://huggingface.co/facebook/xmod-base-75-125k/resolve/main/config.json", - "facebook/xmod-base-75-269k": "https://huggingface.co/facebook/xmod-base-75-269k/resolve/main/config.json", -} + +from ..deprecated._archive_maps import XMOD_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class XmodConfig(PretrainedConfig): diff --git a/src/transformers/models/xmod/modeling_xmod.py b/src/transformers/models/xmod/modeling_xmod.py index ba5ba6b727..2bf76a40d4 100644 --- a/src/transformers/models/xmod/modeling_xmod.py +++ b/src/transformers/models/xmod/modeling_xmod.py @@ -41,18 +41,8 @@ from .configuration_xmod import XmodConfig logger = logging.get_logger(__name__) -XMOD_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "facebook/xmod-base", - "facebook/xmod-large-prenorm", - "facebook/xmod-base-13-125k", - "facebook/xmod-base-30-125k", - "facebook/xmod-base-30-195k", - "facebook/xmod-base-60-125k", - "facebook/xmod-base-60-265k", - "facebook/xmod-base-75-125k", - "facebook/xmod-base-75-269k", - # See all X-MOD models at https://huggingface.co/models?filter=xmod -] + +from ..deprecated._archive_maps import XMOD_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 # Copied from transformers.models.roberta.modeling_roberta.RobertaEmbeddings with Roberta->Xmod diff --git a/src/transformers/models/yolos/configuration_yolos.py b/src/transformers/models/yolos/configuration_yolos.py index 9398d29e04..098210f1a7 100644 --- a/src/transformers/models/yolos/configuration_yolos.py +++ b/src/transformers/models/yolos/configuration_yolos.py @@ -26,10 +26,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -YOLOS_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "hustvl/yolos-small": "https://huggingface.co/hustvl/yolos-small/resolve/main/config.json", - # See all YOLOS models at https://huggingface.co/models?filter=yolos -} + +from ..deprecated._archive_maps import YOLOS_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class YolosConfig(PretrainedConfig): diff --git a/src/transformers/models/yolos/modeling_yolos.py b/src/transformers/models/yolos/modeling_yolos.py index 86ab375cdf..864be38a7d 100755 --- a/src/transformers/models/yolos/modeling_yolos.py +++ b/src/transformers/models/yolos/modeling_yolos.py @@ -63,10 +63,7 @@ _CHECKPOINT_FOR_DOC = "hustvl/yolos-small" _EXPECTED_OUTPUT_SHAPE = [1, 3401, 384] -YOLOS_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "hustvl/yolos-small", - # See all YOLOS models at https://huggingface.co/models?filter=yolos -] +from ..deprecated._archive_maps import YOLOS_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 @dataclass diff --git a/src/transformers/models/yoso/configuration_yoso.py b/src/transformers/models/yoso/configuration_yoso.py index 02d7f44d3c..fe2d4d4403 100644 --- a/src/transformers/models/yoso/configuration_yoso.py +++ b/src/transformers/models/yoso/configuration_yoso.py @@ -20,10 +20,8 @@ from ...utils import logging logger = logging.get_logger(__name__) -YOSO_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "uw-madison/yoso-4096": "https://huggingface.co/uw-madison/yoso-4096/resolve/main/config.json", - # See all YOSO models at https://huggingface.co/models?filter=yoso -} + +from ..deprecated._archive_maps import YOSO_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402 class YosoConfig(PretrainedConfig): diff --git a/src/transformers/models/yoso/modeling_yoso.py b/src/transformers/models/yoso/modeling_yoso.py index 41e34a6c66..b1fed0acc4 100644 --- a/src/transformers/models/yoso/modeling_yoso.py +++ b/src/transformers/models/yoso/modeling_yoso.py @@ -51,10 +51,9 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "uw-madison/yoso-4096" _CONFIG_FOR_DOC = "YosoConfig" -YOSO_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "uw-madison/yoso-4096", - # See all YOSO models at https://huggingface.co/models?filter=yoso -] + +from ..deprecated._archive_maps import YOSO_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402 + lsh_cumulation = None diff --git a/src/transformers/tokenization_utils_base.py b/src/transformers/tokenization_utils_base.py index e4df71c752..7d56ed2044 100644 --- a/src/transformers/tokenization_utils_base.py +++ b/src/transformers/tokenization_utils_base.py @@ -1484,13 +1484,6 @@ INIT_TOKENIZER_DOCSTRING = r""" high-level keys being the `__init__` keyword name of each vocabulary file required by the model, the low-level being the `short-cut-names` of the pretrained models with, as associated values, the `url` to the associated pretrained vocabulary file. - - **max_model_input_sizes** (`Dict[str, Optional[int]]`) -- A dictionary with, as keys, the `short-cut-names` - of the pretrained models, and as associated values, the maximum length of the sequence inputs of this model, - or `None` if the model has no maximum input size. - - **pretrained_init_configuration** (`Dict[str, Dict[str, Any]]`) -- A dictionary with, as keys, the - `short-cut-names` of the pretrained models, and as associated values, a dictionary of specific arguments to - pass to the `__init__` method of the tokenizer class for this pretrained model when loading the tokenizer - with the [`~tokenization_utils_base.PreTrainedTokenizerBase.from_pretrained`] method. - **model_input_names** (`List[str]`) -- A list of inputs expected in the forward pass of the model. - **padding_side** (`str`) -- The default value for the side on which the model should have padding applied. Should be `'right'` or `'left'`. @@ -1561,8 +1554,6 @@ class PreTrainedTokenizerBase(SpecialTokensMixin, PushToHubMixin): vocab_files_names: Dict[str, str] = {} pretrained_vocab_files_map: Dict[str, Dict[str, str]] = {} - pretrained_init_configuration: Dict[str, Dict[str, Any]] = {} - max_model_input_sizes: Dict[str, Optional[int]] = {} _auto_class: Optional[str] = None # first name has to correspond to main model input name @@ -2224,23 +2215,6 @@ class PreTrainedTokenizerBase(SpecialTokensMixin, PushToHubMixin): # Update with newly provided kwargs init_kwargs.update(kwargs) - # Set max length if needed - if pretrained_model_name_or_path in cls.max_model_input_sizes: - # if we're using a pretrained model, ensure the tokenizer - # wont index sequences longer than the number of positional embeddings - - model_max_length = cls.max_model_input_sizes[pretrained_model_name_or_path] - if model_max_length is not None and isinstance(model_max_length, (int, float)): - model_max_length = min(init_kwargs.get("model_max_length", int(1e30)), model_max_length) - # TODO(PVP) - uncomment following line in Transformers v5 - # init_kwargs["model_max_length"] = model_max_length - # TODO(PVP) - remove in Transformers v5 - # --- - init_kwargs["model_max_length"] = cls._eventually_correct_t5_max_length( - pretrained_model_name_or_path, model_max_length, init_kwargs.get("model_max_length") - ) - # --- - # Merge resolved_vocab_files arguments in init_kwargs. added_tokens_file = resolved_vocab_files.pop("added_tokens_file", None) special_tokens_map_file = resolved_vocab_files.pop("special_tokens_map_file", None) diff --git a/src/transformers/utils/dummy_detectron2_objects.py b/src/transformers/utils/dummy_detectron2_objects.py index 41dfb6f81d..22ec32fe30 100644 --- a/src/transformers/utils/dummy_detectron2_objects.py +++ b/src/transformers/utils/dummy_detectron2_objects.py @@ -2,9 +2,6 @@ from ..utils import requires_backends -LAYOUTLM_V2_PRETRAINED_MODEL_ARCHIVE_LIST = None - - class LayoutLMv2Model: def __init__(self, *args, **kwargs): requires_backends(self, ["detectron2"]) diff --git a/src/transformers/utils/dummy_pt_objects.py b/src/transformers/utils/dummy_pt_objects.py index 5b698e0afe..21a76a1d05 100644 --- a/src/transformers/utils/dummy_pt_objects.py +++ b/src/transformers/utils/dummy_pt_objects.py @@ -6806,9 +6806,6 @@ class PvtPreTrainedModel(metaclass=DummyObject): requires_backends(self, ["torch"]) -PVT_V2_PRETRAINED_MODEL_ARCHIVE_LIST = None - - class PvtV2Backbone(metaclass=DummyObject): _backends = ["torch"] diff --git a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/configuration_{{cookiecutter.lowercase_modelname}}.py b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/configuration_{{cookiecutter.lowercase_modelname}}.py index 15dc223595..61f4e81d74 100644 --- a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/configuration_{{cookiecutter.lowercase_modelname}}.py +++ b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/configuration_{{cookiecutter.lowercase_modelname}}.py @@ -20,11 +20,6 @@ from ...utils import logging logger = logging.get_logger(__name__) -{{cookiecutter.uppercase_modelname}}_PRETRAINED_CONFIG_ARCHIVE_MAP = { - "{{cookiecutter.checkpoint_identifier}}": "https://huggingface.co/{{cookiecutter.checkpoint_identifier}}/resolve/main/config.json", - # See all {{cookiecutter.modelname}} models at https://huggingface.co/models?filter={{cookiecutter.lowercase_modelname}} -} - class {{cookiecutter.camelcase_modelname}}Config(PretrainedConfig): r""" diff --git a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_tf_{{cookiecutter.lowercase_modelname}}.py b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_tf_{{cookiecutter.lowercase_modelname}}.py index fdfa32726c..d903c18b2f 100644 --- a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_tf_{{cookiecutter.lowercase_modelname}}.py +++ b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_tf_{{cookiecutter.lowercase_modelname}}.py @@ -64,11 +64,6 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "{{cookiecutter.checkpoint_identifier}}" _CONFIG_FOR_DOC = "{{cookiecutter.camelcase_modelname}}Config" -TF_{{cookiecutter.uppercase_modelname}}_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "{{cookiecutter.checkpoint_identifier}}", - # See all {{cookiecutter.modelname}} models at https://huggingface.co/models?filter={{cookiecutter.lowercase_modelname}} -] - # Copied from transformers.models.bert.modeling_tf_bert.TFBertEmbeddings with Bert->{{cookiecutter.camelcase_modelname}} class TF{{cookiecutter.camelcase_modelname}}Embeddings(keras.layers.Layer): diff --git a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py index 3c4295f715..db109b27fc 100755 --- a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py +++ b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py @@ -57,11 +57,6 @@ logger = logging.get_logger(__name__) _CHECKPOINT_FOR_DOC = "{{cookiecutter.checkpoint_identifier}}" _CONFIG_FOR_DOC = "{{cookiecutter.camelcase_modelname}}Config" -{{cookiecutter.uppercase_modelname}}_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "{{cookiecutter.checkpoint_identifier}}", - # See all {{cookiecutter.modelname}} models at https://huggingface.co/models?filter={{cookiecutter.lowercase_modelname}} -] - def load_tf_weights_in_{{cookiecutter.lowercase_modelname}}(model, config, tf_checkpoint_path): """Load tf checkpoints in a pytorch model.""" @@ -1588,11 +1583,6 @@ _CHECKPOINT_FOR_DOC = "{{cookiecutter.checkpoint_identifier}}" _CONFIG_FOR_DOC = "{{cookiecutter.camelcase_modelname}}Config" -{{cookiecutter.uppercase_modelname}}_PRETRAINED_MODEL_ARCHIVE_LIST = [ - "{{cookiecutter.checkpoint_identifier}}", - # See all {{cookiecutter.modelname}} models at https://huggingface.co/models?filter={{cookiecutter.lowercase_modelname}} -] - def shift_tokens_right(input_ids: torch.Tensor, pad_token_id: int, decoder_start_token_id: int): """ diff --git a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/test_modeling_{{cookiecutter.lowercase_modelname}}.py b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/test_modeling_{{cookiecutter.lowercase_modelname}}.py index 6d5b3fe796..cdb5070e3d 100644 --- a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/test_modeling_{{cookiecutter.lowercase_modelname}}.py +++ b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/test_modeling_{{cookiecutter.lowercase_modelname}}.py @@ -40,8 +40,7 @@ if is_torch_available(): {{cookiecutter.camelcase_modelname}}Model, ) from transformers.models.{{cookiecutter.lowercase_modelname}}.modeling_{{cookiecutter.lowercase_modelname}} import ( - {{cookiecutter.uppercase_modelname}}_PRETRAINED_MODEL_ARCHIVE_LIST, - ) + {{cookiecutter.uppercase_modelname}} ) class {{cookiecutter.camelcase_modelname}}ModelTester: @@ -453,9 +452,9 @@ class {{cookiecutter.camelcase_modelname}}ModelTest(ModelTesterMixin, unittest.T @slow def test_model_from_pretrained(self): - for model_name in {{cookiecutter.uppercase_modelname}}_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = {{cookiecutter.camelcase_modelname}}Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "{{coockiecutter.checkpoint_identifier}}" + model = {{cookiecutter.camelcase_modelname}}Model.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/to_replace_{{cookiecutter.lowercase_modelname}}.py b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/to_replace_{{cookiecutter.lowercase_modelname}}.py index 257dda17b4..f5ed661ade 100644 --- a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/to_replace_{{cookiecutter.lowercase_modelname}}.py +++ b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/to_replace_{{cookiecutter.lowercase_modelname}}.py @@ -30,7 +30,6 @@ {% if cookiecutter.is_encoder_decoder_model == "False" %} _import_structure["models.{{cookiecutter.lowercase_modelname}}"].extend( [ - "{{cookiecutter.uppercase_modelname}}_PRETRAINED_MODEL_ARCHIVE_LIST", "{{cookiecutter.camelcase_modelname}}ForMaskedLM", "{{cookiecutter.camelcase_modelname}}ForCausalLM", "{{cookiecutter.camelcase_modelname}}ForMultipleChoice", @@ -46,7 +45,6 @@ {% else %} _import_structure["models.{{cookiecutter.lowercase_modelname}}"].extend( [ - "{{cookiecutter.uppercase_modelname}}_PRETRAINED_MODEL_ARCHIVE_LIST", "{{cookiecutter.camelcase_modelname}}ForCausalLM", "{{cookiecutter.camelcase_modelname}}ForConditionalGeneration", "{{cookiecutter.camelcase_modelname}}ForQuestionAnswering", @@ -63,7 +61,6 @@ {% if cookiecutter.is_encoder_decoder_model == "False" %} _import_structure["models.{{cookiecutter.lowercase_modelname}}"].extend( [ - "TF_{{cookiecutter.uppercase_modelname}}_PRETRAINED_MODEL_ARCHIVE_LIST", "TF{{cookiecutter.camelcase_modelname}}ForMaskedLM", "TF{{cookiecutter.camelcase_modelname}}ForCausalLM", "TF{{cookiecutter.camelcase_modelname}}ForMultipleChoice", @@ -122,7 +119,7 @@ # Below: " # Models" # Replace with: - "models.{{cookiecutter.lowercase_modelname}}": ["{{cookiecutter.uppercase_modelname}}_PRETRAINED_CONFIG_ARCHIVE_MAP", "{{cookiecutter.camelcase_modelname}}Config", "{{cookiecutter.camelcase_modelname}}Tokenizer"], + "models.{{cookiecutter.lowercase_modelname}}": ["{{cookiecutter.camelcase_modelname}}Config", "{{cookiecutter.camelcase_modelname}}Tokenizer"], # End. # To replace in: "src/transformers/__init__.py" @@ -130,7 +127,6 @@ # Replace with: {% if cookiecutter.is_encoder_decoder_model == "False" %} from .models.{{cookiecutter.lowercase_modelname}} import ( - {{cookiecutter.uppercase_modelname}}_PRETRAINED_MODEL_ARCHIVE_LIST, {{cookiecutter.camelcase_modelname}}ForMaskedLM, {{cookiecutter.camelcase_modelname}}ForCausalLM, {{cookiecutter.camelcase_modelname}}ForMultipleChoice, @@ -144,7 +140,6 @@ ) {% else %} from .models.{{cookiecutter.lowercase_modelname}} import ( - {{cookiecutter.uppercase_modelname}}_PRETRAINED_MODEL_ARCHIVE_LIST, {{cookiecutter.camelcase_modelname}}ForConditionalGeneration, {{cookiecutter.camelcase_modelname}}ForCausalLM, {{cookiecutter.camelcase_modelname}}ForQuestionAnswering, @@ -159,8 +154,7 @@ # Replace with: {% if cookiecutter.is_encoder_decoder_model == "False" %} from .models.{{cookiecutter.lowercase_modelname}} import ( - TF_{{cookiecutter.uppercase_modelname}}_PRETRAINED_MODEL_ARCHIVE_LIST, - TF{{cookiecutter.camelcase_modelname}}ForMaskedLM, + TF_{{cookiecutter.uppercase_modelname}} TF{{cookiecutter.camelcase_modelname}}ForMaskedLM, TF{{cookiecutter.camelcase_modelname}}ForCausalLM, TF{{cookiecutter.camelcase_modelname}}ForMultipleChoice, TF{{cookiecutter.camelcase_modelname}}ForQuestionAnswering, @@ -209,9 +203,9 @@ from .models.{{cookiecutter.lowercase_modelname}} import {{cookiecutter.camelcase_modelname}}TokenizerFast # End. -# Below: " from .models.albert import ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, AlbertConfig" +# Below: " from .models.albert import AlbertConfig" # Replace with: - from .models.{{cookiecutter.lowercase_modelname}} import {{cookiecutter.uppercase_modelname}}_PRETRAINED_CONFIG_ARCHIVE_MAP, {{cookiecutter.camelcase_modelname}}Config, {{cookiecutter.camelcase_modelname}}Tokenizer + from .models.{{cookiecutter.lowercase_modelname}} import {{cookiecutter.uppercase_modelname}}{{cookiecutter.camelcase_modelname}}Config, {{cookiecutter.camelcase_modelname}}Tokenizer # End. @@ -229,11 +223,6 @@ ("{{cookiecutter.lowercase_modelname}}", "{{cookiecutter.camelcase_modelname}}Config"), # End. -# Below: "# Add archive maps here" -# Replace with: - ("{{cookiecutter.lowercase_modelname}}", "{{cookiecutter.uppercase_modelname}}_PRETRAINED_CONFIG_ARCHIVE_MAP"), -# End. - # Below: "# Add full (and cased) model names here" # Replace with: ("{{cookiecutter.lowercase_modelname}}", "{{cookiecutter.camelcase_modelname}}"), diff --git a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/tokenization_fast_{{cookiecutter.lowercase_modelname}}.py b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/tokenization_fast_{{cookiecutter.lowercase_modelname}}.py index 6e6c936983..3712c97029 100644 --- a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/tokenization_fast_{{cookiecutter.lowercase_modelname}}.py +++ b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/tokenization_fast_{{cookiecutter.lowercase_modelname}}.py @@ -30,15 +30,6 @@ PRETRAINED_VOCAB_FILES_MAP = { } } -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "{{cookiecutter.checkpoint_identifier}}": 512, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "{{cookiecutter.checkpoint_identifier}}": {"do_lower_case": False}, -} - class {{cookiecutter.camelcase_modelname}}TokenizerFast(BertTokenizerFast): r""" @@ -53,8 +44,6 @@ class {{cookiecutter.camelcase_modelname}}TokenizerFast(BertTokenizerFast): vocab_files_names = VOCAB_FILES_NAMES pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION slow_tokenizer_class = {{cookiecutter.camelcase_modelname}}Tokenizer {%- elif cookiecutter.tokenizer_type == "Based on BART" %} @@ -67,22 +56,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "{{cookiecutter.checkpoint_identifier}}": "https://huggingface.co/{{cookiecutter.checkpoint_identifier}}/resolve/main/vocab.json", - }, - "merges_file": { - "{{cookiecutter.checkpoint_identifier}}": "https://huggingface.co/{{cookiecutter.checkpoint_identifier}}/resolve/main/merges.txt", - }, - "tokenizer_file": { - "{{cookiecutter.checkpoint_identifier}}": "https://huggingface.co/{{cookiecutter.checkpoint_identifier}}/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "{{cookiecutter.checkpoint_identifier}}": 1024, -} - class {{cookiecutter.camelcase_modelname}}TokenizerFast(BartTokenizerFast): r""" @@ -96,8 +69,6 @@ class {{cookiecutter.camelcase_modelname}}TokenizerFast(BartTokenizerFast): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = {{cookiecutter.camelcase_modelname}}Tokenizer {%- elif cookiecutter.tokenizer_type == "Standalone" %} @@ -114,19 +85,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "{{cookiecutter.checkpoint_identifier}}": "https://huggingface.co/{{cookiecutter.checkpoint_identifier}}/resolve/main/vocab.txt", - }, - "tokenizer_file": { - "{{cookiecutter.checkpoint_identifier}}": "https://huggingface.co/{{cookiecutter.checkpoint_identifier}}/resolve/main/tokenizer.json", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "{{cookiecutter.checkpoint_identifier}}": 1024, -} - class {{cookiecutter.camelcase_modelname}}TokenizerFast(PreTrainedTokenizerFast): """ Construct a "fast" {{cookiecutter.modelname}} tokenizer (backed by HuggingFace's *tokenizers* library). @@ -137,8 +95,6 @@ class {{cookiecutter.camelcase_modelname}}TokenizerFast(PreTrainedTokenizerFast) """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES slow_tokenizer_class = {{cookiecutter.camelcase_modelname}}Tokenizer def __init__( diff --git a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/tokenization_{{cookiecutter.lowercase_modelname}}.py b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/tokenization_{{cookiecutter.lowercase_modelname}}.py index a9c072f977..2f627adeb7 100644 --- a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/tokenization_{{cookiecutter.lowercase_modelname}}.py +++ b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/tokenization_{{cookiecutter.lowercase_modelname}}.py @@ -29,15 +29,6 @@ PRETRAINED_VOCAB_FILES_MAP = { } } -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "{{cookiecutter.checkpoint_identifier}}": 512, -} - - -PRETRAINED_INIT_CONFIGURATION = { - "{{cookiecutter.checkpoint_identifier}}": {"do_lower_case": False}, -} - class {{cookiecutter.camelcase_modelname}}Tokenizer(BertTokenizer): r""" @@ -52,8 +43,6 @@ class {{cookiecutter.camelcase_modelname}}Tokenizer(BertTokenizer): vocab_files_names = VOCAB_FILES_NAMES pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES - pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION {%- elif cookiecutter.tokenizer_type == "Based on BART" %} from ...utils import logging @@ -64,19 +53,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "{{cookiecutter.checkpoint_identifier}}": "https://huggingface.co/{{cookiecutter.checkpoint_identifier}}/resolve/main/vocab.json", - }, - "merges_file": { - "{{cookiecutter.checkpoint_identifier}}": "https://huggingface.co/{{cookiecutter.checkpoint_identifier}}/resolve/main/merges.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "{{cookiecutter.checkpoint_identifier}}": 1024, -} - class {{cookiecutter.camelcase_modelname}}Tokenizer(BartTokenizer): """ @@ -90,8 +66,6 @@ class {{cookiecutter.camelcase_modelname}}Tokenizer(BartTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES {%- elif cookiecutter.tokenizer_type == "Standalone" %} from typing import List, Optional @@ -107,15 +81,6 @@ logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} -PRETRAINED_VOCAB_FILES_MAP = { - "vocab_file": { - "{{cookiecutter.checkpoint_identifier}}": "https://huggingface.co/{{cookiecutter.checkpoint_identifier}}/resolve/main/vocab.txt", - }, -} - -PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { - "{{cookiecutter.checkpoint_identifier}}": 1024, -} class {{cookiecutter.camelcase_modelname}}Tokenizer(PreTrainedTokenizer): """ @@ -127,8 +92,6 @@ class {{cookiecutter.camelcase_modelname}}Tokenizer(PreTrainedTokenizer): """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( @@ -269,8 +232,6 @@ class {{cookiecutter.camelcase_modelname}}TokenizerFast(PreTrainedTokenizerFast) """ vocab_files_names = VOCAB_FILES_NAMES - pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP - max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( diff --git a/tests/models/albert/test_modeling_albert.py b/tests/models/albert/test_modeling_albert.py index 823315bc67..d1e5631b34 100644 --- a/tests/models/albert/test_modeling_albert.py +++ b/tests/models/albert/test_modeling_albert.py @@ -38,7 +38,6 @@ if is_torch_available(): AlbertForTokenClassification, AlbertModel, ) - from transformers.models.albert.modeling_albert import ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST class AlbertModelTester: @@ -322,9 +321,9 @@ class AlbertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = AlbertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "albert/albert-base-v1" + model = AlbertModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/albert/test_modeling_tf_albert.py b/tests/models/albert/test_modeling_tf_albert.py index 7bea29fa9c..a3dab618ee 100644 --- a/tests/models/albert/test_modeling_tf_albert.py +++ b/tests/models/albert/test_modeling_tf_albert.py @@ -32,7 +32,6 @@ if is_tf_available(): from transformers import TF_MODEL_FOR_PRETRAINING_MAPPING from transformers.models.albert.modeling_tf_albert import ( - TF_ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST, TFAlbertForMaskedLM, TFAlbertForMultipleChoice, TFAlbertForPreTraining, @@ -302,9 +301,9 @@ class TFAlbertModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCa @slow def test_model_from_pretrained(self): - for model_name in TF_ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFAlbertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "albert/albert-base-v1" + model = TFAlbertModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_tf diff --git a/tests/models/align/test_modeling_align.py b/tests/models/align/test_modeling_align.py index 2f32978994..ee50a1a74b 100644 --- a/tests/models/align/test_modeling_align.py +++ b/tests/models/align/test_modeling_align.py @@ -51,7 +51,6 @@ if is_torch_available(): AlignTextModel, AlignVisionModel, ) - from transformers.models.align.modeling_align import ALIGN_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -238,9 +237,9 @@ class AlignVisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in ALIGN_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = AlignVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "kakaobrain/align-base" + model = AlignVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) class AlignTextModelTester: @@ -390,9 +389,9 @@ class AlignTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in ALIGN_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = AlignTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "kakaobrain/align-base" + model = AlignTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) class AlignModelTester: @@ -599,9 +598,9 @@ class AlignModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in ALIGN_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = AlignModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "kakaobrain/align-base" + model = AlignModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/altclip/test_modeling_altclip.py b/tests/models/altclip/test_modeling_altclip.py index 10b0e167d7..8c5be789c0 100755 --- a/tests/models/altclip/test_modeling_altclip.py +++ b/tests/models/altclip/test_modeling_altclip.py @@ -43,7 +43,6 @@ if is_torch_available(): import torch.nn as nn from transformers import AltCLIPModel, AltCLIPTextModel, AltCLIPVisionModel - from transformers.models.altclip.modeling_altclip import ALTCLIP_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): from PIL import Image @@ -365,9 +364,9 @@ class AltCLIPTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in ALTCLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = AltCLIPTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "BAAI/AltCLIP" + model = AltCLIPTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) class AltCLIPModelTester: @@ -560,9 +559,9 @@ class AltCLIPModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in ALTCLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = AltCLIPModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "BAAI/AltCLIP" + model = AltCLIPModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_vision diff --git a/tests/models/audio_spectrogram_transformer/test_modeling_audio_spectrogram_transformer.py b/tests/models/audio_spectrogram_transformer/test_modeling_audio_spectrogram_transformer.py index ce596d84e3..564ca4d48c 100644 --- a/tests/models/audio_spectrogram_transformer/test_modeling_audio_spectrogram_transformer.py +++ b/tests/models/audio_spectrogram_transformer/test_modeling_audio_spectrogram_transformer.py @@ -33,9 +33,6 @@ if is_torch_available(): from torch import nn from transformers import ASTForAudioClassification, ASTModel - from transformers.models.audio_spectrogram_transformer.modeling_audio_spectrogram_transformer import ( - AUDIO_SPECTROGRAM_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST, - ) if is_torchaudio_available(): @@ -212,9 +209,9 @@ class ASTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in AUDIO_SPECTROGRAM_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ASTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "MIT/ast-finetuned-audioset-10-10-0.4593" + model = ASTModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on some audio from AudioSet diff --git a/tests/models/auto/test_modeling_auto.py b/tests/models/auto/test_modeling_auto.py index ab5fa95796..a8e42d77f9 100644 --- a/tests/models/auto/test_modeling_auto.py +++ b/tests/models/auto/test_modeling_auto.py @@ -85,10 +85,6 @@ if is_torch_available(): MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING, MODEL_MAPPING, ) - from transformers.models.bert.modeling_bert import BERT_PRETRAINED_MODEL_ARCHIVE_LIST - from transformers.models.gpt2.modeling_gpt2 import GPT2_PRETRAINED_MODEL_ARCHIVE_LIST - from transformers.models.t5.modeling_t5 import T5_PRETRAINED_MODEL_ARCHIVE_LIST - from transformers.models.tapas.modeling_tapas import TAPAS_PRETRAINED_MODEL_ARCHIVE_LIST @require_torch @@ -98,138 +94,134 @@ class AutoModelTest(unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, BertConfig) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, BertConfig) - model = AutoModel.from_pretrained(model_name) - model, loading_info = AutoModel.from_pretrained(model_name, output_loading_info=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, BertModel) + model = AutoModel.from_pretrained(model_name) + model, loading_info = AutoModel.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, BertModel) - self.assertEqual(len(loading_info["missing_keys"]), 0) - # When using PyTorch checkpoint, the expected value is `8`. With `safetensors` checkpoint (if it is - # installed), the expected value becomes `7`. - EXPECTED_NUM_OF_UNEXPECTED_KEYS = 7 if is_safetensors_available() else 8 - self.assertEqual(len(loading_info["unexpected_keys"]), EXPECTED_NUM_OF_UNEXPECTED_KEYS) - self.assertEqual(len(loading_info["mismatched_keys"]), 0) - self.assertEqual(len(loading_info["error_msgs"]), 0) + self.assertEqual(len(loading_info["missing_keys"]), 0) + # When using PyTorch checkpoint, the expected value is `8`. With `safetensors` checkpoint (if it is + # installed), the expected value becomes `7`. + EXPECTED_NUM_OF_UNEXPECTED_KEYS = 7 if is_safetensors_available() else 8 + self.assertEqual(len(loading_info["unexpected_keys"]), EXPECTED_NUM_OF_UNEXPECTED_KEYS) + self.assertEqual(len(loading_info["mismatched_keys"]), 0) + self.assertEqual(len(loading_info["error_msgs"]), 0) @slow def test_model_for_pretraining_from_pretrained(self): - for model_name in BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, BertConfig) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, BertConfig) - model = AutoModelForPreTraining.from_pretrained(model_name) - model, loading_info = AutoModelForPreTraining.from_pretrained(model_name, output_loading_info=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, BertForPreTraining) - # Only one value should not be initialized and in the missing keys. - for key, value in loading_info.items(): - self.assertEqual(len(value), 0) + model = AutoModelForPreTraining.from_pretrained(model_name) + model, loading_info = AutoModelForPreTraining.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, BertForPreTraining) + # Only one value should not be initialized and in the missing keys. + for key, value in loading_info.items(): + self.assertEqual(len(value), 0) @slow def test_lmhead_model_from_pretrained(self): - for model_name in BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, BertConfig) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, BertConfig) - model = AutoModelWithLMHead.from_pretrained(model_name) - model, loading_info = AutoModelWithLMHead.from_pretrained(model_name, output_loading_info=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, BertForMaskedLM) + model = AutoModelWithLMHead.from_pretrained(model_name) + model, loading_info = AutoModelWithLMHead.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, BertForMaskedLM) @slow def test_model_for_causal_lm(self): - for model_name in GPT2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, GPT2Config) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, GPT2Config) - model = AutoModelForCausalLM.from_pretrained(model_name) - model, loading_info = AutoModelForCausalLM.from_pretrained(model_name, output_loading_info=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, GPT2LMHeadModel) + model = AutoModelForCausalLM.from_pretrained(model_name) + model, loading_info = AutoModelForCausalLM.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, GPT2LMHeadModel) @slow def test_model_for_masked_lm(self): - for model_name in BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, BertConfig) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, BertConfig) - model = AutoModelForMaskedLM.from_pretrained(model_name) - model, loading_info = AutoModelForMaskedLM.from_pretrained(model_name, output_loading_info=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, BertForMaskedLM) + model = AutoModelForMaskedLM.from_pretrained(model_name) + model, loading_info = AutoModelForMaskedLM.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, BertForMaskedLM) @slow def test_model_for_encoder_decoder_lm(self): - for model_name in T5_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, T5Config) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, T5Config) - model = AutoModelForSeq2SeqLM.from_pretrained(model_name) - model, loading_info = AutoModelForSeq2SeqLM.from_pretrained(model_name, output_loading_info=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, T5ForConditionalGeneration) + model = AutoModelForSeq2SeqLM.from_pretrained(model_name) + model, loading_info = AutoModelForSeq2SeqLM.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, T5ForConditionalGeneration) @slow def test_sequence_classification_model_from_pretrained(self): - for model_name in BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, BertConfig) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, BertConfig) - model = AutoModelForSequenceClassification.from_pretrained(model_name) - model, loading_info = AutoModelForSequenceClassification.from_pretrained( - model_name, output_loading_info=True - ) - self.assertIsNotNone(model) - self.assertIsInstance(model, BertForSequenceClassification) + model = AutoModelForSequenceClassification.from_pretrained(model_name) + model, loading_info = AutoModelForSequenceClassification.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, BertForSequenceClassification) @slow def test_question_answering_model_from_pretrained(self): - for model_name in BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, BertConfig) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, BertConfig) - model = AutoModelForQuestionAnswering.from_pretrained(model_name) - model, loading_info = AutoModelForQuestionAnswering.from_pretrained(model_name, output_loading_info=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, BertForQuestionAnswering) + model = AutoModelForQuestionAnswering.from_pretrained(model_name) + model, loading_info = AutoModelForQuestionAnswering.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, BertForQuestionAnswering) @slow def test_table_question_answering_model_from_pretrained(self): - for model_name in TAPAS_PRETRAINED_MODEL_ARCHIVE_LIST[5:6]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, TapasConfig) + model_name = "google/tapas-base" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, TapasConfig) - model = AutoModelForTableQuestionAnswering.from_pretrained(model_name) - model, loading_info = AutoModelForTableQuestionAnswering.from_pretrained( - model_name, output_loading_info=True - ) - self.assertIsNotNone(model) - self.assertIsInstance(model, TapasForQuestionAnswering) + model = AutoModelForTableQuestionAnswering.from_pretrained(model_name) + model, loading_info = AutoModelForTableQuestionAnswering.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, TapasForQuestionAnswering) @slow def test_token_classification_model_from_pretrained(self): - for model_name in BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, BertConfig) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, BertConfig) - model = AutoModelForTokenClassification.from_pretrained(model_name) - model, loading_info = AutoModelForTokenClassification.from_pretrained(model_name, output_loading_info=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, BertForTokenClassification) + model = AutoModelForTokenClassification.from_pretrained(model_name) + model, loading_info = AutoModelForTokenClassification.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, BertForTokenClassification) @slow def test_auto_backbone_timm_model_from_pretrained(self): diff --git a/tests/models/auto/test_modeling_tf_auto.py b/tests/models/auto/test_modeling_tf_auto.py index e075861087..53a07b1970 100644 --- a/tests/models/auto/test_modeling_tf_auto.py +++ b/tests/models/auto/test_modeling_tf_auto.py @@ -65,10 +65,6 @@ if is_tf_available(): TF_MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING, TF_MODEL_MAPPING, ) - from transformers.models.bert.modeling_tf_bert import TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST - from transformers.models.gpt2.modeling_tf_gpt2 import TF_GPT2_PRETRAINED_MODEL_ARCHIVE_LIST - from transformers.models.t5.modeling_tf_t5 import TF_T5_PRETRAINED_MODEL_ARCHIVE_LIST - from transformers.models.tapas.modeling_tf_tapas import TF_TAPAS_PRETRAINED_MODEL_ARCHIVE_LIST class NewModelConfig(BertConfig): @@ -107,54 +103,54 @@ class TFAutoModelTest(unittest.TestCase): @slow def test_model_for_causal_lm(self): - for model_name in TF_GPT2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, GPT2Config) + model_name = "openai-community/gpt2" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, GPT2Config) - model = TFAutoModelForCausalLM.from_pretrained(model_name) - model, loading_info = TFAutoModelForCausalLM.from_pretrained(model_name, output_loading_info=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, TFGPT2LMHeadModel) + model = TFAutoModelForCausalLM.from_pretrained(model_name) + model, loading_info = TFAutoModelForCausalLM.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, TFGPT2LMHeadModel) @slow def test_lmhead_model_from_pretrained(self): - for model_name in TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, BertConfig) + model_name = "openai-community/gpt2" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, BertConfig) - model = TFAutoModelWithLMHead.from_pretrained(model_name) - self.assertIsNotNone(model) - self.assertIsInstance(model, TFBertForMaskedLM) + model = TFAutoModelWithLMHead.from_pretrained(model_name) + self.assertIsNotNone(model) + self.assertIsInstance(model, TFBertForMaskedLM) @slow def test_model_for_masked_lm(self): - for model_name in TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, BertConfig) + model_name = "openai-community/gpt2" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, BertConfig) - model = TFAutoModelForMaskedLM.from_pretrained(model_name) - model, loading_info = TFAutoModelForMaskedLM.from_pretrained(model_name, output_loading_info=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, TFBertForMaskedLM) + model = TFAutoModelForMaskedLM.from_pretrained(model_name) + model, loading_info = TFAutoModelForMaskedLM.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, TFBertForMaskedLM) @slow def test_model_for_encoder_decoder_lm(self): - for model_name in TF_T5_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, T5Config) + model_name = "openai-community/gpt2" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, T5Config) - model = TFAutoModelForSeq2SeqLM.from_pretrained(model_name) - model, loading_info = TFAutoModelForSeq2SeqLM.from_pretrained(model_name, output_loading_info=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, TFT5ForConditionalGeneration) + model = TFAutoModelForSeq2SeqLM.from_pretrained(model_name) + model, loading_info = TFAutoModelForSeq2SeqLM.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, TFT5ForConditionalGeneration) @slow def test_sequence_classification_model_from_pretrained(self): - # for model_name in TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: + # model_name = 'openai-community/gpt2' for model_name in ["google-bert/bert-base-uncased"]: config = AutoConfig.from_pretrained(model_name) self.assertIsNotNone(config) @@ -166,7 +162,7 @@ class TFAutoModelTest(unittest.TestCase): @slow def test_question_answering_model_from_pretrained(self): - # for model_name in TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: + # model_name = 'openai-community/gpt2' for model_name in ["google-bert/bert-base-uncased"]: config = AutoConfig.from_pretrained(model_name) self.assertIsNotNone(config) @@ -179,17 +175,17 @@ class TFAutoModelTest(unittest.TestCase): @slow @require_tensorflow_probability def test_table_question_answering_model_from_pretrained(self): - for model_name in TF_TAPAS_PRETRAINED_MODEL_ARCHIVE_LIST[5:6]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, TapasConfig) + model_name = "google/tapas-base" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, TapasConfig) - model = TFAutoModelForTableQuestionAnswering.from_pretrained(model_name) - model, loading_info = TFAutoModelForTableQuestionAnswering.from_pretrained( - model_name, output_loading_info=True - ) - self.assertIsNotNone(model) - self.assertIsInstance(model, TFTapasForQuestionAnswering) + model = TFAutoModelForTableQuestionAnswering.from_pretrained(model_name) + model, loading_info = TFAutoModelForTableQuestionAnswering.from_pretrained( + model_name, output_loading_info=True + ) + self.assertIsNotNone(model) + self.assertIsInstance(model, TFTapasForQuestionAnswering) def test_from_pretrained_identifier(self): model = TFAutoModelWithLMHead.from_pretrained(SMALL_MODEL_IDENTIFIER) diff --git a/tests/models/auto/test_modeling_tf_pytorch.py b/tests/models/auto/test_modeling_tf_pytorch.py index 77b19a8e3a..5b9036cbf1 100644 --- a/tests/models/auto/test_modeling_tf_pytorch.py +++ b/tests/models/auto/test_modeling_tf_pytorch.py @@ -45,9 +45,6 @@ if is_tf_available(): TFRobertaForMaskedLM, TFT5ForConditionalGeneration, ) - from transformers.models.bert.modeling_tf_bert import TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST - from transformers.models.gpt2.modeling_tf_gpt2 import TF_GPT2_PRETRAINED_MODEL_ARCHIVE_LIST - from transformers.models.t5.modeling_tf_t5 import TF_T5_PRETRAINED_MODEL_ARCHIVE_LIST if is_torch_available(): from transformers import ( @@ -74,7 +71,7 @@ if is_torch_available(): class TFPTAutoModelTest(unittest.TestCase): @slow def test_model_from_pretrained(self): - # for model_name in TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: + # model_name = 'google-bert/bert-base-uncased' for model_name in ["google-bert/bert-base-uncased"]: config = AutoConfig.from_pretrained(model_name) self.assertIsNotNone(config) @@ -90,7 +87,7 @@ class TFPTAutoModelTest(unittest.TestCase): @slow def test_model_for_pretraining_from_pretrained(self): - # for model_name in TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: + # model_name = 'google-bert/bert-base-uncased' for model_name in ["google-bert/bert-base-uncased"]: config = AutoConfig.from_pretrained(model_name) self.assertIsNotNone(config) @@ -106,85 +103,79 @@ class TFPTAutoModelTest(unittest.TestCase): @slow def test_model_for_causal_lm(self): - for model_name in TF_GPT2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, GPT2Config) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, GPT2Config) - model = TFAutoModelForCausalLM.from_pretrained(model_name, from_pt=True) - model, loading_info = TFAutoModelForCausalLM.from_pretrained( - model_name, output_loading_info=True, from_pt=True - ) - self.assertIsNotNone(model) - self.assertIsInstance(model, TFGPT2LMHeadModel) + model = TFAutoModelForCausalLM.from_pretrained(model_name, from_pt=True) + model, loading_info = TFAutoModelForCausalLM.from_pretrained( + model_name, output_loading_info=True, from_pt=True + ) + self.assertIsNotNone(model) + self.assertIsInstance(model, TFGPT2LMHeadModel) - model = AutoModelForCausalLM.from_pretrained(model_name, from_tf=True) - model, loading_info = AutoModelForCausalLM.from_pretrained( - model_name, output_loading_info=True, from_tf=True - ) - self.assertIsNotNone(model) - self.assertIsInstance(model, GPT2LMHeadModel) + model = AutoModelForCausalLM.from_pretrained(model_name, from_tf=True) + model, loading_info = AutoModelForCausalLM.from_pretrained(model_name, output_loading_info=True, from_tf=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, GPT2LMHeadModel) @slow def test_lmhead_model_from_pretrained(self): - for model_name in TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, BertConfig) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, BertConfig) - model = TFAutoModelWithLMHead.from_pretrained(model_name, from_pt=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, TFBertForMaskedLM) + model = TFAutoModelWithLMHead.from_pretrained(model_name, from_pt=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, TFBertForMaskedLM) - model = AutoModelWithLMHead.from_pretrained(model_name, from_tf=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, BertForMaskedLM) + model = AutoModelWithLMHead.from_pretrained(model_name, from_tf=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, BertForMaskedLM) @slow def test_model_for_masked_lm(self): - for model_name in TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, BertConfig) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, BertConfig) - model = TFAutoModelForMaskedLM.from_pretrained(model_name, from_pt=True) - model, loading_info = TFAutoModelForMaskedLM.from_pretrained( - model_name, output_loading_info=True, from_pt=True - ) - self.assertIsNotNone(model) - self.assertIsInstance(model, TFBertForMaskedLM) + model = TFAutoModelForMaskedLM.from_pretrained(model_name, from_pt=True) + model, loading_info = TFAutoModelForMaskedLM.from_pretrained( + model_name, output_loading_info=True, from_pt=True + ) + self.assertIsNotNone(model) + self.assertIsInstance(model, TFBertForMaskedLM) - model = AutoModelForMaskedLM.from_pretrained(model_name, from_tf=True) - model, loading_info = AutoModelForMaskedLM.from_pretrained( - model_name, output_loading_info=True, from_tf=True - ) - self.assertIsNotNone(model) - self.assertIsInstance(model, BertForMaskedLM) + model = AutoModelForMaskedLM.from_pretrained(model_name, from_tf=True) + model, loading_info = AutoModelForMaskedLM.from_pretrained(model_name, output_loading_info=True, from_tf=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, BertForMaskedLM) @slow def test_model_for_encoder_decoder_lm(self): - for model_name in TF_T5_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = AutoConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, T5Config) + model_name = "google-bert/bert-base-uncased" + config = AutoConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, T5Config) - model = TFAutoModelForSeq2SeqLM.from_pretrained(model_name, from_pt=True) - model, loading_info = TFAutoModelForSeq2SeqLM.from_pretrained( - model_name, output_loading_info=True, from_pt=True - ) - self.assertIsNotNone(model) - self.assertIsInstance(model, TFT5ForConditionalGeneration) + model = TFAutoModelForSeq2SeqLM.from_pretrained(model_name, from_pt=True) + model, loading_info = TFAutoModelForSeq2SeqLM.from_pretrained( + model_name, output_loading_info=True, from_pt=True + ) + self.assertIsNotNone(model) + self.assertIsInstance(model, TFT5ForConditionalGeneration) - model = AutoModelForSeq2SeqLM.from_pretrained(model_name, from_tf=True) - model, loading_info = AutoModelForSeq2SeqLM.from_pretrained( - model_name, output_loading_info=True, from_tf=True - ) - self.assertIsNotNone(model) - self.assertIsInstance(model, T5ForConditionalGeneration) + model = AutoModelForSeq2SeqLM.from_pretrained(model_name, from_tf=True) + model, loading_info = AutoModelForSeq2SeqLM.from_pretrained(model_name, output_loading_info=True, from_tf=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, T5ForConditionalGeneration) @slow def test_sequence_classification_model_from_pretrained(self): - # for model_name in TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: + # model_name = 'google-bert/bert-base-uncased' for model_name in ["google-bert/bert-base-uncased"]: config = AutoConfig.from_pretrained(model_name) self.assertIsNotNone(config) @@ -200,7 +191,7 @@ class TFPTAutoModelTest(unittest.TestCase): @slow def test_question_answering_model_from_pretrained(self): - # for model_name in TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: + # model_name = 'google-bert/bert-base-uncased' for model_name in ["google-bert/bert-base-uncased"]: config = AutoConfig.from_pretrained(model_name) self.assertIsNotNone(config) diff --git a/tests/models/auto/test_tokenization_auto.py b/tests/models/auto/test_tokenization_auto.py index 7d4a302e4f..ad96064308 100644 --- a/tests/models/auto/test_tokenization_auto.py +++ b/tests/models/auto/test_tokenization_auto.py @@ -25,8 +25,6 @@ import pytest import transformers from transformers import ( - BERT_PRETRAINED_CONFIG_ARCHIVE_MAP, - GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP, AutoTokenizer, BertConfig, BertTokenizer, @@ -72,13 +70,13 @@ class AutoTokenizerTest(unittest.TestCase): @slow def test_tokenizer_from_pretrained(self): - for model_name in (x for x in BERT_PRETRAINED_CONFIG_ARCHIVE_MAP.keys() if "japanese" not in x): + for model_name in {"google-bert/bert-base-uncased", "google-bert/bert-base-cased"}: tokenizer = AutoTokenizer.from_pretrained(model_name) self.assertIsNotNone(tokenizer) self.assertIsInstance(tokenizer, (BertTokenizer, BertTokenizerFast)) self.assertGreater(len(tokenizer), 0) - for model_name in GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP.keys(): + for model_name in ["openai-community/gpt2", "openai-community/gpt2-medium"]: tokenizer = AutoTokenizer.from_pretrained(model_name) self.assertIsNotNone(tokenizer) self.assertIsInstance(tokenizer, (GPT2Tokenizer, GPT2TokenizerFast)) diff --git a/tests/models/beit/test_modeling_beit.py b/tests/models/beit/test_modeling_beit.py index f82cf40cda..50287cb7bc 100644 --- a/tests/models/beit/test_modeling_beit.py +++ b/tests/models/beit/test_modeling_beit.py @@ -42,7 +42,6 @@ if is_torch_available(): BeitModel, ) from transformers.models.auto.modeling_auto import MODEL_FOR_BACKBONE_MAPPING_NAMES, MODEL_MAPPING_NAMES - from transformers.models.beit.modeling_beit import BEIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -385,9 +384,9 @@ class BeitModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in BEIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BeitModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/beit-base-patch16-224" + model = BeitModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/bert/test_modeling_bert.py b/tests/models/bert/test_modeling_bert.py index bc38356852..bdc812ff27 100644 --- a/tests/models/bert/test_modeling_bert.py +++ b/tests/models/bert/test_modeling_bert.py @@ -42,7 +42,6 @@ if is_torch_available(): BertModel, logging, ) - from transformers.models.bert.modeling_bert import BERT_PRETRAINED_MODEL_ARCHIVE_LIST class BertModelTester: @@ -596,9 +595,9 @@ class BertModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin @slow def test_model_from_pretrained(self): - for model_name in BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google-bert/bert-base-uncased" + model = BertModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow @require_torch_accelerator diff --git a/tests/models/big_bird/test_modeling_big_bird.py b/tests/models/big_bird/test_modeling_big_bird.py index e3ae650c56..02af95879a 100644 --- a/tests/models/big_bird/test_modeling_big_bird.py +++ b/tests/models/big_bird/test_modeling_big_bird.py @@ -41,7 +41,6 @@ if is_torch_available(): BigBirdForTokenClassification, BigBirdModel, ) - from transformers.models.big_bird.modeling_big_bird import BIG_BIRD_PRETRAINED_MODEL_ARCHIVE_LIST class BigBirdModelTester: @@ -561,9 +560,9 @@ class BigBirdModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in BIG_BIRD_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BigBirdForPreTraining.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/bigbird-roberta-base" + model = BigBirdForPreTraining.from_pretrained(model_name) + self.assertIsNotNone(model) def test_model_various_attn_type(self): config_and_inputs = self.model_tester.prepare_config_and_inputs() diff --git a/tests/models/biogpt/test_modeling_biogpt.py b/tests/models/biogpt/test_modeling_biogpt.py index b74cbdcb0f..1055288e5c 100644 --- a/tests/models/biogpt/test_modeling_biogpt.py +++ b/tests/models/biogpt/test_modeling_biogpt.py @@ -36,7 +36,6 @@ if is_torch_available(): BioGptModel, BioGptTokenizer, ) - from transformers.models.biogpt.modeling_biogpt import BIOGPT_PRETRAINED_MODEL_ARCHIVE_LIST class BioGptModelTester: @@ -382,9 +381,9 @@ class BioGptModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMix @slow def test_model_from_pretrained(self): - for model_name in BIOGPT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BioGptModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/biogpt" + model = BioGptModel.from_pretrained(model_name) + self.assertIsNotNone(model) # Copied from tests.models.opt.test_modeling_opt.OPTModelTest.test_opt_sequence_classification_model with OPT->BioGpt,opt->biogpt,prepare_config_and_inputs->prepare_config_and_inputs_for_common def test_biogpt_sequence_classification_model(self): diff --git a/tests/models/bit/test_modeling_bit.py b/tests/models/bit/test_modeling_bit.py index 1705aad976..dbc4cacdeb 100644 --- a/tests/models/bit/test_modeling_bit.py +++ b/tests/models/bit/test_modeling_bit.py @@ -32,7 +32,6 @@ if is_torch_available(): from torch import nn from transformers import BitBackbone, BitForImageClassification, BitImageProcessor, BitModel - from transformers.models.bit.modeling_bit import BIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -269,9 +268,9 @@ class BitModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in BIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BitModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/bit-50" + model = BitModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats @@ -285,13 +284,11 @@ def prepare_img(): class BitModelIntegrationTest(unittest.TestCase): @cached_property def default_image_processor(self): - return ( - BitImageProcessor.from_pretrained(BIT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) if is_vision_available() else None - ) + return BitImageProcessor.from_pretrained("google/bit-50") if is_vision_available() else None @slow def test_inference_image_classification_head(self): - model = BitForImageClassification.from_pretrained(BIT_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device) + model = BitForImageClassification.from_pretrained("google/bit-50").to(torch_device) image_processor = self.default_image_processor image = prepare_img() diff --git a/tests/models/blip/test_modeling_blip.py b/tests/models/blip/test_modeling_blip.py index 51f1690ff1..9529abc272 100644 --- a/tests/models/blip/test_modeling_blip.py +++ b/tests/models/blip/test_modeling_blip.py @@ -57,7 +57,6 @@ if is_torch_available(): BlipTextModel, BlipVisionModel, ) - from transformers.models.blip.modeling_blip import BLIP_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -223,9 +222,9 @@ class BlipVisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in BLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BlipVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip-vqa-base" + model = BlipVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) class BlipTextModelTester: @@ -369,9 +368,9 @@ class BlipTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in BLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BlipTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip-vqa-base" + model = BlipTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_pt_tf_model_equivalence(self): super().test_pt_tf_model_equivalence(allow_missing_keys=True) @@ -579,9 +578,9 @@ class BlipModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in BLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BlipModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip-vqa-base" + model = BlipModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_pt_tf_model_equivalence(self): super().test_pt_tf_model_equivalence(allow_missing_keys=True) @@ -1038,9 +1037,9 @@ class BlipTextRetrievalModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in BLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BlipModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip-vqa-base" + model = BlipModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch @@ -1254,9 +1253,9 @@ class BlipTextImageModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in BLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BlipModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip-vqa-base" + model = BlipModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/blip/test_modeling_blip_text.py b/tests/models/blip/test_modeling_blip_text.py index c004a8934e..3c12a7e9ea 100644 --- a/tests/models/blip/test_modeling_blip_text.py +++ b/tests/models/blip/test_modeling_blip_text.py @@ -29,7 +29,6 @@ if is_torch_available(): import torch from transformers import BlipTextModel - from transformers.models.blip.modeling_blip import BLIP_PRETRAINED_MODEL_ARCHIVE_LIST class BlipTextModelTester: @@ -173,9 +172,9 @@ class BlipTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in BLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BlipTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip-vqa-base" + model = BlipTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_pt_tf_model_equivalence(self): super().test_pt_tf_model_equivalence(allow_missing_keys=True) diff --git a/tests/models/blip/test_modeling_tf_blip.py b/tests/models/blip/test_modeling_tf_blip.py index 11e18403dc..a35eb7a1bd 100644 --- a/tests/models/blip/test_modeling_tf_blip.py +++ b/tests/models/blip/test_modeling_tf_blip.py @@ -45,7 +45,6 @@ if is_tf_available(): TFBlipVisionModel, ) from transformers.modeling_tf_utils import keras - from transformers.models.blip.modeling_tf_blip import TF_BLIP_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -191,9 +190,9 @@ class TFBlipVisionModelTest(TFModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in TF_BLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFBlipVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip-vqa-base" + model = TFBlipVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) class TFBlipTextModelTester: @@ -319,9 +318,9 @@ class TFBlipTextModelTest(TFModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in TF_BLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFBlipTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip-vqa-base" + model = TFBlipTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_pt_tf_model_equivalence(self, allow_missing_keys=True): super().test_pt_tf_model_equivalence(allow_missing_keys=allow_missing_keys) @@ -428,9 +427,9 @@ class TFBlipModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in TF_BLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFBlipModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip-vqa-base" + model = TFBlipModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_pt_tf_model_equivalence(self, allow_missing_keys=True): super().test_pt_tf_model_equivalence(allow_missing_keys=allow_missing_keys) @@ -716,9 +715,9 @@ class TFBlipTextRetrievalModelTest(TFModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in TF_BLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFBlipModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip-vqa-base" + model = TFBlipModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip(reason="Tested in individual model tests") def test_compile_tf_model(self): @@ -831,9 +830,9 @@ class TFBlipTextImageModelTest(TFModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in TF_BLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFBlipModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip-vqa-base" + model = TFBlipModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/blip/test_modeling_tf_blip_text.py b/tests/models/blip/test_modeling_tf_blip_text.py index a21bdd109f..7583b61b58 100644 --- a/tests/models/blip/test_modeling_tf_blip_text.py +++ b/tests/models/blip/test_modeling_tf_blip_text.py @@ -31,7 +31,6 @@ if is_tf_available(): import tensorflow as tf from transformers import TFBlipTextModel - from transformers.models.blip.modeling_tf_blip import TF_BLIP_PRETRAINED_MODEL_ARCHIVE_LIST class BlipTextModelTester: @@ -173,9 +172,9 @@ class BlipTextModelTest(TFModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in TF_BLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFBlipTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip-vqa-base" + model = TFBlipTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_pt_tf_model_equivalence(self, allow_missing_keys=True): super().test_pt_tf_model_equivalence(allow_missing_keys=allow_missing_keys) diff --git a/tests/models/blip_2/test_modeling_blip_2.py b/tests/models/blip_2/test_modeling_blip_2.py index 4abbba22f5..ccf3051a17 100644 --- a/tests/models/blip_2/test_modeling_blip_2.py +++ b/tests/models/blip_2/test_modeling_blip_2.py @@ -49,7 +49,6 @@ if is_torch_available(): from torch import nn from transformers import Blip2ForConditionalGeneration, Blip2Model, Blip2VisionModel - from transformers.models.blip_2.modeling_blip_2 import BLIP_2_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -217,9 +216,9 @@ class Blip2VisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in BLIP_2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Blip2VisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip2-opt-2.7b" + model = Blip2VisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) class Blip2QFormerModelTester: @@ -504,9 +503,9 @@ class Blip2ForConditionalGenerationDecoderOnlyTest(ModelTesterMixin, GenerationT @slow def test_model_from_pretrained(self): - for model_name in BLIP_2_PRETRAINED_MODEL_ARCHIVE_LIST: - model = Blip2ForConditionalGeneration.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip2-opt-2.7b" + model = Blip2ForConditionalGeneration.from_pretrained(model_name) + self.assertIsNotNone(model) # this class is based on `T5ModelTester` found in tests/models/t5/test_modeling_t5.py @@ -766,9 +765,9 @@ class Blip2ModelTest(ModelTesterMixin, PipelineTesterMixin, GenerationTesterMixi @slow def test_model_from_pretrained(self): - for model_name in BLIP_2_PRETRAINED_MODEL_ARCHIVE_LIST: - model = Blip2ForConditionalGeneration.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/blip2-opt-2.7b" + model = Blip2ForConditionalGeneration.from_pretrained(model_name) + self.assertIsNotNone(model) def test_get_text_features(self): config, _ = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/bloom/test_modeling_bloom.py b/tests/models/bloom/test_modeling_bloom.py index 95160179c2..d0ee36dc3c 100644 --- a/tests/models/bloom/test_modeling_bloom.py +++ b/tests/models/bloom/test_modeling_bloom.py @@ -30,7 +30,6 @@ if is_torch_available(): import torch from transformers import ( - BLOOM_PRETRAINED_MODEL_ARCHIVE_LIST, BloomForCausalLM, BloomForQuestionAnswering, BloomForSequenceClassification, @@ -396,9 +395,9 @@ class BloomModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixi @slow def test_model_from_pretrained(self): - for model_name in BLOOM_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BloomModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "bigscience/bigscience-small-testing" + model = BloomModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow @require_torch_accelerator diff --git a/tests/models/bloom/test_tokenization_bloom.py b/tests/models/bloom/test_tokenization_bloom.py index 4fbfcb8923..fec0f83af9 100644 --- a/tests/models/bloom/test_tokenization_bloom.py +++ b/tests/models/bloom/test_tokenization_bloom.py @@ -132,13 +132,6 @@ class BloomTokenizationTest(TokenizerTesterMixin, unittest.TestCase): predicted_text = [tokenizer.decode(x, clean_up_tokenization_spaces=False) for x in output_tokens] self.assertListEqual(predicted_text, input_text) - def test_pretrained_model_lists(self): - # The test has to be overriden because BLOOM uses ALiBi positional embeddings that does not have - # any sequence length constraints. This test of the parent class will fail since it relies on the - # maximum sequence length of the positoonal embeddings. - self.assertGreaterEqual(len(self.tokenizer_class.pretrained_vocab_files_map), 1) - self.assertGreaterEqual(len(list(self.tokenizer_class.pretrained_vocab_files_map.values())[0]), 1) - @require_jinja def test_tokenization_for_chat(self): tokenizer = self.get_rust_tokenizer() diff --git a/tests/models/bridgetower/test_modeling_bridgetower.py b/tests/models/bridgetower/test_modeling_bridgetower.py index 8c7bd00ee6..971ea4f08a 100644 --- a/tests/models/bridgetower/test_modeling_bridgetower.py +++ b/tests/models/bridgetower/test_modeling_bridgetower.py @@ -49,7 +49,6 @@ if is_torch_available(): BridgeTowerForMaskedLM, BridgeTowerModel, ) - from transformers.models.bridgetower.modeling_bridgetower import BRIDGETOWER_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): from PIL import Image @@ -356,9 +355,9 @@ class BridgeTowerModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestC @slow def test_model_from_pretrained(self): - for model_name in BRIDGETOWER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BridgeTowerModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "BridgeTower/bridgetower-base" + model = BridgeTowerModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow def test_save_load_fast_init_from_base(self): diff --git a/tests/models/bros/test_modeling_bros.py b/tests/models/bros/test_modeling_bros.py index c4fbaa2f98..755deefcb4 100644 --- a/tests/models/bros/test_modeling_bros.py +++ b/tests/models/bros/test_modeling_bros.py @@ -35,9 +35,6 @@ if is_torch_available(): BrosSpadeEEForTokenClassification, BrosSpadeELForTokenClassification, ) - from transformers.models.bros.modeling_bros import ( - BROS_PRETRAINED_MODEL_ARCHIVE_LIST, - ) class BrosModelTester: @@ -370,9 +367,9 @@ class BrosModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in BROS_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = BrosModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "jinho8345/bros-base-uncased" + model = BrosModel.from_pretrained(model_name) + self.assertIsNotNone(model) def prepare_bros_batch_inputs(): diff --git a/tests/models/byt5/test_tokenization_byt5.py b/tests/models/byt5/test_tokenization_byt5.py index bfc36070b2..3793241d7e 100644 --- a/tests/models/byt5/test_tokenization_byt5.py +++ b/tests/models/byt5/test_tokenization_byt5.py @@ -300,10 +300,6 @@ class ByT5TokenizationTest(TokenizerTesterMixin, unittest.TestCase): self.assertTrue(tokenizer.decode([255]) == "") - # tokenizer can be instantiated without any pretrained files, so no need for pretrained tokenizer list - def test_pretrained_model_lists(self): - pass - # tokenizer does not have vocabulary def test_get_vocab(self): pass diff --git a/tests/models/canine/test_modeling_canine.py b/tests/models/canine/test_modeling_canine.py index f10823fc56..eeb5aa40dd 100644 --- a/tests/models/canine/test_modeling_canine.py +++ b/tests/models/canine/test_modeling_canine.py @@ -36,7 +36,6 @@ if is_torch_available(): CanineForTokenClassification, CanineModel, ) - from transformers.models.canine.modeling_canine import CANINE_PRETRAINED_MODEL_ARCHIVE_LIST class CanineModelTester: @@ -527,9 +526,9 @@ class CanineModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in CANINE_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = CanineModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/canine-s" + model = CanineModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/canine/test_tokenization_canine.py b/tests/models/canine/test_tokenization_canine.py index eb3e6d9b4a..ec987f6dd6 100644 --- a/tests/models/canine/test_tokenization_canine.py +++ b/tests/models/canine/test_tokenization_canine.py @@ -320,10 +320,6 @@ class CanineTokenizationTest(TokenizerTesterMixin, unittest.TestCase): def test_torch_encode_plus_sent_to_model(self): pass - # tokenizer can be instantiated without any pretrained files, so no need for pretrained tokenizer list - def test_pretrained_model_lists(self): - pass - # tokenizer does not have vocabulary def test_get_vocab(self): pass diff --git a/tests/models/chinese_clip/test_modeling_chinese_clip.py b/tests/models/chinese_clip/test_modeling_chinese_clip.py index 06c946bf10..8ee9028eca 100644 --- a/tests/models/chinese_clip/test_modeling_chinese_clip.py +++ b/tests/models/chinese_clip/test_modeling_chinese_clip.py @@ -48,7 +48,6 @@ if is_torch_available(): ChineseCLIPTextModel, ChineseCLIPVisionModel, ) - from transformers.models.chinese_clip.modeling_chinese_clip import CHINESE_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -385,9 +384,9 @@ class ChineseCLIPTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in CHINESE_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ChineseCLIPTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "OFA-Sys/chinese-clip-vit-base-patch16" + model = ChineseCLIPTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_training(self): pass @@ -495,9 +494,9 @@ class ChineseCLIPVisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in CHINESE_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ChineseCLIPVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "OFA-Sys/chinese-clip-vit-base-patch16" + model = ChineseCLIPVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) class ChineseCLIPModelTester: @@ -693,9 +692,9 @@ class ChineseCLIPModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestC @slow def test_model_from_pretrained(self): - for model_name in CHINESE_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ChineseCLIPModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "OFA-Sys/chinese-clip-vit-base-patch16" + model = ChineseCLIPModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of Pikachu diff --git a/tests/models/clap/test_modeling_clap.py b/tests/models/clap/test_modeling_clap.py index fe3e8b0e54..f06fabf0a2 100644 --- a/tests/models/clap/test_modeling_clap.py +++ b/tests/models/clap/test_modeling_clap.py @@ -49,7 +49,6 @@ if is_torch_available(): ClapTextModel, ClapTextModelWithProjection, ) - from transformers.models.clap.modeling_clap import CLAP_PRETRAINED_MODEL_ARCHIVE_LIST class ClapAudioModelTester: @@ -275,16 +274,16 @@ class ClapAudioModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in CLAP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ClapAudioModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "laion/clap-htsat-fused" + model = ClapAudioModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow def test_model_with_projection_from_pretrained(self): - for model_name in CLAP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ClapAudioModelWithProjection.from_pretrained(model_name) - self.assertIsNotNone(model) - self.assertTrue(hasattr(model, "audio_projection")) + model_name = "laion/clap-htsat-fused" + model = ClapAudioModelWithProjection.from_pretrained(model_name) + self.assertIsNotNone(model) + self.assertTrue(hasattr(model, "audio_projection")) class ClapTextModelTester: @@ -444,16 +443,16 @@ class ClapTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in CLAP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ClapTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "laion/clap-htsat-fused" + model = ClapTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow def test_model_with_projection_from_pretrained(self): - for model_name in CLAP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ClapTextModelWithProjection.from_pretrained(model_name) - self.assertIsNotNone(model) - self.assertTrue(hasattr(model, "text_projection")) + model_name = "laion/clap-htsat-fused" + model = ClapTextModelWithProjection.from_pretrained(model_name) + self.assertIsNotNone(model) + self.assertTrue(hasattr(model, "text_projection")) class ClapModelTester: @@ -650,9 +649,9 @@ class ClapModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in CLAP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ClapModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "laion/clap-htsat-fused" + model = ClapModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow diff --git a/tests/models/clip/test_modeling_clip.py b/tests/models/clip/test_modeling_clip.py index fbcb22575a..16c8f47b78 100644 --- a/tests/models/clip/test_modeling_clip.py +++ b/tests/models/clip/test_modeling_clip.py @@ -58,7 +58,6 @@ if is_torch_available(): CLIPVisionModel, CLIPVisionModelWithProjection, ) - from transformers.models.clip.modeling_clip import CLIP_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -250,16 +249,16 @@ class CLIPVisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in CLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = CLIPVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "openai/clip-vit-base-patch32" + model = CLIPVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow def test_model_with_projection_from_pretrained(self): - for model_name in CLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = CLIPVisionModelWithProjection.from_pretrained(model_name) - self.assertIsNotNone(model) - self.assertTrue(hasattr(model, "visual_projection")) + model_name = "openai/clip-vit-base-patch32" + model = CLIPVisionModelWithProjection.from_pretrained(model_name) + self.assertIsNotNone(model) + self.assertTrue(hasattr(model, "visual_projection")) class CLIPTextModelTester: @@ -415,16 +414,16 @@ class CLIPTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in CLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = CLIPTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "openai/clip-vit-base-patch32" + model = CLIPTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow def test_model_with_projection_from_pretrained(self): - for model_name in CLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = CLIPTextModelWithProjection.from_pretrained(model_name) - self.assertIsNotNone(model) - self.assertTrue(hasattr(model, "text_projection")) + model_name = "openai/clip-vit-base-patch32" + model = CLIPTextModelWithProjection.from_pretrained(model_name) + self.assertIsNotNone(model) + self.assertTrue(hasattr(model, "text_projection")) class CLIPModelTester: @@ -741,9 +740,9 @@ class CLIPModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in CLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = CLIPModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "openai/clip-vit-base-patch32" + model = CLIPModel.from_pretrained(model_name) + self.assertIsNotNone(model) class CLIPForImageClassificationModelTester(CLIPModelTester): diff --git a/tests/models/clip/test_modeling_tf_clip.py b/tests/models/clip/test_modeling_tf_clip.py index 8feeeebd0d..4e1ec7f88e 100644 --- a/tests/models/clip/test_modeling_tf_clip.py +++ b/tests/models/clip/test_modeling_tf_clip.py @@ -39,7 +39,6 @@ if is_tf_available(): from transformers import TFCLIPModel, TFCLIPTextModel, TFCLIPVisionModel, TFSharedEmbeddings from transformers.modeling_tf_utils import keras - from transformers.models.clip.modeling_tf_clip import TF_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -257,9 +256,9 @@ class TFCLIPVisionModelTest(TFModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in TF_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFCLIPVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "openai/clip-vit-base-patch32" + model = TFCLIPVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow def test_saved_model_creation_extended(self): @@ -423,9 +422,9 @@ class TFCLIPTextModelTest(TFModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in TF_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFCLIPTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "openai/clip-vit-base-patch32" + model = TFCLIPTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow def test_saved_model_creation_extended(self): @@ -607,9 +606,9 @@ class TFCLIPModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in TF_CLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFCLIPModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "openai/clip-vit-base-patch32" + model = TFCLIPModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip(reason="Currently `saved_model` doesn't work with nested outputs.") @slow diff --git a/tests/models/clipseg/test_modeling_clipseg.py b/tests/models/clipseg/test_modeling_clipseg.py index 8f3ab2b04f..6b82a9af41 100644 --- a/tests/models/clipseg/test_modeling_clipseg.py +++ b/tests/models/clipseg/test_modeling_clipseg.py @@ -52,7 +52,6 @@ if is_torch_available(): from transformers import CLIPSegForImageSegmentation, CLIPSegModel, CLIPSegTextModel, CLIPSegVisionModel from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES - from transformers.models.clipseg.modeling_clipseg import CLIPSEG_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -224,9 +223,9 @@ class CLIPSegVisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in CLIPSEG_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = CLIPSegVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "CIDAS/clipseg-rd64-refined" + model = CLIPSegVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) class CLIPSegTextModelTester: @@ -365,9 +364,9 @@ class CLIPSegTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in CLIPSEG_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = CLIPSegTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "CIDAS/clipseg-rd64-refined" + model = CLIPSegTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) class CLIPSegModelTester: @@ -768,9 +767,9 @@ class CLIPSegModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in CLIPSEG_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = CLIPSegModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "CIDAS/clipseg-rd64-refined" + model = CLIPSegModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/clvp/test_modeling_clvp.py b/tests/models/clvp/test_modeling_clvp.py index 59e6c1be40..7d5064377f 100644 --- a/tests/models/clvp/test_modeling_clvp.py +++ b/tests/models/clvp/test_modeling_clvp.py @@ -45,7 +45,6 @@ if is_torch_available(): import torch from transformers import ClvpEncoder, ClvpForCausalLM, ClvpModel, ClvpModelForConditionalGeneration - from transformers.models.clvp.modeling_clvp import CLVP_PRETRAINED_MODEL_ARCHIVE_LIST from transformers import ClvpFeatureExtractor, ClvpTokenizer @@ -541,9 +540,9 @@ class ClvpModelForConditionalGenerationTest(ModelTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in CLVP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ClvpModelForConditionalGeneration.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "susnato/clvp_dev" + model = ClvpModelForConditionalGeneration.from_pretrained(model_name) + self.assertIsNotNone(model) # Since Clvp has a lot of different models connected with each other it's better to test each of them individually along diff --git a/tests/models/codegen/test_modeling_codegen.py b/tests/models/codegen/test_modeling_codegen.py index e042ccac71..9dce2713f5 100644 --- a/tests/models/codegen/test_modeling_codegen.py +++ b/tests/models/codegen/test_modeling_codegen.py @@ -30,7 +30,7 @@ from ...test_pipeline_mixin import PipelineTesterMixin if is_torch_available(): import torch - from transformers import CODEGEN_PRETRAINED_MODEL_ARCHIVE_LIST, AutoTokenizer, CodeGenForCausalLM, CodeGenModel + from transformers import AutoTokenizer, CodeGenForCausalLM, CodeGenModel class CodeGenModelTester: @@ -456,9 +456,9 @@ class CodeGenModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMi @slow def test_model_from_pretrained(self): - for model_name in CODEGEN_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = CodeGenModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/codegen-350M-nl" + model = CodeGenModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/convbert/test_modeling_convbert.py b/tests/models/convbert/test_modeling_convbert.py index 281a8e477b..80a31c9bc2 100644 --- a/tests/models/convbert/test_modeling_convbert.py +++ b/tests/models/convbert/test_modeling_convbert.py @@ -38,7 +38,6 @@ if is_torch_available(): ConvBertForTokenClassification, ConvBertModel, ) - from transformers.models.convbert.modeling_convbert import CONVBERT_PRETRAINED_MODEL_ARCHIVE_LIST class ConvBertModelTester: @@ -307,9 +306,9 @@ class ConvBertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in CONVBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ConvBertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "YituTech/conv-bert-base" + model = ConvBertModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_attention_outputs(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/convnext/test_modeling_convnext.py b/tests/models/convnext/test_modeling_convnext.py index a56c38e387..9f0789dffc 100644 --- a/tests/models/convnext/test_modeling_convnext.py +++ b/tests/models/convnext/test_modeling_convnext.py @@ -31,7 +31,6 @@ if is_torch_available(): import torch from transformers import ConvNextBackbone, ConvNextForImageClassification, ConvNextModel - from transformers.models.convnext.modeling_convnext import CONVNEXT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -257,9 +256,9 @@ class ConvNextModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in CONVNEXT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ConvNextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/convnext-tiny-224" + model = ConvNextModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/convnextv2/test_modeling_convnextv2.py b/tests/models/convnextv2/test_modeling_convnextv2.py index b13028dba8..5d78d31c3e 100644 --- a/tests/models/convnextv2/test_modeling_convnextv2.py +++ b/tests/models/convnextv2/test_modeling_convnextv2.py @@ -32,7 +32,6 @@ if is_torch_available(): import torch from transformers import ConvNextV2Backbone, ConvNextV2ForImageClassification, ConvNextV2Model - from transformers.models.convnextv2.modeling_convnextv2 import CONVNEXTV2_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -306,9 +305,9 @@ class ConvNextV2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCa @slow def test_model_from_pretrained(self): - for model_name in CONVNEXTV2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ConvNextV2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/convnextv2-tiny-1k-224" + model = ConvNextV2Model.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/ctrl/test_modeling_ctrl.py b/tests/models/ctrl/test_modeling_ctrl.py index 71dcd02ed5..6d44bdfb4a 100644 --- a/tests/models/ctrl/test_modeling_ctrl.py +++ b/tests/models/ctrl/test_modeling_ctrl.py @@ -29,7 +29,6 @@ if is_torch_available(): import torch from transformers import ( - CTRL_PRETRAINED_MODEL_ARCHIVE_LIST, CTRLForSequenceClassification, CTRLLMHeadModel, CTRLModel, @@ -245,9 +244,9 @@ class CTRLModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin @slow def test_model_from_pretrained(self): - for model_name in CTRL_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = CTRLModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/ctrl" + model = CTRLModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/ctrl/test_modeling_tf_ctrl.py b/tests/models/ctrl/test_modeling_tf_ctrl.py index 29a8b6fb6a..d8317c919d 100644 --- a/tests/models/ctrl/test_modeling_tf_ctrl.py +++ b/tests/models/ctrl/test_modeling_tf_ctrl.py @@ -31,7 +31,6 @@ if is_tf_available(): from transformers.modeling_tf_utils import keras from transformers.models.ctrl.modeling_tf_ctrl import ( - TF_CTRL_PRETRAINED_MODEL_ARCHIVE_LIST, TFCTRLForSequenceClassification, TFCTRLLMHeadModel, TFCTRLModel, @@ -249,9 +248,9 @@ class TFCTRLModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in TF_CTRL_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFCTRLModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/ctrl" + model = TFCTRLModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_tf diff --git a/tests/models/cvt/test_modeling_cvt.py b/tests/models/cvt/test_modeling_cvt.py index aef8108e17..8e9376de27 100644 --- a/tests/models/cvt/test_modeling_cvt.py +++ b/tests/models/cvt/test_modeling_cvt.py @@ -31,7 +31,6 @@ if is_torch_available(): import torch from transformers import CvtForImageClassification, CvtModel - from transformers.models.cvt.modeling_cvt import CVT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -236,9 +235,9 @@ class CvtModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in CVT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = CvtModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/cvt-13" + model = CvtModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats @@ -252,11 +251,11 @@ def prepare_img(): class CvtModelIntegrationTest(unittest.TestCase): @cached_property def default_image_processor(self): - return AutoImageProcessor.from_pretrained(CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + return AutoImageProcessor.from_pretrained("microsoft/cvt-13") @slow def test_inference_image_classification_head(self): - model = CvtForImageClassification.from_pretrained(CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device) + model = CvtForImageClassification.from_pretrained("microsoft/cvt-13").to(torch_device) image_processor = self.default_image_processor image = prepare_img() diff --git a/tests/models/cvt/test_modeling_tf_cvt.py b/tests/models/cvt/test_modeling_tf_cvt.py index 4ec245ad49..0cae0bbcf2 100644 --- a/tests/models/cvt/test_modeling_tf_cvt.py +++ b/tests/models/cvt/test_modeling_tf_cvt.py @@ -23,7 +23,6 @@ if is_tf_available(): from transformers import TFCvtForImageClassification, TFCvtModel from transformers.modeling_tf_utils import keras - from transformers.models.cvt.modeling_tf_cvt import TF_CVT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -251,9 +250,9 @@ class TFCvtModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in TF_CVT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFCvtModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/cvt-13" + model = TFCvtModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats @@ -267,11 +266,11 @@ def prepare_img(): class TFCvtModelIntegrationTest(unittest.TestCase): @cached_property def default_image_processor(self): - return AutoImageProcessor.from_pretrained(TF_CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + return AutoImageProcessor.from_pretrained("microsoft/cvt-13") @slow def test_inference_image_classification_head(self): - model = TFCvtForImageClassification.from_pretrained(TF_CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + model = TFCvtForImageClassification.from_pretrained("microsoft/cvt-13") image_processor = self.default_image_processor image = prepare_img() diff --git a/tests/models/data2vec/test_modeling_data2vec_text.py b/tests/models/data2vec/test_modeling_data2vec_text.py index afaa8a76ad..5a3edaa7ad 100644 --- a/tests/models/data2vec/test_modeling_data2vec_text.py +++ b/tests/models/data2vec/test_modeling_data2vec_text.py @@ -39,7 +39,6 @@ if is_torch_available(): Data2VecTextModel, ) from transformers.models.data2vec.modeling_data2vec_text import ( - DATA2VEC_TEXT_PRETRAINED_MODEL_ARCHIVE_LIST, Data2VecTextForTextEmbeddings, create_position_ids_from_input_ids, ) @@ -470,9 +469,9 @@ class Data2VecTextModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTes @slow def test_model_from_pretrained(self): - for model_name in DATA2VEC_TEXT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Data2VecTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/data2vec-text-base" + model = Data2VecTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_create_position_ids_respects_padding_index(self): """Ensure that the default position ids only assign a sequential . This is a regression diff --git a/tests/models/data2vec/test_modeling_data2vec_vision.py b/tests/models/data2vec/test_modeling_data2vec_vision.py index 3e00dd0bf3..c426a6ca7e 100644 --- a/tests/models/data2vec/test_modeling_data2vec_vision.py +++ b/tests/models/data2vec/test_modeling_data2vec_vision.py @@ -36,7 +36,6 @@ if is_torch_available(): Data2VecVisionModel, ) from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES - from transformers.models.data2vec.modeling_data2vec_vision import DATA2VEC_VISION_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -298,9 +297,9 @@ class Data2VecVisionModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.Te @slow def test_model_from_pretrained(self): - for model_name in DATA2VEC_VISION_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Data2VecVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/data2vec-vision-base-ft1k" + model = Data2VecVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/data2vec/test_modeling_tf_data2vec_vision.py b/tests/models/data2vec/test_modeling_tf_data2vec_vision.py index 685a9e4680..bb6e0d5476 100644 --- a/tests/models/data2vec/test_modeling_tf_data2vec_vision.py +++ b/tests/models/data2vec/test_modeling_tf_data2vec_vision.py @@ -40,9 +40,6 @@ if is_tf_available(): TFData2VecVisionModel, ) from transformers.modeling_tf_utils import keras - from transformers.models.data2vec.modeling_tf_data2vec_vision import ( - TF_DATA2VEC_VISION_PRETRAINED_MODEL_ARCHIVE_LIST, - ) if is_vision_available(): from PIL import Image @@ -455,9 +452,9 @@ class TFData2VecVisionModelTest(TFModelTesterMixin, PipelineTesterMixin, unittes @slow def test_model_from_pretrained(self): - for model_name in TF_DATA2VEC_VISION_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFData2VecVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/data2vec-vision-base-ft1k" + model = TFData2VecVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/deberta/test_modeling_deberta.py b/tests/models/deberta/test_modeling_deberta.py index 52758e2222..d511279c78 100644 --- a/tests/models/deberta/test_modeling_deberta.py +++ b/tests/models/deberta/test_modeling_deberta.py @@ -32,7 +32,6 @@ if is_torch_available(): DebertaForTokenClassification, DebertaModel, ) - from transformers.models.deberta.modeling_deberta import DEBERTA_PRETRAINED_MODEL_ARCHIVE_LIST class DebertaModelTester(object): @@ -274,9 +273,9 @@ class DebertaModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in DEBERTA_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DebertaModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/deberta-base" + model = DebertaModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/deberta_v2/test_modeling_deberta_v2.py b/tests/models/deberta_v2/test_modeling_deberta_v2.py index abfbe7402c..80df003b1e 100644 --- a/tests/models/deberta_v2/test_modeling_deberta_v2.py +++ b/tests/models/deberta_v2/test_modeling_deberta_v2.py @@ -33,7 +33,6 @@ if is_torch_available(): DebertaV2ForTokenClassification, DebertaV2Model, ) - from transformers.models.deberta_v2.modeling_deberta_v2 import DEBERTA_V2_PRETRAINED_MODEL_ARCHIVE_LIST class DebertaV2ModelTester(object): @@ -292,9 +291,9 @@ class DebertaV2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCas @slow def test_model_from_pretrained(self): - for model_name in DEBERTA_V2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DebertaV2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/deberta-v2-xlarge" + model = DebertaV2Model.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/decision_transformer/test_modeling_decision_transformer.py b/tests/models/decision_transformer/test_modeling_decision_transformer.py index d99521b2f1..f7f362dce8 100644 --- a/tests/models/decision_transformer/test_modeling_decision_transformer.py +++ b/tests/models/decision_transformer/test_modeling_decision_transformer.py @@ -31,9 +31,6 @@ if is_torch_available(): import torch from transformers import DecisionTransformerModel - from transformers.models.decision_transformer.modeling_decision_transformer import ( - DECISION_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST, - ) class DecisionTransformerModelTester: @@ -164,9 +161,9 @@ class DecisionTransformerModelTest(ModelTesterMixin, GenerationTesterMixin, Pipe @slow def test_model_from_pretrained(self): - for model_name in DECISION_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DecisionTransformerModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "edbeeching/decision-transformer-gym-hopper-medium" + model = DecisionTransformerModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_forward_signature(self): config, _ = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/deit/test_modeling_deit.py b/tests/models/deit/test_modeling_deit.py index 07f581bfeb..9a54f16dab 100644 --- a/tests/models/deit/test_modeling_deit.py +++ b/tests/models/deit/test_modeling_deit.py @@ -50,7 +50,6 @@ if is_torch_available(): MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING_NAMES, MODEL_MAPPING_NAMES, ) - from transformers.models.deit.modeling_deit import DEIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -367,9 +366,9 @@ class DeiTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in DEIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DeiTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/deit-base-distilled-patch16-224" + model = DeiTModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/deit/test_modeling_tf_deit.py b/tests/models/deit/test_modeling_tf_deit.py index 848370a113..26980e8420 100644 --- a/tests/models/deit/test_modeling_tf_deit.py +++ b/tests/models/deit/test_modeling_tf_deit.py @@ -41,7 +41,6 @@ if is_tf_available(): TFDeiTModel, ) from transformers.modeling_tf_utils import keras - from transformers.models.deit.modeling_tf_deit import TF_DEIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -252,9 +251,9 @@ class TFDeiTModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in TF_DEIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFDeiTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/deit-base-distilled-patch16-224" + model = TFDeiTModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/depth_anything/test_modeling_depth_anything.py b/tests/models/depth_anything/test_modeling_depth_anything.py index 9657fb6044..3b807abf71 100644 --- a/tests/models/depth_anything/test_modeling_depth_anything.py +++ b/tests/models/depth_anything/test_modeling_depth_anything.py @@ -30,7 +30,6 @@ if is_torch_available(): import torch from transformers import DepthAnythingForDepthEstimation - from transformers.models.depth_anything.modeling_depth_anything import DEPTH_ANYTHING_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -205,9 +204,9 @@ class DepthAnythingModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.Tes @slow def test_model_from_pretrained(self): - for model_name in DEPTH_ANYTHING_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DepthAnythingForDepthEstimation.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "LiheYoung/depth-anything-small-hf" + model = DepthAnythingForDepthEstimation.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/dinat/test_modeling_dinat.py b/tests/models/dinat/test_modeling_dinat.py index c29339881e..158ce77395 100644 --- a/tests/models/dinat/test_modeling_dinat.py +++ b/tests/models/dinat/test_modeling_dinat.py @@ -32,7 +32,6 @@ if is_torch_available(): from torch import nn from transformers import DinatBackbone, DinatForImageClassification, DinatModel - from transformers.models.dinat.modeling_dinat import DINAT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): from PIL import Image @@ -330,9 +329,9 @@ class DinatModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in DINAT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DinatModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "shi-labs/dinat-mini-in1k-224" + model = DinatModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_initialization(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/dinov2/test_modeling_dinov2.py b/tests/models/dinov2/test_modeling_dinov2.py index f0365cac2a..9896f2c2bb 100644 --- a/tests/models/dinov2/test_modeling_dinov2.py +++ b/tests/models/dinov2/test_modeling_dinov2.py @@ -38,7 +38,6 @@ if is_torch_available(): from torch import nn from transformers import Dinov2Backbone, Dinov2ForImageClassification, Dinov2Model - from transformers.models.dinov2.modeling_dinov2 import DINOV2_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -287,9 +286,9 @@ class Dinov2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in DINOV2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Dinov2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/dinov2-base" + model = Dinov2Model.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/distilbert/test_modeling_distilbert.py b/tests/models/distilbert/test_modeling_distilbert.py index 9ab9d01577..c24eb30960 100644 --- a/tests/models/distilbert/test_modeling_distilbert.py +++ b/tests/models/distilbert/test_modeling_distilbert.py @@ -30,7 +30,6 @@ if is_torch_available(): import torch from transformers import ( - DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST, DistilBertForMaskedLM, DistilBertForMultipleChoice, DistilBertForQuestionAnswering, @@ -261,9 +260,9 @@ class DistilBertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCa @slow def test_model_from_pretrained(self): - for model_name in DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DistilBertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "distilbert-base-uncased" + model = DistilBertModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow @require_torch_accelerator diff --git a/tests/models/distilbert/test_modeling_tf_distilbert.py b/tests/models/distilbert/test_modeling_tf_distilbert.py index 937dd24d6d..270cea00de 100644 --- a/tests/models/distilbert/test_modeling_tf_distilbert.py +++ b/tests/models/distilbert/test_modeling_tf_distilbert.py @@ -30,7 +30,6 @@ if is_tf_available(): import tensorflow as tf from transformers.models.distilbert.modeling_tf_distilbert import ( - TF_DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST, TFDistilBertForMaskedLM, TFDistilBertForMultipleChoice, TFDistilBertForQuestionAnswering, @@ -233,9 +232,9 @@ class TFDistilBertModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.Te @slow def test_model_from_pretrained(self): - for model_name in list(TF_DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]): - model = TFDistilBertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "distilbert/distilbert-base-cased" + model = TFDistilBertModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_tf diff --git a/tests/models/donut/test_modeling_donut_swin.py b/tests/models/donut/test_modeling_donut_swin.py index 23b7094d9b..4d9be165bb 100644 --- a/tests/models/donut/test_modeling_donut_swin.py +++ b/tests/models/donut/test_modeling_donut_swin.py @@ -31,7 +31,6 @@ if is_torch_available(): from torch import nn from transformers import DonutSwinModel - from transformers.models.donut.modeling_donut_swin import DONUT_SWIN_PRETRAINED_MODEL_ARCHIVE_LIST class DonutSwinModelTester: @@ -334,9 +333,9 @@ class DonutSwinModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCas @slow def test_model_from_pretrained(self): - for model_name in DONUT_SWIN_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DonutSwinModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "naver-clova-ix/donut-base" + model = DonutSwinModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_initialization(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/dpr/test_modeling_dpr.py b/tests/models/dpr/test_modeling_dpr.py index b6a687a351..7a41820f2d 100644 --- a/tests/models/dpr/test_modeling_dpr.py +++ b/tests/models/dpr/test_modeling_dpr.py @@ -29,11 +29,6 @@ if is_torch_available(): import torch from transformers import DPRContextEncoder, DPRQuestionEncoder, DPRReader, DPRReaderTokenizer - from transformers.models.dpr.modeling_dpr import ( - DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST, - DPR_QUESTION_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST, - DPR_READER_PRETRAINED_MODEL_ARCHIVE_LIST, - ) class DPRModelTester: @@ -230,21 +225,21 @@ class DPRModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DPRContextEncoder.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/dpr-ctx_encoder-single-nq-base" + model = DPRContextEncoder.from_pretrained(model_name) + self.assertIsNotNone(model) - for model_name in DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DPRContextEncoder.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/dpr-ctx_encoder-single-nq-base" + model = DPRContextEncoder.from_pretrained(model_name) + self.assertIsNotNone(model) - for model_name in DPR_QUESTION_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DPRQuestionEncoder.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/dpr-ctx_encoder-single-nq-base" + model = DPRQuestionEncoder.from_pretrained(model_name) + self.assertIsNotNone(model) - for model_name in DPR_READER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DPRReader.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/dpr-ctx_encoder-single-nq-base" + model = DPRReader.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/dpr/test_modeling_tf_dpr.py b/tests/models/dpr/test_modeling_tf_dpr.py index 1135140862..92d74e72e3 100644 --- a/tests/models/dpr/test_modeling_tf_dpr.py +++ b/tests/models/dpr/test_modeling_tf_dpr.py @@ -30,9 +30,6 @@ if is_tf_available(): import tensorflow as tf from transformers import ( - TF_DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST, - TF_DPR_QUESTION_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST, - TF_DPR_READER_PRETRAINED_MODEL_ARCHIVE_LIST, BertConfig, DPRConfig, TFDPRContextEncoder, @@ -213,21 +210,21 @@ class TFDPRModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in TF_DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFDPRContextEncoder.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/dpr-ctx_encoder-single-nq-base" + model = TFDPRContextEncoder.from_pretrained(model_name) + self.assertIsNotNone(model) - for model_name in TF_DPR_CONTEXT_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFDPRContextEncoder.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/dpr-ctx_encoder-single-nq-base" + model = TFDPRContextEncoder.from_pretrained(model_name) + self.assertIsNotNone(model) - for model_name in TF_DPR_QUESTION_ENCODER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFDPRQuestionEncoder.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/dpr-ctx_encoder-single-nq-base" + model = TFDPRQuestionEncoder.from_pretrained(model_name) + self.assertIsNotNone(model) - for model_name in TF_DPR_READER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFDPRReader.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/dpr-ctx_encoder-single-nq-base" + model = TFDPRReader.from_pretrained(model_name) + self.assertIsNotNone(model) @require_tf diff --git a/tests/models/dpt/test_modeling_dpt.py b/tests/models/dpt/test_modeling_dpt.py index ffd6edbad4..a49f8d5d94 100644 --- a/tests/models/dpt/test_modeling_dpt.py +++ b/tests/models/dpt/test_modeling_dpt.py @@ -32,7 +32,6 @@ if is_torch_available(): from transformers import DPTForDepthEstimation, DPTForSemanticSegmentation, DPTModel from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES - from transformers.models.dpt.modeling_dpt import DPT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -280,9 +279,9 @@ class DPTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in DPT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DPTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Intel/dpt-large" + model = DPTModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/dpt/test_modeling_dpt_auto_backbone.py b/tests/models/dpt/test_modeling_dpt_auto_backbone.py index ea500b47a3..01d5398edd 100644 --- a/tests/models/dpt/test_modeling_dpt_auto_backbone.py +++ b/tests/models/dpt/test_modeling_dpt_auto_backbone.py @@ -31,7 +31,6 @@ if is_torch_available(): from transformers import DPTForDepthEstimation from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES - from transformers.models.dpt.modeling_dpt import DPT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -244,9 +243,9 @@ class DPTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in DPT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = DPTForDepthEstimation.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Intel/dpt-large" + model = DPTForDepthEstimation.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/dpt/test_modeling_dpt_hybrid.py b/tests/models/dpt/test_modeling_dpt_hybrid.py index 2a6e8429ab..a63e736e41 100644 --- a/tests/models/dpt/test_modeling_dpt_hybrid.py +++ b/tests/models/dpt/test_modeling_dpt_hybrid.py @@ -32,7 +32,6 @@ if is_torch_available(): from transformers import DPTForDepthEstimation, DPTForSemanticSegmentation, DPTModel from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES - from transformers.models.dpt.modeling_dpt import DPT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -295,9 +294,9 @@ class DPTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in DPT_PRETRAINED_MODEL_ARCHIVE_LIST[1:]: - model = DPTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Intel/dpt-hybrid-midas" + model = DPTModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_raise_readout_type(self): # We do this test only for DPTForDepthEstimation since it is the only model that uses readout_type diff --git a/tests/models/efficientformer/test_modeling_efficientformer.py b/tests/models/efficientformer/test_modeling_efficientformer.py index 070c7fccae..15a4cb0be3 100644 --- a/tests/models/efficientformer/test_modeling_efficientformer.py +++ b/tests/models/efficientformer/test_modeling_efficientformer.py @@ -40,9 +40,6 @@ if is_torch_available(): MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES, MODEL_MAPPING_NAMES, ) - from transformers.models.efficientformer.modeling_efficientformer import ( - EFFICIENTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST, - ) if is_vision_available(): @@ -371,9 +368,9 @@ class EfficientFormerModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.T @slow def test_model_from_pretrained(self): - for model_name in EFFICIENTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = EfficientFormerModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "snap-research/efficientformer-l1-300" + model = EfficientFormerModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_attention_outputs(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/efficientformer/test_modeling_tf_efficientformer.py b/tests/models/efficientformer/test_modeling_tf_efficientformer.py index 35cbeb75ae..fcd6958ed3 100644 --- a/tests/models/efficientformer/test_modeling_tf_efficientformer.py +++ b/tests/models/efficientformer/test_modeling_tf_efficientformer.py @@ -38,9 +38,6 @@ if is_tf_available(): TFEfficientFormerModel, ) from transformers.modeling_tf_utils import keras - from transformers.models.efficientformer.modeling_tf_efficientformer import ( - TF_EFFICIENTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST, - ) if is_vision_available(): @@ -299,9 +296,9 @@ class TFEfficientFormerModelTest(TFModelTesterMixin, PipelineTesterMixin, unitte @slow def test_model_from_pretrained(self): - for model_name in TF_EFFICIENTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFEfficientFormerModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "snap-research/efficientformer-l1-300" + model = TFEfficientFormerModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_attention_outputs(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/efficientnet/test_modeling_efficientnet.py b/tests/models/efficientnet/test_modeling_efficientnet.py index 19d66aca95..dbca9b31a2 100644 --- a/tests/models/efficientnet/test_modeling_efficientnet.py +++ b/tests/models/efficientnet/test_modeling_efficientnet.py @@ -30,7 +30,6 @@ if is_torch_available(): import torch from transformers import EfficientNetForImageClassification, EfficientNetModel - from transformers.models.efficientnet.modeling_efficientnet import EFFICIENTNET_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -212,9 +211,9 @@ class EfficientNetModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.Test @slow def test_model_from_pretrained(self): - for model_name in EFFICIENTNET_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = EfficientNetModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/efficientnet-b7" + model = EfficientNetModel.from_pretrained(model_name) + self.assertIsNotNone(model) @is_pipeline_test @require_vision diff --git a/tests/models/electra/test_modeling_electra.py b/tests/models/electra/test_modeling_electra.py index a5d3fa585e..f6cab71077 100644 --- a/tests/models/electra/test_modeling_electra.py +++ b/tests/models/electra/test_modeling_electra.py @@ -39,7 +39,6 @@ if is_torch_available(): ElectraForTokenClassification, ElectraModel, ) - from transformers.models.electra.modeling_electra import ELECTRA_PRETRAINED_MODEL_ARCHIVE_LIST class ElectraModelTester: @@ -463,9 +462,9 @@ class ElectraModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in ELECTRA_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ElectraModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/electra-small-generator" + model = ElectraModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_for_causal_lm(self): config_and_inputs = self.model_tester.prepare_config_and_inputs_for_decoder() diff --git a/tests/models/electra/test_modeling_tf_electra.py b/tests/models/electra/test_modeling_tf_electra.py index 537cb1df2f..aba6db1efa 100644 --- a/tests/models/electra/test_modeling_tf_electra.py +++ b/tests/models/electra/test_modeling_tf_electra.py @@ -593,7 +593,7 @@ class TFElectraModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestC @slow def test_model_from_pretrained(self): - # for model_name in TF_ELECTRA_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: + # model_name = 'google/electra-small-generator' for model_name in ["google/electra-small-discriminator"]: model = TFElectraModel.from_pretrained(model_name) self.assertIsNotNone(model) diff --git a/tests/models/ernie/test_modeling_ernie.py b/tests/models/ernie/test_modeling_ernie.py index 6fc557219c..da19d08e46 100644 --- a/tests/models/ernie/test_modeling_ernie.py +++ b/tests/models/ernie/test_modeling_ernie.py @@ -41,7 +41,6 @@ if is_torch_available(): ErnieForTokenClassification, ErnieModel, ) - from transformers.models.ernie.modeling_ernie import ERNIE_PRETRAINED_MODEL_ARCHIVE_LIST class ErnieModelTester: @@ -569,9 +568,9 @@ class ErnieModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixi @slow def test_model_from_pretrained(self): - for model_name in ERNIE_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ErnieModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "nghuyong/ernie-1.0-base-zh" + model = ErnieModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow @require_torch_accelerator diff --git a/tests/models/ernie_m/test_modeling_ernie_m.py b/tests/models/ernie_m/test_modeling_ernie_m.py index 1fafcd34ba..e429a12e6e 100644 --- a/tests/models/ernie_m/test_modeling_ernie_m.py +++ b/tests/models/ernie_m/test_modeling_ernie_m.py @@ -36,7 +36,6 @@ if is_torch_available(): ErnieMForTokenClassification, ErnieMModel, ) - from transformers.models.ernie_m.modeling_ernie_m import ERNIE_M_PRETRAINED_MODEL_ARCHIVE_LIST class ErnieMModelTester: @@ -298,9 +297,9 @@ class ErnieMModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in ERNIE_M_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ErnieMModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "susnato/ernie-m-base_pytorch" + model = ErnieMModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/esm/test_modeling_esm.py b/tests/models/esm/test_modeling_esm.py index 7e99f86bbf..db3ccd6fd2 100644 --- a/tests/models/esm/test_modeling_esm.py +++ b/tests/models/esm/test_modeling_esm.py @@ -30,7 +30,6 @@ if is_torch_available(): from transformers import EsmForMaskedLM, EsmForSequenceClassification, EsmForTokenClassification, EsmModel from transformers.models.esm.modeling_esm import ( - ESM_PRETRAINED_MODEL_ARCHIVE_LIST, EsmEmbeddings, create_position_ids_from_input_ids, ) @@ -243,9 +242,9 @@ class EsmModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in ESM_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = EsmModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/esm2_t6_8M_UR50D" + model = EsmModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_create_position_ids_respects_padding_index(self): """Ensure that the default position ids only assign a sequential . This is a regression diff --git a/tests/models/esm/test_modeling_tf_esm.py b/tests/models/esm/test_modeling_tf_esm.py index 0e92e352fe..4accc16256 100644 --- a/tests/models/esm/test_modeling_tf_esm.py +++ b/tests/models/esm/test_modeling_tf_esm.py @@ -32,7 +32,6 @@ if is_tf_available(): from transformers.modeling_tf_utils import keras from transformers.models.esm.modeling_tf_esm import ( - TF_ESM_PRETRAINED_MODEL_ARCHIVE_LIST, TFEsmForMaskedLM, TFEsmForSequenceClassification, TFEsmForTokenClassification, @@ -253,9 +252,9 @@ class TFEsmModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in TF_ESM_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFEsmModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/esm2_t6_8M_UR50D" + model = TFEsmModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip("Protein models do not support embedding resizing.") def test_resize_token_embeddings(self): diff --git a/tests/models/flaubert/test_modeling_flaubert.py b/tests/models/flaubert/test_modeling_flaubert.py index fc275bdd8a..8c135887ca 100644 --- a/tests/models/flaubert/test_modeling_flaubert.py +++ b/tests/models/flaubert/test_modeling_flaubert.py @@ -36,7 +36,6 @@ if is_torch_available(): FlaubertModel, FlaubertWithLMHeadModel, ) - from transformers.models.flaubert.modeling_flaubert import FLAUBERT_PRETRAINED_MODEL_ARCHIVE_LIST class FlaubertModelTester(object): @@ -458,9 +457,9 @@ class FlaubertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in FLAUBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = FlaubertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "flaubert/flaubert_small_cased" + model = FlaubertModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow @require_torch_accelerator diff --git a/tests/models/flaubert/test_modeling_tf_flaubert.py b/tests/models/flaubert/test_modeling_tf_flaubert.py index 6d74b55ce3..534b529935 100644 --- a/tests/models/flaubert/test_modeling_tf_flaubert.py +++ b/tests/models/flaubert/test_modeling_tf_flaubert.py @@ -30,7 +30,6 @@ if is_tf_available(): import tensorflow as tf from transformers import ( - TF_FLAUBERT_PRETRAINED_MODEL_ARCHIVE_LIST, FlaubertConfig, TFFlaubertForMultipleChoice, TFFlaubertForQuestionAnsweringSimple, @@ -357,9 +356,9 @@ class TFFlaubertModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.Test @slow def test_model_from_pretrained(self): - for model_name in TF_FLAUBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFFlaubertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "hf-internal-testing/tiny-random-flaubert" + model = TFFlaubertModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_tf diff --git a/tests/models/flava/test_modeling_flava.py b/tests/models/flava/test_modeling_flava.py index 48200dd30c..2b628e1413 100644 --- a/tests/models/flava/test_modeling_flava.py +++ b/tests/models/flava/test_modeling_flava.py @@ -57,10 +57,6 @@ if is_torch_available(): FlavaMultimodalModel, FlavaTextModel, ) - from transformers.models.flava.modeling_flava import ( - FLAVA_CODEBOOK_PRETRAINED_MODEL_ARCHIVE_LIST, - FLAVA_PRETRAINED_MODEL_ARCHIVE_LIST, - ) else: FlavaModel = None FlavaForPreTraining = None @@ -335,9 +331,9 @@ class FlavaImageModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in FLAVA_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = FlavaImageModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/flava-full" + model = FlavaImageModel.from_pretrained(model_name) + self.assertIsNotNone(model) class FlavaTextModelTester: @@ -498,9 +494,9 @@ class FlavaTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in FLAVA_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = FlavaTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/flava-full" + model = FlavaTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) class FlavaMultimodalModelTester: @@ -662,9 +658,9 @@ class FlavaMultimodalModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in FLAVA_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = FlavaMultimodalModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/flava-full" + model = FlavaMultimodalModel.from_pretrained(model_name) + self.assertIsNotNone(model) class FlavaImageCodebookTester: @@ -795,9 +791,9 @@ class FlavaImageCodebookTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in FLAVA_CODEBOOK_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = FlavaImageCodebook.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/flava-full" + model = FlavaImageCodebook.from_pretrained(model_name) + self.assertIsNotNone(model) class FlavaModelTester: @@ -1081,9 +1077,9 @@ class FlavaModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): # overwrite from common since FlavaModel/TFFlavaModel return FLAVAOutput/TFFLAVAOutput @slow def test_model_from_pretrained(self): - for model_name in FLAVA_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = FlavaModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/flava-full" + model = FlavaModel.from_pretrained(model_name) + self.assertIsNotNone(model) class FlavaForPreTrainingTester(FlavaModelTester): diff --git a/tests/models/fnet/test_modeling_fnet.py b/tests/models/fnet/test_modeling_fnet.py index 83b84edddc..22de68bf15 100644 --- a/tests/models/fnet/test_modeling_fnet.py +++ b/tests/models/fnet/test_modeling_fnet.py @@ -43,7 +43,6 @@ if is_torch_available(): FNetTokenizerFast, ) from transformers.models.fnet.modeling_fnet import ( - FNET_PRETRAINED_MODEL_ARCHIVE_LIST, FNetBasicFourierTransform, is_scipy_available, ) @@ -464,9 +463,9 @@ class FNetModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in FNET_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = FNetModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/fnet-base" + model = FNetModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/focalnet/test_modeling_focalnet.py b/tests/models/focalnet/test_modeling_focalnet.py index 2b6f8cf9ab..fb2bb1c2c1 100644 --- a/tests/models/focalnet/test_modeling_focalnet.py +++ b/tests/models/focalnet/test_modeling_focalnet.py @@ -37,7 +37,6 @@ if is_torch_available(): FocalNetForMaskedImageModeling, FocalNetModel, ) - from transformers.models.focalnet.modeling_focalnet import FOCALNET_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): from PIL import Image @@ -387,9 +386,9 @@ class FocalNetModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in FOCALNET_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = FocalNetModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/focalnet-tiny" + model = FocalNetModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_initialization(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/gemma/test_tokenization_gemma.py b/tests/models/gemma/test_tokenization_gemma.py index 5e485da491..0e1fe54e35 100644 --- a/tests/models/gemma/test_tokenization_gemma.py +++ b/tests/models/gemma/test_tokenization_gemma.py @@ -153,10 +153,6 @@ class GemmaTokenizationTest(TokenizerTesterMixin, unittest.TestCase): def test_subword_regularization_tokenizer(self): pass - @unittest.skip("This test will be removed from main @LysandreJik") - def test_pretrained_model_lists(self): - pass - @unittest.skip("Skipping") def test_torch_encode_plus_sent_to_model(self): pass diff --git a/tests/models/git/test_modeling_git.py b/tests/models/git/test_modeling_git.py index c503abfb89..6a891f17b0 100644 --- a/tests/models/git/test_modeling_git.py +++ b/tests/models/git/test_modeling_git.py @@ -33,7 +33,6 @@ if is_torch_available(): from torch import nn from transformers import MODEL_FOR_CAUSAL_LM_MAPPING, GitForCausalLM, GitModel, GitVisionModel - from transformers.models.git.modeling_git import GIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -196,9 +195,9 @@ class GitVisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in GIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = GitVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/git-base" + model = GitVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) class GitModelTester: @@ -450,9 +449,9 @@ class GitModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin, @slow def test_model_from_pretrained(self): - for model_name in GIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = GitModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/git-base" + model = GitModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip(reason="GIT has pixel values as additional input") def test_beam_search_generate_dict_outputs_use_cache(self): diff --git a/tests/models/glpn/test_modeling_glpn.py b/tests/models/glpn/test_modeling_glpn.py index aab49c8491..b733164ec1 100644 --- a/tests/models/glpn/test_modeling_glpn.py +++ b/tests/models/glpn/test_modeling_glpn.py @@ -30,7 +30,6 @@ if is_torch_available(): from transformers import GLPNConfig, GLPNForDepthEstimation, GLPNModel from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES - from transformers.models.glpn.modeling_glpn import GLPN_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -309,9 +308,9 @@ class GLPNModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in GLPN_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = GLPNModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "vinvino02/glpn-kitti" + model = GLPNModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats @@ -326,8 +325,8 @@ def prepare_img(): class GLPNModelIntegrationTest(unittest.TestCase): @slow def test_inference_depth_estimation(self): - image_processor = GLPNImageProcessor.from_pretrained(GLPN_PRETRAINED_MODEL_ARCHIVE_LIST[0]) - model = GLPNForDepthEstimation.from_pretrained(GLPN_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device) + image_processor = GLPNImageProcessor.from_pretrained("vinvino02/glpn-kitti") + model = GLPNForDepthEstimation.from_pretrained("vinvino02/glpn-kitti").to(torch_device) image = prepare_img() inputs = image_processor(images=image, return_tensors="pt").to(torch_device) diff --git a/tests/models/gpt2/test_modeling_gpt2.py b/tests/models/gpt2/test_modeling_gpt2.py index c9ecbdde66..d2b9ce8dcf 100644 --- a/tests/models/gpt2/test_modeling_gpt2.py +++ b/tests/models/gpt2/test_modeling_gpt2.py @@ -32,7 +32,6 @@ if is_torch_available(): import torch from transformers import ( - GPT2_PRETRAINED_MODEL_ARCHIVE_LIST, GPT2DoubleHeadsModel, GPT2ForQuestionAnswering, GPT2ForSequenceClassification, @@ -701,9 +700,9 @@ class GPT2ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin @slow def test_model_from_pretrained(self): - for model_name in GPT2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = GPT2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "openai-community/gpt2" + model = GPT2Model.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/gpt2/test_modeling_tf_gpt2.py b/tests/models/gpt2/test_modeling_tf_gpt2.py index 060d4b7198..c56d837939 100644 --- a/tests/models/gpt2/test_modeling_tf_gpt2.py +++ b/tests/models/gpt2/test_modeling_tf_gpt2.py @@ -31,7 +31,6 @@ if is_tf_available(): from transformers import GPT2Tokenizer from transformers.models.gpt2.modeling_tf_gpt2 import ( - TF_GPT2_PRETRAINED_MODEL_ARCHIVE_LIST, TFGPT2DoubleHeadsModel, TFGPT2ForSequenceClassification, TFGPT2LMHeadModel, @@ -422,9 +421,9 @@ class TFGPT2ModelTest(TFModelTesterMixin, TFCoreModelTesterMixin, PipelineTester @slow def test_model_from_pretrained(self): - for model_name in TF_GPT2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFGPT2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "openai-community/gpt2" + model = TFGPT2Model.from_pretrained(model_name) + self.assertIsNotNone(model) # overwrite from common since ONNX runtime optimization doesn't work with tf.gather() when the argument # `batch_dims` > 0" diff --git a/tests/models/gpt_neo/test_modeling_gpt_neo.py b/tests/models/gpt_neo/test_modeling_gpt_neo.py index d4a9dd90eb..ce0aeadf16 100644 --- a/tests/models/gpt_neo/test_modeling_gpt_neo.py +++ b/tests/models/gpt_neo/test_modeling_gpt_neo.py @@ -31,7 +31,6 @@ if is_torch_available(): import torch from transformers import ( - GPT_NEO_PRETRAINED_MODEL_ARCHIVE_LIST, GPT2Tokenizer, GPTNeoForCausalLM, GPTNeoForQuestionAnswering, @@ -601,6 +600,6 @@ class GPTNeoModelLanguageGenerationTest(unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in GPT_NEO_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = GPTNeoModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "EleutherAI/gpt-neo-1.3B" + model = GPTNeoModel.from_pretrained(model_name) + self.assertIsNotNone(model) diff --git a/tests/models/gptj/test_modeling_gptj.py b/tests/models/gptj/test_modeling_gptj.py index fd88b85a13..2ef2e39121 100644 --- a/tests/models/gptj/test_modeling_gptj.py +++ b/tests/models/gptj/test_modeling_gptj.py @@ -40,7 +40,6 @@ if is_torch_available(): import torch from transformers import ( - GPTJ_PRETRAINED_MODEL_ARCHIVE_LIST, AutoTokenizer, GPTJForCausalLM, GPTJForQuestionAnswering, @@ -524,9 +523,9 @@ class GPTJModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin @slow def test_model_from_pretrained(self): - for model_name in GPTJ_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = GPTJModel.from_pretrained(model_name, revision="float16", torch_dtype=torch.float16) - self.assertIsNotNone(model) + model_name = "EleutherAI/gpt-j-6B" + model = GPTJModel.from_pretrained(model_name, revision="float16", torch_dtype=torch.float16) + self.assertIsNotNone(model) @require_flash_attn @require_torch_gpu diff --git a/tests/models/graphormer/test_modeling_graphormer.py b/tests/models/graphormer/test_modeling_graphormer.py index b6a994f459..ddb72543f5 100644 --- a/tests/models/graphormer/test_modeling_graphormer.py +++ b/tests/models/graphormer/test_modeling_graphormer.py @@ -34,7 +34,6 @@ if is_torch_available(): from torch import tensor from transformers import GraphormerForGraphClassification, GraphormerModel - from transformers.models.graphormer.modeling_graphormer import GRAPHORMER_PRETRAINED_MODEL_ARCHIVE_LIST class GraphormerModelTester: @@ -472,9 +471,9 @@ class GraphormerModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCa @slow def test_model_from_pretrained(self): - for model_name in GRAPHORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = GraphormerForGraphClassification.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "clefourrier/graphormer-base-pcqm4mv1" + model = GraphormerForGraphClassification.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/groupvit/test_modeling_groupvit.py b/tests/models/groupvit/test_modeling_groupvit.py index 9f44c3d9ee..5ec9bbbf1a 100644 --- a/tests/models/groupvit/test_modeling_groupvit.py +++ b/tests/models/groupvit/test_modeling_groupvit.py @@ -44,7 +44,6 @@ if is_torch_available(): from torch import nn from transformers import GroupViTModel, GroupViTTextModel, GroupViTVisionModel - from transformers.models.groupvit.modeling_groupvit import GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -352,9 +351,9 @@ class GroupViTVisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = GroupViTVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "nvidia/groupvit-gcc-yfcc" + model = GroupViTVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) class GroupViTTextModelTester: @@ -492,9 +491,9 @@ class GroupViTTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = GroupViTTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "nvidia/groupvit-gcc-yfcc" + model = GroupViTTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) class GroupViTModelTester: @@ -706,9 +705,9 @@ class GroupViTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = GroupViTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "nvidia/groupvit-gcc-yfcc" + model = GroupViTModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/groupvit/test_modeling_tf_groupvit.py b/tests/models/groupvit/test_modeling_tf_groupvit.py index 968d955846..be5ff803d9 100644 --- a/tests/models/groupvit/test_modeling_tf_groupvit.py +++ b/tests/models/groupvit/test_modeling_tf_groupvit.py @@ -47,7 +47,6 @@ if is_tf_available(): from transformers import TFGroupViTModel, TFGroupViTTextModel, TFGroupViTVisionModel, TFSharedEmbeddings from transformers.modeling_tf_utils import keras - from transformers.models.groupvit.modeling_tf_groupvit import TF_GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -314,9 +313,9 @@ class TFGroupViTVisionModelTest(TFModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in TF_GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFGroupViTVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "nvidia/groupvit-gcc-yfcc" + model = TFGroupViTVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip( "TFGroupViTVisionModel does not convert `hidden_states` and `attentions` to tensors as they are all of" @@ -485,9 +484,9 @@ class TFGroupViTTextModelTest(TFModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in TF_GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFGroupViTTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "nvidia/groupvit-gcc-yfcc" + model = TFGroupViTTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow def test_saved_model_creation_extended(self): @@ -697,9 +696,9 @@ class TFGroupViTModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.Test @slow def test_model_from_pretrained(self): - for model_name in TF_GROUPVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFGroupViTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "nvidia/groupvit-gcc-yfcc" + model = TFGroupViTModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip(reason="Currently `saved_model` doesn't work with nested outputs.") @slow diff --git a/tests/models/ibert/test_modeling_ibert.py b/tests/models/ibert/test_modeling_ibert.py index b552cb75a5..fd3809acff 100644 --- a/tests/models/ibert/test_modeling_ibert.py +++ b/tests/models/ibert/test_modeling_ibert.py @@ -30,7 +30,6 @@ if is_torch_available(): from torch import nn from transformers import ( - IBERT_PRETRAINED_MODEL_ARCHIVE_LIST, IBertForMaskedLM, IBertForMultipleChoice, IBertForQuestionAnswering, @@ -292,9 +291,9 @@ class IBertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in IBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = IBertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "kssteven/ibert-roberta-base" + model = IBertModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_create_position_ids_respects_padding_index(self): """Ensure that the default position ids only assign a sequential . This is a regression diff --git a/tests/models/idefics/test_modeling_idefics.py b/tests/models/idefics/test_modeling_idefics.py index 28530c7219..3059b5a2f5 100644 --- a/tests/models/idefics/test_modeling_idefics.py +++ b/tests/models/idefics/test_modeling_idefics.py @@ -40,7 +40,6 @@ if is_torch_available(): from transformers import IdeficsForVisionText2Text, IdeficsModel, IdeficsProcessor from transformers.models.idefics.configuration_idefics import IdeficsPerceiverConfig, IdeficsVisionConfig - from transformers.models.idefics.modeling_idefics import IDEFICS_PRETRAINED_MODEL_ARCHIVE_LIST from transformers.pytorch_utils import is_torch_greater_or_equal_than_2_0 else: is_torch_greater_or_equal_than_2_0 = False @@ -562,9 +561,9 @@ class IdeficsModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in IDEFICS_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = IdeficsModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "HuggingFaceM4/idefics-9b" + model = IdeficsModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch_sdpa @slow diff --git a/tests/models/imagegpt/test_modeling_imagegpt.py b/tests/models/imagegpt/test_modeling_imagegpt.py index 40ea7ce0f4..e18f745335 100644 --- a/tests/models/imagegpt/test_modeling_imagegpt.py +++ b/tests/models/imagegpt/test_modeling_imagegpt.py @@ -40,7 +40,6 @@ if is_torch_available(): import torch from transformers import ( - IMAGEGPT_PRETRAINED_MODEL_ARCHIVE_LIST, ImageGPTForCausalImageModeling, ImageGPTForImageClassification, ImageGPTModel, @@ -336,9 +335,9 @@ class ImageGPTModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterM @slow def test_model_from_pretrained(self): - for model_name in IMAGEGPT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ImageGPTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "openai/imagegpt-small" + model = ImageGPTModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_forward_signature(self): config, _ = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/instructblip/test_modeling_instructblip.py b/tests/models/instructblip/test_modeling_instructblip.py index 9ed95b56b6..8cbbde9868 100644 --- a/tests/models/instructblip/test_modeling_instructblip.py +++ b/tests/models/instructblip/test_modeling_instructblip.py @@ -54,7 +54,6 @@ if is_torch_available(): from torch import nn from transformers import InstructBlipForConditionalGeneration, InstructBlipVisionModel - from transformers.models.instructblip.modeling_instructblip import INSTRUCTBLIP_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -222,9 +221,9 @@ class InstructBlipVisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in INSTRUCTBLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = InstructBlipVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/instructblip-flan-t5-xl" + model = InstructBlipVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) class InstructBlipQFormerModelTester: @@ -526,9 +525,9 @@ class InstructBlipForConditionalGenerationDecoderOnlyTest(ModelTesterMixin, Gene @slow def test_model_from_pretrained(self): - for model_name in INSTRUCTBLIP_PRETRAINED_MODEL_ARCHIVE_LIST: - model = InstructBlipForConditionalGeneration.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Salesforce/instructblip-flan-t5-xl" + model = InstructBlipForConditionalGeneration.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/kosmos2/test_modeling_kosmos2.py b/tests/models/kosmos2/test_modeling_kosmos2.py index 7fbb40e828..9bc95b8bd4 100644 --- a/tests/models/kosmos2/test_modeling_kosmos2.py +++ b/tests/models/kosmos2/test_modeling_kosmos2.py @@ -44,7 +44,6 @@ if is_torch_available(): import torch from transformers import Kosmos2ForConditionalGeneration, Kosmos2Model - from transformers.models.kosmos2.modeling_kosmos2 import KOSMOS2_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -425,9 +424,9 @@ class Kosmos2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in KOSMOS2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Kosmos2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/kosmos-2-patch14-224" + model = Kosmos2Model.from_pretrained(model_name) + self.assertIsNotNone(model) def _create_and_check_torchscript(self, config, inputs_dict): if not self.test_torchscript: diff --git a/tests/models/layoutlm/test_modeling_tf_layoutlm.py b/tests/models/layoutlm/test_modeling_tf_layoutlm.py index 96ce692a66..14fc59ff71 100644 --- a/tests/models/layoutlm/test_modeling_tf_layoutlm.py +++ b/tests/models/layoutlm/test_modeling_tf_layoutlm.py @@ -31,7 +31,6 @@ if is_tf_available(): import tensorflow as tf from transformers.models.layoutlm.modeling_tf_layoutlm import ( - TF_LAYOUTLM_PRETRAINED_MODEL_ARCHIVE_LIST, TFLayoutLMForMaskedLM, TFLayoutLMForQuestionAnswering, TFLayoutLMForSequenceClassification, @@ -265,9 +264,9 @@ class TFLayoutLMModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.Test @slow def test_model_from_pretrained(self): - for model_name in TF_LAYOUTLM_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFLayoutLMModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/layoutlm-base-uncased" + model = TFLayoutLMModel.from_pretrained(model_name) + self.assertIsNotNone(model) # TODO (Joao): fix me @unittest.skip("Onnx compliancy broke with TF 2.10") diff --git a/tests/models/layoutlmv2/test_modeling_layoutlmv2.py b/tests/models/layoutlmv2/test_modeling_layoutlmv2.py index f1a0cc6c43..d70721e04c 100644 --- a/tests/models/layoutlmv2/test_modeling_layoutlmv2.py +++ b/tests/models/layoutlmv2/test_modeling_layoutlmv2.py @@ -36,7 +36,6 @@ if is_torch_available(): LayoutLMv2ForTokenClassification, LayoutLMv2Model, ) - from transformers.models.layoutlmv2.modeling_layoutlmv2 import LAYOUTLMV2_PRETRAINED_MODEL_ARCHIVE_LIST if is_detectron2_available(): from detectron2.structures.image_list import ImageList @@ -422,9 +421,9 @@ class LayoutLMv2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCa @slow def test_model_from_pretrained(self): - for model_name in LAYOUTLMV2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = LayoutLMv2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/layoutlmv2-base-uncased" + model = LayoutLMv2Model.from_pretrained(model_name) + self.assertIsNotNone(model) def test_initialization(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/layoutlmv3/test_modeling_layoutlmv3.py b/tests/models/layoutlmv3/test_modeling_layoutlmv3.py index bf9a0b8314..f280633c6a 100644 --- a/tests/models/layoutlmv3/test_modeling_layoutlmv3.py +++ b/tests/models/layoutlmv3/test_modeling_layoutlmv3.py @@ -40,7 +40,6 @@ if is_torch_available(): LayoutLMv3ForTokenClassification, LayoutLMv3Model, ) - from transformers.models.layoutlmv3.modeling_layoutlmv3 import LAYOUTLMV3_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): from PIL import Image @@ -368,9 +367,9 @@ class LayoutLMv3ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCa @slow def test_model_from_pretrained(self): - for model_name in LAYOUTLMV3_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = LayoutLMv3Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/layoutlmv3-base" + model = LayoutLMv3Model.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/layoutlmv3/test_modeling_tf_layoutlmv3.py b/tests/models/layoutlmv3/test_modeling_tf_layoutlmv3.py index 5ea4cb625c..6ae2e5090e 100644 --- a/tests/models/layoutlmv3/test_modeling_tf_layoutlmv3.py +++ b/tests/models/layoutlmv3/test_modeling_tf_layoutlmv3.py @@ -36,7 +36,6 @@ if is_tf_available(): import tensorflow as tf from transformers import ( - TF_LAYOUTLMV3_PRETRAINED_MODEL_ARCHIVE_LIST, TF_MODEL_FOR_MULTIPLE_CHOICE_MAPPING, TF_MODEL_FOR_QUESTION_ANSWERING_MAPPING, TF_MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING, @@ -468,9 +467,9 @@ class TFLayoutLMv3ModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.Te @slow def test_model_from_pretrained(self): - for model_name in TF_LAYOUTLMV3_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFLayoutLMv3Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/layoutlmv3-base" + model = TFLayoutLMv3Model.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/levit/test_modeling_levit.py b/tests/models/levit/test_modeling_levit.py index fee3eaa086..38c9c88594 100644 --- a/tests/models/levit/test_modeling_levit.py +++ b/tests/models/levit/test_modeling_levit.py @@ -40,7 +40,6 @@ if is_torch_available(): MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES, MODEL_MAPPING_NAMES, ) - from transformers.models.levit.modeling_levit import LEVIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -382,9 +381,9 @@ class LevitModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in LEVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = LevitModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/levit-128S" + model = LevitModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats @@ -398,13 +397,11 @@ def prepare_img(): class LevitModelIntegrationTest(unittest.TestCase): @cached_property def default_image_processor(self): - return LevitImageProcessor.from_pretrained(LEVIT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + return LevitImageProcessor.from_pretrained("facebook/levit-128S") @slow def test_inference_image_classification_head(self): - model = LevitForImageClassificationWithTeacher.from_pretrained(LEVIT_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to( - torch_device - ) + model = LevitForImageClassificationWithTeacher.from_pretrained("facebook/levit-128S").to(torch_device) image_processor = self.default_image_processor image = prepare_img() diff --git a/tests/models/lilt/test_modeling_lilt.py b/tests/models/lilt/test_modeling_lilt.py index 653178e2ad..0d0ed720c5 100644 --- a/tests/models/lilt/test_modeling_lilt.py +++ b/tests/models/lilt/test_modeling_lilt.py @@ -34,7 +34,6 @@ if is_torch_available(): LiltForTokenClassification, LiltModel, ) - from transformers.models.lilt.modeling_lilt import LILT_PRETRAINED_MODEL_ARCHIVE_LIST class LiltModelTester: @@ -295,9 +294,9 @@ class LiltModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin @slow def test_model_from_pretrained(self): - for model_name in LILT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = LiltModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "SCUT-DLVCLab/lilt-roberta-en-base" + model = LiltModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/longt5/test_modeling_longt5.py b/tests/models/longt5/test_modeling_longt5.py index 5a8075c2db..c65af001e1 100644 --- a/tests/models/longt5/test_modeling_longt5.py +++ b/tests/models/longt5/test_modeling_longt5.py @@ -39,7 +39,6 @@ if is_torch_available(): LongT5ForConditionalGeneration, LongT5Model, ) - from transformers.models.longt5.modeling_longt5 import LONGT5_PRETRAINED_MODEL_ARCHIVE_LIST class LongT5ModelTester: @@ -590,9 +589,9 @@ class LongT5ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMix @slow def test_model_from_pretrained(self): - for model_name in LONGT5_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = LongT5Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/long-t5-local-base" + model = LongT5Model.from_pretrained(model_name) + self.assertIsNotNone(model) @slow def test_export_to_onnx(self): diff --git a/tests/models/luke/test_modeling_luke.py b/tests/models/luke/test_modeling_luke.py index 4f1ed2e2e3..a35d5ec3dc 100644 --- a/tests/models/luke/test_modeling_luke.py +++ b/tests/models/luke/test_modeling_luke.py @@ -38,7 +38,6 @@ if is_torch_available(): LukeModel, LukeTokenizer, ) - from transformers.models.luke.modeling_luke import LUKE_PRETRAINED_MODEL_ARCHIVE_LIST class LukeModelTester: @@ -699,9 +698,9 @@ class LukeModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in LUKE_PRETRAINED_MODEL_ARCHIVE_LIST: - model = LukeModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "studio-ousia/luke-base" + model = LukeModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_for_masked_lm(self): config_and_inputs = self.model_tester.prepare_config_and_inputs() diff --git a/tests/models/lxmert/test_modeling_lxmert.py b/tests/models/lxmert/test_modeling_lxmert.py index 63d83de36b..723fef6061 100644 --- a/tests/models/lxmert/test_modeling_lxmert.py +++ b/tests/models/lxmert/test_modeling_lxmert.py @@ -38,7 +38,6 @@ if is_torch_available(): LxmertForQuestionAnswering, LxmertModel, ) - from transformers.models.lxmert.modeling_lxmert import LXMERT_PRETRAINED_MODEL_ARCHIVE_LIST if is_tf_available(): @@ -584,10 +583,10 @@ class LxmertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in LXMERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = LxmertModel.from_pretrained(model_name) - model.to(torch_device) - self.assertIsNotNone(model) + model_name = "unc-nlp/lxmert-base-uncased" + model = LxmertModel.from_pretrained(model_name) + model.to(torch_device) + self.assertIsNotNone(model) def test_attention_outputs(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() @@ -772,7 +771,7 @@ class LxmertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): class LxmertModelIntegrationTest(unittest.TestCase): @slow def test_inference_no_head_absolute_embedding(self): - model = LxmertModel.from_pretrained(LXMERT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + model = LxmertModel.from_pretrained("unc-nlp/lxmert-base-uncased") input_ids = torch.tensor([[101, 345, 232, 328, 740, 140, 1695, 69, 6078, 1588, 102]]) num_visual_features = 10 _, visual_feats = np.random.seed(0), np.random.rand(1, num_visual_features, model.config.visual_feat_dim) diff --git a/tests/models/m2m_100/test_tokenization_m2m_100.py b/tests/models/m2m_100/test_tokenization_m2m_100.py index ced6cf13de..76cadf2f3b 100644 --- a/tests/models/m2m_100/test_tokenization_m2m_100.py +++ b/tests/models/m2m_100/test_tokenization_m2m_100.py @@ -94,10 +94,6 @@ class M2M100TokenizationTest(TokenizerTesterMixin, unittest.TestCase): # The length of the vocab keys can be different # self.assertEqual(len(vocab_keys), tokenizer.vocab_size) - @unittest.skip("Skip this test while all models are still to be uploaded.") - def test_pretrained_model_lists(self): - pass - def test_full_tokenizer(self): tokenizer = self.get_tokenizer() diff --git a/tests/models/mega/test_modeling_mega.py b/tests/models/mega/test_modeling_mega.py index e07f4efedd..872f0a38af 100644 --- a/tests/models/mega/test_modeling_mega.py +++ b/tests/models/mega/test_modeling_mega.py @@ -44,7 +44,6 @@ if is_torch_available(): MegaForTokenClassification, MegaModel, ) - from transformers.models.mega.modeling_mega import MEGA_PRETRAINED_MODEL_ARCHIVE_LIST class MegaModelTester: @@ -672,9 +671,9 @@ class MegaModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin @slow def test_model_from_pretrained(self): - for model_name in MEGA_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = MegaModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "mnaylor/mega-base-wikitext" + model = MegaModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip(reason="Does not work on the tiny model as we keep hitting edge cases.") def test_cpu_offload(self): diff --git a/tests/models/mobilebert/test_modeling_tf_mobilebert.py b/tests/models/mobilebert/test_modeling_tf_mobilebert.py index b2b1e58ec0..c6c7d00da0 100644 --- a/tests/models/mobilebert/test_modeling_tf_mobilebert.py +++ b/tests/models/mobilebert/test_modeling_tf_mobilebert.py @@ -313,7 +313,7 @@ class TFMobileBertModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.Te @slow def test_model_from_pretrained(self): - # for model_name in TF_MOBILEBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: + # model_name = 'google/mobilebert-uncased' for model_name in ["google/mobilebert-uncased"]: model = TFMobileBertModel.from_pretrained(model_name) self.assertIsNotNone(model) diff --git a/tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py b/tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py index 6262475b8d..3be955a729 100644 --- a/tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py +++ b/tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py @@ -30,7 +30,6 @@ if is_torch_available(): import torch from transformers import MobileNetV1ForImageClassification, MobileNetV1Model - from transformers.models.mobilenet_v1.modeling_mobilenet_v1 import MOBILENET_V1_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -212,9 +211,9 @@ class MobileNetV1ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestC @slow def test_model_from_pretrained(self): - for model_name in MOBILENET_V1_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = MobileNetV1Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/mobilenet_v1_1.0_224" + model = MobileNetV1Model.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/mobilenet_v2/test_modeling_mobilenet_v2.py b/tests/models/mobilenet_v2/test_modeling_mobilenet_v2.py index 17dfe452c2..f8a1ce8d26 100644 --- a/tests/models/mobilenet_v2/test_modeling_mobilenet_v2.py +++ b/tests/models/mobilenet_v2/test_modeling_mobilenet_v2.py @@ -30,7 +30,6 @@ if is_torch_available(): import torch from transformers import MobileNetV2ForImageClassification, MobileNetV2ForSemanticSegmentation, MobileNetV2Model - from transformers.models.mobilenet_v2.modeling_mobilenet_v2 import MOBILENET_V2_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -267,9 +266,9 @@ class MobileNetV2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestC @slow def test_model_from_pretrained(self): - for model_name in MOBILENET_V2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = MobileNetV2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/mobilenet_v2_1.4_224" + model = MobileNetV2Model.from_pretrained(model_name) + self.assertIsNotNone(model) @is_flaky(description="is_flaky https://github.com/huggingface/transformers/issues/29516") def test_batching_equivalence(self): diff --git a/tests/models/mobilevit/test_modeling_mobilevit.py b/tests/models/mobilevit/test_modeling_mobilevit.py index fc2ea5eba3..0fb94f38d6 100644 --- a/tests/models/mobilevit/test_modeling_mobilevit.py +++ b/tests/models/mobilevit/test_modeling_mobilevit.py @@ -30,7 +30,6 @@ if is_torch_available(): import torch from transformers import MobileViTForImageClassification, MobileViTForSemanticSegmentation, MobileViTModel - from transformers.models.mobilevit.modeling_mobilevit import MOBILEVIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -272,9 +271,9 @@ class MobileViTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCas @slow def test_model_from_pretrained(self): - for model_name in MOBILEVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = MobileViTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "apple/mobilevit-small" + model = MobileViTModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/mobilevit/test_modeling_tf_mobilevit.py b/tests/models/mobilevit/test_modeling_tf_mobilevit.py index 289d739774..3132b93649 100644 --- a/tests/models/mobilevit/test_modeling_tf_mobilevit.py +++ b/tests/models/mobilevit/test_modeling_tf_mobilevit.py @@ -34,7 +34,6 @@ if is_tf_available(): import tensorflow as tf from transformers import TFMobileViTForImageClassification, TFMobileViTForSemanticSegmentation, TFMobileViTModel - from transformers.models.mobilevit.modeling_tf_mobilevit import TF_MOBILEVIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -366,9 +365,9 @@ class TFMobileViTModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.Tes @slow def test_model_from_pretrained(self): - for model_name in TF_MOBILEVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFMobileViTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "apple/mobilevit-small" + model = TFMobileViTModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/mobilevitv2/test_modeling_mobilevitv2.py b/tests/models/mobilevitv2/test_modeling_mobilevitv2.py index 1fb6be94a2..ff45a8c0b6 100644 --- a/tests/models/mobilevitv2/test_modeling_mobilevitv2.py +++ b/tests/models/mobilevitv2/test_modeling_mobilevitv2.py @@ -31,7 +31,6 @@ if is_torch_available(): from transformers import MobileViTV2ForImageClassification, MobileViTV2ForSemanticSegmentation, MobileViTV2Model from transformers.models.mobilevitv2.modeling_mobilevitv2 import ( - MOBILEVITV2_PRETRAINED_MODEL_ARCHIVE_LIST, make_divisible, ) @@ -279,9 +278,9 @@ class MobileViTV2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestC @slow def test_model_from_pretrained(self): - for model_name in MOBILEVITV2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = MobileViTV2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "apple/mobilevitv2-1.0-imagenet1k-256" + model = MobileViTV2Model.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/mpt/test_modeling_mpt.py b/tests/models/mpt/test_modeling_mpt.py index e70b344d8c..40385fc3fd 100644 --- a/tests/models/mpt/test_modeling_mpt.py +++ b/tests/models/mpt/test_modeling_mpt.py @@ -30,7 +30,6 @@ if is_torch_available(): import torch from transformers import ( - MPT_PRETRAINED_MODEL_ARCHIVE_LIST, AutoTokenizer, MptForCausalLM, MptForQuestionAnswering, @@ -429,9 +428,9 @@ class MptModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin, @slow def test_model_from_pretrained(self): - for model_name in MPT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = MptModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "mosaicml/mpt-7b" + model = MptModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow diff --git a/tests/models/mra/test_modeling_mra.py b/tests/models/mra/test_modeling_mra.py index a1b4b4464c..a0bf0ec65e 100644 --- a/tests/models/mra/test_modeling_mra.py +++ b/tests/models/mra/test_modeling_mra.py @@ -36,7 +36,6 @@ if is_torch_available(): MraForTokenClassification, MraModel, ) - from transformers.models.mra.modeling_mra import MRA_PRETRAINED_MODEL_ARCHIVE_LIST class MraModelTester: @@ -352,9 +351,9 @@ class MraModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in MRA_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = MraModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "uw-madison/mra-base-512-4" + model = MraModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip(reason="MRA does not output attentions") def test_attention_outputs(self): diff --git a/tests/models/mt5/test_modeling_mt5.py b/tests/models/mt5/test_modeling_mt5.py index 9e7dd443e2..f6f138cb33 100644 --- a/tests/models/mt5/test_modeling_mt5.py +++ b/tests/models/mt5/test_modeling_mt5.py @@ -51,7 +51,6 @@ if is_torch_available(): MT5ForTokenClassification, MT5Model, ) - from transformers.models.mt5.modeling_mt5 import MT5_PRETRAINED_MODEL_ARCHIVE_LIST # Copied from tests.models.t5.test_modeling_t5.T5ModelTester with T5->MT5 @@ -546,7 +545,7 @@ class MT5ModelTester: @require_torch -# Copied from tests.models.t5.test_modeling_t5.T5ModelTest with T5->MT5 +# Copied from tests.models.t5.test_modeling_t5.T5ModelTest with T5->MT5, google-t5/t5-small->google/mt5-small class MT5ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin, unittest.TestCase): all_model_classes = ( (MT5Model, MT5ForConditionalGeneration, MT5ForSequenceClassification, MT5ForQuestionAnswering) @@ -835,9 +834,9 @@ class MT5ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin, @slow def test_model_from_pretrained(self): - for model_name in MT5_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = MT5Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/mt5-small" + model = MT5Model.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip("Test has a segmentation fault on torch 1.8.0") def test_export_to_onnx(self): diff --git a/tests/models/nat/test_modeling_nat.py b/tests/models/nat/test_modeling_nat.py index cbdbfc83c5..6a68311cc6 100644 --- a/tests/models/nat/test_modeling_nat.py +++ b/tests/models/nat/test_modeling_nat.py @@ -32,7 +32,6 @@ if is_torch_available(): from torch import nn from transformers import NatBackbone, NatForImageClassification, NatModel - from transformers.models.nat.modeling_nat import NAT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): from PIL import Image @@ -327,9 +326,9 @@ class NatModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in NAT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = NatModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "shi-labs/nat-mini-in1k-224" + model = NatModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_initialization(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/nezha/test_modeling_nezha.py b/tests/models/nezha/test_modeling_nezha.py index a71823d8a5..311866758b 100644 --- a/tests/models/nezha/test_modeling_nezha.py +++ b/tests/models/nezha/test_modeling_nezha.py @@ -40,7 +40,6 @@ if is_torch_available(): NezhaForTokenClassification, NezhaModel, ) - from transformers.models.nezha.modeling_nezha import NEZHA_PRETRAINED_MODEL_ARCHIVE_LIST class NezhaModelTester: @@ -432,9 +431,9 @@ class NezhaModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixi @slow def test_model_from_pretrained(self): - for model_name in NEZHA_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = NezhaModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "sijunhe/nezha-cn-base" + model = NezhaModel.from_pretrained(model_name) + self.assertIsNotNone(model) @slow @require_torch_gpu diff --git a/tests/models/nystromformer/test_modeling_nystromformer.py b/tests/models/nystromformer/test_modeling_nystromformer.py index ae06670103..f5bcb0ba5f 100644 --- a/tests/models/nystromformer/test_modeling_nystromformer.py +++ b/tests/models/nystromformer/test_modeling_nystromformer.py @@ -36,7 +36,6 @@ if is_torch_available(): NystromformerForTokenClassification, NystromformerModel, ) - from transformers.models.nystromformer.modeling_nystromformer import NYSTROMFORMER_PRETRAINED_MODEL_ARCHIVE_LIST class NystromformerModelTester: @@ -284,9 +283,9 @@ class NystromformerModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.Tes @slow def test_model_from_pretrained(self): - for model_name in NYSTROMFORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = NystromformerModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "uw-madison/nystromformer-512" + model = NystromformerModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/openai/test_modeling_openai.py b/tests/models/openai/test_modeling_openai.py index 718c224bf0..49e6d50bc4 100644 --- a/tests/models/openai/test_modeling_openai.py +++ b/tests/models/openai/test_modeling_openai.py @@ -29,7 +29,6 @@ if is_torch_available(): import torch from transformers import ( - OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST, OpenAIGPTConfig, OpenAIGPTDoubleHeadsModel, OpenAIGPTForSequenceClassification, @@ -270,9 +269,9 @@ class OpenAIGPTModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTester @slow def test_model_from_pretrained(self): - for model_name in OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = OpenAIGPTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "openai-community/openai-gpt" + model = OpenAIGPTModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/openai/test_modeling_tf_openai.py b/tests/models/openai/test_modeling_tf_openai.py index 6704ec9753..f6bf7c5217 100644 --- a/tests/models/openai/test_modeling_tf_openai.py +++ b/tests/models/openai/test_modeling_tf_openai.py @@ -30,7 +30,6 @@ if is_tf_available(): import tensorflow as tf from transformers.models.openai.modeling_tf_openai import ( - TF_OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST, TFOpenAIGPTDoubleHeadsModel, TFOpenAIGPTForSequenceClassification, TFOpenAIGPTLMHeadModel, @@ -253,9 +252,9 @@ class TFOpenAIGPTModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.Tes @slow def test_model_from_pretrained(self): - for model_name in TF_OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFOpenAIGPTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "openai-community/openai-gpt" + model = TFOpenAIGPTModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_tf diff --git a/tests/models/owlv2/test_modeling_owlv2.py b/tests/models/owlv2/test_modeling_owlv2.py index 74fbaa58d0..d29f8c08c0 100644 --- a/tests/models/owlv2/test_modeling_owlv2.py +++ b/tests/models/owlv2/test_modeling_owlv2.py @@ -50,7 +50,6 @@ if is_torch_available(): from torch import nn from transformers import Owlv2ForObjectDetection, Owlv2Model, Owlv2TextModel, Owlv2VisionModel - from transformers.models.owlv2.modeling_owlv2 import OWLV2_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -138,7 +137,7 @@ class Owlv2VisionModelTester: @require_torch -# Copied from tests.models.owlvit.test_modeling_owlvit.OwlViTVisionModelTest with OwlViT->Owlv2, OWL-ViT->OwlV2, OWLVIT->OWLV2 +# Copied from tests.models.owlvit.test_modeling_owlvit.OwlViTVisionModelTest with OwlViT->Owlv2, OWL-ViT->OwlV2, OWLVIT->OWLV2, owlvit-base-patch32->owlv2-base-patch16-ensemble class Owlv2VisionModelTest(ModelTesterMixin, unittest.TestCase): """ Here we also overwrite some of the tests of test_modeling_common.py, as OWLV2 does not use input_ids, inputs_embeds, @@ -219,9 +218,9 @@ class Owlv2VisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in OWLV2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Owlv2VisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/owlv2-base-patch16-ensemble" + model = Owlv2VisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) # Copied from tests.models.owlvit.test_modeling_owlvit.OwlViTTextModelTester with OwlViT->Owlv2 @@ -315,7 +314,7 @@ class Owlv2TextModelTester: @require_torch -# Copied from tests.models.owlvit.test_modeling_owlvit.OwlViTTextModelTest with OwlViT->Owlv2, OWL-ViT->OwlV2, OWLVIT->OWLV2 +# Copied from tests.models.owlvit.test_modeling_owlvit.OwlViTTextModelTest with OwlViT->Owlv2, OWL-ViT->OwlV2, OWLVIT->OWLV2, owlvit-base-patch32->owlv2-base-patch16-ensemble class Owlv2TextModelTest(ModelTesterMixin, unittest.TestCase): all_model_classes = (Owlv2TextModel,) if is_torch_available() else () fx_compatible = False @@ -367,9 +366,9 @@ class Owlv2TextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in OWLV2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Owlv2TextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/owlv2-base-patch16-ensemble" + model = Owlv2TextModel.from_pretrained(model_name) + self.assertIsNotNone(model) class Owlv2ModelTester: @@ -430,7 +429,7 @@ class Owlv2ModelTester: @require_torch -# Copied from tests.models.owlvit.test_modeling_owlvit.OwlViTModelTest with OwlViT->Owlv2, OWL-ViT->OwlV2, OWLVIT->OWLV2 +# Copied from tests.models.owlvit.test_modeling_owlvit.OwlViTModelTest with OwlViT->Owlv2, OWL-ViT->OwlV2, OWLVIT->OWLV2, owlvit-base-patch32->owlv2-base-patch16-ensemble class Owlv2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): all_model_classes = (Owlv2Model,) if is_torch_available() else () pipeline_model_mapping = ( @@ -578,9 +577,9 @@ class Owlv2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in OWLV2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Owlv2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/owlv2-base-patch16-ensemble" + model = Owlv2Model.from_pretrained(model_name) + self.assertIsNotNone(model) # Copied from tests.models.owlvit.test_modeling_owlvit.OwlViTForObjectDetectionTester with OwlViT->Owlv2, OWL-ViT->OwlV2, OWLVIT->OWLV2 @@ -644,7 +643,7 @@ class Owlv2ForObjectDetectionTester: @require_torch -# Copied from tests.models.owlvit.test_modeling_owlvit.OwlViTForObjectDetectionTest with OwlViT->Owlv2, OWL-ViT->OwlV2, OWLVIT->OWLV2 +# Copied from tests.models.owlvit.test_modeling_owlvit.OwlViTForObjectDetectionTest with OwlViT->Owlv2, OWL-ViT->OwlV2, OWLVIT->OWLV2, owlvit-base-patch32->owlv2-base-patch16-ensemble class Owlv2ForObjectDetectionTest(ModelTesterMixin, unittest.TestCase): all_model_classes = (Owlv2ForObjectDetection,) if is_torch_available() else () fx_compatible = False @@ -777,9 +776,9 @@ class Owlv2ForObjectDetectionTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in OWLV2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Owlv2ForObjectDetection.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/owlv2-base-patch16-ensemble" + model = Owlv2ForObjectDetection.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/owlvit/test_modeling_owlvit.py b/tests/models/owlvit/test_modeling_owlvit.py index 1966aaeda2..370de65447 100644 --- a/tests/models/owlvit/test_modeling_owlvit.py +++ b/tests/models/owlvit/test_modeling_owlvit.py @@ -50,7 +50,6 @@ if is_torch_available(): from torch import nn from transformers import OwlViTForObjectDetection, OwlViTModel, OwlViTTextModel, OwlViTVisionModel - from transformers.models.owlvit.modeling_owlvit import OWLVIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -217,9 +216,9 @@ class OwlViTVisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in OWLVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = OwlViTVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/owlvit-base-patch32" + model = OwlViTVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) class OwlViTTextModelTester: @@ -363,9 +362,9 @@ class OwlViTTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in OWLVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = OwlViTTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/owlvit-base-patch32" + model = OwlViTTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) class OwlViTModelTester: @@ -573,9 +572,9 @@ class OwlViTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in OWLVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = OwlViTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/owlvit-base-patch32" + model = OwlViTModel.from_pretrained(model_name) + self.assertIsNotNone(model) class OwlViTForObjectDetectionTester: @@ -770,9 +769,9 @@ class OwlViTForObjectDetectionTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in OWLVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = OwlViTForObjectDetection.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/owlvit-base-patch32" + model = OwlViTForObjectDetection.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/perceiver/test_modeling_perceiver.py b/tests/models/perceiver/test_modeling_perceiver.py index a529c4430f..fbd237bc10 100644 --- a/tests/models/perceiver/test_modeling_perceiver.py +++ b/tests/models/perceiver/test_modeling_perceiver.py @@ -56,7 +56,6 @@ if is_torch_available(): MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING_NAMES, MODEL_MAPPING_NAMES, ) - from transformers.models.perceiver.modeling_perceiver import PERCEIVER_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -832,9 +831,9 @@ class PerceiverModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCas @slow def test_model_from_pretrained(self): - for model_name in PERCEIVER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = PerceiverModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "deepmind/language-perceiver" + model = PerceiverModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/perceiver/test_tokenization_perceiver.py b/tests/models/perceiver/test_tokenization_perceiver.py index b5d149e5f2..ff2b6e68dc 100644 --- a/tests/models/perceiver/test_tokenization_perceiver.py +++ b/tests/models/perceiver/test_tokenization_perceiver.py @@ -270,10 +270,6 @@ class PerceiverTokenizationTest(TokenizerTesterMixin, unittest.TestCase): tokenizer = self.perceiver_tokenizer self.assertEqual(tokenizer.decode([178]), "�") - # tokenizer can be instantiated without any pretrained files, so no need for pretrained tokenizer list - def test_pretrained_model_lists(self): - pass - # tokenizer does not have vocabulary def test_get_vocab(self): pass diff --git a/tests/models/pix2struct/test_modeling_pix2struct.py b/tests/models/pix2struct/test_modeling_pix2struct.py index 0745362272..abc29bfbb7 100644 --- a/tests/models/pix2struct/test_modeling_pix2struct.py +++ b/tests/models/pix2struct/test_modeling_pix2struct.py @@ -48,7 +48,6 @@ if is_torch_available(): Pix2StructTextModel, Pix2StructVisionModel, ) - from transformers.models.pix2struct.modeling_pix2struct import PIX2STRUCT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -222,9 +221,9 @@ class Pix2StructVisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in PIX2STRUCT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Pix2StructVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/pix2struct-textcaps-base" + model = Pix2StructVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) class Pix2StructTextModelTester: @@ -371,9 +370,9 @@ class Pix2StructTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in PIX2STRUCT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Pix2StructTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/pix2struct-textcaps-base" + model = Pix2StructTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) class Pix2StructModelTester: diff --git a/tests/models/poolformer/test_modeling_poolformer.py b/tests/models/poolformer/test_modeling_poolformer.py index e387053f11..ca5c3015a7 100644 --- a/tests/models/poolformer/test_modeling_poolformer.py +++ b/tests/models/poolformer/test_modeling_poolformer.py @@ -30,7 +30,6 @@ if is_torch_available(): import torch from transformers import MODEL_MAPPING, PoolFormerConfig, PoolFormerForImageClassification, PoolFormerModel - from transformers.models.poolformer.modeling_poolformer import POOLFORMER_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -209,9 +208,9 @@ class PoolFormerModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCa @slow def test_model_from_pretrained(self): - for model_name in POOLFORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = PoolFormerModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "sail/poolformer_s12" + model = PoolFormerModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/pop2piano/test_modeling_pop2piano.py b/tests/models/pop2piano/test_modeling_pop2piano.py index a99f713a7b..594f79b083 100644 --- a/tests/models/pop2piano/test_modeling_pop2piano.py +++ b/tests/models/pop2piano/test_modeling_pop2piano.py @@ -44,7 +44,6 @@ if is_torch_available(): import torch from transformers import Pop2PianoForConditionalGeneration - from transformers.models.pop2piano.modeling_pop2piano import POP2PIANO_PRETRAINED_MODEL_ARCHIVE_LIST @require_torch @@ -607,9 +606,9 @@ class Pop2PianoModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTester @slow def test_model_from_pretrained(self): - for model_name in POP2PIANO_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Pop2PianoForConditionalGeneration.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "sweetcocoa/pop2piano" + model = Pop2PianoForConditionalGeneration.from_pretrained(model_name) + self.assertIsNotNone(model) @require_onnx def test_export_to_onnx(self): diff --git a/tests/models/pvt/test_modeling_pvt.py b/tests/models/pvt/test_modeling_pvt.py index 3b8c917f1d..d18a336a4a 100644 --- a/tests/models/pvt/test_modeling_pvt.py +++ b/tests/models/pvt/test_modeling_pvt.py @@ -37,7 +37,6 @@ if is_torch_available(): from transformers import PvtConfig, PvtForImageClassification, PvtImageProcessor, PvtModel from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES - from transformers.models.pvt.modeling_pvt import PVT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -254,9 +253,9 @@ class PvtModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in PVT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = PvtModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "Zetatech/pvt-tiny-224" + model = PvtModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/pvt_v2/test_modeling_pvt_v2.py b/tests/models/pvt_v2/test_modeling_pvt_v2.py index b8c53ac3e7..9d8dfafa7c 100644 --- a/tests/models/pvt_v2/test_modeling_pvt_v2.py +++ b/tests/models/pvt_v2/test_modeling_pvt_v2.py @@ -19,6 +19,7 @@ import tempfile import unittest from transformers import PvtV2Backbone, PvtV2Config, is_torch_available, is_vision_available +from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES from transformers.testing_utils import ( require_accelerate, require_torch, @@ -38,8 +39,6 @@ if is_torch_available(): import torch from transformers import AutoImageProcessor, PvtV2ForImageClassification, PvtV2Model - from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES - from transformers.models.pvt_v2.modeling_pvt_v2 import PVT_V2_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -312,9 +311,9 @@ class PvtV2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in PVT_V2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = PvtV2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "OpenGVLab/pvt_v2_b0" + model = PvtV2Model.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/qdqbert/test_modeling_qdqbert.py b/tests/models/qdqbert/test_modeling_qdqbert.py index e8c6d17986..ed7f5a3239 100644 --- a/tests/models/qdqbert/test_modeling_qdqbert.py +++ b/tests/models/qdqbert/test_modeling_qdqbert.py @@ -39,7 +39,6 @@ if is_torch_available(): QDQBertLMHeadModel, QDQBertModel, ) - from transformers.models.qdqbert.modeling_qdqbert import QDQBERT_PRETRAINED_MODEL_ARCHIVE_LIST class QDQBertModelTester: @@ -537,9 +536,9 @@ class QDQBertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in QDQBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = QDQBertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google-bert/bert-base-uncased" + model = QDQBertModel.from_pretrained(model_name) + self.assertIsNotNone(model) # Override def test_feed_forward_chunking(self): diff --git a/tests/models/reformer/test_modeling_reformer.py b/tests/models/reformer/test_modeling_reformer.py index 11cd7e1a33..d3996a31c6 100644 --- a/tests/models/reformer/test_modeling_reformer.py +++ b/tests/models/reformer/test_modeling_reformer.py @@ -37,7 +37,6 @@ if is_torch_available(): from torch import nn from transformers import ( - REFORMER_PRETRAINED_MODEL_ARCHIVE_LIST, ReformerForMaskedLM, ReformerForQuestionAnswering, ReformerForSequenceClassification, @@ -616,9 +615,9 @@ class ReformerLocalAttnModelTest(ReformerTesterMixin, GenerationTesterMixin, Mod @slow def test_model_from_pretrained(self): - for model_name in REFORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ReformerModelWithLMHead.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/reformer-crime-and-punishment" + model = ReformerModelWithLMHead.from_pretrained(model_name) + self.assertIsNotNone(model) def _check_attentions_for_generate( self, batch_size, attentions, min_length, max_length, config, use_cache=False, num_beam_groups=1 diff --git a/tests/models/regnet/test_modeling_regnet.py b/tests/models/regnet/test_modeling_regnet.py index 420609bf03..8840a141fa 100644 --- a/tests/models/regnet/test_modeling_regnet.py +++ b/tests/models/regnet/test_modeling_regnet.py @@ -31,7 +31,6 @@ if is_torch_available(): from torch import nn from transformers import RegNetForImageClassification, RegNetModel - from transformers.models.regnet.modeling_regnet import REGNET_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -220,9 +219,9 @@ class RegNetModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in REGNET_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = RegNetModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/regnet-y-040" + model = RegNetModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats @@ -236,15 +235,11 @@ def prepare_img(): class RegNetModelIntegrationTest(unittest.TestCase): @cached_property def default_image_processor(self): - return ( - AutoImageProcessor.from_pretrained(REGNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) - if is_vision_available() - else None - ) + return AutoImageProcessor.from_pretrained("facebook/regnet-y-040") if is_vision_available() else None @slow def test_inference_image_classification_head(self): - model = RegNetForImageClassification.from_pretrained(REGNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device) + model = RegNetForImageClassification.from_pretrained("facebook/regnet-y-040").to(torch_device) image_processor = self.default_image_processor image = prepare_img() diff --git a/tests/models/regnet/test_modeling_tf_regnet.py b/tests/models/regnet/test_modeling_tf_regnet.py index a2f2bf92ef..70adc9c875 100644 --- a/tests/models/regnet/test_modeling_tf_regnet.py +++ b/tests/models/regnet/test_modeling_tf_regnet.py @@ -32,7 +32,7 @@ from ...test_pipeline_mixin import PipelineTesterMixin if is_tf_available(): import tensorflow as tf - from transformers import TF_REGNET_PRETRAINED_MODEL_ARCHIVE_LIST, TFRegNetForImageClassification, TFRegNetModel + from transformers import TFRegNetForImageClassification, TFRegNetModel if is_vision_available(): @@ -252,9 +252,9 @@ class TFRegNetModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCa @slow def test_model_from_pretrained(self): - for model_name in TF_REGNET_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFRegNetModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/regnet-y-040" + model = TFRegNetModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats @@ -268,15 +268,11 @@ def prepare_img(): class RegNetModelIntegrationTest(unittest.TestCase): @cached_property def default_image_processor(self): - return ( - AutoImageProcessor.from_pretrained(TF_REGNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) - if is_vision_available() - else None - ) + return AutoImageProcessor.from_pretrained("facebook/regnet-y-040") if is_vision_available() else None @slow def test_inference_image_classification_head(self): - model = TFRegNetForImageClassification.from_pretrained(TF_REGNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + model = TFRegNetForImageClassification.from_pretrained("facebook/regnet-y-040") image_processor = self.default_image_processor image = prepare_img() diff --git a/tests/models/rembert/test_modeling_rembert.py b/tests/models/rembert/test_modeling_rembert.py index 557a42243d..fe21ae2ecf 100644 --- a/tests/models/rembert/test_modeling_rembert.py +++ b/tests/models/rembert/test_modeling_rembert.py @@ -38,7 +38,6 @@ if is_torch_available(): RemBertForTokenClassification, RemBertModel, ) - from transformers.models.rembert.modeling_rembert import REMBERT_PRETRAINED_MODEL_ARCHIVE_LIST class RemBertModelTester: @@ -465,9 +464,9 @@ class RemBertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in REMBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = RemBertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/rembert" + model = RemBertModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/resnet/test_modeling_resnet.py b/tests/models/resnet/test_modeling_resnet.py index 543013bc41..0fd32bc72f 100644 --- a/tests/models/resnet/test_modeling_resnet.py +++ b/tests/models/resnet/test_modeling_resnet.py @@ -32,7 +32,6 @@ if is_torch_available(): from torch import nn from transformers import ResNetBackbone, ResNetForImageClassification, ResNetModel - from transformers.models.resnet.modeling_resnet import RESNET_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -273,9 +272,9 @@ class ResNetModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in RESNET_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ResNetModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/resnet-50" + model = ResNetModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats @@ -289,15 +288,11 @@ def prepare_img(): class ResNetModelIntegrationTest(unittest.TestCase): @cached_property def default_image_processor(self): - return ( - AutoImageProcessor.from_pretrained(RESNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) - if is_vision_available() - else None - ) + return AutoImageProcessor.from_pretrained("microsoft/resnet-50") if is_vision_available() else None @slow def test_inference_image_classification_head(self): - model = ResNetForImageClassification.from_pretrained(RESNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device) + model = ResNetForImageClassification.from_pretrained("microsoft/resnet-50").to(torch_device) image_processor = self.default_image_processor image = prepare_img() diff --git a/tests/models/resnet/test_modeling_tf_resnet.py b/tests/models/resnet/test_modeling_tf_resnet.py index 827fc807df..a8e2ce93ee 100644 --- a/tests/models/resnet/test_modeling_tf_resnet.py +++ b/tests/models/resnet/test_modeling_tf_resnet.py @@ -35,7 +35,6 @@ if is_tf_available(): import tensorflow as tf from transformers import TFResNetForImageClassification, TFResNetModel - from transformers.models.resnet.modeling_tf_resnet import TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -214,9 +213,9 @@ class TFResNetModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCa @slow def test_model_from_pretrained(self): - for model_name in TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFResNetModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/resnet-50" + model = TFResNetModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats @@ -230,15 +229,11 @@ def prepare_img(): class TFResNetModelIntegrationTest(unittest.TestCase): @cached_property def default_image_processor(self): - return ( - AutoImageProcessor.from_pretrained(TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) - if is_vision_available() - else None - ) + return AutoImageProcessor.from_pretrained("microsoft/resnet-50") if is_vision_available() else None @slow def test_inference_image_classification_head(self): - model = TFResNetForImageClassification.from_pretrained(TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + model = TFResNetForImageClassification.from_pretrained("microsoft/resnet-50") image_processor = self.default_image_processor image = prepare_img() diff --git a/tests/models/roberta/test_modeling_roberta.py b/tests/models/roberta/test_modeling_roberta.py index 402d60d37a..700f0d1cf7 100644 --- a/tests/models/roberta/test_modeling_roberta.py +++ b/tests/models/roberta/test_modeling_roberta.py @@ -38,7 +38,6 @@ if is_torch_available(): RobertaModel, ) from transformers.models.roberta.modeling_roberta import ( - ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST, RobertaEmbeddings, create_position_ids_from_input_ids, ) @@ -477,9 +476,9 @@ class RobertaModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMi @slow def test_model_from_pretrained(self): - for model_name in ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = RobertaModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "FacebookAI/roberta-base" + model = RobertaModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_create_position_ids_respects_padding_index(self): """Ensure that the default position ids only assign a sequential . This is a regression diff --git a/tests/models/roberta/test_modeling_tf_roberta.py b/tests/models/roberta/test_modeling_tf_roberta.py index 37377ab5ba..8125a7f0a0 100644 --- a/tests/models/roberta/test_modeling_tf_roberta.py +++ b/tests/models/roberta/test_modeling_tf_roberta.py @@ -31,7 +31,6 @@ if is_tf_available(): import tensorflow as tf from transformers.models.roberta.modeling_tf_roberta import ( - TF_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST, TFRobertaForCausalLM, TFRobertaForMaskedLM, TFRobertaForMultipleChoice, @@ -655,9 +654,9 @@ class TFRobertaModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestC @slow def test_model_from_pretrained(self): - for model_name in TF_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFRobertaModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "FacebookAI/roberta-base" + model = TFRobertaModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_tf diff --git a/tests/models/roberta_prelayernorm/test_modeling_roberta_prelayernorm.py b/tests/models/roberta_prelayernorm/test_modeling_roberta_prelayernorm.py index c975718778..3536ccc871 100644 --- a/tests/models/roberta_prelayernorm/test_modeling_roberta_prelayernorm.py +++ b/tests/models/roberta_prelayernorm/test_modeling_roberta_prelayernorm.py @@ -38,7 +38,6 @@ if is_torch_available(): RobertaPreLayerNormModel, ) from transformers.models.roberta_prelayernorm.modeling_roberta_prelayernorm import ( - ROBERTA_PRELAYERNORM_PRETRAINED_MODEL_ARCHIVE_LIST, RobertaPreLayerNormEmbeddings, create_position_ids_from_input_ids, ) @@ -482,11 +481,10 @@ class RobertaPreLayerNormModelTest(ModelTesterMixin, GenerationTesterMixin, Pipe self.model_tester.create_and_check_for_question_answering(*config_and_inputs) @slow - # Copied from tests.models.roberta.test_modeling_roberta.RobertaModelTest.test_model_from_pretrained with ROBERTA->ROBERTA_PRELAYERNORM,Roberta->RobertaPreLayerNorm def test_model_from_pretrained(self): - for model_name in ROBERTA_PRELAYERNORM_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = RobertaPreLayerNormModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "andreasmadsen/efficient_mlm_m0.15" + model = RobertaPreLayerNormModel.from_pretrained(model_name) + self.assertIsNotNone(model) # Copied from tests.models.roberta.test_modeling_roberta.RobertaModelTest.test_create_position_ids_respects_padding_index with Roberta->RobertaPreLayerNorm def test_create_position_ids_respects_padding_index(self): diff --git a/tests/models/roberta_prelayernorm/test_modeling_tf_roberta_prelayernorm.py b/tests/models/roberta_prelayernorm/test_modeling_tf_roberta_prelayernorm.py index 384fa2e9e4..2138541603 100644 --- a/tests/models/roberta_prelayernorm/test_modeling_tf_roberta_prelayernorm.py +++ b/tests/models/roberta_prelayernorm/test_modeling_tf_roberta_prelayernorm.py @@ -31,7 +31,6 @@ if is_tf_available(): import tensorflow as tf from transformers.models.roberta_prelayernorm.modeling_tf_roberta_prelayernorm import ( - TF_ROBERTA_PRELAYERNORM_PRETRAINED_MODEL_ARCHIVE_LIST, TFRobertaPreLayerNormForCausalLM, TFRobertaPreLayerNormForMaskedLM, TFRobertaPreLayerNormForMultipleChoice, @@ -551,7 +550,7 @@ class TFRobertaPreLayerNormModelTester: @require_tf -# Copied from tests.models.roberta.test_modeling_tf_roberta.TFRobertaModelTest with ROBERTA->ROBERTA_PRELAYERNORM,Roberta->RobertaPreLayerNorm +# Copied from tests.models.roberta.test_modeling_tf_roberta.TFRobertaModelTest with ROBERTA->ROBERTA_PRELAYERNORM,Roberta->RobertaPreLayerNorm,FacebookAI/roberta-base->andreasmadsen/efficient_mlm_m0.15 class TFRobertaPreLayerNormModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase): all_model_classes = ( ( @@ -657,9 +656,9 @@ class TFRobertaPreLayerNormModelTest(TFModelTesterMixin, PipelineTesterMixin, un @slow def test_model_from_pretrained(self): - for model_name in TF_ROBERTA_PRELAYERNORM_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFRobertaPreLayerNormModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "andreasmadsen/efficient_mlm_m0.15" + model = TFRobertaPreLayerNormModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_tf diff --git a/tests/models/roc_bert/test_modeling_roc_bert.py b/tests/models/roc_bert/test_modeling_roc_bert.py index d1caca6b6f..d52304ade9 100644 --- a/tests/models/roc_bert/test_modeling_roc_bert.py +++ b/tests/models/roc_bert/test_modeling_roc_bert.py @@ -39,7 +39,6 @@ if is_torch_available(): RoCBertForTokenClassification, RoCBertModel, ) - from transformers.models.roc_bert.modeling_roc_bert import ROC_BERT_PRETRAINED_MODEL_ARCHIVE_LIST class RoCBertModelTester: @@ -718,9 +717,9 @@ class RoCBertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in ROC_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = RoCBertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "weiweishi/roc-bert-base-zh" + model = RoCBertModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/roformer/test_modeling_roformer.py b/tests/models/roformer/test_modeling_roformer.py index 6c130ae174..64ce38c515 100644 --- a/tests/models/roformer/test_modeling_roformer.py +++ b/tests/models/roformer/test_modeling_roformer.py @@ -38,7 +38,6 @@ if is_torch_available(): RoFormerModel, ) from transformers.models.roformer.modeling_roformer import ( - ROFORMER_PRETRAINED_MODEL_ARCHIVE_LIST, RoFormerSelfAttention, RoFormerSinusoidalPositionalEmbedding, ) @@ -482,9 +481,9 @@ class RoFormerModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in ROFORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = RoFormerModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "junnyu/roformer_chinese_small" + model = RoFormerModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip( reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" diff --git a/tests/models/rwkv/test_modeling_rwkv.py b/tests/models/rwkv/test_modeling_rwkv.py index 4ca5cfdf9e..d2a41a863d 100644 --- a/tests/models/rwkv/test_modeling_rwkv.py +++ b/tests/models/rwkv/test_modeling_rwkv.py @@ -30,7 +30,6 @@ if is_torch_available(): import torch from transformers import ( - RWKV_PRETRAINED_MODEL_ARCHIVE_LIST, RwkvForCausalLM, RwkvModel, ) @@ -419,9 +418,9 @@ class RwkvModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin @slow def test_model_from_pretrained(self): - for model_name in RWKV_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = RwkvModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "RWKV/rwkv-4-169m-pile" + model = RwkvModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skipIf( diff --git a/tests/models/sam/test_modeling_sam.py b/tests/models/sam/test_modeling_sam.py index 3e63edb23a..a10365d369 100644 --- a/tests/models/sam/test_modeling_sam.py +++ b/tests/models/sam/test_modeling_sam.py @@ -34,7 +34,6 @@ if is_torch_available(): from torch import nn from transformers import SamModel, SamProcessor - from transformers.models.sam.modeling_sam import SAM_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -442,9 +441,9 @@ class SamModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in SAM_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SamModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/sam-vit-huge" + model = SamModel.from_pretrained(model_name) + self.assertIsNotNone(model) def prepare_image(): diff --git a/tests/models/seamless_m4t/test_modeling_seamless_m4t.py b/tests/models/seamless_m4t/test_modeling_seamless_m4t.py index 365775171e..c08e559057 100644 --- a/tests/models/seamless_m4t/test_modeling_seamless_m4t.py +++ b/tests/models/seamless_m4t/test_modeling_seamless_m4t.py @@ -46,9 +46,6 @@ if is_torch_available(): SeamlessM4TForTextToText, SeamlessM4TModel, ) - from transformers.models.seamless_m4t.modeling_seamless_m4t import ( - SEAMLESS_M4T_PRETRAINED_MODEL_ARCHIVE_LIST, - ) if is_speech_available(): from transformers import SeamlessM4TProcessor @@ -379,9 +376,9 @@ class SeamlessM4TModelWithSpeechInputTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in SEAMLESS_M4T_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SeamlessM4TModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/hf-seamless-m4t-medium" + model = SeamlessM4TModel.from_pretrained(model_name) + self.assertIsNotNone(model) def _get_input_ids_and_config(self, batch_size=2): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() @@ -667,9 +664,9 @@ class SeamlessM4TModelWithTextInputTest( @slow def test_model_from_pretrained(self): - for model_name in SEAMLESS_M4T_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SeamlessM4TModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/hf-seamless-m4t-medium" + model = SeamlessM4TModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_initialization(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/seamless_m4t_v2/test_modeling_seamless_m4t_v2.py b/tests/models/seamless_m4t_v2/test_modeling_seamless_m4t_v2.py index 795f3d8042..699641fcfd 100644 --- a/tests/models/seamless_m4t_v2/test_modeling_seamless_m4t_v2.py +++ b/tests/models/seamless_m4t_v2/test_modeling_seamless_m4t_v2.py @@ -45,9 +45,6 @@ if is_torch_available(): SeamlessM4Tv2ForTextToText, SeamlessM4Tv2Model, ) - from transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2 import ( - SEAMLESS_M4T_V2_PRETRAINED_MODEL_ARCHIVE_LIST, - ) if is_speech_available(): from transformers import SeamlessM4TProcessor @@ -395,9 +392,9 @@ class SeamlessM4Tv2ModelWithSpeechInputTest(ModelTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in SEAMLESS_M4T_V2_PRETRAINED_MODEL_ARCHIVE_LIST: - model = SeamlessM4Tv2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/seamless-m4t-v2-large" + model = SeamlessM4Tv2Model.from_pretrained(model_name) + self.assertIsNotNone(model) def _get_input_ids_and_config(self, batch_size=2): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() @@ -662,9 +659,9 @@ class SeamlessM4Tv2ModelWithTextInputTest(ModelTesterMixin, GenerationTesterMixi @slow def test_model_from_pretrained(self): - for model_name in SEAMLESS_M4T_V2_PRETRAINED_MODEL_ARCHIVE_LIST: - model = SeamlessM4Tv2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/seamless-m4t-v2-large" + model = SeamlessM4Tv2Model.from_pretrained(model_name) + self.assertIsNotNone(model) def test_initialization(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/segformer/test_modeling_segformer.py b/tests/models/segformer/test_modeling_segformer.py index de64de5ad1..fb38338513 100644 --- a/tests/models/segformer/test_modeling_segformer.py +++ b/tests/models/segformer/test_modeling_segformer.py @@ -34,7 +34,6 @@ if is_torch_available(): SegformerModel, ) from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES - from transformers.models.segformer.modeling_segformer import SEGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -335,9 +334,9 @@ class SegformerModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCas @slow def test_model_from_pretrained(self): - for model_name in SEGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SegformerModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "nvidia/segformer-b0-finetuned-ade-512-512" + model = SegformerModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/segformer/test_modeling_tf_segformer.py b/tests/models/segformer/test_modeling_tf_segformer.py index aca621f509..16b5740a08 100644 --- a/tests/models/segformer/test_modeling_tf_segformer.py +++ b/tests/models/segformer/test_modeling_tf_segformer.py @@ -34,7 +34,6 @@ if is_tf_available(): import tensorflow as tf from transformers import TFSegformerForImageClassification, TFSegformerForSemanticSegmentation, TFSegformerModel - from transformers.models.segformer.modeling_tf_segformer import TF_SEGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): from PIL import Image @@ -438,9 +437,9 @@ class TFSegformerModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.Tes @slow def test_model_from_pretrained(self): - for model_name in TF_SEGFORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFSegformerModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "nvidia/segformer-b0-finetuned-ade-512-512" + model = TFSegformerModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/seggpt/test_modeling_seggpt.py b/tests/models/seggpt/test_modeling_seggpt.py index 5f7920f9a3..d4a8a46f03 100644 --- a/tests/models/seggpt/test_modeling_seggpt.py +++ b/tests/models/seggpt/test_modeling_seggpt.py @@ -39,7 +39,6 @@ if is_torch_available(): from torch import nn from transformers import SegGptForImageSegmentation, SegGptModel - from transformers.models.seggpt.modeling_seggpt import SEGGPT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -301,9 +300,9 @@ class SegGptModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in SEGGPT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SegGptModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "BAAI/seggpt-vit-large" + model = SegGptModel.from_pretrained(model_name) + self.assertIsNotNone(model) def prepare_img(): diff --git a/tests/models/siglip/test_modeling_siglip.py b/tests/models/siglip/test_modeling_siglip.py index 45212751a8..8880168484 100644 --- a/tests/models/siglip/test_modeling_siglip.py +++ b/tests/models/siglip/test_modeling_siglip.py @@ -48,7 +48,6 @@ if is_torch_available(): from torch import nn from transformers import SiglipForImageClassification, SiglipModel, SiglipTextModel, SiglipVisionModel - from transformers.models.siglip.modeling_siglip import SIGLIP_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -217,9 +216,9 @@ class SiglipVisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in SIGLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SiglipVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/siglip-base-patch16-224" + model = SiglipVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) class SiglipTextModelTester: @@ -374,9 +373,9 @@ class SiglipTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in SIGLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SiglipTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/siglip-base-patch16-224" + model = SiglipTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) class SiglipModelTester: @@ -578,11 +577,10 @@ class SiglipModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): self.assertDictEqual(config.text_config.to_dict(), text_config.to_dict()) @slow - # Copied from tests.models.clip.test_modeling_clip.CLIPModelTest.test_model_from_pretrained with CLIPModel->SiglipModel, CLIP->SIGLIP def test_model_from_pretrained(self): - for model_name in SIGLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SiglipModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/siglip-base-patch16-224" + model = SiglipModel.from_pretrained(model_name) + self.assertIsNotNone(model) class SiglipForImageClassificationModelTester(SiglipModelTester): diff --git a/tests/models/siglip/test_tokenization_siglip.py b/tests/models/siglip/test_tokenization_siglip.py index fb3cb5b3f1..839c0c3200 100644 --- a/tests/models/siglip/test_tokenization_siglip.py +++ b/tests/models/siglip/test_tokenization_siglip.py @@ -348,14 +348,6 @@ class SiglipTokenizationTest(TokenizerTesterMixin, unittest.TestCase): special_tokens_string_rust = rust_tokenizer.convert_tokens_to_string(special_tokens) self.assertEqual(special_tokens_string, special_tokens_string_rust) - # overwritten from `test_tokenization_common` since Siglip has no max length - # Copied from tests.models.t5.test_tokenization_t5.T5TokenizationTest.test_pretrained_model_lists with T5->Siglip - def test_pretrained_model_lists(self): - # We should have at least one default checkpoint for each tokenizer - # We should specify the max input length as well (used in some part to list the pretrained checkpoints) - self.assertGreaterEqual(len(self.tokenizer_class.pretrained_vocab_files_map), 1) - self.assertGreaterEqual(len(list(self.tokenizer_class.pretrained_vocab_files_map.values())[0]), 1) - @slow def test_tokenizer_integration(self): tokenizer = SiglipTokenizer.from_pretrained("google/siglip-base-patch16-224") diff --git a/tests/models/splinter/test_modeling_splinter.py b/tests/models/splinter/test_modeling_splinter.py index 90ee07c354..b6a2588c87 100644 --- a/tests/models/splinter/test_modeling_splinter.py +++ b/tests/models/splinter/test_modeling_splinter.py @@ -29,7 +29,6 @@ if is_torch_available(): import torch from transformers import SplinterConfig, SplinterForPreTraining, SplinterForQuestionAnswering, SplinterModel - from transformers.models.splinter.modeling_splinter import SPLINTER_PRETRAINED_MODEL_ARCHIVE_LIST class SplinterModelTester: @@ -328,9 +327,9 @@ class SplinterModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in SPLINTER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SplinterModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "tau/splinter-base" + model = SplinterModel.from_pretrained(model_name) + self.assertIsNotNone(model) # overwrite from common since `SplinterForPreTraining` could contain different number of question tokens in inputs. # When the batch is distributed to multiple devices, each replica could get different values for the maximal number diff --git a/tests/models/squeezebert/test_modeling_squeezebert.py b/tests/models/squeezebert/test_modeling_squeezebert.py index bf86792f57..1682146e1a 100644 --- a/tests/models/squeezebert/test_modeling_squeezebert.py +++ b/tests/models/squeezebert/test_modeling_squeezebert.py @@ -28,7 +28,6 @@ if is_torch_available(): import torch from transformers import ( - SQUEEZEBERT_PRETRAINED_MODEL_ARCHIVE_LIST, SqueezeBertForMaskedLM, SqueezeBertForMultipleChoice, SqueezeBertForQuestionAnswering, @@ -277,9 +276,9 @@ class SqueezeBertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestC @slow def test_model_from_pretrained(self): - for model_name in SQUEEZEBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SqueezeBertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "squeezebert/squeezebert-uncased" + model = SqueezeBertModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_sentencepiece diff --git a/tests/models/swiftformer/test_modeling_swiftformer.py b/tests/models/swiftformer/test_modeling_swiftformer.py index a1e6229d5a..c54e092809 100644 --- a/tests/models/swiftformer/test_modeling_swiftformer.py +++ b/tests/models/swiftformer/test_modeling_swiftformer.py @@ -37,7 +37,6 @@ if is_torch_available(): from torch import nn from transformers import SwiftFormerForImageClassification, SwiftFormerModel - from transformers.models.swiftformer.modeling_swiftformer import SWIFTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -186,9 +185,9 @@ class SwiftFormerModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestC @slow def test_model_from_pretrained(self): - for model_name in SWIFTFORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SwiftFormerModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "MBZUAI/swiftformer-xs" + model = SwiftFormerModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip(reason="SwiftFormer does not output attentions") def test_attention_outputs(self): diff --git a/tests/models/swin/test_modeling_swin.py b/tests/models/swin/test_modeling_swin.py index cd0b99fdc9..9220784e23 100644 --- a/tests/models/swin/test_modeling_swin.py +++ b/tests/models/swin/test_modeling_swin.py @@ -32,7 +32,6 @@ if is_torch_available(): from torch import nn from transformers import SwinBackbone, SwinForImageClassification, SwinForMaskedImageModeling, SwinModel - from transformers.models.swin.modeling_swin import SWIN_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -446,9 +445,9 @@ class SwinModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in SWIN_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SwinModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/swin-tiny-patch4-window7-224" + model = SwinModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_initialization(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/swin/test_modeling_tf_swin.py b/tests/models/swin/test_modeling_tf_swin.py index e15ecbc41d..f05ef7a434 100644 --- a/tests/models/swin/test_modeling_tf_swin.py +++ b/tests/models/swin/test_modeling_tf_swin.py @@ -36,7 +36,6 @@ if is_tf_available(): from transformers.modeling_tf_utils import keras from transformers.models.swin.modeling_tf_swin import ( - TF_SWIN_PRETRAINED_MODEL_ARCHIVE_LIST, TFSwinForImageClassification, TFSwinForMaskedImageModeling, TFSwinModel, @@ -374,9 +373,9 @@ class TFSwinModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in TF_SWIN_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFSwinModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/swin-tiny-patch4-window7-224" + model = TFSwinModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_vision diff --git a/tests/models/swin2sr/test_modeling_swin2sr.py b/tests/models/swin2sr/test_modeling_swin2sr.py index 556b65a249..44ca7b9249 100644 --- a/tests/models/swin2sr/test_modeling_swin2sr.py +++ b/tests/models/swin2sr/test_modeling_swin2sr.py @@ -29,7 +29,6 @@ if is_torch_available(): from torch import nn from transformers import Swin2SRForImageSuperResolution, Swin2SRModel - from transformers.models.swin2sr.modeling_swin2sr import SWIN2SR_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): from PIL import Image @@ -233,9 +232,9 @@ class Swin2SRModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in SWIN2SR_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Swin2SRModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "caidas/swin2SR-classical-sr-x2-64" + model = Swin2SRModel.from_pretrained(model_name) + self.assertIsNotNone(model) # overwriting because of `logit_scale` parameter def test_initialization(self): diff --git a/tests/models/swinv2/test_modeling_swinv2.py b/tests/models/swinv2/test_modeling_swinv2.py index 73f731cd60..b8f97ee7c2 100644 --- a/tests/models/swinv2/test_modeling_swinv2.py +++ b/tests/models/swinv2/test_modeling_swinv2.py @@ -32,7 +32,6 @@ if is_torch_available(): from torch import nn from transformers import Swinv2Backbone, Swinv2ForImageClassification, Swinv2ForMaskedImageModeling, Swinv2Model - from transformers.models.swinv2.modeling_swinv2 import SWINV2_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): from PIL import Image @@ -432,9 +431,9 @@ class Swinv2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in SWINV2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = Swinv2Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/swinv2-tiny-patch4-window8-256" + model = Swinv2Model.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip(reason="Swinv2 does not support feedforward chunking yet") def test_feed_forward_chunking(self): diff --git a/tests/models/switch_transformers/test_modeling_switch_transformers.py b/tests/models/switch_transformers/test_modeling_switch_transformers.py index b21fa405c3..f8c3afc1ed 100644 --- a/tests/models/switch_transformers/test_modeling_switch_transformers.py +++ b/tests/models/switch_transformers/test_modeling_switch_transformers.py @@ -45,7 +45,6 @@ if is_torch_available(): SwitchTransformersTop1Router, ) from transformers.models.switch_transformers.modeling_switch_transformers import ( - SWITCH_TRANSFORMERS_PRETRAINED_MODEL_ARCHIVE_LIST, load_balancing_loss_func, router_z_loss_func, ) @@ -670,9 +669,9 @@ class SwitchTransformersModelTest(ModelTesterMixin, GenerationTesterMixin, Pipel @slow def test_model_from_pretrained(self): - for model_name in SWITCH_TRANSFORMERS_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = SwitchTransformersModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/switch-base-8" + model = SwitchTransformersModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip("Test has a segmentation fault on torch 1.8.0") def test_export_to_onnx(self): diff --git a/tests/models/t5/test_modeling_t5.py b/tests/models/t5/test_modeling_t5.py index c0a43dfeab..c215bda5e1 100644 --- a/tests/models/t5/test_modeling_t5.py +++ b/tests/models/t5/test_modeling_t5.py @@ -56,7 +56,6 @@ if is_torch_available(): T5Model, T5Tokenizer, ) - from transformers.models.t5.modeling_t5 import T5_PRETRAINED_MODEL_ARCHIVE_LIST class T5ModelTester: @@ -838,9 +837,9 @@ class T5ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin, @slow def test_model_from_pretrained(self): - for model_name in T5_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = T5Model.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google-t5/t5-small" + model = T5Model.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip("Test has a segmentation fault on torch 1.8.0") def test_export_to_onnx(self): diff --git a/tests/models/t5/test_tokenization_t5.py b/tests/models/t5/test_tokenization_t5.py index 388388ff23..ed753612fc 100644 --- a/tests/models/t5/test_tokenization_t5.py +++ b/tests/models/t5/test_tokenization_t5.py @@ -227,7 +227,7 @@ class T5TokenizationTest(TokenizerTesterMixin, unittest.TestCase): # Since T5 does NOT have a max input length, # this test should be changed to the following in Transformers v5: # self.assertEqual(batch.input_ids.shape, (2, 8001)) - self.assertEqual(batch.input_ids.shape, (2, 512)) + self.assertEqual(batch.input_ids.shape, (2, 8001)) def test_eos_in_input(self): tokenizer = self.t5_base_tokenizer @@ -362,12 +362,6 @@ class T5TokenizationTest(TokenizerTesterMixin, unittest.TestCase): ) # overwritten from `test_tokenization_common` since T5 has no max length - def test_pretrained_model_lists(self): - # We should have at least one default checkpoint for each tokenizer - # We should specify the max input length as well (used in some part to list the pretrained checkpoints) - self.assertGreaterEqual(len(self.tokenizer_class.pretrained_vocab_files_map), 1) - self.assertGreaterEqual(len(list(self.tokenizer_class.pretrained_vocab_files_map.values())[0]), 1) - @slow def test_tokenizer_integration(self): expected_encoding = {'input_ids': [[31220, 7, 41, 14034, 801, 38, 3, 102, 63, 17, 127, 524, 18, 7031, 2032, 277, 11, 3, 102, 63, 17, 127, 524, 18, 2026, 17, 10761, 18, 7041, 61, 795, 879, 18, 19681, 4648, 7, 41, 12920, 382, 6, 350, 6383, 4949, 6, 2158, 12920, 382, 9, 6, 3, 4, 11160, 6, 2043, 17153, 279, 49, 17, 6, 3, 4, 434, 9688, 11439, 21, 6869, 10509, 17725, 41, 567, 9138, 61, 11, 6869, 10509, 11946, 41, 18207, 517, 61, 28, 147, 3538, 1220, 7140, 10761, 2250, 16, 910, 1220, 8024, 11, 1659, 1413, 32, 883, 2020, 344, 2215, 226, 6, 12901, 382, 127, 524, 11, 4738, 7, 127, 15390, 5, 1], [272, 24203, 19, 876, 12, 554, 18, 9719, 1659, 2647, 26352, 6497, 7, 45, 73, 9339, 400, 26, 1499, 57, 22801, 10760, 30, 321, 646, 11, 269, 2625, 16, 66, 7500, 5, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [37, 1704, 4216, 3, 20400, 4418, 7, 147, 8, 19743, 1782, 5, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]} # fmt: skip diff --git a/tests/models/tapas/test_tokenization_tapas.py b/tests/models/tapas/test_tokenization_tapas.py index 4100e02b13..8f2bf9bb69 100644 --- a/tests/models/tapas/test_tokenization_tapas.py +++ b/tests/models/tapas/test_tokenization_tapas.py @@ -1268,10 +1268,6 @@ class TapasTokenizationTest(TokenizerTesterMixin, unittest.TestCase): self.assertListEqual(column_ids.tolist(), expected_results["column_ids"]) self.assertListEqual(row_ids.tolist(), expected_results["row_ids"]) - @unittest.skip("Skip this test while all models are still to be uploaded.") - def test_pretrained_model_lists(self): - pass - @unittest.skip("Doesn't support another framework than PyTorch") def test_np_encode_plus_sent_to_model(self): pass diff --git a/tests/models/timesformer/test_modeling_timesformer.py b/tests/models/timesformer/test_modeling_timesformer.py index d4e71c8c59..3d97d2c0f6 100644 --- a/tests/models/timesformer/test_modeling_timesformer.py +++ b/tests/models/timesformer/test_modeling_timesformer.py @@ -40,7 +40,6 @@ if is_torch_available(): TimesformerForVideoClassification, TimesformerModel, ) - from transformers.models.timesformer.modeling_timesformer import TIMESFORMER_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -213,9 +212,9 @@ class TimesformerModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestC @slow def test_model_from_pretrained(self): - for model_name in TIMESFORMER_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TimesformerModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/timesformer-base-finetuned-k400" + model = TimesformerModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_attention_outputs(self): if not self.has_attentions: diff --git a/tests/models/tvlt/test_modeling_tvlt.py b/tests/models/tvlt/test_modeling_tvlt.py index 3ee7f7adc7..ce27946ee7 100644 --- a/tests/models/tvlt/test_modeling_tvlt.py +++ b/tests/models/tvlt/test_modeling_tvlt.py @@ -41,7 +41,6 @@ if is_torch_available(): import torch.nn as nn from transformers import TvltForAudioVisualClassification, TvltForPreTraining, TvltModel - from transformers.models.tvlt.modeling_tvlt import TVLT_PRETRAINED_MODEL_ARCHIVE_LIST if is_datasets_available(): @@ -414,9 +413,9 @@ class TvltModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in TVLT_PRETRAINED_MODEL_ARCHIVE_LIST: - model = TvltModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "ZinengTang/tvlt-base" + model = TvltModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_training(self): if not self.model_tester.is_training: diff --git a/tests/models/udop/test_modeling_udop.py b/tests/models/udop/test_modeling_udop.py index 3947da62cc..7041f25f4e 100644 --- a/tests/models/udop/test_modeling_udop.py +++ b/tests/models/udop/test_modeling_udop.py @@ -39,7 +39,6 @@ if is_torch_available(): import torch from transformers import UdopEncoderModel, UdopForConditionalGeneration, UdopModel, UdopProcessor - from transformers.models.udop.modeling_udop import UDOP_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -359,9 +358,9 @@ class UdopModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in UDOP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = UdopForConditionalGeneration.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/udop-large" + model = UdopForConditionalGeneration.from_pretrained(model_name) + self.assertIsNotNone(model) class UdopEncoderOnlyModelTester: diff --git a/tests/models/udop/test_tokenization_udop.py b/tests/models/udop/test_tokenization_udop.py index 0519ee0622..720eb09952 100644 --- a/tests/models/udop/test_tokenization_udop.py +++ b/tests/models/udop/test_tokenization_udop.py @@ -1726,10 +1726,6 @@ class UdopTokenizationTest(TokenizerTesterMixin, unittest.TestCase): def test_alignement_methods(self): pass - @unittest.skip("#TODO will be removed in main") - def test_pretrained_model_lists(self): - pass - @unittest.skip("UDOP tokenizer requires boxes besides sequences.") def test_maximum_encoding_length_pair_input(self): pass diff --git a/tests/models/upernet/test_modeling_upernet.py b/tests/models/upernet/test_modeling_upernet.py index c51b254ed5..234cd8af09 100644 --- a/tests/models/upernet/test_modeling_upernet.py +++ b/tests/models/upernet/test_modeling_upernet.py @@ -32,7 +32,6 @@ if is_torch_available(): import torch from transformers import UperNetForSemanticSegmentation - from transformers.models.upernet.modeling_upernet import UPERNET_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -248,9 +247,9 @@ class UperNetModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in UPERNET_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = UperNetForSemanticSegmentation.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "openmmlab/upernet-convnext-tiny" + model = UperNetForSemanticSegmentation.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of ADE20k diff --git a/tests/models/videomae/test_modeling_videomae.py b/tests/models/videomae/test_modeling_videomae.py index 2fd9f90c30..e5b1c6b78e 100644 --- a/tests/models/videomae/test_modeling_videomae.py +++ b/tests/models/videomae/test_modeling_videomae.py @@ -41,7 +41,6 @@ if is_torch_available(): VideoMAEForVideoClassification, VideoMAEModel, ) - from transformers.models.videomae.modeling_videomae import VIDEOMAE_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -237,9 +236,9 @@ class VideoMAEModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in VIDEOMAE_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = VideoMAEModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "MCG-NJU/videomae-base" + model = VideoMAEModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_attention_outputs(self): if not self.has_attentions: diff --git a/tests/models/vilt/test_modeling_vilt.py b/tests/models/vilt/test_modeling_vilt.py index afc883ef8f..4c877c2e18 100644 --- a/tests/models/vilt/test_modeling_vilt.py +++ b/tests/models/vilt/test_modeling_vilt.py @@ -40,7 +40,6 @@ if is_torch_available(): ViltModel, ) from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES - from transformers.models.vilt.modeling_vilt import VILT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): import PIL @@ -528,9 +527,9 @@ class ViltModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in VILT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ViltModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "dandelin/vilt-b32-mlm" + model = ViltModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/visual_bert/test_modeling_visual_bert.py b/tests/models/visual_bert/test_modeling_visual_bert.py index c366e9145e..249ccdd84b 100644 --- a/tests/models/visual_bert/test_modeling_visual_bert.py +++ b/tests/models/visual_bert/test_modeling_visual_bert.py @@ -36,7 +36,6 @@ if is_torch_available(): VisualBertForVisualReasoning, VisualBertModel, ) - from transformers.models.visual_bert.modeling_visual_bert import VISUAL_BERT_PRETRAINED_MODEL_ARCHIVE_LIST class VisualBertModelTester: @@ -551,9 +550,9 @@ class VisualBertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCa @slow def test_model_from_pretrained(self): - for model_name in VISUAL_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = VisualBertModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "uclanlp/visualbert-vqa" + model = VisualBertModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip( reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" diff --git a/tests/models/vit/test_modeling_vit.py b/tests/models/vit/test_modeling_vit.py index c8181d2c2b..7298543a56 100644 --- a/tests/models/vit/test_modeling_vit.py +++ b/tests/models/vit/test_modeling_vit.py @@ -39,7 +39,6 @@ if is_torch_available(): from torch import nn from transformers import ViTForImageClassification, ViTForMaskedImageModeling, ViTModel - from transformers.models.vit.modeling_vit import VIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -237,9 +236,9 @@ class ViTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in VIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ViTModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/vit-base-patch16-224" + model = ViTModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/vit_hybrid/test_modeling_vit_hybrid.py b/tests/models/vit_hybrid/test_modeling_vit_hybrid.py index e9fc3de258..d48a885392 100644 --- a/tests/models/vit_hybrid/test_modeling_vit_hybrid.py +++ b/tests/models/vit_hybrid/test_modeling_vit_hybrid.py @@ -31,7 +31,6 @@ if is_torch_available(): from torch import nn from transformers import ViTHybridForImageClassification, ViTHybridImageProcessor, ViTHybridModel - from transformers.models.vit_hybrid.modeling_vit_hybrid import VIT_HYBRID_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -217,9 +216,9 @@ class ViTHybridModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCas @slow def test_model_from_pretrained(self): - for model_name in VIT_HYBRID_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ViTHybridModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/vit-hybrid-base-bit-384" + model = ViTHybridModel.from_pretrained(model_name) + self.assertIsNotNone(model) @is_flaky(description="is_flaky https://github.com/huggingface/transformers/issues/29516") def test_batching_equivalence(self): @@ -238,16 +237,14 @@ class ViTModelIntegrationTest(unittest.TestCase): @cached_property def default_image_processor(self): return ( - ViTHybridImageProcessor.from_pretrained(VIT_HYBRID_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + ViTHybridImageProcessor.from_pretrained("google/vit-hybrid-base-bit-384") if is_vision_available() else None ) @slow def test_inference_image_classification_head(self): - model = ViTHybridForImageClassification.from_pretrained(VIT_HYBRID_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to( - torch_device - ) + model = ViTHybridForImageClassification.from_pretrained("google/vit-hybrid-base-bit-384").to(torch_device) image_processor = self.default_image_processor image = prepare_img() diff --git a/tests/models/vit_mae/test_modeling_vit_mae.py b/tests/models/vit_mae/test_modeling_vit_mae.py index b5196f12bb..ffb679d646 100644 --- a/tests/models/vit_mae/test_modeling_vit_mae.py +++ b/tests/models/vit_mae/test_modeling_vit_mae.py @@ -35,7 +35,6 @@ if is_torch_available(): from torch import nn from transformers import ViTMAEForPreTraining, ViTMAEModel - from transformers.models.vit.modeling_vit import VIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -276,9 +275,9 @@ class ViTMAEModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in VIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ViTMAEModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/vit-base-patch16-224" + model = ViTMAEModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/vit_msn/test_modeling_vit_msn.py b/tests/models/vit_msn/test_modeling_vit_msn.py index a4cc370ec2..5fe494c105 100644 --- a/tests/models/vit_msn/test_modeling_vit_msn.py +++ b/tests/models/vit_msn/test_modeling_vit_msn.py @@ -31,7 +31,6 @@ if is_torch_available(): from torch import nn from transformers import ViTMSNForImageClassification, ViTMSNModel - from transformers.models.vit_msn.modeling_vit_msn import VIT_MSN_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -192,9 +191,9 @@ class ViTMSNModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in VIT_MSN_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = ViTMSNModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/vit-msn-small" + model = ViTMSNModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/vitmatte/test_modeling_vitmatte.py b/tests/models/vitmatte/test_modeling_vitmatte.py index c93e82bafb..4a8e85160b 100644 --- a/tests/models/vitmatte/test_modeling_vitmatte.py +++ b/tests/models/vitmatte/test_modeling_vitmatte.py @@ -36,7 +36,6 @@ if is_torch_available(): import torch from transformers import VitDetConfig, VitMatteForImageMatting - from transformers.models.vitmatte.modeling_vitmatte import VITMATTE_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -195,9 +194,9 @@ class VitMatteModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in VITMATTE_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = VitMatteForImageMatting.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "hustvl/vitmatte-small-composition-1k" + model = VitMatteForImageMatting.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip(reason="ViTMatte does not support retaining gradient on attention logits") def test_retain_grad_hidden_states_attentions(self): diff --git a/tests/models/vivit/test_modeling_vivit.py b/tests/models/vivit/test_modeling_vivit.py index 152cfac155..9b299c9afa 100644 --- a/tests/models/vivit/test_modeling_vivit.py +++ b/tests/models/vivit/test_modeling_vivit.py @@ -37,7 +37,6 @@ if is_torch_available(): from torch import nn from transformers import MODEL_FOR_VIDEO_CLASSIFICATION_MAPPING, VivitForVideoClassification, VivitModel - from transformers.models.vivit.modeling_vivit import VIVIT_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -225,9 +224,9 @@ class VivitModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in VIVIT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = VivitModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "google/vivit-b-16x2-kinetics400" + model = VivitModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_attention_outputs(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() diff --git a/tests/models/wav2vec2/test_feature_extraction_wav2vec2.py b/tests/models/wav2vec2/test_feature_extraction_wav2vec2.py index c4ab09b606..29e4bf3e28 100644 --- a/tests/models/wav2vec2/test_feature_extraction_wav2vec2.py +++ b/tests/models/wav2vec2/test_feature_extraction_wav2vec2.py @@ -20,7 +20,7 @@ import unittest import numpy as np -from transformers import WAV_2_VEC_2_PRETRAINED_MODEL_ARCHIVE_LIST, Wav2Vec2Config, Wav2Vec2FeatureExtractor +from transformers import Wav2Vec2Config, Wav2Vec2FeatureExtractor from transformers.testing_utils import require_torch, slow from ...test_sequence_feature_extraction_common import SequenceFeatureExtractionTestMixin @@ -224,10 +224,10 @@ class Wav2Vec2FeatureExtractionTest(SequenceFeatureExtractionTestMixin, unittest # this test makes sure that models that are using # group norm don't have their feature extractor return the # attention_mask - for model_id in WAV_2_VEC_2_PRETRAINED_MODEL_ARCHIVE_LIST: - config = Wav2Vec2Config.from_pretrained(model_id) - feat_extract = Wav2Vec2FeatureExtractor.from_pretrained(model_id) + model_id = "facebook/wav2vec2-base-960h" + config = Wav2Vec2Config.from_pretrained(model_id) + feat_extract = Wav2Vec2FeatureExtractor.from_pretrained(model_id) - # only "layer" feature extraction norm should make use of - # attention_mask - self.assertEqual(feat_extract.return_attention_mask, config.feat_extract_norm == "layer") + # only "layer" feature extraction norm should make use of + # attention_mask + self.assertEqual(feat_extract.return_attention_mask, config.feat_extract_norm == "layer") diff --git a/tests/models/wav2vec2/test_tokenization_wav2vec2.py b/tests/models/wav2vec2/test_tokenization_wav2vec2.py index 7310b14848..05109f9736 100644 --- a/tests/models/wav2vec2/test_tokenization_wav2vec2.py +++ b/tests/models/wav2vec2/test_tokenization_wav2vec2.py @@ -24,7 +24,6 @@ import unittest import numpy as np from transformers import ( - WAV_2_VEC_2_PRETRAINED_MODEL_ARCHIVE_LIST, AddedToken, Wav2Vec2Config, Wav2Vec2CTCTokenizer, @@ -357,13 +356,13 @@ class Wav2Vec2TokenizerTest(unittest.TestCase): # this test makes sure that models that are using # group norm don't have their tokenizer return the # attention_mask - for model_id in WAV_2_VEC_2_PRETRAINED_MODEL_ARCHIVE_LIST: - config = Wav2Vec2Config.from_pretrained(model_id) - tokenizer = Wav2Vec2Tokenizer.from_pretrained(model_id) + model_id = "facebook/wav2vec2-base-960h" + config = Wav2Vec2Config.from_pretrained(model_id) + tokenizer = Wav2Vec2Tokenizer.from_pretrained(model_id) - # only "layer" feature extraction norm should make use of - # attention_mask - self.assertEqual(tokenizer.return_attention_mask, config.feat_extract_norm == "layer") + # only "layer" feature extraction norm should make use of + # attention_mask + self.assertEqual(tokenizer.return_attention_mask, config.feat_extract_norm == "layer") class Wav2Vec2CTCTokenizerTest(TokenizerTesterMixin, unittest.TestCase): @@ -703,10 +702,6 @@ class Wav2Vec2CTCTokenizerTest(TokenizerTesterMixin, unittest.TestCase): self.assertListEqual(expected_word_time_stamps_start, word_time_stamps_start) self.assertListEqual(expected_word_time_stamps_end, word_time_stamps_end) - def test_pretrained_model_lists(self): - # Wav2Vec2Model has no max model length => no testing - pass - # overwrite from test_tokenization_common def test_add_tokens_tokenizer(self): tokenizers = self.get_tokenizers(do_lower_case=False) diff --git a/tests/models/wav2vec2_phoneme/test_tokenization_wav2vec2_phoneme.py b/tests/models/wav2vec2_phoneme/test_tokenization_wav2vec2_phoneme.py index 56e38f2cf5..ea81c88ede 100644 --- a/tests/models/wav2vec2_phoneme/test_tokenization_wav2vec2_phoneme.py +++ b/tests/models/wav2vec2_phoneme/test_tokenization_wav2vec2_phoneme.py @@ -337,10 +337,6 @@ class Wav2Vec2PhonemeCTCTokenizerTest(TokenizerTesterMixin, unittest.TestCase): pass @unittest.skip("Wav2Vec2PhonemeModel has no max model length => no testing") - def test_pretrained_model_lists(self): - pass - - # overwrite common def test_add_tokens_tokenizer(self): tokenizers = self.get_tokenizers(do_lower_case=False) for tokenizer in tokenizers: diff --git a/tests/models/x_clip/test_modeling_x_clip.py b/tests/models/x_clip/test_modeling_x_clip.py index bf8339c93e..fc5c1679a6 100644 --- a/tests/models/x_clip/test_modeling_x_clip.py +++ b/tests/models/x_clip/test_modeling_x_clip.py @@ -43,7 +43,6 @@ if is_torch_available(): from torch import nn from transformers import XCLIPModel, XCLIPTextModel, XCLIPVisionModel - from transformers.models.x_clip.modeling_x_clip import XCLIP_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -216,9 +215,9 @@ class XCLIPVisionModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in XCLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = XCLIPVisionModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/xclip-base-patch32" + model = XCLIPVisionModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_gradient_checkpointing_backward_compatibility(self): config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() @@ -454,9 +453,9 @@ class XCLIPTextModelTest(ModelTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in XCLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = XCLIPTextModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/xclip-base-patch32" + model = XCLIPTextModel.from_pretrained(model_name) + self.assertIsNotNone(model) class XCLIPModelTester: @@ -684,9 +683,9 @@ class XCLIPModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in XCLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = XCLIPModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "microsoft/xclip-base-patch32" + model = XCLIPModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on a spaghetti video diff --git a/tests/models/xglm/test_modeling_tf_xglm.py b/tests/models/xglm/test_modeling_tf_xglm.py index 3950ccf652..e651d27423 100644 --- a/tests/models/xglm/test_modeling_tf_xglm.py +++ b/tests/models/xglm/test_modeling_tf_xglm.py @@ -29,7 +29,6 @@ if is_tf_available(): import tensorflow as tf from transformers.models.xglm.modeling_tf_xglm import ( - TF_XGLM_PRETRAINED_MODEL_ARCHIVE_LIST, TFXGLMForCausalLM, TFXGLMModel, ) @@ -161,9 +160,9 @@ class TFXGLMModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase @slow def test_model_from_pretrained(self): - for model_name in TF_XGLM_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFXGLMModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/xglm-564M" + model = TFXGLMModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip(reason="Currently, model embeddings are going to undergo a major refactor.") def test_resize_token_embeddings(self): diff --git a/tests/models/xglm/test_modeling_xglm.py b/tests/models/xglm/test_modeling_xglm.py index e482b1b384..5669da7e26 100644 --- a/tests/models/xglm/test_modeling_xglm.py +++ b/tests/models/xglm/test_modeling_xglm.py @@ -36,7 +36,7 @@ from ...test_pipeline_mixin import PipelineTesterMixin if is_torch_available(): import torch - from transformers import XGLM_PRETRAINED_MODEL_ARCHIVE_LIST, XGLMForCausalLM, XGLMModel, XGLMTokenizer + from transformers import XGLMForCausalLM, XGLMModel, XGLMTokenizer class XGLMModelTester: @@ -349,9 +349,9 @@ class XGLMModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin @slow def test_model_from_pretrained(self): - for model_name in XGLM_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = XGLMModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "facebook/xglm-564M" + model = XGLMModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip("Does not work on the tiny model as we keep hitting edge cases.") def test_model_parallelism(self): diff --git a/tests/models/xlm/test_modeling_tf_xlm.py b/tests/models/xlm/test_modeling_tf_xlm.py index 51ba6c2476..139f29db00 100644 --- a/tests/models/xlm/test_modeling_tf_xlm.py +++ b/tests/models/xlm/test_modeling_tf_xlm.py @@ -30,7 +30,6 @@ if is_tf_available(): import tensorflow as tf from transformers import ( - TF_XLM_PRETRAINED_MODEL_ARCHIVE_LIST, TFXLMForMultipleChoice, TFXLMForQuestionAnsweringSimple, TFXLMForSequenceClassification, @@ -360,9 +359,9 @@ class TFXLMModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase) @slow def test_model_from_pretrained(self): - for model_name in TF_XLM_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFXLMModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "FacebookAI/xlm-mlm-en-2048" + model = TFXLMModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_tf diff --git a/tests/models/xlm/test_modeling_xlm.py b/tests/models/xlm/test_modeling_xlm.py index 09ad95e81a..ac0577bd82 100644 --- a/tests/models/xlm/test_modeling_xlm.py +++ b/tests/models/xlm/test_modeling_xlm.py @@ -36,7 +36,6 @@ if is_torch_available(): XLMModel, XLMWithLMHeadModel, ) - from transformers.models.xlm.modeling_xlm import XLM_PRETRAINED_MODEL_ARCHIVE_LIST class XLMModelTester: @@ -505,9 +504,9 @@ class XLMModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin, @slow def test_model_from_pretrained(self): - for model_name in XLM_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = XLMModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "FacebookAI/xlm-mlm-en-2048" + model = XLMModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/xlnet/test_modeling_tf_xlnet.py b/tests/models/xlnet/test_modeling_tf_xlnet.py index 5d17299f9b..ea223914a3 100644 --- a/tests/models/xlnet/test_modeling_tf_xlnet.py +++ b/tests/models/xlnet/test_modeling_tf_xlnet.py @@ -32,7 +32,6 @@ if is_tf_available(): import tensorflow as tf from transformers.models.xlnet.modeling_tf_xlnet import ( - TF_XLNET_PRETRAINED_MODEL_ARCHIVE_LIST, TFXLNetForMultipleChoice, TFXLNetForQuestionAnsweringSimple, TFXLNetForSequenceClassification, @@ -415,9 +414,9 @@ class TFXLNetModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCas @slow def test_model_from_pretrained(self): - for model_name in TF_XLNET_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = TFXLNetModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "xlnet/xlnet-base-cased" + model = TFXLNetModel.from_pretrained(model_name) + self.assertIsNotNone(model) @unittest.skip("Some of the XLNet models misbehave with flexible input shapes.") def test_compile_tf_model(self): diff --git a/tests/models/xlnet/test_modeling_xlnet.py b/tests/models/xlnet/test_modeling_xlnet.py index cd5a3d52b3..ff89a9aca3 100644 --- a/tests/models/xlnet/test_modeling_xlnet.py +++ b/tests/models/xlnet/test_modeling_xlnet.py @@ -37,7 +37,6 @@ if is_torch_available(): XLNetLMHeadModel, XLNetModel, ) - from transformers.models.xlnet.modeling_xlnet import XLNET_PRETRAINED_MODEL_ARCHIVE_LIST class XLNetModelTester: @@ -685,9 +684,9 @@ class XLNetModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixi @slow def test_model_from_pretrained(self): - for model_name in XLNET_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = XLNetModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "xlnet/xlnet-base-cased" + model = XLNetModel.from_pretrained(model_name) + self.assertIsNotNone(model) @require_torch diff --git a/tests/models/yolos/test_modeling_yolos.py b/tests/models/yolos/test_modeling_yolos.py index 4b2aff3094..64a439f27a 100644 --- a/tests/models/yolos/test_modeling_yolos.py +++ b/tests/models/yolos/test_modeling_yolos.py @@ -31,7 +31,6 @@ if is_torch_available(): from torch import nn from transformers import YolosForObjectDetection, YolosModel - from transformers.models.yolos.modeling_yolos import YOLOS_PRETRAINED_MODEL_ARCHIVE_LIST if is_vision_available(): @@ -319,9 +318,9 @@ class YolosModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in YOLOS_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = YolosModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "hustvl/yolos-small" + model = YolosModel.from_pretrained(model_name) + self.assertIsNotNone(model) # We will verify our results on an image of cute cats diff --git a/tests/models/yoso/test_modeling_yoso.py b/tests/models/yoso/test_modeling_yoso.py index 67d7b9edc4..ca41b074bc 100644 --- a/tests/models/yoso/test_modeling_yoso.py +++ b/tests/models/yoso/test_modeling_yoso.py @@ -36,7 +36,6 @@ if is_torch_available(): YosoForTokenClassification, YosoModel, ) - from transformers.models.yoso.modeling_yoso import YOSO_PRETRAINED_MODEL_ARCHIVE_LIST class YosoModelTester: @@ -351,9 +350,9 @@ class YosoModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @slow def test_model_from_pretrained(self): - for model_name in YOSO_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - model = YosoModel.from_pretrained(model_name) - self.assertIsNotNone(model) + model_name = "uw-madison/yoso-4096" + model = YosoModel.from_pretrained(model_name) + self.assertIsNotNone(model) def test_attention_outputs(self): return diff --git a/tests/test_modeling_utils.py b/tests/test_modeling_utils.py index 46df1feae9..4e68fad8ef 100755 --- a/tests/test_modeling_utils.py +++ b/tests/test_modeling_utils.py @@ -85,7 +85,6 @@ if is_torch_available(): from torch import nn from transformers import ( - BERT_PRETRAINED_MODEL_ARCHIVE_LIST, AutoModelForCausalLM, AutoTokenizer, BertConfig, @@ -217,29 +216,29 @@ def check_models_equal(model1, model2): class ModelUtilsTest(TestCasePlus): @slow def test_model_from_pretrained(self): - for model_name in BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: - config = BertConfig.from_pretrained(model_name) - self.assertIsNotNone(config) - self.assertIsInstance(config, PretrainedConfig) + model_name = "google-bert/bert-base-uncased" + config = BertConfig.from_pretrained(model_name) + self.assertIsNotNone(config) + self.assertIsInstance(config, PretrainedConfig) - model = BertModel.from_pretrained(model_name) - model, loading_info = BertModel.from_pretrained(model_name, output_loading_info=True) - self.assertIsNotNone(model) - self.assertIsInstance(model, PreTrainedModel) + model = BertModel.from_pretrained(model_name) + model, loading_info = BertModel.from_pretrained(model_name, output_loading_info=True) + self.assertIsNotNone(model) + self.assertIsInstance(model, PreTrainedModel) - self.assertEqual(len(loading_info["missing_keys"]), 0) - self.assertEqual(len(loading_info["unexpected_keys"]), 8) - self.assertEqual(len(loading_info["mismatched_keys"]), 0) - self.assertEqual(len(loading_info["error_msgs"]), 0) + self.assertEqual(len(loading_info["missing_keys"]), 0) + self.assertEqual(len(loading_info["unexpected_keys"]), 8) + self.assertEqual(len(loading_info["mismatched_keys"]), 0) + self.assertEqual(len(loading_info["error_msgs"]), 0) - config = BertConfig.from_pretrained(model_name, output_attentions=True, output_hidden_states=True) + config = BertConfig.from_pretrained(model_name, output_attentions=True, output_hidden_states=True) - # Not sure this is the intended behavior. TODO fix Lysandre & Thom - config.name_or_path = model_name + # Not sure this is the intended behavior. TODO fix Lysandre & Thom + config.name_or_path = model_name - model = BertModel.from_pretrained(model_name, output_attentions=True, output_hidden_states=True) - self.assertEqual(model.config.output_hidden_states, True) - self.assertEqual(model.config, config) + model = BertModel.from_pretrained(model_name, output_attentions=True, output_hidden_states=True) + self.assertEqual(model.config.output_hidden_states, True) + self.assertEqual(model.config, config) def test_model_from_pretrained_subfolder(self): config = BertConfig.from_pretrained("hf-internal-testing/tiny-random-bert") diff --git a/tests/test_tokenization_common.py b/tests/test_tokenization_common.py index 8216db084c..4ff17ab557 100644 --- a/tests/test_tokenization_common.py +++ b/tests/test_tokenization_common.py @@ -1023,24 +1023,6 @@ class TokenizerTesterMixin: decoded = tokenizer.decode(encoded, spaces_between_special_tokens=False) self.assertIn(decoded, ["[ABC][SAMPLE][DEF]", "[ABC][SAMPLE][DEF]".lower()]) - def test_pretrained_model_lists(self): - # We should have at least one default checkpoint for each tokenizer - # We should specify the max input length as well (used in some part to list the pretrained checkpoints) - self.assertGreaterEqual(len(self.tokenizer_class.pretrained_vocab_files_map), 1) - self.assertGreaterEqual(len(list(self.tokenizer_class.pretrained_vocab_files_map.values())[0]), 1) - self.assertEqual( - len(list(self.tokenizer_class.pretrained_vocab_files_map.values())[0]), - len(self.tokenizer_class.max_model_input_sizes), - ) - - weights_list = list(self.tokenizer_class.max_model_input_sizes.keys()) - weights_lists_2 = [] - for file_id, map_list in self.tokenizer_class.pretrained_vocab_files_map.items(): - weights_lists_2.append(list(map_list.keys())) - - for weights_list_2 in weights_lists_2: - self.assertListEqual(weights_list, weights_list_2) - def test_mask_output(self): tokenizers = self.get_tokenizers(do_lower_case=False) for tokenizer in tokenizers: diff --git a/tests/tokenization/test_tokenization_fast.py b/tests/tokenization/test_tokenization_fast.py index 6e24009ecd..ac073529e2 100644 --- a/tests/tokenization/test_tokenization_fast.py +++ b/tests/tokenization/test_tokenization_fast.py @@ -70,11 +70,6 @@ class PreTrainedTokenizationFastTest(TokenizerTesterMixin, unittest.TestCase): def test_additional_special_tokens_serialization(self): pass - def test_pretrained_model_lists(self): - # We disable this test for PreTrainedTokenizerFast because it is the only tokenizer that is not linked to any - # model - pass - def test_prepare_for_model(self): # We disable this test for PreTrainedTokenizerFast because it is the only tokenizer that is not linked to any # model diff --git a/tests/utils/test_add_new_model_like.py b/tests/utils/test_add_new_model_like.py index b7eceb6e76..9c150b32bd 100644 --- a/tests/utils/test_add_new_model_like.py +++ b/tests/utils/test_add_new_model_like.py @@ -883,7 +883,7 @@ from typing import TYPE_CHECKING from ...utils import _LazyModule, is_flax_available, is_tf_available, is_tokenizers_available, is_torch_available _import_structure = { - "configuration_gpt2": ["GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP", "GPT2Config", "GPT2OnnxConfig"], + "configuration_gpt2": ["GPT2Config", "GPT2OnnxConfig"], "tokenization_gpt2": ["GPT2Tokenizer"], } @@ -920,7 +920,7 @@ else: _import_structure["modeling_flax_gpt2"] = ["FlaxGPT2Model"] if TYPE_CHECKING: - from .configuration_gpt2 import GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP, GPT2Config, GPT2OnnxConfig + from .configuration_gpt2 import GPT2Config, GPT2OnnxConfig from .tokenization_gpt2 import GPT2Tokenizer try: @@ -967,7 +967,7 @@ from typing import TYPE_CHECKING from ...utils import _LazyModule, is_flax_available, is_tf_available, is_torch_available _import_structure = { - "configuration_gpt2": ["GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP", "GPT2Config", "GPT2OnnxConfig"], + "configuration_gpt2": ["GPT2Config", "GPT2OnnxConfig"], } try: @@ -995,7 +995,7 @@ else: _import_structure["modeling_flax_gpt2"] = ["FlaxGPT2Model"] if TYPE_CHECKING: - from .configuration_gpt2 import GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP, GPT2Config, GPT2OnnxConfig + from .configuration_gpt2 import GPT2Config, GPT2OnnxConfig try: if not is_torch_available(): @@ -1033,7 +1033,7 @@ from typing import TYPE_CHECKING from ...utils import _LazyModule, is_tokenizers_available, is_torch_available _import_structure = { - "configuration_gpt2": ["GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP", "GPT2Config", "GPT2OnnxConfig"], + "configuration_gpt2": ["GPT2Config", "GPT2OnnxConfig"], "tokenization_gpt2": ["GPT2Tokenizer"], } @@ -1054,7 +1054,7 @@ else: _import_structure["modeling_gpt2"] = ["GPT2Model"] if TYPE_CHECKING: - from .configuration_gpt2 import GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP, GPT2Config, GPT2OnnxConfig + from .configuration_gpt2 import GPT2Config, GPT2OnnxConfig from .tokenization_gpt2 import GPT2Tokenizer try: @@ -1085,7 +1085,7 @@ from typing import TYPE_CHECKING from ...utils import _LazyModule, is_torch_available _import_structure = { - "configuration_gpt2": ["GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP", "GPT2Config", "GPT2OnnxConfig"], + "configuration_gpt2": ["GPT2Config", "GPT2OnnxConfig"], } try: @@ -1097,7 +1097,7 @@ else: _import_structure["modeling_gpt2"] = ["GPT2Model"] if TYPE_CHECKING: - from .configuration_gpt2 import GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP, GPT2Config, GPT2OnnxConfig + from .configuration_gpt2 import GPT2Config, GPT2OnnxConfig try: if not is_torch_available(): @@ -1135,7 +1135,7 @@ from typing import TYPE_CHECKING from ...utils import _LazyModule, is_flax_available, is_tf_available, is_torch_available, is_vision_available _import_structure = { - "configuration_vit": ["VIT_PRETRAINED_CONFIG_ARCHIVE_MAP", "ViTConfig"], + "configuration_vit": ["ViTConfig"], } try: @@ -1171,7 +1171,7 @@ else: _import_structure["modeling_flax_vit"] = ["FlaxViTModel"] if TYPE_CHECKING: - from .configuration_vit import VIT_PRETRAINED_CONFIG_ARCHIVE_MAP, ViTConfig + from .configuration_vit import ViTConfig try: if not is_vision_available(): @@ -1217,7 +1217,7 @@ from typing import TYPE_CHECKING from ...utils import _LazyModule, is_flax_available, is_tf_available, is_torch_available _import_structure = { - "configuration_vit": ["VIT_PRETRAINED_CONFIG_ARCHIVE_MAP", "ViTConfig"], + "configuration_vit": ["ViTConfig"], } try: @@ -1245,7 +1245,7 @@ else: _import_structure["modeling_flax_vit"] = ["FlaxViTModel"] if TYPE_CHECKING: - from .configuration_vit import VIT_PRETRAINED_CONFIG_ARCHIVE_MAP, ViTConfig + from .configuration_vit import ViTConfig try: if not is_torch_available(): @@ -1283,7 +1283,7 @@ from typing import TYPE_CHECKING from ...utils import _LazyModule, is_torch_available, is_vision_available _import_structure = { - "configuration_vit": ["VIT_PRETRAINED_CONFIG_ARCHIVE_MAP", "ViTConfig"], + "configuration_vit": ["ViTConfig"], } try: @@ -1303,7 +1303,7 @@ else: _import_structure["modeling_vit"] = ["ViTModel"] if TYPE_CHECKING: - from .configuration_vit import VIT_PRETRAINED_CONFIG_ARCHIVE_MAP, ViTConfig + from .configuration_vit import ViTConfig try: if not is_vision_available(): @@ -1333,7 +1333,7 @@ from typing import TYPE_CHECKING from ...utils import _LazyModule, is_torch_available _import_structure = { - "configuration_vit": ["VIT_PRETRAINED_CONFIG_ARCHIVE_MAP", "ViTConfig"], + "configuration_vit": ["ViTConfig"], } try: @@ -1345,7 +1345,7 @@ else: _import_structure["modeling_vit"] = ["ViTModel"] if TYPE_CHECKING: - from .configuration_vit import VIT_PRETRAINED_CONFIG_ARCHIVE_MAP, ViTConfig + from .configuration_vit import ViTConfig try: if not is_torch_available():