SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Refactoring checkpoint names for multiple models (#10527)

Browse Source 
* Refactor checkpoint name in ALBERT and ALBERT_tf

* Refactor checkpoint name in BART and BART_tf

* Refactor checkpoint name in BERT generation

* Refactor checkpoint name in Blenderbot_tf

* Refactor checkpoint name in Blenderbot_small_tf

* Refactor checkpoint name in ConvBERT AND CONVBERT_TF

* Refactor checkpoint name in CTRL AND CTRL_TF

* Refactor checkpoint name in DistilBERT AND DistilBERT_TF

* Refactor checkpoint name in DistilBERT redo

* Refactor checkpoint name in Electra and Electra_tf

* Refactor checkpoint name in FlauBERT and FlauBERT_tf

* Refactor checkpoint name in FSMT

* Refactor checkpoint name in GPT2 and GPT2_tf

* Refactor checkpoint name in IBERT

* Refactor checkpoint name in LED and LED_tf

* Refactor checkpoint name in Longformer and Longformer_tf

* Refactor checkpoint name in Lxmert and Lxmert_tf

* Refactor checkpoint name in Marian_tf

* Refactor checkpoint name in MBART and MBART_tf

* Refactor checkpoint name in MobileBERT and MobileBERT_tf

* Refactor checkpoint name in mpnet and mpnet_tf

* Refactor checkpoint name in openai and openai_tf

* Refactor checkpoint name in pegasus_tf

* Refactor checkpoint name in reformer

* Refactor checkpoint name in Roberta and Roberta_tf

* Refactor checkpoint name in SqueezeBert

* Refactor checkpoint name in Transformer_xl and Transformer_xl_tf

* Refactor checkpoint name in XLM and XLM_tf

* Refactor checkpoint name in XLNET and XLNET_tf

* Refactor checkpoint name in BERT_tf

* run make tests, style, quality, fixup
This commit is contained in:
Daniel Hug
2021-03-05 18:06:55 -05:00
committed by GitHub
parent defe9e20fe
commit 90ecc29656
47 changed files with 223 additions and 179 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/transformers/models/bert/modeling_tf_bert.py
View File

@@ -64,6 +64,7 @@ from .configuration_bert import BertConfig
logger = logging.get_logger(__name__)
_CHECKPOINT_FOR_DOC = "bert-base-cased"
_CONFIG_FOR_DOC = "BertConfig"
_TOKENIZER_FOR_DOC = "BertTokenizer"
@@ -850,7 +851,7 @@ class TFBertModel(TFBertPreTrainedModel):
@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint="bert-base-cased",
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=TFBaseModelOutputWithPooling,
config_class=_CONFIG_FOR_DOC,
)
@@ -1067,7 +1068,7 @@ class TFBertForMaskedLM(TFBertPreTrainedModel, TFMaskedLanguageModelingLoss):
@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint="bert-base-cased",
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=TFMaskedLMOutput,
config_class=_CONFIG_FOR_DOC,
)
@@ -1171,7 +1172,7 @@ class TFBertLMHeadModel(TFBertPreTrainedModel, TFCausalLanguageModelingLoss):
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint="bert-base-cased",
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=TFCausalLMOutput,
config_class=_CONFIG_FOR_DOC,
)
@@ -1382,7 +1383,7 @@ class TFBertForSequenceClassification(TFBertPreTrainedModel, TFSequenceClassific
@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint="bert-base-cased",
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=TFSequenceClassifierOutput,
config_class=_CONFIG_FOR_DOC,
)
@@ -1492,7 +1493,7 @@ class TFBertForMultipleChoice(TFBertPreTrainedModel, TFMultipleChoiceLoss):
@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, num_choices, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint="bert-base-cased",
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=TFMultipleChoiceModelOutput,
config_class=_CONFIG_FOR_DOC,
)
@@ -1648,7 +1649,7 @@ class TFBertForTokenClassification(TFBertPreTrainedModel, TFTokenClassificationL
@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint="bert-base-cased",
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=TFTokenClassifierOutput,
config_class=_CONFIG_FOR_DOC,
)
@@ -1755,7 +1756,7 @@ class TFBertForQuestionAnswering(TFBertPreTrainedModel, TFQuestionAnsweringLoss)
@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint="bert-base-cased",
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=TFQuestionAnsweringModelOutput,
config_class=_CONFIG_FOR_DOC,
)