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

split configuration and modeling files

Browse Source
This commit is contained in:
thomwolf
2019-09-05 00:26:57 +02:00
parent 0be6a2a624
commit 2a667b1eb9
33 changed files with 1571 additions and 1223 deletions
Download Patch File Download Diff File Expand all files Collapse all files

93
pytorch_transformers/modeling_bert.py
View File

@@ -28,8 +28,9 @@ import torch
from torch import nn
from torch.nn import CrossEntropyLoss, MSELoss
from .modeling_utils import (WEIGHTS_NAME, CONFIG_NAME, PretrainedConfig, PreTrainedModel,
prune_linear_layer, add_start_docstrings)
from .modeling_utils import PreTrainedModel, prune_linear_layer
from .configuration_bert import BertConfig
from .file_utils import add_start_docstrings
logger = logging.getLogger(__name__)
@@ -49,23 +50,6 @@ BERT_PRETRAINED_MODEL_ARCHIVE_MAP = {
'bert-base-cased-finetuned-mrpc': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-pytorch_model.bin",
}
BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
'bert-base-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-config.json",
'bert-large-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-config.json",
'bert-base-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-config.json",
'bert-large-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-config.json",
'bert-base-multilingual-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-config.json",
'bert-base-multilingual-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-config.json",
'bert-base-chinese': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese-config.json",
'bert-base-german-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-cased-config.json",
'bert-large-uncased-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-config.json",
'bert-large-cased-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-config.json",
'bert-large-uncased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-finetuned-squad-config.json",
'bert-large-cased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-finetuned-squad-config.json",
'bert-base-cased-finetuned-mrpc': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-config.json",
}
def load_tf_weights_in_bert(model, config, tf_checkpoint_path):
""" Load tf checkpoints in a pytorch model.
"""
@@ -149,77 +133,6 @@ def swish(x):
ACT2FN = {"gelu": gelu, "relu": torch.nn.functional.relu, "swish": swish}
class BertConfig(PretrainedConfig):
r"""
:class:`~pytorch_transformers.BertConfig` is the configuration class to store the configuration of a
`BertModel`.
Arguments:
vocab_size_or_config_json_file: Vocabulary size of `inputs_ids` in `BertModel`.
hidden_size: Size of the encoder layers and the pooler layer.
num_hidden_layers: Number of hidden layers in the Transformer encoder.
num_attention_heads: Number of attention heads for each attention layer in
the Transformer encoder.
intermediate_size: The size of the "intermediate" (i.e., feed-forward)
layer in the Transformer encoder.
hidden_act: The non-linear activation function (function or string) in the
encoder and pooler. If string, "gelu", "relu" and "swish" are supported.
hidden_dropout_prob: The dropout probabilitiy for all fully connected
layers in the embeddings, encoder, and pooler.
attention_probs_dropout_prob: The dropout ratio for the attention
probabilities.
max_position_embeddings: The maximum sequence length that this model might
ever be used with. Typically set this to something large just in case
(e.g., 512 or 1024 or 2048).
type_vocab_size: The vocabulary size of the `token_type_ids` passed into
`BertModel`.
initializer_range: The sttdev of the truncated_normal_initializer for
initializing all weight matrices.
layer_norm_eps: The epsilon used by LayerNorm.
"""
pretrained_config_archive_map = BERT_PRETRAINED_CONFIG_ARCHIVE_MAP
def __init__(self,
vocab_size_or_config_json_file=30522,
hidden_size=768,
num_hidden_layers=12,
num_attention_heads=12,
intermediate_size=3072,
hidden_act="gelu",
hidden_dropout_prob=0.1,
attention_probs_dropout_prob=0.1,
max_position_embeddings=512,
type_vocab_size=2,
initializer_range=0.02,
layer_norm_eps=1e-12,
**kwargs):
super(BertConfig, self).__init__(**kwargs)
if isinstance(vocab_size_or_config_json_file, str) or (sys.version_info[0] == 2
and isinstance(vocab_size_or_config_json_file, unicode)):
with open(vocab_size_or_config_json_file, "r", encoding='utf-8') as reader:
json_config = json.loads(reader.read())
for key, value in json_config.items():
self.__dict__[key] = value
elif isinstance(vocab_size_or_config_json_file, int):
self.vocab_size = vocab_size_or_config_json_file
self.hidden_size = hidden_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.hidden_act = hidden_act
self.intermediate_size = intermediate_size
self.hidden_dropout_prob = hidden_dropout_prob
self.attention_probs_dropout_prob = attention_probs_dropout_prob
self.max_position_embeddings = max_position_embeddings
self.type_vocab_size = type_vocab_size
self.initializer_range = initializer_range
self.layer_norm_eps = layer_norm_eps
else:
raise ValueError("First argument must be either a vocabulary size (int)"
" or the path to a pretrained model config file (str)")
try:
from apex.normalization.fused_layer_norm import FusedLayerNorm as BertLayerNorm
except (ImportError, AttributeError) as e: