Reorganize repo (#8580)
* Put models in subfolders * Styling * Fix imports in tests * More fixes in test imports * Sneaky hidden imports * Fix imports in doc files * More sneaky imports * Finish fixing tests * Fix examples * Fix path for copies * More fixes for examples * Fix dummy files * More fixes for example * More model import fixes * Is this why you're unhappy GitHub? * Fix imports in conver command
This commit is contained in:
Sylvain Gugger
142
src/transformers/models/bert/configuration_bert.py
Normal file
142
src/transformers/models/bert/configuration_bert.py
Normal file
@@ -0,0 +1,142 @@
|
||||
# coding=utf-8
|
||||
# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team.
|
||||
# Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved.
|
||||
#
|
||||
# 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.
|
||||
""" BERT model configuration """
|
||||
|
||||
from ...configuration_utils import PretrainedConfig
|
||||
from ...utils import logging
|
||||
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
||||
"bert-base-uncased": "https://huggingface.co/bert-base-uncased/resolve/main/config.json",
|
||||
"bert-large-uncased": "https://huggingface.co/bert-large-uncased/resolve/main/config.json",
|
||||
"bert-base-cased": "https://huggingface.co/bert-base-cased/resolve/main/config.json",
|
||||
"bert-large-cased": "https://huggingface.co/bert-large-cased/resolve/main/config.json",
|
||||
"bert-base-multilingual-uncased": "https://huggingface.co/bert-base-multilingual-uncased/resolve/main/config.json",
|
||||
"bert-base-multilingual-cased": "https://huggingface.co/bert-base-multilingual-cased/resolve/main/config.json",
|
||||
"bert-base-chinese": "https://huggingface.co/bert-base-chinese/resolve/main/config.json",
|
||||
"bert-base-german-cased": "https://huggingface.co/bert-base-german-cased/resolve/main/config.json",
|
||||
"bert-large-uncased-whole-word-masking": "https://huggingface.co/bert-large-uncased-whole-word-masking/resolve/main/config.json",
|
||||
"bert-large-cased-whole-word-masking": "https://huggingface.co/bert-large-cased-whole-word-masking/resolve/main/config.json",
|
||||
"bert-large-uncased-whole-word-masking-finetuned-squad": "https://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad/resolve/main/config.json",
|
||||
"bert-large-cased-whole-word-masking-finetuned-squad": "https://huggingface.co/bert-large-cased-whole-word-masking-finetuned-squad/resolve/main/config.json",
|
||||
"bert-base-cased-finetuned-mrpc": "https://huggingface.co/bert-base-cased-finetuned-mrpc/resolve/main/config.json",
|
||||
"bert-base-german-dbmdz-cased": "https://huggingface.co/bert-base-german-dbmdz-cased/resolve/main/config.json",
|
||||
"bert-base-german-dbmdz-uncased": "https://huggingface.co/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
|
||||
}
|
||||
|
||||
|
||||
class BertConfig(PretrainedConfig):
|
||||
r"""
|
||||
This is the configuration class to store the configuration of a :class:`~transformers.BertModel` or a
|
||||
:class:`~transformers.TFBertModel`. It is used to instantiate a BERT model according to the specified arguments,
|
||||
defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration
|
||||
to that of the BERT `bert-base-uncased <https://huggingface.co/bert-base-uncased>`__ architecture.
|
||||
|
||||
Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
|
||||
outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
|
||||
|
||||
|
||||
Args:
|
||||
vocab_size (:obj:`int`, `optional`, defaults to 30522):
|
||||
Vocabulary size of the BERT model. Defines the number of different tokens that can be represented by the
|
||||
:obj:`inputs_ids` passed when calling :class:`~transformers.BertModel` or
|
||||
:class:`~transformers.TFBertModel`.
|
||||
hidden_size (:obj:`int`, `optional`, defaults to 768):
|
||||
Dimensionality of the encoder layers and the pooler layer.
|
||||
num_hidden_layers (:obj:`int`, `optional`, defaults to 12):
|
||||
Number of hidden layers in the Transformer encoder.
|
||||
num_attention_heads (:obj:`int`, `optional`, defaults to 12):
|
||||
Number of attention heads for each attention layer in the Transformer encoder.
|
||||
intermediate_size (:obj:`int`, `optional`, defaults to 3072):
|
||||
Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
|
||||
hidden_act (:obj:`str` or :obj:`Callable`, `optional`, defaults to :obj:`"gelu"`):
|
||||
The non-linear activation function (function or string) in the encoder and pooler. If string,
|
||||
:obj:`"gelu"`, :obj:`"relu"`, :obj:`"silu"` and :obj:`"gelu_new"` are supported.
|
||||
hidden_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
|
||||
The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
|
||||
attention_probs_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
|
||||
The dropout ratio for the attention probabilities.
|
||||
max_position_embeddings (:obj:`int`, `optional`, defaults to 512):
|
||||
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 (:obj:`int`, `optional`, defaults to 2):
|
||||
The vocabulary size of the :obj:`token_type_ids` passed when calling :class:`~transformers.BertModel` or
|
||||
:class:`~transformers.TFBertModel`.
|
||||
initializer_range (:obj:`float`, `optional`, defaults to 0.02):
|
||||
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
||||
layer_norm_eps (:obj:`float`, `optional`, defaults to 1e-12):
|
||||
The epsilon used by the layer normalization layers.
|
||||
gradient_checkpointing (:obj:`bool`, `optional`, defaults to :obj:`False`):
|
||||
If True, use gradient checkpointing to save memory at the expense of slower backward pass.
|
||||
|
||||
Examples::
|
||||
|
||||
>>> from transformers import BertModel, BertConfig
|
||||
|
||||
>>> # Initializing a BERT bert-base-uncased style configuration
|
||||
>>> configuration = BertConfig()
|
||||
|
||||
>>> # Initializing a model from the bert-base-uncased style configuration
|
||||
>>> model = BertModel(configuration)
|
||||
|
||||
>>> # Accessing the model configuration
|
||||
>>> configuration = model.config
|
||||
"""
|
||||
model_type = "bert"
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
vocab_size=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,
|
||||
pad_token_id=0,
|
||||
gradient_checkpointing=False,
|
||||
**kwargs
|
||||
):
|
||||
super().__init__(pad_token_id=pad_token_id, **kwargs)
|
||||
|
||||
self.vocab_size = vocab_size
|
||||
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
|
||||
self.gradient_checkpointing = gradient_checkpointing
|
||||
Reference in New Issue
Block a user