Source code for transformers.configuration_bert

# 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
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# See the License for the specific language governing permissions and
# limitations under the License.
""" BERT model configuration """

from __future__ import absolute_import, division, print_function, unicode_literals

import json
import logging
import sys
from io import open

from .configuration_utils import PretrainedConfig

logger = logging.getLogger(__name__)

    'bert-base-uncased': "",
    'bert-large-uncased': "",
    'bert-base-cased': "",
    'bert-large-cased': "",
    'bert-base-multilingual-uncased': "",
    'bert-base-multilingual-cased': "",
    'bert-base-chinese': "",
    'bert-base-german-cased': "",
    'bert-large-uncased-whole-word-masking': "",
    'bert-large-cased-whole-word-masking': "",
    'bert-large-uncased-whole-word-masking-finetuned-squad': "",
    'bert-large-cased-whole-word-masking-finetuned-squad': "",
    'bert-base-cased-finetuned-mrpc': "",
    'bert-base-german-dbmdz-cased': "",
    'bert-base-german-dbmdz-uncased': "",

[docs]class BertConfig(PretrainedConfig): r""" :class:`~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", "swish" and "gelu_new" 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( 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)")