bert/configuration_bert.py

# 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 """


import logging

from .configuration_utils import PretrainedConfig


logger = logging.getLogger(__name__)

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",
    "bert-base-german-dbmdz-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-config.json",
    "bert-base-german-dbmdz-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-config.json",
    "cl-tohoku/bert-base-japanese": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese/config.json",
    "cl-tohoku/bert-base-japanese-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-whole-word-masking/config.json",
    "cl-tohoku/bert-base-japanese-char": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char/config.json",
    "cl-tohoku/bert-base-japanese-char-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking/config.json",
    "TurkuNLP/bert-base-finnish-cased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-cased-v1/config.json",
    "TurkuNLP/bert-base-finnish-uncased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-uncased-v1/config.json",
    "wietsedv/bert-base-dutch-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/wietsedv/bert-base-dutch-cased/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`.
        It is used to instantiate an 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 different tokens that
                can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.BertModel`.
            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" (i.e., feed-forward) layer in the Transformer encoder.
            hidden_act (:obj:`str` or :obj:`function`, optional, defaults to "gelu"):
                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 (:obj:`float`, optional, defaults to 0.1):
                The dropout probabilitiy 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 `token_type_ids` passed into :class:`~transformers.BertModel`.
            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 False):
                If True, use gradient checkpointing to save memory at the expense of slower backward pass.

        Example::

            >>> 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