84 lines
3.9 KiB
Python
84 lines
3.9 KiB
Python
# These codes are copied from modelscope revision c58451baead80d83281f063d12fb377fad415257
|
|
# 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 __future__ import (absolute_import, division, print_function,
|
|
unicode_literals)
|
|
import logging
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class BertConfig(object):
|
|
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.
|
|
"""
|
|
|
|
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,
|
|
output_attentions=False,
|
|
output_hidden_states=False):
|
|
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
|
|
self.output_attentions = output_attentions
|
|
self.output_hidden_states = output_hidden_states
|