# coding=utf-8
# Copyright 2020 The Google AI Language Team Authors and The HuggingFace Inc. team.
#
# 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.
""" BertGeneration model configuration """
from .configuration_utils import PretrainedConfig
[docs]class BertGenerationConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a :class:`~transformers.BertGenerationPreTrainedModel`.
It is used to instantiate a BertGenerationConfig model according to the specified arguments, defining the model 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 50358):
Vocabulary size of the BertGeneration model. Defines the different tokens that
can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.BertGeneration`.
hidden_size (:obj:`int`, `optional`, defaults to 1024):
Dimensionality of the encoder layers and the pooler layer.
num_hidden_layers (:obj:`int`, `optional`, defaults to 24):
Number of hidden layers in the Transformer encoder.
num_attention_heads (:obj:`int`, `optional`, defaults to 16):
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 :obj:`"gelu"`):
The non-linear activation function (function or string) in the encoder and pooler.
If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"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).
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 :obj:`True`, use gradient checkpointing to save memory at the expense of slower backward pass.
Example::
>>> from transformers import BertGenerationConfig, BertGenerationEncoder
>>> # Initializing a BertGeneration config
>>> configuration = BertGenerationConfig()
>>> # Initializing a modelfrom the config
>>> model = BertGenerationEncoder(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
"""
model_type = "bert-generation"
def __init__(
self,
vocab_size=50358,
hidden_size=1024,
num_hidden_layers=24,
num_attention_heads=16,
intermediate_size=4096,
hidden_act="gelu",
hidden_dropout_prob=0.1,
attention_probs_dropout_prob=0.1,
max_position_embeddings=512,
initializer_range=0.02,
layer_norm_eps=1e-12,
pad_token_id=0,
bos_token_id=2,
eos_token_id=1,
gradient_checkpointing=False,
**kwargs
):
super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_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.initializer_range = initializer_range
self.layer_norm_eps = layer_norm_eps
self.gradient_checkpointing = gradient_checkpointing