Source code for transformers.configuration_openai

# coding=utf-8
# Copyright 2018 The OpenAI Team Authors and 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.
""" OpenAI GPT configuration """


import logging

from .configuration_utils import PretrainedConfig


logger = logging.getLogger(__name__)

OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "openai-gpt": "https://s3.amazonaws.com/models.huggingface.co/bert/openai-gpt-config.json"
}


[docs]class OpenAIGPTConfig(PretrainedConfig): """ This is the configuration class to store the configuration of a :class:`~transformers.OpenAIGPTModel`. It is used to instantiate an GPT 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 `GPT <https://huggingface.co/openai-gpt>`__ architecture from OpenAI. 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 40478): Vocabulary size of the GPT model. Defines the different tokens that can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.CTRLModel`. n_positions (: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). n_ctx (:obj:`int`, optional, defaults to 512): Dimensionality of the causal mask (usually same as n_positions). n_embd (:obj:`int`, optional, defaults to 768): Dimensionality of the embeddings and hidden states. n_layer (:obj:`int`, optional, defaults to 12): Number of hidden layers in the Transformer encoder. n_head (:obj:`int`, optional, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. afn (: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. resid_pdrop (:obj:`float`, optional, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. embd_pdrop (:obj:`int`, optional, defaults to 0.1): The dropout ratio for the embeddings. attn_pdrop (:obj:`float`, optional, defaults to 0.1): The dropout ratio for the attention. layer_norm_epsilon (:obj:`float`, optional, defaults to 1e-5): The epsilon to use in the layer normalization layers initializer_range (:obj:`float`, optional, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. predict_special_tokens (:obj:`boolean`, optional, defaults to :obj:`True`): Whether special tokens should be predicted when the model is has a language modeling head. summary_type (:obj:`string`, optional, defaults to "cls_index"): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.OpenAIGPTDoubleHeadsModel`. Is one of the following options: - 'last' => take the last token hidden state (like XLNet) - 'first' => take the first token hidden state (like Bert) - 'mean' => take the mean of all tokens hidden states - 'cls_index' => supply a Tensor of classification token position (GPT/GPT-2) - 'attn' => Not implemented now, use multi-head attention summary_use_proj (:obj:`boolean`, optional, defaults to :obj:`True`): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.OpenAIGPTDoubleHeadsModel`. Add a projection after the vector extraction summary_activation (:obj:`string` or :obj:`None`, optional, defaults to :obj:`None`): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.OpenAIGPTDoubleHeadsModel`. 'tanh' => add a tanh activation to the output, Other => no activation. summary_proj_to_labels (:obj:`boolean`, optional, defaults to :obj:`True`): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.OpenAIGPTDoubleHeadsModel`. If True, the projection outputs to config.num_labels classes (otherwise to hidden_size). Default: False. summary_first_dropout (:obj:`float`, optional, defaults to 0.1): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.OpenAIGPTDoubleHeadsModel`. Add a dropout before the projection and activation Example:: from transformers import OpenAIGPTConfig, OpenAIGPTModel # Initializing a GPT configuration configuration = OpenAIGPTConfig() # Initializing a model from the configuration model = OpenAIGPTModel(configuration) # Accessing the model configuration configuration = model.config """ model_type = "openai-gpt" def __init__( self, vocab_size=40478, n_positions=512, n_ctx=512, n_embd=768, n_layer=12, n_head=12, afn="gelu", resid_pdrop=0.1, embd_pdrop=0.1, attn_pdrop=0.1, layer_norm_epsilon=1e-5, initializer_range=0.02, predict_special_tokens=True, summary_type="cls_index", summary_use_proj=True, summary_activation=None, summary_proj_to_labels=True, summary_first_dropout=0.1, **kwargs ): super().__init__(**kwargs) self.vocab_size = vocab_size self.n_ctx = n_ctx self.n_positions = n_positions self.n_embd = n_embd self.n_layer = n_layer self.n_head = n_head self.afn = afn self.resid_pdrop = resid_pdrop self.embd_pdrop = embd_pdrop self.attn_pdrop = attn_pdrop self.layer_norm_epsilon = layer_norm_epsilon self.initializer_range = initializer_range self.predict_special_tokens = predict_special_tokens self.summary_type = summary_type self.summary_use_proj = summary_use_proj self.summary_activation = summary_activation self.summary_first_dropout = summary_first_dropout self.summary_proj_to_labels = summary_proj_to_labels @property def max_position_embeddings(self): return self.n_positions @property def hidden_size(self): return self.n_embd @property def num_attention_heads(self): return self.n_head @property def num_hidden_layers(self): return self.n_layer