U &cf @s>dZddlZddlmZeeZddiZGdddeZdS) z OpenAI GPT configuration N)PretrainedConfig openai-gptzJhttps://s3.amazonaws.com/models.huggingface.co/bert/openai-gpt-config.jsoncsZeZdZdZeZdZdfdd ZeddZ eddZ eddZ eddZ Z S)OpenAIGPTConfiga This is the configuration class to store the configuration of an :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 `__ 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 Attributes: pretrained_config_archive_map (Dict[str, str]): A dictionary containing all the available pre-trained checkpoints. r gelu皙?h㈵>{Gz?T cls_indexNc s~tjf|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_||_dSN)super__init__ vocab_sizen_ctx n_positionsn_embdn_layern_headafn resid_pdrop embd_pdrop attn_pdroplayer_norm_epsiloninitializer_rangepredict_special_tokens summary_typesummary_use_projsummary_activationsummary_first_dropoutsummary_proj_to_labels)selfrrrrrrrrrrrrrrr r!r#r"kwargs __class__E/tmp/pip-unpacked-wheel-ymerj3tt/transformers/configuration_openai.pyrxs&zOpenAIGPTConfig.__init__cCs|jSr)rr$r(r(r)max_position_embeddingssz'OpenAIGPTConfig.max_position_embeddingscCs|jSr)rr*r(r(r) hidden_sizeszOpenAIGPTConfig.hidden_sizecCs|jSr)rr*r(r(r)num_attention_headssz#OpenAIGPTConfig.num_attention_headscCs|jSr)rr*r(r(r)num_hidden_layerssz!OpenAIGPTConfig.num_hidden_layers)rrrrr r r r r r r r TrTNTr )__name__ __module__ __qualname____doc__(OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAPZpretrained_config_archive_mapZ model_typerpropertyr+r,r-r. __classcell__r(r(r&r)rs<U+   r) r2loggingZconfiguration_utilsr getLoggerr/loggerr3rr(r(r(r)s