^jejdZddlmZddlmZddlmZedeGdd eZd gZy ) zOpenAI GPT configuration)strict)PreTrainedConfig)auto_docstringzopenai-community/openai-gpt) checkpointcxeZdZUdZdZdddddZdZeed <d Z eed<d Z eed<d Z eed<d Z eed<d Z eed<dZeezed<dZeezed<dZeezed<dZeed<dZeed<dZeed<dZeed<dZedzed<dZeed<dZeezed<dZedzed<dZedzed <dZeeezdzed!<dZeed"<y)#OpenAIGPTConfiga afn (`str` or `Callable`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. layer_norm_epsilon (`float`, *optional*, defaults to 1e-05): The epsilon to use in the layer normalization layers summary_type (`str`, *optional*, defaults to `"cls_index"`): Argument used when doing sequence summary, used in the models [`OpenAIGPTDoubleHeadsModel`] and [`OpenAIGPTDoubleHeadsModel`]. Has to be 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 (like GPT/GPT-2). - `"attn"`: Not implemented now, use multi-head attention. summary_use_proj (`bool`, *optional*, defaults to `True`): Argument used when doing sequence summary, used in the models [`OpenAIGPTDoubleHeadsModel`] and [`OpenAIGPTDoubleHeadsModel`]. Whether or not to add a projection after the vector extraction. summary_activation (`str`, *optional*): Argument used when doing sequence summary, used in the models [`OpenAIGPTDoubleHeadsModel`] and [`OpenAIGPTDoubleHeadsModel`]. Pass `"tanh"` for a tanh activation to the output, any other value will result in no activation. summary_proj_to_labels (`bool`, *optional*, defaults to `True`): Argument used when doing sequence summary, used in the models [`OpenAIGPTDoubleHeadsModel`] and [`OpenAIGPTDoubleHeadsModel`]. Whether the projection outputs should have `config.num_labels` or `config.hidden_size` classes. summary_first_dropout (`float`, *optional*, defaults to 0.1): Argument used when doing sequence summary, used in the models [`OpenAIGPTDoubleHeadsModel`] and [`OpenAIGPTDoubleHeadsModel`]. The dropout ratio to be used after the projection and activation. Examples: ```python >>> from transformers import OpenAIGPTConfig, OpenAIGPTModel >>> # Initializing a GPT configuration >>> configuration = OpenAIGPTConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = OpenAIGPTModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```z openai-gpt n_positionsn_embdn_headn_layer)max_position_embeddings hidden_sizenum_attention_headsnum_hidden_layersi vocab_sizeii geluafng? resid_pdrop embd_pdrop attn_pdropgh㈵>layer_norm_epsilong{Gz?initializer_range cls_index summary_typeTsummary_use_projNsummary_activationsummary_proj_to_labelssummary_first_dropout pad_token_id bos_token_id eos_token_idtie_word_embeddings) __name__ __module__ __qualname____doc__ model_type attribute_maprint__annotations__r r r r rstrrfloatrrrrrrboolrrr r!r"r#listr$z/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/openai/configuration_openai.pyr r s- ^J#0'& MJKFCGSFCC"K"!J !!J ! $$#u##L##!d!%)d )#'D'),53;,#L#*##L#*#+/L#S /D(/ $$r2r N) r(huggingface_hub.dataclassesrconfiguration_utilsrutilsrr __all__r1r2r3r8sK.3#89K%&K%:K%\  r2