T^(h`dZddlmZddlmZej eZGddeZdgZ y)zSplinter model configuration)PretrainedConfig)loggingcFeZdZdZdZ dfd ZxZS)SplinterConfigah This is the configuration class to store the configuration of a [`SplinterModel`]. It is used to instantiate an Splinter 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 Splinter [tau/splinter-base](https://huggingface.co/tau/splinter-base) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 30522): Vocabulary size of the Splinter model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`SplinterModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimension of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. max_position_embeddings (`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). type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids` passed when calling [`SplinterModel`]. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. question_token_id (`int`, *optional*, defaults to 104): The id of the `[QUESTION]` token. Example: ```python >>> from transformers import SplinterModel, SplinterConfig >>> # Initializing a Splinter tau/splinter-base style configuration >>> configuration = SplinterConfig() >>> # Initializing a model from the tau/splinter-base style configuration >>> model = SplinterModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```splinterc t|dd|i|||_| |_||_||_||_||_||_||_ ||_ | |_ | |_ | |_ | |_||_y)N pad_token_id)super__init__ vocab_sizemax_position_embeddings hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangetype_vocab_sizelayer_norm_eps use_cachequestion_token_id)selfr rrrrrrrrrrrrr rkwargs __class__s q/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/splinter/configuration_splinter.pyr zSplinterConfig.__init__Vs& =l=f=$'>$&!2#6 !2$#6 ,H)!2.,"!2)i:wi r i gelu皙?r"ig{Gz?g-q=Th)__name__ __module__ __qualname____doc__ model_typer __classcell__)rs@rrrsI9 vJ%( #!"3"3rrN) r)configuration_utilsrutilsr get_loggerr&loggerr__all__r rrr1s>#3   H %`3%`3F  r