sgPZdZddlmZddlmZej eZGddeZy)zRetriBERT model configuration)PretrainedConfig)loggingcFeZdZdZdZ dfd ZxZS)RetriBertConfiga This is the configuration class to store the configuration of a [`RetriBertModel`]. It is used to instantiate a RetriBertModel 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 RetriBERT [yjernite/retribert-base-uncased](https://huggingface.co/yjernite/retribert-base-uncased) 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 RetriBERT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`RetriBertModel`] hidden_size (`int`, *optional*, defaults to 768): Dimensionality 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): Dimensionality of the "intermediate" (often named 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"`, `"silu"` 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 into [`BertModel`]. 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. share_encoders (`bool`, *optional*, defaults to `True`): Whether or not to use the same Bert-type encoder for the queries and document projection_dim (`int`, *optional*, defaults to 128): Final dimension of the query and document representation after projection retribertc t|dd|i|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_y)N pad_token_id)super__init__ vocab_size hidden_sizenum_hidden_layersnum_attention_heads hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_epsshare_encodersprojection_dim)selfr rrrrrrrrrrrrrr kwargs __class__s s/var/www/html/venv/lib/python3.12/site-packages/transformers/models/deprecated/retribert/configuration_retribert.pyr zRetriBertConfig.__init__Gs& =l=f=$&!2#6 $!2#6 ,H)'>$.!2,,,)i:wi i gelu皙?r#ig{Gz?g-q=T)__name__ __module__ __qualname____doc__ model_typer __classcell__)rs@rrrsI*XJ%( #!"-"-rrN) r*configuration_utilsrutilsr get_loggerr'loggerrr rrr1s3$4   H %Q-&Q-r