g^dZddlmZddlmZejeZGddeZdS)zDPR model configuration)PretrainedConfig)loggingcLeZdZdZdZ ddeffd ZxZS) DPRConfiga [`DPRConfig`] is the configuration class to store the configuration of a *DPRModel*. This is the configuration class to store the configuration of a [`DPRContextEncoder`], [`DPRQuestionEncoder`], or a [`DPRReader`]. It is used to instantiate the components of the DPR model according to the specified arguments, defining the model component architectures. Instantiating a configuration with the defaults will yield a similar configuration to that of the DPRContextEncoder [facebook/dpr-ctx_encoder-single-nq-base](https://huggingface.co/facebook/dpr-ctx_encoder-single-nq-base) architecture. This class is a subclass of [`BertConfig`]. Please check the superclass for the documentation of all kwargs. Args: vocab_size (`int`, *optional*, defaults to 30522): Vocabulary size of the DPR model. Defines the different tokens that can be represented by the *inputs_ids* passed to the forward method of [`BertModel`]. 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" (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"`, `"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. pad_token_id (`int`, *optional*, defaults to 0): Padding token id. position_embedding_type (`str`, *optional*, defaults to `"absolute"`): Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155). For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658). projection_dim (`int`, *optional*, defaults to 0): Dimension of the projection for the context and question encoders. If it is set to zero (default), then no projection is done. Example: ```python >>> from transformers import DPRConfig, DPRContextEncoder >>> # Initializing a DPR facebook/dpr-ctx_encoder-single-nq-base style configuration >>> configuration = DPRConfig() >>> # Initializing a model (with random weights) from the facebook/dpr-ctx_encoder-single-nq-base style configuration >>> model = DPRContextEncoder(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```dpr:w gelu皙?{Gz?-q=absoluteprojection_dimc tjdd| i|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_dS)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_epsrposition_embedding_type)selfrrrrrrr r!r"r#r$r%rr&rkwargs __class__s e/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/dpr/configuration_dpr.pyrzDPRConfig.__init__^s& ==l=f===$&!2#6 $!2#6 ,H)'>$.!2,,'>$$$)rr r r r r r r rrrrrrr)__name__ __module__ __qualname____doc__ model_typeintr __classcell__)r)s@r*rrsA A FJ%( # *!"?"? !"?"?"?"?"?"?"?"?"?"?r+rN) r/configuration_utilsrutilsr get_loggerr,loggerrrr+r*r7s333333  H % %h?h?h?h?h? h?h?h?h?h?r+