U ,-e^@sLdZddlmZddlmZeeZdddddd d ZGd d d eZ d S)z DPR model configuration)PretrainedConfig)loggingzWhttps://huggingface.co/facebook/dpr-ctx_encoder-single-nq-base/resolve/main/config.jsonz\https://huggingface.co/facebook/dpr-question_encoder-single-nq-base/resolve/main/config.jsonzRhttps://huggingface.co/facebook/dpr-reader-single-nq-base/resolve/main/config.jsonzVhttps://huggingface.co/facebook/dpr-ctx_encoder-multiset-base/resolve/main/config.jsonz[https://huggingface.co/facebook/dpr-question_encoder-multiset-base/resolve/main/config.jsonzQhttps://huggingface.co/facebook/dpr-reader-multiset-base/resolve/main/config.json)z'facebook/dpr-ctx_encoder-single-nq-basez,facebook/dpr-question_encoder-single-nq-basez"facebook/dpr-reader-single-nq-basez&facebook/dpr-ctx_encoder-multiset-basez+facebook/dpr-question_encoder-multiset-basez!facebook/dpr-reader-multiset-basecs,eZdZdZdZdedfdd ZZS) 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. 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 ```Zdpr:w gelu皙?{Gz?-q=absolute)projection_dimc sntjfd| 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)selfrrrrrrrrrrrr rr!rkwargs __class__j/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/dpr/configuration_dpr.pyrpszDPRConfig.__init__)rrrrrr r r r r r rrrr)__name__ __module__ __qualname____doc__Z model_typeintr __classcell__r&r&r$r'r-s(@rN) r+Zconfiguration_utilsrutilsrZ get_loggerr(loggerZ!DPR_PRETRAINED_CONFIG_ARCHIVE_MAPrr&r&r&r's