sg'!PdZddlmZddlmZdZeeGddeZy)zRAG model configuration)PretrainedConfig)add_start_docstringsa) [`RagConfig`] stores the configuration of a *RagModel*. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: title_sep (`str`, *optional*, defaults to `" / "`): Separator inserted between the title and the text of the retrieved document when calling [`RagRetriever`]. doc_sep (`str`, *optional*, defaults to `" // "`): Separator inserted between the text of the retrieved document and the original input when calling [`RagRetriever`]. n_docs (`int`, *optional*, defaults to 5): Number of documents to retrieve. max_combined_length (`int`, *optional*, defaults to 300): Max length of contextualized input returned by [`~RagRetriever.__call__`]. retrieval_vector_size (`int`, *optional*, defaults to 768): Dimensionality of the document embeddings indexed by [`RagRetriever`]. retrieval_batch_size (`int`, *optional*, defaults to 8): Retrieval batch size, defined as the number of queries issues concurrently to the faiss index encapsulated [`RagRetriever`]. dataset (`str`, *optional*, defaults to `"wiki_dpr"`): A dataset identifier of the indexed dataset in HuggingFace Datasets (list all available datasets and ids using `datasets.list_datasets()`). dataset_split (`str`, *optional*, defaults to `"train"`) Which split of the `dataset` to load. index_name (`str`, *optional*, defaults to `"compressed"`) The index name of the index associated with the `dataset`. One can choose between `"legacy"`, `"exact"` and `"compressed"`. index_path (`str`, *optional*) The path to the serialized faiss index on disk. passages_path (`str`, *optional*): A path to text passages compatible with the faiss index. Required if using [`~models.rag.retrieval_rag.LegacyIndex`] use_dummy_dataset (`bool`, *optional*, defaults to `False`) Whether to load a "dummy" variant of the dataset specified by `dataset`. label_smoothing (`float`, *optional*, defaults to 0.0): Only relevant if `return_loss` is set to `True`. Controls the `epsilon` parameter value for label smoothing in the loss calculation. If set to 0, no label smoothing is performed. do_marginalize (`bool`, *optional*, defaults to `False`): If `True`, the logits are marginalized over all documents by making use of `torch.nn.functional.log_softmax`. reduce_loss (`bool`, *optional*, defaults to `False`): Whether or not to reduce the NLL loss using the `torch.Tensor.sum` operation. do_deduplication (`bool`, *optional*, defaults to `True`): Whether or not to deduplicate the generations from different context documents for a given input. Has to be set to `False` if used while training with distributed backend. exclude_bos_score (`bool`, *optional*, defaults to `False`): Whether or not to disregard the BOS token when computing the loss. output_retrieved(`bool`, *optional*, defaults to `False`): If set to `True`, `retrieved_doc_embeds`, `retrieved_doc_ids`, `context_input_ids` and `context_attention_mask` are returned. See returned tensors for more detail. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). forced_eos_token_id (`int`, *optional*): The id of the token to force as the last generated token when `max_length` is reached. Usually set to `eos_token_id`. c~eZdZdZdZ dfd ZedededefdZxZ S) RagConfigragTc t#|d ||||||||d|d|vsd|vrtd|jd||j d}|j d}|j d} | j d}!ddlm}"|"j|fi||_|"j|!fi| |_ ||_ ||_ ||_ ||_ ||_| |_| |_| |_||_||_||_| |_| |_||_||_||_||_||_||_||_|j<t?|jd d|_yy) N) bos_token_id pad_token_id eos_token_iddecoder_start_token_idforced_eos_token_idis_encoder_decoderprefix vocab_sizequestion_encoder generatorzA configuraton of type zq cannot be instantiated because both `question_encoder` and `generator` sub-configurations were not passed, only model_type) AutoConfigr ) super__init__ ValueErrorrpopauto.configuration_autor for_modelrr reduce_losslabel_smoothingexclude_bos_scoredo_marginalize title_sepdoc_sepn_docsmax_combined_lengthdataset dataset_split index_nameretrieval_vector_sizeretrieval_batch_size passages_path index_pathuse_dummy_datasetdataset_revisionoutput_retrieveddo_deduplication use_cacher getattr)$selfrrrr r r r r!r"r#r$r(r)r%r&r'r+r*r,rrr/rr r.r0r r-kwargsquestion_encoder_configquestion_encoder_model_typedecoder_configdecoder_model_typer __class__s$ \/var/www/html/venv/lib/python3.12/site-packages/transformers/models/rag/configuration_rag.pyrzRagConfig.__init__Ts@  %%%#9 31!   V +{&/H)$//):;ddjckm #)**-?"@&=&A&A,&O#K0+// =8 4 4 45P lTk l---.@SNS&.!2,"  #6  *$%:"$8!*$!2 0 0 0"  # # +'.t~~?TVZ'[D $ ,r4generator_configreturnc P|d|j|jd|S)a Instantiate a [`EncoderDecoderConfig`] (or a derived class) from a pre-trained encoder model configuration and decoder model configuration. Returns: [`EncoderDecoderConfig`]: An instance of a configuration object )rrr)to_dict)clsr4r;r3s r9'from_question_encoder_generator_configsz1RagConfig.from_question_encoder_generator_configss.v$;$C$C$EQaQiQiQkvouvvr:)NTNNNNNz / z // i,iwiki_dprtrain compressedNNFFgTFFFTNN) __name__ __module__ __qualname__ris_compositionr classmethodrr@ __classcell__)r8s@r9rrOsJN#! ;V\p w&6 wJZ w  w wr:rN)__doc__configuration_utilsrutilsrRAG_CONFIG_DOCrrr:r9rPs?3)7tn%gw gw&gwr: