^jHvdZddlmZddlmZddlmZddlmZed eGd d eZ d gZ y ) zRAG model configuration)strict)PreTrainedConfig)auto_docstring) AutoConfig) checkpointceZdZUdZdZdZdZedzed<dZ e ed<dZ e dzed<dZ edzed<dZedzed <dZeeezdzed <dZedzed <d Ze ed <dZe ed<dZeed<dZeed<dZeed<dZeed<dZe ed<dZe ed<dZe ed<dZe dzed<dZe dzed<d Ze ed!<d Ze ed"<d#Ze ed$<dZ!e ed%<d Z"e ed&<d Z#e ed'<d Z$e ed(<dZ%e ed)<dZ&e dzed*<fd+Z'e(d,e)d-e)d.e)fd/Z*xZ+S)0 RagConfiga% prefix (`str`, *optional*): A string prefix prepended to every input before passing to the generator model. 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`. reduce_loss (`bool`, *optional*, defaults to `False`): Whether or not to reduce the NLL loss using the `torch.Tensor.sum` operation. 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_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. 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`. 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. dataset_revision (`str`, *optional*,): The revision (commit hash, tag, or branch) of the Hugging Face dataset used for retrieval. ragTN vocab_sizeis_encoder_decoderprefix bos_token_id pad_token_id eos_token_iddecoder_start_token_idz / title_sepz // doc_sepn_docsi,max_combined_lengthiretrieval_vector_sizeretrieval_batch_sizewiki_dprdatasettrain dataset_split compressed index_name index_path passages_pathFuse_dummy_dataset reduce_lossglabel_smoothingdo_deduplicationexclude_bos_scoredo_marginalizeoutput_retrieved use_cachedataset_revisionc ^d|vsd|vrtd|jd||jd}|jd}|jd}|jd}tj|fi||_tj|fi||_t| di|y)Nquestion_encoder generatorzA configuration of type zt cannot be instantiated because not both `question_encoder` and `generator` sub-configurations are passed, but only model_type) ValueErrorr1popr for_modelr/r0super __post_init__)selfkwargsquestion_encoder_configquestion_encoder_model_typedecoder_configdecoder_model_type __class__s t/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/rag/configuration_rag.pyr7zRagConfig.__post_init__ms V +{&/H*4??*;s@r?r r s2hJ"!Jd !##FC$J#L#*##L#*#+/L#S /D(/)-C$J-IsGSFCO""!$3$ !#!GS M3 "J"!Jd ! $M3:$#t#K OU !d!#t# ND "d"It#'cDj'(" w&6 wJZ w  w wr@r N) rJhuggingface_hub.dataclassesrconfiguration_utilsrutilsrauto.configuration_autorr __all__r2r@r?rYsO.3#02pw pwpwf -r@