facebook/rag-token-nq

This is the RAG-Token Model of the paper Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks . The model consits of a question_encoder, retriever and a generator . The retriever extracts relevant passages from the wiki_dpr train datasets, which is linked above . In the usage example below only the dummy retriever is used because the complete lecagy index requires over 75 GB of RAM. The model can generate answers to any factoid question as follows: "Who holds the record in 100m freestyle" The model is a uncased model, which means capital letters are simply converted to lower-case letters. The question_,