How to use this model directly from the
from transformers import AutoTokenizer, RagTokenForGeneration tokenizer = AutoTokenizer.from_pretrained("facebook/rag-token-nq") model = RagTokenForGeneration.from_pretrained("facebook/rag-token-nq")
This is the RAG-Token Model of the the paper Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks by Patrick Lewis, Ethan Perez, Aleksandara Piktus et al.
The model is a uncased model, which means that capital letters are simply converted to lower-case letters.
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.
The question_encoder and retriever are based on
facebook/bart-large, which were jointly finetuned on
on the wiki_dpr QA dataset in an end-to-end fashion.
Note: In the usage example below only the dummy retriever of wiki_dpr is used because the complete lecagy index requires over 75 GB of RAM. The model can generate answers to any factoid question as follows:
from transformers import RagTokenizer, RagRetriever, RagTokenForGeneration tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-nq") retriever = RagRetriever.from_pretrained("facebook/rag-token-nq", index_name="exact", use_dummy_dataset=True) model = RagTokenForGeneration.from_pretrained("facebook/rag-token-nq", retriever=retriever) input_dict = tokenizer.prepare_seq2seq_batch("who holds the record in 100m freestyle", return_tensors="pt") generated = model.generate(input_ids=input_dict["input_ids"]) print(tokenizer.batch_decode(generated, skip_special_tokens=True)) # should give michael phelps => sounds reasonable