How to use facebook/rag-sequence-nq with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, RagSequenceForGeneration tokenizer = AutoTokenizer.from_pretrained("facebook/rag-sequence-nq") model = RagSequenceForGeneration.from_pretrained("facebook/rag-sequence-nq", device_map="auto")
https://huggingface.co/facebook/rag-sequence-nq/resolve/main/question_encoder_tokenizer/special_tokens_map.json
hf download hf://facebook/rag-sequence-nq/question_encoder_tokenizer/special_tokens_map.json
curl -L -o special_tokens_map.json https://huggingface.co/facebook/rag-sequence-nq/resolve/main/question_encoder_tokenizer/special_tokens_map.json
