weizhepei
A question about cache_dir
Dear author, would you please tell me what is this cache? thx a lot.
~/workspace/InstructRAG-main$ sh generate_rationale.sh usage: inference.py [-h] [--dataset_name DATASET_NAME] [--rag_model {InstructRAG-FT,InstructRAG-ICL}] [--model_name_or_path MODEL_NAME_OR_PATH] [--load_local_model] [--do_rationale_generation] [--n_docs N_DOCS] [--output_dir OUTPUT_DIR] [--cache_dir CACHE_DIR] [--prompt_dict_path PROMPT_DICT_PATH] [--temperature TEMPERATURE] [--max_tokens MAX_TOKENS] [--seed SEED] [--max_instances MAX_INSTANCES] inference.py: error: argument --cache_dir: expected one argument
I think I have fixed this problem. So vllm needs to download the models manually instead of automatically?
Hi @NoW0NDER, many thanks for bringing this up! The argument --cache_dir is actually optional, and I've updated the script accordingly. Let me know if you have any further questions.
