I am trying to run the code and model from this site which uses hugging face using the code to test how IG and different LLM attribution method works. It makes use of model_name = "meta-llama/Llama-2-13b-chat-hf that I guess is a huge model (around 23GB). The code is the following: model_name = "meta-llama/Llama-2-13b-chat-hf" bnb_config = create_bnb_config() model, tokenizer = load_model(model_name, bnb_config) When I run this code I get the following error: OSError: You are trying to access a gated repo. Make sure to have access to it at https://huggingface.co/meta-llama/Llama-2-13b-chat-hf. 403 Client Error. (Request ID: Root=1-67cf1e66-6ad42848104ba9926befc1c2;075ccb34-0b83-41c5-b4b0-0d5186c69b16) Cannot access gated repo for url https://huggingface.co/meta-llama/Llama-2-13b-chat-hf/resolve/main/config.json. Access to model meta-llama/Llama-2-13b-chat-hf is restricted and you are not in the authorized list. Visit https://huggingface.co/meta-llama/Llama-2-13b-chat-hf to ask for access. How can I feel with issue? Do I need to create a token for accessing this model? Continue reading...
