for --model_name_or_path <your_path_to_hf_converted_llama_ckpt_and_tokenizer>

[yixuan730]

Hello, if i want to follow your code to fine-tune based on llama, what file should i prepare for this --model_name_or_path <your_path_to_hf_converted_llama_ckpt_and_tokenizer>? Thank you very much.

[npvu1510]

I have the same question?
Please help me if you already have a solution

[xqymain]

Clearly, you should navigate to the llama's paths for 7B/13B/30B models and make sure that you have convert pth to hf format. This is a similar work for reference, and convert for reference