meta-llama
llama download obscure signed url requirement
I am trying to use llama-stack on a linux (on AWS x86_64). After installing anaconda & llama-stack llama-build was successful llama configure was successful.
I was told to "llama download --model-id Llama3.1-8B-Instruct"
I'm receiving the following request, not sure where to get this from, any ideas?
Please provide the signed URL you received via email (e.g., https://llama3-1.llamameta.net/ *?Policy...):
Thank you Itime-ren! Would be nice to have this instead of (e.g, https://....).
Also, curious why I didn't need to go through this process with ollama (download was much more streamlined and didn't require a stop at llama.com
ollama 提供的是 gguf模型 是在meta的模型上转换过的，提供下载的是ollama自己的网站，meta和huggingface的需要这个授权链接，你可能需要从https://hf-mirror.com/ 尝试下载，如果直接访问huggingface有障碍，但是同样需要授权
I posted a PR to improve the help text with the URL needed to request access -- #204
