Support Multi-part .bin files?

getumbrel / llama-gpt

A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!

https://apps.umbrel.com/app/llama-gpt

MIT License

10.83k stars 700 forks source link

Open AI-Zebra opened 9 months ago

AI-Zebra commented 9 months ago

Hi Team,

I am trying to run https://huggingface.co/NousResearch/Yarn-Llama-2-13b-128k/tree/main with llama-gpt. However unable to specify multiple .bin files (this model has 3 files) in dockerfile.

Please can you suggest how we can run multi-part bin files?

Thanks!