search

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
10.73k stars 696 forks source link

Add mechanism to detect incomplete model download #94

Open vilicvane opened 1 year ago

vilicvane commented 1 year ago

Something like downloading the model as xxx.tmp and then renaming to xxx.

As downloading the model takes some time, if terminated, it will skip downloading the next time and fail starting the server because of the corrupted model.