Global
1 reply
⚙️
Login
blank's avatar
blank 2 years ago
Can it run any llama2 fine tuned model?
↑ Parent
Login to reply

Replies (1)

Mayank ☂️'s avatar
Mayank ☂️ mayank@umbrel.com 2 years ago
Currently it uses the Nous Hermes Llama 2 (7B). If you’re technical, you can customize the Dockerfile to run a different Llama model:
GitHub
llama-gpt/api/Dockerfile at c76225a6fc26a000fc07b074223a69b0d65b7bcf · 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! - getumb...
1 replies ↓

Generated: 23:15:38 · Zero-JS Hypermedia Browser

↑