Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Support for ggerganov/llama.cpp #17

Open
ricklamers opened this issue Mar 14, 2023 · 5 comments
Open

Support for ggerganov/llama.cpp #17

ricklamers opened this issue Mar 14, 2023 · 5 comments

Comments

@ricklamers
Copy link

Would be cool if it could support https://github.com/ggerganov/llama.cpp

Is it on your roadmap?

@ricklamers
Copy link
Author

Maybe using https://cocktailpeanut.github.io/dalai/#/

@cogentapps
Copy link
Owner

Integrating with the Dalai API should be doable.

How well does Llama perform in a chat style / conversational format?

@schmidp
Copy link
Contributor

schmidp commented Mar 15, 2023

with https://alpaca-ai-custom5.ngrok.io it seems to perform well

@rounakdatta
Copy link

Alpaca is explicitly trained for Instruct-style messages. LLAMA by default isn't ready for conversations (yet) without some clever prompt engineering.

@cogentapps
Copy link
Owner

I'd like to implement this via Dalai's API which now supports Alpaca, but this issue needs resolved first:

cocktailpeanut/dalai#51

It's also a bit slow for longer chats. Ideally it would use llama.cpp's interactive mode instead of resending the whole context with each message, but I don't think this is implemented yet?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants