Should we use the "instruct" or "chat" version of the models? #283
Unanswered
andypotato
asked this question in
Q&A
Replies: 1 comment
-
|
Both will work fine with LocalGPT. I would suggest not to use the "base" versions as they are not fine-tuned for question answer. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
See topic, for many models like Llama2 there are instruct and chat versions available. However it's not clear which version is preferred for use with LocalGPT. Could you please advise?
Beta Was this translation helpful? Give feedback.
All reactions