bug ? repeated text output after 2-3 questions. #573
Unanswered
colindaven
asked this question in
Q&A
Replies: 0 comments
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.
Uh oh!
There was an error while loading. Please reload this page.
-
Hi,
I've used llamafiles including llava, wizardcoder and llama3/3.1. Generally I use an 8B model or similar.
After two or three normal questions, llamafile answers with repetitive rubbish. See below.
This is running on a 768GB RAM CPU only linux x86-64 bit server and appears to be using less than 1-2 % of RAM. Has anyone got any idea what I can set to avoid this problem ?
Thanks.
Beta Was this translation helpful? Give feedback.
All reactions