Thanks for the quick upload. Is it missing the end token?

#1
by deleted - opened
deleted

It might just be GPT4All v2.7.3, but after it finishes a prompt the CPU continues at 100% and it never stops (using Q5_K_M).

This is a base model of Meta-Llama-3-8B, use Meta-Llama-3-8B-Instruct.

deleted

@mufeed Thanks. I was using the Instruct, but returned to the wrong place. Well leave the comment there.

deleted changed discussion status to closed
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment