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

by deleted - opened Apr 18

deleted

Apr 18

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).

mufeed

Apr 18

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

deleted

Apr 18

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

deleted changed discussion status to closed Apr 18

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment