Q3_K_XL outputs EOS token immediately, all messages result in 1 token immediate end of response

by Goldkoron - opened Mar 13

Mar 13

Any fix for this, is the quant broken or something?

Mar 13

Nevermind, it was an issue with the llama-server build I was using.

Goldkoron changed discussion status to closed Mar 13

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