Hacker News new | ask | show | jobs
by Iolaum 40 days ago
Why unquantized instead of Q8 ?
1 comments

Noticed few cliffs. Sometimes it was a spurious stop (had to write "go on" or "continue" to restart), othertimes it was randomly saying: "Oh the user wants [the thing we already resolved]" and goes back in history. Cleared all out on fp16