Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Why unquantized instead of Q8 ?
 help



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



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: