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

If I understand it correctly, this seems to be more than just quantizing, the models are apparently trained in this format as well. So it's possible that the many layers adjust themselves in a way that "cancels out" the inaccuracies of the lower bit count


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

Search: