Hacker News new | past | comments | ask | show | jobs | submit login

Though admittedly I haven't played with phi-2 much, smaller models are hurt much more by quantization. I'd try 8 bits or so, at least.



Consider applying for YC's W25 batch! Applications are open till Nov 12.

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

Search: