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

In my case I would say they are comparable but moe models are looping and getting lost a lot more than dense models.

On the other hand having 90t/s with any local model is nice and Pi with loop police extension can prevent looping a lot.



Looping seems related to quantization and not the model itself. If youre digging deep into quants to get working context then yeah.




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

Search: