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

Excellent release by the Qwen team as always. Pretty much the best open-weights model line so far.

In my early tests however, several of the advertised languages are not really well supported and the model is outputting something that only barely resembles them.

Probably a dataset quality issue for low-resource languages that they cannot personally check for, despite the “119 languages and dialects” claim.



Indeed, I tried several low-resource Romance languages they claim to support and performance is abysmal.


What size/quantification level? IME, small language performance is one of the things that really suffers from the various tricks that are used to reduce size.


Which languages?




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

Search: