Based on qwen2.5-coder? seems like a "why not/resume embellish/show VC" type rel... | Hacker News

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

		dcreater 18 days ago \| parent \| context \| favorite \| on: Show HN: Sweep, Open-weights 1.5B model for next-e... Based on qwen2.5-coder? seems like a "why not/resume embellish/show VC" type release I guess

dang 18 days ago | [–]

"Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something."

https://news.ycombinator.com/newsguidelines.html

kevinlu1248 17 days ago | [–]

You can see that Qwen3 does worse than Qwen2.5 on our benchmark. Reason is it's never been pretrained for FIM / autocomplete.

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