When I was in University this was called overfitting to be honest. This doesn't ... | Hacker News

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

		Svoka 11 months ago \| parent \| context \| favorite \| on: DeepScaleR: Surpassing O1-Preview with a 1.5B Mode... When I was in University this was called overfitting to be honest. This doesn't seem to perform well outside of eval sets.

buyucu 11 months ago [–]

it's a 1.5b model. You should not expect too much outside the area it was optimized on.

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