You can fine tune without the pre training data too. Mistral models are one exam... | Hacker News

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

		tarruda on March 18, 2024 \| parent \| context \| favorite \| on: Grok You can fine tune without the pre training data too. Mistral models are one example, they never released pre training data and there are many fine tunes.

DreamGen on March 19, 2024 [–]

We are in agreement -- that's exactly what I am saying :)

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