Why should we start fine tuning gemma when it is so bad. Why not instead focus t... | Hacker News

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

		wanderingmind 3 months ago \| parent \| context \| favorite \| on: Gemma 3 270M: Compact model for hyper-efficient AI Why should we start fine tuning gemma when it is so bad. Why not instead focus the fine-tuning efforts on Qwen, when it starts off with much, much better outputs?

mdp2021 3 months ago [–]

Speed critical applications, I suppose. Have you compared the speeds?

(I did. I won't give you number (which I cannot remember precisely), but Gemma was much faster. So, it will depend on the application.)

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