It's a much smaller model though. I think the point is more the demonstration th... | Hacker News

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

impossiblefork on Dec 16, 2024 | parent | context | favorite | on: Phi-4: Microsoft's Newest Small Language Model Spe...

It's a much smaller model though.

I think the point is more the demonstration that such a small model can have such good performance than any actual usefulness.

magicalhippo on Dec 16, 2024 [–]

Gemma2 9B has significantly better prompt adherence than Llama 3.1 8B in my experience.

I've just assumed it's down to how it was trained, but no expert.

Consider applying for YC's Fall 2026 batch! Applications are open till July 27.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact