Phi-3 3.8B seems to perform much better on almost every test than Gemma 2 9B. It... | Hacker News

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

		alecco on June 28, 2024 \| parent \| context \| favorite \| on: Gemma 2: Improving Open Language Models at a Pract... Phi-3 3.8B seems to perform much better on almost every test than Gemma 2 9B. It is comparable.

refulgentis on June 28, 2024 [–]

I agree.

The implication in my post is "if the reason was size, it's invalidated later"

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