Which still rounds to 9B and is 21.4% larger. | Hacker News

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

		neodymiumphish on Feb 24, 2024 \| parent \| context \| favorite \| on: Understanding, using, and finetuning Gemma Which still rounds to 9B and is 21.4% larger.

rasbt on Feb 24, 2024 [–]

Yes, it's definitely unfair to count it as a 7B model. In that case, we could call Llama 2, which is 6.6B parameters, a 6B (or even 5B) parameter model.

neodymiumphish on March 2, 2024 | [–]

Except 6.6 rounds to 7. That’s completely reasonable. Arguing otherwise is pedantic.

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