Because GPT 3.5 not very good compared to LLaMA 65b or even 33b finetunes, from ... | Hacker News

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

		brucethemoose2 on July 6, 2023 \| parent \| context \| favorite \| on: InternLM – new open source 7B LLM Because GPT 3.5 not very good compared to LLaMA 65b or even 33b finetunes, from my testing. Also because 3.5 is not really available?

cubefox on July 6, 2023 [–]

Have you actually tested code-davinci-002?

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