That hasn’t been true for a while. Falcon 40B seemingly outperforms LLaMA 60B ac... | Hacker News

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

		kirill5pol on July 11, 2023 \| parent \| context \| favorite \| on: GPT-4 details leaked? That hasn’t been true for a while. Falcon 40B seemingly outperforms LLaMA 60B according to the OpenLLM leaderboard https://huggingface.co/tiiuae/falcon-40b

lolinder on July 11, 2023 [–]

Fair enough. I haven't really looked at Falcon as a replacement for LLaMA yet because it isn't supported by llama.cpp, but it looks promising.

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