News for hackers. Stuff that matters.
Re:GPT-4 Details Leaked by kirill5pol on Tuesday July 11, 2023 @12:08PM (#36683033)
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

Re:GPT-4 Details Leaked by lolinder on Tuesday July 11, 2023 @12:49PM (#36683672)
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.