Llama 3.1: Our most capable models to date

by langitbiruon 7/23/2024, 3:13 PMwith 3 comments

by ChrisArchitecton 7/23/2024, 6:10 PM

[dupe]

More discussion: https://news.ycombinator.com/item?id=41046540

https://news.ycombinator.com/item?id=41046773

by sagzon 7/23/2024, 3:44 PM

405B is already being served on WhatsApp!

https://ibb.co/kQ2tKX5

by msoadon 7/23/2024, 3:42 PM

MMLU PRO is the benchmark I trust the most. I noticed they are using 5 shots and CoT. Is that true for GPT4 and Sonnet as well?