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

If any one is interesting in seeing how 400B model compares with other opensource models, here is a useful chart: https://x.com/natolambert/status/1780993655274414123


Fun fact, it's impossible to 100% the MMLU because 2-3% of it has wrong answers.


You just need to give the wrong answer ;)


Would love to see similar chart but llama 3 400b compared to the closed-source models like opus




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

Search: