News for hackers. Stuff that matters.

A comment on Using LLaMA with M1 Mac and Python 3.11. Parent comment

Re:Using LLaMA with M1 Mac and Python 3.11 by vletal on Sunday March 12, 2023 @04:00PM (#35125441)
Hard to measure these days. The training sets are so large they might contain leaks of test sets. Take these numbers with a grain of salt.
[ Parent | on HN ]
Re:Using LLaMA with M1 Mac and Python 3.11 by code51 on Sunday March 12, 2023 @04:54PM (#35126134)
Or... it could be that Chinchilla study has deficiencies in measuring capabilities of models maybe? Either that or your explanation. Frankly I don't think 13B is better than GPT-3 (text-davinci-001 which I think is not RLHF - but maybe better than base)
[ Parent | on HN ]
Re:Using LLaMA with M1 Mac and Python 3.11 by simonw on Sunday March 12, 2023 @05:03PM (#35126255)
text-davinci-001 is currently classed as "GPT 3.5" by OpenAI, and it did indeed have RLHF in the form of instruction tuning: https://openai.com/research/instruction-following

MY MISTAKE: 002 and 003 are 3.5, but 001 looks to have pre-dated the InstructGPT work.

[ Parent | on HN ]