News for hackers. Stuff that matters.

A comment on RLHF a LLM in <50 lines of Python. Parent comment

Re:RLHF a LLM in <50 lines of Python by changoplatanero on Sunday February 11, 2024 @09:21PM (#39340727)
I can second that. From what I’ve heard from people at leading labs, it’s not clear that dpo is worth switching to from RLHF
[ Parent | on HN ]

There are no comments on this comment yet.