News for hackers. Stuff that matters.

A comment on DeepSpeed Chat: Easy, fast and affordable RLHF training of ChatGPT-like models. Parent comment

Re:DeepSpeed Chat: Easy, fast and affordable RLHF training o... by lcastricato on Thursday April 13, 2023 @08:05AM (#35554131)
FYI they don't compare to trlX bc trlX is roughly just as fast. Similarly, they put trl in the worst light possible (trl is actually must faster than they claim.)
[ Parent | on HN ]
Re:DeepSpeed Chat: Easy, fast and affordable RLHF training o... by lcastricato on Thursday April 13, 2023 @08:05AM (#35554137)
We're doing some stuff with NVIDIA right now that I can't talk about yet. Super exciting though.
[ Parent | on HN ]