DPO Debate: Is RL needed for RLHF?
ฝัง
- เผยแพร่เมื่อ 30 พ.ย. 2023
- All things as we cannot settle if DPO or RL is better. At least it is a good exercise.
Slides: docs.google.com/presentation/...
Recent blog post of mine on DPO: www.interconnects.ai/p/rlhf-p...
DPO Paper: arxiv.org/abs/2305.18290
Finally, I love DP....oh
Thanks for sharing your thoughts
Will LMsys release their chatbot arena preference dataset
great video, thanks
How DPO works under the hood: th-cam.com/video/Ju-pFJNfOfY/w-d-xo.html
@5:00 (14)
❤