search

OptimalScale / LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
https://optimalscale.github.io/LMFlow/
Apache License 2.0
8.23k stars 822 forks source link

Add DPO support #797

Closed wheresmyhair closed 5 months ago

wheresmyhair commented 5 months ago

DPO tested, based on PR #759 . Credit @gzliyu, thanks for the dedicated effort!