Any plan for supporting DPO?

[lorabit110]

🚀 Feature Request

Support DPO (Direct Preference Optimization) loss and data loader.

Motivation

Many recent open LLMs have achieved promising results from using DPO instead of RL-style tuning like PPO for alignment. And it seems to require less changes to llm-foundry than RLHF.

[pretidav]

same question here