7Bx4_DPO_2e / README.md
yunconglong's picture
Create README.md
b2535b2 verified
metadata
license: mit

DPO Trainer TRL supports the DPO Trainer for training language models from preference data, as described in the paper Direct Preference Optimization: Your Language Model is Secretly a Reward Model by Rafailov et al., 2023.


"num_experts_per_tok": 2