yunconglong/13B_MATH_DPO

• DPO Trainer with dataset kyujinpy/orca_math_dpo to improve [yunconglong/MoE_13B_DPO]

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.