yunconglong/13B_MATH_DPO
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
13B_MATH_DPO/README.md
ModelHub XC 6968696e78 初始化项目，由ModelHub XC社区提供模型 
Model: yunconglong/13B_MATH_DPO
Source: Original Platform
2026-04-11 16:10:02 +08:00

434 B
Raw Permalink Blame History

license, tags
license tags
other
moe
DPO
RL-TUNED
  • 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.