yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
084f3b10be884c679ad48b49ea902da9dcad55d6
Truthful_DPO_TomGrc_FusionN…/README.md
ModelHub XC 084f3b10be 初始化项目，由ModelHub XC社区提供模型 
Model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
Source: Original Platform
2026-06-06 21:54:39 +08:00

440 B
Raw Blame History

license, tags
license tags
mit
moe
DPO
RL-TUNED
  • DPO Trainer with dataset jondurbin/truthy-dpo-v0.1 to improve [TomGrc/FusionNet_7Bx2_MoE_14B]

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.