RLHFlow/Qwen2.5-7B-PPO-Zero
8B
•
Updated
•
5
•
2
Online-DPO-R1
This is the collection of the online-DPO-R1 project.
-
-
RLHFlow/Qwen2.5-7B-DPO-Zero
8B • Updated • 5 -
RLHFlow/Qwen2.5-7B-DPO-NLL-Zero
8B • Updated • 3 -
RLHFlow/Qwen2.5-7B-RAFT-Zero
8B • Updated • 3 -
RLHFlow/numia_prompt_ppo
Viewer • Updated • 404k • 9 • 1 -
RLHFlow/numia_prompt_dpo1
Viewer • Updated • 20k • 730 -
RLHFlow/Qwen2.5-7B-DPO
8B • Updated • 4 -
RLHFlow/Qwen2.5-7B-SFT
8B • Updated • 6 -
RLHFlow/qwq_gen_sft_15k
Viewer • Updated • 15k • 21 -
RLHFlow/numia_prompt_dpo2
Viewer • Updated • 20k • 16 -
RLHFlow/numia_prompt_dpo3
Viewer • Updated • 20k • 18 -
Self-rewarding correction for mathematical reasoning
Paper • 2502.19613 • Published • 84