RLHFlow/Qwen2.5-7B-PPO-Zero
Updated
•
130
•
2
Online-DPO-R1
This is the collection of the online-DPO-R1 project.
-
-
RLHFlow/Qwen2.5-7B-DPO-Zero
Updated • 47 -
RLHFlow/Qwen2.5-7B-DPO-NLL-Zero
Updated • 31 -
RLHFlow/Qwen2.5-7B-RAFT-Zero
Updated • 43 -
RLHFlow/numia_prompt_ppo
Viewer • Updated • 404k • 204 • 1 -
RLHFlow/numia_prompt_dpo1
Viewer • Updated • 20k • 121 -
RLHFlow/Qwen2.5-7B-DPO
Updated • 29 -
RLHFlow/Qwen2.5-7B-SFT
Updated • 16 -
RLHFlow/qwq_gen_sft_15k
Viewer • Updated • 15k • 70 -
RLHFlow/numia_prompt_dpo2
Viewer • Updated • 20k • 51 -
RLHFlow/numia_prompt_dpo3
Viewer • Updated • 20k • 63 -
Self-rewarding correction for mathematical reasoning
Paper • 2502.19613 • Published • 75