This is the collection of the online-DPO-R1 project.
AI & ML interests
Workflow of Reinforcement Learning from Human Feedback (RLHF). Blog: https://rlhflow.github.io/
Recent Activity
View all activity
Collections
10
models
27

RLHFlow/Qwen2.5-7B-SFT
Updated
•
33

RLHFlow/Qwen2.5-7B-RAFT-Zero
Updated
•
18

RLHFlow/Qwen2.5-7B-DPO-NLL-Zero
Updated
•
26

RLHFlow/Qwen2.5-7B-DPO-Zero
Updated
•
26

RLHFlow/Qwen2.5-7B-DPO
Updated
•
28

RLHFlow/Qwen2.5-7B-PPO-Zero
Updated
•
65
•
2

RLHFlow/Decision-Tree-Reward-Gemma-2-27B
Text Classification
•
Updated
•
129
•
4

RLHFlow/Decision-Tree-Reward-Llama-3.1-8B
Text Classification
•
Updated
•
185
•
6

RLHFlow/Llama3.1-8B-PRM-Mistral-Data
Text Generation
•
Updated
•
405
•
8

RLHFlow/Llama3.1-8B-PRM-Deepseek-Data
Text Generation
•
Updated
•
23.8k
•
33
datasets
83
RLHFlow/self_rewarding_turn2_example
Updated
•
100
RLHFlow/self_rewarding_turn1_with_rewards_example
Updated
•
81
RLHFlow/self_rewarding_rl_prompt
Updated
•
70
RLHFlow/self_rewarding_sft_prompt
Viewer
•
Updated
•
40k
•
106
RLHFlow/self_rewarding_ift_example_raw_data1
Viewer
•
Updated
•
16.3k
•
66
RLHFlow/self_rewarding_ift_example
Viewer
•
Updated
•
32k
•
226
RLHFlow/qwq_gen_sft_15k
Viewer
•
Updated
•
15k
•
124
RLHFlow/numia_prompt_ppo
Viewer
•
Updated
•
404k
•
186
•
1
RLHFlow/numia_prompt_dpo_test
Viewer
•
Updated
•
1.02k
•
69
RLHFlow/numia_prompt_dpo9
Viewer
•
Updated
•
20k
•
63