AI & ML interests
Workflow of Reinforcement Learning from Human Feedback (RLHF). Blog: https://rlhflow.github.io/
Recent Activity
Collections
11
models
29
RLHFlow/Qwen2.5-Math-7B-Zero-RAFTpp
Text Generation
•
Updated
•
6
•
1
RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej
Text Generation
•
Updated
•
3
•
1
RLHFlow/Llama3.1-8B-PRM-Deepseek-Data
Text Generation
•
Updated
•
49.8k
•
•
34
RLHFlow/Qwen2.5-7B-SFT
Updated
•
29
RLHFlow/Qwen2.5-7B-RAFT-Zero
Updated
•
6
RLHFlow/Qwen2.5-7B-DPO-NLL-Zero
Updated
•
3
RLHFlow/Qwen2.5-7B-DPO-Zero
Updated
•
13
RLHFlow/Qwen2.5-7B-DPO
Updated
•
2
RLHFlow/Qwen2.5-7B-PPO-Zero
Updated
•
17
•
2
RLHFlow/Decision-Tree-Reward-Gemma-2-27B
Text Classification
•
Updated
•
10
•
7
datasets
83
RLHFlow/self_rewarding_turn2_example
Updated
•
13
RLHFlow/self_rewarding_turn1_with_rewards_example
Updated
•
12
RLHFlow/self_rewarding_rl_prompt
Updated
•
8
RLHFlow/self_rewarding_sft_prompt
Viewer
•
Updated
•
40k
•
17
RLHFlow/self_rewarding_ift_example_raw_data1
Viewer
•
Updated
•
16.3k
•
57
RLHFlow/self_rewarding_ift_example
Viewer
•
Updated
•
32k
•
85
RLHFlow/qwq_gen_sft_15k
Viewer
•
Updated
•
15k
•
12
RLHFlow/numia_prompt_ppo
Viewer
•
Updated
•
404k
•
47
•
1
RLHFlow/numia_prompt_dpo_test
Viewer
•
Updated
•
1.02k
•
16
RLHFlow/numia_prompt_dpo9
Viewer
•
Updated
•
20k
•
17