This is a collection of datasets and models of process reward modeling.
AI & ML interests
Workflow of Reinforcement Learning from Human Feedback (RLHF). Blog: https://rlhflow.github.io/
models
19
RLHFlow/Llama3.1-8B-PRM-Mistral-Data
Text Generation
•
Updated
•
10
RLHFlow/Llama3.1-8B-PRM-Deepseek-Data
Text Generation
•
Updated
•
6
RLHFlow/Llama3.1-8B-ORM-Deepseek-Data
Text Generation
•
Updated
•
6
RLHFlow/Llama3.1-8B-ORM-Mistral-Data
Text Generation
•
Updated
•
6
RLHFlow/Llama3-v2-iterative-DPO-iter3
Text Generation
•
Updated
•
20
RLHFlow/Llama3-v2-iterative-DPO-iter2
Text Generation
•
Updated
•
17
RLHFlow/Llama3-v2-iterative-DPO-iter1
Text Generation
•
Updated
•
15
RLHFlow/LLaMA3-SFT-v2
Text Generation
•
Updated
•
2.63k
RLHFlow/Llama3-SFT-v2.0-epoch1
Text Generation
•
Updated
•
4
RLHFlow/Llama3-SFT-v2.0-epoch2
Text Generation
•
Updated
•
7
datasets
56
RLHFlow/Deepseek-MATH500-Test
Viewer
•
Updated
•
500
•
6
RLHFlow/Mistral-MATH500-Test
Viewer
•
Updated
•
500
•
13
RLHFlow/Deepseek-ORM-Data
Viewer
•
Updated
•
253k
•
3
RLHFlow/Deepseek-PRM-Data
Viewer
•
Updated
•
253k
•
5
RLHFlow/Mistral-ORM-Data
Viewer
•
Updated
•
273k
•
8
RLHFlow/Mistral-PRM-Data
Viewer
•
Updated
•
273k
•
16
RLHFlow/Mistral-PRM-Data-No-Final-Ans
Viewer
•
Updated
•
273k
•
5
RLHFlow/Deepseek-ORM-Data-Pairwise
Viewer
•
Updated
•
36k
•
9
RLHFlow/Mistral-ORM-Data-Pairwise
Viewer
•
Updated
•
37.9k
•
9
RLHFlow/Deepseek-GSM8K-Test
Viewer
•
Updated
•
1.32k
•
13