RLHFlow/Mistral-PRM-Data
Viewer
•
Updated
•
273k
•
119
•
7
RLHFlow MATH Process Reward Model
This is a collection of datasets and models of process reward modeling.
-
-
RLHFlow/Mistral-GSM8K-Test
Viewer • Updated • 1.32k • 82 -
RLHFlow/Mistral-MATH500-Test
Viewer • Updated • 500 • 126 -
RLHFlow/Llama3.1-8B-PRM-Mistral-Data
Text Generation • Updated • 1.9k • 6 -
RLHFlow/Deepseek-MATH500-Test
Viewer • Updated • 500 • 91 -
RLHFlow/Mistral-ORM-Data
Viewer • Updated • 273k • 100 • 2 -
RLHFlow/Deepseek-GSM8K-Test
Viewer • Updated • 1.32k • 76 -
RLHFlow/Deepseek-ORM-Data-Pairwise
Viewer • Updated • 36k • 45 -
RLHFlow/Mistral-ORM-Data-Pairwise
Viewer • Updated • 37.9k • 34 -
RLHFlow/Deepseek-PRM-Data
Viewer • Updated • 253k • 46 • 3 -
RLHFlow/Llama3.1-8B-ORM-Deepseek-Data
Text Generation • Updated • 81 -
RLHFlow/Llama3.1-8B-ORM-Mistral-Data
Text Generation • Updated • 391 -
RLHFlow/Llama3.1-8B-PRM-Deepseek-Data
Text Generation • Updated • 5.52k • 23 -
RLHFlow/Deepseek-ORM-Data
Viewer • Updated • 253k • 58 • 1