RLHFlow/Mistral-PRM-Data
Viewer
•
Updated
•
273k
•
134
•
5
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 • 246 -
RLHFlow/Mistral-MATH500-Test
Viewer • Updated • 500 • 159 -
RLHFlow/Llama3.1-8B-PRM-Mistral-Data
Text Generation • Updated • 952 • 5 -
RLHFlow/Deepseek-MATH500-Test
Viewer • Updated • 500 • 122 -
RLHFlow/Mistral-ORM-Data
Viewer • Updated • 273k • 42 -
RLHFlow/Deepseek-GSM8K-Test
Viewer • Updated • 1.32k • 80 -
RLHFlow/Deepseek-ORM-Data-Pairwise
Viewer • Updated • 36k • 38 -
RLHFlow/Mistral-ORM-Data-Pairwise
Viewer • Updated • 37.9k • 34 -
RLHFlow/Deepseek-PRM-Data
Viewer • Updated • 253k • 37 -
RLHFlow/Llama3.1-8B-ORM-Deepseek-Data
Text Generation • Updated • 14 -
RLHFlow/Llama3.1-8B-ORM-Mistral-Data
Text Generation • Updated • 19 -
RLHFlow/Llama3.1-8B-PRM-Deepseek-Data
Text Generation • Updated • 70 • 1 -
RLHFlow/Deepseek-ORM-Data
Viewer • Updated • 253k • 42