RLHFlow/Mistral-PRM-Data
Viewer
•
Updated
•
273k
•
119
•
10
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 • 54 -
RLHFlow/Mistral-MATH500-Test
Viewer • Updated • 500 • 146 -
RLHFlow/Llama3.1-8B-PRM-Mistral-Data
Text Generation • Updated • 1.09k • 8 -
RLHFlow/Deepseek-MATH500-Test
Viewer • Updated • 500 • 173 -
RLHFlow/Mistral-ORM-Data
Viewer • Updated • 273k • 177 • 2 -
RLHFlow/Deepseek-GSM8K-Test
Viewer • Updated • 1.32k • 61 -
RLHFlow/Deepseek-ORM-Data-Pairwise
Viewer • Updated • 36k • 49 • 1 -
RLHFlow/Mistral-ORM-Data-Pairwise
Viewer • Updated • 37.9k • 43 -
RLHFlow/Deepseek-PRM-Data
Viewer • Updated • 253k • 156 • 12 -
RLHFlow/Llama3.1-8B-ORM-Deepseek-Data
Text Generation • Updated • 549 -
RLHFlow/Llama3.1-8B-ORM-Mistral-Data
Text Generation • Updated • 60 -
RLHFlow/Llama3.1-8B-PRM-Deepseek-Data
Text Generation • Updated • 21.9k • 33 -
RLHFlow/Deepseek-ORM-Data
Viewer • Updated • 253k • 59 • 3