RLHFlow/Mistral-PRM-Data
Viewer
•
Updated
•
273k
•
442
•
12
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 • 60 -
RLHFlow/Mistral-MATH500-Test
Viewer • Updated • 500 • 84 -
RLHFlow/Llama3.1-8B-PRM-Mistral-Data
Text Generation • Updated • 779 • • 10 -
RLHFlow/Deepseek-MATH500-Test
Viewer • Updated • 500 • 80 -
RLHFlow/Mistral-ORM-Data
Viewer • Updated • 273k • 160 • 2 -
RLHFlow/Deepseek-GSM8K-Test
Viewer • Updated • 1.32k • 64 -
RLHFlow/Deepseek-ORM-Data-Pairwise
Viewer • Updated • 36k • 23 • 1 -
RLHFlow/Mistral-ORM-Data-Pairwise
Viewer • Updated • 37.9k • 14 -
RLHFlow/Deepseek-PRM-Data
Viewer • Updated • 253k • 104 • 15 -
RLHFlow/Llama3.1-8B-ORM-Deepseek-Data
Text Generation • Updated • 146 • 1 -
RLHFlow/Llama3.1-8B-ORM-Mistral-Data
Text Generation • Updated • 116 -
RLHFlow/Llama3.1-8B-PRM-Deepseek-Data
Text Generation • Updated • 26.6k • • 34 -
RLHFlow/Deepseek-ORM-Data
Viewer • Updated • 253k • 37 • 3