RLHFlow/Mistral-PRM-Data
Viewer
•
Updated
•
273k
•
400
•
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 • 33 -
RLHFlow/Mistral-MATH500-Test
Viewer • Updated • 500 • 68 -
RLHFlow/Llama3.1-8B-PRM-Mistral-Data
Text Generation • Updated • 896 • • 10 -
RLHFlow/Deepseek-MATH500-Test
Viewer • Updated • 500 • 127 -
RLHFlow/Mistral-ORM-Data
Viewer • Updated • 273k • 150 • 2 -
RLHFlow/Deepseek-GSM8K-Test
Viewer • Updated • 1.32k • 77 -
RLHFlow/Deepseek-ORM-Data-Pairwise
Viewer • Updated • 36k • 43 • 1 -
RLHFlow/Mistral-ORM-Data-Pairwise
Viewer • Updated • 37.9k • 19 -
RLHFlow/Deepseek-PRM-Data
Viewer • Updated • 253k • 123 • 13 -
RLHFlow/Llama3.1-8B-ORM-Deepseek-Data
Text Generation • Updated • 263 • 1 -
RLHFlow/Llama3.1-8B-ORM-Mistral-Data
Text Generation • Updated • 131 -
RLHFlow/Llama3.1-8B-PRM-Deepseek-Data
Text Generation • Updated • 37.7k • • 34 -
RLHFlow/Deepseek-ORM-Data
Viewer • Updated • 253k • 47 • 3