RLHFlow/Mistral-PRM-Data
Viewer
•
Updated
•
273k
•
93
•
9
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 • 110 -
RLHFlow/Llama3.1-8B-PRM-Mistral-Data
Text Generation • Updated • 2.29k • 7 -
RLHFlow/Deepseek-MATH500-Test
Viewer • Updated • 500 • 95 -
RLHFlow/Mistral-ORM-Data
Viewer • Updated • 273k • 118 • 2 -
RLHFlow/Deepseek-GSM8K-Test
Viewer • Updated • 1.32k • 66 -
RLHFlow/Deepseek-ORM-Data-Pairwise
Viewer • Updated • 36k • 42 -
RLHFlow/Mistral-ORM-Data-Pairwise
Viewer • Updated • 37.9k • 34 -
RLHFlow/Deepseek-PRM-Data
Viewer • Updated • 253k • 70 • 6 -
RLHFlow/Llama3.1-8B-ORM-Deepseek-Data
Text Generation • Updated • 141 -
RLHFlow/Llama3.1-8B-ORM-Mistral-Data
Text Generation • Updated • 420 -
RLHFlow/Llama3.1-8B-PRM-Deepseek-Data
Text Generation • Updated • 10.8k • 27 -
RLHFlow/Deepseek-ORM-Data
Viewer • Updated • 253k • 51 • 1