MathGenie/InternLM2-SFT-SCDPO
Text Generation
•
20B
•
Updated
•
18
•
1
Step-Controlled DPO
Models and Datasets of Step-Controlled DPO.
-
-
MathGenie/Mistral-7B-Ours-SFT
Text Generation • 7B • Updated • 12 • 1 -
MathGenie/Mistral-7B-Ours-SFT-SCDPO
Text Generation • 7B • Updated • 13 • 2 -
MathGenie/SCDPO-Data-Mistral-Ours
Viewer • Updated • 30.2k • 45 • 3 -
MathGenie/MATH-GSM8K-Tool-81K
Viewer • Updated • 81.1k • 11 • 2 -
MathGenie/DPO-Data-Mistral-Ours
Viewer • Updated • 12.2k • 40 • 1