VectorZhao/CSEG-Bench
Viewer • Updated • 1.16k • 79
CSEG-RM
CSEG reward models (SFT, GRPO, SFT-GRPO at 4B and 8B) and CSEG-Bench.
-
-
VectorZhao/CSEG-RM-SFT-4B
Text Generation • 4B • Updated • 5 -
VectorZhao/CSEG-RM-SFT-8B
Text Generation • 8B • Updated • 5 -
VectorZhao/CSEG-RM-GRPO-4B
Text Generation • 4B • Updated • 1 -
VectorZhao/CSEG-RM-SFT-GRPO-4B
Text Generation • 4B • Updated • 4 -
VectorZhao/CSEG-RM-SFT-GRPO-8B
Text Generation • 8B • Updated • 3 -
VectorZhao/CSEG-RM-GRPO-8B
Text Generation • 8B • Updated • 2