On-Policy Transition Distillation
Paper • 2610.28048 • Published • 1
OPTD
-
-
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain
Text Generation • 2B • Updated • 147 -
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-Mid
Text Generation • 2B • Updated • 140 -
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-Late
Text Generation • 2B • Updated • 145 -
ModalityDance/OPTD-Qwen3-4B-Mid
Text Generation • 4B • Updated • 148 -
ModalityDance/OPTD-Qwen3-4B-Late
Text Generation • 4B • Updated • 145 -
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-7B-Late
Text Generation • 8B • Updated • 152