-
TsinghuaC3I/ZEDA-Qwen3-30B-A3B-Dynamic
Text Generation • 31B • Updated • 26 • 1 -
TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic
Text Generation • 30B • Updated • 28 • 2 -
TsinghuaC3I/ZEDA
Preview • Updated • 52 • 1 -
Post-Trained MoE Can Skip Half Experts via Self-Distillation
Paper • 2605.18643 • Published • 28
AI & ML interests
Large Language Models
Recent Activity
View all activity
Datasets and Models of UltraMedical
-
TsinghuaC3I/ZEDA-Qwen3-30B-A3B-Dynamic
Text Generation • 31B • Updated • 26 • 1 -
TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic
Text Generation • 30B • Updated • 28 • 2 -
TsinghuaC3I/ZEDA
Preview • Updated • 52 • 1 -
Post-Trained MoE Can Skip Half Experts via Self-Distillation
Paper • 2605.18643 • Published • 28
Datasets and Models of UltraMedical