-
TsinghuaC3I/ZEDA-Qwen3-30B-A3B-Dynamic
Text Generation • 31B • Updated • 31 • 1 -
TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic
Text Generation • 30B • Updated • 35 • 2 -
TsinghuaC3I/ZEDA
Preview • Updated • 139 • 1 -
Post-Trained MoE Can Skip Half Experts via Self-Distillation
Paper • 2605.18643 • Published • 30
AI & ML interests
Large Language Models
Papers
Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE
A Survey of Reinforcement Learning for Large Reasoning Models
Organization Card
Center for Collaborative & Conversational Intelligence (C3I), Tsinghua University
-
TsinghuaC3I/ZEDA-Qwen3-30B-A3B-Dynamic
Text Generation • 31B • Updated • 31 • 1 -
TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic
Text Generation • 30B • Updated • 35 • 2 -
TsinghuaC3I/ZEDA
Preview • Updated • 139 • 1 -
Post-Trained MoE Can Skip Half Experts via Self-Distillation
Paper • 2605.18643 • Published • 30
models 10
TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic
Text Generation • 30B • Updated • 35 • 2
TsinghuaC3I/ZEDA-Qwen3-30B-A3B-Dynamic
Text Generation • 31B • Updated • 31 • 1
TsinghuaC3I/Qwen2.5-7B-VL-ReAd-R
8B • Updated • 259 • 2
TsinghuaC3I/Llama-3.1-8B-Instruct-SSRL
Text Generation • 8B • Updated • 13
TsinghuaC3I/Llama-3.2-3B-Instruct-SSRL
Text Generation • 4B • Updated • 22
TsinghuaC3I/Qwen2.5-7B-Instruct-SSRL
Text Generation • 8B • Updated • 26
TsinghuaC3I/Qwen2.5-3B-Instruct-SSRL
Text Generation • 3B • Updated • 22 • 1
TsinghuaC3I/Llama-3-70B-UltraMedical
71B • Updated • 207 • 7
TsinghuaC3I/Llama-3.1-8B-UltraMedical
8B • Updated • 1.68k • 18
TsinghuaC3I/Llama-3-8B-UltraMedical
Text Generation • 8B • Updated • 366 • • 23
datasets 7
TsinghuaC3I/ZEDA-Evaluation
Preview • Updated • 368
TsinghuaC3I/ZEDA
Preview • Updated • 139 • 1
TsinghuaC3I/AdsQA
Viewer • Updated • 800 • 229 • 4
TsinghuaC3I/SSRL
Preview • Updated • 109 • 2
TsinghuaC3I/MedXpertQA
Viewer • Updated • 4.46k • 12.1k • 66
TsinghuaC3I/UltraMedical-Preference
Preview • Updated • 2.38k • 11
TsinghuaC3I/UltraMedical
Viewer • Updated • 410k • 5.38k • 32