yushengsu/qwen3-3b-16E1A
Updated
Yusheng Su
yushengsu
AI & ML interests
None yet
Recent Activity
published a model about 1 hour ago
yushengsu/deepseek-v4.1-flash-dspark-8000step updated a model about 2 hours ago
yushengsu/qwen3-8b-dspark-moe-8expert-2activate-batch-wise-0.005-selection-bias-only-5epoch published a model about 2 hours ago
yushengsu/qwen3-8b-dspark-moe-8expert-2activate-batch-wise-0.005-selection-bias-only-5epochOrganizations
yushengsu/deepseek-v4.1-flash-dspark-8000step
Updated
yushengsu/qwen3-8b-dspark-moe-8expert-2activate-batch-wise-0.005-selection-bias-only-5epoch
Updated
yushengsu/Qwen3-8B-5layer-MoE-2E1A
Updated
yushengsu/Qwen3-8B-5layer-Dense
Updated
yushengsu/Qwen3-8B-2layer-Dense-v2
Updated
yushengsu/Qwen3-8B-2layer-Dense-v1
Updated
yushengsu/Qwen3-8B-2layer-MoE-8E1A-v1
Updated
yushengsu/Qwen3-8B-2layer-MoE-8E1A-v2
Updated
yushengsu/Qwen3-8B-5layer-MoE-8E1A-v1
Updated
yushengsu/deepseek-v4-flash-dspark-3000step
Updated
yushengsu/Qwen3-8B-5layer-MoE-8E1A-v2
Updated
yushengsu/qwen38-dspark-moe-cont1ep-step2000
21B • Updated • 7
yushengsu/sgl-lora-data
Updated
yushengsu/sglang_lora_logprob_diff_without_tuning
Updated • 61
yushengsu/Qwen3-4B-torch-dist
Updated
yushengsu/coke-bert-base-uncased-2hop
Updated • 8
yushengsu/coke-roberta-base-2hop
Updated • 11
yushengsu/CokeBERT
Updated