arxiv:2501.04227
Yusheng Su
yushengsu
AI & ML interests
None yet
Recent Activity
updated a model about 8 hours ago
yushengsu/Qwen3-8B-5layer-Dense-FFN49152 published a model about 9 hours ago
yushengsu/Qwen3-8B-5layer-Dense-FFN49152 published a model about 9 hours ago
yushengsu/Qwen3-8B-5layer-Dense-FFN24576Organizations
models 28
yushengsu/Qwen3-8B-5layer-Dense-FFN49152
Updated
yushengsu/Qwen3-8B-5layer-Dense-FFN24576
Updated
yushengsu/Qwen3-8B-5layer-MoE-8E4A-v1
Updated
yushengsu/deepseek-v4.1-flash-dspark-8000step
Updated
yushengsu/Qwen3-8B-2layer-Dense-FFN6144
Updated
yushengsu/Qwen3-8B-2layer-Dense-FFN3072
Updated
yushengsu/Qwen3-8B-5layer-MoE-8E2A-v1
Updated • 1
yushengsu/Qwen3-8B-5layer-MoE-16E2A-v1
Updated • 1
yushengsu/Qwen3-8B-2layer-MoE-8E4A
Updated
yushengsu/qwen3-8b-dspark-moe-8expert-2activate-batch-wise-0.005-selection-bias-only-5epoch
Updated
datasets 11
yushengsu/profiling-traces
Updated • 35
yushengsu/lora-diff-Qwen3.5-35B-A3B
Updated • 9
yushengsu/lora-diff-NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Updated • 12
yushengsu/lora-diff-NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Updated • 9
yushengsu/rope-dump-DeepSeek-V3.1-Base
Updated • 61
yushengsu/lora-diff-gpt-oss-20b
Updated • 32
yushengsu/lora-diff-Qwen3-VL-30B-A3B-Instruct
Updated • 34
yushengsu/lora-diff-Qwen3-8B
Updated • 778
yushengsu/lora-diff-Qwen3-30B-A3B-Instruct-2507
Updated • 40
yushengsu/lora-diff-Kimi-K2.5
Updated • 23