jayzou3773/qwen3_5-moe-expert_drop-pure_gradient_pruning-r128-s1k-128samples-thinking
19B • Updated • 1
XINKAI ZOU
jayzou3773
AI & ML interests
AI Agent, Human-Computer Interaction, AI4SE
Recent Activity
upvoted a paper about 1 month ago
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism updated a model about 1 month ago
jayzou3773/Qwen1.5-MOE-rebuttal-condenser-static published a model about 1 month ago
jayzou3773/Qwen1.5-MOE-rebuttal-condenser-staticOrganizations
jayzou3773/qwen3_5-moe-expert_drop-pure_expert_gradient_pruning-r128-s1k-128samples-thinking
19B • Updated • 2
jayzou3773/qwen3_5-moe-expert_drop-layerwise_pruning-r128-s1k-128samples-thinking
19B • Updated • 1
jayzou3773/qwen3_5-moe-expert_drop-bias_pruning-r128-s1k-128samples-thinking
19B • Updated • 2
jayzou3773/qwen3-moe-neuron_drop_global-p50-s1k-128samples
31B • Updated • 25
jayzou3773/qwen3-moe-neuron_drop_layer-p50-s1k-128samples
31B • Updated • 22
jayzou3773/qwen3-moe-expert_drop-pure_gradient_pruning-r64-s1k-128samples-thinking
16B • Updated • 2
jayzou3773/qwen3-moe-expert_drop-pure_expert_gradient_pruning-r64-s1k-128samples-thinking
16B • Updated • 1
jayzou3773/qwen3-moe-expert_drop-layerwise_pruning-r64-s1k-128samples-thinking
16B • Updated • 1
jayzou3773/qwen3-moe-expert_drop-bias_pruning-r64-s1k-128samples-thinking
16B • Updated • 1
jayzou3773/qwen3-moe-neuron_structure_drop-p50-s1k-128samples-thinking
16B • Updated • 1
jayzou3773/qwen3_5-moe-neuron_structure_drop-p50-s1k-128samples
19B • Updated • 1
jayzou3773/qwen3_5-moe-expert_drop-weight_magnitude_pruning-r128-s1k-128samples
19B • Updated • 1
jayzou3773/qwen3_5-moe-expert_drop-pure_gradient_pruning-r128-s1k-128samples
19B • Updated • 1
jayzou3773/qwen3_5-moe-expert_drop-pure_expert_gradient_pruning-r128-s1k-128samples
19B • Updated • 1
jayzou3773/qwen3_5-moe-expert_drop-layerwise_pruning-r128-s1k-128samples
19B • Updated • 1
jayzou3773/qwen3_5-moe-expert_drop-bias_pruning-r128-s1k-128samples
19B • Updated • 1
jayzou3773/qwen3-moe-neuron_structure_drop-p50-s1k-128samples
16B • Updated • 1
jayzou3773/qwen3-moe-expert_drop-weight_magnitude_pruning-r64-s1k-128samples
16B • Updated • 3
jayzou3773/qwen3-moe-expert_drop-pure_gradient_pruning-r64-s1k-128samples
16B • Updated • 1
jayzou3773/qwen3-moe-expert_drop-pure_expert_gradient_pruning-r64-s1k-128samples
16B • Updated • 1
jayzou3773/qwen3-moe-expert_drop-layerwise_pruning-r64-s1k-128samples
16B • Updated • 1
jayzou3773/qwen3-moe-expert_drop-bias_pruning-r64-s1k-128samples
16B • Updated • 2
jayzou3773/sft-qwen-math
14B • Updated • 3
jayzou3773/sft-pruned-qwen-math-activation
8B • Updated • 2
jayzou3773/sft-pruned-qwen-math-weight_magnitude
8B • Updated • 2
jayzou3773/sft-pruned-qwen-math-pure_gradient
8B • Updated • 2
jayzou3773/sft-pruned-qwen-math-pure_expert_gradient
8B • Updated • 2
jayzou3773/sft-pruned-qwen-math-densemixer_gradient
8B • Updated • 2
jayzou3773/sft-pruned-qwen-math-bias
8B • Updated • 2