arxiv:2605.04062
Shu-Hao Zhang
zhsh17
·
AI & ML interests
LLM, Lightweight, Security
Recent Activity
upvoted a paper about 15 hours ago
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps authored a paper 12 days ago
TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary
Weights and Distilled Knowledge authored a paper 12 days ago
EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware DistillationOrganizations
None yet
models 8
zhsh17/Qwen3-4B-EdgeRazor-1.88bit-v0129-unquant
2B • Updated • 1
zhsh17/Qwen3-0.6B-Q4_K_M-GGUF
Text Generation • 0.8B • Updated • 8
zhsh17/Qwen3-0.6B-Q2_K-GGUF
Text Generation • 0.8B • Updated • 8
zhsh17/OLMo-2-0425-1B-Instruct-Q4_K_M-GGUF
Text Generation • 1B • Updated • 12
zhsh17/Qwen3-1.7B-Q4_0-GGUF
Text Generation • 2B • Updated • 1
zhsh17/Qwen3-1.7B-Q2_K-GGUF
Text Generation • 2B • Updated • 7
zhsh17/OLMo-2-0425-1B-Instruct-Q2_K-GGUF
Text Generation • 1B • Updated • 7
zhsh17/OLMoE-1B-7B-0125-Instruct-Q2_K-GGUF
Text Generation • 7B • Updated • 15
datasets 0
None public yet