Shu-Hao Zhang

zhsh17's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 5 days ago

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

Paper • 2605.16928 • Published 11 days ago • 90

authored 2 papers 16 days ago

TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge

Paper • 2510.21879 • Published Oct 23, 2025

EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation

Paper • 2605.04062 • Published Apr 10 • 30

commented a paper 19 days ago

EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation

Paper • 2605.04062 • Published Apr 10 • 30 •

1

upvoted a paper 19 days ago

EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation

Paper • 2605.04062 • Published Apr 10 • 30

liked a Space 25 days ago

Running

Agents

7

EdgeRazor Playground

🚀

7

Chat with customizable Llama language models

liked 2 models 28 days ago

zhangsq-nju/Qwen3-0.6B-EdgeRazor-4bit

Text Generation • 0.6B • Updated 16 days ago • 69 • 6

zhangsq-nju/Qwen3-1.7B-EdgeRazor-GGUF

Text Generation • 2B • Updated 16 days ago • 1.07k • 10

upvoted a collection 28 days ago

EdgeRazor-Nbit

Collection

16 items • Updated 19 days ago • 8

updated a model 4 months ago

zhsh17/Qwen3-4B-EdgeRazor-1.88bit-v0129-unquant

2B • Updated Jan 29 • 1

published a model 4 months ago

zhsh17/Qwen3-4B-EdgeRazor-1.88bit-v0129-unquant

2B • Updated Jan 29 • 1