Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps Paper • 2605.16928 • Published 14 days ago • 93
EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation Paper • 2605.04062 • Published Apr 10 • 30
zhangsq-nju/Qwen3-0.6B-EdgeRazor-4bit Text Generation • 0.6B • Updated 19 days ago • 72 • • 6