Sparse checkpoints corresponding to PATCH paper. Paper link: https://arxiv.org/abs/2509.23410 - GitHub Link: https://github.com/Paramathic/patch
Mohammad Mozaffari
mohammad-mozaffari
·
AI & ML interests
Compression of Large Language Models through Sparsity, Quantization, and Low-rank Approximation (the Compression Trinity)
Recent Activity
updated a collection 4 days ago
HyperPrune updated a model 4 days ago
elastix-ai/HyperPrune-Qwen3.6-27B-4to8 published a model 4 days ago
elastix-ai/HyperPrune-Qwen3.6-27B-4to8Organizations