shengqihailuo1

Results 2 comments of


                                            shengqihailuo1

Why the importance of weights evaluated by w^2/(H_ii)^2, instead of w^2/(H_ii) like in SparseGPT?

How to conduct sensitivity analysis of model parameters? Is there a paper and code for that?

Qwen2.5VL 3B calibration using awq takes too long

type: Qwen2_5VL how to work?