Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples
"LLM剪枝" 相关文章
Fewer Weights, More Problems: A Practical Attack on LLM Pruning
Fewer Weights, More Problems: A Practical Attack on LLM Pruning
UniPruning: Unifying Local Metric and Global Feedback for Scalable Sparse LLMs
Pruning Large Language Models by Identifying and Preserving Functional Networks
LLM-Barber: Block-Aware Rebuilder for Sparsity Mask in One-Shot for Large Language Models
MaskLLM: A Learnable AI Method that Facilitates End-to End Training of LLM Sparsity on Large-Scale Datasets
