sparsegpt

Tag

Cards List
#sparsegpt

Building a Nested LADDER for LLM Unstructured Post-Training Pruning

arXiv cs.LG ↗ · 21h ago Cached

论文提出 LADDER(Layer-Wise Allocation via Damage-Driven Evaluation and Refinement),一种针对大语言模型的非均匀后训练剪枝方法,通过逐层评估最小化每移除参数的性能损失,生成嵌套掩码轨迹,在 70% 以上高稀疏度下表现显著优于基线。

0 favorites 0 likes
← Back to home

Submit Feedback