利用注意力稀疏性实现大模型高效压缩，显著提升多模态模型量化效果。
CASP: Compression of Large Multimodal Models Based on Attention Sparsity
- 基于注意力矩阵稀疏性，对查询与键权重进行数据感知的低秩分解。
- 在图像与视频语言任务上，2比特量化性能平均提升21%。
- 兼容任意量化方法，适合追求轻量化部署的多模态研究者。
本文提出一种针对大型多模态模型（LMMs）的极端压缩技术。尽管先前研究已探索将量化作为大型语言模型（LLMs）的高效训练后压缩方法，但多模态模型的低比特压缩仍缺乏深入研究。多模态模型输入的冗余性导致注意力矩阵高度稀疏。我们从理论和实验上证明，注意力矩阵的稀疏性限制了查询与键权重矩阵的压缩误差。基于此，我们提出CASP，一种面向LMMs的模型压缩方法。该方法对查询与键权重矩阵执行数据感知的低秩分解，并通过最优比特分配策略对所有层进行量化。CASP兼容任何量化技术，在图像与视频-语言基准测试中，使当前最先进的2比特量化方法（AQLM与QuIP#）平均提升21%性能。
原文摘要 · Abstract (English)
In this work, we propose an extreme compression technique for Large Multimodal Models (LMMs). While previous studies have explored quantization as an efficient post-training compression method for Large Language Models (LLMs), low-bit compression for multimodal models remains under-explored. The redundant nature of inputs in multimodal models results in a highly sparse attention matrix. We theoretically and experimentally demonstrate that the attention matrix's sparsity bounds the compression error of the Query and Key weight matrices. Based on this, we introduce CASP, a model compression technique for LMMs. Our approach performs a data-aware low-rank decomposition on the Query and Key weight matrix, followed by quantization across all layers based on an optimal bit allocation process. CASP is compatible with any quantization technique and enhances state-of-the-art 2-bit quantization methods (AQLM and QuIP#) by an average of 21% on image- and video-language benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。