提出新量化方法，让模型合并更顺畅。
Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
- 基于误差屏障分析，设计可合并的量化方案
- 保持与预训练模型差异小，损失曲面更平坦
- 适合需要多场景适配的量化模型部署
模型合并已成为融合特定任务权重的强大技术，在多目标领域自适应中表现优异。然而在实际应用中，如对量化模型进行操作时，会带来新挑战：通常针对特定目标数据进行量化，这限制了关注域并引入离散化效应，使模型合并变得极为困难。本文从误差屏障视角分析量化对模型合并的影响，提出一种新型后训练量化方法HDRQ（Hessian and distant regularizing quantization），专为多目标领域自适应中的模型合并设计。该方法在保证量化后模型与源预训练模型偏差极小的同时，有效平坦损失表面，从而实现平滑合并。据我们所知，这是首个针对此问题的研究。大量实验验证了其有效性。
原文摘要 · Abstract (English)
Model merging has emerged as a powerful technique for combining task-specific weights, achieving superior performance in multi-target domain adaptation. However, when applied to practical scenarios, such as quantized models, new challenges arise. In practical scenarios, quantization is often applied to target-specific data, but this process restricts the domain of interest and introduces discretization effects, making model merging highly non-trivial. In this study, we analyze the impact of quantization on model merging through the lens of error barriers. Leveraging these insights, we propose a novel post-training quantization, HDRQ - Hessian and distant regularizing quantization - that is designed to consider model merging for multi-target domain adaptation. Our approach ensures that the quantization process incurs minimal deviation from the source pre-trained model while flattening the loss surface to facilitate smooth model merging. To our knowledge, this is the first study on this challenge, and extensive experiments confirm its effectiveness.
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。