提出QEFT，让大模型微调更快更省资源且不丢性能。
QEFT: Quantization for Efficient Fine-Tuning of LLMs
- 轻量级量化技术，兼顾推理与微调加速。
- 全精度微调质量，资源消耗大幅降低。
- 适合需要高效微调的工程部署场景。
随着大语言模型微调的广泛应用，如何在保持推理效率的同时优化微调成为关键挑战，需同时提升推理速度、微调速度、内存占用和模型质量。现有方法结合量化与微调，但难以同时改善四项指标。本文提出轻量级技术Quantization for Efficient Fine-Tuning（QEFT），兼具理论支撑、高灵活性与良好硬件兼容性。实验表明，QEFT在保持全精度参数高效微调质量与泛化能力的同时，显著降低资源开销。代码已开源：https://github.com/xvyaward/qeft。
原文摘要 · Abstract (English)
With the rapid growth in the use of fine-tuning for large language models (LLMs), optimizing fine-tuning while keeping inference efficient has become highly important. However, this is a challenging task as it requires improvements in all aspects, including inference speed, fine-tuning speed, memory consumption, and, most importantly, model quality. Previous studies have attempted to achieve this by combining quantization with fine-tuning, but they have failed to enhance all four aspects simultaneously. In this study, we propose a new lightweight technique called Quantization for Efficient Fine-Tuning (QEFT). QEFT accelerates both inference and fine-tuning, is supported by robust theoretical foundations, offers high flexibility, and maintains good hardware compatibility. Our extensive experiments demonstrate that QEFT matches the quality and versatility of full-precision parameter-efficient fine-tuning, while using fewer resources. Our code is available at https://github.com/xvyaward/qeft.
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。