FLoRA通过融合前向后向适配器，实现高效微调并降低大模型推理延迟。
FLoRA: Fused forward-backward adapters for parameter efficient fine-tuning and reducing inference-time latencies of LLMs
- 将前向与后向适配器融合到基础模型投影层中，减少参数量
- 在相似参数预算下，准确率和推理延迟均优于LoRA
- 适合需要低延迟高精度微调的场景，如实时应用
随着大语言模型持续增大，高效训练与微调变得愈发重要。近年来，参数高效微调（PEFT）受到广泛关注，低秩适配器（LoRA）等方法应运而生。尽管已有多种PEFT方法被研究，但其潜在空间仍极大。本文提出FLoRA，一种融合前向-后向适配器（FFBA）的家族方法，用于下游任务的参数高效微调。该方法结合了主流LoRA与并行适配器的思想，提升整体微调精度。同时，通过将前向与后向适配器融合至基模型现有投影层，有效降低推理延迟。实验表明，在相近参数预算下，所提FFB适配器在准确率与延迟方面均显著优于常用的LoRA。
原文摘要 · Abstract (English)
As the large language models (LLMs) grow in size each day, efficient training and fine-tuning has never been as important as nowadays. This resulted in the great interest in parameter efficient fine-tuning (PEFT), and effective methods including low-rank adapters (LoRA) has emerged. Although the various PEFT methods have been studied extensively in the recent years, the greater part of the subject remains unexplored with the huge degree of freedom. In this paper, we propose FLoRA, a family of fused forward-backward adapters (FFBA) for parameter-efficient fine-tuning of LLMs on downstream tasks. The FFBA combine ideas from the popular LoRA and parallel adapters to improve the overall fine-tuning accuracies. At the same time, latencies are minimized by fusing the forward and backward adapters into existing projection layers of the base model. Experimental results show that the proposed FFB adapters perform significantly better than the popularly used LoRA in both accuracy and latency for a similar parameter budget.
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。