用CPU也能高效微调大模型，靠预训练适配器组合实现
LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs
- 通过预训练适配器库构建元操作符，实现无需梯度更新的轻量级组合
- 在标准笔记本电脑上运行，生成的适配器性能优于基础模型
- 适合无GPU资源但需微调大模型的研究者与开发者
低秩适配器（LoRA）通过参数高效更新改变了大语言模型（LLM）的微调方式。然而，其广泛应用仍受限于对GPU训练的依赖。本文提出一种理论严谨的LoRA微调方法，专为计算资源有限的用户设计，尤其适用于仅具备普通笔记本CPU的场景。该方法学习一个元操作符，将任意输入数据集（表示为概率分布）映射到一组LoRA权重，利用Mistral-7B-Instruct-v0.2模型的大量预训练适配器库。整个流程不进行新的梯度更新，而是直接在CPU上通过轻量级组合现有LoRA生成新适配器。尽管性能不及GPU训练的版本，但结果始终优于基线Mistral模型，在下游任务中表现稳健，为传统GPU微调提供了实用且可及的替代方案。
原文摘要 · Abstract (English)
Low-Rank Adapters (LoRAs) have transformed the fine-tuning of Large Language Models (LLMs) by enabling parameter-efficient updates. However, their widespread adoption remains limited by the reliance on GPU-based training. In this work, we propose a theoretically grounded approach to LoRA fine-tuning designed specifically for users with limited computational resources, particularly those restricted to standard laptop CPUs. Our method learns a meta-operator that maps any input dataset, represented as a probability distribution, to a set of LoRA weights by leveraging a large bank of pre-trained adapters for the Mistral-7B-Instruct-v0.2 model. Instead of performing new gradient-based updates, our pipeline constructs adapters via lightweight combinations of existing LoRAs directly on CPU. While the resulting adapters do not match the performance of GPU-trained counterparts, they consistently outperform the base Mistral model on downstream tasks, offering a practical and accessible alternative to traditional GPU-based fine-tuning.
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。