统一管理大模型参数高效微调方法，提升可复现性与对比效率。
PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models
- 模块化框架支持19种主流及自定义参数高效微调方法
- 内置27个数据集覆盖12类任务，提供标准与专属评估指标
- 基于LLaMA-Factory衍生，开箱即用，适合研究与工程落地
参数高效微调（PEFT）方法应对大型语言模型日益增长的规模。当前许多新提出的PEFT方法在复现、部署或相互比较时存在困难。为此，我们提出PEFT-Factory，一个统一的框架，用于使用现成和自定义的PEFT方法对自回归大语言模型进行高效微调。其模块化设计支持扩展性，原生提供19种代表性PEFT方法、27个分类与文本生成数据集，覆盖12项任务，并包含标准与专用于PEFT的评估指标。由此，PEFT-Factory提供了一个即用、可控且稳定的环境，提升了PEFT方法的可复现性与基准测试能力。该框架是源自流行的LLaMA-Factory的下游工具，公开可用：https://github.com/kinit-sk/PEFT-Factory。
原文摘要 · Abstract (English)
Parameter-Efficient Fine-Tuning (PEFT) methods address the increasing size of Large Language Models (LLMs). Currently, many newly introduced PEFT methods are challenging to replicate, deploy, or compare with one another. To address this, we introduce PEFT-Factory, a unified framework for efficient fine-tuning LLMs using both off-the-shelf and custom PEFT methods. While its modular design supports extensibility, it natively provides a representative set of 19 PEFT methods, 27 classification and text generation datasets addressing 12 tasks, and both standard and PEFT-specific evaluation metrics. As a result, PEFT-Factory provides a ready-to-use, controlled, and stable environment, improving replicability and benchmarking of PEFT methods. PEFT-Factory is a downstream framework that originates from the popular LLaMA-Factory, and is publicly available at https://github.com/kinit-sk/PEFT-Factory.
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。