PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models

TL;DR

PEFT-Factory is a comprehensive, modular framework that standardizes and simplifies the process of fine-tuning large language models using various parameter-efficient methods, enhancing reproducibility and benchmarking.

Contribution

It introduces a unified, extensible platform supporting 19 PEFT methods, multiple datasets, and evaluation metrics, originating from LLaMA-Factory, with publicly available code.

Findings

Provides a stable environment for benchmarking PEFT methods.

Supports 19 PEFT methods across 12 NLP tasks.

Improves reproducibility and comparison of PEFT techniques.

Abstract

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.