Guardado en:
Detalles Bibliográficos
Autores principales: Belanec, Robert, Srba, Ivan, Bielikova, Maria
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2512.02764
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910213490081792
author Belanec, Robert
Srba, Ivan
Bielikova, Maria
author_facet Belanec, Robert
Srba, Ivan
Bielikova, Maria
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_02764
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models
Belanec, Robert
Srba, Ivan
Bielikova, Maria
Computation and Language
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.
title PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2512.02764