FashionGPT: LLM instruction fine-tuning with multiple LoRA-adapter fusion

We present FashionGPT, a series of fine-tuned Large Language Models (LLMs) which demonstrate outstanding performance and stand at first place in HuggingFace Open LLM Leaderboard twice. In contrast to conventional dataset fusion fine-tuning, we propose a novel instruction fine-tuning paradigm, called...

Full description

Saved in:
Bibliographic Details
Published in:Knowledge-based systems 2024-09, Vol.299, p.112043, Article 112043
Main Authors: Gao, Dehong, Ma, Yufei, Liu, Sen, Song, Mengfei, Jin, Linbo, Jiang, Wen, Wang, Xin, Ning, Wei, Yu, Shanqing, Xuan, Qi, Cai, Xiaoyan, Yang, Libin
Format: Article
Language:English
Subjects:
Instruction fine-tuning
Large language model
LoRA-adapter fusion
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present FashionGPT, a series of fine-tuned Large Language Models (LLMs) which demonstrate outstanding performance and stand at first place in HuggingFace Open LLM Leaderboard twice. In contrast to conventional dataset fusion fine-tuning, we propose a novel instruction fine-tuning paradigm, called multiple LoRA-adapter fusion fine-tuning. This paradigm involves fine-tuning multiple independent LoRA-adapters based on distinct datasets, which are subsequently fused using learnable weights to create a versatile large language model. Extensive experiments demonstrate that the LLMs fine-tuned with the LoRA-adapter fusion approaches outperform those fine-tuned with the dataset fusion approaches. The FashionGPT series is released in https://huggingface.co/ICBU-NPU/ and only for research use.
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2024.112043