Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Zixi, Zhang, Cheng, Gao, Xitong, Mullins, Robert D., Constantinides, George A., Zhao, Yiren
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2406.14956
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913399913316352
author Zhang, Zixi
Zhang, Cheng
Gao, Xitong
Mullins, Robert D.
Constantinides, George A.
Zhao, Yiren
author_facet Zhang, Zixi
Zhang, Cheng
Gao, Xitong
Mullins, Robert D.
Constantinides, George A.
Zhao, Yiren
contents Low-rank Adaption (LoRA) has been the de-facto parameter-efficient fine-tuning technique for large language models. We present HeteroLoRA, a light-weight search algorithm that leverages zero-cost proxies to allocate the limited LoRA trainable parameters across the model for better fine-tuned performance. In addition to the allocation for the standard LoRA-adapted models, we also demonstrate the efficacy of HeteroLoRA by performing the allocation in a more challenging search space that includes LoRA modules and LoRA-adapted shortcut connections. Experiments show that HeteroLoRA enables improvements in model performance given the same parameter budge. For example, on MRPC, we see an improvement of 1.6% in accuracy with similar training parameter budget. We will open-source our algorithm once the paper is accepted.
format Preprint
id arxiv_https___arxiv_org_abs_2406_14956
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unlocking the Global Synergies in Low-Rank Adapters
Zhang, Zixi
Zhang, Cheng
Gao, Xitong
Mullins, Robert D.
Constantinides, George A.
Zhao, Yiren
Machine Learning
Computation and Language
Low-rank Adaption (LoRA) has been the de-facto parameter-efficient fine-tuning technique for large language models. We present HeteroLoRA, a light-weight search algorithm that leverages zero-cost proxies to allocate the limited LoRA trainable parameters across the model for better fine-tuned performance. In addition to the allocation for the standard LoRA-adapted models, we also demonstrate the efficacy of HeteroLoRA by performing the allocation in a more challenging search space that includes LoRA modules and LoRA-adapted shortcut connections. Experiments show that HeteroLoRA enables improvements in model performance given the same parameter budge. For example, on MRPC, we see an improvement of 1.6% in accuracy with similar training parameter budget. We will open-source our algorithm once the paper is accepted.
title Unlocking the Global Synergies in Low-Rank Adapters
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2406.14956