Papers
arxiv:2404.10934

Shears: Unstructured Sparsity with Neural Low-rank Adapter Search

Published on Apr 16
Authors:

Abstract

Recently, several approaches successfully demonstrated that weight-sharing Neural Architecture Search (NAS) can effectively explore a search space of elastic low-rank adapters (LoRA), allowing the parameter-efficient fine-tuning (PEFT) and compression of large language models. In this paper, we introduce a novel approach called Shears, demonstrating how the integration of cost-effective sparsity and a proposed Neural Low-rank adapter Search (NLS) algorithm can further improve the efficiency of PEFT approaches. Results demonstrate the benefits of Shears compared to other methods, reaching high sparsity levels while improving or with little drop in accuracy, utilizing a single GPU for a pair of hours.

Community

Sign up or log in to comment

Models citing this paper 10

Browse 10 models citing this paper

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2404.10934 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2404.10934 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.