Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dong, Yanjie, Zhang, Haijun, Li, Chengming, Guo, Song, Leung, Victor C. M., Hu, Xiping
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2408.10691
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916882810929152
author Dong, Yanjie
Zhang, Haijun
Li, Chengming
Guo, Song
Leung, Victor C. M.
Hu, Xiping
author_facet Dong, Yanjie
Zhang, Haijun
Li, Chengming
Guo, Song
Leung, Victor C. M.
Hu, Xiping
contents Since the release of GPT2-1.5B in 2019, the large language models (LLMs) have evolved from specialized deep models to versatile foundation models. While demonstrating remarkable zero-shot ability, the LLMs still require fine-tuning on local datasets and substantial memory for deployment over the network edges. Traditional first-order fine-tuning techniques require significant GPU memory that exceeds the capacity of mainstream hardware. Besides, the LLMs have been expanded beyond text generation to create images, audio, video, and multi-modal content, necessitating careful investigation of efficient deployment strategies for large-scale foundation models. In response to these challenges, model fine-tuning and model-compression techniques have been developed to support the sustainable growth of LLMs by reducing both operational and capital expenditures. In this work, we provide a comprehensive overview of prevalent memory-efficient fine-tuning methods for deployment at the network edge. We also review state-of-the-art literature on model compression, offering insights into the deployment of LLMs at network edges.
format Preprint
id arxiv_https___arxiv_org_abs_2408_10691
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches
Dong, Yanjie
Zhang, Haijun
Li, Chengming
Guo, Song
Leung, Victor C. M.
Hu, Xiping
Artificial Intelligence
Since the release of GPT2-1.5B in 2019, the large language models (LLMs) have evolved from specialized deep models to versatile foundation models. While demonstrating remarkable zero-shot ability, the LLMs still require fine-tuning on local datasets and substantial memory for deployment over the network edges. Traditional first-order fine-tuning techniques require significant GPU memory that exceeds the capacity of mainstream hardware. Besides, the LLMs have been expanded beyond text generation to create images, audio, video, and multi-modal content, necessitating careful investigation of efficient deployment strategies for large-scale foundation models. In response to these challenges, model fine-tuning and model-compression techniques have been developed to support the sustainable growth of LLMs by reducing both operational and capital expenditures. In this work, we provide a comprehensive overview of prevalent memory-efficient fine-tuning methods for deployment at the network edge. We also review state-of-the-art literature on model compression, offering insights into the deployment of LLMs at network edges.
title Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches
topic Artificial Intelligence
url https://arxiv.org/abs/2408.10691