arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.12408cs.LGcs.AIcs.CL
收藏

ModelGPT:释放大语言模型能力以生成定制化模型

ModelGPT: Unleashing LLM's Capabilities for Tailored Model Generation

Zhejiang University(浙江大学)

Zihao Tang, Zheqi Lv, Shengyu Zhang, Fei Wu, Kun Kuang

AI总结:

本文提出ModelGPT框架,利用大语言模型根据用户数据或任务描述快速生成定制化AI模型,比传统微调范式最多快270倍,并在NLP、CV和表格数据上验证了其有效性。

摘要:

大语言模型(LLMs)的快速发展通过自动化常规任务彻底变革了众多领域,标志着向实现通用人工智能(AGI)迈出了一步。然而,它们在满足用户多样化和特定需求以及简化普通用户对AI模型的使用方面仍存在困难。为此,我们提出了ModelGPT,这是一个新颖的框架,旨在利用大语言模型的能力,根据用户提供的数据或任务描述来确定并生成专门定制的AI模型。在给定用户需求的情况下,ModelGPT能够提供定制模型,其速度比之前的范式(例如全参数微调或LoRA微调)最多快270倍。在NLP、CV和表格数据集上的全面实验证明了我们的框架在使AI模型更易获取和更用户友好方面的有效性。我们的代码可在 https://github.com/IshiKura-a/ModelGPT 获取。

英文摘要:

The rapid advancement of Large Language Models (LLMs) has revolutionized various sectors by automating routine tasks, marking a step toward the realization of Artificial General Intelligence (AGI). However, they still struggle to accommodate the diverse and specific needs of users and simplify the utilization of AI models for the average user. In response, we propose ModelGPT, a novel framework designed to determine and generate AI models specifically tailored to the data or task descriptions provided by the user, leveraging the capabilities of LLMs. Given user requirements, ModelGPT is able to provide tailored models at most 270x faster than the previous paradigms (e.g. all-parameter or LoRA finetuning). Comprehensive experiments on NLP, CV, and Tabular datasets attest to the effectiveness of our framework in making AI models more accessible and user-friendly. Our code is available at https://github.com/IshiKura-a/ModelGPT.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑