ModelGPT: Unleashing LLM's Capabilities for Tailored Model Generation

TL;DR

ModelGPT is a framework that uses large language models to generate customized AI models quickly, making AI more accessible and adaptable to specific user needs across various data domains.

Contribution

We introduce ModelGPT, a novel LLM-based framework that generates tailored AI models at significantly faster speeds than traditional fine-tuning methods.

Findings

Achieves up to 270x faster model generation.

Effective across NLP, CV, and Tabular datasets.

Enhances accessibility and user-friendliness of AI models.

Abstract

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.