Deep learning models have become essential in software engineering, enabling intelligent features like image captioning and document generation. However, their popularity raises concerns about environmental impact and inefficient model selection. This paper introduces GreenRunnerGPT, a novel tool for efficiently selecting deep learning models based on specific use cases. It employs a large language model to suggest weights for quality indicators, optimizing resource utilization. The tool utilizes a multi-armed bandit framework to evaluate models against target datasets, considering tradeoffs. We demonstrate that GreenRunnerGPT is able to identify a model suited to a target use case without wasteful computations that would occur under a brute-force approach to model selection.

翻译：深度学习模型已成为软件工程中不可或缺的组成部分，能够实现图像描述、文档生成等智能化功能。然而，其广泛应用引发了关于环境影响和模型选择效率低下的担忧。本文提出GreenRunnerGPT，一种基于具体用例高效选择深度学习模型的新型工具。该工具通过大语言模型为质量指标生成权重建议，从而优化资源利用效率。其采用多臂赌博机框架，在考量性能权衡的基础上，针对目标数据集对候选模型进行评估。实验证明，与暴力穷举式模型选择方法相比，GreenRunnerGPT能够在不产生冗余计算的前提下，精准定位适用于目标应用场景的深度学习模型。