Modelica组件和测试用例数据集
收藏资源简介:
该数据集是为了评估大型语言模型在生成Modelica组件模型和测试用例方面的性能而构建的。数据集包含了从六个代表性库中选出的129个组件和127个测试组件,涵盖了多种类型和复杂度,用于评估生成代码的性能。这些组件和测试用例经过预处理和标准化,以适应模型训练和评估的需要。数据集旨在推进智能建模工具的发展,并支持系统建模和工程应用的研究。
This curated dataset is developed to evaluate the performance of large language models (LLMs) in generating Modelica component models and test cases. It includes 129 components and 127 test components selected from six representative Modelica libraries, covering a wide range of types and complexity levels, and serves as a benchmark to assess the performance of generated code. These components and test cases have undergone preprocessing and standardization to meet the requirements of model training and evaluation. This dataset is designed to advance the development of intelligent modeling tools and support research in system modeling and engineering applications.

- 1ModiGen: A Large Language Model-Based Workflow for Multi-Task Modelica Code Generation浙江大学 · 2025年



