Zhikai Wu
2023
ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models
Chenliang Li
|
He Chen
|
Ming Yan
|
Weizhou Shen
|
Haiyang Xu
|
Zhikai Wu
|
Zhicheng Zhang
|
Wenmeng Zhou
|
Yingda Chen
|
Chen Cheng
|
Hongzhu Shi
|
Ji Zhang
|
Fei Huang
|
Jingren Zhou
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Large language models (LLMs) have recently demonstrated remarkable capabilities to comprehend human intentions, engage in reasoning, and design planning-like behavior. To further unleash the power of LLMs to accomplish complex tasks, there is a growing trend to build agent frameworks that equips LLMs, such as ChatGPT, with tool-use abilities to connect with massive external APIs. In this work, we introduce ModelScope-Agent, a general and customizable agent framework for real-world applications, based on open-source LLMs as controllers. It provides a user-friendly system library, with a customizable engine design to support model training on multiple open-source LLMs, while also enabling seamless integration with both model APIs and common APIs in a unified way. To equip the LLMs with tool-use abilities, a comprehensive framework has been proposed spanning tool-use data collection, tool retrieval, tool registration, memory control, customized model training, and evaluation for practical real-world applications. Finally, we showcase ModelScopeGPT, a real-world intelligent assistant of ModelScope Community based on the ModelScope-Agent framework, which is able to connect open-source LLMs with more than 1000 public AI models and localized community knowledge in ModelScope. The ModelScope-Agent online demo, library are now publicly available.
Search
Co-authors
- Chenliang Li 1
- He Chen 1
- Ming Yan 1
- Weizhou Shen 1
- Haiyang Xu 1
- show all...