JARVIS is an AI tool developed by Microsoft that connects Language Model Managers (LLMs) – people who are responsible for creating language models for machine learning models – with the machine learning community. Its goal is to facilitate communication and knowledge sharing between LLMs and ML experts. JARVIS achieves this through a system that allows LLMs to easily publish their models and receive feedback from the ML community, as well as search for existing language models and see how they are being used in various applications. JARVIS is open-source and its development is ongoing. The paper outlining the system’s architecture and evaluation can be found on arXiv. The tool is hosted on GitHub, where it is publicly available for use and contribution by developers and researchers. Overall, JARVIS fills a gap in the machine learning ecosystem by providing a platform for language model creators to connect with the broader ML community, which could lead to better language models and more effective use of such models in real-world applications.
