YuzuAI is a community-driven organization focused on advancing Japanese Large Language Models (LLMs) through open-source research and development. By fostering collaboration among enthusiasts, researchers, and developers, YuzuAI aims to stimulate the growth and accessibility of Japanese LLMs.
The organization provides resources such as the Rakuda benchmark, which evaluates Japanese LLMs based on their responses to open-ended questions about Japanese topics.
In addition to benchmarking tools, YuzuAI maintains an active presence on GitHub, offering repositories like ShinRakuda—a comprehensive framework for evaluating and benchmarking Japanese LLMs.
This framework provides researchers and developers with a flexible toolkit for assessing LLM performance across diverse datasets.
