--- title: README emoji: ๐ŸŒŸ colorFrom: yellow colorTo: purple sdk: static pinned: true --- # About Twinkle AI ![banner-twinkle-hf](https://cdn-uploads.huggingface.co/production/uploads/618dc56cbc345ca7bf95f3cd/RW1z8a7_kxktdllwEoh3N.jpeg) ๐ŸŽฎ [Discord](https://discord.gg/Cx737yw4ed) | ๐Ÿ˜บ [GitHub](https://github.com/ai-twinkle) | ๐Ÿค— [Hugging Face](https://huggingface.co/twinkle-ai) | ๐Ÿ”— [Linkedin](https://www.linkedin.com/company/twinkle-ai/) ๐ŸŒŸ **Twinkle AI** is a Traditional Chinese language model research community founded in late 2024. Starting with the open-source LLaMA models, we are gradually building practical technologies tailored for Traditional Chinese. Our community is made up of people from all walks of life, united by a shared passion for model training. From collecting Traditional Chinese corpora to training language models, we are committed to open-sourcing both our datasets and our models. Our mission is to promote knowledge of large language model training through real-world practices. By embracing openness and collaboration, we aim to advance Taiwanโ€™s development in the field of generative AI. ๐Ÿ‘‹ Join our [Discord](https://discord.gg/Cx737yw4ed) to connect and collaborate with the community! ### Featured Projects - ๐Ÿ“Š **[Twinkle Eval](https://github.com/ai-twinkle/Eval)**: A fast and accurate AI evaluation tool that uses parallel and randomized testing methods to provide objective performance analysis and stability assessments. It supports various commonly used benchmark datasets. - ๐Ÿ“ˆ **[Eval Analyzer](https://github.com/ai-twinkle/eval-analyzer)**: A comprehensive visualization and analysis tool designed to interpret evaluation logs, providing deep insights into model performance through granular error tracking and comparative reporting.