Awesome Chinese LLM
A curated collection of open Chinese large language models, covering base models, domain-specific fine-tunes and applications, datasets and tutorials, aimed at models that are small enough to run privately at low training cost.
Awesome Chinese LLM collects and organizes open-source Chinese large language models, focused on models that are comparatively small, deployable privately, and inexpensive to train. It covers base models, applications built by fine-tuning those bases for specific domains, datasets and tutorials.
It documents base model families such as ChatGLM, LLaMA, Baichuan, Qwen, BLOOM, Aquila, InternLM, Mixtral, Yi, DeepSeek, XVERSE and MiniMax, with details on parameter sizes, training token counts, maximum context length and commercial-use terms for each. Application entries cover domain fine-tunes for areas such as healthcare, law, finance, education and cybersecurity, along with LangChain-based applications; further sections list pretraining, supervised fine-tuning and preference datasets, training and inference frameworks, and tutorials on LLM fundamentals, prompt engineering and applied use.
The collection is community-maintained and written in Chinese, and accepts new entries through pull requests in its established format.