datawhalechina/self-llm

Project overview

An open-source tutorial collection that helps learners configure environments, deploy, apply, and fine-tune more than 50 mainstream large language models across Linux systems and multiple hardware platforms. It targets Chinese-speaking beginners who are navigating technical barriers to using open-source models.

Project type

Model Runtime

Use cases

Chat Assistants · Learning & Education

Deployment

Refer to project documentation

License

Apache-2.0

Best for

• Educators and students seeking a localized, structured learning path for deploying, applying, and fine-tuning open-source models.
• Developers working on Linux who need deployment guidance for AMD GPU, Ascend NPU, or Apple M hardware platforms.

Key capabilities

• Provides detailed environment configuration steps tailored to different open-source model requirements on Linux.
• Guides users through deploying and using over 50 mainstream open-source models, covering command-line invocation and online demo deployment.
• Covers full-parameter and efficient fine-tuning methods including LoRA and ptuning.
• Provides environment configuration and deployment tutorials specifically for AMD GPU, Ascend NPU, and Apple M hardware platforms.
• Ships practical application examples and fine-tuned models such as Chat-Zhenhuan, Tianji for social skills, and AMChat for advanced mathematics.

Limitations and risks

• Requires a certain level of technical ability to deploy and use the models, which may present a barrier to entry for some users.

Getting started

• Setup requires following multi-step technical tutorials for Linux environment configuration and deployment. Coding ability is required.

Evidence and sources

• GitHub project description: 针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
• README: 然而，当前普通学生和用户想要使用这些大模型，需要具备一定的技术能力，才能完成模型的部署和使用。对于层出不穷又各有特色的开源 LLM，想要快速掌握一个开源 LLM 的应用方法，是一项比较有挑战的任务。
• README: ✨ 已支持 50+ 主流大语言模型 ✨
• README: 🚀 AMD GPU 平台已支持模型
• README: 🚀 昇腾Ascend NPU 平台已支持模型

Reviewed at: 2026-07-17T09:31:32Z