#1010th of 14 in Learning and cookbooks
self-llm
Chinese-language tutorials for deploying and fine-tuning open LLMs on Linux
- Stars
- 32.5k
- License
- Apache-2.0
- Last commit
- Sep 2026
- Language
- Jupyter Notebook
28,828 on 24 Mar 202632,466 on 13 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A Datawhale tutorial collection, written mostly in Chinese, that walks through environment setup, local deployment and fine-tuning for 50+ open LLMs such as Qwen, GLM, InternLM, Llama and DeepSeek. Content is Jupyter notebooks and Markdown covering CLI calls, online demos, LangChain integration, LoRA, P-Tuning and distributed full fine-tuning. It also has sections for AMD ROCm, Ascend NPU and Apple M hardware.
Who it is for: Chinese-reading students learning to self-host and fine-tune open LLMs
Strengths
- Covers 50+ open models, each with its own deployment and fine-tuning tutorial
- Hardware tracks for AMD ROCm, Ascend NPU and Apple M, beyond NVIDIA
- Worked examples such as LoRA fine-tuning on Zhen Huan dialogue and an advanced-math model
- Active community project with many named contributors and Apache-2.0 license
Weaknesses
- Main README and tutorials are in Chinese; English README is a separate file
- Linux-centered; the MetaX section is marked Coming Soon
- Tutorials are tied to specific model versions and may age as models change
- No installable package or app; notebooks only, with no stated hardware requirements
What it needs
- Needs Linux, Jupyter
- Models: Qwen, GLM, InternLM, Llama, DeepSeek
Also in Learning and cookbooks
See all 14| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on curriculum for building AI systems from math to agents | 82 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 81 out of 100 |
| 3 | hello-agentsChinese-language course on building LLM agents from scratch | 76 out of 100 |
| #4 | llms-from-scratchCode for the book on building a GPT-style LLM in PyTorch | 75 out of 100 |
| #5 | ai-agents-for-beginners18-lesson course on building AI agents with Microsoft Agent Framework | 74 out of 100 |