datawhalechina/self-llm

《开源大模型食用指南》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

59
/ 100
Established

This guide helps students, researchers, and anyone interested in large language models (LLMs) to quickly get started. It provides step-by-step instructions on setting up the necessary environment, deploying various open-source LLMs like LLaMA and ChatGLM, and fine-tuning them for specific tasks. The outcome is a personalized, domain-specific LLM that can be used for various applications without relying on external APIs.

28,927 stars. Actively maintained with 2 commits in the last 30 days.

Use this if you want to deploy and customize open-source large language models on your own Linux system for long-term, low-cost, and specialized applications.

Not ideal if you prefer using commercial API-based LLM services or if you lack a Linux environment and basic command-line familiarity.

AI-learning NLP-customization academic-research AI-application-development personalized-AI
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

28,927

Forks

2,857

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Mar 08, 2026

Commits (30d)

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/datawhalechina/self-llm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.