# 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

Repository: https://github.com/datawhalechina/self-llm
Canonical: https://ross.abutalabs.com/products/self-llm
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: llm, chatglm, internlm2, llama3, lora, minicpm, qwen, qwen1-5, chatglm3, gemma-2b-it, glm-4, qwen2, q-wen
Last push: 2026-08-26T06:33:41+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 35, longevity 73
- inputs: {"age_days": 1022, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 31927, forks 3101 (observed 2026-08-28T04:11:57.286227+00:00)

## What it is
A Chinese-language open-source tutorial guide (Datawhale) for deploying, using, and fine-tuning open-source large language models and multimodal models on Linux. It covers environment setup, local deployment of models like Qwen, ChatGLM, LLaMA, and InternLM, plus full-parameter and LoRA fine-tuning.

## Use cases
- learn to deploy open-source LLMs locally on Linux
- fine-tune an LLM with LoRA on my own data
- set up the environment for running Qwen or ChatGLM
- build a chatbot fine-tuned on custom character dialogue
- find a beginner-friendly Chinese LLM tutorial
- deploy an open-source multimodal model
- integrate a local LLM with LangChain

## When to choose
- you are a Chinese-speaking beginner wanting step-by-step LLM deployment and fine-tuning guides
- you want free, low-cost local LLM usage without paid APIs
- you need tutorials covering many mainstream open-source models in one place

## When to avoid
- you need production-grade deployment tooling rather than tutorials
- you work primarily on Windows or macOS without Linux access
- you want deep theoretical training-from-scratch content rather than practical usage

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, llm-training, rag, prompt-engineering
- domain: large-language-models, tutorials, machine-learning
- platform: python
- tags: open-source-llm, lora-fine-tuning, chinese-tutorial, model-deployment, datawhale, jupyter-notebooks, multimodal-models, natural-language-processing, linux, gpu

## Member repositories
- datawhalechina/self-llm (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:57.286227+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:52:13.156986+00:00, confidence not recorded.
  - readme: https://github.com/datawhalechina/self-llm (fetched 2026-08-28T04:11:57.286227+00:00, sha 0bbfdf4e1d14)
- Data as of 2026-08-30T08:39:29.467469+00:00.