How datawhalechina/self-llm works
This repository is a Chinese-language learning guide and collection of tutorials for using open-source language models, rather than one integrated runtime product. Its documented learning path moves from Linux environment preparation to local model deployment and applications, then to fine-tuning. The graph preserves major documented application and training branches, with representative source paths from the supplied tree. The README describes broader tutorial coverage than the sampled files expose, so unsampled subsystems are represented at the models directory level and their internal wiring is not inferred.
Main entry points: models Model Deployment · run_app_gradio.py MLX Chat App · 05-ChatGLM3-6B接入LangChain搭建知识库助手 Knowledge Assistants · 01-DeepSeek-V4-Flash-LoRA-Inference.py Command-Line Use
Components 18
Learning Path
- Linux Environment
Model Use
- Model Deployment
models - Command-Line Use
models/DeepSeek-V4-Flash/01-DeepSeek-V4-Flash-LoRA-Inference.py - Web Demos
models/Llama4/01-Llama4-对话助手/app/app.py - Multimodal Inference
models/Qwen2-VL/06-Qwen2-VL-2B-Instruct Lora微调案例 - LaTextOCR 参考代码/inference.py - Model APIs
models/Qwen2-VL/01-Qwen2-VL-2B-Instruct FastApi 参考代码/api_server_image.py
Applications
- Knowledge Assistants
models/ChatGLM/05-ChatGLM3-6B接入LangChain搭建知识库助手 - LangChain Model Adapters
models/ChatGLM/05-ChatGLM3-6B接入LangChain搭建知识库助手/LLM.py - MLX Chat App
models_mlx/run_app_gradio.py - MLX Backends
models_mlx/modules/framework.py - Model Download
models_mlx/modules/download_model.py
Fine-Tuning
- Fine-Tuning Methods
models - LoRA Training
models/ChatGLM/06-ChatGLM3-6B-Lora微调.py - P-Tuning
models/Qwen/05-Qwen-7B-Chat Ptuning 微调.py - Distributed Training
models/MiniMax-M3/finetune/train/finetune_m3_bf16_zero3.py
Other components
- Learner
- Model Sources
- Linux Hardware
Connections 19
- Learner → Linux Environment: learns first
- Linux Environment → Model Deployment: prepares for
- Learner → Model Deployment: studies
- Model Deployment → Command-Line Use: covers
- Model Deployment → Web Demos: covers
- Model Deployment → Multimodal Inference: covers
- Model Deployment → Model APIs: covers
- Learner → Knowledge Assistants: studies
- Knowledge Assistants → LangChain Model Adapters: uses adapter
- Learner → MLX Chat App: uses
- MLX Chat App → Model Download: calls
- MLX Chat App → MLX Backends: creates backend
- Learner → Fine-Tuning Methods: studies next
- Fine-Tuning Methods → LoRA Training: covers
- Fine-Tuning Methods → P-Tuning: covers
- Fine-Tuning Methods → Distributed Training: covers
- Model Sources → Model Deployment: provides models
- Linux Hardware → Model Deployment: runs models
- Linux Hardware → Fine-Tuning Methods: supports training