SuperAPI AI Directory
Partner with us中文AI newsFavorites
DirectoryNews and tutorials

self-llm - An Open-Source Large Model Tutorial Launched Specifically for Chinese Developers

Author: AI小集 · Original source: AI工具集

What is self-llm

self-llm (Open-Source Large Model Usage Guide) is an open-source large model tutorial created by Datawhale specifically for domestic beginners. Based on the Linux platform, it provides full-process guidance from environment configuration to model deployment and fine-tuning, coveringLLaMA, ChatGLM and other mainstream models. The project simplifies the usage process of open-source large models, helping students and researchers get started quickly. The tutorial provides detailed tutorials for multiple models, fine-tuning methods (such as LoRA, ptuning), and application cases, suitable for learners at different levels. The project encourages community participation to jointly improve the content and promote the popularization and application of open-source large models.

Open-Source Large Model Usage Guide self-llm

Main Features of self-llm

  • Environment Configuration Guidance: Provides an environment configuration guide for open-source large models based on the Linux platform, helping users set up a basic environment suitable for running different models.
  • Model Deployment Tutorials: Covers local deployment methods for mainstream domestic and international open-source large models (such as LLaMA, ChatGLM,InternLM, etc.), including command-line invocation, online demo deployment, etc.
  • Fine-Tuning Method Guidance: Provides detailed tutorials on efficient fine-tuning methods such as full fine-tuning, LoRA fine-tuning, and ptuning, helping users customize and optimize models according to their needs.
  • Application Development Guidance: In combination with frameworks such as LangChain, guides users on how to integrate open-source large models into practical applications and build domain-specific private models.
  • Community Co-Creation and Support: Encourages users to submit issues or contribute code (PR) to jointly improve the tutorial content, forming a collaborative and supportive system for the open-source community.

Models Supported by self-llm

  • GLM-4.1-Thinking
    • GLM-4.1V-Thinking vLLM Deployment Invocation
    • GLM-4.1V-Thinking Gradio Deployment
    • GLM-4.1V-Thinking LoRA Fine-Tuning and SwanLab Visualization Records
    • GLM-4.1V-Thinking Docker Image
  • GLM-4.5-Air
    • GLM-4.5-Air vLLM Deployment Invocation
    • GLM-4.5-Air EvalScope IQ and EQ Evaluation
    • GLM-4.5-Air LoRA Fine-Tuning
    • GLM-4.5-Air Ucloud Docker Image
  • ERNIE-4.5
    • ERNIE-4.5-0.3B-PT LoRA Fine-Tuning and SwanLab Visualization Records
    • ERNIE-4.5-0.3B-PT LoRA Docker Image
  • Hunyuan-A13B-Instruct
    • Hunyuan-A13B-Instruct Model Architecture Analysis
    • Hunyuan-A13B-Instruct SGLang Deployment Invocation
    • Hunyuan-A13B-Instruct LoRA SwanLab Visualization Fine-Tuning
    • Hunyuan-A13B-Instruct LoRA Docker Image
  • Qwen3
    • Qwen3 Model Structure Analysis
    • Qwen3-8B vllm Deployment Invocation
    • Qwen3-8B Windows LMStudio Deployment Invocation
    • Qwen3-8B Evalscope IQ and EQ Evaluation
    • Qwen3-8B LoRA Fine-Tuning and SwanLab Visualization Records
    • Qwen3-30B-A3B Fine-Tuning and SwanLab Visualization Records
    • Qwen3 Think Decryption
    • Qwen3-8B Docker Image
    • Use Cases of the Qwen3-0.6B Small Model
    • Qwen3-1.7B Medical Reasoning Dialogue Fine-Tuning and SwanLab Visualization Records
    • Qwen3-8B GRPO Fine-Tuning and SwanLab Visualization
  • Kimi-VL-A3B
    • Kimi-VL-A3B Technical Report Interpretation
    • Kimi-VL-A3B-Thinking WebDemo Deployment (Web Dialogue Assistant)
  • Llama4
    • Llama4 Dialogue Assistant
    • SpatialLM
    • SpatialLM 3D Point Cloud Understanding and Object Detection Model Deployment
    • Hunyuan3D-2
    • Hunyuan3D-2 Series Model Deployment
    • Hunyuan3D-2 Series Model Code Invocation
    • Hunyuan3D-2 Series Model Gradio Deployment
    • Hunyuan3D-2 Series Model API Server
    • Hunyuan3D-2 Docker Image
  • Gemma3
    • Gemma-3-4b-it FastApi Deployment and Invocation
    • Gemma-3-4b-it ollama + open-webui Deployment
    • Gemma-3-4b-it Evalscope IQ and EQ Evaluation
    • Gemma-3-4b-it LoRA Fine-Tuning
    • Gemma-3-4b-it Docker Image
    • Gemma-3-4b-it GRPO Fine-Tuning and SwanLab Visualization
  • DeepSeek-R1-Distill
    • DeepSeek-R1-Distill-Qwen-7B FastApi Deployment and Invocation
    • DeepSeek-R1-Distill-Qwen-7B Langchain Integration
    • DeepSeek-R1-Distill-Qwen-7B WebDemo Deployment
    • DeepSeek-R1-Distill-Qwen-7B vLLM Deployment and Invocation
    • DeepSeek-R1-0528-Qwen3-8B-GRPO and SwanLab Visualization
  • MiniCPM-o-2_6
    • MiniCPM-o-2.6 FastApi Deployment and Invocation
    • MiniCPM-o-2.6 WebDemo Deployment
    • MiniCPM-o-2.6 Multimodal Speech Capabilities
    • MiniCPM-o-2.6 Visualized LaTeX_OCR LoRA Fine-Tuning
  • InternLM3
    • InternLM3-8b-instruct FastApi Deployment and Invocation
    • InternLM3-8b-instruct Langchain Integration
    • InternLM3-8b-instruct WebDemo Deployment
    • InternLM3-8b-instruct LoRA Fine-Tuning
    • InternLM3-8b-instruct o1-like Reasoning Chain Implementation
  • phi4
    • phi4 FastApi Deployment and Invocation
    • phi4 Langchain Integration
    • phi4 WebDemo Deployment
    • phi4 LoRA Fine-Tuning
    • phi4 LoRA Fine-Tuning NER Task SwanLab Visualization Recording Version
    • phi4 GRPO Fine-Tuning and SwanLab Visualization
  • Qwen2.5-Coder
    • Qwen2.5-Coder-7B-Instruct FastApi Deployment and Invocation
    • Qwen2.5-Coder-7B-Instruct Langchain Integration
    • Qwen2.5-Coder-7B-Instruct WebDemo Deployment
    • Qwen2.5-Coder-7B-Instruct vLLM Deployment
    • Qwen2.5-Coder-7B-Instruct LoRA Fine-Tuning
    • Qwen2.5-Coder-7B-Instruct LoRA Fine-Tuning SwanLab Visualization Recording Version
  • Qwen2-vl
    • Qwen2-vl-2B FastApi Deployment and Invocation
    • Qwen2-vl-2B WebDemo Deployment
    • Qwen2-vl-2B vLLM Deployment
    • Qwen2-vl-2B LoRA Fine-Tuning
    • Qwen2-vl-2B LoRA Fine-Tuning SwanLab Visualization Recording Version
    • Qwen2-vl-2B LoRA Fine-Tuning Case – LaTeXOCR
  • Qwen2.5
    • Qwen2.5-7B-Instruct FastApi Deployment and Invocation
    • Qwen2.5-7B-Instruct Langchain Integration
    • Qwen2.5-7B-Instruct vLLM Deployment and Invocation
    • Qwen2.5-7B-Instruct WebDemo Deployment
    • Qwen2.5-7B-Instruct LoRA Fine-Tuning
    • Qwen2.5-7B-Instruct o1-like Reasoning Chain Implementation
    • Qwen2.5-7B-Instruct LoRA Fine-Tuning SwanLab Visualization Recording Version
  • Apple OpenELM
    • OpenELM-3B-Instruct FastApi Deployment and Invocation
    • OpenELM-3B-Instruct LoRA Fine-Tuning
  • Llama3_1-8B-Instruct
    • Llama3_1-8B-Instruct FastApi Deployment and Invocation
    • Llama3_1-8B-Instruct Langchain Integration
    • Llama3_1-8B-Instruct WebDemo Deployment
    • Llama3_1-8B-Instruct LoRA Fine-tuning
    • Hands-on conversion of GGUF models and local deployment using Ollama
  • Gemma-2-9b-it
    • Gemma-2-9b-it FastApi Deployment and Invocation
    • Gemma-2-9b-it Langchain Integration
    • Gemma-2-9b-it WebDemo Deployment
    • Gemma-2-9b-it Peft LoRA Fine-tuning
  • Yuan2.0
    • Yuan2.0-2B FastApi Deployment and Invocation
    • Yuan2.0-2B Langchain Integration
    • Yuan2.0-2B WebDemo Deployment
    • Yuan2.0-2B vLLM Deployment and Invocation
    • Yuan2.0-2B LoRA Fine-tuning
  • Yuan2.0-M32
    • Yuan2.0-M32 FastApi Deployment and Invocation
    • Yuan2.0-M32 Langchain Integration
    • Yuan2.0-M32 WebDemo Deployment
  • DeepSeek-Coder-V2
    • DeepSeek-Coder-V2-Lite-Instruct FastApi Deployment and Invocation
    • DeepSeek-Coder-V2-L

self-llm Project Address

  • GitHub Repository：https://github.com/datawhalechina/self-llm

self-llm Application Scenarios

  • Education and Learning: Provides beginners with full-process guidance from environment setup to model fine-tuning, helping students and developers quickly master the use of open-source large models.
  • Enterprise Application Development: Helps enterprises customize and fine-tune open-source large models according to their own business needs, and develop dedicated applications such as intelligent customer service and knowledge management.
  • Personal Project Development: Supports individual developers in using open-source large models to develop projects such as intelligent writing assistants and personal intelligent assistants, improving personal productivity.
  • Research and Innovation: Provides researchers with an experimental platform to support research work such as architecture optimization and training method improvement for open-source large models.