How wenfengcode/dive-into-llms works
This repository is a free, hands-on Chinese tutorial series for learning large-language-model techniques through chapter guides and coding notebooks. The learner workflow is to use the repository overview to choose a topic, study its chapter materials, and practice with that chapter’s notebook. The chapters cover model training and inference, editing and reasoning, multimodal and agent applications, and safety topics. README documentation also describes a separate Ascend-based course hosted by the Ascend community. Notebook implementation details were not sampled, so the graph shows documented topic and learning relationships rather than internal execution flow.
Main entry points: README.md Tutorial overview · dive-tuning.ipynb Fine-tuning and deployment · dive-prompting.ipynb Prompting and reasoning · dive_edit.ipynb Knowledge editing
Components 15
Model foundations
- Fine-tuning and deployment
documents/chapter1/dive-tuning.ipynb - Prompting and reasoning
documents/chapter2/dive-prompting.ipynb
Model methods
- Knowledge editing
documents/chapter3/dive_edit.ipynb - Math reasoning
documents/chapter4/sft_math.ipynb - Model watermarking
documents/chapter5/watermark.ipynb - LLM steganography
documents/chapter7/llm_stega.ipynb
Applications
- Multimodal models
documents/chapter8/mllms.ipynb - GUI agents
documents/chapter9/GUIagent.ipynb
Safety and alignment
- Jailbreak attacks
documents/chapter6/dive-jailbreak.ipynb - Agent safety
documents/chapter10/agent.ipynb - RLHF safety alignment
documents/chapter11/RLHF.ipynb
Other components
- Learner
- Tutorial overview
README.md - Practical LLM skills
- Ascend course
Connections 24
- Learner → Tutorial overview: opens
- Tutorial overview → Fine-tuning and deployment: links
- Tutorial overview → Prompting and reasoning: links
- Tutorial overview → Knowledge editing: links
- Tutorial overview → Math reasoning: links
- Tutorial overview → Model watermarking: links
- Tutorial overview → Jailbreak attacks: links
- Tutorial overview → LLM steganography: links
- Tutorial overview → Multimodal models: links
- Tutorial overview → GUI agents: links
- Tutorial overview → Agent safety: links
- Tutorial overview → RLHF safety alignment: links
- Fine-tuning and deployment → Practical LLM skills: practices
- Prompting and reasoning → Practical LLM skills: practices
- Knowledge editing → Practical LLM skills: practices
- Math reasoning → Practical LLM skills: practices
- Model watermarking → Practical LLM skills: practices
- Jailbreak attacks → Practical LLM skills: practices
- LLM steganography → Practical LLM skills: practices
- Multimodal models → Practical LLM skills: practices
- GUI agents → Practical LLM skills: practices
- Agent safety → Practical LLM skills: practices
- RLHF safety alignment → Practical LLM skills: practices
- Tutorial overview → Ascend course: announces