# wenfengcode/dive-into-llms architecture

> Architecture diagram of the GitHub repository wenfengcode/dive-into-llms, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-29). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/wenfengcode/dive-into-llms
- Repository: https://github.com/wenfengcode/dive-into-llms

## Overview

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`](https://github.com/wenfengcode/dive-into-llms/blob/main/README.md) (Tutorial overview), [`documents/chapter1/dive-tuning.ipynb`](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter1/dive-tuning.ipynb) (Fine-tuning and deployment), [`documents/chapter2/dive-prompting.ipynb`](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter2/dive-prompting.ipynb) (Prompting and reasoning), [`documents/chapter3/dive_edit.ipynb`](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter3/dive_edit.ipynb) (Knowledge editing)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_foundations["Model foundations"]
  node_training["Fine-tuning and deployment<br/>[dive-tuning.ipynb]"]
  node_prompting["Prompting and reasoning"]
end

subgraph group_methods["Model methods"]
  node_editing["Knowledge editing<br/>[dive_edit.ipynb]"]
  node_math["Math reasoning<br/>[sft_math.ipynb]"]
  node_watermark["Model watermarking<br/>[watermark.ipynb]"]
  node_steganography["LLM steganography<br/>[llm_stega.ipynb]"]
end

subgraph group_applications["Applications"]
  node_multimodal["Multimodal models<br/>[mllms.ipynb]"]
  node_guiagent["GUI agents<br/>[GUIagent.ipynb]"]
end

subgraph group_safety["Safety and alignment"]
  node_jailbreak["Jailbreak attacks"]
  node_agentsafety["Agent safety<br/>[agent.ipynb]"]
  node_rlhf["RLHF safety alignment<br/>[RLHF.ipynb]"]
end

node_learner(("Learner"))
node_overview["Tutorial overview<br/>[README.md]"]
node_learning(("Practical LLM skills"))
node_ascend(("Ascend course"))

node_learner -->|"opens"| node_overview
node_overview -->|"links"| node_training
node_overview -->|"links"| node_prompting
node_overview -->|"links"| node_editing
node_overview -->|"links"| node_math
node_overview -->|"links"| node_watermark
node_overview -->|"links"| node_jailbreak
node_overview -->|"links"| node_steganography
node_overview -->|"links"| node_multimodal
node_overview -->|"links"| node_guiagent
node_overview -->|"links"| node_agentsafety
node_overview -->|"links"| node_rlhf
node_training -->|"practices"| node_learning
node_prompting -->|"practices"| node_learning
node_editing -->|"practices"| node_learning
node_math -->|"practices"| node_learning
node_watermark -->|"practices"| node_learning
node_jailbreak -->|"practices"| node_learning
node_steganography -->|"practices"| node_learning
node_multimodal -->|"practices"| node_learning
node_guiagent -->|"practices"| node_learning
node_agentsafety -->|"practices"| node_learning
node_rlhf -->|"practices"| node_learning
node_overview -.->|"announces"| node_ascend

click node_overview "https://github.com/wenfengcode/dive-into-llms/blob/main/README.md"
click node_training "https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter1/dive-tuning.ipynb"
click node_prompting "https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter2/dive-prompting.ipynb"
click node_editing "https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter3/dive_edit.ipynb"
click node_math "https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter4/sft_math.ipynb"
click node_watermark "https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter5/watermark.ipynb"
click node_steganography "https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter7/llm_stega.ipynb"
click node_multimodal "https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter8/mllms.ipynb"
click node_guiagent "https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter9/GUIagent.ipynb"
click node_jailbreak "https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter6/dive-jailbreak.ipynb"
click node_agentsafety "https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter10/agent.ipynb"
click node_rlhf "https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter11/RLHF.ipynb"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_training,node_prompting,node_overview toneBlue
class node_editing,node_math,node_watermark,node_steganography toneAmber
class node_multimodal,node_guiagent toneMint
class node_jailbreak,node_agentsafety,node_rlhf toneRose
class node_learner,node_learning,node_ascend toneIndigo
```

## Components

### Model foundations

- [Fine-tuning and deployment](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter1/dive-tuning.ipynb): `documents/chapter1/dive-tuning.ipynb`
- [Prompting and reasoning](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter2/dive-prompting.ipynb): `documents/chapter2/dive-prompting.ipynb`

### Model methods

- [Knowledge editing](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter3/dive_edit.ipynb): `documents/chapter3/dive_edit.ipynb`
- [Math reasoning](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter4/sft_math.ipynb): `documents/chapter4/sft_math.ipynb`
- [Model watermarking](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter5/watermark.ipynb): `documents/chapter5/watermark.ipynb`
- [LLM steganography](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter7/llm_stega.ipynb): `documents/chapter7/llm_stega.ipynb`

### Applications

- [Multimodal models](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter8/mllms.ipynb): `documents/chapter8/mllms.ipynb`
- [GUI agents](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter9/GUIagent.ipynb): `documents/chapter9/GUIagent.ipynb`

### Safety and alignment

- [Jailbreak attacks](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter6/dive-jailbreak.ipynb): `documents/chapter6/dive-jailbreak.ipynb`
- [Agent safety](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter10/agent.ipynb): `documents/chapter10/agent.ipynb`
- [RLHF safety alignment](https://github.com/wenfengcode/dive-into-llms/blob/main/documents/chapter11/RLHF.ipynb): `documents/chapter11/RLHF.ipynb`

### Other components

- **Learner**
- [Tutorial overview](https://github.com/wenfengcode/dive-into-llms/blob/main/README.md): `README.md`
- **Practical LLM skills**
- **Ascend course**

## Connections

- 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