@Jolyne_AI: I found a solid hands-on tutorial for large language models on GitHub: the "Hands-On Large Model Series." It takes you from zero to mastering the entire tech stack. Using a combination of videos, documents, and code, it links key capabilities like fine-tuning, deployment, RAG, and Agent into a reproducible learning path — each knowledge point can be directly practiced...
Summary
Recommend the "Hands-on Large Model Series" tutorial on GitHub, which systematically explains practical techniques such as fine-tuning, deployment, RAG, and Agent through videos, documents, and code, suitable for AI developers to improve their engineering skills.
I found a solid hands-on tutorial for large models on GitHub: the "Hands-on Large Model Series", which takes you from zero to mastering the full technical stack.
It combines "video + documentation + code" to connect key capabilities such as fine-tuning, deployment, RAG, and Agent into a reproducible learning path: every knowledge point can be practiced directly, and you can apply it to real projects right after learning.
GitHub: http://github.com/echonoshy/cgft-llm…
You will learn:
- Large model fine-tuning and deployment: hands-on practice with mainstream tools like llama-factory, llama.cpp, vllm
- RAG tech stack: retrieval-augmented generation solutions from llama-index to graph-rag, from setup to optimization
- Agent development: function calling, workflow design – build usable agents step by step
- Engineering workflows: from data annotation to production delivery – a complete project pipeline without missing links
- Interview guidance: algorithm engineering roadmap + interview tips to avoid detours
- Creative projects: multi-person podcast tools, voice swapping engines, and other practical applications to produce showcase-worthy work
Each topic comes with clear documentation and supporting code, ideal for AI developers who want to systematically improve their practical large model skills and truly build working systems.
View Cached Full Text
Cached at: 07/03/26, 04:29 AM
I found a very solid hands-on tutorial for large language models on GitHub: “Hands-On LLM Series,” guiding you from scratch through the entire tech stack. It combines “video + documentation + code” to link key capabilities like fine-tuning, deployment, RAG, and Agent into a reproducible learning path—each knowledge point can be directly practiced, and after learning, you can apply it to real projects.
GitHub: http://github.com/echonoshy/cgft-llm
You will learn:
- LLM fine-tuning and deployment: Practical walkthroughs with mainstream tools like llama-factory, llama.cpp, vllm
- RAG tech stack: Retrieval-augmented generation solutions like llama-index, graph-rag, from setup to optimization
- Agent development: function calling, workflow design, step-by-step to build usable agents
- Engineering workflow: From data annotation to deployment and delivery, complete project pipeline with no missing links
- Interview guidance: Algorithm engineer roadmap + interview tips to avoid detours
- Creative projects: Practical applications like multi-person podcast tool, voice changing engine, creating showcase-ready works
Each topic comes with clear documentation and supporting code, suitable for AI developers who want to systematically improve their practical LLM skills and truly implement the technology.
📑 Quick Navigation
- 1. Agent System
- 2. Core LLM Technologies
- 3. Hands-on Open Source Contribution
- 4. Module Knowledge Series
- 5. Offbeat AI Projects
- 6. Bonus Content
📒 1. Agent System
Exploring Agent architecture design and system deployment, latest ongoing series…
| No. | Project | Code & Docs | Video Tutorial | Duration |
|---|---|---|---|---|
| 3 | User Sandbox Agent System | [Docs][ref_agent_3_doc] | [![bilibili][img_agent_3_bili]][ref_agent_3_bili] [![youtube][img_agent_3_yt]][ref_agent_3_yt] | 18:52 |
| 2 | AI Memory and Context | [Docs][ref_agent_2_doc] | [![bilibili][img_agent_2_bili]][ref_agent_2_bili] [![youtube][img_agent_2_yt]][ref_agent_2_yt] | 26:43 |
| 1 | Agent Service Architecture Design | [Docs][ref_agent_1_doc] | [![bilibili][img_agent_1_bili]][ref_agent_1_bili] [![youtube][img_agent_1_yt]][ref_agent_1_yt] | 7:32 |
💡 2. Core LLM Technologies
Covering core practices: LLM fine-tuning, deployment, RAG, workflows, etc.
| No. | Project | Code & Docs | Video Tutorial | Duration |
|---|---|---|---|---|
| 21 | fastmcp: Implementing MCP Server and Client | Docs | [![bilibili][img_llm_21_bili]][ref_llm_21_bili] [![youtube][img_llm_21_yt]][ref_llm_21_yt] | 26:01 |
| 20 | Langfuse: LLM Service Monitoring Platform | [Docs][ref_llm_20_doc] | [![bilibili][img_llm_20_bili]][ref_llm_20_bili] [![youtube][img_llm_20_yt]][ref_llm_20_yt] | 26:15 |
| 19 | Building an Efficient RAG Knowledge Base | [Docs][ref_llm_19_doc] | [![bilibili][img_llm_19_bili]][ref_llm_19_bili] [![youtube][img_llm_19_yt]][ref_llm_19_yt] | 37:41 |
Click to expand and view previous episodes 1-18
| No. | Project | Code & Docs | Video Tutorial | Duration |
|---|---|---|---|---|
| 18 | Milvus Vector Database | [Docs][ref_llm_18_doc] | [![bilibili][img_llm_18_bili]][ref_llm_18_bili] [![youtube][img_llm_18_yt]][ref_llm_18_yt] | 28:13 |
| 17 | Tool-call Principle and Minimal browser-use Implementation | [Docs][ref_llm_17_doc] | [![bilibili][img_llm_17_bili]][ref_llm_17_bili] [![youtube][img_llm_17_yt]][ref_llm_17_yt] | 14:47 |
| 16 | DeepSeek-R1 Model Fine-tuning and Training Data Construction | [Docs][ref_llm_16_doc] | [![bilibili][img_llm_16_bili]][ref_llm_16_bili] [![youtube][img_llm_16_yt]][ref_llm_16_yt] | 14:01 |
| 15 | RPA Automation with LLM Workflow | [Docs][ref_llm_15_doc] | [![bilibili][img_llm_15_bili]][ref_llm_15_bili] [![youtube][img_llm_15_yt]][ref_llm_15_yt] | 13:20 |
| 14 | Dify: Implementing Agent and LLM Workflow | [Docs][ref_llm_14_doc] | [![bilibili][img_llm_14_bili]][ref_llm_14_bili] [![youtube][img_llm_14_yt]][ref_llm_14_yt] | 59:23 |
| 13 | AI Algorithm Project Development Process and Examples | [Docs][ref_llm_13_doc] | [![bilibili][img_llm_13_bili]][ref_llm_13_bili] [![youtube][img_llm_13_yt]][ref_llm_13_yt] | 34:43 |
| 12 | AI Annotation Process and Label Studio Framework | [Docs][ref_llm_12_doc] | [![bilibili][img_llm_12_bili]][ref_llm_12_bili] [![youtube][img_llm_12_yt]][ref_llm_12_yt] | 20:00 |
| 11 | Non-technical Q&A for LLM Algorithm Positions | [Docs][ref_llm_11_doc] | [![bilibili][img_llm_11_bili]][ref_llm_11_bili] [![youtube][img_llm_11_yt]][ref_llm_11_yt] | 16:00 |
| 10 | LLM Learning Path and Interview | [Docs][ref_llm_10_doc] | [![bilibili][img_llm_10_bili]][ref_llm_10_bili] [![youtube][img_llm_10_yt]][ref_llm_10_yt] | 25:01 |
| 9 | Function Calling: Auto-send Email | [Docs][ref_llm_09_doc] | [![bilibili][img_llm_09_bili]][ref_llm_09_bili] [![youtube][img_llm_09_yt]][ref_llm_09_yt] | 23:10 |
| 8 | mkdocs + Read the Docs: Deploy Project Documentation | [Docs][ref_llm_08_doc] | [![bilibili][img_llm_08_bili]][ref_llm_08_bili] [![youtube][img_llm_08_yt]][ref_llm_08_yt] | 11:25 |
| 7 | Graph-RAG Local Deployment | [Docs][ref_llm_07_doc] | [![bilibili][img_llm_07_bili]][ref_llm_07_bili] [![youtube][img_llm_07_yt]][ref_llm_07_yt] | 23:23 |
| 6 | LlamaIndex: Implementing RAG | [Docs][ref_llm_06_doc] | [![bilibili][img_llm_06_bili]][ref_llm_06_bili] [![youtube][img_llm_06_yt]][ref_llm_06_yt] | 21:48 |
| 5 | vLLM Deployment and Paged Attention | [Docs][ref_llm_05_doc] | [![bilibili][img_llm_05_bili]][ref_llm_05_bili] [![youtube][img_llm_05_yt]][ref_llm_05_yt] | 40:28 |
| 4 | Ollama LLM Deployment Tool Introduction | [Docs][ref_llm_04_doc] | [![bilibili][img_llm_04_bili]][ref_llm_04_bili] [![youtube][img_llm_04_yt]][ref_llm_04_yt] | 21:28 |
| 3 | llama.cpp: Lightweight Deployment and Quantization | [Docs][ref_llm_03_doc] | [![bilibili][img_llm_03_bili]][ref_llm_03_bili] [![youtube][img_llm_03_yt]][ref_llm_03_yt] | 46:37 |
| 2 | Training Data Preparation and Fine-tuning Optimization Tips | [Docs][ref_llm_02_doc] | [![bilibili][img_llm_02_bili]][ref_llm_02_bili] [![youtube][img_llm_02_yt]][ref_llm_02_yt] | 20:13 |
| 1 | Using Llama-Factory to Fine-tune Llama 3 | [Docs][ref_llm_01_doc] | [![bilibili][img_llm_01_bili]][ref_llm_01_bili] [![youtube][img_llm_01_yt]][ref_llm_01_yt] | 35:28 |
🛠️ 3. Hands-on Open Source Contribution
Mainly covering open source project standards.
| No. | Project | Code & Docs | Video Tutorial | Duration |
|---|---|---|---|---|
| 4 | Code Testing: pytest | [Docs][ref_opensource_4_doc] | [![bilibili][img_opensource_4_bili]][ref_opensource_4_bili] [![youtube][img_opensource_4_yt]][ref_opensource_4_yt] | 11:21 |
| 3 | Code Commit Check: pre-commit | [Docs][ref_opensource_3_doc] | [![bilibili][img_opensource_3_bili]][ref_opensource_3_bili] [![youtube][img_opensource_3_yt]][ref_opensource_3_yt] | 11:21 |
| 2 | Python Engineering Practice · Code Style: ruff | [Docs][ref_opensource_2_doc] | [![bilibili][img_opensource_2_bili]][ref_opensource_2_bili] [![youtube][img_opensource_2_yt]][ref_opensource_2_yt] | 21:50 |
| 1 | Python Engineering Practice · Dependency Management: uv | [Docs][ref_opensource_1_doc] | [![bilibili][img_opensource_1_bili]][ref_opensource_1_bili] [![youtube][img_opensource_1_yt]][ref_opensource_1_yt] | 24:11 |
📦 4. Module Knowledge Series
Each topic is covered in multiple videos sharing the same link for parts.
| No. | Project | Code & Docs | Video Tutorial | Duration |
|---|---|---|---|---|
| 3 | Docker Container Deployment (Completed) | [Docs][ref_module_3_doc] | [![bilibili][img_module_3_bili]][ref_module_3_bili] [![youtube][img_module_3_yt]][ref_module_3_yt] | 62:59 |
| 2 | Gradio: Building and Sharing AI Apps with Python (Completed) | [Docs][ref_module_2_doc] | [![bilibili][img_module_2_bili]][ref_module_2_bili] [![youtube][img_module_2_yt]][ref_module_2_yt] | 70:51 |
| 1 | Kaggle LLM Competition Series (Updated to Episode 01) | [Docs][ref_module_1_doc] | [![bilibili][img_module_1_bili]][ref_module_1_bili] [![youtube][img_module_1_yt]][ref_module_1_yt] | 25:41 |
🚀 5. Offbeat AI Projects
Turning wild ideas into AI projects.
| No. | Project | Code & Docs | Video Tutorial | Duration |
|---|---|---|---|---|
| 3 | Tracer: LLM + WeChat Automated News Bot | [tracer][ref_project_3_doc] | [![bilibili][img_project_3_bili]][ref_project_3_bili] [![youtube][img_project_3_yt]][ref_project_3_yt] | 15:11 |
| 2 | TingShu: Voice Changing Engine - Read Autobiography with Author’s Voice | [tingshu][ref_project_2_doc] | [![bilibili][img_project_2_bili]][ref_project_2_bili] [![youtube][img_project_2_yt]][ref_project_2_yt] | 4:16 |
| 1 | D.Va: End-to-end Multi-person Podcast Tool Optimized on DeepSeek | [d.va][ref_project_1_doc] | [![bilibili][img_project_1_bili]][ref_project_1_bili] [![youtube][img_project_1_yt]][ref_project_1_yt] | 13:42 |
🎈 6. Bonus Content
A miscellaneous collection of techniques.
| No. | Project | Code & Docs | Video Tutorial | Duration |
|---|---|---|---|---|
| 1 | Bilibili Dynamic Repost Lottery | [Docs][ref_extra_1_doc] | [![bilibili][img_extra_1_bili]][ref_extra_1_bili] [![youtube][img_extra_1_yt]][ref_extra_1_yt] | 4:40 |
Similar Articles
@XAMTO_AI: Stop bookmarking those flashy but useless AI tutorials. This 'Hands-On Large Models' is what you really need—open source, free, and code that runs. The book covers 12 chapters, guiding you step by step through the complete workflow of deploying large models: ① Language Model Basics ② Prompt Engineering ③ Semantic Search ④ Model Fine-Tuning ⑤ Multimodal…
Recommend an open-source free tutorial 'Hands-On Large Models', covering 12 chapters including language model basics, prompt engineering, semantic search, model fine-tuning, multimodal applications, etc. All code can be run directly in Colab.
@wsl8297: Sharing an easy-to-read open-source book 'Foundations of Large Models'. From an introduction to large language models to architectural evolution, then to key technologies such as Prompt engineering, parameter-efficient fine-tuning, model editing, retrieval-augmented generation (RAG), all in one book. GitHub: https://github.com/ZJU-LLMs/…
The Zhejiang University team open-sourced an easy-to-understand textbook on large models 'Foundations of Large Models', covering from architectural evolution to key technologies like RAG, accompanied by the Agent-Kernel multi-agent framework.
@Jolyne_AI: An open-source hands-on book: "Hands-On Large Language Models". The book has 12 chapters, progressing from language model fundamentals to prompt engineering, semantic search, model fine-tuning, and multimodal applications, covering the key paths to deploying large models in practice. GitHub: h…
An open-source hands-on book "Hands-On Large Language Models", with 12 chapters covering language model fundamentals, prompt engineering, semantic search, model fine-tuning, and multimodal applications. It provides runnable code examples, ideal for practical learning.
@NFTCPS: Brothers, doing AI without large models is like doing nothing! Today I have to recommend an open-source masterpiece 'Foundations of LLMs' to you. Don't wait, just read it! This book doesn't beat around the bush—it goes deep from the start! From getting started with large language models to architectural evolution, and then it breaks down Prompt engineering, parameter-efficient fine-tuning, model editing, RAG (Retrieval-Augmented Generation) and other hardcore techniques in one go—a one-stop service.
This article promotes the open-source book 'Foundations of LLMs', which systematically explains knowledge about large language models, and introduces the multi-agent development framework Agent-Kernel.
@FakeMaidenMaker: Folks, we've dug up another AI engineering treasure: Hands-On-AI-Engineering. Just open-sourced, it already hit 2.3K stars. One repo stuffed with over 50 real AI projects that you can run directly. The most practical part is it doesn't talk about vague theories; each project is a complete little…
Recommends the freshly open-sourced GitHub repo Hands-On-AI-Engineering with 2.3K stars, containing over 50 runnable AI projects covering RAG, AI agent, OCR, and more. Each project provides full code and instructions, suitable for hands-on learning.