Keep learning, at your level
Keep learning, at your level
Optional, never counted, and free. Nothing here is required, and nothing is marked. Every resource below is free to read on GitHub.
Nine open resources that go further than the course. They are grouped by level, and each one says which session it continues.
Pick one, not nine. Choose the level that describes you today, open one resource, and follow it for a week. Nine open tabs teach less than one finished lesson.
Which level are you?
| Level | You are here if… | Start with |
|---|---|---|
| Beginner | Python is still new, or AI is new to you | AI Agents for Beginners |
| Intermediate | You finish the session notebooks, and want to know how the parts work | Hands-On Large Language Models |
| Advanced | You want to build a model yourself, or run AI in production | Build a Large Language Model from Scratch |
Not sure? Start with Beginner. It moves fast if you already know it.
Beginner
AI Agents for Beginners
18 lessons from Microsoft on what an agent is, how it uses tools, and how to design one. Each lesson is short and has code.
- Continues: sessions 4 and 5, bounded tools and the agent loop
- Link: github.com/microsoft/ai-agents-for-beginners
Prompt Engineering Guide
Guides, papers and notebooks on how to write prompts, from the basics to reasoning techniques and evaluation. A good reference to keep open.
- Continues: sessions 2 and 3, the model adapter and structured outputs
- Link: github.com/dair-ai/Prompt-Engineering-Guide
LLM Course
Roadmaps and Colab notebooks that cover the whole life of an LLM application. Start with the fundamentals part. The notebooks run in Colab, so you need nothing installed.
- Continues: the whole course, as a map of where each topic fits
- Link: github.com/mlabonne/llm-course
Intermediate
Hands-On Large Language Models
The code for the O'Reilly book Hands-On Large Language Models. Practical notebooks, from tokens and embeddings to fine-tuning. The notebooks are free; the book is not needed to run them.
- Continues: sessions 6 and 7 (retrieval and embeddings), and project 01
- Link: github.com/HandsOnLLM/Hands-On-Large-Language-Models
GenAI Agents
More than 50 tutorials and implementations: agents with memory, many agents working together, and how to orchestrate them.
- Continues: sessions 8 to 11, loops, graphs, state and memory
- Link: github.com/NirDiamant/GenAI_Agents
Awesome Generative AI Guide
A curated collection: research updates, explanations of how models are built, free courses, and interview preparation.
- Continues: anything you want to go deeper on, and the job search after the course
- Link: github.com/aishwaryanr/awesome-generative-ai-guide
Advanced
Build a Large Language Model from Scratch
The code for Sebastian Raschka's book. You build a ChatGPT-like model in PyTorch, step by step: tokens, attention, pretraining, then fine-tuning.
- Continues: the embedding projector and demo 2, when you want to see what is inside the model
- Needs: comfortable Python, and some patience. A GPU helps but is not required for the early chapters.
- Link: github.com/rasbt/LLMs-from-scratch
Made With ML
How to design, build, deploy and improve an ML system that runs in production, not only in a notebook.
- Continues: session 14, deploy and operate, and the capstone
- Link: github.com/GokuMohandas/Made-With-ML
Designing Machine Learning Systems
Summaries and resources for Chip Huyen's book: architecture patterns, trade-offs, and system design for ML in production.
- Continues: session 14 and the capstone, when you design something others will use
- Link: github.com/chiphuyen/dmls-book
How to use a resource well
- Run the code, do not only read it. The same rule as this course.
- Change one thing and run it again. That is where you learn it.
- Ask the coach when a word from the course comes back:
coach("your question"). - Found something useful? Share it in the group, or add a question the coach gets wrong to gecko-ai-coach.