Hands-on guides for running AI models on your own hardware, plus a curated set of external courses and articles for learning the concepts behind modern AI systems, organized from beginner to advanced.
In-repo, step-by-step guides maintained as part of this project.
- How to run LLMs on your machine — Deploy and operate large language models on local hardware, with paths for three skill levels: beginner, intermediate, and expert.
- How to use LLMs in Coding — Integrate LLMs into your coding workflow, in the editor and on the command line.
- How to run Image Generation on your machine — Set up local image generation with open-source models.
- How to Use AI Privately — Apply privacy-preserving practices when working with AI tools.
- How to Select the Right Quantized Model — Understand quantization formats and choose the right one for your hardware.
External, interactive guides hosted on third-party platforms.
- AI Prompt Engineering Tutor — Interactive platform for practising prompt-engineering methods. Built by Loic Baconnier.
- Prompt Engineering Interactive Tutorial — Systematic guide to prompt optimization, by Anthropic.
| Title | Description | Platform |
|---|---|---|
| Fundamentals of Generative AI | Introduction to generative AI and large language models (LLMs). |  |
| Fundamentals of Responsible Generative AI | Using generative AI responsibly. | |
| Introduction to Generative AI | The capabilities, applications, and distinct characteristics of generative AI. |  |
| Introduction to Image Generation | An introduction to diffusion models and how they generate and manipulate images. | |
| Introduction to Large Language Models | LLMs and their use in natural language processing: use cases, limitations, and optimization strategies. | |
| Introduction to Responsible AI | Why responsible AI matters for aligning machine learning systems with human values. | |
| What are foundation models? | An overview of foundation models and what makes them broadly applicable across tasks. |  |
| What are large language models (LLMs)? | A short introduction to LLMs and their use cases. | |
| What are vision language models (VLMs)? | A short introduction to VLMs and their use cases. | |
| What is Conversational AI? | A basic understanding of how conversational AI works. |  |
| What is Generative AI? (AWS) | An overview of the foundational ideas and principles of generative AI. | |
| What is Generative AI? (IBM) | An introduction to generative AI, its potential, and its applications. | |
| What is NLP (natural language processing)? | How language models process and interpret human language. | |
| Title | Description | Platform |
|---|---|---|
| Evaluation of generative AI applications | Exploring and comparing different LLMs. | |
| Generative AI Explained | Concepts, applications, challenges, and opportunities in generative AI. |  |
| Introduction to prompt engineering | Hands-on best practices for prompt engineering. | |
| Vision Language Models Explained | An overview of vision language models, their functionality, and usage. |  |
| What are AI hallucinations? | Why AI systems can produce nonsensical output by perceiving non-existent patterns. | |
| What is Prompt Engineering? | A concise guide to the key concepts, considerations, and methods of prompt engineering. | |
| What is prompt-tuning? | A lightweight method for adapting foundation models to downstream tasks. | |
| What is tool calling? | How LLMs interact with external tools. | |
| Title | Description | Platform |
|---|---|---|
| Augment your LLM Using Retrieval Augmented Generation | A high-level overview of retrieval-augmented generation and its benefits. | |
| Introduction to Quantization | An introduction to quantization, a technique to reduce model size and improve training and inference speed. | |
| Mixture of Experts Explained | An overview of MoEs, how they are trained, and the trade-offs to consider. | |
| Preference Tuning LLMs with Direct Preference Optimization Methods | Three methods for aligning language models without reinforcement learning. | |
| Prompt engineering techniques | Techniques that improve the outcome of your prompts. | |
| What is AI inferencing? | An introduction to the principles and methods of AI inference. | |
| What is instruction tuning? | How instruction tuning improves a pre-trained LLM's ability to follow instructions. | |
| What is KV Cache Quantization? | Using KV cache quantization to reduce memory usage for long-context generation. | |
| What's an LLM context window and why is it getting larger? | The role of the context window in LLMs. | |
| What is LLM orchestration? | How orchestration helps prompt, chain, manage, and monitor LLMs. | |
| What is Model Context Protocol (MCP)? | How MCP connects LLMs to many different sources of context. | |
| What is reasoning in AI? | An introduction to AI reasoning and why it is useful. | |
| What is retrieval-augmented generation? | What retrieval-augmented generation (RAG) is and why it is useful. | |
| What is reinforcement learning from human feedback (RLHF)? | What RLHF is and why it is useful. | |