Large Language Models
Large Language Models (LLMs) like ChatGPT, DeepSeek, Gemini, or Claude, have taken the world by storm.
In this course, you’ll learn all the foundations of how LLMs work, including the whole architecture of transformer models, tokenizers, positional encoding, and a deep dive into the attention mechanism, the secret sauce behind transformers.
-
Chapter 1: Attention Mechanisms
-
Chapter 2: Transformer Architectures
-
Lesson 1: Transformer Architecture
The architecture of transformer models
-
Lesson 2: Tokenization
In this lesson you’ll learn how LLMs tokenize language in order to break it into useful building blocks. You’ll also learn a very common method for tokenization, called Byte-Pair Encoding (BPE).
-
Lesson 3: Positional encoding
Positional encoding
-
Lesson 4: State Space Models and Mamba
-
-
Chapter 3: AI Agents, RAG, and Reasoning Models
Retake this course?
Retaking this course from the beginning will reset all of your tracked progress.