LLMs Deep Dive
Go under the hood. Understand how text becomes tokens, how a language model is actually built, and the transformer architecture and attention mechanism that make modern LLMs work.
What you will be able to do
- Explain tokenization and why token counts drive cost and limits
- Describe how an LLM is trained end to end
- Explain self-attention and the transformer architecture at a high level
Tokens
IntermediateLLMs do not read characters or words, they read tokens. Tokenization determines context limits, pricing, and a surprising number of model quirks.
30 min3 resources · 1 videoBuilding an LLM
AdvancedBuild intuition for what training really does by watching a small GPT come together from scratch, then keep a from-the-ground-up reference to go deeper.
2 hr3 resources · 1 videoAttention & Transformers
AdvancedThe transformer and its self-attention mechanism are the core idea behind every modern LLM. Build a visual, intuitive understanding before touching the math.
1 hr4 resources · 2 videos
Put it to work
Apply what you learned by building real projects.
Test your thinking
Challenge yourself with scenario-based questions. Need 80% to mark complete.