What is Self-Attention? Why does it exist? Where does it appear in Transformer?
Draw or describe a visual model of Self-Attention. What does it look like conceptually?
Work through a concrete manual example of Self-Attention with real numbers or pseudocode.
Implement Self-Attention from scratch in Python. Keep it minimal โ just enough to see it work.
Try Self-Attention on a real example. Vary the inputs and observe what changes.
How is Self-Attention different from related concepts in Transformer? What are the trade-offs?
Explain Self-Attention in plain language using an analogy. Could a non-expert follow it?
Build a small project or demo that uses Self-Attention as a core component.
tiny_llm/transformer.py
๐ full plan โ