Skip to main content

DL05 · Transformers

A free, illustrated L3 course of 11 modules in the Deep Learning track. Modules include: Self-attention from scratch; Multi-head attention; Positional information.

DL05 L3 · Advanced 11 modules · about 44 lessons Planned · Ring 2

Part of the Deep Learning track. Ships in Ring 2 (Spine) of the roadmap.

Modules

  1. Self-attention from scratch
  2. Multi-head attention
  3. Positional information
  4. The transformer block
  5. Encoder, decoder and encoder-decoder variants
  6. Tokenization with byte-pair encoding
  7. Pretraining objectives
  8. Vision transformers
  9. Efficient attention and long context
  10. Mixture of experts and other variants
  11. Build and train a small GPT

Signature illustrations

The pictures a learner should still see in their head a year later:

Query, key and value matching, attention-matrix heatmaps, tensor shapes flowing through one block, the causal mask, positional-encoding stripes.

Status

This course is planned, not written yet. It ships with Ring 2 (Spine).

Every lesson will follow the same twelve-part blueprint with at least three purpose-made figures. Watch the repository to hear when modules ship, or help write and review it.

Back to top