Model Architectures · Go deeper
Transformer Models
Encoder, decoder, or both? Map the transformer family tree — BERT, GPT, T5 — and learn which shape fits which job.
- 45 min lesson
- intermediate level
- Narrated presentation
What you’ll learn
- Encoder vs. decoder
- Bidirectional vs. causal attention
- BERT / GPT / T5 families
- Masked vs. next-token objectives
- Task-to-architecture matching
- Scaling properties
Inside this lesson
A narrated, slide-by-slide presentation with 1 prediction exercise, 1 knowledge check, 3 videos. You answer as you go, and the platform checks your work.