The Illustrated Transformer
by Jay Alammar
See how attention and encoder-decoder blocks fit together.
Alammar explains the original Transformer using diagrams and a translation example. Read it for the architecture's basic moving parts, not as a description of every modern model variant.
- Level
- Beginner
- Models
- any
- Category
- Foundations
- Tags
- Source date
- date not stated
- Added
- 2026-10-18
- Last verified
- 2026-10-18
- Status
- ok
- Prerequisites
- Conceptual or guided prompt use; the main path does not require writing code.
- Subcategory
- llm fundamentals
- Region
- West
- Original language
- en
- Access
- free
- Resource reuse
- closed: No general open-reuse grant established from the inspected page. Closed is the conservative index bucket, not a legal finding; the resource is publicly readable. Facet definitions
Summary in our own words. Rights remain with the original creator. Credit and correction policy.