Skip to content
Sign in
All terms
Glossary · Term

Transformer

L3 · AdvancedFoundational

In plain terms

The attention-based architecture behind modern language models.

Technical definition

A sequence model built from stacked self-attention and feed-forward blocks with residual connections and normalization, processing all positions in parallel rather than recurrently.

Example

GPT-style and BERT-style models are both Transformers.

Try it in the Attention Visualizer labExplore in the AI Universe

Related terms