Glossary

Transformer architecture — Glossary

A neural architecture built around attention mechanisms, foundational to modern LLMs.

Reviewed:

Full definition

Transformers process token sequences with multi-head self-attention and feed-forward blocks. They scale well on parallel hardware and dominate contemporary NLP and multimodal modeling.

Related encyclopedia topic

Transformers — Transformers are neural architectures that use attention mechanisms to model relationships among tokens, forming the backbone of modern language, vision, and…

← Back to glossary · Learning hub