← Back to the AI Glossary 📖 Models & Architecture

Transformer

The neural network architecture, introduced in 2017, that made modern large language models possible by letting a model weigh the importance of every word in relation to every other word at once.

Virtually every major LLM today — Claude, GPT, Gemini, Llama — is built on some variant of the transformer architecture.
One of 60 free AI glossary terms
Plain-language definitions for the AI jargon you'll actually run into — no email needed, ever, for this section.
Browse the Full Glossary →
More in Models & Architecture
Small Language Model (SLM)
A language model with far fewer parameters than a frontier model, built to run faster, che...
Mixture of Experts (MoE)
A model design where only a small subset of the model's total parameters actually activate...
Model Weights
The actual learned numerical values inside a trained AI model that determine how it respon...
Model Card
A short published document describing an AI model's capabilities, limitations, training da...