Home/Glossary/Model Parameters / Weights

AI Glossary

Model Parameters / Weights

The numbers that define what a trained AI model knows

Definition

Parameters (also called weights) are the numerical values stored in a neural network that encode what the model has learned during training. A model with 70 billion parameters (70B) stores 70 billion individual numbers. More parameters generally means more capacity to store knowledge and handle complex tasks, though efficiency improvements are making smaller models increasingly competitive.

Related Terms

Back to Glossary