AI Glossary

Parameters

What does “Parameters” mean?

Parameters: The adjustable numbers inside a model that get set during training, mainly its weights and biases. Together they encode everything the model has learned. Model size is often described by parameter count, but more parameters does not automatically mean a better model.

Parameters visual guide: The adjustable numbers inside a model that get set during training, mainly its weights and biases. Together they encode everything the model has learned. Model size is often described by parameter count, but more parameters does not automatically mean a better model.
Visual guide Open full size (new tab)

What is an example of “Parameters”?

A model described as "7B" has roughly seven billion parameters.

Keep learning

See also

WeightsTermModelTermHyperparameterTermLarge language modelTerm

Same topic

Dense modelTermMixture of expertsTermScaling lawsTermPredictionTermNeural networkTerm