dictionary
Parameters (Weights)
When you hear about a "70-billion parameter model," it refers to the size and complexity of the neural network. Parameters are numbers (weights and biases) that define how input data is transformed into output predictions. Training adjusts these billions of parameters until the model reliably produces accurate results.
CategoryModels
Reading time2 min read
Last updatedFeb 19, 2025
Definition
The internal variables a neural network learns during training. They act as the "knowledge" of the model.
Need this applied?
We help teams go from definitions to deployed workflows—safely and fast.
FAQ
Email this summary + checklist
Get a copy of “Parameters (Weights)” and an AI readiness checklist in your inbox.