Weights
The learned strengths of connections in a neural network — the substance of what a model knows.
Weights determine how much each input contributes to each output at every layer. They start random and are updated by gradient descent until the loss stops improving. When people talk about ‘open weights’, they mean the trained numbers are downloadable, which is what makes local and self-hosted use possible.
In practice: Downloading an open-weights model means downloading a file of billions of floating-point numbers.