AI / A CONCEPT NOTE
Parameters
learnable weights in the model
Overview · mechanism
pitfall · examples
01 / THE SHORT VERSION
The idea in a few sentences.
The internal variables (weights and biases) of a neural network that are adjusted during training to capture language patterns and mathematical relationships.
02 / FOLLOW THE MECHANISM
How parameters drive prediction
Input layer
receives token embeddings vector inputs.
Weight multiply
multiplies inputs by parameter weights across attention layers.
Softmax peak
generates output probabilities, selecting the next token.
04 / COMMAND NOTES
Read the command, then the result.
Inspect the flags and arguments before trying an example. Snippets can need local setup, replacement values, or resources in your own environment.
view parameter counts and sizes
ollama show llama3 --parameters05 / CHECK YOURSELF
Could you explain Parameters to a teammate?
Try it out loud in two sentences: what it is, and the one detail that changes the picture. If you stall, the gap is the part to reread.
Up next in AI engineeringPre-trainingtraining on massive unlabeled data