Skip to content

8. Model Internals

The anatomy of a trained model at rest and at run. Children mix static structure (parameters/weights, architecture, layers, neurons, attention heads, vocabulary) with the runtime pipeline (tokenizer → context window → logits → probabilities → sampling). The throughline: text becomes tokens, tokens flow through weights, the model emits logits, sampling turns logits back into a token. Bridges architecture to inference.

Children

  • parameters / weights
  • architecture
  • layers
  • neurons / units
  • activations
  • attention heads
  • context window
  • tokenizer
  • vocabulary
  • logits
  • probabilities
  • sampling strategy