Pattern
Sampling parameters — temperature, top-p, and top-k
Control the randomness and diversity of model output at generation time through the decoding parameters — temperature, top-p (nucleus sampling), and top-k — trading determinism against exploration to match the task, rather than accepting whatever the defaults produce.
Classification — Controlling output randomness and diversity at generation time through decoding parameters.
Full entry
The complete treatment — problem, how it works, when to use it, sources, and examples — lives in the volume below.
Browse the full pattern index or the catalog.