Skip to content
ai

Temperature

Sampling Temperature

Definition

Temperature is a parameter that scales the logits before the softmax in language model sampling, controlling output randomness. A temperature of 1.0 uses the model's raw distribution; values below 1.0 make the distribution sharper (more deterministic), while values above 1.0 flatten it (more random).

Temperature 0 approximates greedy decoding, while higher values increase creative diversity at the cost of coherence.

Can this ship? Are we exposed? Can you prove it?

Every CISO is asking these three questions. We answer them with facts, not guesses, from repository to runtime.