temperature

The sampling setting that divides the logits before softmax: values below one sharpen the distribution towards the likeliest token, values above one flatten it.

In more detail

Temperature 0 is close to greedy decoding and suits extraction and classification; higher values give more varied wording. Many reasoning models accept only their default, and Anthropic advises changing temperature or top p, not both.

Example

"temperature": 0.2

Related terms

Taught in

References

Certification courses