Transformers and LLMs

Temperature, explained

Temperature is a sampling setting that controls how sharp or random a model's output distribution is.
Back to Glossary

Part of the Semantic Notion technical glossary.

Short Definition

Temperature is a sampling setting that controls how sharp or random a model's output distribution is.

Intuition

Lower temperature makes the model more conservative. Higher temperature makes lower-probability choices more likely.

Technical Definition

Temperature rescales logits before softmax sampling, changing entropy in the resulting token distribution.

Example

A code-generation system may use low temperature for reliability and higher temperature for brainstorming.

Common Misunderstandings

Temperature does not change the model weights.
Higher temperature is not the same as better creativity.

Same Category

More from Transformers and LLMs

AttentionAttention is a neural network mechanism that lets a model decide which parts of an input are most relevant when producing a representation or output.Context WindowA context window is the maximum amount of input and generated tokens a model can consider at one time.Cross-AttentionCross-attention lets one sequence attend to information from a different sequence or modality.Hybrid AttentionHybrid attention combines different attention patterns, such as local and global attention, inside one model.KV CacheA KV cache stores attention keys and values from previous tokens so autoregressive generation does not recompute them every step.Multimodal ModelA multimodal model can process or generate more than one kind of data, such as text, images, audio, or video.

Related Reading

Essays that use this concept

Machine Learning FoundationsWhat Is Softmax and Why Is It Used?

Start here

Need the broader concept map?

Return to the glossary index to move from this definition into adjacent AI, ML, mathematics, and computer science terms.

Browse Glossary