Glossary › LLM

Temperature

Scaling factor applied to logits before softmax. T=0: deterministic (argmax). T=0.7: balanced creativity. T=1.0: default sampling. T>1: more random. Controls output diversity vs. consistency.

Where this is taught

• Tokens, Context Windows & Temperature — Phase 0: How AI Actually Reads Your Words
• Pre-Training a Mini GPT (124M Parameters) — Phase 3: LLM Architecture
• Sampling Methods — Phase 2: Probability & Statistics
• LLM-as-a-Judge & AutoSxS Win-Rate Analytics — Phase 7: AI Evaluation & Observability
• CLIP and Contrastive Vision-Language Pretraining — Phase 0: Multimodal Foundations
• Build the Content Generators — Build an AI Content Factory

Related terms

Top-p · Softmax

More in LLM

Hallucination · Token · Context Window · Top-p (Nucleus Sampling) · In-Context Learning · System Prompt · Function Calling

Learn this by building

DeVenture Academy teaches AI engineering through projects — every lesson is paired with a hands-on lab you run on your own machine with real tools.

Create a free account — the opening phases of 24 of 30 courses are free, no credit card. Or see Pro pricing.

All courses · Pricing · About · FAQ · Glossary