Decoding and inference behavior · MLD-1250
Top-p sampling
Sampling from a high-probability token subset whose cumulative probability reaches a threshold.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Adapt candidate-set size to distribution concentration.
Original caveat
Threshold and ordering with other filters affect outputs.
Context and aliases
Level: Intermediate. Stages: Inference · Evaluation · Deployment.
Tags: SLM · LLM · NLP.
Aliases: Nucleus sampling.
Related concepts
Concepts linking here
Original references
- Hugging Face: generation strategies ↗ · Reference link
- Fast Inference from Transformers via Speculative Decoding ↗ · Consulted
- vLLM documentation ↗ · Consulted
- Original reference URL ↗