Перейти к содержимому
Меню
Русский

Top-p Sampling

Sampling only from the smallest set of tokens whose probabilities reach p.

technique Методы 3 relationships

Обзор

Top-p, or nucleus sampling, keeps the most likely tokens until their cumulative probability reaches a threshold, then samples from that set. It solves the problem that a fixed top-k includes nonsense when the distribution is peaked and excludes reasonable options when it is flat. It exists because the set of plausible continuations should be sized by the model's own confidence.

Граф технологий

Как Top-p Sampling связана с остальным стеком.

Использует и зависит от

Применяется к

Альтернативы

Сравнения

Подробные сопоставления с альтернативами выше.