Sign inSign in
ConceptAI & ML

Top-K sampling

Sampling from the top K most likely probabilities by clamping anything lower than the K-th probability to zero and renormalizing.
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Logits1PyTorch Multinomial1Softmax function1Softmax probabilities1Token generation1

Lecturers

1

    Connections

    3

    The lectures that define it or assume it, and the concepts next to it.

    Concepts2

    1 lecturer. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.