What is Perplexity?

A code-evaluation metric measuring the chance that at least one of k generated samples passes the tests.

The maximum amount of input tokens a language model can process at once.

A decoding strategy that samples only from the k most likely next tokens.

A statistical range that likely contains the true value of a measured model metric.

A decoding setting that reduces the probability of tokens proportionally to how often they've appeared so far.

A decoding setting that reduces the probability of tokens that have appeared at all, encouraging new topics.