What does “Frequency Penalty” mean?

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

A decoding setting that lowers the probability of tokens the model has already produced to reduce loops.

A language-model metric measuring how surprised the model is by true next tokens.

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

A generation strategy that constrains output tokens to valid structures or policy-compliant choices.

An inference acceleration method where a small draft model proposes tokens that a larger model verifies in parallel.