A higher Frequency Penalty parameter encourages the model to generate novel or less common words. It works by scaling down the log probabilities of words that the model has seen frequently during training, making it less likely for the model to generate these common words.

Positive values will decrease the likelihood of the model repeating the same line verbatim by penalizing new tokens that have already been used frequently. If the goal is to significantly suppress repetition, the coefficients can be increased up to 2, but this may negatively impact the quality of the samples.