-2.0
and :obj:2.0
. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics. See more information about frequency and presence penalties. (default: :obj:None
)-2.0
and :obj:2.0
. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim. See more information about frequency and presence penalties. (default: :obj:None
)None
)None
)None
)None
)-100
to :obj:100
. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between:obj: -1
1
should decrease or increase likelihood of selection; values like :obj:-100
or :obj:100
should result in a ban or exclusive selection of the relevant token. (default: :obj:None
)None
)None
)None
)None
)