You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- seed: typing.Optional[float]. If specified, the backend will make a best effort to sample tokens deterministically, such that repeated requests with the same seed and parameters should return the same result. However, determinism cannot be totally guaranteed.
215
216
217
+
- stop_sequences: typing.Optional[typing.Sequence[str]]. A list of up to 5 strings that the model will use to stop generation. If the model generates a string that matches any of the strings in the list, it will stop generating tokens and return the generated text up to that point not including the stop sequence.
218
+
216
219
- frequency_penalty: typing.Optional[float]. Defaults to `0.0`, min value of `0.0`, max value of `1.0`.
217
220
218
221
Used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation.
- seed: typing.Optional[float]. If specified, the backend will make a best effort to sample tokens deterministically, such that repeated requests with the same seed and parameters should return the same result. However, determinism cannot be totally guaranteed.
512
519
520
+
- stop_sequences: typing.Optional[typing.Sequence[str]]. A list of up to 5 strings that the model will use to stop generation. If the model generates a string that matches any of the strings in the list, it will stop generating tokens and return the generated text up to that point not including the stop sequence.
521
+
513
522
- frequency_penalty: typing.Optional[float]. Defaults to `0.0`, min value of `0.0`, max value of `1.0`.
514
523
515
524
Used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation.
- seed: typing.Optional[float]. If specified, the backend will make a best effort to sample tokens deterministically, such that repeated requests with the same seed and parameters should return the same result. However, determinism cannot be totally guaranteed.
1715
1727
1728
+
- stop_sequences: typing.Optional[typing.Sequence[str]]. A list of up to 5 strings that the model will use to stop generation. If the model generates a string that matches any of the strings in the list, it will stop generating tokens and return the generated text up to that point not including the stop sequence.
1729
+
1716
1730
- frequency_penalty: typing.Optional[float]. Defaults to `0.0`, min value of `0.0`, max value of `1.0`.
1717
1731
1718
1732
Used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation.
- seed: typing.Optional[float]. If specified, the backend will make a best effort to sample tokens deterministically, such that repeated requests with the same seed and parameters should return the same result. However, determinism cannot be totally guaranteed.
2012
2030
2031
+
- stop_sequences: typing.Optional[typing.Sequence[str]]. A list of up to 5 strings that the model will use to stop generation. If the model generates a string that matches any of the strings in the list, it will stop generating tokens and return the generated text up to that point not including the stop sequence.
2032
+
2013
2033
- frequency_penalty: typing.Optional[float]. Defaults to `0.0`, min value of `0.0`, max value of `1.0`.
2014
2034
2015
2035
Used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation.
0 commit comments