top
Setter for topP.
topP: Tokens are selected from the most to least probable until the sum of their probabilities equals this value. Use a lower value for less random responses and a higher value for more random responses.
Setter for topP.
topP: Tokens are selected from the most to least probable until the sum of their probabilities equals this value. Use a lower value for less random responses and a higher value for more random responses.