init(samplingMode:temperature:maximumResponseTokens:toolCallingMode:)
Creates generation options that control token sampling behavior.
Declaration
init(samplingMode: GenerationOptions.SamplingMode? = nil, temperature: Double? = nil, maximumResponseTokens: Int? = nil, toolCallingMode: GenerationOptions.ToolCallingMode?)Parameters
- samplingMode:
A strategy to use for sampling from a distribution.
- temperature:
A value between
0and1, inclusive, that controls how sharply the model favors its most likely responses. A higher value increases variety. - maximumResponseTokens:
The maximum number of tokens the model is allowed to produce before being artificially halted. Must be positive.
- toolCallingMode:
The requirements defining how the model should call tools.