interface WatsonxLLMGatewayParamsWatsonxInitOmit<CreateCompletionsParams, keyof WatsonxLLMGatewayKwargs | "stream" | "prompt">Model name to use. Available options are: qwen-turbo, qwen-plus, qwen-max, or Other compatible models.
Abort signal for this call. If provided, the call will be aborted when the signal is aborted.
Amount of randomness injected into the response. Ranges from 0 to 1 (0 is not included). Use temp closer to 0 for analytical / multiple choice, and temp closer to 1 for creative and generative tasks. Defaults to 0.95.
Total probability mass of tokens to consider at each step. Range from 0 to 1.0. Defaults to 0.8.