SampleConfig
The configuration for generating text samples from the model.
Contents
- numSamples
-
The number of independent samples to generate for the prompt.
Type: Integer
Valid Range: Minimum value of 1. Maximum value of 1000.
Required: Yes
- prompt
-
The input prompt to send to the model for text generation.
Type: ModelInput object
Required: Yes
- samplingParams
-
The parameters controlling the sampling strategy.
Type: SamplingParams object
Required: Yes
- includePromptLogprobs
-
Specifies whether to include per-token log-probabilities for the input prompt in the response.
Type: Boolean
Required: No
- modelPackageArn
-
The ARN of the model package whose checkpoint this sample should run against. Must be a valid SageMaker model package ARN in the format
arn:aws:sagemaker:REGION:ACCOUNT:model-package/PACKAGE_NAME/VERSION. When absent, the sample runs against the session's latest checkpoint.Type: String
Required: No
- topkPromptLogprobs
-
The number of top-k log-probabilities to return per prompt token.
Type: Integer
Required: No
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following: