Interface InferenceConfiguration.Builder
- All Superinterfaces:
Buildable,CopyableBuilder<InferenceConfiguration.Builder,,InferenceConfiguration> SdkBuilder<InferenceConfiguration.Builder,,InferenceConfiguration> SdkPojo
- Enclosing class:
InferenceConfiguration
@Mutable
@NotThreadSafe
public static interface InferenceConfiguration.Builder
extends SdkPojo, CopyableBuilder<InferenceConfiguration.Builder,InferenceConfiguration>
-
Method Summary
Modifier and TypeMethodDescriptionThe maximum number of tokens to generate in the model response during evaluation.stopSequences(String... stopSequences) The list of sequences that will cause the model to stop generating tokens when encountered.stopSequences(Collection<String> stopSequences) The list of sequences that will cause the model to stop generating tokens when encountered.temperature(Float temperature) The temperature value that controls randomness in the model's responses.The top-p sampling parameter that controls the diversity of the model's responses by limiting the cumulative probability of token choices.Methods inherited from interface software.amazon.awssdk.utils.builder.CopyableBuilder
copyMethods inherited from interface software.amazon.awssdk.utils.builder.SdkBuilder
applyMutation, buildMethods inherited from interface software.amazon.awssdk.core.SdkPojo
equalsBySdkFields, sdkFieldNameToField, sdkFields
-
Method Details
-
maxTokens
The maximum number of tokens to generate in the model response during evaluation.
- Parameters:
maxTokens- The maximum number of tokens to generate in the model response during evaluation.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
temperature
The temperature value that controls randomness in the model's responses. Lower values produce more deterministic outputs.
- Parameters:
temperature- The temperature value that controls randomness in the model's responses. Lower values produce more deterministic outputs.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
topP
The top-p sampling parameter that controls the diversity of the model's responses by limiting the cumulative probability of token choices.
- Parameters:
topP- The top-p sampling parameter that controls the diversity of the model's responses by limiting the cumulative probability of token choices.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
stopSequences
The list of sequences that will cause the model to stop generating tokens when encountered.
- Parameters:
stopSequences- The list of sequences that will cause the model to stop generating tokens when encountered.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
stopSequences
The list of sequences that will cause the model to stop generating tokens when encountered.
- Parameters:
stopSequences- The list of sequences that will cause the model to stop generating tokens when encountered.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-