Interface InferenceConfiguration.Builder
- All Superinterfaces:
Buildable
,CopyableBuilder<InferenceConfiguration.Builder,
,InferenceConfiguration> SdkBuilder<InferenceConfiguration.Builder,
,InferenceConfiguration> SdkPojo
- Enclosing class:
InferenceConfiguration
-
Method Summary
Modifier and TypeMethodDescriptionmaximumLength
(Integer maximumLength) The maximum number of tokens allowed in the generated response.stopSequences
(String... stopSequences) A list of stop sequences.stopSequences
(Collection<String> stopSequences) A list of stop sequences.temperature
(Float temperature) The likelihood of the model selecting higher-probability options while generating a response.While generating a response, the model determines the probability of the following token at each point of generation.While generating a response, the model determines the probability of the following token at each point of generation.Methods inherited from interface software.amazon.awssdk.utils.builder.CopyableBuilder
copy
Methods inherited from interface software.amazon.awssdk.utils.builder.SdkBuilder
applyMutation, build
Methods inherited from interface software.amazon.awssdk.core.SdkPojo
equalsBySdkFields, sdkFields
-
Method Details
-
maximumLength
The maximum number of tokens allowed in the generated response.
- Parameters:
maximumLength
- The maximum number of tokens allowed in the generated response.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
stopSequences
A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
- Parameters:
stopSequences
- A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
stopSequences
A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
- Parameters:
stopSequences
- A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
temperature
The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.
- Parameters:
temperature
- The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
topK
While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for
topK
is the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you settopK
to 50, the model selects the next token from among the top 50 most likely choices.- Parameters:
topK
- While generating a response, the model determines the probability of the following token at each point of generation. The value that you set fortopK
is the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you settopK
to 50, the model selects the next token from among the top 50 most likely choices.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
topP
While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for
Top P
determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you settopP
to 80, the model only selects the next token from the top 80% of the probability distribution of next tokens.- Parameters:
topP
- While generating a response, the model determines the probability of the following token at each point of generation. The value that you set forTop P
determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you settopP
to 80, the model only selects the next token from the top 80% of the probability distribution of next tokens.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-