AWS::Bedrock::FlowVersion PromptModelInferenceConfiguration

Contains inference configurations related to model inference for a prompt. For more information, see Inference parameters.

Syntax

To declare this entity in your AWS CloudFormation template, use the following syntax:

JSON

{
  "MaxTokens" : Number,
  "StopSequences" : [ String, ... ],
  "Temperature" : Number,
  "TopK" : Number,
  "TopP" : Number
}

YAML

  MaxTokens: Number
  StopSequences: 
    - String
  Temperature: Number
  TopK: Number
  TopP: Number

Properties

MaxTokens

The maximum number of tokens to return in the response.

Required: No

Type: Number

Minimum: 0

Maximum: 4096

Update requires: No interruption

StopSequences

A list of strings that define sequences after which the model will stop generating.

Required: No

Type: Array of String

Minimum: 0

Maximum: 4

Update requires: No interruption

Temperature

Controls the randomness of the response. Choose a lower value for more predictable outputs and a higher value for more surprising outputs.

Required: No

Type: Number

Minimum: 0

Maximum: 1

Update requires: No interruption

TopK

The number of most-likely candidates that the model considers for the next token during generation.

Required: No

Type: Number

Minimum: 0

Maximum: 500

Update requires: No interruption

TopP

The percentage of most-likely candidates that the model considers for the next token.

Required: No

Type: Number

Minimum: 0

Maximum: 1

Update requires: No interruption