ModelConfig class

Configuration options passed to OnDeviceAi.loadModel.

All fields have sensible defaults and can be omitted for most use cases.

Example:

await ai.loadModel(
  'sentiment_analysis.tflite',
  config: ModelConfig(useGPU: false),
);

Constructors

ModelConfig({int maxTokens = 256, double temperature = 0.7, bool useGPU = true})

Creates a ModelConfig with the given options.

const

Properties

hashCode → int

The hash code for this object.

no setter, inherited

maxTokens → int

The maximum number of output tokens to generate.

final

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

temperature → double

The sampling temperature for generative models.

final

useGPU → bool

Whether to attempt to delegate inference to the GPU or Neural Engine.

final

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toMap() → Map<String, dynamic>

Serializes this configuration to a Map for passing over the platform channel.

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited