Transformer class

Minimal Transformer encoder wrapper. We provide a tiny, testable abstraction: token embeddings -> mean pooling -> MLP head (ANN).

Constructors

Transformer({required int vocabSize, int dModel = 64, int heads = 4, required List<int> headLayers, int? seed})

Properties

dModel → int

final

hashCode → int

The hash code for this object.

no setter, inherited

head → ANN

final

heads → int

final

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

vocabSize → int

final

Methods

fit(List<List<int>> X, List<List<double>> Y, {int? batchSize, bool verbose = false}) → void

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

predict(List<List<int>> X) → List<List<double>>

toJson() → String

toMap() → Map<String, dynamic>

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited

Static Methods

fromJson(String s, {int? seed}) → Transformer

fromMap(Map<String, dynamic> m, {int? seed}) → Transformer