SuperGlueDataLoader<T>
Models & Types · AiDotNet.Data.Text.Benchmarks
Loads SuperGLUE benchmark sub-tasks (BoolQ, CB, COPA, MultiRC, ReCoRD, RTE, WiC, WSC).
Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → SuperGlueDataLoader<T>
How It Works
SuperGLUE expects JSONL files:
Features are token-index encoded text Tensor[N, MaxSequenceLength]. Labels are one-hot Tensor[N, NumClasses].
Constructors
| Constructor | Summary |
|---|---|
SuperGlueDataLoader(SuperGlueDataLoaderOptions options) |
Creates a new SuperGLUE data loader. |
Properties
| Property | Summary |
|---|---|
int FeatureCount { get; } |
|
int OutputDimension { get; } |
|
int TotalCount { get; } |
|
string Description { get; } |
|
string Name { get; } |
Methods
| Method | Summary |
|---|---|
ValueTuple<IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>> Split(double trainRatio, double validationRatio, int? seed) |