GlueDataLoaderOptions
Options & Configuration · AiDotNet.Data.Text.Benchmarks
Configuration options for the GLUE benchmark data loader.
How It Works
GLUE (General Language Understanding Evaluation) contains 9 NLU tasks for evaluating language models: CoLA, SST-2, MRPC, QQP, STS-B, MNLI, QNLI, RTE, WNLI.
Constructors
| Constructor | Summary |
|---|---|
GlueDataLoaderOptions() |
Properties
| Property | Summary |
|---|---|
DatasetSplit Split { get; set; } |
Dataset split to load. |
GlueTask Task { get; set; } |
GLUE sub-task to load. |
bool AutoDownload { get; set; } |
Automatically download if not present. |
int MaxSequenceLength { get; set; } |
Maximum sequence length in tokens. |
int VocabularySize { get; set; } |
Maximum vocabulary size. |
int? MaxSamples { get; set; } |
Optional maximum number of samples to load. |
string DataPath { get; set; } |
Root data path. |
Methods
| Method | Summary |
|---|---|
void Validate() |
Validates that all option values are within acceptable ranges. |