NewFeatureExtractionPipeline init a feature extraction pipeline.

NewTextClassificationPipeline initializes a new text classification pipeline.

NewTokenClassificationPipeline Initializes a feature extraction pipeline.

NewZeroShotClassificationPipeline create new Zero Shot Classification Pipeline.

WithHypothesisTemplate can be used to set the hypothesis template for classification.

WithLabels can be used to set the labels to classify the examples.

WithMultilabel can be used to set whether the pipeline is multilabel.

WithNormalization applies normalization to the mean pooled output of the feature pipeline.

WithoutAggregation returns the token labels.

WithOutputName if there are multiple outputs from the underlying model, which output should be returned.

WithSimpleAggregation sets the aggregation strategy for the token labels to simple It reproduces simple aggregation from the huggingface implementation.

FeatureExtractionPipeline A feature extraction pipeline is a go version of https://github.com/huggingface/transformers/blob/main/src/transformers/pipelines/feature_extraction.py.

TokenClassificationPipeline is a go version of huggingface tokenClassificationPipeline.