Bundle
Sentence embeddings from a pretrained BERT-family encoder exported to ONNX: the text is tokenized with WordPieceTokenizer, run through API.Onnx, and pooled into one vector per text.
A library of its own because it needs both System.NLP and API.Onnx, and the compiler resolves every class a linked library names: an embedder inside onnx.obl would make every ONNX program link nlp too, and one inside nlp.obl would make every NLP program need ONNX Runtime (docs/ML_BERT_DESIGN.md). Compile with -lib models,opencv,cipher,json,onnx,nlp,nlp_onnx.
TextClassifier->Function
How logits become scores, as transformers' function_to_apply.
Items
- SOFTMAX — Probabilities over the labels, summing to 1: single-label classification.
- SIGMOID — An independent probability per label: multi-label classification, or one label.
- NONE — The raw logits.