Enum EdgeTokenizerKind
- Namespace
- Qavren.Edge.Embeddings.Onnx
- Assembly
- Qavren.Edge.Embeddings.Onnx.dll
Which tokenizer family a preset's tokenizer asset belongs to.
public enum EdgeTokenizerKind
Fields
WordPieceVocabTxt = 0A WordPiece
vocab.txt, which is every preset SP2 ships.UnigramTokenizerJson = 1A Unigram
tokenizer.json. Present so the multilingual shape is ready when the library is; raises TokenizerKindUnsupported today (ADR 0006).