4 overrides of PreTokenize
Microsoft.ML.Tokenizers (3)
PreTokenizer\RobertaPreTokenizer.cs (1)
25public override IEnumerable<(int Offset, int Length)> PreTokenize(string text)
PreTokenizer\TiktokenPreTokenizer.cs (1)
47public override IEnumerable<(int Offset, int Length)> PreTokenize(string text)
PreTokenizer\WhiteSpacePreTokenizer.cs (1)
36public override IEnumerable<(int Offset, int Length)> PreTokenize(string text)
Microsoft.ML.Tokenizers.Tests (1)
PreTokenizerTests.cs (1)
109public override IEnumerable<(int Offset, int Length)> PreTokenize(string text)
5 references to PreTokenize
Microsoft.ML.Tokenizers (3)
Tokenizer.cs (3)
450splits = preTokenizer.PreTokenize(normalizedString); 472splits = preTokenizer.PreTokenize(normalizedString); 481splits = preTokenizer.PreTokenize(text);
Microsoft.ML.Tokenizers.Tests (1)
PreTokenizerTests.cs (1)
53(int Offset, int Length)[] splitParts = preTokenizer.PreTokenize(text).ToArray<(int Offset, int Length)>();
Microsoft.ML.TorchSharp (1)
NasBert\NerTrainer.cs (1)
379var pre = tokenizer.PreTokenizer.PreTokenize(sentence);