5 overrides of PreTokenizer
Microsoft.ML.Tokenizers (5)
Model\BPETokenizer.cs (1)
255public override PreTokenizer? PreTokenizer => _preTokenizer;
Model\CodeGenTokenizer.cs (1)
249public override PreTokenizer? PreTokenizer => _preTokenizer;
Model\EnglishRobertaTokenizer.cs (1)
244public override PreTokenizer? PreTokenizer => _preTokenizer;
Model\SentencePieceBpeTokenizer.cs (1)
158public override PreTokenizer? PreTokenizer => null;
Model\TiktokenTokenizer.cs (1)
126public override PreTokenizer? PreTokenizer => _preTokenizer;
11 references to PreTokenizer
Microsoft.ML.Tokenizers.Tests (10)
EnglishRobertaTests.cs (1)
239Assert.True(tokenizer.PreTokenizer is RobertaPreTokenizer);
LlamaTests.cs (1)
498Assert.Null(tokenizer.PreTokenizer);
TitokenTests.cs (8)
58Tokenizer tokenizer = TiktokenTokenizer.Create(tokenizerDataFileName, GPT4.PreTokenizer, null, specialTokensEncoder); 63tokenizer = TiktokenTokenizer.Create(stream, GPT4.PreTokenizer, null, specialTokensEncoder); 67tokenizer = await TiktokenTokenizer.CreateAsync(tokenizerDataFileName, GPT4.PreTokenizer, normalizer: null, specialTokensEncoder); 72tokenizer = await TiktokenTokenizer.CreateAsync(stream, GPT4.PreTokenizer, normalizer: null, specialTokensEncoder); 116TiktokenTokenizer externalTokenizer = TiktokenTokenizer.Create(tokenizerDataFileName, tokenizer.PreTokenizer, null, tiktoken.SpecialTokens); 443Assert.NotNull(tokenizer.PreTokenizer); 456Assert.NotNull(tokenizer.PreTokenizer); 509Assert.NotNull(tokenizer.PreTokenizer);
Microsoft.ML.TorchSharp (1)
NasBert\NerTrainer.cs (1)
379var pre = tokenizer.PreTokenizer.PreTokenize(sentence);