16 references to GetIndexByTokenCountFromEnd
Microsoft.ML.Tokenizers.Tests (16)
BpeTests.cs (1)
467Assert.Equal(expectedOffsets[expectedOffsets.Length - 3].Index, tokenizer.GetIndexByTokenCountFromEnd(text, 3, out normalizedString, out tokenCount));
CodeGenTests.cs (5)
470Assert.Equal(expectedIndex, codeGenTokenizer.GetIndexByTokenCountFromEnd(text, 1, out normalizedString, out tokenCount)); 657int index = codeGenTokenizer.GetIndexByTokenCountFromEnd(text, maxTokenCount: 500, out normalizedString, out count); 790index = codeGenTokenizer.GetIndexByTokenCountFromEnd(text, maxTokenCount: 500, out normalizedString, out count); 944index = codeGenTokenizer.GetIndexByTokenCountFromEnd(text, maxTokenCount: 500, out normalizedString, out count); 1018charsConsumed = _codegen350MMonoTokenizer.GetIndexByTokenCountFromEnd(input, maxTokenCount, out _, out tokenCount);
EnglishRobertaTests.cs (1)
219Assert.Equal(expectedOffsets[expectedOffsets.Length - 3].Index, tokenizer.GetIndexByTokenCountFromEnd(text, 3, out normalizedString, out tokenCount));
LlamaTests.cs (1)
642Assert.Equal(expectedOffsets[expectedOffsets.Length - 7].Index, tokenizer.GetIndexByTokenCountFromEnd(text, 7, out normalizedString, out tokenCount));
TitokenTests.cs (2)
602Assert.Equal(expectedOffsets[expectedOffsets.Length - 3].Index, tokenizer.GetIndexByTokenCountFromEnd(text, 3, out normalizedString, out tokenCount)); 708int index = GPT4.GetIndexByTokenCountFromEnd(text, tokenCount, out _, out count);
TokenizerTests.cs (6)
70Assert.Equal(3, tokenizer.GetIndexByTokenCountFromEnd("hello", 2, out string? normalizedString, out int tokenCount)); 74Assert.Equal(0, tokenizer.GetIndexByTokenCountFromEnd("hello", 8, out normalizedString, out tokenCount)); 138int index2 = tokenizer.GetIndexByTokenCountFromEnd(input, maxTokenCount: i, out string? processedText2, out int tokenCount2); 217Assert.Equal(0, tokenizer.GetIndexByTokenCountFromEnd((string)null!, maxTokenCount: 10, out _, out _)); 223Assert.Throws<ArgumentOutOfRangeException>(() => tokenizer.GetIndexByTokenCountFromEnd(input, maxTokenCount: 0, out _, out _)); 224Assert.Throws<ArgumentOutOfRangeException>(() => tokenizer.GetIndexByTokenCountFromEnd(input, maxTokenCount: -1, out _, out _));