10 references to EncodeToIds
Microsoft.ML.Tokenizers.Tests (10)
LlamaTests.cs (3)
272IReadOnlyList<int> encodedIds = bpe.EncodeToIds(normalizedInput.AsSpan(), addBeginningOfSentence: false, addEndOfSentence: false, considerNormalization: false); 282encodedIds = bpe.EncodeToIds(normalizedInput.AsSpan(), addBeginningOfSentence: false, addEndOfSentence: true, considerNormalization: false); 292encodedIds = bpe.EncodeToIds(normalizedInput.AsSpan(), addBeginningOfSentence: true, addEndOfSentence: true, considerNormalization: false);
UnigramTests.cs (7)
384result = _unigramTokenizer.EncodeToIds(inputText.AsSpan(), addBeginningOfSentence: false, addEndOfSentence: false); 395result = _unigramTokenizer.EncodeToIds(inputText.AsSpan(), addBeginningOfSentence: true, addEndOfSentence: false); 412result = _unigramTokenizer.EncodeToIds(inputText.AsSpan(), addBeginningOfSentence: true, addEndOfSentence: true); 505ids1 = _unigramTokenizer.EncodeToIds(normalized!.Substring(0, index).AsSpan(), addBeginningOfSentence: false, addEndOfSentence: false, considerNormalization: false); 506ids2 = index < normalized.Length ? _unigramTokenizer.EncodeToIds(normalized!.Substring(index).AsSpan(), addBeginningOfSentence: false, addEndOfSentence: false, considerNormalization: false) : new List<int>(); 517ids1 = _unigramTokenizer.EncodeToIds(normalized!.Substring(0, index).AsSpan(), addBeginningOfSentence: false, addEndOfSentence: false, considerNormalization: false); 518ids2 = index < normalized.Length ? _unigramTokenizer.EncodeToIds(normalized!.Substring(index).AsSpan(), addBeginningOfSentence: false, addEndOfSentence: false, considerNormalization: false) : new List<int>();