BpeTokenizer
ContinuingSubwordPrefix- EndOfWordSuffix
- FuseUnknownTokens
- Normalizer
- PreTokenizer
- SpecialTokens
- UnknownToken
- Vocabulary
CountTokens(String, ReadOnlySpan<Char>, EncodeSettings)- Create(Stream, Stream)
- Create(String, String)
- Create(Stream, Stream, PreTokenizer, Normalizer, IReadOnlyDictionary<String, Int32>, String, String, String, Boolean)
- Create(String, String, PreTokenizer, Normalizer, IReadOnlyDictionary<String, Int32>, String, String, String, Boolean)
- CreateAsync(Stream, Stream, PreTokenizer, Normalizer, IReadOnlyDictionary<String, Int32>, String, String, String, Boolean)
- Decode(IEnumerable<Int32>)
- Decode(IEnumerable<Int32>, Boolean)
- Decode(IEnumerable<Int32>, Span<Char>, Int32, Int32)
- Decode(IEnumerable<Int32>, Span<Char>, Boolean, Int32, Int32)
- EncodeToIds(String, ReadOnlySpan<Char>, EncodeSettings)
- EncodeToTokens(String, ReadOnlySpan<Char>, EncodeSettings)
- GetIndexByTokenCount(String, ReadOnlySpan<Char>, EncodeSettings, Boolean, String, Int32)
net462
namespace Microsoft.ML.Tokenizers
{
public sealed class BpeTokenizer : Tokenizer
{
[AsyncStateMachine(typeof(<CreateAsync>d__26))]
public static Task<BpeTokenizer!>! CreateAsync(Stream! vocabStream, Stream? mergesStream, PreTokenizer? preTokenizer = null, Normalizer? normalizer = null, IReadOnlyDictionary<string!, int>? specialTokens = null, string? unknownToken = null, string? continuingSubwordPrefix = null, string? endOfWordSuffix = null, bool fuseUnknownTokens = false);
}
}
| .NET | 5.06.07.08.09.0 |
|---|---|
| .NET Core | 2.02.12.23.03.1 |
| .NET Framework | 4.6.14.6.24.74.7.14.7.24.84.8.1 |
| .NET Standard | 2.02.1 |
Information specific to net462 | |
| Assembly | Microsoft.ML.Tokenizers , Version=1.0.0.0, PublicKeyToken=cc7b13ffcd2ddd51 |
| Referencing | Your project needs a package reference to |
| Package | Microsoft.ML.Tokenizers (0.22.0) netstandard2.0 |
| Platform Restrictions | This framework does not have platform annotations. |
- Built-in API
- Package-provided API