Microsoft.ML.Tokenizers 0.22.0-preview.24271.1

Prefix Reserved
This is a prerelease version of Microsoft.ML.Tokenizers.
dotnet add package Microsoft.ML.Tokenizers --version 0.22.0-preview.24271.1                
NuGet\Install-Package Microsoft.ML.Tokenizers -Version 0.22.0-preview.24271.1                
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package.
<PackageReference Include="Microsoft.ML.Tokenizers" Version="0.22.0-preview.24271.1" />                
For projects that support PackageReference, copy this XML node into the project file to reference the package.
paket add Microsoft.ML.Tokenizers --version 0.22.0-preview.24271.1                
#r "nuget: Microsoft.ML.Tokenizers, 0.22.0-preview.24271.1"                
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package.
// Install Microsoft.ML.Tokenizers as a Cake Addin
#addin nuget:?package=Microsoft.ML.Tokenizers&version=0.22.0-preview.24271.1&prerelease

// Install Microsoft.ML.Tokenizers as a Cake Tool
#tool nuget:?package=Microsoft.ML.Tokenizers&version=0.22.0-preview.24271.1&prerelease                


Microsoft.ML.Tokenizers supports various the implementation of the tokenization used in the NLP transforms.

Key Features

  • Extensible tokenizer architecture that allows for specialization of Normalizer, PreTokenizer, Model/Encoder, Decoder
  • BPE - Byte pair encoding model
  • English Roberta model
  • Tiktoken model
  • Llama model

How to Use

using Microsoft.ML.Tokenizers;
using System.Net.Http;
using System.IO;

// Using Tiktoken Tokenizer

// initialize the tokenizer for `gpt-4` model
Tokenizer tokenizer = Tokenizer.CreateTiktokenForModel("gpt-4");

string source = "Text tokenization is the process of splitting a string into a list of tokens.";

Console.WriteLine($"Tokens: {tokenizer.CountTokens(source)}");
// print: Tokens: 16

var trimIndex = tokenizer.LastIndexOfTokenCount(source, 5, out string processedText, out _);
Console.WriteLine($"5 tokens from end: {processedText.Substring(trimIndex)}");
// 5 tokens from end:  a list of tokens.

trimIndex = tokenizer.IndexOfTokenCount(source, 5, out processedText, out _);
Console.WriteLine($"5 tokens from start: {processedText.Substring(0, trimIndex)}");
// 5 tokens from start: Text tokenization is the

IReadOnlyList<int> ids = tokenizer.EncodeToIds(source);
Console.WriteLine(string.Join(", ", ids));
// prints: 1199, 4037, 2065, 374, 279, 1920, 315, 45473, 264, 925, 1139, 264, 1160, 315, 11460, 13

// Using Llama Tokenizer

// Open stream of remote Llama tokenizer model data file
using HttpClient httpClient = new();
const string modelUrl = @"";
using Stream remoteStream = await httpClient.GetStreamAsync(modelUrl);

// Create the Llama tokenizer using the remote stream
Tokenizer llamaTokenizer = Tokenizer.CreateLlama(remoteStream);
string input = "Hello, world!";
ids = llamaTokenizer.EncodeToIds(input);
Console.WriteLine(string.Join(", ", ids));
// prints: 1, 15043, 29892, 3186, 29991

Console.WriteLine($"Tokens: {llamaTokenizer.CountTokens(input)}");
// print: Tokens: 5

Main Types

The main types provided by this library are:

  • Microsoft.ML.Tokenizers.Tokenizer
  • Microsoft.ML.Tokenizers.Bpe
  • Microsoft.ML.Tokenizers.EnglishRoberta
  • Microsoft.ML.Tokenizers.Tiktoken
  • Microsoft.ML.Tokenizers.Normalizer
  • Microsoft.ML.Tokenizers.PreTokenizer

Additional Documentation

Feedback & Contributing

Microsoft.ML.Tokenizers is released as open source under the MIT license. Bug reports and contributions are welcome at the GitHub repository.

Product Compatible and additional computed target framework versions.
.NET net5.0 was computed.  net5.0-windows was computed.  net6.0 was computed.  net6.0-android was computed.  net6.0-ios was computed.  net6.0-maccatalyst was computed.  net6.0-macos was computed.  net6.0-tvos was computed.  net6.0-windows was computed.  net7.0 was computed.  net7.0-android was computed.  net7.0-ios was computed.  net7.0-maccatalyst was computed.  net7.0-macos was computed.  net7.0-tvos was computed.  net7.0-windows was computed.  net8.0 is compatible.  net8.0-android was computed.  net8.0-browser was computed.  net8.0-ios was computed.  net8.0-maccatalyst was computed.  net8.0-macos was computed.  net8.0-tvos was computed.  net8.0-windows was computed. 
.NET Core netcoreapp2.0 was computed.  netcoreapp2.1 was computed.  netcoreapp2.2 was computed.  netcoreapp3.0 was computed.  netcoreapp3.1 was computed. 
.NET Standard netstandard2.0 is compatible.  netstandard2.1 was computed. 
.NET Framework net461 was computed.  net462 was computed.  net463 was computed.  net47 was computed.  net471 was computed.  net472 was computed.  net48 was computed.  net481 was computed. 
MonoAndroid monoandroid was computed. 
MonoMac monomac was computed. 
MonoTouch monotouch was computed. 
Tizen tizen40 was computed.  tizen60 was computed. 
Xamarin.iOS xamarinios was computed. 
Xamarin.Mac xamarinmac was computed. 
Xamarin.TVOS xamarintvos was computed. 
Xamarin.WatchOS xamarinwatchos was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages (5)

Showing the top 5 NuGet packages that depend on Microsoft.ML.Tokenizers:

Package Downloads

Provide access to OpenAI LLM models in Kernel Memory to generate embeddings and text


Microsoft.ML.TorchSharp contains ML.NET integration of TorchSharp.


Provide TikToken tokenizers in Kernel Memory


SDK focused on building AI based applications for Microsoft Teams.


Added some extensions for Kernel Memory.

GitHub repositories (5)

Showing the top 5 popular GitHub repositories that depend on Microsoft.ML.Tokenizers:

Repository Stars
Integrate cutting-edge LLM technology quickly and easily into your apps
Sample application that combines Azure Cosmos DB with Azure OpenAI ChatGPT service
Microsoft Official Build Modern AI Apps reference solutions and content. Demonstrate how to build Copilot applications that incorporate Hero Azure Services including Azure OpenAI Service, Azure Container Apps (or AKS) and Azure Cosmos DB for NoSQL with Vector Search.
Version Downloads Last updated
0.22.0-preview.24271.1 26,425 5/21/2024
0.22.0-preview.24179.1 86,803 4/2/2024
0.22.0-preview.24162.2 18,626 3/13/2024
0.21.1 58,233 1/18/2024
0.21.0 46,855 11/27/2023
0.21.0-preview.23511.1 50,925 10/13/2023
0.21.0-preview.23266.6 49,798 5/17/2023
0.21.0-preview.22621.2 1,998 12/22/2022
0.20.1 75,037 2/1/2023
0.20.1-preview.22573.9 2,056 11/24/2022
0.20.0 27,377 11/8/2022
0.20.0-preview.22551.1 208 11/1/2022