Tokenizers.DotNet 1.3.0

dotnet add package Tokenizers.DotNet --version 1.3.0
                    
NuGet\Install-Package Tokenizers.DotNet -Version 1.3.0
                    
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="Tokenizers.DotNet" Version="1.3.0" />
                    
For projects that support PackageReference, copy this XML node into the project file to reference the package.
<PackageVersion Include="Tokenizers.DotNet" Version="1.3.0" />
                    
Directory.Packages.props
<PackageReference Include="Tokenizers.DotNet" />
                    
Project file
For projects that support Central Package Management (CPM), copy this XML node into the solution Directory.Packages.props file to version the package.
paket add Tokenizers.DotNet --version 1.3.0
                    
#r "nuget: Tokenizers.DotNet, 1.3.0"
                    
#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.
#:package Tokenizers.DotNet@1.3.0
                    
#:package directive can be used in C# file-based apps starting in .NET 10 preview 4. Copy this into a .cs file before any lines of code to reference the package.
#addin nuget:?package=Tokenizers.DotNet&version=1.3.0
                    
Install as a Cake Addin
#tool nuget:?package=Tokenizers.DotNet&version=1.3.0
                    
Install as a Cake Tool

Tokenizers.DotNet

.NET wrapper of HuggingFace Tokenizers library

Build (Windows-x64) Build (Multi-platform)

Nuget Package list

Package main Description
Tokenizers.DotNet Nuget Tokenizers.DotNet Core library
Tokenizers.DotNet.runtime.win-x64 Nuget Tokenizers.DotNet.runtime.win-x64 Native bindings for windows x64
Tokenizers.DotNet.runtime.win-arm64 Nuget Tokenizers.DotNet.runtime.win-arm64 Native bindings for windows arm64
Tokenizers.DotNet.runtime.linux-x64 Nuget Tokenizers.DotNet.runtime.linux-x64 Native bindings for linux x64
Tokenizers.DotNet.runtime.linux-arm64 Nuget Tokenizers.DotNet.runtime.linux-arm64 Native bindings for linux arm64

Requirements

  • .NET 6 / .NET Standard 2.0 or above
  • (Build) Latest Rust

Supported functionalities

  • Download tokenizer files from Hugginface Hub
  • Load tokenizer file(.json) from local
  • Encode string to tokens
  • Decode tokens to string

How to use

(1) Install the packages

  1. From the NuGet, install Tokenizers.DotNet package
  2. And then, install Tokenizers.DotNet.runtime.<OS>-<ARCH> package too (e.a win-x64 or linux-arm64, check Nuget package list above).

(2) Write the code

Check following example code:

using Tokenizers.DotNet;

// Download skt/kogpt2-base-v2/tokenizer.json from the hub
var hubName = "skt/kogpt2-base-v2";
var filePath = "tokenizer.json";
var fileFullPath = await HuggingFace.GetFileFromHub(hubName, filePath, "deps");
Console.WriteLine($"Downloaded {fileFullPath}");

// Create a tokenizer instance
Tokenizer tokenizer;
try
{
    tokenizer = new Tokenizer(vocabPath: fileFullPath);
}
catch (TokenizerException e)
{
	Console.WriteLine(e.Message);
    return;
}
try
{
    var text = "음, 이제 식사도 해볼까요";
    Console.WriteLine($"Input text: {text}");
    var tokens = tokenizer.Encode(text);
    Console.WriteLine($"Encoded: {string.Join(", ", tokens)}");
    var decoded = tokenizer.Decode(tokens);
    Console.WriteLine($"Decoded: {decoded}");
}
catch (TokenizerException e)
{
    Console.WriteLine(e.Message);
    return;
}
Console.WriteLine($"Version of Tokenizers.DotNet.runtime.win: {tokenizer.GetVersion()}");
Console.WriteLine("--------------------------------------------------");

//// Download openai-community/gpt2 from the hub
hubName = "openai-community/gpt2";
filePath = "tokenizer.json";
fileFullPath = await HuggingFace.GetFileFromHub(hubName, filePath, "deps");

// Create a tokenizer instance
Tokenizer tokenizer2;
try
{
    tokenizer2 = new Tokenizer(vocabPath: fileFullPath);
}
catch (TokenizerException e)
{
    Console.WriteLine(e.Message);
    return;
}
try
{
    var text2 = "i was nervous before the exam, and i had a fever.";
    Console.WriteLine($"Input text: {text2}");
    var tokens2 = tokenizer2.Encode(text2);
    Console.WriteLine($"Encoded: {string.Join(", ", tokens2)}");
    var decoded2 = tokenizer2.Decode(tokens2);
    Console.WriteLine($"Decoded: {decoded2}");
}
catch (TokenizerException e)
{
    Console.WriteLine(e.Message);
    return;
}

Console.WriteLine($"Version of Tokenizers.DotNet.runtime.win: {tokenizer2.GetVersion()}");
Console.ReadKey();

How to build

You can use Docker to compile this library for Windows x64/arm64 and Linux x64/arm64

Run update_version.ps1 before running Docker to update the package version.

Windows:

PS > docker build -f Dockerfile -t ghcr.io/sappho192/tokenizers.dotnet:latest .
PS > docker run -v .\nuget:/out --rm ghcr.io/sappho192/tokenizers.dotnet:latest

Linux/MacOS:

$ docker build -f Dockerfile -t ghcr.io/sappho192/tokenizers.dotnet:latest .
$ docker run -v ./nuget:/out --rm ghcr.io/sappho192/tokenizers.dotnet:latest

Built packages will be in the nuget folder.

Building with local machine system

(Note that this has been confirmed only in Windows machine)

  1. Prepare following stuff:
    1. Rust build system (cargo)
    2. .NET build system (dotnet 6.0 or above)
    3. PowerShell (Recommend 7.4.2 or above)
  2. Bump the version number in NATIVE_LIB_VERSION.txt
  3. Run build_all_clean.ps1
    1. To build Tokenizers.DotNet.runtime.<OS> only, run build_rust.ps1
    2. To build Tokenizers.DotNet only, run build_dotnet.ps1

Each build artifacts will be in nuget directory.

Product Compatible and additional computed target framework versions.
.NET net5.0 was computed.  net5.0-windows was computed.  net6.0 is compatible.  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 was computed.  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.  net9.0 was computed.  net9.0-android was computed.  net9.0-browser was computed.  net9.0-ios was computed.  net9.0-maccatalyst was computed.  net9.0-macos was computed.  net9.0-tvos was computed.  net9.0-windows was computed.  net10.0 was computed.  net10.0-android was computed.  net10.0-browser was computed.  net10.0-ios was computed.  net10.0-maccatalyst was computed.  net10.0-macos was computed.  net10.0-tvos was computed.  net10.0-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 (2)

Showing the top 2 NuGet packages that depend on Tokenizers.DotNet:

Package Downloads
EDMTranslator

Text translator library based on LLM models, especially EncoderDecoderModel in HuggingFace

RAGamuffin

Package Description

GitHub repositories (1)

Showing the top 1 popular GitHub repositories that depend on Tokenizers.DotNet:

Repository Stars
axzxs2001/Asp.NetCoreExperiment
原来所有项目都移动到**OleVersion**目录下进行保留。新的案例装以.net 5.0为主,一部分对以前案例进行升级,一部分将以前的工作经验总结出来,以供大家参考!