Microsoft.DeepDev.TokenizerLib
1.3.3
Prefix Reserved
dotnet add package Microsoft.DeepDev.TokenizerLib --version 1.3.3
NuGet\Install-Package Microsoft.DeepDev.TokenizerLib -Version 1.3.3
<PackageReference Include="Microsoft.DeepDev.TokenizerLib" Version="1.3.3" />
paket add Microsoft.DeepDev.TokenizerLib --version 1.3.3
#r "nuget: Microsoft.DeepDev.TokenizerLib, 1.3.3"
// Install Microsoft.DeepDev.TokenizerLib as a Cake Addin #addin nuget:?package=Microsoft.DeepDev.TokenizerLib&version=1.3.3 // Install Microsoft.DeepDev.TokenizerLib as a Cake Tool #tool nuget:?package=Microsoft.DeepDev.TokenizerLib&version=1.3.3
Tokenizer
This repo contains C# and Typescript implementation of byte pair encoding(BPE) tokenizer for OpenAI LLMs, it's based on open sourced rust implementation in the OpenAI tiktoken. Both implementation are valuable to run prompt tokenization in .NET and Nodejs environment before feeding prompt into a LLM.
C# implementation
The TokenizerLib is built in .NET Standard 2.0, which can be consumed in projects on any version of .NET later than .NET Core 2.0 or .NET Framework 4.6.1.
You can download and install the nuget package of TokenizerLib here.
Example C# code to use TokenizerLib in your code:
using System.Collections.Generic;
using Microsoft.DeepDev;
var IM_START = "<|im_start|>";
var IM_END = "<|im_end|>";
var specialTokens = new Dictionary<string, int>{
{ IM_START, 100264},
{ IM_END, 100265},
};
var tokenizer = await TokenizerBuilder.CreateByModelNameAsync("gpt-4", specialTokens);
var text = "<|im_start|>Hello World<|im_end|>";
var encoded = tokenizer.Encode(text, new HashSet<string>(specialTokens.Keys));
Console.WriteLine(encoded.Count);
var decoded = tokenizer.Decode(encoded.ToArray());
Console.WriteLine(decoded);
In production setting, you should pre-download the BPE rank file and call TokenizerBuilder.CreateTokenizer
API to avoid downloading the BPE rank file on the fly.
You can find the model to encoder and encoder to BPE rank file link mapping in: TokenizerBuilder.cs.
C# performance benchmark
PerfBenchmark result based on PerfBenchmark.csproj:
BenchmarkDotNet=v0.13.3, OS=Windows 11 (10.0.22621.1702)
Intel Core i7-1065G7 CPU 1.30GHz, 1 CPU, 8 logical and 4 physical cores
.NET SDK=7.0.300-preview.23179.2
[Host] : .NET 6.0.16 (6.0.1623.17311), X64 RyuJIT AVX2
DefaultJob : .NET 6.0.16 (6.0.1623.17311), X64 RyuJIT AVX2
| Method | Mean | Error | StdDev |
|------- |--------:|---------:|---------:|
| Encode | 2.414 s | 0.0303 s | 0.0253 s |
Typescript implementation
Please follow README.
Contributing
We welcome contributions. Please follow this guideline.
Trademarks
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.
Product | Versions 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 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. |
.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. |
-
.NETStandard 2.0
- No dependencies.
NuGet packages (5)
Showing the top 5 NuGet packages that depend on Microsoft.DeepDev.TokenizerLib:
Package | Downloads |
---|---|
Microsoft.DotNet.Interactive.AIUtilities
Utilities for AI workload in .NET Interactive and Polyglot Notebooks |
|
LangChain.NET
LangChain.NET provides the ability to build applications with LLMs through composability |
|
Cnblogs.KernelMemory.AI.DashScope
Provide access to DashScope LLM models in Kernel Memory to generate embeddings and text |
|
FoundationaLLM.Common
FoundationaLLM.Common is a .NET library that the FoundationaLLM.Client.Core and FoundationaLLM.Client.Management client libraries share as a common dependency. |
|
ContextFlow
Package Description |
GitHub repositories (5)
Showing the top 5 popular GitHub repositories that depend on Microsoft.DeepDev.TokenizerLib:
Repository | Stars |
---|---|
microsoft/semantic-kernel
Integrate cutting-edge LLM technology quickly and easily into your apps
|
|
microsoft/WhatTheHack
A collection of challenge based hack-a-thons including student guide, coach guide, lecture presentations, sample/instructional code and templates. Please visit the What The Hack website at: https://aka.ms/wth
|
|
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!
|
|
dmitry-brazhenko/SharpToken
SharpToken is a C# library for tokenizing natural language text. It's based on the tiktoken Python library and designed to be fast and accurate.
|
|
Azure/Vector-Search-AI-Assistant
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.
|