Table of Contents

Class TokenizerGpt3

Namespace
OpenAI.Tokenizer.GPT3
Assembly
AntRunnerLib.dll

GPT3 Tokenizer.

public static class TokenizerGpt3
Inheritance
System.Object
TokenizerGpt3
Inherited Members
System.Object.Equals(System.Object)
System.Object.Equals(System.Object, System.Object)
System.Object.GetHashCode()
System.Object.GetType()
System.Object.MemberwiseClone()
System.Object.ReferenceEquals(System.Object, System.Object)
System.Object.ToString()

Methods

Encode(String, Boolean)

Encode This method use LF style EOL, if you use CR LF style EOL you need to set cleanUpWindowsEOL to true

public static IEnumerable<int> Encode(string text, bool cleanUpCREOL = false)

Parameters

text System.String
cleanUpCREOL System.Boolean

set it true to get rid of CR

Returns

IEnumerable<System.Int32>

TokenCount(String, Boolean)

Get token count. This method use LF style EOL, if you use CR LF style EOL you need to set cleanUpWindowsEOL to true

public static int TokenCount(string text, bool cleanUpCREOL = false)

Parameters

text System.String
cleanUpCREOL System.Boolean

set it true to get rid of CR

Returns

System.Int32