danny50610/bpe-tokeniser 问题修复 & 功能扩展

解决BUG、新增功能、兼容多环境部署,快速响应你的开发需求

邮箱:yvsm@zunyunkeji.com | QQ:316430983 | 微信:yvsm316

danny50610/bpe-tokeniser

最新稳定版本:0.3.0

Composer 安装命令:

composer require danny50610/bpe-tokeniser

包简介

PHP port for openai/tiktoken (most)

README 文档

README

PHP Test codecov Latest Stable Version Total Downloads License

PHP port for openai/tiktoken (most)

Supported encodings

  • gpt-3.5-turbo
  • gpt-4
  • gpt-4o
  • gpt-oss
  • gpt-5
  • more ...

For available encodings, see src/EncodingFactory.php

Installation

composer require danny50610/bpe-tokeniser

Example

GPT-5 (o200k_base)

use Danny50610\BpeTokeniser\EncodingFactory;

$enc = EncodingFactory::createByModelName('gpt-5-2025-08-07');

var_dump($enc->encode("hello world"));
/**
 * output: 
 * array(2) {
 *  [0]=>
 *  int(24912)
 *  [1]=>
 *  int(2375)
 * }
 */

var_dump($enc->decode($enc->encode("hello world")));
// output: string(11) "hello world"

GPT-4 / GPT-3.5-Turbo (cl100k_base)

use Danny50610\BpeTokeniser\EncodingFactory;

$enc = EncodingFactory::createByEncodingName('cl100k_base');

var_dump($enc->encode("hello world"));
/**
 * output: 
 * array(2) {
 *  [0]=>
 *  int(15339)
 *  [1]=>
 *  int(1917)
 * }
 */

var_dump($enc->decode($enc->encode("hello world")));
// output: string(11) "hello world"
use Danny50610\BpeTokeniser\EncodingFactory;

$enc = EncodingFactory::createByModelName('gpt-3.5-turbo');

var_dump($enc->decode($enc->encode("hello world")));
// output: string(11) "hello world"

统计信息

  • 总下载量: 369.2k
  • 月度下载量: 0
  • 日度下载量: 0
  • 收藏数: 10
  • 点击次数: 1
  • 依赖项目数: 1
  • 推荐数: 0

GitHub 信息

  • Stars: 10
  • Watchers: 1
  • Forks: 0
  • 开发语言: PHP

其他信息

  • 授权协议: MIT
  • 更新时间: 2023-08-19