定制 guttedgarden/tiktoken 二次开发

按需修改功能、优化性能、对接业务系统,提供一站式技术支持

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

guttedgarden/tiktoken

最新稳定版本:1.2.1

Composer 安装命令:

composer require guttedgarden/tiktoken

包简介

PHP 7.4 version of tiktoken

README 文档

README

Yethee's tiktoken library port for PHP 7.4 without the Symfony package

Installation

$ composer require guttedgarden/tiktoken

Usage

use guttedgarden\Tiktoken\EncoderProvider; $provider = new EncoderProvider(); $encoder = $provider->getForModel('gpt-3.5-turbo-0301'); $tokens = $encoder->encode('Hello world!'); print_r($tokens); // OUT: [9906, 1917, 0] $encoder = $provider->get('p50k_base'); $tokens = $encoder->encode('Hello world!'); print_r($tokens); // OUT: [15496, 995, 0]

Cache

The encoder uses an external vocabularies, so caching is used by default to avoid performance issues.

By default, the directory for temporary files is used. You can override the directory for cache via environment variable TIKTOKEN_CACHE_DIR or use EncoderProvider::setVocabCache():

use guttedgarden\Tiktoken\EncoderProvider; $encProvider = new EncoderProvider(); $encProvider->setVocabCache('/path/to/cache'); // Using the provider

Disable cache

You can disable the cache, if there are reasons for this, in one of the following ways:

  • Set an empty string for the environment variable TIKTOKEN_CACHE_DIR.
  • Programmatically:
use guttedgarden\Tiktoken\EncoderProvider; $encProvider = new EncoderProvider(); $encProvider->setVocabCache(null); // disable the cache

Limitations

  • Encoding for GPT-2 is not supported.
  • Special tokens (like <|endofprompt|>) are not supported.

License

MIT

统计信息

  • 总下载量: 17.47k
  • 月度下载量: 0
  • 日度下载量: 0
  • 收藏数: 4
  • 点击次数: 3
  • 依赖项目数: 0
  • 推荐数: 0

GitHub 信息

  • Stars: 4
  • Watchers: 0
  • Forks: 29
  • 开发语言: PHP

其他信息

  • 授权协议: MIT
  • 更新时间: 2026-01-04

承接程序开发

PHP开发

VUE

Vue开发

前端开发

小程序开发

公众号开发

系统定制

数据库设计

云部署

网站建设

安全加固