niieani / gpt-tokenizer

The fastest JavaScript BPE Tokenizer Encoder Decoder for OpenAI's GPT-2 / GPT-3 / GPT-4 / GPT-4o / GPT-o1. Port of OpenAI's tiktoken with additional features.

niieani
niieani
Date Created 2023-03-22 (2 years ago)
Commits 118 (last one 24 days ago)
Stargazers 541 (3 this week)
Watchers 4 (0 this week)
Forks 38
License mit
Ranking

RepositoryStats indexes 632,869 repositories, of these niieani/gpt-tokenizer is ranked #89,459 (86th percentile) for total stargazers, and #366,084 for total watchers. Github reports the primary language for this repository as TypeScript, for repositories using this language it is ranked #6,783/49,880.

niieani/gpt-tokenizer is also tagged with popular topics, for these it's ranked: machine-learning (#2,002/8407),  openai (#507/2485),  gpt-4 (#199/768),  gpt-3 (#122/589)

Other Information

niieani/gpt-tokenizer has 2 open pull requests on Github, 12 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 4 open issues and 39 closed issues.

There have been 28 releases, the latest one was published on 2025-03-05 (24 days ago) with the name 2.9.0.

Homepage URL: https://gpt-tokenizer.dev

Star History

Github stargazers over time

60060050050040040030030020020010010000May '23May '23Jul '23Jul '23Aug '23Aug '23Oct '23Oct '23Nov '23Nov '2320242024Feb '24Feb '24Apr '24Apr '24Jun '24Jun '24Jul '24Jul '24Aug '24Aug '24Oct '24Oct '24Nov '24Nov '2420252025Feb '25Feb '25

Watcher History

Github watchers over time, collection started in '23

554.54.5443.53.5332.52.5221.51.511Jun '23Jun '23Jul '23Jul '23Aug '23Aug '23Sep '23Sep '23Oct '23Oct '23Nov '23Nov '23Dec '23Dec '2320242024Feb '24Feb '24Mar '24Mar '24Apr '24Apr '24May '24May '24Jun '24Jun '24Jul '24Jul '24Aug '24Aug '24Sep '24Sep '24Oct '24Oct '24Nov '24Nov '24Dec '24Dec '2420252025Feb '25Feb '25Mar '25Mar '25

Recent Commit History

79 commits on the default branch (main) since jan '22

808070706060505040403030202010100020232023Jul '23Jul '2320242024Jul '24Jul '2420252025

Yearly Commits

Commits to the default branch (main) per year

45454040353530302525202015151010550020242024

Issue History

Total Issues
Open Issues
Closed Issues
454540403535303025252020151510105500May '23May '23Jul '23Jul '23Aug '23Aug '23Sep '23Sep '23Nov '23Nov '2320242024Feb '24Feb '24Apr '24Apr '24May '24May '24Jul '24Jul '24Aug '24Aug '24Sep '24Sep '24Nov '24Nov '2420252025Feb '25Feb '25

Languages

The primary language is TypeScript but there's also others...

TypeScriptTypeScriptShellShell

updated: 2025-03-27 @ 09:56pm, id: 617290848 / R_kgDOJMscYA