niieani / gpt-tokenizer

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

Date Created 2023-03-22 (about a year ago)

Commits 93 (last one 7 days ago)

Stargazers 433 (4 this week)

Watchers 4 (0 this week)

Forks 35

License mit

Ranking

RepositoryStats indexes 565,600 repositories, of these niieani/gpt-tokenizer is ranked #99,036 (82nd percentile) for total stargazers, and #366,616 for total watchers. Github reports the primary language for this repository as TypeScript, for repositories using this language it is ranked #7,107/42,994.

niieani/gpt-tokenizer is also tagged with popular topics, for these it's ranked: machine-learning (#2,145/7699), openai (#462/2046), gpt-4 (#212/723), gpt-3 (#139/587)

Other Information

niieani/gpt-tokenizer has 1 open pull request on Github, 8 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 4 open issues and 31 closed issues.

There have been 18 releases, the latest one was published on 2024-09-23 (7 days ago) with the name 2.4.0.

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

All Topics

bpe gpt-2 gpt-3 gpt-4 gpt-4o openai decoder encoder tokenizer machine-learning

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

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

Yearly Commits

Commits to the default branch (main) per year

Issue History

Languages

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

updated: 2024-09-30 @ 07:34am, id: 617290848 / R_kgDOJMscYA