bitcannon
crates.ioSIMD Unicode atom classification + bitstream pre-tokenization: one classify pass into byte-exact token spans (cl100k, o200k, GPT-2/ByteLevel, DeepSeek, Whitespace, Bert, ...).
Latest v0.1.0-rc.3 · Oct 19, 2026
Downloads
No download history yet.
Linked repositories
| ## | RepositoryRepository | ConnectionConnection |
|---|---|---|
| 1 | huggingface/tokenizers | Source package · Manifest |
Recent releases
| Version | Published |
|---|---|
| 0.1.0-rc.3 | Oct 19, 2026 |
| 0.1.0-rc.2 | Sep 21, 2026 |
| 0.1.0-rc.1 | Sep 21, 2026 |
| 0.1.0-dev.0 | Sep 21, 2026 |