north-tokenizer / README.md
arthu1's picture
Upload README.md with huggingface_hub
d151ff5 verified
---
license: apache-2.0
tags:
- sentencepiece
- tokenizer
---
# North Tokenizer
Shared SentencePiece tokenizer for the North Star model family:
- [North Air 1](https://huggingface.co/arthu1/north-air-1) — 124M, fast
- [North Star 1](https://huggingface.co/arthu1/north-star-1) — 198M, balanced
- [Wind Arc 1.5](https://huggingface.co/arthu1/wind-arc-1.5) — 198M, deep reasoning
**Vocabulary size:** 32,000
**Format:** SentencePiece (`.model` file)
```python
import sentencepiece as spm
sp = spm.SentencePieceProcessor(model_file="tokenizer.model")
ids = sp.encode("Hello world", out_type=int)
```