Metadata-Version: 2.4
Name: tokenlearn-static-model
Version: 0.1.1
Summary: Rust-accelerated static embedding model with baked-in 10k/64d/int8 weights.
Requires-Python: >=3.9
Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM

# Rust + Python Inference

This package provides:
- A Rust encoder core (`tokenizers + safetensors`) for static Model2Vec-style embeddings.
- A Python wrapper API:
  - `from static_model import get_embeddings`

The default `10k/64d/int8` model files are baked into the package under `static_model/model/`.

## Python Install

```bash
pip install .
```

## Python Usage

```python
from static_model import get_embeddings

embeddings = get_embeddings(["Hello", "World"])  # list[list[float]]
single_embedding = get_embeddings("Hello World")  # list[float]
```

