Metadata-Version: 2.4
Name: hbar
Version: 0.2.0.post1
Summary: Quantum-inspired compression & pruning for large language models (MPO, MixT, and tensor-network friends)
Author: willwu
License: MIT
Keywords: quantum,tensor-network,mpo,compression,pruning,llm
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# ℏ hbar

**Same model. Smaller constant.**

Quantum-inspired compression & pruning for large language models —
matrix product operators (MPO), MixT, and other tensor-network tools
for making big models small.

> ħ = h/2π — the reduced Planck constant. Same physics, ~6.3× smaller.
> That's the business plan.

## Install

```bash
pip install hbar
```

## Status

🚧 Under active development — first release coming soon.

## Why "hbar"?

Every quantum state lives in a Hilbert space. Almost every model lives
in a smaller one — **hbar** finds it.

And ħ is the *reduced* Planck constant: reduction is the whole business.

## License

MIT
