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
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
1 maintainer
Metadata
1 maintainer
Release files for hbar 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| hbar-1.0.0.tar.gz | 2.5 kB | Without provenance | Details for hbar-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| hbar-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for hbar-1.0.0-py3-none-any.whl |
Total release size: 5.1 kB
Release files / hbar-1.0.0.tar.gz
| Download URL | hbar-1.0.0.tar.gz |
|---|---|
| Size | 2.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f65e8765203fb28b2ae22f032e15211096be3f9355fbf8e2cb90570fe1aec143
|
|
BLAKE2b-256 checksum How to use checksums |
925580bdcfbcffb71c55cc54a74944e2db91a24ce3cf1c45b153d7c82536a2dd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.12
|
Release files / hbar-1.0.0-py3-none-any.whl
| Download URL | hbar-1.0.0-py3-none-any.whl |
|---|---|
| Size | 2.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
13a58bd335bba9a3c88dd4f1eee338db24de30bea79de60178e1bab649f64cad
|
|
BLAKE2b-256 checksum How to use checksums |
949d9fccf6aa0ac45dac863a7e73d2925b4a62d940d3302a300f54683e805369
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.12
|
Security for hbar 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
