Yanked

This release has been yanked by its maintainers, and will be ignored by installers, except when explicitly specified.
Consider using release 0.1.0 instead.
Reason given by maintainers: Empty placeholder, use 0.1.0.

blackbar-nano

Local-first PII detection and redaction. A 35-label NER model that runs on CPU at ~38ms per message (Apple M1), trained on ~570k synthetic rows.

Status: release in progress. This version reserves the package name; the model weights (Apache-2.0) and the full SDK land here shortly.

Benchmarks vs GLiNER2-PII (identical data): 96.9% leak-view coverage vs 95.8%, SPY public benchmark 0.518 vs 0.390 avg exact F1, ~34x faster per message.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

blackbar_nano-0.0.1.tar.gz (1.6 kB view details)

Uploaded Jul 20, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

blackbar_nano-0.0.1-py3-none-any.whl (1.8 kB view details)

Uploaded Jul 20, 2026 Python 3

File details

Details for the file blackbar_nano-0.0.1.tar.gz.

File metadata

Download URL: blackbar_nano-0.0.1.tar.gz
Upload date: Jul 20, 2026
Size: 1.6 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for blackbar_nano-0.0.1.tar.gz
Algorithm	Hash digest
SHA256	`6b89614067a4d2f0b6349202133e1ca4e6e036d2e337f77523ee3c8095d59e8b`
MD5	`b798993a4492a7fc09b0258bded00f5f`
BLAKE2b-256	`98cfc7a14d8cef0716b626640538d2befe82b9720485ef26dc935cd1f62be93f`

See more details on using hashes here.

File details

Details for the file blackbar_nano-0.0.1-py3-none-any.whl.

File metadata

Download URL: blackbar_nano-0.0.1-py3-none-any.whl
Upload date: Jul 20, 2026
Size: 1.8 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for blackbar_nano-0.0.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`92e34b595ad9f82834c08d86a4bab473618ecd00306c24f6871692a5cd52716b`
MD5	`1eace22f5f46aa55e2774ad7e930344f`
BLAKE2b-256	`00b2672f0f4042c4c8eca592151dc4477fdbeef7f6fcd441bd610677f41db825`