Skip to main content

milkwashy

The Python half of milkwash: does an LLM paraphrase pass wash a statistical text watermark out of a document?

milkwashy takes long source texts, splits them into 2–8 sentence chunks, rewrites every chunk through a randomly assigned rephrase prompt, and repeats the run against every model a local OpenAI-compatible server can serve. Chunk assembly is done by the Rust extension milkwashr.

uv pip install milkwashy

milkwashy init_config       # TOML config in the platformdirs location
milkwashy gen_indata        # write the four seed texts to 01-indata/
milkwashy models            # list models (LM Studio via `lms`, others via /v1/models)
milkwashy plan              # show the chunk + prompt plan, no inference
milkwashy run --limit 5     # sweep the 5 smallest models

Full documentation: https://github.com/twardoch/milkwash

License

Apache-2.0

Release files for milkwashy 1.0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for milkwashy 1.0.0
File Size Uploaded
milkwashy-1.0.0.tar.gz 23.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for milkwashy 1.0.0
File Interpreter ABI Platform
milkwashy-1.0.0-py3-none-any.whl Python 3 none any Details

Total release size: 45.0 kB

Release files / milkwashy-1.0.0.tar.gz

Download URL milkwashy-1.0.0.tar.gz
Size 23.2 kB
Tags Source
SHA-256 checksum
How to use checksums
83f3241e3f2d054f8bf972468e8939c845fba6c2a9e217a63af3d90b98d9da97
BLAKE2b-256 checksum
How to use checksums
4d251372f1d49705407671447740ac8d5a6f0480ca9eabbc0abd2a3e7168334c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.3 {"installer":{"name":"uv","version":"0.12.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / milkwashy-1.0.0-py3-none-any.whl

Download URL milkwashy-1.0.0-py3-none-any.whl
Size 21.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
bdf298328d1195053014366e0140a642afa5eaeff3cb7e226c53c52bddbcb288
BLAKE2b-256 checksum
How to use checksums
2f39ea4a99ea4a074fe7e496fce1269f286c645f8be27bc7e938a02d9dc4c98a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.3 {"installer":{"name":"uv","version":"0.12.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release history Release notifications | RSS feed

1.0.1

2 release files

This release

1.0.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page