Skip to main content

this is the initial version for myself usage

example usage:

from llm_watermark import assembly_qwen3, huggingface_model


wm_model: huggingface_model = assembly_qwen3("8B")
prompt = "Write a short story about a robot learning to love."
messages = [{"role": "user", "content": prompt}]

wm_response = wm_model.generate(messages, do_watermark=True, max_new_tokens=256)
print("Watermarked Response:", wm_response)
print(wm_model.detect_watermark(wm_response))
print("----------------")

non_wm_response = wm_model.generate(messages, do_watermark=False, max_new_tokens=256)
print("Non-Watermarked Response:", non_wm_response)
print(wm_model.detect_watermark(non_wm_response))

Metadata

Release files for llm-watermark 0.1.18

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

Source distribution (sdist)

Source distribution for llm-watermark 0.1.18
File Size Uploaded
llm_watermark-0.1.18.tar.gz 14.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for llm-watermark 0.1.18
File Interpreter ABI Platform
llm_watermark-0.1.18-py3-none-any.whl Python 3 none any Details

Total release size: 36.8 kB

Release files / llm_watermark-0.1.18.tar.gz

Download URL llm_watermark-0.1.18.tar.gz
Size 14.8 kB
Tags Source
SHA-256 checksum
How to use checksums
3c4f9ed714f1e0bc7508e1f77002f913fd8062fcf05fb69b4b5ffd561c45ca9a
BLAKE2b-256 checksum
How to use checksums
5e1bb442754948a22e4302843db1a97d9ea8c66ee5ffbc8d5c39e087f9da6b25
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.10

Release files / llm_watermark-0.1.18-py3-none-any.whl

Download URL llm_watermark-0.1.18-py3-none-any.whl
Size 22.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7cd83c876cdbb892a88002ed22f862c1750d89c8037e268f1b4f3397cc08045a
BLAKE2b-256 checksum
How to use checksums
faed1de610bd373367ad3c498e9083e1ee61ca99bd7fbb03860d09dea18a555d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.10

Release history Release notifications | RSS feed

This release

0.1.18 This release

2 release files

0.1.13

1 release file

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