Metadata-Version: 2.5
Name: laidline-transformers
Version: 1.0.1
Summary: Laidline helper for Hugging Face model.generate: adds the text watermark logits processor and records text evidence.
Project-URL: Homepage, https://laidline.com
Project-URL: Documentation, https://laidline.com/docs/quickstart
Project-URL: Changelog, https://laidline.com/docs/changelog
Author: Laidline LLC
License-Expression: LicenseRef-Laidline-Source-Available
License-File: LICENSE
Keywords: ai-act,c2pa,llm,provenance,transformers,watermark
Classifier: Development Status :: 5 - Production/Stable
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Multimedia
Classifier: Topic :: Security :: Cryptography
Requires-Python: >=3.12
Requires-Dist: laidline[text]<2,>=1.0
Description-Content-Type: text/markdown

# laidline-transformers

Helper for `model.generate(..., logits_processor=[marker.text_logits_processor(...)])`.

```python
from laidline import MarkContext, Marker
from laidline_transformers import generate_marked

marker = Marker.from_config("laidline.yaml")  # watermark.text.enabled: true
text, record = generate_marked(model, tokenizer, prompt, marker, MarkContext(), max_new_tokens=300)
# record.status is "ok", or "unmarked" with record.reason (below_min_tokens, greedy_decoding, ...)
```

The evidence entry records token counts and the completion's SHA-256 and byte length, never the prompt or text.
