Metadata-Version: 2.4
Name: wisent-guard
Version: 0.4.18
Summary: Monitor and guard against harmful content in language models
Home-page: https://github.com/yourusername/wisent-activation-guardrails
Author: Wisent Team
Author-email: your.email@example.com
Keywords: nlp,machine learning,language models,safety,guardrails,lm-evaluation-harness
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch>=1.9.0
Requires-Dist: transformers>=4.20.0
Requires-Dist: tqdm>=4.50.0
Requires-Dist: scikit-learn>=0.24.0
Requires-Dist: pandas>=1.2.0
Requires-Dist: numpy>=1.21.0
Requires-Dist: datasets>=2.0.0
Requires-Dist: sentence-transformers>=2.0.0
Requires-Dist: faiss-cpu>=1.7.0
Provides-Extra: harness
Requires-Dist: lm-eval==0.4.8; extra == "harness"
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license-file
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# Wisent-Guard

<p align="center">
  <a href="https://github.com/wisent-ai/wisent-guard/stargazers">
    <img src="https://img.shields.io/github/stars/wisent-ai/wisent-guard" alt="stars" />
  </a>
  <a href="https://pypi.org/project/wisent-guard">
    <img src="https://static.pepy.tech/badge/wisent-guard" alt="PyPI - Downloads" />
  </a>
  <br />
</p>

<p align="center">
  <img src="wisent-guard-logo.png" alt="Wisent Guard" width="200">
</p>

A Python package for latent space monitoring and guardrails. Delivered to you by the [Wisent](https://wisent.ai) team led by [Lukasz Bartoszcze](https://lukaszbartoszcze.com).

## Overview

Wisent-Guard allows you to control your AI by identifying brain patterns corresponding to responses you don't like, like hallucinations or harmful outputs. We use contrastive pairs of representations to detect when a model might be generating harmful content or hallucinating. Learn more at https://www.wisent.ai/wisent-guard.  


## License

This project is licensed under the MIT License - see the LICENSE file for details. 
