Skip to main content

Monitor and guard against harmful content in language models

Project description

Wisent-Guard

stars PyPI - Downloads

Wisent Guard

A Python package for latent space monitoring and guardrails. Delivered to you by the Wisent team led by Lukasz Bartoszcze.

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.

Project details


Download files

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

Source Distribution

wisent_guard-0.4.32.tar.gz (540.5 kB view details)

Uploaded Source

Built Distribution

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

wisent_guard-0.4.32-py3-none-any.whl (633.2 kB view details)

Uploaded Python 3

File details

Details for the file wisent_guard-0.4.32.tar.gz.

File metadata

  • Download URL: wisent_guard-0.4.32.tar.gz
  • Upload date:
  • Size: 540.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.14

File hashes

Hashes for wisent_guard-0.4.32.tar.gz
Algorithm Hash digest
SHA256 8fa697d7fd6515cce6653e37675fab228005f68f2cd0472e12a4151ec11a5af1
MD5 112db75195ae80b0483a6bc89017d005
BLAKE2b-256 c5cbfb9f377e282113d419a44307dcb51e03d32db33eaa60a9b3cb0a308a7e90

See more details on using hashes here.

File details

Details for the file wisent_guard-0.4.32-py3-none-any.whl.

File metadata

  • Download URL: wisent_guard-0.4.32-py3-none-any.whl
  • Upload date:
  • Size: 633.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.14

File hashes

Hashes for wisent_guard-0.4.32-py3-none-any.whl
Algorithm Hash digest
SHA256 fb793a5bb98f15833cbd8c8a678afdcfbeaf0008528b6b4a766561c2ae34b244
MD5 45dcf7bb522ed2498249025942f7ffb3
BLAKE2b-256 846173d4e34968f3341db9cd3882ba842518bb0c5b07ddc0303c7f33ba88f842

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page