Skip to main content

Auditing large language models made easy.

Project description

Fiddler Auditor

Auditing Large Language Models made easy!

lint test

What is Fiddler Auditor?

Fiddler Auditor Capabilities

Language models enable companies to build and launch innovative applications to improve productivity and increase customer satisfaction. However, it’s been known that LLMs can hallucinate, generate adversarial responses that can harm users, and even expose private information that they were trained on when prompted or unprompted. It's more critical than ever for ML and software application teams to minimize these risks and weaknesses before launching LLMs and NLP models. As a result, it’s important for you to include a process to audit language models thoroughly before production. The Fiddler Auditor enables you to test LLMs and NLP models, identify weaknesses in the models, and mitigate potential adversarial outcomes before deploying them to production.

Features and Capabilities

Fiddler Auditor Flow

Fiddler Auditor supports

  • Red-teaming LLMs for your use-case with prompt perturbation
  • Integration with LangChain
  • Custom evaluation metrics
  • Generative and Discriminative NLP models
  • Comparison of LLMs

Example Report An example report generated by the Fiddler Auditor for text-davinci-003.

Installation

From PyPI

Auditor is available on PyPI and we test on Python 3.8 and above. We recommend creating a virtual python environment and installing using the following command

pip install fiddler-auditor

From source

You can install from source after cloning this repo using the following command

pip install .

Quick-start guides

Contribution

We are continuously updating this library to support language models as they evolve.

  • Contributions in the form of suggestions and PRs to Fiddler Auditor are welcome!
  • If you encounter a bug, please feel free to raise issues in this repository.

For step-by-step instructions follow the Contrubution Guide.

Community

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

fiddler-auditor-0.0.5.tar.gz (270.3 kB view details)

Uploaded Source

Built Distribution

fiddler_auditor-0.0.5-py3-none-any.whl (276.1 kB view details)

Uploaded Python 3

File details

Details for the file fiddler-auditor-0.0.5.tar.gz.

File metadata

  • Download URL: fiddler-auditor-0.0.5.tar.gz
  • Upload date:
  • Size: 270.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.13

File hashes

Hashes for fiddler-auditor-0.0.5.tar.gz
Algorithm Hash digest
SHA256 e67bcc202d12d2ad06041aab8f55827f23022b0910eda1c95519c471f304e8f0
MD5 c93fdc2d44d75cc9254d1019027d641e
BLAKE2b-256 6c027707d1016b36697bcf5ec84b0bc0e3daf4e345ed95eab7a486c5004b8ab1

See more details on using hashes here.

File details

Details for the file fiddler_auditor-0.0.5-py3-none-any.whl.

File metadata

File hashes

Hashes for fiddler_auditor-0.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 d27874c3d0da5f328b7e4605b84bb3ebaaf12e6061227be08e29713df23bd0a8
MD5 66bad6db59afded4c1982b695b629c63
BLAKE2b-256 74598bacdb31c1d413e34c228f7f7072359ad35d66bbe234cb1de945e45a9179

See more details on using hashes here.

Supported by

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