Metadata-Version: 2.1
Name: aiscan
Version: 0.1.0
Summary: Scan AI models for problems
Home-page: https://github.com/IQTLabs/aiscan
Author: JJ Ben-Joseph
Author-email: jbenjoseph@iqt.org
License: Apache
Keywords: machine_learning artificial_intelligence
Platform: UNKNOWN
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Requires-Dist: pandas
Requires-Dist: tabulate
Requires-Dist: torch
Requires-Dist: transformers
Requires-Dist: types-tabulate

AI Scan
~~~~~~~

This is a scanner that will scan your AI models for problems. Currently it focuses on bias testing. It is currently pre-alpha.


How to Use
~~~~~~~~~~

First install it:

::

    pip install aiscan


Run it in this manner (currently supports models from HuggingFace's repository):

::

    aiscan --huggingface roberta-base --task fill-mask

Here is another example with a different bias task.

::

    aiscan --huggingface cross-encoder/nli-distilroberta-base --task zero-shot-classification

That's it for now. More will come.


Future Work
~~~~~~~~~~~~

* More bias tests. More metrics for bias testing based on the research in the field.
* Integration with other types of testing (eg. adversarial robustness)
* More kinds of models besides HuggingFace models. We are especially interested in MLFlow integration.
* Documentation.

Please contribute if you can. Help is always helpful.

License
~~~~~~~

Apache

Credit
~~~~~~

A project of IQT Labs.


