pangolinn is a Python library for neural network developers that contains test suites aimed at finding bugs (if any) in newly-created models. Each test suite is dedicated to test a specific property of an architecture (model), and it does not require pre-trained weights.

Besides the Github repository with the source code, pangolinn is also available on PyPi and its full documentation is listed on readthedocs.

Licence

pangolinn is licensed under Apache Version 2.0.

Credits

If using this repository, please consider citing:

@inproceedings{papi-et-al-2024-when,
  title={{When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP}},
  author={Papi, Sara and Gaido, Marco and Pilzer, Andrea and Negri, Matteo},
  booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
  address = "Bangkok, Thailand",
  year={2024}
}