Hello and welcome to the Fun With Word Embeddings Practice repository. This code repository is a companion to the chapter, "Combatting Bias in Large Language Models" inside of the book Bias in Machine Learning published by McGraw Hill.
Instructors will be able to get students familiar with word embeddings, how they are created using code and how they can be visualized. This notebook is simply a primer and should be used as a way to get students interested in bias mitigation techniques for language models.
Responsible AI Resources for Large Language Models:
- Model Cards: https://modelcards.withgoogle.com/about
- Repository Tensorflow: https://github.com/tensorflow/model-card-toolkit
- DiCE: https://github.com/interpretml/DiCE
- Shap: https://github.com/shap/shap
- Tensorflow Responsible AI Toolkit: https://www.tensorflow.org/responsible_ai/tutorials
- Microsoft Responsible AI toolbox: https://github.com/microsoft/responsible-ai-toolbox
*If you have any trouble, submit in the bug tracker above.