Transformer-Explainability
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
Visualize how Transformer models make decisions beyond just looking at attention scores.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytime[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
Transformer-Explainability has 2k stars on GitHub. It has been forked 260 times. Transformer-Explainability is written mainly in Jupyter Notebook. It has been in active development since 2020. Transformer-Explainability is available under the MIT license. Its main topics are attention-matrix, attention-visualization, bert, bert-model.
What is Transformer-Explainability?
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
Is Transformer-Explainability open source?
Transformer-Explainability is an open-source project. It is released under the MIT license.
Is Transformer-Explainability free?
Yes. Transformer-Explainability is free and open source — you can use, modify and self-host it.
What license does Transformer-Explainability use?
Transformer-Explainability is available under the MIT license.
What language is Transformer-Explainability written in?
Transformer-Explainability is written mainly in Jupyter Notebook.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/hila-chefer-transformer-explainability.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.