Transformer-Explainability
by hila-chefer · GitHub
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
# attention-matrix# attention-visualization# bert# bert-model
⭐ Stars
2k
🍴 Forks
260
📜 License
MIT
Commercial use OK📅 Created
2020
🔄 Last commit
2 yr ago
🏷️ Category
attention-matrix
💻 Language
Jupyter Notebook
📈 Star history
📊 Star history will build up here over the coming days (1 data point recorded so far).
📄 About
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
🏅 Maintainer of this project?
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://opensourceai.tech/project/hila-chefer-transformer-explainability.html)
🔗 Related projects
leedl-tutorial
《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
★ 16.7k · bert
PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
★ 13k · bert
clip-as-service
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
★ 12.8k · bert