cdpierse/transformers-interpret

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.

语言：Jupyter Notebook · GitHub 星标：1,417 · Fork：99

话题：captum · computer-vision · deep-learning · explainable-ai · interpretability · machine-learning · model-explainability · natural-language-processing

在 GitHub 上查看原仓库