Yang Wenzhuo

Please try to run the code using GPU. SHAP for text is not very efficient, so we recommend using integrated-gradient to generate explanations for large language models. Here are some...

If you run this code at the first time, the code will download the large pretrained language model, it will take more time. Could you run this script again after...

There is no difference in efficiency between NLPExplainer or using individual explainers. NLPExplainer acts as an explainer factory. Which version of polyjuice was installed?

Thanks a lot! We will check this issue.

Thanks for raising this issue. We will add it to backlogs for future updates.

Does the dashboard work well in this case (as shown in the tutorial)? https://github.com/salesforce/OmniXAI/blob/main/tutorials/tabular_classification.ipynb

If this tutorial also has errors, could you please list your python, plotly dash, ipython version?

Besides ipython_plot, you can also try the following code: fig = explanations_lime.plotly_plot(index=0, class_names=class_names) fig.show()

Could you please try a new conda environment and install omnixai? I’m not sure what caused this problem.

Another option is to call “plot” function instead of ipython plot and plotly plot, “plot” uses matplotlib to draw figures.