PrithivirajDamodaran / Interpret

The PyTorch implementation the Smooth Grad [https://arxiv.org/pdf/1706.03825.pdf] and Integrated Gradients [https://arxiv.org/pdf/1703.01365.pdf] for NLP Models. Fixed for latest HF changes by Prithivi Da

Interpret

The PyTorch implementation the Smooth Grad and Integrated Gradients for NLP Models.

This repository based on the Allen NLP Interpret Module but for HuggingFace.

The example of the output:

Integrate your own task-specific model

To integrate your model simply override the forward_step and update_output methods of base class SaliencyInterpreter.