Tobias Pitters

@ncuxomun Would you be so kind to provide an example that reproduces the error? Including the definition of the data and the model?

I would like to work on this.

@camsdixon1 yes, just need to upload the dataset to huggingface. I somehow forgot that.

Thanks for your interest in shap and its future. 1 1/2 years went by and there are a couple active maintainers here and we do our best to provide you...

Could you please show me where the typo is exactly? I'm somehow missing it

Could you please try: `shap.explainers._deep.deep_tf.op_handlers.op_handlers["LeakyReLU"] = shap.explainers._deep.deep_tf.nonlinearity_1d(0)` Not 100% sure if this results in correct shap values but it should pass the call.

Resolved via #3345

I checked a couple of datasets, here is the result: Vicuna: 8032 entries contain at least one escaped backslash CodeAlpaca: 4 Dolly: 0 GradSchoolMathInstructions: 0

Updated.

@DominiqueGarmier we would just add this for the datasets that already support the `reverse_augmentation` keyword for now. Maybe if it yields good results, we can add it in the `DatasetEntry`...