There is a switch button, you can use it when you want to attach the data (csv) you trained your model on or a feature mapping (txt). This is useful when the values are categorical.
If you decide to upload the dataset, it should be a .csv. If you decide to upload the feature mapping, it is a .txt file.
You can only import .pkl models. But it works with joblib and pickle libraries.
You can either upload a .txt file containing the instance with the format : feature1=value1,feature2=value2,... where feature1, feature2 are the names of the columns. But you can also upload a json of your instance.
Attention !!!! If you never mention the feature names in your model or additional information, the instance should be of format : f1=...,f2=... precisely
These are specific to the kind of model you selected, it would mainly be how the explanation should be computed and the kind of explanation.