Fine tuning image transformer on higher resolution

Hi,

I’m findind hard to achieve to set the interporlate_pos_encoding = True by redefining the model’s forward method.
Could you make a brief step by step case on how to do so in order to train the model, and not just make a forward pass?

I thought it was just about modifying the model.config which feeds the module parameters, as one can set the output_attentions = True per example, but I see is not the same case for the inteporlate_pos_encoding.

Thank you!