How to perform inference on already trained checkpoints.

[prateeky2806]

Hi @telxt, @ShengdingHu, @WuNein, thank you for creating this useful repository. I am trying to understand how to use this repo for some use cases.

I see that a lot of the trained checkpoints are available on the hugging face hub. I wanted to use these checkpoints to perform inference on the respective datasets to obtain the val/test set performances of these trained models. I am sure there is a way to run inference for these models available on the hub but I am not able to figure it out. Would it be possible for you to share an example command on how this can be done?

Thanks, Prateek