Pretrained model: size mismatch

[tow70]

I get the following error when trying to load the pretrained model from www.space.ntu.edu.tw:

RuntimeError: Error(s) in loading state_dict for EncoderRNN:
size mismatch for embedding.weight: copying a param with shape torch.Size([92383, 512]) from checkpoint, the shape in current model is torch.Size([92391, 512]).

The sizes seem to be different from each other. How can I make it work?

[hegebharat]

When I load the pretrained model as mentioned in the Read me file.
I got the below Error
RuntimeError: Error(s) in loading state_dict for EncoderRNN:
Missing key(s) in state_dict

The sizes seem to be different from each other. How can I make it work?