Minor Code refinement for performance

[dxyzx0]

In model.py

1. These two for-loops in the model.py lowers the speed of training and testing, since it doesn't utilize broadcasting of matrix operation in torch.
   In main.py and mol_featurizer.py
2. I trained my model on a larger dataset with protein length up to 2000 and 70w interactions. We should use joblib to load and dump large files.

Further Refinement:
I like this model very much. I use this model for production. Hence, there's my refinement of the code https://github.com/DingXiangYuanZhiXing/transformerCPI_DTA

[comeonzyx]

Hello,i would like to ask that do you have "dataset/celegans_uniprot.csv"?

[shaonvpiaoyaodesilian]

The bert.pkl file at this address is damaged. https://github.com/myzhengSIMM/transformerCPI2.0/releases. Can you upload a new one? Thanks