Minor error in Finetuning example code

In 'freeze' method, there is trivial error i think.

When user intend to freeze attention layers, user will set freeze_attn=True.

But, there is no layers contained 'attn' in names of model.module.named_parameters()! (It can not filtered with condition "elif 'attn' in name:")
So, when user freezes 'other' layers, layers contained 'attention' will be freezed, too.

It will be proper to revise "'attn' in name" to "'attention' in name".

Anyway, thank you all developers of ruDALL-E for providing awesome pre-trained model!