Fixed some parameter discrepancy for MDAM

[bokveizen]

Fixed some parameter discrepancy for MDAM. But the encoder still raises ValueError. See GraphAttentionEncoder at models/zoo/mdam/encoder.py. ValueError: too many values to unpack (expected 3); here self.attention_layer(h_old) is a single tensor h_new, attn, V = self.attention_layer(h_old)

[fedebotu]

This model was working, but we did not complete the beam search part, mostly because some newer methods are more efficient anyway. If someone would like to work on it we'd be glad to delegate ;)

[fedebotu]

Note: an update was pushed but forgot to discuss here - now it seems to be working, although the beam search part is still missing. However I would consider this as lower priority at the moment