diff --git a/models/decoder.py b/models/decoder.py index 83e4b11..f613629 100644 --- a/models/decoder.py +++ b/models/decoder.py @@ -1,7 +1,8 @@ import torch import torch.nn as nn import torch.nn.functional as F -1 + + class DecoderLayer(nn.Module): def __init__(self, self_attention, cross_attention, d_model, d_ff=None, dropout=0.1, activation="relu"):