I have tried to learn TrainAD, but I am not learning because of the error Transformer EncoderLayer.forward() got an unexpected keyword argument ‘is_causal’.

class TransformerEncoderLayer(nn.Module):
    def __init__(self, d_model, nhead, dim_feedforward=16, dropout=0):
        super(TransformerEncoderLayer, self).__init__()
        self.self_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
        self.linear1 = nn.Linear(d_model, dim_feedforward)
        self.dropout = nn.Dropout(dropout)
        self.linear2 = nn.Linear(dim_feedforward, d_model)
        self.dropout1 = nn.Dropout(dropout)
        self.dropout2 = nn.Dropout(dropout)

        self.activation = nn.LeakyReLU(True)

    def forward(self, src,src_mask=None, src_key_padding_mask=None, **kwargs):
        src2 = self.self_attn(src, src, src)[0]
        src = src + self.dropout1(src2)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
        src = src + self.dropout2(src2)
        return src

What should I fix here?

def forward(self, src,src_mask=None, src_key_padding_mask=None, **kwargs)
Said I could put **kwargs in but it didn’t work for me.