d_ff = 4*d_model

class PoswiseFeedForwardNet(nn.Module):
    def __init__(self):
        super(PoswiseFeedForwardNet, self).__init__()
        self.fc1 = nn.Linear(d_model, d_ff)
        self.fc2 = nn.Linear(d_ff, d_model)

    def forward(self, x):
        # (batch_size, len_seq, d_model) -> (batch_size, len_seq, d_ff) -> (batch_size, len_seq, d_model)
        return self.fc2(torch.nn.functional.gelu(self.fc1(x)))