module = nn.Concat(dim)
Concat concatenates the output of one layer of "parallel" modules along the provided dimension dim: they take the same inputs, and their output is concatenated. 
mlp=nn.Concat(1);
mlp:add(nn.Linear(5,3))
mlp:add(nn.Linear(5,7))
require "lab"
print(mlp:forward(lab.randn(5)))
which gives the output: 
 0.7486
 0.1349
 0.7924
-0.0371
-0.4794
 0.3044
-0.0835
-0.7928
 0.7856
-0.1815
[torch.Tensor of dimension 10]