Failed to clone the RNN

[Gilbert189]

So, I want your character based LSTM, but whatever I do, I always get the same message:
Here's what my code looks:
user@myPC:~/char-rnn$ th train.lua -gpuid -1 -seed 1411 -num_layers 5 -print_every 5

And what I got is this:
loading data files... cutting off end of data so that the batches/sequences divide evenly reshaping tensor... data load done. Number of data batches in train: 423, val: 23, test: 0 vocab size: 65 creating an lstm with 5 layers setting forget gate biases to 1 in LSTM layer 1 setting forget gate biases to 1 in LSTM layer 2 setting forget gate biases to 1 in LSTM layer 3 setting forget gate biases to 1 in LSTM layer 4 setting forget gate biases to 1 in LSTM layer 5 number of parameters in the model: 636609 cloning criterion cloning rnn Segmentation fault (core dumped)

Can someone help me why this happens?