running `python run_FlipFlop.py` errors with `RuntimeError: rnn: hx is not contiguous`

[IanQS]

Technically I ran into two issues:

1) installing via torch

To address this, I modified requirements-torch so that the last line, pytorch=1.12.1 is instead torch==1.12.1 (note that this installs the CPU version, not the GPU version).

It might be better to just direct users to the official pytorch install page and get them to install it that way.

I've addressed this in #38

2) running the example pytorch script

The error I'm encountering isRuntimeError: rnn: hx is not contiguous

and the full stacktrace is

Traceback (most recent call last):
  File "/tmp/fixed-point-finder/examples/torch/run_FlipFlop.py", line 140, in <module>
    main()
  File "/tmp/fixed-point-finder/examples/torch/run_FlipFlop.py", line 125, in main
    model, valid_predictions = train_FlipFlop()
  File "/tmp/fixed-point-finder/examples/torch/run_FlipFlop.py", line 62, in train_FlipFlop
    losses, grad_norms = model.train(train_data, valid_data,
  File "/tmp/fixed-point-finder/examples/torch/FlipFlop.py", line 245, in train
    avg_loss, avg_norm = self._train_epoch(dataloader, optimizer)
  File "/tmp/fixed-point-finder/examples/torch/FlipFlop.py", line 278, in _train_epoch
    step_summary = self._train_step(batch_data, optimizer)
  File "/tmp/fixed-point-finder/examples/torch/FlipFlop.py", line 305, in _train_step
    batch_pred = self.forward(batch_data)
  File "/tmp/fixed-point-finder/examples/torch/FlipFlop.py", line 155, in forward
    hiddens_bxtxd, _ = self.rnn(inputs_bxtxd, initial_hiddens_1xbxd)
  File "/home/iq/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/iq/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/iq/.local/lib/python3.10/site-packages/torch/nn/modules/rnn.py", line 586, in forward
    result = _VF.rnn_tanh(input, hx, self._flat_weights, self.bias, self.num_layers,
RuntimeError: rnn: hx is not contiguous

---

OS Information from lsb_release -a:

No LSB modules are available.
Distributor ID: Ubuntu
Description:    Ubuntu 22.04.4 LTS
Release:        22.04
Codename:       jammy