Running backend server results in: Found no NVIDIA driver on your system.

[Hi-Angel]

First of, the README is unclear because it suggests running a python EXAMPLE_server.py to run a local server where I presume you might type questions, but there's no such file, and there's a vague comment that points to dstc9_server.py file instead.

So I presume you actually supposed to run python examples/dstc9/dstc9_server.py, however doing so results in it downloading 850M of some unknown data, and then it fails with the error.

Steps to reproduce

On any system without NVidia GPU enter the project and run the following commands:

 λ python examples/dstc9/dstc9_server.py
Downloading: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.18k/1.18k [00:00<00:00, 978kB/s]
Downloading: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 850M/850M [03:51<00:00, 3.85MB/s]
Traceback (most recent call last):
  File "/home/constantine/Projects/GODEL/examples/dstc9/dstc9_server.py", line 57, in <module>
    main()
  File "/home/constantine/Projects/GODEL/GODEL/server.py", line 56, in main
    model = model.to(args.device)
  File "/home/constantine/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 907, in to
    return self._apply(convert)
  File "/home/constantine/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 578, in _apply
    module._apply(fn)
  File "/home/constantine/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 601, in _apply
    param_applied = fn(param)
  File "/home/constantine/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 905, in convert
    return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
  File "/home/constantine/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 216, in _lazy_init
    torch._C._cuda_init()
RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx

Expected

There should be no error, because the project isn't specific to any GPU, and I have AMD and Intel GPU drivers on my system

Actual

There's an error about a GPU which isn't even present on my system

Additional information

I had to apply this PR to make it work.