Minor error during sevenn_inference

[chlwjd1234]

*Dependencies
torch == 2.1.2
torch-geometric == 2.5.2
numpy == 1.26.4
sevenn == 0.10.1

Minor error report. During the sevenn_inference with the attached tmp3 file, I got error below.
tmp3.txt (extracted from omat24 dataset)

Traceback (most recent call last):
  File "/user/hansw/anaconda3/envs/ame=PLUMED7/bin/sevenn_inference", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "/user/hansw/JM/Packages/SevenNet/sevenn/main/sevenn_inference.py", line 50, in main
    inference(
  File "/user/hansw/JM/Packages/SevenNet/sevenn/scripts/inference.py", line 249, in inference
    for batch in tqdm(loader):
  File "/user/hansw/anaconda3/envs/ame=PLUMED7/lib/python3.11/site-packages/tqdm/std.py", line 1181, in __iter__
    for obj in iterable:
  File "/user/hansw/anaconda3/envs/ame=PLUMED7/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 630, in __next__
    data = self._next_data()
           ^^^^^^^^^^^^^^^^^
  File "/user/hansw/anaconda3/envs/ame=PLUMED7/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 674, in _next_data
    data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/user/hansw/anaconda3/envs/ame=PLUMED7/lib/python3.11/site-packages/torch/utils/data/_utils/fetch.py", line 54, in fetch
    return self.collate_fn(data)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/user/hansw/anaconda3/envs/ame=PLUMED7/lib/python3.11/site-packages/torch_geometric/loader/dataloader.py", line 27, in __call__
    return Batch.from_data_list(
           ^^^^^^^^^^^^^^^^^^^^^
  File "/user/hansw/anaconda3/envs/ame=PLUMED7/lib/python3.11/site-packages/torch_geometric/data/batch.py", line 97, in from_data_list
    batch, slice_dict, inc_dict = collate(
                                  ^^^^^^^^
  File "/user/hansw/anaconda3/envs/ame=PLUMED7/lib/python3.11/site-packages/torch_geometric/data/collate.py", line 109, in collate
    value, slices, incs = _collate(attr, values, data_list, stores,
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/user/hansw/anaconda3/envs/ame=PLUMED7/lib/python3.11/site-packages/torch_geometric/data/collate.py", line 253, in _collate
    value_dict[key], slice_dict[key], inc_dict[key] = _collate(
                                                      ^^^^^^^^^
  File "/user/hansw/anaconda3/envs/ame=PLUMED7/lib/python3.11/site-packages/torch_geometric/data/collate.py", line 239, in _collate
    value = torch.tensor(values)
            ^^^^^^^^^^^^^^^^^^^^
TypeError: new(): invalid data type 'str'

The error seems to be caused by "elements=InF" in the datafile. This seems to be considered as infinity , not indium fluoride.
When I print the 'elements' key from the saved graph file, it says

'elements': ['ZrCl', 'ZrCl', 'FeMoP', 'FeMoP', 'FeMoP', inf, 'KO', 'KO', inf, 'ErBRu', 'ZnPS', 'ZnPS', 'KO', inf]

And simply changing InF to arbitrary string removes the error.