Othello Keras Pretrained Model : UnpicklingError

[Dimanjan]

The pretrained model in https://github.com/suragnair/alpha-zero-general/tree/master/pretrained_models/othello/keras cannot be loaded.

Code:

import torch
model=torch.load("6x6 checkpoint_145.pth.tar",map_location='cpu')

Error Message:

---------------------------------------------------------------------------
UnpicklingError                           Traceback (most recent call last)
Cell In [2], line 2
      1 import torch
----> 2 model=torch.load("6x6 checkpoint_145.pth.tar",map_location='cpu')

File c:\Users\entdi\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py:713, in load(f, map_location, pickle_module, **pickle_load_args)
    711             return torch.jit.load(opened_file)
    712         return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
--> 713 return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)

File c:\Users\entdi\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py:920, in _legacy_load(f, map_location, pickle_module, **pickle_load_args)
    914 if not hasattr(f, 'readinto') and (3, 8, 0) <= sys.version_info < (3, 8, 2):
    915     raise RuntimeError(
    916         "torch.load does not work with file-like objects that do not implement readinto on Python 3.8.0 and 3.8.1. "
    917         f"Received object of type \"{type(f)}\". Please update to Python 3.8.2 or newer to restore this "
    918         "functionality.")
--> 920 magic_number = pickle_module.load(f, **pickle_load_args)
    921 if magic_number != MAGIC_NUMBER:
    922     raise RuntimeError("Invalid magic number; corrupt file?")

UnpicklingError: invalid load key, 'H'.

The models in other folders can be loaded with similar code, but not this one.

Also, why is this a .pth.tar file instead of .h5 ?

Sorry, if this is a naive question.