bert word embedding model from a local bin file

when i am trying to load the model from the local file using the path with this instruction:
word_embedding_model = models.BERT('models/bert-base-uncased-pytorch_model.bin')
i am getting this error:
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 0: invalid start byte

Reproduce the failure from the issue using models.BERT with the local bert-base-uncased-pytorch_model.bin path, then inspect the BERT model-loading entry point and how it reads local files. Done means determining whether that local .bin file can be loaded through this instruction without the UnicodeDecodeError, with the expected behavior documented or covered by a relevant test.

Written by the indexing model from the issue text.