checkpoint argument error

[Foreist]

Traceback (most recent call last):
File "demo_app.py", line 38, in
curse_model, hate_model = get_modules()
File "/opt/conda/lib/python3.8/site-packages/streamlit/caching.py", line 573, in wrapped_func
return get_or_create_cached_value()
File "/opt/conda/lib/python3.8/site-packages/streamlit/caching.py", line 557, in get_or_create_cached_value
return_value = func(*args, **kwargs)
File "demo_app.py", line 31, in get_modules
curse = TextClassificationStudentModule.load_from_checkpoint(curse, device)
File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/core/module.py", line 1531, in load_from_checkpoint
loaded = _load_from_checkpoint(
File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/core/saving.py", line 63, in _load_from_checkpoint
checkpoint = _pl_migrate_checkpoint(
File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/utilities/migration/utils.py", line 113, in _pl_migrate_checkpoint
old_version = _get_version(checkpoint)
File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/utilities/migration/utils.py", line 136, in _get_version
return checkpoint["pytorch-lightning_version"]
KeyError: 'pytorch-lightning_version'

서비스하시는 페이지도 동일한 에러가 발생합니다.
모델에 한 번은 접근이 돼야 저런 인자를 가짜로라도 줄 수 있을 텐데 혹시 해결하는 방법이 있을까요?