My pytorch worked, but all of a sudden now has issues for Roberta

All of a sudden, I ran my code and it says:
RuntimeError: Failed to import transformers.models.roberta.modeling_roberta because of the following error (look up to see its traceback):
source code string cannot contain null bytes

I have tried uninstalling torch and reinstalling it multiple times, clearing the cache, etc. Does anyone have advice on what I should try to fix this issue? Thanks

This is also how I initialize my model:
MODEL = f"cardiffnlp/twitter-roberta-base-sentiment-latest"

tokenizer = AutoTokenizer.from_pretrained(MODEL)

config = AutoConfig.from_pretrained(MODEL)

model = AutoModelForSequenceClassification.from_pretrained(MODEL)