from transformers import BertTokenizer

tokenizer = BertTokenizer.from_pretrained("bert-base-cased")

sequence = "A Titan RTX has 24GB of VRAM"

tokenized_sequence = tokenizer.tokenize(sequence)

print(tokenized_sequence)

报错位置：

tokenizer = BertTokenizer.from_pretrained('bert-base-cased')

解决办法：

将双引号改为单引号。