safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge

在加载 bert-base-chinese 分词器的时候出现如下错误：

Traceback (most recent call last):
  File "main.py", line 222, in <module>
    model = train()
  File "main.py", line 205, in train
    model = BiLSTMLighting(drop = dropout, hidden_dim = rnn_hidden, output_dim = class_num)
  File "main.py", line 110, in __init__
    self.model = BiLSTMClassifier(drop, hidden_dim, output_dim)  # Set up model
  File "main.py", line 84, in __init__
    self.embedding = BertModel.from_pretrained('./model/bert-base-chinese')
  File "/home/node/.local/lib/python3.8/site-packages/transformers/modeling_utils.py", line 3613, in from_pretrained
    with safe_open(resolved_archive_file, framework="pt") as f:
safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge

在网上找了很久也没有解决，最后看到有人说是模型文件的问题（我是从 魔搭社区 下载的别人上传的），重新从 Hugging face 下载了模型文件，问题便解决了。