problem：
RuntimeError: Error(s) in loading state_dict for BertForTokenClassification:size mismatch for bert.embeddings.word_embeddings.weight: copying a param with shape torch.Size([21128, 768]) from checkpoint, the shape in current model is torch.Size([119547, 768]).
solution：
torch的参数和model的不一致
我原来的代码是
model = AutoModelForTokenClassification.from_pretrained("bert-base-multilingual-cased", num_labels=len(label_names))
重新安装pytorch即可
conda install pytorch==1.7.1
