1. 先安装transformers
2. 在huggingface下载模型
   模型bert-multi-cased-finetuned-xquadv1可以从huggingface中下载，具体操作方法可以参照文章https://blog.csdn.net/zhaomengsen/article/details/130616837下载
   
3. git clone就可以了
4. 然后使用pipline加载模型

from transformers import pipeline
nlp = pipeline("question-answering",model="mrm8488/bert-multi-cased-finetuned-xquadv1",tokenizer="mrm8488/bert-multi-cased-finetuned-xquadv1")

5. 测试

context = """非root用户使用HBase客户端，请确保该HBase客户端目录的属主为该用户，否则请参考如下命令修改属主"""
question = "命令是什么？"
result = nlp(question=question, context=context)
print("Answer:", result['answer'])
print("Score:", result['score'])

Answer: 修改属主
Score: 0.9437811374664307