language:

• hu pipeline_tag: question-answering

该模型是基于milqa数据集对deepset/xlm-roberta-large-squad2进行微调的版本。

安装大型RoBERTa模型所需依赖包：

sentencepiece==0.1.97
protobuf==3.20.0

使用方法：

from transformers import pipeline
qa_pipeline = pipeline(
  "question-answering",
  model = "ZTamas/xlm-roberta-large-squad2-qa-milqa-impossible",
  tokenizer = "ZTamas/xlm-roberta-large-squad2-qa-milqa-impossible",
  device = 0,                      #GPU选择，-1表示使用CPU
  handle_impossible_answer = True,  #处理无答案情况
  max_answer_len = 50              #可调整最大答案长度
  )

predictions = qa_pipeline({
    'context': context,            #上下文文本
    'question': question           #提问内容
})

print(predictions)