模型:
mrm8488/spanbert-finetuned-squadv2
由 Facebook Research 创建,并在 SQuAD 2.0 上进行Q&A任务的微调。
SpanBERT: Improving Pre-training by Representing and Predicting Spans
SQuAD2.0 将SQuAD1.1中的100,000个问题与由众包工人以类似可回答问题的方式编写的50,000多个无法回答的问题相结合。要在SQuAD2.0上取得好成绩,系统不仅必须在可能时回答问题,还必须确定段落不支持任何答案并且放弃回答。
Dataset | Split | # samples |
---|---|---|
SQuAD2.0 | train | 130k |
SQuAD2.0 | eval | 12.3k |
该模型在Tesla P100 GPU和25GB RAM上进行了训练。微调的脚本可以在 here 找到。
Metric | # Value |
---|---|
EM | 78.80 |
F1 | 82.22 |
{ "exact": 78.80064010780762, "f1": 82.22801347271162, "total": 11873, "HasAns_exact": 78.74493927125506, "HasAns_f1": 85.60951483831069, "HasAns_total": 5928, "NoAns_exact": 78.85618166526493, "NoAns_f1": 78.85618166526493, "NoAns_total": 5945, "best_exact": 78.80064010780762, "best_exact_thresh": 0.0, "best_f1": 82.2280134727116, "best_f1_thresh": 0.0 }
Model | EM | F1 score |
---|---|---|
1238321 | - | 83.6* |
1239321 | 78.80 | 82.22 |
使用pipelines快速使用:
from transformers import pipeline qa_pipeline = pipeline( "question-answering", model="mrm8488/spanbert-finetuned-squadv2", tokenizer="mrm8488/spanbert-finetuned-squadv2" ) qa_pipeline({ 'context': "Manuel Romero has been working hardly in the repository hugginface/transformers lately", 'question': "Who has been working hard for hugginface/transformers lately?" }) # Output: {'answer': 'Manuel Romero','end': 13,'score': 6.836378586818937e-09, 'start': 0}
在西班牙用 ♥ 制作