SQuAD 交叉编码器（QNLI）

该模型使用 SentenceTransformers 的 Cross-Encoder 类进行训练。

训练数据

给定一个问题和段落，问题能否由该段落回答？该模型在 GLUE QNLI 数据集上进行了训练，该数据集将 SQuAD 数据集 转换为了NLI任务。

性能

该模型的性能结果请参阅 [SBERT.net 预训练交叉编码器][https://www.sbert.net/docs/pretrained_cross-encoders.html]。

使用方法

预训练模型的使用方式如下：

from sentence_transformers import CrossEncoder

model = CrossEncoder('cross-encoder/qnli-electra-base')
scores = model.predict([('Query1', 'Paragraph1'), ('Query2', 'Paragraph2')])

#例如
scores = model.predict([('How many people live in Berlin?', 'Berlin had a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.'), ('What is the size of New York?', 'New York City is famous for the Metropolitan Museum of Art.')])

与 Transformers AutoModel 配合使用

您也可以直接使用 Transformers 库（无需 SentenceTransformers 库）：

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model = AutoModelForSequenceClassification.from_pretrained('cross-encoder/qnli-electra-base')
tokenizer = AutoTokenizer.from_pretrained('cross-encoder/qnli-electra-base')

features = tokenizer(['How many people live in Berlin?', 'What is the size of New York?'], ['Berlin had a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.', 'New York City is famous for the Metropolitan Museum of Art.'],  padding=True, truncation=True, return_tensors="pt")

model.eval()
with torch.no_grad():
    scores = torch.nn.functional.sigmoid(model(**features).logits)
    print(scores)