Qnli Distilroberta Base

🚀 Cross-Encoder for SQuAD (QNLI)

This model is designed for text ranking, trained using the Cross-Encoder class to determine if a question can be answered by a given paragraph.

🚀 Quick Start

This model was trained using SentenceTransformers Cross-Encoder class.

✨ Features

• Task: Given a question and paragraph, it can determine whether the question can be answered by the paragraph.
• Training Data: Trained on the GLUE QNLI dataset, which transformed the SQuAD dataset into an NLI task.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

Pre-trained models can be used like this:

from sentence_transformers import CrossEncoder

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

#e.g.
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.')])

Advanced Usage

You can use the model also directly with Transformers library (without SentenceTransformers library):

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

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

📚 Documentation

Training Data

Given a question and paragraph, can the question be answered by the paragraph? The models have been trained on the GLUE QNLI dataset, which transformed the SQuAD dataset into an NLI task.

Performance

For performance results of this model, see SBERT.net Pre-trained Cross-Encoder.

🔧 Technical Details

No detailed technical implementation details are provided in the original document, so this section is skipped.

📄 License

The model is released under the Apache-2.0 license.