Rubert Large Squad

🚀 Den4ikAI/rubert-large-squad

A question-answering model fine-tuned from sberbank-ai/ruBert-base, suitable for answering various questions.

🚀 Quick Start

This model is fine-tuned from sberbank-ai/ruBert-base. You can use the following code to quickly start using it for question-answering tasks.

from transformers import pipeline
qa_pipeline = pipeline(
    "question-answering",
    model="Den4ikAI/rubert-large-squad",
    tokenizer="Den4ikAI/rubert-large-squad"
)
predictions = qa_pipeline({
    'context': "Пушкин родился 6 июля 1799 года",
    'question': "Когда родился Пушкин?"
})
print(predictions)
# output:
#{'score': 0.9613797664642334, 'start': 15, 'end': 31, 'answer': '6 июля 1799 года'}

✨ Features

• Based on ruBert-base: Fine-tuned from sberbank-ai/ruBert-base to better handle question-answering tasks.
• Specific Training: Trained on a dataset with a size of 4 for 2 epochs.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import pipeline
qa_pipeline = pipeline(
    "question-answering",
    model="Den4ikAI/rubert-large-squad",
    tokenizer="Den4ikAI/rubert-large-squad"
)
predictions = qa_pipeline({
    'context': "Пушкин родился 6 июля 1799 года",
    'question': "Когда родился Пушкин?"
})
print(predictions)
# output:
#{'score': 0.9613797664642334, 'start': 15, 'end': 31, 'answer': '6 июля 1799 года'}

Advanced Usage

There is no advanced usage example in the original document.

📚 Documentation

• Model Type: Question-answering model
• Training Data Size: 4
• Epochs: 2

📄 License

This project is licensed under the MIT license.