Autonlp More Fine Tune 24465520 26265898

🚀 Model Trained Using AutoNLP

This model is trained via AutoNLP, designed to solve the extractive question - answering problem.

🚀 Quick Start

This model is trained for extractive question answering. You can access it through different methods as shown below.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

You can use cURL to access this model:

$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"question": "Who loves AutoNLP?", "context": "Everyone loves AutoNLP"}' https://api-inference.huggingface.co/models/teacookies/autonlp-more_fine_tune_24465520-26265898

Advanced Usage

Or use the Python API:

import torch

from transformers import AutoModelForQuestionAnswering, AutoTokenizer

model = AutoModelForQuestionAnswering.from_pretrained("teacookies/autonlp-more_fine_tune_24465520-26265898", use_auth_token=True)

tokenizer = AutoTokenizer.from_pretrained("teacookies/autonlp-more_fine_tune_24465520-26265898", use_auth_token=True)

from transformers import BertTokenizer, BertForQuestionAnswering

question, text = "Who loves AutoNLP?", "Everyone loves AutoNLP"

inputs = tokenizer(question, text, return_tensors='pt')

start_positions = torch.tensor([1])

end_positions = torch.tensor([3])

outputs = model(**inputs, start_positions=start_positions, end_positions=end_positions)

loss = outputs.loss

start_scores = outputs.start_logits

end_scores = outputs.end_logits

📚 Documentation

Model Information

Validation Metrics

Datasets

• teacookies/autonlp-data-more_fine_tune_24465520

Tags

• autonlp
• question-answering

Widget

• text: "Who loves AutoNLP?"
• context: "Everyone loves AutoNLP"