Bert Mini2bert Mini Finetuned Cnn Daily Mail Summarization

🚀 Bert-mini2Bert-mini Summarization with 🤗EncoderDecoder Framework

This project presents a fine - tuned BERT2BERT (mini) model for text summarization. It is warm - started and optimized on the CNN/Dailymail dataset, aiming to provide high - quality summarization results.

🚀 Quick Start

This model is a warm - started BERT2BERT (mini) model fine - tuned on the CNN/Dailymail summarization dataset. It achieves a 16.51 ROUGE - 2 score on the test dataset of CNN/Dailymail.

For more details on the fine - tuning process of the model, please refer to this notebook.

✨ Features

• Fine - tuned on CNN/Dailymail: The model is optimized on the CNN/Dailymail dataset, making it suitable for news summarization tasks.
• Good ROUGE - 2 Score: It achieves a ROUGE - 2 score of 16.51 on the test dataset, indicating its effectiveness in summarization.

💻 Usage Examples

Basic Usage

from transformers import BertTokenizerFast, EncoderDecoderModel
import torch
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
tokenizer = BertTokenizerFast.from_pretrained('mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization')
model = EncoderDecoderModel.from_pretrained('mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization').to(device)

def generate_summary(text):
    # cut off at BERT max length 512
    inputs = tokenizer([text], padding="max_length", truncation=True, max_length=512, return_tensors="pt")
    input_ids = inputs.input_ids.to(device)
    attention_mask = inputs.attention_mask.to(device)

    output = model.generate(input_ids, attention_mask=attention_mask)

    return tokenizer.decode(output[0], skip_special_tokens=True)
  
text = "your text to be summarized here..."
generate_summary(text)

📚 Documentation

Results on test set 📝

📄 License

This project is licensed under the Apache - 2.0 license.

Created by Manuel Romero/@mrm8488 | LinkedIn Made with ♥ in Spain