Finetuned BART Open-Source Text Summarization Model - Finetuned on CNN/DailyMail to Efficiently Extract Text Essentials

Finetuned Bart

Developed by Mousumi

A sequence-to-sequence model based on the BART architecture, fine-tuned on the CNN/DailyMail dataset, suitable for text summarization tasks.

Large Language Model

Transformers

#News Summarization #Chinese Text Processing #Fine-tuned BART Model

Downloads 19

Release Time : 3/2/2022

Model Overview

This model is a sequence-to-sequence model based on the BART architecture, fine-tuned on the CNN/DailyMail dataset, primarily used for text summarization tasks. It can compress long texts into concise summaries.

Model Features

Sequence-to-Sequence Modeling

Capable of processing input sequences and generating output sequences, suitable for tasks like text summarization.

Bidirectional Encoder

Combines a bidirectional encoder and an auto-regressive decoder for better contextual understanding.

Fine-tuning Optimization

Fine-tuned on the CNN/DailyMail dataset, optimized for text summarization tasks.

Model Capabilities

Text Summarization

Sequence Generation

Text Compression

Use Cases

News Summarization

News Article Summarization

Compresses lengthy news articles into concise summaries while retaining key information.

Generates high-quality news summaries suitable for quick browsing.

Content Generation

Text Rewriting

Rewrites long texts into more concise versions while preserving core content.

Generates concise yet information-rich text versions.

🚀 Finetuned BART Model

A BART model finetuned on CNN/DailyMail Dataset with a sample size of 10000, which can be used for text summarization or translation tasks.

🚀 Quick Start

This finetuned BART model can be easily integrated into your projects using the transformers library.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch


src_text = [" PG&E stated it scheduled the blackouts in response to forecasts for high winds amid dry conditions. The aim is to reduce the risk of wildfires. Nearly 800 thousand customers were scheduled to be affected by the shutoffs which were expected to last through at least midday tomorrow.", "In the end, it played out like a movie. A tense, heartbreaking story, and then a surprise twist at the end. As eight of Mary Jane Veloso's fellow death row inmates -- mostly foreigners, like her -- were put to death by firing squad early Wednesday in a wooded grove on the Indonesian island of Nusa Kambangan, the Filipina maid and mother of two was spared, at least for now. Her family was returning from what they thought was their final visit to the prison on so-called \"execution island\" when a Philippine TV crew flagged their bus down to tell them of the decision to postpone her execution. Her ecstatic mother, Celia Veloso, told CNN: \"We are so happy, so happy. I thought I had lost my daughter already but God is so good. Thank you to everyone who helped us."]

torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'

tokenizer = AutoTokenizer.from_pretrained("Mousumi/finetuned_bart")

model = AutoModelForSeq2SeqLM.from_pretrained("Mousumi/finetuned_bart").to(torch_device)

no_samples = len(src_text)
result = []

for i in range(no_samples):
    with tokenizer.as_target_tokenizer():
        tokenized_text = tokenizer([src_text[i]], return_tensors='pt', padding=True, truncation=True)
    batch = tokenized_text.to(torch_device)
    translated = model.generate(**batch)
    tgt_text = tokenizer.batch_decode(translated, skip_special_tokens=True)
    result.append(tgt_text[0])

print(result)

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご