DistilBART-CNN-12-3 Open-Source Text Summarization Model - Save Time and Efficiently Extract Text Key Points!

Distilbart Cnn 12 3

Developed by sshleifer

DistilBART is a distilled version of the BART model, focusing on text summarization tasks, significantly reducing model size and inference time while maintaining high performance.

Text Generation EnglishOpen Source License:Apache-2.0 #Abstract Generation #Lightweight Model #News Summarization

Downloads 145

Release Time : 3/2/2022

Model Overview

A lightweight text summarization model based on the BART architecture, compressed using knowledge distillation techniques, suitable for scenarios like news summarization.

Model Features

Efficient Inference

1.68x faster inference speed compared to the original BART-large model (137ms vs 229ms)

Performance Balance

Achieves a good balance between model size and summarization quality, with Rouge-L score only 0.5% lower than baseline

Multiple Configurations

Offers various parameter configurations (e.g., 12-1, 6-6, 12-3) to meet different scenario requirements

Model Capabilities

News Summarization

Long Text Compression

Key Information Extraction

Use Cases

Media Industry

Automatic News Summarization

Compress lengthy news reports into concise summaries

Achieves 22.12 Rouge-2 score on the XSum dataset

Content Analysis

Document Key Information Extraction

Extract core content from long documents

Retains over 90% of key information from the original document

Property	Details
Model Tags	summarization
License	apache-2.0
Datasets	cnn_dailymail, xsum
Thumbnail	https://huggingface.co/front/thumbnails/distilbart_medium.png

Model Name	MM Params	Inference Time (MS)	Speedup	Rouge 2	Rouge-L
distilbart-xsum-12-1	222	90	2.54	18.31	33.37
distilbart-xsum-6-6	230	132	1.73	20.92	35.73
distilbart-xsum-12-3	255	106	2.16	21.37	36.39
distilbart-xsum-9-6	268	136	1.68	21.72	36.61
bart-large-xsum (baseline)	406	229	1	21.85	36.50
distilbart-xsum-12-6	306	137	1.68	22.12	36.99
bart-large-cnn (baseline)	406	381	1	21.06	30.63
distilbart-12-3-cnn	255	214	1.78	20.57	30.00
distilbart-12-6-cnn	306	307	1.24	21.26	30.59
distilbart-6-6-cnn	230	182	2.09	20.17	29.70

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

Distilbart Cnn 12 3

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 DistilBART Model

🚀 Quick Start

📚 Documentation

Metrics for DistilBART models

📄 License