R

Randeng Pegasus 238M Chinese

Developed by IDEA-CCNL
Chinese version of the PAGASUS-base model specialized in text summarization tasks
Downloads 104
Release Time : 6/9/2022

Model Overview

A Chinese text summarization model trained on the PEGASUS architecture, pre-trained using the WuDao corpus, and optimized for Chinese processing with integrated Jieba segmentation and BERT tokenizer

Model Features

Optimized Chinese Segmentation
Innovatively integrates Jieba segmentation with BERT tokenizer, optimized for Chinese language characteristics
Multiple Size Versions
Offers 238M base version and 523M large version to meet different scenario requirements
Pre-training Optimization
Pre-trained on 180GB WuDao corpus to enhance model generalization capabilities

Model Capabilities

Chinese Text Summarization Generation
Long Text Compression
Key Information Extraction

Use Cases

News Media
News Summarization Generation
Automatically generates concise summaries of news content
Example output: 'As of 9 PM yesterday, multiple executives, including the East China General Manager of Beijing Mercedes-Benz Sales Service Co., Ltd., remained in the Shanghai office.'
Business Analysis
Report Summarization
Automatically extracts core content from business reports
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase