Randeng Pegasus 523M Chinese

🚀 Randeng-Pegasus-523M-Chinese

A Chinese version of PAGASUS-large, specialized in text summarization tasks.

• Main Page: Fengshenbang
• Github: Fengshenbang-LM

🚀 Quick Start

This model is designed to handle Chinese text summarization tasks effectively. Below are the details about the model and how to use it.

✨ Features

It's a Chinese version of PAGASUS-large, which is good at solving text summarization tasks.

📦 Model Taxonomy

📚 Documentation

Model Information

Reference paper: PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization

To solve Chinese abstractive summarization tasks, we follow the PEGASUS guidelines. We employ a version of WuDao Corpora (180 GB version) as a pre-training dataset. In addition, considering that the Chinese sentence chunk is unstable, we utilize jieba and BERT tokenizer in our Randeng-PEGASUS. We also provide a base size version, available with IDEA-CCNL/Randeng-Pegasus-238M-Chinese. And, we also provide a version after fine-tuning on Chinese text summarization datasets: Randeng-Pegasus-523M-Summary-Chinese.

💻 Usage Examples

Basic Usage

from transformers import PegasusForConditionalGeneration
# Need to download tokenizers_pegasus.py and other Python script from Fengshenbang-LM github repo in advance,
# or you can download tokenizers_pegasus.py and data_utils.py in https://huggingface.co/IDEA-CCNL/Randeng_Pegasus_523M/tree/main
# Strongly recommend you git clone the Fengshenbang-LM repo:
# 1. git clone https://github.com/IDEA-CCNL/Fengshenbang-LM
# 2. cd Fengshenbang-LM/fengshen/examples/pegasus/
# and then you will see the tokenizers_pegasus.py and data_utils.py which are needed by pegasus model
from tokenizers_pegasus import PegasusTokenizer

model = PegasusForConditionalGeneration.from_pretrained("IDEA-CCNL/Randeng-Pegasus-523M-Chinese")
tokenizer = PegasusTokenizer.from_pretrained("IDEA-CCNL/Randeng-Pegasus-523M-Chinese")

text = "据微信公众号“界面”报道，4日上午10点左右，中国发改委反垄断调查小组突击查访奔驰上海办事处，调取数据材料，并对多名奔驰高管进行了约谈。截止昨日晚9点，包括北京梅赛德斯-奔驰销售服务有限公司东区总经理在内的多名管理人员仍留在上海办公室内"
inputs = tokenizer(text, max_length=1024, return_tensors="pt")

# Generate Summary
summary_ids = model.generate(inputs["input_ids"])
tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]

# model Output: 截止昨日晚9点，包括北京梅赛德斯-奔驰销售服务有限公司东区总经理在内的多名管理人员仍留在上海办公室内

📄 Citation

If you are using the resource for your work, please cite the our paper:

@article{fengshenbang,
  author    = {Jiaxing Zhang and Ruyi Gan and Junjie Wang and Yuxiang Zhang and Lin Zhang and Ping Yang and Xinyu Gao and Ziwei Wu and Xiaoqun Dong and Junqing He and Jianheng Zhuo and Qi Yang and Yongfeng Huang and Xiayu Li and Yanghan Wu and Junyu Lu and Xinyu Zhu and Weifeng Chen and Ting Han and Kunhao Pan and Rui Wang and Hao Wang and Xiaojun Wu and Zhongshen Zeng and Chongpei Chen},
  title     = {Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence},
  journal   = {CoRR},
  volume    = {abs/2209.02970},
  year      = {2022}
}

You can also cite our website:

@misc{Fengshenbang-LM,
  title={Fengshenbang-LM},
  author={IDEA-CCNL},
  year={2021},
  howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
}