language: zh
tags:
- summarization
inference: false
Randeng_Pegasus_523M_Summary model (Chinese)，which codes has merged into Fengshenbang-LM
The 523M million parameter randeng_pegasus_large model, training with sampled gap sentence ratios on 180G Chinese data, and stochastically sample important sentences. The pretraining task just same as the paper PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization mentioned.
Different from the English version of pegasus, considering that the Chinese sentence piece is unstable, we use jieba and Bertokenizer as the tokenizer in chinese pegasus model.
This model we provided in hugging face hub is only the pretrained model, has not finetuned with downstream data yet.
We also pretained a base model, available with Randeng_Pegasus_238M_Summary
Task: Summarization
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 mv download in tokenizers_pegasus.py and data_utils.py in https://huggingface.co/IDEA-CCNL/Randeng_Pegasus_523M_Summary/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_Summary")
# You can find the vocab.txt in hugging face cache file.
# Or, you can download the vocab.txt manually
tokenizer = PegasusTokenizer.from_pretrained("/path/to/vocab.txt")
text = "在北京冬奥会自由式滑雪女子坡面障碍技巧决赛中，中国选手谷爱凌夺得银牌。祝贺谷爱凌！今天上午，自由式滑雪女子坡面障碍技巧决赛举行。决赛分三轮进行，取选手最佳成绩排名决出奖牌。第一跳，中国选手谷爱凌获得69.90分。在12位选手中排名第三。完成动作后，谷爱凌又扮了个鬼脸，甚是可爱。第二轮中，谷爱凌在道具区第三个障碍处失误，落地时摔倒。获得16.98分。网友：摔倒了也没关系，继续加油！在第二跳失误摔倒的情况下，谷爱凌顶住压力，第三跳稳稳发挥，流畅落地！获得86.23分！此轮比赛，共12位选手参赛，谷爱凌第10位出场。网友：看比赛时我比谷爱凌紧张，加油！"
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]
Citation
If you find the resource is useful, please cite the following website in your paper.
@misc{Fengshenbang-LM,
title={Fengshenbang-LM},
author={IDEA-CCNL},
year={2022},
howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
}