根据输入的短文本,模型生成对应的短文本摘要。本模型为OFA在经典英文摘要数据集Gigaword上finetune得到的模型。
玩转OFA只需区区以下数行代码,就是如此轻松!如果你觉得还不够方便,请点击右上角Notebook
按钮,我们为你提供了配备了GPU的环境,你只需要在notebook里输入提供的代码,就可以把OFA玩起来了!
# 请使用modelscope 1.0以上版本
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.outputs import OutputKeys
ofa_pipe = pipeline(Tasks.text_summarization, model='damo/ofa_summarization_gigaword_large_en')
text = 'five-time world champion michelle kwan withdrew' + \
'from the #### us figure skating championships on wednesday ,' + \
' but will petition us skating officials for the chance to ' +\
'compete at the #### turin olympics .'
result = ofa_pipe({'text': text})
print(result[OutputKeys.TEXT]) # ['kwan withdraws from #### us championships']
OFA(One-For-All)是通用多模态预训练模型,使用简单的序列到序列的学习框架统一模态(跨模态、视觉、语言等模态)和任务(如图片生成、视觉定位、图片描述、图片分类、文本生成等),详见我们发表于ICML 2022的论文:OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework以及我们的官方Github仓库https://github.com/OFA-Sys/OFA。
Github  |  Paper   |  Blog
Model | Params-en | Params-zh | Backbone | Hidden size | Intermediate size | Num. of heads | Enc layers | Dec layers |
---|---|---|---|---|---|---|---|---|
OFATiny | 33M | - | ResNet50 | 256 | 1024 | 4 | 4 | 4 |
OFAMedium | 93M | - | ResNet101 | 512 | 2048 | 8 | 4 | 4 |
OFABase | 180M | 160M | ResNet101 | 768 | 3072 | 12 | 6 | 6 |
OFALarge | 470M | 440M | ResNet152 | 1024 | 4096 | 16 | 12 | 12 |
OFAHuge | 930M | - | ResNet152 | 1280 | 5120 | 16 | 24 | 12 |
OFA的Huge模型在Gigaword上取得最优变现,具体结果如下:
Task | Gigaword | ||
---|---|---|---|
Metric | ROUGE-1 | ROUGE-2 | ROUGE-L |
ProhphetNet | 39.55 | 20.27 | 36.57 |
OFA | 39.81 | 20.66 | 37.11 |
本模型训练数据集是gigaword数据集。
finetune能力请参考OFA Tutorial 1.4节。
训练数据集自身有局限,有可能产生一些偏差,请用户自行评测后决定如何使用。
如果你觉得OFA好用,喜欢我们的工作,欢迎引用:
@article{wang2022ofa,
author = {Peng Wang and
An Yang and
Rui Men and
Junyang Lin and
Shuai Bai and
Zhikang Li and
Jianxin Ma and
Chang Zhou and
Jingren Zhou and
Hongxia Yang},
title = {OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence
Learning Framework},
journal = {CoRR},
volume = {abs/2202.03052},
year = {2022}
}