arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.00823cs.CL
收藏

M6:汉语多模态预训练器

M6: A Chinese Multimodal Pretrainer

Alibaba Group(阿里巴巴集团);Tsinghua University(清华大学)
Junyang Lin, Rui Men, An Yang, Chang Zhou, Ming Ding, Yichang Zhang, Peng Wang, Ang Wang, Le Jiang, Xianyan Jia, Jie Zhang, Jianwei Zhang, Xu Zou, Zhikang Li, X… 展开作者

Junyang Lin, Rui Men, An Yang, Chang Zhou, Ming Ding, Yichang Zhang, Peng Wang, Ang Wang, Le Jiang, Xianyan Jia, Jie Zhang, Jianwei Zhang, Xu Zou, Zhikang Li, Xiaodong Deng, Jie Liu, Jinbao Xue, Huiling Zhou, Jianxin Ma, Jin Yu, Yong Li, Wei Lin, Jingren Zhou, Jie Tang, Hongxia Yang

摘要:

在这项工作中,我们构建了最大的中文多模态预训练数据集,其中包括超过1.9TB的图像和292 GB的文本,涵盖了广泛的领域。我们提出了一种称为M6的跨模态预训练方法,参考Multi-Modality to Multi-Modality Multi-Task Mega-transformer,用于对单模态和多模态数据进行统一的预训练。我们将模型规模扩展到100亿和1000亿参数,并在中文中构建最大的预训练模型。我们将该模型应用到一系列下游应用中,并与强基线相比展示了其出色的性能。此外,我们专门设计了一个文本引导图像生成的下游任务,并表明微调的M6可以创建具有高分辨率和丰富细节的高质量图像。

英文摘要:

In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1.9TB images and 292GB texts that cover a wide range of domains. We propose a cross-modal pretraining method called M6, referring to Multi-Modality to Multi-Modality Multitask Mega-transformer, for unified pretraining on the data of single modality and multiple modalities. We scale the model size up to 10 billion and 100 billion parameters, and build the largest pretrained model in Chinese. We apply the model to a series of downstream applications, and demonstrate its outstanding performance in comparison with strong baselines. Furthermore, we specifically design a downstream task of text-guided image generation, and show that the finetuned M6 can create high-quality images with high resolution and abundant details.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑