TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities
Abstract
Recently, the success of pre-training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-training models within a uniform framework. In this paper, we present TencentPretrain, a toolkit supporting pre-training models of different modalities. The core feature of TencentPretrain is the modular design. The toolkit uniformly divides pre-training models into 5 components: embedding, encoder, target embedding, decoder, and target. As almost all of common modules are provided in each component, users can choose the desired modules from different components to build a complete pre-training model. The modular design enables users to efficiently reproduce existing pre-training models or build brand-new one. We test the toolkit on text, vision, and audio benchmarks and show that it can match the performance of the original implementations.
Cite
@article{arxiv.2212.06385,
title = {TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities},
author = {Zhe Zhao and Yudong Li and Cheng Hou and Jing Zhao and Rong Tian and Weijie Liu and Yiren Chen and Ningyuan Sun and Haoyan Liu and Weiquan Mao and Han Guo and Weigang Guo and Taiqiang Wu and Tao Zhu and Wenhang Shi and Chen Chen and Shan Huang and Sihong Chen and Liqun Liu and Feifei Li and Xiaoshuai Chen and Xingwu Sun and Zhanhui Kang and Xiaoyong Du and Linlin Shen and Kimmo Yan},
journal= {arXiv preprint arXiv:2212.06385},
year = {2023}
}