Pre-trained Language Models (PLMs) have proven to be beneficial for various downstream NLP tasks. Recently, GPT-3, with 175 billion parameters and 570GB training data, drew a lot of attention due to the capacity of few-shot (even zero-shot) learning. However, applying GPT-3 to address Chinese NLP tasks is still challenging, as the training corpus of GPT-3 is primarily English, and the parameters are not publicly available. In this technical report, we release the Chinese Pre-trained Language Model (CPM) with generative pre-training on large-scale Chinese training data. To the best of our knowledge, CPM, with 2.6 billion parameters and 100GB Chinese training data, is the largest Chinese pre-trained language model, which could facilitate several downstream Chinese NLP tasks, such as conversation, essay generation, cloze test, and language understanding. Extensive experiments demonstrate that CPM achieves strong performance on many NLP tasks in the settings of few-shot (even zero-shot) learning. The code and parameters are available at https://github.com/TsinghuaAI/CPM-Generate.
@article{arxiv.2012.00413,
title = {CPM: A Large-scale Generative Chinese Pre-trained Language Model},
author = {Zhengyan Zhang and Xu Han and Hao Zhou and Pei Ke and Yuxian Gu and Deming Ye and Yujia Qin and Yusheng Su and Haozhe Ji and Jian Guan and Fanchao Qi and Xiaozhi Wang and Yanan Zheng and Guoyang Zeng and Huanqi Cao and Shengqi Chen and Daixuan Li and Zhenbo Sun and Zhiyuan Liu and Minlie Huang and Wentao Han and Jie Tang and Juanzi Li and Xiaoyan Zhu and Maosong Sun},
journal= {arXiv preprint arXiv:2012.00413},
year = {2020}
}