Wenzhong-GPT2-3.5B

• Github: Fengshenbang-LM
• Docs: Fengshenbang-Docs

简介 Brief Introduction

善于处理NLG任务，目前最大的，中文版的GPT2

Focused on handling NLG tasks, the current largest, Chinese GPT2.

模型分类 Model Taxonomy

模型信息 Model Information

为了可以获得一个强大的单向语言模型，我们采用GPT模型结构，并且应用于中文语料上。具体地，这个模型拥有30层解码器和35亿参数，这比原本的GPT2-XL还要大。我们在100G的中文语料上预训练，这消耗了32个NVIDIA A100显卡大约28小时。据我们所知，它是目前最大的中文的GPT模型。

To obtain a robust unidirectional language model, we adopt the GPT model structure and apply it to the Chinese corpus. Specifically, this model has 30 decoder layers and 3.5 billion parameters, which is larger than the original GPT2-XL. We pre-train it on 100G of Chinese corpus, which consumes 32 NVIDIA A100 GPUs for about 28 hours. To the best of our knowledge, it is the largest Chinese GPT model currently available.

使用 Usage

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

pipeline_ins = pipeline(
        'text-generation',
        model='Fengshenbang/Wenzhong-GPT2-3.5B',
        model_revision='v1.0.0'
)

print(pipeline_ins('从前，'))

引用 Citation

如果您在您的工作中使用了我们的模型，可以引用我们的论文：

If you are using the resource for your work, please cite the our paper:

@article{fengshenbang,
  author    = {Junjie Wang and Yuxiang Zhang and Lin Zhang and Ping Yang and Xinyu Gao and Ziwei Wu and Xiaoqun Dong and Junqing He and Jianheng Zhuo and Qi Yang and Yongfeng Huang and Xiayu Li and Yanghan Wu and Junyu Lu and Xinyu Zhu and Weifeng Chen and Ting Han and Kunhao Pan and Rui Wang and Hao Wang and Xiaojun Wu and Zhongshen Zeng and Chongpei Chen and Ruyi Gan and Jiaxing Zhang},
  title     = {Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence},
  journal   = {CoRR},
  volume    = {abs/2209.02970},
  year      = {2022}
}

也可以引用我们的网站:

You can also cite our website:

@misc{Fengshenbang-LM,
  title={Fengshenbang-LM},
  author={IDEA-CCNL},
  year={2021},
  howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
}