Erlangshen-DeBERTa-v2-186M-Chinese-SentencePiece

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

简介 Brief Introduction

善于处理NLU任务，采用sentence piece分词的，中文版的1.86亿参数DeBERTa-v2。

Good at solving NLU tasks, adopting sentence piece, Chinese DeBERTa-v2 with 186M parameters.

模型分类 Model Taxonomy

模型信息 Model Information

为了得到一个中文版的DeBERTa-v2（186M），我们用悟道语料库(180G版本)进行预训练。我们使用了Sentence Piece的方式分词（词表大小：约128000）。具体地，我们在预训练阶段中使用了封神框架大概花费了8张3090TI（24G）约21天。

To get a Chinese DeBERTa-v2 (186M), we use WuDao Corpora (180 GB version) for pre-training. We employ the sentence piece as the tokenizer (vocabulary size: around 128,000). Specifically, we use the fengshen framework in the pre-training phase which cost about 21 days with 8 3090TI（24G） GPUs.

下游效果 Performance

我们展示了下列下游任务的结果（dev集）：

We present the results (dev set) on the following tasks:

使用 Usage

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

pipeline_ins = pipeline(
		'fill-mask',
		model='Fengshenbang/Erlangshen-DeBERTa-v2-186M-Chinese-SentencePiece',
        model_revision='v1.0.0'
)

print(pipeline_ins('中国首都位于<mask>。'))

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}},
}