Erlangshen-MacBERT-325M-TextMatch-Chinese

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

简介 Brief Introduction

3.25亿参数的MacBERT，在句子匹配任务上进行预训练，并在FewCLUE的BUSTM任务上微调。

The MacBERT with 325M parameters is pre-trained for Chinese text-matching tasks, and finetuned on task BUSTM from FewCLUE.

模型分类 Model Taxonomy

模型信息 Model Information

为了提高模型在句子匹配上的效果，我们收集了大量句子匹配数据进行预训练，随后在FewCLUE的BUSTM任务进行微调，所有的训练均基于我们提出的UniMC框架。最终结果表明，3.25亿参数的模型通过我们的训练策略可以在句子匹配任务上超过1.3亿参数的大模型。

To improve the model performance on the text-matching task, we collected numerous text-matching datasets for pre-training. Then the model was finetuned on a specific text-matching task, BUSTM from FewCLUE. All the training is based on the UniMC framework we proposed. The results show that our model with 325M parameters could surpass the model with 1.3B parameters on the text-matching task via our training strategies.

下游效果 Performance

BUSTM任务上的效果：

The results on BUSTM:

示例代码

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

pipeline_ins = pipeline(
		'fill-mask',
		model='Fengshenbang/Erlangshen-MacBERT-325M-TextMatch-Chinese',
        model_revision='v1.0.1'
)

print(pipeline_ins('下面是一则关于[MASK][MASK]的新闻：股票放量下趺，大资金出逃谁在接盘？'))

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}},
}