善于处理NLU任务,采用中文分词的,中文版的0.97亿参数DeBERTa-v2-Base。
Good at solving NLU tasks, adopting Chinese Word Segmentation (CWS), Chinese DeBERTa-v2-Base with 97M parameters.
需求 Demand | 任务 Task | 系列 Series | 模型 Model | 参数 Parameter | 额外 Extra |
---|---|---|---|---|---|
通用 General | 自然语言理解 NLU | 二郎神 Erlangshen | DeBERTa-v2 | 97M | 中文分词-中文 CWS-Chinese |
参考论文:DeBERTa: Decoding-enhanced BERT with Disentangled Attention
为了得到一个中文版的DeBERTa-v2-Base(97M),我们用悟道语料库(180G版本)进行预训练。我们使用了中文分词。具体地,我们在预训练阶段中使用了封神框架大概花费了24张A100约7天。
To get a Chinese DeBERTa-v2-Base (97M), we use WuDao Corpora (180 GB version) for pre-training. We employ Chinese Word Segmentation (CWS). Specifically, we use the fengshen framework in the pre-training phase which cost about 7 days with 24 A100 GPUs.
from modelscope.models import Model
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
if __name__ == '__main__':
task = Tasks.fill_mask
test_input = '法国的首都是巴[MASK]。'
model_id = 'Fengshenbang/Erlangshen-DeBERTa-v2-97M-CWS-Chinese'
model = Model.from_pretrained(model_id)
pipeline_ins = pipeline(task=Tasks.fill_mask, model=model, model_revision='v1.0.3')
print(pipeline_ins(input=test_input))
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}},
}