ERNIE-3.0-nano-zh

介绍

ERNIE 3.0：大规模知识增强预训练的语言理解和生成详细信息： https://arxiv.org/abs/2107.02137

发布的模型信息

此发布的pytorch模型是从官方发布的PaddlePaddle ERNIE模型转换而来，并进行了一系列实验来检查转换的准确性。

• 官方PaddlePaddle ERNIE仓库： https://paddlenlp.readthedocs.io/zh/latest/model_zoo/transformers/ERNIE/contents.html
• Pytorch转换仓库： https://github.com/nghuyong/ERNIE-Pytorch

如何使用

from transformers import BertTokenizer, ErnieModel

tokenizer = BertTokenizer.from_pretrained("nghuyong/ernie-3.0-nano-zh")
model = ErnieModel.from_pretrained("nghuyong/ernie-3.0-nano-zh")

引用

@article{sun2021ernie,
  title={Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation},
  author={Sun, Yu and Wang, Shuohuan and Feng, Shikun and Ding, Siyu and Pang, Chao and Shang, Junyuan and Liu, Jiaxiang and Chen, Xuyi and Zhao, Yanbin and Lu, Yuxiang and others},
  journal={arXiv preprint arXiv:2107.02137},
  year={2021}
}