language: zh

ERNIE-3.0-base-zh

模型简介

ERNIE 3.0：面向语言理解与生成的大规模知识增强预训练模型
技术细节详见：https://arxiv.org/abs/2107.02137

发布模型信息

本次发布的PyTorch模型由官方PaddlePaddle版ERNIE模型转换而来，并通过系列实验验证了转换结果的准确性。

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

使用方式

可通过常规方式加载ERNIE-3.0模型：

from transformers import BertTokenizer, ErnieForMaskedLM

tokenizer = BertTokenizer.from_pretrained("nghuyong/ernie-3.0-base-zh")
model = ErnieForMaskedLM.from_pretrained("nghuyong/ernie-3.0-base-zh")

引用文献

@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}
}