Mengzi Bert Base

🚀 Mengzi-BERT base model (Chinese)

A pre-trained model on 300G Chinese corpus, using Masked Language Modeling (MLM), Part-of-Speech (POS) tagging, and Sentence Order Prediction (SOP) as training tasks.

🚀 Quick Start

The Mengzi-BERT base model is pre-trained on a 300G Chinese corpus. It employs Masked Language Modeling (MLM), Part-of-Speech (POS) tagging, and Sentence Order Prediction (SOP) as training tasks.

# Code examples remain unchanged
from transformers import BertTokenizer, BertModel
tokenizer = BertTokenizer.from_pretrained("Langboat/mengzi-bert-base")
model = BertModel.from_pretrained("Langboat/mengzi-bert-base")

💻 Usage Examples

Basic Usage

# Code examples remain unchanged
from transformers import BertTokenizer, BertModel
tokenizer = BertTokenizer.from_pretrained("Langboat/mengzi-bert-base")
model = BertModel.from_pretrained("Langboat/mengzi-bert-base")

📚 Documentation

Scores on nine chinese tasks (without any data augmentation)

Note: RoBERTa-wwm-ext scores are from CLUE baseline.

Paper Reference

Mengzi: A lightweight yet Powerful Chinese Pre-trained Language Model

📄 License

This project is licensed under the Apache-2.0 license.

📚 Citation

If you find the technical report or resource is useful, please cite the following technical report in your paper.

@misc{zhang2021mengzi,
      title={Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese}, 
      author={Zhuosheng Zhang and Hanqing Zhang and Keming Chen and Yuhang Guo and Jingyun Hua and Yulong Wang and Ming Zhou},
      year={2021},
      eprint={2110.06696},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}