README.md

---
language: Chinese
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
license: apache-2.0
widget:
    source_sentence: "那个人很开心"
    sentences:
        - 那个人非常开心
        - 那只猫很开心
        - 那个人在吃东西
---

# Chinese Sentence BERT

## Model description

This model is pre-trained by [UER-py](https://arxiv.org/abs/1909.05658).

## Training data

[ChineseTextualInference](https://github.com/liuhuanyong/ChineseTextualInference/) is used as training data. 

## Training procedure

This model is fine-tuned by [UER-py](https://github.com/dbiir/UER-py/) on [Tencent Cloud](https://cloud.tencent.com/). We fine-tune three epochs with a sequence length of 512 on the basis of the Google's pre-trained Chinese BERT model. At the end of each epoch, the model is saved when the best performance on development set is achieved. 

```
python3 finetune/run_classifier_siamese.py --pretrained_model_path models/google_zh_model.bin \
                                           --vocab_path models/google_zh_vocab.txt \
                                           --config_path models/sbert/base_config.json \
                                           --train_path datasets/ChineseTextualInference/train.tsv \
                                           --dev_path datasets/ChineseTextualInference/dev.tsv \
                                           --epochs_num 3 --batch_size 32
```


Finally, we convert the pre-trained model into Huggingface's format:

```
python3 scripts/convert_sbert_from_uer_to_huggingface.py --input_model_path cluecorpussmall_bart_base_seq512_model.bin-250000 \                                                                
                                                         --output_model_path pytorch_model.bin \                                                                                            
                                                         --layers_num 12
```


### BibTeX entry and citation info

```
@article{reimers2019sentence,
  title={Sentence-bert: Sentence embeddings using siamese bert-networks},
  author={Reimers, Nils and Gurevych, Iryna},
  journal={arXiv preprint arXiv:1908.10084},
  year={2019}
}
@article{zhao2019uer,
  title={UER: An Open-Source Toolkit for Pre-training Models},
  author={Zhao, Zhe and Chen, Hui and Zhang, Jinbin and Zhao, Xin and Liu, Tao and Lu, Wei and Chen, Xi and Deng, Haotang and Ju, Qi and Du, Xiaoyong},
  journal={EMNLP-IJCNLP 2019},
  pages={241},
  year={2019}
}
```