Instructions to use mingcai/ESimCSE-chinese-bert-wwm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mingcai/ESimCSE-chinese-bert-wwm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="mingcai/ESimCSE-chinese-bert-wwm")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("mingcai/ESimCSE-chinese-bert-wwm") model = AutoModel.from_pretrained("mingcai/ESimCSE-chinese-bert-wwm") - Notebooks
- Google Colab
- Kaggle
基于论文ESimCSE进行复现,基于STS-B训练集进行训练,在中文STS-B的验证集spermanr相关性得分为0.7226.
论文参考:
@inproceedings{Wu2021ESimCSEES,
title={ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding},
author={Xing Wu and Chaochen Gao and Liangjun Zang and Jizhong Han and Zhongyuan Wang and Songlin Hu},
booktitle={International Conference on Computational Linguistics},
year={2021}
}
- Downloads last month
- 5