Downloads · 30 days
10
2% of all-time downloads
ESimCSE-chinese-bert-wwm
mingcai/ESimCSE-chinese-bert-wwm
ESimCSE-chinese-bert-wwm is a feature extraction model from mingcai. Use it when you need embeddings to search or compare text. It is set up for transformers.
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.
All-time downloads
609
Public
Repo size
1.2 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt409 MB · 50%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Feb 8, 2023
- Updated
- Feb 8, 2023
- SHA
- 8b07836b
Model card
From the Hugging Face model README
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}
}
- Task
- Feature Extraction
- Library
- transformers
- Type
- bert
- Languages
- zh
- Created
- Feb 8, 2023
- Updated
- Feb 8, 2023