Congen BERT Small

🚀 kornwtp/ConGen-BERT-Small

这是一个 ConGen 模型，它可以将句子映射到一个 512 维的密集向量空间，可用于语义搜索等任务。

🚀 快速开始

使用此模型前，你需要安装 ConGen，安装命令如下：

pip install -U git+https://github.com/KornWtp/ConGen.git

安装完成后，你可以按照以下方式使用该模型：

💻 使用示例

基础用法

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('kornwtp/ConGen-BERT-Small')
embeddings = model.encode(sentences)
print(embeddings)

📚 详细文档

评估结果

若要对该模型进行自动评估，请参考 Sentence Embeddings Benchmark：语义文本相似度

引用与作者

@inproceedings{limkonchotiwat-etal-2022-congen,
    title = "{ConGen}: Unsupervised Control and Generalization Distillation For Sentence Representation",
    author = "Limkonchotiwat, Peerat  and
      Ponwitayarat, Wuttikorn  and
      Lowphansirikul, Lalita and
      Udomcharoenchaikit, Can  and
      Chuangsuwanich, Ekapol  and
      Nutanong, Sarana",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    year = "2022",
    publisher = "Association for Computational Linguistics",
}

📄 许可证

本项目采用 Apache-2.0 许可证。