Sentence Transformers Multilingual E5 Large

🚀 embaas/sentence-transformers-multilingual-e5-large

这是一个 sentence-transformers 模型，它可以将句子和段落映射到一个 1024 维的密集向量空间，可用于聚类或语义搜索等任务。

🚀 快速开始

当你安装了 sentence-transformers 后，使用这个模型就变得很简单：

pip install -U sentence-transformers

然后你可以像这样使用该模型：

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

model = SentenceTransformer('embaas/sentence-transformers-multilingual-e5-large')
embeddings = model.encode(sentences)
print(embeddings)

💻 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('embaas/sentence-transformers-multilingual-e5-large')
embeddings = model.encode(sentences)
print(embeddings)

📚 详细文档

评估结果

要对该模型进行自动评估，请参阅 Sentence Embeddings Benchmark：https://seb.sbert.net

完整模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
  (2): Normalize()
)

引用与作者

如果你想了解更多信息，请参考相关文档。