E5 Small V2 Sentence Embeddings

Description

Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022

Predicted Entities

Download Copy S3 URI

How to use

embeddings =E5Embeddings.pretrained("e5_small_v2","en") \ .setInputCols(["documents"]) \ .setOutputCol("instructor") pipeline = Pipeline().setStages([document_assembler, embeddings]) 
val embeddings = E5Embeddings.pretrained("e5_small_v2","en") .setInputCols(["document"]) .setOutputCol("e5_embeddings") val pipeline = new Pipeline().setStages(Array(document, embeddings)) 

Model Information

Model Name: e5_small_v2
Compatibility: Spark NLP 5.0.0+
License: Open Source
Edition: Official
Input Labels: [documents]
Output Labels: [e5]
Language: en
Size: 80.9 MB

References

https://huggingface.co/intfloat/e5-small-v2