E5 Large 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 URICopied!

How to use

embeddings =E5Embeddings.pretrained("e5_large","en") \
            .setInputCols(["documents"]) \
            .setOutputCol("instructor")

pipeline = Pipeline().setStages([document_assembler, embeddings])

Model Information

Model Name: e5_large
Compatibility: Spark NLP 5.0.0+
License: Open Source
Edition: Official
Input Labels: [documents]
Output Labels: [e5]
Language: en
Size: 799.1 MB

References

https://huggingface.co/intfloat/e5-large