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
How to use
embeddings =E5Embeddings.pretrained("e5_small_quantized","en") \
.setInputCols(["documents"]) \
.setOutputCol("instructor")
pipeline = Pipeline().setStages([document_assembler, embeddings])
val embeddings = E5Embeddings.pretrained("e5_small_quantized","en")
.setInputCols(["document"])
.setOutputCol("e5_embeddings")
val pipeline = new Pipeline().setStages(Array(document, embeddings))
Model Information
Model Name: | e5_small_quantized |
Compatibility: | Spark NLP 5.1.0+ |
License: | Open Source |
Edition: | Official |
Input Labels: | [documents] |
Output Labels: | [e5] |
Language: | en |
Size: | 22.6 MB |