English mpnet_embedding_stsb_mpnet_base_v2 TFMPNetModel from sentence-transformers

Description

Pretrained mpnet model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.mpnet_embedding_stsb_mpnet_base_v2 is a English model originally trained by sentence-transformers.

Download Copy S3 URI

How to use


document_assembler = DocumentAssembler() \
    .setInputCol("text") \
    .setOutputCol("documents")

instruction = MPNetEmbeddings \
    .pretrained("mpnet_embedding_stsb_mpnet_base_v2", "en")\
    .setInputCols(["documents"]) \
    .setOutputCol("mpnet_embeddings")

pipeline = Pipeline(stages=[
  document_assembler,
  instruction,
])

pipelineModel = pipeline.fit(data)

pipelineDF = pipelineModel.transform(data)

val document_assembler = new DocumentAssembler()
    .setInputCol("text") 
    .setOutputCol("documents")

val instruction = MPNetEmbeddings
    .pretrained("mpnet_embedding_stsb_mpnet_base_v2", "en")
    .setInputCols(Array("documents")) 
    .setOutputCol("mpnet_embeddings") 

val pipeline = new Pipeline().setStages(Array(document_assembler, instruction))

val pipelineModel = pipeline.fit(data)

val pipelineDF = pipelineModel.transform(data)

Model Information

Model Name: mpnet_embedding_stsb_mpnet_base_v2
Compatibility: Spark NLP 5.1.0+
License: Open Source
Edition: Official
Input Labels: [documents]
Output Labels: [mpnet_embeddings]
Language: en
Size: 408.6 MB