Description
Pretrained MPNetEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.biencoder_all_mpnet_base_v2_mmarcofr is a French model originally trained by antoinelouis.
How to use
document_assembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("documents")
embeddings =MPNetEmbeddings.pretrained("biencoder_all_mpnet_base_v2_mmarcofr","fr") \
.setInputCols(["documents"]) \
.setOutputCol("mpnet_embeddings")
pipeline = Pipeline().setStages([document_assembler, embeddings])
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)
val document_assembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("documents")
val embeddings = MPNetEmbeddings
.pretrained("biencoder_all_mpnet_base_v2_mmarcofr", "fr")
.setInputCols(Array("documents"))
.setOutputCol("mpnet_embeddings")
val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings))
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)
Model Information
| Model Name: | biencoder_all_mpnet_base_v2_mmarcofr |
| Compatibility: | Spark NLP 5.1.1+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [documents] |
| Output Labels: | [mpnet_embeddings] |
| Language: | fr |
| Size: | 406.8 MB |
References
https://huggingface.co/antoinelouis/biencoder-all-mpnet-base-v2-mmarcoFR