Edit on GitHub
  • John Snow Labs
  • Sep 06, 2024

German bert_base_german_dbmdz_uncased BertEmbeddings from huggingface

  • bert
  • de
  • open_source
  • fill_mask
  • onnx

Description

Pretrained BertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.bert_base_german_dbmdz_uncased is a German model originally trained by huggingface.

Predicted Entities

Download Copy S3 URI

How to use

document_assembler = DocumentAssembler() \
    .setInputCol("text") \
    .setOutputCol("documents")
    
    
embeddings =BertEmbeddings.pretrained("bert_base_german_dbmdz_uncased","de") \
            .setInputCols(["documents","token"]) \
            .setOutputCol("embeddings")

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

pipelineModel = pipeline.fit(data)

pipelineDF = pipelineModel.transform(data)

val document_assembler = new DocumentAssembler()
    .setInputCol("text") 
    .setOutputCol("embeddings")
    
val embeddings = BertEmbeddings 
    .pretrained("bert_base_german_dbmdz_uncased", "de")
    .setInputCols(Array("documents","token")) 
    .setOutputCol("embeddings") 

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

val pipelineModel = pipeline.fit(data)

val pipelineDF = pipelineModel.transform(data)

Model Information

Model Name: bert_base_german_dbmdz_uncased
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Input Labels: [document, token]
Output Labels: [bert]
Language: de
Size: 409.9 MB

References

References

https://huggingface.co/bert-base-german-dbmdz-uncased