Edit on GitHub
  • John Snow Labs
  • Sep 12, 2023

Moldavian, Moldovan, Romanian romanian_bert_tweet_large BertEmbeddings from Iulian277

  • bert
  • ro
  • open_source
  • fill_mask
  • onnx

Description

Pretrained BertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.romanian_bert_tweet_large is a Moldavian, Moldovan, Romanian model originally trained by Iulian277.

Download Copy S3 URI

How to use



document_assembler = DocumentAssembler() \
    .setInputCol("text") \
    .setOutputCol("documents")
    
    
embeddings =BertEmbeddings.pretrained("romanian_bert_tweet_large","ro") \
            .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("romanian_bert_tweet_large", "ro")
    .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: romanian_bert_tweet_large
Compatibility: Spark NLP 5.1.1+
License: Open Source
Edition: Official
Input Labels: [documents, token]
Output Labels: [embeddings]
Language: ro
Size: 1.3 GB

References

https://huggingface.co/Iulian277/ro-bert-tweet-large