Romanian Legal Roberta Embeddings

Description

Pretrained Legal Roberta Embeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. legal-romanian-roberta-base is a Romanian model originally trained by joelito.

Download Copy S3 URI

How to use

sentence_embeddings = RoBertaEmbeddings.pretrained("roberta_base_romanian_legal", "ro")\
  .setInputCols(["sentence"])\
  .setOutputCol("embeddings")
val sentence_embeddings = RoBertaEmbeddings.pretrained("roberta_base_romanian_legal", "ro")
  .setInputCols("sentence")
  .setOutputCol("embeddings"))

Model Information

Model Name: roberta_base_romanian_legal
Compatibility: Spark NLP 4.2.4+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [embeddings]
Language: ro
Size: 416.0 MB
Case sensitive: true

References

https://huggingface.co/joelito/legal-romanian-roberta-base