Description
Pretrained RobertaForMaskedLM model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. zuBERTa is a Zulu model originally trained by MoseliMotsoehli.
How to use
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols("document") \
.setOutputCol("token")
roberta_loaded = RoBertaEmbeddings.pretrained("roberta_embeddings_zuberta","zu") \
.setInputCols(["document", "token"]) \
.setOutputCol("embeddings") \
.setCaseSensitive(True)
pipeline = Pipeline(stages=[documentAssembler, tokenizer, roberta_loaded])
data = spark.createDataFrame([["I love Spark NLP"]]).toDF("text")
result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = new Tokenizer()
.setInputCols("document")
.setOutputCol("token")
val roberta_loaded = RoBertaEmbeddings.pretrained("roberta_embeddings_zuberta","zu")
.setInputCols(Array("document", "token"))
.setOutputCol("embeddings")
.setCaseSensitive(true)
val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, roberta_loaded))
val data = Seq("I love Spark NLP").toDS.toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("zu.embed.roberta").predict("""I love Spark NLP""")
Model Information
| Model Name: | roberta_embeddings_zuberta |
| Compatibility: | Spark NLP 4.2.4+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence, token] |
| Output Labels: | [embeddings] |
| Language: | zu |
| Size: | 256.0 MB |
| Case sensitive: | true |
References
- https://huggingface.co/MoseliMotsoehli/zuBERTa
- https://wortschatz.uni-leipzig.de/en/download
- https://zu.wikipedia.org/wiki/Special:AllPages