Description
Pretrained RoBERTa Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. muppet-roberta-large is a English model orginally trained by facebook.
How to use
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols("document") \
.setOutputCol("token")
embeddings = RoBertaEmbeddings.pretrained("roberta_embeddings_muppet_roberta_large","en") \
.setInputCols(["document", "token"]) \
.setOutputCol("embeddings")
pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])
data = spark.createDataFrame([["I love Spark NLP"]]).toDF("text")
result = pipeline.fit(data).transform(data)
Model Information
| Model Name: | roberta_embeddings_muppet_roberta_large |
| Compatibility: | Spark NLP 3.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence, token] |
| Output Labels: | [bert] |
| Language: | en |
| Size: | 849.1 MB |
| Case sensitive: | true |
References
- https://huggingface.co/facebook/muppet-roberta-large
- https://arxiv.org/abs/2101.11038