Description
Pretrained RoBertaEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.polish_roberta_large_v1_pipeline is a Polish model originally trained by sdadas.
How to use
pipeline = PretrainedPipeline("polish_roberta_large_v1_pipeline", lang = "pl")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("polish_roberta_large_v1_pipeline", lang = "pl")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | polish_roberta_large_v1_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | pl |
| Size: | 845.7 MB |
References
https://huggingface.co/sdadas/polish-roberta-large-v1
Included Models
- DocumentAssembler
- TokenizerModel
- RoBertaEmbeddings