Description
Pretrained XlmRoBertaForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.xlmroberta_qa_ukrainian_pipeline is a Ukrainian model originally trained by robinhad.
How to use
pipeline = PretrainedPipeline("xlmroberta_qa_ukrainian_pipeline", lang = "uk")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("xlmroberta_qa_ukrainian_pipeline", lang = "uk")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | xlmroberta_qa_ukrainian_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | uk |
| Size: | 401.3 MB |
References
https://huggingface.co/robinhad/ukrainian-qa
Included Models
- MultiDocumentAssembler
- XlmRoBertaForQuestionAnswering