Description
Pretrained XlmRoBertaForSequenceClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.korean_reranker_pipeline is a Korean model originally trained by Dongjin-kr.
How to use
pipeline = PretrainedPipeline("korean_reranker_pipeline", lang = "ko")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("korean_reranker_pipeline", lang = "ko")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | korean_reranker_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ko |
| Size: | 2.0 GB |
References
https://huggingface.co/Dongjin-kr/ko-reranker
Included Models
- DocumentAssembler
- TokenizerModel
- XlmRoBertaForSequenceClassification