Description
Pretrained RoBertaForTokenClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.roberta_base_ner_demo_fire12_pipeline is a Mongolian model originally trained by fire12.
How to use
pipeline = PretrainedPipeline("roberta_base_ner_demo_fire12_pipeline", lang = "mn")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("roberta_base_ner_demo_fire12_pipeline", lang = "mn")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | roberta_base_ner_demo_fire12_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | mn |
| Size: | 465.7 MB |
References
https://huggingface.co/fire12/roberta-base-ner-demo
Included Models
- DocumentAssembler
- TokenizerModel
- RoBertaForTokenClassification