Description
Pretrained RoBertaEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.kaz_roberta_conversational_pipeline is a Kazakh model originally trained by kz-transformers.
How to use
pipeline = PretrainedPipeline("kaz_roberta_conversational_pipeline", lang = "kk")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("kaz_roberta_conversational_pipeline", lang = "kk")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | kaz_roberta_conversational_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Language: | kk |
| Size: | 311.7 MB |
References
https://huggingface.co/kz-transformers/kaz-roberta-conversational
Included Models
- DocumentAssembler
- TokenizerModel
- RoBertaEmbeddings