Description
Pretrained DistilBertForSequenceClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.topics_classifier_distilbert_base_ukrainian_cased_pipeline is a Ukrainian model originally trained by ua-l.
How to use
pipeline = PretrainedPipeline("topics_classifier_distilbert_base_ukrainian_cased_pipeline", lang = "uk")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("topics_classifier_distilbert_base_ukrainian_cased_pipeline", lang = "uk")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | topics_classifier_distilbert_base_ukrainian_cased_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | uk |
| Size: | 197.2 MB |
References
https://huggingface.co/ua-l/topics-classifier-distilbert-base-uk-cased
Included Models
- DocumentAssembler
- TokenizerModel
- DistilBertForSequenceClassification