Description
Pretrained BertSentenceEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.sent_bert_large_nordic_pile_1m_steps_pipeline is a Swedish model originally trained by AI-Sweden-Models.
How to use
pipeline = PretrainedPipeline("sent_bert_large_nordic_pile_1m_steps_pipeline", lang = "sv")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("sent_bert_large_nordic_pile_1m_steps_pipeline", lang = "sv")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | sent_bert_large_nordic_pile_1m_steps_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | sv |
| Size: | 1.4 GB |
References
https://huggingface.co/AI-Sweden-Models/bert-large-nordic-pile-1M-steps
Included Models
- DocumentAssembler
- TokenizerModel
- SentenceDetectorDLModel
- BertSentenceEmbeddings