Description
Pretrained MPNetEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.cross_all_bs192_hardneg_finetuned_webnlg2020_relevance_pipeline is a English model originally trained by teven.
How to use
pipeline = PretrainedPipeline("cross_all_bs192_hardneg_finetuned_webnlg2020_relevance_pipeline", lang = "en")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("cross_all_bs192_hardneg_finetuned_webnlg2020_relevance_pipeline", lang = "en")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | cross_all_bs192_hardneg_finetuned_webnlg2020_relevance_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 407.3 MB |
References
https://huggingface.co/teven/cross_all_bs192_hardneg_finetuned_WebNLG2020_relevance
Included Models
- DocumentAssembler
- MPNetEmbeddings