Description
Pretrained MPNetEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.embed_andegpt_h768_pipeline is a Castilian, Spanish model originally trained by enpaiva.
How to use
pipeline = PretrainedPipeline("embed_andegpt_h768_pipeline", lang = "es")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("embed_andegpt_h768_pipeline", lang = "es")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | embed_andegpt_h768_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | es |
| Size: | 379.4 MB |
References
https://huggingface.co/enpaiva/embed-andegpt-H768
Included Models
- DocumentAssembler
- MPNetEmbeddings