Description
Pretrained CamemBertEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.adminbert_4gb_pipeline is a French model originally trained by taln-ls2n.
How to use
pipeline = PretrainedPipeline("adminbert_4gb_pipeline", lang = "fr")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("adminbert_4gb_pipeline", lang = "fr")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | adminbert_4gb_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | fr |
| Size: | 412.8 MB |
References
https://huggingface.co/taln-ls2n/AdminBERT-4GB
Included Models
- DocumentAssembler
- TokenizerModel
- CamemBertEmbeddings