Description
Pretrained BertForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.mbert_hindi_bengali_mlm_squad_tydi_mlqa_pipeline is a Hindi model originally trained by hapandya.
How to use
pipeline = PretrainedPipeline("mbert_hindi_bengali_mlm_squad_tydi_mlqa_pipeline", lang = "hi")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("mbert_hindi_bengali_mlm_squad_tydi_mlqa_pipeline", lang = "hi")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | mbert_hindi_bengali_mlm_squad_tydi_mlqa_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | hi |
| Size: | 663.7 MB |
References
https://huggingface.co/hapandya/mBERT-hi-bn-MLM-SQuAD-TyDi-MLQA
Included Models
- MultiDocumentAssembler
- BertForQuestionAnswering