Description
Pretrained BertForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.minilmv2_l6_h768_from_bert_large_mrqa_pipeline is a English model originally trained by VMware.
How to use
pipeline = PretrainedPipeline("minilmv2_l6_h768_from_bert_large_mrqa_pipeline", lang = "en")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("minilmv2_l6_h768_from_bert_large_mrqa_pipeline", lang = "en")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | minilmv2_l6_h768_from_bert_large_mrqa_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 247.9 MB |
References
https://huggingface.co/VMware/minilmv2-l6-h768-from-bert-large-mrqa
Included Models
- MultiDocumentAssembler
- BertForQuestionAnswering