Description
Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.msmarco_hindi_mt5_base_v1_pipeline is a Hindi model originally trained by doc2query.
How to use
pipeline = PretrainedPipeline("msmarco_hindi_mt5_base_v1_pipeline", lang = "hi")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("msmarco_hindi_mt5_base_v1_pipeline", lang = "hi")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | msmarco_hindi_mt5_base_v1_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Language: | hi |
| Size: | 2.4 GB |
References
https://huggingface.co/doc2query/msmarco-hindi-mt5-base-v1
Included Models
- DocumentAssembler
- T5Transformer