Description
Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.vietnamese_t5_doc2query_trimm_vocab_pipeline is a English model originally trained by Turbo-AI.
How to use
pipeline = PretrainedPipeline("vietnamese_t5_doc2query_trimm_vocab_pipeline", lang = "en")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("vietnamese_t5_doc2query_trimm_vocab_pipeline", lang = "en")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | vietnamese_t5_doc2query_trimm_vocab_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 944.9 MB |
References
https://huggingface.co/Turbo-AI/vi-t5-doc2query-trimm-vocab
Included Models
- DocumentAssembler
- T5Transformer