Description
Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.pruned_mt5_small_pipeline is a Japanese model originally trained by X-Wang.
How to use
pipeline = PretrainedPipeline("pruned_mt5_small_pipeline", lang = "ja")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("pruned_mt5_small_pipeline", lang = "ja")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | pruned_mt5_small_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ja |
| Size: | 394.7 MB |
References
https://huggingface.co/X-Wang/pruned-mt5-small
Included Models
- DocumentAssembler
- T5Transformer