Description
Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.detoxify_inference_pipeline_pipeline is a English model originally trained by Benezio.
How to use
pipeline = PretrainedPipeline("detoxify_inference_pipeline_pipeline", lang = "en")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("detoxify_inference_pipeline_pipeline", lang = "en")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | detoxify_inference_pipeline_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 346.2 MB |
References
https://huggingface.co/Benezio/detoxify-inference-pipeline
Included Models
- DocumentAssembler
- T5Transformer