Edit on GitHub
  • John Snow Labs
  • Apr 01, 2025

English minilm_l12_h384_uncased_nvidia_aegis_ai_safety_pipeline pipeline BertForSequenceClassification from AC

  • en
  • open_source
  • pipeline
  • onnx

Description

Pretrained BertForSequenceClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.minilm_l12_h384_uncased_nvidia_aegis_ai_safety_pipeline is a English model originally trained by AC.

Predicted Entities

Download Copy S3 URI

How to use

pipeline = PretrainedPipeline("minilm_l12_h384_uncased_nvidia_aegis_ai_safety_pipeline", lang = "en")
annotations =  pipeline.transform(df)

val pipeline = new PretrainedPipeline("minilm_l12_h384_uncased_nvidia_aegis_ai_safety_pipeline", lang = "en")
val annotations = pipeline.transform(df)

Model Information

Model Name: minilm_l12_h384_uncased_nvidia_aegis_ai_safety_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: en
Size: 114.1 MB

References

References

https://huggingface.co/AC/MiniLM-L12-H384-uncased_Nvidia-Aegis-AI-Safety

Included Models

  • DocumentAssembler
  • TokenizerModel
  • BertForSequenceClassification