54-type PII coverage
According to the model card, the model identifies 54 sensitive-information types spanning personal, financial, medical, and contact categories, including credit cards, CVV, SSNs, and record numbers.
Open Source Model Profile · OpenMed
OpenMed-PII-SuperClinical-Large-434M-v1
OpenMed-PII-SuperClinical-Large-434M-v1 is a 434.12M-parameter DeBERTa token-classification model from OpenMed. Its model card documents PII detection across 54 sensitive-information types.
- Publisher
- OpenMed
- Task
- token-classification
- Model type
- deberta-v2
- License
- apache-2.0
- Library
- transformers
- Publication status
- Approved for indexing
Model overview
OpenMed-PII-SuperClinical-Large-434M-v1 is published by OpenMed as a token-classification model. The captured configuration identifies DebertaV2ForTokenClassification and Safetensors metadata reports 434,120,810 parameters. According to the model card, it is fine-tuned for PII detection over names, addresses, SSNs, medical record numbers, and more.
Recorded capabilities
Reported 0.9608 micro-F1
According to the model card, evaluation on a stratified 2,000-sample NVIDIA Nemotron-PII test set reports micro-F1 0.9608, precision 0.9685, recall 0.9532, and accuracy 0.9940.
Documented limits by entity
According to the model card, occupation, time, sexuality, education level, and fax number score lower and may need post-processing; some PII may be missed.
Use cases in the source record
- Automated redaction of PII in clinical notes, medical records, and documents for de-identification workflows.
- Privacy-compliance support for HIPAA and GDPR data preprocessing, auditing, and research preparation.
Limitations and unknowns
- No context-window value beyond the documented 384-token training length was extracted as a serving limit.
- Performance figures are publisher-reported on Nemotron-PII and were not independently verified by Ethen.
- The publisher notes English-primary training, possible false negatives, context sensitivity, and weaker occupation, time, and sexuality results.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: OpenMed/OpenMed-PII-SuperClinical-Large-434M-v1
Captured: Unknown. Processed: 2026-09-07T19:34:35.256764+00:00.
OpenMed-PII-SuperClinical-Large-434M-v1 PII Detection Model | 434M Parameters | Open Source Model Description OpenMed-PII-SuperClinical-Large-434M-v1 is a transformer-based token classification model fine-tuned for Personally Identifiable Information (PII) detection in text. This model identifies and classifies 54 types of sensitive information including names, addresses, SSNs, medical record numbers, and more. Key Features High Accuracy : Achieves strong F1 scores across diverse PII categories Comprehensive Coverage : Detects 50+ entity types spanning personal, financial, medical, and contact information Privacy-Focused : Designed…
F001F002F003F004F005F006F007F009F010F012F013F014F016F017