This is an ONNX version of scanpatch/pii-ner-nemotron. It was automatically converted and uploaded using this Hugging Face Space.
See the pipeline documentation for token-classification: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.TokenClassificationPipeline
PII NER model trained on nemotron dataset for multilingual PII entity extraction.
xlm-roberta-largescanpatch/pii-ner-nemotronpii-ner-nemotron2025-12-29T12:06:13.731145+00:00addressaddress_apartmentaddress_buildingaddress_cityaddress_countryaddress_districtaddress_geolocationaddress_houseaddress_postal_codeaddress_regionaddress_streetdatedocument_numberemailfirst_nameiplast_namemiddle_namemilitary_individual_numbermobile_phonenamename_initialsnicknameorganizationsnilstinvehicle_number| Metric | Value |
|---|---|
test_f1 |
0.9768405285513023 |
test_precision |
0.9734942064790006 |
test_recall |
0.9802099354987895 |
test_accuracy |
0.9977181928808507 |
train_runtime |
1693.5057 |
train_samples_per_second |
238.116 |
from transformers import pipeline
ner = pipeline(
"token-classification",
model="scanpatch/pii-ner-nemotron",
aggregation_strategy="simple",
)
text = "Contact me at test@example.com and my phone is +380 67 123 45 67."
print(ner(text))
onnx/model_bnb4.onnx 1.2 GBonnx/model_q4.onnx 1.2 GBonnx/model_q4f16.onnx 684 MBonnx/model_uint8.onnx 561 MBonnx/model_int8.onnx 561 MBonnx/model_quantized.onnx 561 MBonnx/model.onnx 488.6 kBonnx/model_fp16.onnx 0.1 kB