Token Classification
GLiNER
PyTorch
pii-detection
ner
multilingual
romanian
cee
on-device
privacy
Eval Results (legacy)
Instructions to use flowxai/cee-pii with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER
How to use flowxai/cee-pii with GLiNER:
from gliner import GLiNER model = GLiNER.from_pretrained("flowxai/cee-pii") - Notebooks
- Google Colab
- Kaggle
Link inference contract from card (ceepii_labels_v1)
Browse files
README.md
CHANGED
|
@@ -50,6 +50,16 @@ model-index:
|
|
| 50 |
value: 0.000
|
| 51 |
---
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
<!--
|
| 54 |
PREPARED FOR HUGGING FACE — NOT YET UPLOADED. Nothing here has been published.
|
| 55 |
|
|
|
|
| 50 |
value: 0.000
|
| 51 |
---
|
| 52 |
|
| 53 |
+
## Inference contract
|
| 54 |
+
|
| 55 |
+
`cee-pii` is a GLiNER model — its contract is the **exact label set** it was fine-tuned
|
| 56 |
+
on plus the GLiNER call and post-processing. See [`inference_contract/`](./inference_contract):
|
| 57 |
+
|
| 58 |
+
- [`INFERENCE.md`](./inference_contract/INFERENCE.md) — load + `predict_entities(text, LABELS, threshold=0.5)`, the verbatim label contract, span-alignment drop, and the per-type checksum validators.
|
| 59 |
+
- [`labels_ceepii_v1.json`](./inference_contract/labels_ceepii_v1.json) — the 34 canonical labels (short id ↔ phrasing). Pass the **phrasings** verbatim.
|
| 60 |
+
|
| 61 |
+
Label-set version `ceepii_labels_v1`, frozen with the weights.
|
| 62 |
+
|
| 63 |
<!--
|
| 64 |
PREPARED FOR HUGGING FACE — NOT YET UPLOADED. Nothing here has been published.
|
| 65 |
|