Zero-Shot Classification
Transformers
ONNX
English
nli
compliance
popia
south-africa
data-protection
ai-act
Eval Results (legacy)
Instructions to use labrat-aiko/nli-popia-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use labrat-aiko/nli-popia-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="labrat-aiko/nli-popia-v2")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("labrat-aiko/nli-popia-v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Add calibration.json (temperature scaling constant T*=2.5492, ECE 0.171 -> 0.075)
Verified signaturef602d3e -
Fix model size (22M -> 82M), quantized size (~25MB -> ~79MB), dataset links, and model-index YAML structure
Verified signature6ad2742 -
Initial release: ONNX + eval bundles for POPIA-Judge v2 (10-clause)
Verified signature6f98042 -
initial commit
Verified signatured9e9dc1