Instructions to use yethdev/gliner2-pii-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER2
How to use yethdev/gliner2-pii-onnx with GLiNER2:
from gliner2 import GLiNER2 model = GLiNER2.from_pretrained("yethdev/gliner2-pii-onnx") # Extract entities text = "Apple CEO Tim Cook announced iPhone 15 in Cupertino yesterday." result = extractor.extract_entities(text, ["company", "person", "product", "location"]) print(result) - Notebooks
- Google Colab
- Kaggle
| { | |
| "source_model": "fastino/gliner2-privacy-filter-PII-multi", | |
| "opset": 17, | |
| "quantization": { | |
| "scheme": "B_fp16_weights", | |
| "description": "weight-only compression, fp32 compute: MatMul weights stored fp16 (Cast to fp32 at load), 250112x768 token-embedding table stored int8 with per-row symmetric scales (dequantized after Gather)", | |
| "max_prob_drift_vs_pytorch": 0.005668938159942627, | |
| "span_set_parity": "identical to PyTorch engine at thresholds 0.3/0.5/0.7 on the golden suite" | |
| }, | |
| "fp32_parity": "max prob drift 1.29e-05, span sets identical (see export_to_onnx.py output)", | |
| "files": { | |
| "model.quantized.onnx": { | |
| "sizeBytes": 446391629, | |
| "sha256": "489edc522a34b8c6a0630c4710998abf0227b11acf45600ba2bce95bcd943930" | |
| }, | |
| "tokenizer.json": { | |
| "sizeBytes": 16020604, | |
| "sha256": "f6df10ec83bea993035b2dd7c39345a3d4fcf23421c2adb6cb4ffc1e6d1bc4b5" | |
| }, | |
| "tokenizer_config.json": { | |
| "sizeBytes": 711, | |
| "sha256": "233beed1f1095cccfc7907cde31a8d90a0c6aa4fdfaf6493f8e55fd162e81ae6" | |
| } | |
| } | |
| } |