Instructions to use bijinpanicker/NuNER_Zero-span-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER
How to use bijinpanicker/NuNER_Zero-span-ONNX with GLiNER:
from gliner import GLiNER model = GLiNER.from_pretrained("bijinpanicker/NuNER_Zero-span-ONNX") text = "Cristiano Ronaldo dos Santos Aveiro was born on 5 February 1985 in Funchal, Madeira, Portugal." labels = ["person", "date", "location"] entities = model.predict_entities(text, labels) for entity in entities: print(entity["text"], "=>", entity["label"]) - Notebooks
- Google Colab
- Kaggle
NuNER Zeroβspan (8-bit ONNX)
This is an 8-bit quantized ONNX version of numind/NuNER_Zero-span, a zero-shot named entity recognition (NER) model based on the GLiNER architecture.
π§ Features
- π§ Zero-shot span-based NER
- π¦ Quantized to 8-bit for faster, smaller inference
- π¬ Input: text + list of labels
- πͺ Output: text spans per label (max span length = 12 tokens)
- π Format: ONNX
π License
MIT License β same as the original model.
π Acknowledgements
Model tree for bijinpanicker/NuNER_Zero-span-ONNX
Base model
numind/NuNER_Zero-span