Token Classification
GLiNER
atomizer
atomic-claims
claim-extraction
decontextualization
fact-checking
check-worthiness
Instructions to use nishparadox/atomizer-gliner2.5-base-native with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER
How to use nishparadox/atomizer-gliner2.5-base-native with GLiNER:
from gliner import GLiNER model = GLiNER.from_pretrained("nishparadox/atomizer-gliner2.5-base-native") 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
card: parameter count, possessive wording
Browse files
README.md
CHANGED
|
@@ -111,8 +111,8 @@ print(atomizer.explain(text).show()) # every head's predictions
|
|
| 111 |
|
| 112 |
Those of the small model (its [card](https://huggingface.co/nishparadox/atomizer-gliner-small)), plus: ~1.6× slower
|
| 113 |
than the small model on a CPU (12 encoder layers to its 6); `v0.1` collapses on heavily repetitive text (100+
|
| 114 |
-
near-identical sentences); `v0.2` resolves "I" to a self-given name but
|
| 115 |
-
|
| 116 |
|
| 117 |
## License
|
| 118 |
|
|
|
|
| 111 |
|
| 112 |
Those of the small model (its [card](https://huggingface.co/nishparadox/atomizer-gliner-small)), plus: ~1.6× slower
|
| 113 |
than the small model on a CPU (12 encoder layers to its 6); `v0.1` collapses on heavily repetitive text (100+
|
| 114 |
+
near-identical sentences); `v0.2` resolves "I" and "my" to a self-given name, but writes the
|
| 115 |
+
possessive ("Paradox's lab") less reliably than the small `v0.6`.
|
| 116 |
|
| 117 |
## License
|
| 118 |
|