Instructions to use Delicalib/ru_patents_ner-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- spaCy
How to use Delicalib/ru_patents_ner-tiny with spaCy:
!pip install https://huggingface.co/Delicalib/ru_patents_ner-tiny/resolve/main/ru_patents_ner-tiny-any-py3-none-any.whl # Using spacy.load(). import spacy nlp = spacy.load("ru_patents_ner-tiny") # Importing as module. import ru_patents_ner-tiny nlp = ru_patents_ner-tiny.load() - Notebooks
- Google Colab
- Kaggle
| Feature | Description |
|---|---|
| Name | ru_patents_ner_tiny |
| Version | 1.0.0 |
| spaCy | >=3.8.5,<3.9.0 |
| Default Pipeline | transformer, ner |
| Components | transformer, ner |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | n/a |
Label Scheme
View label scheme (3 labels for 1 components)
| Component | Labels |
|---|---|
ner |
ATTRIBUTE, COMPONENT, SYSTEM |
Accuracy
| Type | Score |
|---|---|
F1_MICRO |
56.28 |
F1_MACRO |
47.31 |
F1_WEIGHTED |
54.85 |
F1_COMPONENT |
62.57 |
F1_SYSTEM |
51.35 |
F1_ATTRIBUTE |
28.00 |
ENTS_P |
57.47 |
ENTS_R |
55.14 |
ENTS_F |
56.28 |
TRANSFORMER_LOSS |
327438.36 |
NER_LOSS |
528888.28 |
- Downloads last month
- 3
Evaluation results
- NER Precisionself-reported0.575
- NER Recallself-reported0.551
- NER F Scoreself-reported0.563