Instructions to use Delicalib/ru_patents_ner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- spaCy
How to use Delicalib/ru_patents_ner with spaCy:
!pip install https://huggingface.co/Delicalib/ru_patents_ner/resolve/main/ru_patents_ner-any-py3-none-any.whl # Using spacy.load(). import spacy nlp = spacy.load("ru_patents_ner") # Importing as module. import ru_patents_ner nlp = ru_patents_ner.load() - Notebooks
- Google Colab
- Kaggle
| Feature | Description |
|---|---|
| Name | ru_patents_ner |
| Version | 1.0.0 |
| spaCy | >=3.8.5,<3.9.0 |
| Default Pipeline | transformer, ner |
| Components | transformer, ner |
| Vectors | 500002 keys, 500002 unique vectors (300 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 |
61.24 |
F1_MACRO |
54.82 |
F1_WEIGHTED |
60.09 |
F1_COMPONENT |
67.20 |
F1_SYSTEM |
64.79 |
F1_ATTRIBUTE |
32.48 |
ENTS_P |
61.87 |
ENTS_R |
60.63 |
ENTS_F |
61.24 |
TRANSFORMER_LOSS |
144452.32 |
NER_LOSS |
222665.13 |
- Downloads last month
- 3
Evaluation results
- NER Precisionself-reported0.619
- NER Recallself-reported0.606
- NER F Scoreself-reported0.612