Instructions to use jfrei/de_GERNERMEDpp_GottBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- spaCy
How to use jfrei/de_GERNERMEDpp_GottBERT with spaCy:
!pip install https://huggingface.co/jfrei/de_GERNERMEDpp_GottBERT/resolve/main/de_GERNERMEDpp_GottBERT-any-py3-none-any.whl # Using spacy.load(). import spacy nlp = spacy.load("de_GERNERMEDpp_GottBERT") # Importing as module. import de_GERNERMEDpp_GottBERT nlp = de_GERNERMEDpp_GottBERT.load() - Notebooks
- Google Colab
- Kaggle
GermanBERT-based model of the GERNERMED++ German NER model for medical entities.
| Feature | Description |
|---|---|
| Name | de_GERNERMEDpp_GottBERT |
| Version | 1.0.0 |
| spaCy | >=3.2.3,<3.3.0 |
| Default Pipeline | transformer, ner |
| Components | transformer, ner |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | Johann Frei |
Label Scheme
View label scheme (6 labels for 1 components)
| Component | Labels |
|---|---|
ner |
Dosage, Drug, Duration, Form, Frequency, Strength |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
92.24 |
ENTS_P |
92.40 |
ENTS_R |
92.07 |
TRANSFORMER_LOSS |
353176.15 |
NER_LOSS |
525846.32 |
- Downloads last month
- 14
Evaluation results
- NER Precisionself-reported0.924
- NER Recallself-reported0.921
- NER F Scoreself-reported0.922