Instructions to use Sahajtomar/NER_legal_de with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sahajtomar/NER_legal_de with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Sahajtomar/NER_legal_de")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("Sahajtomar/NER_legal_de") model = AutoModelForTokenClassification.from_pretrained("Sahajtomar/NER_legal_de") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Error:"datasets[0]" with value "legal entity recognition" is not valid. If possible, use a dataset id from https://hf.co/datasets.
NER model trained on BERT
MODEL used for fine tuning is GBERT Large by deepset.ai
Test
Accuracy: 98
F1: 84.1
Precision: 82.7
Recall: 85.5
Model inferencing:
!pip install -q transformers
from transformers import pipeline
ner = pipeline(
"ner",
model="Sahajtomar/NER_legal_de",
tokenizer="Sahajtomar/NER_legal_de")
nlp_ner("Für eine Zuständigkeit des Verwaltungsgerichts Berlin nach § 52 Nr. 1 bis 4 VwGO hat der \
Antragsteller keine Anhaltspunkte vorgetragen .")
- Downloads last month
- 9