# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("PRAli22/arabert_arabic_ner")
model = AutoModelForTokenClassification.from_pretrained("PRAli22/arabert_arabic_ner", device_map="auto")Quick Links
AraBERT_Arabic_NER
This is fine tuned AraBERT model for Arabic NER
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation results
Accuracy score was about 97% F1 score was 0.82
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: None
- training_precision: float32
- Downloads last month
- 62
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="PRAli22/arabert_arabic_ner")