Text Classification
Transformers
Safetensors
Arabic
xlm-roberta
semantic-highlighting
arabic
sentence-relevance
rag
reranker
Eval Results (legacy)
text-embeddings-inference
Instructions to use HeshamHaroon/arabic-semantic-highlighter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HeshamHaroon/arabic-semantic-highlighter with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="HeshamHaroon/arabic-semantic-highlighter")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("HeshamHaroon/arabic-semantic-highlighter") model = AutoModelForSequenceClassification.from_pretrained("HeshamHaroon/arabic-semantic-highlighter") - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_name": "BAAI/bge-reranker-base", | |
| "dataset": "HeshamHaroon/arabic-semantic-relevance", | |
| "task": "sentence-level-highlighting", | |
| "epochs": 3, | |
| "batch_size": 8, | |
| "learning_rate": 2e-05, | |
| "train_sentences": 88110, | |
| "test_results": { | |
| "eval_loss": 0.2000904530286789, | |
| "eval_accuracy": 0.9313270046455262, | |
| "eval_f1": 0.9457562220804084, | |
| "eval_precision": 0.94848, | |
| "eval_recall": 0.9430480432707604, | |
| "eval_auc": 0.9823959128165132, | |
| "eval_runtime": 14.9552, | |
| "eval_samples_per_second": 331.055, | |
| "eval_steps_per_second": 20.729, | |
| "epoch": 3.0 | |
| }, | |
| "completed_at": "2026-01-13T14:39:05.018353" | |
| } |