Downloads · 30 days
0
arabart-lr-classifier
mEissa2254/arabart-lr-classifier
arabart-lr-classifier is a text classification model from mEissa2254. Use it when you need a label for a piece of text.
1. AraBART generates a summary from the input Arabic text 2. TF-IDF vectorizes both the original text and the generated summary 3. Logistic Regression classifies the combined features
Access
Public
Updated May 18, 2026
Repo size
559 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors557 MB · 99%
At a glance
- Task
- Text Classification
- Access
- Public
- Created
- May 18, 2026
- Updated
- May 18, 2026
- SHA
- fafc1ef5
Try a prompt
Model card
From the Hugging Face model README
AraBART + Logistic Regression — Arabic Text Classifier
Pipeline
- AraBART generates a summary from the input Arabic text
- TF-IDF vectorizes both the original text and the generated summary
- Logistic Regression classifies the combined features
Test Results
- Accuracy : 95.92%
- F1-score : 95.91%
Files
| File | Description |
|---|---|
| arabart/ | Fine-tuned AraBART model + tokenizer |
| lr_model.pkl | Trained Logistic Regression |
| tfidf_text.pkl | TF-IDF vectorizer for original text |
| tfidf_sum.pkl | TF-IDF vectorizer for AraBART summaries |
- Task
- Text Classification
- Languages
- ar
- Created
- May 18, 2026
- Updated
- May 18, 2026