Downloads · 30 days
17
11% of all-time downloads
marabert2-levantine-toxic-model-v4
alan9622/marabert2-levantine-toxic-model-v4
marabert2-levantine-toxic-model-v4 is a text classification model from alan9622. Use it when you need a label for a piece of text. The card lists the license as apache-2.0.
This model identifies Hate Speech and Abusive Language in Levantine Arabic tweets. It was fine-tuned on the dataset: alan9622/marabert2-levantine-toxic-model-v4-dataset.
All-time downloads
161
Public
Parameters
163M
651 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors651 MB · 100%
At a glance
- Task
- Text Classification
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Mar 2, 2026
- Updated
- Mar 2, 2026
- SHA
- 79520deb
Try a prompt
Base models
Model card
From the Hugging Face model README
Levantine Hate Speech Classifier
This model identifies Hate Speech and Abusive Language in Levantine Arabic tweets. It was fine-tuned on the dataset: alan9622/marabert2-levantine-toxic-model-v4-dataset.
📊 Evaluation
| Metric | Score |
|---|---|
| Accuracy | 0.9128205128205128 |
| F1 Score | 0.908218073979278 |
📖 Labels
| ID | Label | Definition |
|---|---|---|
| 0 | normal | Safe text. |
| 1 | toxic | abusive or hate Insults/Vulgarity not directed at identity or Attacks based on religion, sect, gender, or nationality. |
Usage
from transformers import pipeline
classifier = pipeline("text-classification", model="alan9622/marabert2-levantine-toxic-model-v4")
classifier("يا زلمة حل عني")
- Task
- Text Classification
- Type
- bert
- License
- apache-2.0
- Languages
- ar
- Created
- Mar 2, 2026
- Updated
- Mar 2, 2026