|
--- |
|
license: apache-2.0 |
|
language: |
|
- ar |
|
base_model: |
|
- Kalmundi/Q8BERTA |
|
tags: |
|
- transformers |
|
- safetensors |
|
- sentiment-analysis |
|
--- |
|
|
|
|
|
# Fine-Tuned SA-Q8BERTA Model for Sentiment Analysis |
|
|
|
This model is a fine-tuned version of [Kalmundi/Q8BERTA](https://huggingface.co/Kalmundi/Q8BERTA), which was trained on a customized dataset for sentiment analysis. |
|
This model mainly focuses on Sentiment Analysis for the Kuwaiti Dialect. |
|
|
|
## Model Details |
|
|
|
- **Base Model**: The original model is [Kalmundi/Q8BERTA](https://huggingface.co/Kalmundi/Q8BERTA), a transformer-based model pre-trained on a sufficient size Kuwaiti Dialect dataset. |
|
- **Fine-Tuning**: This model was fine-tuned on a dataset for sentiment analysis related to Kuwaiti Dialect, and it can classify text as either positive or negative. |
|
- **Fine-Tuning Task**: The model was fine-tuned for 5 epochs with a learning rate of `2e-5`. |
|
|
|
## Model Usage |
|
|
|
To use the model for sentiment analysis: |
|
|
|
```python |
|
from transformers import pipeline |
|
|
|
# Load the fine-tuned model |
|
classifier = pipeline("text-classification", model="Kalmundi/Q8BERTA-SA") |
|
|
|
# Test the classifier |
|
result = classifier("ุงูุฌู ุงูููู
ูุงูุฏ ุญูู") |
|
print(result) |