Arabic-MARBERT-Sentiment Model
Model description
Arabic-MARBERT-Sentiment Model is a Sentiment analysis model that was built by fine-tuning the MARBERT model. For the fine-tuning, I used KAUST dataset, which includes 3 labels(positive,negative,and neutral).
How to use
To use the model with a transformers pipeline:
>>>from transformers import pipeline
>>>model = pipeline('text-classification', model='Ammar-alhaj-ali/arabic-MARBERT-sentiment')
>>>sentences = ['لقد استمتعت بالحفلة', 'خدمة المطعم كانت محبطة']
>>>model(sentences)
[{'label': 'positive', 'score': 0.9577557444572449},
{'label': 'negative', 'score': 0.9158180952072144}]
- Downloads last month
- 223
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.