Downloads · 30 days
97
0% of all-time downloads
Ammar-alhaj-ali/arabic-MARBERT-news-article-classification
arabic-MARBERT-news-article-classification is a text classification model from Ammar-alhaj-ali. Use it when you need a label for a piece of text. It is set up for transformers.
arabic-MARBERT-news-article-classification Model is a news article classification model that was built by fine-tuning the MARBERT model. For the fine-tuning, I used SANAD: Single-Label Arabic News Articles Dataset tha…
Downloads · 30 days
97
0% of all-time downloads
All-time downloads
79.9K
Public
Repo size
1.3 GB
Likes
4
Public
Click a slice to open those files.
.bin651 MB · 99%
From the Hugging Face model README
arabic-MARBERT-news-article-classification Model is a news article classification model that was built by fine-tuning the MARBERT model. For the fine-tuning, I used SANAD: Single-Label Arabic News Articles Dataset that includes 7 labels(Culture,Finance,Medical,Politics,Religion,Sports,and Tech).
To use the model with a transformers pipeline:
>>>from transformers import pipeline
>>>model = pipeline('text-classification', model='Ammar-alhaj-ali/arabic-MARBERT-news-article-classification')
>>>sentences = ['أخطرت شركة أرامكو السعودية 4 على الأقل من المشترين في شمال آسيا بأنها ستورد إليهم الكميات المتعاقد عليها من النفط الخام كاملة في سبتمبرأيلول المقبل. وقالت مصادر مطلعة لرويترز إن السعودية، أكبر مصدر النفط في العالم، كانت قد رفعت سعر البيع الرسمي للمشترين الآسيويين إلى مستويات قياسية لذلك الشهر.']
>>>model(sentences)
[{'label': 'Finance', 'score': 0.9998553991317749}]