This collection brings together a set of Arabic-focused models, datasets, and tools designed to improve the security and safety of LLMs
AI & ML interests
ArabicNLP, LLMs, RAG, Evaluation, Embeddings, Datasets
Recent Activity
View all activity
𝐵𝑢𝑖𝑙𝑡 𝑜𝑛 𝑡ℎ𝑒 𝑝𝑜𝑤𝑒𝑟𝑓𝑢𝑙 𝑄𝑤𝑒𝑛2 𝑉𝐿 2𝐵 𝑎𝑛𝑑 𝑓𝑖𝑛𝑒-𝑡𝑢𝑛𝑒𝑑 𝑜𝑛 𝑎𝑛 𝐴𝑟𝑎𝑏𝑖𝑐 𝑂𝐶𝑅 𝑑𝑎𝑡𝑎𝑠𝑒𝑡, 𝑄𝑎𝑟𝑖 𝑣0.1 𝑑𝑒
-
Arabic OCR Demos
🐢66Arabic OCR Models Demo
-
QARI-OCR: High-Fidelity Arabic Text Recognition through Multimodal Large Language Model Adaptation
Paper • 2506.02295 • Published • 14 -
NAMAA-Space/Qari-OCR-0.4.0-VL-4B-Instruct
Image-to-Text • Updated • 1.58k • 6 -
NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct
Image-Text-to-Text • 2B • Updated • 2.59k • 17
AraModernBert is an advanced Arabic language model built on the ModernBERT architecture.
This blog post introduces the Zaraah family of static embedding models, designed for Arabic language tasks and built using the model2vec distillation
Unified hub for Saudi Arabic dialect datasets, models, and benchmarks produced by NAMAA Community.
This collection contains different Arabic datasets and models for retrieval and reranking tasks.
This collection includes datasets, models , and spaces for dialect Translator.
Versatile, plug-and-play NER model tailored for Arabic, designed to work with custom entity types—no fine-tuning needed.
This collection brings together a set of Arabic-focused models, datasets, and tools designed to improve the security and safety of LLMs
Unified hub for Saudi Arabic dialect datasets, models, and benchmarks produced by NAMAA Community.
𝐵𝑢𝑖𝑙𝑡 𝑜𝑛 𝑡ℎ𝑒 𝑝𝑜𝑤𝑒𝑟𝑓𝑢𝑙 𝑄𝑤𝑒𝑛2 𝑉𝐿 2𝐵 𝑎𝑛𝑑 𝑓𝑖𝑛𝑒-𝑡𝑢𝑛𝑒𝑑 𝑜𝑛 𝑎𝑛 𝐴𝑟𝑎𝑏𝑖𝑐 𝑂𝐶𝑅 𝑑𝑎𝑡𝑎𝑠𝑒𝑡, 𝑄𝑎𝑟𝑖 𝑣0.1 𝑑𝑒
-
Arabic OCR Demos
🐢66Arabic OCR Models Demo
-
QARI-OCR: High-Fidelity Arabic Text Recognition through Multimodal Large Language Model Adaptation
Paper • 2506.02295 • Published • 14 -
NAMAA-Space/Qari-OCR-0.4.0-VL-4B-Instruct
Image-to-Text • Updated • 1.58k • 6 -
NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct
Image-Text-to-Text • 2B • Updated • 2.59k • 17
This collection contains different Arabic datasets and models for retrieval and reranking tasks.
AraModernBert is an advanced Arabic language model built on the ModernBERT architecture.
This collection includes datasets, models , and spaces for dialect Translator.
This blog post introduces the Zaraah family of static embedding models, designed for Arabic language tasks and built using the model2vec distillation
Versatile, plug-and-play NER model tailored for Arabic, designed to work with custom entity types—no fine-tuning needed.