-
NAMAA-Space/halluscoring-camelbert-qa
Text Classification • 0.1B • Updated • 8 -
NAMAA-Space/halluscoring-camelbert-nli
Text Classification • 0.1B • Updated • 14 -
NAMAA-Space/halluscoring-marbert-nli
Text Classification • 0.2B • Updated • 13 -
NAMAA-Space/halluscoring-arbert-nli
Text Classification • 0.2B • Updated • 15
AI & ML interests
ArabicNLP, LLMs, RAG, Evaluation, Embeddings, Datasets
Recent Activity
View all activity
NAMAA at DialectSentEval 2026 Subtask 2 (Arabic Dialect Sentiment Swap): 6 fine-tuned seq2seq backbones. 96.78 dev / 0.7597 test.
NAMAA at KnowledgeGraphEval 2026 (ArabicNLP 2026): AdaptNER 1st (75.96), RE 2nd (93.48).
-
NAMAA-Space/KnowledgeGraphEval-2026-AdaptNER-AraBERTv02-Nested
Token Classification • 0.1B • Updated • 54 • 1 -
NAMAA-Space/KnowledgeGraphEval-2026-AdaptNER-MARBERTv2-Nested
Token Classification • 0.2B • Updated • 16 -
NAMAA-Space/KnowledgeGraphEval-2026-AdaptNER-AraBERTv02-Flat
Token Classification • 0.1B • Updated • 24 -
NAMAA-Space/KnowledgeGraphEval-2026-AdaptNER-Experiments
Updated
This collection shows NAMAA's list of Arabic ASR Models and datasets
-
NAMAA-Space/Cohere-Speech-Tashkeel-2B
Automatic Speech Recognition • 2B • Updated • 2.53k • 32 -
NAMAA-Space/cohere-transcribe-arabic-07-2026-int4
Automatic Speech Recognition • 2B • Updated • 100 • 5 -
NAMAA-Space/cohere-transcribe-arabic-07-2026-int8
Automatic Speech Recognition • 2B • Updated • 387 • 3 -
NAMAA-Space/EgypTalk-ASR-v2
Updated • 194 • 19
This collection brings together a set of Arabic-focused models, datasets, and tools designed to improve the security and safety of LLMs
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.
-
NAMAA-Space/aragenre-e5-large-mnrl-augmented-defs
Sentence Similarity • 0.6B • Updated • 15 -
NAMAA-Space/aragenre-qwen2.5-7b-fewshot-v3
Text Generation • Updated -
NAMAA-Space/aragenre-mdeberta-devgold-finetune
Text Classification • 0.3B • Updated • 9 -
NAMAA-Space/aragenre-multiembedding-fusion-ensemble-v3
Updated
-
NAMAA-Space/NAMAA-BAREC2026-Sent-AraBERTv2-Reg-run1
Text Classification • 0.1B • Updated • 24 -
NAMAA-Space/NAMAA-BAREC2026-Sent-AraBERTv2-Reg-run2
Text Classification • Updated • 28 -
NAMAA-Space/NAMAA-BAREC2026-Sent-CAMeL-AraBERTv2-d3tok-OrdThr
Text Classification • 0.1B • Updated • 30 -
NAMAA-Space/NAMAA-BAREC2026-Sent-AraELECTRA-OrdThr
Text Classification • 0.1B • Updated • 25
-
NAMAA-Space/nadi26-adi20-whisper-small
Audio Classification • 88.8M • Updated • 57 -
NAMAA-Space/nadi26-adi20-ensemble
Audio Classification • Updated -
NAMAA-Space/nadi26-adi20-ecapa-tdnn
Audio Classification • 21.2M • Updated -
NAMAA-Space/nadi26-adi20-xls-r-300m
Audio Classification • 0.3B • Updated • 40
𝐵𝑢𝑖𝑙𝑡 𝑜𝑛 𝑡ℎ𝑒 𝑝𝑜𝑤𝑒𝑟𝑓𝑢𝑙 𝑄𝑤𝑒𝑛2 𝑉𝐿 2𝐵 𝑎𝑛𝑑 𝑓𝑖𝑛𝑒-𝑡𝑢𝑛𝑒𝑑 𝑜𝑛 𝑎𝑛 𝐴𝑟𝑎𝑏𝑖𝑐 𝑂𝐶𝑅 𝑑𝑎𝑡𝑎𝑠𝑒𝑡, 𝑄𝑎𝑟𝑖 𝑣0.1 𝑑𝑒
-
Arabic OCR Demos
🐢75Arabic OCR Models Demo
-
NAMAA-Space/KhattVision-Muse-Glimmer-30B-LoRA
Image-Text-to-Text • Updated • 44 • 5 -
QARI-OCR: High-Fidelity Arabic Text Recognition through Multimodal Large Language Model Adaptation
Paper • 2506.02295 • Published • 16 -
NAMAA-Space/Qari-OCR-0.4.0-VL-4B-Instruct
Image-to-Text • Updated • 1.01k • 10
These are NAMAA Models for AlexandriaX-2026 Shared Task in ArabicNLP2026
Unified hub for Saudi Arabic dialect datasets, models, and benchmarks produced by NAMAA Community.
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
-
NAMAA-Space/halluscoring-camelbert-qa
Text Classification • 0.1B • Updated • 8 -
NAMAA-Space/halluscoring-camelbert-nli
Text Classification • 0.1B • Updated • 14 -
NAMAA-Space/halluscoring-marbert-nli
Text Classification • 0.2B • Updated • 13 -
NAMAA-Space/halluscoring-arbert-nli
Text Classification • 0.2B • Updated • 15
-
NAMAA-Space/aragenre-e5-large-mnrl-augmented-defs
Sentence Similarity • 0.6B • Updated • 15 -
NAMAA-Space/aragenre-qwen2.5-7b-fewshot-v3
Text Generation • Updated -
NAMAA-Space/aragenre-mdeberta-devgold-finetune
Text Classification • 0.3B • Updated • 9 -
NAMAA-Space/aragenre-multiembedding-fusion-ensemble-v3
Updated
NAMAA at DialectSentEval 2026 Subtask 2 (Arabic Dialect Sentiment Swap): 6 fine-tuned seq2seq backbones. 96.78 dev / 0.7597 test.
-
NAMAA-Space/NAMAA-BAREC2026-Sent-AraBERTv2-Reg-run1
Text Classification • 0.1B • Updated • 24 -
NAMAA-Space/NAMAA-BAREC2026-Sent-AraBERTv2-Reg-run2
Text Classification • Updated • 28 -
NAMAA-Space/NAMAA-BAREC2026-Sent-CAMeL-AraBERTv2-d3tok-OrdThr
Text Classification • 0.1B • Updated • 30 -
NAMAA-Space/NAMAA-BAREC2026-Sent-AraELECTRA-OrdThr
Text Classification • 0.1B • Updated • 25
-
NAMAA-Space/nadi26-adi20-whisper-small
Audio Classification • 88.8M • Updated • 57 -
NAMAA-Space/nadi26-adi20-ensemble
Audio Classification • Updated -
NAMAA-Space/nadi26-adi20-ecapa-tdnn
Audio Classification • 21.2M • Updated -
NAMAA-Space/nadi26-adi20-xls-r-300m
Audio Classification • 0.3B • Updated • 40
NAMAA at KnowledgeGraphEval 2026 (ArabicNLP 2026): AdaptNER 1st (75.96), RE 2nd (93.48).
-
NAMAA-Space/KnowledgeGraphEval-2026-AdaptNER-AraBERTv02-Nested
Token Classification • 0.1B • Updated • 54 • 1 -
NAMAA-Space/KnowledgeGraphEval-2026-AdaptNER-MARBERTv2-Nested
Token Classification • 0.2B • Updated • 16 -
NAMAA-Space/KnowledgeGraphEval-2026-AdaptNER-AraBERTv02-Flat
Token Classification • 0.1B • Updated • 24 -
NAMAA-Space/KnowledgeGraphEval-2026-AdaptNER-Experiments
Updated
This collection shows NAMAA's list of Arabic ASR Models and datasets
-
NAMAA-Space/Cohere-Speech-Tashkeel-2B
Automatic Speech Recognition • 2B • Updated • 2.53k • 32 -
NAMAA-Space/cohere-transcribe-arabic-07-2026-int4
Automatic Speech Recognition • 2B • Updated • 100 • 5 -
NAMAA-Space/cohere-transcribe-arabic-07-2026-int8
Automatic Speech Recognition • 2B • Updated • 387 • 3 -
NAMAA-Space/EgypTalk-ASR-v2
Updated • 194 • 19
𝐵𝑢𝑖𝑙𝑡 𝑜𝑛 𝑡ℎ𝑒 𝑝𝑜𝑤𝑒𝑟𝑓𝑢𝑙 𝑄𝑤𝑒𝑛2 𝑉𝐿 2𝐵 𝑎𝑛𝑑 𝑓𝑖𝑛𝑒-𝑡𝑢𝑛𝑒𝑑 𝑜𝑛 𝑎𝑛 𝐴𝑟𝑎𝑏𝑖𝑐 𝑂𝐶𝑅 𝑑𝑎𝑡𝑎𝑠𝑒𝑡, 𝑄𝑎𝑟𝑖 𝑣0.1 𝑑𝑒
-
Arabic OCR Demos
🐢75Arabic OCR Models Demo
-
NAMAA-Space/KhattVision-Muse-Glimmer-30B-LoRA
Image-Text-to-Text • Updated • 44 • 5 -
QARI-OCR: High-Fidelity Arabic Text Recognition through Multimodal Large Language Model Adaptation
Paper • 2506.02295 • Published • 16 -
NAMAA-Space/Qari-OCR-0.4.0-VL-4B-Instruct
Image-to-Text • Updated • 1.01k • 10
These are NAMAA Models for AlexandriaX-2026 Shared Task in ArabicNLP2026
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.
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.