Towards a Fully Arabic Retrieval-Augmented Generation (RAG) Pipeline:
•
6
Omartificial Intelligence Space PRO
Omartificial-Intelligence-Space
AI & ML interests
NLP & LLM
Recent Activity
updated
a model
about 8 hours ago
Omartificial-Intelligence-Space/GATE-AraBert-v1
liked
a model
about 11 hours ago
NAMAA-Space/AraModernBert-Topic-Classifier
upvoted
a
collection
1 day ago
Arabic-STS
Articles
Organizations
Collections
8
This collection highlights efforts to enhance Arabic NLP tasks using the latest ModernBERT models.
Collection of a comprehensive dataset of Arabic text sourced from the FineWeb2 project, representing diverse content across Arabic MSA and Dialect.
-
HuggingFaceFW/fineweb-2
Viewer • Updated • 12.5B • 91.1k • 389 -
Omartificial-Intelligence-Space/FineWeb2-MSA
Viewer • Updated • 907M • 3.13k • 1 -
Omartificial-Intelligence-Space/FineWeb2-Egyptian-Arabic
Viewer • Updated • 23.9M • 119 • 1 -
Omartificial-Intelligence-Space/FineWeb2-Moroccan-Arabic
Viewer • Updated • 69.6M • 106 • 1
Papers
2
spaces
7
models
20
Omartificial-Intelligence-Space/GATE-AraBert-v1
Sentence Similarity
•
Updated
•
2.65k
•
11
Omartificial-Intelligence-Space/GATE-AraBert-v0
Sentence Similarity
•
Updated
•
94
•
1
Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka
Sentence Similarity
•
Updated
•
335
•
1
Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2
Sentence Similarity
•
Updated
•
855
•
10
Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet
Sentence Similarity
•
Updated
•
1.09k
•
10
Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet
Sentence Similarity
•
Updated
•
373
•
4
Omartificial-Intelligence-Space/Arabic-labse-Matryoshka
Sentence Similarity
•
Updated
•
357
•
2
Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka
Sentence Similarity
•
Updated
•
343
•
1
Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka
Sentence Similarity
•
Updated
•
1.46k
•
10
Omartificial-Intelligence-Space/E5-all-nli-triplet-Matryoshka
Sentence Similarity
•
Updated
•
8
•
1
datasets
20
Omartificial-Intelligence-Space/FineWeb2-MSA
Viewer
•
Updated
•
907M
•
3.13k
•
1
Omartificial-Intelligence-Space/ARA-DPO-co2
Viewer
•
Updated
•
23.4k
•
54
•
1
Omartificial-Intelligence-Space/FineWeb2-Najdi-Arabic
Viewer
•
Updated
•
48.4M
•
168
•
1
Omartificial-Intelligence-Space/FineWeb2-North-Levantine-Arabic
Viewer
•
Updated
•
223k
•
141
•
1
Omartificial-Intelligence-Space/FineWeb2-Moroccan-Arabic
Viewer
•
Updated
•
69.6M
•
106
•
1
Omartificial-Intelligence-Space/FineWeb2-Egyptian-Arabic
Viewer
•
Updated
•
23.9M
•
119
•
1
Omartificial-Intelligence-Space/ILMAAM-Arabic-Culturally-Aligned-MMLU
Viewer
•
Updated
•
12.5k
•
46
Omartificial-Intelligence-Space/ARA-DPO-co
Viewer
•
Updated
•
23.4k
•
36
Omartificial-Intelligence-Space/Arabic_Reasoning_Dataset
Viewer
•
Updated
•
9.21k
•
45
•
2
Omartificial-Intelligence-Space/Arabic-finanical-rag-embedding-dataset
Viewer
•
Updated
•
7k
•
127
•
6