Arabic Clip
non-profit
AI & ML interests
None defined yet.
Organization Card
About org cards
Arabic CLIP: Bridging the gap to text-to-image understanding in Arabic
🔥 Project's purpose
This work creating the base for different directions in the connection between two fields, Natural Langauge Processing (NLP) and Computer Vision (CV), such as text-to-image generation, image retervial system, video understanding and medical imaging.
🔎 What you can find in this organization?
You can find a list of the datastes, models and demos.
📃 Citation
Coming soon.
Collections
1
spaces
1
models
31
Arabic-Clip/bert-base-arabertv2-ViT-B-16-SigLIP-512-epoch-155-trained-2M-fp32
Feature Extraction
•
Updated
•
1
Arabic-Clip/bert-base-arabertv2-ViT-B-16-SigLIP-512-epoch-155-trained-2M-mscoco-200
Feature Extraction
•
Updated
•
1
Arabic-Clip/arabertv2-Vit-B-16-plus-epoch-36-trained-1M-corrupted
Feature Extraction
•
Updated
•
1
Arabic-Clip/arbertv2-Vit-B-16-plus-epoch-54-2M_3M_5M
Feature Extraction
•
Updated
•
2
Arabic-Clip/ARBERTv2-Vit-B-16-plus-240-epoch-103
Feature Extraction
•
Updated
•
4
Arabic-Clip/arbertv2-Vit-B-16-plus-epoch-200-msoco
Feature Extraction
•
Updated
•
2
Arabic-Clip/arabertv2-Vit-B-16-plus-epoch-60-trained-mscoco-training-fp32
Feature Extraction
•
Updated
•
1
Arabic-Clip/arabertv2-Vit-B-16-plus-epoch-41-trained-1M-corrupted
Feature Extraction
•
Updated
•
1
Arabic-Clip/bert-base-arabertv2-ViT-B-16-SigLIP-512-epoch-55-trained-2M
Feature Extraction
•
Updated
•
1
Arabic-Clip/bert-base-arabertv2-ViT-B-16-SigLIP-512-epoch-155-trained-2M
Feature Extraction
•
Updated
•
3
datasets
4
Arabic-Clip/Arabic_dataset_13M_translated_cleaned_v2_jsonl_format_ViT-B-16-SigLIP-512_validation
Viewer
•
Updated
•
5k
Arabic-Clip/mscoco_captions_ViT-B-16-SigLIP-512
Viewer
•
Updated
•
123k
Arabic-Clip/arabic_dataset_translated_v2_ViT-B-16-SigLIP-512
Viewer
•
Updated
•
780k
Arabic-Clip/Arabic_dataset_13M_translated_cleaned_v2_jsonl_format_ViT-B-16-plus-240
Viewer
•
Updated
•
927k
•
1