Elsayed Mohamed

sayedM's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked 2 Spaces 8 days ago

Running

Featured

27

Gemma 4 - Vision Token Budget

🖼

27

Resize images for visual token budgets while keeping aspect ratio

Running on L40S

30

Cosmos3 Action Viewer

🤖

30

Explore interactive visualizations with Viser

liked a model 9 days ago

sensenova/SenseNova-Vision-7B-MoT

Any-to-Any • Updated 13 days ago • 920 • 90

liked a model 11 days ago

SupraLabs/Supra-50M-Base

Text Generation • 51.8M • Updated May 27 • 984 • 34

liked a Space 16 days ago

Running on CPU Upgrade

Agents

21

Cohere Transcribe Arabic ASR

🎙

21

Transcribe Arabic or English audio into text

liked a model 16 days ago

CohereLabs/cohere-transcribe-arabic-07-2026

Automatic Speech Recognition • 2B • Updated 10 days ago • 31.7k • 132

liked a model 19 days ago

google/tabfm-1.0.0-pytorch

Tabular Classification • Updated 19 days ago • 34.4k • 402

liked a Space 25 days ago

Running on Zero

Agents

Featured

280

Unlimited OCR

🏆

280

Extract text from images and PDFs instantly

liked a model 26 days ago

nvidia/GLM-5.2-NVFP4

Text Generation • 381B • Updated 27 days ago • 1.56M • 277

upvoted a collection about 1 month ago

Arabic Voice Collection - مكتبة الصوت العربي

Collection

This collection will have all the Arabic voice datasets in different dialects - ~1750 hours • 13 items • Updated 6 days ago • 10

liked a dataset about 1 month ago

CodeDevX/Vibe-Coding-Instruct

Viewer • Updated Jun 18 • 1.1M • 1.71k • 188

liked a model about 1 month ago

PaddlePaddle/PP-OCRv6_medium_det_safetensors

Image-to-Text • 22M • Updated Jun 12 • 2.84k • 114

liked a model about 2 months ago

google/gemma-4-12B-it

Any-to-Any • 12B • Updated 3 days ago • 3M • 1.34k

liked a dataset about 2 months ago

oddadmix/arabic-audio-collection-mostafa-mahmoud

Viewer • Updated Jun 18 • 33.6k • 544 • 13

liked a model about 2 months ago

tiiuae/Falcon-Perception

Mask Generation • 0.6B • Updated May 11 • 4.85k • 129

upvoted an article about 2 months ago

view article

Article

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

• 

nvidia

•

Jun 1

• 87

liked a model about 2 months ago

datalab-to/surya-ocr-2

Image-Text-to-Text • 0.7B • Updated May 27 • 694k • 79

liked a Space about 2 months ago

Running on Zero

Agents

419

LocateAnything

💬

419

Detect and label objects in images and videos

liked a model about 2 months ago

nvidia/LocateAnything-3B

Image-Text-to-Text • 4B • Updated Jun 12 • 1.61M • 2.77k

liked a dataset 2 months ago

zhifeixie/Voices-in-the-Wild-2M

Updated May 29 • 3.78k • 45