merve PRO

merve's activity

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

liked a dataset about 2 hours ago

Open-Bee/Honey-Data-15M

Updated 8 days ago • 61 • 33

liked 3 models about 2 hours ago

Open-Bee/Bee-8B-RL

Image-Text-to-Text • 9B • Updated 3 days ago • 3.27k • 56

nvidia/omnivinci

Updated 3 days ago • 95 • 61

krea/krea-realtime-video

Text-to-Video • Updated 3 days ago • 725 • 142

upvoted a changelog about 2 hours ago

view changelog

Changelog

Cleaner Collection URLs

about 7 hours ago

• 18

liked a model about 3 hours ago

datalab-to/chandra

Image-to-Text • 9B • Updated 2 days ago • 1.9k • 34

liked a model about 23 hours ago

deepseek-ai/DeepSeek-OCR

Image-Text-to-Text • 3B • Updated about 11 hours ago • 302k • 1.56k

upvoted an article 1 day ago

view article

Article

Supercharge your OCR Pipelines with Open Models

3 days ago

• 108

updated a dataset 1 day ago

merve/vlm_test_images

Viewer • Updated 1 day ago • 25 • 459 • 2

updated a dataset 2 days ago

huggingface/documentation-images

Viewer • Updated about 4 hours ago • 55 • 1.98M • 88

upvoted an article 2 days ago

view article

Article

SOTA OCR on-device with Core ML and dots.ocr

22 days ago

• 47

updated a model 2 days ago

merve/SmolVLM2-2.2B-DocVQA

Image-Text-to-Text • 2B • Updated 2 days ago • 113 • 3

liked a model 2 days ago

strangervisionhf/paddle

1.0B • Updated 6 days ago • 77 • 1

published an article 3 days ago

view article

Article

Supercharge your OCR Pipelines with Open Models

3 days ago

• 108

liked a Space 3 days ago

Running on Zero

MCP

6

6

VLM Parsing

📄

for document parsing task

liked a model 3 days ago

allenai/olmOCR-7B-0825

Image-to-Text • 8B • Updated 1 day ago • 7.53k • 54

posted an update 3 days ago

view post

Post

4116

deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages

See translation

• 

• 
• 
• 2 replies

·

🚀

8

8

👍

2

2

+

Reply

New activity in PaddlePaddle/PaddleOCR-VL 6 days ago

Enable download counts

2

#9 opened 6 days ago by

merve

liked a Space 6 days ago

Running

115

115

PaddleOCR-VL Online Demo

📈

Parse and recognize content in images

New activity in nanonets/Nanonets-OCR2-3B 7 days ago

License

➕ 6

#7 opened 7 days ago by

merve