Dogan Ozcan

doganozcan's activity

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

liked a model 1 day ago

google/gemma-3-27b-it

Image-Text-to-Text • Updated 2 days ago • 85.2k • 531

upvoted a collection 10 days ago

Türkçe VLMler

Collection

11 items • Updated 10 days ago • 7

upvoted an article 10 days ago

view article

Article

FastRTC: The Real-Time Communication Library for Python

18 days ago

• 143

liked a Space 17 days ago

Running on Zero

196

196

OCR

🍍

perfect ocr vlm

liked a Space about 1 month ago

Running on Zero

3.01k

3.01k

IC Light V2

📈

Execute custom code from environment variable

upvoted an article about 2 months ago

view article

Article

We now support VLMs in smolagents!

Jan 24

• 92

upvoted 2 collections about 2 months ago

ProLIP

Collection

Official ProLIP weights • 7 items • Updated 2 days ago • 6

DeepSeek-R1

Collection

8 items • Updated Jan 21 • 575

liked a Space about 2 months ago

Running on Zero

171

171

MatchAnything

🏢

Find similar images from a collection

liked a Space 3 months ago

Running on Zero

1.75k

1.75k

Stable Video Diffusion 1.1

📺

Generate a short video from an image

liked 3 models 3 months ago

Qwen/QVQ-72B-Preview

Image-Text-to-Text • Updated Jan 12 • 173k • • 563

tencent/HunyuanVideo

Text-to-Video • Updated 8 days ago • 5.52k • • 1.75k

Qwen/Qwen2-VL-72B

Image-Text-to-Text • Updated Dec 6, 2024 • 3.19k • 75

upvoted a collection 3 months ago

InternVL2.5

Collection

Better than InternVL 2.0 • 19 items • Updated 11 days ago • 88

liked a model 3 months ago

Qwen/QwQ-32B-Preview

Text Generation • Updated Jan 12 • 241k • • 1.72k

upvoted a collection 4 months ago

AIMv2

Collection

A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. • 19 items • Updated Nov 22, 2024 • 74

liked a model 4 months ago

OpenGVLab/Mono-InternVL-2B

Image-Text-to-Text • Updated 2 days ago • 7.36k • 32

upvoted a collection 4 months ago

LLM2CLIP

Collection

LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. • 11 items • Updated 2 days ago • 55

liked a Space 4 months ago

Running on Zero

78

78

LongVU

🌖

Generate responses to video or image inputs

upvoted an article 5 months ago

view article

Article

Visually Multilingual: Introducing mcdse-2b

By •

Oct 27, 2024

• 38