Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
ceyda
's Collections
Korean Models
Useful Tools
vid-gen
Clips
VQA (Image captioning,QA)
Color
Nice~
Fashion
Cool names
VQA (Image captioning,QA)
updated
Aug 7
Upvote
-
Running
35
📊
FuseCap
Running
on
T4
418
💻
Kosmos 2
Running
6
🚀
Vilt Nlvr
Build error
125
⚡
Qwen VL
Running
on
T4
385
🔥
LLaVA
Runtime error
309
👁
Fuyu Multimodal
Sleeping
158
🚀
MoE LLaVA
Runtime error
168
🐨
IDEFICS2 Playground
Running
on
Zero
82
🐐
CuMo 7b Zero
Running
on
Zero
281
🐬
Chat with DeepSeek VL 7B
What matters when building vision-language models?
Paper
•
2405.02246
•
Published
May 3
•
101
Running
on
Zero
391
🌔
moondream2
a tiny vision language model
Running
97
📊
Idefics3
Upvote
-
Share collection
View history
Collection guide
Browse collections