Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
tencent
/
Youtu-VL-4B-Instruct
like
144
Follow
Tencent
8.69k
Image-Text-to-Text
Transformers
Safetensors
youtu_vl
text-generation
conversational
custom_code
arxiv:
2601.19798
arxiv:
2512.24618
License:
youtu-vl
Model card
Files
Files and versions
xet
Community
8
Deploy
Use this model
main
Youtu-VL-4B-Instruct
/
assets
5.23 MB
5 contributors
History:
1 commit
Yinsongliu
Upload model with LFS assets
2951b22
12 days ago
architecture.png
Safe
1.07 MB
xet
Upload model with LFS assets
12 days ago
general-multimodal-performance.png
Safe
408 kB
xet
Upload model with LFS assets
12 days ago
logo.png
Safe
614 kB
xet
Upload model with LFS assets
12 days ago
vision-centric-performance.png
Safe
534 kB
xet
Upload model with LFS assets
12 days ago
youtu-vl-logo.png
Safe
95.4 kB
xet
Upload model with LFS assets
12 days ago
youtu-vl-overview.png
Safe
2.51 MB
xet
Upload model with LFS assets
12 days ago