Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Enxin
/
VideoNSA
like
2
Video-Text-to-Text
Safetensors
English
qwen2_5_vl
video-understanding
sparse-attention
vision-language
qwen2.5-vl
multimodal
arxiv:
2510.02295
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
main
VideoNSA
/
merges.txt
Enxin
Upload folder using huggingface_hub
80a80d5
verified
28 days ago
raw
Copy download link
history
contribute
delete
Safe
1.67 MB
File too large to display, you can
check the raw version
instead.