Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
EurekaTian
/
ROMA
like
1
Video-Text-to-Text
Transformers
Safetensors
qwen2_5_omni
multimodal
video-understanding
audio-understanding
streaming
real-time
omni-modal
arxiv:
2601.10323
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
ROMA
/
vocab.json
EurekaTian
Upload folder using huggingface_hub
789f831
verified
about 1 month ago
raw
Copy download link
history
contribute
delete
Safe
2.78 MB
File too large to display, you can
check the raw version
instead.