Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
EurekaTian
/
ROMA
like
0
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
File size: 74 Bytes
789f831
1
2
3
4
5
{
"_from_model_config"
:
true
,
"transformers_version"
:
"4.50.0.dev0"
}