hugpadhugpad

ATH-MaaS / Ovis-Omni-Embedding-3B

Embeddings58364Updated Oct 10, 2026
Hugging Face

Downloads

583

Likes

64

Last updated

Oct 10, 2026

License

apache-2.0

Ovis-Omni-Embedding-3B is a 3B-parameter universal embedding model for text, images, visual documents, video, audio, and interleaved multimodal inputs. It maps every supported input type into one coherent representation space, enabling any-to-any retrieval with a single encoder.

Tasks & library

  • feature extraction
  • transformers

Tags

  • transformers
  • qwen2_5_omni
  • text-to-audio
  • multimodal
  • text
  • image

Technical specifications

ParametersNot available
Librarytransformers
LanguagesNot available
Licenseapache-2.0