Task
Visual Document Retrieval
E
Haon-Chen/e5-omni-7B
Visual Document Retrieval·Haon-Chen· 66.5K· 7
sentence-transformers
mit
Visual Document Retrieval
8.9B params
arxiv:2601.03666base_model:Qwen/Qwen2.5-Omni-7Bbase_model:finetune:Qwen/Qwen2.5-Omni-7Blicense:mitregion:us
e5-omni-7B is a high-performance omni-modal embedding model built on top of Qwen2.5-Omni-7B. It produces a single, unified embedding space for text, images, audio, and video—making cross-modal retrieval accurate and easy to use across a wide range of applications. Paper.
# pull & run locally
pip install mlforge-sdk && mlforge pull Haon-Chen/e5-omni-7B
pip install mlforge-sdk && mlforge pull Haon-Chen/e5-omni-7B
Model details
Provider
Haon-Chen
Framework
sentence-transformers
Parameters
8.9B
Size
17 GB
License
mit
Downloads
66.5K
Likes
7
Paper
arXiv:2601.03666
Updated
2026-04-24
About Haon-Chen/e5-omni-7B
e5-omni-7B is a high-performance omni-modal embedding model built on top of Qwen2.5-Omni-7B. It produces a single, unified embedding space for text, images, audio, and video—making cross-modal retrieval accurate and easy to use across a wide range of applications. Paper.