Back to List
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
PythonAIDC-AI/Ovis

Ovis

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

56.6/100
1.4KForks: 85
View on GitHubHomepage →
Loading report...

Similar Projects

MaxKB

90

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

Python20.8K

MobileAgent

69

Mobile-Agent: The Powerful GUI Agent Family

Python8.5K

VLM-R1

65

Solve Visual Understanding with Reinforced VLMs

Python5.9K

align-anything

54

Align Anything: Training All-modality Model with Feedback

Python4.6K
Back to List