# Cross-modal understanding

Qwen2.5-Omni-7B-GGUF is the GGUF format version of the Qwen2.5-Omni-7B model, supporting multimodal inputs including text, audio, and images.

VITA-1.5 is a multimodal interaction model designed to achieve GPT-4o level real-time vision and voice interaction capabilities.

CSUMLM is a cutting-edge artificial intelligence system that integrates the advantages of multimodal AI engines and large language models, featuring multimodal processing, complex language understanding, and real-time learning capabilities.

Pre-trained visual encoder-text decoder model supporting Korean and English