yjj23
/

minivlm

vision-language-model

Model card Files Files and versions Community

VLM Model: Qwen2.5 + SigLIP

This model combines:

Vision encoder: google/siglip-base-patch16-224
Language model: Qwen/Qwen2.5-0.5B-Instruct

Downloads last month: 484

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support