zhuqiang

Vision-OPD-Qwen3.5-4B-RandomDrop5-Step30

zhuqiang/Vision-OPD-Qwen3.5-4B-RandomDrop5-Step30

Vision-OPD-Qwen3.5-4B-RandomDrop5-Step30 is a image-text-to-text model from zhuqiang. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers.

Qwen3.5-4B trained with Vision-OPD using random 5% visual-token retention for the student and full visual tokens for the teacher. This is the 30-step proof-of-concept checkpoint.