zhuqiang

Vision-OPD-Qwen2.5-VL-7B-Instruct-RandomDrop5-Step30

zhuqiang/Vision-OPD-Qwen2.5-VL-7B-Instruct-RandomDrop5-Step30

Vision-OPD-Qwen2.5-VL-7B-Instruct-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.

Qwen2.5-VL-7B-Instruct trained for 30 Vision-OPD optimizer steps. The student retains a replayable random 5% subset of post-merge visual tokens, while the EMA teacher uses the full visual-token sequence.