ByteDance/Sa2VA-Qwen2_5-VL-3B download history

ByteDance/Sa2VA-Qwen2_5-VL-3B is a 4.3B-parameter image text to text model by ByteDance. In the last 30 days it was downloaded 1,154 times (623 in the last 7 days), and 2,653 times in total.

It ranks #33,744 on the Hub by monthly downloads and #2,743 among image text to text models.

It has 3 likes.

It is a merge of OpenGVLab/InternVL3-8B.

Open ByteDance/Sa2VA-Qwen2_5-VL-3B on Hugging Face