How to use Qwen2.5-VL for computer use?
#30
by
luffycodes
- opened
Is there any available setup or guide for using Qwen2.5-VL to control a desktop? The model card does mention "Qwen2.5-VL directly plays as a visual agent that can reason and dynamically direct tools, which is capable of computer use and phone use". Curious what frameworks (e.g., Python libraries, browser automation tools) are used to enable this kind of desktop control with Qwen2.5-VL.
Bro smolagents have done it, search for computer use space in hugging face , you can get it there .