<point> vs |box_start|, |box_end|

[tcnguyen]

Hi team,

I saw 2 different prompts using different tokens

click(start_box='<|box_start|>(x1,y1)<|box_end|>')

click(point='<point>x1 y1</point>')

Which one should I use for UITARS 1.5-7B https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B?

Do you recommend UITARS 1.5-7B over UI-TARS-7B like UI-TARS-7B-DPO?

Thank you.

[JjjFangg]

"click(start_box='<|box_start|>(x1,y1)<|box_end|>')" is for UI-TARS-1.5-7B.

Yes, UI-TARS-1.5-7B is better than UI-TARS-7B.

[tcnguyen]

@JjjFangg many thanks!