ByteDance-Seed
/

UI-TARS-1.5-7B

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions Community

Resources

View closed (2)

How to fine tune uitars like fine-tuning qwen-vl-2.5?

#14 opened 23 days ago by

Early access to the top-performing UI-TARS-1.5 model

#12 opened about 1 month ago by

قلللل

#11 opened about 1 month ago by

Why is a 7B model with a file size of over 30GB?

#10 opened 2 months ago by

If I only want to use the UI element positioning recognition function, is there any way?

#9 opened 2 months ago by

Demo 👀

#8 opened 3 months ago by

Ollama deployment

#7 opened 3 months ago by

Dataset request

#5 opened 3 months ago by

Good-quality quants

#4 opened 3 months ago by

Error bbox locating

#3 opened 3 months ago by

Apply for 70B/32B version

#2 opened 3 months ago by

how do I load this model in 4bit quant?

#1 opened 3 months ago by