Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
legolasyiu
/
Qwen2.5-VL-7B-GUI-OSWorld-GDPval
like
0
Image-Text-to-Text
mlfoundations/Click-100k
showlab/ShowUI-desktop
English
gui-agent
computer-use
osworld
gdpval
gui-grounding
qwen2.5-vl
arxiv:
2505.13227
arxiv:
2510.04374
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Qwen2.5-VL-7B-GUI-OSWorld-GDPval
24.8 kB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
legolasyiu
Add T4-optimized training script (16GB VRAM: fp16, 720p, LoRA r=8)
b8318f1
verified
about 1 month ago
.gitattributes
Safe
1.52 kB
initial commit
about 1 month ago
README.md
4.7 kB
Add comprehensive README with training recipe and usage instructions
about 1 month ago
train_gui_grounding.py
9.09 kB
Add training script for GUI grounding (OSWorld + GDPval)
about 1 month ago
train_gui_grounding_t4.py
9.45 kB
Add T4-optimized training script (16GB VRAM: fp16, 720p, LoRA r=8)
about 1 month ago
