Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
LEONW24
/
BEPA-7B-S2
like
0
Image-Text-to-Text
Transformers
Safetensors
osworld
English
Chinese
qwen2_5_vl
image-to-text
gui-agent
computer-use
vision-language
reinforcement-learning
osworld
conversational
text-generation-inference
arxiv:
2601.05787
License:
mit
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
BEPA-7B-S2
/
preprocessor_config.json
Commit History
Upload folder using huggingface_hub
270ace6
verified
LEONW24
commited on
5 days ago