Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
weathon
/
Qwen2.5-VL-3B-Instruct-Thinking-Vision-Reward
like
0
Image-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
Generated from Trainer
trl
grpo
conversational
text-generation-inference
arxiv:
2402.03300
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Qwen2.5-VL-3B-Instruct-Thinking-Vision-Reward
/
preprocessor_config.json
Commit History
Training in progress, step 100
09ba0ee
verified
weathon
commited on
Oct 4, 2025
Training in progress, step 100
ca7636d
verified
weathon
commited on
Oct 4, 2025
Training in progress, step 10
e3e6e76
verified
weathon
commited on
Sep 18, 2025