MAPO: Mixed Advantage Policy Optimization
Paper • 2509.18849 • Published • 27
qwen2_5_vl_7b_geo_12_grporandpro
This model is a fine-tuned version of Qwen/Qwen2.5-VL-7B-Instruct via RL.
This model is based on the paper MAPO: Mixed Advantage Policy Optimization.
Code can be found at: https://github.com/wenkehuang/MAPO
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for WilliamHuang91/qwen2_5_vl_7b_geo_12_grporandpro
Base model
Qwen/Qwen2.5-VL-7B-Instruct