VerlTool
/

pixel_reasoner-7b-grpo-n8-b128-t1.0-lr1e-6-complex-reward-new_global_step_50

Model card Files Files and versions

No model card

Downloads last month: 203

Safetensors

Model size

8.29B params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support