RogerLos
/

verl-grpo-128k-Qwen2.5-7B-Instruct-global_step_70

Model card Files Files and versions

No model card

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

F32

·

Inference Providers NEW

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

Collection including RogerLos/verl-grpo-128k-Qwen2.5-7B-Instruct-global_step_70

Long_CoT_Degradation_RL

119 items • Updated 8 days ago