RogerLos
/

verl-grpo-8k-Qwen2.5-0.5B-Instruct-global_step_80

Model card Files Files and versions

No model card

Downloads last month: 14

Safetensors

Model size

0.6B 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-8k-Qwen2.5-0.5B-Instruct-global_step_80

Long_CoT_Degradation_RL

119 items • Updated 9 days ago