mlfoundations-cua-dev
/

qwen-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-220

Model card Files Files and versions

No model card

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

·

Inference Providers NEW

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