resistz
/

RLCR-Calibrated-Qwen3-4B-DAPO-Math14k-3Epoch-330Step

Model card Files Files and versions

Qwen3-4B (NoThink) is trained on DAPO-Math14k using RLCR with 3 epochs and 330 steps.

Downloads last month: 14

Safetensors

Model size

4B params

Tensor type

BF16

·

Inference Providers NEW

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