HomeAI Tutorial

QT-R1

Public

STaR × S1 math pipeline on Qwen2.5-1.5B. LoRA, strict Final: format, ~20–30% acc (OpenR1-Math split).

Creat2025-09-06T14:02:05
Update2025-09-06T15:04:37
1
Stars
0
Stars Increase

Related projects