Developed by Sijun Tan (UC Berkeley) & team, this model smashes benchmarks w/ a 43.1% Pass@1 accuracy on AIME2024, a +14.3% over its base model! DeepScaleR, a 1.5B parameter model fine tuned from Deepseek-R1-Distilled-Qwen-1.5B. Watch for more: https://
bit.ly/4kmLiRf

→ View original post on X — @sambanovaai,