SFT + RS-SFT + GRPO (500 steps, beta=0.04). GSM8K ~46.2%

cbc68ed verified about 1 month ago

7.63 kB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.

NotoriousH2
/

gemma-3-1b-it-Math-GRPO