NotoriousH2
/

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

Model card Files Files and versions

gemma-3-1b-it-Math-GRPO / tokenizer.json

Commit History

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

cbc68ed
verified

NotoriousH2 commited on Mar 19