Skip to content

[LLM] Rewrite GSM8K reward function to follow standard GRPO conventions#3542

Open
vmoens wants to merge 1 commit intogh/vmoens/234/basefrom
gh/vmoens/234/head
Open

[LLM] Rewrite GSM8K reward function to follow standard GRPO conventions#3542
vmoens wants to merge 1 commit intogh/vmoens/234/basefrom
gh/vmoens/234/head

Commits

Commits on Mar 5, 2026