Tobi Lütke 189916d6fb Move GRPO training out of default finetune pipeline hai 3 meses
..
gepa 1d7d167b29 finetune: strict Pydantic schema, one canonical data format hai 3 meses
grpo 189916d6fb Move GRPO training out of default finetune pipeline hai 3 meses
lfm2 1d7d167b29 finetune: strict Pydantic schema, one canonical data format hai 3 meses