Tobi Lütke 189916d6fb Move GRPO training out of default finetune pipeline há 4 meses atrás
..
gepa 1d7d167b29 finetune: strict Pydantic schema, one canonical data format há 4 meses atrás
grpo 189916d6fb Move GRPO training out of default finetune pipeline há 4 meses atrás
lfm2 1d7d167b29 finetune: strict Pydantic schema, one canonical data format há 4 meses atrás