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