suby/qmd

Tobi Lütke 189916d6fb Move GRPO training out of default finetune pipeline		3 月之前
..
accelerate_multi_gpu.yaml	bf1b8fc90a lots of training stuff	3 月之前
sft.yaml	cbeeb1f89b Add wall-clock checkpoints and full eval defaults	3 月之前
sft_local.yaml	cbeeb1f89b Add wall-clock checkpoints and full eval defaults	3 月之前