Tobi Lütke 8cc7d8c138 Add sampled /only: variants (399) for training balance 3 달 전
..
grpo.yaml eb1b77c8cb Deploy fine-tuned GRPO model as default query expansion (#67) 3 달 전
sft.yaml eb1b77c8cb Deploy fine-tuned GRPO model as default query expansion (#67) 3 달 전
sft_v4.yaml 8cc7d8c138 Add sampled /only: variants (399) for training balance 3 달 전