Tobi Lutke 8572c2fd94 Deploy fine-tuned GRPO model as default for query expansion 3 mēneši atpakaļ
..
train 32706a720f Refactor finetune folder: train/rl scripts with YAML configs 4 mēneši atpakaļ
train_v2 8572c2fd94 Deploy fine-tuned GRPO model as default for query expansion 3 mēneši atpakaļ
qmd_expansion_v2.jsonl 8572c2fd94 Deploy fine-tuned GRPO model as default for query expansion 3 mēneši atpakaļ