Commit Verlauf

Autor SHA1 Nachricht Datum
  Tobi Lütke bf1b8fc90a lots of training stuff vor 3 Monaten
  Tobi Lutke 7de18ee066 Merge main into finetune vor 3 Monaten
  Tobi Lutke 785620467a refactor: reorder output format to put hyde line first vor 3 Monaten
  Tobi Lütke 46ff098361 Change only: format to only:lex (no space after colon) vor 3 Monaten
  Tobias Lütke eb1b77c8cb Deploy fine-tuned GRPO model as default query expansion (#67) vor 3 Monaten
  Tobi Lutke 32706a720f Refactor finetune folder: train/rl scripts with YAML configs vor 4 Monaten