Commit History

Author SHA1 Message Date
  Tobi Lütke 189916d6fb Move GRPO training out of default finetune pipeline 3 months ago
  Tobi Lutke 599935754b finetune: remove orphaned files and abandoned experiments 3 months ago
  Tobi Lütke 102ff861d3 fix: use Qwen3 recommended sampling params to prevent repetition loops 3 months ago
  Tobi Lütke bf1b8fc90a lots of training stuff 3 months ago