تاریخچه Commit ها

نویسنده SHA1 پیام تاریخ
  Tobi Lütke 189916d6fb Move GRPO training out of default finetune pipeline 3 ماه پیش
  Tobi Lutke 599935754b finetune: remove orphaned files and abandoned experiments 3 ماه پیش
  Tobi Lütke 102ff861d3 fix: use Qwen3 recommended sampling params to prevent repetition loops 3 ماه پیش
  Tobi Lütke bf1b8fc90a lots of training stuff 3 ماه پیش