Inicio Explorar Axuda
Rexistro Iniciar sesión
suby
/
qmd
1
0
Fork 0
Ficheiros Incidencias 0 Pull Requests 0 Wiki
Árbore: 2ae1baba2f
Ramas Etiquetas

Commit History

Autor SHA1 Mensaxe Data
  Tobi Lütke 189916d6fb Move GRPO training out of default finetune pipeline hai 3 meses
  Tobi Lutke 599935754b finetune: remove orphaned files and abandoned experiments hai 3 meses
  Tobi Lütke 102ff861d3 fix: use Qwen3 recommended sampling params to prevent repetition loops hai 3 meses
  Tobi Lütke bf1b8fc90a lots of training stuff hai 3 meses