Accueil Explorer Aide
S'inscrire Connexion
suby
/
qmd
1
0
Fork 0
Fichiers Tickets 0 Pull Requests 0 Wiki
Aborescence: 9b3a209a97
Branches Tags

Historique des commits

Auteur SHA1 Message Date
  Tobi Lutke 9b3a209a97 Fix GRPO training: apply chat template to prompts il y a 4 mois
  Tobi Lutke 891f3262cf Fix GRPO reward function to handle think blocks and end tokens il y a 4 mois
  Tobi Lutke 8a1c4cdab0 Add 1.7B and 4B GRPO training and GGUF conversion scripts il y a 4 mois