Accueil Explorer Aide
Connexion
radu
/
LLamaRecipes
miroir de https://github.com/facebookresearch/llama-recipes.git
Suivre 1
Voter 0
Fork 0
Fichiers Tickets 0 Wiki
Aborescence: 7edf3d8df0
Branches Tags
LLamaRecipes
/
end-to-end-use-cases
/
coding
/
text2sql
/
fine-tuning
/
grpo
Jeff Tang 7edf3d8df0 llm as a judge running now il y a 1 mois
..
deepspeed_zero3.yaml c88e10fab6 grpo llama 3.2 3b with 3 reward functions il y a 1 mois
grpo-llama323b-text2sql.yaml 7edf3d8df0 llm as a judge running now il y a 1 mois
grpo_text2sql.py 7edf3d8df0 llm as a judge running now il y a 1 mois
requirements.txt 57c05170eb added llm as a judge reward func il y a 1 mois