ai-post-training

Name: ai-post-training
Author: vasilyu1983

SKILLWorkflowcommunauté

v0.0.0vasilyu1983MITMis à jour il y a 7 jSource →

Post-training and alignment: reward modeling, RLHF/PPO, DPO/DAAs, GRPO, RLVR, RLAIF, over-optimization. Use when adapting an SFT model with preference or verifiable-reward signals.

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →

75Étoiles du dépôt

1Clients

1Formats

il y a 7 jDernière mise à jour

Skill

Auteurvasilyu1983

Version0.0.0

LicenceMIT

CatégorieWorkflow

Formatsskill.md

PromptNon publié

Compatibilité

Claude✓ Pris en charge

Cursor—

Copilot—

ChatGPT—

Gemini—

À propos

Post-training and alignment: reward modeling, RLHF/PPO, DPO/DAAs, GRPO, RLVR, RLAIF, over-optimization. Use when adapting an SFT model with preference or verifiable-reward signals.

Mots-clés

skillclaude