ai-post-training

Name: ai-post-training
Author: vasilyu1983

SKILLFlusso di lavorocommunity

v0.0.0vasilyu1983MITAggiornato 7 g faFonte →

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 →

75Stelle del repo

1Client

1Formati

7 g faUltimo aggiornamento

Skill

Autorevasilyu1983

Versione0.0.0

LicenzaMIT

CategoriaFlusso di lavoro

Formatiskill.md

PromptNon pubblicato

Compatibilità

Claude✓ Supportato

Cursor—

Copilot—

ChatGPT—

Gemini—

Descrizione

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.

Parole chiave

skillclaude