pytorch-preference-optimization

Name: pytorch-preference-optimization
Author: cxcscmu

SKILLFlusso di lavorocommunity

v0.0.0cxcscmuMITAggiornato 1 mesi faFonte →

PyTorch patterns for implementing preference optimization losses (DPO, SimPO, etc.) for LLM training.

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

77Stelle del repo

1Client

1Formati

1 mesi faUltimo aggiornamento

Skill

Autorecxcscmu

Versione0.0.0

LicenzaMIT

CategoriaFlusso di lavoro

Formatiskill.md

PromptNon pubblicato

Compatibilità

Claude✓ Supportato

Cursor—

Copilot—

ChatGPT—

Gemini—

Descrizione

PyTorch patterns for implementing preference optimization losses (DPO, SimPO, etc.) for LLM training.

Parole chiave

skillclaude