What is Reward Model? Definition | AI Understanding

Maanaam

Benn xeetu poñ buy joxe poñ ci siñaal yiñ taamu, ñu koy faral di jëfandikoo ci pipeline RLHF yi.

Term yu ci méngoo

Jàng mu am doole ci feedback nit (RLHF)

Xeetu tàggat yaram buy jëfandikoo siñaal yi nit ñi taamu ngir jëmmal xeetu doxalin.

Jàng buy dooleel

Tàggat ci siñaal neexal, di barab bi ab ndawu liggéey di jàngee jëf yuy yokk ndàmpaay ci diir bu yàgg.

Etiketu royuwaay yiñ mëna wóolu ngir tàggat wala jàngat modelu génne yi.

DPO (Optimisation préférence directe)

Xeetu tàggat yaram buy gëna suqali xeetu model yi ci ñaari tànneef te soxlawul xeetu neexal bu wuute.

Diggu tàggat yaram

Diggante tàggat yaram diggante tàggat yaram ak ginaaw tàggat yaram, ñu koy faral di jëfandikoo ngir defar kàttan wala domen.

Sistem losisel bu mëna seetlu, xalaat, ak jël ay matuwaay ngir mëna yegg ci mébet, di faral di jëfandikoo jumtukaay ak mémoire.

Nekk leen ci sunuy tegtal yu amul fayda

AI Models Explained Model Collapse Model Lifecycle Model Context Protocol

Xoolal itam

Retrieval Robustness Safety Filter Scaling Law Red Teaming Semantic Search Recommendation System Self-Supervised Learning

Xoolal Glossaire IA bi yépp Saytu bépp tegtal IA bu amul fayda