Baatu Glossaire IA

Luy DPO (Optimisation préférence directe)?

Maanaam

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

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.
Ginaaw tàggat yaram
Jéego yi ñuy jëfandikoo ngir tàggat yaram ginaaw bi ñu njëkkee tàggat, lu ci melni ajustement instruction, gëna xéewale tànneef yi, ak ajustement kaaraange.
Wéyal jàng
Xeetu tàggat yaram buy may model bi mu wéy di jàng ci done yu bees te du fàtte xam-xam bimu amoon bu njëkk.
Akordement bu baax
Wéyal tàggat ci done yuñ jagleel benn domen ngir méngale xeetu tàggat buñ njëkka tàggat ak benn liggéey buñ jagleel.
Wàccig degrade
Pexem optimisation buy yeesal paramet yi ci wàll wi wàññi njuumte.
Tegtal yi tuning
Fine-tuning ab model ci ñaari tegtal-tontu ngir gëna mëna topp liggéey bi.

Nekk leen ci sunuy tegtal yu amul fayda

AI Inference OptimizationBidirectional Recurrent NetworksSecond-Order Optimization and Newton MethodsOdds Ratio Preference Optimization

Xoolal itam

Tree of ThoughtsQLoRAReActFlash AttentionAgentic LoopMulti-Head AttentionMCP (Model Context Protocol)Positional Encoding
Xoolal Glossaire IA bi yéppSaytu bépp tegtal IA bu amul fayda