홈
카테고리
태그
아카이브
정보

홈 태그 DPO

태그

DPO 1

Iterative Reasoning Preference Optimization 2024/06/10

최근 업데이트

Speculative speculative decoding
HydraLoRA, An Asymmetric LoRA Architecture for Efficient Fine-Tuning
GQA, Training Generalized Multi Query Transformer Models from Multi Head Checkpoints
Foundational Autoraters, Taming Large Language Models for Better Automatic Evaluation
Chain-of-verification Reduces Hallucination in Large Language Models

인기 태그

LLM Factuality Peft DecisionMaking DPO Evaluation inference LoRA Optimization speculative decoding

© 2026 Minkyu Kim. 일부 권리 보유

Powered by Jekyll with Chirpy theme

인기 태그

LLM Factuality Peft DecisionMaking DPO Evaluation inference LoRA Optimization speculative decoding

새 버전의 콘텐츠를 사용할 수 있습니다.