참고할만한 내용
- (p.9) RLHF(Reinforcement Learning from Human Feedback)와 DPO(Direct Preference Optimization) 비교
- (p.15~17) RAG의 정의 및 동작방식, LangChain 및 벡터 DB(Vector DB)
https://www.nia.or.kr/site/nia_kor/ex/bbs/View.do?cbIdx=25932&bcIdx=26223&parentSeq=26223
'Programming > NLP' 카테고리의 다른 글
Tokenizer 종류 (0) | 2023.01.25 |
---|---|
[DST] AG-DST (0) | 2022.04.04 |
[Seq2Seq] Sequence to Sequence Learning with Neural Networks (0) | 2022.03.11 |
Ontology, 온톨로지 (0) | 2022.03.10 |
[Transformer #1] Positional Encoding (Position Embedding) (0) | 2021.11.16 |