inblog logo
/

Kim Hojin

About Deep Learning/Machine Learning, Start-up
See AllDeep LearningInsight
Retrieval Augmented Generation at Planet Scale 아티클

Retrieval Augmented Generation at Planet Scale 아티클

논문은 아니고, RAG 관련 글에 대한 번역
Sep 14, 2023Deep Learning
LLaVA 논문 읽으면서 생각들

LLaVA 논문 읽으면서 생각들

[paper] LLaVA : Visual Instruction Tuning
Aug 31, 2023Deep Learning
[논문] Multi-persona LLM

[논문] Multi-persona LLM

[논문] Multi-persona LLM, UNLEASHING COGNITIVE SYNERGY IN LARGE LANGUAGE MODELS: A TASK SOLVING AGENT THROUGH MULTI-PERSONA SELF-COLLABORATION
Aug 19, 2023Deep Learning
World Model in 강화학습
: 미래예측

World Model in 강화학습 : 미래예측

About World model in RL, 강화학습에서의 월드모델
Aug 13, 2023Deep Learning
Speed-up LLM inference : Inference 최적화 방법

Speed-up LLM inference : Inference 최적화 방법

LLM을 Inference할 때 최적화하는 방법에 관하여
Aug 11, 2023Deep Learning
Patterns for Building LLM-based Systems

Patterns for Building LLM-based Systems

Patterns for Building LLM-based Systems이라는 긴 아티클을 읽고 중요하다고 생각되는 부분만 뽑아서 정리한 내용
Aug 05, 2023Deep Learning
[논문리뷰] What is LoRA? : Low-Rank Adaptation of Large Language Models

[논문리뷰] What is LoRA? : Low-Rank Adaptation of Large Language Models

LoRA에 관해서. 읽고 간단하게 작성 논문 : https://arxiv.org/abs/2106.09685
Aug 05, 2023Deep Learning