Scaling Law Scaling law is one of the most important findings in LLMs (and neural networks in general) 1. You can make almost all important decisions about training of models with scaling law. For example you can choose model size, number of training steps 2, hyperparameters such as learning rate and batch size 3, learning rate schedules 4, mixture of training datasets 5, etc. So if you are serious about …

In the field of large language models, the most important recipes to cook the model is not opened to publics. Model architecture itself is quite well-known because many state-of-the-art models are now open weights, and in many cases we find it is a boringly simple vanilla transformers. But for datasets and training objectives it is not well known, and many LLM builders deliberately obfuscates the details of these two. And, …

Helpful & Harmless Agent AI 모델의 정렬(Alignment)이라고 이야기할 때 흔히 나오는 Helpfulness와 Harmlessness는 어떤 의미인가? 이는 정의 …

이미지 생성 하면 Style GAN이었던 시절에도 일러스트 생성 등은 오타쿠적 인기가 있는 주제였다. 문제의 Danbooru 데이터셋 같은 경우에도 그 시점에 이미 만들어진 데이터셋이었 …

Kim Seonghyeon

Machine learning enthusiast

Graduate student in HCCLab at Seoul National University

Korea, Republic of