확률 기반 Next Token Prediction을 통한 LLM 아키텍처 구현
How AI Actually Works
How AI Actually Works
Judgment 데이터 축적과 Fintech 결합을 통한 AI 시대의 시스템 해자 구축
Building an Artist Attribution Model with PyTorch and ResNet-50
Transfer Learning: Stand on a Pretrained Model
2.8천만 건의 API 교환을 통한 Claude 모델 역량 Distillation 시도 포착
AI Development in 2026: A Practical Guide for Founders and CTOs
Building a Financial Named Entity Recognition Pipeline for Enterprise AI
Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModel
If a 270M Model Already Worked, Why Did I Fine-Tune a 7B One?
How AI Will Shape the Technology Industry in 2027
LLMs เข้าใจและเขียนโค้ดได้อย่างไร?
Fine-Tuning AI Models for Specialized Tasks
Foundation vs. Instruct vs. Chat Models: One Question, Three Answers
The Complete Open-Source LLM Developer Curriculum — Now Free Forever
I built a 3B lease risk scanner that runs without an external LLM API
I was fine-tuning a language model on Arabic. The loss was perfect. It spoke Chinese.
A Chinese 8B model beat the Western 8B models at Japanese RAG. I still wouldn't put it in the default deployment — and that distinction is the point.
NeuroBait: I fine-tuned a model to spark dopamine for ADHD brain
RAG Retrieval Quality: Are Large Models Really Necessary?
Fine-tuned 7B LLM as a broke student. And Can't even use it 😭.