This post covers everything from planning to study LLM (Large Language Model) to writing actual code.

Accurate Post-Training Quantization for Generative Pre-trained Transformers compresses LLMs by reducing weight bit depth, maintaining processing speed…

Curiosity: How can we make LLM fine-tuning accessible to everyone? What tools enable low-code, GUI-based fine-tuning for practitioners at all levels?

Curiosity: What if LLMs could do more than just answer questions?

We will implement a simple XOR sample example while understanding the overall flow of training with PyTorch.

Curiosity: Where can we find practical examples for building AI applications with open-source tools? What makes the Hugging Face Cookbook valuable?

Curiosity: How do modern systems efficiently manage and process data? What are the key phases that make data pipelines effective?

Category  Schedule  Item  Notes  .

There’s an interesting professor. It’s Professor Hong Jeong-mo (former)!