Skip to content

About This Guide

This comprehensive guide explores the landscape of training and deploying large language models at scale. From fundamental principles to cutting-edge techniques, we dive deep into what makes modern LLMs work.

Walter J.T.V

A passionate technologist and researcher exploring the frontiers of large language models, optimization, and scalable AI systems. This guide represents a curated collection of knowledge, best practices, and insights gathered from research, experimentation, and learning from the incredible AI community.

Connect & Learn More:

  • Scaling Laws — Understanding the predictable relationships between model size, data, and compute
  • Transformers — Modern architectures and attention mechanisms that power LLMs
  • Compression — Making models efficient without sacrificing performance
  • Retrieval & RAG — Grounding language models with external knowledge
  • Training & Optimization — From pre-training to fine-tuning to deployment

The field of large language models is moving at an incredible pace. This guide aims to provide:

  • Structured learning — Organized from fundamentals to advanced topics
  • Practical insights — Real techniques used in production systems
  • Current perspectives — Covering recent advances and best practices
  • Community knowledge — Standing on the shoulders of giants in the ML community

Last Updated: June 2026

For questions, ideas, or feedback, feel free to reach out or explore the documentation!


P.S. — Curious about the previous version? Check out the old portfolio — a nostalgic journey through earlier iterations.