Philip's Learning Blog

AI Web Development Security Linux Cloud & DevOps Programming Practical Scripting Data Science and ML Raspberry Pi Retro Computing Databases Projects Networking Japan Hungary France YouTube

Data Science and ML

Data Science Fundamentals Machine Learning Fundamentals Neural Networks & Deep Learning NLP LLMs What an LLM Actually Is (Not Another Prompting Course) Subword Tokenization: Byte-Pair Encoding Embeddings & Positional Encoding at Scale Self-Attention, Formalized: Query, Key & Value Multi-Head Attention & the Full Transformer Block Decoder-Only vs. Encoder-Decoder: GPT vs. BERT vs. T5 Pretraining at Scale: Self-Supervised Learning Scaling Laws Fine-Tuning & RLHF: From GPT-3 to ChatGPT Context Windows, Quadratic Attention & Honest Limitations Tracing a Prompt Through a Real LLM, End to End Beginner Projects Intermediate Projects

Home › Data Science and ML › LLMs

LLMs

1. What an LLM Actually Is (Not Another Prompting Course)
2. Subword Tokenization: Byte-Pair Encoding
3. Embeddings & Positional Encoding at Scale
4. Self-Attention, Formalized: Query, Key & Value
5. Multi-Head Attention & the Full Transformer Block
6. Decoder-Only vs. Encoder-Decoder: GPT vs. BERT vs. T5
7. Pretraining at Scale: Self-Supervised Learning
8. Scaling Laws
9. Fine-Tuning & RLHF: From GPT-3 to ChatGPT
10. Context Windows, Quadratic Attention & Honest Limitations
11. Tracing a Prompt Through a Real LLM, End to End