Journey of Curiosity Arshad Kazi
← Blogs

Complete Since April 27, 2026 7 days · 18 min

Overview of Modern Nets

I'd used transformers but couldn't explain the architecture end to end without stumbling. A revision pass, piece by piece: tokenizers, positional encoding, attention, BERT vs GPT, and the GPT family.

Coverage

7 of 7 strands covered

Syllabus

24 of 28 topics written up

  1. 1 Tokenization 1/1
  2. 2 Embeddings and position 2/3
  3. 3 Attention 3/3
  4. 4 Architecture 4/5
  5. 5 Training objectives 2/2
  6. 6 Model families 5/7
  7. 7 Tooling 7/7

Index

Everything written, tangents included, A to Z