Topic

Transformer Architecture

7 posts on transformer architecture — part of glossary on the n4n AI blog.

What is the attention mechanism, in plain English?

A clear technical explanation of the attention mechanism in transformers, covering how it works, why it matters for LLMs, and common misconceptions engineers should avoid.

July 28, 20265 min read

GlossaryDefinition

What is a transformer? The architecture behind every LLM

A precise technical explanation of the transformer architecture — attention mechanisms, encoder-decoder structure, and why it replaced recurrence for LLMs.

July 28, 20266 min read

GlossaryGuide

Transformer architecture explained, layer by layer

A layer-by-layer breakdown of transformer architecture with code, tradeoffs, and common pitfalls for engineers building LLM systems.

July 28, 20265 min read

GlossaryComparison

How GPT's transformer architecture differs from BERT's

Technical comparison of GPT's decoder-only and BERT's encoder-only transformer architectures, covering training objectives, inference patterns, fine-tuning strategies, and when to use each.

July 28, 20265 min read

GlossaryAnalysis

From Attention Is All You Need to GPT-4: a brief history

Trace the transformer architecture from its 2017 debut through GPT-4, examining key innovations, scaling laws, and what each breakthrough actually changed for practitioners.

July 28, 20266 min read

GlossaryComparison

Encoder vs decoder transformers: what's the difference?

A practitioner's comparison of encoder vs decoder transformers across architecture, training objectives, inference characteristics, and when to use each for real systems.

July 28, 20266 min read

GlossaryComparison

Decoder-only vs encoder-decoder models explained

A practitioner's comparison of decoder-only and encoder-decoder transformer architectures across capabilities, cost, latency, ergonomics, and ecosystem — with a clear verdict by use case.

July 28, 20266 min read