Transformer
The neural-network architecture behind today’s language models, introduced in 2017. Its attention mechanism lets every token weigh every other token in the context.
01In short
The neural-network architecture behind today’s language models, introduced in 2017. Its attention mechanism lets every token weigh every other token in the context.
02Video
slot · videoTransformer in 90 secondsadd: GUIDES['transformer'].video
03Guide
slot · guide
A step-by-step guide for “Transformer” goes here. Suggested outline:
- What it is — in one paragraph
- Why it matters in production
- How to do it — 3 to 7 steps
- Pitfalls we see in the field
04Checklist
slot · checklist
Four to eight things a team can tick before go-live.
05FAQ
slot · FAQ
The three questions clients actually ask about “Transformer”.
06Related terms
BasicsLLMA neural network trained on huge amounts of text to predict the next token. That simple objective produces models that write, summarise, translate and reason in language.BasicsDeep learningMachine learning with neural networks of many layers. It is behind speech recognition, image recognition and every modern language model.
Talk to us