eqho
/
LLM Lab
model
lab-tiny
the run
01 / 09
Lesson 01
How big is a model?
From one learned number to a trillion of them.
Next: Text becomes tokens
01
How big is a model?
One parameter
A layer is a grid of them
Stack the blocks
The scale ladder
02
Text becomes tokens
03
Tokens become vectors
04
Attention
05
The transformer block
06
Predicting the next token
07
Training
08
From autocomplete to assistant
09
Inference in production
01 / 01
One parameter
A parameter is a single number the model learned. Everything else is just a lot of them.
←
→
space