Category

AI Model Plumbing

These terms cover the basic pipeline from tokenizing text to shaping model behavior.

How to recognize this theme

Words for turning text into features and adapting models.

In a daily board, this category groups terms by their shared role. Look for four cards that describe the same mechanism, risk area, or workflow rather than four words that merely sound similar.

Educational context

These entries are vocabulary notes for learning. They are not project endorsements, token recommendations, exchange rankings, or trading signals.

Tokenizer

A tokenizer splits text into units that an AI model can process.

Embedding

An embedding is a numeric vector that captures meaning or similarity for text, images, or other data.

Attention

Attention is a model mechanism that weighs which input parts matter most for each output step.

Fine-tuning

Fine-tuning updates a pretrained model on a narrower dataset to better fit a specific task.