Easy GPT vs BERT Question 23 of 223

Is BERT an encoder or a decoder model?

GenAI / LLM · Speak this in 60–90 seconds · Faridabad & Delhi NCR

The model does not read letters like humans. It reads these pieces, then predicts the next one.

BERT is an encoder-only transformer.

LLMs use tokens (not full words) because it helps them:

GPT vs BERT questions

separate people who only read docs from people who shipped.

Keep it short, concrete,

and tied to GenAI / LLM work.

Stable token IDs

Each piece maps to a number the network can learn.

Fits the model

Fixed pieces are what transformers expect as input.

Before the model can read a sentence, it goes through these steps:

1
Tokenization
BERT is an encoder-only transformer.
2
Every token can attend
to every other token in the input.
3
You typically add a
small head on top for classification or span prediction rather than sampling long text.
4
Context mix
Attention looks at nearby tokens together.
5
Next token
The model scores what should come next.
6
Decode
IDs turn back into readable text.

Let's see how a real sentence is tokenized (tokens may vary by model):

Input text

“Every token can attend to every other token in the input.”

Tokenized output

Everytokencanattendtoevery

Token IDs (example)

2987408337471632900

Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).

BERT is an encoder-only transformer. Every token can attend to every other token in the input.