Why do token limits matter?
PICTURE THIS: A SENTENCE BECOMES TOKENS
The model does not read letters like humans. It reads these pieces, then predicts the next one.
Simple meaning
Models accept a maximum context window measured in tokens, not words.
WHY — Tokens instead of words?
LLMs use tokens (not full words) because it helps them:
on Tokens.
the situation, the default choice, and one exception - that reads as experience.
Each piece maps to a number the network can learn.
Fixed pieces are what transformers expect as input.
STEPS — What happens with tokens?
Before the model can read a sentence, it goes through these steps:
- 1Models accept a maximum
context window measured in tokens, not words.
- 2Long chats and big
docs must be trimmed or summarized.
- 3Cost and latency also
grow with tokens.
- 4Context mix
Attention looks at nearby tokens together.
- 5Next token
The model scores what should come next.
- 6Decode
IDs turn back into readable text.
EXAMPLE — See it in action
Let's see how a real sentence is tokenized (tokens may vary by model):
Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).
Key takeaway
Models accept a maximum context window measured in tokens, not words. Long chats and big docs must be trimmed or summarized.