TRANSFORMERS & LLMs • 69 / 397
Follow text from characters to tokens, attention, transformers and generation.
Output Tokens
Output tokens are the tokens generated by the model.
Think of it like
Think of Output Tokens as part of a very fast reader that repeatedly decides what information matters and what should come next.
Real life
Autocomplete, translation and chat assistants depend on concepts such as Output Tokens.
SRE lens
Verbose responses consume more output tokens and generation time.
Remember thisOutput tokens are the tokens generated by the model.