TRANSFORMERS & LLMs • 67 / 397
Follow text from characters to tokens, attention, transformers and generation.
Context Window
The context window is the maximum amount of tokenized information a model can consider in one interaction.
Think of it like
Think of Context Window 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 Context Window.
SRE lens
Huge logs can overflow the context window, so retrieval and summarization become operational requirements.
Remember thisThe context window is the maximum amount of tokenized information a model can consider in one interaction.