Context Window
Quick Definition
Maximum tokens a language model can process at once
Full Definition
The maximum number of tokens a language model can process in a single input.
Examples
long document processing, conversation history, retrieval context
Related Terms
large-language-model
attention
More Large Language Models Terms
Instruction Tuning
Fine-tuning on instruction-response pairs for better following
Tokenization
Breaking text into tokens for language model processing
Adapter Layer
Small trainable modules in frozen transformer layers
Quantization LLM
Reducing LLM weight precision for efficient inference
Pre-training
Initial training learning general language patterns from text
Fine-Tuning
Further training pre-trained models on specific domain data