api: YAML JSON TOON Database
version: 1.0.0
format: yaml
dataset:
  id: 440
  slug: llm-glossary
  title: Large Language Model Glossary
  description: "Key terms and concepts in LLM technology: tokens, context windows, temperature, RAG, fine-tuning, quantization, KV cache, and emergence."
  category: AI & ML Terms
  category_slug: ai-ml-terms
  tags: llm,ai,glossary,nlp
  view_count: 7
  created_at: 1781275786
  updated_at: 1781275786
data:
  terms:
    - term: Token
      definition: A unit of text processed by LLMs, typically a word fragment or punctuation
    - term: Context Window
      definition: Maximum number of tokens an LLM can process in a single inference
    - term: Temperature
      definition: Sampling parameter controlling randomness in generation (0 = deterministic, >1 = creative)
    - term: RAG
      definition: "Retrieval-Augmented Generation: combining LLMs with external knowledge retrieval"
    - term: Fine-tuning
      definition: Adapting a pre-trained model to specific tasks with additional training
    - term: Quantization
      definition: Reducing model precision (e.g., FP16 to INT8) to decrease size and increase speed
    - term: KV Cache
      definition: Key-Value cache storing attention computations for efficient autoregressive generation
    - term: Emergence
      definition: Capabilities that appear only at certain model scales, not predictable from smaller models