7 terms
A context window is the maximum number of tokens a language model can process at once, covering the prompt, conversation history and its output.
GPT, the generative pre-trained transformer, is a family of decoder-only language models that generate text by predicting the next token in a sequence.
Hallucination in language models is fluent, confident output that is false, unsupported or inconsistent with the given source, such as invented facts.
An LLM (large language model) is a neural network trained on vast text corpora to predict the next token, which lets it generate and analyze language.
A prompt is the input text, instructions and context given to a language model, which the model continues or answers to produce its output.
Temperature is a sampling parameter in language models that scales token probabilities, controlling how predictable or varied generated text becomes.
A token is the basic unit of text a language model reads and writes, usually a word, word piece, character or byte sequence mapped to an…