Temperature, Top-k, and Top-p: How Decoding Changes What a GPT Model Says
Experiments with temperature, greedy decoding, top-k, and top-p to understand the trade-offs between predictability, repetition, coherence, and creativity.
Written by
LLM enthusiast
Product manager learning to build AI from the inside out — from LLM architecture to product applications.
Responses
Markdown supported · ⌘↵ to post
No responses yet.