Inference
Domain: LLM Concepts
🎯 Motivation
Using a trained model to generate output is called inference. This is different from training, which is the learning phase.
📋 Concrete Example
When you type a question to ChatGPT and it responds - that’s inference. The model uses its learned parameters to predict the answer. No learning happens during inference.
🔗 Analogy
Taking a final exam - you studied for months (training), but during the exam (inference) you just use what you learned. No new learning happens during the exam.