Model (machine learning model)
A learned function with parameters fit on data: the artifact produced by training and used at inference time.
In machine learning, a model is the parameterized system you optimize during training and run during inference: weights, architecture, and sometimes adapters or heads. A large language model (LLM) is one prominent kind; smaller classifiers, embedding models, and reward models used in RLHF are others.
Lifecycle: pretrain a base model, optionally fine-tune for tasks or tone, deploy behind chatbots or RAG pipelines. “Model” can mean the math, the checkpoint file, or the hosted API endpoint depending on context.