models

Definition

The plural of model: systems whose parameters encode regularities extracted from data. In titles it usually names a family — vision-language models, diffusion models — rather than one specific artifact. Note that the word covers both a concrete set of trained weights you can load and run, and the architecture that defines its shape; which sense is meant is normally clear from context.

Explainers using this term

• Chain-of-Thought from Scratch — What Changes When You Make a Model Show Its WorkChain-of-Thought Prompting Elicits Reasoning in Large Language Models
• Paper Walkthrough: One Training Example Keeps On-Policy Distillation Improving for Hundreds of StepsRethinking On-Policy Distillation of Large Language Models II: One Training Example
• Paper Walkthrough: Language Models Can Control Their Own AttentionLanguage Models Can Control Their Own Attention