Tag
An article simplifying the concept of LLM distillation for a political audience, explaining how smaller models learn from larger ones.
An article from 2004 explaining the difference between ABI (Application Binary Interface) and API (Application Programming Interface), likely discussing their roles in software development and compatibility.
This article explains the technical principles of knowledge distillation in machine learning, pointing out that merely collecting output dialogues from ChatGPT/Claude cannot achieve effective distillation due to the lack of probability distribution information, and discusses the limitations of using generated data in SFT and pre-training.
This article explains that Windows does not have a built-in concept of binary vs. text mode at the OS level; such distinctions are handled by runtime libraries like the C runtime. It clarifies that all files are treated as bytes by Windows and that content transformations must be done manually or via libraries.