aptsunny.github.io - Yue'Log

home > domains > aptsunny.github.io

Description: Document my learning notes.

Example domain paragraphs

Posts Archive Search Tags Details Nation 👋 Welcome to Yue’Log Hi, this is Sun Yue (孙越). I’m preparing to documente my computational photography notes in this blog. Other than writing the blogs, I’m a Staff Deep Learning Research Engineer at XiaoMi. Before joining XiaoMi, I also worked/interned at Sensetime, Amazon and Orbbec.

Prompt Engineering Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics. This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models....

Many new Transformer architecture improvements have been proposed since my last post on “The Transformer Family” about three years ago. Here I did a big refactoring and enrichment of that 2020 post — restructure the hierarchy of sections and improve many sections with more recent papers. Version 2.0 is a superset of the old version, about twice the length. Notations Symbol Meaning $d$ The model size / hidden state dimension / positional encoding size....

Links to aptsunny.github.io (4)



© example3.com 2024