Gen AI Study Group Introductory Tutorial - Transformers, ChatGPT, Prompt Engineering, Projects
We're beginning a study group for Singaporeans at AI Space, and this is the introductory tutorial session. I have covered the basics of Transformers, ChatGPT, Prompt Engineering and some possible projects which could be done as a group project. I have enhanced my previous ChatGPT game to include DALL-E API for images of the choices (separate video on that soon!), as well as showcase a WebScraper with Selenium, Custom Search JSON API and ChatGPT (separate video on that soon!)!
For the projects, you can find the implementation notebooks here:
https://github.com/tanchongmin/TensorFlow-Implementations/tree/main/Tutorial
This tutorial is a short excerpt of my previous Youtube tutorials:
How ChatGPT Works: https://www.youtube.com/watch?v=wA8rjKueB3Q
Prompt Engineering and LLMOPs: https://www.youtube.com/watch?v=1Pao2ie4OG8
Evolution ChatGPT Game: https://www.youtube.com/watch?v=5xyGi6aXBw8
Strict JSON Framework: https://www.youtube.com/watch?v=A6sIh-lmApk
Here's the video for the implementations:
Web Scraper with Selenium and ChatGPT: https://www.youtube.com/watch?v=4xsBJQs2Hao
Evolution Game using DALL-E and ChatGPT: https://www.youtube.com/watch?v=kTKeAcOWh-k
The study group will go through some of Deeplearning.ai short courses to learn the basics of application programming and prompt engineering with GPT.
ChatGPT Prompt Engineering for Developers: https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/
Building Systems with ChatGPT API: https://learn.deeplearning.ai/chatgpt-building-system
LangChain for Application Development: https://www.deeplearning.ai/short-courses/langchain-for-llm-application-development/
LangChain Retrieval Augmented Generation: https://learn.deeplearning.ai/langchain-chat-with-your-data
Personally, I am not a fan of LangChain as it is hard to customize, so I have created my own framework to do so - The StrictJSON Framework. Check it out here! https://github.com/tanchongmin/strictjson
~~~~~~~~~~~~~~~~~~~~~~
0:00 Introduction
0:50 Embedding Space
3:25 Transformer Architecture
16:40 Attention Details
19:32 Decoder-one models (GPT)
25:01 How Transformers are trained
32:11 How are tokens generated
37:30 Q&A on Transformers
43:08 LLMs vs Computer Programs
45:20 LLMs as a system and prompting tips
48:30 Fixed JSON Framework
49:50 Project Showcase
~~~~~~~~~~~~~~~~~~~~~~
AI and ML enthusiast. Likes to think about the essences behind breakthroughs of AI and explain it in a simple and relatable way. Also, I am an avid game creator.
Discord: https://discord.gg/bzp87AHJy5
LinkedIn: https://www.linkedin.com/in/chong-min-tan-94652288/
Online AI blog: https://delvingintotech.wordpress.com/
Twitter: https://twitter.com/johntanchongmin
Try out my games here: https://simmer.io/@chongmin
Other Videos By John Tan Chong Min
Other Statistics
Prompt Statistics For John Tan Chong Min
There are 843 views in 1 video for Prompt. Less than an hour worth of Prompt videos were uploaded to his channel, less than 0.32% of the total video content that John Tan Chong Min has uploaded to YouTube.