ChatGPT: Zero to Hero
ChatGPT from zero to hero.
ABOUT ME
⭕ Subscribe: https://www.youtube.com/c/CodeEmporiu...
📚 Medium Blog: / dataemporium
💻 Github: https://github.com/ajhalthor
👔 LinkedIn: / ajay-halthor-477974bb
RESOURCES
[1 🔎] Transformer Neural Networks video: • Transformer Neural Networks - EXPLAINED! (...
[2 🔎] ChatGPT blog: https://openai.com/blog/chatgpt/
[3 🔎] Proximal Policy Optimization is how ChatGPT makes use of human rankings to update model parameters and make it more "safe" and "truthful": https://openai.com/blog/openai-baseli...
[4 🔎] Here is a paper that shows how Reinforcement learning through human feedback actually helps: https://arxiv.org/pdf/2009.01325.pdf
[5 🔎] Every timestep, a subword token is generated. Here is some more information on this process with BPE: https://towardsdatascience.com/byte-p...
[6 🔎] Basic Concepts in Reinforcement Learning: https://www.baeldung.com/cs/ml-policy...
[7 🔎] What is GPT-3.5? https://beta.openai.com/docs/model-in...
[8🔎] GPT-3 Main Paper: https://arxiv.org/pdf/2005.14165.pdf
[9 🔎] GPT-2 Main Paper: https://d4mucfpksywv.cloudfront.net/b...
[10 🔎] GPT original paper: https://s3-us-west-2.amazonaws.com/op...
[11 🔎] A very Nice intuitive understanding of GPT-3 architecture: https://dugas.ch/artificial_curiosity...
[12 🔎] Why Does GPT-3 write non-sensical stuff that sounds legit? https://www.alignmentforum.org/posts/...
[13 🔎] Main paper for instructGPT (the model ChatGPT was modeled after): https://arxiv.org/pdf/2203.02155.pdf
[14 🔎] Likert Scale: • Likert-Scale [Simply Explained]
[15 🔎] Human feedback used in training ChatGPT: https://arxiv.org/pdf/2009.01325.pdf
[16 🔎] Reinforcement Learning explained : http://karpathy.github.io/2016/05/31/rl/
[17 🔎] Example to show how the policy backward step is only called when an episode (a sequence of actions that is complete response in ChatGPT) is complete: https://gist.github.com/karpathy/a416...
[18 🔎] Dictionary of Terms in Reinforcement Learning: https://towardsdatascience.com/the-co...
RESOURCES
PLAYLISTS FROM MY CHANNEL
⭕ ChatGPT Playlist of all other videos: • ChatGPT
⭕ Transformer Neural Networks: • Natural Language Processing 101
⭕ Convolutional Neural Networks: • Convolution Neural Networks
⭕ The Math You Should Know : • The Math You Should Know
⭕ Probability Theory for Machine Learning: • Probability Theory for Machine Learning
⭕ Coding Machine Learning: • Code Machine Learning
MATH COURSES (7 day free trial)
📕 Mathematics for Machine Learning: https://imp.i384100.net/MathML
📕 Calculus: https://imp.i384100.net/Calculus
📕 Statistics for Data Science: https://imp.i384100.net/AdvancedStati...
📕 Bayesian Statistics: https://imp.i384100.net/BayesianStati...
📕 Linear Algebra: https://imp.i384100.net/LinearAlgebra
📕 Probability: https://imp.i384100.net/Probability
OTHER RELATED COURSES (7 day free trial)
📕 ⭐ Deep Learning Specialization: https://imp.i384100.net/Deep-Learning
📕 Python for Everybody: https://imp.i384100.net/python
📕 MLOps Course: https://imp.i384100.net/MLOps
📕 Natural Language Processing (NLP): https://imp.i384100.net/NLP
📕 Machine Learning in Production: https://imp.i384100.net/MLProduction
📕 Data Science Specialization: https://imp.i384100.net/DataScience
📕 Tensorflow: https://imp.i384100.net/Tensorflow
0:00 Introduction
0:47 Fundamental Concepts
7:35 Overview of ChatGPT working
10:18 Step 1: GPT in ChatGPT
23:06 Step 2: Rewards Model
37:37 Step 3: Use Reinforcement Learning to fine tune ChatGPT
48:47 Conclusion