Decoder-Only Transformers, ChatGPTs specific Transformer, Clearly Explained!!!

NOTE: This StatQuest was supported by these awesome people who support StatQuest at the Double BAM level: I. Urosev, S. Ágoston, M. Steenbergen, P. Keener, Alex, S. Kundapurkar, JWC, BufferUnderrrun, S. Jeffcoat, S. Handschuh, J. Le, D. Greene, D. Schioberg, Z. Rosenberg, H-M Chang, M. Ayoubieh, Losings, F. Pedemonte, S. Song US, A. Tolkachev, L. Cisterna, J. Alexander

6 thoughts on “Decoder-Only Transformers, ChatGPTs specific Transformer, Clearly Explained!!!

  1. Hi!!
    A small fan boy from India. I find your ML and Statistics video series. The concepts are explained with astonishing clarity and simplicity. Simply love the way you teach. Kudos for this!!
    Just a small request – Could you please provide the slides or notes for your Statistics playlist ? Would be a great help.

  2. Hi,
    Thanks for all the great content in your youtube channel. I have bought the illustrated guide for ML v2.2, however I was surprised that it doesn’t include topics like Transformers, CNN, and other topics that are explained on Youtube. I hope you someday update the guide and share it as a free upgrade to those who already purchased it.

    Thanks and keep up.
    Regards

    • Converting the content in my videos into a book form takes a surprising amount of time. However, once I finish two more videos on neural networks, I hope to create an entire book about the topic that also includes code examples. Fingers crossed that I can get it done next year.

    • In theory they would be different, but this example is just too simple to show all of the nuances in how transformers work.

Leave a Reply

Your email address will not be published. Required fields are marked *