LLMs: A Journey Through Time and Architecture

Поделиться
HTML-код
  • Опубликовано: 18 дек 2024

Комментарии • 42

  • @SebastianRaschka
    @SebastianRaschka  2 месяца назад +4

    If someone is interested in a code tutorial converting the GPT model to Llama, I have a step-by-step guide here: github.com/rasbt/LLMs-from-scratch/blob/main/ch05/07_gpt_to_llama/converting-gpt-to-llama2.ipynb (will add it to the description)

    • @SHAMIKII
      @SHAMIKII 2 месяца назад +1

      Certainly, me, me, me.
      Thank you very much for all your content.

  • @hiramcoriarodriguez1252
    @hiramcoriarodriguez1252 2 месяца назад +4

    Your book is a master peace, congratulations

  • @SanjaySingh-gj2kq
    @SanjaySingh-gj2kq 2 месяца назад +3

    Bought your book on manning last year - one of the best book on LLM internals. Looking forward to get the print book

    • @SebastianRaschka
      @SebastianRaschka  2 месяца назад +1

      Thanks for the kind words, glad to hear that you've been enjoying it! The print copies started shipping and I hope you get your's soon!

  • @oldmankatan7383
    @oldmankatan7383 Месяц назад +1

    Nice round up! Thank you for this.

  • @abdulhamidmerii5538
    @abdulhamidmerii5538 2 месяца назад +1

    Just received the print version of your book yesterday, I look forward to reading it!

    • @SebastianRaschka
      @SebastianRaschka  2 месяца назад

      Good timing! I hope you like it and have a fun weekend ahead!

  • @tee_iam78
    @tee_iam78 2 месяца назад +1

    A brilliant content. Thank you.

  • @vaioslaschos
    @vaioslaschos 2 месяца назад +2

    I think the grouped-query attention is more than a trick for computational reduction. It says something deep about what is the best way to share information in a multiagent system to have the best performance. And it says something alont the lines that it is better to give little essential info and at the same time request multiple info from many sources.

    • @SebastianRaschka
      @SebastianRaschka  2 месяца назад +2

      That's a nice interpretation regarding multi- and grouped-query attention. Thanks for sharing! If you go by the original papers though, the intention was more computation constraints and efficiency (e.g., see arxiv.org/abs/2305.13245), but yeah, perhaps it can actually help with modeling performance as well in certain scenarios (for instance, where there is massive overfitting otherwise).

    • @vaioslaschos
      @vaioslaschos 2 месяца назад

      @@SebastianRaschka I have no doubt that what you say is true, and in no way I wanted to imply you missed something. Two years ago, I spent couple of months training 100M models with different architectures. I did some weird stuff like putting all the attention layers first and then a big nonlinear layer. You will be surprised with how many monstrosities can actually work without losing too much performance. The two things I got from all this is a) There is some interesting intuition in group querying (that I cant fully articulate), and it will make sense for this to be explored further, b) skip connection, where you pass the value from previous layers to the current, is not a gimmick. If you remove it the performance drops a lot, which for me implies that attention mechanism is actually applied to get only the "new" info. I think that intuitions about the architecture is not passed from the researchers to the community and It is a pity. Also it is a pity that experimenting with architecture is a rich persons hobby. Anyway, I really like your channel. I subscribed :-).

  • @thefatcat-hd6ze
    @thefatcat-hd6ze 2 месяца назад +3

    Enjoying your book a lot :))

    • @SebastianRaschka
      @SebastianRaschka  2 месяца назад

      Thanks! Glad to hear that it was worth all the long hours and weekends!

    • @thefatcat-hd6ze
      @thefatcat-hd6ze 2 месяца назад

      @@SebastianRaschka 🙏

  • @dc33333
    @dc33333 2 месяца назад +1

    my favorite YT channel

  • @maikerodrigo4249
    @maikerodrigo4249 2 месяца назад +2

    Llama 3.2 just came out today

    • @SebastianRaschka
      @SebastianRaschka  2 месяца назад +1

      Ha yes, I wish I could insert additional slides! What's interesting is that the small model is back from RMSNorm to LayerNorm

  • @mahdipourmirzaei1048
    @mahdipourmirzaei1048 2 месяца назад +3

    GPT2 training did not train on 40 billion tokens, it was 40 GB of text which is equivalent to roughly 8 billion tokens or less.

  • @Ken-de6tp
    @Ken-de6tp 2 месяца назад +1

    Reading your new book ! 🎉🎉

    • @SebastianRaschka
      @SebastianRaschka  2 месяца назад

      Hope you'll like it! Happy coding and reading!

  • @1msirius
    @1msirius Месяц назад +1

    Hey, thanks for your videos also can you suggest to me your best book on Gen AI (I want to learn about transformers in detail)

    • @SebastianRaschka
      @SebastianRaschka  Месяц назад

      Glad you found the videos useful! Since you asked for a book recommendation: Build a Large Language Model From Scratch (amzn.to/4fqvn0D), where you build a transformer-based LLM from the ground up, implementing each single component.

  • @cletadjos
    @cletadjos 2 месяца назад +1

    Thanks for sharing 😊

  • @Innovatead_Solutions-e4u
    @Innovatead_Solutions-e4u 2 месяца назад

    Dear Sebastian Raschka, your channel caught our attention and we would like to explore advertising possibilities with you. Looking forward to discussing potential opportunities!

  • @SaiKiran-he5vy
    @SaiKiran-he5vy 2 месяца назад +1

    What is the pre-requisites knowledge required to explore your new book: `Build a Large Language Model (From Scratch)`

    • @SebastianRaschka
      @SebastianRaschka  2 месяца назад +1

      Good question! It would require Python knowledge. PyTorch knowledge is also good to get started quicker, but not strictly necessary. If you are new to PyTorch, you can start with Appendix A, which is a ~50 page intro to PyTorch to get you up to speed

  • @SettimiTommaso
    @SettimiTommaso 2 месяца назад

    Yes!

  • @subaruhassufferredenough7892
    @subaruhassufferredenough7892 2 месяца назад

    What do you mean by high quality annealing?

    • @SebastianRaschka
      @SebastianRaschka  2 месяца назад

      They would select a small subset of very high quality data for the final annealing stage.

    • @subaruhassufferredenough7892
      @subaruhassufferredenough7892 2 месяца назад +1

      What does annealing mean in the context of LLMs? Is it the same as what we mean by an annealing LR scheduler?

    • @SebastianRaschka
      @SebastianRaschka  2 месяца назад +1

      @@subaruhassufferredenough7892 Yes, it's basically the same

    • @subaruhassufferredenough7892
      @subaruhassufferredenough7892 2 месяца назад

      Do you know how they determined which data was high quality?

  • @parvesh-rana
    @parvesh-rana 2 месяца назад

    Explain transformers in detail

    • @SebastianRaschka
      @SebastianRaschka  2 месяца назад +2

      That would be a very long video :D. But you might find my book useful in that respect.

  • @rafsanjaniLab
    @rafsanjaniLab 2 месяца назад

    Hi Prof. Raschka, could you please attach the slides?

  • @SerikPoliasc
    @SerikPoliasc 2 месяца назад

    Moore Daniel Taylor Brenda Anderson Eric