What Is Positional Encoding? How To Use Word and Sentence Embeddings with BERT and Instructor-XL!

Поделиться
HTML-код
  • Опубликовано: 17 ноя 2024

Комментарии • 30

  • @smellslikeupdog80
    @smellslikeupdog80 Год назад +7

    Man I don't know anyone who explains things in a clear, technical, and straightforward way. This is great stuff.

    • @AemonAlgiz
      @AemonAlgiz  Год назад

      Thank you! I try my best to make the content digestible

  • @johnholdsworth1878
    @johnholdsworth1878 Год назад +3

    These videos are amazing! You are an absolutely brilliant teacher. I have just made the viewing of this video mandatory for my entire team. The ability to explain complex topics in an understandable way is a sign of genius - thank you.

    • @AemonAlgiz
      @AemonAlgiz  Год назад +1

      Thank you! Hopefully the training corpus one is as helpful

  • @AemonAlgiz
    @AemonAlgiz  Год назад +1

    Edit: My father-in-law had a heart attack this morning. Fortunately he is going to be fine, but the universe is opposed to me being on schedule this week. My apologies all.
    Hey all, the LoRA training video is almost done! I decided to add some extra material on how we to prepare and preprocess datasets, since the video didn’t feel super cohesive without it. I figured you all would prefer quality over rushing, so I’ll have it out by the morning.

  • @blondiedawn
    @blondiedawn Год назад +3

    This one was easy to follow and understand. Thank you for the great tutorial!

  • @LoneRanger.801
    @LoneRanger.801 Год назад +2

    Wow! Love your detailed explanations and code examples. Subscribed ❤

    • @AemonAlgiz
      @AemonAlgiz  Год назад +1

      Thank you, I’m glad it was helpful!

  • @kaymcneely7635
    @kaymcneely7635 Год назад +4

    Yet another easy to understand video. Thank you for the time and effort you put into these!

  • @PMX
    @PMX Год назад +2

    Japanese is read left to right, unless you are talking about vertical text (in that case is top to bottom, right to left), but most Japanese text online, which is what an llm would be trained on, would be regular left to right.

    • @AemonAlgiz
      @AemonAlgiz  Год назад

      I was thinking about tategaki, I should have been more specific. Thanks for the correction!

  • @Moonz97
    @Moonz97 Год назад +2

    Great video!
    Are sentence embeddings simply constructed from aggregating word embeddings and applying some operation, such as mean pooling or max pooling?

    • @AemonAlgiz
      @AemonAlgiz  Год назад

      Indeed, typically you can capture the output from attention and use that as an embedding

  • @TariqHabibAfridi
    @TariqHabibAfridi Год назад +2

    I was thinking to Learn about LoRA for the past several days but you just rocked it. it is so simple. Thanks alot and i really appreciate your videos.
    One more thing i am currently doing my PhD and the topic of my PhD is Vision-language Pre-trained models. However my main problem until now is that i have small resources at most i can get two 3090 GPUs. I would appreciate any useful suggestion and help regarding Pre-training The large Vision-language Pre-trained models with such resources. I would also like to have any colloborations in this regard. Thank you so much again

    • @AemonAlgiz
      @AemonAlgiz  Год назад +1

      ViT’s use a ton of resources for training, though you do have some options.
      1. If you have some funds, you could use Lambda Labs which lets you rent an A100 for as little as $1.10/hr. I use them for work and they have been great.
      2. You could always try 8/4-bit quantizing them, GPTQ for LLaMA has a great example of how to implement the algorithm.
      1. There is the Hyena paper which shows some ways to diagonalize the attention layer, but there is no algorithm for it yet.
      My discord is Aemon Algiz#0033 if you’d like to chat.

    • @TariqHabibAfridi
      @TariqHabibAfridi Год назад +1

      @@AemonAlgiz Thank you i will explore each of these options. especially 4 bit quantization GPTQ for LLaMA.

  • @wilfredomartel7781
    @wilfredomartel7781 Год назад +1

    Such a good explanation! by the way, is instructor-xl multilingual?

    • @AemonAlgiz
      @AemonAlgiz  Год назад +1

      You know, I’m honestly not sure, though I suspect it’s primarily English. There are multilingual embedding models, though. I’ll check when I get home!

    • @wilfredomartel7781
      @wilfredomartel7781 Год назад

      @@AemonAlgiz thank you

    • @AemonAlgiz
      @AemonAlgiz  Год назад

      So, it looks like it is English, though this one is multi-lingual:
      huggingface.co/sentence-transformers/stsb-xlm-r-multilingual
      I would personally test instructor-xl and see if works for multi-lingual

  • @Heccintech
    @Heccintech Год назад +2

    this is exactly where my research is lacking.

    • @AemonAlgiz
      @AemonAlgiz  Год назад +1

      I’m glad it was helpful!

  • @lizesu8049
    @lizesu8049 10 месяцев назад

    Hey thanks for the great video but the IDE font is a little bit small.

    • @lizesu8049
      @lizesu8049 10 месяцев назад

      the code part is fine but the project file names and debugger infomation are hard to read

  • @aamir122a
    @aamir122a Год назад +1

    hey mate your audio and video are not in sync, mabe be out by a second ,

    • @AemonAlgiz
      @AemonAlgiz  Год назад

      Huh, I wonder why that’s happened. It seemed fine before I uploaded it.

  • @RandyHawkinsMD
    @RandyHawkinsMD Год назад +1

    I’m glad I discovered this valuable resource. Your simple, straightforward explanations are very helpful. One suggestion: The thin white scribe pen you use is difficult to follow at times, so if you could supplement it with a surrounding halo or some other highlight those of us with slight visual impairment would appreciate it. 🫡

    • @AemonAlgiz
      @AemonAlgiz  Год назад

      I can do that! Do you have an example of what would be best for you?