Loading video...

Video Failed to Load

Go Home

building large language models from scratch by Sebastian Raschka was a great chance for me to sit down and study again all the LLM basics > token and positional embeddings > self-attention and what QKV is about > causal & multi-head attention studying llms and how they work can...

49,292 views • 1 year ago •via X (Twitter)

3 Comments

ℏεsam's profile picture
ℏεsam1 year ago

thanks professor @ProfTomYeh for the video, he advised me to share the notes to spread the word and I'm happy I did. here's the link to the repo if you're curios.

Power Homeschool's profile picture
Power Homeschool2 years ago

The Acellus® Learning System automates much of the busy-work associated with grading & keeping records so that parents can focus on what matters most–helping your child succeed. Enroll now! ⬇️

Callum's profile picture
Callum1 year ago

Great insights I came to the AI space late, so I was a little confused when I cracked open Tensorflow. I expected training to provide visibility to the underlying data, but was disappointed when I found out this wasn’t the case. I started structuring data myself, and found I was able to extract meaningful results and Create, Read, Update and Delete nodes and edges on the fly within my own Cube4D tensors. It made me come to the breakthrough that model training is just finding patterns within the data, and found that I was able to bypass the need for brute force model training by simply mapping the relationships in the schema itself. I essentially created a tesseract of data, which is a cornerstone of my Relational Intelligence Framework. I’d be keen to hear others thoughts on my approach to see if I’m on to something here. I’ve built, tested, validated, formalized it and licensed it behind CC-BY-NC-SA 4.0, but no one seems to understand it. Would really be keen to chat to others in the space.

Related Videos

New short course: Attention in Transformers: Concepts and Code in PyTorch. Last week we released a course on how LLM transformers work. This week, go deeper and learn about the technical ideas behind the attention mechanism, and see how to code it in PyTorch. This course is built with Joshua Starmer, Founder and CEO of StatQuest. The attention mechanism was a breakthrough that led to transformers, the architecture powering large language models like ChatGPT. Transformers, introduced in the 2017 paper: "Attention is All You Need" by Viswani and others, took off because of its highly scalable design. In this course, you’ll learn how the attention mechanism, a key element of transformer-based LLMs, works and implement it in PyTorch. You'll develop deep intuition about building reliable, functional, and scalable AI applications. What you will do: - Understand the evolution of the attention mechanism, a key breakthrough that led to transformers. - Learn the relationships between word embeddings, positional embeddings, and attention. - Learn about the Query, Key, and Value matrices, and how to produce and use them in attention. - Walk through the math required to calculate self-attention and masked self-attention to learn why and how they work. - Understand the difference between self-attention and masked self-attention and how one is used in the encoder to build context-aware embeddings and the other is used in the decoder for generative outputs. - Learn the details of the encoder-decoder architecture, cross-attention, and multi-head attention and how they are all incorporated into a transformer. - Use PyTorch to code a class that implements self-attention, masked self-attention, and multi-head attention. There're lots of exciting technical details in this course. Please sign up here:

Andrew Ng

132,285 views • 1 year ago

I hear so often from the Dommes I work with that they struggle with people online fetichizing them and simply seeing them for how sexy and beautiful they are. They project their fantasies and their desires onto you. That stops immediately once you move the attention from you to them. From 'look at me' to 'I see you'. What does that look like? When you create content, think of them and what this scene or that narrative is evoking. What will they learn from you? What they want is not to passively watch how sexy you are, but for you to train them, to give them instructions, to teach them, to guide them, to be in charge, to command them. This is not being an object but the main subject. The Authority figure. How is your content already doing that. The sexy photos can still be there, they are important to already capture des attention. But what you do with that attention once you have it, is where the power dynamic is established. Positioning yourself as more than a stunning Goddess, but actually a woman who has a voice, opinions, perspective, a philosophy, a way to doing things, teaching them what you like, how you like it, why you like it, already makes them want to be that for you. You hold the attention, you hold the power, so you direct it. And for that, you want them to know you get them and you know what lives within them... that creates the desire for you to be the one exposing it. You instantly build trust. Not because you demanded it, but because you earned it: you showed them you know what you are doing. You have experience, you understand them. They are not told to come see you, they are seduced into it. They desire it. And they will work for it. This will attract better clients (real subs) and instead of you trying to get their attention, they will work to earn yours. If you want to learn more about power dynamics, building a brand as a Pro or the psychology behind BDSM, you can now access all my trainings and classes in one place for a fraction of the cost of The Dominatrix Academy. And you can reinvest the total amount towards the Program. Message me [SECRET] for the details. This offer is not available on my website.

Ms. Malissia

16,120 views • 3 months ago

.tobi lutke removed all the Norman doors from Shopify’s offices because he couldn’t have excellent people surrounded by bad design. Ramp Cofounder Eric Glyman says he learned the same lesson by studying Breville toasters: “ If you care about design, you should buy a Breville toaster.” “ One of the big problems in a lot of B2B software is: it starts out clean and elegant. There's a bunch of businesses who love the product and they start serving more customers and have more requirements and more ideas.” “Before you know it, you end up with these disasters of B2B softwares which require a PhD to learn how to use.” “ If you were to go ask people, ‘What do you want in a toaster or in a microwave?’ They might say I like toast but sometimes I want to reheat pizza. I should have a ‘reheat frozen pizza’ mode. Or maybe you're cooking stuff and want it to be more like an oven, or you want to make popcorn and it's a toaster/microwave and all these things.” “Before you know it, you end up with these toasters filled with buttons and buttons and knobs and dials.” “That is literally asking customers what they want and building exactly that.” “ if you watch people toast things, what they actually do falls into two categories: you hit start and either you've undercooked the toast and need to put it back in, or you've overdone it and have to start over.” “If you look at the [Breville] there are only a few buttons. One of the four buttons is called ‘A Bit More.’” “ No one would ask you for ‘A Bit More.’ They just want the perfect level of toast and it's hard to know that, so they built that in.”

David Senra

172,242 views • 1 month ago