Loading video...
Video Failed to Load
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... show more
49,292 views • 1 year ago •via X (Twitter)
3 Comments

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.

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! ⬇️

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.
