Summary
Full Transcript
In this lecture, we learn about multi-head attention with weight splits. We see a step by step mathematical explanation of each and every step of calculating multi-head attention. After this in-depth lecture, you will master the foundations of multi-head attention: theory as well as code. The key reference book which this video series very closely follows is Build a Large Language Model from Scratch by Manning Publications. All schematics and their descriptions are borrowed from this incredible book! This book serves as a comprehensive guide to understanding and building large language models, covering key concepts, techniques, and implementations. Affiliate links for purchasing the book will be added soon. Stay tuned for updates! 0:00 Multi-head attention recap 3:18 Multi-head attention with weight splits introduction 9:41 Defining inputs 11:44 Decide output dimension, number of heads 13:45 Initialize trainable key, query, value weight matrices 16:12 Calculate the key, query and value matrices 19:14 Unroll key, query, value dimensions to include num_heads 24:48 Group matrices by number of heads 28:45 Finding attention scores 36:00 Finding attention weights 44:05 Finding multi-head context vectors 54:50 Hands on example testing 59:31 Conclusion Link to code file: https://drive.google.com/file/d/13oYPezurWAV4AbnFV9JWAG4uJVM65ZWB/view?usp=sharing ================================================= ✉️ Join our FREE Newsletter: https://vizuara.ai/our-newsletter/ ================================================= Vizuara philosophy: As we learn AI/ML/DL the material, we will share thoughts on what is actually useful in industry and what has become irrelevant. We will also share a lot of information on which subject contains open areas of research. Interested students can also start their research journey there. Students who are confused or stuck in their ML journey, maybe courses and offline videos are not inspiring enough. What might inspire you is if you see someone else learning and implementing machine learning from scratch. No cost. No hidden charges. Pure old school teaching and learning. ================================================= 🌟 Meet Our Team: 🌟 🎓 Dr. Raj Dandekar (MIT PhD, IIT Madras department topper) 🔗 LinkedIn: https://www.linkedin.com/in/raj-abhijit-dandekar-67a33118a/ 🎓 Dr. Rajat Dandekar (Purdue PhD, IIT Madras department gold medalist) 🔗 LinkedIn: https://www.linkedin.com/in/rajat-dandekar-901324b1/ 🎓 Dr. Sreedath Panat (MIT PhD, IIT Madras department gold medalist) 🔗 LinkedIn: https://www.linkedin.com/in/sreedath-panat-8a03b69a/ 🎓 Sahil Pocker (Machine Learning Engineer at Vizuara) 🔗 LinkedIn: https://www.linkedin.com/in/sahil-p-a7a30a8b/ 🎓 Abhijeet Singh (Software Developer at Vizuara, GSOC 24, SOB 23) 🔗 LinkedIn: https://www.linkedin.com/in/abhijeet-singh-9a1881192/ 🎓 Sourav Jana (Software Developer at Vizuara) 🔗 LinkedIn: https://www.linkedin.com/in/souravjana131/
Continue this lesson in the app
Install CourseHive on Android or iOS to keep learning while you move.
