RSS Amplifier

Video feed

Building LLMs from scratch

youtube.com ↗Source feed ↗15 videos

Subscribe:.rss.atom.json.md

Dormant Last read · last published · next check
Read 3 days ago and current, but nothing has been published for 23 months.

Written by

Latest videos

Saves to your Watch queue, to pick up on another day or another device.

Lecture 15: Coding the self attention mechanism with key, query and value matrices

Play

Lecture 14: Simplified Attention Mechanism - Coded from scratch in Python | No trainable weights

Play

Lecture 13: Introduction to the Attention Mechanism in Large Language Models (LLMs)

Play

Lecture 12: The entire Data Preprocessing Pipeline of Large Language Models (LLMs)

Play

Lecture 11: The importance of Positional Embeddings

Play

Lecture 10: What are token embeddings?

Play

Lecture 9: Creating Input-Target data pairs using Python DataLoader

Play

Lecture 8: The GPT Tokenizer: Byte Pair Encoding

Play

Lecture 7: Code an LLM Tokenizer from Scratch in Python

Play

Lecture 6: Stages of building an LLM from Scratch

Play

Lecture 5: How does GPT-3 really work?

Play

Lecture 4: What are transformers?

Play

Lecture 3: Pretraining LLMs vs Finetuning LLMs

Play

Lecture 2: Large Language Models (LLM) Basics

Play

Lecture 1: Building LLMs from scratch: Series introduction

Play