Skip to content

berkinersoz/LLMs-From-Scratch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LLMs From Scratch

This repository contains implementations and exercises for building a Large Language Model (LLM) from the ground up, based on the book and resources from the original repository by Sebastian Raschka.

Each chapter covers a critical component of the LLM pipeline, from data preparation to instruction fine-tuning.

Folder Structure

  • ch02: Working with Text Data - Tokenization and data sampling.
  • ch03: Coding Attention Mechanisms - Self-attention, causal attention, and multi-head attention.
  • ch04: Implementing a GPT Model - Building the GPT architecture and various attention optimizations.
  • ch05: Training on Unlabeled Data - Loss calculation, training loops, and loading pretrained weights.
  • ch06: Fine-Tuning for Classification - Adapting the model for tasks like spam detection.
  • ch07: Fine-Tuning to Follow Instructions - Instruction fine-tuning for conversational capabilities.

Getting Started

  • Each folder contains a main notebook and supporting scripts to demonstrate the concepts covered in that chapter.
  • For the authoritative source and additional resources, please visit the main repository.

About

Training LLMs with building from scratch

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors