Library/LLMs-from-scratch
Library/LLMs-from-scratchForked

rasbt/LLMs-from-scratch

LLMs-from-scratch

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Builder

rasbt

rasbt

rasbt • individual

Stars

89,504

Using upstream star count

Forks

13,666

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Jul 23, 2023

Project creation date

README Summary

This repository provides a comprehensive, step-by-step implementation of a ChatGPT-like Large Language Model (LLM) using PyTorch from scratch. The project includes detailed Jupyter notebooks that walk through the entire process of building, training, and fine-tuning a transformer-based language model. It serves as an educational resource for understanding the inner workings of modern LLMs without relying on high-level abstractions.

AI Dev Skills

Unmapped

Transformer ArchitectureLarge Language Model ImplementationNeural Network ProgrammingDeep Learning from ScratchPyTorch DevelopmentNatural Language ProcessingAttention MechanismsModel TrainingLanguage Model Architecture

Tags

Transformer ArchitectureLarge Language Model ImplementationNeural Network ProgrammingDeep Learning from ScratchPyTorch DevelopmentNatural Language ProcessingAttention MechanismsModel TrainingLanguage Model ArchitectureNeural Network Architecture DesignDeveloper ToolsOpen Source AI ImplementationTextCustom Language Model DevelopmentResearch EnvironmentUnderstanding Transformer ArchitectureEducationPyTorch Deep LearningLarge Language ModelsDeep Learning Research and PrototypingEducational AI ResourcesSelf-hostedEducational LLM ImplementationLanguage Model TrainingJupyter Notebook

Taxonomy

Recent Activity

Updated 1 months ago

7 Days

0

30 Days

0

90 Days

0

Quality

research
Quality
medium
Maturity
research

Categories

Dev Tools & AutomationPrimaryLearning ResourcesNLP & TextData Science & AnalyticsSearch & KnowledgeOther AI / MLModel TrainingFoundation Models

PM Skills

Developer Platform

Languages

Jupyter Notebook100.0%

Timeline

Project created
Jul 23, 2023
Forked
Mar 12, 2026
Your last push
1 months ago
Upstream last push
7 days ago
Tracked since
Mar 7, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…