Library/reasoning-from-scratchForked

rasbt/reasoning-from-scratch

reasoning-from-scratch

Implement a reasoning LLM in PyTorch from scratch, step by step

View on GitHub↗Upstream rasbt/reasoning-from-scratch↗

Builder

rasbt

rasbt • individual

Stars

3,966

Using upstream star count

Forks

560

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Mar 4, 2025

Project creation date

README Summary

This repository provides a step-by-step implementation of a reasoning-capable Large Language Model (LLM) built from scratch using PyTorch. The tutorial walks through the complete process of creating and training a model that can perform logical reasoning tasks, presented in an educational Jupyter Notebook format.

AI Dev Skills

Unmapped

Large Language Model ArchitecturePyTorch Deep LearningReasoning Model ImplementationNeural Network TrainingTransformer ArchitectureLanguage Model Fine-tuningStep-by-step Model Development

Taxonomy

AI Trends

Reasoning AI Educational AI Implementation From-Scratch Model Development

Deployment Context

Self-hosted Research Environment

Industries

Education Research

Modalities

Text

Skill Areas

Large Language Model Architecture PyTorch Deep Learning Reasoning Model Implementation Neural Network Training Transformer Architecture Language Model Fine-tuning Step-by-step Model Development

Use Cases

Educational Tutorial for LLM Development Research Implementation of Reasoning Models Learning PyTorch for Language Models Understanding LLM Internal Mechanisms

Recent Activity

Updated 27 days ago

7 Days

30 Days

90 Days

Quality

research

Quality: medium
Maturity: research

PM Skills

Product Discovery

Languages

Jupyter Notebook100.0%

Timeline

Project created: Mar 4, 2025
Forked: Mar 12, 2026
Your last push: 27 days ago
Upstream last push: 6 days ago
Tracked since: Mar 17, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…