Nikshaan/llm-from-scratch

Implementation of build a LLM from scratch by Sebastian Raschka.

31
/ 100
Emerging

This project provides a hands-on implementation for building, training, and fine-tuning a Large Language Model (LLM) from the ground up, following a GPT-style architecture. It takes raw text data as input and produces a functional LLM capable of generating text, classifying content like spam, or following specific instructions. This is ideal for machine learning engineers, researchers, or advanced students who want to deeply understand LLM mechanics beyond just using existing APIs.

Use this if you are a machine learning practitioner or researcher who wants to understand the intricate details of how a GPT-style LLM is constructed and trained from scratch.

Not ideal if you are looking for a pre-built, production-ready LLM to deploy directly or if your goal is to simply use an existing LLM for immediate application.

Large Language Models Natural Language Processing Deep Learning Model Training Text Classification
No License No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 5 / 25
Community 10 / 25

How are scores calculated?

Stars

15

Forks

2

Language

Python

License

Last pushed

Jan 22, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Nikshaan/llm-from-scratch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.