Nikshaan/llm-from-scratch
Implementation of build a LLM from scratch by Sebastian Raschka.
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.
Stars
15
Forks
2
Language
Python
License
—
Category
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.
Higher-rated alternatives
AI-Hypercomputer/maxtext
A simple, performant and scalable Jax LLM!
rasbt/reasoning-from-scratch
Implement a reasoning LLM in PyTorch from scratch, step by step
mindspore-lab/mindnlp
MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless...
mosaicml/llm-foundry
LLM training code for Databricks foundation models
rickiepark/llm-from-scratch
<밑바닥부터 만들면서 공부하는 LLM>(길벗, 2025)의 코드 저장소