Orchestrate reproducible model pretraining pipelines with dataset, checkpoint, and resume utilities.

This repository contains the code for coding, pretraining, and finetuning a GPT-like LLM and is the official code repository for the book [Build a Large Language Model (From Scratch)](http://mng.bz/orYv).

Is the benchmark you are quoting inside the data you trained on? Contamination scanning with the matching text shown, on your machine, nothing uploaded.

Explore any codebase — generate rich architecture docs with diagrams, then chat with an AI that already read the code

Explore any codebase — generate rich architecture docs with diagrams, then chat with an AI that already read the code

A fully standalone, terminal-based AI model CLI for training and inference