nanoGPT
The simplest, fastest repository for training and finetuning medium-sized GPTs.
Course
A straightforward method for training your LLM, from downloading data to generating text.
Built with love by Shushant Lakhyani. Building bestproductivityresources.com
Screenshot or bookmark this page so you find it later, then share it with your network.
train-llm-from-scratch is a step-by-step guide and codebase for training your own language model: downloading and preparing data, configuring training, and generating text with the result. A practical on-ramp to how LLMs are actually built.
Developers and students who want to genuinely understand LLM training by doing it.
People looking to just use AI tools, not build them.
Similar resources to Train LLM From Scratch, picked from the directory.
The simplest, fastest repository for training and finetuning medium-sized GPTs.
Bare bones NumPy implementations of machine learning models and algorithms.
A course to get into large language models with roadmaps and Colab notebooks.
Harness engineering beginner tutorial, from 0 to 1.
OpenAI's educational resource for learning deep reinforcement learning.
A curated list of large language model papers, frameworks and resources.
Free resources that cover similar ground.
Python examples of popular ML algorithms with interactive Jupyter demos.
Harvard's open textbook on ML systems, agentic AI and physical AI.
Interactive deep learning book with code, math and discussions.
60+ deep learning paper implementations with side-by-side notes.
Practical deep learning courses for coders.
A practical guide to building with open models.
Made Train LLM From Scratch? Add this free badge to your website or README. It links to this page.
<a href="https://bestproductivityresources.com/resources/train-llm-from-scratch" target="_blank" rel="noopener"><img src="https://bestproductivityresources.com/badges/featured-light.svg" alt="Featured on Best Productivity Resources" width="250" height="54" /></a>Open stats
This site's analytics are open for everyone to see.