MyGPT a toy LLM which can be trained on Project Gutenberg and dad jokes
My puny version of ChatGPT. This was based on the excellent LLM lecture series by Andrej Karpathy: https://www.youtube.com/watch?v=kCc8FmEb1nY The main points of differentiation are that my version is token-based (tiktoken) with code to load up multiple text files as a trining set. Plus, it has a minimal server which is a drop-in replacement for the OpenAI REST API. So you can train the default tiny 15M parameter model, and use that in your projects instead of ChatGPT. I trained it on 20Mb of Project Gutenberg encyclopaedias, then fine-tuned it on 120 dad jokes, to get a Q: A:…
In plain words
MyGPT is a small language model trainer and server based on Andrej Karpathy's LLM lecture series. It allows users to train a 15-million-parameter model on custom text files from Project Gutenberg and other sources, then deploy it via a minimal server that mimics OpenAI's REST API. The creator trained an example model on encyclopedia entries and dad jokes to demonstrate the system. MyGPT is designed for entertainment and experimentation rather than production use, with minimal server functionality and intentionally rough code.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
My puny version of ChatGPT. This was based on the excellent LLM lecture series by Andrej Karpathy: https://www.youtube.com/watch?v=kCc8FmEb1nY The main points of differentiation are that my version is token-based (tiktoken) with code to load up multiple text files as a trining set. Plus, it has a minimal server which is a drop-in replacement for the OpenAI REST API. So you can train the default tiny 15M parameter model, and use that in your projects instead of ChatGPT. I trained it on 20Mb of Project Gutenberg encyclopaedias, then fine-tuned it on 120 dad jokes, to get a Q: A: prompt format. This model + training set is so small that the results are basically a joke; it's for entertainment purposes only. The code is also very rough, and the server only has the minimum functionality filled in. I embodied this model in my talking LLM-driven hexapod robot, and it could give very silly answers to spoken questions.
Does the same job
all alternatives →
- IWI “wrote” a kid's book with ChatGPT and Midjourney2023 · adventure-of-penelope.vercel.app · ▲417
Two of my friends recently welcomed their first child and I "wrote" a kid's book for them using ChatGPT for the story and Midjourney for illustrations. The plot was sourced from a group of friends.
- IBI built a free in-browser Llama 3 chatbot powered by WebGPU2024 · github.com · ▲547
I spent the last few days building out a nicer ChatGPT-like interface to use Mistral 7B and Llama 3 fully within a browser (no deps and installs). I’ve used the WebLLM project by MLC AI for a while to interact with LLMs in the browser when handling sensitive data but I found their UI quite lacking for serious use so I built a much better interface around WebLLM. I’ve been using it as a therapist and coach. And it’s wonderful knowing that my personal information never leaves my local computer. Should work on Desktop with Chrome or Edge. Other browsers are adding WebGPU support as well - see…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
