kyegomez/TeraGPT
Train a production grade GPT in less than 400 lines of code. Better than Karpathy's verison and GIGAGPT
This project helps machine learning engineers and researchers quickly build and train very large language models, like those with hundreds of billions of parameters, from scratch. You provide your training data, and it outputs a ready-to-use GPT-style model. It's designed for those who want to experiment with large-scale language model architectures without the complexity of traditional enterprise frameworks.
Available on PyPI.
Use this if you need to train or fine-tune a large language model (GPT-3 size or larger) and prefer a simple, compact codebase for rapid development and scaling.
Not ideal if you are looking for a pre-trained model or a no-code solution for applying existing large language models.
Stars
16
Forks
1
Language
Python
License
MIT
Category
Last pushed
Feb 06, 2026
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kyegomez/TeraGPT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jingyaogong/minimind
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
theosorus/GPT2-Hasktorch
GPT2 implementation in Haskell with the Hasktorch library, inspired by Andrej Karpathy's Pytorch...
noah-hein/mazeGPT
AI model for making mazes that extends OpenAIs GPT2 model
RohitPawar001/GPT-2-Implementation
This repository contains the implementation of OpenAI's GPT-2 with LORA, QLORA, RLHF, PPO,GRPO,...
miguelvanegas-c/LLMImplementation
This repository demonstrates how to build a functional AI agent using LangChain in Python,...