noah-hein/mazeGPT
AI model for making mazes that extends OpenAIs GPT2 model
This project creates unique, complex mazes using an AI model. Unlike traditional algorithms that can produce repetitive patterns, this tool generates mazes with more chaotic, human-like designs. You input desired maze dimensions, and it outputs a novel maze structure in a simple string format, which can then be visualized. It's ideal for game designers, puzzle creators, or educators who need distinct mazes.
No commits in the last 6 months.
Use this if you need to generate mazes that avoid predictable, algorithm-specific patterns and instead offer more varied and challenging structures.
Not ideal if you require mazes with specific solvable paths or properties that traditional, deterministic algorithms can guarantee.
Stars
15
Forks
1
Language
Python
License
MIT
Category
Last pushed
Dec 21, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/noah-hein/mazeGPT"
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!
kyegomez/TeraGPT
Train a production grade GPT in less than 400 lines of code. Better than Karpathy's verison and GIGAGPT
theosorus/GPT2-Hasktorch
GPT2 implementation in Haskell with the Hasktorch library, inspired by Andrej Karpathy's Pytorch...
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,...