Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[Neurips 2023] Generating Mario Levels with GPT2. Code for the paper "MarioGPT: Open-Ended Text2Level Generation through Large Language Models" https://arxiv.org/abs/2302.05981
| Date | Stars |
|---|---|
| 2026-07-31 | 1148 |
| 2026-08-06 | 1148 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> # MarioGPT: Open-Ended Text2Level Generation through Large Language Models [](https://arxiv.org/abs/2302.05981) [](https://pypi.org/project/mario-gpt) <a href="https://huggingface.co/spaces/multimodalart/mariogpt"><img src="https://img.shields.io/badge/%20HuggingFace%20-Demo-blue.svg" alt="HuggingFace Spaces"></a> [](https://colab.research.google.com/drive/16KR9idJUim6RAiyPASoQAaC768AvOGxP?usp=sharing) [Playing Generated Level](#interacting-with-levels) | Generated Level :-------------------------:|:-------------------------:  |  </div> How does it work? ---- Architecture | Example Prompt Generations :-------------------------:|:-------------------------:  |  MarioGPT is a finetuned GPT2 model (specifically, [distilgpt2](https://huggingface.co/distilgpt2)), that is trained on a subset Super Mario Bros and Super Mario Bros: The Lost Levels levels, provided by [The Video Game Level Corpus](https://github.com/TheVGLC/TheVGLC). MarioGPT is able to generate levels, guided by a simple text prompt. This generation is not perfect, but we believe this is a great first step more controllable and diverse level / environment generation. Forward generation:  Requirements ---- - python3.8+ Installation --------------- from pypi ``` pip install mario-gpt ``` or from source ``` git clone [email protected]:shyamsn97/mario-gpt.git python setup.py install ``` Generating Levels ------------- Since our models are built off of the amazing [transformers](https://github.com/huggingface/transformers) library, we host our model in https://huggingface.co/shyamsn97/Mario-GPT2-700-context-length This code snippet is the minimal code you need to generate a mario level! ```python from mario_gpt import MarioLM, SampleOutput # pretrained_model = shyamsn97/Mario-GPT2-700-context-length mario_lm = MarioLM() # use cuda to speed stuff up # import torch # device = torch.device('cuda') # mario_lm = mario_lm.to(device) prompts = ["many pipes, many enemies, some blocks, high elevation"] # generate level of size 1400, pump temperature up to ~2.4 for more stochastic but playable levels generated_level = mario_lm.sample( prompts=prompts, num_steps=1400, temperature=2.0, use_tqdm=True ) # show string list generated_level.level # show PIL image generated_level.img # save image generated_level.img.save("generated_level.png") # save text level to file generated_level.save("generated_level.txt") # play in interactive generated_level.play() # run Astar agent generated_level.run_astar() # Continue generation generated_level_continued = mario_lm.sample( seed=generated_level, prompts=prompts, num_steps=1400, temperature=2.0, use_tqdm=True ) # load from text file loaded_level = SampleOutput.load("generated_level.txt") # play from loaded (should be the same level that we generated) loaded_level.play() ... ``` Training ------------- The code to train MarioGPT is pretty simple and straightforward, the training class is located [here](mario_gpt/trainer.py), with a small example [notebook](notebooks/Train.ipynb) ```python import torch from mario_gpt import MarioDataset, MarioLM, TrainingConfig, MarioGPTTrainer # create basic gpt model BASE = "distilgpt2" mario_lm = MarioLM(lm_path=BASE, tokenizer_path=BASE) # create dataset dataset = MarioDataset(mario_lm.tokenizer) # create training config and trainer config = TrainingConfig(save_iteration=10) trainer = MarioGPTTrainer(mario_lm, dataset, config=config) # train for 100 iterations! trainer.train(100, batch_size=1) ``` ##### See [notebook]
Excerpt of 6,644 characters
Read on GitHub
37
Omar Sanseviero · Google · Switzerland
1
Chayim · New Thing · Israel
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f5a2fa392c11b749, llm:Repository description: 'Generating Mario Levels with GPT2. Code for the paper "MarioGPT: Open-Ended Text2Level Generation through Large Language Models"' (NeurIPS 2023). Uses GPT-2 to generate game levels (procedural content generation).
matched fp:f5a2fa392c11b749, llm:Repository description: 'Generating Mario Levels with GPT2. Code for the paper "MarioGPT: Open-Ended Text2Level Generation through Large Language Models"' (NeurIPS 2023). Uses GPT-2 to generate game levels (procedural content generation).
matched fp:f5a2fa392c11b749, llm:Repository description: 'Generating Mario Levels with GPT2. Code for the paper "MarioGPT: Open-Ended Text2Level Generation through Large Language Models"' (NeurIPS 2023). Uses GPT-2 to generate game levels (procedural content generation).