short alias lmurg
This Python-based NNGPT project leverages large language models (LLMs) to automate the creation of neural network architectures, streamlining the design process for machine learning practitioners. It leverages various neural networks from the LEMUR Dataset to fine-tune LLMs and provide insights into potential architectures during the creation of new neural network models.
For Linux/Mac:
python3 -m venv .venv
source .venv/bin/activateFor Windows:
python3 -m venv .venv
.venv\Scripts\activateIt is also assumed that CUDA 12.6 is installed. If you have a different version, please replace 'cu126' with the appropriate version number.
-
On Debian/Ubuntu systems, run:
sudo apt install libmpich-dev # for MPICH sudo apt install libopenmpi-dev # for Open MPI -
On Fedora/RHEL systems, run:
sudo dnf install mpich-devel # for MPICH sudo dnf install openmpi-devel # for Open MPI
Create a virtual environment, activate it, and run the following command to install all the project dependencies:
python -m pip install --upgrade pip
pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cu126If there are installation problems, install the dependencies from the 'requirements.txt' file one by one.
Remove an old version and install LEMUR Dataset from GitHub to get the most recent code and statistics updates:
rm -rf db
pip uninstall nn-dataset -y
pip install git+https://github.com/ABrain-One/nn-dataset --upgrade --force --extra-index-url https://download.pytorch.org/whl/cu126Installing the stable version:
pip install nn-dataset --upgrade --extra-index-url https://download.pytorch.org/whl/cu126Adding functionality to export data to Excel files and generate plots for analyzing neural network performance:
pip install nn-stat --upgrade --extra-index-url https://download.pytorch.org/whl/cu126and export/generate:
python -m ab.stat.exportAll versions of this project are compatible with AI Linux and can be seamlessly run within its Docker container.
Installing the latest version of the project from GitHub
docker run --rm -u $(id -u):ab -v $(pwd):/a/mm abrainone/ai-linux bash -c "[ -d nn-gpt ] && git -C nn-gpt pull || git -c advice.detachedHead=false clone --depth 1 https://github.com/ABrain-One/nn-gpt"Running script
docker run --rm -u $(id -u):ab --shm-size=16G -v $(pwd)/nn-gpt:/a/mm abrainone/ai-linux bash -c "python -m ab.gpt.TuneNNGen_8B"The recently added dependencies might be missing in the AI Linux. In this case, you can create a container from the Docker image abrainone/ai-linux, install the missing packages (preferably using pip install <package name>), and then create a new image from the container using docker commit <container name> <new image name>. You can use this new image locally or push it to the registry for deployment on the computer cluster.
Use NNAlter*.py to generate initial modified CV models, specify by argument -e to determine the number of epochs for initial CV model generation.
Use TuneNNGen*.py to perform generation and evaluation of CV model, along with fine-tuning/evaluation of a LLM. The -s flag allows to skip CV model generation for a specified number of epochs.
The original version of this project was created at the Computer Vision Laboratory of the University of Würzburg by the authors mentioned below. If you find this project to be useful for your research, please consider citing our articles for NNGPT framework and hyperparameter tuning:
@article{ABrain.NNGPT,
title = {NNGPT: Rethinking AutoML with Large Language Models},
author = {Kochnev, Roman and Khalid, Waleed and Uzun, Tolgay Atinc and Zhang, Xi and Dhameliya, Yashkumar Sanjaybhai and Qin, Furui and Ignatov, Dmitry and Timofte, Radu},
year = {2025}
}
@article{ABrain.HPGPT,
title={Optuna vs Code Llama: Are LLMs a New Paradigm for Hyperparameter Tuning?},
author={Kochnev, Roman and Goodarzi, Arash Torabi and Bentyn, Zofia Antonina and Ignatov, Dmitry and Timofte, Radu},
journal={arXiv preprint arXiv:2504.06006},
year={2025}
}This project is distributed under the following licensing terms:
- models with pretrained weights under the legacy DeepSeek LLM V2 license
- all neural network models and their weights not covered by the above licenses, as well as all other files and assets in this project, are subject to the MIT license