Skip to content

spagdoon0411/hubbard-transformer

Repository files navigation

Setup

pip install -r requirements.txt

Based on platform you might have to follow the PyTorch setup process to enable CUDA support.

Run scripts as modules:

python -m optimization.optimization

Training Loop

Use

python -m optimization.optimization

to run the training loop. Configure run and system params in optimization/optimization.py.

Neptune logging is configured. To use it, set

export NEPTUNE_API_TOKEN="..."

in .env.

About

A transformer neural network that tries to find the ground state of a Hubbard-model system

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published