Spaces:
Running
MLIP Arena
MLIP Arena is currently in pre-alpha. The results are not stable. Please intepret them with care.
If you're interested in joining the effort, please reach out to Yuan at cyrusyc@berkeley.edu. See project page for some outstanding tasks.
MLIP Arena is an open-source platform for benchmarking machine learning interatomic potentials (MLIPs). The platform provides a unified interface for users to evaluate the performance of their models on a variety of tasks, including single-point density functional theory calculations and molecular dynamics simulations. The platform is designed to be extensible, allowing users to contribute new models, benchmarks, and training data to the platform.
Contribute
MLIP Arena is now in pre-alpha. If you're interested in joining the effort, please reach out to Yuan at cyrusyc@berkeley.edu. See project page for some outstanding tasks.
Add new MLIP models
If you have pretrained MLIP models that you would like to contribute to the MLIP Arena and show benchmark in real-time, there are two ways:
Hugging Face Model
- Inherit Hugging Face ModelHubMixin class to your awesome model class definition. We recommend PytorchModelHubMixin.
- Create a new Hugging Face Model repository and upload the model file using push_to_hub function.
- Follow the template to code the I/O interface for your model, and upload the script along with metadata to the MLIP Arena here.
- CPU benchmarking will be performed automatically. Due to the limited amount GPU compute, if you would like to be considered for GPU benchmarking, please create a pull request to demonstrate the offline performance of your model (published paper or preprint). We will review and select the models to be benchmarked on GPU.
Add new benchmark tasks
- Create a new Hugging Face Dataset repository and upload the reference data (e.g. DFT, AIMD, experimental measurements such as RDF).
- Follow the task template to implement the task class and upload the script along with metadata to the MLIP Arena here.
- Code a benchmark script to evaluate the performance of your model on the task. The script should be able to load the model and the dataset, and output the evaluation metrics.
Molecular dynamics calculations
Single-point density functional theory calculations
- MPTrj
- QM9
- Alexandria