vldgroup / graph-pes
train and use graph-based ML models of potential energy surfaces
Why this job: works in the areas we cover, but does not say which job it does
What it does
- Experiment with new model architectures by inheriting from our GraphPESModel base class.
- Train your own or existing model architectures (e.g., SchNet, NequIP, PaiNN, MACE, TensorNet, OrB etc.).
- Use and fine-tune foundation models via a unified interface: MACE-MP0, MACE-OFF, MatterSim, GO-MACE, Egret and Orb v2/3.
- Easily configure distributed training, learning rate scheduling, weights and biases logging, and other features using our graph-pes-train command line interface.
- Use our data-loading pipeline within your own training loop.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 51 days ago
- Stars
- 131
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- 1.0.2
- Released 51 days ago
- Built with
- Python
- 96% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 70% closed
- 6 still open
- Pull requests
- 147 merged
- 4 waiting
- Releases
- 11
- 3 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| ACEsuit / mace-foundations | 324 | 2 months ago | MIT | No downloads |
| CederGroupHub / chgnet | 414 | 58 days ago | Custom | No downloads |
| mir-group / nequip | 974 | 2 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 96%
- C++ 3%
- Shell 1%
Topics
- chemistry
- deep-learning
- force-fields
- framework
- machine-learning
Project record
- JobOther AI tools
- StatusListed
- Commits378
- Forks16
- Watching1
- Stars in 28 days0
- CreatedOct 9, 2023
- First seen by usNov 7, 2026
- CheckedNov 8, 2026