v0.3.6

What's Changed

• bugfix for stress loss by @JPDarby in #438
• change stress normalization + setup.cfg with numpy<2.0 by @ilyes319 in #467
• fix universal loss stress by default by @ilyes319 in #472
• Support for schedulefree optimizer by @RokasEl in #477
• Add Command-Line Argument for Specifying Wandb Directory by @nqhq-lou in #466
• Add DOI badge and automated release by @ElliottKasoar in #404
• Merge latest develop by @ilyes319 in #480
• remove DOI from badge by @ilyes319 in #482
• add finetuning to readme TOC by @ilyes319 in #485
• add support for hessian in calculator by @ilyes319 in #486
• prepare the model for hessian by @ilyes319 in #490
• BUG: Single atoms not isolated incorrectly removed from training set by @jameskermode in #492
• Fix bug with isolated atoms by @ilyes319 in #493
• correct pbc extension by @ilyes319 in #506
• change dynamo to optional by @ilyes319 in #510
• Simplify installation steps by @vue1999 in #514
• Develop by @ilyes319 in #515
• remove Literal for python >3.9 by @ilyes319 in #516

New Contributors

• @JPDarby made their first contribution in #438
• @nqhq-lou made their first contribution in #466
• @ElliottKasoar made their first contribution in #404
• @jameskermode made their first contribution in #492

Full Changelog: v0.3.5...v0.3.6

v0.3.5

What's Changed

• on the fly data loading by @davkovacs in #73
• On the fly dataloading by @davkovacs in #81
• Make matscipy default neighbour list by @ilyes319 in #64
• Multi gpu by @ilyes319 in #99
• Slight modification to HDF5Dataset by @sivonxay in #117
• Multi-node, multi-GPU data parallel training. by @samwaltonnorwood in #105
• Multi-processing by @mavaylon1 in #133
• Develop by @ilyes319 in #207
• load_foundations support for max_L other than 2 by @bernstei in #273
• print validation error before any training by @bernstei in #288
• update foundations with develop by @ilyes319 in #299
• Ilyes319 patch 3 by @ilyes319 in #305
• Warning on float64 training with PyTorch 2.1 by @ilyes319 in #306
• Foundations by @ilyes319 in #307
• initial torch.compile support (inference only) by @hatemhelal in #300
• Handle a wider range of possible slurm env vars by @bernstei in #332
• Update plot_train.py by @zhubonan in #352
• add note on mp corrections on energies by @chiang-yuan in #342
• Update compile test case to use larger test system by @hatemhelal in #310
• Adding pre-commit checks and github action runners by @hatemhelal in #302
• Add torch.compile compatiblity by @ilyes319 in #354
• Add an option to set the D3 damping function, which defaults to D3(BJ) by @Andrew-S-Rosen in #268
• Use HTTPS for MACE MP checkpoint URLs by @janosh in #318
• Add multi-GPU, data parallelisation, pair repulsion and distance transforms. by @ilyes319 in #359
• Add multi-GPU dataparallel by @ilyes319 in #74
• Add mutli-GPU training, data parrallelisation, pair repulsion, distance transform and other features by @ilyes319 in #363
• Add metadata saving to compiled model and hot fix stress extraction by @ilyes319 in #387
• Fix workflows check by @ilyes319 in #388
• add GitPython to deps by @ilyes319 in #389
• add pylint to pre-commit by @ilyes319 in #391
• fixed readme typos, and commit by @ilyes319 in #399
• make cli scripts importable from python by @alinelena in #398
• Develop by @ilyes319 in #418
• Improve warning for "energy", "forces" key by @ilyes319 in #419
• log errors and handle checkpoint io on rank 0 only by @jharrymoore in #420
• Fix checkpoint for multi-GPU by @ilyes319 in #421
• removed wront argument parsing in preprocess_data by @VondrakMar in #423
• Fix preprocess data and pylint by @ilyes319 in #424
• fix atom e0s being subtracted twice in mace calculator by @RokasEl in #425
• fix atom e0s being subtracted twice in mace calculator by @ilyes319 in #426
• fix bug test set stress key by @ilyes319 in #428

New Contributors

• @samwaltonnorwood made their first contribution in #105
• @mavaylon1 made their first contribution in #133
• @hatemhelal made their first contribution in #300
• @zhubonan made their first contribution in #352
• @Andrew-S-Rosen made their first contribution in #268
• @alinelena made their first contribution in #398
• @VondrakMar made their first contribution in #423
• @RokasEl made their first contribution in #425

Full Changelog: v0.3.4...v0.3.5

v0.3.4

What's Changed

• update license info of mace-off by @davkovacs in #284
• update mace-off printing info by @ilyes319 in #285
• Add link to github models by @janosh in #290
• Update mace_mp links to include github links by @ilyes319 in #291
• Update readme for foundation models by @ilyes319 in #292
• edit readme example for foundation models by @ilyes319 in #293
• Change stress input + update version by @ilyes319 in #296

Full Changelog: v0.3.3...v0.3.4

0.3.3

What's Changed

• Add small model and warning for float32 accuracy in mace_mp by @ilyes319 in #257
• update the small model to energy model by @ilyes319 in #263
• Add MACE-OFF23 models by @davkovacs in #275
• Add MACE-OFF2023 by @ilyes319 in #277
• Change package name in setup.cfg for PyPI by @ilyes319 in #281
• Change package name in setup.cfg for PyPI by @ilyes319 in #282
• update installation with PyPI by @ilyes319 in #283

Full Changelog: v0.3.2...v0.3.3

v0.3.2

What's Changed

• Update version to 0.3.2 for conda installation by @ilyes319 in #250

Full Changelog: v0.3.1...v0.3.2

v0.3.0

This Release Introduces:

1. Committee of models in the ASE calculator.
2. Active learning for MD in the ASE script.
3. Implementation of the Huber loss function.
4. Can use dipole model within the ASE calculator.
5. A LAMMPS wrapper for executing LAMMPS MD simulations.
6. The matscipy neighbor list set as the default.
7. Gaussian radial basis functions.
8. Element-dependent radial basis functions using a MLP on the radial components and node features of the sender and receiver.
9. MACE descriptors from the ASE calculator.
10. A universal pretrained MACE model on the Materials Project, available as an ASE calculator.

Major Interface Changes:

1. The scripts have been moved to mace/cli/ from the previous scripts directory to facilitate access.
2. The mace_run_train command is now available if MACE is installed via pip.

What's Changed

• merge readme edits to develop by @davkovacs in #76
• Require stress in shape (3,3) or (6,) by @LarsSchaaf in #77
• Committee error by @LarsSchaaf in #78
• Doc update by @ilyes319 in #85
• no gradient with respect to model params in eval by @davkovacs in #83
• Update active_learning_md.py by @sandipde in #89
• Update utils.py by @sandipde in #91
• Huberloss by @ilyes319 in #96
• not break if exponential LR by @bigd4 in #98
• hopefully limit unnecessary memory use. by @wcwitt in #103
• ASE calculator refactor and jit dipole models by @davkovacs in #95
• Fix unweighted EnergyForcesLoss by @chaitjo in #100
• Lammps wrapper by @wcwitt in #108
• Update Installation by @ilyes319 in #129
• matscipy neighbour list as default by @ilyes319 in #116
• Gaussian radial basis and element dependent radial by @ilyes319 in #131
• MACE descriptors by @ilyes319 in #144
• Add readme section 'Pretrained Universal MACE Checkpoints' by @janosh in #188
• fix table of content readme by @ilyes319 in #190
• Scripts entrypoints by @bernstei in #178
• add foundations model calculators by @ilyes319 in #204
• add deprecated model_path arg to asse calculator by @davkovacs in #209
• MACE 0.3.0 release by @ilyes319 in #142

New Contributors

• @LarsSchaaf made their first contribution in #77
• @sandipde made their first contribution in #89
• @bigd4 made their first contribution in #98
• @chaitjo made their first contribution in #100

Full Changelog: v0.2.0...v0.3.0

v0.2.0-alpha

This release introduces:

1. Full compilation of the mace model with torchscript.
2. Computation of stress and virials for training and evaluation.
3. Compatibility with LAMMPs and OpenMM.
4. New models to fit atomic dipoles.
5. More extensive range of testing, including mock fit testing.
6. Better ase calculator of NVT and NPT dynamics.

What's Changed

• Average e0 by @davkovacs in #4
• Error tables by @davkovacs in #6
• make mace compatible with pytorch lightning by @felixmusil in #9
• Dipole MACE model by @davkovacs in #14
• small bug fix of compute_energy flag for model=MACE by @davkovacs in #16
• Enable per-config weight in mace data reading by @bernstei in #19
• bugfix. by @wcwitt in #28
• Changes required for LAMMPS integration by @wcwitt in #29
• Per config energy/forces/stress/virials weight by @bernstei in #22
• ASE Calculator stress by @bernstei in #26
• Change stress to Voigt notation by @vue1999 in #33
• add num_interactions for access from torchscript-ified models. by @wcwitt in #39
• stress tweaks. by @wcwitt in #49
• sort instructions in tp_out_irreps_with_instructions by @mariogeiger in #51
• torchscript tweaks. by @wcwitt in #50
• Update lammps_mace by @wcwitt in #55
• openmm-interop compatibility changes by @jharrymoore in #62
• SWA fixes and improvements by @davkovacs in #61
• update installation instructions in readme by @stenczelt in #56
• Weights and Biases support by @davkovacs in #70
• Debug and clean up evaluation code by @davkovacs in #72

New Contributors

• @davkovacs made their first contribution in #4
• @felixmusil made their first contribution in #9
• @bernstei made their first contribution in #19
• @wcwitt made their first contribution in #28
• @vue1999 made their first contribution in #33
• @mariogeiger made their first contribution in #51
• @jharrymoore made their first contribution in #62
• @stenczelt made their first contribution in #56

Full Changelog: https://github.com/ACEsuit/mace/commits/v0.2.0