Add files via upload

mace-bench/3rdparty/SevenNet/CHANGELOG.md

+# Changelog
+All notable changes to this project will be documented in this file.
+
+
+## [0.11.1]
+From here, the version of 'main' branch has 'devX' after it diverges from the latest stable version
+
+CLI interface changed in backward-compatible manner. Now `sevenn` has subcommands for
+inference, train, etc
+
+### Added
+- subcommand with some aliases
+- strict e3nn version requirement from __init__.py
+
+### Changed
+- pre-commit uses python3.11
+- cuequivaraiance optional libraries
+- some gitignores
+
+### Fixed
+- Circular import in sevenn.checkpoint (dev0)
+- Fix typing issues
+
+
+## [0.11.0]
+
+Multi-fidelity learning implemented & New pretrained-models
+
+### Added
+- Build multi-fidelity model, SevenNet-MF, based on given modality in the yaml
+- Modality support for sevenn_inference, sevenn_get_modal, and SevenNetCalculator
+- sevenn_cp tool for checkpoint summary, input generation, multi-modal routines
+- Modality append / assign using sevenn_cp
+- Loss weighting for energy, force and stress for corresponding data label
+- Ignore unlabelled data when calculating loss. (e.g. stress data for non-pbc structure)
+- Dict style dataset input for multi-modal and data-weight
+- (experimental) cuEquivariance support
+- Downloading large checkpoints from url (7net-MF-ompa, 7net-omat)
+- D3 wB97M param
+
+### Changed
+- Sort instructions of tensor product in convolution (+ fix flipped w3j coeff of old model)
+- Lazy initialization for `IrrepsLinear` and `SelfConnection*`
+- Checkpoint things using `sevenn/checkpoint.py`
+- e3nn >= 0.5.0, to ensure changed CG coeff later on
+- pandas as dependency
+- old v1 presets are removed, liquid electrolyte fine-tune yaml is added
+
+### Fixed
+- More refactor for shift scale things + few bug fixes
+- Correctly shuffle training set when distributed training is enabled
+- D3 calculator system swap memory error fixed
+- D3 compile uses $HOME/.cache if package directory is not writable
+
+
+## [0.10.4]
+### Added
+- feats: D3 calculator
+### Fixed
+- bug: info dict sharing (therefore energy stress) when structure_list used
+- torch >= 2.5.0 works
+- numpy >= 2.0 works (need more testing)
+### Changed
+- sevennet_calculator.py => calculator
+- fine tunine preset to use original loss function (Huber) and loss weights
+
+
+## [0.10.3]
+### Added
+- SevenNet-l3i5, checkpoint, preset. (keywords: 7net-l3i5, sevennet-l3i5)
+- SevenNet-l3i5 test
+### Changed
+- Now --help do not load unnecessary imports (fast!)
+- README
+
+
+## [0.10.2]
+### Added
+- Accelerated graph build routine if matscipy is installed  @hexagonerose
+- matscipy vs. ase neighborlist unit test
+- If valid set is not given but data_divide_ratio is given, validaset is created using random split. (shift, scale, and conv_denoiminator uses original whole statistics)
+### Changed
+- matscipy is included as dependency
+- data_divide_ration defaults to 0.0 (not used)
+### Fixed
+- For torch version >= 2.4.0, Loading graph dataset no more raises warnings.
+- Raise error when unknown element is found (SevenNetCalculator)
+
+## [0.10.1]
+### Added
+- experimental `SevenNetAtomsDataset` which is memory efficient, can be enabled with `dataset_type='atoms'`
+- Save meta data & statistics when the `SevenNetGraphDataset` saves its data.
+### Changed
+- Save checkpoint_0.pth (model before any training)
+- `SevenNetGraphDataset._file_to_graph_list` -> `SevenNetGraphDataset.file_to_graph_list`
+- Refactoring `SevenNetGraphDataset`, skips computing statistics if it is loaded, more detailed logging
+- Prefer use .get when accessing config dict
+### Fixed
+- Fix error when loading `SevenNetGraphDataset` with other types of data (ex: extxyz) in one dataset
+
+
+## [0.10.0]
+SevenNet now have CI workflows using pytest and its coverage is 78%!
+Substantial changes in cli apps and some outputs.
+
+### Added
+- [train_v2]: train_v2, with lots of refactoring + support `load_testset_path`. Original routine is accessible: `sevenn -m train_v1`.
+- [train_v2]: `SevenNetGraphDataset` replaces old `AtomGrpahDataset`, which extends `InMemoryDataset` of PyG.
+- [train_v2]: `sevenn_graph_build` for SevenNetGraphDataset. Previous .sevenn_data is accessible with --legacy option
+- [train_v2]: Any number of additional datasets will be evaluated and recorded if it is given as 'load_{NAME}set_path' key (input.yaml).
+- 'Univ' keyword for 'chemical_species'
+- energy_key, force_key, stress_key options for `sevenn_graph_build`, @thangckt
+- OpenMPI distributed training @thangckt
+### Changed
+- Read EFS of atoms from y_* keys of .info or .arrays dict, instead of caclculator results
+- Now `type_map` and requires_grad is hidden inside `AtomGraphSequential`, and don't need to care about it.
+- `log.sevenn` and `lc.csv` automatically find a safe filename (log0.sevenn, log1.sevenn, ...) to avoid overwriting.
+- [train_v2]: train_v2 loads its training set via `load_trainset_path`, rather than previous `load_dataset_path`.
+- [train_v2]: log.csv -> lc.csv, and columns have no units, (easier to postprocess with it) but still on `log.sevenn`.
+### Fixed
+- [e3gnn_serial]: can continue simulation even when atom tag becomes not consecutive (removing atom dynamically), @gasplant64
+- [e3gnn_parallel]: undefined behavior when there is no atoms to send/recv (for non pbc system)
+- [e3gnn_parallel]: incorrect force/stress in some edge cases (too small simulation cell & 2 process)
+- [e3gnn_parallel]: revert commit 14851ef, now e3gnn_parallel is sane.
+- [e3gnn_*]: += instead of = when saving virial stress and forces @gasplant64
+- Now Logger correctly closes a file.
+- ... and lots of small bugs I found during writing `pytest`.
+
+## [0.9.5]
+### Note
+This version is not stable, but I tag it as v0.9.5 before making further changes.
+LAMMPS `pair_e3gnn_parallel.*` should be re-compiled for the below changes regarding LAMMPS parallel.
+This is the first changelog and may not reflect all the changes.
+### Added
+- Stress compute for LAMMPS sevennet parallel
+- `sevenn_inference` now takes .extxyz input
+- `sevenn_inference` gives MAE error
+- Experimental `sevenn_inference` on the fly graph build option
+### Changed
+- **[Breaking]** Parallel LAMMPS model changed, old deployed parallel models will not work
+- **[Breaking]** Parallel LAMMPS takes the directory of potentials as input. Accordingly, `sevenn_get_model -p` creates a folder with potentials.
+- **[Breaking]** Except for serial LAMMPS models, force and stress are computed from gradients of edge vectors, not positions.
+- Separate interaction block from model build
+- Add typing for most of functions
+- Remove clang pre-commit hook as it breaks lammps pair files
+- `torch.load` with `weights_only=False`
+- Line length limit 80 -> 85
+- Refactor
+### Fixed
+- Correct batch size for SevenNet-0(11July2024)
+
+## [0.9.4] - 2024-08-26
+### Added
+- D3 correction (contributed from dambi3613) for LAMMPS serial

mace-bench/3rdparty/SevenNet/example_inputs/md_parallel_example/in.lmp

+#--------------------------- Simulation variables -----------------------------#
+
+  # Simulation control parameters.
+  variable          T equal 500
+
+  # Simulation steps (t_eq)
+  variable          t_eq equal 100
+  variable          output equal 1 #freq to print output
+  variable          dumpstep equal 1
+
+#------------------------------------------------------------------------------#
+
+
+#---------------------------- Atomic setup ------------------------------------#
+  units            metal
+  boundary         p p p
+  # Create atoms.
+  box tilt large
+  read_data        ./res.dat
+  replicate 2 2 2
+
+  # Define interatomic potential.
+  pair_style       e3gnn/parallel
+  # The order of element should be the same as the order of elements in the data file (type)
+  # * * {number of deployed parallel models} {path to deployed parallel models} {elements}
+  pair_coeff       * * 4 ./deployed_parallel Hf O
+
+  timestep         0.002
+
+#----------------------------- Run simulation ---------------------------------#
+
+    # Setup output
+    thermo          ${output}
+    thermo_style    custom step tpcpu pe ke vol press temp
+    dump            mydump all custom 1 dump.traj id type x y z fx fy fz
+    dump_modify     mydump sort id
+
+    fix f1 all nve
+    fix               comfix all momentum 1 linear 1 1 1
+    velocity        all create ${T} 1 dist gaussian mom yes
+
+    run 5
+
+#------------------------------------------------------------------------------#

mace-bench/3rdparty/SevenNet/example_inputs/md_parallel_example/res.dat

+# generated from poscar module             (Converted from VASP)
+
+96 atoms
+2 atom types
+
+0.00000000    10.12978631  xlo xhi
+0.00000000    10.37111894  ylo yhi
+0.00000000    10.26314330  zlo zhi
+
+   1.73035484    0.00000000    0.00000000  xy xz yz
+
+Masses
+
+1    178.490000
+2    16.000000
+
+Atoms
+
+   1    1  10.07858846   8.73752520   7.46334159
+   2    1   9.43739481   3.62108575   2.41757962
+   3    1   8.95522965   1.01658239   0.30135971
+   4    1  10.05681289   8.87631272   2.35008881
+   5    1   9.75638582   6.30304558   0.18303097
+   6    1   8.91443797   1.06674577   5.54199800
+   7    1   9.79081409   6.26490552   5.22104118
+   8    1   4.41792703   3.81788503   2.39528244
+   9    1   2.17257241   4.11562894   4.98715163
+  10    1   1.66417958   1.51957159   2.91326352
+  11    1   5.17465464   8.94063393   2.34565890
+  12    1   2.85135280   9.31925586   4.96912733
+  13    1   5.06412333   8.89798173   7.34081071
+  14    1   2.43171878   6.73610078   7.90086842
+  15    1   4.79358115   6.33415175   5.30470215
+  16    1   4.38083973   3.71776573   7.50514775
+  17    1   2.16740031   4.19218670  10.14985882
+  18    1   1.72740111   1.53804994   8.11741499
+  19    1   3.81409500   1.12760478   5.36341140
+  20    1   2.91124600   9.28502610  10.05473353
+  21    1   2.43508812   6.79222574   2.84272933
+  22    1   4.63828767   6.35818290   0.06495312
+  23    1   3.96862029   1.21993115   0.31149240
+  24    1   7.95945527   9.30919854   9.99874912
+  25    1   7.20953615   4.10124686  10.06760490
+  26    1   7.97413259   9.31020496   4.88564505
+  27    1   7.48292324   6.67094881   2.71417363
+  28    1   7.22354435   4.09214379   4.91151391
+  29    1   6.77110223   1.50790865   2.82107672
+  30    1   7.60040235   6.67278986   7.89547614
+  31    1   9.41001699   3.69515647   7.55969566
+  32    1   6.77374601   1.50559611   7.98091486
+  33    2  10.09033948   1.85325366   6.96757279
+  34    2  10.99511263   7.08138493   6.69600728
+  35    2  11.28967512   9.60939027   6.04904275
+  36    2  10.78802723   6.95960696   1.75182521
+  37    2   8.32036165   2.47159112   3.91830180
+  38    2  10.07211065   1.65854646   1.87162718
+  39    2  10.48460341   4.35174196   0.83957607
+  40    2   9.58543540  10.25525675   3.81736961
+  41    2   9.15581971   7.61785575   3.82383341
+  42    2  11.28280065   9.42551408   0.89622391
+  43    2  10.61871694   4.46990764   6.09305074
+  44    2   3.63623823   5.03045204   3.82116882
+  45    2   3.22065417   2.54566037   3.96054713
+  46    2   5.13228413   1.96508633   1.75400085
+  47    2   0.49972311   0.85950986   4.41955106
+  48    2   4.49795126  10.25514684   3.94724065
+  49    2   4.08831630   7.74684459   3.86494489
+  50    2   5.90127151   7.07173966   1.66530214
+  51    2   6.32939463   9.71904813   0.93714394
+  52    2   5.44334962   4.45855194   0.80863483
+  53    2   3.54898001   7.91810753   6.27738026
+  54    2   3.21454568   5.33370189   6.39780696
+  55    2   4.08744202   7.79255573   8.94430580
+  56    2   5.89610679   7.08975961   6.71713664
+  57    2   1.22356400   5.98776133   9.31853387
+  58    2   6.36149555   9.67586631   6.06078686
+  59    2   3.62496983   5.17884441   8.87967862
+  60    2   2.79091790   2.70312051   6.50630496
+  61    2   2.20642369   0.12199325   6.50943225
+  62    2   3.36642075   2.52335751   9.09596150
+  63    2   5.04873139   1.85222299   6.87617402
+  64    2   0.50463414   0.78101050   9.52304998
+  65    2   0.95275450   3.34556660   8.69553848
+  66    2   5.46251140   4.47527874   6.00302102
+  67    2   4.49817894  10.30428629   8.95760259
+  68    2   1.73952474   8.56368775   8.58555417
+  69    2   3.62337333   7.98128068   1.17332847
+  70    2   3.16118634   5.40721734   1.22906859
+  71    2   1.31418904   5.97276567   4.19215008
+  72    2   2.79848347   2.74889192   1.27175505
+  73    2   2.29397766   0.16984188   1.46074130
+  74    2   0.96707618   3.44188647   3.47135866
+  75    2   1.75476287   8.54415321   3.43405286
+  76    2   9.58968370  10.11019896   9.02264863
+  77    2   9.12010305   7.60109276   8.90873480
+  78    2   8.21690550   5.34991345   1.37662298
+  79    2   6.43083748   5.94959474   4.24019201
+  80    2   8.69454708   4.99651781   3.88811596
+  81    2   7.96833563   2.69478887   1.20584684
+  82    2   7.33313963   0.16345962   1.36457040
+  83    2   5.57830829   0.81411424   4.28350294
+  84    2   6.12969978   3.45445964   3.35501959
+  85    2   8.55281287   7.89834015   1.15270373
+  86    2   6.84047748   8.56744003   3.45602018
+  87    2   7.33002089   0.08127731   6.53509276
+  88    2   5.55795729   0.84809385   9.39286244
+  89    2   8.58051171   7.87084401   6.29048766
+  90    2   8.28348300   5.22136388   6.47631887
+  91    2   6.42127905   6.05984919   9.37655897
+  92    2   6.82699499   8.52585391   8.47852948
+  93    2   8.68865624   5.09200133   8.99426977
+  94    2   7.84842127   2.70204335   6.42490863
+  95    2   8.25796997   2.46457586   9.01312304
+  96    2   6.08861225   3.44495302   8.57088233