Add torch-sim integration as a separate metatomic-torchsim package #167
Add torch-sim integration as a separate metatomic-torchsim package #167Luthaf merged 1 commit intometatensor:mainfrom
Conversation
|
Thanks @CompRhys! We had a chat about this 1h ago, and plan to create a separate metatomic-torchsim (and metatomic-ase, …) python package that would live in this repository but have a separate version number and release schedule. This might take us a couple of weeks to do, how urgent is getting this code out of torchsim for you? @HaoZeke in the mean time can you help bringing this PR in a state where it supports all the same features as the other engine integrations? |
In the same vein, @CompRhys, would you be OK with me making changes to this PR? I'd like to setup the python package first.
Yup, in the package 😁 |
|
Not urgent. We just cut a 0.5.2 release and so will be a while till we cut 0.5.3. Hopefully this could land in that release. The big switch also relies on there being new releases with the upstreamed interfaces for Please feel free to take this over or delete! |
|
We decided to drop support for StateDict, I am confused about why there are two implementations so removed it from both both lmk if there are any issues |
Sorry about that, the inline one should have been removed, since we now split into the standalone |
|
Thanks! look's great please let me know if there's anything I can help with. |
- Restructure as flat metatomic_torchsim package (no namespace shims) - Rename _calculator.py to _model.py (matches MetatomicModel class) - Convert all md docs to rst under docs/src/engines/ - Remove separate docs/ directory, wire into main doc toctree - Add version bounds: metatomic-torch >=0.1.11,<0.2, torch-sim >=0.5,<0.6 - Remove towncrier/tbump config (premature for unreleased package) - Update URLs to point to torch-sim engine docs - Inline test helpers into fixtures, convert _make_ni_atoms_2 to fixture - Update imports: metatomic.torchsim -> metatomic_torchsim - Remove **kwargs from AtomisticModel.save() (no purpose) - Update README: reference upet instead of pet-mad
- Restructure as flat metatomic_torchsim package (no namespace shims) - Rename _calculator.py to _model.py (matches MetatomicModel class) - Convert all md docs to rst under docs/src/engines/ - Remove separate docs/ directory, wire into main doc toctree - Add version bounds: metatomic-torch >=0.1.11,<0.2, torch-sim >=0.5,<0.6 - Remove towncrier/tbump config (premature for unreleased package) - Update URLs to point to torch-sim engine docs - Inline test helpers into fixtures, convert _make_ni_atoms_2 to fixture - Update imports: metatomic.torchsim -> metatomic_torchsim - Remove **kwargs from AtomisticModel.save() (no purpose) - Update README: reference upet instead of pet-mad
a4272d0 to
80e1b9c
Compare
a8cf071 to
b2b4f67
Compare
There was a problem hiding this comment.
Does this need to be in the user documentation? Or should we move it to dev docs (or even just MD or rst files next to the code?)
There was a problem hiding this comment.
Follow up later? We need to do a migration for the other packages, might as well standardize then.
There was a problem hiding this comment.
Sure, then I'll remove these files for now and we can add them back in the follow-up.
I'll keep a copy locally in addition to the git history.
There was a problem hiding this comment.
This should be turned into an example in here (https://github.com/metatensor/metatomic/tree/main/python/examples) I think
There was a problem hiding this comment.
This is a lot more verbose than the documentation we have for ASE ^_^. I'm not against it, but we need to think a bit how to show this.
- Remove support for loading .ckpt files directly - Remove 'pet-mad' shortcut (requires metatrain) - Update documentation to point users to upet for model export - Remove metatrain from optional dependencies Metatrain checkpoints should now be exported using upet before using with torchsim: pip install upet && upet export model.ckpt Addresses review comment from @Luthaf on PR metatensor#167
- Remove support for loading .ckpt files directly - Remove 'pet-mad' shortcut (required metatrain) - Update documentation to point users to upet for model export - Remove metatrain from optional dependencies Metatrain checkpoints should now be exported using upet before using with torchsim: pip install upet && upet export model.ckpt Addresses review comment from @Luthaf on PR metatensor#167
- Remove _memory_scales_with attribute (generic statement not needed) - Remove pytest tool options from pyproject.toml - Remove torchsim-docs tox environment (docs don't exist)
bc365b2 to
2500857
Compare
1d01bd8 to
f53ce49
Compare
|
thanks for the great work here guys! |
It will hold the TorchSim <=> metatomic integration as a standalone module. Co-Authored-By: Rhys Goodall <rhys.goodall@outlook.com> Co-Authored-By: Guillaume Fraux <guillaume.fraux@epfl.ch>
Move the torchsim model upstream.