-
**Submitting author:** @rohskopf (Andrew Rohskopf)
**Repository:** https://github.com/FitSNAP/FitSNAP
**Branch with paper.md** (empty if default branch):
**Version:** 3.0.1
**Editor:** @jmschrei
**Re…
-
微博内容精选
-
I have trained a NEP model on ~130 structures; the model itself seems fine for the most part, but the predicted energies are rather odd. A parity plot based on the contents of `energy_train.out` has b…
-
**Submitting author:** @LMMorgan (Lucy M. Morgan)
**Repository:** https://github.com/LMMorgan/PopOff
**Branch with paper.md** (empty if default branch):
**Version:** v1.0.0
**Editor:** @arfon
**Revie…
-
**Summary**
In the potential file `Au_u3.eam` that is shipped with LAMMPS, the cutoff value is inconsistent with the range of interatomic distance values: There are 500 data points with dr = 1.1212…
-
Hello,
We try to run ML-PACE in LAMMPS and ML-SNAP in LAMMPS. But we found out the ML-SNAP is faster than ML-PACE.
We use "Si" potential file to run simulation in LAMMPS.
LAMMPS version: 2021/…
-
There are a few (related) decisions to be made:
- ACEConfig vs just anything iterable
- do we distinguish site state from (i,j) pair state? The distinction is very natural in the context of interat…
-
Dear Developers,
I ran into a problem while training a test snap model.
The fact is that for a supercell smaller than 12 angstroms, everything is fine. And for a larger supercell, the correlation …
-
## 🐛 Bug
When using CSR sparse matrices and autograd, I get:
```
RuntimeError: Could not run 'aten::empty.memory_format' with arguments from the 'SparseCsrCUDA' backend.
```
## To Reproduce
…
-
Note I've decided in the end to start this package from scratch. IPFitting is too messy to fork from it. Instead my proposal it to maintain IPFitting purely for ACE v0.8 but focus all work for the lat…