Hang Xiao, 肖航
Hang Xiao, 肖航
> I'm not sure whether this package be used to study nanocrystals. Any hints/comments will be helpful. > > Regards, Zhao Thank you for your inquiry about using our package...
> Hello, I am really thankful for your open sources about SLICES representations. I am really interested in SLICES representations and your paper. Here, I try to run "Tutorial_2_inverse_design_case_study.ipynb" in...
> Thank you so much for answering me carefully. I finished localinstallation and I try app.py for MatterGPT. But it shows like that. (I used raw_mp_20_dataset.csv. I think my installation...
> [`m3gnet`](https://github.com/xiaohang007/SLICES/blob/6da5d686610cf6c43d2199251fba99fbf4bcac84/setup.py#L31) is used by this package currently, but as noted [here](https://github.com/materialsvirtuallab/m3gnet?tab=readme-ov-file): > > > NOTE: A new implementation based on the Deep Graph Library and PyTorch called the [Materials...
> [`m3gnet`](https://github.com/xiaohang007/SLICES/blob/6da5d686610cf6c43d2199251fba99fbf4bcac84/setup.py#L31) is used by this package currently, but as noted [here](https://github.com/materialsvirtuallab/m3gnet?tab=readme-ov-file): > > > NOTE: A new implementation based on the Deep Graph Library and PyTorch called the [Materials...
> > Thank you for your suggestion. I have conducted an internal test on SLICES with matgl, and it turned out to be around 10x slower than the CHGNet implementation...
> Thank you for identifying the bug. I've resolved it by adding the following lines to ./data/mp20_nonmetal/workflow/0_run.pbs: > "export PATH=/opt/conda/bin:$PATH > source activate chgnet" > This activates the chgnet environment...
> Thank you for the update, but the issue in Tutorial 2.1 doesn't seem to be solved. The problem seems to originate in line 67 of the "1. building training...
> Hi, > > I wonder what's the GPU-based hardware requirement to run this package. Any tips will be helpful. > > Regards, Zhao For training MatterGPT models, a GPT-2...
> Thank you for your comments by providing the experience in model training. BTW, based on my understanding and knowledge, the 4090 is a gaming card, not a computing card....