OneScience-Group
/

MACE

machine-learning-potential

molecular-simulation

materials-computing

graph-neural-network

equivariant-neural-network

Model card Files Files and versions

dadadaxi commited on about 1 month ago

Commit

76436d6

·

verified ·

1 Parent(s): 9281c5c

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -72,7 +72,7 @@ Try intelligent, one-click AI4S programming in the OneCode online environment:
 ### Download the Model Package
 ```bash
-hf download --model OneScience-Group/MACE --local-dir ./mace
 cd mace
 ```
@@ -103,7 +103,7 @@ pip install onescience[matchem-gpu] -i http://mirrors.onescience.ai:3141/pypi/si
 Training data is not bundled with this repository. Using the introductory DMC dataset as an example, download it from Hugging Face to `data/` in the repository root:
 ```bash
-hf download --dataset OneScience-Group/DMC --local-dir ./data
 ```
 After downloading, the data is located at `data/data/DMC/`. `scripts/demo/run.sh` automatically sets the repository root as `ONESCIENCE_DATASETS_DIR`, so you do not need to set this variable manually for the paths in the configuration file to resolve.

 ### Download the Model Package
 ```bash
+hf download OneScience-Group/MACE
 cd mace
 ```
 Training data is not bundled with this repository. Using the introductory DMC dataset as an example, download it from Hugging Face to `data/` in the repository root:
 ```bash
+hf download OneScience-Group/DMC --repo-type dataset
 ```
 After downloading, the data is located at `data/data/DMC/`. `scripts/demo/run.sh` automatically sets the repository root as `ONESCIENCE_DATASETS_DIR`, so you do not need to set this variable manually for the paths in the configuration file to resolve.