From e6ff351cca2dc12a88a507c50355467aa7aca7b4 Mon Sep 17 00:00:00 2001 From: hexagonrose Date: Thu, 19 Dec 2024 10:58:45 +0900 Subject: [PATCH 1/3] Update README.md: tutorial --- README.md | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/README.md b/README.md index 3433c6e..b83a818 100644 --- a/README.md +++ b/README.md @@ -60,6 +60,7 @@ In addition to these latest models, you can find our legacy models from [pretrai - [Usage](#usage) - [ASE calculator](#ase-calculator) - [Training & inference](#training-and-inference) + - [Tutorials](#tutorial) - [MD simulation with LAMMPS](#md-simulation-with-lammps) - [Installation](#installation) - [Single-GPU MD](#single-gpu-md) @@ -183,6 +184,14 @@ sevenn_get_model {checkpoint path} -p This will create a directory with multiple `deployed_parallel_*.pt` files. The directory path itself is an argument for the lammps script. Please do not modify or remove files under the directory. These models can be used as lammps potential to run parallel MD simulations with GNN potential using multiple GPU cards. +### Tutorials +| Notebooks | Google Colab | Descriptions | +|-----------|-------------------|--------------| +|[Python tutorial](https://github.com/MDIL-SNU/sevennet_tutorial/blob/main/notebooks/SevenNet_python_tutorial.ipynb)|[![Open in Google Colab]](https://colab.research.google.com/github/MDIL-SNU/sevennet_tutorial/blob/main/notebooks/SevenNet_python_tutorial.ipynb)|We can learn how to train the SevenNet, predict energy, forces, and stress using the trained model, perform structure relaxation, and draw EOS curves.| +|[Fine-tuning](https://github.com/MDIL-SNU/sevennet_tutorial/blob/main/notebooks/SevenNet_finetune_tutorial.ipynb)|[![Open in Google Colab]](https://colab.research.google.com/github/MDIL-SNU/sevennet_tutorial/blob/main/notebooks/SevenNet_finetune_tutorial.ipynb)|We can learn how to fine-tune the SevenNet and compare the results of the pretrained model with the fine-tuned model.| + +[Open in Google Colab]: https://colab.research.google.com/assets/colab-badge.svg + ### MD simulation with LAMMPS #### Installation From 24689f2ba7ff851e19fbd6f464ba1ea0b76a93e9 Mon Sep 17 00:00:00 2001 From: hexagonrose Date: Thu, 19 Dec 2024 11:06:36 +0900 Subject: [PATCH 2/3] Update README.md: tutorial --- README.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/README.md b/README.md index b83a818..a9dc67e 100644 --- a/README.md +++ b/README.md @@ -192,6 +192,11 @@ These models can be used as lammps potential to run parallel MD simulations with [Open in Google Colab]: https://colab.research.google.com/assets/colab-badge.svg +Sometimes, the Colab environment may crash due to memory issues. If you have good GPU resources in your local environment, it is recommended to download the tutorial from GitHub and run it locally. +```bash +git clone https://github.com/MDIL-SNU/sevennet_tutorial.git +``` + ### MD simulation with LAMMPS #### Installation From 742ffb43a30151d8cb29fdc98ff0fd9bf87b1c84 Mon Sep 17 00:00:00 2001 From: hexagonrose Date: Thu, 19 Dec 2024 11:10:54 +0900 Subject: [PATCH 3/3] Update README.md: tutorial --- README.md | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index a9dc67e..ec4a779 100644 --- a/README.md +++ b/README.md @@ -60,7 +60,7 @@ In addition to these latest models, you can find our legacy models from [pretrai - [Usage](#usage) - [ASE calculator](#ase-calculator) - [Training & inference](#training-and-inference) - - [Tutorials](#tutorial) + - [Notebook tutorials](#notebook-tutorial) - [MD simulation with LAMMPS](#md-simulation-with-lammps) - [Installation](#installation) - [Single-GPU MD](#single-gpu-md) @@ -184,10 +184,13 @@ sevenn_get_model {checkpoint path} -p This will create a directory with multiple `deployed_parallel_*.pt` files. The directory path itself is an argument for the lammps script. Please do not modify or remove files under the directory. These models can be used as lammps potential to run parallel MD simulations with GNN potential using multiple GPU cards. -### Tutorials +### Notebook tutorials + +If you want to learn how to use the `sevenn` python library instead of the CLI command, please check out the notebook tutorials below. + | Notebooks | Google Colab | Descriptions | |-----------|-------------------|--------------| -|[Python tutorial](https://github.com/MDIL-SNU/sevennet_tutorial/blob/main/notebooks/SevenNet_python_tutorial.ipynb)|[![Open in Google Colab]](https://colab.research.google.com/github/MDIL-SNU/sevennet_tutorial/blob/main/notebooks/SevenNet_python_tutorial.ipynb)|We can learn how to train the SevenNet, predict energy, forces, and stress using the trained model, perform structure relaxation, and draw EOS curves.| +|[From scratch](https://github.com/MDIL-SNU/sevennet_tutorial/blob/main/notebooks/SevenNet_python_tutorial.ipynb)|[![Open in Google Colab]](https://colab.research.google.com/github/MDIL-SNU/sevennet_tutorial/blob/main/notebooks/SevenNet_python_tutorial.ipynb)|We can learn how to train the SevenNet from scratch, predict energy, forces, and stress using the trained model, perform structure relaxation, and draw EOS curves.| |[Fine-tuning](https://github.com/MDIL-SNU/sevennet_tutorial/blob/main/notebooks/SevenNet_finetune_tutorial.ipynb)|[![Open in Google Colab]](https://colab.research.google.com/github/MDIL-SNU/sevennet_tutorial/blob/main/notebooks/SevenNet_finetune_tutorial.ipynb)|We can learn how to fine-tune the SevenNet and compare the results of the pretrained model with the fine-tuned model.| [Open in Google Colab]: https://colab.research.google.com/assets/colab-badge.svg