You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* Update README.md with logo and badge enhancements
* Enhance README.md with new section headers and improved formatting
* Improve formatting in README.md for better readability
DeePTB is an innovative Python package that uses deep learning to accelerate *ab initio* electronic structure simulations. It offers versatile, accurate, and efficient simulations for a wide range of materials and phenomena. Trained on small systems, DeePTB can predict electronic structures of large systems, handle structural perturbations, and integrate with molecular dynamics for finite temperature simulations, providing comprehensive insights into atomic and electronic behavior.
9
24
10
-
11
-
#### Key Features:
25
+
-**Key Features**
12
26
DeePTB contains two main components:
13
-
1.**DeePTB-SK**: deep learning based local environment dependent Slater-Koster TB.
14
-
- Customizable Slater-Koster parameterization with neural network corrections for .
15
-
- Flexible basis and exchange-correlation functional choices.
16
-
- Handle systems with strong spin-orbit coupling (SOC) effects.
27
+
1.**DeePTB-SK**: deep learning based local environment dependent Slater-Koster TB.
28
+
- Customizable Slater-Koster parameterization with neural network corrections for .
29
+
- Flexible basis and exchange-correlation functional choices.
30
+
- Handle systems with strong spin-orbit coupling (SOC) effects.
17
31
18
-
1.**DeePTB-E3**: E3-equivariant neural networks for representing quantum operators.
19
-
- Construct DFT Hamiltonians/density and overlap matrices under full LCAO basis.
20
-
- Utilize (**S**trictly) **L**ocalized **E**quivariant **M**essage-passing (**(S)LEM**) model for high data-efficiency and accuracy.
21
-
- Employs SO(2) convolution for efficient handling of higher-order orbitals in LCAO basis.
32
+
2.**DeePTB-E3**: E3-equivariant neural networks for representing quantum operators.
33
+
- Construct DFT Hamiltonians/density and overlap matrices under full LCAO basis.
34
+
- Utilize (**S**trictly) **L**ocalized **E**quivariant **M**essage-passing (**(S)LEM**) model for high data-efficiency and accuracy.
35
+
- Employs SO(2) convolution for efficient handling of higher-order orbitals in LCAO basis.
22
36
23
37
24
38
For more details, see our papers:
@@ -27,49 +41,50 @@ For more details, see our papers:
27
41
28
42
29
43
30
-
## Installation
44
+
## 🛠️ Installation
31
45
32
46
Installing **DeePTB** is straightforward. We recommend using a virtual environment for dependency management.
33
47
34
-
### Requirements
35
-
- Python 3.8 or later.
36
-
- Torch 1.13.0 or later ([PyTorch Installation](https://pytorch.org/get-started/locally)).
37
-
- ifermi (optional, for 3D fermi-surface plotting).
38
-
39
-
### Installation Steps
40
-
41
-
#### Using PyPi
42
-
1. Ensure you have Python 3.8 or later and Torch installed.
2. Navigate to the root directory and install DeePTB:
67
+
```bash
68
+
cd DeePTB
69
+
pip install .
70
+
```
71
+
72
+
## 📚 Documentation
73
+
74
+
- **Online documentation**
75
+
76
+
For a comprehensive guide and usage tutorials, visit [our documentation website](https://deeptb.readthedocs.io/en/latest/).
62
77
78
+
- **Community**
63
79
64
-
## Community
80
+
DeePTB joins the DeepModeling community, a community devoted of AI for science, as an incubating level project. To learn more about the DeepModeling community, see the [introduction of community](https://github.com/deepmodeling/community).
65
81
66
-
**DeePTB** joins the DeepModeling community, a community devoted of AI for science, as an incubating level project. To learn more about the DeepModeling community, see the [introduction of community](https://github.com/deepmodeling/community).
82
+
- **Contributing**
67
83
68
-
## Contributing
69
-
We welcome contributions to **DeePTB**. Please refer to our [contributing guidelines](https://deeptb.readthedocs.io/en/latest/community/contribution_guide.html) for details.
84
+
We welcome contributions to DeePTB. Please refer to our [contributing guidelines](https://deeptb.readthedocs.io/en/latest/community/contribution_guide.html) for details.
70
85
71
86
72
-
## How to Cite
87
+
## 🤝 How to Cite
73
88
74
89
The following references are required to be cited when using DeePTB. Specifically:
0 commit comments