Doc: update docs and tutorial

README.md

@@ -1,8 +1,10 @@
+<h1>
 <p align="center">
-    <img src="docs/_static/mattersim.png" alt="MatterSim logo" width="200"/>
+    <img src="docs/_static/mattersim-banner.jpg" alt="MatterSim logo" width="600"/>
 </p>
+</h1>
 
-<h1 align="center">MatterSim</h1>
+<!-- <h1 align="center">MatterSim</h1> -->
 
 <h4 align="center">
 

docs/examples/relax_example.rst

@@ -10,8 +10,10 @@ Import the necessary modules
 
     import numpy as np
     from ase.build import bulk
+    from ase.units import GPa
     from mattersim.forcefield.potential import Potential
     from mattersim.forcefield.potential import DeepCalculator
+    from mattersim.applications.relax import Relaxer
 
 Set up the structure to relax
 -----------------------------
@@ -28,12 +30,24 @@ Set up the structure to relax
     potential = Potential.load(load_path="/path/to/checkpoint", device="cuda:0")
 
     # create a calculator from the model
-    calculator = DeepCalculator(potential=potential)
+    calc = DeepCalculator(potential=potential, stress_weight=GPa)
 
     # attach the calculator to the atoms object
-    si.calc = calculator
+    si.calc = calc
 
-Create the optimizer
+Run the relaxation
 --------------------
 
 MatterSim implements a built-in relaxation class to support the relaxation of ase atoms.
+
+.. code-block:: python
+
+    # initialize the relaxation object
+    relaxer = Relaxer(
+        optimizer="BFGS", # the optimization method
+        filter="ExpCellFilter", # filter to apply to the cell
+        constrain_symmetry=True, # whether to constrain the symmetry
+    )
+
+    relaxed_structure = relaxer.run(si, steps=500)
+

docs/index.rst

@@ -23,8 +23,8 @@ Pre-trained Models
 
 We currently offer two pre-trained versions of MatterSim with **M3GNet** architecture:
 
-1. **mattersim-mini-v1.0.0**: A mini version of the model that is faster to run. 
-2. **mattersim-medium-v1.0.0**: A medium version of the model that is more accurate.
+1. **mattersim-v1.0.0-1M**: A mini version of the model that is faster to run. 
+2. **mattersim-v1.0.0-5M**: A medium version of the model that is more accurate.
 
 These models have been trained using the data generated through the workflows 
 introduced in the `MatterSim <https://arxiv.org/abs/2405.04967>`_ manuscript, which provides an in-depth 

docs/user_guide/getting_started.rst

@@ -40,6 +40,7 @@ MatterSim provides an interface to the Atomic Simulation Environment (ASE) to fa
     :linenos:
 
     from ase.build import bulk
+    from ase.units import GPa
     from mattersim.forcefield.potential import DeepCalculator
 
     # same as before
@@ -50,7 +51,7 @@ MatterSim provides an interface to the Atomic Simulation Environment (ASE) to fa
     calculator = DeepCalculator(
         potential=potential,
         # important! convert GPa to eV/Angstrom^3
-        stress_weight=1 / 160.21766208,
+        stress_weight=GPa,
     )
 
     si.calc = calculator

docs/user_guide/installation.rst

@@ -8,7 +8,6 @@ Install from source code
 Requirements:
 
 * Python == 3.9
-* PyTorch == 1.11.0
 
 To install the package, run the following command under the root of the folder: