deploy: e357091

_sources/autoapi/ocpmodels/common/index.rst

@@ -33,7 +33,6 @@ Submodules
    gp_utils/index.rst
    hpo_utils/index.rst
    logger/index.rst
-   model_registry/index.rst
    registry/index.rst
    transforms/index.rst
    tutorial_utils/index.rst

_sources/autoapi/ocpmodels/models/index.rst

@@ -28,6 +28,45 @@ Submodules
 
    base/index.rst
    dimenet_plus_plus/index.rst
+   model_registry/index.rst
    schnet/index.rst
 
 
+Package Contents
+----------------
+
+
+Functions
+~~~~~~~~~
+
+.. autoapisummary::
+
+   ocpmodels.models.model_name_to_local_file
+
+
+
+Attributes
+~~~~~~~~~~
+
+.. autoapisummary::
+
+   ocpmodels.models.available_pretrained_models
+
+
+.. py:data:: available_pretrained_models
+
+   
+
+.. py:function:: model_name_to_local_file(model_name: str, local_cache: str | pathlib.Path) -> str
+
+   Download a pretrained checkpoint if it does not exist already
+
+   :param model_name: the model name. See available_pretrained_checkpoints.
+   :type model_name: str
+   :param local_cache:
+   :type local_cache: str
+
+   Returns:
+
+
+

_sources/autoapi/ocpmodels/models/model_registry/index.rst

@@ -0,0 +1,49 @@
+:py:mod:`ocpmodels.models.model_registry`
+=========================================
+
+.. py:module:: ocpmodels.models.model_registry
+
+
+Module Contents
+---------------
+
+
+Functions
+~~~~~~~~~
+
+.. autoapisummary::
+
+   ocpmodels.models.model_registry.model_name_to_local_file
+
+
+
+Attributes
+~~~~~~~~~~
+
+.. autoapisummary::
+
+   ocpmodels.models.model_registry.MODEL_REGISTRY
+   ocpmodels.models.model_registry.available_pretrained_models
+
+
+.. py:data:: MODEL_REGISTRY
+
+   
+
+.. py:data:: available_pretrained_models
+
+   
+
+.. py:function:: model_name_to_local_file(model_name: str, local_cache: str | pathlib.Path) -> str
+
+   Download a pretrained checkpoint if it does not exist already
+
+   :param model_name: the model name. See available_pretrained_checkpoints.
+   :type model_name: str
+   :param local_cache:
+   :type local_cache: str
+
+   Returns:
+
+
+

_sources/core/INSTALL.md

@@ -1,4 +1,24 @@
-## Installation
+# Installation
+
+## pip (fast, easy to get started)
+
+Installing the OCP package and necessary dependencies is now as easy as:
+
+(GPU)
+```
+pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu117
+pip install pyg_lib torch_scatter torch_sparse -f https://data.pyg.org/whl/torch-1.13.1+cu117.html
+pip install -i https://test.pypi.org/simple/ ocp-models
+```
+
+or if you want the CPU-only install (no cuda/etc):
+```
+pip install torch==1.13.1 torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu # install CPU torch
+pip install pyg_lib torch_scatter torch_sparse -f https://data.pyg.org/whl/torch-1.13.1+cpu.html
+pip install -i https://test.pypi.org/simple/ ocp-models
+```
+
+## Conda (preferred for model training & development)
 
 - We'll use `conda` to install dependencies and set up the environment.
 We recommend using the [Python 3.9 Miniconda installer](https://docs.conda.io/en/latest/miniconda.html#linux-installers).

_sources/core/QUICKSTART.md

@@ -0,0 +1,55 @@
+---
+jupytext:
+  text_representation:
+    extension: .md
+    format_name: myst
+    format_version: 0.13
+    jupytext_version: 1.16.1
+kernelspec:
+  display_name: Python 3 (ipykernel)
+  language: python
+  name: python3
+---
+
+Quickstart simulation using pre-trained models
+----------
+
+1. First, install OCP in a fresh python environment using one of the approaches in [installation documentation](INSTALL).
+2. See what pre-trained potentials are available 
+```{code-cell} ipython3
+from ocpmodels.models.model_registry import available_pretrained_models
+print(available_pretrained_models)
+```
+3. Choose a checkpoint you want to use and download it automatically! We'll use the GemNet-OC potential, trained on both the OC20 and OC22 datasets.
+```{code-cell} ipython3
+from ocpmodels.models.model_registry import model_name_to_local_file
+checkpoint_path = model_name_to_local_file('GemNet-OC OC20+OC22', local_cache='/tmp/ocp_checkpoints/')
+checkpoint_path
+```
+4. Finally, use this checkpoint in an ASE calculator for a simple relaxation!
+```
+from ocpmodels.common.relaxation.ase_utils import OCPCalculator
+from ase.build import fcc111, add_adsorbate
+from ase.optimize import BFGS
+import matplotlib.pyplot as plt
+from ase.visualize.plot import plot_atoms
+
+# Define the model atomic system, a Pt(111) slab with an *O adsorbate!
+slab = fcc111('Pt', size=(2, 2, 5), vacuum=10.0)
+add_adsorbate(slab, 'O', height=1.2, position='fcc')
+
+# Load the pre-trained checkpoint!
+calc = OCPCalculator(checkpoint_path=checkpoint_path, cpu=False)
+slab.set_calculator(calc)
+
+# Run the optimization!
+opt = BFGS(slab)
+opt.run(fmax=0.05, steps=100)
+
+# Visualize the result!
+fig, axs = plt.subplots(1, 2)
+plot_atoms(slab, axs[0]);
+plot_atoms(slab, axs[1], rotation=('-90x'))
+axs[0].set_axis_off()
+axs[1].set_axis_off()
+```