diff --git a/_sources/autoapi/ocpmodels/common/index.rst b/_sources/autoapi/ocpmodels/common/index.rst
index 20d96be2c..df4749a65 100644
--- a/_sources/autoapi/ocpmodels/common/index.rst
+++ b/_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
diff --git a/_sources/autoapi/ocpmodels/common/model_registry/index.rst b/_sources/autoapi/ocpmodels/common/model_registry/index.rst
deleted file mode 100644
index f6efc71c4..000000000
--- a/_sources/autoapi/ocpmodels/common/model_registry/index.rst
+++ /dev/null
@@ -1,34 +0,0 @@
-:py:mod:`ocpmodels.common.model_registry`
-=========================================
-
-.. py:module:: ocpmodels.common.model_registry
-
-
-Module Contents
----------------
-
-
-Functions
-~~~~~~~~~
-
-.. autoapisummary::
-
- ocpmodels.common.model_registry.model_name_to_local_file
-
-
-
-Attributes
-~~~~~~~~~~
-
-.. autoapisummary::
-
- ocpmodels.common.model_registry.MODEL_REGISTRY
-
-
-.. py:data:: MODEL_REGISTRY
-
-
-
-.. py:function:: model_name_to_local_file(model_name: str, local_cache: str) -> str | None
-
-
diff --git a/_sources/autoapi/ocpmodels/models/index.rst b/_sources/autoapi/ocpmodels/models/index.rst
index 51c7291ea..d2c6d2d40 100644
--- a/_sources/autoapi/ocpmodels/models/index.rst
+++ b/_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:
+
+
+
diff --git a/_sources/autoapi/ocpmodels/models/model_registry/index.rst b/_sources/autoapi/ocpmodels/models/model_registry/index.rst
new file mode 100644
index 000000000..3ddf1db32
--- /dev/null
+++ b/_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:
+
+
+
diff --git a/_sources/core/INSTALL.md b/_sources/core/INSTALL.md
index 04df9863f..9602f5e95 100644
--- a/_sources/core/INSTALL.md
+++ b/_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).
diff --git a/_sources/core/QUICKSTART.md b/_sources/core/QUICKSTART.md
new file mode 100644
index 000000000..fee7abfac
--- /dev/null
+++ b/_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()
+```
\ No newline at end of file
diff --git a/_sources/core/datasets/oc20.md b/_sources/core/datasets/oc20.md
index 72de8cbc3..eaea373fe 100644
--- a/_sources/core/datasets/oc20.md
+++ b/_sources/core/datasets/oc20.md
@@ -331,87 +331,83 @@ Please consider citing the following paper in any research manuscript using the
## Per-adsorbate trajectories
-
-Download links are in the table below:
-
-|Adsorbate symbol |Downloadable path |size |MD5 checksum |
-|--- |--- |--- |--- |
-|*O |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/0.tar |1006M |d4151542856b4b6405f276808f75358a |
-|*H |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/1.tar |850M |3697f04faf04251a23da8b88a78209f7 |
-|*OH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/2.tar |1.6G |a21081f3f55eb0c98a91021bbe3dac44 |
-|*OH2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/3.tar |1.8G |b12b706854f5d899e02a9ae6578b5d45 |
-|*C |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/4.tar |1.1G |e4fe9890764fcf59e01e3ceab089b978 |
-|*CH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/6.tar |1.4G |ec9aa2c4c4bd4419359438ba7fbb881d |
-|*CHO |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/7.tar |1.4G |d32200f74ad5c3bfd42e8835f36d57ab |
-|*COH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/8.tar |1.6G |5418a1b331f6c7689a5405cca4cc8d15 |
-|*CH2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/9.tar |1.6G |8ee1066149c305d7c17c219b369c5a73 |
-|*CH2*O |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/10.tar |1.7G |960c2450814024b66f3c79121179ac60 |
-|*CHOH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/11.tar |1.8G |60ac9f965f9589a3389483e3d1e58144 |
-|*CH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/12.tar |1.7G |7e123e6f4fb10d6897be3f47721dfd4a |
-|*OCH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/13.tar |1.8G |0823047bbbe05fa0e63f9d83ec601487 |
-|*CH2OH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/14.tar |1.9G |9ac71e198d75b1427182cd34abb73e4d |
-|*CH4 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/15.tar |1.9G |a405ce403018bf8afbd4425d5c0b34d5 |
-|*OHCH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/16.tar |2.1G |d3c829f1952db6e4f428273ee05f59b1 |
-|*C*C |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/17.tar |1.5G |d687a151345305897b9245af4b0f9967 |
-|*CCO |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/18.tar |1.7G |214ca96e620c5ec6e8a6ff8144a22a04 |
-|*CCH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/19.tar |1.6G |da2268545e80ca1664026449dd2fdd24 |
-|*CHCO |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/20.tar |1.7G |386c99407fe63080d26cda525dfdd8cd |
-|*CCHO |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/21.tar |1.8G |918b20960438494ab160a9dbd9668157 |
-|*COCHO |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/22.tar |1.8G |84424aa2ad30301e23ece1438ea39923 |
-|*CCHOH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/23.tar |2.0G |3cc90425ec042a70085ba7eb2916a79a |
-|*CCH2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/24.tar |1.8G |9dbcf7566e40965dd7f8a186a75a718e |
-|*CH*CH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/25.tar |1.7G |a193b4c72f915ba0b21a41790696b23c |
-|CH2*CO |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/26.tar |1.8G |de83cf50247f5556fa4f9f64beff1eeb |
-|*CHCHO |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/27.tar |1.9G |1d140aaa2e7b287124ab38911a711d70 |
-|*CH*COH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/28.tar |1.3G |682d8a6b05ca5948b34dc5e5f6bbcd61 |
-|*COCH2O |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/29.tar |1.9G |c8742faa8ca40e8edb4110069817fa70 |
-|*CHO*CHO |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/30.tar |2.0G |8cfbb67beb312b98c40fcb891dfa480a |
-|*COHCHO |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/31.tar |1.9G |6ffa903a62d8ec3319ecec6a03b06276 |
-|*COHCOH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/32.tar |2.0G |caca0058b641bfdc9f8de4527e60feb7 |
-|*CCH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/33.tar |1.8G |906543aaefc171edab388ff4f0fe8a20 |
-|*CHCH2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/34.tar |1.8G |4dfab479495f76179749c1956046fbd8 |
-|*COCH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/35.tar |1.9G |29d1b992715054e920e8bb2afe97b393 |
-|*CHCHOH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/38.tar |2.0G |9e5912df6f7b11706d1046cdb9e3087e |
-|*CCH2OH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/39.tar |2.1G |7bcae43cee451306e34ec416588a7f09 |
-|*CHOCHOH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/40.tar |2.0G |f98866d08fe3451ae7ebc47bb51599aa |
-|*COCH2OH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/41.tar |1.4G |bfaf689e5827fcf26c51e567bb8dd1be |
-|*COHCHOH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/42.tar |2.0G |236fe4e950aa2fbdde94ef2821fb48d2 |
-|*OCHCH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/44.tar |2.1G |66acc5460a999625c3364f0f3bcca871 |
-|*COHCH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/45.tar |2.1G |bb4a01956736399c8cee5e219f8c1229 |
-|*CHOHCH2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/46.tar |2.1G |e836de4ec146b1b611533f1ef682cace |
-|*CHCH2OH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/47.tar |2.0G |66df44121806debef6dc038df7115d1d |
-|*OCH2CHOH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/48.tar |2.2G |ff6981fdbcd2e65d351505c15d218d76 |
-|*CHOCH2OH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/49.tar |2.1G |448f7d352ab6e32f754e24de64ca302a |
-|*COHCH2OH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/50.tar |2.1G |8bff6bf3e10cc84acc4a283a375fcc23 |
-|*CHOHCHOH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/51.tar |2.0G |9c9e4d617d306751760a80f1453e71f1 |
-|*CH2CH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/52.tar |2.0G |ec1e964d2ee6f468fa5773743e3994a4 |
-|*OCH2CH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/53.tar |2.1G |d297b27b02822f9b6af80bdb64aee819 |
-|*CHOHCH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/54.tar |2.1G |368de083dafdc3bbdb560d35e2a102c0 |
-|*CH2CH2OH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/55.tar |2.1G |3c1aaf790659f7ff89bf1eed8b396b63 |
-|*CHOHCH2OH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/56.tar |2.2G |2d71adb9e305e6f3bca49e5df9b5a86a |
-|*OHCH2CH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/57.tar |2.3G |cf51128f8522b7b66fc68d79980d6def |
-|*NH2N(CH3)2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/58.tar |1.6G |36ba974d80c20ff636431f7c0ad225da |
-|*ONN(CH3)2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/59.tar |2.3G |fdc4cd19977496909d61be4aee61c4f1 |
-|*OHNNCH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/60.tar |2.1G |50a6ff098f9ba7adbba9ac115726cc5a |
-|*ONH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/62.tar |1.8G |47573199c545afe46c554ff756c3e38f |
-|*NHNH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/63.tar |1.7G |dd456b7e19ef592d9f0308d911b91d7c |
-|*N*NH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/65.tar |1.6G |c05289fd56d64c74306ebf57f1061318 |
-|*NO2NO2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/67.tar |2.1G |4822a06f6c5f41bdefd3cbbd8856c11f |
-|*N*NO |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/68.tar |1.6G |2a27de122d32917cc5b6ac0a21c63c1c |
-|*N2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/69.tar |1.5G |cc668fecf679b6edaac8fd8fb9cdd404 |
-|*ONNH2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/70.tar |2.1G |dff880f1a5baa7f67b52fd3ed745443d |
-|*NH2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/71.tar |1.6G |c7f383b50faa6244e265c9611466cb8f |
-|*NH3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/72.tar |1.9G |2b355741f9300445703270e0e4b8c01c |
-|*NONH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/73.tar |1.8G |48877a0c6f2994baac82cb722711aaa2 |
-|*NH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/74.tar |1.4G |7979b9e7ab557d6979b33e352486f0ef |
-|*NO2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/75.tar |1.7G |9f352fbc32bb2b8caf4788aba28b2eb7 |
-|*NO |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/76.tar |1.4G |482ee306a5ae2eee78cac40d10059ebc |
-|*N |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/77.tar |1.1G |bfb6e03d4a687987ff68976f0793cc46 |
-|*NO3 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/78.tar |1.8G |700834326e789a6e38bf3922d9fcb792 |
-|*OHNH2 |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/79.tar |2.1G |fa24472e0c02c34d91f3ffe6b77bfb11 |
-|*ONOH |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/80.tar |1.4G |4ddcccd62a834a76fe6167461f512529 |
-|*CN |https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/81.tar |1.5G |bc7c55330ece006d09496a5ff01d5d50 |
-
+|Adsorbate symbol |Size |MD5 checksum (download link) |
+|--- |--- |--- |
+|*O |1006M |[d4151542856b4b6405f276808f75358a](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/0.tar) |
+|*H |850M |[3697f04faf04251a23da8b88a78209f7](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/1.tar) |
+|*OH |1.6G |[a21081f3f55eb0c98a91021bbe3dac44](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/2.tar) |
+|*OH2 |1.8G |[b12b706854f5d899e02a9ae6578b5d45](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/3.tar) |
+|*C |1.1G |[e4fe9890764fcf59e01e3ceab089b978](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/4.tar) |
+|*CH |1.4G |[ec9aa2c4c4bd4419359438ba7fbb881d](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/6.tar) |
+|*CHO |1.4G |[d32200f74ad5c3bfd42e8835f36d57ab](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/7.tar) |
+|*COH |1.6G |[5418a1b331f6c7689a5405cca4cc8d15](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/8.tar) |
+|*CH2 |1.6G |[8ee1066149c305d7c17c219b369c5a73](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/9.tar) |
+|*CH2*O |1.7G |[960c2450814024b66f3c79121179ac60](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/10.tar) |
+|*CHOH |1.8G |[60ac9f965f9589a3389483e3d1e58144](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/11.tar) |
+|*CH3 |1.7G |[7e123e6f4fb10d6897be3f47721dfd4a](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/12.tar) |
+|*OCH3 |1.8G |[0823047bbbe05fa0e63f9d83ec601487](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/13.tar) |
+|*CH2OH |1.9G |[9ac71e198d75b1427182cd34abb73e4d](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/14.tar) |
+|*CH4 |1.9G |[a405ce403018bf8afbd4425d5c0b34d5](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/15.tar) |
+|*OHCH3 |2.1G |[d3c829f1952db6e4f428273ee05f59b1](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/16.tar) |
+|*C*C |1.5G |[d687a151345305897b9245af4b0f9967](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/17.tar) |
+|*CCO |1.7G |[214ca96e620c5ec6e8a6ff8144a22a04](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/18.tar) |
+|*CCH |1.6G |[da2268545e80ca1664026449dd2fdd24](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/19.tar) |
+|*CHCO |1.7G |[386c99407fe63080d26cda525dfdd8cd](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/20.tar) |
+|*CCHO |1.8G |[918b20960438494ab160a9dbd9668157](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/21.tar) |
+|*COCHO |1.8G |[84424aa2ad30301e23ece1438ea39923](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/22.tar) |
+|*CCHOH |2.0G |[3cc90425ec042a70085ba7eb2916a79a](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/23.tar) |
+|*CCH2 |1.8G |[9dbcf7566e40965dd7f8a186a75a718e](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/24.tar) |
+|*CH*CH |1.7G |[a193b4c72f915ba0b21a41790696b23c](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/25.tar) |
+|CH2*CO |1.8G |[de83cf50247f5556fa4f9f64beff1eeb](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/26.tar) |
+|*CHCHO |1.9G |[1d140aaa2e7b287124ab38911a711d70](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/27.tar) |
+|*CH*COH |1.3G |[682d8a6b05ca5948b34dc5e5f6bbcd61](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/28.tar) |
+|*COCH2O |1.9G |[c8742faa8ca40e8edb4110069817fa70](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/29.tar) |
+|*CHO*CHO |2.0G |[8cfbb67beb312b98c40fcb891dfa480a](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/30.tar) |
+|*COHCHO |1.9G |[6ffa903a62d8ec3319ecec6a03b06276](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/31.tar) |
+|*COHCOH |2.0G |[caca0058b641bfdc9f8de4527e60feb7](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/32.tar) |
+|*CCH3 |1.8G |[906543aaefc171edab388ff4f0fe8a20](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/33.tar) |
+|*CHCH2 |1.8G |[4dfab479495f76179749c1956046fbd8](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/34.tar) |
+|*COCH3 |1.9G |[29d1b992715054e920e8bb2afe97b393](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/35.tar) |
+|*CHCHOH |2.0G |[9e5912df6f7b11706d1046cdb9e3087e](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/38.tar) |
+|*CCH2OH |2.1G |[7bcae43cee451306e34ec416588a7f09](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/38.tar) |
+|*CHOCHOH |2.0G |[f98866d08fe3451ae7ebc47bb51599aa](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/40.tar) |
+|*COCH2OH |1.4G |[bfaf689e5827fcf26c51e567bb8dd1be](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/41.tar) |
+|*COHCHOH |2.0G |[236fe4e950aa2fbdde94ef2821fb48d2](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/42.tar) |
+|*OCHCH3 |2.1G |[66acc5460a999625c3364f0f3bcca871](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/44.tar) |
+|*COHCH3 |2.1G |[bb4a01956736399c8cee5e219f8c1229](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/45.tar) |
+|*CHOHCH2 |2.1G |[e836de4ec146b1b611533f1ef682cace](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/46.tar) |
+|*CHCH2OH |2.0G |[66df44121806debef6dc038df7115d1d](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/47.tar) |
+|*OCH2CHOH |2.2G |[ff6981fdbcd2e65d351505c15d218d76](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/48.tar) |
+|*CHOCH2OH |2.1G |[448f7d352ab6e32f754e24de64ca302a](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/49.tar) |
+|*COHCH2OH |2.1G |[8bff6bf3e10cc84acc4a283a375fcc23](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/50.tar) |
+|*CHOHCHOH |2.0G |[9c9e4d617d306751760a80f1453e71f1](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/51.tar) |
+|*CH2CH3 |2.0G |[ec1e964d2ee6f468fa5773743e3994a4](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/52.tar) |
+|*OCH2CH3 |2.1G |[d297b27b02822f9b6af80bdb64aee819](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/53.tar) |
+|*CHOHCH3 |2.1G |[368de083dafdc3bbdb560d35e2a102c0](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/54.tar) |
+|*CH2CH2OH |2.1G |[3c1aaf790659f7ff89bf1eed8b396b63](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/55.tar) |
+|*CHOHCH2OH |2.2G |[2d71adb9e305e6f3bca49e5df9b5a86a](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/56.tar) |
+|*OHCH2CH3 |2.3G |[cf51128f8522b7b66fc68d79980d6def](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/57.tar) |
+|*NH2N(CH3)2 |1.6G |[36ba974d80c20ff636431f7c0ad225da](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/58.tar) |
+|*ONN(CH3)2 |2.3G |[fdc4cd19977496909d61be4aee61c4f1](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/59.tar) |
+|*OHNNCH3 |2.1G |[50a6ff098f9ba7adbba9ac115726cc5a](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/60.tar) |
+|*ONH |1.8G |[47573199c545afe46c554ff756c3e38f](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/62.tar) |
+|*NHNH |1.7G |[dd456b7e19ef592d9f0308d911b91d7c](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/63.tar) |
+|*N*NH |1.6G |[c05289fd56d64c74306ebf57f1061318](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/65.tar) |
+|*NO2NO2 |2.1G |[4822a06f6c5f41bdefd3cbbd8856c11f](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/67.tar) |
+|*N*NO |1.6G |[2a27de122d32917cc5b6ac0a21c63c1c](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/68.tar) |
+|*N2 |1.5G |[cc668fecf679b6edaac8fd8fb9cdd404](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/69.tar) |
+|*ONNH2 |2.1G |[dff880f1a5baa7f67b52fd3ed745443d](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/70.tar) |
+|*NH2 |1.6G |[c7f383b50faa6244e265c9611466cb8f](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/71.tar) |
+|*NH3 |1.9G |[2b355741f9300445703270e0e4b8c01c](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/72.tar) |
+|*NONH |1.8G |[48877a0c6f2994baac82cb722711aaa2](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/73.tar) |
+|*NH |1.4G |[7979b9e7ab557d6979b33e352486f0ef](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/74.tar) |
+|*NO2 |1.7G |[9f352fbc32bb2b8caf4788aba28b2eb7](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/75.tar) |
+|*NO |1.4G |[482ee306a5ae2eee78cac40d10059ebc](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/76.tar) |
+|*N |1.1G |[bfb6e03d4a687987ff68976f0793cc46](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/77.tar) |
+|*NO3 |1.8G |[700834326e789a6e38bf3922d9fcb792](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/78.tar) |
+|*OHNH2 |2.1G |[fa24472e0c02c34d91f3ffe6b77bfb11](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/79.tar) |
+|*ONOH |1.4G |[4ddcccd62a834a76fe6167461f512529](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/80.tar) |
+|*CN |1.5G |[bc7c55330ece006d09496a5ff01d5d50](https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/81.tar) |
Note - A few adsorbates are intentionally left out for the test splits.
diff --git a/_sources/tutorials/NRR/NRR_example.md b/_sources/tutorials/NRR/NRR_example.md
index d99f599f9..3a07ae2c8 100644
--- a/_sources/tutorials/NRR/NRR_example.md
+++ b/_sources/tutorials/NRR/NRR_example.md
@@ -121,7 +121,7 @@ You need to provide the calculator with a path to a model checkpoint file. That
Running the model with BFGS prints at each relaxation step is a lot to print. So we will just run one to demonstrate what happens on each iteration.
```{code-cell} ipython3
-from ocpmodels.common.model_registry import model_name_to_local_file
+from ocpmodels.models.model_registry import model_name_to_local_file
checkpoint_path = model_name_to_local_file('eSCN-L6-M3-Lay20All+MD', local_cache='/tmp/ocp_checkpoints/')
diff --git a/_sources/tutorials/OCP-introduction.md b/_sources/tutorials/OCP-introduction.md
index 655ade029..4420ffefa 100644
--- a/_sources/tutorials/OCP-introduction.md
+++ b/_sources/tutorials/OCP-introduction.md
@@ -58,7 +58,7 @@ The first step is getting a checkpoint for the model we want to use. eSCN is cur
The different models have different compute requirements. If you find your kernel is crashing, it probably means you have exceeded the allowed amount of memory. This checkpoint works fine in this example, but it may crash your kernel if you use it in the NRR example.
```{code-cell}
-from ocpmodels.common.model_registry import model_name_to_local_file
+from ocpmodels.models.model_registry import model_name_to_local_file
checkpoint_path = model_name_to_local_file('eSCN-L6-M3-Lay20All+MD', local_cache='/tmp/ocp_checkpoints/')
```
diff --git a/_sources/tutorials/advanced/mass-inference.md b/_sources/tutorials/advanced/mass-inference.md
index 61c157dc2..110b74ed1 100644
--- a/_sources/tutorials/advanced/mass-inference.md
+++ b/_sources/tutorials/advanced/mass-inference.md
@@ -33,13 +33,13 @@ You can retrieve the dataset below. In this notebook we learn how to do "mass in
You have to choose a checkpoint to start with. The newer checkpoints may require too much memory for this environment.
```{code-cell} ipython3
-from ocpmodels.common.model_registry import MODEL_REGISTRY
-print(MODEL_REGISTRY.keys())
+from ocpmodels.models.model_registry import available_pretrained_models
+print(available_pretrained_models)
```
```{code-cell} ipython3
-from ocpmodels.common.model_registry import model_name_to_local_file
+from ocpmodels.models.model_registry import model_name_to_local_file
checkpoint_path = model_name_to_local_file('GemNet-dT OC22', local_cache='/tmp/ocp_checkpoints/')
checkpoint_path
diff --git a/_sources/tutorials/fine-tuning/fine-tuning-oxides.md b/_sources/tutorials/fine-tuning/fine-tuning-oxides.md
index 7710afbc3..73ccbc02e 100644
--- a/_sources/tutorials/fine-tuning/fine-tuning-oxides.md
+++ b/_sources/tutorials/fine-tuning/fine-tuning-oxides.md
@@ -27,7 +27,7 @@ First we get the checkpoint that we want. According to the [MODELS](../../core/M
We get this checkpoint here.
```{code-cell} ipython3
-from ocpmodels.common.model_registry import model_name_to_local_file
+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/')
```
diff --git a/_sources/tutorials/intro.md b/_sources/tutorials/intro.md
index 25906ed1c..31d301303 100644
--- a/_sources/tutorials/intro.md
+++ b/_sources/tutorials/intro.md
@@ -14,7 +14,7 @@ kernelspec:
Intro and background on OCP and DFT
----------
-# Abstract
+## Abstract
The most recent, state of the art machine learned potentials in atomistic simulations are based on graph models that are trained on large (1M+) datasets. These models can be downloaded and used in a wide array of applications ranging from catalysis to materials properties. These pre-trained models can be used on their own, to accelerate DFT calculation, and they can also be used as a starting point to fine-tune new models for specific tasks. In this workshop we will focus on large, graph-based, pre-trained machine learned models from the Open Catalyst Project (OCP) to showcase how they can be used for these purposes. OCP provides several pre-trained models for a variety of tasks related to atomistic simulations. We will explain what these models are, how they differ, and details of the datasets they are trained from. We will introduce an Atomic Simulation Environment (ase) calculator that leverages an OCP pre-trained model for typical simulation tasks including adsorbate geometry relaxation, adsorption energy calculations, and reaction energies. We will show how pre-trained models can be fine-tuned on new data sets for new tasks. We will also discuss current limitations of the models and opportunities for future research. Participants will need a laptop with internet capability.
@@ -24,7 +24,7 @@ The most recent, state of the art machine learned potentials in atomistic simula
+++
-# Introduction
+## Introduction
Density functional theory (DFT) has been a mainstay in molecular simulation, but its high computational cost limits the number and size of simulations that are practical. Over the past two decades machine learning has increasingly been used to build surrogate models to supplement DFT. We call these models machine learned potentials (MLP) In the early days, neural networks were trained using the cartesian coordinates of atomistic systems as features with some success. These features lack important physical properties, notably they lack invariance to rotations, translations and permutations, and they are extensive features, which limit them to the specific system being investigated. About 15 years ago, a new set of features called symmetry functions were developed that were intensive, and which had these invariances. These functions enabled substantial progress in MLP, but they had a few important limitations. First, the size of the feature vector scaled quadratically with the number of elements, practically limiting the MLP to 4-5 elements. Second, composition was usually implicit in the functions, which limited the transferrability of the MLP to new systems. Finally, these functions were "hand-crafted", with limited or no adaptability to the systems being explored, thus one needed to use judgement and experience to select them. While progess has been made in mitigating these limitations, a new approach has overtaken these methods.
@@ -40,45 +40,45 @@ The [Open Catalyst Project (OCP)](https://github.com/Open-Catalyst-Project) is a
+++
-## Models
+### Models
OCP provides several [models](../core/MODELS). Each model represents a different approach to featurization, and a different machine learning architecture. The models can be used for different tasks, and you will find different checkpoints associated with different datasets and tasks.
+++
-## Datasets / Tasks
+### Datasets / Tasks
OCP provides several different datasets like [OC20](../core/datasets/oc20) that correspond to different tasks that range from predicting energy and forces from structures to Bader charges, relaxation energies, and others.
+++
-## Checkpoints
+### Checkpoints
To use a pre-trained model you need to have [ocp](https://github.com/Open-Catalyst-Project/ocp) installed. Then you need to choose a checkpoint and config file which will be loaded to configure OCP for the predictions you want to make. There are two approaches to running OCP, via scripts in a shell, or using an ASE compatible calculator.
We will focus on the ASE compatible calculator here. To facilitate using the checkpoints, there is a set of [utilities](./ocp-tutorial) for this tutorial. You can list the checkpoints that are readily available here:
```{code-cell} ipython3
-from ocpmodels.common.model_registry import MODEL_REGISTRY
-print(MODEL_REGISTRY.keys())
+from ocpmodels.models.model_registry import available_pretrained_models
+print(available_pretrained_models)
```
You can get a checkpoint file with one of the keys listed above like this. The resulting string is the name of the file downloaded, and you use that when creating an OCP calculator later.
```{code-cell} ipython3
-from ocpmodels.common.model_registry import model_name_to_local_file
+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
```
-# Goals for this tutorial
+## Goals for this tutorial
This tutorial will start by using OCP in a Jupyter notebook to setup some simple calculations that use OCP to compute energy and forces, for structure optimization, and then an example of fine-tuning a model with new data.
+++
-# About the compute environment
+## About the compute environment
[ocp-tutorial.ipynb](./ocp_tutorial_helper.py) provides `describe_ocp` to output information that might be helpful in debugging.
diff --git a/autoapi/index.html b/autoapi/index.html
index 16391ad28..ed797e430 100644
--- a/autoapi/index.html
+++ b/autoapi/index.html
@@ -177,9 +177,10 @@
-
+
+
+
+