deploy: 58f2726

FAIR-Chem · May 16, 2024 · 596d804 · 596d804
1 parent c2cc719
commit 596d804
Show file tree

Hide file tree

Showing 279 changed files with 5,688 additions and 2,840 deletions.
diff --git a/_downloads/5fdddbed2260616231dbf7b0d94bb665/train.txt b/_downloads/5fdddbed2260616231dbf7b0d94bb665/train.txt
diff --git a/_downloads/819e10305ddd6839cd7da05935b17060/mass-inference.txt b/_downloads/819e10305ddd6839cd7da05935b17060/mass-inference.txt
@@ -1,17 +1,16 @@
-2024-05-15 22:09:46 (INFO): Project root: /home/runner/work/fairchem/fairchem/src/fairchem
-/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch/cuda/amp/grad_scaler.py:126: UserWarning: torch.cuda.amp.GradScaler is enabled, but CUDA is not available.  Disabling.
-  warnings.warn(
-2024-05-15 22:09:47 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
-2024-05-15 22:09:47 (INFO): amp: true
+2024-05-16 01:16:48 (INFO): Project root: /home/runner/work/fairchem/fairchem/src/fairchem
+2024-05-16 01:16:49 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
+2024-05-16 01:16:49 (INFO): amp: true
 cmd:
-  checkpoint_dir: ./checkpoints/2024-05-15-22-09-04
-  commit: d0f61fa
+  checkpoint_dir: ./checkpoints/2024-05-16-01-16-48
+  commit: 58f2726
   identifier: ''
-  logs_dir: ./logs/tensorboard/2024-05-15-22-09-04
+  logs_dir: ./logs/tensorboard/2024-05-16-01-16-48
   print_every: 10
-  results_dir: ./results/2024-05-15-22-09-04
+  results_dir: ./results/2024-05-16-01-16-48
   seed: 0
-  timestamp_id: 2024-05-15-22-09-04
+  timestamp_id: 2024-05-16-01-16-48
+  version: 0.1.dev1+g58f2726
 dataset:
   a2g_args:
     r_energy: false
@@ -122,25 +121,23 @@ test_dataset:
 trainer: ocp
 val_dataset: null
 
-2024-05-15 22:09:47 (INFO): Loading dataset: ase_db
-2024-05-15 22:09:47 (INFO): rank: 0: Sampler created...
-2024-05-15 22:09:47 (INFO): Batch balancing is disabled for single GPU training.
-2024-05-15 22:09:47 (INFO): rank: 0: Sampler created...
-2024-05-15 22:09:47 (INFO): Batch balancing is disabled for single GPU training.
-2024-05-15 22:09:47 (INFO): Loading model: gemnet_t
-2024-05-15 22:09:48 (INFO): Loaded GemNetT with 31671825 parameters.
-2024-05-15 22:09:48 (WARNING): Model gradient logging to tensorboard not yet supported.
-2024-05-15 22:09:49 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gndt_oc22_all_s2ef.pt
-2024-05-15 22:09:49 (INFO): Overwriting scaling factors with those loaded from checkpoint. If you're generating predictions with a pretrained checkpoint, this is the correct behavior. To disable this, delete `scale_dict` from the checkpoint. 
-2024-05-15 22:09:49 (WARNING): Scale factor comment not found in model
-2024-05-15 22:09:49 (INFO): Predicting on test.
+2024-05-16 01:16:49 (INFO): Loading dataset: ase_db
+2024-05-16 01:16:49 (INFO): rank: 0: Sampler created...
+2024-05-16 01:16:49 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-16 01:16:49 (INFO): rank: 0: Sampler created...
+2024-05-16 01:16:49 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-16 01:16:49 (INFO): Loading model: gemnet_t
+2024-05-16 01:16:51 (INFO): Loaded GemNetT with 31671825 parameters.
+2024-05-16 01:16:51 (WARNING): Model gradient logging to tensorboard not yet supported.
+2024-05-16 01:16:51 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gndt_oc22_all_s2ef.pt
+2024-05-16 01:16:51 (INFO): Overwriting scaling factors with those loaded from checkpoint. If you're generating predictions with a pretrained checkpoint, this is the correct behavior. To disable this, delete `scale_dict` from the checkpoint. 
+2024-05-16 01:16:51 (WARNING): Scale factor comment not found in model
+2024-05-16 01:16:51 (INFO): Predicting on test.
 device 0:   0%|                                           | 0/3 [00:00<?, ?it/s]/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch_geometric/data/collate.py:145: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
   storage = elem.storage()._new_shared(numel)
 /opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch_geometric/data/collate.py:145: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
   storage = elem.storage()._new_shared(numel)
-/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch/amp/autocast_mode.py:250: UserWarning: User provided device_type of 'cuda', but CUDA is not available. Disabling
-  warnings.warn(
-device 0:  33%|███████████▋                       | 1/3 [00:03<00:06,  3.39s/it]device 0:  67%|███████████████████████▎           | 2/3 [00:05<00:02,  2.75s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:06<00:00,  1.97s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:06<00:00,  2.25s/it]
-2024-05-15 22:09:56 (INFO): Writing results to ./results/2024-05-15-22-09-04/ocp_predictions.npz
-2024-05-15 22:09:56 (INFO): Total time taken: 6.8953797817230225
-Elapsed time = 13.0 seconds
+device 0:  33%|███████████▋                       | 1/3 [00:03<00:06,  3.32s/it]device 0:  67%|███████████████████████▎           | 2/3 [00:06<00:03,  3.17s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:06<00:00,  1.99s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:07<00:00,  2.33s/it]
+2024-05-16 01:16:58 (INFO): Writing results to ./results/2024-05-16-01-16-48/ocp_predictions.npz
+2024-05-16 01:16:58 (INFO): Total time taken: 7.149884939193726
+Elapsed time = 13.2 seconds

diff --git a/...02025691c6a130c88e07728e1797c128651fb.png → ...6a052f8635f048b5b7f495a17409cb544df72.png b/...02025691c6a130c88e07728e1797c128651fb.png → ...6a052f8635f048b5b7f495a17409cb544df72.png
diff --git a/...6181d9b7dc0330f894982e3e7d5fc1e1c14e2.png → ...4ef1566bd2800215484dd031eacea9d34b8ed.png b/...6181d9b7dc0330f894982e3e7d5fc1e1c14e2.png → ...4ef1566bd2800215484dd031eacea9d34b8ed.png
diff --git a/_images/1a87ab72394df5335018399dc17656ad6864aca27cdaaf97e6abfccce58247d6.png b/_images/1a87ab72394df5335018399dc17656ad6864aca27cdaaf97e6abfccce58247d6.png
diff --git a/_images/1ab8c89a79c57f0b49529bf8d8f167310393f62863b88c0c494b14c5521582dd.png b/_images/1ab8c89a79c57f0b49529bf8d8f167310393f62863b88c0c494b14c5521582dd.png
diff --git a/_images/25cca8b44a24377d5260d439b8fdc0b58249f8070795f85271860184cf5da245.png b/_images/25cca8b44a24377d5260d439b8fdc0b58249f8070795f85271860184cf5da245.png
diff --git a/_images/2e3debb0c5900734aaf65875d1ae693cd076dc0a39f792ae689e3b61a8a8f823.png b/_images/2e3debb0c5900734aaf65875d1ae693cd076dc0a39f792ae689e3b61a8a8f823.png
diff --git a/_images/30a71d43578e09f3f84b19d3c0b3bc54fc595474ef488ca176cb128ab25e9521.png b/_images/30a71d43578e09f3f84b19d3c0b3bc54fc595474ef488ca176cb128ab25e9521.png
diff --git a/...2325fae1d7b98e150839405d0c583fc558890.png → ...ebfda153643d4b11dc71a09f6161ce695c67c.png b/...2325fae1d7b98e150839405d0c583fc558890.png → ...ebfda153643d4b11dc71a09f6161ce695c67c.png
diff --git a/...74884ea76ff057f50956a969eda20fa151a33.png → ...d67f42a28c228c33b7b8a35c33f393440382a.png b/...74884ea76ff057f50956a969eda20fa151a33.png → ...d67f42a28c228c33b7b8a35c33f393440382a.png
diff --git a/_images/465a1182185664bb277aabcfc6a3c1679be3fa045e94c19106af4ad70f380a9f.png b/_images/465a1182185664bb277aabcfc6a3c1679be3fa045e94c19106af4ad70f380a9f.png
diff --git a/_images/46bad9555dd3bb9446f36adbec85921ea5c90bfac9f12a9d0c668ef3e3bc2a79.png b/_images/46bad9555dd3bb9446f36adbec85921ea5c90bfac9f12a9d0c668ef3e3bc2a79.png
diff --git a/...4f403895acc2e3c741b016c67563997413fe5.png → ...0dbec8644e6b8165949be66d93ad908a3a94c.png b/...4f403895acc2e3c741b016c67563997413fe5.png → ...0dbec8644e6b8165949be66d93ad908a3a94c.png
diff --git a/_images/637965f277c35e91d7ccfb67509bac530fef6914e6f0ac9778e1d15ea4c06e87.png b/_images/637965f277c35e91d7ccfb67509bac530fef6914e6f0ac9778e1d15ea4c06e87.png
diff --git a/...3467296c7c1ce5ddb6c0e7daffc68d22cf2f8.png → ...fab282da4371e89979a0744574aaa167e16fc.png b/...3467296c7c1ce5ddb6c0e7daffc68d22cf2f8.png → ...fab282da4371e89979a0744574aaa167e16fc.png
diff --git a/_images/6903f584d9ae5d999aa5c9e320b8a21966af012bc13951da7d1ef126c2190c2a.png b/_images/6903f584d9ae5d999aa5c9e320b8a21966af012bc13951da7d1ef126c2190c2a.png
diff --git a/...1e20f60472ed1fbcf8520c41ee4e842a0fb07.png → ...f84e52cbeee8ab9c16e8abc25a1c42d77bf2e.png b/...1e20f60472ed1fbcf8520c41ee4e842a0fb07.png → ...f84e52cbeee8ab9c16e8abc25a1c42d77bf2e.png
diff --git a/...0cd23fada1ff98e8dc907657e2eb109af0402.png → ...41e648ebf742911fe25095bde7b712d7234d4.png b/...0cd23fada1ff98e8dc907657e2eb109af0402.png → ...41e648ebf742911fe25095bde7b712d7234d4.png
diff --git a/_images/79f63ae35abce32511d849a00e1daf5b1c041193634c30ebd638481bbb93b61d.png b/_images/79f63ae35abce32511d849a00e1daf5b1c041193634c30ebd638481bbb93b61d.png
diff --git a/_images/86e50dd50fffa230849cbbdbf675714ecf18b7c5dff2366634cbed1af1e6552d.png b/_images/86e50dd50fffa230849cbbdbf675714ecf18b7c5dff2366634cbed1af1e6552d.png
diff --git a/...9b0d05865f32d61379c925b6404131f102a6b.png → ...aa56af0a05a83b148ec0823e6f4c10cf0cd88.png b/...9b0d05865f32d61379c925b6404131f102a6b.png → ...aa56af0a05a83b148ec0823e6f4c10cf0cd88.png
diff --git a/...471c5b3bdd07e6e86f649611890e40bb8eb54.png → ...f954270bca8b6e60d88b947cc42c8e7018929.png b/...471c5b3bdd07e6e86f649611890e40bb8eb54.png → ...f954270bca8b6e60d88b947cc42c8e7018929.png
diff --git a/...4ac45118f28233509bc2ed674c2d47bc9c137.png → ...659b784f34bf0b8ebdceb934bee7ddc222d55.png b/...4ac45118f28233509bc2ed674c2d47bc9c137.png → ...659b784f34bf0b8ebdceb934bee7ddc222d55.png
diff --git a/...6909771b53c44a5d2aff0c98237d9fa037636.png → ...05a2fef563d024b57288137bc0adf4344b0b9.png b/...6909771b53c44a5d2aff0c98237d9fa037636.png → ...05a2fef563d024b57288137bc0adf4344b0b9.png
diff --git a/...e4ff60bcf30a070a02bebd17c29b837ed824c.png → ...fb6b0f7a36c57d7a4025b34de029233d8d3f8.png b/...e4ff60bcf30a070a02bebd17c29b837ed824c.png → ...fb6b0f7a36c57d7a4025b34de029233d8d3f8.png
diff --git a/_images/9ce49b032d20cc623eec4af76d9390aec70f2402b041547c779eb38e6833f3fb.png b/_images/9ce49b032d20cc623eec4af76d9390aec70f2402b041547c779eb38e6833f3fb.png
diff --git a/_images/a4998c9bbb09558a8c456f9a58fa462978ec708c732a2cb63aee9a745ac2ea92.png b/_images/a4998c9bbb09558a8c456f9a58fa462978ec708c732a2cb63aee9a745ac2ea92.png
diff --git a/_images/b1cfc90cc419d069dd99989294a40d5a6e89d4dd4b502a65dc42cb4ecb22a526.png b/_images/b1cfc90cc419d069dd99989294a40d5a6e89d4dd4b502a65dc42cb4ecb22a526.png
diff --git a/...ef6813e5b46342e1bcd68f000211ae06cef95.png → ...d59f84f0614aee01a6b563e2eda73664e980d.png b/...ef6813e5b46342e1bcd68f000211ae06cef95.png → ...d59f84f0614aee01a6b563e2eda73664e980d.png
diff --git a/...3aa9a969d3fcfd9d5e00eb523ba2ea9c48a32.png → ...034ec451475c82b447ad813ae1b9b24601637.png b/...3aa9a969d3fcfd9d5e00eb523ba2ea9c48a32.png → ...034ec451475c82b447ad813ae1b9b24601637.png
diff --git a/_images/bdb18b94e0ad6060f5cefbc67f6c495610920d0b5d1afb8db36045aa5d55e2ea.png b/_images/bdb18b94e0ad6060f5cefbc67f6c495610920d0b5d1afb8db36045aa5d55e2ea.png
diff --git a/_images/cdd346b5ad1a083a442db2a659b20079346702eccccecdad9bef3632fa981bc1.png b/_images/cdd346b5ad1a083a442db2a659b20079346702eccccecdad9bef3632fa981bc1.png
diff --git a/...d3ab84029ec793e343f776087096bfa4b1efd.png → ...ebe0a2cd7bc24bdda4bc2cd0905198d1021e9.png b/...d3ab84029ec793e343f776087096bfa4b1efd.png → ...ebe0a2cd7bc24bdda4bc2cd0905198d1021e9.png
diff --git a/_images/e034aa0bf50e94c9b8c21dfd38685144358e18df151b860989429ad3c691fad5.png b/_images/e034aa0bf50e94c9b8c21dfd38685144358e18df151b860989429ad3c691fad5.png
diff --git a/...ab25e1c749fcaf926372dcc438a7eefc23ee4.png → ...4fc620bea274782085e3f1bb89ccfb4f910f0.png b/...ab25e1c749fcaf926372dcc438a7eefc23ee4.png → ...4fc620bea274782085e3f1bb89ccfb4f910f0.png
diff --git a/_images/e698424119c0abd3303073fa4f8a3082d5ed4775e8cb6f265911a22487db6a08.png b/_images/e698424119c0abd3303073fa4f8a3082d5ed4775e8cb6f265911a22487db6a08.png
diff --git a/_sources/core/datasets/oc20dense.md b/_sources/core/datasets/oc20dense.md
@@ -0,0 +1,38 @@
+
+# Open Catalyst 2020 Dense (OC20Dense)
+
+## Overview
+The OC20Dense dataset is a validation dataset which was used to assess model performance in [AdsorbML: A Leap in Efficiency for Adsorption Energy Calculations using Generalizable Machine Learning Potentials](https://arxiv.org/abs/2211.16486). OC20-Dense contains a dense sampling of adsorbate configurations on ~1,000 randomly selected adsorbate+surface materials from the [OC20](https://arxiv.org/abs/2010.09990) dataset. It comprises a total of 85,658 unique input configurations. This dataset, and the paper written for it, supports the determination of global minimum adsorbate-surface energies (the adsorption energy). This differs from OC20, which contains local adsorbate relaxations. Under low coverage conditions, the global minimum energy site is the most likely to be occupied. For computational catalysis research, we correlate the adsorption energy with important figures of merit, so aquisition of it is an important task.
+
+## File Contents and Download
+|Splits |Size of compressed version (in bytes)  |Size of uncompressed version (in bytes)    | MD5 checksum (download link)   |
+|---    |---    |---    |---    |
+|LMDB    |654M   |9.8G   | [0163b0e8c4df6d9c426b875a28d9178a](https://dl.fbaipublicfiles.com/opencatalystproject/data/adsorbml/oc20_dense_data.tar.gz)   |
+|ASE Trajectories    |29G    |112G   | [ee937e5290f8f720c914dc9a56e0281f](https://dl.fbaipublicfiles.com/opencatalystproject/data/adsorbml/oc20_dense_trajectories.tar.gz)   |
+
+The following files are also provided to be used for evaluation and general information:
+* `oc20dense_mapping.pkl` : Mapping of the LMDB `sid` to general metadata information -
+  * `system_id`: Unique system identifier for an adsorbate, bulk, surface combination.
+  * `config_id`: Unique configuration identifier, where `rand` and `heur` correspond to random and heuristic initial configurations, respectively.
+  * `mpid`: Materials Project bulk identifier.
+  * `miller_idx`: 3-tuple of integers indicating the Miller indices of the surface.
+  * `shift`: C-direction shift used to determine cutoff for the surface (c-direction is following the nomenclature from Pymatgen).
+  * `top`: Boolean indicating whether the chosen surface was at the top or bottom of the originally enumerated surface.
+  * `adsorbate`: Chemical composition of the adsorbate.
+  * `adsorption_site`: A tuple of 3-tuples containing the Cartesian coordinates of each binding adsorbate atom
+* `oc20dense_targets.pkl` :  DFT adsorption energies across different system and placement ids.
+* `oc20dense_compute.pkl` :  DFT compute as measured in the number of ionic and scf steps for each evaluated relaxation.
+* `oc20dense_ref_energies.pkl` : Reference energy used for a specified `system_id`. This energy includes the relaxed clean surface and the gas phase adsorbate energy to ensure consistency across calculations.
+* `oc20dense_tags.pkl` : Tag information used for a specified `system_id`. Where 0 = subsurface, 1 = surface, 2 = adsorbate.
+
+All mappings can be obtained at the following downloadable link: https://dl.fbaipublicfiles.com/opencatalystproject/data/adsorbml/oc20_dense_mappings.tar.gz
+
+MD5 checksums:
+```
+c18735c405ce6ce5761432b07287d8d9  oc20_dense_mappings.tar.gz
+3e26c3bcef01ccfc9b001931065ea6e6  oc20dense_mapping.pkl
+fd589b013b72e62e11a6b2a5bd1d323c  oc20dense_targets.pkl
+78d25997e0aaf754df526ab37276bb89  oc20dense_compute.pkl
+b07c64158e4bfa5f7b9bf6263753ecc5  oc20dense_ref_energies.pkl
+1ba0bc266130f186850f5faa547b6a02  oc20dense_tags.pkl
+```
diff --git a/_sources/core/datasets/oc20neb.md b/_sources/core/datasets/oc20neb.md
@@ -0,0 +1,62 @@
+
+# Open Catalyst 2020 Nudged Elastic Band (OC20NEB)
+
+## Overview
+This is a validation dataset which was used to assess model performance in [CatTSunami: Accelerating Transition State Energy Calculations with Pre-trained Graph Neural Networks](https://arxiv.org/abs/2405.02078). It is comprised of 932 NEB relaxation trajectories. There are three different types of reactions represented: desorptions, dissociations, and transfers. NEB calculations allow us to find transition states. The rate of reaction is determined by the transition state energy, so access to transition states is very important for catalysis research. For more information, check out the paper.
+
+## File Structure and Contents
+The tar file contains 3 subdirectories: dissociations, desorptions, and transfers. As the names imply, these directories contain the converged DFT trajectories for each of the reaction classes. Within these directories, the trajectories are named to identify the contents of the file. Here is an example and the anatomy of the name:
+
+```desorption_id_83_2409_9_111-4_neb1.0.traj```
+
+1. `desorption` indicates the reaction type (dissociation and transfer are the other possibilities)
+2. `id` identifies that the material belongs to the validation in domain split (ood - out of domain is th e other possibility)
+3. `83` is the task id. This does not provide relavent information
+4. `2409` is the bulk index of the bulk used in the ocdata bulk pickle file
+5. `9` is the reaction index. for each reaction type there is a reaction pickle file in the repository. In this case it is the 9th entry to that pickle file
+6. `111-4` the first 3 numbers are the miller indices (i.e. the (1,1,1) surface), and the last number cooresponds to the shift value. In this case the 4th shift enumerated was the one used.
+7. `neb1.0` the number here indicates the k value used. For the full dataset, 1.0 was used so this does not distiguish any of the trajectories from one another.
+
+
+The content of these trajectory files is the repeating frame sets. Despite the initial and final frames not being optimized during the NEB, the initial and final frames are saved for every iteration in the trajectory. For the dataset, 10 frames were used - 8 which were optimized over the neb. So the length of the trajectory is the number of iterations (N) * 10. If you wanted to look at the frame set prior to optimization and the optimized frame set, you could get them like this:
+
+```python
+from ase.io import read
+
+traj = read("desorption_id_83_2409_9_111-4_neb1.0.traj", ":")
+unrelaxed_frames = traj[0:10]
+relaxed_frames = traj[-10:]
+```
+
+## Download 
+|Splits |Size of compressed version (in bytes)  |Size of uncompressed version (in bytes)    | MD5 checksum (download link)   |
+|---    |---    |---    |---    |
+|ASE Trajectories   |1.5G  |6.3G   | [52af34a93758c82fae951e52af445089](https://dl.fbaipublicfiles.com/opencatalystproject/data/oc20neb/oc20neb_dft_trajectories_04_23_24.tar.gz)   |
+
+
+
+## Use
+One more note: We have not prepared an lmdb for this dataset. This is because it is NEB calculations are not supported directly in ocp. You must use the ase native OCP class along with ase infrastructure to run NEB calculations. Here is an example of a use:
+
+```python
+from ase.io import read
+from ase.optimize import BFGS
+from fairchem.applications.cattsunami.core import OCPNEB
+
+traj = read("desorption_id_83_2409_9_111-4_neb1.0.traj", ":")
+neb_frames = traj[0:10]
+neb = OCPNEB(
+    neb_frames,
+    checkpoint_path=YOUR_CHECKPOINT_PATH,
+    k=k,
+    batch_size=8,
+)
+optimizer = BFGS(
+    neb,
+    trajectory=f"test_neb.traj",
+)
+conv = optimizer.run(fmax=0.45, steps=200)
+if conv:
+    neb.climb = True
+    conv = optimizer.run(fmax=0.05, steps=300)
+```
diff --git a/_sources/core/install.md b/_sources/core/install.md
@@ -1,66 +1,71 @@
 # Installation
 
-## conda or better yet [mamba](https://mamba.readthedocs.io/en/latest/user_guide/mamba.html) - easy
+### conda or better yet [mamba](https://mamba.readthedocs.io/en/latest/user_guide/mamba.html) - easy
 
-We do not have official conda recipes (yet!), so to install with conda or mamba you will need to clone the
-[fairchem](https://github.com/FAIR-Chem/fairchem) and run the following from inside the repo directory to create an environment with all the
-necessary dependencies.
+We do not have official conda recipes (yet!); in the meantime you can use the
+following environment yaml files for CPU [env.cpu.yml](https://raw.githubusercontent.com/FAIR-Chem/fairchem/main/packages/env.cpu.yml)
+and GPU [env.gpu.yml](https://raw.githubusercontent.com/FAIR-Chem/fairchem/main/packages/env.gpu.yml) to easily set up a
+working environment and install `fairchem-core`.
 
-1. Create a *fairchem* environment
+1. Create an environment to install *fairchem*
    1. **GPU**
 
       The default environment uses cuda 11.8, if you need a different version you will have to edit *pytorch-cuda* version
       accordingly.
       ```bash
-      conda env create -f packages/env.gpu.yml
+      conda env create -f env.gpu.yml
       ```
 
    2. **CPU**
       ```bash
-      conda env create -f packages/env.cpu.yml
+      conda env create -f env.cpu.yml
       ```
 
-2. Activate the environment and install `fairchem-core`
+2. Activate the environment and install `fairchem-core` from PyPi
    ```bash
    conda activate fair-chem
-   pip install packages/fairchem-core
+   pip install fairchem-core
    ```
 
-## PyPi - flexible
+### PyPi - flexible
+You can also install `pytorch` and `torch_geometric` dependencies from PyPI to select specific CPU or CUDA versions.
+
 1. Install `pytorch` by selecting your installer, OS and CPU or CUDA version following the official
 [Pytorch docs](https://pytorch.org/get-started/locally/)
 
 2. Install `torch_geometric` and the `torch_scatter`, `torch_sparse`, and `torch_cluster` optional dependencies
    similarly by selecting the appropriate versions in the official
    [PyG docs](https://pytorch-geometric.readthedocs.io/en/latest/notes/installation.html)
 
-3. Install `fairchem-core`
-   1. From test-PyPi (until we have our official release on PyPi soon!)
-      ```bash
-      pip install -i https://test.pypi.org/simple/fairchem-core
-      ```
-   2. Or by cloning the repo and then using pip
-      ```bash
-      pip install packages/fairchem-core
-      ```
+3. Install `fairchem-core` from PyPi
+   ```bash
+   pip install -i fairchem-core
+   ```
+
 
 ## Additional packages
 
 `fairchem` is a namespace package, meaning all packages are installed seperately. If you need
 to install other packages you can do so by:
 ```bash
-pip install -e pip install packages/fairchem-{package-to-install}
+pip install fairchem-{package-to-install}
 ```
 
 ## Dev install
 
-If you plan to make contributions you will need to clone (for windows user please see next section) the repo and install `fairchem-core` in editable mode with dev
+If you plan to make contributions you will need to clone (for windows user please see next section) the repo and install
+`fairchem-core` in editable mode with dev
 dependencies,
 ```bash
 pip install -e pip install packages/fairchem-core[dev]
 ```
 
-## Cloning git repository on windows
+And similarly for any other namespace package:
+```bash
+pip install packages/fairchem-{package-to-install}
+```
+
+### Cloning and installing the git repository on windows
 
 Our build system requires the use of symlinks which are not available by default on windows. To properly build fairchem packages you must enable symlinks and clone the repository with them enabled.
 

diff --git a/_sources/index.md b/_sources/index.md
@@ -30,6 +30,8 @@ tasks, data, and metrics, please read the documentations and respective papers:
  - [OC20](core/datasets/oc20)
  - [OC22](core/datasets/oc22)
  - [ODAC23](core/datasets/odac)
+ - [OC20Dense](core/datasets/oc20dense)
+ - [OC20NEB](core/datasets/oc20neb)
 
 ### Projects and models built on `fairchem`:
 

diff --git a/_sources/tutorials/cattsunami_walkthrough.md b/_sources/tutorials/cattsunami_walkthrough.md
@@ -113,10 +113,7 @@ for config in product2_configs:
 
 ## Enumerate NEBs
 Here we use the class we created to handle automatic generation of NEB frames to create frames using the structures we just relaxed as input.
-
-```{code-cell} ipython3
-Image(filename="dissociation_scheme.png")
-```
+![dissociation_scheme](https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/applications/cattsunami/tutorial/dissociation_scheme.png)
 
 ```{code-cell} ipython3
 af = AutoFrameDissociation(

diff --git a/autoapi/adsorbml/2023_neurips_challenge/challenge_eval/index.html b/autoapi/adsorbml/2023_neurips_challenge/challenge_eval/index.html
@@ -210,6 +210,8 @@
 
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/datasets/oc22.html">Open Catalyst 2022 (OC22)</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/datasets/odac.html">Open Direct Air Capture 2023 (ODAC23)</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../core/datasets/oc20dense.html">Open Catalyst 2020 Dense (OC20Dense)</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../core/datasets/oc20neb.html">Open Catalyst 2020 Nudged Elastic Band (OC20NEB)</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/model_checkpoints.html">Pretrained FAIRChem models</a></li>
 
 
@@ -233,8 +235,6 @@
 </ul>
 <p aria-level="2" class="caption" role="heading"><span class="caption-text">Catalysis Case Studies &amp; Tutorials</span></p>
 <ul class="nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="../../../../tutorials/cattsunami_walkthrough.html">CatTSunami tutorial</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../../tutorials/adsorbml_walkthrough.html">AdsorbML tutorial</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../tutorials/intro.html">Intro and background on OCP and DFT</a></li>
 
 
@@ -246,6 +246,8 @@
 
 
 
+<li class="toctree-l1"><a class="reference internal" href="../../../../tutorials/adsorbml_walkthrough.html">AdsorbML tutorial</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../tutorials/cattsunami_walkthrough.html">CatTSunami tutorial</a></li>
 <li class="toctree-l1 has-children"><a class="reference internal" href="../../../../tutorials/NRR/NRR_toc.html">Screening catalysts with OCP</a><input class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul>
 <li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/NRR/NRR_example.html">Using OCP to enumerate adsorbates on alloy catalyst surfaces</a></li>