Release verified A1 Step2 and Step1 encoders for private testing

LICENSE

@@ -0,0 +1,399 @@
+Attribution-NonCommercial 4.0 International
+
+=======================================================================
+
+Creative Commons Corporation ("Creative Commons") is not a law firm and
+does not provide legal services or legal advice. Distribution of
+Creative Commons public licenses does not create a lawyer-client or
+other relationship. Creative Commons makes its licenses and related
+information available on an "as-is" basis. Creative Commons gives no
+warranties regarding its licenses, any material licensed under their
+terms and conditions, or any related information. Creative Commons
+disclaims all liability for damages resulting from their use to the
+fullest extent possible.
+
+Using Creative Commons Public Licenses
+
+Creative Commons public licenses provide a standard set of terms and
+conditions that creators and other rights holders may use to share
+original works of authorship and other material subject to copyright
+and certain other rights specified in the public license below. The
+following considerations are for informational purposes only, are not
+exhaustive, and do not form part of our licenses.
+
+     Considerations for licensors: Our public licenses are
+     intended for use by those authorized to give the public
+     permission to use material in ways otherwise restricted by
+     copyright and certain other rights. Our licenses are
+     irrevocable. Licensors should read and understand the terms
+     and conditions of the license they choose before applying it.
+     Licensors should also secure all rights necessary before
+     applying our licenses so that the public can reuse the
+     material as expected. Licensors should clearly mark any
+     material not subject to the license. This includes other CC-
+     licensed material, or material used under an exception or
+     limitation to copyright. More considerations for licensors:
+	wiki.creativecommons.org/Considerations_for_licensors
+
+     Considerations for the public: By using one of our public
+     licenses, a licensor grants the public permission to use the
+     licensed material under specified terms and conditions. If
+     the licensor's permission is not necessary for any reason--for
+     example, because of any applicable exception or limitation to
+     copyright--then that use is not regulated by the license. Our
+     licenses grant only permissions under copyright and certain
+     other rights that a licensor has authority to grant. Use of
+     the licensed material may still be restricted for other
+     reasons, including because others have copyright or other
+     rights in the material. A licensor may make special requests,
+     such as asking that all changes be marked or described.
+     Although not required by our licenses, you are encouraged to
+     respect those requests where reasonable. More_considerations
+     for the public:
+	wiki.creativecommons.org/Considerations_for_licensees
+
+=======================================================================
+
+Creative Commons Attribution-NonCommercial 4.0 International Public
+License
+
+By exercising the Licensed Rights (defined below), You accept and agree
+to be bound by the terms and conditions of this Creative Commons
+Attribution-NonCommercial 4.0 International Public License ("Public
+License"). To the extent this Public License may be interpreted as a
+contract, You are granted the Licensed Rights in consideration of Your
+acceptance of these terms and conditions, and the Licensor grants You
+such rights in consideration of benefits the Licensor receives from
+making the Licensed Material available under these terms and
+conditions.
+
+Section 1 -- Definitions.
+
+  a. Adapted Material means material subject to Copyright and Similar
+     Rights that is derived from or based upon the Licensed Material
+     and in which the Licensed Material is translated, altered,
+     arranged, transformed, or otherwise modified in a manner requiring
+     permission under the Copyright and Similar Rights held by the
+     Licensor. For purposes of this Public License, where the Licensed
+     Material is a musical work, performance, or sound recording,
+     Adapted Material is always produced where the Licensed Material is
+     synched in timed relation with a moving image.
+
+  b. Adapter's License means the license You apply to Your Copyright
+     and Similar Rights in Your contributions to Adapted Material in
+     accordance with the terms and conditions of this Public License.
+
+  c. Copyright and Similar Rights means copyright and/or similar rights
+     closely related to copyright including, without limitation,
+     performance, broadcast, sound recording, and Sui Generis Database
+     Rights, without regard to how the rights are labeled or
+     categorized. For purposes of this Public License, the rights
+     specified in Section 2(b)(1)-(2) are not Copyright and Similar
+     Rights.
+  d. Effective Technological Measures means those measures that, in the
+     absence of proper authority, may not be circumvented under laws
+     fulfilling obligations under Article 11 of the WIPO Copyright
+     Treaty adopted on December 20, 1996, and/or similar international
+     agreements.
+
+  e. Exceptions and Limitations means fair use, fair dealing, and/or
+     any other exception or limitation to Copyright and Similar Rights
+     that applies to Your use of the Licensed Material.
+
+  f. Licensed Material means the artistic or literary work, database,
+     or other material to which the Licensor applied this Public
+     License.
+
+  g. Licensed Rights means the rights granted to You subject to the
+     terms and conditions of this Public License, which are limited to
+     all Copyright and Similar Rights that apply to Your use of the
+     Licensed Material and that the Licensor has authority to license.
+
+  h. Licensor means the individual(s) or entity(ies) granting rights
+     under this Public License.
+
+  i. NonCommercial means not primarily intended for or directed towards
+     commercial advantage or monetary compensation. For purposes of
+     this Public License, the exchange of the Licensed Material for
+     other material subject to Copyright and Similar Rights by digital
+     file-sharing or similar means is NonCommercial provided there is
+     no payment of monetary compensation in connection with the
+     exchange.
+
+  j. Share means to provide material to the public by any means or
+     process that requires permission under the Licensed Rights, such
+     as reproduction, public display, public performance, distribution,
+     dissemination, communication, or importation, and to make material
+     available to the public including in ways that members of the
+     public may access the material from a place and at a time
+     individually chosen by them.
+
+  k. Sui Generis Database Rights means rights other than copyright
+     resulting from Directive 96/9/EC of the European Parliament and of
+     the Council of 11 March 1996 on the legal protection of databases,
+     as amended and/or succeeded, as well as other essentially
+     equivalent rights anywhere in the world.
+
+  l. You means the individual or entity exercising the Licensed Rights
+     under this Public License. Your has a corresponding meaning.
+
+Section 2 -- Scope.
+
+  a. License grant.
+
+       1. Subject to the terms and conditions of this Public License,
+          the Licensor hereby grants You a worldwide, royalty-free,
+          non-sublicensable, non-exclusive, irrevocable license to
+          exercise the Licensed Rights in the Licensed Material to:
+
+            a. reproduce and Share the Licensed Material, in whole or
+               in part, for NonCommercial purposes only; and
+
+            b. produce, reproduce, and Share Adapted Material for
+               NonCommercial purposes only.
+
+       2. Exceptions and Limitations. For the avoidance of doubt, where
+          Exceptions and Limitations apply to Your use, this Public
+          License does not apply, and You do not need to comply with
+          its terms and conditions.
+
+       3. Term. The term of this Public License is specified in Section
+          6(a).
+
+       4. Media and formats; technical modifications allowed. The
+          Licensor authorizes You to exercise the Licensed Rights in
+          all media and formats whether now known or hereafter created,
+          and to make technical modifications necessary to do so. The
+          Licensor waives and/or agrees not to assert any right or
+          authority to forbid You from making technical modifications
+          necessary to exercise the Licensed Rights, including
+          technical modifications necessary to circumvent Effective
+          Technological Measures. For purposes of this Public License,
+          simply making modifications authorized by this Section 2(a)
+          (4) never produces Adapted Material.
+
+       5. Downstream recipients.
+
+            a. Offer from the Licensor -- Licensed Material. Every
+               recipient of the Licensed Material automatically
+               receives an offer from the Licensor to exercise the
+               Licensed Rights under the terms and conditions of this
+               Public License.
+
+            b. No downstream restrictions. You may not offer or impose
+               any additional or different terms or conditions on, or
+               apply any Effective Technological Measures to, the
+               Licensed Material if doing so restricts exercise of the
+               Licensed Rights by any recipient of the Licensed
+               Material.
+
+       6. No endorsement. Nothing in this Public License constitutes or
+          may be construed as permission to assert or imply that You
+          are, or that Your use of the Licensed Material is, connected
+          with, or sponsored, endorsed, or granted official status by,
+          the Licensor or others designated to receive attribution as
+          provided in Section 3(a)(1)(A)(i).
+
+  b. Other rights.
+
+       1. Moral rights, such as the right of integrity, are not
+          licensed under this Public License, nor are publicity,
+          privacy, and/or other similar personality rights; however, to
+          the extent possible, the Licensor waives and/or agrees not to
+          assert any such rights held by the Licensor to the limited
+          extent necessary to allow You to exercise the Licensed
+          Rights, but not otherwise.
+
+       2. Patent and trademark rights are not licensed under this
+          Public License.
+
+       3. To the extent possible, the Licensor waives any right to
+          collect royalties from You for the exercise of the Licensed
+          Rights, whether directly or through a collecting society
+          under any voluntary or waivable statutory or compulsory
+          licensing scheme. In all other cases the Licensor expressly
+          reserves any right to collect such royalties, including when
+          the Licensed Material is used other than for NonCommercial
+          purposes.
+
+Section 3 -- License Conditions.
+
+Your exercise of the Licensed Rights is expressly made subject to the
+following conditions.
+
+  a. Attribution.
+
+       1. If You Share the Licensed Material (including in modified
+          form), You must:
+
+            a. retain the following if it is supplied by the Licensor
+               with the Licensed Material:
+
+                 i. identification of the creator(s) of the Licensed
+                    Material and any others designated to receive
+                    attribution, in any reasonable manner requested by
+                    the Licensor (including by pseudonym if
+                    designated);
+
+                ii. a copyright notice;
+
+               iii. a notice that refers to this Public License;
+
+                iv. a notice that refers to the disclaimer of
+                    warranties;
+
+                 v. a URI or hyperlink to the Licensed Material to the
+                    extent reasonably practicable;
+
+            b. indicate if You modified the Licensed Material and
+               retain an indication of any previous modifications; and
+
+            c. indicate the Licensed Material is licensed under this
+               Public License, and include the text of, or the URI or
+               hyperlink to, this Public License.
+
+       2. You may satisfy the conditions in Section 3(a)(1) in any
+          reasonable manner based on the medium, means, and context in
+          which You Share the Licensed Material. For example, it may be
+          reasonable to satisfy the conditions by providing a URI or
+          hyperlink to a resource that includes the required
+          information.
+
+       3. If requested by the Licensor, You must remove any of the
+          information required by Section 3(a)(1)(A) to the extent
+          reasonably practicable.
+
+       4. If You Share Adapted Material You produce, the Adapter's
+          License You apply must not prevent recipients of the Adapted
+          Material from complying with this Public License.
+
+Section 4 -- Sui Generis Database Rights.
+
+Where the Licensed Rights include Sui Generis Database Rights that
+apply to Your use of the Licensed Material:
+
+  a. for the avoidance of doubt, Section 2(a)(1) grants You the right
+     to extract, reuse, reproduce, and Share all or a substantial
+     portion of the contents of the database for NonCommercial purposes
+     only;
+
+  b. if You include all or a substantial portion of the database
+     contents in a database in which You have Sui Generis Database
+     Rights, then the database in which You have Sui Generis Database
+     Rights (but not its individual contents) is Adapted Material; and
+
+  c. You must comply with the conditions in Section 3(a) if You Share
+     all or a substantial portion of the contents of the database.
+
+For the avoidance of doubt, this Section 4 supplements and does not
+replace Your obligations under this Public License where the Licensed
+Rights include other Copyright and Similar Rights.
+
+Section 5 -- Disclaimer of Warranties and Limitation of Liability.
+
+  a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
+     EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
+     AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
+     ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
+     IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
+     WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
+     PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
+     ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
+     KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
+     ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
+
+  b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
+     TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
+     NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
+     INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
+     COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
+     USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
+     ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
+     DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
+     IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
+
+  c. The disclaimer of warranties and limitation of liability provided
+     above shall be interpreted in a manner that, to the extent
+     possible, most closely approximates an absolute disclaimer and
+     waiver of all liability.
+
+Section 6 -- Term and Termination.
+
+  a. This Public License applies for the term of the Copyright and
+     Similar Rights licensed here. However, if You fail to comply with
+     this Public License, then Your rights under this Public License
+     terminate automatically.
+
+  b. Where Your right to use the Licensed Material has terminated under
+     Section 6(a), it reinstates:
+
+       1. automatically as of the date the violation is cured, provided
+          it is cured within 30 days of Your discovery of the
+          violation; or
+
+       2. upon express reinstatement by the Licensor.
+
+     For the avoidance of doubt, this Section 6(b) does not affect any
+     right the Licensor may have to seek remedies for Your violations
+     of this Public License.
+
+  c. For the avoidance of doubt, the Licensor may also offer the
+     Licensed Material under separate terms or conditions or stop
+     distributing the Licensed Material at any time; however, doing so
+     will not terminate this Public License.
+
+  d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
+     License.
+
+Section 7 -- Other Terms and Conditions.
+
+  a. The Licensor shall not be bound by any additional or different
+     terms or conditions communicated by You unless expressly agreed.
+
+  b. Any arrangements, understandings, or agreements regarding the
+     Licensed Material not stated herein are separate from and
+     independent of the terms and conditions of this Public License.
+
+Section 8 -- Interpretation.
+
+  a. For the avoidance of doubt, this Public License does not, and
+     shall not be interpreted to, reduce, limit, restrict, or impose
+     conditions on any use of the Licensed Material that could lawfully
+     be made without permission under this Public License.
+
+  b. To the extent possible, if any provision of this Public License is
+     deemed unenforceable, it shall be automatically reformed to the
+     minimum extent necessary to make it enforceable. If the provision
+     cannot be reformed, it shall be severed from this Public License
+     without affecting the enforceability of the remaining terms and
+     conditions.
+
+  c. No term or condition of this Public License will be waived and no
+     failure to comply consented to unless expressly agreed to by the
+     Licensor.
+
+  d. Nothing in this Public License constitutes or may be interpreted
+     as a limitation upon, or waiver of, any privileges and immunities
+     that apply to the Licensor or You, including from the legal
+     processes of any jurisdiction or authority.
+
+=======================================================================
+
+Creative Commons is not a party to its public
+licenses. Notwithstanding, Creative Commons may elect to apply one of
+its public licenses to material it publishes and in those instances
+will be considered the “Licensor.” The text of the Creative Commons
+public licenses is dedicated to the public domain under the CC0 Public
+Domain Dedication. Except for the limited purpose of indicating that
+material is shared under a Creative Commons public license or as
+otherwise permitted by the Creative Commons policies published at
+creativecommons.org/policies, Creative Commons does not authorize the
+use of the trademark "Creative Commons" or any other trademark or logo
+of Creative Commons without its prior written consent including,
+without limitation, in connection with any unauthorized modifications
+to any of its public licenses or any other arrangements,
+understandings, or agreements concerning use of licensed material. For
+the avoidance of doubt, this paragraph does not form part of the
+public licenses.
+
+Creative Commons may be contacted at creativecommons.org.

NOTICE

@@ -0,0 +1,5 @@
+GRASP adapts the MolE molecular encoder released by Recursion Pharmaceuticals.
+The MolE source is distributed under CC BY-NC 4.0; its license is LICENSE and
+vendor/MOLE_LICENSE. The bundled DeBERTa implementation is distributed under
+the MIT license in vendor/DEBERTA_LICENSE. Source code implementing the paper's
+training and evaluation is retained in reproduction/supplement.

README.md

@@ -0,0 +1,108 @@
+---
+license: cc-by-nc-4.0
+library_name: pytorch
+tags:
+  - chemistry
+  - molecular-representation-learning
+  - graph-transformer
+  - replaced-token-detection
+  - assay-supervision
+  - grasp
+  - ablation
+---
+
+# GRASP-A1
+
+**GRASP-A1** is the GRASP molecular graph Transformer trained without absolute atom-position embeddings. It retains shortest-path relative attention, radius-0 atom-environment tokens, and the replaced-token-detection objective. The encoder has **93,091,584 parameters**, 12 layers, hidden size 768, and 12 attention heads.
+
+This private research release provides the completed **50,000-update Step2 encoder** by default and the corresponding **Step1 encoder** under `step1/`. Step1 saw **1,538,242,560 molecule presentations** from ZINC20; this is a presentation budget, not a count of certified unique molecules. Step2 used the audited 511,897-molecule ChEMBL 36 set with 642 assay tasks.
+
+## Use
+
+Install Python 3.10–3.13 and the [GRASP code repository](https://github.com/caithmac/GRASP). This repository uses its custom `GRASPEncoder` loader; a standard Transformers `AutoModel` is not provided.
+
+```bash
+python -m pip install "git+https://github.com/caithmac/GRASP.git@7843e72606dd208517cd8cf86ee07b3bb965cc79"
+hf auth login
+```
+
+Authenticate with an account permitted to read this private repository, then:
+
+```python
+from grasp import GRASPEncoder
+
+encoder = GRASPEncoder.from_pretrained("caithmac/GRASP-A1")
+vectors = encoder.encode(["CCO", "c1ccccc1"])
+print(vectors.shape)  # (2, 768)
+```
+
+The output is the final-layer CLS state. A property prediction requires a fitted endpoint head. The default embedding is different from the learned layer-mixture and atom-attention readout used in the primary OpenADMET evaluation.
+
+To test Step1 before assay adaptation:
+
+```python
+from pathlib import Path
+from huggingface_hub import snapshot_download
+from grasp import GRASPEncoder
+
+snapshot = snapshot_download("caithmac/GRASP-A1", allow_patterns="step1/*")
+encoder_s1 = GRASPEncoder.from_pretrained(Path(snapshot) / "step1")
+vectors_s1 = encoder_s1.encode(["CCO", "c1ccccc1"])
+```
+
+## Fine-tune on your tasks
+
+Create separate `train.csv` and `valid.csv` files with `smiles` and `target` columns. Keep test molecules separate from training and model selection. Regression targets use their original units; binary targets must be 0 or 1.
+
+```bash
+python -m grasp finetune --model caithmac/GRASP-A1 \
+  --train-csv train.csv --valid-csv valid.csv \
+  --smiles-column smiles --target-column target \
+  --task regression --method full --output-dir runs/a1_my_task
+
+python -m grasp predict --model runs/a1_my_task \
+  --input-csv test.csv --output-csv predictions.csv
+```
+
+Use `--task binary` for binary classification. `--method frozen` trains the readout and head with a fixed encoder; `--method lora` provides LoRA adaptation. Use a separate output directory per endpoint. To compare against published GRASP, repeat the same split, preprocessing, method and seed with `--model caithmac/GRASP`.
+
+## Model details and provenance
+
+| Property | Value |
+|---|---|
+| Architecture | 12 layers, width 768, 12 heads, FFN width 3072 |
+| Encoder parameters | 93,091,584 |
+| Vocabulary | 211 radius-0 atom-environment and special tokens |
+| Absolute position embeddings | Removed throughout training |
+| Relative attention | Graph shortest-path, content-to-position (`c2p`) |
+| Step1 objective | Replaced-token detection, 25% selected atom positions, GDES |
+| Step1 budget | 1,538,242,560 molecule presentations |
+| Step2 | 50,000 updates; sparse supervision on 642 ChEMBL 36 assays |
+| Default representation | Final-layer CLS, 768 dimensions |
+
+`model.safetensors` contains Step2 encoder tensors; `step1/model.safetensors` contains the effective GDES discriminator encoder before Step2. Generator weights, optimizer states, and fitted downstream heads are omitted. Each SafeTensors file is checked tensor by tensor against its encoder export. `training_provenance.json` records source checkpoint hashes and architecture; `SHA256SUMS` records release file hashes. `validation_report.json` describes the actual loading and adaptation smoke checks, which are not benchmark evaluations.
+
+## Evaluation
+
+The matched control/A1 experiment completed 23 OpenADMET endpoints with three split/seed runs per endpoint, using endpoint-specific full fine-tuning with a learned layer mixture and atom-attention pooler:
+
+| Model in the matched experiment | Mean endpoint MAE | Endpoints with lower mean MAE |
+|---|---:|---:|
+| Retrained control with absolute positions | 0.370232 | 12/23 |
+| A1 without absolute positions | 0.368588 | 11/23 |
+
+The MAE difference is **−0.001644**, about **0.44%** relative to the matched control. This is mixed, near-parity evidence rather than a general superiority claim. These results come from one pretraining seed; downstream split and seed change together. The matched control is a separately retrained comparator, and these numbers are not a direct benchmark against the public `caithmac/GRASP` weights or zero-shot encoder scores. TDC evaluation and fixed-split training repeats were still incomplete when this release was prepared. AqSolDB remains blocked because two official test molecules failed parsing; its test set was not modified.
+
+Removing absolute positions addresses atom-order dependence. Existing direct atom-permutation audits measured relative embedding drift on the order of 1e-6 for A1. Numerically equivalent embeddings can still differ slightly with batching and floating-point arithmetic. Chemical standardization or parsing changes can change the graph and are outside this invariance statement.
+
+## Intended use and limitations
+
+Use this model for research on molecular embeddings and property prediction after endpoint-specific fitting. The vocabulary and graph distances still omit tetrahedral and E/Z assignments: **A1 remains stereo-blind**. It does not supply explicit bond-type inputs, 3D conformers, protonation-state ensembles, or measured uncertainty. Improvements proposed for A2/A3 are not part of this checkpoint.
+
+Structural pretraining used molecules with at most 96 heavy atoms. The GRASP loader accepts at most 511 atoms and rejects larger or invalid inputs explicitly; accepting a molecule does not establish that it is in the training domain. Standardization, tautomer handling, charged fragments and salts should be considered consistently when defining a task. This encoder is not a calibrated assay predictor and does not provide clinical or toxicological determinations.
+
+## Training data, license and citation
+
+Structural pretraining used ZINC20; assay adaptation used ChEMBL 36. Raw datasets are not redistributed. Model and MolE-derived implementation terms are **CC BY-NC 4.0**; bundled DeBERTa code retains its separate MIT license. See `LICENSE` and `NOTICE` and the [GRASP source and reproduction records](https://github.com/caithmac/GRASP).
+
+Satya Pratik Srivastava, Rohan Gorantla, Sharath Krishna Chundru, Harshit Singh, Antonia S. J. S. Mey, and Rajeev Kumar Singh. *GRASP: Graph Representation Learning with Assay Supervision for Molecular Properties*. Use the citation metadata in the GRASP code repository. A1 is an experimental ablation checkpoint, not a separately established paper result.

SHA256SUMS

@@ -0,0 +1,12 @@
+5b2636c65d69d21303a60eb7f2e9dad76b6b1ba78e27202079184a27b5789b62  config.json
+6318960741814b0ae14a6769b0e129451ae7f3bec6ecbf0764fbb519407bc6a4  LICENSE
+7f355e252de37e3a4affbb3ca2aabe79a92c9e893bbee01c9f0fd171b3e41e92  model.safetensors
+ac8a653d18e0fdfad95a2edf74b2c813d820d86bcf03527d88029bef8b04cd21  NOTICE
+53dae9e0d17f514ee38eae7f605715285a2fea1f4e644cdfcb638f4e7f86bd6f  README.md
+adcb0cb97d071880ee1e540d20434c8138dfdd63f9db654f5eef4c8584d38108  requirements-tested.txt
+784e6a4c9f2e22dbbc7f02d3bd151fe6de96e065aa50c3df21f238e9addb2948  step1/config.json
+e1fbbfb34f65b3a30072f2df482a600024b4749d131e542b0d0a3c23604334f9  step1/model.safetensors
+95c56c82dd3144fbb1d022e84118cf0c155e66acac3a0a4a548818521606ea11  step1/vocab.json
+f2ec92690b7917049cc8cd591da941769fdd27bdc0bc79a0ecb51a608d9cd6cf  training_provenance.json
+9bff469cb60ccbbb9e6f685727438555f061303e9fd10deafec33dae85c78967  validation_report.json
+95c56c82dd3144fbb1d022e84118cf0c155e66acac3a0a4a548818521606ea11  vocab.json

config.json

@@ -0,0 +1,29 @@
+{
+  "architecture": {
+    "embedding_size": 768,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_hidden_layers": 12,
+    "num_attention_heads": 12,
+    "attention_head_size": 64,
+    "attention_probs_dropout_prob": 0.1,
+    "hidden_dropout_prob": 0.1,
+    "hidden_act": "gelu",
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-07,
+    "max_position_embeddings": 0,
+    "max_relative_positions": 512,
+    "position_buckets": 0,
+    "norm_rel_ebd": "none",
+    "pos_att_type": "c2p",
+    "position_biased_input": false,
+    "relative_attention": true,
+    "share_att_key": false,
+    "type_vocab_size": 0,
+    "vocab_size": 211
+  },
+  "source_checkpoint_sha256": "5ec58973aa95dc71495081857abadfc5e736fe019ebd55866a8c269a5f3e2914",
+  "representation": "final_layer_cls",
+  "model_variant": "A1",
+  "training_stage": "step2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f355e252de37e3a4affbb3ca2aabe79a92c9e893bbee01c9f0fd171b3e41e92
+size 372391552

requirements-tested.txt

@@ -0,0 +1,11 @@
+torch==2.14.1
+torch-geometric==2.8.1
+rdkit==2025.3.6
+numpy==1.26.4
+pandas==2.3.3
+scipy==1.15.3
+scikit-learn==1.7.2
+safetensors==0.8.0
+huggingface-hub==2.2.0
+pytorch-lightning==2.6.6
+torchmetrics==1.9.0

step1/config.json

@@ -0,0 +1,29 @@
+{
+  "architecture": {
+    "embedding_size": 768,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_hidden_layers": 12,
+    "num_attention_heads": 12,
+    "attention_head_size": 64,
+    "attention_probs_dropout_prob": 0.1,
+    "hidden_dropout_prob": 0.1,
+    "hidden_act": "gelu",
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-07,
+    "max_position_embeddings": 0,
+    "max_relative_positions": 512,
+    "position_buckets": 0,
+    "norm_rel_ebd": "none",
+    "pos_att_type": "c2p",
+    "position_biased_input": false,
+    "relative_attention": true,
+    "share_att_key": false,
+    "type_vocab_size": 0,
+    "vocab_size": 211
+  },
+  "source_checkpoint_sha256": "8c61648a30c85c69cd628e8b5eb69f161c0ea727190dee3d40f6beb6429a436c",
+  "representation": "final_layer_cls",
+  "model_variant": "A1",
+  "training_stage": "step1"
+}

step1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1fbbfb34f65b3a30072f2df482a600024b4749d131e542b0d0a3c23604334f9
+size 372391552

step1/vocab.json

@@ -0,0 +1 @@
+{"1009961767": 128, "1010215930": 205, "1010228075": 154, "1012972668": 48, "1013338319": 89, "1016841875": 59, "1016845826": 4, "1017642631": 52, "1026654242": 15, "1026654305": 37, "1026822558": 176, "1026924773": 100, "1026928756": 44, "1026928821": 76, "1056139193": 187, "1070894407": 135, "1073491469": 5, "11594061": 141, "12277426": 74, "1611362324": 7, "1622062563": 198, "1659542613": 34, "1660341273": 10, "1660362024": 126, "1673608309": 45, "1677254294": 61, "1677325492": 75, "1844073467": 206, "1844282154": 127, "1844343863": 21, "1893173645": 168, "1988401551": 169, "2041434490": 159, "2041738475": 104, "2092489639": 180, "2092554703": 191, "2114006677": 62, "2114539071": 25, "2130998634": 153, "2132511834": 35, "2143075994": 65, "2155415144": 38, "2192730848": 98, "2192738690": 161, "2192742899": 203, "2193111430": 165, "2194492085": 79, "2194662096": 90, "2196961854": 24, "2197104911": 110, "2197211467": 139, "2197215675": 188, "2197215866": 47, "2208356666": 131, "2245108812": 31, "2245273601": 2, "2245277810": 42, "2245384272": 32, "2245897107": 171, "2245900962": 68, "2245901155": 149, "2246699750": 101, "2246699815": 125, "2246703125": 8, "2246703798": 77, "2246703991": 157, "2246728737": 13, "2246994583": 63, "2246997269": 112, "2246997334": 146, "2261158082": 86, "2445181571": 51, "2462807768": 95, "2572184638": 28, "2572973538": 197, "2849135538": 186, "2850007887": 143, "2850012158": 207, "2865977551": 88, "2866063486": 49, "2866325538": 14, "2968968094": 173, "2976033787": 138, "2976816164": 16, "2998938176": 26, "3027842437": 164, "3027882655": 67, "3040320797": 117, "3132583778": 148, "3156024848": 6, "318908292": 163, "318909215": 119, "3189457552": 56, "3189554341": 71, "319552149": 60, "3205230712": 46, "3206325537": 121, "3206345777": 20, "3217377045": 113, "3217380708": 150, "3217425642": 103, "3217695935": 84, "321854373": 178, "3218681120": 120, "3218693969": 144, "322382141": 132, "322422332": 23, "323195681": 122, "327066619": 108, "3351552914": 170, "3351556771": 69, "3387140397": 129, "3387315712": 1, "3388932168": 30, "3388977530": 158, "3388985371": 11, "3388989546": 40, "3421018950": 134, "3593562157": 18, "3593562348": 106, "3594119454": 118, "3594120102": 179, "3594325843": 145, "3595735704": 66, "3595739785": 55, "3595956281": 22, "3609219177": 39, "3609504524": 109, "3612109269": 193, "3612926680": 94, "369185560": 115, "370425064": 102, "370453531": 12, "370453657": 64, "370453720": 96, "370454343": 137, "370687140": 70, "370711622": 29, "370732245": 92, "371070650": 81, "371508627": 172, "384719280": 185, "384719345": 202, "384719475": 43, "384960988": 195, "384961118": 36, "3855292234": 140, "3858165842": 33, "3858440414": 97, "3912561944": 116, "3912762629": 107, "3922503314": 57, "4179524517": 181, "4181736951": 204, "4267512994": 72, "4274663090": 73, "847336149": 91, "847342868": 111, "847433064": 151, "847433129": 182, "847690172": 189, "847694221": 167, "847698334": 174, "847867887": 201, "847950754": 177, "847954377": 190, "847957139": 58, "847958490": 194, "847961216": 50, "848127915": 184, "848128881": 155, "849271271": 200, "849275503": 41, "849279553": 27, "864408791": 93, "864662309": 123, "864662311": 124, "864662502": 199, "864666390": 114, "864674484": 80, "864674487": 78, "864677235": 156, "864937294": 142, "864942729": 53, "864942730": 54, "864942795": 87, "881066519": 9, "882399112": 166, "882671422": 133, "984188929": 3, "984189120": 85, "984193073": 19, "984213985": 196, "984453308": 83, "984465735": 136, "984473645": 17, "984473836": 105, "995319674": 160, "995543427": 162, "996772578": 99, "999334238": 147, "999334303": 175, "999338447": 192, "999346357": 82, "999598394": 130, "999602538": 152, "999602603": 183, "CLS": 210, "MASK": 208, "PAD": 0, "UNK": 209}

training_provenance.json

@@ -0,0 +1,72 @@
+{
+  "variant": "A1",
+  "default_checkpoint": "step2",
+  "step1": {
+    "source_checkpoint_sha256": "8c61648a30c85c69cd628e8b5eb69f161c0ea727190dee3d40f6beb6429a436c",
+    "export_checkpoint_sha256": "8e3830bd824de1f0b6f3c17da591daaf5721efea287bbee661014230e101ced6",
+    "architecture": {
+      "embedding_size": 768,
+      "hidden_size": 768,
+      "intermediate_size": 3072,
+      "num_hidden_layers": 12,
+      "num_attention_heads": 12,
+      "attention_head_size": 64,
+      "attention_probs_dropout_prob": 0.1,
+      "hidden_dropout_prob": 0.1,
+      "hidden_act": "gelu",
+      "initializer_range": 0.02,
+      "layer_norm_eps": 1e-07,
+      "max_position_embeddings": 0,
+      "max_relative_positions": 512,
+      "position_buckets": 0,
+      "norm_rel_ebd": "none",
+      "pos_att_type": "c2p",
+      "position_biased_input": false,
+      "relative_attention": true,
+      "share_att_key": false,
+      "type_vocab_size": 0,
+      "vocab_size": 211
+    },
+    "encoder_parameters": 93091584,
+    "finite": true,
+    "step2_updates": 0,
+    "step1_molecule_presentations": 1538242560
+  },
+  "step2": {
+    "source_checkpoint_sha256": "5ec58973aa95dc71495081857abadfc5e736fe019ebd55866a8c269a5f3e2914",
+    "export_checkpoint_sha256": "9958206598b4e31b09329520614ceda9870699bf5e2e345d33fe7387747c655f",
+    "architecture": {
+      "embedding_size": 768,
+      "hidden_size": 768,
+      "intermediate_size": 3072,
+      "num_hidden_layers": 12,
+      "num_attention_heads": 12,
+      "attention_head_size": 64,
+      "attention_probs_dropout_prob": 0.1,
+      "hidden_dropout_prob": 0.1,
+      "hidden_act": "gelu",
+      "initializer_range": 0.02,
+      "layer_norm_eps": 1e-07,
+      "max_position_embeddings": 0,
+      "max_relative_positions": 512,
+      "position_buckets": 0,
+      "norm_rel_ebd": "none",
+      "pos_att_type": "c2p",
+      "position_biased_input": false,
+      "relative_attention": true,
+      "share_att_key": false,
+      "type_vocab_size": 0,
+      "vocab_size": 211
+    },
+    "encoder_parameters": 93091584,
+    "finite": true,
+    "step2_updates": 50000,
+    "step1_molecule_presentations": 1538242560
+  },
+  "vocabulary_sha256": "95c56c82dd3144fbb1d022e84118cf0c155e66acac3a0a4a548818521606ea11",
+  "step2_audited_molecules": 511897,
+  "step2_assays": 642,
+  "source_export_manifest_sha256": "1e97a589195b356999bbf18e10ee9461b429130737fc1e5012d608206ffcdb62",
+  "license": "cc-by-nc-4.0",
+  "grasp_code_commit": "7843e72606dd208517cd8cf86ee07b3bb965cc79"
+}

validation_report.json

@@ -0,0 +1,70 @@
+{
+  "status": "passed",
+  "stages": {
+    "step2": {
+      "tensor_identical_conversion": true,
+      "strict_load": true,
+      "raw_encoder_output_parity": true,
+      "eidf_input_parity": true,
+      "eidf_output_max_abs_error": 2.205371856689453e-06,
+      "embedding_shape": [
+        3,
+        768
+      ],
+      "permutation_relative_l2_max": 4.634867991626379e-07,
+      "stereo_input_collision_preserved": true,
+      "stereo_embedding_max_abs_error": 1.6763806343078613e-06,
+      "encoder_parameters": 93091584
+    },
+    "step1": {
+      "tensor_identical_conversion": true,
+      "strict_load": true,
+      "raw_encoder_output_parity": true,
+      "eidf_input_parity": true,
+      "eidf_output_max_abs_error": 9.5367431640625e-07,
+      "embedding_shape": [
+        3,
+        768
+      ],
+      "permutation_relative_l2_max": 2.9877668339395314e-07,
+      "stereo_input_collision_preserved": true,
+      "stereo_embedding_max_abs_error": 5.960464477539062e-07,
+      "encoder_parameters": 93091584
+    }
+  },
+  "adaptation_smokes": {
+    "regression": {
+      "method": "frozen",
+      "epochs": 1,
+      "train_rows": 8,
+      "valid_rows": 4,
+      "finite_predictions": true,
+      "save_reload_parity": true,
+      "benchmark_result": false
+    },
+    "binary": {
+      "method": "full",
+      "epochs": 1,
+      "train_rows": 8,
+      "valid_rows": 4,
+      "finite_predictions": true,
+      "save_reload_parity": true,
+      "benchmark_result": false
+    }
+  },
+  "python": "3.12.13",
+  "runtime_packages": {
+    "torch": "2.14.1",
+    "torch-geometric": "2.8.1",
+    "rdkit": "2025.3.6",
+    "numpy": "1.26.4",
+    "pandas": "2.3.3",
+    "scipy": "1.15.3",
+    "scikit-learn": "1.7.2",
+    "safetensors": "0.8.0",
+    "huggingface-hub": "2.2.0",
+    "pytorch-lightning": "2.6.6",
+    "torchmetrics": "1.9.0"
+  },
+  "scope": "CPU conversion, loading, permutation controls and tiny adaptation smokes; no new benchmark evaluation"
+}

vocab.json

@@ -0,0 +1 @@
+{"1009961767": 128, "1010215930": 205, "1010228075": 154, "1012972668": 48, "1013338319": 89, "1016841875": 59, "1016845826": 4, "1017642631": 52, "1026654242": 15, "1026654305": 37, "1026822558": 176, "1026924773": 100, "1026928756": 44, "1026928821": 76, "1056139193": 187, "1070894407": 135, "1073491469": 5, "11594061": 141, "12277426": 74, "1611362324": 7, "1622062563": 198, "1659542613": 34, "1660341273": 10, "1660362024": 126, "1673608309": 45, "1677254294": 61, "1677325492": 75, "1844073467": 206, "1844282154": 127, "1844343863": 21, "1893173645": 168, "1988401551": 169, "2041434490": 159, "2041738475": 104, "2092489639": 180, "2092554703": 191, "2114006677": 62, "2114539071": 25, "2130998634": 153, "2132511834": 35, "2143075994": 65, "2155415144": 38, "2192730848": 98, "2192738690": 161, "2192742899": 203, "2193111430": 165, "2194492085": 79, "2194662096": 90, "2196961854": 24, "2197104911": 110, "2197211467": 139, "2197215675": 188, "2197215866": 47, "2208356666": 131, "2245108812": 31, "2245273601": 2, "2245277810": 42, "2245384272": 32, "2245897107": 171, "2245900962": 68, "2245901155": 149, "2246699750": 101, "2246699815": 125, "2246703125": 8, "2246703798": 77, "2246703991": 157, "2246728737": 13, "2246994583": 63, "2246997269": 112, "2246997334": 146, "2261158082": 86, "2445181571": 51, "2462807768": 95, "2572184638": 28, "2572973538": 197, "2849135538": 186, "2850007887": 143, "2850012158": 207, "2865977551": 88, "2866063486": 49, "2866325538": 14, "2968968094": 173, "2976033787": 138, "2976816164": 16, "2998938176": 26, "3027842437": 164, "3027882655": 67, "3040320797": 117, "3132583778": 148, "3156024848": 6, "318908292": 163, "318909215": 119, "3189457552": 56, "3189554341": 71, "319552149": 60, "3205230712": 46, "3206325537": 121, "3206345777": 20, "3217377045": 113, "3217380708": 150, "3217425642": 103, "3217695935": 84, "321854373": 178, "3218681120": 120, "3218693969": 144, "322382141": 132, "322422332": 23, "323195681": 122, "327066619": 108, "3351552914": 170, "3351556771": 69, "3387140397": 129, "3387315712": 1, "3388932168": 30, "3388977530": 158, "3388985371": 11, "3388989546": 40, "3421018950": 134, "3593562157": 18, "3593562348": 106, "3594119454": 118, "3594120102": 179, "3594325843": 145, "3595735704": 66, "3595739785": 55, "3595956281": 22, "3609219177": 39, "3609504524": 109, "3612109269": 193, "3612926680": 94, "369185560": 115, "370425064": 102, "370453531": 12, "370453657": 64, "370453720": 96, "370454343": 137, "370687140": 70, "370711622": 29, "370732245": 92, "371070650": 81, "371508627": 172, "384719280": 185, "384719345": 202, "384719475": 43, "384960988": 195, "384961118": 36, "3855292234": 140, "3858165842": 33, "3858440414": 97, "3912561944": 116, "3912762629": 107, "3922503314": 57, "4179524517": 181, "4181736951": 204, "4267512994": 72, "4274663090": 73, "847336149": 91, "847342868": 111, "847433064": 151, "847433129": 182, "847690172": 189, "847694221": 167, "847698334": 174, "847867887": 201, "847950754": 177, "847954377": 190, "847957139": 58, "847958490": 194, "847961216": 50, "848127915": 184, "848128881": 155, "849271271": 200, "849275503": 41, "849279553": 27, "864408791": 93, "864662309": 123, "864662311": 124, "864662502": 199, "864666390": 114, "864674484": 80, "864674487": 78, "864677235": 156, "864937294": 142, "864942729": 53, "864942730": 54, "864942795": 87, "881066519": 9, "882399112": 166, "882671422": 133, "984188929": 3, "984189120": 85, "984193073": 19, "984213985": 196, "984453308": 83, "984465735": 136, "984473645": 17, "984473836": 105, "995319674": 160, "995543427": 162, "996772578": 99, "999334238": 147, "999334303": 175, "999338447": 192, "999346357": 82, "999598394": 130, "999602538": 152, "999602603": 183, "CLS": 210, "MASK": 208, "PAD": 0, "UNK": 209}