Use neutral OriDynamic checkpoint names and official upstream Protenix base
Browse files- README.md +20 -13
- all_atom_struct_vae_step0100000.pt → ae.ckpt +0 -0
- joint_step0000200.pt → oridynamic.ckpt +0 -0
- protenix_base_default_v1.0.0.pt +0 -3
- weights_manifest.json +15 -11
README.md
CHANGED
|
@@ -18,7 +18,7 @@ inference: false
|
|
| 18 |
|
| 19 |
**All-atom conformational ensembles for biomolecular systems**
|
| 20 |
|
| 21 |
-
v0 · Alpha inference weights
|
| 22 |
|
| 23 |
[Code](https://github.com/JiahaoYoung0520/oridynamic_test_alpha) · [Installation](https://github.com/JiahaoYoung0520/oridynamic_test_alpha/blob/main/INSTALL.md) · [Examples](https://github.com/JiahaoYoung0520/oridynamic_test_alpha/tree/main/examples) · [Model notes](https://github.com/JiahaoYoung0520/oridynamic_test_alpha/blob/main/docs/model_card.md)
|
| 24 |
|
|
@@ -30,17 +30,16 @@ The inference interface accepts protein monomers, protein–ligand complexes, an
|
|
| 30 |
|
| 31 |
## Model files
|
| 32 |
|
| 33 |
-
This repository provides
|
| 34 |
|
| 35 |
| File | Role | Size |
|
| 36 |
| :--- | :--- | ---: |
|
| 37 |
-
| `
|
| 38 |
-
| `
|
| 39 |
-
| `joint_step0000200.pt` | Latent flow module, coordinate refiner, and trunk adaptation (Joint200) | 0.95 GB |
|
| 40 |
|
| 41 |
Joint200 is the checkpoint saved after **200 predicted-anchor adaptation updates from Joint11500**. The frozen codec, latent flow module, and refiner use the shared online LoRA trunk context. This requires the matching updated inference code; changing the weight file alone in the earlier code is insufficient.
|
| 42 |
|
| 43 |
-
The
|
| 44 |
|
| 45 |
These files contain inference tensors, required configuration, and latent normalization information. They do not contain optimizers or training datasets. File sizes and SHA-256 checksums are provided in [weights_manifest.json](weights_manifest.json). The loader checks the export schemas and the correspondence between the backbone, autoencoder, and Joint weights.
|
| 46 |
|
|
@@ -60,15 +59,21 @@ python -m pip install -e .
|
|
| 60 |
python -m pip install -U huggingface_hub
|
| 61 |
```
|
| 62 |
|
| 63 |
-
Download the
|
| 64 |
|
| 65 |
```bash
|
|
|
|
| 66 |
hf download DanielYoung0520/oridynamic_v0 \
|
| 67 |
-
|
| 68 |
-
all_atom_struct_vae_step0100000.pt \
|
| 69 |
-
joint_step0000200.pt \
|
| 70 |
-
weights_manifest.json \
|
| 71 |
--local-dir weights
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
```
|
| 73 |
|
| 74 |
Prepare the CCD resources following the [installation guide](https://github.com/JiahaoYoung0520/oridynamic_test_alpha/blob/main/INSTALL.md#2-model-weights-and-ccd), then set their location:
|
|
@@ -109,12 +114,14 @@ Each target's output directory contains `anchor.cif`, `proposals.cif`, `ensemble
|
|
| 109 |
- These weights match the existing alpha inference implementation. They should not be mixed with checkpoints from other model branches or training runs.
|
| 110 |
- Joint200 was adapted using labeled monomer and protein–ligand systems from the original test split. Results on these systems are not independent held-out evaluation and should not be equated with earlier Joint11500 benchmark results.
|
| 111 |
- Protein–protein systems were excluded from this adaptation and remain outside its training scope, although the inference interface accepts them.
|
| 112 |
-
- The exported tensors are verified against the source checkpoint. Full-size CPU loading and small-module sampling regressions check compatibility and the online codec route.
|
| 113 |
- The output is a time-independent ensemble. It does not provide a molecular-dynamics trajectory, physical transition times, or calibrated thermodynamic state populations.
|
| 114 |
- GPU memory requirements depend on system size and sampling settings. Arbitrary-length inference on smaller GPUs has not been established.
|
| 115 |
|
|
|
|
|
|
|
| 116 |
## Attribution and license
|
| 117 |
|
| 118 |
The OriDynamic autoencoder and joint-model inference weights in this repository are released under the [Apache License 2.0](LICENSE). Copyright 2026 LGLab Frontier AI Group for the OriDynamic contributions and model adaptations.
|
| 119 |
|
| 120 |
-
OriDynamic reuses the Protenix cofolding architecture and adapts its model parameters. The
|
|
|
|
| 18 |
|
| 19 |
**All-atom conformational ensembles for biomolecular systems**
|
| 20 |
|
| 21 |
+
v0 · Alpha inference weights
|
| 22 |
|
| 23 |
[Code](https://github.com/JiahaoYoung0520/oridynamic_test_alpha) · [Installation](https://github.com/JiahaoYoung0520/oridynamic_test_alpha/blob/main/INSTALL.md) · [Examples](https://github.com/JiahaoYoung0520/oridynamic_test_alpha/tree/main/examples) · [Model notes](https://github.com/JiahaoYoung0520/oridynamic_test_alpha/blob/main/docs/model_card.md)
|
| 24 |
|
|
|
|
| 30 |
|
| 31 |
## Model files
|
| 32 |
|
| 33 |
+
This repository provides two OriDynamic inference checkpoints for the [alpha code release](https://github.com/JiahaoYoung0520/oridynamic_test_alpha). The compatible code commit is recorded in [weights_manifest.json](weights_manifest.json). Download the Protenix v1.0.0 backbone separately from its official distribution.
|
| 34 |
|
| 35 |
| File | Role | Size |
|
| 36 |
| :--- | :--- | ---: |
|
| 37 |
+
| `ae.ckpt` | Structural autoencoder | 0.81 GB |
|
| 38 |
+
| `oridynamic.ckpt` | Latent flow module, coordinate refiner, and trunk adaptation (Joint200) | 0.95 GB |
|
|
|
|
| 39 |
|
| 40 |
Joint200 is the checkpoint saved after **200 predicted-anchor adaptation updates from Joint11500**. The frozen codec, latent flow module, and refiner use the shared online LoRA trunk context. This requires the matching updated inference code; changing the weight file alone in the earlier code is insufficient.
|
| 41 |
|
| 42 |
+
The OriDynamic download is approximately **1.76 GB**. The separately obtained official Protenix v1.0.0 backbone is approximately **1.48 GB**. The joint export includes the flow module; no separate flow checkpoint is needed. Filenames match the updated default path configuration; the loader verifies checkpoint identity independently of filenames. The AE and Joint checkpoint bytes are unchanged from the preceding release.
|
| 43 |
|
| 44 |
These files contain inference tensors, required configuration, and latent normalization information. They do not contain optimizers or training datasets. File sizes and SHA-256 checksums are provided in [weights_manifest.json](weights_manifest.json). The loader checks the export schemas and the correspondence between the backbone, autoencoder, and Joint weights.
|
| 45 |
|
|
|
|
| 59 |
python -m pip install -U huggingface_hub
|
| 60 |
```
|
| 61 |
|
| 62 |
+
Download the two OriDynamic files and the official Protenix base into the code repository `weights/` directory. Downloads are public and do not require `hf auth login`.
|
| 63 |
|
| 64 |
```bash
|
| 65 |
+
python -m pip install -U huggingface_hub
|
| 66 |
hf download DanielYoung0520/oridynamic_v0 \
|
| 67 |
+
ae.ckpt oridynamic.ckpt weights_manifest.json \
|
|
|
|
|
|
|
|
|
|
| 68 |
--local-dir weights
|
| 69 |
+
|
| 70 |
+
# Obtain the exact Protenix v1 base from its official distribution.
|
| 71 |
+
curl -fL --retry 3 \
|
| 72 |
+
https://protenix.tos-cn-beijing.volces.com/checkpoint/protenix_base_default_v1.0.0.pt \
|
| 73 |
+
-o weights/protenix_base_default_v1.0.0.pt
|
| 74 |
+
printf '%s %s\n' \
|
| 75 |
+
'2b7d5a8b30494514fc47fd2271a16260528cdba170ba09cc112fdecd8f85ec04' \
|
| 76 |
+
weights/protenix_base_default_v1.0.0.pt | sha256sum -c -
|
| 77 |
```
|
| 78 |
|
| 79 |
Prepare the CCD resources following the [installation guide](https://github.com/JiahaoYoung0520/oridynamic_test_alpha/blob/main/INSTALL.md#2-model-weights-and-ccd), then set their location:
|
|
|
|
| 114 |
- These weights match the existing alpha inference implementation. They should not be mixed with checkpoints from other model branches or training runs.
|
| 115 |
- Joint200 was adapted using labeled monomer and protein–ligand systems from the original test split. Results on these systems are not independent held-out evaluation and should not be equated with earlier Joint11500 benchmark results.
|
| 116 |
- Protein–protein systems were excluded from this adaptation and remain outside its training scope, although the inference interface accepts them.
|
| 117 |
+
- The exported tensors are verified against the source checkpoint. Full-size CPU loading and small-module sampling regressions check compatibility and the online codec route. An author-supplied H20 deployment report dated 2026-11-01 records Joint200 execution with five bundled MSA examples and ten conformations, plus twelve samples each for one monomer, PL, and PP system. Raw H20 outputs have not been independently reviewed in this release update. The report used an existing dependency image and does not validate a fresh public Dockerfile build. These checks do not establish ensemble quality.
|
| 118 |
- The output is a time-independent ensemble. It does not provide a molecular-dynamics trajectory, physical transition times, or calibrated thermodynamic state populations.
|
| 119 |
- GPU memory requirements depend on system size and sampling settings. Arbitrary-length inference on smaller GPUs has not been established.
|
| 120 |
|
| 121 |
+
Seeds do not guarantee identical GPU coordinates. Changing sample chunk size can change intermediate stochastic noise assignment and produce different conformations. Keep sampling settings and the runtime environment fixed for comparisons; see the [reproducibility notes](https://github.com/JiahaoYoung0520/oridynamic_test_alpha/blob/main/docs/model_card.md#reproducibility).
|
| 122 |
+
|
| 123 |
## Attribution and license
|
| 124 |
|
| 125 |
The OriDynamic autoencoder and joint-model inference weights in this repository are released under the [Apache License 2.0](LICENSE). Copyright 2026 LGLab Frontier AI Group for the OriDynamic contributions and model adaptations.
|
| 126 |
|
| 127 |
+
OriDynamic reuses the Protenix cofolding architecture and adapts its model parameters. The separately obtained Protenix v1 backbone retains its upstream Apache-2.0 license; a copy is provided in [LICENSE-PTX](LICENSE-PTX). Upstream copyright notices are preserved; see [NOTICE](NOTICE) and [source attribution](https://github.com/JiahaoYoung0520/oridynamic_test_alpha/blob/main/docs/SOURCES.md). Third-party dependencies and external data resources retain their respective terms.
|
all_atom_struct_vae_step0100000.pt → ae.ckpt
RENAMED
|
File without changes
|
joint_step0000200.pt → oridynamic.ckpt
RENAMED
|
File without changes
|
protenix_base_default_v1.0.0.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b0d59aa3f6d8bb6b051486a04af8d1198af2b236f05e438c5bab593f0161f107
|
| 3 |
-
size 1475509357
|
|
|
|
|
|
|
|
|
|
|
|
weights_manifest.json
CHANGED
|
@@ -1,27 +1,31 @@
|
|
| 1 |
{
|
| 2 |
-
"schema": "
|
| 3 |
"release": "alpha",
|
| 4 |
"code_repository": "https://github.com/JiahaoYoung0520/oridynamic_test_alpha",
|
| 5 |
-
"compatible_code_commit": "
|
| 6 |
"weights": {
|
| 7 |
-
"native": {
|
| 8 |
-
"file": "protenix_base_default_v1.0.0.pt",
|
| 9 |
-
"sha256": "b0d59aa3f6d8bb6b051486a04af8d1198af2b236f05e438c5bab593f0161f107",
|
| 10 |
-
"bytes": 1475509357,
|
| 11 |
-
"schema_version": "oridynamic_native_inference_v1"
|
| 12 |
-
},
|
| 13 |
"codec": {
|
| 14 |
-
"file": "
|
| 15 |
"sha256": "950ca1971e9b86d3c5560df694328d389877722569ddc40e0a48d6e11ac5e0ea",
|
| 16 |
"bytes": 813638719,
|
| 17 |
"schema_version": "oridynamic_codec_inference_v1"
|
| 18 |
},
|
| 19 |
"joint": {
|
| 20 |
-
"file": "
|
| 21 |
"sha256": "3719e2eb8465d21116b0442702132a2f95ff5ae9792edba265fd21271228c9ad",
|
| 22 |
"bytes": 948744621,
|
| 23 |
"schema_version": "oridynamic_joint_inference_v1"
|
| 24 |
}
|
| 25 |
},
|
| 26 |
-
"notes": "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"schema": "oridynamic_weights_bundle_v2",
|
| 3 |
"release": "alpha",
|
| 4 |
"code_repository": "https://github.com/JiahaoYoung0520/oridynamic_test_alpha",
|
| 5 |
+
"compatible_code_commit": "0a0d3112cefc9fe712b98b78d49e1fb5b1c8818d",
|
| 6 |
"weights": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"codec": {
|
| 8 |
+
"file": "ae.ckpt",
|
| 9 |
"sha256": "950ca1971e9b86d3c5560df694328d389877722569ddc40e0a48d6e11ac5e0ea",
|
| 10 |
"bytes": 813638719,
|
| 11 |
"schema_version": "oridynamic_codec_inference_v1"
|
| 12 |
},
|
| 13 |
"joint": {
|
| 14 |
+
"file": "oridynamic.ckpt",
|
| 15 |
"sha256": "3719e2eb8465d21116b0442702132a2f95ff5ae9792edba265fd21271228c9ad",
|
| 16 |
"bytes": 948744621,
|
| 17 |
"schema_version": "oridynamic_joint_inference_v1"
|
| 18 |
}
|
| 19 |
},
|
| 20 |
+
"notes": "OriDynamic AE and Joint tensors are unchanged; only filenames changed. Obtain the exact official Protenix v1.0.0 base separately. The compatible code accepts the pinned official file and the previously verified inference wrapper; both have identical model tensors. Joint requires shared online LoRA codec context.",
|
| 21 |
+
"external_dependencies": {
|
| 22 |
+
"native": {
|
| 23 |
+
"file": "protenix_base_default_v1.0.0.pt",
|
| 24 |
+
"url": "https://protenix.tos-cn-beijing.volces.com/checkpoint/protenix_base_default_v1.0.0.pt",
|
| 25 |
+
"sha256": "2b7d5a8b30494514fc47fd2271a16260528cdba170ba09cc112fdecd8f85ec04",
|
| 26 |
+
"bytes": 1475950125,
|
| 27 |
+
"format": "official_protenix_model_dict",
|
| 28 |
+
"legacy_export_sha256": "b0d59aa3f6d8bb6b051486a04af8d1198af2b236f05e438c5bab593f0161f107"
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
}
|