Feature Extraction
Transformers
Safetensors
fast_esmfold
protein-language-model
fastplms
custom_code
Instructions to use Synthyra/FastESMFold with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Synthyra/FastESMFold with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Synthyra/FastESMFold", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Synthyra/FastESMFold", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update FastPLMs runtime files
Browse filesAdd-only FastPLMs files-only publication. Checkpoint weights and complete-artifact attestations are unchanged.
- README.md +4 -5
- config.json +3 -3
- runtime-attestation.json +5 -5
README.md
CHANGED
|
@@ -18,11 +18,11 @@ Supported Transformers entry points are `AutoConfig`, `AutoModel`.
|
|
| 18 |
|
| 19 |
## Install and platform requirements
|
| 20 |
|
| 21 |
-
Install
|
| 22 |
|
| 23 |
```bash
|
| 24 |
python -m pip install \
|
| 25 |
-
"fastplms[structure] @ git+https://github.com/Synthyra/FastPLMs.git
|
| 26 |
```
|
| 27 |
|
| 28 |
Python 3.11-3.14, PyTorch 2.13, and Transformers 5.13 are required. Structure inference requires the `structure` extra and a CUDA device for the published execution contract. The current validated release target is the exact NVIDIA GH200 on Linux aarch64; Linux x86-64, CPU-only, Windows, and macOS structure runs are not current release evidence. The Hub quick start below requires network
|
|
@@ -102,9 +102,8 @@ does not contain a trained masked-language-model head for that objective, so
|
|
| 102 |
## Release record
|
| 103 |
|
| 104 |
- FastPLMs weights: `Synthyra/FastESMFold`
|
| 105 |
-
- Runtime revision:
|
| 106 |
-
-
|
| 107 |
-
- Runtime bundle SHA-256: `e38948c5e408464e3174518d3c907f85ee3ea37c6d5fcbe77da921d7adbda818`
|
| 108 |
- Generator/schema version and complete/runtime-only attestations: recorded in `provenance.json`
|
| 109 |
- Official checkpoint: `facebook/esmfold_v1`
|
| 110 |
- Artifact source: `fast`
|
|
|
|
| 18 |
|
| 19 |
## Install and platform requirements
|
| 20 |
|
| 21 |
+
Install the current FastPLMs package:
|
| 22 |
|
| 23 |
```bash
|
| 24 |
python -m pip install \
|
| 25 |
+
"fastplms[structure] @ git+https://github.com/Synthyra/FastPLMs.git"
|
| 26 |
```
|
| 27 |
|
| 28 |
Python 3.11-3.14, PyTorch 2.13, and Transformers 5.13 are required. Structure inference requires the `structure` extra and a CUDA device for the published execution contract. The current validated release target is the exact NVIDIA GH200 on Linux aarch64; Linux x86-64, CPU-only, Windows, and macOS structure runs are not current release evidence. The Hub quick start below requires network
|
|
|
|
| 102 |
## Release record
|
| 103 |
|
| 104 |
- FastPLMs weights: `Synthyra/FastESMFold`
|
| 105 |
+
- Runtime revision: recorded separately in the built artifact and published commit
|
| 106 |
+
- Source-tree and runtime-bundle SHA-256: recorded in `provenance.json`
|
|
|
|
| 107 |
- Generator/schema version and complete/runtime-only attestations: recorded in `provenance.json`
|
| 108 |
- Official checkpoint: `facebook/esmfold_v1`
|
| 109 |
- Artifact source: `fast`
|
config.json
CHANGED
|
@@ -56,10 +56,10 @@
|
|
| 56 |
"fastplms_checkpoint_repo_id": "Synthyra/FastESMFold",
|
| 57 |
"fastplms_checkpoint_revision": "b88c8cb50d19b2cf7ab4fee4b0a61f5e02da7823",
|
| 58 |
"fastplms_model_id": "esmfold",
|
| 59 |
-
"fastplms_release_tool_revision": "
|
| 60 |
-
"fastplms_release_tool_sha256": "
|
| 61 |
"fastplms_runtime_bundle_sha256": "e38948c5e408464e3174518d3c907f85ee3ea37c6d5fcbe77da921d7adbda818",
|
| 62 |
-
"fastplms_runtime_revision": "
|
| 63 |
"fastplms_source_tree_sha256": "6dbdf570cd69776d3f0239168f6388b979affda62c6ba4c78e2d9fac1d81bd6d",
|
| 64 |
"fastplms_weights_revision": "b88c8cb50d19b2cf7ab4fee4b0a61f5e02da7823",
|
| 65 |
"hidden_act": "gelu",
|
|
|
|
| 56 |
"fastplms_checkpoint_repo_id": "Synthyra/FastESMFold",
|
| 57 |
"fastplms_checkpoint_revision": "b88c8cb50d19b2cf7ab4fee4b0a61f5e02da7823",
|
| 58 |
"fastplms_model_id": "esmfold",
|
| 59 |
+
"fastplms_release_tool_revision": "95691a87c781f052f65b6ab3ca99dfce4ebb59c7",
|
| 60 |
+
"fastplms_release_tool_sha256": "19b4247aba04a74de5069397518374ab2c3b9e0ce18ba9f36de34f0f4c5d1ceb",
|
| 61 |
"fastplms_runtime_bundle_sha256": "e38948c5e408464e3174518d3c907f85ee3ea37c6d5fcbe77da921d7adbda818",
|
| 62 |
+
"fastplms_runtime_revision": "95691a87c781f052f65b6ab3ca99dfce4ebb59c7",
|
| 63 |
"fastplms_source_tree_sha256": "6dbdf570cd69776d3f0239168f6388b979affda62c6ba4c78e2d9fac1d81bd6d",
|
| 64 |
"fastplms_weights_revision": "b88c8cb50d19b2cf7ab4fee4b0a61f5e02da7823",
|
| 65 |
"hidden_act": "gelu",
|
runtime-attestation.json
CHANGED
|
@@ -6,9 +6,9 @@
|
|
| 6 |
"LICENSES/openfold/LICENSE": "sha256:cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30",
|
| 7 |
"LICENSES/openfold/MODIFICATIONS.md": "sha256:fd6f0aa1086a0c996cf967b326d18e965660cda0ad5c7f36a3474a8490720da3",
|
| 8 |
"LICENSES/openfold/PROVENANCE.md": "sha256:48c903db43a217a3126afaefbac60b7ddac7efda2dfcc0cbff0bffc7d6c30081",
|
| 9 |
-
"README.md": "sha256:
|
| 10 |
"THIRD_PARTY_NOTICES.md": "sha256:25704b3c76404696cae52e7fca13088d329f70f412687340351259e86cd62baa",
|
| 11 |
-
"config.json": "sha256:
|
| 12 |
"fastplms/__init__.py": "sha256:4fb3196022ca8ec699d59d09bdbc5f0184195552b773698ab9b061fe3cd7df12",
|
| 13 |
"fastplms/attention/__init__.py": "sha256:f60b9fecfb4bcb37a4e7c26dc2f752b9035f9cbad627b4a84213f3a92ec88f7d",
|
| 14 |
"fastplms/attention/_core.py": "sha256:8f7ec5b65bd8b6c6fa4951d50d1c0e499abf03ae00914794b51fc410201e3e33",
|
|
@@ -34,10 +34,10 @@
|
|
| 34 |
},
|
| 35 |
"model_id": "esmfold",
|
| 36 |
"redistributable": true,
|
| 37 |
-
"release_tool_revision": "
|
| 38 |
-
"release_tool_sha256": "
|
| 39 |
"runtime_bundle_sha256": "e38948c5e408464e3174518d3c907f85ee3ea37c6d5fcbe77da921d7adbda818",
|
| 40 |
-
"runtime_revision": "
|
| 41 |
"schema_version": 2,
|
| 42 |
"scope": "runtime-only",
|
| 43 |
"source_tree_sha256": "6dbdf570cd69776d3f0239168f6388b979affda62c6ba4c78e2d9fac1d81bd6d",
|
|
|
|
| 6 |
"LICENSES/openfold/LICENSE": "sha256:cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30",
|
| 7 |
"LICENSES/openfold/MODIFICATIONS.md": "sha256:fd6f0aa1086a0c996cf967b326d18e965660cda0ad5c7f36a3474a8490720da3",
|
| 8 |
"LICENSES/openfold/PROVENANCE.md": "sha256:48c903db43a217a3126afaefbac60b7ddac7efda2dfcc0cbff0bffc7d6c30081",
|
| 9 |
+
"README.md": "sha256:578d1eca99c24e5e6f0ad6721fe344e4a0e84992030cc9477ebb767b18532c82",
|
| 10 |
"THIRD_PARTY_NOTICES.md": "sha256:25704b3c76404696cae52e7fca13088d329f70f412687340351259e86cd62baa",
|
| 11 |
+
"config.json": "sha256:d32b8505ccd23422e3b67dabbcdd2d7c4b505cd1386c07342036b57cfd6cfdce",
|
| 12 |
"fastplms/__init__.py": "sha256:4fb3196022ca8ec699d59d09bdbc5f0184195552b773698ab9b061fe3cd7df12",
|
| 13 |
"fastplms/attention/__init__.py": "sha256:f60b9fecfb4bcb37a4e7c26dc2f752b9035f9cbad627b4a84213f3a92ec88f7d",
|
| 14 |
"fastplms/attention/_core.py": "sha256:8f7ec5b65bd8b6c6fa4951d50d1c0e499abf03ae00914794b51fc410201e3e33",
|
|
|
|
| 34 |
},
|
| 35 |
"model_id": "esmfold",
|
| 36 |
"redistributable": true,
|
| 37 |
+
"release_tool_revision": "95691a87c781f052f65b6ab3ca99dfce4ebb59c7",
|
| 38 |
+
"release_tool_sha256": "19b4247aba04a74de5069397518374ab2c3b9e0ce18ba9f36de34f0f4c5d1ceb",
|
| 39 |
"runtime_bundle_sha256": "e38948c5e408464e3174518d3c907f85ee3ea37c6d5fcbe77da921d7adbda818",
|
| 40 |
+
"runtime_revision": "95691a87c781f052f65b6ab3ca99dfce4ebb59c7",
|
| 41 |
"schema_version": 2,
|
| 42 |
"scope": "runtime-only",
|
| 43 |
"source_tree_sha256": "6dbdf570cd69776d3f0239168f6388b979affda62c6ba4c78e2d9fac1d81bd6d",
|