Instructions to use Synthyra/ESMplusplus_small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Synthyra/ESMplusplus_small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="Synthyra/ESMplusplus_small", trust_remote_code=True)# Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("Synthyra/ESMplusplus_small", 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 @ git+https://github.com/Synthyra/FastPLMs.git
|
| 26 |
```
|
| 27 |
|
| 28 |
Python 3.11-3.14, PyTorch 2.13, and Transformers 5.13 are required. Eager, SDPA, and Flex use the core install. FlashAttention requires the `flash` extra, compatible CUDA hardware, and BF16 execution. The Hub quick start below requires network
|
|
@@ -210,9 +210,8 @@ not constitute parity or quality claims.
|
|
| 210 |
## Release record
|
| 211 |
|
| 212 |
- FastPLMs weights: `Synthyra/ESMplusplus_small`
|
| 213 |
-
- Runtime revision:
|
| 214 |
-
-
|
| 215 |
-
- Runtime bundle SHA-256: `b01a730b69d0e25723da00aed2f25c2ede185e260e0ab1f7f29cc62934ab17d1`
|
| 216 |
- Generator/schema version and complete/runtime-only attestations: recorded in `provenance.json`
|
| 217 |
- Official checkpoint: `biohub/ESMC-300M`
|
| 218 |
- 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 @ git+https://github.com/Synthyra/FastPLMs.git"
|
| 26 |
```
|
| 27 |
|
| 28 |
Python 3.11-3.14, PyTorch 2.13, and Transformers 5.13 are required. Eager, SDPA, and Flex use the core install. FlashAttention requires the `flash` extra, compatible CUDA hardware, and BF16 execution. The Hub quick start below requires network
|
|
|
|
| 210 |
## Release record
|
| 211 |
|
| 212 |
- FastPLMs weights: `Synthyra/ESMplusplus_small`
|
| 213 |
+
- Runtime revision: recorded separately in the built artifact and published commit
|
| 214 |
+
- Source-tree and runtime-bundle SHA-256: recorded in `provenance.json`
|
|
|
|
| 215 |
- Generator/schema version and complete/runtime-only attestations: recorded in `provenance.json`
|
| 216 |
- Official checkpoint: `biohub/ESMC-300M`
|
| 217 |
- Artifact source: `fast`
|
config.json
CHANGED
|
@@ -13,10 +13,10 @@
|
|
| 13 |
"fastplms_checkpoint_repo_id": "Synthyra/ESMplusplus_small",
|
| 14 |
"fastplms_checkpoint_revision": "46c5f7d562e47d4c14165b424c71ab7db008e6fb",
|
| 15 |
"fastplms_model_id": "esmc_small",
|
| 16 |
-
"fastplms_release_tool_revision": "
|
| 17 |
-
"fastplms_release_tool_sha256": "
|
| 18 |
"fastplms_runtime_bundle_sha256": "b01a730b69d0e25723da00aed2f25c2ede185e260e0ab1f7f29cc62934ab17d1",
|
| 19 |
-
"fastplms_runtime_revision": "
|
| 20 |
"fastplms_source_tree_sha256": "a95686f9e9cb31ebf4a3ced01c54787c6496336528fba0f696d407b053ebabc6",
|
| 21 |
"fastplms_weights_revision": "46c5f7d562e47d4c14165b424c71ab7db008e6fb",
|
| 22 |
"hidden_size": 960,
|
|
|
|
| 13 |
"fastplms_checkpoint_repo_id": "Synthyra/ESMplusplus_small",
|
| 14 |
"fastplms_checkpoint_revision": "46c5f7d562e47d4c14165b424c71ab7db008e6fb",
|
| 15 |
"fastplms_model_id": "esmc_small",
|
| 16 |
+
"fastplms_release_tool_revision": "95691a87c781f052f65b6ab3ca99dfce4ebb59c7",
|
| 17 |
+
"fastplms_release_tool_sha256": "19b4247aba04a74de5069397518374ab2c3b9e0ce18ba9f36de34f0f4c5d1ceb",
|
| 18 |
"fastplms_runtime_bundle_sha256": "b01a730b69d0e25723da00aed2f25c2ede185e260e0ab1f7f29cc62934ab17d1",
|
| 19 |
+
"fastplms_runtime_revision": "95691a87c781f052f65b6ab3ca99dfce4ebb59c7",
|
| 20 |
"fastplms_source_tree_sha256": "a95686f9e9cb31ebf4a3ced01c54787c6496336528fba0f696d407b053ebabc6",
|
| 21 |
"fastplms_weights_revision": "46c5f7d562e47d4c14165b424c71ab7db008e6fb",
|
| 22 |
"hidden_size": 960,
|
runtime-attestation.json
CHANGED
|
@@ -4,9 +4,9 @@
|
|
| 4 |
"LICENSES/biohub-esm/LICENSE.md": "sha256:b63df9ca1dd96b3b21eec226b51b236d0bd152ac20eafc43aad46bf832b48d8a",
|
| 5 |
"LICENSES/biohub-esm/THIRD_PARTY_NOTICE.md": "sha256:5bff8515ba4e0f53abdc43714c180b79c5b606160497d98de741a369cb9b6a23",
|
| 6 |
"LICENSES/biohub-transformers/LICENSE": "sha256:77fd4710def9ec3c0f6225800e0235f15a425abd4a8b03559127fcd782612049",
|
| 7 |
-
"README.md": "sha256:
|
| 8 |
"THIRD_PARTY_NOTICES.md": "sha256:25704b3c76404696cae52e7fca13088d329f70f412687340351259e86cd62baa",
|
| 9 |
-
"config.json": "sha256:
|
| 10 |
"fastplms/__init__.py": "sha256:4fb3196022ca8ec699d59d09bdbc5f0184195552b773698ab9b061fe3cd7df12",
|
| 11 |
"fastplms/attention/__init__.py": "sha256:f60b9fecfb4bcb37a4e7c26dc2f752b9035f9cbad627b4a84213f3a92ec88f7d",
|
| 12 |
"fastplms/attention/_core.py": "sha256:8f7ec5b65bd8b6c6fa4951d50d1c0e499abf03ae00914794b51fc410201e3e33",
|
|
@@ -33,10 +33,10 @@
|
|
| 33 |
},
|
| 34 |
"model_id": "esmc_small",
|
| 35 |
"redistributable": true,
|
| 36 |
-
"release_tool_revision": "
|
| 37 |
-
"release_tool_sha256": "
|
| 38 |
"runtime_bundle_sha256": "b01a730b69d0e25723da00aed2f25c2ede185e260e0ab1f7f29cc62934ab17d1",
|
| 39 |
-
"runtime_revision": "
|
| 40 |
"schema_version": 2,
|
| 41 |
"scope": "runtime-only",
|
| 42 |
"source_tree_sha256": "a95686f9e9cb31ebf4a3ced01c54787c6496336528fba0f696d407b053ebabc6",
|
|
|
|
| 4 |
"LICENSES/biohub-esm/LICENSE.md": "sha256:b63df9ca1dd96b3b21eec226b51b236d0bd152ac20eafc43aad46bf832b48d8a",
|
| 5 |
"LICENSES/biohub-esm/THIRD_PARTY_NOTICE.md": "sha256:5bff8515ba4e0f53abdc43714c180b79c5b606160497d98de741a369cb9b6a23",
|
| 6 |
"LICENSES/biohub-transformers/LICENSE": "sha256:77fd4710def9ec3c0f6225800e0235f15a425abd4a8b03559127fcd782612049",
|
| 7 |
+
"README.md": "sha256:98dbdd2fa604333a8bf937acfb8665c9cb8f3ad0c5c71f4b7a77896d355e1804",
|
| 8 |
"THIRD_PARTY_NOTICES.md": "sha256:25704b3c76404696cae52e7fca13088d329f70f412687340351259e86cd62baa",
|
| 9 |
+
"config.json": "sha256:991c6328679ba116f8ef67b7e81daf84063e2fe1db93fb605a2f70ee671afa15",
|
| 10 |
"fastplms/__init__.py": "sha256:4fb3196022ca8ec699d59d09bdbc5f0184195552b773698ab9b061fe3cd7df12",
|
| 11 |
"fastplms/attention/__init__.py": "sha256:f60b9fecfb4bcb37a4e7c26dc2f752b9035f9cbad627b4a84213f3a92ec88f7d",
|
| 12 |
"fastplms/attention/_core.py": "sha256:8f7ec5b65bd8b6c6fa4951d50d1c0e499abf03ae00914794b51fc410201e3e33",
|
|
|
|
| 33 |
},
|
| 34 |
"model_id": "esmc_small",
|
| 35 |
"redistributable": true,
|
| 36 |
+
"release_tool_revision": "95691a87c781f052f65b6ab3ca99dfce4ebb59c7",
|
| 37 |
+
"release_tool_sha256": "19b4247aba04a74de5069397518374ab2c3b9e0ce18ba9f36de34f0f4c5d1ceb",
|
| 38 |
"runtime_bundle_sha256": "b01a730b69d0e25723da00aed2f25c2ede185e260e0ab1f7f29cc62934ab17d1",
|
| 39 |
+
"runtime_revision": "95691a87c781f052f65b6ab3ca99dfce4ebb59c7",
|
| 40 |
"schema_version": 2,
|
| 41 |
"scope": "runtime-only",
|
| 42 |
"source_tree_sha256": "a95686f9e9cb31ebf4a3ced01c54787c6496336528fba0f696d407b053ebabc6",
|