Instructions to use Synthyra/DPLM2-150M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Synthyra/DPLM2-150M with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, EsmForDPLM2 tokenizer = AutoTokenizer.from_pretrained("Synthyra/DPLM2-150M", trust_remote_code=True) model = EsmForDPLM2.from_pretrained("Synthyra/DPLM2-150M", 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
|
@@ -20,11 +20,11 @@ Supported Transformers entry points are `AutoConfig`, `AutoModel`,
|
|
| 20 |
|
| 21 |
## Install and platform requirements
|
| 22 |
|
| 23 |
-
Install
|
| 24 |
|
| 25 |
```bash
|
| 26 |
python -m pip install \
|
| 27 |
-
"fastplms @ git+https://github.com/Synthyra/FastPLMs.git
|
| 28 |
```
|
| 29 |
|
| 30 |
Python 3.11-3.14, PyTorch 2.13, and Transformers 5.13 are required. The declared CPU gate covers tiny offline contracts; published checkpoint throughput and parity require the documented device tier. The Hub quick start below requires network
|
|
@@ -163,9 +163,8 @@ subject to all artifact, legal, parity, and atomic-publication preflights.
|
|
| 163 |
## Release record
|
| 164 |
|
| 165 |
- FastPLMs weights: `Synthyra/DPLM2-150M`
|
| 166 |
-
- Runtime revision:
|
| 167 |
-
-
|
| 168 |
-
- Runtime bundle SHA-256: `f1b6cea1b423b81666a6711526d598b40481a9aa77eea25445093b7c4a3ec7e0`
|
| 169 |
- Generator/schema version and complete/runtime-only attestations: recorded in `provenance.json`
|
| 170 |
- Canonical transformed state SHA-256: `82e1751f59052b8de72b082517557db47947e8d9b4ac2f11278369e6c0cbf001`
|
| 171 |
- Conversion equality attestation: recorded in `provenance.json`
|
|
|
|
| 20 |
|
| 21 |
## Install and platform requirements
|
| 22 |
|
| 23 |
+
Install the current FastPLMs package:
|
| 24 |
|
| 25 |
```bash
|
| 26 |
python -m pip install \
|
| 27 |
+
"fastplms @ git+https://github.com/Synthyra/FastPLMs.git"
|
| 28 |
```
|
| 29 |
|
| 30 |
Python 3.11-3.14, PyTorch 2.13, and Transformers 5.13 are required. The declared CPU gate covers tiny offline contracts; published checkpoint throughput and parity require the documented device tier. The Hub quick start below requires network
|
|
|
|
| 163 |
## Release record
|
| 164 |
|
| 165 |
- FastPLMs weights: `Synthyra/DPLM2-150M`
|
| 166 |
+
- Runtime revision: recorded separately in the built artifact and published commit
|
| 167 |
+
- Source-tree and runtime-bundle SHA-256: recorded in `provenance.json`
|
|
|
|
| 168 |
- Generator/schema version and complete/runtime-only attestations: recorded in `provenance.json`
|
| 169 |
- Canonical transformed state SHA-256: `82e1751f59052b8de72b082517557db47947e8d9b4ac2f11278369e6c0cbf001`
|
| 170 |
- Conversion equality attestation: recorded in `provenance.json`
|
config.json
CHANGED
|
@@ -20,10 +20,10 @@
|
|
| 20 |
"fastplms_checkpoint_repo_id": "airkingbd/dplm2_150m",
|
| 21 |
"fastplms_checkpoint_revision": "3451d984d06497f835ed49634bd68c9dfb54d730",
|
| 22 |
"fastplms_model_id": "dplm2_150m",
|
| 23 |
-
"fastplms_release_tool_revision": "
|
| 24 |
-
"fastplms_release_tool_sha256": "
|
| 25 |
"fastplms_runtime_bundle_sha256": "f1b6cea1b423b81666a6711526d598b40481a9aa77eea25445093b7c4a3ec7e0",
|
| 26 |
-
"fastplms_runtime_revision": "
|
| 27 |
"fastplms_source_tree_sha256": "ee643a6280d7718a31a95a544ddd9849aa4e2178272147e74ccd161e3e6b08d2",
|
| 28 |
"fastplms_weights_revision": "3451d984d06497f835ed49634bd68c9dfb54d730",
|
| 29 |
"hidden_act": "gelu",
|
|
|
|
| 20 |
"fastplms_checkpoint_repo_id": "airkingbd/dplm2_150m",
|
| 21 |
"fastplms_checkpoint_revision": "3451d984d06497f835ed49634bd68c9dfb54d730",
|
| 22 |
"fastplms_model_id": "dplm2_150m",
|
| 23 |
+
"fastplms_release_tool_revision": "95691a87c781f052f65b6ab3ca99dfce4ebb59c7",
|
| 24 |
+
"fastplms_release_tool_sha256": "19b4247aba04a74de5069397518374ab2c3b9e0ce18ba9f36de34f0f4c5d1ceb",
|
| 25 |
"fastplms_runtime_bundle_sha256": "f1b6cea1b423b81666a6711526d598b40481a9aa77eea25445093b7c4a3ec7e0",
|
| 26 |
+
"fastplms_runtime_revision": "95691a87c781f052f65b6ab3ca99dfce4ebb59c7",
|
| 27 |
"fastplms_source_tree_sha256": "ee643a6280d7718a31a95a544ddd9849aa4e2178272147e74ccd161e3e6b08d2",
|
| 28 |
"fastplms_weights_revision": "3451d984d06497f835ed49634bd68c9dfb54d730",
|
| 29 |
"hidden_act": "gelu",
|
runtime-attestation.json
CHANGED
|
@@ -3,9 +3,9 @@
|
|
| 3 |
"LICENSES/FastPLMs-Apache-2.0.txt": "sha256:2d2b50c7b1414bff1189a1db1f0cfb92e3e064b50f4c2b1019827b683e1b629a",
|
| 4 |
"LICENSES/dplm/LICENSE": "sha256:cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30",
|
| 5 |
"LICENSES/dplm/PROVENANCE.md": "sha256:a659f74be9073cf1ad2d2f7071531ca56959b421f111152cf4c41184ace5970e",
|
| 6 |
-
"README.md": "sha256:
|
| 7 |
"THIRD_PARTY_NOTICES.md": "sha256:25704b3c76404696cae52e7fca13088d329f70f412687340351259e86cd62baa",
|
| 8 |
-
"config.json": "sha256:
|
| 9 |
"fastplms/__init__.py": "sha256:4fb3196022ca8ec699d59d09bdbc5f0184195552b773698ab9b061fe3cd7df12",
|
| 10 |
"fastplms/attention/__init__.py": "sha256:f60b9fecfb4bcb37a4e7c26dc2f752b9035f9cbad627b4a84213f3a92ec88f7d",
|
| 11 |
"fastplms/attention/_core.py": "sha256:8f7ec5b65bd8b6c6fa4951d50d1c0e499abf03ae00914794b51fc410201e3e33",
|
|
@@ -34,10 +34,10 @@
|
|
| 34 |
},
|
| 35 |
"model_id": "dplm2_150m",
|
| 36 |
"redistributable": true,
|
| 37 |
-
"release_tool_revision": "
|
| 38 |
-
"release_tool_sha256": "
|
| 39 |
"runtime_bundle_sha256": "f1b6cea1b423b81666a6711526d598b40481a9aa77eea25445093b7c4a3ec7e0",
|
| 40 |
-
"runtime_revision": "
|
| 41 |
"schema_version": 2,
|
| 42 |
"scope": "runtime-only",
|
| 43 |
"source_tree_sha256": "ee643a6280d7718a31a95a544ddd9849aa4e2178272147e74ccd161e3e6b08d2",
|
|
|
|
| 3 |
"LICENSES/FastPLMs-Apache-2.0.txt": "sha256:2d2b50c7b1414bff1189a1db1f0cfb92e3e064b50f4c2b1019827b683e1b629a",
|
| 4 |
"LICENSES/dplm/LICENSE": "sha256:cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30",
|
| 5 |
"LICENSES/dplm/PROVENANCE.md": "sha256:a659f74be9073cf1ad2d2f7071531ca56959b421f111152cf4c41184ace5970e",
|
| 6 |
+
"README.md": "sha256:51b71957c45e24d2b01bbf7d6b70e30524c71177b5b04616939b324953707591",
|
| 7 |
"THIRD_PARTY_NOTICES.md": "sha256:25704b3c76404696cae52e7fca13088d329f70f412687340351259e86cd62baa",
|
| 8 |
+
"config.json": "sha256:651cdbffbc35f761d456b008f7f33f48bac24428d87841a44db139a47bcc2476",
|
| 9 |
"fastplms/__init__.py": "sha256:4fb3196022ca8ec699d59d09bdbc5f0184195552b773698ab9b061fe3cd7df12",
|
| 10 |
"fastplms/attention/__init__.py": "sha256:f60b9fecfb4bcb37a4e7c26dc2f752b9035f9cbad627b4a84213f3a92ec88f7d",
|
| 11 |
"fastplms/attention/_core.py": "sha256:8f7ec5b65bd8b6c6fa4951d50d1c0e499abf03ae00914794b51fc410201e3e33",
|
|
|
|
| 34 |
},
|
| 35 |
"model_id": "dplm2_150m",
|
| 36 |
"redistributable": true,
|
| 37 |
+
"release_tool_revision": "95691a87c781f052f65b6ab3ca99dfce4ebb59c7",
|
| 38 |
+
"release_tool_sha256": "19b4247aba04a74de5069397518374ab2c3b9e0ce18ba9f36de34f0f4c5d1ceb",
|
| 39 |
"runtime_bundle_sha256": "f1b6cea1b423b81666a6711526d598b40481a9aa77eea25445093b7c4a3ec7e0",
|
| 40 |
+
"runtime_revision": "95691a87c781f052f65b6ab3ca99dfce4ebb59c7",
|
| 41 |
"schema_version": 2,
|
| 42 |
"scope": "runtime-only",
|
| 43 |
"source_tree_sha256": "ee643a6280d7718a31a95a544ddd9849aa4e2178272147e74ccd161e3e6b08d2",
|