Instructions to use Synthyra/ESM3_small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Synthyra/ESM3_small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Synthyra/ESM3_small", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Synthyra/ESM3_small", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,16 +1,19 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
| 3 |
tags:
|
| 4 |
-
- biology
|
| 5 |
-
- protein-language-model
|
| 6 |
-
- esm3
|
| 7 |
-
- multimodal-protein-model
|
| 8 |
---
|
| 9 |
|
| 10 |
# FastPLMs ESM3 Small
|
| 11 |
|
| 12 |
FastPLMs ESM3 Small is a Hugging Face compatible implementation of Biohub's open ESM3 small model. It loads through `AutoModel`, supports sequence-only inference by default, and exposes ESM3's additional tensor tracks directly through normal keyword arguments.
|
| 13 |
|
|
|
|
|
|
|
| 14 |
## Use With Transformers
|
| 15 |
|
| 16 |
```python
|
|
@@ -151,5 +154,6 @@ Available delegated methods include `encode`, `decode`, `generate`, `batch_gener
|
|
| 151 |
## Source
|
| 152 |
|
| 153 |
- Biohub ESM repository: https://github.com/Biohub/esm
|
|
|
|
| 154 |
- Paper: https://biohub.ai/papers/esm_protein.pdf
|
| 155 |
- Official model source: https://huggingface.co/biohub/esm3-sm-open-v1
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
tags:
|
| 5 |
+
- biology
|
| 6 |
+
- protein-language-model
|
| 7 |
+
- esm3
|
| 8 |
+
- multimodal-protein-model
|
| 9 |
---
|
| 10 |
|
| 11 |
# FastPLMs ESM3 Small
|
| 12 |
|
| 13 |
FastPLMs ESM3 Small is a Hugging Face compatible implementation of Biohub's open ESM3 small model. It loads through `AutoModel`, supports sequence-only inference by default, and exposes ESM3's additional tensor tracks directly through normal keyword arguments.
|
| 14 |
|
| 15 |
+
This repository includes the Biohub ESM MIT license in `LICENSE`.
|
| 16 |
+
|
| 17 |
## Use With Transformers
|
| 18 |
|
| 19 |
```python
|
|
|
|
| 154 |
## Source
|
| 155 |
|
| 156 |
- Biohub ESM repository: https://github.com/Biohub/esm
|
| 157 |
+
- Biohub ESM license: https://github.com/Biohub/esm/blob/main/LICENSE.md
|
| 158 |
- Paper: https://biohub.ai/papers/esm_protein.pdf
|
| 159 |
- Official model source: https://huggingface.co/biohub/esm3-sm-open-v1
|