Instructions to use mila-intel/protst-esm1b-for-sequential-classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mila-intel/protst-esm1b-for-sequential-classification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="mila-intel/protst-esm1b-for-sequential-classification", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mila-intel/protst-esm1b-for-sequential-classification", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +1 -9
config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"ProtSTForProteinPropertyPrediction"
|
| 5 |
],
|
| 6 |
"auto_map": {
|
| 7 |
-
"AutoConfig": "Jiqing/
|
| 8 |
"AutoModel": "Jiqing/protst-esm1b-for-sequential-classification--modeling_protst.ProtSTForProteinPropertyPrediction"
|
| 9 |
},
|
| 10 |
"model_type": "protest",
|
|
@@ -33,14 +33,6 @@
|
|
| 33 |
"torch_dtype": "float32",
|
| 34 |
"vocab_size": 33
|
| 35 |
},
|
| 36 |
-
"text_config": {
|
| 37 |
-
"architectures": [
|
| 38 |
-
"BertForMaskedLM"
|
| 39 |
-
],
|
| 40 |
-
"cls_token_id": 2,
|
| 41 |
-
"model_type": "bert",
|
| 42 |
-
"sep_token_id": 3
|
| 43 |
-
},
|
| 44 |
"torch_dtype": "float32",
|
| 45 |
"transformers_version": "4.36.2"
|
| 46 |
}
|
|
|
|
| 4 |
"ProtSTForProteinPropertyPrediction"
|
| 5 |
],
|
| 6 |
"auto_map": {
|
| 7 |
+
"AutoConfig": "Jiqing/protst-esm1b-for-sequential-classification--configuration_protst.ProtSTConfig",
|
| 8 |
"AutoModel": "Jiqing/protst-esm1b-for-sequential-classification--modeling_protst.ProtSTForProteinPropertyPrediction"
|
| 9 |
},
|
| 10 |
"model_type": "protest",
|
|
|
|
| 33 |
"torch_dtype": "float32",
|
| 34 |
"vocab_size": 33
|
| 35 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
"torch_dtype": "float32",
|
| 37 |
"transformers_version": "4.36.2"
|
| 38 |
}
|