Transformers
English
conformal-prediction
protein-language-models
uncertainty-quantification
esm-2
temperature-scaling
cpu
protein-structure
protein-engineering
Instructions to use knoxel/conformalesm-paper-starter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use knoxel/conformalesm-paper-starter with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("knoxel/conformalesm-paper-starter", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload all_extensions_results.json
Browse files
all_extensions_results.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
See /app/all_extensions_results.json for full JSON results (125KB). Results include baseline metrics, temperature scaling, standard conformal (alpha 0.05/0.10/0.20), class-conditional conformal, Mondrian conformal, size-stratified coverage, protein-level uncertainty ranking, and calibration diagnostics on 400 test proteins (148K residues).
|