AmelieSchreiber
commited on
Commit
•
5e8cce3
1
Parent(s):
400bbb0
Update README.md
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ tags:
|
|
22 |
# ESM-2 for Binding Site Prediction
|
23 |
|
24 |
This model is a finetuned version of the 35M parameter `esm2_t12_35M_UR50D` ([see here](https://huggingface.co/facebook/esm2_t12_35M_UR50D)
|
25 |
-
and [here](https://huggingface.co/docs/transformers/model_doc/esm) for more
|
26 |
the binay token classification task of predicting binding sites (and active sites) of protein sequences based on sequence alone.
|
27 |
The model may be underfit and undertrained, however it still achieved better performance on the test set in terms of loss, accuracy,
|
28 |
precision, recall, F1 score, ROC_AUC, and Matthews Correlation Coefficient (MCC) compared to the models trained on the smaller
|
|
|
22 |
# ESM-2 for Binding Site Prediction
|
23 |
|
24 |
This model is a finetuned version of the 35M parameter `esm2_t12_35M_UR50D` ([see here](https://huggingface.co/facebook/esm2_t12_35M_UR50D)
|
25 |
+
and [here](https://huggingface.co/docs/transformers/model_doc/esm) for more details). The model was finetuned with LoRA for
|
26 |
the binay token classification task of predicting binding sites (and active sites) of protein sequences based on sequence alone.
|
27 |
The model may be underfit and undertrained, however it still achieved better performance on the test set in terms of loss, accuracy,
|
28 |
precision, recall, F1 score, ROC_AUC, and Matthews Correlation Coefficient (MCC) compared to the models trained on the smaller
|