QBind: QLoRA for ESM-2 Binding Sites Prediction
Collection
QLoRAs for various ESM-2 models for predicting binding sites of protein sequences. • 10 items • Updated • 4
ESM-2 QLoRA for Predicting Binding Sites
QLoRA Info
trainable params: 208322 || all params: 17382365 || trainable%: 1.198467527289871
Testing for Overfitting
Train metrics:
{'eval_loss': 0.09572703391313553,
'eval_accuracy': 0.9670769479865963,
'eval_precision': 0.3970221190232079,
'eval_recall': 0.9411011487595375,
'eval_f1': 0.5584507515735834,
'eval_auc': 0.9543828770020467,
'eval_mcc': 0.5996252550053665}
Test metrics:
{'eval_loss': 0.1680256575345993,
'eval_accuracy': 0.943313091525589,
'eval_precision': 0.2342637814982173,
'eval_recall': 0.7618306193745306,
'eval_f1': 0.35833816875074714,
'eval_auc': 0.8544971814140561,
'eval_mcc': 0.40290081143832884}
The metrics on the PDB datasets from this paper can be found here.
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support