CoolFace
Modelpublic

SaProtHub/Model-Thermostability-650M

sourceHugging Facemitupdated 2y agoView on Hugging Face
1likes
Model Card

Base model: westlake-repl/SaProt_650M_AF2

Task type: protein-level regression

Label corresponds to the protein melting temperature (Tm) normalized using the Min-Max normalization method.

Dataset: SaProtHub/Dataset-Thermostability-FLIP

Model input type: SA(Structure-aware) sequence

Performance (on test set): 0.706 Spearman's ρ

LoRA config:

  • r: 8
  • lora_dropout: 0.1
  • lora_alpha: 8
  • target_modules: ["query", "key", "value", "intermediate.dense", "output.dense"]
  • modules_to_save: ["classifier"]

Training config:

  • optimizer:
  • class: AdamW
  • betas: (0.9, 0.98)
  • weight_decay: 0.01
  • learning rate: 1e-4
  • epoch: 50
  • batch size: 64
  • precision: 16-mixed