metadata
base_model: westlake-repl/SaProt_35M_AF2
library_name: peft
Model Card for Model ID
This model is used to predict mutation fitness score of protein DLG4_RAT.
Task type
protein level regression
Dataset description
The dataset is from SESNet: sequence-structure feature-integrated deep learning method for data-efficient protein engineering.
Model input type
Amino acid sequence
Performance
LoRA config
lora_dropout: 0.0 lora_alpha: 16 target_modules: ["query", "key", "value", "intermediate.dense", "output.dense"] modules_to_save: ["classifier"]
Training config
class: AdamW
betas: (0.9, 0.98)
weight_decay: 0.01
learning rate: 1e-4
epoch: 50
batch size: 2
precision: 16-mixed