| | --- |
| | base_model: westlake-repl/SaProt_35M_AF2 |
| | library_name: peft |
| | --- |
| | |
| | # Base model: [westlake-repl/SaProt_35M_AF2](https://huggingface.co/westlake-repl/SaProt_35M_AF2) |
| |
|
| | # Model Card for Model ID |
| |
|
| | <!-- Provide a quick summary of what the model is/does. --> |
| | AVIDa-hIL6 is an antigen-variable domain of heavy chain of heavy chain antibody (VHH) interaction dataset |
| | produced from an alpaca immunized with the human interleukin-6 (IL-6) protein. This model is used to predict |
| | interaction between AVIDa-hIL6 and IL-6 protein. |
| |
|
| |
|
| | ### Task type |
| | protein-protein pair classification |
| |
|
| | ### Dataset description |
| | The dataset is from [AVIDa-hIL6](https://cognanous.com/datasets/avida-hil6), |
| | which contains 573,891 antigen-VHH pairs with amino acid sequences. |
| |
|
| | Binary label represented by 1 for the binding pair and 0 for the non-binding pair. |
| |
|
| | ### Model input type |
| | Amino acid sequence pair |
| |
|
| | ### Performance |
| | test_acc: 0.99 |
| | |
| | ### 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: 10 |
| | |
| | batch size: 280 |
| | |
| | precision: 16-mixed |
| | |
