Instructions to use CluelessNovice/Subcellular_Localization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use CluelessNovice/Subcellular_Localization with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("westlake-repl/SaProt_35M_AF2") model = PeftModel.from_pretrained(base_model, "CluelessNovice/Subcellular_Localization") - Notebooks
- Google Colab
- Kaggle
| base_model: westlake-repl/SaProt_35M_AF2 | |
| library_name: peft | |
| # Model Card for Model-Subcellular_Localization-35M | |
| This model is used for the Subcellular Localization Classification Task. It takes a protein sequence as input and outputs which of the 10 categories the protein belongs to. | |
| ## Task type | |
| Protein-level Classification | |
| ## Model input type | |
| SA Sequence | |
| ## Label meanings | |
| 0: Nucleus | |
| 1: Cytoplasm | |
| 2: Extracellular | |
| 3: Mitochondrion | |
| 4: Cell.membrane | |
| 5: Endoplasmic.reticulum | |
| 6: Plastid | |
| 7: Golgi.apparatus | |
| 8: Lysosome/Vacuole | |
| 9: Peroxisome | |
| ## LoRA config | |
| - **r:** 8 | |
| - **lora_dropout:** 0.0 | |
| - **lora_alpha:** 16 | |
| - **target_modules:** ['query', 'intermediate.dense', 'key', 'value', 'output.dense'] | |
| - **modules_to_save:** ['classifier'] | |
| ## Training config | |
| - **optimizer:** | |
| - **class:** AdamW | |
| - **betas:** (0.9, 0.98) | |
| - **weight_decay:** 0.01 | |
| - **learning rate:** 0.001 | |
| - **epoch:** 1 | |
| - **batch size:** 2 | |
| - **precision:** 16-mixed | |