Tabular Classification
PyTorch
TabPFN
tabpfn-finetuned
species-distribution-modeling
ecology
biodiversity
finetuned
Instructions to use rdinnager/tabpfn-sdm-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TabPFN
How to use rdinnager/tabpfn-sdm-finetuned with TabPFN:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| { | |
| "model_type": "tabpfn-finetuned", | |
| "base_model": "Prior-Labs/TabPFN-v2-clf", | |
| "task": "binary-classification", | |
| "domain": "species-distribution-modeling", | |
| "variants": { | |
| "nonspatial": { | |
| "filename": "tabpfn-sdm-nonspatial.pt", | |
| "description": "Standard train/test split evaluation", | |
| "step1_epochs": 40, | |
| "step2_epochs": 100, | |
| "final_val_roc_auc": 0.747, | |
| "final_val_pr_auc": 0.261, | |
| "final_train_loss": 0.460, | |
| "final_val_loss": 3.429 | |
| }, | |
| "spatial": { | |
| "filename": "tabpfn-sdm-spatial.pt", | |
| "description": "Spatially-separated (10km buffer) evaluation", | |
| "step1_epochs": 25, | |
| "step2_epochs": 50, | |
| "final_val_roc_auc": 0.653, | |
| "final_val_pr_auc": 0.144, | |
| "final_train_loss": 0.470, | |
| "final_val_loss": 5.469 | |
| } | |
| }, | |
| "training": { | |
| "optimizer": "AdamW", | |
| "lr_schedule": "OneCycleLR", | |
| "step1_learning_rate": 1e-5, | |
| "step2_learning_rate": 1e-6, | |
| "max_train_size_per_subbatch": 1500, | |
| "max_test_size": 1500, | |
| "n_estimators_training": 2, | |
| "n_estimators_inference": 8, | |
| "seed": 32639, | |
| "species_split_seed": 12345 | |
| }, | |
| "data": { | |
| "total_species": 226, | |
| "finetune_species_fraction": 0.625, | |
| "validation_species_fraction": 0.075, | |
| "test_species_fraction": 0.30, | |
| "regions": ["AWT", "NSW", "CAN", "NZ", "SA", "SWI"], | |
| "categorical_variables": { | |
| "CAN": ["ontveg"], | |
| "NSW": ["vegsys"], | |
| "NZ": ["age", "toxicats"], | |
| "SWI": ["calc"] | |
| } | |
| }, | |
| "checkpoint_format": { | |
| "keys": ["model_state_dict", "config", "history", "step1_path"], | |
| "framework": "pytorch" | |
| } | |
| } | |