dotfiles

HuggingFace ecosystem — transformers, datasets, huggingface_hub. Model loading, tokenization, training, and dataset handling.

DGL (Deep Graph Library) — graph construction, message passing, GNN layers, heterogeneous graphs, and batching for fraud detection on blockchain graphs

Optuna hyperparameter optimization — study creation, samplers, pruners, storage, and best practices for ML tuning

Pydantic v2 and pydantic-settings — BaseModel, field validation, config structs, and BaseSettings for CLI/config management (replaces argparse.Namespace)

PyTorch Lightning — LightningModule, Trainer, callbacks, logging, and checkpointing patterns for deep learning training loops