Track large data files with Git LFS

Add Kaggle silver training data, retrain model, reorganize data directory

Best model: noise-augmented training, ONNX export, README update

Extract city_country_map to separate file with 317 cities

Make text preprocessor config-driven via resume_config.json

Add noise augmentation for OCR robustness training

Add DATE config and widen entity punctuation cleanup

Add section detection for hybrid NER entity extraction

Fix gold labels: 100% match rate (was 88.8%)

Add text preprocessor for PDF extraction artifacts

Add 93 gold-labeled resume resource training examples

Retrain model with 98 real-world PDF resumes and export ONNX

Make post-processing fully config-driven from resume_config.json

Move post-processing rules from Python to resume_config.json

Remove hand-picked short skills allowlist for generic post-processing

Improve post-processing and add 98 real-world resume training data

Add 50 long dense resume training examples and new synthetic formats

Add section-aware chunked inference for resumes exceeding 512 tokens

Track model weights with Git LFS

Improve structured benchmark analysis and robustness

Clean up training pipeline and add export benchmarks

Initial commit