docs: rewrite README with tech stack, full API reference, and training guide

chore: remove unused model checkpoints

docs: fix README model name, add health endpoint, fix local dev port

fix: pin dependency versions, seed data split, add missing scikit-learn, fix size limit comment

fix: add file size limit, return 400 on invalid images, use inference_mode

refactor: consolidate 8 duplicated train/eval scripts into 2 parameterized scripts

fix: fail fast on model load error instead of silently continuing

Update .gitattributes with comprehensive LFS tracking patterns

Add GitHub Action to sync with Hugging Face Space

Sync: Align with Hugging Face deployment, set up Git LFS for models, and consolidate project structure

Robustness Update: Added confidence thresholding, file type validation, and error handling

Initial commit: Food Spoilage Detection Project with Swin Transformer