fix: f-string backslash syntax error in generate_explanation_text

refactor: clean up inference.py, remove inline comments, extract _patch_xlnet_configs

fix: use slow tokenizer for roberta to avoid tokenizer.json format incompatibility

fix: default MODEL_NAMES to fine-tuned HF repos, fix .gitignore

fix: smart MODELS_DIR path resolution for Docker

fix: remove deprecated use_cache from xlnet config

fix: patch xlnet tokenizer_config at runtime

fix: Python 3.9 compat list[dict] type hints

fix: preload all models at startup

fix: evict model cache to prevent OOM

fix: remove syntax error in xlnet inference

fix: xlnet list fields in _token_importance

fix: xlnet tokenizer list fields

fix: distilbert token_type_ids and xlnet inference errors

Initial deployment