deploy: Space overrides -- CUDA requirements.txt and app_space.py entry point

refactor: Collapse four inference backends into one MLX path

fix: Use a prebuilt CPU wheel for llama-cpp-python, not a source build

fix: Wire up the GGUF deployment path and fix its tokenizer mismatch

fix: Include the actual Gradio/ZeroGPU code changes missed in the last commit

feat: Enforce high-speed GGUF Q4_K_M llama_cpp execution on Hugging Face Spaces CPU

fix: Add jsonschema, scikit-learn, pyyaml, and dependencies to requirements.txt

feat: Add Dockerfile and Hugging Face Space configuration

fix: Simplify Colab notebook, fix rank_bm25 import handling, and clean up prompts