build-small-hackathon/Case-Lantern

Update README.md

Upgrade llama-cpp-python CPU wheel

Use prebuilt CPU llama-cpp wheel

Fix llama.cpp CPU deployment on Spaces

Fix model loading: verbose logging, proper GPU detection, detailed error messages

Remove show_api (removed in Gradio 6) from launch kwargs

Remove deprecated show_copy_button param from Chatbot (Gradio 6)

Migrate to Gradio 6 API: theme/css/head to launch(), remove Chatbot type param

Upgrade to gradio 6.15.2 (latest) to fix json_schema bug

Fix: remove gradio/huggingface_hub version pins to resolve spaces compatibility

Pin huggingface_hub<0.27 to fix HfFolder import error with Gradio 4.44.1

Use prebuilt CUDA wheel for llama-cpp-python (skip compilation)

Add ZeroGPU support: @spaces.GPU + n_gpu_layers=-1

Case Lantern: GGUF backend + custom dark frontend for Build Small Hackathon