docs: update README with UI improvements and Advanced Mode features

docs: update README with new UI features and custom GGUF loading

feat: Add GLM-4.7-Flash-30B (Original) IQ2_XXS 2-bit quantization

feat: Add Breeze 3B Q4 model (mradermacher/breeze-3b-GGUF)

docs: Update README with 22 models, reasoning modes, and GPU support

Exclude transcripts from HF Spaces deployment

Add HuggingFace Spaces demo with Gradio UI

refactor: fix streaming summary bug and simplify to streaming-only output