fix: enable sampling — temperature=0.8 for MCQ, 0.4 for evaluator

feat: retarget fine-tune pipeline to MiniCPM4.1-8B

feat: upgrade to MiniCPM4.1-8B + official GGUF, disable thinking mode

feat: llama.cpp runtime ready for the Space (Llama Champion)

feat: switch to our fine-tuned MiniCPM4-8B-PaperProf model (Well-Tuned)

feat: Well-Tuned + Llama Champion groundwork

fix: skip bitsandbytes on HF Spaces (ZeroGPU), only use 4-bit locally

fix: infinite spinner on question gen, 4-bit quant for low VRAM

feat: switch to MiniCPM4-8B, add robustness, score tracker, language selector

fix: switch to MiniCPM3-4B for better transformers compatibility

feat: initial project structure with all core modules