Major update: Add NFL training data generation and improve model handling

Add ChatGPT-style Gradio interface for question generation

Fix XetHub issue: use Meta-Llama-3.1-8B-Instruct (official HF storage)

Fix download errors and warnings: retry logic + clean startup logs

Fix version conflict: use PyTorch 2.5.0 + TorchVision 0.20.0 exact match

Use PyTorch 2.5.1 with safetensors to avoid CVE-2025-32434 - practical fix

Fix PyTorch/TorchVision compatibility: use exact versions 2.6.0/0.21.0

Fix PyTorch CVE-2025-32434: upgrade to v2.6+, use safetensors, restore Llama 3.1

Fix permissions error: proper cache directory and HF token auth for Llama 3.1

Major optimization: Replace llama-cpp-python with transformers to eliminate compilation

Optimize build speed: use pre-built llama-cpp-python wheels, remove build deps

Simplify build: use CPU llama-cpp-python for reliability

Fix LLAMA_CUBLAS deprecated error: Use GGML_CUDA flag with CPU fallback

Add fixed Dockerfile using python:3.10 base image

Initial setup: Question Generation API with DeepHermes reasoning model