Fix Gradio runtime error by moving theme to gr.Blocks

Update with existing environment

Fix GRPO group-loss training and align UI defaults.

Migrate LLM pipeline to custom GRPO with robust rewards

Multi-model benchmark pipeline: VRAM cleanup + EMA graph + detailed output

Max GPU utilization: flash-attn2 + grad accumulation + 15 steps/ep + 1024 seq len

Cap LLM iterations at 50 to prevent timeout on 8B models

Switch to Llama 3.1 8B + fix low-timestep crash (min 5000)

Add LLM RL training with Gemma 7B + LoRA

Fix Gradio 6.0 theme deprecation

Add Cloud Arena Mathematical Model RL environment