feat: add script to migrate max_new_tokens from GRPOConfig to GRPOTrainer in notebook

fix: move max_new_tokens from GRPOConfig to GRPOTrainer generation_kwargs

feat: add script to patch gridmind_grpo_colab.ipynb with torch import in cell 5e5826e4

feat: add script to automate TRL dependency updates in the GRPO Colab notebook

chore: add script to update trl dependency version in gridmind_grpo_colab.ipynb

feat: update HF space URL, add judge demo scripts and project documentation

fix: update health check endpoint in GridMind notebook and provide utility script to apply fix