feat: add GridMind-RL GRPO training notebook for industrial energy management

scripts/gridmind_grpo_colab.ipynb

@@ -216,20 +216,40 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import torch\n",
     "import gc\n",
+    "import importlib.metadata as importlib_metadata\n",
+    "import subprocess\n",
+    "import sys\n",
+    "\n",
+    "\n",
+    "def _ensure_package(package_name, pip_spec):\n",
+    "    try:\n",
+    "        version = importlib_metadata.version(package_name)\n",
+    "        print(f\"{package_name} {version} already installed\")\n",
+    "    except importlib_metadata.PackageNotFoundError:\n",
+    "        print(f\"Installing {pip_spec}...\")\n",
+    "        subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"-q\", \"-U\", pip_spec])\n",
+    "\n",
+    "\n",
+    "_ensure_package(\"bitsandbytes\", \"bitsandbytes>=0.46.1\")\n",
+    "_ensure_package(\"accelerate\", \"accelerate>=0.34.0\")\n",
+    "\n",
+    "import torch\n",
     "from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig\n",
     "\n",
+    "if not torch.cuda.is_available():\n",
+    "    raise RuntimeError(\"CUDA GPU is not available. In Colab, set Runtime -> Change runtime type -> T4 GPU.\")\n",
+    "\n",
     "# Clear previous model if it exists\n",
-    "for _var in ['model', 'trainer']:\n",
+    "for _var in [\"model\", \"trainer\"]:\n",
     "    if _var in globals():\n",
-    "        exec(f\"del {_var}\")\n",
+    "        del globals()[_var]\n",
     "gc.collect()\n",
     "torch.cuda.empty_cache()\n",
     "\n",
     "MODEL_NAME = \"Qwen/Qwen2.5-1.5B-Instruct\"\n",
     "\n",
-    "print(f\"Loading {MODEL_NAME}...\")\n",
+    "print(f\"Loading {MODEL_NAME} with 4-bit quantization...\")\n",
     "tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)\n",
     "if tokenizer.pad_token is None:\n",
     "    tokenizer.pad_token = tokenizer.eos_token\n",
@@ -253,7 +273,7 @@
     "gpu_used_gb = torch.cuda.memory_allocated() / 1e9\n",
     "\n",
     "print(f\"Model loaded on {next(model.parameters()).device}\")\n",
-    "print(f\"VRAM: {gpu_used_gb:.1f}GB / {gpu_total_gb:.1f}GB\")"
+    "print(f\"GPU memory: {gpu_used_gb:.2f} GB / {gpu_total_gb:.2f} GB\")\n"
    ]
   },
   {