feat: add Kaggle training notebook

- 9-step notebook for Kaggle GPU training
- Uses Kaggle P100 (16GB VRAM)
- Downloads model, trains LoRA, merges model

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

kaggle_train_stack29.ipynb

@@ -0,0 +1,213 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# 🚀 Stack 2.9 - Kaggle Training Notebook\n",
+    "\n",
+    "**Free GPU training on Kaggle**\n",
+    "\n",
+    "This notebook trains a LoRA adapter for Stack 2.9 on **Qwen2.5-Coder-7B** using Kaggle's free GPU.\n",
+    "\n",
+    "⏱️ **Expected runtime:** 2-4 hours\n",
+    "💾 **VRAM needed:** ~16GB (Kaggle P100 has 16GB)\n",
+    "\n",
+    "---\n",
+    "\n",
+    "**Instructions:**\n",
+    "1. Kaggle → New Notebook\n",
+    "2. Add this notebook's code OR clone from GitHub\n",
+    "3. Enable GPU (Settings → Accelerator → GPU P100)\n",
+    "4. Run cells in order\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check GPU\n",
+    "!nvidia-smi"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 1: Clone the repo\n",
+    "import os\n",
+    "import shutil\n",
+    "\n",
+    "REPO_DIR = \"/kaggle/working/stack-2.9\"\n",
+    "\n",
+    "# Remove old if exists\n",
+    "if os.path.exists(REPO_DIR):\n",
+    "    shutil.rmtree(REPO_DIR)\n",
+    "\n",
+    "!git clone https://github.com/my-ai-stack/stack-2.9.git {REPO_DIR}\n",
+    "\n",
+    "os.chdir(REPO_DIR)\n",
+    "print(f\"✅ Working in: {os.getcwd()}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 2: Install dependencies\n",
+    "!pip install -q torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118\n",
+    "!pip install -q transformers peft accelerate datasets pyyaml tqdm scipy bitsandbytes\n",
+    "print(\"✅ Dependencies installed\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 3: Download Base Model\n",
+    "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
+    "\n",
+    "MODEL_NAME = \"Qwen/Qwen2.5-Coder-7B\"\n",
+    "MODEL_DIR = os.path.join(REPO_DIR, \"base_model_qwen7b\")\n",
+    "\n",
+    "if not os.path.exists(os.path.join(MODEL_DIR, \"config.json\")):\n",
+    "    print(f\"Downloading {MODEL_NAME}...\")\n",
+    "    print(\"This takes ~10-15 minutes...\")\n",
+    "    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)\n",
+    "    tokenizer.save_pretrained(MODEL_DIR)\n",
+    "    model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, trust_remote_code=True)\n",
+    "    model.save_pretrained(MODEL_DIR)\n",
+    "    print(\"✅ Model downloaded!\")\n",
+    "else:\n",
+    "    print(\"✅ Model already exists\")\n",
+    "\n",
+    "!ls -lh {MODEL_DIR} | head -5"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 4: Setup paths and config\n",
+    "import yaml\n",
+    "\n",
+    "config_path = os.path.join(REPO_DIR, \"stack/training/train_config_local.yaml\")\n",
+    "\n",
+    "with open(config_path, 'r') as f:\n",
+    "    config = yaml.safe_load(f)\n",
+    "\n",
+    "# Update for Kaggle GPU\n",
+    "config['model']['name'] = MODEL_DIR\n",
+    "config['hardware']['device'] = \"cuda\"\n",
+    "config['hardware']['num_gpus'] = 1\n",
+    "\n",
+    "OUTPUT_DIR = os.path.join(REPO_DIR, \"training_output\")\n",
+    "config['output']['lora_dir'] = os.path.join(OUTPUT_DIR, \"lora\")\n",
+    "config['output']['merged_dir'] = os.path.join(OUTPUT_DIR, \"merged\")\n",
+    "\n",
+    "os.makedirs(OUTPUT_DIR, exist_ok=True)\n",
+    "updated_config = os.path.join(OUTPUT_DIR, \"train_config.yaml\")\n",
+    "\n",
+    "with open(updated_config, 'w') as f:\n",
+    "    yaml.dump(config, f)\n",
+    "\n",
+    "print(f\"✅ Config saved to: {updated_config}\")\n",
+    "print(f\"   Device: {config['hardware']['device']}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 5: Train LoRA\n",
+    "import sys\n",
+    "sys.path.insert(0, os.path.join(REPO_DIR, \"stack/training\"))\n",
+    "\n",
+    "print(\"=\"*60)\n",
+    "print(\"STARTING TRAINING\")\n",
+    "print(\"=\"*60)\n",
+    "\n",
+    "from train_lora import train_lora\n",
+    "trainer = train_lora(updated_config)\n",
+    "\n",
+    "print(\"=\"*60)\n",
+    "print(\"TRAINING COMPLETED\")\n",
+    "print(\"=\"*60)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 6: Merge and save\n",
+    "import sys\n",
+    "sys.path.insert(0, os.path.join(REPO_DIR, \"stack/training\"))\n",
+    "from merge_adapter import merge_adapter\n",
+    "\n",
+    "merged_dir = os.path.join(OUTPUT_DIR, \"merged\")\n",
+    "os.makedirs(merged_dir, exist_ok=True)\n",
+    "\n",
+    "merge_config = {\n",
+    "    'model': {'name': MODEL_DIR, 'trust_remote_code': True},\n",
+    "    'output': {'lora_dir': os.path.join(OUTPUT_DIR, 'lora'), 'merged_dir': merged_dir},\n",
+    "    'quantization': {'enabled': False}\n",
+    "}\n",
+    "\n",
+    "merge_cfg_path = os.path.join(OUTPUT_DIR, \"merge_config.yaml\")\n",
+    "with open(merge_cfg_path, 'w') as f:\n",
+    "    yaml.dump(merge_config, f)\n",
+    "\n",
+    "merge_adapter(merge_cfg_path, os.path.join(OUTPUT_DIR, \"lora\"), merged_dir)\n",
+    "\n",
+    "print(f\"✅ Model saved to: {merged_dir}\")\n",
+    "!ls -lh {merged_dir}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 7: Download the trained model (for saving)\n",
+    "# The model is saved at OUTPUT_DIR/merged/\n",
+    "# You can download it from the Kaggle outputs\n",
+    "\n",
+    "print(\"Training complete!\")\n",
+    "print(f\"Model saved at: {merged_dir}\")\n",
+    "print(\"\\nTo download:\")\n",
+    "print(\"1. Click 'Output' tab in Kaggle\")\n",
+    "print(\"2. Download the files from training_output/merged/\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kaggle": {
+   "accelerator": "gpu",
+   "dataSources": [],
+   "kernelSpec": {
+    "displayName": "Python 3",
+    "language": "python",
+    "name": "python3"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}