{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/duoan/TorchCode/blob/master/templates/19_gelu.ipynb)\n",
    "\n",
    "# 🟢 Easy: GELU Activation\n",
    "\n",
    "Implement the **GELU** (Gaussian Error Linear Unit) activation.\n",
    "\n",
    "$$\\text{GELU}(x) = x \\cdot \\Phi(x) = x \\cdot 0.5 \\cdot (1 + \\text{erf}(x / \\sqrt{2}))$$\n",
    "\n",
    "### Signature\n",
    "```python\n",
    "def my_gelu(x: Tensor) -> Tensor: ...\n",
    "```\n",
    "\n",
    "### Rules\n",
    "- Do NOT use `F.gelu`, `nn.GELU`, or `torch.nn.functional.gelu`\n",
    "- Use `torch.erf` for the exact version"
   ],
   "outputs": []
  },
  {
   "cell_type": "code",
   "metadata": {},
   "source": [
    "# Install torch-judge in Colab (no-op in JupyterLab/Docker)\n",
    "try:\n",
    "    import google.colab\n",
    "    get_ipython().run_line_magic('pip', 'install -q torch-judge')\n",
    "except ImportError:\n",
    "    pass\n"
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import math"
   ],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ✏️ YOUR IMPLEMENTATION HERE\n",
    "\n",
    "def my_gelu(x):\n",
    "    pass"
   ],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 🧪 Debug\n",
    "x = torch.tensor([-2., -1., 0., 1., 2.])\n",
    "print('Output:', my_gelu(x))\n",
    "print('Ref:   ', torch.nn.functional.gelu(x))"
   ],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ✅ SUBMIT\n",
    "from torch_judge import check\n",
    "check('gelu')"
   ],
   "execution_count": null
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.11.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}