Add official Google Colab quickstart notebook

vibe_coder_quickstart.ipynb

@@ -0,0 +1,163 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# 🚀 VIBE CODER v2.0 MAX — Official Google Colab Quickstart\n",
+    "\n",
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/shawaz03/vibe-coder/blob/main/vibe_coder_quickstart.ipynb)\n",
+    "\n",
+    "This notebook demonstrates how to run **Vibe Coder v2.0 MAX (7B)** on a **Free Google Colab T4 GPU** using **4-bit NF4 Quantization** (uses only ~5.2 GB VRAM with zero memory warnings).\n",
+    "\n",
+    "- **Model**: [`shawaz03/vibe-coder-7b-max`](https://huggingface.co/shawaz03/vibe-coder-7b-max)\n",
+    "- **Specialization**: Full-Stack React, Next.js 15, TypeScript, Tailwind CSS, Prisma, Zustand, and Anti-AI Aesthetic Directives."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 1. Install Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Install required libraries\n",
+    "!pip install -q transformers torch accelerate bitsandbytes huggingface_hub"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 2. Load Model in 4-bit (Fast & Zero Memory Overhead)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer\n",
+    "\n",
+    "MODEL_ID = \"shawaz03/vibe-coder-7b-max\"\n",
+    "\n",
+    "print(f\"🚀 Loading {MODEL_ID} in 4-bit NF4 for Google Colab...\")\n",
+    "\n",
+    "# 4-bit configuration (Fits smoothly in 5.2 GB VRAM on Colab T4)\n",
+    "bnb_config = BitsAndBytesConfig(\n",
+    "    load_in_4bit=True,\n",
+    "    bnb_4bit_quant_type=\"nf4\",\n",
+    "    bnb_4bit_use_double_quant=True,\n",
+    "    bnb_4bit_compute_dtype=torch.float16,\n",
+    ")\n",
+    "\n",
+    "tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)\n",
+    "model = AutoModelForCausalLM.from_pretrained(\n",
+    "    MODEL_ID,\n",
+    "    quantization_config=bnb_config,\n",
+    "    device_map=\"auto\",\n",
+    "    trust_remote_code=True,\n",
+    ")\n",
+    "model.eval()\n",
+    "streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)\n",
+    "\n",
+    "print(\"\\n✅ VIBE CODER IS READY TO GENERATE CODE!\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 3. Interactive Code Generator"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Vibe Coder System Prompt\n",
+    "VIBE_CODER_SYSTEM_PROMPT = \"\"\"You are Vibe Coder, a world-class principal full-stack software engineer and UI/UX designer.\n",
+    "ENGINEERING DIRECTIVES:\n",
+    "1. ZERO PLACEHOLDERS: Never output '// TODO' or incomplete stubs. Every component, hook, and route must be fully written.\n",
+    "2. MODERN DESIGN SYSTEM: Use Tailwind CSS with dark neutral palettes (bg-neutral-900, border-neutral-800), clean accents (cyan, emerald, violet), and Lucide icons.\n",
+    "3. TYPE SAFETY: Include full TypeScript interfaces and prop types.\"\"\"\n",
+    "\n",
+    "def ask_vibe_coder(prompt_text, temperature=0.2, max_tokens=1500):\n",
+    "    messages = [\n",
+    "        {\"role\": \"system\", \"content\": VIBE_CODER_SYSTEM_PROMPT},\n",
+    "        {\"role\": \"user\", \"content\": prompt_text}\n",
+    "    ]\n",
+    "    \n",
+    "    formatted_prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)\n",
+    "    inputs = tokenizer(formatted_prompt, return_tensors=\"pt\").to(\"cuda\")\n",
+    "    \n",
+    "    print(\"=\" * 75)\n",
+    "    print(f\"🚀 PROMPT: {prompt_text}\")\n",
+    "    print(\"=\" * 75 + \"\\n\")\n",
+    "    \n",
+    "    with torch.no_grad():\n",
+    "        model.generate(\n",
+    "            **inputs,\n",
+    "            streamer=streamer,\n",
+    "            max_new_tokens=max_tokens,\n",
+    "            temperature=temperature,\n",
+    "            top_p=0.95,\n",
+    "            repetition_penalty=1.05,\n",
+    "            do_sample=True,\n",
+    "            eos_token_id=tokenizer.eos_token_id,\n",
+    "            pad_token_id=tokenizer.pad_token_id,\n",
+    "        )\n",
+    "    print(\"\\n\" + \"=\" * 75)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 4. Run Example Prompts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Example 1: Full-Stack Component\n",
+    "ask_vibe_coder(\"Build an interactive pricing card in React with Tailwind CSS, monthly/annual toggle, and checkmark feature list.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Example 2: Next.js Server Action\n",
+    "ask_vibe_coder(\"Write a Next.js Server Action with Zod validation to update user settings with error handling.\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "gpuType": "T4",
+   "provenance": []
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}