{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import AutoTokenizer, LlamaForCausalLM\n",
    "\n",
    "model_id = \"meta-llama/Llama-3.2-1B-Instruct\"\n",
    "tokenizer = AutoTokenizer.from_pretrained(model_id, cache_dir=\"wm_detector/static/hf_cache\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[4438, 311, 1304, 264, 19692]\n",
      "['How', 'Ġto', 'Ġmake', 'Ġa', 'Ġcake']\n",
      "['How', ' to', ' make', ' a', ' cake']\n"
     ]
    }
   ],
   "source": [
    "def tokenize_text(text):\n",
    "    return tokenizer.encode(text, add_special_tokens=False)\n",
    "\n",
    "text = \"How to make a cake\"\n",
    "token_ids = tokenize_text(text)\n",
    "tokens = tokenizer.convert_ids_to_tokens(token_ids)\n",
    "token_strs = [tokenizer.convert_tokens_to_string([token]) for token in tokens]\n",
    "decoded = tokenizer.decode(tokenize_text(text))\n",
    "\n",
    "print(token_ids)\n",
    "print(tokens)\n",
    "print(token_strs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}