{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## tokenizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import AutoTokenizer\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"liam168/c2-roberta-base-finetuned-dianping-chinese\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['这', '是', '中', '英', '文', 'test', '语', '句', '，', 'mix', '中', '英', '文', '及', '标', '点', '符', '号']\n"
     ]
    }
   ],
   "source": [
    "input = \"这是中英文test语句，mix中英文及标点符号\"\n",
    "result = tokenizer([input],padding=True,truncation=True,max_length=512,return_tensors=\"pt\")\n",
    "a = tokenizer.tokenize(input)\n",
    "print(a)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'input_ids': tensor([[  101,  6821,  3221,   704,  5739,  3152, 10060,  6427,  1368,  8024,\n",
      "          9678,   704,  5739,  3152,  1350,  3403,  4157,  5016,  1384,   102]]), 'token_type_ids': tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]), 'attention_mask': tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]])}\n"
     ]
    }
   ],
   "source": [
    "#print(result.input_ids)\n",
    "print(result)\n",
    "tokenizer.convert_ids_to_tokens(result.input_ids)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.10"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "916dbcbb3f70747c44a77c7bcd40155683ae19c65e1c03b4aa3499c5328201f1"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}