set_tokens.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from tokenizers.processors import BertProcessing\n",
    "\n",
    "# set [CLS] and [SEP] to be added to start-end of sequences\n",
    "tokenizer._tokenizer.post_processor = BertProcessing(\n",
    "    ('[SEP]', tokenizer.token_to_id('[SEP]')),\n",
    "    ('[CLS]', tokenizer.token_to_id('[CLS]'))\n",
    ")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "ML",
   "language": "python",
   "name": "ml"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}