course/videos/tokenizer_pipeline.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook regroups the code sample of the video below, which is a part of the [Hugging Face course](https://huggingface.co/course)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "cellView": "form"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/Yffk5aydLzg?rel=0&amp;controls=0&amp;showinfo=0\" frameborder=\"0\" allowfullscreen></iframe>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#@title\n",
    "from IPython.display import HTML\n",
    "\n",
    "HTML('<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/Yffk5aydLzg?rel=0&amp;controls=0&amp;showinfo=0\" frameborder=\"0\" allowfullscreen></iframe>')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Install the Transformers and Datasets libraries to run this notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "! pip install datasets transformers[sentencepiece]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[101, 2292, 1005, 1055, 3046, 2000, 19204, 4697, 999, 102]\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"bert-base-uncased\")\n",
    "inputs = tokenizer(\"Let's try to tokenize!\")\n",
    "print(inputs[\"input_ids\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['let', \"'\", 's', 'try', 'to', 'token', '##ize', '!']\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"bert-base-uncased\")\n",
    "tokens = tokenizer.tokenize(\"Let's try to tokenize!\")\n",
    "print(tokens)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['▁let', \"'\", 's', '▁try', '▁to', '▁to', 'ken', 'ize', '!']\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"albert-base-v1\")\n",
    "tokens = tokenizer.tokenize(\"Let's try to tokenize!\")\n",
    "print(tokens)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2292, 1005, 1055, 3046, 2000, 19204, 4697, 999]\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"bert-base-uncased\")\n",
    "tokens = tokenizer.tokenize(\"Let's try to tokenize!\")\n",
    "input_ids = tokenizer.convert_tokens_to_ids(tokens)\n",
    "print(input_ids)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[101, 2292, 1005, 1055, 3046, 2000, 19204, 4697, 999, 102]\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"bert-base-uncased\")\n",
    "tokens = tokenizer.tokenize(\"Let's try to tokenize!\")\n",
    "input_ids = tokenizer.convert_tokens_to_ids(tokens)\n",
    "final_inputs = tokenizer.prepare_for_model(input_ids)\n",
    "print(final_inputs[\"input_ids\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CLS] let's try to tokenize! [SEP]\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"bert-base-uncased\")\n",
    "inputs = tokenizer(\"Let's try to tokenize!\")\n",
    "\n",
    "print(tokenizer.decode(inputs[\"input_ids\"]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<s>Let's try to tokenize!</s>\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"roberta-base\")\n",
    "inputs = tokenizer(\"Let's try to tokenize!\")\n",
    "\n",
    "print(tokenizer.decode(inputs[\"input_ids\"]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'input_ids': [101, 2292, 1005, 1055, 3046, 2000, 19204, 4697, 999, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"bert-base-uncased\")\n",
    "inputs = tokenizer(\"Let's try to tokenize!\")\n",
    "print(inputs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "The tokenization pipeline",
   "provenance": []
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}