{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['lets', '##s', 'try', 'to', 'token', '##ize']\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')\n",
    "tokens = tokenizer.tokenize('''Letss try to tokenize''')\n",
    "print(tokens)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c2fdecef86644ec1b3467bf653e8d30d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)lve/main/config.json:   0%|          | 0.00/684 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6a4c6b7d714c40ca9695acf581de7bb2",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)ve/main/spiece.model:   0%|          | 0.00/760k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "49267a76ecfc4aee9d4906e96ddbca5b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)/main/tokenizer.json:   0%|          | 0.00/1.31M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['▁let', \"'\", 's', '▁learn', '▁to', '▁code', '▁in', '▁hugging', 'face']\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "albert_tokenizer = AutoTokenizer.from_pretrained('albert-base-v2')\n",
    "tokens = albert_tokenizer.tokenize('''Let's learn to code in huggingface''')\n",
    "print(tokens)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['these', 'are', 'broken', 'down', 'into', 'token', '##s']\n",
      "[2122, 2024, 3714, 2091, 2046, 19204, 2015]\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "tokeninzer = AutoTokenizer.from_pretrained('bert-base-uncased')\n",
    "tokens = tokenizer.tokenize('These are broken down into tokens')\n",
    "print(tokens)\n",
    "input_ids = tokenizer.convert_tokens_to_ids(tokens)\n",
    "print(input_ids)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['this', 'is', 'me', 'practicing']\n",
      "[2023, 2003, 2033, 12560]\n",
      "['this', 'is', 'me', 'practicing']\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')\n",
    "tokens = tokenizer.tokenize('This is me practicing')\n",
    "print(tokens)\n",
    "\n",
    "input_ids = tokenizer.convert_tokens_to_ids(tokens)\n",
    "print(input_ids)\n",
    "\n",
    "tokens = tokenizer.convert_ids_to_tokens(input_ids)\n",
    "print(tokens)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['this', 'is', 'me', 'practicing']\n",
      "[2023, 2003, 2033, 12560]\n",
      "['this', 'is', 'me', 'practicing']\n",
      "this is me practicing\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')\n",
    "tokens = tokenizer.tokenize('This is me practicing')\n",
    "print(tokens)\n",
    "input_ids = tokenizer.convert_tokens_to_ids(tokens)\n",
    "print(input_ids)\n",
    "tokens_2 = tokenizer.convert_ids_to_tokens(input_ids)\n",
    "print(tokens_2)\n",
    "strings = tokenizer.convert_tokens_to_string(tokens)\n",
    "print(strings)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "You're using a BertTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'input_ids': [101, 2023, 2003, 2033, 12560, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1]}\n"
     ]
    }
   ],
   "source": [
    "final_ids = tokenizer.prepare_for_model(input_ids)\n",
    "print(final_ids)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "You're using a BertTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['this', 'is', 'me', 'practicing', 'the', 'use', 'of', 'auto', '##tok', '##eni', '##zer']\n",
      "[2023, 2003, 2033, 12560, 1996, 2224, 1997, 8285, 18715, 18595, 6290]\n",
      "{'input_ids': [101, 2023, 2003, 2033, 12560, 1996, 2224, 1997, 8285, 18715, 18595, 6290, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}\n",
      "[CLS] this is me practicing the use of autotokenizer [SEP]\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "sentence = 'This is me practicing the use of AutoTokenizer'\n",
    "tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')\n",
    "tokens = tokenizer.tokenize(sentence)\n",
    "print(tokens)\n",
    "input_ids = tokenizer.convert_tokens_to_ids(tokens)\n",
    "print(input_ids)\n",
    "inputs = tokenizer.prepare_for_model(input_ids)\n",
    "print(inputs)\n",
    "\n",
    "decode = tokenizer.decode(inputs['input_ids'])\n",
    "print(decode)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}