LLMs-from-scratch/ch02/01_main-chapter-code/exercise-solutions.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "ab88d307-61ba-45ef-89bc-e3569443dfca",
   "metadata": {},
   "source": [
    "# Chapter 2 Exercise solutions"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6f678e62-7bcb-4405-86ae-dce94f494303",
   "metadata": {},
   "source": [
    "# Exercise 2.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7614337f-f639-42c9-a99b-d33f74fa8a03",
   "metadata": {},
   "outputs": [],
   "source": [
    "import tiktoken\n",
    "\n",
    "tokenizer = tiktoken.get_encoding(\"gpt2\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "664397bc-6daa-4b88-90aa-e8fc1fbd5846",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[33901]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.encode(\"Ak\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "d3664332-e6bb-447e-8b96-203aafde8b24",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[86]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.encode(\"w\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2773c09d-c136-4372-a2be-04b58d292842",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[343]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.encode(\"ir\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "8a6abd32-1e0a-4038-9dd2-673f47bcdeb5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[86]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.encode(\"w\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "26ae940a-9841-4e27-a1df-b83fc8a488b3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[220]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.encode(\" \")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "a606c39a-6747-4cd8-bb38-e3183f80908d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[959]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.encode(\"ier\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "47c7268d-8fdc-4957-bc68-5be6113f45a7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Akwirw ier'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.decode([33901, 86, 343, 86, 220, 959])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "29e5034a-95ed-46d8-9972-589354dc9fd4",
   "metadata": {},
   "source": [
    "# Exercise 2.2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "4d50af16-937b-49e0-8ffd-42d30cbb41c9",
   "metadata": {},
   "outputs": [],
   "source": [
    "import tiktoken\n",
    "import torch\n",
    "from torch.utils.data import Dataset, DataLoader\n",
    "\n",
    "\n",
    "class GPTDatasetV1(Dataset):\n",
    "    def __init__(self, txt, tokenizer, max_length, stride):\n",
    "        self.tokenizer = tokenizer\n",
    "        self.input_ids = []\n",
    "        self.target_ids = []\n",
    "\n",
    "        # Tokenize the entire text\n",
    "        token_ids = tokenizer.encode(txt)\n",
    "\n",
    "        # Use a sliding window to chunk the book into overlapping sequences of max_length\n",
    "        for i in range(0, len(token_ids) - max_length, stride):\n",
    "            input_chunk = token_ids[i:i + max_length]\n",
    "            target_chunk = token_ids[i + 1: i + max_length + 1]\n",
    "            self.input_ids.append(torch.tensor(input_chunk))\n",
    "            self.target_ids.append(torch.tensor(target_chunk))\n",
    "\n",
    "    def __len__(self):\n",
    "        return len(self.input_ids)\n",
    "\n",
    "    def __getitem__(self, idx):\n",
    "        return self.input_ids[idx], self.target_ids[idx]\n",
    "\n",
    "\n",
    "def create_dataloader(txt, batch_size=4, max_length=256, stride=128):\n",
    "    # Initialize the tokenizer\n",
    "    tokenizer = tiktoken.get_encoding(\"gpt2\")\n",
    "\n",
    "    # Create dataset\n",
    "    dataset = GPTDatasetV1(txt, tokenizer, max_length, stride)\n",
    "\n",
    "    # Create dataloader\n",
    "    dataloader = DataLoader(dataset, batch_size=batch_size)\n",
    "\n",
    "    return dataloader\n",
    "\n",
    "\n",
    "with open(\"the-verdict.txt\", \"r\", encoding=\"utf-8\") as f:\n",
    "    raw_text = f.read()\n",
    "\n",
    "tokenizer = tiktoken.get_encoding(\"gpt2\")\n",
    "encoded_text = tokenizer.encode(raw_text)\n",
    "\n",
    "vocab_size = 50257\n",
    "output_dim = 256\n",
    "token_embedding_layer = torch.nn.Embedding(vocab_size, output_dim)\n",
    "pos_embedding_layer = torch.nn.Embedding(vocab_size, output_dim)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "0128eefa-d7c8-4f76-9851-566dfa7c3745",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[  40,  367],\n",
       "        [2885, 1464],\n",
       "        [1807, 3619],\n",
       "        [ 402,  271]])"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataloader = create_dataloader(raw_text, batch_size=4, max_length=2, stride=2)\n",
    "\n",
    "for batch in dataloader:\n",
    "    x, y = batch\n",
    "    break\n",
    "\n",
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "ff5c1e90-c6de-4a87-adf6-7e19f603291c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[   40,   367,  2885,  1464,  1807,  3619,   402,   271],\n",
       "        [ 2885,  1464,  1807,  3619,   402,   271, 10899,  2138],\n",
       "        [ 1807,  3619,   402,   271, 10899,  2138,   257,  7026],\n",
       "        [  402,   271, 10899,  2138,   257,  7026, 15632,   438]])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataloader = create_dataloader(raw_text, batch_size=4, max_length=8, stride=2)\n",
    "\n",
    "for batch in dataloader:\n",
    "    x, y = batch\n",
    "    break\n",
    "\n",
    "x"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}