diff --git "a/Week 16_\354\230\210\354\212\265\352\263\274\354\240\234_\353\254\270\354\233\220\354\240\225.ipynb" "b/Week 16_\354\230\210\354\212\265\352\263\274\354\240\234_\353\254\270\354\233\220\354\240\225.ipynb"
new file mode 100644
index 0000000..2e16e06
--- /dev/null
+++ "b/Week 16_\354\230\210\354\212\265\352\263\274\354\240\234_\353\254\270\354\233\220\354\240\225.ipynb"	
@@ -0,0 +1,831 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "e14558a2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "534b48b6df5241d8ab12ea1ef1e337ef",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/972k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "f8b104277e084ad6aa3d377ae717da8a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/29.0 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "34c34d422a47418c8f87ba1256dd903a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/1.87M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ed24fd0ad927464d8475adb81d5434ef",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/625 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "from transformers import BertTokenizer, BertModel\n",
+    "tokenizer = BertTokenizer.from_pretrained('bert-base-multilingual-cased')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "cfe6d8ae",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['[CLS]', '나는', '파', '##이', '##토', '##치를', '이', '##용한', '딥', '##러', '##닝', '##을', '학', '##습', '##중', '##이다', '.', '[SEP]']\n"
+     ]
+    }
+   ],
+   "source": [
+    "text = \"나는 파이토치를 이용한 딥러닝을 학습중이다.\"\n",
+    "marked_text = \"[CLS] \" + text + \" [SEP]\"\n",
+    "tokenized_text = tokenizer.tokenize(marked_text)\n",
+    "print(tokenized_text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3740f31f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[CLS]           101\n",
+      "과             8,898\n",
+      "##수          15,891\n",
+      "##원에         108,280\n",
+      "사             9,405\n",
+      "##과          11,882\n",
+      "##가          11,287\n",
+      "많             9,249\n",
+      "##았다         27,303\n",
+      ".               119\n",
+      "친             9,781\n",
+      "##구          17,196\n",
+      "##가          11,287\n",
+      "나             8,982\n",
+      "##에게         26,212\n",
+      "사             9,405\n",
+      "##과          11,882\n",
+      "##했다         12,490\n",
+      ".               119\n",
+      "백             9,331\n",
+      "##설          31,928\n",
+      "##공          28,000\n",
+      "##주는         100,633\n",
+      "독             9,088\n",
+      "##이          10,739\n",
+      "든             9,115\n",
+      "사             9,405\n",
+      "##과          11,882\n",
+      "##를          11,513\n",
+      "먹             9,266\n",
+      "##었다         17,706\n",
+      ".               119\n",
+      "[SEP]           102\n"
+     ]
+    }
+   ],
+   "source": [
+    "text = \"과수원에 사과가 많았다.\" \\\n",
+    "       \"친구가 나에게 사과했다.\"\\\n",
+    "       \"백설공주는 독이 든 사과를 먹었다.\"\n",
+    "\n",
+    "marked_text = \"[CLS] \" + text + \" [SEP]\"\n",
+    "tokenized_text = tokenizer.tokenize(marked_text)\n",
+    "indexed_tokens = tokenizer.convert_tokens_to_ids(tokenized_text)\n",
+    "\n",
+    "for tup in zip(tokenized_text, indexed_tokens):\n",
+    "    print('{:<12} {:>6,}'.format(tup[0], tup[1]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "9da9f047",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]\n"
+     ]
+    }
+   ],
+   "source": [
+    "segments_ids = [1] * len(tokenized_text)\n",
+    "print (segments_ids)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "1b9a81c0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tokens_tensor = torch.tensor([indexed_tokens])\n",
+    "segments_tensors = torch.tensor([segments_ids])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "2637806e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b75c2ed4c0e745169544118ef8889ad5",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          | 0.00/681M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Some weights of the model checkpoint at bert-base-multilingual-cased were not used when initializing BertModel: ['cls.predictions.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.decoder.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.bias']\n",
+      "- This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
+      "- This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "BertModel(\n",
+       "  (embeddings): BertEmbeddings(\n",
+       "    (word_embeddings): Embedding(119547, 768, padding_idx=0)\n",
+       "    (position_embeddings): Embedding(512, 768)\n",
+       "    (token_type_embeddings): Embedding(2, 768)\n",
+       "    (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "    (dropout): Dropout(p=0.1, inplace=False)\n",
+       "  )\n",
+       "  (encoder): BertEncoder(\n",
+       "    (layer): ModuleList(\n",
+       "      (0): BertLayer(\n",
+       "        (attention): BertAttention(\n",
+       "          (self): BertSelfAttention(\n",
+       "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (output): BertSelfOutput(\n",
+       "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "        (intermediate): BertIntermediate(\n",
+       "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "        )\n",
+       "        (output): BertOutput(\n",
+       "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (dropout): Dropout(p=0.1, inplace=False)\n",
+       "        )\n",
+       "      )\n",
+       "      (1): BertLayer(\n",
+       "        (attention): BertAttention(\n",
+       "          (self): BertSelfAttention(\n",
+       "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (output): BertSelfOutput(\n",
+       "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "        (intermediate): BertIntermediate(\n",
+       "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "        )\n",
+       "        (output): BertOutput(\n",
+       "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (dropout): Dropout(p=0.1, inplace=False)\n",
+       "        )\n",
+       "      )\n",
+       "      (2): BertLayer(\n",
+       "        (attention): BertAttention(\n",
+       "          (self): BertSelfAttention(\n",
+       "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (output): BertSelfOutput(\n",
+       "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "        (intermediate): BertIntermediate(\n",
+       "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "        )\n",
+       "        (output): BertOutput(\n",
+       "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (dropout): Dropout(p=0.1, inplace=False)\n",
+       "        )\n",
+       "      )\n",
+       "      (3): BertLayer(\n",
+       "        (attention): BertAttention(\n",
+       "          (self): BertSelfAttention(\n",
+       "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (output): BertSelfOutput(\n",
+       "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "        (intermediate): BertIntermediate(\n",
+       "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "        )\n",
+       "        (output): BertOutput(\n",
+       "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (dropout): Dropout(p=0.1, inplace=False)\n",
+       "        )\n",
+       "      )\n",
+       "      (4): BertLayer(\n",
+       "        (attention): BertAttention(\n",
+       "          (self): BertSelfAttention(\n",
+       "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (output): BertSelfOutput(\n",
+       "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "        (intermediate): BertIntermediate(\n",
+       "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "        )\n",
+       "        (output): BertOutput(\n",
+       "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (dropout): Dropout(p=0.1, inplace=False)\n",
+       "        )\n",
+       "      )\n",
+       "      (5): BertLayer(\n",
+       "        (attention): BertAttention(\n",
+       "          (self): BertSelfAttention(\n",
+       "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (output): BertSelfOutput(\n",
+       "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "        (intermediate): BertIntermediate(\n",
+       "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "        )\n",
+       "        (output): BertOutput(\n",
+       "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (dropout): Dropout(p=0.1, inplace=False)\n",
+       "        )\n",
+       "      )\n",
+       "      (6): BertLayer(\n",
+       "        (attention): BertAttention(\n",
+       "          (self): BertSelfAttention(\n",
+       "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (output): BertSelfOutput(\n",
+       "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "        (intermediate): BertIntermediate(\n",
+       "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "        )\n",
+       "        (output): BertOutput(\n",
+       "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (dropout): Dropout(p=0.1, inplace=False)\n",
+       "        )\n",
+       "      )\n",
+       "      (7): BertLayer(\n",
+       "        (attention): BertAttention(\n",
+       "          (self): BertSelfAttention(\n",
+       "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (output): BertSelfOutput(\n",
+       "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "        (intermediate): BertIntermediate(\n",
+       "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "        )\n",
+       "        (output): BertOutput(\n",
+       "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (dropout): Dropout(p=0.1, inplace=False)\n",
+       "        )\n",
+       "      )\n",
+       "      (8): BertLayer(\n",
+       "        (attention): BertAttention(\n",
+       "          (self): BertSelfAttention(\n",
+       "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (output): BertSelfOutput(\n",
+       "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "        (intermediate): BertIntermediate(\n",
+       "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "        )\n",
+       "        (output): BertOutput(\n",
+       "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (dropout): Dropout(p=0.1, inplace=False)\n",
+       "        )\n",
+       "      )\n",
+       "      (9): BertLayer(\n",
+       "        (attention): BertAttention(\n",
+       "          (self): BertSelfAttention(\n",
+       "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (output): BertSelfOutput(\n",
+       "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "        (intermediate): BertIntermediate(\n",
+       "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "        )\n",
+       "        (output): BertOutput(\n",
+       "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (dropout): Dropout(p=0.1, inplace=False)\n",
+       "        )\n",
+       "      )\n",
+       "      (10): BertLayer(\n",
+       "        (attention): BertAttention(\n",
+       "          (self): BertSelfAttention(\n",
+       "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (output): BertSelfOutput(\n",
+       "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "        (intermediate): BertIntermediate(\n",
+       "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "        )\n",
+       "        (output): BertOutput(\n",
+       "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (dropout): Dropout(p=0.1, inplace=False)\n",
+       "        )\n",
+       "      )\n",
+       "      (11): BertLayer(\n",
+       "        (attention): BertAttention(\n",
+       "          (self): BertSelfAttention(\n",
+       "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (output): BertSelfOutput(\n",
+       "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "        (intermediate): BertIntermediate(\n",
+       "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "        )\n",
+       "        (output): BertOutput(\n",
+       "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (dropout): Dropout(p=0.1, inplace=False)\n",
+       "        )\n",
+       "      )\n",
+       "    )\n",
+       "  )\n",
+       "  (pooler): BertPooler(\n",
+       "    (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "    (activation): Tanh()\n",
+       "  )\n",
+       ")"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = BertModel.from_pretrained('bert-base-multilingual-cased',\n",
+    "                                  output_hidden_states = True,)\n",
+    "\n",
+    "model.eval()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "3ba79d70",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with torch.no_grad():\n",
+    "    outputs = model(tokens_tensor, segments_tensors)\n",
+    "    hidden_states = outputs[2]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "e61815e4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "계층 수: 13   (initial embeddings + 12 BERT layers)\n",
+      "배치 수: 1\n",
+      "토큰 수: 33\n",
+      "은닉층 유닛 수: 768\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (\"계층 수:\", len(hidden_states), \"  (initial embeddings + 12 BERT layers)\")\n",
+    "layer_i = 0\n",
+    "\n",
+    "print (\"배치 수:\", len(hidden_states[layer_i]))\n",
+    "batch_i = 0\n",
+    "\n",
+    "print (\"토큰 수:\", len(hidden_states[layer_i][batch_i]))\n",
+    "token_i = 0\n",
+    "\n",
+    "print (\"은닉층 유닛 수:\", len(hidden_states[layer_i][batch_i][token_i]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "6c79e83e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "은닉 상태의 유형:  <class 'tuple'>\n",
+      "각 계층에서의 텐서 형태:  torch.Size([1, 33, 768])\n"
+     ]
+    }
+   ],
+   "source": [
+    "print('은닉 상태의 유형: ', type(hidden_states))\n",
+    "print('각 계층에서의 텐서 형태: ', hidden_states[0].size())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "9633fe69",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "torch.Size([13, 1, 33, 768])"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "token_embeddings = torch.stack(hidden_states, dim=0)\n",
+    "token_embeddings.size()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "5d777453",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "torch.Size([13, 33, 768])"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "token_embeddings = torch.squeeze(token_embeddings, dim=1)\n",
+    "token_embeddings.size()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "aa6a4d37",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "torch.Size([33, 13, 768])"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "token_embeddings = token_embeddings.permute(1,0,2)\n",
+    "token_embeddings.size()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "5b2f7874",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "형태는: 33 x 3072\n"
+     ]
+    }
+   ],
+   "source": [
+    "token_vecs_cat = []\n",
+    "for token in token_embeddings:\n",
+    "    cat_vec = torch.cat((token[-1], token[-2], token[-3], token[-4]), dim=0)\n",
+    "    token_vecs_cat.append(cat_vec)\n",
+    "print ('형태는: %d x %d' % (len(token_vecs_cat), len(token_vecs_cat[0])))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "7621bc1b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "형태는: 33 x 768\n"
+     ]
+    }
+   ],
+   "source": [
+    "token_vecs_sum = []\n",
+    "for token in token_embeddings:\n",
+    "    sum_vec = torch.sum(token[-4:], dim=0)\n",
+    "    token_vecs_sum.append(sum_vec)\n",
+    "print ('형태는: %d x %d' % (len(token_vecs_sum), len(token_vecs_sum[0])))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "2a14ae7e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "최종 임베딩 벡터의 형태: torch.Size([768])\n"
+     ]
+    }
+   ],
+   "source": [
+    "token_vecs = hidden_states[-2][0]\n",
+    "sentence_embedding = torch.mean(token_vecs, dim=0)\n",
+    "print (\"최종 임베딩 벡터의 형태:\", sentence_embedding.size())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "a0b581d9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0 [CLS]\n",
+      "1 과\n",
+      "2 ##수\n",
+      "3 ##원에\n",
+      "4 사\n",
+      "5 ##과\n",
+      "6 ##가\n",
+      "7 많\n",
+      "8 ##았다\n",
+      "9 .\n",
+      "10 친\n",
+      "11 ##구\n",
+      "12 ##가\n",
+      "13 나\n",
+      "14 ##에게\n",
+      "15 사\n",
+      "16 ##과\n",
+      "17 ##했다\n",
+      "18 .\n",
+      "19 백\n",
+      "20 ##설\n",
+      "21 ##공\n",
+      "22 ##주는\n",
+      "23 독\n",
+      "24 ##이\n",
+      "25 든\n",
+      "26 사\n",
+      "27 ##과\n",
+      "28 ##를\n",
+      "29 먹\n",
+      "30 ##었다\n",
+      "31 .\n",
+      "32 [SEP]\n"
+     ]
+    }
+   ],
+   "source": [
+    "for i, token_str in enumerate(tokenized_text):\n",
+    "    print (i, token_str)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "eb56c9a3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "사과가 많았다 tensor([-0.5844, -4.0836,  0.4906,  0.8915, -1.8054])\n",
+      "나에게 사과했다 tensor([-0.8631, -3.4047, -0.7351,  0.9805, -2.6700])\n",
+      "사과를 먹었다 tensor([ 0.6756, -0.3618,  0.0586,  2.2050, -2.4193])\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"사과가 많았다\", str(token_vecs_sum[6][:5]))\n",
+    "print(\"나에게 사과했다\", str(token_vecs_sum[10][:5]))\n",
+    "print(\"사과를 먹었다\", str(token_vecs_sum[19][:5]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "dbc2e65c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "*유사한* 의미에 대한 벡터 유사성:  0.86\n",
+      "*다른* 의미에 대한 벡터 유사성:  0.91\n"
+     ]
+    }
+   ],
+   "source": [
+    "from scipy.spatial.distance import cosine\n",
+    "diff_apple = 1 - cosine(token_vecs_sum[5], token_vecs_sum[27])\n",
+    "same_apple = 1 - cosine(token_vecs_sum[5], token_vecs_sum[16])\n",
+    "print('*유사한* 의미에 대한 벡터 유사성:  %.2f' % same_apple)\n",
+    "print('*다른* 의미에 대한 벡터 유사성:  %.2f' % diff_apple)"
+   ]
+  }
+ ],
+ "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": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git "a/Week 16_\354\230\210\354\212\265\352\263\274\354\240\234_\353\254\270\354\233\220\354\240\225.pdf" "b/Week 16_\354\230\210\354\212\265\352\263\274\354\240\234_\353\254\270\354\233\220\354\240\225.pdf"
new file mode 100644
index 0000000..303071a
Binary files /dev/null and "b/Week 16_\354\230\210\354\212\265\352\263\274\354\240\234_\353\254\270\354\233\220\354\240\225.pdf" differ