Hugging Face's logo

recommender-system
/
learning-models

Model card Files
xet
Community
aitek230telu commited on
Commit
7f25ade
·
verified ·
1 Parent(s): 71291a3

Latihan PLM BERT, SciBERT, dan Neural networks.

Browse files
Files changed (3) hide show
  1. 7. Latihan_Neural_Networks.ipynb +245 -0
  2. 8. BERT_FOR_RS.ipynb +1956 -0
  3. 9. Latihan_SciBERT_For_RS.ipynb +1277 -0
7. Latihan_Neural_Networks.ipynb ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": []
7
+ },
8
+ "kernelspec": {
9
+ "name": "python3",
10
+ "display_name": "Python 3"
11
+ },
12
+ "language_info": {
13
+ "name": "python"
14
+ }
15
+ },
16
+ "cells": [
17
+ {
18
+ "cell_type": "code",
19
+ "execution_count": 1,
20
+ "metadata": {
21
+ "colab": {
22
+ "base_uri": "https://localhost:8080/"
23
+ },
24
+ "id": "GfIYHqSbw5i1",
25
+ "outputId": "ac83b86d-d4cb-41f3-da04-18bfe1130c3b"
26
+ },
27
+ "outputs": [
28
+ {
29
+ "output_type": "stream",
30
+ "name": "stdout",
31
+ "text": [
32
+ "Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz\n",
33
+ "Failed to download (trying next):\n",
34
+ "HTTP Error 403: Forbidden\n",
35
+ "\n",
36
+ "Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-images-idx3-ubyte.gz\n",
37
+ "Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-images-idx3-ubyte.gz to ./data/MNIST/raw/train-images-idx3-ubyte.gz\n"
38
+ ]
39
+ },
40
+ {
41
+ "output_type": "stream",
42
+ "name": "stderr",
43
+ "text": [
44
+ "100%|██████████| 9912422/9912422 [00:03<00:00, 2700722.18it/s]\n"
45
+ ]
46
+ },
47
+ {
48
+ "output_type": "stream",
49
+ "name": "stdout",
50
+ "text": [
51
+ "Extracting ./data/MNIST/raw/train-images-idx3-ubyte.gz to ./data/MNIST/raw\n",
52
+ "\n",
53
+ "Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz\n",
54
+ "Failed to download (trying next):\n",
55
+ "HTTP Error 403: Forbidden\n",
56
+ "\n",
57
+ "Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-labels-idx1-ubyte.gz\n",
58
+ "Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-labels-idx1-ubyte.gz to ./data/MNIST/raw/train-labels-idx1-ubyte.gz\n"
59
+ ]
60
+ },
61
+ {
62
+ "output_type": "stream",
63
+ "name": "stderr",
64
+ "text": [
65
+ "100%|██████████| 28881/28881 [00:00<00:00, 497356.67it/s]\n"
66
+ ]
67
+ },
68
+ {
69
+ "output_type": "stream",
70
+ "name": "stdout",
71
+ "text": [
72
+ "Extracting ./data/MNIST/raw/train-labels-idx1-ubyte.gz to ./data/MNIST/raw\n",
73
+ "\n",
74
+ "Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz\n",
75
+ "Failed to download (trying next):\n",
76
+ "HTTP Error 403: Forbidden\n",
77
+ "\n",
78
+ "Downloading https://ossci-datasets.s3.amazonaws.com/mnist/t10k-images-idx3-ubyte.gz\n",
79
+ "Downloading https://ossci-datasets.s3.amazonaws.com/mnist/t10k-images-idx3-ubyte.gz to ./data/MNIST/raw/t10k-images-idx3-ubyte.gz\n"
80
+ ]
81
+ },
82
+ {
83
+ "output_type": "stream",
84
+ "name": "stderr",
85
+ "text": [
86
+ "100%|██████████| 1648877/1648877 [00:00<00:00, 4524040.32it/s]\n"
87
+ ]
88
+ },
89
+ {
90
+ "output_type": "stream",
91
+ "name": "stdout",
92
+ "text": [
93
+ "Extracting ./data/MNIST/raw/t10k-images-idx3-ubyte.gz to ./data/MNIST/raw\n",
94
+ "\n",
95
+ "Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz\n",
96
+ "Failed to download (trying next):\n",
97
+ "HTTP Error 403: Forbidden\n",
98
+ "\n",
99
+ "Downloading https://ossci-datasets.s3.amazonaws.com/mnist/t10k-labels-idx1-ubyte.gz\n",
100
+ "Downloading https://ossci-datasets.s3.amazonaws.com/mnist/t10k-labels-idx1-ubyte.gz to ./data/MNIST/raw/t10k-labels-idx1-ubyte.gz\n"
101
+ ]
102
+ },
103
+ {
104
+ "output_type": "stream",
105
+ "name": "stderr",
106
+ "text": [
107
+ "100%|██████████| 4542/4542 [00:00<00:00, 3718627.52it/s]"
108
+ ]
109
+ },
110
+ {
111
+ "output_type": "stream",
112
+ "name": "stdout",
113
+ "text": [
114
+ "Extracting ./data/MNIST/raw/t10k-labels-idx1-ubyte.gz to ./data/MNIST/raw\n",
115
+ "\n"
116
+ ]
117
+ },
118
+ {
119
+ "output_type": "stream",
120
+ "name": "stderr",
121
+ "text": [
122
+ "\n"
123
+ ]
124
+ }
125
+ ],
126
+ "source": [
127
+ "import torch\n",
128
+ "import torch.nn as nn\n",
129
+ "import torch.optim as optim\n",
130
+ "from torchvision import datasets, transforms\n",
131
+ "\n",
132
+ "# Transformasi data\n",
133
+ "transform = transforms.Compose([transforms.ToTensor()])\n",
134
+ "\n",
135
+ "# Memuat dataset MNIST\n",
136
+ "train_dataset = datasets.MNIST(root='./data', train=True, transform=transform, download=True)\n",
137
+ "train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=64, shuffle=True)"
138
+ ]
139
+ },
140
+ {
141
+ "cell_type": "markdown",
142
+ "source": [
143
+ "### Latihan:\n",
144
+ "#### Implementasi dari awal:\n",
145
+ "\n",
146
+ "1. Coba implementasikan neural network sederhana dengan beberapa lapisan hidden dan latih pada dataset sederhana seperti MNIST atau CIFAR-10.\n",
147
+ "2. Eksperimen dengan fungsi aktivasi yang berbeda, jumlah neuron di setiap lapisan, dan jenis optimizer.\n",
148
+ "\n",
149
+ "#### Visualisasi:\n",
150
+ "\n",
151
+ "1. Coba visualisasikan bagaimana bobot dan bias dari model berubah seiring dengan proses pelatihan.\n",
152
+ "2. Visualisasikan loss dan akurasi seiring waktu untuk memahami bagaimana model belajar.\n",
153
+ "\n",
154
+ "#### Perbedaan Lapisan dan Arsitektur:\n",
155
+ "\n",
156
+ "1. Coba modifikasi arsitektur jaringan (menambah lapisan, mengubah jumlah neuron, dll.) dan lihat bagaimana hal ini mempengaruhi performa model."
157
+ ],
158
+ "metadata": {
159
+ "id": "7HttM3uSyHDc"
160
+ }
161
+ },
162
+ {
163
+ "cell_type": "markdown",
164
+ "source": [
165
+ "#### Implementasi Awal"
166
+ ],
167
+ "metadata": {
168
+ "id": "KrbSxsRjyWbm"
169
+ }
170
+ },
171
+ {
172
+ "cell_type": "code",
173
+ "source": [
174
+ "## Tambahkan Jumlah Lapisan Neuran\n",
175
+ "class CustomSizeLayerNN(nn.Module):\n",
176
+ " def __init__(self, layer_size):\n",
177
+ " super(CustomSizeLayerNN, self).__init__()\n",
178
+ " self.layers = nn.ModuleList()\n",
179
+ " temp_layer_size = layer_size\n",
180
+ " while temp_layer_size > 64:\n",
181
+ " if (temp_layer_size == layer_size and len(self.layers) == 0):\n",
182
+ " self.layers.append(nn.Linear(28*28, temp_layer_size))\n",
183
+ " else:\n",
184
+ " self.layers.append(nn.Linear(temp_layer_size, int(temp_layer_size/2)))\n",
185
+ " temp_layer_size = int(temp_layer_size/2)\n",
186
+ " self.layers.append(nn.Linear(temp_layer_size, 10))\n",
187
+ "\n",
188
+ " def forward(self, x):\n",
189
+ " x = x.view(-1, 28*28)\n",
190
+ " for i, layer in enumerate(self.layers):\n",
191
+ " if i < len(self.layers) - 1:\n",
192
+ " ## Ganti fungsi aktivasi\n",
193
+ " x = torch.relu(layer(x))\n",
194
+ " # x = torch.sigmoid(layer(x))\n",
195
+ " # x = torch.tanh(layer(x))\n",
196
+ " else:\n",
197
+ " x = layer(x)\n",
198
+ " return x\n",
199
+ "\n",
200
+ "# Inisialisasi model, loss function, dan optimizer\n",
201
+ "model = CustomSizeLayerNN(layer_size=128)\n",
202
+ "criterion = nn.CrossEntropyLoss()\n",
203
+ "# Ganti optimizer\n",
204
+ "# optimizer = optim.SGD(model.parameters(), lr=0.01)\n",
205
+ "optimizer = optim.Adam(model.parameters(), lr=0.01)\n",
206
+ "\n",
207
+ "# Training Loop\n",
208
+ "for epoch in range(10): # 10 epochs\n",
209
+ " for images, labels in train_loader:\n",
210
+ " optimizer.zero_grad()\n",
211
+ " output = model(images)\n",
212
+ " loss = criterion(output, labels)\n",
213
+ " loss.backward()\n",
214
+ " optimizer.step()\n",
215
+ " print(f'Epoch {epoch+1}, Loss: {loss.item()}')"
216
+ ],
217
+ "metadata": {
218
+ "colab": {
219
+ "base_uri": "https://localhost:8080/"
220
+ },
221
+ "id": "LU_a_JjtyZ_2",
222
+ "outputId": "7d70e235-db9e-4169-e719-b188b34a52dd"
223
+ },
224
+ "execution_count": 20,
225
+ "outputs": [
226
+ {
227
+ "output_type": "stream",
228
+ "name": "stdout",
229
+ "text": [
230
+ "Epoch 1, Loss: 0.20903132855892181\n",
231
+ "Epoch 2, Loss: 0.2800661027431488\n",
232
+ "Epoch 3, Loss: 0.04195380210876465\n",
233
+ "Epoch 4, Loss: 0.010990972630679607\n",
234
+ "Epoch 5, Loss: 0.16205546259880066\n",
235
+ "Epoch 6, Loss: 0.004210921470075846\n",
236
+ "Epoch 7, Loss: 0.14686189591884613\n",
237
+ "Epoch 8, Loss: 0.0029904020484536886\n",
238
+ "Epoch 9, Loss: 0.00271606189198792\n",
239
+ "Epoch 10, Loss: 0.005243723280727863\n"
240
+ ]
241
+ }
242
+ ]
243
+ }
244
+ ]
245
+ }
8. BERT_FOR_RS.ipynb ADDED
@@ -0,0 +1,1956 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": []
7
+ },
8
+ "kernelspec": {
9
+ "name": "python3",
10
+ "display_name": "Python 3"
11
+ },
12
+ "language_info": {
13
+ "name": "python"
14
+ },
15
+ "widgets": {
16
+ "application/vnd.jupyter.widget-state+json": {
17
+ "222776c1f6d140bc93eb7860a259444b": {
18
+ "model_module": "@jupyter-widgets/controls",
19
+ "model_name": "HBoxModel",
20
+ "model_module_version": "1.5.0",
21
+ "state": {
22
+ "_dom_classes": [],
23
+ "_model_module": "@jupyter-widgets/controls",
24
+ "_model_module_version": "1.5.0",
25
+ "_model_name": "HBoxModel",
26
+ "_view_count": null,
27
+ "_view_module": "@jupyter-widgets/controls",
28
+ "_view_module_version": "1.5.0",
29
+ "_view_name": "HBoxView",
30
+ "box_style": "",
31
+ "children": [
32
+ "IPY_MODEL_f56e4df7c4104d228b6fb45d4a3853c5",
33
+ "IPY_MODEL_3e050cbb980b4560b44b37ef16772bea",
34
+ "IPY_MODEL_419d595aa37941e78c1caff94ebb3f48"
35
+ ],
36
+ "layout": "IPY_MODEL_1fa5a41a884645b9be9b6427e9118499"
37
+ }
38
+ },
39
+ "f56e4df7c4104d228b6fb45d4a3853c5": {
40
+ "model_module": "@jupyter-widgets/controls",
41
+ "model_name": "HTMLModel",
42
+ "model_module_version": "1.5.0",
43
+ "state": {
44
+ "_dom_classes": [],
45
+ "_model_module": "@jupyter-widgets/controls",
46
+ "_model_module_version": "1.5.0",
47
+ "_model_name": "HTMLModel",
48
+ "_view_count": null,
49
+ "_view_module": "@jupyter-widgets/controls",
50
+ "_view_module_version": "1.5.0",
51
+ "_view_name": "HTMLView",
52
+ "description": "",
53
+ "description_tooltip": null,
54
+ "layout": "IPY_MODEL_bf5a1e82216d453197b70832888c7704",
55
+ "placeholder": "​",
56
+ "style": "IPY_MODEL_15ea32962b2341e3ad5d20a7e65d35ca",
57
+ "value": "tokenizer_config.json: 100%"
58
+ }
59
+ },
60
+ "3e050cbb980b4560b44b37ef16772bea": {
61
+ "model_module": "@jupyter-widgets/controls",
62
+ "model_name": "FloatProgressModel",
63
+ "model_module_version": "1.5.0",
64
+ "state": {
65
+ "_dom_classes": [],
66
+ "_model_module": "@jupyter-widgets/controls",
67
+ "_model_module_version": "1.5.0",
68
+ "_model_name": "FloatProgressModel",
69
+ "_view_count": null,
70
+ "_view_module": "@jupyter-widgets/controls",
71
+ "_view_module_version": "1.5.0",
72
+ "_view_name": "ProgressView",
73
+ "bar_style": "success",
74
+ "description": "",
75
+ "description_tooltip": null,
76
+ "layout": "IPY_MODEL_9656534abe284e09a66b81d1381c17d5",
77
+ "max": 48,
78
+ "min": 0,
79
+ "orientation": "horizontal",
80
+ "style": "IPY_MODEL_d270ccd8d9de4749b535c93f39f09631",
81
+ "value": 48
82
+ }
83
+ },
84
+ "419d595aa37941e78c1caff94ebb3f48": {
85
+ "model_module": "@jupyter-widgets/controls",
86
+ "model_name": "HTMLModel",
87
+ "model_module_version": "1.5.0",
88
+ "state": {
89
+ "_dom_classes": [],
90
+ "_model_module": "@jupyter-widgets/controls",
91
+ "_model_module_version": "1.5.0",
92
+ "_model_name": "HTMLModel",
93
+ "_view_count": null,
94
+ "_view_module": "@jupyter-widgets/controls",
95
+ "_view_module_version": "1.5.0",
96
+ "_view_name": "HTMLView",
97
+ "description": "",
98
+ "description_tooltip": null,
99
+ "layout": "IPY_MODEL_136c9a8ddb134246ac72881c8821ff1a",
100
+ "placeholder": "​",
101
+ "style": "IPY_MODEL_62d892261d0e42bf90ed96f82f9af608",
102
+ "value": " 48.0/48.0 [00:00&lt;00:00, 405B/s]"
103
+ }
104
+ },
105
+ "1fa5a41a884645b9be9b6427e9118499": {
106
+ "model_module": "@jupyter-widgets/base",
107
+ "model_name": "LayoutModel",
108
+ "model_module_version": "1.2.0",
109
+ "state": {
110
+ "_model_module": "@jupyter-widgets/base",
111
+ "_model_module_version": "1.2.0",
112
+ "_model_name": "LayoutModel",
113
+ "_view_count": null,
114
+ "_view_module": "@jupyter-widgets/base",
115
+ "_view_module_version": "1.2.0",
116
+ "_view_name": "LayoutView",
117
+ "align_content": null,
118
+ "align_items": null,
119
+ "align_self": null,
120
+ "border": null,
121
+ "bottom": null,
122
+ "display": null,
123
+ "flex": null,
124
+ "flex_flow": null,
125
+ "grid_area": null,
126
+ "grid_auto_columns": null,
127
+ "grid_auto_flow": null,
128
+ "grid_auto_rows": null,
129
+ "grid_column": null,
130
+ "grid_gap": null,
131
+ "grid_row": null,
132
+ "grid_template_areas": null,
133
+ "grid_template_columns": null,
134
+ "grid_template_rows": null,
135
+ "height": null,
136
+ "justify_content": null,
137
+ "justify_items": null,
138
+ "left": null,
139
+ "margin": null,
140
+ "max_height": null,
141
+ "max_width": null,
142
+ "min_height": null,
143
+ "min_width": null,
144
+ "object_fit": null,
145
+ "object_position": null,
146
+ "order": null,
147
+ "overflow": null,
148
+ "overflow_x": null,
149
+ "overflow_y": null,
150
+ "padding": null,
151
+ "right": null,
152
+ "top": null,
153
+ "visibility": null,
154
+ "width": null
155
+ }
156
+ },
157
+ "bf5a1e82216d453197b70832888c7704": {
158
+ "model_module": "@jupyter-widgets/base",
159
+ "model_name": "LayoutModel",
160
+ "model_module_version": "1.2.0",
161
+ "state": {
162
+ "_model_module": "@jupyter-widgets/base",
163
+ "_model_module_version": "1.2.0",
164
+ "_model_name": "LayoutModel",
165
+ "_view_count": null,
166
+ "_view_module": "@jupyter-widgets/base",
167
+ "_view_module_version": "1.2.0",
168
+ "_view_name": "LayoutView",
169
+ "align_content": null,
170
+ "align_items": null,
171
+ "align_self": null,
172
+ "border": null,
173
+ "bottom": null,
174
+ "display": null,
175
+ "flex": null,
176
+ "flex_flow": null,
177
+ "grid_area": null,
178
+ "grid_auto_columns": null,
179
+ "grid_auto_flow": null,
180
+ "grid_auto_rows": null,
181
+ "grid_column": null,
182
+ "grid_gap": null,
183
+ "grid_row": null,
184
+ "grid_template_areas": null,
185
+ "grid_template_columns": null,
186
+ "grid_template_rows": null,
187
+ "height": null,
188
+ "justify_content": null,
189
+ "justify_items": null,
190
+ "left": null,
191
+ "margin": null,
192
+ "max_height": null,
193
+ "max_width": null,
194
+ "min_height": null,
195
+ "min_width": null,
196
+ "object_fit": null,
197
+ "object_position": null,
198
+ "order": null,
199
+ "overflow": null,
200
+ "overflow_x": null,
201
+ "overflow_y": null,
202
+ "padding": null,
203
+ "right": null,
204
+ "top": null,
205
+ "visibility": null,
206
+ "width": null
207
+ }
208
+ },
209
+ "15ea32962b2341e3ad5d20a7e65d35ca": {
210
+ "model_module": "@jupyter-widgets/controls",
211
+ "model_name": "DescriptionStyleModel",
212
+ "model_module_version": "1.5.0",
213
+ "state": {
214
+ "_model_module": "@jupyter-widgets/controls",
215
+ "_model_module_version": "1.5.0",
216
+ "_model_name": "DescriptionStyleModel",
217
+ "_view_count": null,
218
+ "_view_module": "@jupyter-widgets/base",
219
+ "_view_module_version": "1.2.0",
220
+ "_view_name": "StyleView",
221
+ "description_width": ""
222
+ }
223
+ },
224
+ "9656534abe284e09a66b81d1381c17d5": {
225
+ "model_module": "@jupyter-widgets/base",
226
+ "model_name": "LayoutModel",
227
+ "model_module_version": "1.2.0",
228
+ "state": {
229
+ "_model_module": "@jupyter-widgets/base",
230
+ "_model_module_version": "1.2.0",
231
+ "_model_name": "LayoutModel",
232
+ "_view_count": null,
233
+ "_view_module": "@jupyter-widgets/base",
234
+ "_view_module_version": "1.2.0",
235
+ "_view_name": "LayoutView",
236
+ "align_content": null,
237
+ "align_items": null,
238
+ "align_self": null,
239
+ "border": null,
240
+ "bottom": null,
241
+ "display": null,
242
+ "flex": null,
243
+ "flex_flow": null,
244
+ "grid_area": null,
245
+ "grid_auto_columns": null,
246
+ "grid_auto_flow": null,
247
+ "grid_auto_rows": null,
248
+ "grid_column": null,
249
+ "grid_gap": null,
250
+ "grid_row": null,
251
+ "grid_template_areas": null,
252
+ "grid_template_columns": null,
253
+ "grid_template_rows": null,
254
+ "height": null,
255
+ "justify_content": null,
256
+ "justify_items": null,
257
+ "left": null,
258
+ "margin": null,
259
+ "max_height": null,
260
+ "max_width": null,
261
+ "min_height": null,
262
+ "min_width": null,
263
+ "object_fit": null,
264
+ "object_position": null,
265
+ "order": null,
266
+ "overflow": null,
267
+ "overflow_x": null,
268
+ "overflow_y": null,
269
+ "padding": null,
270
+ "right": null,
271
+ "top": null,
272
+ "visibility": null,
273
+ "width": null
274
+ }
275
+ },
276
+ "d270ccd8d9de4749b535c93f39f09631": {
277
+ "model_module": "@jupyter-widgets/controls",
278
+ "model_name": "ProgressStyleModel",
279
+ "model_module_version": "1.5.0",
280
+ "state": {
281
+ "_model_module": "@jupyter-widgets/controls",
282
+ "_model_module_version": "1.5.0",
283
+ "_model_name": "ProgressStyleModel",
284
+ "_view_count": null,
285
+ "_view_module": "@jupyter-widgets/base",
286
+ "_view_module_version": "1.2.0",
287
+ "_view_name": "StyleView",
288
+ "bar_color": null,
289
+ "description_width": ""
290
+ }
291
+ },
292
+ "136c9a8ddb134246ac72881c8821ff1a": {
293
+ "model_module": "@jupyter-widgets/base",
294
+ "model_name": "LayoutModel",
295
+ "model_module_version": "1.2.0",
296
+ "state": {
297
+ "_model_module": "@jupyter-widgets/base",
298
+ "_model_module_version": "1.2.0",
299
+ "_model_name": "LayoutModel",
300
+ "_view_count": null,
301
+ "_view_module": "@jupyter-widgets/base",
302
+ "_view_module_version": "1.2.0",
303
+ "_view_name": "LayoutView",
304
+ "align_content": null,
305
+ "align_items": null,
306
+ "align_self": null,
307
+ "border": null,
308
+ "bottom": null,
309
+ "display": null,
310
+ "flex": null,
311
+ "flex_flow": null,
312
+ "grid_area": null,
313
+ "grid_auto_columns": null,
314
+ "grid_auto_flow": null,
315
+ "grid_auto_rows": null,
316
+ "grid_column": null,
317
+ "grid_gap": null,
318
+ "grid_row": null,
319
+ "grid_template_areas": null,
320
+ "grid_template_columns": null,
321
+ "grid_template_rows": null,
322
+ "height": null,
323
+ "justify_content": null,
324
+ "justify_items": null,
325
+ "left": null,
326
+ "margin": null,
327
+ "max_height": null,
328
+ "max_width": null,
329
+ "min_height": null,
330
+ "min_width": null,
331
+ "object_fit": null,
332
+ "object_position": null,
333
+ "order": null,
334
+ "overflow": null,
335
+ "overflow_x": null,
336
+ "overflow_y": null,
337
+ "padding": null,
338
+ "right": null,
339
+ "top": null,
340
+ "visibility": null,
341
+ "width": null
342
+ }
343
+ },
344
+ "62d892261d0e42bf90ed96f82f9af608": {
345
+ "model_module": "@jupyter-widgets/controls",
346
+ "model_name": "DescriptionStyleModel",
347
+ "model_module_version": "1.5.0",
348
+ "state": {
349
+ "_model_module": "@jupyter-widgets/controls",
350
+ "_model_module_version": "1.5.0",
351
+ "_model_name": "DescriptionStyleModel",
352
+ "_view_count": null,
353
+ "_view_module": "@jupyter-widgets/base",
354
+ "_view_module_version": "1.2.0",
355
+ "_view_name": "StyleView",
356
+ "description_width": ""
357
+ }
358
+ },
359
+ "567320fc6a8d4809b07af8e731fc6c8e": {
360
+ "model_module": "@jupyter-widgets/controls",
361
+ "model_name": "HBoxModel",
362
+ "model_module_version": "1.5.0",
363
+ "state": {
364
+ "_dom_classes": [],
365
+ "_model_module": "@jupyter-widgets/controls",
366
+ "_model_module_version": "1.5.0",
367
+ "_model_name": "HBoxModel",
368
+ "_view_count": null,
369
+ "_view_module": "@jupyter-widgets/controls",
370
+ "_view_module_version": "1.5.0",
371
+ "_view_name": "HBoxView",
372
+ "box_style": "",
373
+ "children": [
374
+ "IPY_MODEL_b91785c4cee645fba4f33a44d83e1cc8",
375
+ "IPY_MODEL_d1d966ed26b04ee48509b26d5f333404",
376
+ "IPY_MODEL_c2f6606ed6764833a6b22feb4e648ad8"
377
+ ],
378
+ "layout": "IPY_MODEL_576db19e9a2242dfa1924fff4216c2a6"
379
+ }
380
+ },
381
+ "b91785c4cee645fba4f33a44d83e1cc8": {
382
+ "model_module": "@jupyter-widgets/controls",
383
+ "model_name": "HTMLModel",
384
+ "model_module_version": "1.5.0",
385
+ "state": {
386
+ "_dom_classes": [],
387
+ "_model_module": "@jupyter-widgets/controls",
388
+ "_model_module_version": "1.5.0",
389
+ "_model_name": "HTMLModel",
390
+ "_view_count": null,
391
+ "_view_module": "@jupyter-widgets/controls",
392
+ "_view_module_version": "1.5.0",
393
+ "_view_name": "HTMLView",
394
+ "description": "",
395
+ "description_tooltip": null,
396
+ "layout": "IPY_MODEL_7df364097e4141d8b6d8a154dd0b5167",
397
+ "placeholder": "​",
398
+ "style": "IPY_MODEL_2ef10079e12b493eb72872a193ea8418",
399
+ "value": "vocab.txt: 100%"
400
+ }
401
+ },
402
+ "d1d966ed26b04ee48509b26d5f333404": {
403
+ "model_module": "@jupyter-widgets/controls",
404
+ "model_name": "FloatProgressModel",
405
+ "model_module_version": "1.5.0",
406
+ "state": {
407
+ "_dom_classes": [],
408
+ "_model_module": "@jupyter-widgets/controls",
409
+ "_model_module_version": "1.5.0",
410
+ "_model_name": "FloatProgressModel",
411
+ "_view_count": null,
412
+ "_view_module": "@jupyter-widgets/controls",
413
+ "_view_module_version": "1.5.0",
414
+ "_view_name": "ProgressView",
415
+ "bar_style": "success",
416
+ "description": "",
417
+ "description_tooltip": null,
418
+ "layout": "IPY_MODEL_e29681c9faf4469988ec914982979cad",
419
+ "max": 231508,
420
+ "min": 0,
421
+ "orientation": "horizontal",
422
+ "style": "IPY_MODEL_9a538eb4f01440a6ac1a83ca12db9872",
423
+ "value": 231508
424
+ }
425
+ },
426
+ "c2f6606ed6764833a6b22feb4e648ad8": {
427
+ "model_module": "@jupyter-widgets/controls",
428
+ "model_name": "HTMLModel",
429
+ "model_module_version": "1.5.0",
430
+ "state": {
431
+ "_dom_classes": [],
432
+ "_model_module": "@jupyter-widgets/controls",
433
+ "_model_module_version": "1.5.0",
434
+ "_model_name": "HTMLModel",
435
+ "_view_count": null,
436
+ "_view_module": "@jupyter-widgets/controls",
437
+ "_view_module_version": "1.5.0",
438
+ "_view_name": "HTMLView",
439
+ "description": "",
440
+ "description_tooltip": null,
441
+ "layout": "IPY_MODEL_6aec82e9ef844d0bb363b913258bfe01",
442
+ "placeholder": "​",
443
+ "style": "IPY_MODEL_7f19e624ef904c36b8e6fe896999fe6d",
444
+ "value": " 232k/232k [00:00&lt;00:00, 1.57MB/s]"
445
+ }
446
+ },
447
+ "576db19e9a2242dfa1924fff4216c2a6": {
448
+ "model_module": "@jupyter-widgets/base",
449
+ "model_name": "LayoutModel",
450
+ "model_module_version": "1.2.0",
451
+ "state": {
452
+ "_model_module": "@jupyter-widgets/base",
453
+ "_model_module_version": "1.2.0",
454
+ "_model_name": "LayoutModel",
455
+ "_view_count": null,
456
+ "_view_module": "@jupyter-widgets/base",
457
+ "_view_module_version": "1.2.0",
458
+ "_view_name": "LayoutView",
459
+ "align_content": null,
460
+ "align_items": null,
461
+ "align_self": null,
462
+ "border": null,
463
+ "bottom": null,
464
+ "display": null,
465
+ "flex": null,
466
+ "flex_flow": null,
467
+ "grid_area": null,
468
+ "grid_auto_columns": null,
469
+ "grid_auto_flow": null,
470
+ "grid_auto_rows": null,
471
+ "grid_column": null,
472
+ "grid_gap": null,
473
+ "grid_row": null,
474
+ "grid_template_areas": null,
475
+ "grid_template_columns": null,
476
+ "grid_template_rows": null,
477
+ "height": null,
478
+ "justify_content": null,
479
+ "justify_items": null,
480
+ "left": null,
481
+ "margin": null,
482
+ "max_height": null,
483
+ "max_width": null,
484
+ "min_height": null,
485
+ "min_width": null,
486
+ "object_fit": null,
487
+ "object_position": null,
488
+ "order": null,
489
+ "overflow": null,
490
+ "overflow_x": null,
491
+ "overflow_y": null,
492
+ "padding": null,
493
+ "right": null,
494
+ "top": null,
495
+ "visibility": null,
496
+ "width": null
497
+ }
498
+ },
499
+ "7df364097e4141d8b6d8a154dd0b5167": {
500
+ "model_module": "@jupyter-widgets/base",
501
+ "model_name": "LayoutModel",
502
+ "model_module_version": "1.2.0",
503
+ "state": {
504
+ "_model_module": "@jupyter-widgets/base",
505
+ "_model_module_version": "1.2.0",
506
+ "_model_name": "LayoutModel",
507
+ "_view_count": null,
508
+ "_view_module": "@jupyter-widgets/base",
509
+ "_view_module_version": "1.2.0",
510
+ "_view_name": "LayoutView",
511
+ "align_content": null,
512
+ "align_items": null,
513
+ "align_self": null,
514
+ "border": null,
515
+ "bottom": null,
516
+ "display": null,
517
+ "flex": null,
518
+ "flex_flow": null,
519
+ "grid_area": null,
520
+ "grid_auto_columns": null,
521
+ "grid_auto_flow": null,
522
+ "grid_auto_rows": null,
523
+ "grid_column": null,
524
+ "grid_gap": null,
525
+ "grid_row": null,
526
+ "grid_template_areas": null,
527
+ "grid_template_columns": null,
528
+ "grid_template_rows": null,
529
+ "height": null,
530
+ "justify_content": null,
531
+ "justify_items": null,
532
+ "left": null,
533
+ "margin": null,
534
+ "max_height": null,
535
+ "max_width": null,
536
+ "min_height": null,
537
+ "min_width": null,
538
+ "object_fit": null,
539
+ "object_position": null,
540
+ "order": null,
541
+ "overflow": null,
542
+ "overflow_x": null,
543
+ "overflow_y": null,
544
+ "padding": null,
545
+ "right": null,
546
+ "top": null,
547
+ "visibility": null,
548
+ "width": null
549
+ }
550
+ },
551
+ "2ef10079e12b493eb72872a193ea8418": {
552
+ "model_module": "@jupyter-widgets/controls",
553
+ "model_name": "DescriptionStyleModel",
554
+ "model_module_version": "1.5.0",
555
+ "state": {
556
+ "_model_module": "@jupyter-widgets/controls",
557
+ "_model_module_version": "1.5.0",
558
+ "_model_name": "DescriptionStyleModel",
559
+ "_view_count": null,
560
+ "_view_module": "@jupyter-widgets/base",
561
+ "_view_module_version": "1.2.0",
562
+ "_view_name": "StyleView",
563
+ "description_width": ""
564
+ }
565
+ },
566
+ "e29681c9faf4469988ec914982979cad": {
567
+ "model_module": "@jupyter-widgets/base",
568
+ "model_name": "LayoutModel",
569
+ "model_module_version": "1.2.0",
570
+ "state": {
571
+ "_model_module": "@jupyter-widgets/base",
572
+ "_model_module_version": "1.2.0",
573
+ "_model_name": "LayoutModel",
574
+ "_view_count": null,
575
+ "_view_module": "@jupyter-widgets/base",
576
+ "_view_module_version": "1.2.0",
577
+ "_view_name": "LayoutView",
578
+ "align_content": null,
579
+ "align_items": null,
580
+ "align_self": null,
581
+ "border": null,
582
+ "bottom": null,
583
+ "display": null,
584
+ "flex": null,
585
+ "flex_flow": null,
586
+ "grid_area": null,
587
+ "grid_auto_columns": null,
588
+ "grid_auto_flow": null,
589
+ "grid_auto_rows": null,
590
+ "grid_column": null,
591
+ "grid_gap": null,
592
+ "grid_row": null,
593
+ "grid_template_areas": null,
594
+ "grid_template_columns": null,
595
+ "grid_template_rows": null,
596
+ "height": null,
597
+ "justify_content": null,
598
+ "justify_items": null,
599
+ "left": null,
600
+ "margin": null,
601
+ "max_height": null,
602
+ "max_width": null,
603
+ "min_height": null,
604
+ "min_width": null,
605
+ "object_fit": null,
606
+ "object_position": null,
607
+ "order": null,
608
+ "overflow": null,
609
+ "overflow_x": null,
610
+ "overflow_y": null,
611
+ "padding": null,
612
+ "right": null,
613
+ "top": null,
614
+ "visibility": null,
615
+ "width": null
616
+ }
617
+ },
618
+ "9a538eb4f01440a6ac1a83ca12db9872": {
619
+ "model_module": "@jupyter-widgets/controls",
620
+ "model_name": "ProgressStyleModel",
621
+ "model_module_version": "1.5.0",
622
+ "state": {
623
+ "_model_module": "@jupyter-widgets/controls",
624
+ "_model_module_version": "1.5.0",
625
+ "_model_name": "ProgressStyleModel",
626
+ "_view_count": null,
627
+ "_view_module": "@jupyter-widgets/base",
628
+ "_view_module_version": "1.2.0",
629
+ "_view_name": "StyleView",
630
+ "bar_color": null,
631
+ "description_width": ""
632
+ }
633
+ },
634
+ "6aec82e9ef844d0bb363b913258bfe01": {
635
+ "model_module": "@jupyter-widgets/base",
636
+ "model_name": "LayoutModel",
637
+ "model_module_version": "1.2.0",
638
+ "state": {
639
+ "_model_module": "@jupyter-widgets/base",
640
+ "_model_module_version": "1.2.0",
641
+ "_model_name": "LayoutModel",
642
+ "_view_count": null,
643
+ "_view_module": "@jupyter-widgets/base",
644
+ "_view_module_version": "1.2.0",
645
+ "_view_name": "LayoutView",
646
+ "align_content": null,
647
+ "align_items": null,
648
+ "align_self": null,
649
+ "border": null,
650
+ "bottom": null,
651
+ "display": null,
652
+ "flex": null,
653
+ "flex_flow": null,
654
+ "grid_area": null,
655
+ "grid_auto_columns": null,
656
+ "grid_auto_flow": null,
657
+ "grid_auto_rows": null,
658
+ "grid_column": null,
659
+ "grid_gap": null,
660
+ "grid_row": null,
661
+ "grid_template_areas": null,
662
+ "grid_template_columns": null,
663
+ "grid_template_rows": null,
664
+ "height": null,
665
+ "justify_content": null,
666
+ "justify_items": null,
667
+ "left": null,
668
+ "margin": null,
669
+ "max_height": null,
670
+ "max_width": null,
671
+ "min_height": null,
672
+ "min_width": null,
673
+ "object_fit": null,
674
+ "object_position": null,
675
+ "order": null,
676
+ "overflow": null,
677
+ "overflow_x": null,
678
+ "overflow_y": null,
679
+ "padding": null,
680
+ "right": null,
681
+ "top": null,
682
+ "visibility": null,
683
+ "width": null
684
+ }
685
+ },
686
+ "7f19e624ef904c36b8e6fe896999fe6d": {
687
+ "model_module": "@jupyter-widgets/controls",
688
+ "model_name": "DescriptionStyleModel",
689
+ "model_module_version": "1.5.0",
690
+ "state": {
691
+ "_model_module": "@jupyter-widgets/controls",
692
+ "_model_module_version": "1.5.0",
693
+ "_model_name": "DescriptionStyleModel",
694
+ "_view_count": null,
695
+ "_view_module": "@jupyter-widgets/base",
696
+ "_view_module_version": "1.2.0",
697
+ "_view_name": "StyleView",
698
+ "description_width": ""
699
+ }
700
+ },
701
+ "4ee356f5fe034c3f8d644b5671a4cfcc": {
702
+ "model_module": "@jupyter-widgets/controls",
703
+ "model_name": "HBoxModel",
704
+ "model_module_version": "1.5.0",
705
+ "state": {
706
+ "_dom_classes": [],
707
+ "_model_module": "@jupyter-widgets/controls",
708
+ "_model_module_version": "1.5.0",
709
+ "_model_name": "HBoxModel",
710
+ "_view_count": null,
711
+ "_view_module": "@jupyter-widgets/controls",
712
+ "_view_module_version": "1.5.0",
713
+ "_view_name": "HBoxView",
714
+ "box_style": "",
715
+ "children": [
716
+ "IPY_MODEL_eac117b1ab5f49e2b5928a862828fd83",
717
+ "IPY_MODEL_aa6bce5cf9244895bc37535203051a61",
718
+ "IPY_MODEL_8e32bb708c54412ab85a28937e392e91"
719
+ ],
720
+ "layout": "IPY_MODEL_d83cbbfdf7cd4944a54c39509425cc83"
721
+ }
722
+ },
723
+ "eac117b1ab5f49e2b5928a862828fd83": {
724
+ "model_module": "@jupyter-widgets/controls",
725
+ "model_name": "HTMLModel",
726
+ "model_module_version": "1.5.0",
727
+ "state": {
728
+ "_dom_classes": [],
729
+ "_model_module": "@jupyter-widgets/controls",
730
+ "_model_module_version": "1.5.0",
731
+ "_model_name": "HTMLModel",
732
+ "_view_count": null,
733
+ "_view_module": "@jupyter-widgets/controls",
734
+ "_view_module_version": "1.5.0",
735
+ "_view_name": "HTMLView",
736
+ "description": "",
737
+ "description_tooltip": null,
738
+ "layout": "IPY_MODEL_8621ab22d387462da8319af86aab4586",
739
+ "placeholder": "​",
740
+ "style": "IPY_MODEL_3b68a677d8384cebb43f325c8514e85a",
741
+ "value": "tokenizer.json: 100%"
742
+ }
743
+ },
744
+ "aa6bce5cf9244895bc37535203051a61": {
745
+ "model_module": "@jupyter-widgets/controls",
746
+ "model_name": "FloatProgressModel",
747
+ "model_module_version": "1.5.0",
748
+ "state": {
749
+ "_dom_classes": [],
750
+ "_model_module": "@jupyter-widgets/controls",
751
+ "_model_module_version": "1.5.0",
752
+ "_model_name": "FloatProgressModel",
753
+ "_view_count": null,
754
+ "_view_module": "@jupyter-widgets/controls",
755
+ "_view_module_version": "1.5.0",
756
+ "_view_name": "ProgressView",
757
+ "bar_style": "success",
758
+ "description": "",
759
+ "description_tooltip": null,
760
+ "layout": "IPY_MODEL_c8972f68b6324a2db5ec949f29e0c363",
761
+ "max": 466062,
762
+ "min": 0,
763
+ "orientation": "horizontal",
764
+ "style": "IPY_MODEL_1f13de458f444de5af2dc07f493b59ee",
765
+ "value": 466062
766
+ }
767
+ },
768
+ "8e32bb708c54412ab85a28937e392e91": {
769
+ "model_module": "@jupyter-widgets/controls",
770
+ "model_name": "HTMLModel",
771
+ "model_module_version": "1.5.0",
772
+ "state": {
773
+ "_dom_classes": [],
774
+ "_model_module": "@jupyter-widgets/controls",
775
+ "_model_module_version": "1.5.0",
776
+ "_model_name": "HTMLModel",
777
+ "_view_count": null,
778
+ "_view_module": "@jupyter-widgets/controls",
779
+ "_view_module_version": "1.5.0",
780
+ "_view_name": "HTMLView",
781
+ "description": "",
782
+ "description_tooltip": null,
783
+ "layout": "IPY_MODEL_11225598bb8e4ae4bbba64b3dddb61ba",
784
+ "placeholder": "​",
785
+ "style": "IPY_MODEL_5aecdef3dc2a48ebb27e6b28b210deb5",
786
+ "value": " 466k/466k [00:00&lt;00:00, 4.96MB/s]"
787
+ }
788
+ },
789
+ "d83cbbfdf7cd4944a54c39509425cc83": {
790
+ "model_module": "@jupyter-widgets/base",
791
+ "model_name": "LayoutModel",
792
+ "model_module_version": "1.2.0",
793
+ "state": {
794
+ "_model_module": "@jupyter-widgets/base",
795
+ "_model_module_version": "1.2.0",
796
+ "_model_name": "LayoutModel",
797
+ "_view_count": null,
798
+ "_view_module": "@jupyter-widgets/base",
799
+ "_view_module_version": "1.2.0",
800
+ "_view_name": "LayoutView",
801
+ "align_content": null,
802
+ "align_items": null,
803
+ "align_self": null,
804
+ "border": null,
805
+ "bottom": null,
806
+ "display": null,
807
+ "flex": null,
808
+ "flex_flow": null,
809
+ "grid_area": null,
810
+ "grid_auto_columns": null,
811
+ "grid_auto_flow": null,
812
+ "grid_auto_rows": null,
813
+ "grid_column": null,
814
+ "grid_gap": null,
815
+ "grid_row": null,
816
+ "grid_template_areas": null,
817
+ "grid_template_columns": null,
818
+ "grid_template_rows": null,
819
+ "height": null,
820
+ "justify_content": null,
821
+ "justify_items": null,
822
+ "left": null,
823
+ "margin": null,
824
+ "max_height": null,
825
+ "max_width": null,
826
+ "min_height": null,
827
+ "min_width": null,
828
+ "object_fit": null,
829
+ "object_position": null,
830
+ "order": null,
831
+ "overflow": null,
832
+ "overflow_x": null,
833
+ "overflow_y": null,
834
+ "padding": null,
835
+ "right": null,
836
+ "top": null,
837
+ "visibility": null,
838
+ "width": null
839
+ }
840
+ },
841
+ "8621ab22d387462da8319af86aab4586": {
842
+ "model_module": "@jupyter-widgets/base",
843
+ "model_name": "LayoutModel",
844
+ "model_module_version": "1.2.0",
845
+ "state": {
846
+ "_model_module": "@jupyter-widgets/base",
847
+ "_model_module_version": "1.2.0",
848
+ "_model_name": "LayoutModel",
849
+ "_view_count": null,
850
+ "_view_module": "@jupyter-widgets/base",
851
+ "_view_module_version": "1.2.0",
852
+ "_view_name": "LayoutView",
853
+ "align_content": null,
854
+ "align_items": null,
855
+ "align_self": null,
856
+ "border": null,
857
+ "bottom": null,
858
+ "display": null,
859
+ "flex": null,
860
+ "flex_flow": null,
861
+ "grid_area": null,
862
+ "grid_auto_columns": null,
863
+ "grid_auto_flow": null,
864
+ "grid_auto_rows": null,
865
+ "grid_column": null,
866
+ "grid_gap": null,
867
+ "grid_row": null,
868
+ "grid_template_areas": null,
869
+ "grid_template_columns": null,
870
+ "grid_template_rows": null,
871
+ "height": null,
872
+ "justify_content": null,
873
+ "justify_items": null,
874
+ "left": null,
875
+ "margin": null,
876
+ "max_height": null,
877
+ "max_width": null,
878
+ "min_height": null,
879
+ "min_width": null,
880
+ "object_fit": null,
881
+ "object_position": null,
882
+ "order": null,
883
+ "overflow": null,
884
+ "overflow_x": null,
885
+ "overflow_y": null,
886
+ "padding": null,
887
+ "right": null,
888
+ "top": null,
889
+ "visibility": null,
890
+ "width": null
891
+ }
892
+ },
893
+ "3b68a677d8384cebb43f325c8514e85a": {
894
+ "model_module": "@jupyter-widgets/controls",
895
+ "model_name": "DescriptionStyleModel",
896
+ "model_module_version": "1.5.0",
897
+ "state": {
898
+ "_model_module": "@jupyter-widgets/controls",
899
+ "_model_module_version": "1.5.0",
900
+ "_model_name": "DescriptionStyleModel",
901
+ "_view_count": null,
902
+ "_view_module": "@jupyter-widgets/base",
903
+ "_view_module_version": "1.2.0",
904
+ "_view_name": "StyleView",
905
+ "description_width": ""
906
+ }
907
+ },
908
+ "c8972f68b6324a2db5ec949f29e0c363": {
909
+ "model_module": "@jupyter-widgets/base",
910
+ "model_name": "LayoutModel",
911
+ "model_module_version": "1.2.0",
912
+ "state": {
913
+ "_model_module": "@jupyter-widgets/base",
914
+ "_model_module_version": "1.2.0",
915
+ "_model_name": "LayoutModel",
916
+ "_view_count": null,
917
+ "_view_module": "@jupyter-widgets/base",
918
+ "_view_module_version": "1.2.0",
919
+ "_view_name": "LayoutView",
920
+ "align_content": null,
921
+ "align_items": null,
922
+ "align_self": null,
923
+ "border": null,
924
+ "bottom": null,
925
+ "display": null,
926
+ "flex": null,
927
+ "flex_flow": null,
928
+ "grid_area": null,
929
+ "grid_auto_columns": null,
930
+ "grid_auto_flow": null,
931
+ "grid_auto_rows": null,
932
+ "grid_column": null,
933
+ "grid_gap": null,
934
+ "grid_row": null,
935
+ "grid_template_areas": null,
936
+ "grid_template_columns": null,
937
+ "grid_template_rows": null,
938
+ "height": null,
939
+ "justify_content": null,
940
+ "justify_items": null,
941
+ "left": null,
942
+ "margin": null,
943
+ "max_height": null,
944
+ "max_width": null,
945
+ "min_height": null,
946
+ "min_width": null,
947
+ "object_fit": null,
948
+ "object_position": null,
949
+ "order": null,
950
+ "overflow": null,
951
+ "overflow_x": null,
952
+ "overflow_y": null,
953
+ "padding": null,
954
+ "right": null,
955
+ "top": null,
956
+ "visibility": null,
957
+ "width": null
958
+ }
959
+ },
960
+ "1f13de458f444de5af2dc07f493b59ee": {
961
+ "model_module": "@jupyter-widgets/controls",
962
+ "model_name": "ProgressStyleModel",
963
+ "model_module_version": "1.5.0",
964
+ "state": {
965
+ "_model_module": "@jupyter-widgets/controls",
966
+ "_model_module_version": "1.5.0",
967
+ "_model_name": "ProgressStyleModel",
968
+ "_view_count": null,
969
+ "_view_module": "@jupyter-widgets/base",
970
+ "_view_module_version": "1.2.0",
971
+ "_view_name": "StyleView",
972
+ "bar_color": null,
973
+ "description_width": ""
974
+ }
975
+ },
976
+ "11225598bb8e4ae4bbba64b3dddb61ba": {
977
+ "model_module": "@jupyter-widgets/base",
978
+ "model_name": "LayoutModel",
979
+ "model_module_version": "1.2.0",
980
+ "state": {
981
+ "_model_module": "@jupyter-widgets/base",
982
+ "_model_module_version": "1.2.0",
983
+ "_model_name": "LayoutModel",
984
+ "_view_count": null,
985
+ "_view_module": "@jupyter-widgets/base",
986
+ "_view_module_version": "1.2.0",
987
+ "_view_name": "LayoutView",
988
+ "align_content": null,
989
+ "align_items": null,
990
+ "align_self": null,
991
+ "border": null,
992
+ "bottom": null,
993
+ "display": null,
994
+ "flex": null,
995
+ "flex_flow": null,
996
+ "grid_area": null,
997
+ "grid_auto_columns": null,
998
+ "grid_auto_flow": null,
999
+ "grid_auto_rows": null,
1000
+ "grid_column": null,
1001
+ "grid_gap": null,
1002
+ "grid_row": null,
1003
+ "grid_template_areas": null,
1004
+ "grid_template_columns": null,
1005
+ "grid_template_rows": null,
1006
+ "height": null,
1007
+ "justify_content": null,
1008
+ "justify_items": null,
1009
+ "left": null,
1010
+ "margin": null,
1011
+ "max_height": null,
1012
+ "max_width": null,
1013
+ "min_height": null,
1014
+ "min_width": null,
1015
+ "object_fit": null,
1016
+ "object_position": null,
1017
+ "order": null,
1018
+ "overflow": null,
1019
+ "overflow_x": null,
1020
+ "overflow_y": null,
1021
+ "padding": null,
1022
+ "right": null,
1023
+ "top": null,
1024
+ "visibility": null,
1025
+ "width": null
1026
+ }
1027
+ },
1028
+ "5aecdef3dc2a48ebb27e6b28b210deb5": {
1029
+ "model_module": "@jupyter-widgets/controls",
1030
+ "model_name": "DescriptionStyleModel",
1031
+ "model_module_version": "1.5.0",
1032
+ "state": {
1033
+ "_model_module": "@jupyter-widgets/controls",
1034
+ "_model_module_version": "1.5.0",
1035
+ "_model_name": "DescriptionStyleModel",
1036
+ "_view_count": null,
1037
+ "_view_module": "@jupyter-widgets/base",
1038
+ "_view_module_version": "1.2.0",
1039
+ "_view_name": "StyleView",
1040
+ "description_width": ""
1041
+ }
1042
+ },
1043
+ "3f75e2cce7a24f34be8029d15f6863c6": {
1044
+ "model_module": "@jupyter-widgets/controls",
1045
+ "model_name": "HBoxModel",
1046
+ "model_module_version": "1.5.0",
1047
+ "state": {
1048
+ "_dom_classes": [],
1049
+ "_model_module": "@jupyter-widgets/controls",
1050
+ "_model_module_version": "1.5.0",
1051
+ "_model_name": "HBoxModel",
1052
+ "_view_count": null,
1053
+ "_view_module": "@jupyter-widgets/controls",
1054
+ "_view_module_version": "1.5.0",
1055
+ "_view_name": "HBoxView",
1056
+ "box_style": "",
1057
+ "children": [
1058
+ "IPY_MODEL_f5cb3dc4fcab48a599f3491e245015cb",
1059
+ "IPY_MODEL_081bb0de9a39418a8902283155e43152",
1060
+ "IPY_MODEL_df6992acb63f4afba408dd046b06c1e3"
1061
+ ],
1062
+ "layout": "IPY_MODEL_b948765a1d6f461ca809cf07eb053991"
1063
+ }
1064
+ },
1065
+ "f5cb3dc4fcab48a599f3491e245015cb": {
1066
+ "model_module": "@jupyter-widgets/controls",
1067
+ "model_name": "HTMLModel",
1068
+ "model_module_version": "1.5.0",
1069
+ "state": {
1070
+ "_dom_classes": [],
1071
+ "_model_module": "@jupyter-widgets/controls",
1072
+ "_model_module_version": "1.5.0",
1073
+ "_model_name": "HTMLModel",
1074
+ "_view_count": null,
1075
+ "_view_module": "@jupyter-widgets/controls",
1076
+ "_view_module_version": "1.5.0",
1077
+ "_view_name": "HTMLView",
1078
+ "description": "",
1079
+ "description_tooltip": null,
1080
+ "layout": "IPY_MODEL_c504b8137cba4a8097f2a83ab3db4e65",
1081
+ "placeholder": "​",
1082
+ "style": "IPY_MODEL_4d7ddc0a2d3a41ffb50bce0413724a5f",
1083
+ "value": "config.json: 100%"
1084
+ }
1085
+ },
1086
+ "081bb0de9a39418a8902283155e43152": {
1087
+ "model_module": "@jupyter-widgets/controls",
1088
+ "model_name": "FloatProgressModel",
1089
+ "model_module_version": "1.5.0",
1090
+ "state": {
1091
+ "_dom_classes": [],
1092
+ "_model_module": "@jupyter-widgets/controls",
1093
+ "_model_module_version": "1.5.0",
1094
+ "_model_name": "FloatProgressModel",
1095
+ "_view_count": null,
1096
+ "_view_module": "@jupyter-widgets/controls",
1097
+ "_view_module_version": "1.5.0",
1098
+ "_view_name": "ProgressView",
1099
+ "bar_style": "success",
1100
+ "description": "",
1101
+ "description_tooltip": null,
1102
+ "layout": "IPY_MODEL_f38d8a3b88c0475eaa1a42c72bfa9464",
1103
+ "max": 570,
1104
+ "min": 0,
1105
+ "orientation": "horizontal",
1106
+ "style": "IPY_MODEL_c7b1b4df988e4224979b32cc65c3b1f3",
1107
+ "value": 570
1108
+ }
1109
+ },
1110
+ "df6992acb63f4afba408dd046b06c1e3": {
1111
+ "model_module": "@jupyter-widgets/controls",
1112
+ "model_name": "HTMLModel",
1113
+ "model_module_version": "1.5.0",
1114
+ "state": {
1115
+ "_dom_classes": [],
1116
+ "_model_module": "@jupyter-widgets/controls",
1117
+ "_model_module_version": "1.5.0",
1118
+ "_model_name": "HTMLModel",
1119
+ "_view_count": null,
1120
+ "_view_module": "@jupyter-widgets/controls",
1121
+ "_view_module_version": "1.5.0",
1122
+ "_view_name": "HTMLView",
1123
+ "description": "",
1124
+ "description_tooltip": null,
1125
+ "layout": "IPY_MODEL_4ed79ea00d974bce8cf6d6234c0cf5b0",
1126
+ "placeholder": "​",
1127
+ "style": "IPY_MODEL_64ecfc18946441f4a373acab64c489ee",
1128
+ "value": " 570/570 [00:00&lt;00:00, 9.22kB/s]"
1129
+ }
1130
+ },
1131
+ "b948765a1d6f461ca809cf07eb053991": {
1132
+ "model_module": "@jupyter-widgets/base",
1133
+ "model_name": "LayoutModel",
1134
+ "model_module_version": "1.2.0",
1135
+ "state": {
1136
+ "_model_module": "@jupyter-widgets/base",
1137
+ "_model_module_version": "1.2.0",
1138
+ "_model_name": "LayoutModel",
1139
+ "_view_count": null,
1140
+ "_view_module": "@jupyter-widgets/base",
1141
+ "_view_module_version": "1.2.0",
1142
+ "_view_name": "LayoutView",
1143
+ "align_content": null,
1144
+ "align_items": null,
1145
+ "align_self": null,
1146
+ "border": null,
1147
+ "bottom": null,
1148
+ "display": null,
1149
+ "flex": null,
1150
+ "flex_flow": null,
1151
+ "grid_area": null,
1152
+ "grid_auto_columns": null,
1153
+ "grid_auto_flow": null,
1154
+ "grid_auto_rows": null,
1155
+ "grid_column": null,
1156
+ "grid_gap": null,
1157
+ "grid_row": null,
1158
+ "grid_template_areas": null,
1159
+ "grid_template_columns": null,
1160
+ "grid_template_rows": null,
1161
+ "height": null,
1162
+ "justify_content": null,
1163
+ "justify_items": null,
1164
+ "left": null,
1165
+ "margin": null,
1166
+ "max_height": null,
1167
+ "max_width": null,
1168
+ "min_height": null,
1169
+ "min_width": null,
1170
+ "object_fit": null,
1171
+ "object_position": null,
1172
+ "order": null,
1173
+ "overflow": null,
1174
+ "overflow_x": null,
1175
+ "overflow_y": null,
1176
+ "padding": null,
1177
+ "right": null,
1178
+ "top": null,
1179
+ "visibility": null,
1180
+ "width": null
1181
+ }
1182
+ },
1183
+ "c504b8137cba4a8097f2a83ab3db4e65": {
1184
+ "model_module": "@jupyter-widgets/base",
1185
+ "model_name": "LayoutModel",
1186
+ "model_module_version": "1.2.0",
1187
+ "state": {
1188
+ "_model_module": "@jupyter-widgets/base",
1189
+ "_model_module_version": "1.2.0",
1190
+ "_model_name": "LayoutModel",
1191
+ "_view_count": null,
1192
+ "_view_module": "@jupyter-widgets/base",
1193
+ "_view_module_version": "1.2.0",
1194
+ "_view_name": "LayoutView",
1195
+ "align_content": null,
1196
+ "align_items": null,
1197
+ "align_self": null,
1198
+ "border": null,
1199
+ "bottom": null,
1200
+ "display": null,
1201
+ "flex": null,
1202
+ "flex_flow": null,
1203
+ "grid_area": null,
1204
+ "grid_auto_columns": null,
1205
+ "grid_auto_flow": null,
1206
+ "grid_auto_rows": null,
1207
+ "grid_column": null,
1208
+ "grid_gap": null,
1209
+ "grid_row": null,
1210
+ "grid_template_areas": null,
1211
+ "grid_template_columns": null,
1212
+ "grid_template_rows": null,
1213
+ "height": null,
1214
+ "justify_content": null,
1215
+ "justify_items": null,
1216
+ "left": null,
1217
+ "margin": null,
1218
+ "max_height": null,
1219
+ "max_width": null,
1220
+ "min_height": null,
1221
+ "min_width": null,
1222
+ "object_fit": null,
1223
+ "object_position": null,
1224
+ "order": null,
1225
+ "overflow": null,
1226
+ "overflow_x": null,
1227
+ "overflow_y": null,
1228
+ "padding": null,
1229
+ "right": null,
1230
+ "top": null,
1231
+ "visibility": null,
1232
+ "width": null
1233
+ }
1234
+ },
1235
+ "4d7ddc0a2d3a41ffb50bce0413724a5f": {
1236
+ "model_module": "@jupyter-widgets/controls",
1237
+ "model_name": "DescriptionStyleModel",
1238
+ "model_module_version": "1.5.0",
1239
+ "state": {
1240
+ "_model_module": "@jupyter-widgets/controls",
1241
+ "_model_module_version": "1.5.0",
1242
+ "_model_name": "DescriptionStyleModel",
1243
+ "_view_count": null,
1244
+ "_view_module": "@jupyter-widgets/base",
1245
+ "_view_module_version": "1.2.0",
1246
+ "_view_name": "StyleView",
1247
+ "description_width": ""
1248
+ }
1249
+ },
1250
+ "f38d8a3b88c0475eaa1a42c72bfa9464": {
1251
+ "model_module": "@jupyter-widgets/base",
1252
+ "model_name": "LayoutModel",
1253
+ "model_module_version": "1.2.0",
1254
+ "state": {
1255
+ "_model_module": "@jupyter-widgets/base",
1256
+ "_model_module_version": "1.2.0",
1257
+ "_model_name": "LayoutModel",
1258
+ "_view_count": null,
1259
+ "_view_module": "@jupyter-widgets/base",
1260
+ "_view_module_version": "1.2.0",
1261
+ "_view_name": "LayoutView",
1262
+ "align_content": null,
1263
+ "align_items": null,
1264
+ "align_self": null,
1265
+ "border": null,
1266
+ "bottom": null,
1267
+ "display": null,
1268
+ "flex": null,
1269
+ "flex_flow": null,
1270
+ "grid_area": null,
1271
+ "grid_auto_columns": null,
1272
+ "grid_auto_flow": null,
1273
+ "grid_auto_rows": null,
1274
+ "grid_column": null,
1275
+ "grid_gap": null,
1276
+ "grid_row": null,
1277
+ "grid_template_areas": null,
1278
+ "grid_template_columns": null,
1279
+ "grid_template_rows": null,
1280
+ "height": null,
1281
+ "justify_content": null,
1282
+ "justify_items": null,
1283
+ "left": null,
1284
+ "margin": null,
1285
+ "max_height": null,
1286
+ "max_width": null,
1287
+ "min_height": null,
1288
+ "min_width": null,
1289
+ "object_fit": null,
1290
+ "object_position": null,
1291
+ "order": null,
1292
+ "overflow": null,
1293
+ "overflow_x": null,
1294
+ "overflow_y": null,
1295
+ "padding": null,
1296
+ "right": null,
1297
+ "top": null,
1298
+ "visibility": null,
1299
+ "width": null
1300
+ }
1301
+ },
1302
+ "c7b1b4df988e4224979b32cc65c3b1f3": {
1303
+ "model_module": "@jupyter-widgets/controls",
1304
+ "model_name": "ProgressStyleModel",
1305
+ "model_module_version": "1.5.0",
1306
+ "state": {
1307
+ "_model_module": "@jupyter-widgets/controls",
1308
+ "_model_module_version": "1.5.0",
1309
+ "_model_name": "ProgressStyleModel",
1310
+ "_view_count": null,
1311
+ "_view_module": "@jupyter-widgets/base",
1312
+ "_view_module_version": "1.2.0",
1313
+ "_view_name": "StyleView",
1314
+ "bar_color": null,
1315
+ "description_width": ""
1316
+ }
1317
+ },
1318
+ "4ed79ea00d974bce8cf6d6234c0cf5b0": {
1319
+ "model_module": "@jupyter-widgets/base",
1320
+ "model_name": "LayoutModel",
1321
+ "model_module_version": "1.2.0",
1322
+ "state": {
1323
+ "_model_module": "@jupyter-widgets/base",
1324
+ "_model_module_version": "1.2.0",
1325
+ "_model_name": "LayoutModel",
1326
+ "_view_count": null,
1327
+ "_view_module": "@jupyter-widgets/base",
1328
+ "_view_module_version": "1.2.0",
1329
+ "_view_name": "LayoutView",
1330
+ "align_content": null,
1331
+ "align_items": null,
1332
+ "align_self": null,
1333
+ "border": null,
1334
+ "bottom": null,
1335
+ "display": null,
1336
+ "flex": null,
1337
+ "flex_flow": null,
1338
+ "grid_area": null,
1339
+ "grid_auto_columns": null,
1340
+ "grid_auto_flow": null,
1341
+ "grid_auto_rows": null,
1342
+ "grid_column": null,
1343
+ "grid_gap": null,
1344
+ "grid_row": null,
1345
+ "grid_template_areas": null,
1346
+ "grid_template_columns": null,
1347
+ "grid_template_rows": null,
1348
+ "height": null,
1349
+ "justify_content": null,
1350
+ "justify_items": null,
1351
+ "left": null,
1352
+ "margin": null,
1353
+ "max_height": null,
1354
+ "max_width": null,
1355
+ "min_height": null,
1356
+ "min_width": null,
1357
+ "object_fit": null,
1358
+ "object_position": null,
1359
+ "order": null,
1360
+ "overflow": null,
1361
+ "overflow_x": null,
1362
+ "overflow_y": null,
1363
+ "padding": null,
1364
+ "right": null,
1365
+ "top": null,
1366
+ "visibility": null,
1367
+ "width": null
1368
+ }
1369
+ },
1370
+ "64ecfc18946441f4a373acab64c489ee": {
1371
+ "model_module": "@jupyter-widgets/controls",
1372
+ "model_name": "DescriptionStyleModel",
1373
+ "model_module_version": "1.5.0",
1374
+ "state": {
1375
+ "_model_module": "@jupyter-widgets/controls",
1376
+ "_model_module_version": "1.5.0",
1377
+ "_model_name": "DescriptionStyleModel",
1378
+ "_view_count": null,
1379
+ "_view_module": "@jupyter-widgets/base",
1380
+ "_view_module_version": "1.2.0",
1381
+ "_view_name": "StyleView",
1382
+ "description_width": ""
1383
+ }
1384
+ },
1385
+ "998398ce2a944ad39820e8a62b3e9f46": {
1386
+ "model_module": "@jupyter-widgets/controls",
1387
+ "model_name": "HBoxModel",
1388
+ "model_module_version": "1.5.0",
1389
+ "state": {
1390
+ "_dom_classes": [],
1391
+ "_model_module": "@jupyter-widgets/controls",
1392
+ "_model_module_version": "1.5.0",
1393
+ "_model_name": "HBoxModel",
1394
+ "_view_count": null,
1395
+ "_view_module": "@jupyter-widgets/controls",
1396
+ "_view_module_version": "1.5.0",
1397
+ "_view_name": "HBoxView",
1398
+ "box_style": "",
1399
+ "children": [
1400
+ "IPY_MODEL_899e87bb4fc14328864c84c9569a38df",
1401
+ "IPY_MODEL_42f8515bc37f4340ab6a149652c75c46",
1402
+ "IPY_MODEL_d59f6dc0386449d8907a28b9e74a7e8a"
1403
+ ],
1404
+ "layout": "IPY_MODEL_d0e78dfeca05454097f4b9bdef31876d"
1405
+ }
1406
+ },
1407
+ "899e87bb4fc14328864c84c9569a38df": {
1408
+ "model_module": "@jupyter-widgets/controls",
1409
+ "model_name": "HTMLModel",
1410
+ "model_module_version": "1.5.0",
1411
+ "state": {
1412
+ "_dom_classes": [],
1413
+ "_model_module": "@jupyter-widgets/controls",
1414
+ "_model_module_version": "1.5.0",
1415
+ "_model_name": "HTMLModel",
1416
+ "_view_count": null,
1417
+ "_view_module": "@jupyter-widgets/controls",
1418
+ "_view_module_version": "1.5.0",
1419
+ "_view_name": "HTMLView",
1420
+ "description": "",
1421
+ "description_tooltip": null,
1422
+ "layout": "IPY_MODEL_7fb6f5cc399c43f6bc871778b61f5717",
1423
+ "placeholder": "​",
1424
+ "style": "IPY_MODEL_c6cb62ce51be437c95de41f0fadae844",
1425
+ "value": "model.safetensors: 100%"
1426
+ }
1427
+ },
1428
+ "42f8515bc37f4340ab6a149652c75c46": {
1429
+ "model_module": "@jupyter-widgets/controls",
1430
+ "model_name": "FloatProgressModel",
1431
+ "model_module_version": "1.5.0",
1432
+ "state": {
1433
+ "_dom_classes": [],
1434
+ "_model_module": "@jupyter-widgets/controls",
1435
+ "_model_module_version": "1.5.0",
1436
+ "_model_name": "FloatProgressModel",
1437
+ "_view_count": null,
1438
+ "_view_module": "@jupyter-widgets/controls",
1439
+ "_view_module_version": "1.5.0",
1440
+ "_view_name": "ProgressView",
1441
+ "bar_style": "success",
1442
+ "description": "",
1443
+ "description_tooltip": null,
1444
+ "layout": "IPY_MODEL_5cd183c4694a4c8287c442fa3dbb3283",
1445
+ "max": 440449768,
1446
+ "min": 0,
1447
+ "orientation": "horizontal",
1448
+ "style": "IPY_MODEL_659f449525854475b748338c8fd821e8",
1449
+ "value": 440449768
1450
+ }
1451
+ },
1452
+ "d59f6dc0386449d8907a28b9e74a7e8a": {
1453
+ "model_module": "@jupyter-widgets/controls",
1454
+ "model_name": "HTMLModel",
1455
+ "model_module_version": "1.5.0",
1456
+ "state": {
1457
+ "_dom_classes": [],
1458
+ "_model_module": "@jupyter-widgets/controls",
1459
+ "_model_module_version": "1.5.0",
1460
+ "_model_name": "HTMLModel",
1461
+ "_view_count": null,
1462
+ "_view_module": "@jupyter-widgets/controls",
1463
+ "_view_module_version": "1.5.0",
1464
+ "_view_name": "HTMLView",
1465
+ "description": "",
1466
+ "description_tooltip": null,
1467
+ "layout": "IPY_MODEL_c1a027432110420886fc6edb50c05d49",
1468
+ "placeholder": "​",
1469
+ "style": "IPY_MODEL_9e3d161934b546f3a0d11dea47c694a1",
1470
+ "value": " 440M/440M [00:07&lt;00:00, 18.9MB/s]"
1471
+ }
1472
+ },
1473
+ "d0e78dfeca05454097f4b9bdef31876d": {
1474
+ "model_module": "@jupyter-widgets/base",
1475
+ "model_name": "LayoutModel",
1476
+ "model_module_version": "1.2.0",
1477
+ "state": {
1478
+ "_model_module": "@jupyter-widgets/base",
1479
+ "_model_module_version": "1.2.0",
1480
+ "_model_name": "LayoutModel",
1481
+ "_view_count": null,
1482
+ "_view_module": "@jupyter-widgets/base",
1483
+ "_view_module_version": "1.2.0",
1484
+ "_view_name": "LayoutView",
1485
+ "align_content": null,
1486
+ "align_items": null,
1487
+ "align_self": null,
1488
+ "border": null,
1489
+ "bottom": null,
1490
+ "display": null,
1491
+ "flex": null,
1492
+ "flex_flow": null,
1493
+ "grid_area": null,
1494
+ "grid_auto_columns": null,
1495
+ "grid_auto_flow": null,
1496
+ "grid_auto_rows": null,
1497
+ "grid_column": null,
1498
+ "grid_gap": null,
1499
+ "grid_row": null,
1500
+ "grid_template_areas": null,
1501
+ "grid_template_columns": null,
1502
+ "grid_template_rows": null,
1503
+ "height": null,
1504
+ "justify_content": null,
1505
+ "justify_items": null,
1506
+ "left": null,
1507
+ "margin": null,
1508
+ "max_height": null,
1509
+ "max_width": null,
1510
+ "min_height": null,
1511
+ "min_width": null,
1512
+ "object_fit": null,
1513
+ "object_position": null,
1514
+ "order": null,
1515
+ "overflow": null,
1516
+ "overflow_x": null,
1517
+ "overflow_y": null,
1518
+ "padding": null,
1519
+ "right": null,
1520
+ "top": null,
1521
+ "visibility": null,
1522
+ "width": null
1523
+ }
1524
+ },
1525
+ "7fb6f5cc399c43f6bc871778b61f5717": {
1526
+ "model_module": "@jupyter-widgets/base",
1527
+ "model_name": "LayoutModel",
1528
+ "model_module_version": "1.2.0",
1529
+ "state": {
1530
+ "_model_module": "@jupyter-widgets/base",
1531
+ "_model_module_version": "1.2.0",
1532
+ "_model_name": "LayoutModel",
1533
+ "_view_count": null,
1534
+ "_view_module": "@jupyter-widgets/base",
1535
+ "_view_module_version": "1.2.0",
1536
+ "_view_name": "LayoutView",
1537
+ "align_content": null,
1538
+ "align_items": null,
1539
+ "align_self": null,
1540
+ "border": null,
1541
+ "bottom": null,
1542
+ "display": null,
1543
+ "flex": null,
1544
+ "flex_flow": null,
1545
+ "grid_area": null,
1546
+ "grid_auto_columns": null,
1547
+ "grid_auto_flow": null,
1548
+ "grid_auto_rows": null,
1549
+ "grid_column": null,
1550
+ "grid_gap": null,
1551
+ "grid_row": null,
1552
+ "grid_template_areas": null,
1553
+ "grid_template_columns": null,
1554
+ "grid_template_rows": null,
1555
+ "height": null,
1556
+ "justify_content": null,
1557
+ "justify_items": null,
1558
+ "left": null,
1559
+ "margin": null,
1560
+ "max_height": null,
1561
+ "max_width": null,
1562
+ "min_height": null,
1563
+ "min_width": null,
1564
+ "object_fit": null,
1565
+ "object_position": null,
1566
+ "order": null,
1567
+ "overflow": null,
1568
+ "overflow_x": null,
1569
+ "overflow_y": null,
1570
+ "padding": null,
1571
+ "right": null,
1572
+ "top": null,
1573
+ "visibility": null,
1574
+ "width": null
1575
+ }
1576
+ },
1577
+ "c6cb62ce51be437c95de41f0fadae844": {
1578
+ "model_module": "@jupyter-widgets/controls",
1579
+ "model_name": "DescriptionStyleModel",
1580
+ "model_module_version": "1.5.0",
1581
+ "state": {
1582
+ "_model_module": "@jupyter-widgets/controls",
1583
+ "_model_module_version": "1.5.0",
1584
+ "_model_name": "DescriptionStyleModel",
1585
+ "_view_count": null,
1586
+ "_view_module": "@jupyter-widgets/base",
1587
+ "_view_module_version": "1.2.0",
1588
+ "_view_name": "StyleView",
1589
+ "description_width": ""
1590
+ }
1591
+ },
1592
+ "5cd183c4694a4c8287c442fa3dbb3283": {
1593
+ "model_module": "@jupyter-widgets/base",
1594
+ "model_name": "LayoutModel",
1595
+ "model_module_version": "1.2.0",
1596
+ "state": {
1597
+ "_model_module": "@jupyter-widgets/base",
1598
+ "_model_module_version": "1.2.0",
1599
+ "_model_name": "LayoutModel",
1600
+ "_view_count": null,
1601
+ "_view_module": "@jupyter-widgets/base",
1602
+ "_view_module_version": "1.2.0",
1603
+ "_view_name": "LayoutView",
1604
+ "align_content": null,
1605
+ "align_items": null,
1606
+ "align_self": null,
1607
+ "border": null,
1608
+ "bottom": null,
1609
+ "display": null,
1610
+ "flex": null,
1611
+ "flex_flow": null,
1612
+ "grid_area": null,
1613
+ "grid_auto_columns": null,
1614
+ "grid_auto_flow": null,
1615
+ "grid_auto_rows": null,
1616
+ "grid_column": null,
1617
+ "grid_gap": null,
1618
+ "grid_row": null,
1619
+ "grid_template_areas": null,
1620
+ "grid_template_columns": null,
1621
+ "grid_template_rows": null,
1622
+ "height": null,
1623
+ "justify_content": null,
1624
+ "justify_items": null,
1625
+ "left": null,
1626
+ "margin": null,
1627
+ "max_height": null,
1628
+ "max_width": null,
1629
+ "min_height": null,
1630
+ "min_width": null,
1631
+ "object_fit": null,
1632
+ "object_position": null,
1633
+ "order": null,
1634
+ "overflow": null,
1635
+ "overflow_x": null,
1636
+ "overflow_y": null,
1637
+ "padding": null,
1638
+ "right": null,
1639
+ "top": null,
1640
+ "visibility": null,
1641
+ "width": null
1642
+ }
1643
+ },
1644
+ "659f449525854475b748338c8fd821e8": {
1645
+ "model_module": "@jupyter-widgets/controls",
1646
+ "model_name": "ProgressStyleModel",
1647
+ "model_module_version": "1.5.0",
1648
+ "state": {
1649
+ "_model_module": "@jupyter-widgets/controls",
1650
+ "_model_module_version": "1.5.0",
1651
+ "_model_name": "ProgressStyleModel",
1652
+ "_view_count": null,
1653
+ "_view_module": "@jupyter-widgets/base",
1654
+ "_view_module_version": "1.2.0",
1655
+ "_view_name": "StyleView",
1656
+ "bar_color": null,
1657
+ "description_width": ""
1658
+ }
1659
+ },
1660
+ "c1a027432110420886fc6edb50c05d49": {
1661
+ "model_module": "@jupyter-widgets/base",
1662
+ "model_name": "LayoutModel",
1663
+ "model_module_version": "1.2.0",
1664
+ "state": {
1665
+ "_model_module": "@jupyter-widgets/base",
1666
+ "_model_module_version": "1.2.0",
1667
+ "_model_name": "LayoutModel",
1668
+ "_view_count": null,
1669
+ "_view_module": "@jupyter-widgets/base",
1670
+ "_view_module_version": "1.2.0",
1671
+ "_view_name": "LayoutView",
1672
+ "align_content": null,
1673
+ "align_items": null,
1674
+ "align_self": null,
1675
+ "border": null,
1676
+ "bottom": null,
1677
+ "display": null,
1678
+ "flex": null,
1679
+ "flex_flow": null,
1680
+ "grid_area": null,
1681
+ "grid_auto_columns": null,
1682
+ "grid_auto_flow": null,
1683
+ "grid_auto_rows": null,
1684
+ "grid_column": null,
1685
+ "grid_gap": null,
1686
+ "grid_row": null,
1687
+ "grid_template_areas": null,
1688
+ "grid_template_columns": null,
1689
+ "grid_template_rows": null,
1690
+ "height": null,
1691
+ "justify_content": null,
1692
+ "justify_items": null,
1693
+ "left": null,
1694
+ "margin": null,
1695
+ "max_height": null,
1696
+ "max_width": null,
1697
+ "min_height": null,
1698
+ "min_width": null,
1699
+ "object_fit": null,
1700
+ "object_position": null,
1701
+ "order": null,
1702
+ "overflow": null,
1703
+ "overflow_x": null,
1704
+ "overflow_y": null,
1705
+ "padding": null,
1706
+ "right": null,
1707
+ "top": null,
1708
+ "visibility": null,
1709
+ "width": null
1710
+ }
1711
+ },
1712
+ "9e3d161934b546f3a0d11dea47c694a1": {
1713
+ "model_module": "@jupyter-widgets/controls",
1714
+ "model_name": "DescriptionStyleModel",
1715
+ "model_module_version": "1.5.0",
1716
+ "state": {
1717
+ "_model_module": "@jupyter-widgets/controls",
1718
+ "_model_module_version": "1.5.0",
1719
+ "_model_name": "DescriptionStyleModel",
1720
+ "_view_count": null,
1721
+ "_view_module": "@jupyter-widgets/base",
1722
+ "_view_module_version": "1.2.0",
1723
+ "_view_name": "StyleView",
1724
+ "description_width": ""
1725
+ }
1726
+ }
1727
+ }
1728
+ }
1729
+ },
1730
+ "cells": [
1731
+ {
1732
+ "cell_type": "code",
1733
+ "execution_count": 1,
1734
+ "metadata": {
1735
+ "colab": {
1736
+ "base_uri": "https://localhost:8080/",
1737
+ "height": 324,
1738
+ "referenced_widgets": [
1739
+ "222776c1f6d140bc93eb7860a259444b",
1740
+ "f56e4df7c4104d228b6fb45d4a3853c5",
1741
+ "3e050cbb980b4560b44b37ef16772bea",
1742
+ "419d595aa37941e78c1caff94ebb3f48",
1743
+ "1fa5a41a884645b9be9b6427e9118499",
1744
+ "bf5a1e82216d453197b70832888c7704",
1745
+ "15ea32962b2341e3ad5d20a7e65d35ca",
1746
+ "9656534abe284e09a66b81d1381c17d5",
1747
+ "d270ccd8d9de4749b535c93f39f09631",
1748
+ "136c9a8ddb134246ac72881c8821ff1a",
1749
+ "62d892261d0e42bf90ed96f82f9af608",
1750
+ "567320fc6a8d4809b07af8e731fc6c8e",
1751
+ "b91785c4cee645fba4f33a44d83e1cc8",
1752
+ "d1d966ed26b04ee48509b26d5f333404",
1753
+ "c2f6606ed6764833a6b22feb4e648ad8",
1754
+ "576db19e9a2242dfa1924fff4216c2a6",
1755
+ "7df364097e4141d8b6d8a154dd0b5167",
1756
+ "2ef10079e12b493eb72872a193ea8418",
1757
+ "e29681c9faf4469988ec914982979cad",
1758
+ "9a538eb4f01440a6ac1a83ca12db9872",
1759
+ "6aec82e9ef844d0bb363b913258bfe01",
1760
+ "7f19e624ef904c36b8e6fe896999fe6d",
1761
+ "4ee356f5fe034c3f8d644b5671a4cfcc",
1762
+ "eac117b1ab5f49e2b5928a862828fd83",
1763
+ "aa6bce5cf9244895bc37535203051a61",
1764
+ "8e32bb708c54412ab85a28937e392e91",
1765
+ "d83cbbfdf7cd4944a54c39509425cc83",
1766
+ "8621ab22d387462da8319af86aab4586",
1767
+ "3b68a677d8384cebb43f325c8514e85a",
1768
+ "c8972f68b6324a2db5ec949f29e0c363",
1769
+ "1f13de458f444de5af2dc07f493b59ee",
1770
+ "11225598bb8e4ae4bbba64b3dddb61ba",
1771
+ "5aecdef3dc2a48ebb27e6b28b210deb5",
1772
+ "3f75e2cce7a24f34be8029d15f6863c6",
1773
+ "f5cb3dc4fcab48a599f3491e245015cb",
1774
+ "081bb0de9a39418a8902283155e43152",
1775
+ "df6992acb63f4afba408dd046b06c1e3",
1776
+ "b948765a1d6f461ca809cf07eb053991",
1777
+ "c504b8137cba4a8097f2a83ab3db4e65",
1778
+ "4d7ddc0a2d3a41ffb50bce0413724a5f",
1779
+ "f38d8a3b88c0475eaa1a42c72bfa9464",
1780
+ "c7b1b4df988e4224979b32cc65c3b1f3",
1781
+ "4ed79ea00d974bce8cf6d6234c0cf5b0",
1782
+ "64ecfc18946441f4a373acab64c489ee",
1783
+ "998398ce2a944ad39820e8a62b3e9f46",
1784
+ "899e87bb4fc14328864c84c9569a38df",
1785
+ "42f8515bc37f4340ab6a149652c75c46",
1786
+ "d59f6dc0386449d8907a28b9e74a7e8a",
1787
+ "d0e78dfeca05454097f4b9bdef31876d",
1788
+ "7fb6f5cc399c43f6bc871778b61f5717",
1789
+ "c6cb62ce51be437c95de41f0fadae844",
1790
+ "5cd183c4694a4c8287c442fa3dbb3283",
1791
+ "659f449525854475b748338c8fd821e8",
1792
+ "c1a027432110420886fc6edb50c05d49",
1793
+ "9e3d161934b546f3a0d11dea47c694a1"
1794
+ ]
1795
+ },
1796
+ "id": "BMTOQild8_ZN",
1797
+ "outputId": "7d1ccbad-68e6-4314-e2cf-23abb596001b"
1798
+ },
1799
+ "outputs": [
1800
+ {
1801
+ "output_type": "stream",
1802
+ "name": "stderr",
1803
+ "text": [
1804
+ "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: UserWarning: \n",
1805
+ "The secret `HF_TOKEN` does not exist in your Colab secrets.\n",
1806
+ "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n",
1807
+ "You will be able to reuse this secret in all of your notebooks.\n",
1808
+ "Please note that authentication is recommended but still optional to access public models or datasets.\n",
1809
+ " warnings.warn(\n"
1810
+ ]
1811
+ },
1812
+ {
1813
+ "output_type": "display_data",
1814
+ "data": {
1815
+ "text/plain": [
1816
+ "tokenizer_config.json: 0%| | 0.00/48.0 [00:00<?, ?B/s]"
1817
+ ],
1818
+ "application/vnd.jupyter.widget-view+json": {
1819
+ "version_major": 2,
1820
+ "version_minor": 0,
1821
+ "model_id": "222776c1f6d140bc93eb7860a259444b"
1822
+ }
1823
+ },
1824
+ "metadata": {}
1825
+ },
1826
+ {
1827
+ "output_type": "display_data",
1828
+ "data": {
1829
+ "text/plain": [
1830
+ "vocab.txt: 0%| | 0.00/232k [00:00<?, ?B/s]"
1831
+ ],
1832
+ "application/vnd.jupyter.widget-view+json": {
1833
+ "version_major": 2,
1834
+ "version_minor": 0,
1835
+ "model_id": "567320fc6a8d4809b07af8e731fc6c8e"
1836
+ }
1837
+ },
1838
+ "metadata": {}
1839
+ },
1840
+ {
1841
+ "output_type": "display_data",
1842
+ "data": {
1843
+ "text/plain": [
1844
+ "tokenizer.json: 0%| | 0.00/466k [00:00<?, ?B/s]"
1845
+ ],
1846
+ "application/vnd.jupyter.widget-view+json": {
1847
+ "version_major": 2,
1848
+ "version_minor": 0,
1849
+ "model_id": "4ee356f5fe034c3f8d644b5671a4cfcc"
1850
+ }
1851
+ },
1852
+ "metadata": {}
1853
+ },
1854
+ {
1855
+ "output_type": "display_data",
1856
+ "data": {
1857
+ "text/plain": [
1858
+ "config.json: 0%| | 0.00/570 [00:00<?, ?B/s]"
1859
+ ],
1860
+ "application/vnd.jupyter.widget-view+json": {
1861
+ "version_major": 2,
1862
+ "version_minor": 0,
1863
+ "model_id": "3f75e2cce7a24f34be8029d15f6863c6"
1864
+ }
1865
+ },
1866
+ "metadata": {}
1867
+ },
1868
+ {
1869
+ "output_type": "display_data",
1870
+ "data": {
1871
+ "text/plain": [
1872
+ "model.safetensors: 0%| | 0.00/440M [00:00<?, ?B/s]"
1873
+ ],
1874
+ "application/vnd.jupyter.widget-view+json": {
1875
+ "version_major": 2,
1876
+ "version_minor": 0,
1877
+ "model_id": "998398ce2a944ad39820e8a62b3e9f46"
1878
+ }
1879
+ },
1880
+ "metadata": {}
1881
+ },
1882
+ {
1883
+ "output_type": "stream",
1884
+ "name": "stdout",
1885
+ "text": [
1886
+ "torch.Size([5, 768])\n"
1887
+ ]
1888
+ }
1889
+ ],
1890
+ "source": [
1891
+ "from transformers import BertTokenizer, BertModel\n",
1892
+ "import torch\n",
1893
+ "\n",
1894
+ "# Inisialisasi tokenizer dan model BERT\n",
1895
+ "tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')\n",
1896
+ "model = BertModel.from_pretrained('bert-base-uncased')\n",
1897
+ "\n",
1898
+ "# Misalkan kita memiliki daftar artikel\n",
1899
+ "articles = [\n",
1900
+ " \"Breaking news: AI is revolutionizing industries.\",\n",
1901
+ " \"Discover the wonders of the universe with the latest space exploration.\",\n",
1902
+ " \"Stock market sees record highs amid economic recovery.\",\n",
1903
+ " \"New advancements in quantum computing could change the world.\",\n",
1904
+ " \"Climate change impacts are becoming more severe.\"\n",
1905
+ "]\n",
1906
+ "\n",
1907
+ "# Ekstraksi embedding untuk setiap artikel\n",
1908
+ "embeddings = []\n",
1909
+ "for article in articles:\n",
1910
+ " inputs = tokenizer(article, return_tensors='pt', max_length=512, truncation=True, padding=True)\n",
1911
+ " with torch.no_grad():\n",
1912
+ " outputs = model(**inputs)\n",
1913
+ " # Ambil embedding dari token [CLS]\n",
1914
+ " cls_embedding = outputs.last_hidden_state[:, 0, :]\n",
1915
+ " embeddings.append(cls_embedding)\n",
1916
+ "\n",
1917
+ "# Konversi list of tensors menjadi satu tensor besar\n",
1918
+ "embeddings = torch.cat(embeddings, dim=0)\n",
1919
+ "print(embeddings.shape) # Output: (jumlah artikel, 768)"
1920
+ ]
1921
+ },
1922
+ {
1923
+ "cell_type": "code",
1924
+ "source": [
1925
+ "from torch.nn.functional import cosine_similarity\n",
1926
+ "\n",
1927
+ "# Misalkan embedding pengguna (simulasi, diambil dari rata-rata beberapa artikel yang disukai pengguna)\n",
1928
+ "user_embedding = torch.mean(embeddings[:2], dim=0) # Misalkan pengguna menyukai dua artikel pertama\n",
1929
+ "\n",
1930
+ "# Hitung kesamaan dengan semua artikel\n",
1931
+ "similarities = cosine_similarity(user_embedding.unsqueeze(0), embeddings)\n",
1932
+ "\n",
1933
+ "# Ambil indeks artikel dengan kesamaan tertinggi\n",
1934
+ "top_k = similarities.topk(k=3) # Kembalikan 3 artikel teratas\n",
1935
+ "print(\"Top 3 Recommended Articles:\", articles[top_k.indices[0]])"
1936
+ ],
1937
+ "metadata": {
1938
+ "colab": {
1939
+ "base_uri": "https://localhost:8080/"
1940
+ },
1941
+ "id": "ez5mZ9Bu9mXg",
1942
+ "outputId": "e5fc0004-41c6-4f81-e4cb-16fd0eb5b8d4"
1943
+ },
1944
+ "execution_count": 8,
1945
+ "outputs": [
1946
+ {
1947
+ "output_type": "stream",
1948
+ "name": "stdout",
1949
+ "text": [
1950
+ "Top 3 Recommended Articles: Discover the wonders of the universe with the latest space exploration.\n"
1951
+ ]
1952
+ }
1953
+ ]
1954
+ }
1955
+ ]
1956
+ }
9. Latihan_SciBERT_For_RS.ipynb ADDED
@@ -0,0 +1,1277 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": []
7
+ },
8
+ "kernelspec": {
9
+ "name": "python3",
10
+ "display_name": "Python 3"
11
+ },
12
+ "language_info": {
13
+ "name": "python"
14
+ },
15
+ "widgets": {
16
+ "application/vnd.jupyter.widget-state+json": {
17
+ "885937018a634de0a6deb830bb194716": {
18
+ "model_module": "@jupyter-widgets/controls",
19
+ "model_name": "HBoxModel",
20
+ "model_module_version": "1.5.0",
21
+ "state": {
22
+ "_dom_classes": [],
23
+ "_model_module": "@jupyter-widgets/controls",
24
+ "_model_module_version": "1.5.0",
25
+ "_model_name": "HBoxModel",
26
+ "_view_count": null,
27
+ "_view_module": "@jupyter-widgets/controls",
28
+ "_view_module_version": "1.5.0",
29
+ "_view_name": "HBoxView",
30
+ "box_style": "",
31
+ "children": [
32
+ "IPY_MODEL_2483b50c7f9342faa91062f6dac2f2a8",
33
+ "IPY_MODEL_64a96102ed7b4ab0b59b0b1d97add383",
34
+ "IPY_MODEL_986a7cf0b85b4cc7803a03b4373edcaf"
35
+ ],
36
+ "layout": "IPY_MODEL_d1b7ccd4754744509c3e45db8d651e5d"
37
+ }
38
+ },
39
+ "2483b50c7f9342faa91062f6dac2f2a8": {
40
+ "model_module": "@jupyter-widgets/controls",
41
+ "model_name": "HTMLModel",
42
+ "model_module_version": "1.5.0",
43
+ "state": {
44
+ "_dom_classes": [],
45
+ "_model_module": "@jupyter-widgets/controls",
46
+ "_model_module_version": "1.5.0",
47
+ "_model_name": "HTMLModel",
48
+ "_view_count": null,
49
+ "_view_module": "@jupyter-widgets/controls",
50
+ "_view_module_version": "1.5.0",
51
+ "_view_name": "HTMLView",
52
+ "description": "",
53
+ "description_tooltip": null,
54
+ "layout": "IPY_MODEL_0c1c8ec0ed6445b48f3f8787ac66ffe2",
55
+ "placeholder": "​",
56
+ "style": "IPY_MODEL_117698ddf34d4592ad0309fa403f6122",
57
+ "value": "config.json: 100%"
58
+ }
59
+ },
60
+ "64a96102ed7b4ab0b59b0b1d97add383": {
61
+ "model_module": "@jupyter-widgets/controls",
62
+ "model_name": "FloatProgressModel",
63
+ "model_module_version": "1.5.0",
64
+ "state": {
65
+ "_dom_classes": [],
66
+ "_model_module": "@jupyter-widgets/controls",
67
+ "_model_module_version": "1.5.0",
68
+ "_model_name": "FloatProgressModel",
69
+ "_view_count": null,
70
+ "_view_module": "@jupyter-widgets/controls",
71
+ "_view_module_version": "1.5.0",
72
+ "_view_name": "ProgressView",
73
+ "bar_style": "success",
74
+ "description": "",
75
+ "description_tooltip": null,
76
+ "layout": "IPY_MODEL_16774c5f05ca45d790eb770a2f1d2ef3",
77
+ "max": 385,
78
+ "min": 0,
79
+ "orientation": "horizontal",
80
+ "style": "IPY_MODEL_1a2e33ca554e4e1c9daee3c9d9568604",
81
+ "value": 385
82
+ }
83
+ },
84
+ "986a7cf0b85b4cc7803a03b4373edcaf": {
85
+ "model_module": "@jupyter-widgets/controls",
86
+ "model_name": "HTMLModel",
87
+ "model_module_version": "1.5.0",
88
+ "state": {
89
+ "_dom_classes": [],
90
+ "_model_module": "@jupyter-widgets/controls",
91
+ "_model_module_version": "1.5.0",
92
+ "_model_name": "HTMLModel",
93
+ "_view_count": null,
94
+ "_view_module": "@jupyter-widgets/controls",
95
+ "_view_module_version": "1.5.0",
96
+ "_view_name": "HTMLView",
97
+ "description": "",
98
+ "description_tooltip": null,
99
+ "layout": "IPY_MODEL_6aad8d81d1964d31babe734f809aca79",
100
+ "placeholder": "​",
101
+ "style": "IPY_MODEL_a5f0667376174a3fad64da397a3dd92f",
102
+ "value": " 385/385 [00:00&lt;00:00, 4.79kB/s]"
103
+ }
104
+ },
105
+ "d1b7ccd4754744509c3e45db8d651e5d": {
106
+ "model_module": "@jupyter-widgets/base",
107
+ "model_name": "LayoutModel",
108
+ "model_module_version": "1.2.0",
109
+ "state": {
110
+ "_model_module": "@jupyter-widgets/base",
111
+ "_model_module_version": "1.2.0",
112
+ "_model_name": "LayoutModel",
113
+ "_view_count": null,
114
+ "_view_module": "@jupyter-widgets/base",
115
+ "_view_module_version": "1.2.0",
116
+ "_view_name": "LayoutView",
117
+ "align_content": null,
118
+ "align_items": null,
119
+ "align_self": null,
120
+ "border": null,
121
+ "bottom": null,
122
+ "display": null,
123
+ "flex": null,
124
+ "flex_flow": null,
125
+ "grid_area": null,
126
+ "grid_auto_columns": null,
127
+ "grid_auto_flow": null,
128
+ "grid_auto_rows": null,
129
+ "grid_column": null,
130
+ "grid_gap": null,
131
+ "grid_row": null,
132
+ "grid_template_areas": null,
133
+ "grid_template_columns": null,
134
+ "grid_template_rows": null,
135
+ "height": null,
136
+ "justify_content": null,
137
+ "justify_items": null,
138
+ "left": null,
139
+ "margin": null,
140
+ "max_height": null,
141
+ "max_width": null,
142
+ "min_height": null,
143
+ "min_width": null,
144
+ "object_fit": null,
145
+ "object_position": null,
146
+ "order": null,
147
+ "overflow": null,
148
+ "overflow_x": null,
149
+ "overflow_y": null,
150
+ "padding": null,
151
+ "right": null,
152
+ "top": null,
153
+ "visibility": null,
154
+ "width": null
155
+ }
156
+ },
157
+ "0c1c8ec0ed6445b48f3f8787ac66ffe2": {
158
+ "model_module": "@jupyter-widgets/base",
159
+ "model_name": "LayoutModel",
160
+ "model_module_version": "1.2.0",
161
+ "state": {
162
+ "_model_module": "@jupyter-widgets/base",
163
+ "_model_module_version": "1.2.0",
164
+ "_model_name": "LayoutModel",
165
+ "_view_count": null,
166
+ "_view_module": "@jupyter-widgets/base",
167
+ "_view_module_version": "1.2.0",
168
+ "_view_name": "LayoutView",
169
+ "align_content": null,
170
+ "align_items": null,
171
+ "align_self": null,
172
+ "border": null,
173
+ "bottom": null,
174
+ "display": null,
175
+ "flex": null,
176
+ "flex_flow": null,
177
+ "grid_area": null,
178
+ "grid_auto_columns": null,
179
+ "grid_auto_flow": null,
180
+ "grid_auto_rows": null,
181
+ "grid_column": null,
182
+ "grid_gap": null,
183
+ "grid_row": null,
184
+ "grid_template_areas": null,
185
+ "grid_template_columns": null,
186
+ "grid_template_rows": null,
187
+ "height": null,
188
+ "justify_content": null,
189
+ "justify_items": null,
190
+ "left": null,
191
+ "margin": null,
192
+ "max_height": null,
193
+ "max_width": null,
194
+ "min_height": null,
195
+ "min_width": null,
196
+ "object_fit": null,
197
+ "object_position": null,
198
+ "order": null,
199
+ "overflow": null,
200
+ "overflow_x": null,
201
+ "overflow_y": null,
202
+ "padding": null,
203
+ "right": null,
204
+ "top": null,
205
+ "visibility": null,
206
+ "width": null
207
+ }
208
+ },
209
+ "117698ddf34d4592ad0309fa403f6122": {
210
+ "model_module": "@jupyter-widgets/controls",
211
+ "model_name": "DescriptionStyleModel",
212
+ "model_module_version": "1.5.0",
213
+ "state": {
214
+ "_model_module": "@jupyter-widgets/controls",
215
+ "_model_module_version": "1.5.0",
216
+ "_model_name": "DescriptionStyleModel",
217
+ "_view_count": null,
218
+ "_view_module": "@jupyter-widgets/base",
219
+ "_view_module_version": "1.2.0",
220
+ "_view_name": "StyleView",
221
+ "description_width": ""
222
+ }
223
+ },
224
+ "16774c5f05ca45d790eb770a2f1d2ef3": {
225
+ "model_module": "@jupyter-widgets/base",
226
+ "model_name": "LayoutModel",
227
+ "model_module_version": "1.2.0",
228
+ "state": {
229
+ "_model_module": "@jupyter-widgets/base",
230
+ "_model_module_version": "1.2.0",
231
+ "_model_name": "LayoutModel",
232
+ "_view_count": null,
233
+ "_view_module": "@jupyter-widgets/base",
234
+ "_view_module_version": "1.2.0",
235
+ "_view_name": "LayoutView",
236
+ "align_content": null,
237
+ "align_items": null,
238
+ "align_self": null,
239
+ "border": null,
240
+ "bottom": null,
241
+ "display": null,
242
+ "flex": null,
243
+ "flex_flow": null,
244
+ "grid_area": null,
245
+ "grid_auto_columns": null,
246
+ "grid_auto_flow": null,
247
+ "grid_auto_rows": null,
248
+ "grid_column": null,
249
+ "grid_gap": null,
250
+ "grid_row": null,
251
+ "grid_template_areas": null,
252
+ "grid_template_columns": null,
253
+ "grid_template_rows": null,
254
+ "height": null,
255
+ "justify_content": null,
256
+ "justify_items": null,
257
+ "left": null,
258
+ "margin": null,
259
+ "max_height": null,
260
+ "max_width": null,
261
+ "min_height": null,
262
+ "min_width": null,
263
+ "object_fit": null,
264
+ "object_position": null,
265
+ "order": null,
266
+ "overflow": null,
267
+ "overflow_x": null,
268
+ "overflow_y": null,
269
+ "padding": null,
270
+ "right": null,
271
+ "top": null,
272
+ "visibility": null,
273
+ "width": null
274
+ }
275
+ },
276
+ "1a2e33ca554e4e1c9daee3c9d9568604": {
277
+ "model_module": "@jupyter-widgets/controls",
278
+ "model_name": "ProgressStyleModel",
279
+ "model_module_version": "1.5.0",
280
+ "state": {
281
+ "_model_module": "@jupyter-widgets/controls",
282
+ "_model_module_version": "1.5.0",
283
+ "_model_name": "ProgressStyleModel",
284
+ "_view_count": null,
285
+ "_view_module": "@jupyter-widgets/base",
286
+ "_view_module_version": "1.2.0",
287
+ "_view_name": "StyleView",
288
+ "bar_color": null,
289
+ "description_width": ""
290
+ }
291
+ },
292
+ "6aad8d81d1964d31babe734f809aca79": {
293
+ "model_module": "@jupyter-widgets/base",
294
+ "model_name": "LayoutModel",
295
+ "model_module_version": "1.2.0",
296
+ "state": {
297
+ "_model_module": "@jupyter-widgets/base",
298
+ "_model_module_version": "1.2.0",
299
+ "_model_name": "LayoutModel",
300
+ "_view_count": null,
301
+ "_view_module": "@jupyter-widgets/base",
302
+ "_view_module_version": "1.2.0",
303
+ "_view_name": "LayoutView",
304
+ "align_content": null,
305
+ "align_items": null,
306
+ "align_self": null,
307
+ "border": null,
308
+ "bottom": null,
309
+ "display": null,
310
+ "flex": null,
311
+ "flex_flow": null,
312
+ "grid_area": null,
313
+ "grid_auto_columns": null,
314
+ "grid_auto_flow": null,
315
+ "grid_auto_rows": null,
316
+ "grid_column": null,
317
+ "grid_gap": null,
318
+ "grid_row": null,
319
+ "grid_template_areas": null,
320
+ "grid_template_columns": null,
321
+ "grid_template_rows": null,
322
+ "height": null,
323
+ "justify_content": null,
324
+ "justify_items": null,
325
+ "left": null,
326
+ "margin": null,
327
+ "max_height": null,
328
+ "max_width": null,
329
+ "min_height": null,
330
+ "min_width": null,
331
+ "object_fit": null,
332
+ "object_position": null,
333
+ "order": null,
334
+ "overflow": null,
335
+ "overflow_x": null,
336
+ "overflow_y": null,
337
+ "padding": null,
338
+ "right": null,
339
+ "top": null,
340
+ "visibility": null,
341
+ "width": null
342
+ }
343
+ },
344
+ "a5f0667376174a3fad64da397a3dd92f": {
345
+ "model_module": "@jupyter-widgets/controls",
346
+ "model_name": "DescriptionStyleModel",
347
+ "model_module_version": "1.5.0",
348
+ "state": {
349
+ "_model_module": "@jupyter-widgets/controls",
350
+ "_model_module_version": "1.5.0",
351
+ "_model_name": "DescriptionStyleModel",
352
+ "_view_count": null,
353
+ "_view_module": "@jupyter-widgets/base",
354
+ "_view_module_version": "1.2.0",
355
+ "_view_name": "StyleView",
356
+ "description_width": ""
357
+ }
358
+ },
359
+ "b4309550192c49019293c1d1ce0f97d4": {
360
+ "model_module": "@jupyter-widgets/controls",
361
+ "model_name": "HBoxModel",
362
+ "model_module_version": "1.5.0",
363
+ "state": {
364
+ "_dom_classes": [],
365
+ "_model_module": "@jupyter-widgets/controls",
366
+ "_model_module_version": "1.5.0",
367
+ "_model_name": "HBoxModel",
368
+ "_view_count": null,
369
+ "_view_module": "@jupyter-widgets/controls",
370
+ "_view_module_version": "1.5.0",
371
+ "_view_name": "HBoxView",
372
+ "box_style": "",
373
+ "children": [
374
+ "IPY_MODEL_79868f65f0ad4ffc8384e8de8f79bf0c",
375
+ "IPY_MODEL_50959c940ac44e23b6fc8db4d0021bc0",
376
+ "IPY_MODEL_e9d4ada4ded3484f88f9d41ebc9d1994"
377
+ ],
378
+ "layout": "IPY_MODEL_10f4d53cfc8544b7a3a43d0a766ac18c"
379
+ }
380
+ },
381
+ "79868f65f0ad4ffc8384e8de8f79bf0c": {
382
+ "model_module": "@jupyter-widgets/controls",
383
+ "model_name": "HTMLModel",
384
+ "model_module_version": "1.5.0",
385
+ "state": {
386
+ "_dom_classes": [],
387
+ "_model_module": "@jupyter-widgets/controls",
388
+ "_model_module_version": "1.5.0",
389
+ "_model_name": "HTMLModel",
390
+ "_view_count": null,
391
+ "_view_module": "@jupyter-widgets/controls",
392
+ "_view_module_version": "1.5.0",
393
+ "_view_name": "HTMLView",
394
+ "description": "",
395
+ "description_tooltip": null,
396
+ "layout": "IPY_MODEL_c739b23d114f422cb34b0d391f80ee12",
397
+ "placeholder": "​",
398
+ "style": "IPY_MODEL_350fb7675a154f8da40406da0271ab4d",
399
+ "value": "vocab.txt: 100%"
400
+ }
401
+ },
402
+ "50959c940ac44e23b6fc8db4d0021bc0": {
403
+ "model_module": "@jupyter-widgets/controls",
404
+ "model_name": "FloatProgressModel",
405
+ "model_module_version": "1.5.0",
406
+ "state": {
407
+ "_dom_classes": [],
408
+ "_model_module": "@jupyter-widgets/controls",
409
+ "_model_module_version": "1.5.0",
410
+ "_model_name": "FloatProgressModel",
411
+ "_view_count": null,
412
+ "_view_module": "@jupyter-widgets/controls",
413
+ "_view_module_version": "1.5.0",
414
+ "_view_name": "ProgressView",
415
+ "bar_style": "success",
416
+ "description": "",
417
+ "description_tooltip": null,
418
+ "layout": "IPY_MODEL_2158fcf3bfd543c193fa439198ce8153",
419
+ "max": 227845,
420
+ "min": 0,
421
+ "orientation": "horizontal",
422
+ "style": "IPY_MODEL_ffa1c39e07a64dff8ba37d5b6116c3a8",
423
+ "value": 227845
424
+ }
425
+ },
426
+ "e9d4ada4ded3484f88f9d41ebc9d1994": {
427
+ "model_module": "@jupyter-widgets/controls",
428
+ "model_name": "HTMLModel",
429
+ "model_module_version": "1.5.0",
430
+ "state": {
431
+ "_dom_classes": [],
432
+ "_model_module": "@jupyter-widgets/controls",
433
+ "_model_module_version": "1.5.0",
434
+ "_model_name": "HTMLModel",
435
+ "_view_count": null,
436
+ "_view_module": "@jupyter-widgets/controls",
437
+ "_view_module_version": "1.5.0",
438
+ "_view_name": "HTMLView",
439
+ "description": "",
440
+ "description_tooltip": null,
441
+ "layout": "IPY_MODEL_82e2ec198bef407db007a5ddac81c079",
442
+ "placeholder": "​",
443
+ "style": "IPY_MODEL_efd1dc15513f4227b37c471aac422104",
444
+ "value": " 228k/228k [00:00&lt;00:00, 1.27MB/s]"
445
+ }
446
+ },
447
+ "10f4d53cfc8544b7a3a43d0a766ac18c": {
448
+ "model_module": "@jupyter-widgets/base",
449
+ "model_name": "LayoutModel",
450
+ "model_module_version": "1.2.0",
451
+ "state": {
452
+ "_model_module": "@jupyter-widgets/base",
453
+ "_model_module_version": "1.2.0",
454
+ "_model_name": "LayoutModel",
455
+ "_view_count": null,
456
+ "_view_module": "@jupyter-widgets/base",
457
+ "_view_module_version": "1.2.0",
458
+ "_view_name": "LayoutView",
459
+ "align_content": null,
460
+ "align_items": null,
461
+ "align_self": null,
462
+ "border": null,
463
+ "bottom": null,
464
+ "display": null,
465
+ "flex": null,
466
+ "flex_flow": null,
467
+ "grid_area": null,
468
+ "grid_auto_columns": null,
469
+ "grid_auto_flow": null,
470
+ "grid_auto_rows": null,
471
+ "grid_column": null,
472
+ "grid_gap": null,
473
+ "grid_row": null,
474
+ "grid_template_areas": null,
475
+ "grid_template_columns": null,
476
+ "grid_template_rows": null,
477
+ "height": null,
478
+ "justify_content": null,
479
+ "justify_items": null,
480
+ "left": null,
481
+ "margin": null,
482
+ "max_height": null,
483
+ "max_width": null,
484
+ "min_height": null,
485
+ "min_width": null,
486
+ "object_fit": null,
487
+ "object_position": null,
488
+ "order": null,
489
+ "overflow": null,
490
+ "overflow_x": null,
491
+ "overflow_y": null,
492
+ "padding": null,
493
+ "right": null,
494
+ "top": null,
495
+ "visibility": null,
496
+ "width": null
497
+ }
498
+ },
499
+ "c739b23d114f422cb34b0d391f80ee12": {
500
+ "model_module": "@jupyter-widgets/base",
501
+ "model_name": "LayoutModel",
502
+ "model_module_version": "1.2.0",
503
+ "state": {
504
+ "_model_module": "@jupyter-widgets/base",
505
+ "_model_module_version": "1.2.0",
506
+ "_model_name": "LayoutModel",
507
+ "_view_count": null,
508
+ "_view_module": "@jupyter-widgets/base",
509
+ "_view_module_version": "1.2.0",
510
+ "_view_name": "LayoutView",
511
+ "align_content": null,
512
+ "align_items": null,
513
+ "align_self": null,
514
+ "border": null,
515
+ "bottom": null,
516
+ "display": null,
517
+ "flex": null,
518
+ "flex_flow": null,
519
+ "grid_area": null,
520
+ "grid_auto_columns": null,
521
+ "grid_auto_flow": null,
522
+ "grid_auto_rows": null,
523
+ "grid_column": null,
524
+ "grid_gap": null,
525
+ "grid_row": null,
526
+ "grid_template_areas": null,
527
+ "grid_template_columns": null,
528
+ "grid_template_rows": null,
529
+ "height": null,
530
+ "justify_content": null,
531
+ "justify_items": null,
532
+ "left": null,
533
+ "margin": null,
534
+ "max_height": null,
535
+ "max_width": null,
536
+ "min_height": null,
537
+ "min_width": null,
538
+ "object_fit": null,
539
+ "object_position": null,
540
+ "order": null,
541
+ "overflow": null,
542
+ "overflow_x": null,
543
+ "overflow_y": null,
544
+ "padding": null,
545
+ "right": null,
546
+ "top": null,
547
+ "visibility": null,
548
+ "width": null
549
+ }
550
+ },
551
+ "350fb7675a154f8da40406da0271ab4d": {
552
+ "model_module": "@jupyter-widgets/controls",
553
+ "model_name": "DescriptionStyleModel",
554
+ "model_module_version": "1.5.0",
555
+ "state": {
556
+ "_model_module": "@jupyter-widgets/controls",
557
+ "_model_module_version": "1.5.0",
558
+ "_model_name": "DescriptionStyleModel",
559
+ "_view_count": null,
560
+ "_view_module": "@jupyter-widgets/base",
561
+ "_view_module_version": "1.2.0",
562
+ "_view_name": "StyleView",
563
+ "description_width": ""
564
+ }
565
+ },
566
+ "2158fcf3bfd543c193fa439198ce8153": {
567
+ "model_module": "@jupyter-widgets/base",
568
+ "model_name": "LayoutModel",
569
+ "model_module_version": "1.2.0",
570
+ "state": {
571
+ "_model_module": "@jupyter-widgets/base",
572
+ "_model_module_version": "1.2.0",
573
+ "_model_name": "LayoutModel",
574
+ "_view_count": null,
575
+ "_view_module": "@jupyter-widgets/base",
576
+ "_view_module_version": "1.2.0",
577
+ "_view_name": "LayoutView",
578
+ "align_content": null,
579
+ "align_items": null,
580
+ "align_self": null,
581
+ "border": null,
582
+ "bottom": null,
583
+ "display": null,
584
+ "flex": null,
585
+ "flex_flow": null,
586
+ "grid_area": null,
587
+ "grid_auto_columns": null,
588
+ "grid_auto_flow": null,
589
+ "grid_auto_rows": null,
590
+ "grid_column": null,
591
+ "grid_gap": null,
592
+ "grid_row": null,
593
+ "grid_template_areas": null,
594
+ "grid_template_columns": null,
595
+ "grid_template_rows": null,
596
+ "height": null,
597
+ "justify_content": null,
598
+ "justify_items": null,
599
+ "left": null,
600
+ "margin": null,
601
+ "max_height": null,
602
+ "max_width": null,
603
+ "min_height": null,
604
+ "min_width": null,
605
+ "object_fit": null,
606
+ "object_position": null,
607
+ "order": null,
608
+ "overflow": null,
609
+ "overflow_x": null,
610
+ "overflow_y": null,
611
+ "padding": null,
612
+ "right": null,
613
+ "top": null,
614
+ "visibility": null,
615
+ "width": null
616
+ }
617
+ },
618
+ "ffa1c39e07a64dff8ba37d5b6116c3a8": {
619
+ "model_module": "@jupyter-widgets/controls",
620
+ "model_name": "ProgressStyleModel",
621
+ "model_module_version": "1.5.0",
622
+ "state": {
623
+ "_model_module": "@jupyter-widgets/controls",
624
+ "_model_module_version": "1.5.0",
625
+ "_model_name": "ProgressStyleModel",
626
+ "_view_count": null,
627
+ "_view_module": "@jupyter-widgets/base",
628
+ "_view_module_version": "1.2.0",
629
+ "_view_name": "StyleView",
630
+ "bar_color": null,
631
+ "description_width": ""
632
+ }
633
+ },
634
+ "82e2ec198bef407db007a5ddac81c079": {
635
+ "model_module": "@jupyter-widgets/base",
636
+ "model_name": "LayoutModel",
637
+ "model_module_version": "1.2.0",
638
+ "state": {
639
+ "_model_module": "@jupyter-widgets/base",
640
+ "_model_module_version": "1.2.0",
641
+ "_model_name": "LayoutModel",
642
+ "_view_count": null,
643
+ "_view_module": "@jupyter-widgets/base",
644
+ "_view_module_version": "1.2.0",
645
+ "_view_name": "LayoutView",
646
+ "align_content": null,
647
+ "align_items": null,
648
+ "align_self": null,
649
+ "border": null,
650
+ "bottom": null,
651
+ "display": null,
652
+ "flex": null,
653
+ "flex_flow": null,
654
+ "grid_area": null,
655
+ "grid_auto_columns": null,
656
+ "grid_auto_flow": null,
657
+ "grid_auto_rows": null,
658
+ "grid_column": null,
659
+ "grid_gap": null,
660
+ "grid_row": null,
661
+ "grid_template_areas": null,
662
+ "grid_template_columns": null,
663
+ "grid_template_rows": null,
664
+ "height": null,
665
+ "justify_content": null,
666
+ "justify_items": null,
667
+ "left": null,
668
+ "margin": null,
669
+ "max_height": null,
670
+ "max_width": null,
671
+ "min_height": null,
672
+ "min_width": null,
673
+ "object_fit": null,
674
+ "object_position": null,
675
+ "order": null,
676
+ "overflow": null,
677
+ "overflow_x": null,
678
+ "overflow_y": null,
679
+ "padding": null,
680
+ "right": null,
681
+ "top": null,
682
+ "visibility": null,
683
+ "width": null
684
+ }
685
+ },
686
+ "efd1dc15513f4227b37c471aac422104": {
687
+ "model_module": "@jupyter-widgets/controls",
688
+ "model_name": "DescriptionStyleModel",
689
+ "model_module_version": "1.5.0",
690
+ "state": {
691
+ "_model_module": "@jupyter-widgets/controls",
692
+ "_model_module_version": "1.5.0",
693
+ "_model_name": "DescriptionStyleModel",
694
+ "_view_count": null,
695
+ "_view_module": "@jupyter-widgets/base",
696
+ "_view_module_version": "1.2.0",
697
+ "_view_name": "StyleView",
698
+ "description_width": ""
699
+ }
700
+ },
701
+ "0a2021d1809a45e3ab98a356b570ce8b": {
702
+ "model_module": "@jupyter-widgets/controls",
703
+ "model_name": "HBoxModel",
704
+ "model_module_version": "1.5.0",
705
+ "state": {
706
+ "_dom_classes": [],
707
+ "_model_module": "@jupyter-widgets/controls",
708
+ "_model_module_version": "1.5.0",
709
+ "_model_name": "HBoxModel",
710
+ "_view_count": null,
711
+ "_view_module": "@jupyter-widgets/controls",
712
+ "_view_module_version": "1.5.0",
713
+ "_view_name": "HBoxView",
714
+ "box_style": "",
715
+ "children": [
716
+ "IPY_MODEL_0239813f725d41b3b24ca76e571b6802",
717
+ "IPY_MODEL_cb08c7136b364c43a839d4f0fd614f79",
718
+ "IPY_MODEL_593d3e4dd7d348ffa65358f5b5f7c895"
719
+ ],
720
+ "layout": "IPY_MODEL_43c2f54217b64c549b7ff584b2336fbc"
721
+ }
722
+ },
723
+ "0239813f725d41b3b24ca76e571b6802": {
724
+ "model_module": "@jupyter-widgets/controls",
725
+ "model_name": "HTMLModel",
726
+ "model_module_version": "1.5.0",
727
+ "state": {
728
+ "_dom_classes": [],
729
+ "_model_module": "@jupyter-widgets/controls",
730
+ "_model_module_version": "1.5.0",
731
+ "_model_name": "HTMLModel",
732
+ "_view_count": null,
733
+ "_view_module": "@jupyter-widgets/controls",
734
+ "_view_module_version": "1.5.0",
735
+ "_view_name": "HTMLView",
736
+ "description": "",
737
+ "description_tooltip": null,
738
+ "layout": "IPY_MODEL_ff027cb6473d4f86abfbc1051319ee60",
739
+ "placeholder": "​",
740
+ "style": "IPY_MODEL_ddd00dce908b4c91a64c5acd6ed00250",
741
+ "value": "pytorch_model.bin: 100%"
742
+ }
743
+ },
744
+ "cb08c7136b364c43a839d4f0fd614f79": {
745
+ "model_module": "@jupyter-widgets/controls",
746
+ "model_name": "FloatProgressModel",
747
+ "model_module_version": "1.5.0",
748
+ "state": {
749
+ "_dom_classes": [],
750
+ "_model_module": "@jupyter-widgets/controls",
751
+ "_model_module_version": "1.5.0",
752
+ "_model_name": "FloatProgressModel",
753
+ "_view_count": null,
754
+ "_view_module": "@jupyter-widgets/controls",
755
+ "_view_module_version": "1.5.0",
756
+ "_view_name": "ProgressView",
757
+ "bar_style": "success",
758
+ "description": "",
759
+ "description_tooltip": null,
760
+ "layout": "IPY_MODEL_7e46e2992ef74a2996f1169a57097f83",
761
+ "max": 442221694,
762
+ "min": 0,
763
+ "orientation": "horizontal",
764
+ "style": "IPY_MODEL_7f1fc507745b4d78a6f33da01f7b99ec",
765
+ "value": 442221694
766
+ }
767
+ },
768
+ "593d3e4dd7d348ffa65358f5b5f7c895": {
769
+ "model_module": "@jupyter-widgets/controls",
770
+ "model_name": "HTMLModel",
771
+ "model_module_version": "1.5.0",
772
+ "state": {
773
+ "_dom_classes": [],
774
+ "_model_module": "@jupyter-widgets/controls",
775
+ "_model_module_version": "1.5.0",
776
+ "_model_name": "HTMLModel",
777
+ "_view_count": null,
778
+ "_view_module": "@jupyter-widgets/controls",
779
+ "_view_module_version": "1.5.0",
780
+ "_view_name": "HTMLView",
781
+ "description": "",
782
+ "description_tooltip": null,
783
+ "layout": "IPY_MODEL_1b321bcba6af48da98e686785e5e5dfc",
784
+ "placeholder": "​",
785
+ "style": "IPY_MODEL_138b31dcc121455ea8cd0f1b04def3b1",
786
+ "value": " 442M/442M [00:05&lt;00:00, 29.9MB/s]"
787
+ }
788
+ },
789
+ "43c2f54217b64c549b7ff584b2336fbc": {
790
+ "model_module": "@jupyter-widgets/base",
791
+ "model_name": "LayoutModel",
792
+ "model_module_version": "1.2.0",
793
+ "state": {
794
+ "_model_module": "@jupyter-widgets/base",
795
+ "_model_module_version": "1.2.0",
796
+ "_model_name": "LayoutModel",
797
+ "_view_count": null,
798
+ "_view_module": "@jupyter-widgets/base",
799
+ "_view_module_version": "1.2.0",
800
+ "_view_name": "LayoutView",
801
+ "align_content": null,
802
+ "align_items": null,
803
+ "align_self": null,
804
+ "border": null,
805
+ "bottom": null,
806
+ "display": null,
807
+ "flex": null,
808
+ "flex_flow": null,
809
+ "grid_area": null,
810
+ "grid_auto_columns": null,
811
+ "grid_auto_flow": null,
812
+ "grid_auto_rows": null,
813
+ "grid_column": null,
814
+ "grid_gap": null,
815
+ "grid_row": null,
816
+ "grid_template_areas": null,
817
+ "grid_template_columns": null,
818
+ "grid_template_rows": null,
819
+ "height": null,
820
+ "justify_content": null,
821
+ "justify_items": null,
822
+ "left": null,
823
+ "margin": null,
824
+ "max_height": null,
825
+ "max_width": null,
826
+ "min_height": null,
827
+ "min_width": null,
828
+ "object_fit": null,
829
+ "object_position": null,
830
+ "order": null,
831
+ "overflow": null,
832
+ "overflow_x": null,
833
+ "overflow_y": null,
834
+ "padding": null,
835
+ "right": null,
836
+ "top": null,
837
+ "visibility": null,
838
+ "width": null
839
+ }
840
+ },
841
+ "ff027cb6473d4f86abfbc1051319ee60": {
842
+ "model_module": "@jupyter-widgets/base",
843
+ "model_name": "LayoutModel",
844
+ "model_module_version": "1.2.0",
845
+ "state": {
846
+ "_model_module": "@jupyter-widgets/base",
847
+ "_model_module_version": "1.2.0",
848
+ "_model_name": "LayoutModel",
849
+ "_view_count": null,
850
+ "_view_module": "@jupyter-widgets/base",
851
+ "_view_module_version": "1.2.0",
852
+ "_view_name": "LayoutView",
853
+ "align_content": null,
854
+ "align_items": null,
855
+ "align_self": null,
856
+ "border": null,
857
+ "bottom": null,
858
+ "display": null,
859
+ "flex": null,
860
+ "flex_flow": null,
861
+ "grid_area": null,
862
+ "grid_auto_columns": null,
863
+ "grid_auto_flow": null,
864
+ "grid_auto_rows": null,
865
+ "grid_column": null,
866
+ "grid_gap": null,
867
+ "grid_row": null,
868
+ "grid_template_areas": null,
869
+ "grid_template_columns": null,
870
+ "grid_template_rows": null,
871
+ "height": null,
872
+ "justify_content": null,
873
+ "justify_items": null,
874
+ "left": null,
875
+ "margin": null,
876
+ "max_height": null,
877
+ "max_width": null,
878
+ "min_height": null,
879
+ "min_width": null,
880
+ "object_fit": null,
881
+ "object_position": null,
882
+ "order": null,
883
+ "overflow": null,
884
+ "overflow_x": null,
885
+ "overflow_y": null,
886
+ "padding": null,
887
+ "right": null,
888
+ "top": null,
889
+ "visibility": null,
890
+ "width": null
891
+ }
892
+ },
893
+ "ddd00dce908b4c91a64c5acd6ed00250": {
894
+ "model_module": "@jupyter-widgets/controls",
895
+ "model_name": "DescriptionStyleModel",
896
+ "model_module_version": "1.5.0",
897
+ "state": {
898
+ "_model_module": "@jupyter-widgets/controls",
899
+ "_model_module_version": "1.5.0",
900
+ "_model_name": "DescriptionStyleModel",
901
+ "_view_count": null,
902
+ "_view_module": "@jupyter-widgets/base",
903
+ "_view_module_version": "1.2.0",
904
+ "_view_name": "StyleView",
905
+ "description_width": ""
906
+ }
907
+ },
908
+ "7e46e2992ef74a2996f1169a57097f83": {
909
+ "model_module": "@jupyter-widgets/base",
910
+ "model_name": "LayoutModel",
911
+ "model_module_version": "1.2.0",
912
+ "state": {
913
+ "_model_module": "@jupyter-widgets/base",
914
+ "_model_module_version": "1.2.0",
915
+ "_model_name": "LayoutModel",
916
+ "_view_count": null,
917
+ "_view_module": "@jupyter-widgets/base",
918
+ "_view_module_version": "1.2.0",
919
+ "_view_name": "LayoutView",
920
+ "align_content": null,
921
+ "align_items": null,
922
+ "align_self": null,
923
+ "border": null,
924
+ "bottom": null,
925
+ "display": null,
926
+ "flex": null,
927
+ "flex_flow": null,
928
+ "grid_area": null,
929
+ "grid_auto_columns": null,
930
+ "grid_auto_flow": null,
931
+ "grid_auto_rows": null,
932
+ "grid_column": null,
933
+ "grid_gap": null,
934
+ "grid_row": null,
935
+ "grid_template_areas": null,
936
+ "grid_template_columns": null,
937
+ "grid_template_rows": null,
938
+ "height": null,
939
+ "justify_content": null,
940
+ "justify_items": null,
941
+ "left": null,
942
+ "margin": null,
943
+ "max_height": null,
944
+ "max_width": null,
945
+ "min_height": null,
946
+ "min_width": null,
947
+ "object_fit": null,
948
+ "object_position": null,
949
+ "order": null,
950
+ "overflow": null,
951
+ "overflow_x": null,
952
+ "overflow_y": null,
953
+ "padding": null,
954
+ "right": null,
955
+ "top": null,
956
+ "visibility": null,
957
+ "width": null
958
+ }
959
+ },
960
+ "7f1fc507745b4d78a6f33da01f7b99ec": {
961
+ "model_module": "@jupyter-widgets/controls",
962
+ "model_name": "ProgressStyleModel",
963
+ "model_module_version": "1.5.0",
964
+ "state": {
965
+ "_model_module": "@jupyter-widgets/controls",
966
+ "_model_module_version": "1.5.0",
967
+ "_model_name": "ProgressStyleModel",
968
+ "_view_count": null,
969
+ "_view_module": "@jupyter-widgets/base",
970
+ "_view_module_version": "1.2.0",
971
+ "_view_name": "StyleView",
972
+ "bar_color": null,
973
+ "description_width": ""
974
+ }
975
+ },
976
+ "1b321bcba6af48da98e686785e5e5dfc": {
977
+ "model_module": "@jupyter-widgets/base",
978
+ "model_name": "LayoutModel",
979
+ "model_module_version": "1.2.0",
980
+ "state": {
981
+ "_model_module": "@jupyter-widgets/base",
982
+ "_model_module_version": "1.2.0",
983
+ "_model_name": "LayoutModel",
984
+ "_view_count": null,
985
+ "_view_module": "@jupyter-widgets/base",
986
+ "_view_module_version": "1.2.0",
987
+ "_view_name": "LayoutView",
988
+ "align_content": null,
989
+ "align_items": null,
990
+ "align_self": null,
991
+ "border": null,
992
+ "bottom": null,
993
+ "display": null,
994
+ "flex": null,
995
+ "flex_flow": null,
996
+ "grid_area": null,
997
+ "grid_auto_columns": null,
998
+ "grid_auto_flow": null,
999
+ "grid_auto_rows": null,
1000
+ "grid_column": null,
1001
+ "grid_gap": null,
1002
+ "grid_row": null,
1003
+ "grid_template_areas": null,
1004
+ "grid_template_columns": null,
1005
+ "grid_template_rows": null,
1006
+ "height": null,
1007
+ "justify_content": null,
1008
+ "justify_items": null,
1009
+ "left": null,
1010
+ "margin": null,
1011
+ "max_height": null,
1012
+ "max_width": null,
1013
+ "min_height": null,
1014
+ "min_width": null,
1015
+ "object_fit": null,
1016
+ "object_position": null,
1017
+ "order": null,
1018
+ "overflow": null,
1019
+ "overflow_x": null,
1020
+ "overflow_y": null,
1021
+ "padding": null,
1022
+ "right": null,
1023
+ "top": null,
1024
+ "visibility": null,
1025
+ "width": null
1026
+ }
1027
+ },
1028
+ "138b31dcc121455ea8cd0f1b04def3b1": {
1029
+ "model_module": "@jupyter-widgets/controls",
1030
+ "model_name": "DescriptionStyleModel",
1031
+ "model_module_version": "1.5.0",
1032
+ "state": {
1033
+ "_model_module": "@jupyter-widgets/controls",
1034
+ "_model_module_version": "1.5.0",
1035
+ "_model_name": "DescriptionStyleModel",
1036
+ "_view_count": null,
1037
+ "_view_module": "@jupyter-widgets/base",
1038
+ "_view_module_version": "1.2.0",
1039
+ "_view_name": "StyleView",
1040
+ "description_width": ""
1041
+ }
1042
+ }
1043
+ }
1044
+ }
1045
+ },
1046
+ "cells": [
1047
+ {
1048
+ "cell_type": "code",
1049
+ "execution_count": 1,
1050
+ "metadata": {
1051
+ "id": "Nku0ikZgEJ9L"
1052
+ },
1053
+ "outputs": [],
1054
+ "source": [
1055
+ "dataset = [\n",
1056
+ " \"Deep learning approaches have dramatically improved the performance of automatic speech recognition systems.\",\n",
1057
+ " \"Natural language processing tasks have benefited greatly from pre-trained language models like BERT.\",\n",
1058
+ " \"Machine learning techniques have been applied to various problems in bioinformatics, including gene prediction.\",\n",
1059
+ " \"Recent advancements in reinforcement learning have opened new avenues in artificial intelligence research.\",\n",
1060
+ " \"Quantum computing is a rapidly growing field with potential applications in cryptography and material science.\"\n",
1061
+ "]"
1062
+ ]
1063
+ },
1064
+ {
1065
+ "cell_type": "code",
1066
+ "source": [
1067
+ "import torch\n",
1068
+ "from transformers import AutoModel, AutoTokenizer\n",
1069
+ "from sklearn.metrics.pairwise import cosine_similarity\n",
1070
+ "import numpy as np"
1071
+ ],
1072
+ "metadata": {
1073
+ "id": "4hNYliISEui3"
1074
+ },
1075
+ "execution_count": 2,
1076
+ "outputs": []
1077
+ },
1078
+ {
1079
+ "cell_type": "code",
1080
+ "source": [
1081
+ "# Load SciBERT model and tokenizer\n",
1082
+ "model_name = \"allenai/scibert_scivocab_uncased\"\n",
1083
+ "tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
1084
+ "model = AutoModel.from_pretrained(model_name)"
1085
+ ],
1086
+ "metadata": {
1087
+ "colab": {
1088
+ "base_uri": "https://localhost:8080/",
1089
+ "height": 242,
1090
+ "referenced_widgets": [
1091
+ "885937018a634de0a6deb830bb194716",
1092
+ "2483b50c7f9342faa91062f6dac2f2a8",
1093
+ "64a96102ed7b4ab0b59b0b1d97add383",
1094
+ "986a7cf0b85b4cc7803a03b4373edcaf",
1095
+ "d1b7ccd4754744509c3e45db8d651e5d",
1096
+ "0c1c8ec0ed6445b48f3f8787ac66ffe2",
1097
+ "117698ddf34d4592ad0309fa403f6122",
1098
+ "16774c5f05ca45d790eb770a2f1d2ef3",
1099
+ "1a2e33ca554e4e1c9daee3c9d9568604",
1100
+ "6aad8d81d1964d31babe734f809aca79",
1101
+ "a5f0667376174a3fad64da397a3dd92f",
1102
+ "b4309550192c49019293c1d1ce0f97d4",
1103
+ "79868f65f0ad4ffc8384e8de8f79bf0c",
1104
+ "50959c940ac44e23b6fc8db4d0021bc0",
1105
+ "e9d4ada4ded3484f88f9d41ebc9d1994",
1106
+ "10f4d53cfc8544b7a3a43d0a766ac18c",
1107
+ "c739b23d114f422cb34b0d391f80ee12",
1108
+ "350fb7675a154f8da40406da0271ab4d",
1109
+ "2158fcf3bfd543c193fa439198ce8153",
1110
+ "ffa1c39e07a64dff8ba37d5b6116c3a8",
1111
+ "82e2ec198bef407db007a5ddac81c079",
1112
+ "efd1dc15513f4227b37c471aac422104",
1113
+ "0a2021d1809a45e3ab98a356b570ce8b",
1114
+ "0239813f725d41b3b24ca76e571b6802",
1115
+ "cb08c7136b364c43a839d4f0fd614f79",
1116
+ "593d3e4dd7d348ffa65358f5b5f7c895",
1117
+ "43c2f54217b64c549b7ff584b2336fbc",
1118
+ "ff027cb6473d4f86abfbc1051319ee60",
1119
+ "ddd00dce908b4c91a64c5acd6ed00250",
1120
+ "7e46e2992ef74a2996f1169a57097f83",
1121
+ "7f1fc507745b4d78a6f33da01f7b99ec",
1122
+ "1b321bcba6af48da98e686785e5e5dfc",
1123
+ "138b31dcc121455ea8cd0f1b04def3b1"
1124
+ ]
1125
+ },
1126
+ "id": "4Hn7dNP7EwbH",
1127
+ "outputId": "a1ed65e2-6c34-4a6f-ad39-06d2685c5768"
1128
+ },
1129
+ "execution_count": 3,
1130
+ "outputs": [
1131
+ {
1132
+ "output_type": "stream",
1133
+ "name": "stderr",
1134
+ "text": [
1135
+ "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: UserWarning: \n",
1136
+ "The secret `HF_TOKEN` does not exist in your Colab secrets.\n",
1137
+ "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n",
1138
+ "You will be able to reuse this secret in all of your notebooks.\n",
1139
+ "Please note that authentication is recommended but still optional to access public models or datasets.\n",
1140
+ " warnings.warn(\n"
1141
+ ]
1142
+ },
1143
+ {
1144
+ "output_type": "display_data",
1145
+ "data": {
1146
+ "text/plain": [
1147
+ "config.json: 0%| | 0.00/385 [00:00<?, ?B/s]"
1148
+ ],
1149
+ "application/vnd.jupyter.widget-view+json": {
1150
+ "version_major": 2,
1151
+ "version_minor": 0,
1152
+ "model_id": "885937018a634de0a6deb830bb194716"
1153
+ }
1154
+ },
1155
+ "metadata": {}
1156
+ },
1157
+ {
1158
+ "output_type": "display_data",
1159
+ "data": {
1160
+ "text/plain": [
1161
+ "vocab.txt: 0%| | 0.00/228k [00:00<?, ?B/s]"
1162
+ ],
1163
+ "application/vnd.jupyter.widget-view+json": {
1164
+ "version_major": 2,
1165
+ "version_minor": 0,
1166
+ "model_id": "b4309550192c49019293c1d1ce0f97d4"
1167
+ }
1168
+ },
1169
+ "metadata": {}
1170
+ },
1171
+ {
1172
+ "output_type": "display_data",
1173
+ "data": {
1174
+ "text/plain": [
1175
+ "pytorch_model.bin: 0%| | 0.00/442M [00:00<?, ?B/s]"
1176
+ ],
1177
+ "application/vnd.jupyter.widget-view+json": {
1178
+ "version_major": 2,
1179
+ "version_minor": 0,
1180
+ "model_id": "0a2021d1809a45e3ab98a356b570ce8b"
1181
+ }
1182
+ },
1183
+ "metadata": {}
1184
+ }
1185
+ ]
1186
+ },
1187
+ {
1188
+ "cell_type": "code",
1189
+ "source": [
1190
+ "# Function to get embeddings for a list of texts\n",
1191
+ "def get_embeddings(text_list):\n",
1192
+ " embeddings = []\n",
1193
+ " for text in text_list:\n",
1194
+ " inputs = tokenizer(text, return_tensors=\"pt\", truncation=True, padding=True)\n",
1195
+ " with torch.no_grad():\n",
1196
+ " outputs = model(**inputs)\n",
1197
+ " embedding = outputs.last_hidden_state.mean(dim=1).squeeze().numpy()\n",
1198
+ " embeddings.append(embedding)\n",
1199
+ " return np.array(embeddings)\n",
1200
+ "\n",
1201
+ "# Function to recommend items based on an index\n",
1202
+ "def recommend(item_index, similarity_matrix, top_n=3):\n",
1203
+ " similarity_scores = list(enumerate(similarity_matrix[item_index]))\n",
1204
+ " similarity_scores = sorted(similarity_scores, key=lambda x: x[1], reverse=True)\n",
1205
+ " recommended_indices = [i[0] for i in similarity_scores[1:top_n+1]]\n",
1206
+ " return recommended_indices"
1207
+ ],
1208
+ "metadata": {
1209
+ "id": "zGS9ubQ9Ezhe"
1210
+ },
1211
+ "execution_count": 4,
1212
+ "outputs": []
1213
+ },
1214
+ {
1215
+ "cell_type": "code",
1216
+ "source": [
1217
+ "# Get embeddings for the dataset\n",
1218
+ "embedding_matrix = get_embeddings(dataset)\n",
1219
+ "\n",
1220
+ "# Calculate similarity matrix\n",
1221
+ "similarity_matrix = cosine_similarity(embedding_matrix)"
1222
+ ],
1223
+ "metadata": {
1224
+ "colab": {
1225
+ "base_uri": "https://localhost:8080/"
1226
+ },
1227
+ "id": "sJQYM4ILE9J9",
1228
+ "outputId": "68d29ef8-b729-487b-e388-12e245dc6adf"
1229
+ },
1230
+ "execution_count": 5,
1231
+ "outputs": [
1232
+ {
1233
+ "output_type": "stream",
1234
+ "name": "stderr",
1235
+ "text": [
1236
+ "Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.\n"
1237
+ ]
1238
+ }
1239
+ ]
1240
+ },
1241
+ {
1242
+ "cell_type": "code",
1243
+ "source": [
1244
+ "# Example: Recommend similar papers to the first paper in the dataset\n",
1245
+ "item_index = 0 # Index of the item to base recommendations on\n",
1246
+ "recommended_indices = recommend(item_index, similarity_matrix)\n",
1247
+ "\n",
1248
+ "print(f\"Original Paper: {dataset[item_index]}\")\n",
1249
+ "print(\"\\nRecommended Papers:\")\n",
1250
+ "for idx in recommended_indices:\n",
1251
+ " print(f\"- {dataset[idx]}\")"
1252
+ ],
1253
+ "metadata": {
1254
+ "colab": {
1255
+ "base_uri": "https://localhost:8080/"
1256
+ },
1257
+ "id": "Uxr2ifEbE_LH",
1258
+ "outputId": "342c7f2d-337d-451a-e111-377802699623"
1259
+ },
1260
+ "execution_count": 6,
1261
+ "outputs": [
1262
+ {
1263
+ "output_type": "stream",
1264
+ "name": "stdout",
1265
+ "text": [
1266
+ "Original Paper: Deep learning approaches have dramatically improved the performance of automatic speech recognition systems.\n",
1267
+ "\n",
1268
+ "Recommended Papers:\n",
1269
+ "- Natural language processing tasks have benefited greatly from pre-trained language models like BERT.\n",
1270
+ "- Machine learning techniques have been applied to various problems in bioinformatics, including gene prediction.\n",
1271
+ "- Recent advancements in reinforcement learning have opened new avenues in artificial intelligence research.\n"
1272
+ ]
1273
+ }
1274
+ ]
1275
+ }
1276
+ ]
1277
+ }