From 2159da677eaa5950f3a2b036393fc0c0147d38b1 Mon Sep 17 00:00:00 2001
From: Shivendra Singh <94288086+shivendrra@users.noreply.github.com>
Date: Thu, 28 Mar 2024 16:33:17 +0530
Subject: [PATCH 1/2] 500million model training

---
 base/AIVA_500m.ipynb | 282 +++++++++++++++++++++++++++++++------------
 1 file changed, 203 insertions(+), 79 deletions(-)

diff --git a/base/AIVA_500m.ipynb b/base/AIVA_500m.ipynb
index bad4cb5..f0e9704 100644
--- a/base/AIVA_500m.ipynb
+++ b/base/AIVA_500m.ipynb
@@ -6,7 +6,7 @@
       "provenance": [],
       "machine_shape": "hm",
       "gpuType": "T4",
-      "authorship_tag": "ABX9TyOeYX5zp+reGmNxsWXca/e6",
+      "authorship_tag": "ABX9TyOKRNYqoTheFEeCtRMCsj24",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -37,14 +37,14 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "7986e6e4-75e4-4f10-e868-dfbda7a0d3e7"
+        "outputId": "3c6bd684-4cfd-4429-8f9b-8cfe48292ab2"
       },
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "Mounted at /content/drive\n"
+            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
           ]
         }
       ],
@@ -63,7 +63,7 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "f3204533-15b0-4b94-df77-93925fa224b1"
+        "outputId": "8486c391-3e34-48f7-d608-f72855183b40"
       },
       "execution_count": 2,
       "outputs": [
@@ -71,17 +71,13 @@
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "Collecting tiktoken\n",
-            "  Downloading tiktoken-0.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.8 MB)\n",
-            "\u001b[?25l     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/1.8 MB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K     \u001b[91m━━━━━━\u001b[0m\u001b[91m╸\u001b[0m\u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.3/1.8 MB\u001b[0m \u001b[31m9.6 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K     \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[90m╺\u001b[0m\u001b[90m━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.8 MB\u001b[0m \u001b[31m16.0 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K     \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m20.2 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m17.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.10/dist-packages (from tiktoken) (2023.12.25)\n",
+            "Requirement already satisfied: tiktoken in /usr/local/lib/python3.10/dist-packages (0.6.0)\n",
+            "Requirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.10/dist-packages (from tiktoken) (2023.12.25)\n",
             "Requirement already satisfied: requests>=2.26.0 in /usr/local/lib/python3.10/dist-packages (from tiktoken) (2.31.0)\n",
             "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken) (3.3.2)\n",
             "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken) (3.6)\n",
             "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken) (2.0.7)\n",
-            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken) (2024.2.2)\n",
-            "Installing collected packages: tiktoken\n",
-            "Successfully installed tiktoken-0.6.0\n"
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken) (2024.2.2)\n"
           ]
         }
       ]
@@ -90,17 +86,17 @@
       "cell_type": "code",
       "source": [
         "# data for model\n",
-        "with open('/content/drive/MyDrive/training data/consolidated_350m.txt', 'r', encoding='utf-8') as file:\n",
+        "with open('/content/drive/MyDrive/training data/consolidated_300m.txt', 'r', encoding='utf-8') as file:\n",
         "  train_data = file.read()\n",
         "\n",
-        "print(len(train_data)/1e6, 'million words')"
+        "print(f\"{(len(train_data)/1e9):.2f} billion words\")"
       ],
       "metadata": {
         "id": "BSh3yuTGfu21",
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "86e17e89-11a4-45cf-bfab-6f68002ef9bc"
+        "outputId": "d25005b5-2a18-41df-eea3-569d3948dbd7"
       },
       "execution_count": 3,
       "outputs": [
@@ -108,7 +104,7 @@
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "2274.16219 million words\n"
+            "1.98 billion words\n"
           ]
         }
       ]
@@ -121,8 +117,7 @@
         "tokenizer = tiktoken.encoding_for_model(\"text-davinci-003\")\n",
         "\n",
         "input_data = tokenizer.encode(train_data)\n",
-        "\n",
-        "print(\"total tokens\", len(input_data)/1e6, 'million')\n",
+        "print(f\"total tokens: {(len(input_data)/1e6):.0f} million\")\n",
         "\n",
         "n = int(0.9*len(input_data)) # first 90% will be train, rest val\n",
         "train_data = input_data[:n]\n",
@@ -131,10 +126,22 @@
         "del input_data, n"
       ],
       "metadata": {
-        "id": "VmBZRVhqfyn2"
+        "id": "VmBZRVhqfyn2",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "1cc10125-583f-4d17-d9f3-62af9b4a9712"
       },
-      "execution_count": null,
-      "outputs": []
+      "execution_count": 4,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "total tokens: 400 million\n"
+          ]
+        }
+      ]
     },
     {
       "cell_type": "code",
@@ -153,34 +160,18 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "9aaaea88-25d5-4a97-ace1-7c817fca7270"
+        "outputId": "d24fc1e5-669f-46dc-d9de-9c415bbbebc0"
       },
-      "execution_count": 9,
+      "execution_count": 5,
       "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "<ipython-input-9-045391eab4ca>:4: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).\n",
-            "  train_data = torch.tensor(train_data, dtype=torch.long)\n"
-          ]
-        },
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "train data 588 million\n",
-            "validation data 65 million\n",
-            "train data = tensor([ 3886,    25,  7443,    13,   785, 48073, 19433,    25,  2932,   860]), \n",
-            "val data = tensor([ 7579,  2885, 17941,  1847,  7446,  8696,  2389, 18310,    13,  3336])\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "<ipython-input-9-045391eab4ca>:5: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).\n",
-            "  val_data = torch.tensor(val_data, dtype=torch.long)\n"
+            "train data 360 million\n",
+            "validation data 40 million\n",
+            "train data = tensor([ 5239,   197, 16963,   457,   197,  5239,    62, 30001,    62, 13664]), \n",
+            "val data = tensor([  13,  198, 1532,  345,  561,  588,  285,    1, 1911,  198])\n"
           ]
         }
       ]
@@ -191,21 +182,21 @@
         "# hyperparameters\n",
         "batch_size = 10\n",
         "block_size = 256\n",
-        "max_iters = 1000\n",
+        "max_iters = 5000\n",
         "eval_interval = 100\n",
         "learning_rate = 3e-5\n",
         "device = 'cuda' if torch.cuda.is_available() else 'cpu'\n",
-        "eval_iters = 10\n",
+        "eval_iters = 100\n",
         "d_model = 512\n",
-        "n_head = 20\n",
-        "n_layers = 18\n",
+        "n_head = 18\n",
+        "n_layers = 12\n",
         "dropout = 0.2\n",
         "norm_eps = 1e-05"
       ],
       "metadata": {
         "id": "tJuCsc1QPdts"
       },
-      "execution_count": 10,
+      "execution_count": 6,
       "outputs": []
     },
     {
@@ -258,7 +249,7 @@
         "    super().__init__()\n",
         "    self.key = nn.Linear(d_model, head_size, bias=True)\n",
         "    self.query = nn.Linear(d_model, head_size, bias=True)\n",
-        "    self.value = nn.Linear(d_model, head_size, bias=True)\n",
+        "    self.value = nn.Linear(d_model, head_size, bias=False)\n",
         "    self.dropout = nn.Dropout(dropout)\n",
         "    self.rel_pos_embd = nn.Parameter(torch.randn(block_size, block_size, head_size))\n",
         "\n",
@@ -329,8 +320,8 @@
         "class FinalHead(nn.Module):\n",
         "  def __init__(self, d_model, head_size, dropout, block_size):\n",
         "    super().__init__()\n",
-        "    self.key = nn.Linear(d_model, head_size, bias=True)\n",
-        "    self.query = nn.Linear(d_model, head_size, bias=True)\n",
+        "    self.key = nn.Linear(d_model, head_size, bias=False)\n",
+        "    self.query = nn.Linear(d_model, head_size, bias=False)\n",
         "    self.value = nn.Linear(d_model, head_size, bias=True)\n",
         "    self.dropout = nn.Dropout(dropout)\n",
         "\n",
@@ -364,9 +355,9 @@
         "  def __init__(self, d_model, dropout):\n",
         "    super().__init__()\n",
         "    self.net = nn.Sequential(\n",
-        "      nn.Linear(d_model, 10*d_model),\n",
+        "      nn.Linear(d_model, 4*d_model),\n",
         "      nn.GELU(),\n",
-        "      nn.Linear(10*d_model, d_model),\n",
+        "      nn.Linear(4*d_model, d_model),\n",
         "      nn.Dropout(dropout)\n",
         "    )\n",
         "\n",
@@ -570,7 +561,7 @@
       "metadata": {
         "id": "OusOJ_H8gARB"
       },
-      "execution_count": 11,
+      "execution_count": 7,
       "outputs": []
     },
     {
@@ -589,7 +580,6 @@
         "  and can become ~99% accurate with next token prediction\n",
         "\"\"\"\n",
         "\n",
-        "torch.manual_seed(1400)\n",
         "# data loading\n",
         "def get_batch(split):\n",
         "    # generate a small batch of data of inputs x and targets y\n",
@@ -616,6 +606,9 @@
         "\n",
         "vocab_size = tokenizer.n_vocab\n",
         "model = Transformer(vocab_size)\n",
+        "# checkpoint_path = '/content/drive/MyDrive/aiva_base-886m.pth'\n",
+        "# checkpoint = torch.load(checkpoint_path)\n",
+        "# model.load_state_dict(checkpoint)\n",
         "m = model.to(device)\n",
         "\n",
         "# no of parameters\n",
@@ -646,30 +639,59 @@
       ],
       "metadata": {
         "colab": {
-          "base_uri": "https://localhost:8080/"
+          "base_uri": "https://localhost:8080/",
+          "height": 932
         },
         "id": "dORKqYKmPmit",
-        "outputId": "62d9926c-a50f-427b-abcf-bb71ec82348e"
+        "outputId": "a1c1f52c-a3f6-4db6-f2e5-0d378ad66505"
       },
-      "execution_count": 12,
+      "execution_count": 8,
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
             "vocab size: 50281\n",
-            "886 million parameters\n",
-            "step 0: train loss 10.9287, val loss 10.9229\n",
-            "step 100: train loss 8.3812, val loss 9.0325\n",
-            "step 200: train loss 7.2081, val loss 8.0959\n",
-            "step 300: train loss 6.7217, val loss 7.8882\n",
-            "step 400: train loss 6.5446, val loss 7.8266\n",
-            "step 500: train loss 6.8072, val loss 7.8396\n",
-            "step 600: train loss 6.4265, val loss 7.6559\n",
-            "step 700: train loss 6.3871, val loss 7.7765\n",
-            "step 800: train loss 6.4383, val loss 7.5266\n",
-            "step 900: train loss 6.2296, val loss 7.3788\n",
-            "step 999: train loss 6.3129, val loss 7.3048\n"
+            "536 million parameters\n",
+            "step 0: train loss 10.9446, val loss 10.9414\n",
+            "step 100: train loss 8.6948, val loss 8.7504\n",
+            "step 200: train loss 7.8092, val loss 7.9258\n",
+            "step 300: train loss 7.6445, val loss 7.7898\n",
+            "step 400: train loss 7.6184, val loss 7.7647\n",
+            "step 500: train loss 7.5690, val loss 7.7763\n",
+            "step 600: train loss 7.5422, val loss 7.7430\n",
+            "step 700: train loss 7.5362, val loss 7.7559\n",
+            "step 800: train loss 7.4778, val loss 7.7400\n",
+            "step 900: train loss 7.4192, val loss 7.6667\n",
+            "step 1000: train loss 7.3854, val loss 7.6163\n",
+            "step 1100: train loss 7.3321, val loss 7.5843\n",
+            "step 1200: train loss 7.2594, val loss 7.5148\n",
+            "step 1300: train loss 7.2283, val loss 7.4860\n",
+            "step 1400: train loss 7.1611, val loss 7.4022\n",
+            "step 1500: train loss 7.0903, val loss 7.3789\n",
+            "step 1600: train loss 7.0679, val loss 7.3126\n",
+            "step 1700: train loss 6.9863, val loss 7.2131\n",
+            "step 1800: train loss 6.9202, val loss 7.1764\n",
+            "step 1900: train loss 6.9034, val loss 7.1758\n",
+            "step 2000: train loss 6.8178, val loss 7.1035\n",
+            "step 2100: train loss 6.7434, val loss 7.0638\n",
+            "step 2200: train loss 6.7087, val loss 7.0001\n",
+            "step 2300: train loss 6.6774, val loss 7.0209\n",
+            "step 2400: train loss 6.6049, val loss 6.8982\n",
+            "step 2500: train loss 6.5634, val loss 6.9102\n"
+          ]
+        },
+        {
+          "output_type": "error",
+          "ename": "KeyboardInterrupt",
+          "evalue": "",
+          "traceback": [
+            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+            "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+            "\u001b[0;32m<ipython-input-8-48f74470a47d>\u001b[0m in \u001b[0;36m<cell line: 55>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     66\u001b[0m   \u001b[0mlogits\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mloss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mxb\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0myb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     67\u001b[0m   \u001b[0moptimizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mzero_grad\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mset_to_none\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 68\u001b[0;31m   \u001b[0mloss\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     69\u001b[0m   \u001b[0moptimizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/_tensor.py\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(self, gradient, retain_graph, create_graph, inputs)\u001b[0m\n\u001b[1;32m    520\u001b[0m                 \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    521\u001b[0m             )\n\u001b[0;32m--> 522\u001b[0;31m         torch.autograd.backward(\n\u001b[0m\u001b[1;32m    523\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgradient\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mretain_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcreate_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    524\u001b[0m         )\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/autograd/__init__.py\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)\u001b[0m\n\u001b[1;32m    264\u001b[0m     \u001b[0;31m# some Python versions print out the first line of a multi-line function\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    265\u001b[0m     \u001b[0;31m# calls in the traceback and some print out the last line\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 266\u001b[0;31m     Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass\n\u001b[0m\u001b[1;32m    267\u001b[0m         \u001b[0mtensors\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    268\u001b[0m         \u001b[0mgrad_tensors_\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
           ]
         }
       ]
@@ -677,14 +699,14 @@
     {
       "cell_type": "code",
       "source": [
-        "model_save_name = f'aiva_base-{n_param:.0f}m.pth'\n",
+        "model_save_name = f'base-500m.pth'\n",
         "path = f\"/content/drive/MyDrive/{model_save_name}\"\n",
         "torch.save(model.state_dict(), path)"
       ],
       "metadata": {
         "id": "e6NM24zMhH_2"
       },
-      "execution_count": 15,
+      "execution_count": 9,
       "outputs": []
     },
     {
@@ -692,7 +714,7 @@
       "source": [
         "import matplotlib.pyplot as plt\n",
         "\n",
-        "plt.figure(figsize=(10, 6))\n",
+        "plt.figure(figsize=(12, 6))\n",
         "plt.plot(steps, train_losses, label='Train Loss')\n",
         "plt.plot(steps, val_losses, label='Validation Loss')\n",
         "plt.title('Loss Over Steps')\n",
@@ -708,7 +730,7 @@
           "base_uri": "https://localhost:8080/",
           "height": 564
         },
-        "outputId": "d2bd4dcf-f197-447b-8f19-48aaa3f3c0d2"
+        "outputId": "a6487980-796b-45ef-f7c1-f8e92504a4b2"
       },
       "execution_count": 17,
       "outputs": [
@@ -716,9 +738,9 @@
           "output_type": "display_data",
           "data": {
             "text/plain": [
-              "<Figure size 1000x600 with 1 Axes>"
+              "<Figure size 1200x600 with 1 Axes>"
             ],
-            "image/png": "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\n"
+            "image/png": "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\n"
           },
           "metadata": {}
         }
@@ -738,15 +760,67 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "1be93194-d8fe-4a1e-ac84-06384242c10f"
+        "outputId": "f5e29c2f-61f2-472c-cdfb-8a5f2e5cafb3"
+      },
+      "execution_count": 18,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Would you like to tell me your name because   and revealed them an agon. This SOL with the\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# 8-bit quantization\n",
+        "\n",
+        "import torch\n",
+        "import torch.quantization\n",
+        "\n",
+        "# model = Transformer(vocab_size=9)\n",
+        "# checkpoint_path = '/content/drive/MyDrive/enigma-2.5b.pth'\n",
+        "# checkpoint = torch.load(checkpoint_path)\n",
+        "# model.load_state_dict(checkpoint)\n",
+        "# model = model.to(device)\n",
+        "\n",
+        "quantized_model = torch.quantization.quantize_dynamic(\n",
+        "  model,\n",
+        "  dtype=torch.qint8\n",
+        ")"
+      ],
+      "metadata": {
+        "id": "YsqYoGaxPFYd"
+      },
+      "execution_count": 19,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "model_save_name = f'base-8bit.pth'\n",
+        "path = f\"/content/drive/MyDrive/{model_save_name}\"\n",
+        "torch.save(quantized_model.state_dict(), path)\n",
+        "\n",
+        "print(\"Quantized model saved successfully.\")"
+      ],
+      "metadata": {
+        "id": "tqz4Rb2mPNKX",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "adc3ce05-6584-4992-8d9f-38ceb48a5cb9"
       },
-      "execution_count": 23,
+      "execution_count": 22,
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "Would you like to tell me your name because   the full comic throw in so said disinfect mess V\n"
+            "Quantized model saved successfully.\n"
           ]
         }
       ]
@@ -759,7 +833,57 @@
       "metadata": {
         "id": "v8y1w-wVYCts"
       },
-      "execution_count": 30,
+      "execution_count": 16,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!nvidia-smi"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "vhOJz2WyPLLb",
+        "outputId": "060d278f-de4b-424a-c1cd-d17ec75116a6"
+      },
+      "execution_count": 21,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Thu Mar 28 11:01:55 2024       \n",
+            "+---------------------------------------------------------------------------------------+\n",
+            "| NVIDIA-SMI 535.104.05             Driver Version: 535.104.05   CUDA Version: 12.2     |\n",
+            "|-----------------------------------------+----------------------+----------------------+\n",
+            "| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
+            "| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |\n",
+            "|                                         |                      |               MIG M. |\n",
+            "|=========================================+======================+======================|\n",
+            "|   0  Tesla T4                       Off | 00000000:00:04.0 Off |                    0 |\n",
+            "| N/A   72C    P0              31W /  70W |   6969MiB / 15360MiB |      0%      Default |\n",
+            "|                                         |                      |                  N/A |\n",
+            "+-----------------------------------------+----------------------+----------------------+\n",
+            "                                                                                         \n",
+            "+---------------------------------------------------------------------------------------+\n",
+            "| Processes:                                                                            |\n",
+            "|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |\n",
+            "|        ID   ID                                                             Usage      |\n",
+            "|=======================================================================================|\n",
+            "+---------------------------------------------------------------------------------------+\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "6c-tPdQpuTdM"
+      },
+      "execution_count": null,
       "outputs": []
     }
   ]

From 6beab5aee91504f500f433278a640ecf2272408b Mon Sep 17 00:00:00 2001
From: Shivendra Singh <94288086+shivendrra@users.noreply.github.com>
Date: Fri, 29 Mar 2024 01:23:27 +0530
Subject: [PATCH 2/2] continuing training

---
 base/AIVA_500m.ipynb | 175 ++++++++++++++++++++++---------------------
 1 file changed, 91 insertions(+), 84 deletions(-)

diff --git a/base/AIVA_500m.ipynb b/base/AIVA_500m.ipynb
index f0e9704..14a9666 100644
--- a/base/AIVA_500m.ipynb
+++ b/base/AIVA_500m.ipynb
@@ -6,7 +6,7 @@
       "provenance": [],
       "machine_shape": "hm",
       "gpuType": "T4",
-      "authorship_tag": "ABX9TyOKRNYqoTheFEeCtRMCsj24",
+      "authorship_tag": "ABX9TyOSmZVNAuJ4s9862r68suiH",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -37,14 +37,14 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "3c6bd684-4cfd-4429-8f9b-8cfe48292ab2"
+        "outputId": "fcf336a5-e07e-4ee7-b9e5-35920d5e38ac"
       },
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
+            "Mounted at /content/drive\n"
           ]
         }
       ],
@@ -63,7 +63,7 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "8486c391-3e34-48f7-d608-f72855183b40"
+        "outputId": "72fa4c3c-2f99-4870-d0fc-d32eb37b0e6f"
       },
       "execution_count": 2,
       "outputs": [
@@ -71,13 +71,17 @@
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "Requirement already satisfied: tiktoken in /usr/local/lib/python3.10/dist-packages (0.6.0)\n",
-            "Requirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.10/dist-packages (from tiktoken) (2023.12.25)\n",
+            "Collecting tiktoken\n",
+            "  Downloading tiktoken-0.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.8 MB)\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m11.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25hRequirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.10/dist-packages (from tiktoken) (2023.12.25)\n",
             "Requirement already satisfied: requests>=2.26.0 in /usr/local/lib/python3.10/dist-packages (from tiktoken) (2.31.0)\n",
             "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken) (3.3.2)\n",
             "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken) (3.6)\n",
             "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken) (2.0.7)\n",
-            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken) (2024.2.2)\n"
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken) (2024.2.2)\n",
+            "Installing collected packages: tiktoken\n",
+            "Successfully installed tiktoken-0.6.0\n"
           ]
         }
       ]
@@ -96,7 +100,7 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "d25005b5-2a18-41df-eea3-569d3948dbd7"
+        "outputId": "08745a76-8b4f-46eb-c71d-1ba558dc2657"
       },
       "execution_count": 3,
       "outputs": [
@@ -130,7 +134,7 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "1cc10125-583f-4d17-d9f3-62af9b4a9712"
+        "outputId": "6650f4ad-8815-4172-c6ba-92dbf0cfa85e"
       },
       "execution_count": 4,
       "outputs": [
@@ -160,7 +164,7 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "d24fc1e5-669f-46dc-d9de-9c415bbbebc0"
+        "outputId": "9cfcaad4-2baa-423b-d4b4-332676bba442"
       },
       "execution_count": 5,
       "outputs": [
@@ -176,17 +180,43 @@
         }
       ]
     },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(f\"train data = {tokenizer.decode(train_data[:10].tolist())}, \\nval data = {tokenizer.decode(val_data[:10].tolist())}\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "AHT8PAnQMP-Z",
+        "outputId": "aa3be956-f874-486c-cd8e-6e7d8fd48e89"
+      },
+      "execution_count": 6,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "train data = text\tprompt\ttext_token_length, \n",
+            "val data = .\n",
+            "If you would like m\"\".\n",
+            "\n"
+          ]
+        }
+      ]
+    },
     {
       "cell_type": "code",
       "source": [
         "# hyperparameters\n",
         "batch_size = 10\n",
         "block_size = 256\n",
-        "max_iters = 5000\n",
+        "max_iters = 2500\n",
         "eval_interval = 100\n",
         "learning_rate = 3e-5\n",
         "device = 'cuda' if torch.cuda.is_available() else 'cpu'\n",
-        "eval_iters = 100\n",
+        "eval_iters = 250\n",
         "d_model = 512\n",
         "n_head = 18\n",
         "n_layers = 12\n",
@@ -196,7 +226,7 @@
       "metadata": {
         "id": "tJuCsc1QPdts"
       },
-      "execution_count": 6,
+      "execution_count": 7,
       "outputs": []
     },
     {
@@ -561,7 +591,7 @@
       "metadata": {
         "id": "OusOJ_H8gARB"
       },
-      "execution_count": 7,
+      "execution_count": 8,
       "outputs": []
     },
     {
@@ -606,9 +636,9 @@
         "\n",
         "vocab_size = tokenizer.n_vocab\n",
         "model = Transformer(vocab_size)\n",
-        "# checkpoint_path = '/content/drive/MyDrive/aiva_base-886m.pth'\n",
-        "# checkpoint = torch.load(checkpoint_path)\n",
-        "# model.load_state_dict(checkpoint)\n",
+        "checkpoint_path = '/content/drive/MyDrive/base-500m.pth'\n",
+        "checkpoint = torch.load(checkpoint_path)\n",
+        "model.load_state_dict(checkpoint)\n",
         "m = model.to(device)\n",
         "\n",
         "# no of parameters\n",
@@ -639,13 +669,12 @@
       ],
       "metadata": {
         "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 932
+          "base_uri": "https://localhost:8080/"
         },
         "id": "dORKqYKmPmit",
-        "outputId": "a1c1f52c-a3f6-4db6-f2e5-0d378ad66505"
+        "outputId": "fa3b98aa-1839-4e97-a3f9-faf6bb936522"
       },
-      "execution_count": 8,
+      "execution_count": 9,
       "outputs": [
         {
           "output_type": "stream",
@@ -653,45 +682,32 @@
           "text": [
             "vocab size: 50281\n",
             "536 million parameters\n",
-            "step 0: train loss 10.9446, val loss 10.9414\n",
-            "step 100: train loss 8.6948, val loss 8.7504\n",
-            "step 200: train loss 7.8092, val loss 7.9258\n",
-            "step 300: train loss 7.6445, val loss 7.7898\n",
-            "step 400: train loss 7.6184, val loss 7.7647\n",
-            "step 500: train loss 7.5690, val loss 7.7763\n",
-            "step 600: train loss 7.5422, val loss 7.7430\n",
-            "step 700: train loss 7.5362, val loss 7.7559\n",
-            "step 800: train loss 7.4778, val loss 7.7400\n",
-            "step 900: train loss 7.4192, val loss 7.6667\n",
-            "step 1000: train loss 7.3854, val loss 7.6163\n",
-            "step 1100: train loss 7.3321, val loss 7.5843\n",
-            "step 1200: train loss 7.2594, val loss 7.5148\n",
-            "step 1300: train loss 7.2283, val loss 7.4860\n",
-            "step 1400: train loss 7.1611, val loss 7.4022\n",
-            "step 1500: train loss 7.0903, val loss 7.3789\n",
-            "step 1600: train loss 7.0679, val loss 7.3126\n",
-            "step 1700: train loss 6.9863, val loss 7.2131\n",
-            "step 1800: train loss 6.9202, val loss 7.1764\n",
-            "step 1900: train loss 6.9034, val loss 7.1758\n",
-            "step 2000: train loss 6.8178, val loss 7.1035\n",
-            "step 2100: train loss 6.7434, val loss 7.0638\n",
-            "step 2200: train loss 6.7087, val loss 7.0001\n",
-            "step 2300: train loss 6.6774, val loss 7.0209\n",
-            "step 2400: train loss 6.6049, val loss 6.8982\n",
-            "step 2500: train loss 6.5634, val loss 6.9102\n"
-          ]
-        },
-        {
-          "output_type": "error",
-          "ename": "KeyboardInterrupt",
-          "evalue": "",
-          "traceback": [
-            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-            "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
-            "\u001b[0;32m<ipython-input-8-48f74470a47d>\u001b[0m in \u001b[0;36m<cell line: 55>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     66\u001b[0m   \u001b[0mlogits\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mloss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mxb\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0myb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     67\u001b[0m   \u001b[0moptimizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mzero_grad\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mset_to_none\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 68\u001b[0;31m   \u001b[0mloss\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     69\u001b[0m   \u001b[0moptimizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/_tensor.py\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(self, gradient, retain_graph, create_graph, inputs)\u001b[0m\n\u001b[1;32m    520\u001b[0m                 \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    521\u001b[0m             )\n\u001b[0;32m--> 522\u001b[0;31m         torch.autograd.backward(\n\u001b[0m\u001b[1;32m    523\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgradient\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mretain_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcreate_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    524\u001b[0m         )\n",
-            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/autograd/__init__.py\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)\u001b[0m\n\u001b[1;32m    264\u001b[0m     \u001b[0;31m# some Python versions print out the first line of a multi-line function\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    265\u001b[0m     \u001b[0;31m# calls in the traceback and some print out the last line\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 266\u001b[0;31m     Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass\n\u001b[0m\u001b[1;32m    267\u001b[0m         \u001b[0mtensors\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    268\u001b[0m         \u001b[0mgrad_tensors_\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+            "step 0: train loss 5.4611, val loss 5.7733\n",
+            "step 100: train loss 5.4859, val loss 5.7609\n",
+            "step 200: train loss 5.4366, val loss 5.7421\n",
+            "step 300: train loss 5.4118, val loss 5.7483\n",
+            "step 400: train loss 5.3847, val loss 5.7439\n",
+            "step 500: train loss 5.3921, val loss 5.7199\n",
+            "step 600: train loss 5.3781, val loss 5.7384\n",
+            "step 700: train loss 5.4029, val loss 5.7142\n",
+            "step 800: train loss 5.3649, val loss 5.6579\n",
+            "step 900: train loss 5.3712, val loss 5.6517\n",
+            "step 1000: train loss 5.3437, val loss 5.6734\n",
+            "step 1100: train loss 5.3674, val loss 5.6478\n",
+            "step 1200: train loss 5.3534, val loss 5.6327\n",
+            "step 1300: train loss 5.2754, val loss 5.6200\n",
+            "step 1400: train loss 5.2781, val loss 5.6002\n",
+            "step 1500: train loss 5.2356, val loss 5.5554\n",
+            "step 1600: train loss 5.1945, val loss 5.5598\n",
+            "step 1700: train loss 5.2314, val loss 5.5781\n",
+            "step 1800: train loss 5.2540, val loss 5.5091\n",
+            "step 1900: train loss 5.2265, val loss 5.5613\n",
+            "step 2000: train loss 5.2028, val loss 5.5447\n",
+            "step 2100: train loss 5.1583, val loss 5.5405\n",
+            "step 2200: train loss 5.1471, val loss 5.4592\n",
+            "step 2300: train loss 5.1682, val loss 5.4512\n",
+            "step 2400: train loss 5.1460, val loss 5.4517\n",
+            "step 2499: train loss 5.1224, val loss 5.4268\n"
           ]
         }
       ]
@@ -699,14 +715,14 @@
     {
       "cell_type": "code",
       "source": [
-        "model_save_name = f'base-500m.pth'\n",
+        "model_save_name = f'base-500m-v1.pth'\n",
         "path = f\"/content/drive/MyDrive/{model_save_name}\"\n",
         "torch.save(model.state_dict(), path)"
       ],
       "metadata": {
         "id": "e6NM24zMhH_2"
       },
-      "execution_count": 9,
+      "execution_count": 10,
       "outputs": []
     },
     {
@@ -730,9 +746,9 @@
           "base_uri": "https://localhost:8080/",
           "height": 564
         },
-        "outputId": "a6487980-796b-45ef-f7c1-f8e92504a4b2"
+        "outputId": "bd1337f6-ceb6-4ce1-fea3-5a2a78c92fe8"
       },
-      "execution_count": 17,
+      "execution_count": 11,
       "outputs": [
         {
           "output_type": "display_data",
@@ -740,7 +756,7 @@
             "text/plain": [
               "<Figure size 1200x600 with 1 Axes>"
             ],
-            "image/png": "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\n"
+            "image/png": "iVBORw0KGgoAAAANSUhEUgAAA+kAAAIjCAYAAAB/OVoZAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAACjbElEQVR4nOzdd3gU9drG8e+m94SQ0ENCSOhVmtJVUBERKYIIIgj2hkdsx4bl6Ksox4p6VORYUFDBY0Gq0nuTDklICIFQEkgndef9YyAQgSWBJJNyf65rruzOzM48m1By76/ZDMMwEBERERERERHLOVldgIiIiIiIiIiYFNJFREREREREKgiFdBEREREREZEKQiFdREREREREpIJQSBcRERERERGpIBTSRURERERERCoIhXQRERERERGRCkIhXURERERERKSCUEgXERERERERqSAU0kVEREREREQqCIV0ERGRYpg+fTo2m40NGzZYXUqxrFy5kkGDBlG7dm3c3d0JCwvj3nvvJT4+3urSzisuLo6xY8fSuHFjPDw8qFOnDj179uTFF18sct7UqVOZPn26NUWKiIiUA5thGIbVRYiIiFR006dPZ+zYsaxfv56OHTtaXY5D77//Po8++ijh4eGMGTOGunXrsmvXLj777DMA5s6dS9euXS2u8ozo6Gg6deqEp6cnd911F2FhYSQmJrJp0yZ+//13srOzC89t1aoVQUFBLFmyxLqCRUREypCL1QWIiIhI6Vm5ciUTJkyge/fuzJs3Dy8vr8Jj999/P926dWPo0KHs2LGDGjVqlFtdmZmZeHt7n/fYv//9bzIyMtiyZQuhoaFFjh09erQ8yhMREakw1N1dRESkFG3evJl+/frh5+eHj48P1157LWvWrClyTl5eHi+99BKRkZF4eHhQs2ZNunfvzsKFCwvPOXz4MGPHjqVBgwa4u7tTt25dBg4cSFxcnMP7v/LKK9hsNv773/8WCegAjRs35s033yQxMZFPPvkEgLfeegubzcb+/fvPudYzzzyDm5sbJ06cKNy3du1abrjhBvz9/fHy8qJXr16sXLmyyOsmTZqEzWZj586d3H777dSoUYPu3btfsOaYmBgaNGhwTkAHqFWrVuHjsLAwduzYwdKlS7HZbNhsNnr37l14PCUlhQkTJhASEoK7uzsRERG88cYb2O32wnPi4uKw2Wy89dZb/Pvf/yY0NBRPT0969erF9u3bi9z7Un8GIiIil0Mt6SIiIqVkx44d9OjRAz8/P5588klcXV355JNP6N27N0uXLqVLly6AGWJff/11xo8fT+fOnUlLS2PDhg1s2rSJvn37AjBkyBB27NjBww8/TFhYGEePHmXhwoXEx8cTFhZ23vtnZWWxePFievToQaNGjc57zvDhw7nnnnv49ddfefrppxk2bBhPPvkks2bN4oknnihy7qxZs7juuusKW9z/+OMP+vXrR4cOHXjxxRdxcnLiiy++4JprrmH58uV07ty5yOtvvfVWIiMjee2113A0ui40NJRFixbxxx9/cM0111zwvHfeeYeHH34YHx8fnn32WQBq165d+N579erFwYMHuffee2nYsCGrVq3imWeeITExkXfeeafItb788kvS09N58MEHyc7O5t133+Waa65h27Zthde8lJ+BiIjIZTNERETkor744gsDMNavX3/Bc2655RbDzc3NiImJKdx36NAhw9fX1+jZs2fhvrZt2xr9+/e/4HVOnDhhAMbkyZNLVOOWLVsMwHj00UcdntemTRsjMDCw8PlVV11ldOjQocg569atMwDjyy+/NAzDMOx2uxEZGWlcf/31ht1uLzwvKyvLaNSokdG3b9/CfS+++KIBGCNGjChW3du3bzc8PT0NwGjXrp3x6KOPGj/99JORmZl5zrktW7Y0evXqdc7+V155xfD29jb27t1bZP/TTz9tODs7G/Hx8YZhGEZsbKwBGJ6enkZCQkLheWvXrjUA47HHHjMM49J/BiIiIpdL3d1FRERKQUFBAQsWLOCWW24hPDy8cH/dunW5/fbbWbFiBWlpaQAEBASwY8cOoqKiznstT09P3NzcWLJkSZGu5heTnp4OgK+vr8PzfH19C2sBs3V948aNxMTEFO6bOXMm7u7uDBw4EIAtW7YQFRXF7bffTnJyMklJSSQlJZGZmcm1117LsmXLinQrB7jvvvuKVXfLli3ZsmULo0aNIi4ujnfffZdbbrmF2rVr8+mnnxbrGt9//z09evSgRo0ahbUlJSXRp08fCgoKWLZsWZHzb7nlFurXr1/4vHPnznTp0oW5c+cCl/4zEBERuVwK6SIiIqXg2LFjZGVl0bRp03OONW/eHLvdzoEDBwB4+eWXSUlJoUmTJrRu3ZonnniCrVu3Fp7v7u7OG2+8we+//07t2rXp2bMnb775JocPH3ZYw+lwfjqsX0h6enqRIH/rrbfi5OTEzJkzATAMg++//75wbD1Q+IHCnXfeSXBwcJHts88+Iycnh9TU1CL3uVCX+/Np0qQJX331FUlJSWzdupXXXnsNFxcX7rnnHhYtWnTR10dFRTFv3rxzauvTpw9w7gR0kZGR563h9HjzS/0ZiIiIXC6FdBERkXLWs2dPYmJimDZtGq1ateKzzz7jiiuuKFwiDWDChAns3buX119/HQ8PD55//nmaN2/O5s2bL3jdiIgIXFxcigT+v8vJyWHPnj20aNGicF+9evXo0aMHs2bNAmDNmjXEx8czfPjwwnNOt5JPnjyZhQsXnnfz8fEpci9PT8+SfWMAZ2dnWrduzTPPPMOcOXMA+Oabby76OrvdTt++fS9Y25AhQ0pcy6X8DERERC6XJo4TEREpBcHBwXh5ebFnz55zju3evRsnJydCQkIK9wUGBjJ27FjGjh1LRkYGPXv2ZNKkSYwfP77wnMaNG/P444/z+OOPExUVRbt27Xj77bf5+uuvz1uDt7c3V199NX/88Qf79+8/72zps2bNIicnh5tuuqnI/uHDh/PAAw+wZ88eZs6ciZeXFwMGDChSC4Cfn19h63RZO70efWJiYuE+m8123nMbN25MRkZGsWs731CDvXv3njMhXEl/BiIiIpdLLekiIiKlwNnZmeuuu47//e9/RZboOnLkCDNmzKB79+6FXceTk5OLvNbHx4eIiAhycnIAc6by7OzsIuc0btwYX1/fwnMu5LnnnsMwDMaMGcPJkyeLHIuNjeXJJ5+kbt263HvvvUWODRkyBGdnZ7799lu+//57brrppiLrmnfo0IHGjRvz1ltvkZGRcc59jx075rAuR5YvX05eXt45+0+PDz97CIG3tzcpKSnnnDts2DBWr17N/PnzzzmWkpJCfn5+kX0//fQTBw8eLHy+bt061q5dS79+/YDL+xmIiIhcDrWki4iIlMC0adOYN2/eOfsfffRRXn31VRYuXEj37t154IEHcHFx4ZNPPiEnJ4c333yz8NwWLVrQu3dvOnToQGBgIBs2bOCHH37goYceAswW3WuvvZZhw4bRokULXFxcmDNnDkeOHOG2225zWF/Pnj156623+Mc//kGbNm0YM2YMdevWZffu3Xz66afY7Xbmzp1buKzaabVq1eLqq69mypQppKenF+nqDuDk5MRnn31Gv379aNmyJWPHjqV+/focPHiQP//8Ez8/P3755ZdL+p6+8cYbbNy4kcGDB9OmTRsANm3axJdffklgYCATJkwoPLdDhw589NFHvPrqq0RERFCrVi2uueYannjiCX7++WduuukmxowZQ4cOHcjMzGTbtm388MMPxMXFERQUVHidiIgIunfvzv33309OTg7vvPMONWvW5Mknn7zsn4GIiMhlsXp6eRERkcrg9BJsF9oOHDhgGIZhbNq0ybj++usNHx8fw8vLy7j66quNVatWFbnWq6++anTu3NkICAgwPD09jWbNmhn/+te/jNzcXMMwDCMpKcl48MEHjWbNmhne3t6Gv7+/0aVLF2PWrFnFrnfZsmXGwIEDjaCgIMPV1dVo2LChcffddxtxcXEXfM2nn35qAIavr69x8uTJ856zefNmY/DgwUbNmjUNd3d3IzQ01Bg2bJixePHiwnNOL8F27NixYtW6cuVK48EHHzRatWpl+Pv7F9Y7ZsyYIsvZGYZhHD582Ojfv7/h6+trAEWWY0tPTzeeeeYZIyIiwnBzczOCgoKMrl27Gm+99Vbh9/b0EmyTJ0823n77bSMkJMRwd3c3evToYfz111+F1yqNn4GIiMilsBmGYVj0+YCIiIhIuYqLi6NRo0ZMnjyZiRMnWl2OiIjIOTQmXURERERERKSCUEgXERERERERqSAU0kVEREREREQqCI1JFxEREREREakg1JIuIiIiIiIiUkEopIuIiIiIiIhUEC5WF1De7HY7hw4dwtfXF5vNZnU5IiIiIiIiUsUZhkF6ejr16tXDyekibeVWLtL+4osvGkCRrWnTpg5f8+9//9to0qSJ4eHhYTRo0MCYMGGCcfLkyWLf88CBA+fcU5s2bdq0adOmTZs2bdq0aSvr7cCBAxfNrJa3pLds2ZJFixYVPndxuXBJM2bM4Omnn2batGl07dqVvXv3MmbMGGw2G1OmTCnW/Xx9fQE4cOAAfn5+l1e8iIiIiIiIyEWkpaUREhJSmEcdsTyku7i4UKdOnWKdu2rVKrp168btt98OQFhYGCNGjGDt2rUXfE1OTg45OTmFz9PT0wHw8/NTSBcREREREZFyU5wh15ZPHBcVFUW9evUIDw9n5MiRxMfHX/Dcrl27snHjRtatWwfAvn37mDt3LjfeeOMFX/P666/j7+9fuIWEhJT6exAREREREREpDZauk/7777+TkZFB06ZNSUxM5KWXXuLgwYNs3779gt0A3nvvPSZOnIhhGOTn53Pffffx0UcfXfAef29JP93NIDU1VS3pIiIiIiIiUubS0tLw9/cvVg61NKT/XUpKCqGhoUyZMoVx48adc3zJkiXcdtttvPrqq3Tp0oXo6GgeffRR7r77bp5//vli3aMk3xwRERERERGRy1WSHGr5mPSzBQQE0KRJE6Kjo897/Pnnn+eOO+5g/PjxALRu3ZrMzEzuuecenn322YtPZS8iIiIiItXa6R65BQUFVpciVYyrqyvOzs6XfZ0KFdIzMjKIiYnhjjvuOO/xrKysc4L46W9CBeoQICIiIiIiFVBubi6JiYlkZWVZXYpUQTabjQYNGuDj43NZ17E0pE+cOJEBAwYQGhrKoUOHePHFF3F2dmbEiBEAjB49mvr16/P6668DMGDAAKZMmUL79u0Lu7s///zzDBgwoFQ+sRARERERkarJbrcTGxuLs7Mz9erVw83NrVgzbYsUh2EYHDt2jISEBCIjIy8rn1oa0hMSEhgxYgTJyckEBwfTvXt31qxZQ3BwMADx8fFFWs6fe+45bDYbzz33HAcPHiQ4OJgBAwbwr3/9y6q3ICIiIiIilUBubi52u52QkBC8vLysLkeqoODgYOLi4sjLy7uskF6hJo4rD5o4TkRERESk+snOziY2NpZGjRrh4eFhdTlSBTn6M1aSHKqZ1kREREREREQqCIV0ERERERERkQpCIV1ERERERKQaCQsL45133rG6DLkAhXQREREREZEKyGazOdwmTZp0Sdddv34999xzz2XV1rt3byZMmHBZ15Dzq1DrpIuIiIiIiIgpMTGx8PHMmTN54YUX2LNnT+G+s9fjNgyDgoICXFwuHvFOr6YlFZNa0kVEREREpNoxDIOs3HxLtuIusFWnTp3Czd/fH5vNVvh89+7d+Pr68vvvv9OhQwfc3d1ZsWIFMTExDBw4kNq1a+Pj40OnTp1YtGhRkev+vbu7zWbjs88+Y9CgQXh5eREZGcnPP/98Wd/fH3/8kZYtW+Lu7k5YWBhvv/12keNTp04lMjISDw8PateuzdChQwuP/fDDD7Ru3RpPT09q1qxJnz59yMzMvKx6KhO1pIuIiIiISLVzMq+AFi/Mt+TeO1++Hi+30oliTz/9NG+99Rbh4eHUqFGDAwcOcOONN/Kvf/0Ld3d3vvzySwYMGMCePXto2LDhBa/z0ksv8eabbzJ58mTef/99Ro4cyf79+wkMDCxxTRs3bmTYsGFMmjSJ4cOHs2rVKh544AFq1qzJmDFj2LBhA4888ghfffUVXbt25fjx4yxfvhwwew+MGDGCN998k0GDBpGens7y5cuL/cFGVaCQLiIiIiIiUkm9/PLL9O3bt/B5YGAgbdu2LXz+yiuvMGfOHH7++WceeuihC15nzJgxjBgxAoDXXnuN9957j3Xr1nHDDTeUuKYpU6Zw7bXX8vzzzwPQpEkTdu7cyeTJkxkzZgzx8fF4e3tz00034evrS2hoKO3btwfMkJ6fn8/gwYMJDQ0FoHXr1iWuoTJTSK+okqLh4AZoeCUEhILNZnVFIiIiIiJVhqerMztfvt6ye5eWjh07FnmekZHBpEmT+O233woD78mTJ4mPj3d4nTZt2hQ+9vb2xs/Pj6NHj15STbt27WLgwIFF9nXr1o133nmHgoIC+vbtS2hoKOHh4dxwww3ccMMNhV3t27Zty7XXXkvr1q25/vrrue666xg6dCg1atS4pFoqI4X0imrXz7D4JfOxbz0zrId2Nb/WagFOpfcXW0RERESkurHZbKXW5dxK3t7eRZ5PnDiRhQsX8tZbbxEREYGnpydDhw4lNzfX4XVcXV2LPLfZbNjt9lKvF8DX15dNmzaxZMkSFixYwAsvvMCkSZNYv349AQEBLFy4kFWrVrFgwQLef/99nn32WdauXUujRo3KpJ6KRhPHVVQ+taB+R3BygfRDsGM2zJ0IH3eHNxrB10Nh+duwfxXkZVtdrYiIiIiIVAArV65kzJgxDBo0iNatW1OnTh3i4uLKtYbmzZuzcuXKc+pq0qQJzs5mY6OLiwt9+vThzTffZOvWrcTFxfHHH38A5gcE3bp146WXXmLz5s24ubkxZ86ccn0PVqr8Hx1VVe1HmVtuFhzcCPGrze3AOshJheiF5gbg7Ab1rjjT2h7SGTyrT3cQERERERExRUZGMnv2bAYMGIDNZuP5558vsxbxY8eOsWXLliL76taty+OPP06nTp145ZVXGD58OKtXr+aDDz5g6tSpAPz666/s27ePnj17UqNGDebOnYvdbqdp06asXbuWxYsXc91111GrVi3Wrl3LsWPHaN68eZm8h4pIIb2ic/OCRj3MDaAgH45sPxPa96+GzKNwYI25rXwHsJld4s/uIu/fwMp3ISIiIiIi5WDKlCncdddddO3alaCgIJ566inS0tLK5F4zZsxgxowZRfa98sorPPfcc8yaNYsXXniBV155hbp16/Lyyy8zZswYAAICApg9ezaTJk0iOzubyMhIvv32W1q2bMmuXbtYtmwZ77zzDmlpaYSGhvL222/Tr1+/MnkPFZHNqE5z2QNpaWn4+/uTmpqKn5+f1eVcPsOA4/vOhPb4NZAcfe55/iHQ8KozwT2oKThptIOIiIiIVA/Z2dnExsbSqFEjPDw8rC5HqiBHf8ZKkkPVkl7Z2WxQs7G5tR9l7ss4aob108E9cSukHoBtB2DbLPMczxoQcuWZ0F63Hbi4WfY2RERERERERCG9avKpBS1uNjeAnHRI2HAmtCdsgJMnYO/v5gbg4gH1O5xqbb/KHNfuUQV6GoiIiIiIiFQiCunVgbsvNL7a3AAK8szW9cIu8qshKxn2rzQ3AJsT1G4JDbuaLe2RfcHN+8L3EBERERERkcumkF4dObtCgw7m1vUhc1x7UlTR0H4iDg5vM7d1n4CrNzS/CVoPg/De4Kw/OiIiIiIiIqVNSUvMce3BTcytw53mvrTEMxPRRS2AE7Gwdaa5eQdDq6HQZhjUa2++XkRERERERC6bQrqcn19daDXY3Iw3zHHs22bB9h8h8xis/cjcakZCm+HQeigENrK6ahERERERkUpNa3DJxdlsENIJbpwMj++B22dBqyHg4gnJUfDnq/BeO/j8Olj/GWQdt7piERERERGRSkkt6VIyzq7Q5Hpzy0mHXb+aXeBjl8KBteb2+1MQeR20vhWa9gNXT6urFhERERERqRQU0uXSuftCuxHmlpZodoXfOhMOb4U9c83NzRdaDDTHr4d1Bydnq6sWERERERGpsNTdXUqHX11zpvj7lsMDa6HH4+DfEHLTYcvX8OXN8O9WsOA5c8Z4w7C6YhERERGRaqF3795MmDCh8HlYWBjvvPOOw9fYbDZ++umny753aV2nOlFIl9JXqxlc+wI8+heM/R06jAGPAEg/BKveh4+7w0ddYcW/ITXB6mqLLy8bkmPg6G7ITAa73eqKRERERKQKGzBgADfccMN5jy1fvhybzcbWrVtLfN3169dzzz33XG55RUyaNIl27dqdsz8xMZF+/fqV6r3+bvr06QQEBJTpPcqTurtL2XFygtCu5tbvTYhaaHaH3zsPju6ERZNg0UtmN/jWt5rd4j0DrKnVMMwJ71IPmB8cpCacenzW84wjRV9jcwKvmuAVBN6nt2Bz86p56nHQmeeeNbRcnYiIiIgU27hx4xgyZAgJCQk0aNCgyLEvvviCjh070qZNmxJfNzg4uLRKvKg6deqU272qCoV0KR8u7tD8JnM7mQI7/wfbvoe45We2uU+YE9K1GQ6Rfc3XlJb8XEg7eFYAT4DU+KLP87KK8T48wcUNslPBsJvL0WUeg2PFqMHJpWh49zod6k/tK3x+KvC7+ynUi4iIiJQVwyje739lwdWrWL/n3XTTTQQHBzN9+nSee+65wv0ZGRl8//33TJ48meTkZB566CGWLVvGiRMnaNy4Mf/85z8ZMWLEBa8bFhbGhAkTCrvAR0VFMW7cONatW0d4eDjvvvvuOa956qmnmDNnDgkJCdSpU4eRI0fywgsv4OrqyvTp03nppZcAs3s7mB8ijBkzBpvNxpw5c7jlllsA2LZtG48++iirV6/Gy8uLIUOGMGXKFHx8fAAYM2YMKSkpdO/enbfffpvc3Fxuu+023nnnHVxdXYv17f27+Ph4Hn74YRYvXoyTkxM33HAD77//PrVr1wbgr7/+YsKECWzYsAGbzUZkZCSffPIJHTt2ZP/+/Tz00EOsWLGC3NxcwsLCmDx5MjfeeOMl1VIcCulS/jwDoMOd5pZyALb/AH/NhGO7YNfP5uYRAC1vMQN7yJVmq/yFGAZkp5jXulArePphoBjj4L1rQUAI+DcA//N89Qo0/0EtyIOs5FMhPenUdgyyTn3NTD7reRLkpIE932yN/3uL/IU4u53bSn/28wadzaEFIiIiIlJyeVnwWj1r7v3PQ+DmfdHTXFxcGD16NNOnT+fZZ58tDMDff/89BQUFjBgxgoyMDDp06MBTTz2Fn58fv/32G3fccQeNGzemc+fOF72H3W5n8ODB1K5dm7Vr15Kamlpk/Pppvr6+TJ8+nXr16rFt2zbuvvtufH19efLJJxk+fDjbt29n3rx5LFq0CAB/f/9zrpGZmcn111/PVVddxfr16zl69Cjjx4/noYceYvr06YXn/fnnn9StW5c///yT6Ohohg8fTrt27bj77rsv+n7O9/4GDhyIj48PS5cuJT8/nwcffJDhw4ezZMkSAEaOHEn79u356KOPcHZ2ZsuWLYUfCDz44IPk5uaybNkyvL292blzZ+EHCmVFIV2sFRAC3R+DbhPgyHazO/y2HyA9ETZONzf/htDmVrNbfMaxs8L3WSE8N+Pi93LxOBW2G5wVvkPOPPerD64exavb2RV865hbceTnmGG9MMT/Pdif/TzZfD8FueY4/vRDF75uRF/o9giE9VCru4iIiEgVdNdddzF58mSWLl1K7969AbOVesiQIfj7++Pv78/EiRMLz3/44YeZP38+s2bNKlZIX7RoEbt372b+/PnUq2d+aPHaa6+dM4787Jb8sLAwJk6cyHfffceTTz6Jp6cnPj4+uLi4OOzePmPGDLKzs/nyyy/x9jY/pPjggw8YMGAAb7zxRmHLdo0aNfjggw9wdnamWbNm9O/fn8WLF19SSF+8eDHbtm0jNjaWkJAQAL788ktatmzJ+vXr6dSpE/Hx8TzxxBM0a2Y2gEVGRha+Pj4+niFDhtC6dWsAwsPDS1xDSSmkS8Vgs0Gd1ubW5yWIWwFbZ5nd4lPjYfnb5uaIV5DjVnDvIOuCrIs7+Nc3t+LIzSoa3v8e7tMSzO9R9EJzq9vODOvNB4Kz/lqLiIiIXJSrl9mibdW9i6lZs2Z07dqVadOm0bt3b6Kjo1m+fDkvv/wyAAUFBbz22mvMmjWLgwcPkpubS05ODl5exbvHrl27CAkJKQzoAFddddU5582cOZP33nuPmJgYMjIyyM/Px8/Pr9jv4/S92rZtWxjQAbp164bdbmfPnj2FIb1ly5Y4O59Zurlu3bps27atRPc6+54hISGFAR2gRYsWBAQEsGvXLjp16sQ//vEPxo8fz1dffUWfPn249dZbady4MQCPPPII999/PwsWLKBPnz4MGTLkkuYBKAn9Ni8Vj5MzhPcyt/5vwZ7fzfHrSXvBr17R1u/C1vD64OppdeWlx80L3BpCQMMLn3N8H6z+EDZ/DYlb4Ie7zPOvegjajypWFyoRERGRastmqzS/L40bN46HH36YDz/8kC+++ILGjRvTq1cvACZPnsy7777LO++8Q+vWrfH29mbChAnk5uaW2v1Xr17NyJEjeemll7j++uvx9/fnu+++4+23L9KIdon+PvbcZrNhL8OVlSZNmsTtt9/Ob7/9xu+//86LL77Id999x6BBgxg/fjzXX389v/32GwsWLOD111/n7bff5uGHHy6zerQEm1Rsrp7QajCM+BYe3gh3/gK3TIWr/wlXjIbGV0NQRNUK6MUVGA7934bHdkCvp8EzEFLi4fcn4d8t4Y9XzeEBVVlSFPz5Gnx5i9nT4mSK1RWJiIiIlLphw4bh5OTEjBkz+PLLL7nrrrsKx6evXLmSgQMHMmrUKNq2bUt4eDh79+4t9rWbN2/OgQMHSExMLNy3Zs2aIuesWrWK0NBQnn32WTp27EhkZCT79+8vco6bmxsFBQUXvddff/1FZmZm4b6VK1fi5ORE06ZNi11zSZx+fwcOHCjct3PnTlJSUmjRokXhviZNmvDYY4+xYMECBg8ezBdffFF4LCQkhPvuu4/Zs2fz+OOP8+mnn5ZJracppItUdt5BcPUzZli/8S2o0QhOnoBlk82w/sujkBRtdZWlJ+0QrPoAPukFH3SEpW/Avj9h8cvm+53/LKQetLpKERERkVLj4+PD8OHDeeaZZ0hMTGTMmDGFxyIjI1m4cCGrVq1i165d3HvvvRw5UsyJioE+ffrQpEkT7rzzTv766y+WL1/Os88+W+ScyMhI4uPj+e6774iJieG9995jzpw5Rc4JCwsjNjaWLVu2kJSURE5Ozjn3GjlyJB4eHtx5551s376dP//8k4cffpg77rijsKv7pSooKGDLli1Ftl27dtGnTx9at27NyJEj2bRpE+vWrWP06NH06tWLjh07cvLkSR566CGWLFnC/v37WblyJevXr6d58+YATJgwgfnz5xMbG8umTZv4888/C4+VFYV0karCzQs63232OLj1v1C/AxTkmJPvfdARvhsJ8WutrvLSnDwBG/8L02+CKS1gwbNmF3+bM0ReZ85jUKuFOeHe6g/g3bbw0wNwdLfVlYuIiIiUinHjxnHixAmuv/76IuPHn3vuOa644gquv/56evfuTZ06dQqXOysOJycn5syZw8mTJ+ncuTPjx4/nX//6V5Fzbr75Zh577DEeeugh2rVrx6pVq3j++eeLnDNkyBBuuOEGrr76aoKDg/n222/PuZeXlxfz58/n+PHjdOrUiaFDh3LttdfywQcflOybcR4ZGRm0b9++yDZgwABsNhv/+9//qFGjBj179qRPnz6Eh4czc+ZMAJydnUlOTmb06NE0adKEYcOG0a9fv8Il5QoKCnjwwQdp3rw5N9xwA02aNGHq1KmXXa8jNsMwirEuVdWRlpaGv78/qampJZ7oQKRSMQzYvwpWvQd7553ZH9IFuj4CTW90vLSd1fJOmnVv+wGiFpiz3Z/W8CpoPRRa3GL2JADz/UYthJXvwv4VZ85tcoO5ekDDKzUDvoiISDWWnZ1NbGwsjRo1wsOjmCv6iJSAoz9jJcmhCuki1cHR3bD6fXPG/NNht2aEOclc2xHFX3qurBXkQ+xSM5jv+gVy088cq9XSDOathkCNUMfXSdhghvVdvwCn/olr0Bm6PVrxP5wQERGRMqGQLmVNIf0SKaRLtZZ+GNZ+DOunQU6quc87GLrcCx3HgVdg+ddkGGao3vY97JhtLjV3mn9DM5i3Hgq1W5b82knR5ocTW741u/4D1Iw0l6trM9xcGk9ERESqBYV0KWsK6ZdIIV0EyEmHTV/C6qnmmusArt5wxR1w5QMXb6kuDcf2mMF82/dwIu7Mfq+a0HIQtL7VbP0ujVbv9COnPpz4/MyHEz614cr7oeNd4OF/+fcQERGRCk0hXcqaQvolUkgXOUtBHuyYAyvfgyPbzH02Z2h5izluvV670r1f6kHY/iNsmwWHt53Z7+oNzfpDm2EQ3hucXS94icuSk25OQLf6Q0g/ZO5z84WOY83A7lfP8etFRESk0lJIl7KmkH6JFNJFzsMwzGXMVr5nfj2tUU/o+ihEXHvpk65lHYed/zPHme9fSeEYcScXiOhrdmVv2g/cvC/7bRRbfi5s/8Ect37s1AzwTq5mF/huj0Bw2azTKSIiItY5HaDCwsLw9PS0uhypgk6ePElcXJxCekkppItcROJWWPW+2eJtFJj7arWErg+bk7a5uF38GrlZsPf3UzOzLwR73pljod3OzMxuxRj4s9ntEL0QVrwD8avO7G96oznJXMMrLStNRERESldBQQF79+6lVq1a1KxZ0+pypApKTU3l0KFDRERE4OpatGeoQroDCukixZRyANZ8BJv+a64/DuBbz+wW3mEMePzt709BHuxbanZl3/3bmdcA1GltjjFvNQT8G5TbWyiRA+vMlvXdv1HY2h/SxVy+rckNmhFeRESkCkhMTCQlJYVatWrh5eWFTcuzSimx2+0cOnQIV1dXGjZseM6fLYV0BxTSRUro5AnY8IU58VrGEXOfu58Z1LvcB6kJp2ZmnwNZSWdeFxBqBvPWt0KtZpaUfkmSosy15f/67sxydUFNzDH6bYZpRngREZFKzDAMDh8+TEpKitWlSBXk5OREo0aNcHM7t+epQroDCukilyg/x1xnfdX7kLTn/Od4B0PLwadmZu946ePYK4L0w2ZPgg3TICfN3Odb96yeBJoRXkREpLIqKCggLy/v4ieKlICbmxtOF+h9qZDugEK6yGWy2yFqgdnavH8luPlA8wHmOPNGvcHZxeoKS1d2GmycDmumQnqiuc/d79SM8A+Abx1LyxMRERGRik8h3QGFdJFSlHYIPALAzcvqSspefq7ZrX/lu2d6Eji7mTPCd30EgptYW5+IiIiIVFgK6Q4opIvIZbHbIWq+GdbjV5/aaTPXee/2KIR0trQ8EREREal4SpJDNV2xiEhJODmZ67rfNQ/uWgBN+wMG7P4VPu9rjtkXEREREblECukiIpeqYRcYMQMeXA9tbjP3LXgONn1pbV0iIiIiUmkppIuIXK7gJjD4E3NNdYBfHoUdP1lZkYiIiIhUUgrpIiKlpc8kc3k2ww4/jofoxVZXJCIiIiKVjEK6iEhpsdmg/xRzrXh7HswcBfFrra5KRERERCoRhXQRkdLk5AyDPoGIPpCXBTNuhcPbra5KRERERCoJS0P6pEmTsNlsRbZmzZpd8PzevXufc77NZqN///7lWLWIyEW4uMGwryDkSshOha8GQXKM1VWJiIiISCXgYnUBLVu2ZNGiRYXPXVwuXNLs2bPJzc0tfJ6cnEzbtm259dZby7RGEZESc/OC22fC9JvgyDb46ha4az741bO6MhERERGpwCwP6S4uLtSpU6dY5wYGBhZ5/t133+Hl5aWQLiIVk2cA3DEbpt0Ax2PMFvWxv4NX4EVfKiIiIiLVk+Vj0qOioqhXrx7h4eGMHDmS+Pj4Yr/2888/57bbbsPb2/uC5+Tk5JCWllZkExEpNz61YPRP4Fcfju2Gr4dATrrVVYmIiIhIBWVpSO/SpQvTp09n3rx5fPTRR8TGxtKjRw/S0y/+C+y6devYvn0748ePd3je66+/jr+/f+EWEhJSWuWLiBRPQEO44yfwqgmHNsG3IyAv2+qqRERERKQCshmGYVhdxGkpKSmEhoYyZcoUxo0b5/Dce++9l9WrV7N161aH5+Xk5JCTk1P4PC0tjZCQEFJTU/Hz8yuVukVEiuXQZpg+AHLToWl/GPYlOFs+6khEREREylhaWhr+/v7FyqGWd3c/W0BAAE2aNCE6OtrheZmZmXz33XcXDfIA7u7u+Pn5FdlERCxRrz3c/h04u8Oe3+B/D4LdbnVVIiIiIlKBVKiQnpGRQUxMDHXr1nV43vfff09OTg6jRo0qp8pEREpJWHcY9l+wOcPW72De01BxOjSJiIiIiMUsDekTJ05k6dKlxMXFsWrVKgYNGoSzszMjRowAYPTo0TzzzDPnvO7zzz/nlltuoWbNmuVdsojI5WvaDwZ9DNhg3Sew5P+srkhEREREKghLB0MmJCQwYsQIkpOTCQ4Opnv37qxZs4bg4GAA4uPjcXIq+jnCnj17WLFiBQsWLLCiZBGR0tFmGGSnwtyJsPT/zOXarrzf6qpERERExGIVauK48lCSAfsiImVu6WT481Xz8S0fQbvbra1HREREREpdpZ04TkSk2uk5Ea56yHz8v4dg16/W1iMiIiIillJIFxGxks0G170K7UaBUQA/jIV9S6yuSkREREQsopAuImI1mw0GvAvNB0BBLnx7OyRssLoqEREREbGAQrqISEXg7AJDPofw3pCXCd8MhSM7ra5KRERERMqZQrqISEXh4g7Dv4EGneDkCfhqEByPtboqERERESlHCukiIhWJuw/cPgtqtYCMw/DVLZB+2OqqRERERKScKKSLiFQ0XoFwxxyoEQYn4swW9azjVlclIiIiIuVAIV1EpCLyrQOj/wc+deDoTpgxDHIyrK5KRERERMqYQrqISEVVIwxG/wSeNSBhPcwcBfk5VlclIiIiImVIIV1EpCKr1RxG/gCu3rDvT/hxHBTkW11VxZeTARumwRc3wsw74OBGqysSERERKRabYRiG1UWUp7S0NPz9/UlNTcXPz8/qckREimffEvjmVnMd9XajYOAH5vrqUtTR3bDhc9jyLeSmFz0W0Qd6PgkNu1hTm4iIiFRbJcmhCukiIpXFrl9g1mgw7HDVQ3DdqwrqAAV5sPtXWP85xC0/s79mBFxxpzmmf+ssMArM/Y16Qq+nIKy7NfWKiIhItaOQ7oBCuohUaltmwE/3m4+vfg56PWFtPVZKPQgbp8Om/0LGEXOfzQma3gid74ZGvc58iHE8FlZMMb9/9lPDBRp2Nb9/4Vfrww4REREpUwrpDiiki0ilt+YjmPe0+fjGt8xAWl0Yhtn1f/1nsOf3M63jPrWhwxiz5dy//oVfnxIPK96BzV+ZQwcA6neEXk9C5HUK6yIiIlImFNIdUEgXkSrhz9dg6Rvm48GfQpth1tZT1k6eMMeZb/gckqPP7A/rAZ3GQbObwNm1+NdLOwQr34ONX0B+trmvblvo+QQ07Q9OmldVRERESo9CugMK6SJSJRgG/P4UrPsEbM5w2zfQtJ/VVZW+Q1vMVvNtP0D+SXOfmy+0GwEd7zJnv78cGUdh1fvmePa8THNfrZbQcyK0GAhOzpd3fREREREU0h1SSBeRKsNuN8enb/0OnN1h1I/QqIfVVV2+vGzYMccM5wc3nNlfqyV0Hg+th4G7T+neMzMZ1nwIa/9zZlb4oCbQYyK0GgLOLqV7PxEREalWFNIdUEgXkSqlIM+c8X3PXLOF+c6fof4VVld1aY7Hmmubb/4aTh439zm5QstboNN4COlS9mPGT56AtZ/AmqmQnWruCwyH7v+AtreVrEu9iIiIyCkK6Q4opItIlZOXDd8MNZcf8wyEu+ZBcFOrqyoeewFELTRbzaMXAaf+S/IPgY5jof1o8Aku/7qy02Ddf2D1h2c+MAhoCN0fg3YjwcW9/GsSERGRSksh3QGFdBGpknLS4b8D4NBm8AgwJ0ELCDHDrn+DU1sI+NUHVw+rq4WMY+YM6xu+gNT4M/sj+pit5pHXVYzx4DkZZuv+qvch86i5z68+dHsUrhgNrp7W1iciIiKVgkK6AwrpIlJlZSbD9P5wbJfj87xrmaG9SIg/66tXYNl0KzcMOLDObDXf+dOZJdA8a0D7UeZEcIHhpX/f0pB3Ejb+F1a+A+mJ5j6f2tD1EbPF383b0vJERESkYlNId0AhXUSqtPwcSFgPKQcgNQFS//Y1L+vi13D1Oqv1/XSAP6tF3q8+uLgVv6acDNg2y5xB/cj2M/vrdzBbzVsOqjwt0nnZsOVrc6311APmPq+acNVD5nr17r6WliciIiIVk0K6AwrpIlJtGYY5MVpK/Kngfjq8HzjzPONIMS5kA986fwvyDYs+96wBx/aY65pv+fbMjOkuHtB6qBnO67Uv07dbpvJzzVn1l78NJ+LMfR4BcOUD0OVe8AywsDgRERGpaBTSHVBIFxFxID/nrAB/eosv+jw/++LXcfU+s+44QGBjM5i3G2EG+KqiIB+2fQ/L34LkaHOfu58Z1K98wBw6ICIiItWeQroDCukiIpfBMCAz6dxu9Ke/phyArCTzXJsTNL3RDOeNeoGTk7W1lyV7gbm2+7K3zswJ4OYDncbBVQ9bM0O9iIiIVBgK6Q4opIuIlLG8k2Zg9wiofuHUbofdv8CyyXB4m7nPxdOcXK7jXVAzouzXehcREZEKRyHdAYV0EREpc4YBe+fB0jfh0KYz+2uEmcvLRfSFsO7g5mVZiSIiIlJ+FNIdUEgXEZFyYxgQsxhWT4W45WeWnQNzEr2wHmZoj+wLgY2sq1NERETKlEK6AwrpIiJiiZwMiF0GUQsgaiGkJRQ9XjPyVGDvA6HdwMXdmjpFRESk1CmkO6CQLiIiljMMOLrLDOzRiyB+Ndjzzxx39YbwXmYLe0RfCAixrlYRERG5bArpDiiki4hIhZOdCvuWnGll//t69bVaQEQfs6W94ZXg7GpJmSIiInJpFNIdUEgXEZEKzTDg8FYzrEcthIR1YNjPHHf3g/Depyag6wN+dS0rVURERIpHId0BhXQREalUso5DzB9mYI9eCFnJRY/XaX1qLPt1UL8jOLtYU6eIiIhckEK6AwrpIiJSadntcGizGdajFsDBTcBZ/417BEDEtWZgb3xt9VunXkREpIJSSHdAIV1ERKqMjGPmEm9RCyB6MWSnnHXQBvXan2llr9cenJysqlRERKRaU0h3QCFdRESqpIJ8OLjx1ORzC8xx7WfzCjJb2Rv1hNCuUKMR2GzW1CoiIlLNKKQ7oJAuIiLVQlqiubxb1AJz5victKLHfeuaYb3hVea67MHN1NIuIiJSRhTSHVBIFxGRaqcgDw6sNbvE719ltrjb84qe41kDGnaF0KvM8F6nrSahExERKSUK6Q4opIuISLWXdxISNkD8ati/Eg6sg7ysoue4+UBIZzOwh3aDeleAq4c19YqIiFRyCukOKKSLiIj8TUEeJP5lBvb9q8zwnp1a9BxnN3OJt9Cu5hbSGdx9ralXRESkklFId0AhXURE5CLsdji60wzsp4N75tGi59icoW7bM6G94VXgFWhNvSIiIhWcQroDCukiIiIlZBiQHAPxq84E95T4c8+r1aLoZHR+dcu/VhERkQpIId0BhXQREZFSkHLg1Jj2U8E9ac+559RoZIb1063tNcK07JuIiFRLCukOKKSLiIiUgYxjZ4X2lXBkOxj2ouecXvYtrDs0HwjeNa2pVUREpJwppDugkC4iIlIOslPNWeNPj2k/uKnosm9OrtD0Bmg3CiL6aLk3ERGp0hTSHVBIFxERsUBuFhzcAPtXw565kLjlzDGf2tBmOLQfBcFNLStRRESkrCikO6CQLiIiUgEc3g5bZsDWmZCVdGZ//Q7QbiS0GgKeAZaVJyIiUpoU0h1QSBcREalA8nMhagFs+Qb2zgejwNzv4gHNboL2I6FRL3BytrZOERGRy6CQ7oBCuoiISAWVcdRsWd/8DRzbdWa/XwNoNwLa3Q6B4dbVJyIicokU0h1QSBcREangDAMObTZb17d9b05Cd1poN7M7fIuB4O5jXY0iIiIloJDugEK6iIhIJZKXDXt+M1vXY/4ATv3a4uoNLW8xA3toV62/LiIiFZpCugMK6SIiIpVU6kH461uzhf34vjP7azQyw3q7EeDfwLr6RERELkAh3QGFdBERkUrOMCB+jRnWd8yB3IxTB2wQ3ttcyq1Zf3D1tLJKERGRQgrpDiiki4iIVCG5mbDzZzOwxy0/s9/dH1oPgXajoP4V6g4vIiKWKkkOdSqnms5r0qRJ2Gy2IluzZs0cviYlJYUHH3yQunXr4u7uTpMmTZg7d245VSwiIiIVipu32c19zK/wyBbo9RT4h0BOKmyYBp9dA1OvhJXvQfoRq6sVERG5KBerC2jZsiWLFi0qfO7icuGScnNz6du3L7Vq1eKHH36gfv367N+/n4CAgHKoVERERCq0wEZw9T+h19MQt8ycbG7Xz3BsNyx8HhZNgsi+5vj1JjeAi5vVFYuIiJzD8pDu4uJCnTp1inXutGnTOH78OKtWrcLV1RWAsLCwMqxOREREKh0nJ3NsenhvyH7LHLe++RtIWAd755mbV00zrF/9T41dFxGRCsXS7u4AUVFR1KtXj/DwcEaOHEl8fPwFz/3555+56qqrePDBB6lduzatWrXitddeo6Cg4IKvycnJIS0trcgmIiIi1YSHP3QYA+MXwoProdsE8KkDWcmw6j2Y3h8yjlpdpYiISCFLQ3qXLl2YPn068+bN46OPPiI2NpYePXqQnp5+3vP37dvHDz/8QEFBAXPnzuX555/n7bff5tVXX73gPV5//XX8/f0Lt5CQkLJ6OyIiIlKRBTeBvi/BYztg+NfgWQMOboRPr4Wju6yuTkREBKhgs7unpKQQGhrKlClTGDdu3DnHmzRpQnZ2NrGxsTg7OwMwZcoUJk+eTGJi4nmvmZOTQ05OTuHztLQ0QkJCNLu7iIhIdZccA9/cCsdjwN0Pbp0OEddaXZWIiFRBlWZ2978LCAigSZMmREdHn/d43bp1adKkSWFAB2jevDmHDx8mNzf3vK9xd3fHz8+vyCYiIiJCzcYwfhGEdoOcNDOwb5hmdVUiIlLNVaiQnpGRQUxMDHXr1j3v8W7duhEdHY3dbi/ct3fvXurWrYubm2ZoFRERkRLyCoQ75kCb28AogF8fg/nPgv3C892IiIiUJUtD+sSJE1m6dClxcXGsWrWKQYMG4ezszIgRIwAYPXo0zzzzTOH5999/P8ePH+fRRx9l7969/Pbbb7z22ms8+OCDVr0FERERqexc3GHQx3D1c+bz1R/ArNGQm2ltXSIiUi1ZugRbQkICI0aMIDk5meDgYLp3786aNWsIDg4GID4+HienM58jhISEMH/+fB577DHatGlD/fr1efTRR3nqqaesegsiIiJSFdhs0OsJc631nx6A3b/CFzfCiO/A7/w9/ERERMpChZo4rjyUZMC+iIiIVEPxa+G7EeYybX714faZUKe11VWJiEglVmknjhMRERGxXMMuMH4xBDWBtIMw7QbYu8DqqkREpJpQSBcRERH5u8BGMG4BNOoJuRnw7XBY+x+rqxIRkWpAIV1ERETkfDxrwKjZ0P4OMOzw+xMw90nN/C4iImVKIV1ERETkQpxd4eb3oc9L5vN1n8C3IyAn3dq6RESkylJIFxEREXHEZoPuE2DYl+DiAVHzYVo/SD1odWUiIlIFKaSLiIiIFEeLgTBmLnjXgiPb4NNr4NBmq6uqOnLSzQn6so5bXYmIiKUU0kVERESKq0EHuHsxBDeHjMPmWuq7f7O6qsorP8f8/n0/BiZHwoxbYXp/yM2yujIREcsopIuIiIiUREBDGDcfGl8LeVnw3UhY/SEYhtWVVQ72Ati3FP73ELwVCd/dDjvmQP5JsDnB0Z0wd6LVVYqIWMbF6gJEREREKh0Pf7h9ljnj+4ZpMP+fkBwN/SaDs369OodhwMFNsP0H2D7b7IVwmm9daDUEWg81u7x/ORC2fAOhXaH9KOtqFhGxiP4XEREREbkUzi7QfwrUjID5z5ph/cR+uHU6ePhZXV3FcGwPbPsetv0AJ2LP7PcIgJa3QKuhZhh3cj5z7Opn4Y9X4LfHoW47qNOqnIsWEbGWzTCqV9+stLQ0/P39SU1Nxc9P/4GKiIhIKdj9G/w43uz+XqsF3D7T7BZfHaUcgO0/msH8yLYz+129oOmN0PpWaHwNuLid//V2O8wYBtELIbAx3LNEH3qISKVXkhyqkC4iIiJSGg5tgW9vg/REcwb4Ed+ZE81VB5lJ5rjy7T9C/Ooz+51cIKKPGcyb9gM37+JdL+s4fNwD0hKg5SAY+oW5FJ6ISCWlkO6AQrqIiIiUmdSDMGO42YLs4gGD/2Mu3VYV5aSbPQi2fQ8xf4JRcOqADcK6m+PMWwwEr8BLu/6BdfBFP7Dnw41vQee7S610EZHyppDugEK6iIiIlKmcdPhhHETNN5/3eQm6PVo1WoLzcyBqoRnM986D/Owzx+q2M1vMWw0Gv3qlc7/VU2H+M+Dkas6oX7+a9EwQkSpHId0BhXQREREpc/YCc8b3tR+bz9vfATf9G5xdra3rUtgLIHaZOTP7zl8gJ/XMsZoRp4L5UAiKKP17GwbMugN2/QL+DeHepZfeMi8iYqGS5FDN7i4iIiJS2pycod8b5sRn856CzV9Byn4Y9hV4Blhd3cUZBhzcaE7+tmM2ZBw5c8y3ntla3vpWqNu2bHsI2Gww8EM4vN2cHf6n++G2b8HJqezuKSJiMbWki4iIiJSlvQvgh7GQmwFBTcz11QMbWV3V+R3dbXZl3/4DnIg7s9+zhjm+vPWt0LBr+YfkxL/gs75QkGMOH+g+oXzvb4XkGNj9K4R2h/pXVI3hEiLVmLq7O6CQLiIiIuXu8DZzQrm0g+AVBLfNgIZdyr8Oe4E5c3pWEmQeM2dlz0o2Z6TfOx+ObD9zrqsXNOtvdmV3tGRaednwBfw6AWzOMOZXc331qurwNvjvzXDyuPncr775s2h2E4R2A2d1hhWpbBTSHVBIFxEREUukHzaDeuIWcHaHW6ZC66GXd80Lhe7Cx0nm19OPs44DDn71c3I9tWTa0JItmVYeDAPm3AtbZ4JvXbh3OfgEW11V6Ts7oPs3NH+eeZlnjnvWgCb9oPlN5ocnrp7W1SoixaaQ7oBCuoiIiFgmNxNm32N2Ywa4+jnoOfFMV+bSDt0X4lkDvIPNVn3vmubXeu2g+c0Ve2K2nAz49BpI2gPhvWHUbHP8f1WRuBW+vBlOnjBnsh81G1zcYd8S2PUr7Jl7pnUdzN4OEddCswHQ5PrKMd+BSDWlkO6AQrqIiIhYym6HRS/AqvfN57VbQ0HuZYbuQPAOOhW6g856HHwmhHsHm/s9Ayt3d+mju+HTqyEvC3o9DVc/Y3VFpSPxL7MFPTvFDOh3zAEP/6LnFORD/GrzQ55dv0JawpljTi4Q1sNsYW92E/jWKdfyRcQxhXQHFNJFRESkQtgwDX6bCEbB3w7YTrV0nwrWXjXPehxU9UL3pfhrJsy5B7DBHbPNbt+V2aEt8OXAUwG9o/me/h7Q/84wzKETu341Q/ux3UWPN+hkhvXmA6Bm4zIqXESKSyHdAYV0ERERqTCO7TEnaysM4NU0dF+KXx6FjdPN79t9y8GvntUVXZqzA3qDTmYXd49L+B01KRp2/2KG9oMbih6r1eJUYL8J6rTRTPEiFlBId0AhXURERKQKyMuGz/uYE62FXGnO+O7sanVVJXNo86mAngoNOsOoHy8toP9d2iHY/ZvZwh63Auz5Z475NzzTJb7hlVVrTL9IBaaQ7oBCuoiIiEgVcXwffNILctKg6yNw3StWV1R8BzfBV7eYAT2kC4z8oXQC+t+dPGEur7frF4heDPknzxzzCjJn8W8+ABr1AleP0r+/iAAK6Q4ppIuIiIhUITt/hll3mI9v+xaa3WhtPcVxcCN8OQhyTgX0UT+Cu2/Z3zc3C2IWm13i9/5ufkBwmpsPRPY1W9gjryubDwxEqjGFdAcU0kVERESqmHnPwJqp5mRr9y6DGmFWV3RhCRvhq9MB/UoY9UP5BPS/K8gzu8Lv/tXsGp+eeOaYs5vZst78Jmjav2quRy9SzhTSHVBIFxEREali8nNh+o2QsB7qtYe75pvri1c0CRtOBfQ0aHgVjPzemoD+d3Y7HNpkdonf/SskR5910AZ1WptLunnVLLp5BxV97hEATk5WvQuRCk0h3QGFdBEREZEqKOUAfNLDHIPd6W7o/5bVFRV1YD18PfhUQO96KqD7WF3VuQzDXHXg9EzxiVuK/1qbk7k6QWF4Dzz19aww73120A8CN68yeysiFYlCugMK6SIiIiJVVNRC+Gao+XjoNGg1xNp6Tjuw3mxBz02H0G5w+6yKGdDPJ+WAOYN+VvKpLQmyjpuPM5NO7Ttudt+/FC6e5w/vp0P+2a31gY3Bxa10359IOSlJDtUinCIiIiJSNUT2hR6Pw/K34edHzDXBgyKtrenAOvhq8KmA3h1un1l5AjpAQIi5XUx+Lpz8e3g/z5Z5VtgvyDVnm09LMLeLqRkB4xaa4V2kClNLuoiIiIhUHQX55tJmccuhVgsYv9i6LtXxa+HrIWZAD+thBnQ3b2tqqWgMA3IzzhPeT7fWn2qhPx340w5CXha0HQGDPra6epESU3d3BxTSRURERKq49CPwcXfIPArtRsItU8u/hvg1pwJ6hgJ6aTiwHj7vCxjmknURfayuSKRESpJDNf2iiIiIiFQtvrXNMek2J9jyDWz+unzvv3/13wL6LAX0yxXSCbrcZz7+5THIybC2HpEypJAuIiIiIlVPox5w9bPm498eh8Pby+e+Zwf0Rj1PBXTNYF4qrnkO/BtCajz88arV1YiUGYV0EREREamauv8DIvpCfjbMGg3ZaWV7v/2rzICelwnhvWHETAX00uTuAwPeMR+v/djsAi9SBSmki4iIiEjV5OQEg/8Dfg3geAz88og5YVlZiFsJXw89K6B/p4BeFiKuNSePw4CfHzZnlRepYhTSRURERKTq8gqEW78AJxfYMQfWf1b694hbYa7PnpcJ4VebAd3Vs/TvI6brXzPXUj+2C1ZMsboakVKnkC4iIiIiVVtIZ+j7ivl43jNwcGPpXTt2OXxzq7k8WONrYMS3CuhlzSsQbnzTfLzsLTi6y9p6REqZQrqIiIiIVH1X3g/NB4A9D2aNgZMnLv+ascthxrBTAf1auE0Bvdy0HAxN+pk/z58fBnuB1RWJlBqFdBERERGp+mw2GPgh1Ghkzg4+536w2y/9evuWnmlBj+gDt80AV4/Sq1ccs9mg/9vg5gsJ62Hdp1ZXJFJqFNJFREREpHrw8Idh/wVnd9j7O6x679Kus28JzBgO+SfN2eOHf6OAbgX/+tD3JfPx4pchJd7aekRKiUK6iIiIiFQfddtCvzfMx4tfNpdNK4mzA3rkdTD8awV0K3UYC6HdzEn7fplQdrP3i5QjhXQRERERqV46jIE2w8EogB/ugoxjxXtdzJ+nAno2RF6vgF4RODnBgPfM3hExi2HrTKsrErlsCukiIiIiUr3YbNB/CgQ1hfREmD3+4hOPxfwB395mBvQmN8Dwr8DFvXzqFceCIqD3U+bjeU8X/0MXkQpKIV1EREREqh93Hxj2Jbh6mV3Yl7554XOjF8OM0wG9n/k6BfSKpesjUKe1OWv/vKesrkbksiiki4iIiEj1VKsZ3PSO+XjpG2Zr+d9FL4JvR0BBzqmA/l8F9IrI2RVufh9sTrD9R9gzz+qKRC6ZQrqIiIiIVF9th5tj1DHgx7sh7dCZY1GL4NvbzYDetL9a0Cu6eu3hqofMx7/9A7LTrK1H5BIppIuIiIhI9XbDG2ZX6awkcyK5gjyIWgjfnQrozW6CW6eDi5vVlcrF9H4GajSCtIOwaJLV1YhcEoV0EREREaneXD3MVnJ3P4hfDTPvKBrQh36hgF5ZuHnBze+Zjzd8XvIl9kQqAIV0EREREZHAcBj4ofl47+9QkKsW9MqqUU+4YrT5+OeHIS/b2npESkghXUREREQEoMXN5izhAM1vNgO6s6ulJckl6vsK+NSB5GhY5mDmfpEKyGYYhmF1EeUpLS0Nf39/UlNT8fPzs7ocEREREaloTuyHgIbmeupSee36BWaOAicXuGeJOe+AiEVKkkMtbUmfNGkSNputyNasWbMLnj99+vRzzvfw8CjHikVERESkyqsRqoBeFTQfYPaIsOfD/x6CgnyrKxIpFherC2jZsiWLFi0qfO7i4rgkPz8/9uzZU/jcpn9ARURERETkfG58C2KXQuIWWDMVuj1idUUiF2V5SHdxcaFOnTrFPt9ms5XofBERERERqaZ8a8N1/4KfH4I/X4PmN5mTBIpUYJZPHBcVFUW9evUIDw9n5MiRxMfHOzw/IyOD0NBQQkJCGDhwIDt27HB4fk5ODmlpaUU2ERERERGpJtqPgka9IP8k/PIoVK8puaQSsjSkd+nShenTpzNv3jw++ugjYmNj6dGjB+np6ec9v2nTpkybNo3//e9/fP3119jtdrp27UpCQsIF7/H666/j7+9fuIWEhJTV2xERERERkYrGZoMB74KLJ8Qug81fWV2RiEMVanb3lJQUQkNDmTJlCuPGjbvo+Xl5eTRv3pwRI0bwyiuvnPecnJwccnJyCp+npaUREhKi2d1FRERERKqTVe/DgufA3R8eWge+GkIr5afSzO7+dwEBATRp0oTo6Ohine/q6kr79u0dnu/u7o6fn1+RTUREREREqpku90O99pCTCnMnWl2NyAVVqJCekZFBTEwMdevWLdb5BQUFbNu2rdjni4iIiIhINeXsAjd/YK6bvusX2Pmz1RWJnJelIX3ixIksXbqUuLg4Vq1axaBBg3B2dmbEiBEAjB49mmeeeabw/JdffpkFCxawb98+Nm3axKhRo9i/fz/jx4+36i2IiIiIiEhlUacVdJtgPp47EU6esLQckfOxdAm2hIQERowYQXJyMsHBwXTv3p01a9YQHBwMQHx8PE5OZz5HOHHiBHfffTeHDx+mRo0adOjQgVWrVtGiRQur3oKIiIiIiFQmPZ+Anf+D5ChY8DwM/MDqikSKqFATx5WHkgzYFxERERGRKmj/avjiBvPx6J8hvJe19UiVV2knjhMRERERESlzoVdBp1NDZn95BHKzrK1H5CwK6XJBR9OyeX3uLm79eBUb9x+3uhwRERERkdJz7YvgVx9OxMGS16yuRqSQQrqcIy4pk2dmb6P7G3/yybJ9rI87wajP1rE86pjVpYmIiIiIlA4PP7jp3+bj1R/CwU3W1iNyikK6FNpxKJWHZmzimreX8O26eHIL7HQIrcGV4YGczCtg3PQNzNt+2OoyRURERERKR5ProdVQMOzw88NQkGd1RSKaOK66MwyDdbHH+WhpDEv2nGkpv7ppMPf3jqBzo0By8guY8N0Wft9+GGcnG28OacOQDg0srFpEREREpJRkJsEHneDkcbjmeeg50eqKpAoqSQ5VSK+mDMPgj91Hmbokho37zfUhnWzQv0097u/VmBb1in5v8gvsPD17Gz9sTADgpZtbcmfXsPIuW0RERESk9P01E+bcA87ucP9KCIq0uiKpYkqSQy1dJ13KX36BnV+3JvLRkhj2HEkHwM3ZiaEdG3Bvz3BCa3qf93Uuzk68OaQNPu4uTF8Vx4s/7yA9O48Hr47AZrOV51sQERERESldbYbBtu8heqHZ7X3MXHDSyGCxhkJ6NZGdV8D3Gw7wybJ9JJw4CYC3mzOjrgxlXPdG1PLzuOg1nJxsvDigBX6erry3OIq3FuwlPTufp/s1U1AXERERkcrLZoObpsCHV0L8atg47cwSbSLlTCG9ikvLzuPrNfuZtiKOpIwcAAK93birWxh3XBmGv5dria5ns9n4R98m+Hm48Opvu/hk2T7Sc/J5ZWArnJ0U1EVERESkkgpoCH1ehN+fhIWToEk/8K9vdVVSDSmkV1HH0nOYtjKWr1fvJz0nH4D6AZ7c0zOcYR1D8HRzvqzrj+8Rjo+7C8/M2caMtfFkZOfz9rC2uDqrW5CIiIiIVFKdxsO2HyBhHfz2DxjxndnKLlKOFNKrmAPHs/hkWQyzNiSQm28HILKWD/f1aszN7eqVaoi+rXNDvN1deGzmFn7+6xAZOflMHXkFHq6X9wGAiIiIiIglnJzh5vfg4x6wdx5s/xFaD7W6KqlmNLt7FbH7cBofL4nhl62JFNjNH2m7kAAe6N2YPs1r41SGXdH/2H2E+7/eRE6+nSvDA/nszk74uOvzHxERERGppJb8Hyx5HbyC4KH14BVodUVSyWkJNgeqWkjfuP84U/+MYfHuo4X7ekQG8UDvCK4MDyy3Cd3W7Etm/H83kJGTT9sG/kwf25ka3m7lcm8RERERkVKVnwuf9IRju6DNbTD4E6srkkpOId2BqhDSDcNgyd5jfPRnDOvijgPmUJl+repwf68IWjfwt6SurQkpjJ62jpSsPJrW9uWrcZ2LNWu8iIiIiEiFc2A9fN4XMGDkjxDZx+qKpBJTSHegMof0ArvBb9vMNc53JaYB4OpsY3D7BtzbK5zwYB+LK4S9R9IZ9dlajqbn0DDQi2/GdyEk0MvqskRERERESu73p2HtR+AfAg+sAXfrf9+WyqnMQ/qBAwew2Ww0aNAAgHXr1jFjxgxatGjBPffcc2lVl5PKGNKz8wqYvekgnyyLYX9yFgBebs7c3rkh43uEU8e/YrVWxydnMfLzNRw4fpI6fh58Pb4zEbV8rS5LRERERKRkcjJg6lWQGg9d7oN+b1hdkVRSZR7Se/TowT333MMdd9zB4cOHadq0KS1btiQqKoqHH36YF1544ZKLL2uVKaRn5OTzzZr9fL4ilqPp5hrnNbxcGdO1EaOvCq3QY74Pp2Zzx+driTqaQaC3G1/e1ZlW9a3phi8iIiIicsmiF8PXgwEbjFsAIZ2trkgqoZLk0Etaj2v79u107mz+4Zw1axatWrVi1apVfPPNN0yfPv1SLil/M21FLF1fX8zrv+/maHoOdf09eP6mFqx8+hoe7RNZoQM6QB1/D2beexWt6/tzPDOXEf9Zw7rY41aXJSIiIiJSMhHXQtsRgAE/Pwz5OVZXJFXcJYX0vLw83N3dAVi0aBE333wzAM2aNSMxMbH0qqvGDCAtO5/wYG/eHNqGpU9czbjujfByqzxLmwV6uzHj7i50bhRIek4+o6etZcmeoxd/oYiIiIhIRXL9a+ZybMd2w4/jYMMXELcC0o9A9ZriS8rBJXV379KlC1dffTX9+/fnuuuuY82aNbRt25Y1a9YwdOhQEhISyqLWUlFZurtn5uSzPOoYfVvUwbkM1zgvDydzC7j/m40s2XMMV2cb797Wnhtb17W6LBERERGR4ts+G34Ye+5+dz+o2RhqRkJQJNSMOLO5aQJlMZX5mPQlS5YwaNAg0tLSuPPOO5k2bRoA//znP9m9ezezZ8++tMrLQWUJ6VVNbr6dx2Zt4betiTjZ4P+GtGFYxxCryxIRERERKb4982DfEkiOgqQoSInH7AN7AX4NICjCDPA1I8489g8Bp0vq1CyVVLkswVZQUEBaWho1atQo3BcXF4eXlxe1atW6lEuWC4V06xTYDZ6ds43v1h8A4IWbWnBX90YWVyUiIiIiconysuFErBnYk6MgKRqSo83HJ09c+HUuHhAYfiq4R57VCt8YPGtc+HVSaZV5SD958iSGYeDlZXbf2L9/P3PmzKF58+Zcf/31l1Z1OVFIt5ZhGPzrt118tiIWgAl9Inn02khstsrdpV9EREREpIjMZDOsJ0efCvGnvh7fB/a8C7/OK+hMt/nC7vORUCMMXCr25NFyYWUe0q+77joGDx7MfffdR0pKCs2aNcPV1ZWkpCSmTJnC/ffff8nFlzWFdOsZhsF7i6P596K9AIzr3ojn+jdXUBcRERGRqq8g31x3PSn63BCf7mASbpuzGdSDIiGwMbh6glEAht3c7PYzj4vsLzAntztnn/3crcj+06873/5Tj51cocVA6DQO3H3L7VtYGZV5SA8KCmLp0qW0bNmSzz77jPfff5/Nmzfz448/8sILL7Br165LLr6sKaRXHNNWxPLyrzsBGN4xhNcGt670k+SJiIiIiFyynHRIjjkruJ8O8dGQl2l1dRfmEQBd7oMu94JXoNXVVEglyaGXtJ5XVlYWvr7mJyULFixg8ODBODk5ceWVV7J///5LuaRUQ3d1b4SPhwtP/7iVmRsOkJGbz7+HtcPNRZNoiIiIiEg15O4L9dqZ29kMw2xlP93ifnwf2PPN1nWbDWxO4ORsfi3cTj+3/e3YWY+dznf+2deyXWD/qS31AKx636xp6f/B6g+g41i46iHwrWPFd7BKuKSQHhERwU8//cSgQYOYP38+jz32GABHjx5V67SUyLCOIfi4u/Dod5v5bWsimTn5fDSyA55uzlaXJiIiIiJSMdhs4FfP3MJ7WV1NUe3vgF0/w7K34cg2M7Sv/Q9ccQd0fQRqhFpdYaVzSU2WL7zwAhMnTiQsLIzOnTtz1VVXAWarevv27Uu1QKn6bmxdl09Hd8TD1Ykle45x57R1pGc7mExDREREREQqBidnaDkI7lsOt8+CBp2hIAfWfwbvXwFz7odje62uslK55CXYDh8+TGJiIm3btsXp1Bp/69atw8/Pj2bNmpVqkaVJY9IrrvVxx7nri/Wk5+TTur4//72rM4HemsFSRERERKTSMAyIWwHL3zLXlAfABi1uhh6PQ922VlZnmXJZJ/20hIQEABo0aHA5lyk3CukV2/aDqYyeto7jmblE1vLhq3FdqOPvYXVZIiIiIiJSUgkbYfnbsOe3M/sir4MeE6FhF+vqskBJcugldXe32+28/PLL+Pv7ExoaSmhoKAEBAbzyyivY7fZLKloEoFV9f2bdeyV1/DyIOprBrZ+sIj45y+qyRERERESkpBp0gBEz4P5V0GqoOdlc1AKYdh180R9i/jBb3qWIS2pJf+aZZ/j888956aWX6NatGwArVqxg0qRJ3H333fzrX/8q9UJLi1rSK4cDx7MY9fla9idnUcvXna/Hd6FJba29KCIiIiJSaSXHwMp3YMu3YD81B1W9K6DnRGjSz5xtvooq8+7u9erV4+OPP+bmm28usv9///sfDzzwAAcPHizpJcuNQnrlcTQtmzs+X8eeI+kEeLny37GdaRsSYHVZIiIiIiJyOVITYNUHsHE65J8099VqAd3/YU5C53xJi5BVaGXe3f348ePnnRyuWbNmHD9+/FIuKXKOWn4ezLz3StqGBJCSlcdt/1nD67/v4mhattWliYiIiIjIpfJvAP3+DyZsM4O5ux8c3Qmzx8MHHU+F9xyrq7TMJbWkd+nShS5duvDee+8V2f/www+zbt061q5dW2oFlja1pFc+GTn53PfVRlZEJwHg5uLE0A4NuK9nYxrW9LK4OhERERERuSwnU2D9p7B6Kpw81ejrWw+6PQJXjAY3b0vLKw1l3t196dKl9O/fn4YNGxaukb569WoOHDjA3Llz6dGjx6VVXg4U0isnu93gj91Hmbokmk3xKQA42eCmNvW4v3djmtfVz1JEREREpFLLzTRb0Ve9D+mJ5j6vmnDlA9D5bvDwt7S8y1EuS7AdOnSIDz/8kN27dwPQvHlz7rnnHl599VX+85//XMoly4VCeuVmGAZrY48zdUkMy/YeK9x/TbNaPNC7MR3DAi2sTkRERERELlt+DmyZYU4ydyLO3OfuZwb1Kx8A7yArq7sk5bpO+tn++usvrrjiCgoKCkrrkqVOIb3q2H4wlY+WxDB3e2Lhyg2dwmrwQO8IejcNxmazWVugiIiIiIhcuoJ82DHbXGv9mNk4jKsXdBgDVz0E/vUtLa8kFNIdUEivemKTMvlkaQw/bkogr8D849y8rh/3925M/9Z1cXZSWBcRERERqbTsdtjzGyx7CxK3mPucXKHd7dB9AgSGW1ldsSikO6CQXnUdTs3ms+X7mLEunqxc889gaE0v7u3ZmMFX1MfD1dniCkVERERE5JIZBsT8Ybas719p7rM5Qauh0OdFc9b4Ckoh3QGF9KrvRGYuX67ez/RVsZzIygOglq8747o3YuSVofi4V711F0VEREREqpX9q82wHr0QXDzM5dx8alld1QWVWUgfPHiww+MpKSksXbpUIV0qhKzcfL5dd4DPlu8jMdVcW93Pw4U7u4YxpmsYNX3cLa5QREREREQuy6EtcGQ7tB9ldSUOlVlIHzt2bLHO++KLL4p7yXKnkF795Obb+WnLQT5eGsO+Y5kAeLg6cVunhtzdM5z6AZ4WVygiIiIiIlWZZd3dKwOF9OqrwG6wYMdhpi6JYdvBVABcnGwMbFef+3uHE1HL1+IKRURERESkKlJId0AhXQzDYEV0Eh8tiWFVTDIANhtc16I2D/SOoG1IgLUFioiIiIhIlaKQ7oBCupxtc/wJPloSw4KdRwr3dYuoyf29IugWUVNrrYuIiIiIyGVTSHdAIV3OJ+pIOh8tjeHnLYfIt5t/Jdo28Of+3o25rkUdnLTWuoiIiIiIXCKFdAcU0sWRhBNZfLY8lu/Wx5OdZwegcbA39/VqzMB29XFzcbK4QhERERERqWwU0h1QSJfiSM7I4YuVcfx3dRzp2fkA1PP3YHyPcG7rHIKXm9ZaFxERERGR4lFId0AhXUoiPTuPGWvj+WxFLMfScwCo6e3G/b0bM+rKUDxcnS2uUEREREREKjqFdAcU0uVSZOcV8OOmBD5Zuo/441kA1PHz4KFrIhjWMUTd4EVERERE5IIU0h1QSJfLkVdgZ/amBN5bHM3BlJMANKjhyaPXRjKofX1cnBXWRURERESkKIV0BxTSpTTk5Bfw3boDfPBndGE3+PBgbx7r04T+retqNngRERERESmkkO6AQrqUppO5BXy1Jo6PlsRwIisPgGZ1fHn8uqb0aV5L66yLiIiIiEiJcqilfXMnTZqEzWYrsjVr1qxYr/3uu++w2WzccsstZVukiAOebs7c07Mxy5+6hn/0bYKvuwu7D6dz95cbuGXqKpZHHaOafQ5WbaVk5bJ2XzIFdv28RUREROTSWb6OVMuWLVm0aFHhcxeXi5cUFxfHxIkT6dGjR1mWJlJsPu4uPHJtJKOvCuU/y/bxxco4/jqQwh2fr6Nzo0AmXteUzo0CrS5TysCRtGw+W76Pb9bGk5VbQNfGNfn38HbU9vOwujQRERERqYQsn+XKxcWFOnXqFG5BQUEOzy8oKGDkyJG89NJLhIeHl1OVIsUT4OXGkzc0Y/lTVzOueyPcXJxYF3ucYZ+sZvS0dfx1IMXqEqWU7E/O5JnZ2+jxxp98ujyWrNwCbDZYFZPMDe8sY9HOI1aXKCIiIiKVkOUhPSoqinr16hEeHs7IkSOJj493eP7LL79MrVq1GDduXLGun5OTQ1paWpFNpKwF+bjz/E0tWPpEb0Z2aYiLk41le48x8MOV3P3lBnYl6s9hZbUrMY2Hv93M1W8t4dt18eQW2OkUVoMvxnRi4WO9aFnPjxNZeYz/cgOTft5Bdl6B1SWLiIiISCVi6cRxv//+OxkZGTRt2pTExEReeuklDh48yPbt2/H19T3n/BUrVnDbbbexZcsWgoKCGDNmDCkpKfz0008XvMekSZN46aWXztmvieOkPMUnZ/Hu4ijmbE7AboDNBje1qceEPpE0Dvaxujwphg1xx5m6JIY/dh8t3Ne7aTAP9I4oMpQhJ7+AN+ft4fMVsYA5keAHt7cnota5/6aJiIiISPVQaWd3T0lJITQ0lClTppzTUp6enk6bNm2YOnUq/fr1AyhWSM/JySEnJ6fweVpaGiEhIQrpYonooxm8s2gvv25NBMDJBkOuaMAj10YSEuhlcXXyd4ZhsHTvMab+GcO6uOOA+QHLja3rcn+vxrSq73/B1/655ygTZ/1FcmYuHq5OvDigJbd1CtGM/yIiIiLVUKUN6QCdOnWiT58+vP7660X2b9myhfbt2+Ps7Fy4z263A+Dk5MSePXto3LjxRa+vJdikIth5KI0pC/eyaJc5btnV2cbwTiE8fE2kJhyrAArsBr9vT+SjJTHsOGQOTXB1tjHkigbc26sxjYK8i3Wdo+nZPD7rL5ZHJQFwY+s6vD6oDf5ermVWu4iIiIhUPJU2pGdkZNCwYUMmTZrEI488UuRYdnY20dHRRfY999xzpKen8+6779KkSRPc3Nwueg+FdKlIthxI4e0FewpDnLuLE3dcGcr9vRtT08fd4uouLCs3n/jjWRw8cZKGgV5E1PKpEi3Eufl25mxO4OOl+4hNygTA09WZ27s0ZHyPRtT19yzxNe12g0+X72Py/D3k2w3qB3jy7m3t6Bim2f5FREREqotKE9InTpzIgAEDCA0N5dChQ7z44ots2bKFnTt3EhwczOjRo6lfv/45reqnFae7+98ppEtFtGZfMm8v2MP6uBMAeLk5c1e3RtzdI9yyVtf07Dz2J2exPzmLuORM9idnEpecxf7kTI6k5RQ5t7afO90igugRGUS3xkHUqmS9AbJy85mxNp7PlsdyOC0bAH9PV8Z0DWNM1zBqeF/8A8CL+etACo98t5n9yVk42WBCnyY8eHUEzk6V/8MNEREREXGsJDnU0nXSExISGDFiBMnJyQQHB9O9e3fWrFlDcHAwAPHx8Tg5WT4BvUiZuzK8JrPuvYplUUm8vWAPWxNS+eDPaP67Oo57eoQztnsjfNxL/69ralYe+49nEpuUeVYYN4N4Ukauw9cGeLlS19+TfccyOJKWw+xNB5m96SAATWr70D0imO6RNenSqCbeZVB7aUjJyuW/q/YzfVUsJ7LyAKjl687dPcIZ0aVhqX7P24YE8NsjPXjhp+3M3nyQKQv3siI6iXeGt6NeQMlb6EVERESkaqpQ3d3Lg1rSpaIzDIMFO48wZcFe9hxJByDQ2437ezXmjqtC8XB1vsgVil7rRFbemZbwpKwiLeKng+mFBPm4EVrTm9CaXoT97WuAl9m6nJ1XwMb9J1gRncSKqCS2H0rl7H9VXJxsXNGwBt0jg+gWEUTbBv64OFv74dvRtGw+WxHLN2v2k5lrLpEWWtOL+3o1ZvAV9XF3Kf73+FLM2ZzAc3O2k5lbgL+nK28MacMNreqU6T1FRERExDqVpru7FRTSpbKw2w1+3ZbIOwv3su/U+Ohavu48fE0Ewzs1xM3FDLqGYZCUkUtcciZxf2sRj0vOJD073+F9avm6nwngQUWDuK9Hybvan8jMZVVMshnao49x4PjJIsd93V24snFNs2t8RBDhQd7lNp59f3ImHy/dx48bE8gtMCeebFbHlweujuDGVnXK9cODuKRMHvluM1sTUgEYdWVDnuvfokQfwoiIiIhI5aCQ7oBCulQ2+QV2Zm8+yLuLojiYYgbe+gGetGngX9g1/XRr8IXU8/cgtKY3YUFe5tea5teGgV5l3hU9PjmrMLCvjE4m9WTR1vt6/h50iwgqbGkPKoMJ83YlpvHRkhh+3XoI+6l/8TqG1uCBqxtzddNalk16l5tv5+2Fe/hk6T7AHCbw/ograFpHa6qLiIiIVCUK6Q4opEtllZtvZ+b6eN7/I5qj6UUnbnOyQb0Az3O6pIcFmUG8orTOFtgNdhxKLewavyHuRGGL9mnN6vgWtrJ3aVQTT7dLr33j/uNM/TOGxbuPFu7r1SSYB6+OoHOjijO7+rK9x/jHrL9IysjB3cWJ525qwaguDavEjPkiIiIiopDukEK6VHbZeQX8b8tBMnIKaHSqZbxBDc8yH0ddFk7mFrA+7jgro5NYHpXEzsS0IsfdnJ24IjSAHpHBdIsIonV9/4vOhm4YBsuikvjwz2jWxR4HwGaDG1vX5f5ejWlV37/M3s/lSMrIYeL3f7FkzzEArmtRmzeGtCmVmeVFRERExFoK6Q4opItUXMkZOeZ49qgkVkQnFXbvP83Pw4Wujc2u8d0jggit6VXY2lxgN5i3/TBTl0Sz45AZ9l2dbQxu34B7e4UTHuxT7u+npOx2gy9WxfF/v+8ir8Cgrr8H/x7ejivDa1pdmoiIiIhcBoV0BxTSRSoHwzCIOz2ePeoYq2KSz5kEr36AJz0igwgP9ua7dQcKJ9jzdHXm9i4NGd+jEXX9K9/yZtsPpvLIt5vZl5SJkw0eujqCR66NtHxWfBERERG5NArpDiiki1RO+QV2th1MLewavyn+BHkFRf/58vd05c6uYYzpGkZgJe8mnpmTz6Sfd/D9xgQAOoTW4N3b2tGghpfFlYmIiIhISSmkO6CQLlI1ZOXmsy72OCuikthzJJ0ekUHc3iUUnzKerb68/fzXIZ6dvY30nHx8PVz4v8Ft6N+mrtVliYiIiEgJKKQ7oJAuIpXNgeNZPPLdZjbHpwBwW6cQXhjQAi+3qvWBhIiIiEhVVZIcqgGOIiIVXEigF7PuvYoHr26MzQbfrT/AgPdXsPNQ2sVfLCIiIiKVilrSRUQqkVXRSTw2awtH0nJwc3binzc2486uYZasqW4YBmkn80lIyeLgiZMcTDnJwRMnOZRqfg329eDBqxvTvmGNcq9NREREpCJRd3cHFNJFpLI7npnLkz/8xaJdRwG4tlkt3hzahpo+7qV6H7vd4FhGDglnBfCDZwXyQynZZOTkX/Q6fVvUZuJ1TWlax7dU6xMRERGpLBTSHVBIF5GqwDAMvly9n3/N3UVuvp1avu68M7wdXSOCin2NnPwCElOyzQBeGMLPfE1MPXnODPrnU9PbjXoBntQP8KR+DfNrXX8P/th9lB83JWA3wGaDW9rVZ0KfSEJrel/OW690svMKWB6VRJCPG63r+2spPRERkWpIId0BhXQRqUp2Jabx8LebiT6agc0G9/dqzGN9m+Dq7ER6dt55w/fpx8cycrjY/wDOTjbq+HkUBvB6AR7UD/AqDOP1AzzxdHO+4Oujj2YwZeEe5m47DICLk43hnUJ4+JpI6vh7lOa3osJJysjhq9X7+WrNfo5n5gLg6+FC18Y16R4RRPfIYMJqelkyVEFERETKl0K6AwrpIlLVnMwt4OVfd/LtungAavu5czK3gLTsi3dF93B1KmwFb1DjTGt4PX/zax0/j1Jp+d2WkMpbC/awdO8xANxdnLizaxj39Wpc6de0/7uYYxl8tjyWHzclkJtvB6CuvweZOfnn/EzqB3jSPSKIbpFBdGtcs9SHLIiIiEjFoJDugEK6iFRVc7cl8vSPW4sEwQAv18IW73p/C+L1AzwJ9HYr15bctfuSmTx/Dxv2nwDAx92F8T0aMb5HeKVe494wDNbGHuez5fsK5woAaNvAn3t6Nub6lrWx2WxsO5jKyugklkcdY+P+E+cMJ2hR14/ukUF0jwiiU1igw14KIiIiUnkopDugkC4iVVlyRg47E9Oo7edBvQDPChl8DcNgyd5jTJ63h52J5jJygd5uPNC7MaOuDMXDtfIE0/wCO79vP8yny/exNSEVMMff92lem7t7hNMprMYFPwTJys1nXezxU6E9id2H04scd3N2omNYDbpFBNEjMoiW9fxxdlLXeBERkcpIId0BhXQRkYrBbjf4ffth3l64h33HMgGo4+fBI9dGcmvHBrhW4AnWMnLymbn+ANNWxHIw5SRgduEf2qEB47o3IjzYp8TXPJaew6qYJFZEJbEiOonE1OwixwO8XOnauCbdIsyW9uo2AZ+IiEhlppDugEK6iEjFkl9gZ/amg7yzaC+HTgXT0Jpe/KNvEwa0qYdTBWo9PpyazRerYpmxNp70U8MKanq7ccdVodxxZWipjSk3DIN9SZmFrexrYpJJ/9tydyGB5nj27hHBdG1ckxpVbGy/iIhIVaKQ7oBCuohIxZSTX8CMtfF8+Gc0SRnmbOjN6vgy8bqmXNu8lqWzoO88lMZny/fx81+HyLeb/22GB3szvns4g6+oX+Zd9PML7Gw9mFrYyr5p/4nCOsDsYt+qnn9h1/gOoTUq1bABERGRqk4h3QGFdBGRii0zJ5/pq+L4eGlMYWt1+4YBPHF9U7o2Lv468JfLMAyWRSXx2fJ9LI9KKtzfpVEgd/cI55pmtSxr5c/MMcezL49KYmV0EnuOFB3P7u7iROdGgYVd41vU9atQPRJERESqG4V0BxTSRUQqh5SsXD5Zto8vVsaSnWcuZdY9IoiJ1zelXUhAmd03J7+An7cc4vMVsYWTuTk72ejXqg539winbRne+1IdTctmZUwSK6KSWRF9jCNpOUWO1/BypWtEEL0igxl0Rf0KPd5fRESkKlJId0AhXUSkcjmans2Hf0QzY1184ZJl17WozePXNaVpHd9Su09qVh7frNvP9JVxHE03Q663mzPDOzVkbLcwQgK9Su1eZckwDGKOZRS2sq+OSSYzt6Dw+M1t6/HeiPYWVigiIlL9KKQ7oJAuIlI5HTiexbuLo5i9KQG7YY7DHtSuPhP6NKFhzUsP0AeOZ/H5ilhmbThA1qkwW9vPnbHdGjGic0P8PV1L6y1YIq/Azl8HUli29xgfLomhwG4wdeQV3Ni6rtWliYiIVBsK6Q4opIuIVG7RR9OZsnAvc7cdBsDFycZtnUN4+JpIavt5FPs6m+NP8NnyWH7fnsjpOdia1fHlnp7h3NSmHm4uVa9L+NsL9vD+H9EEerux4LGeBJXSbPQiIiLimEK6AwrpIiJVw7aEVCYv2MOyvccAc7K0MV3DuK9X4wsuR2a3GyzadYRPl+9jfdyJwv09mwRzT49wukXUtHQW+bKWm2/n5g9WsPtwOv1a1WHqyCuq9PsVERGpKBTSHVBIFxGpWtbsS+at+XvYsN8M3b7uLozvEc64Ho3wcXcB4GRuAT9uSuDzFbHEJmUC4OpsY2C7+ozv0YhmdarP/wc7DqUy8IOV5NsN3hvRnpvb1rO6JBERkSpPId0BhXQRkarHMAyW7DnG5Pl72JmYBkCgtxv392pMek4+X6/Zz/FMc+11Pw8XRl0Zyp1dw0rUPb4qeXdRFP9etJcAL1cWPNaTWr7V8/sgIiJSXhTSHVBIFxGpuux2g7nbE5myYC/7TrWYnxYS6Mm4bo24tWMI3qda2KurvAI7t3y4kh2H0ujbojb/uaODur2LiIiUIYV0BxTSRUSqvvwCO7M3HWTaylh8PVwY07UR17esjYvWBy+0+3AaA95fQV6Bwb+Ht2VQ+wZWlyQiIlJlKaQ7oJAuIiJi+vDPaCbP34OfhwsLHutFHX91excRESkLJcmhalIQERGppu7tGU7bBv6kZefzzOytVLPP7UVERCokhXQREZFqysXZibdubYubixN/7jnG9xsTrC5JRESk2lNIFxERqcYia/vyeN8mALzyy04OpZy0uCIREZHqTSFdRESkmhvfI5wrGgaQnpPPUz+q27uIiIiVFNJFRESqOWcnG2/d2hZ3FyeWRyXx7boDVpckIiJSbSmki4iICOHBPjx5QzMA/vXbTg4cz7K4IhERkepJIV1EREQAGNs1jM5hgWTmFvDkD1ux29XtXUREpLwppIuIiAgATk42Jt/aBk9XZ1bvS+brtfutLklERKTaUUgXERGRQqE1vXnmRrPb++tzd7M/OdPiikRERKoXhXQREREpYlSXUK4Kr8nJvAKe+F7d3kVERMqTQrqIiIgU4eRk482hbfB2c2Zd3HG+WBVndUkiIiLVhkK6iIiInCMk0Itn+7cA4M15u9l3LMPiikRERKoHhXQRERE5rxGdQ+gRGUROvp2J3/9Fgbq9i4iIlDmFdBERETkvm83GG0Pa4Ovuwqb4FD5fsc/qkkRERKo8hXQRERG5oHoBnjx/k9nt/a0Fe4k6km5xRSIiIlWbQrqIiIg4dGvHBlzdNJjcU93e8wvsVpckIiJSZSmki4iIiEM2m43XB7fBz8OFvxJS+WSZur2LiIiUFYV0ERERuag6/h5MurklAO8s2svuw2kWVyQiIlI1KaSLiIhIsQxqX58+zWuTV2Dw+Ky/yFO3dxERkVKnkC4iIiLFYrPZeG1wKwK8XNlxKI2pf8ZYXZKIiEiVo5AuIiIixVbL14OXB7YC4P0/othxKNXiikRERKoWhXQREREpkQFt6tKvVR3y7Wa399x8dXsXEREpLZaG9EmTJmGz2YpszZo1u+D5s2fPpmPHjgQEBODt7U27du346quvyrFiERERsdlsvHJLKwK93dh9OJ33/4iyuiQREZEqw/KW9JYtW5KYmFi4rVix4oLnBgYG8uyzz7J69Wq2bt3K2LFjGTt2LPPnzy/HikVERCTIx51/3WJ2e5+6JIatCSnWFiQiIlJFWB7SXVxcqFOnTuEWFBR0wXN79+7NoEGDaN68OY0bN+bRRx+lTZs2DoO9iIiIlI1+resyoG09Ck51e8/JL7C6JBERkUrP8pAeFRVFvXr1CA8PZ+TIkcTHxxfrdYZhsHjxYvbs2UPPnj0veF5OTg5paWlFNhERESkdL9/ckiAfd6KOZvDvher2LiIicrksDeldunRh+vTpzJs3j48++ojY2Fh69OhBenr6BV+TmpqKj48Pbm5u9O/fn/fff5++ffte8PzXX38df3//wi0kJKQs3oqIiEi1VMPbjdcGmd3e/7Mshk3xJyyuSEREpHKzGYZhWF3EaSkpKYSGhjJlyhTGjRt33nPsdjv79u0jIyODxYsX88orr/DTTz/Ru3fv856fk5NDTk5O4fO0tDRCQkJITU3Fz8+vLN6GiIhItfOPmVuYvfkg4cHezH2kBx6uzlaXJCIiUmGkpaXh7+9frBzqUk41FUtAQABNmjQhOjr6guc4OTkREREBQLt27di1axevv/76BUO6u7s77u7uZVGuiIiInPLigJasiE5i37FM3l6wh2f7t7C6JBERkUrJ8jHpZ8vIyCAmJoa6desW+zV2u71IS7mIiIiUP38vV/5vSGsAPlsRy/q44xZXJCIiUjlZGtInTpzI0qVLiYuLY9WqVQwaNAhnZ2dGjBgBwOjRo3nmmWcKz3/99ddZuHAh+/btY9euXbz99tt89dVXjBo1yqq3ICIiIqdc06w2t3ZogGHAE9//RVZuvtUliYiIVDqWdndPSEhgxIgRJCcnExwcTPfu3VmzZg3BwcEAxMfH4+R05nOEzMxMHnjgARISEvD09KRZs2Z8/fXXDB8+3Kq3ICIiImd5fkALVkQnEZecxZvz9jDp5pZWlyQiIlKpVKiJ48pDSQbsi4iISMkt23uM0dPWAfDt3VdyVeOaFlckIiJirZLk0Ao1Jl1EREQqv55NghnRuSEAT/zwF5k56vYuIiJSXArpIiIiUuqe7d+c+gGeJJw4yeu/77K6HBERkUpDIV1ERERKnY+7C5OHtgHg6zXxrIhKsrgiERGRykEhXURERMpE14ggRl8VCsBTP24lPTvP4opEREQqPoV0ERERKTNP3dCMhoFeHEw5yb9+U7d3ERGRi1FIFxERkTLjfarbu80G360/wJI9R60uSUREpEKzdJ10ERERqfq6hNdkbNdGTFsZy9M/bmP+Yz3x93S97Ova7QaZuflk5hSQkZNPRk4+mWd9NR8XkJGTV3jO2ceDfd15rn8LQgK9SuFdioiIlA6FdBERESlzT1zflD/3HCU2KZOXft7BY32bFAnNGWeF6szz7jfDeGZOPumn9mXlFlx2Xetij/Ph7VfQNSKoFN6liIjI5bMZhmFYXUR5Kski8iIiIlJ6Nu4/ztCPV1Pav3k4O9nwcXfBx90Fb3dnvE8/dnPBx+P8+z3dnPloSQzbDqbi7GTj+f7NubNrGDabrXSLExERoWQ5VCFdREREys27i6J4d/Fe3Fyc8HF3xedUeC4M0O4u+Lg7n/XY5azjzvi4u+L9t+PuLk6XFK6z8wp4ZvY25mw+CMCtHRrw6qBWuLs4l/bbFhGRak4h3QGFdBEREWsZhlFhWqwNw+Cz5bG8/vsu7Aa0bxjAJ6M6UMvPw+rSRESkCilJDtXs7iIiIlKuKkpAB7OWu3uGM31sZ/w8XNgcn8KAD1awOf6E1aWJiEg1pZAuIiIi1V7PJsH8/FB3Imv5cCQth+GfrOH7DQesLktERKohhXQRERERICzImzkPdqNvi9rkFth54oetvPTLDvIL7FaXJiIi1YhCuoiIiMgpPu4ufDKqA49cGwnAFyvjuPOLdZzIzLW4MhERqS4U0kVERETO4uRk4x99m/DxqCvwcnNmZXQyN3+4gt2H06wuTUREqgGFdBEREZHzuKFVXWY/0JWQQE8OHD/J4KmrmLc90eqyRESkilNIFxEREbmAZnX8+PnB7nSLqElWbgH3fb2JKQv2YLdXqxVsRUSkHCmki4iIiDhQw9uN/47tzF3dGgHw3h/R3PPVRtKz8yyuTEREqiKFdBEREZGLcHF24oUBLXjr1ra4uTixaNcRBk9dRVxSptWliYhIFaOQLiIiIlJMQzs0YOY9V1LL152ooxnc/MEKlu49ZnVZIiJShSiki4iIiJRA+4Y1+OXh7rRvGEBadj5jv1jHp8v2YRgap14VFNgNEk5kUaB5B0TEIgrpIiIiIiVU28+D7+65kmEdG2A34F9zd/GPWX+RnVdgdWlyiVJP5vHZ8n1c/dYSur/xJze8s4x52w/rwxcRKXc2o5r9y5OWloa/vz+pqan4+flZXY6IiIhUYoZh8OXq/bz8604K7Aat6/vzyR0dqBfgaXVpUkwxxzL476o4ftiYQFbuuR+ytGngzxPXN6V7RBA2m82CCkWkKihJDlVIFxEREblMq6KTeHDGJk5k5RHk48bHozrQMSzQ6rLkAux2g6VRx5i+Mq7InAJNavswtlsjrmlWi6/X7OfzFbGFwf3K8ECeuL4ZHUJrWFW2iFRiCukOKKSLiIhIWThwPIu7v9zA7sPpuDrbeHlgK0Z0bmh1WXKWjJx8ftyYwH9XxbHv1Mz8Nhtc26w2d3UL46rGNYu0lh9Lz2Hqkmi+WRNPboEdgD7Na/H4dU1pXle/R4pI8SmkO6CQLiIiImUlKzefid//xdxthwG448pQXhjQAldnTQNkpf3Jmfx31X6+33CA9Jx8AHw9XBjeMYTRV4XRsKaXw9cfTDnJe4ui+H7jAeyGGewHtKnHY32b0CjIuzzegohUcgrpDiiki4iISFkyDIMP/4zm7YV7MQzo3CiQqSOvIMjH3erSqhXDMFgZncwXK2P5Y89RTv/GGx7szdiuYQy+ogHe7i4lumbMsQymLNzLb1sTAXB2sjGsYwiPXBtBXX/NQyAiF6aQ7oBCuoiIiJSHRTuPMGHmFjJy8qkf4Mknd3SgVX1/q8uq8rJy85mz+SDTV8YRdTSjcH/vpsGM7daIHhFBODld3gRw2w+m8vaCPfy5xxzP7ubixOgrQ3ng6ggCvd0u69oiUjUppDugkC4iIiLlJfpoOnd/uZHYpEw8XJ14c2hbbm5bz+qyqqSEE1l8tXo/366LJy3b7NLu7ebM0A4NuLNrGOHBPqV+z/Vxx5k8bw/r4o4X3m98j3DG92iEr4drqd9PRCovhXQHFNJFRESkPKWezOORbzcXziJ+f+/GTLyuKc6X2ZorZpf2tbHHmb4yjgU7D2M/9Vttw0Av7uwaxq0dG+BXxmHZMAyW7j3G5Pl72HEoDYAAL1ce6N2Y0VeF4eHqXKb3F5HKQSHdAYV0ERERKW8FdoM35+/mk6X7ALPr9bu3tcffU62tlyI7r4Cftxzii1Vx7EpMK9zfPSKIsd3C6N20Vrl/CGK3G8zbcZi3Fuxh3zFz5vjafu48cm0kwzqGaPJAkWpOId0BhXQRERGxyv+2HOTJH7aSk28nPMib/4zuSESt0u+GXVUlpp7k6zX7mbE2nhNZeQB4uDox+IoGjO0aRmRtX4srhPwCO7M3H+TdRVEcTDkJmC37/+jbhAFt66kHhUg1pZDugEK6iIiIWGlbQir3frWBQ6nZ+Lq78O6IdlzTrLbVZVVYhmGwKf4E01bGMW/7YQpO9WmvH+DJnV1DGdYxhACvijdZW05+Ad+ujeeDP6NJysgFoGltXyZe35Q+zWsVWY9dRKo+hXQHFNJFRETEakkZOdz/9UbWx53AZoNHr43kkWsiL3vW8aokJ7+A37Ym8sXKOLYdTC3c36VRIGO7NaJP81q4VIIu5Jk5+UxfFcfHS2NIPzWhXbuQAJ68vildI4Isrk5EyotCugMK6SIiIlIR5ObbefnXHXy9Jh6Aa5rV4t/D2uHvVb3HqR9Nz+abNfF8szaepIwcwFzi7JZ29RjTtREt6lXO399Ss/L4ZFkMX6yM42ReAQDdImoy8bqmtG9Yw+LqRKSsKaQ7oJAuIiIiFcn3Gw7w3E/bycm30zDQi0/u6EDzutXvd5Qjadm88ftuftl6iLwC89fTOn4e3HFVKCM6N6wy648fTc/mwz+imbEuvvB9XteiNo9f15SmdawfUy8iZUMh3QGFdBEREaloth9M5b6vN5Jw4iQerk783+A23NK+vtVllZt52xN5Zva2wsngOoTWYEzXMG5oVafKzop+4HgW7y6OYvamBOwG2GxwS7v6PNanCQ1relldnoiUMoV0BxTSRUREpCI6kZnLozO3sOzUeupjuobxzxub4+ZSNUMqQEZOPi//soNZGxIAaFXfj1dvaU27kABrCytH0UfTeXvBXn7ffhgAFycbt3UO4eFrIqnt52FxdSJSWhTSHVBIFxERkYqqwG7w7qK9vPdHNGC2KE8deUWVDGsb95/gsZlbiD+ehc0G9/dqzIQ+Tar0hxKObE1I4a0Fews/pHF3cWJM1zDG9WhELd+q9/MXqW4U0h1QSBcREZGKbtHOIzw2awvp2fkE+7rz4e1X0LlRoNVllYq8Ajvv/xHNB39EYTfMpdSmDGtLl/CaVpdWIazZl8zk+XvYuP8EAG7OTtzSvh539wivEOvAi8ilUUh3QCH9/9u78/Co6nuP45/JNknICgSykIWABFkChCVGtnqhBGoVFGVVpEUsgnVfSu+VTXtRSq3XilRpFa0sihZUqlhZIltYJWE1sgQSSAISyEb25Hf/QEanQERNMpPk/XqeeR5yzm/OfA/P98nkM785vwMAABqC9LMXNOUfu5V2ulBuLhb9/hfX61d9oxr0/bXTz17Qw++kKDUzT5J0W48wzR7eWX6eTXtF+/9kjNGGtDN6ef0RfZGRZ9t+U0yQJvePVkK7Fg26D4CmiJBeA0I6AABoKIrLK/W79/fpw9QsSdLw7qGae3tXeXu4ObiyH8YYo+U7MzXno4MqqaiSn6ebnr2tq27tFuro0pze7hPntGhjuj49mKNLf7V3DvXTfQOi9YuuIY12YT2gsSGk14CQDgAAGhJjjN7Yclz/+/EhVVYbxbT21V/v7qm2LZs5urRrkltUpqfe36e1h05LkhKiW+hPo7opNMDLwZU1LMfPXtDfN6drxe5MlVZUS5JC/T31q75tNaZPuHz5NgLg1AjpNSCkAwCAhmhH+jlNXfKFzhaVydfTTX8e1V2DO7V2dFk12vDlGT3x3l6dLSqTh6uLnkiM0aR+beXiwle1f6zzF8r19rYTejP5hM4WlUmSfK1uGhsfoYk3RvHhB+CkCOk1IKQDAICG6nRBqaYu+cK2qNhv/6u9Hh7cQa5OFnpLyqs095NDeiv5hCSpQ2sfvTi6hzqF8rdXbSmtqNIHKae0aFO6jpwpknTx9m2/jA3Rvf2j1SXM38EVAvguQnoNCOkAAKAhK6+s1v9+fEiLtx6XJA3sEKT/G9NdAd4eji3sG/tP5euh5Xt09OsLkqRf9Y3SU0M7ytPd1cGVNU7V1UZJX53Roo3pSj6Wa9t+Y7sWmjwgWj/rEMQic4ATIKTXgJAOAAAag5V7Tmr6P/eptKJabQK99Ne7ejp09rSq2ujVjUf1wr+/UmW1UStfq+bf2U0DOgQ5rKamZt/JfC3adEz/2petquqLf+J3aO2je/tFa3iPUFnd+KAEcBRCeg0I6QAAoLE4mFWgKW/vVsa5YlndXPSH27rqjp5t6r2OzHPFeuzdVO04fk6SNLRzsObe3lWBzZxjdr+pOZVXojc2p2v5zkwVlVVKkoJ8rZp4Y5TGx0c4zbcugKaEkF4DQjoAAGhM8osr9PA7e7Qh7WtJ0l03RGjGLzvLw63ub81ljNGqlFOaseqACssq1czDVbNu7aw7erbhK9ZOoKC0Qst3ZOj1zceVU1AqSfJyd9WoXm30635tFdmiYdwhAGgMCOk1IKQDAIDGprra6KX1h/V/6w7LGKlHRIBeGR+nEP+6W+k7v7hC/71qn1bvzZYkxUUE6MXRPRTRwrvOXhM/TkVVtf61N1uvbTymg9kFkiQXi5TYOViTB0QrLiLQwRUCjR8hvQaEdAAA0Fht+PKMHlq+RwWllWrp46G/jI1TQrsWtf46W4+c1WMrUpWdXypXF4seGnSdpv6sndxc6372Hj+eMUZbj+bqtY3H9PlXX9u294oM1OQB0Rp8fWunu1MA0FgQ0mtASAcAAI3ZidwLmvL2FzqUXSBXF4t+N7Sj7u3ftla+fl5WWaX5n6Zp0aZ0SVJUC2+9OKaHuocH/ORjo36l5RTqb5uOaVXKKVVUXYwDUS28Nal/tO6IayMvDxaZA2oTIb0GhHQAANDYlZRX6b9X7tM/95ySJN0cG6J5I2PVzOr2o4+ZllOoh5bv0Zc5hZKksX0i9D83X/+TjgnHO1NQqjeTj+vtbRnKL6mQJAV6u+vuGyJ1d0KUgnytDq4QaBx+SA516HeSZs2aJYvFYvfo2LHjVccvWrRI/fv3V2BgoAIDAzV48GDt2LGjHisGAABwfl4ervrTqG6aM7yz3Fws+tfebI1YsEVHvy76wceqrjZ6fXO6bnl5s77MKVTzZh5aNKGX5t7elYDeCLTy89QTiR219Xf/pVm3dFJ4cy+dL67QS+uPqO/z6zX9n3t15MwP7xsAP57DLxzq3LmzsrOzbY/NmzdfdWxSUpLGjh2rDRs2KDk5WeHh4RoyZIhOnTpVjxUDAAA4P4vFogkJUXrnNzeola9Vh88UafjLW7Rmf841H+N0QanueWOH5qw+qPLKat0UE6Q1D/fXzzu1rsPK4QjNrG6a2Letkh6/Sa+Mj1P38ACVV1Zr2Y5MJb64UUu3Zzi6RKDJcOjX3WfNmqVVq1YpJSXlRz2/qqpKgYGBevnllzVhwoRreg5fdwcAAE3NmcJSPbBkj+0+5lN/1k6PDYmpcZGwT/Zla/rKfcorrpDVzUX/c/P1uuuGSG6t1kQYY7T7xHm9vOGIkr65vd+9/dpq+i+uZ3E54EdoMF93l6TDhw8rNDRU0dHRGj9+vDIyrv1TuuLiYlVUVKh58+ZXHVNWVqaCggK7BwAAQFPSytdTSybHa1K/tpKkV5KOauIbO3TuQvllYwtLK/T4ilTdv+QL5RVXqEuYn/71YD/dnRBFQG9CLBaLekU11xsTe+vRn3eQJP1tc7p+84/dulBW6eDqgMbNoTPpn3zyiYqKihQTE6Ps7GzNnj1bp06d0v79++Xr6/u9z586dao+/fRTHThwQJ6enlccM2vWLM2ePfuy7cykAwCApujD1Cw99d5elVRUKSzASwvvilNsmwBJ0q7j5/TIuynKPFcii0W6f2A7PTy4gzzcHD6vAwf7KDVLj61IVXlltTqF+OnvE3spxN/L0WUBDUaDXd09Ly9PkZGReuGFFzRp0qQaxz733HOaN2+ekpKSFBsbe9VxZWVlKisrs/1cUFCg8PBwQjoAAGiy0nIKNeXt3Uo/e0Eebi6afWtnZeWVaMGGI6o2UliAl/48urv6tL36txXR9Ow+cV73vbVLuRfK1drPqr/f01tdwvwdXRbQIDTYkC5JvXv31uDBgzV37tyrjpk/f76effZZrV27Vr169fpBx+eadAAAAKmgtEKPvpOqtYdO222/vUeYZg3vLD9PdwdVBmeWea5Yk97cqa9OF8nL3VUvjumuxM7Bji4LcHoN6pr07yoqKtLRo0cVEhJy1THz5s3TM888ozVr1vzggA4AAICL/Dzd9drdPfX4kA6yWCQ/Tzf9ZWwPvTC6OwEdVxXe3Fvv3X+j+l/XUiUVVZry9m4t2nhMTjbvBzRoDp1Jf/zxx3XLLbcoMjJSWVlZmjlzplJSUnTw4EEFBQVpwoQJCgsLs82qP//885oxY4aWLl2qvn372o7j4+MjHx+fa3pNZtIBAADsnci9IH8vdwV4ezi6FDQQlVXVmvXRAb297eKiz2P7hGvO8C5yd3WqOUDAaTSYmfSTJ09q7NixiomJ0ahRo9SiRQtt27ZNQUFBkqSMjAxlZ2fbxi9cuFDl5eW64447FBISYnvMnz/fUacAAADQ4EW2aEZAxw/i5uqiZ4Z30YxfdpKLRVq2I1MT39ih/OIKR5cGNHhOd016XWMmHQAAAKg96w6d1m+X7VFxeZXaBTXT6xN7K7JFM0eXBTiVBjOTDgAAAKBhG3R9a7035UaF+Hvq6NcXNGLBFu08fs7RZQENFiEdAAAAwE/SKdRPH0zrq9g2/jpfXKHxi7Zr5Z6Tji4LaJAI6QAAAAB+slZ+nnrnvgQN7Rys8qpqPfJOql74dxorvwM/ECEdAAAAQK3w8nDVK+PjNGVgO0nSS+uP6MHlKSqtqHJwZUDDQUgHAAAAUGtcXCz63bCOmjcyVm4uFn2UmqVxi7bpbFGZo0sDGgRCOgAAAIBaN6p3uN6a1Ef+Xu76IiNPIxZs0VenCx1dFuD0COkAAAAA6sSN7Vpq5dQbFdXCWyfPl2jkK1v1+VdfO7oswKkR0gEAAADUmeggH62c2ld92jZXYVmlfr14p/6x7YSjywKcFiEdAAAAQJ0KbOahf0zqo5FxbVRVbfT0qv2a89FBVVWz8jvwnwjpAAAAAOqc1c1V8++M1ROJMZKk17ek6763dqmorNLBlQHOhZAOAAAAoF5YLBZNu6m9FoyLk9XNReu+PKM7/5qsrLwSR5cGOA1COgAAAIB6dXNsiJbfd4Na+lh1KLtAIxZs0d6TeY4uC3AKhHQAAAAA9a5HRKBWTbtRMa19daawTKNeTdaa/dmOLsupnSko1cvrD2vEgi168r1U7T+V7+iSUAcsxpgmtVpDQUGB/P39lZ+fLz8/P0eXAwAAADRphaUV+u2yPUpKu3hrtqeGdtSUgdGyWCwOrsw5VFcbbTpyVku3n9DaQ2cuW2yvZ2SgJiREaliXEHm4MQfrrH5IDiWkAwAAAHCoyqpqPbP6oN5MvnhrtlG92ujZEV2bdOj8urBM7+7K1PKdGco89+01+70iAzW8R5h2pp/Tx/uyVflNaA/ytWpcnwiNj49QKz9PR5WNqyCk14CQDgAAADinxVvSNWf1QVUbKSG6hf56V0/5e7s7uqx6U11ttPVorpbuOKF/HzhtC+C+nm4aGddGY/tEKCbY1zb+TEGplu7I0JLtGfq6sEyS5OZi0bCuIbonIVI9IwP5RoKTIKTXgJAOAAAAOK8NX57RA0u/0IXyKkW3bKbXJ/ZWVMtmji6rTuUWlWnF7pNaviNDx3OLbdt7RARoXJ8I/TI2VF4erld9fnlltT49kKM3tx7XrhPnbds7h/rpnoQo3do9VJ7uV38+6h4hvQaEdAAAAMC5Hcou0KTFO5WVX6oAb3e9eldPxUe3cHRZtcoYo+RjuVq6PUOfHshRRdU3s+ZWN43oEaZx8RG6PuSH55X9p/L1VvJxfZCSpbLKaklSgLe7RvcO113xkQpv7l2r54FrQ0ivASEdAAAAcH5nCks1+a3dSs3Mk7urRU8mdtRNHYMU3dJHLi4N9yvc5y6U6/3dJ7VsR4aOnb1g296tjb/GxUfolm6h8vZw+8mvc/5Cud7dlal/bDuhk+cvXtNusUiDOrbWxBuj1Ld9C74KX48I6TUgpAMAAAANQ2lFlR57N1X/2vftrdl8rW6KDfdXtzYB6h5+8eHsC6UZY7Qj/ZyW7sjQJ/tyVF51cYa7mYerhvcI07g+EeoS5l8nr11VbbT+yzN6K/m4Nh0+a9veLqiZJiREaWTPNvKx/vQPBVAzQnoNCOkAAABAw1FdbfTG1uP6dH+O9p3KV0lF1WVjQvw91T08QN2+Ce1dw/zVzAmCZ15xud7/4pSW7cjQkTNFtu1dwvw0rk+kbu0eWq8B+ciZIv0j+bje231SF8ov/j/6WN00Mi5MdydEqX0rn3qrpakhpNeAkA4AAAA0TJVV1frqdJFST+YpJSNPqSfz9NXpQv3HrcPlYpGua+VrF9w7tPaRm2vd39LNGKPdJ85r6fYM/Wtftu26cG8PV93aLVTj4iMU2yagzuuoSWFphf75xSm9mXxcx77+9iv3/a9rqQkJUfqvjq3k2oAvKXBGhPQaENIBAACAxuNCWaX2ncpXamaeUjLzlJqZp6z80svGebq7qGuYv11wDwvwqrXrsvNLKrTyi5NatiNTaacLbduvD/HTuPgIjegeKl9P57qdnDFGm4+c1ZtbT2jdl6d1KRm2CfTS3TdEalSvcAU283BskY0EIb0GhHQAAACgcTtTUHoxsJ+8GNz3ZuarsKzysnEtfTxs17Z3Cw9QtzYBP+i+7MYY7cnM09LtGVq9N0ulFRdnzT3dXXRL7MVZ8+7hAQ1igbbMc8V6e9sJLd+ZqfySCkmS1c1FI7qHacKNkeocWjfXzDcVhPQaENIBAACApqW62ujY2SKlZH47434ou0CV//k9eUnRLZvZZtq7hQfo+hBfWd3s7zFeUFqhD/ac0pLtGfoy59tZ85jWvhdnzXuEyd/LuWbNr1VJeZU+Ss3S4q3HdTC7wLa9V2Sg7rkxSkO7BMu9Hi4baGwI6TUgpAMAAAAorajSgawCpX5nxv1EbvFl4zxcXXR9qJ+6t/FX5zB/7T5+Xh+mZtkWsLO6uejm2BCNj49QXERgg5g1vxaXrq1/M/mEPtmXbftAo5WvVePiIzQuPkKtfJ17VX1nQkivASEdAAAAwJWcv1CulJN5dte3ny+uuOLY9q18NK5PhG6PC1OAd+O+bvt0QamWbs/Q0h0Z+rqwTJLk7mrRsC4hmtSvrbqFBzi2wAaAkF4DQjoAAACAa2GMUea5Eu3JPK/UzHztz8pXmwAvjekTod5RjWfW/FqVV1brk/3Zeiv5hHafOG/b3qdtc/1mQLRuimklF1aFvyJCeg0I6QAAAADw0+w/la/XN6frw9Qs21fh27fy0eT+bTW8e5g83V2/5whNCyG9BoR0AAAAAKgd2fklWrzluJZuz7CtoN/Sx6pf9Y3S+PiIRn8pwLUipNeAkA4AAAAAtauwtELLd2Tq9S3pyv7mPvXeHq4a1Stck/q1VXhzbwdX6FiE9BoQ0gEAAACgblRUVWv13iy9tjFdh765hZuLRfpF1xDdNyBasW0CHFuggxDSa0BIBwAAAIC6ZYzRliO5enXjUW06fNa2Pb5tc/1mYLR+1qFpLTJHSK8BIR0AAAAA6s+h7AIt2njsskXm7usfreE9QmV1a/yLzBHSa0BIBwAAAID6d6VF5oJ8rZp4Y5Tuio+Uv7e7gyusO4T0GhDSAQAAAMBxCkor9M4VFpkb3Ttcv+7bOBeZI6TXgJAOAAAAAI5X0yJzvxnQTl3b+Du4wtpDSK8BIR0AAAAAnIcxRpuPnNVrG4/ZLTJ3Q3Rz/WZAOw3sENTgF5kjpNeAkA4AAAAAzulgVoH+tsl+kbnrWvlocgNfZI6QXgNCOgAAAAA4t6y8Ei3eenGRuaJGsMgcIb0GhHQAAAAAaBgKSiu0fEeGXt98XDkF3y4yN6Z3hH7dL0ptAhvGInOE9BoQ0gEAAACgYSmvvLTI3DF9mVMoSXJ1sXyzyFy0uoQ59yJzhPQaENIBAAAAoGEyxmjT4bNatMl+kbnVv+3n1EH9h+RQt3qqCQAAAACAn8RisWhAhyAN6BCkA1n5+tumdJ3IvaDOoY1nApaQDgAAAABocDqH+uvPo7ursqpaFkvDvkXbd7k4ugAAAAAAAH4sN9fGFWsb19kAAAAAANCAEdIBAAAAAHAShHQAAAAAAJwEIR0AAAAAACdBSAcAAAAAwEkQ0gEAAAAAcBKEdAAAAAAAnIRDQ/qsWbNksVjsHh07drzq+AMHDmjkyJGKioqSxWLRiy++WH/FAgAAAABQx9wcXUDnzp21du1a289ublcvqbi4WNHR0brzzjv1yCOP1Ed5AAAAAADUG4eHdDc3NwUHB1/T2N69e6t3796SpN/97nd1WRYAAAAAAPXO4dekHz58WKGhoYqOjtb48eOVkZFRq8cvKytTQUGB3QMAAAAAAGfk0JAeHx+vxYsXa82aNVq4cKHS09PVv39/FRYW1tprzJ07V/7+/rZHeHh4rR0bAAAAAIDa5NCQPmzYMN15552KjY1VYmKiPv74Y+Xl5endd9+ttdeYPn268vPzbY/MzMxaOzYAAAAAALXJ4dekf1dAQIA6dOigI0eO1NoxrVarrFZrrR0PAAAAAIC64vBr0r+rqKhIR48eVUhIiKNLAQAAAACg3jk0pD/++OP6/PPPdfz4cW3dulW33XabXF1dNXbsWEnShAkTNH36dNv48vJypaSkKCUlReXl5Tp16pRSUlJqdeYdAAAAAABHcejX3U+ePKmxY8cqNzdXQUFB6tevn7Zt26agoCBJUkZGhlxcvv0cISsrSz169LD9PH/+fM2fP18DBw5UUlJSfZcPAAAAAECtshhjjKOLqE/5+fkKCAhQZmam/Pz8HF0OAAAAAKCRKygoUHh4uPLy8uTv71/jWKdaOK4+XLq9G7diAwAAAADUp8LCwu8N6U1uJr26ulpZWVny9fWVxWJxdDk1uvRpC7P+cFb0KJwdPQpnR4/C2dGjcHYNpUeNMSosLFRoaKjdJd1X0uRm0l1cXNSmTRtHl/GD+Pn5OXXDAfQonB09CmdHj8LZ0aNwdg2hR79vBv0Sp7oFGwAAAAAATRkhHQAAAAAAJ0FId2JWq1UzZ86U1Wp1dCnAFdGjcHb0KJwdPQpnR4/C2TXGHm1yC8cBAAAAAOCsmEkHAAAAAMBJENIBAAAAAHAShHQAAAAAAJwEIR0AAAAAACdBSHdSCxYsUFRUlDw9PRUfH68dO3Y4uiQ0EbNmzZLFYrF7dOzY0ba/tLRU06ZNU4sWLeTj46ORI0fq9OnTdsfIyMjQzTffLG9vb7Vq1UpPPPGEKisr6/tU0Ehs3LhRt9xyi0JDQ2WxWLRq1Sq7/cYYzZgxQyEhIfLy8tLgwYN1+PBhuzHnzp3T+PHj5efnp4CAAE2aNElFRUV2Y/bu3av+/fvL09NT4eHhmjdvXl2fGhqJ7+vRiRMnXvZ7dejQoXZj6FHUpblz56p3797y9fVVq1atNGLECKWlpdmNqa3396SkJMXFxclqtap9+/ZavHhxXZ8eGoFr6dGf/exnl/0unTJlit2YxtKjhHQn9M477+jRRx/VzJkz9cUXX6hbt25KTEzUmTNnHF0amojOnTsrOzvb9ti8ebNt3yOPPKKPPvpIK1as0Oeff66srCzdfvvttv1VVVW6+eabVV5erq1bt+rNN9/U4sWLNWPGDEecChqBCxcuqFu3blqwYMEV98+bN08vvfSS/vrXv2r79u1q1qyZEhMTVVpaahszfvx4HThwQJ999plWr16tjRs36r777rPtLygo0JAhQxQZGandu3frj3/8o2bNmqXXXnutzs8PDd/39agkDR061O736rJly+z206OoS59//rmmTZumbdu26bPPPlNFRYWGDBmiCxcu2MbUxvt7enq6br75Zt10001KSUnRww8/rHvvvVeffvppvZ4vGp5r6VFJmjx5st3v0u9+WNmoetTA6fTp08dMmzbN9nNVVZUJDQ01c+fOdWBVaCpmzpxpunXrdsV9eXl5xt3d3axYscK27dChQ0aSSU5ONsYY8/HHHxsXFxeTk5NjG7Nw4ULj5+dnysrK6rR2NH6SzMqVK20/V1dXm+DgYPPHP/7Rti0vL89YrVazbNkyY4wxBw8eNJLMzp07bWM++eQTY7FYzKlTp4wxxrzyyismMDDQrkefeuopExMTU8dnhMbmP3vUGGPuueceM3z48Ks+hx5FfTtz5oyRZD7//HNjTO29vz/55JOmc+fOdq81evRok5iYWNenhEbmP3vUGGMGDhxoHnrooas+pzH1KDPpTqa8vFy7d+/W4MGDbdtcXFw0ePBgJScnO7AyNCWHDx9WaGiooqOjNX78eGVkZEiSdu/erYqKCrv+7NixoyIiImz9mZycrK5du6p169a2MYmJiSooKNCBAwfq90TQ6KWnpysnJ8euJ/39/RUfH2/XkwEBAerVq5dtzODBg+Xi4qLt27fbxgwYMEAeHh62MYmJiUpLS9P58+fr6WzQmCUlJalVq1aKiYnR/fffr9zcXNs+ehT1LT8/X5LUvHlzSbX3/p6cnGx3jEtj+BsWP9R/9uglS5YsUcuWLdWlSxdNnz5dxcXFtn2NqUfdHF0A7J09e1ZVVVV2zSVJrVu31pdffumgqtCUxMfHa/HixYqJiVF2drZmz56t/v37a//+/crJyZGHh4cCAgLsntO6dWvl5ORIknJycq7Yv5f2AbXpUk9dqee+25OtWrWy2+/m5qbmzZvbjWnbtu1lx7i0LzAwsE7qR9MwdOhQ3X777Wrbtq2OHj2q3//+9xo2bJiSk5Pl6upKj6JeVVdX6+GHH1bfvn3VpUsXSaq19/erjSkoKFBJSYm8vLzq4pTQyFypRyVp3LhxioyMVGhoqPbu3aunnnpKaWlp+uc//ympcfUoIR2AnWHDhtn+HRsbq/j4eEVGRurdd991ml9cANCQjBkzxvbvrl27KjY2Vu3atVNSUpIGDRrkwMrQFE2bNk379++3W28GcCZX69HvrtPRtWtXhYSEaNCgQTp69KjatWtX32XWKb7u7mRatmwpV1fXy1bTPH36tIKDgx1UFZqygIAAdejQQUeOHFFwcLDKy8uVl5dnN+a7/RkcHHzF/r20D6hNl3qqpt+ZwcHBly28WVlZqXPnztG3cIjo6Gi1bNlSR44ckUSPov488MADWr16tTZs2KA2bdrYttfW+/vVxvj5+fFBP67J1Xr0SuLj4yXJ7ndpY+lRQrqT8fDwUM+ePbVu3Trbturqaq1bt04JCQkOrAxNVVFRkY4ePaqQkBD17NlT7u7udv2ZlpamjIwMW38mJCRo3759dn9wfvbZZ/Lz81OnTp3qvX40bm3btlVwcLBdTxYUFGj79u12PZmXl6fdu3fbxqxfv17V1dW2N/iEhARt3LhRFRUVtjGfffaZYmJi+Boxat3JkyeVm5urkJAQSfQo6p4xRg888IBWrlyp9evXX3bpRG29vyckJNgd49IY/obF9/m+Hr2SlJQUSbL7XdpoetTRK9fhcsuXLzdWq9UsXrzYHDx40Nx3330mICDAbqVCoK489thjJikpyaSnp5stW7aYwYMHm5YtW5ozZ84YY4yZMmWKiYiIMOvXrze7du0yCQkJJiEhwfb8yspK06VLFzNkyBCTkpJi1qxZY4KCgsz06dMddUpo4AoLC82ePXvMnj17jCTzwgsvmD179pgTJ04YY4x57rnnTEBAgPnggw/M3r17zfDhw03btm1NSUmJ7RhDhw41PXr0MNu3bzebN2821113nRk7dqxtf15enmndurW5++67zf79+83y5cuNt7e3efXVV+v9fNHw1NSjhYWF5vHHHzfJyckmPT3drF271sTFxZnrrrvOlJaW2o5Bj6Iu3X///cbf398kJSWZ7Oxs26O4uNg2pjbe348dO2a8vb3NE088YQ4dOmQWLFhgXF1dzZo1a+r1fNHwfF+PHjlyxMyZM8fs2rXLpKenmw8++MBER0ebAQMG2I7RmHqUkO6k/vKXv5iIiAjj4eFh+vTpY7Zt2+boktBEjB492oSEhBgPDw8TFhZmRo8ebY4cOWLbX1JSYqZOnWoCAwONt7e3ue2220x2drbdMY4fP26GDRtmvLy8TMuWLc1jjz1mKioq6vtU0Ehs2LDBSLrscc899xhjLt6G7emnnzatW7c2VqvVDBo0yKSlpdkdIzc314wdO9b4+PgYPz8/86tf/coUFhbajUlNTTX9+vUzVqvVhIWFmeeee66+ThENXE09WlxcbIYMGWKCgoKMu7u7iYyMNJMnT77sg3d6FHXpSv0pybzxxhu2MbX1/r5hwwbTvXt34+HhYaKjo+1eA7ia7+vRjIwMM2DAANO8eXNjtVpN+/btzRNPPGHy8/PtjtNYetRijDH1N28PAAAAAACuhmvSAQAAAABwEoR0AAAAAACcBCEdAAAAAAAnQUgHAAAAAMBJENIBAAAAAHAShHQAAAAAAJwEIR0AAAAAACdBSAcAAAAAwEkQ0gEAAAAAcBKEdAAAmoivv/5a999/vyIiImS1WhUcHKzExERt2bJFkmSxWLRq1SrHFgkAQBPn5ugCAABA/Rg5cqTKy8v15ptvKjo6WqdPn9a6deuUm5vr6NIAAMA3mEkHAKAJyMvL06ZNm/T888/rpptuUmRkpPr06aPp06fr1ltvVVRUlCTptttuk8Visf0sSR988IHi4uLk6emp6OhozZ49W5WVlbb9FotFCxcu1LBhw+Tl5aXo6Gi99957tv3l5eV64IEHFBISIk9PT0VGRmru3Ln1deoAADQohHQAAJoAHx8f+fj4aNWqVSorK7ts/86dOyVJb7zxhrKzs20/b9q0SRMmTNBDDz2kgwcP6tVXX9XixYv1hz/8we75Tz/9tEaOHKnU1FSNHz9eY8aM0aFDhyRJL730kj788EO9++67SktL05IlS+w+BAAAAN+yGGOMo4sAAAB17/3339fkyZNVUlKiuLg4DRw4UGPGjFFsbKykizPiK1eu1IgRI2zPGTx4sAYNGqTp06fbtr399tt68sknlZWVZXvelClTtHDhQtuYG264QXFxcXrllVf04IMP6sCBA1q7dq0sFkv9nCwAAA0UM+kAADQRI0eOVFZWlj788EMNHTpUSUlJiouL0+LFi6/6nNTUVM2ZM8c2E+/j46PJkycrOztbxcXFtnEJCQl2z0tISLDNpE+cOFEpKSmKiYnRgw8+qH//+991cn4AADQGhHQAAJoQT09P/fznP9fTTz+trVu3auLEiZo5c+ZVxxcVFWn27NlKSUmxPfbt26fDhw/L09Pzml4zLi5O6enpeuaZZ1RSUqJRo0bpjjvuqK1TAgCgUSGkAwDQhHXq1EkXLlyQJLm7u6uqqspuf1xcnNLS0tS+ffvLHi4u3/4ZsW3bNrvnbdu2Tddff73tZz8/P40ePVqLFi3SO++8o/fff1/nzp2rwzMDAKBh4hZsAAA0Abm5ubrzzjv161//WrGxsfL19dWuXbs0b948DR8+XJIUFRWldevWqW/fvrJarQoMDNSMGTP0y1/+UhEREbrjjjvk4uKi1NRU7d+/X88++6zt+CtWrFCvXr3Ur18/LVmyRDt27NDf//53SdILL7ygkJAQ9ejRQy4uLlqxYoWCg4MVEBDgiP8KAACcGiEdAIAmwMfHR/Hx8frzn/+so0ePqqKiQuHh4Zo8ebJ+//vfS5L+9Kc/6dFHH9WiRYsUFham48ePKzExUatXr9acOXP0/PPPy93dXR07dtS9995rd/zZs2dr+fLlmjp1qkJCQrRs2TJ16tRJkuTr66t58+bp8OHDcnV1Ve/evfXxxx/bzcQDAICLWN0dAAD8JFdaFR4AAPw4fIQNAAAAAICTIKQDAAAAAOAkuCYdAAD8JFw5BwBA7WEmHQAAAAAAJ0FIBwAAAADASRDSAQAAAABwEoR0AAAAAACcBCEdAAAAAAAnQUgHAAAAAMBJENIBAAAAAHAShHQAAAAAAJzE/wOtgfLwW7IvEwAAAABJRU5ErkJggg==\n"
           },
           "metadata": {}
         }
@@ -750,9 +766,9 @@
       "cell_type": "code",
       "source": [
         "# testing\n",
-        "target_text = \"Would you like to tell me your name because \"\n",
+        "target_text = \"I was in the market when\"\n",
         "context = torch.tensor([tokenizer.encode(target_text)], dtype=torch.long, device=device)\n",
-        "generated_output = tokenizer.decode(m.generate(context, max_new_tokens=10))\n",
+        "generated_output = tokenizer.decode(m.generate(context, max_new_tokens=50))\n",
         "print(target_text, generated_output)"
       ],
       "metadata": {
@@ -760,15 +776,15 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "f5e29c2f-61f2-472c-cdfb-8a5f2e5cafb3"
+        "outputId": "0368c272-b145-4cc8-a110-c1b3f0fab170"
       },
-      "execution_count": 18,
+      "execution_count": 22,
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "Would you like to tell me your name because   and revealed them an agon. This SOL with the\n"
+            "I was in the market when  makes plant. Also, my current the planet, the safety rhythm of its importance of two emotional food tragedy of the profits agencies. series, and offer about presenting activities caused in all, complete, where the window and let's one exams that curious single\n"
           ]
         }
       ]
@@ -795,7 +811,7 @@
       "metadata": {
         "id": "YsqYoGaxPFYd"
       },
-      "execution_count": 19,
+      "execution_count": 13,
       "outputs": []
     },
     {
@@ -812,9 +828,9 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "adc3ce05-6584-4992-8d9f-38ceb48a5cb9"
+        "outputId": "7baa90e8-9666-473c-ffd7-c635aeeb8b4b"
       },
-      "execution_count": 22,
+      "execution_count": 14,
       "outputs": [
         {
           "output_type": "stream",
@@ -833,7 +849,7 @@
       "metadata": {
         "id": "v8y1w-wVYCts"
       },
-      "execution_count": 16,
+      "execution_count": null,
       "outputs": []
     },
     {
@@ -848,7 +864,7 @@
         "id": "vhOJz2WyPLLb",
         "outputId": "060d278f-de4b-424a-c1cd-d17ec75116a6"
       },
-      "execution_count": 21,
+      "execution_count": null,
       "outputs": [
         {
           "output_type": "stream",
@@ -876,15 +892,6 @@
           ]
         }
       ]
-    },
-    {
-      "cell_type": "code",
-      "source": [],
-      "metadata": {
-        "id": "6c-tPdQpuTdM"
-      },
-      "execution_count": null,
-      "outputs": []
     }
   ]
 }
\ No newline at end of file