diff --git a/.gitignore b/.gitignore
index f3e111f53211cf88d62ddd987212dd4116651613..e4fd93b57d785d9fc04065d73fd18b679e99ba8f 100644
--- a/.gitignore
+++ b/.gitignore
@@ -127,3 +127,7 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+# data folders
+MNIST/
+cGAN_pretrained_models/
\ No newline at end of file
diff --git a/BE2_GAN_and_cGAN.ipynb b/BE2_GAN_and_cGAN.ipynb
index 7243c8909272f2e776695baf70e3aea2aa9b3aef..b68ee7d0836800a496feb6044a87ec831078b299 100644
--- a/BE2_GAN_and_cGAN.ipynb
+++ b/BE2_GAN_and_cGAN.ipynb
@@ -60,7 +60,7 @@
     "id": "jiHCy4_UUBFb"
    },
    "source": [
-    "##Work to do\n",
+    "## Work to do\n",
     "Now we want to generate handwritten digits using the MNIST dataset. It is available within torvision package (https://pytorch.org/vision/stable/generated/torchvision.datasets.MNIST.html#torchvision.datasets.MNIST)\n",
     "\n",
     "Please re-train the DCGAN and display some automatically generated handwritten digits.\n",
@@ -69,7 +69,502 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Random Seed:  999\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<torch._C.Generator at 0x10aca9390>"
+      ]
+     },
+     "execution_count": 59,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from __future__ import print_function\n",
+    "#%matplotlib inline\n",
+    "import argparse\n",
+    "import os\n",
+    "import random\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.nn.parallel\n",
+    "import torch.backends.cudnn as cudnn\n",
+    "import torch.optim as optim\n",
+    "import torch.utils.data\n",
+    "import torchvision.datasets as dset\n",
+    "import torchvision.transforms as transforms\n",
+    "import torchvision.utils as vutils\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib.animation as animation\n",
+    "from IPython.display import HTML\n",
+    "\n",
+    "# Set random seed for reproducibility\n",
+    "manualSeed = 999\n",
+    "#manualSeed = random.randint(1, 10000) # use if you want new results\n",
+    "print(\"Random Seed: \", manualSeed)\n",
+    "random.seed(manualSeed)\n",
+    "torch.manual_seed(manualSeed)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Number of workers for dataloader\n",
+    "workers = 2\n",
+    "\n",
+    "# Batch size during training\n",
+    "batch_size = 128\n",
+    "\n",
+    "# Spatial size of training images. All images will be resized to this\n",
+    "#   size using a transformer.\n",
+    "image_size = 64\n",
+    "\n",
+    "# Number of channels in the training images. For color images this is 3\n",
+    "nc = 1\n",
+    "\n",
+    "# Size of z latent vector (i.e. size of generator input)\n",
+    "nz = 100\n",
+    "\n",
+    "# Size of feature maps in generator\n",
+    "ngf = 64\n",
+    "\n",
+    "# Size of feature maps in discriminator\n",
+    "ndf = 64\n",
+    "\n",
+    "# Number of training epochs\n",
+    "num_epochs = 5\n",
+    "\n",
+    "# Learning rate for optimizers\n",
+    "lr = 0.0002\n",
+    "\n",
+    "# Beta1 hyperparam for Adam optimizers\n",
+    "beta1 = 0.5\n",
+    "\n",
+    "# Number of GPUs available. Use 0 for CPU mode.\n",
+    "ngpu = 1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MPS is available.  Training on MAC GPU ...\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Load dataset\n",
+    "dataset = dset.MNIST(\n",
+    "    '', \n",
+    "    download=True, \n",
+    "    transform=transforms.Compose([\n",
+    "        transforms.Resize(image_size),\n",
+    "        transforms.CenterCrop(image_size),\n",
+    "        transforms.ToTensor(),\n",
+    "        transforms.Normalize((0.5,), (0.5,)),\n",
+    "    ])\n",
+    ")\n",
+    "\n",
+    "# Create the dataloader\n",
+    "dataloader = torch.utils.data.DataLoader(dataset, batch_size=batch_size,\n",
+    "                                         shuffle=True, num_workers=workers)\n",
+    "\n",
+    "# check if GPU is available\n",
+    "if torch.cuda.is_available():\n",
+    "    device = torch.device(\"cuda:0\")\n",
+    "    print(\"CUDA is available!  Training on GPU ...\")\n",
+    "elif torch.backends.mps.is_available():\n",
+    "    device = torch.device(\"mps\")\n",
+    "    print(\"MPS is available.  Training on MAC GPU ...\")\n",
+    "else:\n",
+    "    device = torch.device(\"cpu\")\n",
+    "    print(\"Nor CUDA or MPS are available. Training on CPU ...\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x141119d00>"
+      ]
+     },
+     "execution_count": 62,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAcEAAAHRCAYAAAASbQJzAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOz9aWyjV9smiF0P901cRFJcJIraRVISJVK7VJtdtstlu7/uN909/TVmggTIIMEAQRAgwQTJj+nBYJIfQRKkgyTAYCZoDNAzyGydb+vv3fy+LrtK+75SIkVS3PdNFEXtzI/yOSarVHbZVRIlFy+ggLJLrDo3n+dc937fTKlUQg011FBDDTV8iGBV+wA11FBDDTXUUC3UlGANNdRQQw0fLGpKsIYaaqihhg8WNSVYQw011FDDB4uaEqyhhhpqqOGDRU0J1lBDDTXU8MGipgRrqKEMDMP8lmGY/8n7/tkaaqjhdoKp9QnWcNfBMMxh2X+KAJwAuPj+v/8XpVLpv7r5U/1yMAzzCMC/LpVKTVU+Sg01/OrBqfYBaqjhXVEqlSTk9wzD7AP490ul0tev/hzDMJxSqXR+k2eroYYabjdq4dAafrVgGOYRwzBBhmH+dwzDRAH8K4ZhFAzD/B3DMAmGYTLf/76p7DPPGIb597///f+UYZgXDMP8X77/WS/DME9/4c+2MgzzHcMweYZhvmYY5v/FMMy/fks5njEM858yDDPNMMwhwzB/yzCMkmGY/4phmAOGYRYYhmkp+/l/yTBM4Ps/W2IY5n7ZnwkZhvkvvz+jg2GY/5BhmGDZn+sZhvkfvv9+vAzD/K/K/myEYZjF7//eGMMw/7ef+0xqqOG2oaYEa/i1QwugHoARwP8cL9/5f/X9fzcDKAL4f/7I50cB7AJQAfg/A/j/MAzD/IKf/a8BzANQAviPAfyPf6Ycf/n9ZxoBtAOY+V6OegAOAP+i7GcXAAx8/2f/NYD/jmEYwfd/9i8AtABoA/ApgH+PfIhhGBaAvwWw9v2/8xjA/5phmCff/8i/BPAvS6WS9Psz/Lc/U4Yaarh1qCnBGn7tuATwL0ql0kmpVCqWSqVUqVT6H0ql0lGpVMoD+D8CePgjn/eVSqX/vFQqXQD4LwHoAGh+zs8yDNMMYBjAf1QqlU5LpdILAH/zM+X4V6VSyV0qlXIAfgvAXSqVvv4+vPvfAbCRHyyVSv/6eznPS6XS/xUAH0D393/87wD4P5VKpUypVAoC+H+U/RvDANSlUuk/+f6cHgD/OV4qYAA4A9DBMIyqVCodlkql2Z8pQw013DrUlGANv3YkSqXSMfkPhmFEDMP8ZwzD+BiGOQDwHQA5wzDsN3w+Sn5TKpWOvv+t5Gf+rB5Auuz/AUDgZ8oRK/t98Yr/Ls+L/m+/D3XmGIbJApDhpXeK789S/m+X/94IQM8wTJb8AvB/wA9K/38GoAvAzvch2K9+pgw11HDrUCuMqeHXjlfLn/83eOkVjZZKpSjDMAMAVgC8KcT5PhABUM8wjKhMERqu4x/6Pv/3H+JlKHOrVCpdMgyTwQ/yRQA0Adi+4hwBAN5SqdR51d9dKpVcAP7592HT/xGA/55hGGWpVCpcgyg11HAjqHmCNXxoqMNLzynLMEw9KnNp14JSqeQDsAjgP2YYhscwzDiAf3BN/1wdgHMACQAchmH+IwDSsj//bwH8778vEGoE8L8s+7N5APnvC4mEDMOwGYbpZRhmGAAYhvn3GIZRl0qlSwDZ7z9zeU1y1FDDjaCmBGv40PB/ByAEkAQwC+B3N/Tv/rsAxgGkAPynAP4bvOxnfN/4PV7K5ATgA3CMypDnfwIgCMAL4GsA/z05x/e5zK/wsqjGi5ff0X+Bl+FUAPgcwNb3fZn/EsBflkql4jXIUEMNN4Zas3wNNVQBDMP8NwB2SqXStXuiP3GO/wAvldmPFQfVUMOvFjVPsIYabgAMwwwzDNPOMAyLYZjPAfxDAH9VhXPoGIaZ/P4c3XiZI/3/3fQ5aqjhtqBWGFNDDTcDLYB/g5d9gkEA/0GpVFqpwjl4AP4zAK14mdf7/wL4f1fhHDXUcCtQC4fWUEMNNdTwwaIWDq2hhhpqqOGDRU0J1lBDDTXU8MHiR3OCDMPUYqU11FBDDTXcaZRKpTcOw6h5gjXUUEMNNXywqCnBGmqooYYaPljUlGANNdRQQw0fLGpKsIYaaqihhg8WNSVYQw011FDDB4uaEqyhhhpqqOGDRU0J1lBDDTXU8MGipgRrqKGGGmr4YPGrG6DNMAwY5mVfZKlUwq9lNmpNrruFmlx3D0S2X6tcwK/rmb0vuX5VSlAqlUKj0YDH4+H8/ByZTAapVAoXFxfVPto7QSwWo6GhAUKhEKVSCblcDolEAmdnZ9U+2juBz+dDo9FAIpGAYRjk83nE43EcHx9X+2jvBA6Hg4aGBshkMrBYLBwdHSEej6NQKFT7aO8EhmGgVqtRX18PNpuNk5MTJBIJ5HK5ah/tncAwDBQKBdRqNTgcDs7OzpBKpZBKpap9tHeGVCpFQ0MD+Hw+Li4ukMlkkEwm7zwnikQiaDSaCk5MJpM4PT392X/Xr0YJslgstLe344svvoBKpcLh4SFmZmbw7NkzHB0dVft4vxgMw0Cv1+PLL7+EwWDA+fk5lpeX8fXXX9/5S6pQKPDZZ5+hu7sbbDYbW1tb+MMf/oBAIPDTH77FEAqFuH//Pux2O3g8Hvb39/Hb3/4WTqez2kd7J3A4HAwPD2NychJCoRDRaBRff/01lpaWqn20dwKLxYLFYsGTJ08gkUiQyWTw3Xff4fnz53daWbBYLLS2tuLLL7+EWq1GoVDA7OwsvvnmmzttkDEMA51Oh6+++grNzc24uLignJhMJn/233frlCCfz4dIJMLZ2RmOjo5weXn5k58RCASor6+HyWTC2NgYBAIBfD4fxGIxdZerDS6XC7FYjIuLCxwdHb3V5eLxeJDL5ejs7MTIyAg0Gg0ikQicTifYbPYNnPqnwWaz6fdcKBRwfn7+k5/hcDiQyWRob2/H0NAQOjs7kc1mEQgEwOHcjleSxWJBJBKBy+WiUCi8lYXJZrMhkUjQ3NwMu92OoaEhFAoF5HI58Hi8Gzj1T4NhGAiFQgiFQhQKBZycnPxkGInFYkEsFkOlUqG/vx8jIyM4OTnB+fk5+Hz+DZ38x8EwDOWO4+NjFIvFn5SLfBdKpRI9PT0YGxvDxcUF9vb2IBQKb+jkPw0ejwexWPyzOVGhUMBsNmNsbAxCoRB+v//WcaJIJEKpVEKhUPhZnNjV1YWRkRFotVpEo1G4XK5fzIm3qjCGxWKhrq4OLS0t0Gg0b0WILBYLCoUCPT09sFqtaGtrA8MwCIVCSCQSt8KSYxgGIpEIBoMBjY2Nb00cEokE3d3dGBgYQEdHBwQCAcLhMKLR6C9y+68DAoEAjY2NaG5uhkgkeqsLJhAI0NbWBrvdjs7OTkilUsRiMYRCoVsTCuVyudBqtWhtbUVdXR1YrJ++Knw+H83NzRgcHER3dzeUSiUymQz8fv+tsbw5HA5UKhXa29shl8vfSi4ulwudTofBwUGYzWZotVoUCgUEAgEcHBzcwKl/Gmw2GwqFAu3t7VAqlW9FiGw2G2q1Gv39/ejr66ORlkAggHQ6fStyZywWC1Kp9Gdzolwur+BEFot1qzgRAOVEvV7/1pwoFovR1dVFOVEoFCISiSASifxiTrwdZjdeXk6JRIKOjg6MjY0hGAzi5OQE6XT6jVYdn8+HSqWC2WzGgwcPYLfboVAo4HK54Pf7b0Xsm81mQygUwmg0Ynx8HMViEefn54hEIigWi1dadcTa6ejowL179zA6OgqNRgOPx4NAIIBoNFr1fCCLxQKfz4dOp8PIyAgEAgEAwO/34/Dw8MrvnXiAzc3NGB8fx+TkJJqampDL5RAKhRAMBquuBIlHoVKpYLPZ0NTUhOnpabhcLuTz+Su/d0JUjY2NGB4exsOHD9Ha2goWi4VoNHprlCCPx0N9fT16e3vR19eHubk5XFxcIJfLvZFA6urqoNVqYbPZ8PDhQ3R3d0MgECCVSsHn892KfCCXy4VMJkN3dzdGRkawublJawLe5OmKRCI0NDSgr68PDx8+RG9vLyQSCXK5HPx+/61QghwOB2KxGG1tbRgfH6dEn0qlcHx8fCV38Pl8KJXKCk6sr6+Hx+OB3+9HPB6/FZwoEAgoD5ycnODi4gKRSOSNni6Xy6VGTjkn7u/vU06800qQYRiIxWLo9XpYrVZ88skncDgcCAaDOD09xenp6WthNhaLRV/8sbExPHz4EEajEZeXl0gkEggGg0in028VOrgukHCLRqOBxWLBRx99hFwuh3A4jEKhgLOzs9ceHMMwkEgkaGtrw8jICB48eACz2Qwul4tUKoVgMFj1ophyRdHd3Y0HDx5AJBIhHo/j4OCAvtSvfkYoFFJP6f79+xgaGgKPx4PP50MwGEQsFsPJyUmVpHp5RqIo2tvbMTExga6uLqTTaaTTaZycnLz2vZPP6PV6DAwM4N69e7h37x74fD78fj/C4TDC4TCKxWKVpHp5RjabDblcjpaWFoyMjODhw4c4OjpCIpHA6ekpzs7OXiN9UuDT19eHyclJPHz4EFKpFJlMBpFIBKFQCIeHh1WS6iWIAWIwGGC32/HkyRPweDxEo1GcnJzg9PT0NblYLBbq6+thsVgwPj6OR48eoaGhAScnJzQiUW3lXs6J/f39+OSTT+B0OhEIBKhcr3Ib4cSuri6MjY3hwYMHaG1tRalUopyYyWSqqgQJDzQ0NFBOzOfziEQiNO3wJk5sbW2lnGixWMDj8ZBOpxEIBJBIJN4qFXMVqq4EORwOhEIhWlpaMDo6isnJSXR3dyOZTILL5V4ZXiO5F4PBgIGBAQwMDECv1+Pk5ARutxubm5s0VFMtJchisSAUCtHY2IihoSHcu3cPFosFXq8XAoHgyjAUyb3odDpYrVYMDQ2hubkZpVIJOzs7WF9fh8/nQzabrdqLXK7YBwYGMDk5ib6+PhSLRYhEojeGoYjl3dPTg+HhYbS1tYHH48Hj8WBtbQ0ejwepVKqqYV5iRVutVoyOjsJms6G+vh51dXVgs9lXvosCgQBKpRLd3d0YGhpCV1cXJBIJ9vf3sbq6CpfLhUQiUVXlTjwli8WC0dFRDA8Po6WlBTKZDBwO50q5+Hw+pFIpOjo6MDg4CIvFAqVSiXA4jM3NTezu7iIajVZVuZOcUkdHB0ZHRzE+Po6Ojg6sra2Bw+Fcece4XC4kEglaWlpgt9thtVqh0WhwcHCAnZ0dbG9vU+VeLU+wPHpUzomZTIZy4qvPjHBiU1MTbDYbBgYG0NjYiJOTEzgcDsqJuVyu6pyo1+srONHv94PP54PFYr0mF1GAr3IigApOzGQyd1MJEo+CEM8XX3yB/v5+SKVSlEolFIvFKy1UHo8HtVpNC0YsFgsYhsHe3h7++Mc/Ym5uDqFQCIVCoSovcrlHYTKZ8Pnnn2N8fBwymQxerxfFYvFKC5XNZkOpVNKCkf7+fggEAvj9fvz5z3/G9PQ0fD4f8vl8VS8oKWp5/PgxHj9+DKVSid3dXZycnOD4+Pi1szEMA7lcjtbWVthsNgwODkImkyEajeLFixd48eIF9vb2qm60SKVSGI1GPHjwAE+ePIFer0c6ncbp6emV3i3wMlzY3NyM/v5+DA8Po6GhAel0GvPz8/j222/hcDje6YK+KwiJ6PV6jI2N4auvvkJraysA4Pz8HMfHxzg/P3/tmYlEIjQ2NlKjxWAwoFAoYHV1Fd988w3W19epF1kNlBtjg4OD+PLLL2E2myGRSHBxcUG541UIBAJoNBqYzWYMDw+jvb0dZ2dncDgc+MMf/oClpaWqKneGYSAQCKBSqdDX14cvvvgCAwMDP8mJXC63ghN7enrAYrHgdDrxxz/+EbOzswgGg1XjRHJGhUJBOXFiYgIymQx+vx/Hx8c4OTl57f6z2WwamRkaGsLAwAAt8vnmm28wPT2N/f19HB4e/mLuqJoS5HK5UCqVaG1txfDwMEZHR9HV1YWLiwusra1he3sbiUTiyhhxXV0dhoeHcf/+fbS0tODw8BCzs7NYWVnBwsICfD4fjo6OqvKwyUNramrC0NAQRkZG0NfXBw6Hg93dXWxsbCAajV5ZDcXn82G1Wmnu5eLiArOzs1hdXcXCwgI8Hk/VLFQSatFqtRgcHMTIyAgGBwchkUjg9XqxsrKCYDCIw8PDK0PXJpOJ5l74fD7W1tawtraGhYUF7O7uVs1CZRgGdXV1UKlUsNvtGB4exsjICPV6NjY2aO7rKlJtaWnBo0ePYLPZUFdXh729PayurmJxcRFbW1tIpVJVUYCkGKu+vh59fX3UA9Tr9chkMnA6nXC73chkMlcqMp1Oh0ePHmFkZAQqlQrBYBAbGxuYn5/H+vo6YrHYlWR8EyDV4CQHODo6ipaWFhwdHcHhcMDpdNK82avnq6+vx+TkJCYmJtDY2IhUKoWNjQ0sLy9jcXGR1iJUQy4ul4v6+nq0tbVhaGioghPX19cpJxaLxde4o66ujnpXLS0tKBQKmJubo5y4v7//VhWz1wHCiSQq9ionrq+v03DoT3Hi5eUl5ubmKCe63e53UoBAlZQgCfs1NzdjaGgIX3zxBSwWC4RCIbxeLxYWFrC5uYlUKlXxQrLZbPD5fOj1eoyOjmJkZAQSiQS7u7v485//jOXlZQQCgbduQbgOuUi15MDAAJ48eQKbzUa9ntXVVayuriIWi1W8kKTIRK1Ww263Y2xsDCqVCqFQCFNTU3jx4gUCgQDy+XxV5CKerUajQV9fHx4/fozx8XEolUrk83lsbW1hcXER4XC44oUkn5NKpTSvpNfrkcvlMD8/j6+//hqBQKBqnhI5n1KppEr64cOH0Gg0ODs7w97eHmZnZ6n3Tc7IMAy4XC4EAgFMJhMePHiA5uZmHB8fY319HX/zN39D8xTVyN0yDAMOh0PbayYnJ/HkyRM0NjbS0Pr09DQ8Hk9FUQz5HKnevX//PiUep9OJv/3bv4Xb7aZFCNUwWthsNurq6tDW1obR0VF8+eWXaG9vB5vNhsPhwMzMDHZ3d6lyJ3eMyGU0GjE5OQm73U5J+Pe//z22trZodXI15CItOSRn/sUXX6CnpwdCoRD7+/tYXFzExsbGa8qdcI5Op8Po6ChGR0dRV1cHl8uFP//5z1haWqo6JxLOJpxot9shk8kQi8Wwtrb2k5xos9kwNjYGtVqNSCRSwYkHBwfvLNeNK0HSV6bT6dDX14eBgQEYjUaIRCJaJej1ehGPxyssTQ6Hg7q6OpqvsVqtqKurQygUwtbWFpxOJ0KhUFUftkgkglqthsViweDgINra2iCVSnF0dIRwOIz9/X1EIpHXFLtIJKLhGbvdDqVSiWQySXMvRAFWS1EIhULU19ejq6uL9vUpFAqcnZ0hEonQwpZy75vE/0krxMjICHQ6HQ4ODrC9vY3d3V0axqhWkQ+fz6cVZ8PDwzCZTFCpVCiVSojH4/D5fFQBkneKxWKBx+OhubkZVqsVk5OTaG5uxsnJCXZ3d+FwOODxeJDP56sWKiQ5wJaWFgwODqKnpwdarRZsNhuxWAyBQAAej6cit0wUu1arRX9/Px4+fIjOzk4AgNvtxvb2Nvb29pBMJqvmKXE4HEilUjQ1NdG2hqamJnC5XKTTaQSDQZpbJiFeUhREUi6Tk5O0qGJ/fx9bW1twuVw0BFotT+lNnHhwcIBQKASPx4N4PF6h2IlBUM6JUqmU5m1vCyeqVKrXOLFYLFZwYrliJzlRs9mMoaEhDA4OQqVSIZVKUU4kVejvgxNvTAmSWLdUKoVOp0N3dzfsdjtMJhPq6uqQz+ext7eH7e1teL3eispO8rCbmpowPj6O+/fvQ6vVIp/PY3Nzk4bi8vl8Vaw4gUCAuro6NDQ0oK2tDTabDb29vaivr0exWITX68X29jbcbneFd0A8Yq1Wi6GhIXzyyScVhLq0tERDcdWQi8fjQSKRQK1Ww2g0YmBgADabDQ0NDTg7O0MwGMTW1hb29vZoZSchHlIB1t/fj88//xydnZ24vLyEx+PB0tISDcVVK+xELmdzczMGBgYwODgIvV4PAAiHw9je3obL5UIoFKogR1IVSyaM9PT0gM1mIxAIYHl5GU6nE+l0uiqkQ7wdpVJJFcXg4CCMRiM4HA7i8Th2dnaoYVXutZNQXGdnJz7++GMMDAxAJBLRAp/yUNxNPzNiUMlkMjQ2NlJC7ezshFAopOHdnZ2d1+5LeVXsgwcPMDo6ivr6eiQSCayvr1eE4m5arnJO1Gq1lBPNZjOkUukv4sTDw0NsbW3dCk6USCTQaDS0FoBw4vHxcQUnxuNxqswIJ5Jc72effQaj0VjBifv7+++VE29MCXK5XDQ3N8NkMqG3txe9vb3o6OiAUqnEyckJdnZ28Oc//xkrKyvUmiNEwufzYTQaMTQ0hKGhIRiNRiSTSWxvb+P58+dYWVlBNputWhiDKPWenh709vaiq6sLOp0OFxcX8Hq9+OabbzA/P0+tOaIEORwOGhsbYbPZMDQ0RCvAXC4Xnj9/jvn5ecTj8aoVi6jVanR3d8NisVC5WlpaALzsB3zx4gWmpqawt7dHrTnynTQ0NMBms9H4f6FQwObmJv1MKBSqmlyktYbI1d3dTUNq0WgUMzMzePHiBXZ2dl4rsFIoFOjt7cXIyAhsNhsA0PDi1NQUvF5v1YpgxGIxOjo6YLFY0NfXB5PJRIcspFIpLC4u0mIdv9+Pg4MDKpdEIqHTRex2O6RSKdxuN+bm5vDixQta+FQNo4VEFEwmE6xWK8xmMzo6OqiiWFtbw7Nnz7C+vg6v14tMJkPfrfLqUbvdDo1Gg1AohJWVFTx//hybm5vvnFP6pSCc2N3dXcGJKpWKkv7bcmJLSwtSqRQcDge+++47rKysVHwPN4lXObGnpwfd3d3Q6XS4vLyE2+2mnEiUIImacDgc6PV62Gw2DA8Po7u7G9lslnLi3NwcEonEe5XrRpQgCWV2d3fj/v37NPQkEolQKBTgdruxsrKCZ8+eYWdnp6KJnFgGHR0dmJiYoNafx+PB/Pw8NjY2EAgEqhJ6Ik2f7e3tmJycpFVZdXV1uLi4gNvtxsbGBr799lssLy/TRnngByuwubkZo6OjsFgskMvl2NrawsLCAlZXV7G/v1+V0noWiwUOhwODwUDzDFarFQqFAhwOBx6PBw6HA8+fP8fz589pzyORi8vl0jLovr4+NDQ0YGFhAUtLS1heXobb7a5K8zjJeel0OgwNDWF8fBz9/f10OPn+/j6cTiemp6fxzTff0GZr8lkyYcRms8Fms6GxsRG7u7tYXl7G0tISnE4nstls1eRSq9UYGBjA/fv3MTAwgKamJohEIkQiEXg8HszNzeHZs2cV1Y8Mw9AJI6QE3Wg0Uk9pYWEBOzs7VWuyJrnNnp4e2lva2toKkUiETCaD/f19LCws4NmzZ7TyujwkL5FI6DjF9vZ2nJ+fY2dnB3Nzc9ja2kI4HK5KOJ60NHR1db3GicVisYITHQ7Ha5xIlPv4+Dg6OzshEomwtLREOdHv91dNLoFAgNbWVkxMTFBOlEqlr3Hi0tLSa5xIpi6Vc+L29jYWFxextrYGr9f73jnx2semkVFojY2N9JK1tLTQmXHxeJwSJAmpXV5eUtLh8XiQyWRobW2FyWQCh8OhYTifz0fLpG96hiFpZtXpdLBYLBgeHqbWKcMwyGQyWF1dxfz8PILBYEVFF8krkfJ6i8UCsViMSCQCh8MBt9sNNpsNrVZ74zMMy0OZ3d3dGB4ehtlshkKhAJvNpuGWubk57O/v4+joqCKUQWak6vV6mM1m1NfXI5lMYnd3F7u7uzg/P4dWq4VEIrlxuUgok+QA+/r6oFarwePxcHJyApfLhdnZ2demwxCjoPx7IflNki87PDyESqWCTCa7cbk4HA4UCgXNAdpsNuh0OvD5fJydncHn82F6ehrb29vIZrMVhTCEtJRKJbq6umA0GnF8fIz9/X2sr68jlUpBLpejvr7+rUasvU+QUGZ5yLqpqQlCoRCXl5cIh8OYmZnB+vp6Ra6SyEVyvh0dHTQc7/f7sbGxgUgkQquCb3pebTkn9vX1YXh4GK2trRCLxQCARCKBhYUFLC8v/ygntrS00EEahBP39/dpG8hNz6slFclarZZyYmdnJ2QyGRiGQTabxdra2k9yosFggMVigUQiQTQahcPhwN7eHh2cLRKJ3uu5r+3pEyVB+sN6enowMDCA1tZW8Hg8JBIJxGIxSqg7OzvIZrOUUMkLSkirt7cXjY2NODg4wMHBAfU2mpqaaLn2u0wN+DkQCoX0cpI4fnt7O8RiMTKZDOLxOPb29jA3N0erXMm5xGIxlEol1Go17S8jk9DT6TQYhoFGo4FGo0Eul8Pq6irtUbvuUBSfz6d5F6Iouru7IZPJcHh4iGQyCb/fj7m5OaytrdHxbaVSiRKpSqWi4YyWlhYIhULE43GUSiUolUrIZDIcHx9jbW2NKtDrlosUimg0GnR0dNDeUpVKhePjY0QiEUSjUczNzWF5eZmOb7u8vKStPEqlEg0NDRgaGkJHRwfq6upoc79MJoNAIMDZ2Rl2d3dpEdN1h6LYbDakUinUajXa29sxODiIvr4+aLVanJ+f0yk8c3NzWFxcxP7+Pi1DZ7FYVC61Wg2r1Yquri7U19cjlUqhWCzSyUWlUom25xwfH1+7R0g8ONIfZrVa6T0BgGg0ilgshuXlZczPz8PlctEqQbIWibyLJpMJZrOZ9m8WCgXw+XwYDAYYjUb6rHO53LXLRZSEQqFAa2srLBYLvSeEE+PxOOXEV3tMyzmxra0NfX19aGxsRD6ff40TSdrlpjnRYDCgq6sLg4ODr3EiCa9vbm4imUy+xokkR0+edalUQiwWA8MwaGhoQENDA3K5HNbW1uh7+D6449qUIAk79ff301ChwWAAn8+nVgv5Qnw+H714wMuXxWAwYGxsDDabDRaLBQaDAQKBgH4pDx8+BIvFoj00qVQKh4eH114JxWKx6NBdMs3BaDRCIpEgFovRUMvq6ip8Ph8SiQQN/ZGHOTY2Rqv2WlpaIJfLadXo8PAwxsbGAIA2kKfT6QqP67ogk8lo0/fk5CQ6OjpQX1+PdDoNp9OJxcVF2nMUjUYrehblcjmGh4cxODiI/v5+tLa2QqVSIZPJIJfLwWKxwGq1AgAtsY/FYjg6Orr2ULZIJKLFFJOTkzCZTNBoNDg8PITT6cTKygrm5ubg8XgQDocrqkFFIhEtMOnv70dXVxfUajWOj4+RzWZhNBrR3t4OhmGQTqfx29/+llauXTUQ4X2Cz+ejo6MDdrsdk5OT1FAk7R1ra2uYm5uDy+Wi00KId8vlcmlFcn9/P/VuS6USDg4OoFQq8Zvf/Ibuefz2228RCATe2H/3PkGqb202G+7du0dDuywWCx6PB5ubm9RwJtNCysPWpH2iv78fZrMZjY2N4HA4KBQKEIlE+Pzzz8FisXBycoK5uTl69940y/d9geS7+vv7aajQYDBAKBReyYnJZLKCExsbGzExMYGBgQHKicTIBIAHDx5QTiTtFDfFieUbRu7duwej0Yi6ujpajFXOieW7NcmOSsKJvb29MBqNUCgUiEajOD4+pj2TAGjlNTFobnV1KCn6mJiYwNjYGHp7eyEQCJDP51EoFBCPxxGJRJBOp2kJs1KppGGnwcFBPHr0CFarlVpKp6endMGsRqOBWCxGsVhELpdDXV3dG0dAvU8QJUhySjabjcbxi8UikskkIpEIEokEgJfKQSaT0bJfi8WChw8fwm63o6Ojg66NItYQWcZ6dnaGy8tLyOXyN46Pe58gU13IKLShoSHaBhGNRpFKpRCNRhGJRHB+fg6pVErHifH5fLS2tlbkNqRSKc7Pz3FyckIt8/r6elxeXqKurg5KpRJcLvdGQmxisRgWiwWTk5MYHh6GVqtFqVRCNptFJpNBLBZDOBzG8fExJBIJRCIRDc9otVpMTk5ibGyMeo9kOalUKoVEIkFDQwMAIBQKYXl5GTwe70ZWXQkEAnR2dtJcGakCjUQiyOVyVK7Dw0MIhULw+XzaGymTyTA+Po579+6hp6eHKsB8Pg+pVAqFQkHbKhKJBJxOJ4RC4Y3IxeVyYTQa6aDkzs5O8Hg8ZDIZung5HA4jm82Cx+NBpVLRsLBIJKKzhHt7e2EwGMBms3F0dASJRAKBQACtVgs+n09bssRi8Y2ERIljMDY2hrGxMfT19V3JialUqoITCXfY7XY8evQIfX19NKJ2enpKUwuEE4+Pj+lzvClOVKlUGBoawsTEBOx2e8VKK8KJJCJUzokCgYByYrn3eHZ2Roc9aDQamlMEQGsT3hd3XMuTJ71vBoOBznorJ3JyCdva2uiOPRLLF4lEUCqV1KpQqVR01iZZMHt+fg4ul4vLy0s6hPry8hKlUulaLVTyMpKp+h0dHRUz78hcQqPRCDabXRHqI+FCkqTX6/V01ibxEGUyGbhcLgDg+Pj4xhqSCeGTUU0mk4nuHSN5CLFYTPO65aE+Mh6OTLpvbm6umLVZX18PkUhEX1ri+ZEX+jqfF4vFonkl4omSbe+Xl5e0wECr1aK3t5eGQEulErhcLg3vjI2N0ZVPbDabFpIQZcfhcOgovJsI7xLCr6urQ2dnJ+x2O9RqNVVQpIFarVbDZDKhqamJ3jHSa6fRaKhil8vl9LPk/QVeKiMyNPym5CIFIy0tLRgeHoZOp6NETvK6pJVDpVLRc5HPKZVKjIyMYGBgAAqFghpahI8uLi7A4/FwdnZWIdd1y/YqJxqNxoo5oOWcKBKJruREq9WKkZERqNXqCk7U6XQ4OzsDj8d7jROvG0SRabVaut6IcCKACk5ksVivcWL5HtjGxsYf5UQyOPx9e7XvVQmSwoimpiZYLBaMjIygtbW14pKRfqSOjg6aayJfCnngMpkMRqMRjY2N4PF49CUll+Tk5ASpVAqxWAxerxfLy8u0/+46XmZSGNHQ0ACz2UyrVMv3lpEqNlL009HRUSEXn8+HXC5HY2MjbYQtl4u80MlkEolEAn6/H2trawiFQtcWViNkSkjl3r17MJlMaGhooBe0fEo/j8eDwWCouFzk8pLde6QwpFwuNpuNTCaDVCqFQCAAh8NBK1+v66KStU1kLB9pGOfxeJR4SAEPm82GRqOpuFxEWajVatrKwzBMReUhl8tFLpejjdq7u7twOp1vnMf5vuQSiURoaWnBwMAA+vv76T0hchFDrVQqQaVSVYSby5VFe3s7NBoNJaxSqUTf9Xw+j3A4jFAohL29PWxtbb235uSrQCIKzc3N6Ovrw+DgIN1RSc5HZgZ3dXVBoVC8VglKahDa2tqg0+no3SznjuPjYyQSCUQiEVqBSfJu18UdXC6X9jeOjIygra3tSk5sb2+HVCp9jRPLaxCampreyInRaBTxeJxyImk9uI47Roz+hoYGmEwmyokqlaqCE0kBj1AoRHt7+2ucSGoQjEYjxGLxj3JiIBCo4MT3JRfzYw+eYZif9VaQ6p6PP/4Y//gf/2O6j638gpZbKmdnZ69pdXIJeTweBAIBSqUSLi8v6efS6TTdJLy6uorZ2VmaO7suUiV7vUZGRvCXf/mXGBsbo+XnxLstlUo4Pz+ncl01P5NUdpHde0Su8/Nz5HI5xONxuFwurK+vY35+HltbW8jlcteWqyDE0dPTg3/2z/4ZPvroIzQ1NUEqlVaEGohcV620IoqUjBEjXhaRK5/PI5lMUiIlsydTqRSdC/u+yYcYU+3t7fjNb36Dp0+foqWl5bUKx/Pzc/ouvkqChFxIAzqHw6FyXVxcoFAoIJ1Ow+PxYHt7GwsLC1hZWUE8HqcNytdBqiKRCHq9Hl999RX+4i/+Ap2dndBoNBWbBS4uLiru2KtykTsmEAhoRIX8KhaLSKfT8Pv92NnZoZXboVCIFvxch1xkkP6TJ0/wm9/8Bj09PWhsbKReAcMwr8lVfifKDS6BQEAVBZGL7CYNhUJwOp20ncDn8+Hg4OC1v+99gQyc+Oijj/BP/sk/gd1uf++cmMlkEI1G4XQ6sba2Riucb4ITh4aG8M//+T+nnFgeQSIc8K6cuLe3V8GJ2Wz2Z3NiqVR6Y0z4vXqC5OGQuW98Pr9iBQ3R8OTPfuwylXt7JJFaKBToFuFQKET7ulKp1PsU441ylZ/91Vg7CWmQy/cmnJ6e0ocbi8WQz+dRLBYRi8Uq5HK5XIhEItcqFwAqF1FiV+XpuFwubX14k2zn5+c4PDxEKpVCJBLBwcEBisUitbpDoRD8fj9cLheCweC1V+K9OjPyx+QiXvlVIBsJiPGVyWRwfHxMc6RELrfbDZ/Pd+19nUS5cjgc8Pn8K+XicDg0t/4muUqlEt0nSHK+JL8eiUQQDocRCATgdrvh9Xqvva+TeADlSuxV7mCz2fTPf+yOFYtFxONxRKNRJJNJHB0d0Z11kUgEwWAQbrcbbrf72vcGvsqJV8n1LpxIRjKSd9Hr9cLlciGZTN6IXIT3XuVEItfbcOLZ2VkFJ5JinnJO9Pl8cLlcCIfD712W96oELy8v6eZjv98PnU4HmUx2Zb8KCb2QX+VW7Pn5OQ0xraysYHNzE4lEAplMBoFAAMlkksb0b6JJvlQq4ezsDNlsFn6/HwaDAXV1dW/82XKrlMhVbt1EIhG6RSESiSCbzSIcDiMSidy4XOfn5zg4OEAwGEQgEHhjkcCb5CJ/x+HhIe1zXFpaQjAYRDabRTQapcuRiVw3oQDLz+Tz+VBXV0etzTfJRX6R/39xcYGjoyMaeVhaWqJDp2OxGO11KrfirxvkTLFYDD6fD3K5/Mp3kchFPNpX5To9PUU0GoXH46Hj3rLZLF2+Svokb0quy8tLGqr0+XxQqVSQy+VXFj+Uc0d5oQ7hjng8Dr/fj5WVFTgcDqRSKRqKJ6HPm5Tr9PSUeteEE6/qa34TJ5ZHwci0m83NTcTjcWQymYpF29XgxEAgQKtBryrCeRtOjEajr3FiKBS6EU68FiW4v7+PZ8+e4eDgAPF4vCKuT8jp/PwcarUaWq0WWq2WVknGYjHs7e1hb28PTqcTXq8XwWCQehbZbPbGp40QUg2Hw3jx4gUODw8Rj8fpJSWhmkKhgOPjY6hUKmg0Guh0Ojo9JplMwu12Y29vDy6XC263G36/n4Y7c7kcDg4OqiJXMpnE3NwcbVsgeSIS0jg6OkKxWKQzDrVaLRQKBUqlEnK5HPb29uB2u+FyueDxeOicw2KxiHw+j2w2e+Pjti4uLpDNZrGysoLLy0skEgmanCeXsFgs0rL5hoYG6HQ6KJVKsFgsFAoFeDyeiufl9Xrp/Ewi101PUbm4uKADC9hsNlKpFLq7uysU+MnJCQ4PD2nORqvVQqPRgMPh4OjoCIFAAC6Xi8rl8XgQjUZxdHSEQqFQ0VB/UyChWJfLhT/96U+0t6y8CvDs7Az5fJ4WTZA7RoYdhEIh+h66XC54vV5aHUvkIqP9blKus7OzCk5MJBI/yolErlc50e12w+l0wuPx3BpOJDtBDw8PEYvFoFAoruREpVJJ5SKVnqlUqoI7CCeScOdNceJ7D4een5/TzcypVArxeBxisZhabCRPxGaz6TLc8i9la2sL09PT2NzcxM7ODg4ODmhjJMnH3DSIXIlEAvPz80gmk0gmk7RUFwB94GdnZzCZTLi8vIREIgHDMMjlcnA6nZiamsLa2hp2dnaokiCVltXaFE+a9FdWVqjFTErjy5XgyckJWlpacHFxAZFIBB6Ph0KhAK/Xi6mpKSwvL9PxWkdHRzQXdRNN/m+S6+DggO70y2QytIWAFLgcHx/j6OiIVocKhUIIhUJKqDMzM5ifn8fOzg7C4TAKhQJNyF9cXFTlmZHnQQZ1ZzIZ+P3+CmVBlKBCoUBPTw9dZ3V+fo5IJIKlpSVMT0/TPrvDw0OaO6rWu1huQB8cHNCwH5fLpdxBlCDp+yQ7Lo+PjxGLxbC+vo7p6WlsbW3B7XYjn8/fGu4g708qlUIikXiNEw8PD8EwDCwWCwBAKpXi8vKSzkienp7GxsYGdnd3qfK7DXKR6TaEE+vr66/kRLKSSyKRgMViIZfLweVyVXAiCcnfNCe+9xYJQi7n5+dwOp3I5/M0CQz8sNm5o6ODWt5ktBNpqHQ4HAiHw9TFr9ag5VdxenqKbDYLt9uN4+NjCIXCirYPtVqNlpYWankDoLMNl5eX4XA4EAgEEI/Hq7a37CqcnZ3h4OAAPp8PZ2dnqKuro4TK4XCgVCrR3NwMtVoNvV4PDoeDUChEl+KScU1EAV5XUcjPBSGXUCiEUqkEr9dL5SJtDgaDASqVig5jSCaT2NjYwOLiIjY3N+FyuZBIJGgD/W2Qi5DL+fk5GIZBJBKhcjEMQ7cLkOXOEokEuVwOOzs7mJ+fx+bmJhwOB+LxOHK53I20P7wNiDdIemwzmUxF+IxU8+r1ejQ2NtIKUbfbTQuudnZ2aP/xTUzteRuUc2KpVMLh4eGVnNje3g6dTkdbP5xOZwUnhkKhW8uJHo8Hx8fHFcWChBONRiONIAGAz+er4ES/319VTryWPkESLyYJ3PIeH51Oh7a2NlgsFnR3d9NpKfPz8/irv/orbG1t0Wqt23Axy0GsH2KBk4dNZlKSdSjd3d3Q6/U09/e3f/u3WFxcRC6Xq9ok/p/C5eUlcrkcDTcBoL1ypH/JZDKhpaUFsVgM29vb+O1vf4tvv/2WFovclotZjsvLSzqknchFKtusVisMBgPdtpBOp+FyufD111/jT3/6E2KxGN0gcdueGSHW/f19+P1+AD/0bHV3d2NwcBBmsxldXV04PT2F2+3Gt99+i9/+9rd0GeltlYt44qQwjBSVNDc3o6enh8rF4/EQCAQwPT2Nv/u7v6sYn3Yb5To7O0M8HkcikXiNE1taWign1tfXIxwOY2FhgXIimfZzG+X6MU7UaDTo6uqinEhyf3/3d3+H+fn5W8GJ1zomofyS8fl8tLe3w26348GDBxgYGKCT+//4xz9ienoabrf71irAcpTLxWazYTAYMDAwgAcPHmB4eBgymQzhcBh/+tOf8OLFCzgcDmSz2VsvF4AKRUZ20t27d49udk6lUvjuu+/w7bffYnV1Fel0+lr7/d4Xys+nVqvR19eHiYkJTExMoKmpCYVCAfPz8/jzn/9MBxcTr/Y2g4ScgZdj78xmM50E09HRQccK/uEPf6CtDtVaHfRzUC6XUCiEyWTC0NAQ7t+/T3c4Op1O/P73v6fD3Ku1ePrn4FVOJEunHz58CJvNRjnx66+/pmvKbqsCLEe5XCwWC01NTZQTR0ZGqLNDOJEMc78Nct3I+HQejweFQkEvKOkfDAaDcDgcePHiBZaXl3FwcFC1bdy/BMSj6OjooLPv2traEIvF4HK5MD09jdnZWaRSqaqsRPqlII3LLS0tGB0dpdPg8/k8nE4n5ufnMTMzg1gsRmcb3gUQj6KxsZHOaCX5W7/fj8XFRUxNTSEYDN4JBUhAJv5oNBrYbDZMTEygp6eHzqRcW1vDd999VzFA+y6AlNiTSUYTExOwWq1QqVQIBoPY3NzEd999h52dnTuhAMtBoiwmk6mCE0OhEHZ2dvDixQssLS0hl8vdOU4kw0LGxsYwNDSEtrY22u83MzNz6zjxWpUgKYslY7WsViusVivUajUKhQK2trawtLSEQCBQsbrmtoPIJZPJYDAY0Nvbi/7+fuj1erpJYH5+Hl6vt2Jo8V0AWfOi0Wjo5g8yRmt/fx8zMzPY29ujHuBdARmdpdFoYDKZ6OxWLpcLr9eLmZkZ7Ozs0OrPu6IAiaIo30xO9tLFYjEsLCxgY2OD5mvvkgIkOxI7OjowMDCA3t5eyOVyZLNZrK6uYnV1FZFIBIeHh3dKrqs4saGhAUdHR9ja2sLi4iJdenxXuIOEd2UyGZqamio4sTy/6fV6q1J9/GO41lVKQqGQhmjINoj6+nrk83kEg0EsLS1hfX0diUTi2ifuv0/w+XxIpVK0t7fDZrPBarVCo9HQXMbKygqWl5fptvW7QqikipCMriLT+0ulEvb392khjN/vv1OESuZs6vV69PX10dmNbDYbwWAQ6+vrmJ2dhdfrvVOESma6NjQ0oLe3l+60FAqFFWvKnE4nDg4O7oynRAwWhUKB3t5eDA4O0pVeqVQKbrebFmSl0+k7pSiEQiGkUinlxJ6eHiiVSuTzeYRCoTvPiW1tbRgYGIDVaoVWq8XJyQnC4TDlRDKo/jZx4rUpQTabDZVKhe7ubnzyySeYnJyEXC6n62tImTa5oHflYZOqwu7ubty7dw+ffPIJVCoV9QDX1tbw4sULbG5u3siOsvcFhmEgkUhoGOPTTz9FU1MT2Gw2lWt2dhYrKysVex/vAsima7vdjs8++wwdHR0QCATwer10HBMp874rhAq8DKkZDAZYrVZ89tln6O3thUQiQSgUwsbGBhYWFjA7O0uJ566Aw+FAo9HAYrHgyZMnGBwcpAqQRI+mp6fpUue7ArIZoru7G48fP8b9+/chl8tRKBTgdDqxvLyMqakpOJ1O5HK5O8WJMpmsghPVajX1ANfW1jA1NYWNjY2q9Nb+FK5ljw2xvNva2ugaGrPZDIZh6LLZ6elpuFwuupj0LoBY3gaDAaOjozRHwefz4fP5sLi4iOfPn9Py87tCPGTrgE6nw9DQECYnJ2G32yGTyeh6oBcvXmBjY4M2Vd+FC0qq78ius3v37mFoaAgajQaJRIJezpWVlTtTMAL8EAJVKBSwWCx0hZXBYMDBwQE2NjYwPT2NxcVF+Hw+5HK5OyEX8MMC5K6uLlpU0d7ejpOTE+zs7NCcksfjoW0QdwFvw4kvXryA0+lEMpm8U5xItmOMjo5ifHwc/f39EAgEFZy4vb2NWCx2KznxWjxBoVAIjUZDLVTSZE2KRebn5+FwOGj5+V0BSdKbzWZ8/PHHsFgsYLPZ8Pl8mJ2dxezsLDY3N++UZwu8JB6FQoHOzk48ePAAQ0NDEIvF2N/fp0Uwa2trSKfTd4ZMgR82QbS2tmJychKTk5Oor6+vKIJZXV1FLBa7M2QK/LB5nRDPxx9/TCt319fXaaEZ2Zp+V0AGn+v1ethsNnz22WfQ6XQ4OTmhBXTz8/PweDx3ygMEXkYjGhoa0NfXh88++wytra24vLzE3t7er4ITTSYTPv74Y/T09IDD4bzGibfZs70WJSgWi6HT6dDU1EQTvpFIBKurq1hfX8f+/j6y2ex1/NPXCrKixmAwQKvV4uLigm7wXltbg8fjQSqVulOKAnj5Ijc0NMBgMNAVND6fD2tra1hdXYXT6aQ5irsELpcLpVIJg8EAvV4PoVCIUCiEzc1NrK6uYmdnh3q2dwlsNhsKhQJNTU3Q6/WQSqVIJBLY2dnBysoKtra2EA6Hkc/nq33UnwWytkuv16OpqQkqlQrZbBb7+/tYWVnBxsYG7XG8a3iVE4vFIjweD9bW1ignZjKZah/zZ4PsEjQYDHQdWTknut1uJJPJW82J710JkjFoTU1NkMvlODo6gs/nw8rKCubn5+Fyua59cvt1QSQSobGxke5oc7vdWF1dpZWFqVTq1lo7PwYSCtVqtbi8vITP58PGxgZmZmawtbWFeDx+pzwlAtI2QHKbkUgE6+vrWFhYwNraGsLh8J1T7MAPU3yumnKzvLwMv99/p1pXCBiGgVwuR1NTE+rq6pDL5bC9vY3l5WUsLi7C4/Hg8PCw2sf8RSCcSKbckAHfc3NzcLlcd9IpAH7gRLVajbOzM3g8njvHidfiCcpkMjQ3N4PH42Fvb48+bFJaf5dCNOWQSCRobm6GVCql63NIHJ+U1t/2B34VhEIhDAYD1Go1YrEYotEopqamsL29TT2l22zJvQk8Hg86nQ56vZ5uICEJ+lAodKd65spBFjwbDAYUi0VsbGzQ0K7P57tzPXMEpHWgubkZpVIJ29vbmJ2dxdLSUkXT+F0DcQzKOZEUmt3FdqNykBoJqVSKQCAAj8dDOTEej98JTrwWJcjj8SAWi3F4eAiv14uFhQWsrq7SZvi7SKjAS/KRSCQ4PT2Fw+HA2toalpaWkMlkbmRF0HWBbBsHgL29PTgcDiwuLiISieDk5OTOykVyZzwejxotCwsL8Pl8dADxbb+gV4G0EAgEAsRiMfj9fiwsLMDlctGZondRLoZhIBAIIBKJkMlk4HA4sLCwgM3NTdpHfBflAl62EIjFYhQKBTo7c2Vl5c5zIpfLRV1dHc7Pz+FwOLC+vo6lpSWk0+k7w4nXogSj0Sjm5+fB4XCQTqfpap27aJ2WI5PJYGlpCRKJhO4Hu0uVXG9CPp+nlZ9kZ9ldzJW9imKxiJ2dHbpuhuw2vGu5sldxcnICj8cDFouFo6MjxONxuiH9rpIp8HIweDAYxMzMDN2g4Ha7b2VZ/c9BqVSinMjj8ZBKpX5VnLi8vEwr/QOBwJ2rH2B+zLJiGOYXmV1k6zXwwz6tu/6wgR/GibFYLLrA8y6GZ14FGSfGZrPpiqC7bHUTkHFiHA6Hrma5TRP4fylIiwSXy6VynZ+f32lFQcDlcukSbvK8fg1ycTgcujmixok3j1Kp9Pq23+9xLUqwhhpqqKGGGm4LfkwJXkuzfA011FBDDTXcBdSUYA011FBDDR8sakqwhhpqqKGGDxY1JVhDDTXUUMMHi5oSrKGGGmqo4YNFTQnWUEMNNdTwwaKmBGuooYYaavhgUVOCNdRQQw01fLCoKcEaaqihhho+WNSUYA011FBDDR8sakqwhhpqqKGGDxY1JVhDDTXUUMMHi5oSrKGGGmqo4YPFtewTrBaEQiFkMhk4HA4uLi5QKBSQz+fv/EogPp8PqVRKV8wcHR3h4ODgzq+Y4XA4kMlkEAgEYBgGxWIRBwcHt3IVy88Bi8WCVCqFSCQCi8XCyckJDg4O7uz2cAKGYVBXVweJRAIWi4WzszMcHBygWCxW+2jvDLFYDKlUCjabjfPzcxweHuLw8LDax3pnCIVCSKVSunaLyHXX14m9T0781ShBhmHQ1taGjz/+GAqFAkdHR1heXsb09DSOj4+rfbxfDIZhoNPp8PjxY+j1epyfn2NzcxMvXrxAJpOp9vHeCQqFAo8fP0Z7eztYLBacTie+++47RCKRah/tnSAUCnH//n309vaCx+MhEAjg2bNn8Hg81T7aO4HNZmNoaAhDQ0MQCARIJpN4/vw5NjY2qn20dwKLxYLFYsHDhw8hEomQy+UwNzeH+fn5O60sGIZBa2srPv74Y9TX16NYLFJOvMuGC8Mw0Gq1ePz4MRobG3FxcUE5MZ1O/+y/79YpQS6XCz6fj/Pzc5ycnLyVF8fj8VBXV4fu7m589NFHkEgkCIVCCAaDYLPZN3DqnwabzYZAIECpVMLx8fFbXS4Oh4O6ujq0t7fj/v37aGxsRDKZRCqVApfLvYFT/zRYLBb15I6Pj9/KEmOz2RCLxWhubsb4+DjMZjMKhQKOj48hFApv4NQ/DYZhIBAIwGazcXx8/FYLUFksFoRCIfR6PYaHhzE6OorT01NwOBwsLCzcwKl/GmQhL4/Hw8nJyVttACffhUKhgM1mw8cff4yLiws4nU6sr6/fwKnfDjweD3w+H6enpzg9PX0r7uDz+ZDJZOjp6cFHH30ENpsNr9eLvb09MMwbV9DdKN6FE7u6uvDo0SNIpVKEw2EEg0FwOLeD9n8pJ0okEsqJTU1NSKVSSKfT1Cv8ubhVOUGGYSCRSGA0GtHQ0PBWCoxhGMhkMpjNZvT19aG1tRUsFguRSATJZPLWWHIikQhNTU3QarVv/bDEYjE6OjrQ39+Pzs5OCIVCRKNRxOPxWxMy5PP50Ol0aGpqemsFxufz0draCpvNhq6uLshkMiSTSYTD4VvjtXO5XDQ0NMBoNEIikbwVIfJ4PDQ1NcFut8NkMkGlUiGXyyEYDOLo6OgGTv3TYLPZUCqVaG1thVQqBYv10xTA4XCg0WgwMDAAs9kMnU6H4+NjBINBHBwc3MCpfxpsNhsymQytra2or69/K7nId9HX14fe3l40Nzfj4uIC4XAYmUzmVqRRCCc2NzejoaHhrRQYwzCQSqUwm82wWq1oa2sDm82mnHhb0igikQiNjY3Q6XQ/ixM7OzthtVrR0dEBkUiEWCyGWCz2VgbdVbgdJgFevpBCoRBGoxF2ux2RSAQnJyfIZrNvtOq4XC7kcjk6OzsxMTGBgYEBqNVqBINBBAIBJBKJqj9wFosFPp8PvV6PwcFB6lUkEgkcHx9fKRfxAFtaWjA6OoqhoSHodDoEAgEEg0FEIpGqK0GGYcDlcqFWqzEwMAA+n49SqYRQKIRisXil8UE8QPJdjI+Po7m5GUdHR9RKrbYSJHIpFAr09PRAp9NhYWEB+/v7KBQKV75PDMNALBZDo9Ggv78f9+/fR1tbG3g8HuLxOAKBAAqFQhWkqQSXy4VMJkNXVxfMZjOWl5dxcXGBw8PDN75PQqEQarUavb29uHfvHrq6uiAWi5FOp+H3+2+FEiz3DgYGBrCzs0PzlW8iRj6fj/r6epjNZty7dw89PT2Qy+XY2tqC3+//RWG19w3Cic3NzbDb7YjFYm/FiTKZDJ2dnRgfH8fAwAAaGhoQiURuFSfyeDzodDoMDg7i9PQU5+fniMfjODk5uZI7yDM2Go0YGRnB8PAw9Ho9QqEQAoEAIpHI3VeCQqEQWq0WVqsVT58+xe7uLrVastnsa+EoYu10dXVhbGwMn3zyCTo6OsBms5FKpeiLXO0HzufzoVKpYDab8emnnyKfzyOTyeD09BQXFxdXPjixWIzW1laMjIzg8ePH6Ovrg0gkQjabhd/vRyKRqLoS5PF4UCgU6OzsxEcffQSxWIx8Po/j42PE4/ErlRmfz4fBYIDNZsNHH32E0dFRSCQSqiiI4VNNkGKd1tZW3L9/H52dnTg+PqYK8CplxuVyodPpYLVa8ejRI3z00Ueoq6tDOBymyr3aniCbzUZdXR0MBgNGR0fx8OFDlEolHBwcIBQK4fz8/DVSZbPZaGhoQG9vLx48eIBPPvkEKpUKh4eHiEajCAQCyOfzVZLoJYgBotfrYbfb8cUXX0AqlSKTyeDi4gLn5+evkSrDMFAoFDCbzZicnMSnn36KpqYmXF5eIpFIIBAIIJvNVt0TFAqF0Gg06Ovrw9OnT7G3t0ejW5lM5kpOJCFQwomdnZ3gcDiUE1Op1K3gRKVSSTmxUCggk8ng5OQE6XT6Sk4UiUQVnGi1WiEWi5HL5RAIBN4pOlZ1Jchms8Hn89HU1ASbzYbx8XH09vbi8PAQQqHwSvefxWJBJBJBr9fDarXCbrejtbUVDMPA5XJhd3cXwWAQuVyuauFQ4gESxT45OYn+/n74/X5IJJIr5WIYhr74PT09GBoaQkdHBwQCAfb39+FwOKhyf5sc1XWAYZgKxU488PPzc8hkMnC53CtDhwKBgH5maGgI3d3dkMlkCAaDcDgc8Hq9SKVSv9iaex/g8XiQy+UwmUwYHh6G3W6HVquFQqEAj8e7Ui4+n0+NgcHBQVgsFqjVaoRCITgcDrjdbmrhVgtcLhcSiQQdHR0YGhrC8PAwuru7oVarwefzrwwdks+QsHVvby8aGxuRSqWws7ODvb09RKPRqip3DocDgUCAlpYW2O12jI6OoqenB06nk+ZzX31mHA6Helc2mw39/f0wGo04Pj6Gx+OB0+lEOBzG4eFh1ZQg4cTGxsYKTiQ586vkehMnslgsuFwu7Ozs3BpO1Gg0lBOtVivC4TAkEsmV3PEqJw4ODlJO9Pl8cDgc8Pl8VxoFb4uqK0FiFfT19eHLL7+E3W6HSqUCABwfH1+p3Xk8HtRqNTo7OzE6OgqLxQI2mw23241nz55hdnYWwWAQhUKhai8yCal1d3fj6dOnGB8fh0ajoSG/q8IZbDYb9fX1aG9vx/DwMAYGBiAUCuH3+/Htt9/ixYsX8Pl8yOfzVbPm2Gw2pFIp2tra8Omnn+Kjjz6CXq+Hx+PBycnJleEMhmEgl8spoQ4NDUEulyMajeLFixd48eIF9vb2kMvlqiYXsaKbm5vx8OFDfPrpp2hpaUE+n8fZ2dkbwzTEu7JarRgeHoZGo0E6ncb8/DyeP38Oh8OBdDpdNc+93FMaHx/H06dP0dXVRQstSDHTq+8iydf09PRgZGQERqMRxWIRq6ur+O6777C2tlZ15S4QCNDQ0IDBwUF89dVX6O3tRV1dHS4vL2na4VW5CAmbTCaMjIygs7MT5+fncDgc+Oabb7C4uIhIJFJV5c7j8VBfX4/e3t43cuKrcnG5XKhUKnR2dmJkZAQ9PT1v5MRqKUEOhwO5XE45cWJiAhqNBtFoFMfHx1feMcKJbW1tGBoags1mg0gkQiAQwLfffoupqSns7++/U8tY1ZQgCTs1NTXBarVSa0coFMLj8VDP4Kr8klgsRl9fH0ZHR9He3o5SqYTl5WWsrq5ienoabrcbh4eHVSFU0iNGPECizBQKBcLhMPb29pBIJHB0dPSaXDweDyaTCaOjozCZTODz+dje3sbGxgamp6exu7tbNUVBlAQxWEipvFarRTKZhNPpRCwWu/J7Z7FYaGtrw+joKHp7eyGTyeDxeOBwODA9PY3NzU2kUqmqeLcMw0AkEkEul6O3txc2mw2jo6Nobm5GPp/Hzs4OIpEIVYavorGxEWNjY+jv74darUY0GsXOzg5mZmawtrb2Tgn7dwXpEevu7obNZsPk5CTa2tpwdnYGt9tNPYOrzqdWqzEyMoLBwUHo9XpkMhksLi5iZmYGS0tLCIVCb13R977B4/FoyLq/vx+Tk5Po7u6mbTZ+v5+G115VFnK5HIODgxgeHqYe4NbWFhYXFzE3Nwefz1c1RcHhcCCVSl/jRJFIhP39fXg8HqRSqSu/93JO7OjoAACsrq5STtzb26ua8Uw4kXiAb+LEq7iey+Wiu7sbY2NjMJvNEAgEcDgclBN3dnbemROrogRJyXVTUxNGRkbw5Zdfwmq1oq6uDoFAADMzM1hdXaVfDHmRGYahFV0TExN48OABVCoV3G43fve732FpaQler7dqChD4IT80MDCAL7/8EkNDQ1CpVEgmk1hcXMTCwgLC4fBrSpDkbAYHB/Ho0SPo9XokEgk8e/YML168gNfrRS6Xq5pHweFwoFKp0NPTg6dPn2JychJarRbFYhEbGxuYmZmB3+9/7aKRFoq+vj58/PHHaGlpQbFYxMzMDL7++mvs7+8jmUxWTS42mw2FQoGuri588sknePToEZqamgAAKysreP78OTweD3K5XIWSZrFYYLPZ9HMdHR24uLjA2toa/uqv/gr7+/u0kKFackmlUrS3t+PBgwd4+vQpjEYjOBwONjY28OzZM+zu7tL8NAHDMOBwODAajfjkk0/Q29sLDoeD9fV1/Jt/82/gdDqrqgCJZ2s0GjE+Po6vvvoK3d3dEAgEcLlceP78OTWqygvPCHfodDo8fPiQ5qPX19fx13/919jc3ITP50OxWKyaMUbSQsPDw/jqq69gtVohlUoRDAYpJ8bjcRwdHV3JiePj43jw4AHUajU8Hg9+//vf06KuakaPynPmX331FeXEdDqN5eVlyomvGh+EE+12Ox49ekRbxJ49e4bnz59jf38f2Wz2nbnjxpUgiV3rdDr09vZiYGAA7e3tkEqlODw8RCgUgtvtRjQarbDkSGVhd3c3hoaG0N/fD4VCgWg0iq2tLezs7FQ1VEjIniR87XY7Ojs7UV9fj5OTE0QiEXg8ntcIhPSWtbW1YWBgAIODg2hoaEAmk8HW1hbNl72Ph/1LQC4nURTDw8MwmUxoaGjA5eUlYrEY9vf34ff7K15iEv83GAw0pNbU1IRCoQCn0wmHw0FDoNVSFKRHjIRaLBYL9Ho9WCwW4vE4fD5fhQIslUq0z06n06G7uxsTExNobW3F+fk53G43tre34XQ6kcvl3lj9e93gcrk0tGu329HX1weDwQA+n49kMolAIIC9vT2aRyFyEUPHZDLh/v376O7uBpvNxv7+Pra3t7Gzs4NYLFZBwjcJNpsNiUSCxsZG9Pf3o7+/H62trbRoLBgMwuVyIZFIVKQbSNTJZDJR70osFiMYDFK5qhkqJJyo1WppNKK9vR0ymQyFQgHhcBhut5tWQL7KiV1dXRgaGsLAwADq6+sRi8Wwvb1NawiqNV2K5PPq6+thMpkwODiIzs5OKJVKnJ6eUk4MBoMVXiDh0vb2dvT392NwcBAajQbZbJbKRZyC9xFluTElSMhDLBajoaEBnZ2dsNvttDT56OgIPp8PTqcT+/v7SKfTFV+KWCyGTqejHqDBYMDJyQkcDgdWV1fh9/urFirk8XgQiURQqVQwGo0YGBig4bGzszMEAgHs7u7C6/VWVHaSl0StVmN4eJh6FJeXl3C73VheXobX66WVbjcNUkSgVCpp3stut0On01EFuLu7e6XRQnK9pNq3p6cHHA4HLpcLS0tL2Nvbq1qlGmnSVSgUaGpqQl9fH4aHh2EwGMBms5FIJOB0OuF2u6nXTuQiVbEmkwlPnz6leVu3243V1VVa1XxVPuq6QQwPmUwGvV5Pi6va2trA5/ORTqfhdrvhcrkQCAQqij+Iomhvb8enn36KwcFByOVyhEIhrK+vY2trixbCVEMuHo8HiUQCnU4Hs9mMwcFBdHd3QywW4+DgAF6vFy6XCz6fD7lcrkJRkD67Bw8eYGJiAlqtFtlsFpubm9jY2EAoFEI+n79xBUjacSQSCRoaGtDR0QGbzYaenh4oFAoUi8XXOJHcl3LFSTixubkZJycn2NnZwcrKCvx+P7LZbFXuGJfLhUgkglqtvpITg8FgBScS77ucEwcHB/Hpp5+is7MTpVIJbrebRvveJyfemBLkcDhobGxEW1sbzGYzenp6YLFYoNPpcH5+Do/Hg++++w4rKytwOp0VBEnCBAMDAxgeHkZ7ezvy+TxcLhempqawsrJStXYIFouFhoYGtLe3o7u7GxaLhTbeMgwDn8+HFy9eYGFhATs7OxWlvBwOBzqdjubYenp6cHx8jL29PUxPT2N+fh6xWKxqlaBKpRJtbW3o6uqCxWKBxWJBZ2cnuFwuwuEw5ubmMDMzA4fDQZPb5DtRqVTo7e3F8PAwbDYbnTAyOzuLmZkZBIPBqslFCns6OzupXCTfkEgkaO5rc3MToVCogvjlcjnMZjOGh4cxNDQEPp8Pj8eD+fl5TE9Pw+PxVC0HSMKEpA+QyCaVSpHNZrG2toapqSlsbGxQD4EQP/EoiFwqlQrBYBCLi4uYmprC7u7uG/s/rxt8Ph/Nzc1ob29HT08PlU2lUqFYLGJ7exsvXrzA6uoqPB4PstksPadQKERrayutim1qakIikcDGxgb9LqoVPSKc2N7eDpPJhN7eXpjNZjoe0ev1Uk4sbxkj34nBYEB/fz+tIs/n89jb26s6JzIMA41Gg7a2NphMJpjNZvT29sJoNILFYsHv9+PFixeYn5/H7u4u4vE4vTMcDgdarZZyIqmK3d7evjZOvBElSKyWjo4OTE5O0uqluro6nJ6eIhgMYnV1FV9//TW2t7dxeHhYEaYRCoVob2/HxMQELBYLZDIZdnZ2MDs7i8XFRezt7VUtVMjj8dDS0oLx8XGMjo6ir68PCoUCDMMgEAhga2sLf/rTn7C4uIjDw0MaziBhxubmZvq5hoYGzM/PY35+HnNzc3A4HFUJFZI8Q2NjI0ZGRjA6OoqBgQGoVCoIBAIEg0E4nU58++23+Pbbb3FwcFAR+iPKnYRoDAYDVldXsbi4iNnZWWxublZtODHpfbPb7RgbG4PNZoNer4dEIqHhmampKfzxj39EMpl8LUyjVCphs9kwODiI1tZWeL1erKysYHZ2Fmtra1Wb50qq6Pr6+nDv3j3Y7XYYjUbU1dUhlUrB6/VidnYWf/jDH14L/ZGpS319fRgZGUFHRwdyuRzN9a6uriIajVa1qMJkMlHu6OjoQF1dHQ4PD+Hz+bC4uIg//vGP2Nvbo/2c5I5JJBIaBiXFM6urq5iZmcHy8jL8fn9VuIOkQV7lRKlUSqNHa2tr+Prrr7G1tXUlJ7a1tWFiYoJG0wgnLiwswOVyVZUTSc52dHQUVquVcmIwGMTW1hb+/Oc/Y35+/jVO5PF4tJfVarVCo9FQTpyfn78WTrz2sWmkqpDE8UdHR9HZ2Qm5XE4b2xcXF7G4uIhgMEgfNvBDGISEaXp7e8Hn8xEOh7GxsQG32w0OhwOlUnnjszRJgl6r1aKnpwejo6Mwm81QqVTgcrk4ODjA2toa5ufn4fP56PSKUqkEFotVkbfp6+uDTCZDPB6Hw+GA0+nE5eUl1Go1BALBjcslFAqhUqnQ3d1NFbRGo4FAIECxWITD4cDc3FxFTo+8xFwuF2KxmJbXNzQ0IJ1OY3d3Fw6HA8fHx1AqlRCJRDcuFwnRtre3Y3R0FDabDY2NjRCJRDg/P8fe3h5mZ2dpWwPJ3ZJ8GelXMpvNNL/pdruxsbGBbDYLuVyOurq6G5eLTE5qaWmhnlxzczMkEglKpRICgQCmp6exsbFBCyvK5SK5bJPJhPb2dpydncHn82F1dRWxWAwSiQQymeytRpG9T5BRaAaDAXa7HSMjI3TcG8MwiEajmJ2dxcrKCiKRCAqFAuUO0mtHJkqZzWawWCwEg0Gsr68jEAjQkPhNzxcu50Sr1YqxsTF0dXXRs6RSKSwtLb3GiYQ7eDwejWYQToxEItja2qKcSHjopuX6MU7M5/NYX1/H/Pw8bWt4EyeSKvJyTry4uIBKpQKfz3+v5742T5CQjlgshsFggNlsRn9/P7q7uyGRSOiUgK2tLczNzWFra6uin0okEkEqlUIul1O32mg0olAoIJVKoVAogM/no62tDTKZDKenpzg7O7uRcA3Jbep0OnR0dNCZikqlEicnJ8hkMvB4PFhcXKT9VEQugUCAuro6yOVyNDY2wmw200b/cDiMfD4PNpuN5uZmKBQKOjT3JqxwDodDc7YtLS0YGBhAT08PtFotLi4ukMlkEAqFsLS0hOXlZYRCIaoAycBemUyGhoYGmM1mtLe3QywWI5lM4uDgAKVSCTqdDvX19SiVSpSMrzvHxGazIRKJoFQqqVx9fX20CjSVSiGZTGJlZQWLi4vw+/0oFou4uLigVZZSqRQKhYKGhBUKBTKZDC2aUalUqK+vB4fDoeG165aLeBNyubwi79LS0gIWi4VsNot0Oo21tTUsLCxUtA6RiUvkjlksFnR1dUGtViObzdIWA7lcDoVCAT6fT632675jpHq8rq4ORqMRVquVzs/l8XjI5/NIp9PY2NjA3NwcdnZ2KqZKkbVIZPBBd3c39Ho9crkc0uk0jo6OIBKJ6PtZLBZvZL3Qq5xoMpnQ39+Prq4u1NXVUU7c3t7G/Pw8Njc3r+REUsxFOPHo6AipVAqHh4fg8XjUUDg9PUUqlbpxTiQFLUQBklFvHo8HCwsLtHWIyEXWIsnlcuj1epjNZrS1tdEZ0IeHh2CxWDAYDFAoFLi4uHivnHhtSpCExCwWC51/2d7eDqFQiHA4DJfLheXlZWxubsLlclXklBiGQVNTEwYHB2mcvKOjA0KhEMlkEiwWCw8ePMC9e/dweXmJra0tutfsuvMWJN/V09NDQ2rEs00kEvB4PFheXsb6+jpcLhedPkHkamhooJMqzGZzxWePj49pQygA7O/v4+TkBPl8/kZKtwkZkl45k8kEjUaDXC4Hr9eLtbU1LC8v08KK8gIEuVxOKxF7e3vR1dUFrVaLw8ND5HI5SrIAkEgkAID2gV532EYkEsFisdBIhMViQXNzM4rFIrxeLzY3N7G8vIzd3V3s7+9XJN3FYjEl4Z6eHphMJjpoOZvNorm5Gf/0n/5TAEA2m8Wf/vQnWkBy3aFsPp+Pjo4OWK1W6rG3tbXh/PwcPp8P29vbWFlZoZNrygmVy+XCZDJRQ8dkMlHiOTg4gFKpxD/6R/8IpVIJhUIBU1NTiMfjSKfTb73J4JeCx+NRb2BsbIxWkJNKVafTieXlZWxvb9NqUPJds1gstLe30wITk8mEjo4OcLlcFAoFiEQiPHnyBBcXFzg7O8PS0hKdwFTejnUdYLPZ1EsaGRmhuTyRSIRIJHIlJ5KVRwzDoLGx8TVOFIlEdM7p/fv3MTk5icvLSzgcDuTzeRwdHb31dpdfCpImeJUTFQoFksnka5wYCoVe40S73Q6r1Uo5kXy2WCzCbrejv78fAODz+eh+zvfFidemBNlsNvR6PcbGxnDv3j1aRVcoFHBwcACfz4ednR243W4cHR1BIBCAz+fTMEZ/fz8ePnwIm82GtrY2CIVCnJ2d0XJ9jUYDsVhMJ0MoFApwudxrH8DMYrFo5dK9e/cwOjqKuro6nJycoFAo0Kqn3d1d5PN5cLlcOtWex+PBYrHg/v37dHSVRCLBxcUFcrkc6urq0NDQAKlUiouLC4hEIkxNTYHH4127XCQvZLVacf/+fYyOjkKlUuHi4gKJRIIaLtvb2zg4OACLxYJcLq/Ii05MTGBkZAS9vb2Qy+W4vLzE6ekp3aBBPMD9/X3Mz8+Dz+ffSM5TLBbT731sbIy2QQSDQcRiMbjdbmp1A6DWNtmeMDY2hvHxcRoWLpVKyGQyNLza0NAAAAiHw9jd3YVAIMDJyQkYhrlWUhUIBOjo6KDPiwztjsViSCaTVMFHIhFcXFxALBZDLBbTpuzh4WHcu3cPVqsVTU1NYLFYyOfzdDOIVqsFm81GMplEKBSCSCS6keXAXC4Xzc3NuHfvHl21JRAIqIdKWja8Xi9OTk4gEonoODGBQACbzYZHjx5Rr5jwApk0RUL7BwcH9N5xOJxrf14cDgd6vR6jo6OUE0Ui0WucSHKbfD4fPB6PtgxYrVbKicShOD8/p+P+NBoNJBIJDeOTcX/X/byIY1DOiVKpFCcnJwgGg5QTd3Z2ruREk8mEe/fuYWRkhHrFFxcXODg4oJWzMpkMFxcXkEgklBPfl1zXogQJMTY2NtLLSeaAkqILMueOYRg65JYU0JC9ZePj49BqtXSTNVGsZ2dnEAqF9LMsFgsMw9Bf1wWSQyFK0GQyUVI5PT2lL6tWq8XJyUnF8F6Sf7BYLJiYmEBzczPdZH15eQmNRgOZTAahUAgWi4VisUjlugmwWCwoFApYrVaqxDgcTkUeQqVSoauri4bESBhUoVCgvb0dk5OTaG9vh1wuB4/Hw+XlJZRKJQQCAQQCASWj8tmH1y0fKY6wWCwYGBiAUqmkZyPvKRlVRxZ0lkolOuLJYDBgcnISJpMJ9fX14PF4KJVK9Pshu/lOT0+vnOl4nXIJhUJ0dnZieHgYOp0OfD6f3oHyQeBKpZLmlEh4V6PRYGJiAlarlRY8AaDbS8i7fH5+Dg6Hc2P5QBIKNRqNGBsbg8FgqJgDSrYJGAwGmssl3CGRSFBfX4+xsTHabysSicAwDA2nXV5eQigU0nB8OXdct1xcLhd6vR4jIyNoa2uDSCR6IyeS1A4JedfX12NgYIByYl1dXQUnqtVqyokXFxc3xh3lnEhWiJHZyFdxYnnKinAimUFMCrk4HA4uLy+pQ0A48fj4+Frkeq9KkDwUtVpNe166urqgVCpp8pmQS0tLCwQCAfL5fMX0A7FYDIVCgba2NmrZAqAXmCxwJfmOQCCAzc1NZDKZK2fqvQ+Ql1ShUKC1tZX2KGk0GjoIm5BLU1MT2Gw2jEZjxVmEQiEUCgUtYSdFC0TJEAI7PDxEOp1GJBKhEyKuWy4y/3J4eJg2jJOB0aRHU6/XAwD1hAiIEmxsbITJZIJCoQCAimovACgUCohGo4hGo3A4HAiHw9eawy1f20RCY4RQiewikQgajYZGEspDRuQ91Wq1dDgA8RTK+7sKhQKSySRisRjtUyMbQq5LLkIqPT096Ovro3eJkLlAIKCzdYlFXv55qVQKtVqN7u5uNDY20rtJlL9YLMbR0RHi8ThisRg8Hg/29vZonvQ6QAythoYGGqYlOTuigIkH0dbWBrFYXLHRo1wJdnV1oaWlhd5Nwh1CoRDHx8dIp9NIJBLU88rn89eWaijnRBKm7erqgkqlonIRg8VoNILP57/GiSKRiMrd3t7+Rk7M5XJIpVIIBoPY2NioGIbwvlHOiS0tLRgaGoLJZIJWq63gxLq6OhplaG5uvpITm5ubac8nketVTsxkMohEIhU1Fu+LO5gf+4IYhvlZ3x4hhnv37uEf/IN/ULEFgWjwi4sLmrsj3tKrI4BIoyVZZnp5eYnLy0ucnZ0hl8vRi7m1tYWFhQU6t/JN+97eFaQy0Gaz4Te/+Q3Gx8fR2dlJrTEi18nJCYrF4pVDbolcQqGQfo7IRVx/Ej/f3t7G0tIStra2EIvF6MSH9/0yE8+7u7sb//Af/kM8evSITrkpJ8ZyuV4d/E2qukghA7HiSqUS3VWXTqfh9Xqxs7OD5eVl2qBMihnet1zES2ppacHTp0/x2Wef0Qtabkmenp5WvIuvysXhcMDn81FXV0c9QPK8jo6OkM1maTPzysoKVldXEQwG6c6261DwZOXYp59+iqdPn9Ke1HK5zs7O6PN6dbwZsdxJIRPZ7E3exePjY2SzWYRCIbhcLqysrGBlZQX7+/t0Est1yEXSHI8ePcJXX31VkQckspG8XTl3vCoX4SCRSESNzMvLS1qcEY1G4Xa7sba2hqWlJbrl47ryZqRaenJyEn/xF3+B4eHhKznx+PiY5pF/Dieen58jm80iHo9XcCLpvyuvmH2fIJ7rwMAAfvOb32BiYoK2rhCv/X1xotfrreDEaDT6szmxVCq90X187+FQEn7S6XR0VUt5CTKZ4CCRSN74d5RKJboUM51OI5PJoFgs4ujoCNFoFOFwGH6/H06nE1tbW4jH4+9bjCvlIuPeSE7hVblEItGPlv6XSiWcn5/j6OgI6XSaVqoVi0XE43FEIhH4/X6aewsEAtcuF/DDNH6dTkfDuwREoRBSeZNc5CLH43Ekk0kUCgUcHx8jlUpRuchYMa/Xe+3VrsQLValUaGxspAq6HHw+HwKBAHK5/I1yEQIlebZ8Pk8rgKPRKPx+Px0G7na7b2QpMIfDgUKhgF6vh0wmey0My+Px6JLjN8lFjJtkMolUKoVsNksLDqLRKILBILxeLy1Pv4m+ThaLRafdkErb8jAsWTb9Y20oRK5MJkPlOj4+pjsQQ6EQ9QAdDseN9HWSlgidTkdL/F/lDpKv/TG5zs7OkM/nkUqlXuPESCQCn88Hl8tFjefrlolwg1arhUajeW313c/lRPLMSDEP4USfz4e9vT1sb2/D7/e/d1neqxIkhRDZbBaRSATNzc00AVqOqxLQ5BKTC5rP56n7u7W1hWQyiUwmQ5fKHh8f05fgukG80IODA0QiESQSCZr3ehWvyvaqXCTMtL6+jo2NDUSjUWp5h8Nhar3fhFzkBczn84hGo4jFYjQv+XPkAl6ueEkkEtTbC4VCyOVyiEQidDYg+XXdCpDIVSgU6EV6Uw/fT8l1dnaGZDIJt9uNlZUVeDweHBwcIBaL0dFj5Vb8dYN4oclkEpFIBCqVCgqF4sr79GNykZaX/f19rK6uwuVyIZvN0qWyuVyu4pndhFwkVBkOh6HVaqFUKl/7uTfJRWQrlUrI5XIIhUJYXV3Fzs4O0uk0nZlK+j+J8XndIJxIwnlv4sSr8Cp3HB4eVnBiIpFAJpOhS2UJJ96UXO+bEzc2NrCxsYFIJIJcLodgMIhIJEI9yevixGtRgj6fD8+fP6f9KyRhS1zko6MjnJ+fo76+HkqlkjaFn52d0Q3I+/v7cLlccLlc2N/fRy6Xo6G1m95mTaywSCSC6elp6uGQ6kgSniBhGrlcDqVSCZVKBbFYjMvLS7oVnqxE2d3dhcfjod5gOp1GNpu9cbnOz8+RTCaxsLCAUqmEZDKJhoYGGqoplUr0JZRIJFCpVFCpVFShHB4ewu/3w+fzwe12Y29vD06nE8lkkoYMy+fA3hRImGhtbQ1cLhepVKoibFge5iXN4mq1mjaFHx0dIRgM0iHaRK5oNEqr+aqx/omEmB0OB4RCIbLZLLq6umj+FngZ5j06OqI5NKVSSfPyx8fHiEajr8lFytaJp3HTk4pIKHZvbw/Pnj2j3y8pHCHh0EKhAIZhqFwqlYpWCiYSCeqZE7kCgQAODg5weHhIvYybluvs7Ax+v7+CE0nBzps4UaVS0Yr4dDoNv98Pr9eLvb09yonZbJb2TVeLE6PRKGZmZmhUQS6X0zv2KifW19dDrVZXcGIgEMD+/j7cbjecTiflRNIzmc1mr73f9r0qQfLFkI0C8Xgc0WgUYrGYuv8kr1cqlWgjK6nWymazcDgcmJmZwcbGBhwOB33Q5+fnuLi4qMq8SRLui0ajtF8qHo9DoVBQ95/EsI+Pj9HZ2QmTyQQejwc2m43Dw0O43W5MT09jdXUVDoeDhgxJjqVaczQvLi6QSqWwsLCARCKBeDwOnU5HQ2yXl5c4PDxEoVCAwWCgC4y5XC5OTk7g9/sxPT2N5eVlOkM0n8/T4pDyCtmbliuXy2F1dRXJZBKJRIIWSxBLtFAoIJ/PQ61Ww2w202bm8/NzOo1kfn6ebhkgz5c8r2o8s4uLCxQKBWxvb9Mm//39/YrQYbFYxMHBAR03RooOSqUSEokElpeXMTMzg+3tbTpwmnjopH/upkGUoNvtxsHBAeUO0iIAgEaZ+Hx+hVxEUZAxb6TPLpfL4ejoqKpyvYkTJRIJ5URisJVKJXR3d9PVUMDL3lOyn5JwYiaTwdHREc7OzqrOibFYDNPT05QTSRgbqOTEjo6OCk4k05bKOTGRSLzGiTcxrP295wRJcy0RhEwxIC8yGYNmMBggl8vprLy9vT2srq5ibW0N6+vr8Pl8dHVItTYhl6NUKtE4NSnuKa9cI71XWq2WThe5vLyE3+/HxsYGVlZWsL6+Do/HQ138au33KkepVKKTJc7Pz3F2dkatOeCHHG5DQwMkEgmUSiUdWeVwOLCysoK1tbWKwQA3MS3lbUBIk1SSeb1eSjykElmtVtNp9xwOB6lUCi6Xiy4kJZWs5euUqo3z83M6cgoAotFoRWEMmY7T0NBAPQqyaaH8joXDYdoofhvu2OXlJTWgiKdQbrTw+XzU19ejpaUFCoWCTnshs4fX1tawsbFBw4M3NUHqp0BCfuQ8h4eH4PP5FZwolUopJ8pkMrr4+FVODIfDt5YTj4+Pr+REjUZDOZGM8XuVE8PhcNU48Vr6BMvDh8lksqJ3qaGhAWNjYzCZTDCZTFCr1XS54l//9V9jY2ODhmNuC+kQlIcPc7lcxcOur6+n+7LMZjOam5uRTqextbWFv/mbv8H8/DwNx9xGucgElEKhQBUFKXG2Wq0wGo10SkU2m4XT6cRvf/tbfPvtt0gkEnS+4W24nOW4vLxEoVCAy+WCx+MB8EObgdlsplMqTCYTCoUCPB4Pvv76a/zpT39CKBTCwcEBjULcJpBQk9frpQVUpFK3vb0dXV1ddIJ/qVRCMBjEd999h9/97nd0Kg7xJG4TSJg6GAwiGo1S7uByuWhsbKTvodlshlgsRjwex+zsLP7tv/232N3dRTqdplGI23bHSPgwlUpVcKJara7gRI1Gg1QqRTlxfX2d5jJvI3e8iRMVCgUGBwfR0dEBs9kMo9FYwYlzc3M0HXRdbWBvg2ubGEO+HOKqk+Z5MuKpv78fdXV1iEQiePHiBaamprC9vU23cd+mB/0qSHgFAO1/IaOQBgcHoVQqkUqlMDU1hampKayvryMSieDk5OTWKYlykEpIAjLHb2RkhDZkHx4eYmFhAc+fP8fS0hJCodCt8WrfhFflIk3/Q0NDGBkZgdFoxNnZGdbX1/H8+XPMzs7SBc3VClO/DYgXTzxC0hxP5Ors7ASLxYLD4cC3336L2dlZeDye17bJ3zYQhVE+M5OsUiNj7wQCAfx+P7799ltMTU3B6XRWjE+7jbiKE/V6PeXEgYEBSKXSXw0nWiwWOh5OqVQinU5TTlxbW7s1nHgjq5RISM1sNuP+/fu0zy4ej2N3dxd/+MMfsLi4eOsv56sg0xA6Ojpw7949TE5Oore3F+l0Gh6PB9988w2eP39Oq1nvCkiDb3NzMyYmJnDv3j309/fj5OQEHo8Hz58/xx//+EdEIpGqbRn/JSA9V1qtFqOjo3j48CHsdjvYbDbC4TBmZ2fxu9/9jlZ9Vvtyvi2IXGR01cOHDzE8PAypVIpYLIaVlRX8/d//PTweT9V25/1SsNlsyOVy9PX14eHDhxgZGYFOp0MsFsPm5iZ++9vf0tnB1cj5/VKQtohyTuzq6kI8HofT6cQf//hHzM/P09aVuwLS5N7e3k45sa+vD5lMBi6Xq4ITb6KK9W1wrUqQuPz19fV0GrzVakVDQwOOjo6wtbWF5eVlWsF1m63uV0F6mnQ6HXp7e9Hf30+XYbpcLiwsLMDr9dKc1F0BmbyhUqnoqDEyRsvn82F2dhZ7e3s3Mkj5fYL0NKnVaphMJtjtdnR0dIDH4yEQCGB2dhY7Ozuv7RC87Sjvh+zq6oLNZqOhQrIgeGNjA7FYjG7tuAsoV+xkUwsZ55fL5bC2tobV1VWah74r3EE4kUyP6uvro5xIFgQvLS3Rpcd3jTukUmkFJzY2NlJOnJ+fp1vhb5Ozc+2rlCQSCTo6OtDf34/e3l7odDq6NHJ5eZnuLCtfynrbwePxIJFIKl5ig8EAhmHg9/uxurp6Z0KF5SjfBWg2mzEwMIDW1lZwuVxEIhG6usbn890p4iFNuxqNhm7J6OjooIrC4XBgdnaWVibeFeIhcyWVSiXMZjPsdju6u7shl8uRzWaxu7uLubk57O7uIpfL3Sri+TEQb0Imk8FkMsFms8FisVDjeX9/H4uLi9jc3KxKO8cvBeFEsVhcwYnEeA6FQnTyEAmB3hWjhaxSIpzY19eH5uZmMAxDFwTfVk68NiVIBjK3tbXh0aNHmJychE6nw8nJCZxOJ1ZXVzE9PQ2Hw1Gxkue2g2EYutBybGwMH3/8Md1Lt7u7i62tLUxNTdECn9v0sH8KIpEILS0tGBwcxOPHj9HW1gY+n0+n9k9PT2NlZQXJZPLOKEDgZVWhwWCA1WrF48ePYTabIZVKEQqF6ILghYUFRKPRO6MogJdGC1lX9vHHH6O/vx8NDQ10aMHi4iLm5ubg9/vvVDiezNrs7OzE48ePMTQ0BK1Wi4ODA1q5OzMzQ7ct3BUQTmxtbaWcqNfrcXp6CqfTibW1NUxNTdHWsLuiAMlEnHJONBgMAECner148QLr6+tIJpO3jhOvRQmSeLfRaMT4+DjNvaRSKTidTszMzNAN3rFY7M4oQJID1Ov1GB4exoMHDzA5OYl8Po+9vT0sLCzQPqVgMHinXmIyvNhms+HBgwd48OABSqUS3QVG+pR8Pt+te4nfBFJ9R7ZjPHjwAA8fPkRdXR18Ph/W19dp4ZLb7b5TCpCUn5tMJty/fx8PHz6EXq9HJBLB9vY2pqam6I7Emxh59r5A6gdITunBgwfo6upCIpGA0+nE1NQUFhcXab/cXeEOEo1obm7G+Pg4Hjx4gKGhIaTTaezu7mJ2dpZyYjQavTNyXcWJ9+7dw+Hh4WucGAgEbiUnXosSJLMorVYrnjx5gq6uLpRKJbjdbkxNTWFubg7b29t3ygMEXrr8SqUSFosFjx8/htVqBZfLhd/vpy8xKWe+jQ/7TeByuZDL5ejs7KTFB3V1dXA6nfQlJhst7ooCBH7YmNDS0oLJyUncv38fSqUSsVgMy8vLmJqawsrKCkKh0J0JgQI/KIqmpiaMjo7i8ePH0Ov1ODw8pBWuS0tL8Pl8t6b44G1QPp/XbrfjyZMnMBqNOD09hcPhwPPnzzE/Pw+Xy4XDw8M7xR1XcSIA2jA+NzeHra2tO8uJZrOZRiPK8+yEE29qw/0vwbUoQbFYDJ1Oh9bWVrS3t4PFYlU0jbtcrmsf8HodICtsjEYjXWoZDoextbWFlZUV7OzsIBwO39qH/SaQZaNELplMRnNly8vL2NraQjAYvDO5FwIyNqy5uRltbW1Qq9XI5XLY3d2lG7x9Pt+dCqkBP1RMGgwGtLW1obGxEcVisaK5mhRl3SWQsFpjYyNaW1vR2tqK09NTBAIBrK+vY3V1FXt7e0gmk9U+6s8GUe4tLS1oa2sDm82u4ESyCeeuQSAQQKPRoKWlBe3t7RCJRBWcSIZN3Gbj+Vq2SJAXWS6Xo1gsYm9vDxsbG9SKu2uXk4Dsp1Or1XSiw+bmJmZmZugotLtkxREIBAK6SZxMdCDj68hE+ruUAyQgId6mpiZwOBw65WZhYQHr6+sIhUJ3KgRKwGazoVQq0dTUBIFAgFQqRaf3LC8vw+/33ykPkIDFYkEul6OpqQl1dXU0B7i2tobFxUW43e47FdotB+FEhUKB4+NjeL3eXwUnkkXAarUa5+fndJ0T4cTb7AESXIsnSMaiCQQCmnuZm5vDzs7OreoP+bkQi8UwGAy0oXV/fx/T09PY3t5GNBq9Uz1z5RAIBGhsbIRarUYqlUIqlcLMzAxVFGQU2l0Dj8eDTqeDXq+ng6Gnp6extrYGn89359pyCMiUkaamJpydndEq0OXlZbjd7jvXlkPAYrFQX19Pl7CSnNLi4iKdBnPXohHAS8egnBOJBzg3NweHw4F4PH5nOVEkEsFgMEAmk9HB7NPT09ja2kIkEkGhULj1nHgtniCZyUimcMzMzNBm+JOTkztJqADoxm42m42dnR1apZZMJq9tKedNgIRDRSIR3SE3PT2NUChEBxDfRXA4HCiVSsjlcoRCIXg8HkxPT8Pr9aJQKFR1VNO7gIRDyWSiYDCI6elpuiX91cXHdwUkiqRSqVAoFOD1eqkxlsvl7lTLwKsg82kvLi6oUzA/P/+r48S1tTXMzMzQASF3Qa5rGaCdTCaxsbEBLpeLRCJBtxzfReu0HLlcDg6HA6FQiG5yJqN/7jLIbM3Dw0MkEgns7+/TqSl3GSTsxGazkU6n6dqWm1jPcp04OztDMBjE8vIyCoUCQqEQ3G73nSvIehWXl5eIxWJYW1vD5eUlotEoHYd2F8j0x5BKpbCxsQE+n0+nwvwaOPHg4IDm/RKJBB2GfZc4kfkxMmAY5hcxhVAopNPEz87O6E6pu0w8AGjzP5vNxvn5OV1iedfl4nK5kEgk4PF4ODs7o3v27jKhAj9UUQoEApyfn+P09BTFYvFOhkDLwWKxIBaLIRKJcHFxQeW664RKqkPJJvJy7rjr+LVyIo/HQ11d3a3nxFKpxLzpz65FCdZQQw011FDDbcGPKUHWTR6khhpqqKGGGm4TakqwhhpqqKGGDxY1JVhDDTXUUMMHi5oSrKGGGmqo4YNFTQnWUEMNNdTwwaKmBGuooYYaavhgUVOCNdRQQw01fLCoKcEaaqihhho+WNSUYA011FBDDR8sakqwhhpqqKGGDxY1JVhDDTXUUMMHi5oSrKGGGmqo4YNFTQnWUEMNNdTwweJaNstXC1wuF0KhECwWC6VSCScnJ7+KdSUcDgcCgQAcDgelUgmnp6d3esEoAYvFglAoBJfLBfBydc5dWcT5Y2AYBgKBADweDwzD0BUzd32FE/ByiSqfzwfDMLi4uMDx8fGdX+EEvFwJJBAIwGKxcHl5SbnjroPL5UIgEIDNZv+qOZFwxy/hxF+NEmQYBi0tLZiYmIBMJkOxWMTm5iaWl5fv9MvMMAy0Wi0mJiag0WhwcXGB3d1dLCws4ODgoNrHeyfI5XJMTk6iubkZLBYLXq8X8/PziMfj1T7aO0EoFGJ8fBxdXV3gcrmIRCKYnZ1FIBCo9tHeCWw2G3a7HX19feDz+Uin01hYWMDu7m61j/ZOYLFYMJlMGB0dhVAoRD6fx+rqKl3ue1fBMAyMRiMmJiYgl8txfHyMra0tLC0t4fj4uNrHeydoNBpMTExAq9Xi4uICTqcTCwsLyOVyP/vvunVKkM1mg8vl4uLi4q0tTA6HA6FQiK6uLjx9+hRyuRzxeByFQgEbGxu3QgmyWCxwuVxqtbyNJUY8pZaWFnzyyScwGo3I5XIolUrY3Ny8FUqQYRhwuVwwDIOzs7O3Ig0WiwU+nw+9Xo8HDx6gt7cXp6enmJmZgcPhuBVKkGEYcDgcsNlsnJ2dvZV3yjAMeDweVCoVxsbGMDExAQBYX1/H7u7urVGCHA4HHA7nZ8nF5XJRV1cHu92OJ0+egM1mY29vDz6f79YoQSLX+fn5W3vdXC4XIpEIPT09+PLLL8Hn8xEMBpFMJrG+vn7NJ347sNlscDgcXF5evjUnstlsiEQidHZ24vPPP4dSqUQ8HsfR0RHW19dvhRJ8F040Go14/PgxWlpakM/nwTAMNjc3f5ESvFU5QYZhIJFI0NzcDLVaDQ7np3U0wzCQSqUwm83o6+tDW1sbOBwOotEo0un0rQmtCYVCNDY2QqvVgsfjvdVnxGIxOjo6YLVa0dnZCZFIhHg8jkQicWtCUHw+HzqdDo2NjRAIBG/9mZaWFgwMDKCrqwtyuRypVAqRSORWGCzAS0JtaGhAc3MzxGIxGOaNOzkpeDweGhsbYbPZYDaboVarcXBwgFAohGKxeAOn/mlwOBwolUq0trZCJpOBxfppCmCz2dBoNOjv74fFYoFer8fx8THC4TAODw9v4NQ/DRaLBZlMhtbWVtTX14PNZr/VZ+rr69Hb24ve3l4YjUaUSiVEIhFks9nrP/RboJwTGxoa3poTZTIZTCYT+vr60N7eDg6Hg1gshlQqdes4UafT/WxO7O/vR2dnJyQSCeLxOOLx+C/mxFvjCbJYLAgEAuj1elitVsRiMZycnODg4ADn5+dXWgkcDgcSiQQtLS0YHh5Gf38/NBoNEokEgsEgEolE1R848Q4aGhpgtVppDiWVSr3R+mGz2RAKhWhqaoLdbsfg4CAaGxsRjUYRDAYRiUSqrgSJp1RfXw+LxQI+n4/Ly0tEo9E35hyIFdfQ0ID+/n6Mjo7CaDTi7OwMkUjk1igLDocDqVSKrq4uaDQarK6uIhAIoFgsXunpkhygUqmExWLBxMQE2traIBQKkUgkEAgEUCgUqiBJJdhsNiQSCVpbW9HZ2YmNjQ2cnZ3h6OjojfeEz+dDoVCgq6sLExMT6OrqglQqRS6Xg9/v/0WW9/sG8XoMBgN6e3uxt7eH09NTHB4evtEj5HK5kMlkaG9vx9jYGHp6elBfX4+9vT34/X6k0+mq581IxESn08FqtSKRSOD4+PgnOVEsFsNoNFJO1Gq12N7eRiAQuDWcyOVyoVar0dfXh9PTU8qJp6enP8qJxMgcHBxEU1MT4vE45cTT09NfdJ5bowT5fD6USiV6enrw+eefY29vj160bDZ75YOTSCRob2/HyMgIPvnkE5jNZggEAmSzWQQCAaRSqarH9Hk8HuRyObq6uvDJJ5/g8PAQh4eHuLi4QCaTuVKZEXd/cHAQjx8/hs1mg0wmw97eHgKBwDtZPe8LRFG0tLTg0aNHEIvFKBaLODs7QzKZvNKj4/F40Ov16Ovrw0cffYSxsTGo1Wq43W76IlfbEySKwmAwYHJyEp2dnbSwhYSTXgWHw4FGo4HFYsHDhw/x8ccfo6GhAYlEApFIBMFg8MrP3SRYLBbEYjF0Oh2Gh4dx//59cDgcFAoFRKNR5PP51z7DMAyUSiVMJhPu3buHTz/9FI2NjTg7O0MsFkMgELjyczcNYlgNDAzg888/x/T0NPL5PEKhEA4ODq7kAJlMRhX7Z599htbWVrDZbKRSKQQCAWSz2aorQT6fD5VKRTnR6/Uim81S4+MqBS8Wiys40WKxQCgUUk5MJpNVV4LlnPj48WMUi0VqsLyJEwUCAZqbm2G32ys40ev1vjMnVl0JkriwVqtFb28vxsbGMDw8DACQSqU03/TqZ/h8PjQaDaxWK4aHh9HT0wOxWIxgMAi3201f5GopQWLtqFQqmEwmKlc4HMb09DT4fP5roajynJLFYsHIyAj6+vpoPJ/kYNLpdFUrDclL3NnZibGxMYyMjAAA5ubmaHXuVZ+pr69Hd3c3tVAbGxsRj8fhdruxv7+PeDz+i6259wGS92pra4PdbsfIyAgMBgMWFxchEomuDLFxuVxIpVK0tbVhaGgINpsNra2tSCaT8Hg88Hq9iEajVc3BkJx5S0sL9cDtdjs2NjYgkUjA4XDAMEwF6ZPPGI1G2O122O12dHd34+DgAF6vFx6PB+FwuKrKnc1m0xB0X18fxsbGMDQ0hHA4jLq6uiu5g81mg8/no7GxEQMDAxgcHITZbMbl5SX29/fhdrup8qyWEiScqNFoKjiRzWZDLpcjGo1eyYk8Hg8ajQZ9fX2UEyUSCYLBIDWgbwsndnd3U+6IxWI/yYlqtbqCE9VqdQUnplKpX8yJVVeCPB4PCoUCvb29+PLLLzE0NASVSgWGYd5YVk6+yM7OToyMjKCnpwccDgdutxtTU1OYnZ1FMBhEoVCo2gPncrk0jPT06VNMTEygsbERsVgMx8fHV7r9bDYb9fX1aG9vx9DQEAYGBiASiRAIBDA9PY0XL17A5/Ph4OCgatYcm82mpP/JJ5/g0aNHaG1tRSAQoOXXr37nDMNALpfDaDTCZrNheHgYcrmcvvxTU1PU86+Wcie5F4PBQL257u5unJyc4OzsDCcnJ2+MRhgMBvT392N4eBharRbZbBbz8/OYmprC9vY20ul0VZW7SCSCVqvF2NgYPvvsM1gsFggEAlxcXLxRLqFQCL1ej56eHgwPD8NoNKJYLGJtbQ1TU1NYX1+n4blqgYSg7XY7Pv/8cwwMDEAqlaJUKlHuePWO8fl8NDQ0wGQyYWRkBJ2dnbTi+sWLF1hcXEQkEqlqWP7HOJFEW16Vi4QXX+VEj8eD6elpWp1cTU7kcDjUeH769CkmJyfR1NREI0dXyUXytuVGplgsppw4NTWF/f195PP5X8yJVVOCJOyk1WphNpsxOTmJwcFBquHD4TCy2eyVvR8ikQgmkwmDg4MwmUwQCoVwOp1YXV3F8+fPsbOz80a3+rpByJR4gCMjI9SjyOVyCAaDSKfTKBaLrz00LpeL9vZ2DA4Oore3FwqFAj6fD9vb23j+/Dk2NzdpLrEacgmFQsjlcvrdj42NoaOjA4VCgYafC4XCa3IxDIPm5mYMDg6ir68PGo0GsVgMLpcLz58/x9raGmKxWNUUhUAgQF1dHbq7u9Hf34/x8XGYzWZcXFzA5/MhkUi8Mb+k0+lgt9vR39+PpqYmHBwcYG1tDS9evMDS0hJCoRCOj4+r4lXw+XyIxWK0tbXBarVicnISvb294PF48Pl8iMViODg4uNIgUyqVsNlssNlsaGlpwenpKRYXF6mRub+/f+WzvglwuVyIxWIYDAZYLBbcv38fAwMDkMlkCIVCiEQiyOVyV+ampVIp+vr6MDg4iI6ODrBYLGxsbFDZ9vb2aM7tpsFmsyEWiyknTkxMYHBwEA0NDUgmkz/KiUKhEN3d3dSzFYlEcLlcWFtbw/Pnz+FwOJDNZqvKiSS0Pjw8TDnx4OAAwWAQqVTqytw0l8tFW1sbBgcHad7W7/e/xonvwh1VU4IkP2S32/H06VMMDAxApVIhHo9jdnYWq6uriMfjVxYjyGQyjI+P4+HDh9Dr9QgGg/jd736HxcVFuFwu5HK5quXMSH6op6cHT58+xfDwMBobG5HP57G8vIzFxUWEw+ErLTKBQAC73U69q4ODAzx79gzT09NwuVxIpVJVs7zZbDaUSiW6u7vx5MkTTE5Owmg04vLyEpubm5iZmYHf77/SImOz2bBYLPj444/R2dmJUqmE2dlZ/PnPf8be3h5isVjVLG8WiwW5XI7W1tYKz5bH42FlZQXPnz+Hx+N54zvV3t5O89FcLhdzc3P4+7//e7hcLoRCIRwdHVVFARLiMRqNePDgAZ48eYKOjg6IxWLq9ezu7iKTyVxJII2NjXj8+DEGBgYgFouxsrKCv/u7v8P29jb8fn/VFCDwkvANBgPGxsbwxRdfwGKxQCaTwe/3Y3Z2FltbW0gmk1caH2q1Gg8ePMDExASUSiWcTif+5m/+BhsbG9jb2/vRYprrBuFEm82Gp0+fwmazQa1WI5FIYHZ2FisrK/SuvModUqkUY2NjePjwIRobGxEOh/H73/+ecmI2m62akUkqrV/lxEKhgOXlZSwsLPwoJ9psNjx69AhtbW3I5/N49uwZNVjIc36n873Tp38BSBVoQ0MDLBYL7HY7enp6oNVqUSwWEQ6HsbOzQ6vxyEUr75kjFqpWq0Umk8HOzg7W19fhdDqrli9jGIZW0nV3d2NoaAh9fX1oamqiVZMulwv7+/u0MIbIxefz0dTUhJ6eHgwODqK5uRnFYhFOpxMbGxtwOBxIp9NVKRohMXmpVIqOjg4MDw/DarWipaUFHA6H5mDdbjcNZ5ZKJfo5rVaLjo4OjIyMoK2tDZeXl/B4PNjY2MDm5iYymUzV8kokB9jS0oKhoSH09/fTqs5kMgmv10vfKeItlec1WlpaMDY2hu7ubnA4HPj9fmxtbWFtbQ3pdBqHh4dVUYCkQtBgMMBms9FWFIlEQgsrHA4HEokEDV8zDAM2mw2FQkGHTvT29kIsFiMcDmN7exurq6uIRCJvLDa5bpAqUFItabfbYTaboVQqkc/nEQwGsb29TQusyBnZbDZ9zmNjYxgYGEB9fT0SiQQcDgfW1tbg8XiQyWSqIhfhRJL3IpEgnU5HW1F+ihMHBgZgt9uh0+mQzWYpJ+7u7ladE+VyOeXE3t5eGAwGlEolGg16Eyc2NjbCYrFgaGjoWjnxRpUgSbYrlUp0dHTAZrPRwo/T01OEw2F4PB7s7+8jnU7TF7JccU5OTuLBgwfo6OhAqVSCy+XC6uoq9vf3kclkqmKdstlsCAQCKBQKNDc3o7+/HwMDA9BoNPRhkyKJRCJBX0iiKBQKBYaGhvDJJ5/QWL7T6cTS0hI8Hg+SyWRVXmLyMsrlcjQ2NqK3t5eWJrPZ7NeKP8rDT6R4pq+vD0+ePKEehcvlwvLyMlwuV8V3cdNykYIWvV5PE+4tLS3g8/nIZDLwer3wer2veXMcDoeGTj/77DOa3/T7/VhbW8POzg5isdhbN/++T5C2lbq6Omi1WlqERHpMDw8P4fP54PF4EAgEKpQ0i8Wi7UZPnjzB6OgoNBoN4vE4Njc3sbW1RfsCb1pREAUtFovR0NCArq4uGvYj06GCwSA8Hg98Ph9yuVwFd5D85qNHj+iEoqOjIzgcDqyvryMQCFR85iZBxn+pVCq0t7dTTlSpVDg7O6OcSAriXuVEtVqNiYmJ1zhxZWWl6pzI5/NRX19Pc+YDAwPQarUolUqIRqMVBXEkylLOiYODg/j000/R09MDLpeLvb09LC8vw+12v1dOvDElyOFwoNVq0dzcjM7OTvT09KC/v59aBV6vFzMzM5Qgy5s6SQVYT08PRkZGYDKZcHJygv39fczMzGBlZaWquTK1Wg2DwYCOjg6YTCbYbDbatB8KhTA3N4eFhQXs7OxUPHASOjWZTNQTAQCXy4XZ2VksLCxUtSdQoVDAYDCgra0NJpMJVquV5mBjsRhWVlYwNzeHzc1NqgSBH5LZxPobGhoCl8vF/v4+FhYWaOFStcIzEokETU1NVC7SLC2VSpHJZLC+vo75+XmsrKxQJUhA+gcHBwcxMjICuVyOUCiEpaUlzMzMwO12Vy1kLRKJoNfr0draiu7ubvT09GBgYABKpRKHh4fY3t7G3NwcVldXaeiakCrJHZKqWL1ej3g8jpWVFczOzmJnZ6dqIVAejwedTgej0Ujl6u/vh06nw+npKVwuF+bm5rC8vEzbCIhcpLTeZrNhZGSEphkcDgdmZmbolJFqGGPlnNjR0UHlam5ufo0TnU5nRXsDl8utKFwym804PT2Fz+ejnJhMJqvGiSqV6jVOJE37oVAI8/PzWFhYwPb2dgUnstlsWrhEqsgZhsHe3h7m5uYwPz+PaDT6XuW6ESVIiio6OjowOjpKy3fr6+upp7S2toY//OEP2NzcRDabrahaEwqFaG9vp4l9hUKB1dVVzMzMYHZ2Fk6nsyo5JRIaa25upmXMVqsVarUaPB4PsVgM29vb+PrrrzE/P0+T2uTC8Xg8+lliJa2vr2Nubg4zMzPY2NioWqiQxWJBr9djZGSkoum2rq4O8XgcLpcL33zzDb799luk0+kKguRwOLQfzW63o6WlBQ6HA4uLi5iensbKykrVRr6xWCyo1WpK9jabDU1NTVAoFDQE+vz5c/zpT3+i/XMkxMtisaBSqWCz2TA0NITOzk6EQiGsrKxgenoaS0tLSCaTVZNLLpejt7cX4+PjsNvtdHrKwcEBfD4fZmdn8bvf/a6iz4yEeEnBCAnvFotFrKysYGpqiuZsqhVSq6uro7M9SUVnfX09Tk5OEA6Hsbi4iN/97ndwOp3I5XI4PT2lIV6xWAyTyYSJiQk61IE8r7m5Oezv71ctzSAQCNDW1ka5o7e390pO3NjYuJIT29raMDExgb6+PtTX11dw4u7u7q3gxJGRkdc40eFwVHBisVis4ESS7+3v74der6dG6fT0NDY2Nt774IlrV4LkRSTFIqOjozCZTNDpdGCxWIhGo1hfX68I/ZFQEovFouGd1tZW9PX1QSKRIJ1Ow+FwwOVy4ezsDCKRCKenpzdqpRLFrlAoYDabMTo6ip6eHjQ1NYHL5SKXy1HiJ6E/MluThK1I3oaEhA8ODuB0OrG7u4ujoyOIxWKcnp7eKPmQOL5EIqG5PGKdCv7/7P3nc6PXlh0OL+ScAQYATADBDII5s9lJV56xZ8rl8dguu+wPtv85f7Cva3zvb0a60r2tDswRDCBAkEhEIHIGSILg+0HvOQK62VJLahDEFVdVl1TVzW5sPOdZe58d1ubzcX19DafTia2tLRwfHyMUCtHvntglEAjQ2tqKwcFBtLa2olAo4OzsDIeHh0gmkxAIBMjn8/d6EyQvJ0n5TU1NYXx8HJ2dnRCLxWAwGPB6vdja2sLR0RH8fj9yuRxKpRJNxxHln/7+fnR0dKBUKsHr9WJ/fx/hcBhcLhc8Hu/eSZUoJ7W1tWF8fByTk5Po6uqCQqGg79jm5ib29/fprNj19TW1i8Ph0M490jEZCASwt7cHv99P0+L33eVKUrRarZbON/b09ECtVoPFYiEYDGJnZ4eWQ+LxOLWLpLxJSz5xgCS963K5cHt7C4FAcO/Pq5ITh4aGPuDEi4sL7O/vY3t7+0c5kXT9SiQSyokOh6PunEg6yKenpzE0NEQ5MZ1O4/j4GFtbWzg5OaE3wEpOJBJxJCWcTqdxcnJCMxFCoRCXl5eflRNr6gTZbDZ4PB6tT4yMjMBisUCpVAIAUqkUXC4X1tbWsLOzg0gkQomRrDYhL3dPTw9MJhOKxSKCwSB8Ph/S6TSamprA4/Go9M59vKSEEDUaDTo7OzE8PIyRkRG0traCxWIhk8nA6/Vic3OTzh2RF43UAMRiMVpbW2EymdDb2wsOh4NAIIDz83MkEgnI5XJwuVyUSqV7W31CBm6VSiX0ej3MZjNGR0fR0dEBDoeDQqGAi4sL7O7uYm1tDV6vlxIjqYsKhUKoVCoYjUb09vZCJpMhHA7D7/cjEolAJBKhq6sL5XIZhULhXuwidQaZTEbT6uPj43TLw+XlJVKpFPb397G6uorT01PqAEntRSAQQCqVoqurC319fdBoNEgmk7Qln81mo729HQwG497qZsSxi0Qi6PV62mhGCP/6+hqZTAbHx8dYXl7G8fEx0uk0dRQ8Hg9CoZB2kfb19dExD3IWy+UyrQHn8/l7e8fICiCtVou+vj6MjY1heHgYIpEI5XIZqVQKJycnWF5epg1WJEXG5XIhEAggEonQ3t6O3t5edHV1IZPJUO4oFApobW2l5/q+ziKbzaZD7XdxIhEjIOndSgEJsiqOPG+TyQSTyYTLy0sqqZjJZOitqx6cSBrGhoeHafMim81GNpulnEgyC+9zIlE06u7uRm9vL7hcLlVcisfjkMvl4PF4dL71c9lVMydIUmImk4kqTgwMDEAoFCIYDMLtduPg4IAW3c/Pz+n1ncFgUBWInp4eWrcRCoVIJpNgMplYWFjAxMQEANCr/9XV1S/eKfWpICkxk8lE1WoGBgZoOs3n81G7Dg4O4PF4qMgwg8GgrcL9/f3o7e2l6d14PI5isYixsTH09fWBwWDA5/OhXC4jn8/fy549mUwGk8lEG2DITB/pvCONBIeHh7QblBxEkorr6+tDX18fBgYG0NLSQvVfe3t7odfrcXt7i1gshq+++grpdLoqFVIrENFd0nlnNpvR1taGYrEIp9MJh8OBg4MDWK3WD+rRZMMAeV6Dg4Po6OgA8H0Q19bWhn/37/4dbm9vkU6n8ebNG8RiMXoeawkej4euri709/fTWcXe3l7c3NzA6XTi9PSUduG+X3vhcDj0OfX09ND/MplMZDIZKJVK/P3f/z2VjFtfX0cikaCt9rUkVi6XC71eT+feRkZGMDAwQDtwXS4X9vf3cXh4iIODAwSDQVqHZTKZMBgMGBwcrOIODoeDfD4PgUCAly9f0gyL1WpFJpOhqj61tIvUAN/nRJFIhFAoBI/HU8UdxFkD1ZzY29uLvr4+qpJF9Fvn5uYwNjYGAHA4HLi8vLw3TlSpVFWcODg4CLlcjng8/pOcqNFoMDQ0VPWOKRQKmiol3c0MBoMGZrlc7rNxYk2doFarxezsLBYWFjA2NgaxWIxisYh4PA673Y61tTUcHx9TMpVIJDRqHxwcxNOnTzE2NkbVwm9ubsBkMmkqQCQSoVgsgsfjYWNjA36/v+apDVJTmpiYwMLCAmZnZyGTyVAqlRAIBHB6eorNzU3s7e0hmUyiVCpBJBJBJBKBy+Wit7cXT548ocVsmUwG4HtC5fP5tEHj5uYGh4eH2NnZwcnJSc1TG0TVxWKx4MmTJ5idnUVzczMAwOPxwO120yYJUp/g8/l0sWVHRwdmZ2cxPT1NUxkAEIlEwGKx0NPTA4VCAQBwu904OjqC1Wq9l3SvUCjEwMAAnj59itnZWbS1tYHL5cLv9+P8/BxWqxXv3r1DJBJBPp+nt2EWiwWNRoOpqSnMzc1heHgYWq0WTCYTiUSC7msjah4kGhcIBLi6uvpAiuxzg8fjwWQy0bm37u5uOt4RDAZxcHCAd+/ewe/3I5PJUMUO8g6Nj49jYWGBprs5HA5yuRwYDAZaW1thsVionmYymcTy8jKy2WzNnTuHw0FHRwcWFxcxPz9PHUUmk0E4HKZNLS6XC6lUim5NILfb4eFhLC0t0QY1Pp+Pq6srStb9/f3g8Xi03ru6uopYLFbzjAuLxfqAEyUSCYrFIhKJBBwOB9bX12Gz2e7kRHKGCSdKJBKUy2UqPGIwGGgaVCAQYHNzEz6fj9ZIawXSCFPJiXK5HKVSiXaBbm5uYnd3l87bEk7kcDjo7e3FwsICTQvL5XIAQCaTqeLEcrlMOZGkfR+0E2SxWLQ5wmQyUR1Q4qQ4HA6USiXa29ur8sIkpzw2NoaFhQXatMBisVAqldDS0gKlUgmJRAI2m02/KKJ/+Ckrb34NyItE1uWQKzppYGGxWJDJZGhra6NLcIHvu9RkMhkGBwexsLAAo9EIpVJJdydqNBqIRCKIxWJwuVwUi8V7tQv4QU2DaPMR8iB2SyQS6HQ6qNVqlMtl3N7eUjX+7u5uLC4uore3FxqNhm6VUCqVtP5J/j6hUAg2mw0mk3kvdgmFQvT392N0dBStra00pQb8UJ9paWmhwcft7S2tu+j1errzsLm5GUKhELe3t5DJZOjs7KQp4FKphHQ6TbfJ34ddPB6PiiXr9XqIRCKqvUgaL5qammhanaStyajB4uIi/U4kEgltkiFLjiUSCd0ez+Vy7+15cTgctLW1YXp6Gp2dnfRdJ98rSbuR/XqkViYUCqFQKDA3N4epqSnodDpIpVIwmUzqgMrlMnUs5XIZPB4PLBbrXuwiN0HCiTKZrIoT2Ww2HbOqbO4hnDgyMoKFhQW0tbV9wIkKhYJ+T9lslm6Tvw+7KjmRZMU+hRPJ+FV/fz8WFxdhNBqhUqmqOFEgEEAikYDL5eLy8hICgYCehc+Fz+oESaFdKpWivb0dg4ODGBwcRFNTExUfJoOrOp0OANDZ2UmjL0JIarWapmh4PN4PH5bNhkwmo1d8EvFWasfVIpIjhXZSxxscHKQFX7Lfi6j0k2J3a2tr1Wch85EGgwFDQ0OQSCT090gkx+fzUSwWEYlEEIlEcHp6Sjdo1CpCJStKNBoNfV4dHR3g8XjUbvL7vb29kMvlVVEll8uFSqWixWylUkkPKBluJk49FoshFovh5OSEDvDWKkIltTyy6mlwcBBGoxECgQDAD05CrVaju7ubOjICQkhkPpI0LZCfFQgE4HA4KBaLSCaTiMViOD09xcXFRc3tqtSlJWm/SuFy8vtdXV20oYWAEBI5p+3t7fQMVwo+XF1dIZPJIB6Pw+Px0BpOLe0iAtFdXV0YHBzEwMAAJBIJtYu8/+3t7WCxWFW7DInTJuLzJpMJHA6H/j5pkrm6ukKhUEAymcT5+Tl8Pt+PrpL6tSDvEHEC5B1rbm7+gBO1Wi1ub2/pXkPy8yKRCCqVinJi5d5Oss2lkhNDodC9cSKp4xG7PsaJRBDlLk4kTY/vc6JIJKLnt5ac+FmdIJvNhlAoxPj4OL788ku6Koeog5OXTK/XQyaTobe3t6pwSzqEeDweZDIZJeLb21uUy2UabUejUbrRent7GzabDV6v96P73n4tiCPo7+/H3/7t32Jubg56vb4qiiTqKKT+VJlaIcEBj8eDRCKhS1qJXTc3N8hms5RwHA4H9vb2cHBwALfbjXw+X5OUIXEUBoMBX375JZ4+fQqTyQSBQEBfUDabDbVaDT6fj87Ozg8aCIhdIpGIRt23t7e4vb3Fzc0NcrkcXePidDqxt7eH/f19nJ2d1UyiqvKcPX/+HC9evIDZbKabIMiNgihZ6PV65PP5qrNDOiJJBzD5PsrlMm3qIVqwpPZmtVpxenqKTCZTs4YE0pC1tLSEly9fYmxsDCKRqCrql0gk6O7uRktLC7WrciieNFgoFArqKIhdpEkoFArR2tve3h6tldYqZUgcHFltNDk5SbNHhDuIOgpxdJUC2aRJiDhxskGCvGNXV1dIp9MIh8PweDxVaTWi71oL7iCB4NjY2Ec5kc/nQ6fT0UW4lTXXSk6USqUf5cRYLAaPx4Pj42Ps7OzAZrPB4/HcCycSMey2trYPOLG5uZmud/oYJ4rFYgiFQmrX7e0tSqUS5USv11tTTvzsN8FK7cyuri56fSUgERnJ+94F8iUUCgWk02lkMhlcXl7S7kSionB4eEilnGoJ8sDIraKnp6cqRQP8sF1BKpX+qF03Nzd0gWQmk0GxWMTl5SUikQi16/j4GLu7u3C5XDW1C/hhI3dvby9NZVRG0ESDkqTLiB2V6QjyQhK7UqkUtSsejyMUCuHs7Ax2u50Saq3rgCQKNRqNNL1baRfwfZpUJBJ9lNTJC3l9fY1kMolUKkVHO5LJJC4uLuB2u2G322G1WnF8fFzz2SxCPh0dHTCbzdBqtR+sDCLdrKQue5ddAHB9fY10Oo1UKoVcLkdvf6FQCD6fDycnJ7QRqtZznYQ0SfNHe3s7JXwCUqslnZQfs+36+hq5XA7pdBrZbBaXl5fI5XK4uLigyjJWqxVWqxWxWKymdpGRBtIQR+p2lZxIarWfwolkqS7hxGKxSDnx9PQUR0dH2NnZuTdOVCgUGBgYQG9vLw1aCH4uJyYSCaTT6SpODAaDODs7q5K3+9z4rE6QRFzJZBKhUKgqd10JcrB/jHzIoT06OsLx8THi8TgSiQTOz88RDoeRzWaRyWTuZbM1Ifh0Oo1gMIhoNAqZTAYul1tlw6fYVSgUEI1GYbPZaMdeOp2mrfbErvsYJieEkc1mEQqFEA6HIZFIaMrwrj9/1/8DwOXlJWKxGJxOJ6xWK9WYDIVCtDGD2FXrLldCGPl8HuFwGKFQCFKpFGKx+Cfteh/Esbvdbuzv78Pr9dIbxfn5OVKpFLLZLN1aUGuQ4JCUAlQqFeRy+Z02/JhdZKnz+fk5vZmTLIvP50MikUA2m0U6nb4XwYZyuUyb5oLBIJqbm6FUKu/cL/djdt3e3iKTySAQCODw8JCKR8diMZyfnyMajVK77uMdu7m5oZwYDAbR3t7+qzgxHA7j8PAQdrudNiyRpbL3zYmVQVM0GoVUKgWXy/3ZdpE0biUnplIpBAIBKtVXS06siRM8Pz/HxsYGJX0+n09TUJU7zCQSCWQyGZ2Ju7m5QSqVolurT09PYbPZcHp6ing8jkwmg0gkUiXgex8zMMRZhMNhbG9v05kp0pFGiuxkJ5ZYLIZMJoNMJoNAIEC5XEY2m6WRKOmOJFJI2WwW0Wi0ShvwvoaSS6USYrEY9vf3qb5kU1MTtev29hZXV1e4urqizT1yuRxCoRAAqKPx+/30VmSz2XBxcUHTGZFIhKbk7ssucpZsNhvkcjny+Tz0ej1NQZFnenl5SQXC5XI5HZyvvJ273W6cnJzAZrPh/Pwc2WwWiUSCCiDct125XA5OpxMrKys0zUeeF4PBoHaRSJycRSaTiaurK8RiMVo3cjqddDMEuRWGw2E6LnCfdhWLRXg8HqytrVFnX5m+Jn8GAL1hyOVysNlselsnt3PCHaSDNJVK0ZVYlRmNWoOcM7/fj83NTQCgoxqfyonpdPoDTnQ6nUgkErRjth6cWCqVqjgxl8tBLpd/lBPJ83qfE/1+P1wuFx32J8+J9BDU2q7P7gSvr6/hcrmQy+XowK1YLKaRz9XVFeLxOG5ubmAymdDT00PTi9lsFg6Hg0qGHR0dIRaL0bZsElXdt34heeCBQAB/+ctfEAgE4Pf7aRs9g8FAqVRCMplELpeD0WikdrFYLBSLRaoDuLe3h6Ojo6pdbqVS6bO1+/5cu25ubhCJRPD27Vt6a2ttbaWpXjKYnMlk6OByT08PWlpaUCqV4Pf7qb7h0dERAoEATYeSNEc95LbITWdjY4Pup+zq6gKLxaJ1SxI1k6aDvr4+ms6JRCJU8/Xo6IjejoiK//X1dc3n5T5mVyaTwd7eHr0N9vf3025bAMjlckgkEhCLxVSMgdSg4vE4ldc6OjqCy+VCIpGg4gClUqnmLfV3gdwEychUIBCAz+cDl8ul3EFuimw2u4o7+Hw+kskkjo6OKHeQ5itSd66nXVdXV3C5XMjn85Q7RCIRTYleXV3RYX9iV29vLyQSCXK53J2cmMlkHgwnvnr1itqlUqnu5ESDwVDFiZXaz7u7u5QTSZr3Pu367CMS5XIZ6XSaStuQdl3ygpJiaHNzM1WFIcKvNpsNu7u7VCmcbCuv196ySpB0BIlsisVilXMnjRQKhYJKh5FDQoq6W1tbcDgcdB9bZcNCPe0qFotU/uzq6oo6d+CHJhOpVErb8MvlMsLhMFwuF6xWKzY3N6tuE7XsZv05dpHbHOlqdLlcVTcLskpJqVTSG2AikaArkTY3N2G1WuH1emk3a73tAr5P0RJxBbKmq7IxhqjIEHURMkpEUoQ7OzvY2tqC1+utkvOrN8jtnXBHMpmscu7kvdLpdBAIBOByuSgUCvD5fLDZbNjZ2aFSY8FgsC5O7y6QgKuSEyu7eQknknEWwolk5RXhRKfT+eA4MZ/Pw+/30+5UiUTyASeS27pQKMTNzQ0CgQBd+Lu1tQW73V5XTmT82D/IYDB+8ach5EkcICmkqlQqjI+PY35+HhMTE2hpaUE2m8Xm5ib++Mc/wmq1IhwOU4fzEA5xJQh5VnZQkrbz4eFhzM3NYXp6GgaDgSr3/+EPf8DGxsYHkc5DA5GqIrch0tk2MDBQNQifz+fhdDrx1Vdf4c2bNwgGg1UCvw/BUVSCjIGQegV5OU0mE7VrfHwc19fX8Pl8+Oabb/Dq1St4vV7aEflQHGAlSHdv5TgLES6YmZmhwsxsNhvhcBjfffcd/vSnP+H09BSRSATFYrEuK59+CuT5VJZRSMNdpV0ymQzJZBLv3r3Dv/zLv9AtLUSt5yFyB5F0e58TR0dHMT8/j8nJSWi1WrqE+w9/+AOsVisuLi4akhPNZjPlRKPRiGw2C5vNhj/+8Y9YX1+nGbFac+Lt7e1HBwtrNixPbhgkh09Wf3R0dNDVNUqlEqlUChsbG3j79i1d8VJrmZ9fg8oaGfD9C9vS0kKX4losFjQ1NVEV/uXlZXqzvQ/ps1+D6+vrqhUlGo0Gra2t6O/vx8jICHQ6HVWyWVlZwfr6OhwOR81GOD4XyAgKgVwuh16vR09PDywWC10QTJRIVldXqWpHvdZYfQqIpB5pXCE6u93d3bBYLHTchaTi3759S7eu12NzwqeCjKCQTls+n09XXw0PD6O/vx9SqZSmrF+/fo39/X06y/jQnDoByU5UDsfrdDo6Yzs8PAyVSvUBJ3o8nobiRKI4RHR6LRYLmpubUSwWsbu7i+XlZWxubsLpdD4ITry3VUp8Ph99fX14+vQplpaWMDAwgGQyCYfDgT/84Q9YX19HNBq9d6X6Xws2mw2j0YgnT55gaWkJY2NjtLb59ddf4/Xr1wgGg1WLWRsBDAYDbW1tmJ+fx9OnTzE5OYnb21v4fD68evUKX3/9NRXsbTS7mpqaMDs7i6dPn2JmZgZ8Ph+xWAzLy8v4p3/6J7jdbqRSqbq/nD8HDAaDLiJ9/vw55ufnoVKpkEwmsb29jd///ve0U/IhO/b3wWB8v0rJbDbj2bNnWFxcRHt7OxKJBA4PD/H73/8e+/v7SCQSD9qxvw/Cib29vZQTBwcHkUwmcXJygj/+8Y9YXV1tWE7s6uqq4sR8Pg+Hw4E//elPePXqFUKh0IPhxJo7QbLnrHK7cGtrKy4vL3F8fEwXYcZisbo0GvxSEAUZorwxOjpKl2Genp5iY2MDTqeT1qQaxS6iUEFmIsfHx2EwGMDhcHB6eoq1tTXY7XZcXFw8mEP8KSCko1Qq0dfXR7dIkAXBZIUSGVNpFAdIUlFKpRI9PT0YGxvD4OAgXRC8vb0Nq9UKv9+PdDr9oG/slSDpXaVSCaPRiJGREXpTymaz2N/fx87ODrxeb8M59koFmcoNNIQTyVq5eDzekJzY1NREN9C0t7cDAOXEk5OTB+fYa+YEK/PElSnQjo4OMJlMnJ+fY2dnBzs7O1TB/aFe998HqZ3p9Xr09/fDbDbDYDCAx+PRXWCbm5s4Pz+nXXeNALLShCjdDw8PU6Fesq+MLCIlqiiNAFI7q9z+0dfXB5VKhUwmQ7vvnE4nXcraCCCrr8jOvOHhYbq9o1gs4uzsjAoyJxKJhiFUUjsj2+4tFguVKby5ucH5+Tm2trawv79PU7uNYtf7nGg2m9HZ2QkWi4VAIIDd3V3KibVSe6kFCCfqdLoqTuTz+XSH40PlxJo5QXIDbG9vp8rinZ2duLm5wfHxMQ4ODrCysgKbzYZkMtkwD5soqLS3t2NychJPnjyB0WgEi8XC6ekp7HY73r17B6vVimg02jA3CuB7Lb+2tjaMjIzgyZMn6Ovrg1AopOoh7969w/b2NoLBYMM4QOB7oV6dToeBgQEsLS1haGgIcrkcoVAITqcT6+vr2NjYoJ13jYLK1TxLS0sYGRmBVqtFPB7H2dkZtra2sLq6CpfLdW/78j4HSLNIV1cXlpaWMDExgY6ODhQKBbrOa2VlBQ6Ho2ru76GjkhPn5uYwNzeHrq4u3NzcwG63U048OjpqWE4cHx/H0tISjEYj2Gw2zs7O4HA48O7dO+zt7SESiTwoBwjUyAmSyFun02FiYgJLS0uYnp5GPp+Hy+XC+vo6VldXYbVaEQgEGsZRVOrhjYyMYHFxEc+fP6ddhWTV0M7ODtxu94PsKLwLpPtOqVRiaGgICwsLePnyJbhcLgKBAPb397GysoKdnR04nc4H2VH4MRBx4r6+PszPz+PFixdQqVSIRCJ02ez29jaOj48bKhtBBIaNRiNmZ2fx/PlzdHR0IJlMwm63Y3l5maZ4U6lUw9hFtkF0dHRgenoaz549w8DAADKZDE5PT7GysoKNjQ3s7+8jEok0DHeQjletVovx8XFaj87n83C73djY2MDKygpNXTeKXYQTm5qa6Bq2Fy9e3MmJLpfrQXIi86f/yM8Hn8+HRqPB8PAw/tW/+lcYGhoCl8ulw5HLy8t02PchfikfA9mY0N/fj5cvX2J8fBxisRjBYBBra2t49+4dtra2EAqFGspREPFik8mEp///nXtqtRrxeBxbW1t4+/Zt1W6yRrJLIpGgs7MTCwsLWFpaglarRS6Xw87ODt68eYP19XWcnZ01lAMkuqh6vR7T09P44osv0NHRgevraxweHuLNmze0dpvJZBrGLgaDAaFQiJaWFoyOjuJv/uZvYDKZwGAw4HQ68fbtW6ysrODw8BCJRKJhHAUAOgdoNpvx5ZdfUk70eDxVnEhuSo3yjhE9176+Prx8+RITExMQi8UIhUJYX1+nnEiyRw/RrprcBIVCId0qb7FYIBKJEIlEcHR0hM3NTbo1udFA9rMZjUYMDw+jubmZRt5ksNrtdjfUywmA7mcjK03IVgWn00mXYTqdzoZKFQI/rEMi9Rej0Yjr62u43W5sb29je3sbJycnyGQy9f6oPwtkBkuv12NgYAADAwNUqWl3dxebm5tUb7eRQNJqRJloeHgYAOD3+2md3WazIRQK1fmT/nwQ524ymTAyMgKxWEz1Mjc3N6kubaOBOPdKTkylUrDb7dja2oLVaoXL5XrQnPjZnSBpadbpdFAoFCgUClT5YG1tDQ6HA8lk8nP/s/cCoVAInU4HjUaDUqlEa4ArKys4Pj6u0rlrJPD5fLS2ttJ9X2TtEYm6yY68RgNJ0+h0OrBYLFoD3NzcxN7eHvx+f8M5duB7565SqaDX6+l4h9PppMoiXq/3XkSvPzdIzUyv10MikSCdTsPtduPg4AAbGxt0TVUjopITi8Uizs/P/yo5kWyLIf0e0Wj0wXNiTW6CRGJLIBAgGAzi4OAA6+vrODg4oDNzjQiSgpLJZFRtn9Q2G3FmjoDP50Or1aKpqQnpdBo+nw9ra2vY2dmBx+NpqJpSJciOR51Oh0KhAIfDQe1yuVxIJpMN6dxZLBbUajXtljw9PcX6+jq2trbo3r9G6XCtBJPJhEKhoItZvV4vtre36Q2QCHs3GhgMRpXsYDAYxNHREdbW1hqeE4VCIfR6PRQKBaLRKPx+fxUnNkLjUk1uglKpFDqdDgwGA4eHh1hdXcX6+joikUhNtzjXGiTqEQgEVPvu7du3dGNCIxIq8EP3pFwuh8/nw/HxMd68eQOv14tsNvtgc/k/BQ6Hg5aWFjQ1NSEcDsPtduPt27d0FKJRWuvfB5vNhkajgVarRTqdpp27R0dHdGi8EYMWMvCv0+lwfX1N1UV2d3cRi8WoeHkjgnAik8mknLi2toZoNIpcLtewdhFOFAqFOD09pZwYCoUahhM/uxO8vb1FOp2Gy+WC3+9HKBSi+e5Gaqu/C7lcjopEh0IhHB8fw+12N2R0WonLy0v4/X4wmUyaMjw9Pb2XfWu1xNXVFS4uLnB8fIxIJAKXy0XXVzWi8yMolUqIRqNwOBzIZDI0cAkGgw3p/Ahub2+RSCTgdDpRLpfh9/txeHgIv9/fEGT6YyCcGAwGaXbsr4ET8/k8DZaDwSDsdjvcbnfNl0t/TtREQFsqlUKhUIDJZKJYLCKTySCXyzU08QDfRz0qlQocDgeXl5d02WMjEw/w/U1QpVJBIBDQLdyZTKbhiYcoqYjFYlxdXaFQKND1VY0MstFbKpVWbRtv9GCMwWDQXXoAqF2NNOP4MZBtJUwmE5eXl8hkMg2RKvwpNAon/piAds22SDziEY94xCMe8RDwY06wJnOCj3jEIx7xiEc0Ah6d4CMe8YhHPOI3i0cn+IhHPOIRj/jN4tEJPuIRj3jEI36zeHSCj3jEIx7xiN8sHp3gIx7xiEc84jeLRyf4iEc84hGP+M3i0Qk+4hGPeMQjfrN4dIKPeMQjHvGI3yweneAjHvGIRzziN4tHJ/iIRzziEY/4zeLRCT7iEY94xCN+s3h0go94xCMe8YjfLGqyWb5eYLPZ4HK5YDKZuL29xfX1dcOvzQG+X51D7AK+3yd3dXXV8GtYmEwmuFwuWCwWAODm5gZXV1cPbg3LzwWDwQCXywWbzQaDwaB2Neri1EpwuVxwOBwwGAyUy2VcXV01/MotoJo7yuUyrq+vG37XH/A9d/B4vEdO/BH81ThBBoMBrVYLi8UCiUSCy8tLOJ1O2Gy2hn/oarUaFosFKpUKNzc38Hg8ODw8RDabrfdH+1WQSCQYGRlBS0sLmEwm/H4/Dg4OEI/H6/3RfhV4PB4sFgs6OjrAZrMRjUZhtVoRCoXq/dF+FVgsFvr7+2EymcDlcpFKpXB4eAi3213vj/arwGAwYDAYMDQ0BD6fj1wuB7vdDofD0dABGYPBgE6nq+LE09NT2Gw2XF5e1vvj/SqoVCqMjIxApVKhXC7D4/Hg4ODgF3Hig3OCDAaDRi2fegBJ5N3T04N//+//PTQaDeLxOP7lX/4Fp6enD8IJ/lK7OBwO2tra8Hd/93cwGAwoFAr4y1/+Arfb/WCcIJPJpDeDT43E2Gw2NBoNvvjiC1gsFtze3mJ1dRWBQODBOMFfYheLxYJUKsXi4iIWFhbA4XBwcHCAi4uLB+MEf4ldTCYTAoEAU1NT+Ju/+RvweDx6Bh+KE/wl7xiTyQSPx8PQ0BD+03/6TxCLxQgGg/inf/onnJyc1PgTfxp+DSd2d3fjH/7hH9DU1IREIoGvvvoKp6enD8IJ/lK72Gw22tra8G/+zb+B0WhEsVjEq1ev4PF4Gt8JMhgMiMViqNVq5PN5RKPRn0whkW3UHR0dGBoaQnd3NwqFAiKRCBKJxIOJ5AQCAdRqNUqlEqLR6Cc5ZpFIhLa2NgwPD6OnpwcCgQA+nw+xWOzBpKB4PB7UajWYTCai0SgKhcJP/gyfz4der8fIyAh6e3uhVCpxenqKcDj8IF5O4HsnrVKpIBQKEYlEkMvlftJhcLlcNDc3o7+/H/39/WhubobP58PFxcUnfS/3AbKVXiaTIRqNftIWcBKwdHV1YWBgADqdDsFgEKFQ6EEFYlKpFCqVCslk8pPefSaTCaVSic7OTgwNDaGzsxOxWAzhcBipVOqePvmPg3CiSqVCoVD4JE4EAKlUio6ODpjNZnR3d+Py8vLBcSKfz4darcbNzc0nc6JQKER7ezvlRKFQiPPzc0Sj0V+cvn4wjTEMBgM8Hg/Nzc0YGhpCV1cXxGIx2OyP+2kWiwWRSASdToexsTFYLBZotVpcX1/D5/MhEonUvQ5DbnMqlQr9/f3o6emBTCajdZW7QKLu5uZmWCwWjI2Nob29HQwGA+fn5wgGgw+iXsFisSCTydDT04OBgQEolUpwudyP2sVgMMDn86FSqTA4OIjJyUl0dXWBx+MhFArh/PwcxWLxnq34ECwWC2KxGEajEWazGU1NTbSu8jFwuVwoFAr09vZidnYW3d3dEIlEiEaj8Hg8yOfz92jB3WAymRAKhWhra8PIyAi0Wi34fP6P2sXhcCCTyWAwGDAzM4Pe3l4oFAqk02l4vV6k0+l7tOBuMJlM8Pl8Wg5pb2+HSCSitea7wGazIZFI0NHRgcnJSQwODkKj0SCfz8Pr9SIej9e95k5uc01NTRgaGoLBYPgkThSLxR9wYqlUwvn5OcLhcMNz4vDwMMbGxtDW1kbLKMFg8Bdn/B7MTZCQSF9fH7744gu4XC5kMhn4/X5kMpk7H5xQKERHRwfGx8fx/PlzmM1mCIVCpNNpnJ+fIxaL1f2Bs9lsSKVSGAwGPHv2DLlcDvl8Hqenp0ilUnfe6Ph8Ps3lP336FBMTE1AoFPB6vfQg19sJstlsiEQitLe3Y2FhASKRCJeXl7i5uUE8Hr/zQHK5XLS0tKCvrw9PnjzB3NwcvS2Rg1xvJ8hisSAUCtHa2orp6WkYjUbaKPGxmy65KfX09GBhYQHPnz9HW1sbUqkUQqEQ/H5/3Z0gg8GgJDI2NobZ2VlwOBwUi0WEw2Hkcrk7f0ahUKC7uxuzs7N4+fIlDAYDGAwGIpEIfD4fMplMHaypBslGmM1mvHz5Emtra8jlcvSmetfNRyKRoKurC1NTU/jiiy/Q29sLLpeLRCIBn8+HZDJZdydYGVh98cUX8Hq9lBPT6fSd3CYQCKo4cXh4GGKxGOl0mmaRHhInPn36FMViEYVCgXLiXdzG4/Gg0+kwPDxMOVGpVCIQCMDn8/0qTqz7TbAyKujt7cXExAQWFhYwODgItVoNgUDwQXRAIiS1Wo3BwUFMTU1hYmICLS0tSCQS8Hq98Pl8db36k9y1XC5Hd3c3JiYmMDc3B4vFgubmZgiFwjsjVQ6HQw/+1NQUJicn0d7ejmw2C5/PB6/Xi1gsVlcnSKLorq4ujI6OYm5uDhMTE9Dr9RCLxXfaRQ6+0WjE5OQkJicn0dPTQyNUj8eDcDhc1/otcYBtbW2wWCyYmZnB9PQ0Ojs7IZVK74zASTaCEM/k5CSGhobAZDIRDAbh8XgQDAbrmg5lsVj0pjQ0NITp6WnMz8/DaDRCLpffeXsnkTdJW09NTWF0dBQCgQChUAgejweBQKCu6VDSXUxS0FNTU1hYWEBfXx+USiV4PN6ddpFgbHh4GFNTUxgbG4NCoUA4HIbX66VOpl5O8H1OnJycxPz8POXEu27vP4cT6+UEKznRaDRifHwc8/PztDlOKBTemZW4ixM7OjqQz+cpJ0aj0V9cIqr7TZDL5UImk2FoaAhffvklJicn0dzcDDabjaurqzvJnhwQk8mE6elpmM1mWqhfX1/H6uoqfD7fR6PA+0BlqvB3v/sd5ufn0d7ejmQySduv33/JSL3GYDBgcnIS4+PjkEgkCAQC2NzcxJs3b+ByuZBKpep2kJlMJiQSCb3ZPn36FCaTCcFg8KNtypV127GxMUxPT0OtViMajWJjYwPLy8twOBz0u6kXRCIR9Ho9lpaW8PTpU5jNZlq0/9johlgshl6vh8ViwfT0NHQ6HTKZDDY3N7GysoKjoyPEYrG6OneBQICmpiZMT0/jxYsXGBkZgVgsBoCPjm4IhUI0NTVhcHAQ09PTMBgMuL6+htVqxdraGvb29nBxcVHXmzuPx4NCocDo6ChevnyJ8fFxKBQKMBgMatf7Z5HH40GlUqGvrw8zMzPo6+sDg8GAw+HA6uoqNjc34ff777wZ3xcIJw4ODuLLL7/E1NQUWltbcXR0REdS3reLcGJ3dzemp6cxPDwMHo8Hj8eDjY0NrKys0JtkvZw74USTyUQ5saOjA5lMhnL9T3HixMQEJBIJgsFgFSem0+nGc4Ikj6/RaGi9YXZ2Fu3t7SgUCojH40in07i8vPyAfAQCAYxGIywWC4aGhqBSqRAIBLC3t4fvvvsO+/v7n1xo/dwgdS8S7ZAorq+vD1dXV4jFYkilUigWix/YxeFwaNF3eHgYWq0WsVgMdrsdr1+/xs7OTl2bR3g8HnWAo6OjmJ+fh8Viwc3NDWKxGJLJJAqFwgekSsZXzGYzLBYLOjs7aVfh27dvsbW1hUAgULfbEpfLhUAgQFdXF8xmM73ZstlsuN1uJBIJ5HK5O18yjUaDoaEhWCwWmjrd39/H8vIyVldX4Xa7P6mpphZgs9kQCARoa2tDf38/5ubmMDU1BalUilgshkQigWw2eyf5yOVyDAwMwGKxoKenB2w2G3a7HWtra3j37h2cTudHU3K1BrnZtrS0oKenB7Ozs5iZmUFTUxPS6TTi8TgymQwuLy8/sEssFqOnpwcWiwX9/f0Qi8Vwu93Y2NjA69evYbPZ6haMEU5Uq9UwGo2Ynp7G7OwsOjo6PuDE9+3i8/kwGAxVnBgMBmG1WvHq1Svs7+/XLRgjnCiTyao4sb+/v4oTC4XCB5xIOkErOTEej8PhcFRx4q8JxurmBLlcLrRaLYaHh/Hy5UuMjY1Br9cjmUxiZ2cHOzs7tKvu/S9GKpVidnYWS0tL0Ol0iEaj+Prrr7G1tQWbzVbXdCGbzUZzczP6+vrw4sULTE1NoaurC8ViETs7O9jY2KCR5vsEwuPxMDY2hmfPnsFoNCKbzeIvf/kLVldXcXx8XNfIm8ViQaVSwWg04sWLF5ibm0N3dzcAYH9/HysrK/B4PHdGZEwmEwMDA3j+/Dn6+/tRLpexurqKN2/e4Pj4uK6RN5PJhEwmQ3t7O54/f47FxUX09vZCIBDg6OgIKysrOD09/SgxGo1GvHz5EmazGVwuF5ubm/jmm29gs9ng8XjqFnkzGAxIJBLo9XrMz8/jxYsX6Ovrg1wuh8fjwdraGux2+0frtzqdjt6upFIpjo6O8Kc//QkHBwc4PT1FOp2uW5aFpGknJibwxRdfwGw2o7m5GaFQCDs7Ozg8PEQ0GkWxWPzgu1er1VhaWsL8/DzUajW8Xi++/vpr7O3t4fj4GMlksm6d14QTSW1zfHwcer0eqVSqihPz+fwH371EIsHMzAyePn0KvV6PWCxWxYn1uhQA33NHU1MTent78fLlS8qJl5eX2NnZwfr6+o9y4ujoKOXEfD6PV69eUU4MhUK/mhPv3QmSLlCVSoWenh6MjY1hfHwcXV1dKJVKCIfDODo6ohE0OZBknqelpQVmsxmjo6Po7OykA6Db29vY399HJBKpW7RDOumMRiNGR0cxPj6Onp4eWh+y2+2UQAihkp9ramqCyWTC6OgodS5utxt7e3vY3d1FJBK586W+D3A4HIjFYnR0dGB0dBRjY2Po7+8Hn89HKBSC0+mE3W5HIpGg6VCS/1cqlWhra6M/w+VycX5+DqvViq2tLUQiEWSz2brdlEgKlHThDg0NQSKRIJlMwuVy4ejoCJFIhGYkGAwGWCwW5HI5Wlpaqn7m4uICh4eHWF9fRzgcrpujYLFYEAgEaGlpwdDQEEZHR2GxWKBQKGht+eDggDYiEeJhsViQSCRoaWnB6OgoHUaOx+M4Pj7G+vo6zs/P61ZXIjelpqYm9Pf307PY0tKCYrGIYDCI/f19nJ+fI5/P089IumLJ8xobG4NWq0Umk8HJyQk2NzdxcnLyq+pKvwaknqdUKikHjI+Pw2Aw4ObmpooTs9lsFSeS+qbZbMbY2Bg6OztxdXWFs7MzbG9vw2q11p0TSS9AJSeSLMuPcaJGo0F3dzfGxsbQ3d0NBoMBj8dTxYmFQuFXc8e9OkHiABUKBTo7OzE2NkaLogAQDofhdrvhcrmqupjIl6JUKrGwsIAnT55gcHAQHA4HNpsNOzs7OD09RSQSqcsNsNIB6vV6DA8P0yiOKIa43W643W5cXFxUfUbycxMTE3j+/DlGR0chEongcDiwvb0Nh8NBf+a+HQUhfIlEgtbWVlof6uzsBI/HQyqVgsfjgcvlQiAQqHLSpHmGRLXT09NQKBRwu93Y2dmB3W5HIBCoi13ADw0t5NZOxhrEYjFyuRx8Ph/cbjd8Ph/y+Tz9jEwmEyKRCCaTid6IW1paaDr+6OgI5+fndZN/Iw0tJKianp7GwMAA5HI5isUiAoEAXC4XvaWSz0h+rr29HS9evKA17EQigcPDQxwcHNCRiHo4wMrg2WAwYGJiAmazGSqVCqVSCaFQiL5jlU6aBM/Nzc30pm8ymVAqlWC327G7uwuXy4V4PF5XB0g4cXR0FKOjo3dyYuWM4Mc4kcvlwm63Y3t7G6enp79qfu7X2kW4jXR1Tk5OQq/Xg8PhfMCJlU76Lk4Ui8U4OTnB1tYWHA4HQqHQZ+OOe3OCLBYLarUara2tMBgMGBgYwMTEBDo7O8FkMuHz+bC5uYmtrS04nc4qJ8jhcGhrPWmEub29xenpKdbX17Gzs1PXaEepVKK1tRWdnZ20m8tkMtH5t52dHWxubuL4+LjKUbPZbKjVanR3d9OiLylmb25uYmNjA8FgsG41QKlUipaWFnR0dKCnpwejo6O0jhKPx3FwcICNjQ0cHR0hFArRz8lkMqs6wGZnZ2mDz87ODtbW1uD1euuW2hWLxWhqakJ7eztMJhMsFguGh4ehUCiQyWRgs9mwtbWFvb09BAKBqpre+12xzc3NiEQitGHE6XTWbRyCCDK0t7eju7sbZrMZIyMjaGpqQqFQgNPpxObmJra3tz9okiDjRiMjI5ibm0NHRweVRVtbW4PNZvtVzQe/BqTrUavVwmQyYWBggAaZRDKLcMfZ2RmSySR17qS13mw20zlHIqm4trZGZfrqwR2kxKDVaqkQAeFEFosFn8+Hra2tj3Jic3Mz7ZgcHh4GAJydnVFOrFf/AOHElpaWOznx4uKiihMrxxuISAXpqJ+cnASfz4fX66WcGAgEPqtd9+IESWGUkOL4+DiGhobQ1NQENpuNeDyO3d1d/PM//zNtaqlMZ5BGmPn5eRr92Ww2WqS32Wx1a9Vms9lob2/HxMQExsfHMTw8jNbWVgiFQsTjcdhsNnz99dfY2NigqT/ywLlcLtrb2zEzM4PR0VHodDrY7XZsbGzg7du32N3drdscFpPJRGtrK+1StVgs0Ol0UCgUSCQSODk5wZ///Ge8fv0aFxcXVekMFouF1tZW+p0YDAaannn79i02NzfrJo3GYDCgUqkwNjaGiYkJjIyMoL29HU1NTUilUnC73Xjz5g3+/Oc/09QfiTgZDAbUajVGR0cxNTWF3t5eRCIR7O7u4s2bN1hfX8fFxUXd7JLJZDCbzZicnMTo6CiMRiN1gH6/HysrK/j6669ppqXytiqVSqmj6O/vR6lUwv7+Pt68eUO7ret1AxSJROjr68P4+DgmJibQ09ODpqYm3N7eIhKJYHNzE//8z/+M4+NjWgskdpGfnZ+fx9DQEMRiMY6OjvD27Vta762XoyCcODExQdPqpDM+Ho/DarVSTiSpP2IX+dn5+XkMDw9DrVbDZrNhfX0d7969w9HRUV05sa2t7QNOFIlEVZy4vr5OVYsId5DmQMKJer0ex8fH2NzcpJz4uQUaau4EyZCuRqPBwMAAZmZmMDg4iPb2dpoqPD4+xs7ODo6Pj2kqqbKuRDoSLRYLlEolcrkcHA4Hjo+PkU6nwWAw6pIq5PF4dAyCtCUTBZRsNovT01Ps7Ozg6OgIHo+Hkg6xq3ImraWlhdY3SVs9gLrYxeFwIBQKaSfX2NgYDAYDRCIRbm5u4PP5sLu7i4ODA7hcLlpXIulTPp+P1tZWmM1mtLe3o1wuw+v14uDgAKFQ6GdpVn5OcDgcmvIjs4pGoxEymQwsFguhUAh7e3uwWq20TlEqlahdpE4xODgIo9EINptdVYeqVzMWmW/U6XQYHR3FzMwMTCYTVCoVOBwO/H4/rFYr9vb2cHJyUtUlyGQywWazoVAo0N/fj76+PvD5fLjdblitVvp86wGSoiU1r5mZGQwMDKClpQVsNhvn5+c4ODioSq9X2kV0XE0mE8xmMyQSCU3vnpycIJfLfVShpJYgnKhWq9Hf34/p6WkMDQ1RTiQd4ZWcSDpCyftJMhKkbks40WazIZVK1c0uHo8HqVRKOZF0gxNh8rOzs0/mxNbWVlxeXtLaPOHEz42aOsHKJgLS+j8+Po7m5mbweDxazF5fX8f29jYdlr69vaUvp0AggFKphMFgQF9fH92iQLoKxWIxWlpacHV1dW+RDxF+lUgk0Ol0GBoawsTEBNra2iAQCHB5eYloNFrV+UQOMXk5yRhFZ2cn+vv7IRQKEQwG4XA44PF4wOVyodPp6Bqe+wKpeZH08+TkJLq7uyEUClEqlZBMJrG/v4+1tTW43W4anZJDzOVyIZVKodfr0d/fD4VCgUgkAqfTidPTU9ze3lIZp/skV9JU0dzcDJPJhImJCQwODkIkEqFcLiObzeL4+BgrKytwOp3IZDI09UfWthAlmd7eXrS0tNDmGbvdjmKxiObmZpTL5XvtdCXNEaStntzaxWIxGAwGCoUCXC4XlpeXcXR0hFQqRc8TsYt8L729vXREyePxUEJVq9W4vb2tys7UGpWNVaRWNjY2BqVSCTabjWKxCJ/Ph5WVFVit1irHzmKxKHeQckN3dzf9GZvNhnA4DLlcjtvb26rmoPuwi8zLVXJiS0sL5cRQKISNjQ1sbW3h4uKiijvYbDb4fH4VJ5bLZfh8PuowxWIxWltbPzpnXSu7mEwmlWwbHBzExMQE2tvbfzYndnR0oL+/HyKRiHKi2+0Gh8OBTqdDqVRqjHQoaYvt7OzE8PAwRkZGMDo6CqlUikgkgkAgALvdTiO5ynkqsgKkp6cHRqMRPT09dHA8FArh9vYWk5OT6OvrA/B9Hvzbb7+Fx+O5c4bmc4Kk0zo6OjA4OEgL2SqVCqlUCna7HXa7HUdHR9je3qaESuzSaDQwmUzo7u6mnWBqtRrpdBr5fB5DQ0PQ6/VgMBgIBAL49ttvcXl5eedc4ecGGWjv6+ujz0ur1SKfz8PtdsPpdFK7SDco+UxyuRwmkwlGo5HW2YizSyaTMBgMkMlkuL29RTKZxF/+8hfk83lcXl7WvM5E6l1kPmxkZASdnZ0olUpwOBxwuVw4Pj7G9vY27QYlpCgUCuk5NBqN9LbPZDKRTCbR0tKCf/2v/zV1fisrK0in0ygWizUnIB6PB71ej+7ubmpXf38/GAwG3G43vF4vbf7Y3d2tqttyOBx6Dg0GAwYHB9Hb2wsOh4NwOAypVIovvviC7p/b3t5GJpNBOp2ueVBGegAMBgNGRkZgsVhgsVggEAjg9/txfn4Ou90Oq9WKnZ0dnJ+f0xlTJpOJzs5OmEwmGAwG2kXK5/MRi8XA5XKxuLiIiYkJ3NzcwGazoVAoVAXgtQKLxYJGo/mAE4mYeSAQwPHxMQ4PD7G9vf0BJ2q1WvT29sJgMKC3txdjY2OQSCQIh8Mol8uYmJhAb28vGAzGB5xYS+4gNcDOzk4MDAxQTlSr1UilUnA4HB9wYqUij1qtvpMTM5kM8vk8BgcHodVqwWAwEAwGKScSmcZfi5o5QTabDa1Wi5mZGTx58gQTExOQyWS4urqijQRv3ryBzWZDPB5HPp8Hl8ulSztNJhOePXuG8fFx9Pb2QiaTAfg+PSgUCjEzMwOBQICrqyusr6/TVNv19XVNozomkwm1Wo3JyUksLCxgbm6O7rQ6OzuDzWbD69evsbu7i3g8jlwuRzss2Ww2urq6sLCwQLv2VCoVmEwmUqkUWCwWVfO4vb3F4eEh7HY73G43rq+va36QZTIZLBYLFhcXMT8/D61WCxaLBa/XC4fDQQfAY7EYMpkMVbhns9nQ6/WYmZnBzMwMLBYLmpqawGKxEIlEUC6X6YwaAHi9Xup4SqVSzZ2gSCTCwMAAXW9E0jOhUAgulwurq6t49+4dQqEQHWsgsnZqtRoTExOYnZ3FyMgI2trawGazqe4r6XJmMBi4uLhALBbD9vY2tauWpMrj8WAymejcW29vL21a8vl8tLZMtDBLpRKEQiGts1ksFiwsLGB0dJSm8fP5PEqlEhWyZ7FYtHFke3sbhUKh5h29XC4XHR0dWFxcxOLiIoaGhiCVSpHP5xEMBrGzs4M3b97g9PSUjuXw+XwIBAJwOBwMDg7iyZMntLVeLBbT94cEa1wuF7lcDjweDzs7O3QOtJZ23cWJcrkcV1dXNP385s0bHB0dIR6Po1AofMCJT58+xfj4OPr6+ignlstl8Pl8TE9PQygU4vr6GhsbG1WcWEvuIJw4Pj6OhYUFzM/PQ6VS4fb2Fi6Xq4oTY7HYRzmRpLsJJ2YyGTCZTJrZuL29hc1mq+LEB+8EiQhxX18f1Go1OBwOJYbb21uIRCI0NTVBLpfTmhKfz4dUKsX4+DgWFxfR1dUFtVoNNpuN6+trNDU1QSaTQSaTgcvlIpvNQiwWg8Ph0D1ptQR54JWFbEIeRGKLpGEkEgk9fCRNODAwgKWlJfT09KC5uRlcLhelUgkqlQpcLhdyuRx8Ph+Xl5eQSCR0e/J95PhlMhmNULVaLcRiMY36y+UyeDwelEolhEIhlaQi9Qmj0YilpSW6aofP5+Pm5gYKhQLA912VIpEI19fXSCaTdCvDfdglFArR399P0zNSqZSewXK5TFuy2Ww2PZ+VavxLS0sYHh5GW1sbxGIxrWmS9LdUKqXpXYFAcG928Xg8qizS1dUFuVxOtRfL5TKtibW2ttKUJqkfqtVqSsTt7e2UUJlMJnQ6HS1jVJ5pFot1L3aRHZozMzPo7u6GSqUCm82uSr2TeUalUolyuUzrhzKZDPPz85iZmUFHRwdUKhUYDAYuLy/R0tJCHSGTyUQikYBIJKLcUWuwWCy0tLRQTtRoND+LE0dHRyknajSaKk6USqVUBzaXy1FOvI/nxWQyabMZES7g8/l0qJ+cH5VKBYlEQh0Xl8uFRCKhnNjb20s3thBOJO8mSakSTmQwGJ/Nts/qBMkHI4OppCDd0tJCRZXJ4CoRvW1paaEHgNSjSMHYbDZDJBLRA0rmYkiUnUqlEIlEEA6H6QtSq0iO1JSIasrQ0BC9FRDbye/39PRAoVDQz1NZCO/u7sbIyAjkcjn9ToiorEgkQqlUQiaTQSKRwMXFBXK5XM3tIlqFpE27q6sLfD6f2kUGeQ0GA3g8XtXnIbNbpEhPboCVTU18Ph+lUgn5fB7JZBLBYBDZbPZObcfPhcoGgo6ODgwMDMBkMkEkEtFGKhJ0dHR0gMlkVt0EyFkjAtJkvonUdIRCIQ1gisUiUqkUgsEg1XWtpV1kyL+trQ19fX10bIW8J0SsnIwQVA4Us9lsyGQytLS0YGRkhD5TQiikPlgqlXB9fY10Oo1QKFTVJVsru8j7T0ohZrO5yrGTwKS1tRXX19fo6Oig3EFuFmq1GhaLhTb4kJ8lmyYIdxC7otFoTdOFd3Hi0NAQWltbqziRzHaSPZR3cWJfXx+Gh4d/lBPT6fQHnFgrEE5UKpWUE9vb28HhcKrsIpwol8s/4ESiAX0XJ8pkMtqLkM1mkUgkEAqFqHP9XGfxszpBolQxMjKCp0+fYn5+Hs3NzTQ6Br4/jFqtlnYfvl/gJDqOSqWSbiQgBt/c3CCXyyGRSOD8/Bynp6ewWq04PDykXWy1eOgsFgs8Hg+9vb14/vw5HSSuVD0navY8Ho9q/VWCdCbK5XK6O4tE2YSokskk/H4/zs7OcHh4iP39fdhstpo1JJBB4o6ODiwtLdFojKQ4CeGq1WqwWCzodLoPdDDJMycLTblcLn2Bb25uUCwWkU6nEQgE4Ha76eD10dHRR/U4Pwd4PB5aW1sxNzeHp0+fYnh4mKZfKhu2TCYTmpubYTabq84OeYHFYjE0Gg14PB4AVAlqZzIZulHBZrPR5/UxPc7PAS6XC5VKhenpaSwtLWF6epp2txJHJhaLYTAY6L62yrNDgjUikM3n82lQQFZGZTIZRCIReL1eHB8fY39/n6boalU3IwHTxMQEnj59itnZWbqfkrxjpLOXdGRX1lxJsEZuueTdJNxBiDQWi+H8/BwOhwNWqxVHR0d0FrdW3CEQCGCxWLC0tISFhQW0trZ+wIk6nQ5CoZA28FTiLk4kz6uSE/1+/52cWAvuIJzY09NDObGjo6OKE4kSFklvvz8/S5qXfowTU6nUnZx4l0bxL8VndYKEVLu6uvDkyROYzWZIpdKq1TpcLhcajQYajeajf0/lA85kMrQOcXl5iXA4jPPzc5ycnGBvbw9ra2vw+/2f04wPQF4wnU6HhYUFTE1N0ReUfF7SyaZUKn/ULuIcSCMMaTwghfGTkxPs7+9jfX0dTqez5naRodvZ2VksLi5CoVBQu4AflN9Jauyn7CLP6/LyEtfX1zR6Ozk5weHhITY2NmCz2WpaB6zsLBwfH8ezZ8+qHBmBWCyGRCL5UbsA4ObmBvl8njbykBvSxcUFHWnZ3NzEwcFBzQflSYrTbDbj+fPn0Ov1H6xCEgqFEIlE0Gq1P2nX5eUl8vk8beTJZrNUpYTMZ+3t7SGZTNbcLpFIhJ6eHrqZ5P01akQ2kaipfMw2EqQUCgUUCgWahSCrkhwOBx1Cj0QiNbWLcGJnZydNq5NgjIB096rV6p+062Oc6Pf7qWNfW1vD+fl5Te0inKjVammPQyUnAvhFnFgoFHB1dUU5MRgMfsCJnzsI+6xOkBw+skxUr9dDJpPdufsK+PgM3O3tLXK5HKLRKBwOBy2Ap1IpulQ2mUwiHo8jkUh8ThM++nkqI/9YLAaJREKv/eTP/JRdAKgavNPppHqFZFEmSafF43FEo9F7sYsQXygUwsXFBYRCIU2FEpCbwo/ZdXl5iUQiQckzHA4jk8ng4uICfr8fiUQCyWSySvqplnZVEl8oFIJYLIZIJPron/8YiCM/Pz+nYznkpuT3+xGPx6ld9zF0TRwyIQi5XE5rnO/jx+wql8s0NX18fEwVZMhNiWwFIcIVtQbJGiQSCQSDQVr7/yXckU6nEQ6HYbfb6eoxclOKRCJIJpO0uavWKJfLuLy8pOlyvV7/wcXgU+0inHhycoLT01O6VeL8/BwXFxeUO+5DiOJ9ToxGo7QO+XPsAr7nRCLAUcmJgUAAwWAQyWQSiUQC0Wi0NlmIz/mXESdIVniQ+hGpOTAYjKrdbEKhEGKxmH555Gofj8fh9/vhdrtxcHAAh8OBeDyOVCqFi4sLKotEftUa5XIZpVIJkUgEBwcHtHYnlUqr7CLdSgKBACKRCGKxmKYH8/k8fcG9Xi8ODw9hs9kQiUToSxuNRmn65j7sIs4ikUjg+PgYKpUK19fX0Gg01C7iKEulEng8HrWLOEpCXBcXFzR9RrrSMpkMotEoLi4uaPH/vgblSX3E6XRia2sLNzc3yGazVXaRuheHw6F2kdvH1dUVkskkTQuSaJRsU4/FYlTzkJzD+7CLOEG3243t7W0A3+8ErGwUIHaRehKxjcFg0Fp6LBaD1+uF0+mkogfpdJo+y8q6y329Y8ViEefn59jd3aVlEOIsGAwGbm5uaAqU3HZJ6p7U0klnLEmfOZ1OJJNJJJNJXFxcUL3U++SO6+trhEIh7O/vg8/n027Ou7iD2EWC7EpOJLqvh4eHcDgciMVitLZZL06MRqOUE29ubj7KiXw+n9pFOJFcCEKhEBXTqAygCSeSGnut7KqJEzw7O8PV1RVCoRACgQBEIhGtWVxeXiIej+P6+hpdXV0wGo3o7u6GVCqlg72kvffo6AjhcBiJRIKmoUga4D5BCDMQCOAvf/kLLi4uEAwGoVQqqV3kxpDL5dDe3k7n5UjROhAIYH19ndZXAoEAbYMmzRX3rV9I7AqHw3j79i2i0Sj8fj8djWAymbi5uUEqlUI6nUZzczN9XqShKRKJYGNjA7u7u1Q8mtweiF31UBy5ublBIpHAxsYG4vE4gsEgurq6wGazwWQy6Y0hmUxCLpfDYDCgp6cHOp2OzgBubW3R2UGPx1Ml8UTSbfetfEPSYXt7ezTjMjAwQJ8Xg8GgpEl2JJJZQDLaUan5enZ2hkgkglQqRe26z+FxAlIDOj4+Rj6fp9xR2R1dLBYRi8XAYDBgMBjoWRQIBMhms3A4HNjc3MT+/j5OTk5oxogMjZN37b7turq6gsvlquJEUtsjAVc8Hsfl5SXlRJPJBKlUimKxSPcdEk68uLh4UJz46tWrKk4kdXfSCZ7NZtHe3g6DwUCVjCo50Wq1wmaz0YxRJXfcR3bls49IlMtlOh9HugFJe3Ul5HI5WltbabogEAjg9PQUe3t7WF1dpakM0uxSD5mtSpTLZaRSKeTzeeRyOWQyGdqQUAnSBXp7e0vz9V6vF1arFaurq5R4at0d+akgaRYymJvL5WgjTGU9hhTnge9ThLFYDIFAAIeHh1hdXYXVaqXixbWej/sUkEjz/PycLlg9PT2tsovUDg0GA4Dv7UqlUjSVtrq6iq2tLargX+t5q08BOVfkpn15eQm/30+dIPBDp6Ver0d7ezt1nGQZ6dbWFtbW1nB6eopQKFS3jRfv20WyLdlsFoVCAbFYrGp8gTy3pqamqs7XcDgMp9NJxdkdDgeVGquH3un7eJ8TU6nUnZwok8nQ2tpKVWyy2SzOzs4+4MRad8J/KsrlMq3jZbNZZLPZj3KiSqUCgCpO3N/fx+rqKg4PD+vKiYwf+wcZDMYv/jSku04ikdBIjslkQqFQYGhoCFNTU5icnIROp8PV1RWsViu++uorqtxPHM5DeNiVIIXuyk5DIhfU39+P8fFxOt90dXUFp9OJr776ii7TrYx0HpJdpNBdOYdDWqC7u7sxPj6OqakpWCwWlEoleL1e/PnPf6bD2GQItl6rkT6G90c1SKqGw+Ggs7MT4+PjdIMHg8FAOBzGd999h++++w4ul4umBh+Co3gfZFSCjH2QZ6bT6ajY9NTUFAQCAVKpFN69e4c///nPODk5QSAQoA0xD80uMoJCUrhMJpPO546OjlLdV5VKhUKhgLW1NXzzzTc0w5LJZOpym/0pVHYck2CMbFyp5ES9Xo+rqyvs7+9TTvT7/Uin0zUfmfolIB3Hd3EiET4nerZXV1c4PT3FV199hfX1dZoRqzUn3t7efnSosGbD8kRGiugostlsaDQayOVydHd300Hzq6sr7O3tUbX6s7Ozms+3/BqQ6JOMQJDNAq2trejq6sLw8DC0Wi1ub2+pFuXKygqOjo7uVXvx54LcMCrTDwqFAkqlEu3t7TCbzejo6ACXy4XD4aAbPHZ2dqjze4ggNc3KZgGi+Uo0Dg0GA8RiMRwOB1VZ2draomokDxWkvpdKpQCAzt8S3VcymxUIBLC5uYk3b95gY2MD4XC4bqLYnwJycyWNKzweDxqNBiqVCr29vejv76eyWkQ9hiz8rUeK+lPxPicSGbVKTiQ6yFarFW/fvqWceNc2+YcCknWp5ESVSlXFiTqdDgBgt9spJx4eHj4ITry3fYJkzm5xcZG2ChcKBRwcHOAPf/gDVldXEQgEHrQDvAssFgtdXV1YXFzE06dPMTk5iVKpBLfbja+//hqvX7+G1+ulEVwjQafTYW5uDktLS5iZmaG6kt999x1dyZPJZOp+iH8u1Go1nbObm5uDVCpFOp3GysoK/vCHP+Dk5KRuS1Z/DWQyGUZHR/Hs2TM6j5bP57Gzs4P/83/+D23Eqtd+yl8KoVCIoaEhPHnyBE+ePIHBYEChUMDR0RF+//vf0915D9kB3gUyZ/fkyRMsLS3BYrFQu/74xz9iZWUFfr//QTvAu8BkMqkUGuFEsvjgT3/6E169evWgOPFeVilJJBJotVqYzWaMj4+jo6MDDAYDLpeLrgsh6ZmH8KV8Coj+okqlwuDgIMbHx2E0GsHj8Wjnns1mo92EjWQXn8+HTCZDX18fFeUVi8Xw+XzY3t7G4eEhPB4PVUdpBJB0r0wmq9oiIZfLkUgkYLVasb+/X7VlvBEItXIrQeUWCY1Gg3w+j4ODA7oaioxxNIJdwPdkSpSMRkZGMDY2RkXZiTC4w+HAxcUFisViw9hFOLG1tZVukSCqRW63m3JiozlAooyjUqno4mOj0Qg+nw+Hw0GbzHw+H7LZ7IOxq6ZOkKzW0Wq1GBwcxPDwMHp6eiAUCuky0u3tbeoAG4VQyQqapqYm9PT0YHh4GP39/ZDL5bT7bm1tDR6Pp2olz0NH5Vqerq4umM1mDA4OUkIlItpk195DTYG+DyaTCQ6HQ7tAzWYzzGYztFotrq+vcXZ2huXlZTgcDpoCbQRCrax3dnZ2YmhoCMPDw+jo6AAA+Hw+uj2dLJttFLuI0kpbWxsGBwdhsVjQ3d1NdzhubW1hb28PFxcXDXUDrOTEgYEByokikYhy4tbWFnWAf42cWLlY/CGgZk6QRHFarRbT09NUNBYAnE4njo+PaWdQIpFomIdNNidotVqqwt/f3w8ulwuPx4OzszO64ywajTaMAwS+7+JqbW3F4OAg5ubmYDabIRaLEQqF4Ha7sby8jO3tbQSDwYZxFMD38k2tra3o6enB3NwcLBYLVCoVYrEYPB4P1tfXsb6+Dq/X2zCOAvieUJuamtDV1YW5uTmMjY1Bp9Mhk8nA5/PRbklSZ28Uu1gsFpRKJdra2jA3N4eJiQkYDAZcXV3B4/Hg4OCAdktms9mGsYtwYmtrK6ampjAzM4O+vj4wGAycnp42NCcShaJKTuTxeHRjDOHESCTyoBwgUCMnSDYMt7a2YmxsDM+fP8fMzAydDSEt2js7O/D5fA+6+aASpKtQrVZjeHgYT58+xYsXL8BkMnFxcYHd3V2sr69ja2sLTqezoRwFEfEmK4e+/PJLiMViRKNRHB4eYm1tDVtbW3SBbKO8oGT5cU9PD+bn5/Hll1+iubkZ6XQadrud2nV4eFhTLdPPDSJEbzAYMDMzg9/97ncwGo0oFAo4OTmhdlmt1oaqb5KO5La2NkxNTeHly5cwm824urqC1+vF2toaNjc3sbOzQ8UKGgGEE1taWignzs3N4ebm5gNO9Hq9DWVXJScuLS3hiy++oJy4t7dXxYkPMR1fk/0hZLPAwMAAXrx4geHhYUilUoTDYWxvb2N1dZUu+XyILdofA0mp9fT0YGlpCePj49BoNEgkEtjd3aUvKOlSaxRHQVJqlXu9dDodrSmtrq5iY2MDbre74VI0IpGI7jokuwTL5TJsNhtWV1exvr6Ok5MTZLPZhnIUAoEALS0tGB8fx/Pnz2EymcBisXB6eoq1tTWsr6/DZrPVfPvD5wRxFBqNBsPDw3j58iX6+/shEAhwfn6OjY0NrK2tYX9/v+Hqm2QNWX9/P168eAGLxQKZTIZwOIytrS2srq5iZ2enITmR1NmXlpYwOTkJjUaDZDJJ5xs3Nzfh8/keLHfU5CZI1oYMDg5icXGR5oVtNhuWl5fpAHKjgcfjoampCb29vXSTxOXlJZxOJ3UUDofjQT7oHwPZTGAymTAzM4PBwUEAgNvtxvr6Ok09vb8Z46GDzWZDoVCgs7MTk5OTGBsbAwCcnJxgc3OTjq6k0+k6f9KfB5JWa2trw9jYGKanp+k28Z2dHSwvL9M6YCOBlBp0Oh2Gh4exuLgIDodDJceWl5exs7ODQCBQ74/6s0GCFsKJCoUCmUwGNpsNKysrlBMbxakTVHLi3NwcOjs76Xx0JSc+5ADzsztB0vmk0+mgUChweXmJ4+NjmqJxOBw1V6SvFYRCIbRaLTQaDW5ubuByuXB6eoqVlRXYbDaq/dloeF+d//z8HB6Ph5LpxcXFg8vjfwpIoZ7sAry4uIDH46FNFURVpNHAZrOhUqnoUt9EIgGPxwOr1Yrt7W14PJ57Eb3+3CCD40RkOpvNwu/3w2azYXNzE6enp/ciel0LEE5UKpW4vLyE3W7HyckJ1tfXaUNWozlA4HvnrtVq0dTURDmR9EWQkZyHfimoyU2QLPQkHU82mw0bGxuUeLLZbC3+2ZqDpNYUCgUVw15bW8Pu7i48Hg/S6XTDHmSdTofm5mbk83lEIhGsr69je3sbZ2dnDVWkrwTZ8UhUiU5PT7GxsYHt7W2cnJwgFos1pHMnOx71ej0AwOPxYGNjA1tbW7DZbAiHww3p3BkMBhQKBV0P5ff7sb29ja2tLezv79M54kYDg8GgnCgWixGJRGC326nmrs/nowP0jQbCiUqlkmrZktpmo3BiTW6CJFXDZrNhs9mwtraGtbU1BIPBhhoZeB9km7dIJMLZ2RkODg7w7t07nJ+fUwHiRgSfz6cH2e/3w+l04u3bt3C5XA01MvA+uFwuWltb0dLSQsXB3717B7vdjlgsVtON4rUEUV/S6/XIZrPwer301h6JRBqqplQJJpMJpVIJvV6Pm5sbqi1JmmAeak3pUyCVSiknHh8f0zJDKBR6cCMDPwdCoRBtbW0Qi8VwuVxVnJhMJhvCrs/uBIn8FtGDCwQC2NnZebCdQT8HZL2Ox+NBIBDAwcEB7HY78vl8Q9tF1g6dn58jEAjAbrfTpopGtousoQmFQlRk+fDwEKFQqCGdBEG5XEY+n6ergdxuN/b39+H1ehs2wAR+kN+KRqMIh8Pw+XzY29ujW2kaGYQTC4UCAoEAdnd3/yo4kYjOu91uKqhvt9uRy+Uaxq6aCGgrlUo0NzeDyWTShYmpVKqhiQcAVb7hcrlUDb5RU4WVEAqFaG1thUgkQqFQQDqdpuuuGhmk1imXy6nSfTwef9C6mZ8CMh9I9j+S1UmNHowRkWyNRkN3cMbjcWQymYa2C/jr5sTW1lbweLwHzYk/JqBdsy0Sj3jEIx7xiEc8BPyYE6zJnOAjHvGIRzziEY2ARyf4iEc84hGP+M3i0Qk+4hGPeMQjfrN4dIKPeMQjHvGI3yweneAjHvGIRzziN4tHJ/iIRzziEY/4zeLRCT7iEY94xCN+s3h0go94xCMe8YjfLB6d4CMe8YhHPOI3i0cn+IhHPOIRj/jN4tEJPuIRj3jEI36zeHSCj3jEIx7xiN8sHp3gIx7xiEc84jeLmmyWrxeYTCY4HA4YDAZub29xc3PT0PvVCJhMJthsNpjM72MWYlejr5dhMBhgs9lgsVgA/nrsAgAOh0PtKpfLKJVKDb82BwB9XuQdu76+/quwi8Vigc1mU7tKpdKDWwf0S/DIiT+NvxonyGAw0NzcjJ6eHohEIlxdXcHr9cLlcjX8XjyFQoHe3l7IZDKUy2UEAgGcnp4in8/X+6P9KohEIvT29kKj0YDBYNDFt6lUqt4f7VeBy+Wit7cXra2tYLPZSCQSODk5QTQarfdH+1VgMpkwGAzo6OgAh8NBNpuF0+lEIBCo90f7VWAwGNDr9eju7gaPx0OhUIDb7Ybb7W7ogIzBYKCpqQm9vb0QCoW4vr6Gz+fD2dlZw3OiXC5Hb28v5HI5yuUygsEgnE7nL+LEvxonyGQyYTQa8R/+w39Ac3Mz0uk0/vSnPyEQCDT0A2cymdBqtfj7v/97GI1GXF1d4c2bNwiHww3tBBkMBpRKJX73u9/BYrGAxWJhY2MDyWSy4Z2gSCTC4uIi5ufnwePxYLfb8b/+1/9qeCfI4XAwOTmJL7/8EkKhED6fD//7f//vhneCLBYLAwMD+Md//EdIpVJEIhH88Y9/hNfrbejbIAla/vEf/xEtLS1Ip9P49ttv/2o48e/+7u/Q3d2N6+trvH379hdz4oNyggwGA0KhEAqFAoVCAclk8pMOoVQqhVarhdlsxuDgIEqlEkKhEPL5/INJ1fD5fCgUCtzc3CCRSHzSISQb34eHhzE4OAipVAqn04lsNvtgXk4OhwOlUgkmk4l4PI7Ly8uf/Bkej4fm5mYMDw9jaGgIOp0OPp8PmUzmwbycLBYLCoUCfD4f8XgchULhJ28FHA4HarUaJpMJZrMZHR0duLi4QCqVwtXV1T198h8Hk8mETCaDRCJBIpFANpv9SbtYLBaUSiXa2tpgNpthNBoRi8WQyWQ+6XnfB5hMJsRiMeRyOdLpNNLp9E++++S70Ol0GB4eRl9fH9LpNFwuFwqFwj198h8H4US5XI5isfjJnCiRSKDVajE8PIyBgQHc3t7i4uICuVyuoTlRIBBQrh8aGoJMJsPp6emv4sQH0xjDYDDA4XCgUqnQ29uL9vZ2CAQCmvO9C0wmE3w+H01NTbBYLBgeHoZer8fNzQ18Ph/C4fCDcBYsFgtyuRwmkwldXV0Qi8W0XnQXGAwGuFwuVCoVhoaGMDo6is7OTrBYLJyfnyMYDD4IUmUymZBIJOjq6oLJZIJMJgOb/fG4ijxjmUyGvr4+TExMwGAwQCAQIBQK4fz8HMVi8R4tuBtMJhNCoRDt7e3o6+uDSqWidZWPgc1mQyKRwGg0YmpqCiaTCVKpFLFYDF6vF7lc7h4tuBsMBgN8Ph+tra0YGBhAU1MTeDzej9rFYrEgFovR0dGBqakp+n1kMhl4vV6k0+l7tOBukPelqakJAwMD0Gq14PF4P8kdAoEAOp0O4+PjGBwcRHNzM4rFInw+H+LxeN1ToaRmrlQq0dfXh46Ojk/mxObmZsqJbW1tlBMjkciD4USZTIbu7m4YDIafxYmDg4MYGxtDZ2cn2Gz2r+bEB3MT5HA4NM/7/PlzuN1u5HI5hEIhZLPZO6MXcohHRkbw7NkzjIyMQCwWI5PJwOfzIRaL1T3q4XA4EIvF6OrqwpMnT5DP53F5eQmPx4NMJnNnkZrH46GlpQWDg4NYWlrC5OQklEolQqEQfD4fLi4u6n5jYrFYEAqF0Ov1mJ+fh1AoRKlUwsnJCZLJ5J2fj8PhQKPRwGQyYXFxEXNzc2htbUUwGITf70cgEKj7zYKQY0tLC6amptDZ2QkGg4FSqfTRmy6LxYJKpYLBYMDs7CyeP3+O9vZ2FAoF6tzrnbpmMBgQCARoamrC6OgoJicnwefzcXV1hWg0eufNh8FgQC6Xo7OzE1NTU3j+/Dm6u7vBZrMRiUTo7b3e4PF4UCqV9H3Z2tpCsVhEOBxGLpe705lJJBK0tbVhfHwcL168wNDQEPh8PhKJBHw+HxKJRN2dIAkYe3t78ezZM5yfnyOXyyEYDCKXy93pzMhNyWKx4NmzZxgdHYVEIkEmk8H5+Tmi0WjdnSCbza7ixGKxiMvLS7jd7h/lxObm5ipOVKlUiEQiOD8//1WcWHcnyGAwwGQyIZfL0dXVhdHRUTx58gRyuRxHR0dIp9N3pjXZbDYUCgX6+/sxNTWFmZkZNDc3I5/PIxAI4Pz8HIlEoq4PnETRbW1tsFgsWFxcRCwWg91uRzQavfN2UBkhTU5OYnp6GkajEZeXl5RQY7FYXTu8mEwmRCIRtFothoaGMDc3Bz6fD6fTiYuLC2Sz2Q8OJIvFgkgkQldXFyYmJjAzM4OhoSFcXV0hHA5T515PJ0ii6JaWFvT392NmZgbd3d1wu904Pz+/M/1HnGZbWxtGR0cxMzODsbExXF9f4/z8HD6fD8FgsK7pNdIhqFar0dPTg8nJSSwtLSEYDFLiKRaLVaRPIm+Sjp+ZmcH09DSYTCb8fj/9lc1m62YXg8Ggqdru7m5MTEzg6dOnuLy8hNPpRDqdRqFQqOIA8jMajQaDg4OYnp7GzMwMxGIxkskkAoEA/H4/0ul03Zwg4USZTIauri6MjIxgaWkJh4eHODw8RCqV+sAu4AdO7Ovro3a1tLSgUCggGAxS517PiwGLxaIBCOHEZDJJOTGfz3/AbSwWC1KplHLizMwM7Y8gF4NoNNq4TpCkkfr6+vDs2TPMzMygra0NJycnuLm5udOJcTgcKBQKGI1GTE5OwmKxQCKRIBgMYm9vDxsbGzRKrddBJg/baDTi6dOnmJ+fp86sXC7faRdJm3Z0dGBiYgITExNQqVSIx+OwWq1YWVmBy+VCKpWqm3MntZf29nYsLCzgyZMn6O/vRywWA4CPtimTgz8yMoKpqSm0tLQgl8thb28PKysrODk5+eS6QK0gFArR0tKC2dlZPHnyBBaLhY463Nzc3GmXSCRCa2srzGYzpqen0dHRgevra+zv72NtbQ02mw3RaLSu6Wsejwe1Wk2dBDlXHA7no89LIBBArVbTILO7uxssFgvHx8fY2tqC1WrFxcVFXdPXXC4XMpkMw8PDePr0KT1XPB6PjqS8bxuXy4VCoYDJZML09DQGBgbA5/Ph8Xiwvb2N7e1t+P3+uqavCSeSrBjhRJfLhZubmzvtIpk0g8GAqakpWCwWSKVShEIh7O3tYX19HT6f75NqpbUC4USDwVDFiXa7nY5vvG8XCQY6OjowPj5Oz24ikcDe3h6Wl5d/NSfWzQmS+pBcLkd7ezsmJibw4sULdHd34/b2FrlcDtlsFldXVx98MTweD21tbRgaGsLY2Bja2tqQTqexv7+Pb775Bjs7OwiFQnV7QTkcDiX90dFRPH/+HBaLBQwGg9pFnGElWCwWWltbMTg4iNHRUXR3d+Py8hInJyf485//jM3NTfj9/rql1thsNgQCAfR6PSWe+fl5sFgs+Hw+ZLNZFIvFD+xiMploampCX18fRkdHaaHe4XDgzZs3WF1dhcfjqRvxsFgscLlcaLVa9Pf348mTJ3j27BlEIhENpvL5/J0vmVKpRE9PD0ZGRmhK7ezsDMvLy3j37h29kdQjGGMymeByuWhubobJZML8/DyePXsGtVqNTCaDbDaLfD6P6+vrDz4fibxJXUkul8Pv92NjYwOvXr2CzWZDPB6vSzBWebPt7OzEzMwMnj9/jra2NpRKJWSzWeRyuTsDKpKNGB4exsjICJqbmxGJRLC7u4tvvvkG+/v7iEajdclIVHJiW1sbJicn8eLFC5hMJtze3iKbzVLu+ClObG9vp5z47bffYnt7u+6cSIJnwokjIyOUE0k24q6Mn1arpXVAk8lEb/qvXr3CxsbGr+bEujlBkmoZGBjA0tISxsfH0dbWhlQqhcPDQ+zu7tKW1/e/GJlMhpmZGSwtLUGn0yEajeLNmzfY2trCwcEBQqFQ3SJvNpuN5uZmdHd309x1T08PLi8vcXh4SB3ZXTl9Pp+PsbExPH36FEajEblcDm/fvsX6+joODg7g9/vrli4kda+Ojg48efIEMzMzGBgYAAAcHBxgZWUFHo8H6XT6g3QGk8nEwMAAXrx4gf7+fpTLZaytrWF1dRX7+/t1dYAkFa/Vammdkjizk5MTbGxs4OzsDKlU6k5SNRgMePnyJSwWC7hcLqxWK968eYODgwOcnp4ilUrVxQEyGAxIJBK0trZiamoKS0tLGBoaglwuh8/nw+7uLux2O+Lx+J3vilarxYsXLzA5OQmJRIKTkxO8efMGe3t79OfqdaMQCARobW2FxWLB06dPqTMLh8M0ZRiNRu8kVbVajSdPnmB+fh5qtRrn5+d48+YNdnd3cXBw8KvSar8WhBNJIDYxMUGdWSUnFgqFD+ySSCRVnBiLxR4cJxqNRjx58gRTU1OUE4+Ojqgju4sTeTweRkZG8PTpU3R3dyOfz1dx4udoprt3J1gZ7RiNRoyNjWFubg7d3d1gMBjw+XywWq00giYHktQolEol+vv7MTExgd7eXgCAx+PB2toadnd3EQqF7oyU7gMk2uns7MTo6ChmZ2cxNDQELpcLn88Hm82G4+NjJBIJ6sxIBxipiY6NjWFwcJDeKDY3N7G2tlbXkQ82m02bYEZGRjAzM4Px8XGIxWJEo1E4HA5KPOSGS2ovUqkUzc3NGBkZwfDwMKRSKS4uLrC7u4u3b9/i4uICmUymLjcKFotFCdVsNmNqagpTU1NQKBTIZDI4OzvD3t4e/e7JZyS1XpVKBYvFgrGxMZq2Pjw8xOvXrxEKhZBMJutSuyW1TY1GQ9+V2dlZqNVq2v24vb1NGy3IZyRdsSqVCmazGZOTk9DpdMhkMrDb7Xjz5g08Hg+tSd/3O1bJAT09PRgfH8fc3Bz0ej1KpRKCwSB2dnZonbOSO/h8Pu0snJychMFgwOXlJU5PT/Hu3Ts4HA7aXFEPu0gTjMFgwNjYGObn52EymcBgMHB+fo79/X3KicSZVXbU9/f3Y3x8HH19fWAwGJQTd3Z2aNq6npzY0dGBkZGRqiDzUzixo6MDY2NjGBoagkAgoJy4urr62Tjx3p0gyQvrdDpYLBZYLBbodDpwOBza6VP5ogE/fCnkBri4uIihoSEIhUIcHx9Tp0kaK+rxsEnjR0tLS1VKgs/nI5VK4fz8HG63+4MuJkKopCFodHQUcrkcHo8He3t7ODk5QTAYvDOqvQ+Qxg+NRoO+vj5KIGKxmDYheTweBAKBqs9ICLWvrw9LS0uYnp6GRqNBMBiE1WqF3W6H3+9HsVisiwOsJMbu7m4ancrlctqE5PV6qaMgZ4o4GIPBgIWFBSwsLNDI++joCDabDV6vF4VCoW7NS6TuZTAYMDExgYGBASiVStzc3NAmJDLeQJ4Xg8EAj8eDTqfD4uIiFhcX0dXVhXw+T4McUnup102psnwyOjoKs9mM5uZmMBgMxGIx+Hw+uN3uquYP4ijUajWtYff19YHFYuHs7AwHBwc4OztDJBKpiwMEqjmRpGkJJ0ajUcod0Wi06kwRTpyensbi4iLMZjOEQiHsdjvlxHA4XHdOJF2d4+PjdPQtlUrB7/fD4/Hg4uKi6pZKfs5isWBpaQljY2OUE61W62fnxHtzguRWoNFo0N7ejoGBAUxOTsJkMoHH49EC7ubmJpxOJ6LRKDWQzWZDrVaju7sbc3NzmJqagkAgwPn5OTY3N7G9vV23DjySdlKr1Whra4PJZMLU1BT6+/shEokQj8dxcHCAra0tOBwOhMNhSiJkIJvMYC0sLEChUODi4gI7Ozu0mF2vVKFYLIZSqYRer6dNSKQ+lE6n4XA4sLW1BZvNRg8l+U6kUimt9T579gxNTU1IJBI4ODjA6uoqXC5X3ToLBQIBFAoFtFotjEYjRkdHMTY2Bo1Gg0KhgNPTU5oee98JikQieiN+9uwZOjo6kM1mYbPZsLa2BofDUbfZOR6PB5lMhtbWVhgMBgwPD2NiYgJarRY3NzfweDzY3d3F7u4uHdEhdvH5fOh0OpjNZjx58gS9vb24vr7GyckJ1tfXcXR0VLfGJXIraGpqQldXF73NdXZ2gslkwufzYW9vD9vb2zg7O0MymaTcQeYHBwcHsbi4CIvFAiaTCbfbjY2NDezt7SESidSlVkaaPggnVjYh8Xg8XFxcYG9vD1tbW5QTScBIHLvRaKScKBQK4ff7sbW1ha2tLQSDwbr0D1Ryol6vr2pCEovFNGOytbUFu93+o5y4uLgIpVKJcDiM3d1drK2tfXZOvDcnyOPxYDQaafpocHAQOp0OAoEA6XQae3t7+P/+v/8PVqsVwWCwSgGAz+fDaDRifn4eIyMj0Gg0cLlc2Nrawps3b3B4eFi3eSUWi4X29naMjIzQlF9bWxtkMhkymQyOj4/x1VdfYX19HcFgsCqS5nA4aG9vx+zsLL05ut1u7O7u4vXr19ja2kIikaiLXQwGAy0tLVV2dXR0oKmpCblcDmdnZ/j222/x5s0b+P3+qnQGafCZnJzExMQETCYTzs/PcXBwgO+++w5ra2uIRCJ1s0upVGJ0dBQjIyOwWCwwGAzQarUoFArwer14/fo1Xr16RaNvkkpiMBhQqVQYHR2lLzVpPnjz5g1WVlbqKiEmlUppFmJkZATd3d3Q6XS4ublBIBDAysoKvvnmG5o1qawtSaVSmM1mmsJnMpk4ODjA27dvsby8DLfbXbebLdGYHRkZwdjYGHp7e6HT6cBisRCLxbC5uYmvv/4aR0dHH6TIRCIR+vr6MD8/D7PZDJlMBqfTidXVVbx9+xYOh6NuzSI8Hg8GgwEjIyMYHR3F0NAQtFothEIhstks5USSkq8sG5BsxPz8PCwWC5qbm3F2dobt7W28fv0aBwcHdQvGWCwW7QQnN/a2tjbI5XJks1nKiaTMUzlXzOFw0NbWRksuhBP39vYoJ8bj8c/6ee/FCRJ5nL6+PszOzsJisaCrqws8Hg+JRAJnZ2fY2dnB3t4eTk9Pq0iHDFaSXHlLSwuNUPf39xEKhe6cmbkPcLlcSCQSdHd3Y3p6GqOjozCZTBAIBCgUCrQBYWdnB3a7HZeXl7i5uaH1MqFQSDtI29vbAQButxv7+/t0wLoexMPhcMDn8+mQ9Pj4OHp6eiCRSAAAp6ensFqt2NnZwdHRUVXqj8lkgsfj0cYFo9EIDoeDQCBAm2BI1+99g8Vigc/nQ6/XY2JigiqgKBQKcDgc6qh3dnZwcHBQFbAQ1XqNRoOhoSH09vZCJBLR74I0wdTDLpKibW1txcjICObn59Hf308VYVwuF46OjrCzs4P9/X2Ew2H6OZlMJo2++/v7q5pn9vf3YbfbEYvF6uIoSMqafOdzc3Mwm83Q6XTg8XgIBoNwOByUO87Pz2nqj3CHVCql3bsajQaZTAY2mw2Hh4f0BliPMgOPx6vixOHhYRgMhipO3N3dxd7eHpxOZ1Wtnc1mQyQSUU5sbW1FqVSC0+ms4sR62MXlciEWiyknjo2Nobu7GwKBAJeXl/TW/j4nAj/U6Cs5kdQ3a8mJNZdNI9Jaer0eZrMZExMT6OzshFAoRLlcRjgcxsbGBra3t6tqesRRkFmgrq4u9Pf3U+mww8NDeDweCIVCNDc3g8fj1dqUD+wiNUCSnjGZTNRRJBIJ7O7u0s4nUvsig7DEgZLUsFAoRDAYhM1mw+npKb1NCQSCe7WLEA9Rn5+YmEB/fz8UCgVYLBYymQwODw+xtrYGt9tddSiJXWSQvq+vD0qlEpFIBA6HA3a7HaVSCS0tLRCLxfduF5mXI0O3ZrMZarUaHA4HxWIRDocDq6urODk5qVKuIC35AoEAzc3N6OvrQ0tLC1KpFE5PT3F0dIRcLgeNRgOZTHbvdpEh6c7OToyPj2NkZITOy11fX8PtdmNlZQVHR0dVUTdx7Hw+H2q1msoVki0K+/v7iMfjUCgUUCqVPyqvVguQdCHJtIyPj0Ov10MgEKBUKtHb7d7eHmKx2AcOkMfjQS6Xo7u7GyaTCTc3N/B6vdjf30cwGIREIoFGo/lRqb9a2UVqgGazGePj4+jq6qKcGIlEsLGxga2tLcqJlc1mhBM7OzvR399PpcMIJ5JzyuVy790uMmtLyl3d3d2QSqVgMBiUE9fX1z/gRGIXGS0j5aRgMIjj42M4nU4wmUy0tLR8dk6s2dMn0SUZgyD1CbVajWw2C4/HA5fLRWtEZ2dnVB6NrADp6OhAW1sbenp6MDExAYVCQVuYu7u7oVAowGQy4fV68fbtWwQCgTvnCj8nSL1Lq9Wip6cHZrOZKjOQhgqXy4Xj42Osrq7C4XAglUrRqIzku9va2mA0GquUbrLZLNrb28HlculqoXfv3uH09BRXV1c1j+zEYjFaW1thNBqpmkZ7ezvK5TLcbjd8Ph91FEdHR4jFYjSKk0gk1K7Ozk5MTk5Cr9eDyWQimUyiqakJc3NzKJfLyGQyWF5eRqFQwNXVVc1v8eSW1NnZSeeNjEYj2Gw2VT45OzvD6uoqrFYrrVHc3t6Cz+dTu9ra2jA2Noauri5wuVyEQiFIpVJMTU2hVCqhWCxie3ubdvDV+hbP4XDQ3NyM9vZ2Ols6MDAAgUCAcDhMzyKpm5PmpdvbW7DZbLS3t1O7yO1WKBQiFAqBy+VidHQU/f39KJVKODw8pDOuta4LstlsqFQq6PV6DA4O0gY6mUyGeDyOSCQCl8tFh8C9Xi/y+Tx1gHq9Hu3t7dDr9ejr68Pw8DDEYjEuLi4AAIODg2hra8Pt7S2cTieKxSJisVjNb/FMJpPWovv7+yknajQa5HI5eDweuN1uyomnp6fIZDJ3cqLJZKJyiuSzE04kXfZv376F3++/V04k4vEzMzNobW3F1dUVTk5O4Ha7KSfa7faquq1CoUB7ezva29thMBgwPT1NlW6y2Sza2trorsdIJIK3b99+Vk6smRNks9nQ6XSYm5ujsyFKpRKlUglerxfb29t48+YNjo6OEIlEqJo9j8cDi8WiSiuTk5NVN5GrqytwuVwsLS1BIBDg+voaGxsbcLlciMfjNV+GSQa/SSPL4uIi3YdXmbsmMz3kRsHlcmmu/MmTJ5iensbQ0BCamprA4XCQTqdxc3ODyclJiEQi3N7ewmazUU1NohRRS8jlcoyOjmJ+fh5PnjyBXq8Hh8OB3+/H/v4+lpeXsbKygkgkgmQySZ8FidBmZ2dpWri1tRU8Ho/ONQ0ODmJ2dpa+oNFoFC6X66PqOZ8TIpEIQ0NDmJ+fx+LiIgwGA0QiEcLhMH0x3759i2AwSGubRDBbqVTSVnwiZM7j8ZBKpZDL5ehYCwlarq6ucHR0ROs3tSQfPp+Pnp4eeg77+/shk8mQTCZxenqK9fV1vH37lnZbFwoFsFgsmoofHh7G/Pw8xsfHYTQaIRKJUCgUkM/n0dzcTG8ZiUQCPB4PNpuNOvda2sXlctHZ2Um7OS0WCxQKBYrFIrxeL+0FcDqdiEQitPmDx+OBzWajr68Pi4uLmJiYQE9PD2QyGW5ublAsFiGVSvHll1+Cy+Uin8/j9evXcDgcyGazNV98fBcnqlQq3Nzc4OTkBNvb23j79i0ODg7u5MSuri48e/aMcqJSqaScyOFw8OTJE8qJW1tbcLlcNFCtZUDGZDKh0WgwOTlJz2JTUxNNZRJO3NnZQSQSobPEhBP1ej2dPa7kRPJMyDjW7e0t7Sr/nJxY05sgGdQdHBxEa2sruFwuJfvr62sqD8Tlcum1mFyJx8fHsbi4iJ6eHrS0tIDNZuPq6gpqtZp2LfL5fORyOcjlcqoaX+uUDZPJhFqtxvj4OCwWC/R6Pfh8Pp0ju7q6oqnS1tZWNDU1AfhhXmZgYACLi4u0MYjP5+P6+preapVKJV0KHAqFwOfz78UuBoNBJajGxsbQ0dEBiURCoy0S/RMRZqVSSW8UIpEIRqMRi4uLGB4epunuUqkEmUwGvV4PuVwOiUSCUqmEfD4PgUBAN5TXGkKhkM7LGQwGqFQq3N7e0s3ohGjUajVkMhlub2+po9BqtXjy5Am9ARJCLZfLtIlBoVCgXC6jXC5TNfz7sIvH49Hai8lkgkajoRsGyMZ3IjEoFotRLpfpyItSqcTi4iKmp6ervhPSEEVuY8APMl4kGq81KhvG+vr60NzcDA6Hg8vLSxrkkrk6Pp9P7eLxeJBIJFhYWMD8/Dy6u7vR1NQEJpOJYrGIpqYm3NzcQKVSgc1mI5lMQiaT0UCu1mCz2VSYfXBwEFqt9gNOJOMSd3Hi6OhoFSdyOBxcX19DpVLR+U7CRZWcWGswmUyoVCqMjY1RThQIBHdyItFtvb29paUTwolkrVolJ5JAlHBiOBz+7Jz42Z0gOYxqtRoGgwEWiwVarZauySBq9qQGoVarqRYeg8GgQ8gkvSOVSunLx+VyodFoaCSaz+cRj8eRTCZp3rxWESr590k6k+yLI/UEUnNSKBTo7u6GRCKhNwFis0qlQk9PD8bGxmgtiswxKZVKSCQS3N7eolgsIpVKIR6P08J9Le3icDi09X9wcBBGoxF8Pr/KblKXfV9Hk8fjQaVSobOzExMTEzTYqZztFAgE1OGk02l6K6m1XUTmjaSf+vr6IJFIwGAwcHt7WyVvR15W8nmI89Dr9RgfH0dHRwf4fD6tX4jFYnC5XHqTzWQyiMViNKVfS7tIg09LSwt6enpoMwshBfL5yD65ym5J0izS0tKC8fFx2shFyJI4fvKMs9ks4vE4zWjU0q7KTRekk1ylUlHuIDWn5uZmDAwMQKfT0WCG1NnUajVGR0cxODhYFZCQLQTErlwuh3g8TpufankDJHX2Sk4k3a3Ersq6rEqlquJEkUgEtVqNgYEBjI2NVXEi2cxCnk2hUEA8HkcikbiXNCiXy6VD7WazGZ2dneBwOPT3KzlRLBZXcQfxAyaTCePj4x9wIgne7uJE8tw/Bz6rEyQvJ1ExJxI+IpGIvmTkMDKZTOh0uqrZPvKlkQFLhUIBNptNDb69vcXV1RXS6TQuLi7g9XpxdHQEq9VKO8NqcZhJw0dXVxcd1u/s7IREIqEHmcztkMj1/RUuJOrRaDTQaDTg8XhVdl1fXyObzeLi4oLW3kjXYa0Gysn3rdVqMTExgSdPntD0EXnJSG23u7sbKpUKfX19VXaRm6BSqURLSwuEQmGVXaVSCYVCAeFwGOfn5zg5OcHh4SHtKq1VKpSQw+joKBYWFqijIA66chciaZ6oPDvkJiiXy6HT6WgjD7H95uYGl5eXiEQiCAQCcDqdODw8xM7ODlVhqQUBkRvQ8PAwZmdnMT4+TsWwyTsmEonQ3t4OkUiEzs7OqlQYuQlKpVLodDpIJBIw3n99AwAAt+tJREFUmUzc3t7S2+zl5SXi8TiCwSBOT09hs9mws7NDHUYt7CID0iRtPj8/D41GQ6N+4IdZRj6fj7a2tioJQeJoiPOXyWRgsVj0HJbLZVxdXSGZTOLi4gJnZ2ew2WzY29ujaexa2cXj8X6UE4m+K+HEytk+4mjEYvFHOfH6+hqpVIpyos1mg9Vqhc/nq1n3K+FEot1KxBXu4sTe3l46WnUXJ6rVaqjVavD5/A+4o5ITT05Oqjjxc9nF+LEHz2AwftapIDeGv/3bv8V//a//FWazGXK5vOoWSKKbSmPf+zfp/5MHfH19TUmHKCgQNfvl5WV4PJ7PGhm8D5LKXFhYwP/4H/+DSmtVRjyV//bHPkulbZV2XV1dIR6PIxAIwG63Y2dnBysrKzg+Pq7prYLcGEZGRvDf//t/x/Pnz+k29bvwKXaVSiVcX1/T/5KX0263040RBwcHNVWxIBmF3t5e/Jf/8l/w93//91Cr1RCJRL/YLpKuIrZlMhlEIhE6qrO6uoqdnZ1P2tT+ayASidDW1ob/+B//I/7hH/4Ber0eUqn0F9tFUt3Erlwuh0gkUtWgQWazanlbIqMQ//bf/lv85//8n9Hd3V11u/0l3EHql6RpKRKJUCextrZG59RqaReXy4VUKsXf/M3f4L/9t/8Gs9lM+xt+iV0AcHV1VcUdkUgEfr8fx8fH2N7exrt37+B2u2vKiSRFPjc3h//5P/8npqenaZBZaRfBL+XEYDBYxYk2m+0XceLt7e1Hc6ef9SZIoq10Oo1IJIJUKgWpVEofeOUHrzzcd4GkK1wuFzweD1KpFDKZDPx+P0KhEGKxGMLhcJWyTK1A7Mpms4hEIkgkEpBIJNQJErsqbfmYXYVCAalUCm63Gy6XC4lEAtlsFsFgEIFAgNoVDAZr3jBCgox8Po9IJIJYLAaRSPSBE/wUu66urqg8HFG3yOVyCIfD8Pv9VXbVOk1TaVcsFkMkEoFYLP7ACX6KXaVSCalUit6KQqEQcrkcotEoAoEAIpEIIpEInc2qtTwVIXTSJalUKu90giS9+LHPUy6XaUbl7OyM7gYkwVilXaRDsZYgQW4qlUI4HEZzczPkcjn9/U/ljtvbW5qaPjs7o1tAkskk/H4/5QwypH1f3JFOpxEOh5FKpegt9efYBXzPiYlEoooT0+k0/H4/Li4uEIvFcHFxgUgkUnO7SJBBODEej9MSQaVdP4cTycRAPB6nnBgMBmvOiTVxgqTrjhTTeTwe/QLINZc0I/D5fPD5fLDZbJTLZRSLRWQyGYRCITokabPZEIvFkEwmaQcf2TV4H0PyhFRjsRgcDgftyiL1JfJnyOfhcrng8/kQCATgcDi4vb3F5eUlvT2QQeSjoyNcXFwgnU4jFAohHA7fu12lUgnJZBJOpxNarRYMBgNqtfqD2x1pRiDPixz26+trSjrkhr63t4dAIECDoWAwSP+O++hyBUDrdORGw2KxUCqVPrjd3dzc0JSVQCCg86bkVpRIJHB+fg6Hw4G9vT0qNxaNRqlU3H3blc/n4fP5cHh4SNO7wA8kUy6XUSqVaH2ePDMmk0kbk0jA8v6wP4m+iaL/fZ1F8u6TWVny7lQ2QFR2EhO7SD3z5uYGhUKBBsputxtWqxUOhwOJRAKJRIIqNt3n86rkRLvdDqlUCg6H81FOrOSO9znx4uKiihOj0SgN0Mhaq/vmxHg8XsWJZCaQ/JlP5UQiEn54eFjFiZFIpIo7aoHP6gRJdHB2doZvvvmGRpIk/81gMGhe/urqis6Ukfra5eUlbak9OjrC8fEx/H4/otEoCoUCLi8vkcvl7n2dECGVQCCAV69e0UiSpDUYDAa9MeRyOeh0OrS3t6OrqwsKhQI3NzcIBoPY3d2ldnm9XkQiEeRyOVxdXSGXy9279il5+SKRCJaXl+kL1dLSAhaLRcklk8kgnU5Do9Ggo6MDXV1d0Gg0AIBoNIq9vT0cHBzg+PgYHo+H3h7Ibawe2qc3NzdIJBLY3NykBNLZ2UntIk0fJFtBnpdWqwWTyUQqlcL+/j729/dxfHwMl8uFYDBIh80LhQJyudy9q3KQ57G/v49CoYCLiwsMDAyAyWTSdyyfzyORSIDP56O9vR2dnZ1ob28Hm82mslW7u7s4Pj7G6ekpJdGrqysUi8WqzRL3BUL2RFDh4uICoVCoyhEWi0UkEgkwGAy0t7fTs0g6Ik9PTyl3nJyc0MxKsVjE5eXlvcw4vg/iLNxuN7799tsqTiTc8T4nErsIJ3q9Xuzu7sJms8Fms9Gb+kPkROIM3+dErVZL7SKcGAqFsLu7i8PDQxwfH8Pn8yEcDt87J352J3hzc0NnXDKZDBKJBIRCIb3+k8hIIBDQOgA5pOfn57BarXj37h2Ojo7gdDqpIgkhm1qnmz6GcrmMRCJBo+h0Ok0bSMjnIq3ApGWYPMCLiwscHh7i3bt3VAWdrIl6CHal02nY7Xaacm5qaqIHuXKMwGQyQaVS0e8gHo/j+PgY7969w87ODhwOB+LxOM3r19suonGaTCaRz+eh1+ur2vzJ52xvb4dcLqc3CaIEs7KygvX1dZycnFCle+Ic6mUX6ZTzer3UrkAgQJ078EP9srm5GRKJhDYl5HI5Khy9vLwMh8NRpdxBbKqHbeT9IRkEkl2oHF8gTTtyuZw2mZFUGpk9Xl5exvHxMdxuN5Xzq7ddZHtHNptFOp1GMpm8kxP5fD7trCcOzu/3V3HiycnJg+LEZDKJw8NDyolyufxOTiS6u5WceHR0RDmRCM/XgxM/a2NMJUjTBWmMITUKouU3NjaGyclJqplps9nw7bff0pQTacuu9cDxzwVp067sNGQwGBAKhbSte3p6Gj09PQC+33X45z//GRsbG/B4PIhGo/RhPyS7SHcdaYwhdvF4PNr+PDk5iZGRETCZTIRCIbx+/RrLy8twuVw0hXEfyjY/B5Vt3CKRiNpFhnSJbNXk5CS4XC4SiQSWl5fx9u1beptIp9N105j8GCpHUEgKivxqbm6mQtpTU1OQSqUoFApYX1/Hd999R6PudDpNxyceylkkz0YikdDGGNLNq1AoMDAwgNHRUUxNTdGRh+3tbbx69QoHBwc0OKj1qMovAemArcwgEU40mUzUro6ODgDA8fHxB5xIZgofkl0/xolkm8nMzAzd/+r1eqs4kQzQ15IT760xphI3NzdIpVJIpVIAvj8AcrmcDk8PDAxQWS273Y7l5WV89913ODk5qUua6VNRLpeRzWbpGiAyZN7W1kbnl8geQYfDgbW1NXz33XewWq11STN9KsiMUWX6gciokUXGXV1dkEqlcDqd2NjYwOvXr7G6ulq1wPShgdQeiGQW8MPAPyEfMv7h8Xiws7OD169f4927d1SP8iGC3NCj0Sii0SiAH0SZu7q6YDQa0dPTg+bmZsRiMezt7eHNmzd4/fp13daOfQpIip7U8YAf9ghqNBqql6nVaulm8nfv3uG7776Dx+Oh8mkPETc3N0in03S7A5PJpJyo0+kwODgIvV4PFosFu92OlZUVfPfdd3A4HA3HiVKplHLi4OAg3SNot9spJ+7t7T0ITrw35Vgul4uenh7Mzc3h6dOnGBkZoXJB/+///T+srKxQQeaH+rDvApPJRFdXF2ZnZ7G0tITJyUmwWCz4fD589dVXeP36NU5PT2mjQSNBp9NhdnaWShoJhUKEw2G8evUK3377Lex2e5XQdKNAo9HQRaRzc3NQq9VIp9NYWVnBv/zLv+Do6IjWyBoJcrkcY2NjWFpawsLCAvR6Pa6urrCzs4P/+3//Lw4ODuiS1UaCSCSC2WymcmM9PT24ubmBzWbD73//e2xtbdG07kN1gHeBx+N9wInlchlOp/OvihOnpqbo4oM//elP+O677+B0Oh8MJ9ZcU4coHrS2tmJoaAgTExPo7u6mQr37+/u0O41c9RsBleoWfX19mJiYoGt5YrEYDg4OaP0vkUjUXG/xc4GkQFUqFUwmEyYmJjA4OAiNRoNsNkvtOj4+rus27l8CokLR1dVFZe+IyO/x8TGsVivdSVevbdy/BCwWi25bGBsbw9jYGPR6PQDA6XTCarXSBcGNRKiV2xaI2HRXVxc4HA68Xi+sViusVivcbnfV/tGHDsKJZAMN2bkpEok+4ETSzdoIIJyo0WjoBppKTtzf38fe3h7t2H0onFjTmyBZ1dLU1ISenh5YLBYMDQ1BoVAglUrRTfJkU3Cj3CjIDjalUgmDwQCz2Qyz2YympiYUCgUcHR1hdXUVbreb5robAaQeQwh1aGiIagGSfWXLy8vUsTfKTalS6oysrhodHUVXVxcV+X337h2Oj49pN+FDeDk/BWQHm06nQ39/P91pyePx4Ha7sbq6iv39fdpN2EgOkMvloqWlhS7UHRgYgEgkQiQSwdbWFnZ2duj29Eayi+ylrOREpVKJdDoNq9VKOZEISDcCKvdSkjqg2WxGc3MzCoUCbDbbg+XEmjlBJpMJqVSKpqYmWqDv7+8Hh8OBx+Oh250PDg5oVNAIIFEcWfQ5MzODkZERuvvK6/VidXUVu7u7tKOwUQiVdOv29vbSZbokivP7/VhdXcXGxgYCgUBD3ZSIhJrBYMDU1BRGR0fR3NyMdDqNYDCI9fV1rK2twePx3MvA++cCEblua2ujz6u9vR3FYhEejwe7u7tYXV2lqadGcRSkf6C1tRWTk5M0e3R7+/3qIxJkHh8fI51ON4xdlZxImmAGBgbA5XLh9XopJ5I9jo3EiUKhEE1NTRgcHKScKBaLEQqFPuDEh5Y9qokTJAKozc3NsFgsePnyJWZnZ8Fms+lc2fr6OjY3N2krc6OAzWZDqVRiaGgIT58+xcuXL8Hn85FIJHB0dISNjQ2sr6/D4XA86CL9+yALTPv7+7GwsIDf/e53UCgUyGazsNvt2NzcxObmJmw2G1WHbwSQoKW7uxszMzP48ssvodfrcXl5iZOTE2xubmJjYwNWq5WueGkEkG5eIlz+5Zdfoqenh+5+JM9rd3cX0Wi0oW7tPB4POp0Oo6Oj+N3vfoeRkREwGAwEg0FsbW1hc3Ozqg7YCCCc2NTUBIvFghcvXmB+fp5yotVqpZzocrkaihNJVmxoaAhLS0t4+fIlBAIBHZ/Y2trC2toa7Hb7g7y116QmSGovvb29ePr0KY28k8kkrFYrVldXsbm5ifPz84bK5XM4HEilUro2aGpqCm1tbfS6v7a2hvX1dbjd7oZqGKlMFc7MzGB2dhYGgwG3t7dwOBzY2NjA2toaTk5OkEqlGoZQSes2uVEsLCygp6cHXC4XZ2dn2NjYoDeKeDzeMLfbynq0xWLB06dPMTAwALFYDL/fj83NTXqjIPscG8Eu4IetJAMDA3j+/DmGh4ehVCoRiUSws7NDNVobLQ1KOlwJJ46NjaGlpYWKMqytrVWlQRuNEw0GAxYWFjA1NUWzETabjWZZHjIn1uQmSNadmM1mvHjxguaFT05OsLKygo2NDZycnDTMgyYgg6x9fX14+vQpjEYjGAwGrb0QQm2kFCjwfeeuUqmEyWTC4uIiRkdHwePx4Pf7sbGxgZWVFRweHtZcHPpzg8zRdXZ2YnZ2FjMzM+Dz+VR8/d27dzQd30hnkczRtbW1YXJyEktLS+Dz+fD5fNjb28O7d++wt7eHi4uLhrKL7JzTarUYHR3FixcvIJFIEI/HqdjE1tYWfD5fQ9kFfD+WQ+Y3X7x4gZaWFhSLxQ848SE6iR8Dl8ulnLi0tASTyXQnJz7kALMmTlAikUCv10OtVgMAzs7O4HK5sLa2hqOjI4TD4YZ72ABoAwKRFfP7/fD5fHQzQqN1FRLweDy0tLRAq9XSbfDBYBDLy8vY29uDz+drqKYKAi6Xi6amJrS1tUEoFCKVSsFms2F7exs7OzvweDwNFXUTkPRTW1sbpFIp8vk8nE4nDg4OsLW11XBdhQRk5lav10OhUKBUKsFut9NshN1ub6haWSUIJxK5QZfLBZfLhfX1dcqJD6lZ5FMhFAopJ7LZbAQCAfh8PtrvEQwGa7bi7nPhsztBMihJVrwkk0laU6oknkaESCSCTqeDUqlENptFOBzGxsYGtra2qDxXozlA4PuGGK1Wi+bmZhSLRZydndFa2cnJCWKxWEMSD9nTptPpUC6X4fF4aD3JZrM1LPGw2Wyo1WoqA+f3+7G1tYWtrS3s7+9T4mk0EFUYspk8HA5jd3cXW1tb2NvboyMejYa7OJEITmxtbdFUYSOCOEGVSlUly0eCsfvY1PFrUZObIHngLBYLx8fHtKZEpJoakXiAH5aVisViuFwu2Gw2vH37Fh6Pp6FGBt4Hn8+HXq+HSqVCIBCA2+2msmGkqaIRnTuXy0VraytaW1sRjUYRDofpKEQ4HK7ZsuJag4wd6fV6ZLNZ7O7uYmVlBVarlarBNKJdTCYTSqUSer0e5XKZ7jPc3t6mq54aMRgDfuBENptNLwV/DZwoFArR1tYGiUQCl8uF4+PjhuPEmjhBIpxK9kFtb2/DZrM17MtJQKSqyHogsvqD7FtrREcBgG7eTiaTCIVCdDN1LBZ7cDqFPwfErmw2i2g0SgfHA4HAg2vT/rkol8soFAqIRqNwu93Y3d2Fy+V6cNqtPxdEJNvn8+H8/By7u7twOP5/7L33c6PXlSb8IOecIzNAEoEJYO6gVrIk72yNp3Zqdmur5j/c2vlmxh5bVmw2c04gCYIAkQMRSCQmkN8P2ntFdLOlltUkSAtPVZerZKH1nve+9zn5nL0HN7v1l4IsL04mk0gkElhZWXl0lda3gYy5I6vFCCeS1pXHcMfuZIC2Xq+H1WoFi8VCqVRCKpW6l+W3dw2lUklXtxBiTaVSj9Y6JZBIJGhra4NMJkOpVKLLOR9jSO0mhEIhWlpaoNFo6G7AVCrVkNVO7xNcLhcWiwUGg4EuoiUDzB8D6bwNLBYLRqOReoJkr+hjCKn9HHQ6HVpaWignkuW+j1kBAqDN8Q+dE39qgPadbZFoookmmmiiiYeAn1KCdz47tIkmmmiiiSYeKppKsIkmmmiiid8smkqwiSaaaKKJ3yyaSrCJJppooonfLJpKsIkmmmiiid8smkqwiSaaaKKJ3yyaSrCJJppooonfLJpKsIkmmmiiid8smkqwiSaaaKKJ3yyaSrCJJppooonfLJpKsIkmmmiiid8smkqwiSaaaKKJ3yyaSrCJJppooonfLO5kn2CjwGAwwGKxwGAw6C65x76CBfhBLiaTCQbjh0Ho19fXj34FCwE5L+DvSy4mk0nPjHyHj3nNEcFNuch5/T3K9ffEHU1O/Gn8XSlBpVIJq9UKPp+Py8tLpFIpxOPxB7fb6pdCIpGgpaUFYrEYV1dXODo6QjQaffT7/gQCAVpaWiCXy8FgMJDP5xGJRB79vj8OhwOr1Qq1Wg0mk4lisYhIJILj4+NGP9qvApPJhNlshk6nA5vNRrVaRTQaxdHRUaMf7VeBwWBAq9XCbDaDw+Hg7OwMiUQCyWTy0Sv4v2dOtFqtEIvFuL6+xtHREWKxGE5PT3/x3/V3owSZTCY6Ojrwhz/8ARqNBsViEd9//z3+/Oc/P+oDZzAYMBqN+Id/+Ae0trbi8vISs7Oz+OMf/4hMJtPox/tVUCgU+OSTT+BwOMBisbC6uor/+I//ePRKUCAQ4MmTJxgeHgafz8f+/j7+7//9v49eCbJYLHi9Xjx//hxCoRDxeBz/+Z//+eiVIJPJRG9vL/7hH/4BEokE2WwWf/3rX5FOpx91ZILJZKKtrQ1/+MMfoNPpUCqVKCeWSqVGP97fDAaDAYPBgH/4h39AW1sbarUa5ubm8J//+Z9/H0qQz+dDKpXi7OwMxWLxnVx3oVAIrVaL3t5eDAwMgMViIRAIUFf5IYDL5UIqlaJWq6FYLL6TYubz+VCr1ejp6cHAwABUKhXC4fCDkovNZkMqlYLBYKBYLOL8/Pxnf8PhcKBSqdDd3Y2+vj50dHQgnU6DyXw4KWomkwmJRAIej4eTk5N3ulxsNhsymQxtbW3o6+tDb28vCoXCg5NLJBJBKBSiWCyiWq3+rLfDZDIhlUqh1+vhcrngcrlQKpUelBHGYDAgFAohFotRLpdRLpd/Vi4GgwGxWAytVgun04n+/n6cnp6iWCw+qDvG5/MhkUhwfn7+izhRo9FQTuRwODg4OHhQcnG5XEgkElxdXb0zJ/J4PMqJ/f390Gg0iEQiv0quh3M78QOJKBQKdHZ2wmg0gsvl/qxwbDYbarUabrcbfX19aG1txfX1NSKRyIOx5AihtrW1wWq1QiAQ/KxcLBYLMpkMvb29GBwcREdHB7hcLmKxGBKJxDspm7sGIR6r1Yr29naIxeKfJXxCwl1dXfB4PLDZbBCLxUgmk4hEIqhWq/f09G8Hg8EAn8+HyWRCZ2cn5HI5WCzWT/6GyWRCIBCgra0Nw8PD6O7uhkKhQDabxeHh4YPxbrlcLnQ6Hex2O1QqFdjsn7aDybswm80YHh5Gb28vdDodisUiQqHQg/Fu2Ww2VCoV7HY7dDodOBzOT94xBoMBLpcLvV6PwcFBuFwumEwmnJ+fIxwOI5vNPohQKIvFglwuR2dnJ0wm0ztzokqlgtvtRn9/P9ra2gDgwXJiS0vLO3Eik8ms48TOzk7weDzEYjHE4/G/mRMfjCfI4XAgkUjQ1dWFyclJRCIRnJ6eIpPJoFKp3Gr9CAQC6HQ6OJ1OPH36FAMDA5BKpTQHc3R01PADZ7PZEAqFaG1txeTkJCqVCi4uLhCNRlEul299Ph6PRz2lyclJDA8PQ61WY29vD5FIBKlUChcXFw2Q5kewWCyqKEZHRyEQCHB1dYWDg4O3WnXkcra1tWF8fBwTExMwGAzIZrOIx+OIx+MNz3MymUzweDxotVp4PB5YLBawWCzUajUcHx/fetGYTCYUCgWsVitGRkbw/PlzWK1W1Go1pFIpRCIRVCqVBkjzIxgMBrWiCTm+evUKl5eXyOfzb/V0ZTIZTCYTPB4Pnj9/js7OTnA4HGSzWUQiERSLxXuW5E1wuVwoFAr09PRgfHwca2trOD8/RzabfaunKxKJYDAY0N/fjw8++AAOhwMCgQCFQgHRaBT5fL7hSpBwYmdnJ548eYJYLIZqtfqznEg8W8KJMpkMOzs7D4YTWSwWhEIhWlpaMDk5idPTU5yfn78TJ9rt9jpODAQCiEajv4oTH4QSJFaB1WpFf38/Xrx4ga2tLQQCAVQqFZyenr5x4MRC6u7uxsjICCYnJ2E2m3F+fo5UKkU/5EZWQjGZTAiFQhiNRrhcLjx79gz5fJ5a0Kenp28cOHkXnZ2dGB4exuTkJGw2GwAgk8nQD7mReU4mkwk+nw+dToeenh48efIEAoEA0WgUuVwO1Wr1jecjHmBLSwuGhoYwOTmJgYEBAKCEmkqlGqoEiXeg0Whgs9kwNjaGrq4uJJNJpNNpVKvVN5TgTU9pYGAA4+PjGB0dBYPBwMHBAaLRKBKJREM9XAaDAQ6HA6VSiY6ODgwPD+Pp06coFAqIx+OoVCo4OzurI33yG51OB7fbjbGxMUxOToLP5yOdTiMejyMWizU0t0QqBOVyOVpbWzE0NISPPvoIABAOhyl3vC4Xk8mEWq2Gw+GgcimVSlQqFSQSCUSj0YZ7uIQHLBYL5cSdnZ2f5USZTFbHiRaLBRcXF5QTc7lcQ5Ug4QGj0Qin04lnz57h5OQEh4eHP8uJHR0d8Hq9mJychN1uB/AjJ2YymcerBNlsNkQiETo6OjA5OYnx8XG0t7cjGo2CyWTeao2RPFRLSwsGBwdpbPj4+Bg7OztYXV1FJBLByclJw5QgsXasViv1emw2G/x+P9hs9q1ykcM2m83o7+/H0NAQ9Ho9qtUqdnd3sby8jMPDQxQKhYYpQQaDAYFAAJPJRD/I3t5eFItFcDict/6OWN4ulwterxcWiwVXV1fY3d3F4uIiAoEAcrlcQz1cgUAAjUaDwcFBTExMoL+/H2KxGHw+/62/IbmXnp4eeL1edHR0gM1mY29vD4uLi9jb20Mmk2mocufxeJDL5XC73ZiYmIDH44HRaIRQKHxrCIrH40GhUMBms8Hj8cBut0MkEiEUCmFtbQ3b29tIpVINVe4cDgdisRjd3d2YmJjA2NgYrFYrJBLJW+XicDiQSqVob2+Hx+OBw+GAXC5HJpPB5uYmNjc3EY/H3ymneFcgnNje3o6JiQlMTEygvb0diUTirekGNptNq8hvcuLJyUkdJ75rTvEuQBSg1WrF2NgYJiYmYLfbEQgE3ppuIJxoMpnQ19cHj8cDg8GA09NT7O7uYmlpCaFQCIVC4XG2SJCXotfrMTAwgM8++wwOhwM8Hg+Xl5c0dPj6x0hi+d3d3RgeHobNZsPl5SV2d3fx5z//GfPz89TCbZRcxFNyOp349NNPaaXgzs4OKpUKzs/P35CLxWJBq9VS4nG5XGAymTg4OMBXX32F2dlZhMPhhlnfTCYTHA4HarUadrsdH374IT744AOIxWJsbW2hWq3eaqEyGAwolUp0dnZicHAQg4OD4PP5iEQi+P777/Hq1SsEAgGcnJw0RC7SS0U8pefPn+OTTz6BSqVCMpnE2dnZrRYqAEilUrS1tVGjRS6XI5lMYnZ2Ft999x12dnZQKBQaQjzE65HJZGhpacH4+Dg+//xzmM1mnJ2d4ezsjHrtr3+LYrEYVqsVbrebEk+hUMDy8jK+/vprbGxs4OjoqGFGC4vFgkQigdFoxPDwMD7//HN0dnaCzWbj/PyccsfrIAacw+GAx+NBa2srqtUqNjc38V//9V9YWVlBMpn8m6oM3wducmJ/fz8+//xzOJ3OOk68jTu4XC4MBgO6u7vh9Xpht9tRq9XqODEWizUsN01y5lqtFg6HA59++ilGRkbA5/Oxt7d3azQC+OGcSWSGcCKLxcLBwQG+/vprzMzM/GpObJgS5HK5lPDHxsbg9XrR2tqKUqmE1dVVrK2tIZVK3Rr7lkqlGB0dxdOnT2E2m5HL5bC4uIjl5WWsrKwgGo027CMmh9ba2orx8XF4vV709PTg8vISa2trWFpaQjweR6lUeoNU+Xw+BgYG8MEHH6CrqwvVahWLi4tYWlrC6uoqDg8PG2Z5M5lMKJVKmM1mjI6OYmRkBP39/WCz2fD5fJibm0M4HMbJyckbXiqLxUJvby9evHgBh8MBBoOB+fl5LC4uYnV1FYFAoGGKncFgQCaTQafTYXR0FKOjo9QDPDg4wMrKCg4ODlAoFG7NB3Z0dOCjjz5Cf38/+Hw+Njc3MT8/j9XVVezu7jZUAYrF4jrPllQYx+NxbG1tYW9vD7lc7la5jEYjPvzwQwwPD0MmkyEQCGBhYQHLy8vY2tpqaEj+JpmOj49TzzaXy8Hv92N7extHR0e3GmRqtRpPnz7F5OQkdDodEokElWttbQ3JZLJhiv31ULzX60VbWxvK5TLW1tZ+khMlEglGRkbw5MkTWK1W5PP5NzixUdEIwonEEHsbJ96WD+TxeDRva7PZcHp6iqWlJcqJoVDoVzs7DVGCxHVvbW3F4OAgXrx4ge7ubrDZbAQCAaysrFALmhwcsdZJRZHX64Xb7QaPx0MoFMLLly+xsrKCeDyOarXaEOJhsVgQiUQ0jv/8+XO43W6IRCLE43FsbGxQArlp9bBYLIjFYppXIsnscDiMubk5vHr16q2K8z5ArDgSziQ9cHK5HIVCATs7O/SC3nz3LBYLAoEASqWShjLUajVyuRz1KGKxGI6PjxsmFymCIYT65MkTqNVqVKtVBAIBLC0tvZGwJ56+RCJBb28vRkZGYDAYUCqVsLm5iS+//BKxWAzZbLYhioLkNpVKJex2O0ZGRvDixQvo9XpcXFwgEolgfn4eh4eHKBaLlPRJ8YxEIoHdbsfY2Bja29txenqKvb09/PWvf8XBwQHS6fStEZr7kIvNZkMul6OjowMejwcfffQRWlpaAAChUAgLCwsIBAJ1RUwkv0nySqOjo+jp6QEABINBfPPNN/D5fLTquhHcwWazIRaL3+BELpeLQCCA1dXVd+LEvr4+GnGamprC8vIyLahpFCcKhULKic+ePUN/fz9EIhESiQQNQROj5SYnikQimEwmDAwMYHBwEDKZDJFIhHIiyUn/Wu64dyVICN9kMtEqNYvFAh6Ph1wuh2g0imAw+IalSZK+Xq8X4+PjcLvdEIvFCAaDWF9fh9/vpwUIjThsEsbQ6XRwOBwYGhpCa2srxGIxSqUSYrEYQqEQDa+9fthutxvj4+MYGhqCUqlEIpHA+vo6dnd3EYvFUKlUGqIoSA5Qo9HAbrfD6/Wis7MTMpkMZ2dniMfjCIVCb1w0ogBJkn5kZAR6vR7ZbBabm5vY2dlBOBxGuVxumEdBKs46OztpCEmpVOLy8hLpdBrhcJiGWohcRAES0pmcnITVakWxWITP54PP50MwGES5XG6oR6FQKNDW1gaPx4Pe3l5oNBoAwNHRESKRCC3OIt8UUZwkvPj06VN0dHSgVqthf3+fFqqRvG0j8mWkD9NisWBgYAButxsGgwFsNhvpdBqRSATBYLCu+IMoTrVaTc+rp6cHHA4He3t72NzcxP7+PtLp9K3huPsA4USj0VjHiXw+H/l8HrFYDMFgkBofN38nlUrh9XoxNjYGt9sNiUSCUCiEjY0N7O3tPQhOJD3cQ0NDaGtrg0gkQrlc/sWcmEwmqVzRaPS9ceK9KUFSKalQKGA0GtHT04PBwUHYbDaIRCLk83ns7Oxgc3MTwWAQ2WyWCkisv5aWFoyNjWF8fBwKhQK5XA7r6+tYXV1taDJbKBRCJpPBYDCgs7MTQ0NDcDgckMlkKJVK2Nvbw9raGgKBADKZDCV90oRsNBrpJA69Xo9isYjt7W0sLS3RZHYj5CKDC/R6Pdra2jA4OIi+vj6oVCqcnp7SIgm/308/ZODH/kFSgv7xxx/DarVSj2JxcREHBwc4Pj5uiFykSVer1VLLe3BwEHq9HrVaDZFIhCpqklsmz3kz1/vRRx/BZrOhVqshGAxiaWkJe3t7DQuBcjgciEQiaDQaWK1W9PX1YXBwEFarFQwGA/F4HJubm9je3kYkEkGpVKJykfREd3c3nj9/DpfLBTabjVAohJWVFfh8PhrBuG8QUlQqlbBYLNTIbG9vB4/HQzqdxvb2Nra2tmiRBHn/bDab5qMnJyfh9XohFosRj8exurqKjY0NpFKphuTKCCfK5XKYTCbY7XYMDg7CbrdDLBajUCjA5/NhY2MDBwcHyOVydXLJ5XJYrVaMjo5iYmICSqWSciKJit084/vETU7s6OjA4OAg5cRyuQy/30858aZyv1kI4/F48MEHH8BoNFJOXFxcpBGM9yXXvSlBLpeL9vZ2OJ1O9PX1wel0oqWlBVKpFOVyGRsbG/jzn/+MtbU1RCKRumofPp9PwxhDQ0MwmUyIx+NYW1vDN998g42NjYYRKovFgsVigdPphNvthtPpRHt7O1QqFc7Pz7G/v08T05FIpC4Hw+FwYLFYMDw8TD0skq/59ttvsbCwgEwm07AqNUL2brcbLpcLHR0dMBqNOD8/p4npqakpHB4eIpPJ0Dwsk8mEwWCA1+vFyMgIent7cXR0hL29PXz33XeYmZlBIpFomFxKpRJOpxMulwtutxudnZ1oaWnB5eUlLdb57rvvEAgEkEwm64wrlUqFgYEBjI2Noa+vD6enp1hbW8PU1BSmpqYQiUQaVn0nkUjQ09ODvr4+uN1u2Gw2tLS0gMViIZVKYWZmBl9//TWNLpTLZfqsUqkULpeLVsXy+Xz4fD5MT0/j+++/RyAQaJhnKxQKYbPZ4HQ6MTAwgO7ubtpgTXJfX331FTY3NxGNRusqIEUiEa0eHRwchFqtRjAYxPz8PC1calQBHYfDQVtb2xucSBTF5uYm/vznP9PKzuPjY2pA83g8tLe3Y3R0FB6PB2azGfF4HOvr6/j222+xtraGQqHQME40m8113NHW1gaNRoOzszMEAgH85S9/wdzcHCKRCLLZ7E9yYiKRwNbWFr777jvMzc3h6Ojovcp1L0qQw+FAJpPBbrdjfHwcg4OD6OrqAp/Px8nJCaLRKFZWVjA3Nwe/31+X0CZWYHt7O7xeL6xWK5hMJs0dEq+xERNUbrZ3EAXd3d0NkUhEJ0+sr6/TQombFYYkz2a1WuHxeNDR0QEej4doNIrV1VX4/f46xXKfYLFY4HK5aGlpoR8jseIYDAb29vawtbWFhYUFLC4uolKp1Hm3PB4PBoMBAwMDsNvtkEql2NraosUiJLl/32AymTTkNzQ0hNHRUTgcDqjVavB4POzv72NnZwcLCwtYWFioK4YhYTWNRgO32w2HwwGVSoWtrS3aMhCPxxvSPE5CmVqtFn19fXjy5AlcLhcMBgMEAgEikQj8fj+WlpYwPz9f1495s9eut7cXfX190Ol0NPS0sbFB++buW7nf7G90OByYnJykni2fz8fR0RGCwSCWl5dpYRbJK93Ml9lsNmo8n56ewufz0UKzfD7fkHA84USbzVbHiQKBAMVikfLA3Nwc9vb2buVEEu62Wq20YpIUcjWSE4VCIdrb2zEyMgKv10s58eLignLi3NwcVlZW3uBEPp8Pi8WCoaEhdHZ2gs/n03dB2o3ed3HgnY9NIyE/k8kEl8tFy5KFQiGur6+RTqcxPz+P5eVlGpe/urqiHzGXy6XzGLu7u8FisRCNRrG5uYnDw0M6NYbH4921KHVgMBi0lLm3txcejwddXV10jmY+n8fq6ioWFhbodPNarUZJh4TkLBYLenp6aKLY5/PRvhmDwQChUHjvcpHqO5ID7OnpgUKhAIvFQqlUwtbWFubm5hAMBlGtVus+Yg6HQwcE9PT0QKlUIpPJYG9vD7u7u7i4uIBer4dIJLp3ucjEFNJ063K5oNFowOFwaKh2dnYWfr+/rmCEyHXzvej1ehwfH9N8WalUgkajgUwmu3e5iKJoa2vD0NAQBgYGoNfrwePxcH5+jlAohOnpaWxvb6NQKNQVwrDZbPD5fDqNo6WlBdVqFcFgEBsbG8jlclAoFFAqlfc+A5UoZzJEg3g8fD4ftVoNsVgMMzMzWF9fRzabpXklwh2k17GzsxNdXV24urpCOBzGxsYGEokEJBIJ1Gr1z46Ouwu5SMiPtKCQXBnhRFIVTgyWt3FiT08P2Gw2otEotra2cHh4CD6fT8//PvE6JxJPjnBioVCgnEgq+Ilcr3Nib28vxGJxHScymUza3/o+cWenTw5ao9Ggq6sLTqcTg4ODMBqNuLq6wuHhIWKxGDY3N6kHeDNRr1AoYDAYoNfr0dnZib6+Pmi1WhQKBVQqFTrxgclkIh6PY2FhAalU6taep/cJctBqtRptbW30sImHSiZp7O3tYWZmBtvb23WJeolEAr1eD4PBgNbWVng8Hjqz8Pj4GFKpFN3d3WAwGMjlclhYWMDZ2dm9FCMIBAKo1WpYrVbY7XaMjo6ivb2dTglJJpMIBoN49eoVNjc366Y0kBygTqeDxWLB6OgorFYruFwukskkBAIBurq60N7ejkqlgsXFRVSrVVxcXNy5h8HlcqFSqWA2m6liJzNL8/k8nToxNTWF1dVVWiV4fX0NHo8HvV4PnU4Hg8GA4eFhdHR0QCgUIp1Og81mo729nU4r2tjYoAr0rguZSL7LYDDAZrPRvItCoUCpVEI4HEY0GsXc3ByWlpYQDodpkQSLxYJer6d/XC4XbDYbJBIJMpkMrq6uYLFYoFQq6VADMpj6ruUiRXDE4CBzgbVaLU5PT5FMJhGLxbCysoL5+XkEg0FavETWIhG57HY7fSeZTAbn5+fQ6/V0tmgoFMLp6em9eISEE9VqdR0nmkymOk7c2tqixtjJycmtnNjR0YH+/n7odDrKiSqVCr29vWAymUgkEri4uEAymbx3Tuzp6cHw8DANxZORiG/jRFJ3YDAY0NLSAq/XC5PJhIuLizpOBIB8Po/5+fn3yol3pgTZbDZNbj558gQjIyPQ6XS0+XttbY2SaSKRoCXNxNppaWnBkydPaHUb8faq1SpYLBaeP38OLpeLWq2G5eVlJJNJnJyc3PklZTKZ0Gg0tEp1cnKSDvsmHioh03g8TucyEmvHYDBgcnISIyMjcDqdMBqNEIlEiMViOD8/p5V5ALC7u4tsNotMJnMv1YZyuRz9/f0YGxvDkydP0NraCpFIhFQqRS/m7Ows4vE4ncvIYDDAYDCgUqkwPDyMkZERDAwMwGKxQCwW4+joCCcnJ3A6nRgeHgYAmrAnJc53HbYRiURwOp20j6qrq4sWVm1vb2NhYQHT09MIh8N0LuP19TWYTCbEYjH6+/sxOjqKgYEBdHR00Pm0x8fHaG1thdPpBIPBwNHREQ1LkbzUXZIPn89HV1cXlYuEdsvlMvb29rC8vIxXr17h4OCA5javrq5oyJqMDSOhOIVCgYuLCxSLRWg0GvzhD38Ai8XC8fEx/vrXvyIYDOLy8vKdNk/8GtwMxZP5l1qtFpeXl7RQ59WrV7T68eTkBBcXF9Sz7ezsxMTEBE1PkL2OlUoFIpEIn332GTgcDqrVKl69ekUHt79tHuf7AovFgtForONEvV4PJpOJYDD4BieSdgjCiRaLBU+fPqWcqNfrwefzkUwmwWAw8OzZM8qJpOn/+Pj4zjmRwWDQ6lvCHSaTiaZ3CCeSYp3XOVGn01FOdLlclBPJLGGv14snT54AAPx+/3vnxDtVgkajEWNjYzS+y+FwUCwW6ZokkhdSKBSQSqUAfqxwIwN7e3t765ZdKhQK8Hg8aDQaCIVCVCoVxGIxCIXCui3ldwWiBD0eDx0nxefz6YSKUqlEc2RSqZS67iRW7nA48Pz5c/T19aGlpQV8Ph8XFxeQSqUwGAxQq9WQSCS4uLjAyckJxGLxvcjFYDCoEhwZGUFPTw9kMhnOz89xeXlJvYDz83OIRCJwuVwAP7ZCtLe349mzZ3S6u1gsxsXFBc7OzqDX66FUKiGXy2lIWCqVgs1m30uITSQSobe3F2NjY3A6ndBoNHQRZ6VSQblcxunpKQ0jEQXI5/NhMBjw9OlTOplIoVDg8vISV1dX0Gq1EIvFUKlUuL6+hkAggEKhuDe5eDweurq6MDExAbfbDbPZDCaTiVKphGq1Sv+XzWZDq9XSUCEJEz558gRjY2Ow2+3QarW4urpCqVSiIUKtVgsmk4l0Og2VSgUul3svcnE4HDpcmWxBYLPZyOfzdXIR40uhUNC8qEgkwuTkJJ4+fYru7m4YDAYwmUxUq1UolUrqYXK5XBQKBfj9fvD5/J/dEvI+cJMTyT3hcrlvcOL19TXkcjkkEgl9HyKRCIODg3WcyOVycXZ2BrlcThvtCScmEol75US1Wg2Px0NbjQQCAZ21SzixVqvdyok9PT2UE1tbW9/KiZeXlyiVSu+dE9+7EiQ5CjLbc2BgAEajkT40uYRKpZKSSq1WoxdUJBJBpVLR/KFCoQCHw6HWq06nw+XlJZhMJlU6xCK4vr6+MwuVWJk3Y/ltbW00rELklslkNIRI5AJ+CDWSvIvX64VOpwOfz68bRSaVSunGgkqlQr2ku5aLbIQgPY4kQf+63FarFVdXV3XhFdKU3d7ejuHhYZjNZjqTksPhQKFQQCAQ0DmwlUqF7h28a0+J5E/I/rGenh46V/L6+rquIdftdtc1SpO1XmSFEFkVRd6HVCqtW2tTrVZRLBZpYcZdykXyJ0qlEl1dXXC73VAqlfRZSIOyXq+H0+ms63MkvWV6vR7Dw8Ow2+2QSCRgMpm0r8tsNlND4KbSuevzIopMLpejra2NeoBMJpPeMdKz2t3dTVtayDsRi8VQq9UYGhqC2+2GTCYDm82mvzMajajVamAymTg7O6PccR/hQsINJL9pNpvps93kxK6uLmosEk4UCoVQq9VwOp2UE4lBQjjx4uICLBarzmC9D7lIkz+p+XidE0n+krSzvM6JZKCD1+ulnu1NTpRIJJQTy+UySqXSe08NvVclSEinvb0dAwMDmJiYgNVqhVQqpRYksVjsdjs0Gk1dfw6ZyE9657RaLTgcDiUV8qdareLo6AjxeBx+v5+6/rfN1HsfIIdCBluTRuKbe+ZuTumXy+Vv9LGQSRx6vR5GoxECgaCOLK+vr2kMPx6P0/BIOBymifH3DXI5tVotXC4Xnc6uVCrph0y2dZDG/46Ojjq5yCQOjUYDi8VCrdebcl1dXSGTySCZTCIUCmF7e5tWAd9VmIacR09PD0ZHR6kHSBTXzc0lAoGADvQmIA3MKpUKLS0tkMvlVHkSua6vr5HNZpFOpxEKhWifK7F67+JbJO/bZrPB6/ViYGAAOp2uzksTCoUwmUzgcDgwGo11ISOi6Ejf7c2CFyL/9fU1jo+PkclkcHh4SIe33zYS732BzWZDIBDQPtuRkRF6T8jzkfwsCaHdrJwmykIqlcJqtVJv9nXuKJVKdGAACRmTSsq7OC/CiWS+7MTEBG0Nu40TSTj7plxkOpHJZKK7El/njtPTU2SzWcRiMezv72NlZeVOJ+AQTjSZTHWcSCIhwI85646ODshksjc4kSwa1+l0MJlMP8mJiUQCBwcHWF9fx+HhIc7Ozt4bdzB+6uAZDMYv+iqIUJ9++in+5//8n3C73dBqtfSlEBKp1Wr0z+v/fUJQLBYLbDYbV1dXuLq6Qq1Ww8XFBd09t7Ozg+XlZUxNTSEYDFJCvYsPmVg74+Pj+Nd//VcMDw9Do9HQ7QJELvKctVrt1iHSxNrmcDhUrqurK1xcXKBQKCCZTNKJ79PT0/D5fG8dcPw+QDyhvr4+/O///b/x4sULaLXaN7YLkOckYcDX5SLKkpwzkf/y8hInJyfIZDLY3d3F+vo6rea76eW+b5CIgs1mwz//8z/j97//PQwGA61SI3j9W3wdN8/r9fdQKpWQzWaxv7+PjY0NzM7OYnl5Gfl8/k4nj5ARVH/4wx/wj//4j1SRvS7XzfN6/VmIXCRsS86LRCCy2SxCoRDNAy8uLtZVKd4F+Hw+1Go1fv/73+Of//mfqZFMFAWDwajjgp/iDjabDRaLRf/dq6srqiQikQh2dnYwPz+P2dnZuirFuzgzwokff/wx/tf/+l/o6+ujFcnkmd8nJ66srGBqagoHBwf3womjo6P413/9V4yMjECr1f4qTiTvgXy7+XweyWQSu7u7WF1dxczMDLa2tnB6evqLvcHr6+u3xk7fqydIHp5Mp389aUkems1mv3WdEAHx9qLRKGKxGIrFIkqlEuLxOJLJJN2PRSZf3CWur6+pXGTa+W1ysVgssFisn5Tr7OwMR0dHiMVitP+qXC4jkUggkUggnU4jFovh8PDwzrcqkI/u/Pwc1Wq1rhT7JohcP1VKfnFxQT/acDiMfD6PSqWCdDqNRCJBrTnSm3XXFaFErtPT07pS7Jt4/QK+7e8hXhEpnKlWq5R4UqkU4vE4wuHwvWxVuLq6onKR9pS3yfVTd4zk/27ucqxUKsjn81SuZDKJw8PDe1mZRIzBm5stXlfsJPz2c9xRLpeRz+cRiUSQSCRQLpdxfHxcJ1ckErmXrQo35SIbIF6XC/jlnEh6UovFYh0nxmKxe9k0QziRcMfrBu374ETCGTflugtOfK9K8Pr6Gufn5zg6OsLBwQHUajWEQiF4PB49eGIdXF9fg81mg8Ph0JwfcX/JRvlIJILV1VVsb28jk8nQrc+5XA6Xl5e4vLy8lykW5LkKhQKCwSBtQiahv5tWD8k1EbnIB0CUKCHP9fV1rK+v0wouoiiIXPfRwEvkOj4+xuHhIQKBAHg8Hv1giVxENqIwOBwOVYhELkIy29vbWFlZoYOxSXj34uKCynXXCpC871KphGg0iv39fQgEAhq6Jt8isaiJwiByMRgM1Go1mjci5d1kOANRimReaq1Wu7czq9VqqFariMfj2N/fr9t3eFOum+RKzox4U2TVUDwep8OZ/X4/CoUCJSMymPg+Wj2IXKenp0ilUggEApDL5RCJRDQfCPzIHW+Ti3AHCbuTodO5XA65XA6xWIzu4rzPO0Y4MRgMQqPRQCQS/U2ceHR0hHA4jLW1NWxtbVFOvDms/b65I5/P/2pOzOVydALYxsYGkskkCoUCVYA3ueMu8N49wfPzcwSDQXz99dfI5XJIpVIQCoX0YyZVjxcXFzAYDDCZTLBYLBCJRHQg8/b2Nm2uDofD1Jo7PT3FycnJva8TIgcWj8fx/fffo1AoIJVK0Zwgg8HA5eUlisUiqtUqdDodjEYjLBYLZDIZarUanW+4u7uLvb09hEIhxONxnJyc4PT0FKVS6d7XCRFPMJPJYGZmhlpfJO/CZDKpx1Aul6FQKGAymWA2m6FSqQAAuVwOPp8POzs72NvbQzAYRDQapeXdpVKpIbNPa7Ua8vk8lpaWcHZ2hlQqhdbWVirXzSIdMrzYYrFAq9WCwWCgWCxid3eXynVwcIBwOEybssvlMorF4r0PNa/VaigWi9jc3KRnR4ZIkNB0tVrFyckJndxjNpthNBrBZrNRLpdxcHBA79j+/j7dzF2tVulv73tEGglZ7u3tgcVi4ejoCKlUioZsGQwG7aUFflj1RL5FPp+ParWKcDhMv0W/31/n4RK57nv2KVHOoVCojhNvKvjbONFsNkMsFuP8/PwNTjw8PEQymUSpVGo4JyYSiTpOJEM1XudErVZL5SKFP+l0Gj6fj3JiMBiknEiqZe+DE9+7J0heTKlUQqFQQDabrSvVJVU+HA4HLpeLVk1eXFwglUphY2MDr169ovvOSO6IxLYbMZeRKAtSUp/L5ZDP5+sOnFjoV1dXdDEwydUQRfHq1Susra3RPXMkudsouYAfw32bm5vI5/MoFArQ6XTUIyLkdHFxgfb2dlq9R0q79/f36cqW3d1duhKF5DHvulLybSDKe3d3F7lcDicnJ3S8FFGCZLGsyWSiDdqkxPzw8BAzMzOYn5/H7u4uncZP5CJeZCPkqlarODg4QD6fp2MHb7ZlkBCVWq3G9fU1JBIJ5HI5zs7OEI1Gsbi4iOnpaezs7NAeORLOapRcxGOKRCI4OTlBoVBAJpOhBT+EVMvlMsRiMS4vL2klOUknkFz61tYWDg4OaPiReCONkuvy8pIqLcKJIpHoVk50Op20avLy8pL26JL+wd3d3QfFidlsFqurq8jn88jn81AqlVSuq6sr2nvZ29sLPp8PhUIBJpOJXC6HnZ2dOk4k+fT7luu9Fsbc+B2tKiRJYOL6C4VCWK1WOBwOujSSx+MhGAzi5cuXWFtbw/7+PlKpFPL5fMPWttyGm1WFWq0WPB6vrnLNbDbDZrNhZGQE3d3dtJH11atXWFxcxP7+PuLxOB2i3SjFdxvIRHutVguRSES9CjabDYPBgK6uLjqSiwwuJsUFZLVJLpdr2NqWt4FU12m1WloYQ86RTDMiI7mkUimq1SqWlpYwMzODnZ0dhEIh5HI52mj+kL5F0v5BjC1yx0hFntvthtfrpcpwbW2Njk/b399HLpej3uxDkotUFarV6rp+MIlEgvb2djgcDgwPD8NkMtGlzq9evcLGxgb29/eRyWTosOmHJNfNSTivcyIZFUbacW7uSSWbWtLpdENXWb0NZEYrKRa8yYkmkwk2mw3Dw8Po6emh06cIJ/r9/nvhxHsrjLnxH8Tl5SWOjo5wdHQE4MfSbIvFQsf7dHR0QCQSIRgMYmZmBn/84x+xs7PTsOWxPwdi/RQKBRQKBQA/lmbr9Xp0d3ejt7cXnZ2dUCqVODw8xOLiIv70pz9heXmZ9rg8RBDP6Wb4gVTstbS0wGazwWazQa/XIxwOY3V1FX/5y18wNTVVt8D0oYG01BweHtJ/RrxZjUaDtrY22O12WK1WJJNJbG5u4quvvsI333zTsAHm7wLiycZiMcRiMQA/tE+IxWKIxWI6k7atrQ3FYhE7Ozv49ttv6cLfRqwOeheQXFMqlUIqlQLwY7tKW1sbnUvZ3t4OANjf38fLly/xpz/9CQcHBw1bHfRzIJyYzWaRzWYB/Gh4WiwW9PX1weFwoKOjA2KxGKFQCLOzs/jjH/8In8/3YDkRwBucCIByot1uR09PD7q6uqBWqxEKhSgnLi0tPQhOvNdVSqS3iWwXJpvk//jHP2J6ehqHh4d3PrrofYPJZNIZoM+ePYPX64VAIEA0GsVf/vIXvHz5Ent7ew1dHvu3wmQyYWhoCE+ePMHo6CjkcjkymQy+//57fPPNN9jc3LzT3rG7AmmonpiYwPj4ON3hODs7iy+//BLr6+t1K68eC2QyGdxuNyYmJjA5OYnW1lacn59jdXUVf/zjH7G6uopUKvVgFfvbIBKJ4HA4MDIygqdPn9Kt8D6fD//xH/9Bh9Tf9Ti39w3CicPDw3j+/Dn6+/vB4XBwcHBAOTEUCj16ThweHoZQKEQ0GsWXX3754DjxzmcgkXCURqNBb28vXV+jUqmQz+extbWF+fl5bG5uIpvNPjhX/6dAxk/Z7XaMjIzQTdelUgk+nw8LCwtYW1tDOp2+s564uwCZ+EOmwJBZoJeXl9jd3cXS0hKWl5cRi8XutHfsfYP0NpH1VWR6P1nNtby8TJd2PibiIVEWk8mEwcFBjIyMoLOzk65RWltbw/z8PPb39xtSzPO3gkRZdDod3G43RkdH0d3dDalUSusH5ubmsLOzQ6s+HwMIJ6rVavT29mJkZAQOhwMajQaFQoFy4sbGxqPjRC6XC4VCQdNCfX19MBqNKJfL2NnZweLiIjXGHgon3qkSJLkXlUqF9vZ2umCRTIrZ2tqq257+mD5iEt+/uRSTTOfY29vD/Pw8QqHQgw4Vvg5yXkRROBwO9Pf3w2q1AgANW+/v79Mk9mMB2d9oMpnQ3d2NwcFBdHR0gMPhIB6PY3Z2lg4sJ6PPHgPIyC29Xg+bzUZ3OJItFwsLC9jc3EQ6nX5Uip3kBjUaDd0iQ3ZakpU8ZOPHfWy2eF8gd4yMGnS5XG/lxFKp9Cg5kQyV7+vrg8FgqONE0mL0kDjxTlcpiUQiKJVKOgfU4XBALBbTMVNzc3NYX1+/lybj9wUyh5DMvPN4POjr64NCoaC9LWQ/YjKZvNPpIe8bPB4PcrkcHR0dGBgYgMfjgU6nQ6VSobH8+fl5WlH4WAiVw+HQvXQDAwPwer0wm824vLyE3+/H4uIiZmZmEAwGHxWhkhmmZIGxx+NBe3s7mEwmQqEQndCzt7f3qDxAkgPUaDTo7+/H0NAQHVQfjUaxt7eHubk5uh/xMSmK1znR6XTS9VWHh4d1nPiQFMXPgQyPt9vtGBoaQn9/P5RKJe0Vnp+fx9LS0oPkxDvdIqHRaOBwOPDxxx9jYmICQqEQhUKBrq+Zm5tDIBC49/64XwMmkwmFQoHe3l48ffoUH330EWQyGSqVCp1FODMzA5/PR9fpPAYwGAxIJBLY7XaMj4/jk08+oYN5fT4fVlZWMDc3R/flPRZCJUYLWaT76aeforW1FQwGg85YnJ+fx8rKCq1GfizgcrmwWq0YHBzEJ598gt7eXnA4HBweHtLlpWTk2WMiVA6HA4PBALfbjU8//RSDg4Pg8/lIpVJYW1vD0tISZmdnqTH2WEA2c/T29uKjjz7C5OQkRCIRjo+Psb29jcXFRczOzj46TiSdAIQTP/74Y0ilUtr3SThxe3v7QXLinYRDSU6pq6sLT548gdfrRUtLC05PT7Gzs4O5uTm6mfwxWXJkm0JrayvGx8cxOjoKm82G6+tr7O/vY35+HtPT0/D7/Y+qsIJsHTCZTBgeHsb4+Dh6e3tpmTbpK/P5fLQP8CFZcm8DWYek0+kwODiIyclJuFwuSKVSRKNRLC8vY3p6Gpubm7Sp+jHIdTOn5HK58PTpU/T390OtViOTydA5i2Sn5c0tEg8dJKfU3d2N58+f00XcJycn2NzcxOzsLBYWFmg/4WMxxsgWiY6ODsqJbW1tODs7o5w4OzuLYDD4qIwxkmd/nROJkTk/P4+ZmZkHzYl34gkKBALodDq4XC58/PHHMJvNqNVq8Pv9mJ6epg3IjymnBKBuLc+LFy9gt9vBYrFoOfPs7Cy2t7dRLpcfBZkSkI0LXV1dePr0KYaGhiASiWgcnyiK4+PjRyUXm82mOYqJiQlMTExAKpUiEAhgaWkJU1NTNPT0WAwx4Me1QWazGSMjI/jggw8gk8mQTCaxvr5et9T5Md0xEi40GAwYHBzExx9/DJVKhWKxiO3tbUxNTWFxcRGhUOhRyQW8yYkWiwW1Wg37+/t1nPjYKncJJ3Z3d+ODDz6g04sODw8pJ25tbT1oTrwTJUj2S+n1eojFYjoHdHl5GVtbW4jFYnSh7mOCQCCAwWCA0WiERCLB8fExXTOzsbFBC3wei9VNwOPxoNVq6UijarWKaDSKpaUlrK+vIxQKoVAoPBrrlIDsJLNYLHQZLlm9tbq6ikAggFwu9+gIlTSTm81m2lBOVlQtLy9jb2/vQfc4vg1MJhNSqRQmk4luJIjFYggEAlhZWYHP50MymXxUIVACotwNBgPEYjFd57S0tEQ58aH2bv4UbnKiVCrFyckJ/H4/lpaWsLGxgXA4/OA58U6W6kqlUkqoxWKRWt6kTPuutyPcFcjCUbVajdPTU8RiMSwtLWFubo5WFj7kw34b+Hw+NVouLy8RDAZpDnBrawvpdPrRhJ1ugsvlQqfTwWw2g8FgIBqNYmVlBQsLC1hfX6f71h4b2Gw21Go1rFYruFwukskkVlZWsLi4iJWVlUeXKyMg+Xar1QqxWIxcLof19XUsLS1hcXGRFi49NhBOtFgskMvlKJVKODg4oJzo9/vpTNTHBqFQCLPZDI1Gg9PTUyQSCcqJOzs7j4IT78QTlMlksFgsYLPZ2Nvboy/lsbUMvA4y8YZMdNjb28PU1BT1KB6rXHw+nw7FTiQSiEajePXqFXZ2dmgO8KF/yLeBy+VSKzWXyyEQCNC5tGQ90GOUi8ViQaPRwGw2o1wu0yrQtbU1RKNRutT3sYG0DpjNZlxdXWFrawtzc3NYWlrC4eHho2oZeB1ECXI4HFosQuoi/h44USKR4PDwEH6/n3JiPp9/FHLdiRIkO6TIxPTFxUVsbGzQj/ihxoZ/DmTlDvFu19bWsLq6SucUPkZCBX7cMH92doZIJAKfz4fl5WWk02lcXFw8erlqtRoODg6wv7+P5eVlRKPR97qZ+r5B5AKAaDSKw8NDLC0tIRAI0OHljxVkVijZ07i4uAifz0dbVx4rd9zkxHQ6TcOFpD/6scpFOLFUKiEQCGBjYwOrq6u04PExcMd7H6DNYDBgsVhgs9nAZrPpDsBEIvFoSYdAp9Ohp6cHIpGI9gRGIpFHlyt7HaTlQ6lU0pUojzWkdhNisRh2ux0mk4luuCc5iscMPp+Pzs5OWnGdzWbpIuPHSqbAD4qira0NnZ2duLq6Qj6fp4uMHwOZ/hQsFgvsdjvYbDaOj4/pYtzHzomk5eOhc+JPDdC+sy0SZJJ4I9fpvG/8vcoFoG556UPalvBr8balrI8df69y/b3esaZcjcW9K8EmmmiiiSaaeCj4KSV45wO0m2iiiSaaaOKhoqkEm2iiiSaa+M2iqQSbaKKJJpr4zaKpBJtoookmmvjNoqkEm2iiiSaa+M2iqQSbaKKJJpr4zaKpBJtoookmmvjNoqkEm2iiiSaa+M2iqQSbaKKJJpr4zaKpBJtoookmmvjNoqkEm2iiiSaa+M2iqQSbaKKJJpr4zeJO9gk2EmSyPoAHOc38b8VNuYC/H9macj0+/BbuWFOuh4/3dcf+rpSgVCqFRqMBl8tFrVZDPp9HNpt99GtmhEIhtFotBAIBrq+vcXx8jKOjowe3s+uXgsfjQaPRQCwWg8FgoFgs0k32jxlsNhsajQZSqRRMJhPVahWZTAblcrnRj/arwGAwoFaroVAowGKxcHZ2hqOjI5ycnDT60X4VGAwG5HI5NBoNWCwWLi4ukMvlkMvlGv1ovxoSiQRarZZyYqFQQDabffR7DN8nJ/7dKEEmk4n29nZ8/vnnUKlUKJfLmJmZwbfffvuol8MyGAwYjUZ88cUXMJvNuLy8xMrKCr766itks9lGP96vgkKhwCeffAK73Q4Wi4WtrS18+eWXiEajjX60XwWBQIAnT55gYGAAXC4XoVAIf/7zn7G3t9foR/tVYLFY8Hq9GB8fh0AgQCqVwl//+lcsLy83+tF+FZhMJnp7e/HJJ59ALBYjn8/j5cuXmJqaetTKgnDiZ599Bo1Gg3K5jLm5OXzzzTeoVCqNfry/GQwGAwaDAZ9//jmsVitqtRrlxKOjo1/89z04JcjlciESiXB+fo5KpfJOLi6fz4dCoUBPTw/GxsbA5/NxeHgIsVhMFz42GhwOB0KhEFdXV6hUKu90ubhcLuRyOWw2G0ZGRqDT6ZBMJhEIBMBise7hqX8eLBYLIpEIDAYD5XIZl5eXP/sbNpsNqVSK9vZ2eL1e2Gw2FAoFxGIxcDice3jqnweTyYRQKASHw0G5XMb5+fnP/obFYkEsFsNisWBwcBAejweVSgXFYhFcLvcenvrnwWAwIBAIwOfzUalUcHZ29rN3jLwLjUaDvr4+jI6O0t/x+fx7evKfBoPBAI/Hg1AoRLVaxenp6c/KRd6FUqmE0+nE2NgYrq6usL+/D6FQeE9P/vPgcrkQCoW4uLhAtVp9p8gW4cTu7m6MjY1BKBQiHA4/KE5ks9kQiUS/mBNlMhm6urowMjICg8GAVCr1qzjxYbyN/wcmkwmpVIrW1lbodDqw2T+vo5lMJuRyOXp7e+FyudDW1gYGg4FYLIajo6MHY8kJhUJYLBYYjcZ3JkSxWAybzYa+vj50dnaCz+cjHo8jmUy+EynfB3g8HoxGIywWC4RC4Rtx+tvA5/PR3t6OwcFB2Gw2SKVSpNNpxGKxBxMK5XA40Ol0aG1thUQieSfi4HK5sFgsGBoaQnd3N1QqFfL5PCKRyIMJhbLZbKhUKrS3t0Mul7+TXGw2GwaDAQMDA+jp6YFer0elUkE4HH4woVDCA+3t7VCr1e9EiCwWC2q1Gm63G06nExaLBZeXl4hGo8jlcg8if8ZkMiGRSNDa2gq9Xv9OnMhgMCCTydDb2wu324329nYwmUzE43FkMpkHw4kikQgWiwUmkwk8Hu+df2Oz2dDf34/Ozk4IBIJfzYkPxhMkVkFHRwdGRkYQi8Vwfn6ObDb7VquOx+NBpVKhp6cHT58+xeDgIJRKJQKBACKRyIM4cBaLBT6fD6vVirGxMVSrVdRqNSQSibdadRwOB3K5HJ2dnZiYmKBe4MHBASKRCBKJRMPzgUwmkyrA4eFh6hGEw2GUy+Vb3zvxAMm7mJiYgNlsxvHxMWKx2INQggwGA1wuFxqNBgMDAzCZTJiZmYHf70exWLzV0yVEZTKZ4PV68ezZM7S1tYHJZCKVStF30mhwuVzq9bhcLszNzaFWq+H4+PitBCIWi6HX6zEwMIBnz57BbreDz+fj6OjowShBDocDqVQKu92O4eFhbG5u4uLiAoVC4a2eLvFsXS4Xnj17BqfTCYlEguPjY4TDYeTz+YYrwdc5MZFI4Ozs7J04sbu7G0+ePMHg4CBUKhWCwSDC4fCD4kSLxYKxsTGcnZ2hVqshHo//LCd2dHRQTtTr9QiFQr+aEx+EEmQwGBCJRDAajXC73fj444/h8/kQjUZxdnaGi4uLN8iHyWRCJpPBbrdjdHQUz58/R2trK66vr5HJZBCJRJDL5RpaFEPCLVqtFr29vfjggw9wfHyMRCKBcrmMi4uLN8iHwWBALBajvb0dw8PDePbsGXp7e8HhcJDL5RCJRBpeFENCT2q1GjabDU+fPoVQKEQmk0GxWMT5+fkbF43BYFBjYGhoCE+fPsXQ0BB4PB7C4TCi0SiSySTOzs4aJNWPClCpVKK9vR3j4+M0VJvP53F+fv7Gd0h+YzKZ0N/fj8nJSUxOToLP5yMSiSAWi9HL3SgwGAywWCzI5XK0tLTQ76pareLo6Ajn5+e4uLh4g1TZbDZ0Oh1cLhcmJibw/PlzSKVSFAoFJJNJxGIxlEqlBkn1A4gBQkLQn376KbhcLvUMzs/P35CLyWRCqVSit7cXY2NjeP78OXQ6Hc7Pz5FOpxGNRlEoFBoj0P/DbZy4t7eHaDRKz+s2TpRKpbDZbJQT29racH19jaOjI+rhNlIJEh7Q6XSUE0ul0jtxYltbWx0ncrlcGmnJZDKPVwmy2Wzw+Xy0trbC6/ViYmIC3d3dyGaz4HK5t4ZrSO7FbDZjYGCAWuxnZ2fw+XzY3NxENBrFyclJw5Qgk8mEQCCA0WiEx+PB5OQkHA4HgsEg+Hz+rXIxmcy6D9/j8aClpQUAsLu7i/X1dRweHiKfzzfsQ775Eff392NiYgJutxvVahVCofCtYSihUAidTgeHwwGv14v29nbweDwEg0Gsra3h4OAAuVyuocqdx+NBqVTC7XZjZGSERhYkEglYLNatoV4+nw+VSgWbzQaPxwO73Q6pVIpgMIjV1VXs7+8jnU43VLkTT6mnpwcjIyPwer1oa2uDTCYDm82+VS4ejwepVIqOjg4MDQ2ht7cXKpUKiUQCm5ub2N3dRSKRaGiBBcmzd3V1YXh4GGNjY+jq6sL6+jo4HM6td4zD4UAkEqGlpQWDg4Nwu93Q6/U4OTnB7u4utre3EY/HUSqVGuYJslgsCAQCWK1WDA8PU04sFArgcrlgMBhvnBnJzZvNZvT391NOPD8/x87ODjY3NxGJRB4EJ5pMJgwNDVFOPDw8pJz4ulzEGDAYDHWcyGAw6jixUCi8Uz3CbWioErzpUbhcLnzxxRfo6+uDTCbD9fU1qtXqrRYqCVfZbDZ4vV709PSAwWAgEAjgyy+/xNzcHKLRKMrlcsM+ZC6XSxPTv/vd7zA2Nga5XI5gMIjT09OftFA7Ojrg8XjQ398PPp+PcDiMr7/+GtPT0zg8PESpVGrYh0w8is7OTnz44Yf48MMPoVarsbu7i7Ozs1vDT6QEvbW1FQMDAxgaGoJMJkMymcTU1BSmpqawv7+P4+Pjhl5QqVSKlpYWPH36FJ9++ilMJhNyuRzOz89xdnZ267NJJBJYrVb09fXB6/VCq9Uim81ifn4e33//PXw+H/L5/N98QX8tiBVtMpkwOjqK3//+9zRvfnl5idPTU1xeXr5xZkKhECaTCU6nE8PDw7BarahUKlhdXcU333yD9fV1ZDKZhuWmb0ZZBgcH8cUXX6CnpwcSiQS1Wo1yx+vg8XjQ6/Xo6enB8PAwOjs7cXFxAZ/Phy+//BJLS0s0VdEIECNTpVJRTuzv7/9ZTuRwONBqtdQg6O3tBZPJhN/vx5dffonZ2VlEo9GGKncOhwOFQgG73Y7f/e53GB8fh1wuRzgcxunp6a13jMViQaVS1XGiQCBAJBLBN998QzmxWCz+zdzRMCXI4XCgVCrR1tYGj8eDkZER2Gw2XF1dYWNjAz6fD5lM5tYYsUQiod5VW1sbKpUKFhYWsLy8jIWFBYRCIVSr1YYcNovFgkKhgNlshsfjgdfrhcvlAofDwd7eHjY3N6nr/7o3x+fz4Xa78eTJE9jtdlxdXWF+fh6rq6tYWFjA/v5+wxQgCT/rdDoMDQ3B6/ViaGgIEokEoVAIq6uriMVit+bNmEwm7HY7zb3w+Xysr69jfX0d8/Pz2N3dbZgCZDAYkEgkUKlUtKJzZGQEarUaiUQCGxsbCIfDb82btba24tmzZxgYGIBUKkUgEMDa2hoWFhawtbWFo6OjhilAkUgEpVIJh8OBkZERDA8Pw2g0olAoYH9/HwcHBzTM+zr0ej2ePn0Kr9cLtVqNWCyGzc1NzM/PY21tDclk8lYyvg/w+XwolUpK+CMjI2hra0O1WsXe3h78fv9b82YqlQrj4+MYHx+H0WhELpfD5uYmlpaWsLi4SFMwjZCLcGJra2sdJ15fX7/Bia9zh0Qiod4VeRcLCwtYWVmhnPiu1fbvG4QTTSZTHSdyuVzs7e1hY2ODRhVel4vL5cLpdFJOvL6+xsLCwnvlxIYoQVJybbVa4fF48MUXX8DhcEAgECAYDGJ+fh4bGxtvfMhMJhN8Ph8GgwGjo6MYGRmBVCrF7u4uvvrqKywtLSESibxzue1dyMXj8Wh+6NNPP8Xg4CBkMhlSqRRWV1exsrKCVCpVp6SZTCa4XC7UajUGBwcxPj4OtVqNeDyOly9f4tWrVzSU0Qi5SN5Lq9XC5XLho48+wujoKNRqNYrFIra2trC4uIhYLFan3MnvxGIxXC4XJicnYTQacXJygvn5eXz55ZeIRCIN85QYDAY4HA4tJHj+/DmePn0KvV6Py8tL+P1+zMzMUEuTPCP5HY/Hg91ux9OnT9HS0oLT01Osr6/j3/7t3xAOhxuau71ZXDU5OYnf/e53MJlMAIC9vT1MTU0hEAjUKXeSOyTVu6QQ5urqCru7u/j//r//D/v7+zTf1gijhcViQSKRoK2tDaOjo/jiiy/Q0dEBNpuNnZ0dTE9PY2dnhyp3csduFmNMTExgaGiIGqZ/+tOfsL29jWg0itPT04YZma9zotPphEAgwOHhIRYWFt7KicS7HRkZwejoKKRSKfx+P77++mvKiW8rVrsPuUgB3U1OlMvlSKfTWFtbo5x4U0nfxokajYZGj16+fPneOPHelSCJXRuNRrhcLvT396O1tRVCoZBWCR4cHCCdTtdZmuTjJ/kal8sFqVRKLdS9vT3EYrGGKkBScdbb24uhoSG0t7dDKpWiUqkgHo8jGAzSCq+bcgkEAvT09MDj8dBqrmw2S3Mv4XAYpVKpYYqC9FLZ7XZ4vV50dXVBqVTi4uICyWQSoVAI0WgUlUqFEggxWNrb2zEwMIDh4WEYDAacnJxge3sbOzs7VLk0SlHweDxaceb1emG326HRaHB9fY10Oo1wOEyfkXxT5HJaLBa43W5MTEzAarXi7OwMe3t78Pl8ODg4wMnJScPygKSXqqWlBUNDQ3A4HNDr9WCxWFSuYDCIQqFQZ7CQtpC+vj48e/YMnZ2dAICDgwNsb29jf38fmUymYZ4Sm82GRCKheS+32w2z2Qwul4tcLodoNIqDgwNks1ka4iWKneR6JyYm4HA46BCDra0t+P1+JJPJhkaPSN7L6XTWceLJyQmi0SiCwSBSqdStnOhyuTA8PAy32w2pVIp4PF7HiY1UgEKhEGq1uo4TZTIZqtXqz3Jid3c3PB4PhoaGoFarKSfu7OwgEom8tVr7l+LelCCJdUulUuj1etjtdgwODtI4frFYRCAQgM/nQygUqqvsJIdNSmqfPHkCvV6PUqmEra0trK6uIhqN/qq48K8Bn8+HWCyGVqulpO90OqFUKnF6eopQKITt7W0cHBwgk8nQgyOFMDqdDh6PBx9//DFaWlpwdnaG3d1dLC0t4fDwsGGhQjK4QKPRoKWlBX19fejv74dWq6X9VFtbWwgEArSykxAPydf09fXhs88+Q1dXF66urhAMBrG0tERDcY2Qi8PhQCAQQK1W03ze0NAQ9ZQSiQS2t7fh9/sRj8frLFRinfb29uLTTz+Fw+EAh8PBwcEBlpeXsbu727CxVIQ8lEolzGYzlau1tRVsNhuZTAY7OzvY29tDJBKpCyORUJzNZsOLFy8wMDAAkUhEQ93b29tIp9MNURTEoJLL5TAajejt7cXg4CA6OzshFAqRz+ext7dHDaub94XFYkEmk6GtrQ1Pnz7FyMgIlEoljo6OsLGxQUNxjciV3eREnU4Hm81GOVEqlaJUKlFODAaDdZWdhBNNJhPlRIPBgFKphO3tbaysrDS0OPAmJ7a1tWFgYAAulwsqlQqnp6cIBoN1nEgMYaI49Xo9hoaG8Mknn6C1tRXn5+fY29ujnFgoFN6bXPemBDkcDqxWK2w2G5xOJ5xOJ7q6uqBWqynpf/PNN1hZWUEgEKgjEh6Ph9bWVgwNDdHqoFwuh+3tbbx8+RIrKysNI1QmkwmDwQCbzQaHwwGHwwG73Q6j0Yjr62sEAgF88803WFhYQCAQQDqdpuEnNpsNo9GIgYEBWll4fHwMv9+Ply9fYn5+HplMpmHFIqQFore3F06nE3a7HW1tbQB+6Ad89eoVXr16Bb/fj0QiQXv8mEwmtFot+vv7afy/Uqlga2sLU1NTmJ6eRiwWa1iFq0wmg81mQ09PD5Wrq6sLLBYLyWQSs7OzmJqaws7ODrWkCUEqFApaLDIwMAAGg0HDcK9evUIwGGxYDlAsFqOjo4OeV3d3N7q6uiAQCJDL5bC4uIjvv/8e29vbtMePyCUWi9Hd3Y3h4WEawj84OMDc3Bympqawt7fXMA+QRBTsdjvcbjd6enrQ1dUFmUyGYrGI9fV1fPvtt9jY2MDBwUEdQQoEAnR2dtJqX71ej3g8jpWVFbx8+RKbm5sNy7NzOBxYLBbY7XY4HA7KiRqNBmdnZzSkuby8jIODg7rhHzwej3r6Ho8Hra2tyOVy8Pl8+P777xvOiXq9/g1ONJlMuL6+xsHBAb799lvMzc0hEAgglUrdyoler5dWxe7v72Nqagpzc3NIp9PvVa57UYLEaiE9ZUQ4oVCISqWCg4MDrKys4JtvvsHOzs4bYTXSMEr6toRCIZaXlzE3N4f19XWEw+GGVKndzJ9MTExgeHgYDocDUqkUtVoNgUAAGxsb+O6777C0tIRqtVqXV+Lz+WhpacHIyAgcDgcUCgW2t7dp4jcYDDYkpMZkMsFms2G1Wmnu1e12Q6lUgs1m4+DggF62ly9folQqUUuOhNUMBgM8Hg/6+vqg1+uxsLCApaUlLC8vw+/3N6R5nMFggM1mQ6/Xw+PxYGxsDH19fdDpdDT34vf7MT09jW+++Qa5XI6+fwaDASaTSZvoBwcHYTabsbe3h+XlZSwuLmJ3d7ch/WUk5KdWq9Hf348nT56gv78fZrMZIpEIyWSSKrRvvvnmjepHMm3F7XZjeHgYra2tODo6wvr6OhYWFuDz+ZBOpxtitLDZbMjlcjgcDjx58gQejwft7e0QCoUoFArw+/1YWFjAN998g2Aw+EauXSKR0NFhnZ2dqNVq2NnZwdzcHDY3NxGLxRoSjidtXjabDU+ePKFV7mTs201O9Pl8dcUwxFvq6OjA2NgYbDYbRCIRVlZWMD8/T9sGGiHXzTQI4USn00k58eDgABsbG/j222+xuLj4BifyeDxYrdY6TvT5fLTI5+Dg4L1z4p2PTSOl5yaTifZ5tLW1QSQSAQAymQwlyGQySRPT5GJzuVxIpVK0tbWhp6cHbDYbsVgMW1tbODw8pGG3dx27877AYDCo297b20tzZTKZDAwGA/l8Hmtra5ifn0c0Gn3jI+ZyuTTE29vbC5FIhEQiAZ/Ph0AgQK0pgUBw73IJBIK6FpTe3l4olUqwWCwabpmbm0MwGKybF8pkMmkfltFoRE9PD5RKJTKZDHZ3d7Gzs4OLiwvodDp6/vcpF2nH6ejowPDwMFwuF52wT3J6s7Oz2Nvbw8nJSZ1iZ7PZEAgE0Ol06O7upr1l+/v72NraQqlUglqthkwmu3e52Gw2rbQeGhrCwMAADAYD+Hw+Li4uEAqFMDMzg+3t7bpqUPLbm72OpMAnGAxifX0d2WwWcrkcCoXi3mdOklCm1WpFf38/hoaGYLFYIBAIcHV1hXg8jpmZGayvr+Po6KguHM9iscDj8aBQKNDZ2UnD8eFwGOvr64jH45BIJFCr1e80iux9gihnUhdB+jZ/ihNrtdqtnEgGaRBODIVCtI/3vufVkp4+0oJCOFEqlYLBYKBQKPwiThSLxXWcyGAw7oQT7+z0iZKQy+X0sPr7+2mT9NHREdLpNLa2tjA3Nwefz1fX8EjK1glpOZ1OGI1GFItFHB8fg8ViQa/Xw2g00iqj+ypHFwgEkMlkNJRB8hMikQiFQgHpdBr7+/vU2rz5XKRsneSj3G43Wlpa6Oon4IcwpEajoR8NGSt016EoHo8HmUwGo9FIh1t3d3dDLpejVCohl8shHA5jbm7ujTJ5UrauUqloOKOtrQ0CgYB6EQqFAhKJBKenp9jY2KBW4F3LxWazaXsHUYC9vb007JRKpZBIJDA/P4/l5eW6KkGSK1OpVNBoNPSspVIpstkszs/PaVP55eUldnd3acL+rkNRJMJC7sjQ0BBcLhcMBgNqtRpisRjS6TTm5+exsLBAjZZarUZ7Uskdc7vdsNvtUCqVyGazqFQqEAqFaGlpgdVqpb991wHOvwYk+kMm9/T19aGvr482SadSKaTTaSwvL2N+fh5+v59WCZKeVJVKRat+e3p6oNVqkcvl6DBzs9kMq9VKyfg+Kq9vcmJrayt6e3vpPSGj6NLpNDUyidFCuEMsFkOtVtO+OafTCZPJRDmRyWRCp9PBYDDQPNvNGoS7BOFEs9kMu92OoaEhdHZ2QiwW4/j4GJlMBoFAgHLizee6yYkWi4WeNSlQu76+pnKfnJy8d068MyVIYrukIsvr9cJqtYLP5yMajWJ7exvz8/PY3NxEKBTC0dERDdEwGAyYzWaMjo6iv78fvb29sFqtlFAZDAaePn0KJpOJWq1GS4fL5fKdV4cymUyo1Wr09fXRaQ5kyHIqlcLu7i5VEqFQCOl0mob+GAwGtFotzU84nU60trbSxvHT01N4vV6MjIwAAAKBAEqlEvL5PCqVyp1/zDKZDG63m67L6erqgkqlQi6Xg9/vx+LiIu05SiaTKBaL9COUy+Xwer0YHBxEX18f2traqCI/Pj6mA84BUOVJyqLvOpQtEoloMQWZvkGKCPx+Pw0jBQIBxOPxumICoVBIC0zcbjdsNht0Oh1OT09RKBRgtVrR3t4OAMjlcvjzn/9Mi05uG4jwPsHj8dDZ2UlLyF0uF0wmEy4uLrC/v0/7MEkhzPHxMfVuORwOrUju6+ujeWwAODk5gVqtxj/+4z8CAEqlEr777jtEo1FcXV2904aGXwMulwur1YqBgQFMTExgYGAAFosFTCYTwWCQ9iv6fD4cHh7SgQbAD3eMVPv29fWhp6cHZrMZbDYb5XIZQqEQv/vd78BgMHB2dob5+Xna8nHXCp4MIu/r68PY2BhGRkaoZxuLxSgnbmxs4PDwsG635s9xIgDKiaTXOpfLoVQq3QsnqlSqNziRDMZ/nRNTqVQdJ2o0GoyMjNBK5tbWVsjlctpK5vF4MDw8DOCHSmVikL8vTrxzJTg2NoaxsTE4nU7weDwUi0WUy2WkUinEYjFkMhlqlZKcE5/Ph8fjwfPnz+F2u9HW1gYul4vz83NarajX6yESiVCtVlEsFiGVSt86Aup9guSFiKIYGhqicXyyPDUejyOVSuHq6goymQwymYzmD3t7e/Hs2TMMDQ2ho6MDQqEQl5eXEAqFUCqV0Ol0kEql9HDlcjk4HM6dy0UsaDIKzev1QqFQ0DaIo6MjJBIJxONxnJ+fQyKRQCQS0bBTW1tbXW6DyHB2dkYtc6VSSRPjKpXqraOt3jdEIhEcDgcmJyfh9Xqh1+sBAIVCAblcDslkknoEQqEQAoGA9jjq9XpMTExgdHQUDocDarWaeu1SqZRWwAFALBbD6uoquFzuvay64vP56Orqou+9paWFFvccHx9TuYrFIvh8Pg2PkR5CMsTc6XTCYDAAAIrFIiQSCRQKBW2ryGQy8Pv9EAgE9yIXh8NBS0sLJicnacM4mRN5cnKCVCqFaDSKfD4PDocDtVoN4AfOEQqFGB4exvPnz+lmCDabjUqlArFYTHvq+Hw+neMrEonuJSTKYrFgNBoxOjqKsbExuN1u8Hg8lEqlOk48OjoCg8GAQqGgC4wFAgEGBwfx/Plz9PX1obW1FTwer44TdTodxGJxwzjR4/FQThSJRDg9Pa3jxGQyiVqtRjmR5A97enooJ5KK35ucqNVqIZPJcHl5CSaTCYVC8V65405OnsVi0dVBxAMkD00KJ0jZslAoRK1Ww9XVFU343rQq1Gp13Vw5o9GIi4sLcLlcXF1d4fLyEhcXF7i6usL19fWdWqjk0MhU/c7OTvB4vDq5xGIxrFYrmExmXaiP5F26u7sxOjoKo9FIlQgJY8hkMkpUZHD4fVR3kVweGV/X09NDdwSSPIRQKKQ5DBLqu76+pnkXkqRvaWmpm7WpUqnoXj6yZf2mXHd5XiTnJZPJ0NPTA7fbDblcDhaLRb83kudzOBw0BHp9fU0VhcViwejoKM33kvOSy+VU2bHZbJyenuLi4uJewtbkTCQSCbq6umgfFXnn5DvVaDS0Ko88F+m10+v1VLHL5XKqBMRiMVpbWwH8oIzI0PD7CFsTuUQiER2WbDQaKZGTvK5CoaBRCvJcpNBEpVJheHgY/f39UCqVdP6wUCiE2WzG1dUVuFwulYn8/q5lI3fIbDZTg+VtnCgQCG7lRNIjTTiRnPfrnFir1e4lHA/8yIk6nQ4DAwPo6uoCn8+nipfNZlNOJKP6bnKiUqmknGgymeo4UavVQiqVUk4kg8Pft1f7XpUgIVOTyUSLRdra2ijxAKATOjo6OiCRSOqm0JOiDDLtnjTCko+UXJLz83OaFyB9Z2Q6x118zOQj1Wg0dZVmN/eWEbJtaWmhZdk3n4XP59OYOWmEvSkXk8kEk8lENpulWzBWV1ep53VXcrHZbFo8MDk5ie7ubmi1Wup93pzST3IpN5+FKAu9Xk8bYQHUnRebzUahUEA2m0U0GqVhrLfN43wfIGubyFg+h8MBg8FQN4CYFPCwWCzodLq6y0V+r9Fo6FkzGIy6ykMOh4OTkxPkcjnEYjHs7u7SVoK7UobE2yF9m319fTCZTHVyEVK6urqCSqWqCzffVBYdHR3Q6XTUor6+vqaVwWSyfzwex/7+Pra3t+90YAOJKFgsFjidTgwODsJqtUIoFNLnIz2aNpsNcrn8jQpXoVAIhUKB9vZ2eq5ELvKtl8tlGtU4ODjA6uoqrUW4i/Mi3wnpbxweHkZbWxv18ADQwqb29nbaM01wkxOtVus7cWIoFMLy8jKd7XoXd4y8T61WC7vdTtMnN40xUtnb0tICPp+Pjo6OundMhlWYTCa0trZCJBK9IdfrnEiKmt6nXIyfOngGg/GLvgpS3fPBBx/gn/7pn2gs/+YFrdVqdF3GbVqdXEIejwc+n4/r62tcXV3h6uoKFxcXyOfzSCQS2N/fx9raGmZnZ7G/v093h93FgZO9Xl6vF//yL/9CY/nkgjIYDPp8ZH3LbXKRyi5S3UTkury8xPHxMS2o2djYwPz8PLa2tlAoFG6dFfg+QAoQHA4H/sf/+B948eIFLBYLpFJpXajhply3rRJis9m0AZ3kJIhcxWIR2WyWVlEuLCzQar5yuUw9r/cJUoDQ0dGB//7f/zs+//xztLa2QqVS1cl1eXlJ5Xq9nJxcQg6HAz6fDzabTeWq1Wool8vI5XK06XdxcZGOfyI5xbsgVTKF/4svvsB/+2//DTabDXq9vm6zQK1Wq5Pr9ecgholAIACHw6FyXV1doVqt0pVdOzs7WFxcxNLSEmKxGI6Pj+9MWZA9eJ988gn+8R//EQ6HA2azmRIq4Y6bct02bJmkHXg8Xh13nJ2dUWPF7/djaWmJ5rdJrvQuuIOMDXz+/Dn+6Z/+iVa43uTEq6urOrnexomEO27jxGQyCb/fj/X1dczOzsLv9+P4+PjOxsARThwaGsK//Mu/YGxs7Cc58W2rn97GibVaDYVCAZlMpo4TNzc3/yZOvL6+fmtM+L16guRwSAz7pstO/n/iPhMF9zaQ5ZHpdBqZTAblchnlchmJRILmOoLBIJ3QcZcgcpFnJ+Rx04ImoRpy+d6Gi4sLnJycIJ1OI5VKoVQqoVqt0grFWCyGYDBIp5XcNciz3yYXAZfLpSGJt8l2eXlJE9aJRAInJyc4PT2lVnc0GqV9eJFI5M4r8chz8ng8CIXCW9dycTgc2tLxNrmurq5QqVQo0RQKBZyenlI5Y7EYwuEw/H4/9W7vWq7r62twudy3ysVms6nH+Da5yEaCo6MjJJNJ5HI5VKtVmieLx+OIRCLw+/20MvQ+5CLK+TbuILxCFMHbUK1W6f0iBXfFYhGJRIJ+i/v7+3RzyV3L9XOcSO7fu3BiLpdDKpWinFipVOrkCgaD2Nvbw9HR0b3IRVIKAoEAbDb7rZxI/tltuMmJ6XSaFvOk02nE43HEYjGEQiH4/X7EYrH3Lst7VYLEoiGl9AaDgeZOXsfNMODNZDvxIMgswNXVVVpS+/pSWWI93TWur69xcXGB4+NjRCIRWK1W2vvyU3Ld3I9FrBtSsLC6ukrbDAqFAmKxGN2OfN9yFYtFRKNRRKNRiMVicDicd5br+voatVoNpVIJyWQS29vbWFpaQjQapYQai8Vwdnb2Vi/5LuS6vLykRlM4HIZEIrm1v4jIdVO2m3Kdnp4imUzSkU0HBwfUayfrusiZ3Ucpeq1WQ6VSQSqVwuHhIeRyOaRS6Vv//dvkIvc0lUrRcW97e3vI5/PIZDK0mOZtXvJdgFSdko31Go0Gcrn81uIHYkzflAv44d3UajX6dywvL8Pn8yGbzdJQPNlZeZ9yEU6MRCIwmUyQyWS39jX/FHcQTiTFVxsbG8hkMm8slb24uLiXARuvcyKpBXjbeb0LJ66trWFtbQ2JROJeOfFOlGAoFMJ3332Hk5MTZDIZGiYDfvQYarUaNBoNtFotDAYDBAIBLZsPBAIIBALY29vDwcEBnYFXqVRQKBTufdoIIdV4PI6pqSmUy2VkMpm6S3p1dYVyuYzT01OoVCrodDro9Xq63yybzVK5/H4/9vf3EQ6HqWt/fHyMk5OThsiVyWQwNzdHiZHkiUgOrFKpoFKp0F47vV4PuVwO4IcKSyLX/v4+AoEAnXNI+q8KhcK9j9siFZwrKyu036ilpaXuElarVVo2T75DlUoFBoOBcrmMYDBIPYZAIEAHu1erVdq6ct9TVIjBsbW1BRaLhVwuB7vdXifX2dkZSqUS3bup1+uh1WpplWQkEqFy7e/v0yHGlUoFpVIJhULh3icwkVCs3+/HV199hXw+j3Q6XeddXFxc0BoCrVZLv0Uy7CAej9fdr4ODA7ogt1wu07t233JdXFzg8PCQcmI6na7LdZIzvbi4oFWeer0eQqEQFxcXSKfT9H75/X4cHBzQDQrVahX5fL5hnJhIJCgnptNpKBSKujDvTU7UarXQ6/V0ekwul6NykT+EEyuVyr1x4nsPh5LByqVSiTZ/koofADRPxGQy0dvbi+vra/pSstkstra2MD09TaeFk7AaqXZqxOgmIhdpPD46OkImk4FCoaBVdVdXV/RDttvtqNVqEIlEYDKZOD4+xt7eHqanp7G6uoqdnR2qJEjOplHzJm8qC2Ixk9J4ogTJh9za2krXu3A4HFQqFQSDQUxPT1OrO51Oo1Kp0BzLfVRLvk2uk5MTbG5uIpvNIpfLoaWlpa5kvFqtolKpQK/Xw+Fw0JDw2dkZYrEYZmZmMD8/j52dHUqmJCHfqG+RhGd3d3eRy+WQz+cRDodpEQHwoxJUKBR0oohEIsHl5SWSySSWlpboyiGypJkU8zRSLmJAn5ycIJvNIpVK1YV7SdRCIBDA4XCAwWBAJpPh9PQU6XQa6+vrmJ6epkPdi8UinbZCvKn7BrnbZAYt4Y6bnFir1VAsFsFgMNDT04Pr62tIJBJcXV0hm81ie3u7jhNJru8hcGImk6GceHR09JOcSKrOWSwWnZF8kxOz2WwdJ96XXO+9ReL6+pqGNa6vr+mEBvIh83g8aLVadHZ2Qq/XQ6VSUUuJLOzc3t5GPB6n65QaNUD6dZyfnyOfzyMQCNCeMiIXaTFoaWmBTqejvWOhUAiLi4tYXl6mg4vT6XTD9pbdBhLKI/MGSVjj5hoai8UCtVpNq+7i8ThdHru9vU1XvZC5r41QfK+DRB2i0Siur68RDAapXKQv0mw2060LfD4fmUyG7kfc2NiA3+9HOp2m65QeglykMIeQRCKRqPMEyXYBstyZTO3Y3d2le+mIwXKXlZG/FETBk+fJ5/N1yl0gEMBoNEKv19NUC5k9TAqufD4fEokEXaf0EO7Y65xIvPTXObGjowN6vR5qtRqXl5fY29ur40QyAeihcSKJBp2ent7KiVarlXruwA+cuLS0hKWlJfh8PoTDYaRSqYZx4p30CZJ4MUngAj/OhjMYDGhtbUVPTw/sdjsUCgWSySQWFxfxb//2b9jc3KRVaA/loAmI9ZPNZumIM9JUrVar6ToU0ptF4tz//u//joWFBRwfH99pW8CvwdXVFY6Pj2l59s3epcHBQbS3t6O7uxutra1IpVLw+Xz405/+hO+//556tQ9VrnK5jP39/bq+R5FIBJfLBbPZjJ6eHnR2dtJp9X/961/x17/+lRYu3Ucf2S8FKWw5PDxEOByu6w+02+0YGBhAd3c3bDYbLi4uEAgE8N133+FPf/oTwuEwXTv2EOUioc1EIkHlIlNkent7KXfweDxEIhFMT0/jP/7jP+j4tIei1G/ipzhRr9ejpaWFyqVSqZBIJN7gxIek/AgIJ+ZyOTo8nnAiCYG+zonr6+v493//d8zPzz8ITrzTMQk3XVo2m4329nYMDg7i6dOn6O/vh1AoRCgUwldffYVXr17Raq276vd7X7gpF4vFoks+nz59iuHhYcjlcsTjcXz99deYmpqiMwAf4kd8E6+HIMjQ88nJSYyOjkKr1SKbzWJqagrfffcdVldX6eDihywXgLrnU6lUcLlcGB8fx/j4OCwWCyqVCubn5/HNN99gaWmJjnZ6THKRxuOxsTFMTk7SrQnr6+v4y1/+QlsdSE7+IeOmXGKxGHa7HR6PB0+ePIHD4QCLxcLu7i6+/PJLzM7O0jBqoxY0vyte58S2tjbKiQMDA29wot/vR6FQeFScyGQyYTKZ6jiRODtfffXVg+PEexmfThqqe3p6MDY2hsHBQVgsFsRiMezs7ODly5dYWlrCyclJQ1Yi/a0gvTKdnZ0YHR2Fx+NBR0cHUqkU9vf3MT09jdnZWWSz2YZtGf9bQHp3yJqn4eFh2Gw2lEol7O3tYW5uDq9evaKz/R4LiOVtMpng9XoxOjqKnp4eul1gcXERL1++RDQarVvn9dBBLG+dTkfniDocDgiFQlph/f3339cN0H4MINEIYrRMTEygr68ParWabk347rvv4PP53tuW8fsCibIQo+VtnHh8fPzoOFEoFL7BiWT03vT0NGZmZh4UJ96pEiShDJVKhfb2drjdbrjdbmg0GpTLZWxtbWFpaYmGZx66FUdAwmpkAozL5UJfXx8dX0Ri+cFgsCGVdr8GTCYTYrGYFov09/ejpaUFwA+xfNKIe3PX3mMAmShCViGRbRAcDgfBYBCzs7PY2dmhQ4sfkwLk8Xg0FE/CoCKRCOl0GouLi9jc3KT52sekANlsNjQaDbq6utDf3w+n0wmZTIbj42Osrq7SiUqPwbMlIJxIJsTc5MRKpUJbjEj152PhROCHOyaTyWAymeB0Ouk0o5v5zYfIiXe6SkkgEEAqlaKnpwcDAwPo7e2FSqWixQpLS0tYX1+n430esrt/EzweD1KpFO3t7ejv74fL5YJer6e5jJWVFSwvL9Nt64+FUMnEH6vVCpfLRRezXl9f4/DwkO4Ci0Qij4pQybxMg8EAl8uFoaEhtLa20t2UGxsbmJ2dpRPqH4tHQXKbGo0GTqcTXq+XDiC+uaaM7Ed8LHKRBmyFQkFHqHV3d0Mmk9HCtIWFBWxtbdGQ2mPATU7s7u7GwMAAHcpeLpcRi8UoJ6bT6UfFiXw+HxKJhHKi2+2GXq/H+fk5EonEg+bEO1OCZNO1zWbDhx9+iMnJSSgUCpTLZbqNe3p6Gru7uzg5OXk0h02sHbIR+sMPP4RGo8Hl5SX8fj9WV1fx6tUrbGxsoFAoPBpFQWZpdnZ2YmRkBB9//DGdwL+3t4f19XXMzMxgZWWlbu/jYwCfz0draysGBwfxySefoLOzEwKBAKFQCBsbG5ibm8PCwgKOjo4elIX6c+BwODQS8cknn9AN3vF4HBsbG1hcXMTs7Czi8fij8trZbDZdzPrJJ5/A4/FAJpMhl8vR6NH09DRCodC998f9GrBYLLq8mHCiUqlEuVyG3++v48Tj4+NHyYkTExP46KOPoNVqUavVsLm5ifX1dUxNTWF9ff1BcuKdKEFiebe1tWFiYgJjY2Po7e1FMpmky2bn5ubg9/tp2fBjwM3tGKOjoxgfH0d/fz9yuRx8Ph8WFhZoWC2VSj0auZhMJng8HgwGAzweDyYnJ+HxeOi29eXlZbqZPJFIPCgr7qdws3K3r6+Prhzi8XgIBAJYXV2l/VfRaPRReRQcDgcKhQIOhwNPnz6l2wXC4TA2Njbw6tUrrK+vIxQKoVKpNPqR3xkkV9bV1YWnT59idHQUra2tiMfj2NnZwfT0NFZWVhAIBGg14mMA2aZwkxMdDgcdDnKTEzOZzKPhDjIOzmw2Y2RkhO5/zOVy2NnZwcLCAl2a/lA58U6UIJli73a78fHHH6O9vR21Wo0Wi5CFmOVy+UG+lLeBlP329PTgxYsXtErt8PAQs7OzmJ2dpeXMj0kuQqiEeDweD0QiEUKhEObn5zEzM4O1tTVks9lHowCBHzdBtLa2YmJiAuPj41AqlYhEIlhcXMSrV6+wurqKZDL5qDxbkrc1m80YHh7GixcvoNFokM/nqdW9vLyMSCRCl7I+BpDB5waDgXrtBoMBZ2dn2N7extTUFBYWFnBwcPCoPEDgR050uVyUE6+uruo4cXt7+1FyolqtRk9PDz744AM4nU6w2WyEw2HKiRsbGw862ncnSlAsFsNgMMBsNkOv16NarSKRSGB1dRXr6+sIBoO0z+4xQSAQQK/Xw2KxwGAw4OrqCoFAgM68CwQCODo6elSKAgAdr2WxWOj+NuJRrK6uYm9vj+YoHhNIZaHFYoHJZIJQKEQ8Hsfm5iadUkHGhT0msFgsuuvQZDJBLpcjm81iZ2cHKysr2NraQiwWq1vJ8xjAZDIhlUphMplgNpuh0WhwcnKCUChE52VGIpE7H3p9FxCJRDAYDLBYLNDr9Tg9PUUoFMLa2tqj5kSi3AknXl9fPzpOfO9KkMFgQCqVwmw2Q6FQ0Ibe1dVVzM/P0xUfjxFCoRAmkwkajYY2IK+urmJmZoaO/Xmo1s5Pgc/nw2g00o+YKMCZmRlsbW0hlUo9Kk+JgMvlQqvV0pU8pFF3cXERa2triMVij06xAz94uGq1mk65OTo6wsbGBpaWlrC8vIxwOPyoWlcIbk7xIVNufD4fVlZWsLi4SAuXHiOIcid7EMm+UFK49JhCuzdxkxMvLy/pjsaZmRn4fL5Hke66E09QJpPRnVn7+/tYWVnB3Nwc9vf3H1R/yC+FSCSC1WqFRCJBOBxGIBDAq1evsLu7SwcrP/QDvw0kpq9Wq5FKpZBMJukMRuIpPWRL7m3gcrkwGo0wmUzI5/OIRqO0aInMcnxoSfp3AVlmarFYcHp6io2NDZorC4VCj6rd6CZI64DFYgEA+Hw+zM7OYmlpie4MfYxGC3EMrFYrzUeTXaiPsd3oJggnSqVSRCIRHBwcUE7MZDKPghPvRAmSRZLlchmhUAgLCwtYXV2ljZ+PkVAB1A0i9vl8WFtbw+LiInK53L2sCLorsFgsOi90f38fPp8P8/PzSCaTdADxYwTZos7lchGJRBAIBDA/P49wOExbPB76Bb0NpOdRKBQimUwiEonQKAtZ7fQY5SJ79UQiEQqFAi2s2NzcpKudHqNcwA9tVWKxGJVKBeFwGPPz81hZWfm740QSaclms4+GE+9ECaZSKSwsLIDD4SCbzeLg4IAOtH3MINsW/H4/stkswuEw7XF8zCgWi9jc3EQ6nUY2m0UsFkMymXx0xQevg2xbODs7Qz6fp4tHi8XioyVT4IctEcFgkK5GSqVSdEP6YyVT4IfB4LFYDLOzs7i6usLR0RECgUBDVla9T1xfXyOVSmFxcZFyYjAY/LvixP39fbpH9rHVDzB+igwYDMbfxBQcDgdcLhcMBgO1Wg0XFxeP/rCBHzwLPp9Pd2WRJZaPHSwWCzweDywWC7VaDZeXl4/Wm7gJMiaNw+HQVToPYVbhrwVp/eByuXSVzsXFxaNWFARELgB/V9zxOieSb/Gxg3Aik8l80NxxfX395gb0/4c7UYJNNNFEE0008VDwU0qQeZ8P0kQTTTTRRBMPCU0l2EQTTTTRxG8WTSXYRBNNNNHEbxZNJdhEE0000cRvFk0l2EQTTTTRxG8WTSXYRBNNNNHEbxZNJdhEE0000cRvFk0l2EQTTTTRxG8WTSXYRBNNNNHEbxZNJdhEE0000cRvFk0l2EQTTTTRxG8WTSXYRBNNNNHEbxZNJdhEE0000cRvFneyT7BREAgEkEgkYLPZuLq6QrlcRqlUenBrPX4puFwupFIpuFwurq+vUa1WUSwWH/3qHDabDalUCj6fDwA4PT19tFvRb4LJZEIqlUIgEIDBYOD8/BzFYvHRbg8nYDAYEIvFEIvFYDAYuLy8RLFYRLVabfSj/WqIRCK6WLpWq6FUKj36fZoAwOfzIZVKKSdWKhWUSqVHv07sfXLi340SZDAYaGtrwwcffACFQoFKpYKVlRXMzMzg9PS00Y/3N4PBYMBoNOLFixcwGAyo1WrY3NzE1NQUCoVCox/vV0GhUODFixdob28Hi8XC3t4eXr58iUQi0ehH+1UQCASYnJyEw+EAl8tFNBrFt99+i2Aw2OhH+1VgsVjweDzweDzg8/nIZDKYmprC5uZmox/tV4HJZKKnpwdPnz6FUCjEyckJ5ufnMT8//6iVxU1OVCqVqFarlBMfs+HCYDBgMBjw4sULGI1G1Go1bG1tYWpqCvl8/hf/fQ9OCbLZbPD5fFxeXuLs7OydvDgulwuJRAK73Y4XL15ALBYjHo8jHo+DxWLdw1P/PMjyyaurK5ydnb3T5WKz2RCLxWhvb8eTJ09gMpmQy+WQz+fp4tFGg8lk0kXDp6en72SJsVgsCIVCWK1WjI2Nobe3F+VyGWdnZ1hcXLyHp/55MBgM8Hg8sNlsnJ6evtNiVyaTCYFAAIPBAK/Xi5GREVxcXIDH4z0oucji2tPT03fyuhkMBvh8PuRyOQYGBvDixQtcXV1hb2/vQSlALpcLHo+H8/NznJ+fvxN38Hg8SKVSOBwOfPjhh2CxWAiFQggEAmAw3rqC7l7xt3Aih8OhnPjBBx9AJpMhHo8jkUiAzX4YtP8+ONFsNiOfz6NQKIDH4/1Nz/GgcoIMBgMSiQRWqxUajeadFBiDwYBMJkNPTw9cLhf1KhKJBI6Ojh6MJScUCmEymWAwGN5ZgYlEInR1daGvrw9dXV0QCoVIJpNIpVIPJmTI4/FgMBhgMpkgEAje+TdtbW3o7++HzWaDTCbD0dER4vH4g/HaORwOtFotWlpaaPjvXX5jMpkwODiI7u5uaDQanJycIBqNolKp3MNT/zxYLBaUSiXa2togk8nAZP48BbDZbOh0OvT396OnpwcGgwGnp6eIxWI4OTm5h6f+ebBYLMhkMrS2tkKpVL6TXCwWCyqVCi6XC06nE1arFbVaDbFYDIVC4UGkUW5yolarfScF9jondnR01HHiQ0mjCASCX8yJQqEQnZ2d6OvrQ2dnJ0QiEeXE8/Pzv+k5HoZJgB8+SIFAAKvVisHBQSQSCZydneH4+PitVh2Hw4FMJkNnZydGR0fR398PjUaDWCyGSCTyIA6cyWSCy+XCYDBgaGgI1WoVFxcXyGQyb7XqiLXT2toKr9cLj8cDg8GAaDSKSCSCZDLZcCXIYDDA4XCg0WjQ19cHHo+H6+trxONxVKvVW40PJpMJsVhM38XY2BisViuq1Sri8ThisVjDlSCDwQCbzYZCoYDD4YBer8fS0hJCoRDK5fKt3xODwYBQKIROp0NfXx+ePHmC9vZ2cLlcpNNphMPhB5FfYrPZkMlksNls6O7uxsrKCi4vL1Eqld7q6QoEAqjVajgcDkxOTsJut0MsFiOfz+Pw8PBBKEEWi0W9g76+Puzu7tI87NuIkcfjQaFQwG63Y2JiAg6HA3K5HFtbW4hEIsjlcvcsxZtgMpkQCoWwWCwYHBxEKpXC2dkZCoXCL+bERCKBaDSKTCbzoDhxcHAQZ2dnuLy8RDqd/llOtFqtGB4ehsfjgdFoRDweRzQa/VWc+GCUoEAggE6ng9vtxmeffYa9vT0cHR0hFAqhUCi8cUkZDAakUilsNhtGR0fx8ccfo7OzE2w2G9lsFpFIBNlstuEHzuPxoFKp0NPTg48//hjFYhGFQgEXFxfI5XK3XlKhUIi2tjYMDw/jo48+gsvlgkgkwvHxMSKRCNLpdMOVIJfLhVwuR2dnJz744AOIRCKUSiWcnp4ik8ncqsz4fD4sFgv6+/vxwQcfYGRkBBKJBLu7u4hEItTwaSSIomhtbcWTJ0/Q1dWFs7MzqgBvU2YcDgdGoxEulwvPnj3DixcvIJVKkUgkEIvFEIvFGp6DYbFYkEqlsFgsGBkZwbNnzwAAxWIRsVgMxWLxDfJhsVjQaDRwOp14+vQpPvroI2g0GpTLZSSTSUSjURSLxUaIQ0GKdYxGIwYHB/H5559DJpOhUCggHA7j8vLyDYOMwWBAoVCgp6cHk5OT+OSTT2CxWHB1dYVMJoNIJPIgPEGhUAitVguXy4XPPvsM+/v7NLqVz+dv5USJRIKuri7KiV1dXeBwOMjlcgiHww+SE8vlMnV2fooTW1tbMTw8jA8//BButxtisRgnJycIh8OP2xNksVjgcrkwmUzo7+/H6OgoXC4XyuUyhELhre7/zdyL2+3G4OAgDYPu7+9jd3cX0WgUx8fHDQuHEmuHKPaJiQn09fUhEonQCtbXQ2wMBoMaAw6HAx6PB11dXRAIBAiHw/D5fAiHw7degPsCySmp1Wr09PRgbGwMAwMDuLy8hEwmA5fLvTV0yOfzoVar0d3dDY/Hg+7ubsjlcsRiMezs7CAUCuHo6Ohv/pDfB4hit9vt8Hg8GBoagl6vh1KpfKtcPB6PGgNDQ0NwOBzQarWIx+PY2dnBwcEBUqlUQz1cDocDkUiEjo4ODA0Nwev1oru7G7Ozs+DxeLeGDjkcDsRiMdra2jAwMACXywWLxYJsNoudnR3s7+8jkUg0VLmTXFlLSwsGBgYwMjICh8MBv98PPp8PFov1xpmx2WwIBAJYLBYMDAygv78fra2tODs7w8HBAfx+/1uNgvsC4USj0Yj+/n6MjY3B5XLh7OwMQqHwVrnexolsNhuBQODBcaLL5cL4+Dj6+voQj8chFovB4XDeyolarRYOhwNDQ0M0NfS+OLHhSpDH40GpVMLlcuH3v/89BgcHoVKpAOCtiXsulwuNRgObzUY/fBaLhUAggG+//RYzMzOIRqMol8sN+5BJSK27uxufffYZxsbGoNfracjv/Pz8jY+R5Gs6Ojrg9XrR398PgUCASCSCb7/9Fq9evUIoFGpoewTJvXR0dODjjz/GBx98AJPJhIODA5ydnd2a4GYwGJDL5WhtbcXAwAA8Hg/kcjmSySSmpqYwNTWF/f19HB8fN0yum7mXZ8+e4aOPPkJ7eztt2Xhb4p78pq+vD8PDw9Dr9cjn85ifn8fLly+xvb2NXC7XMM+dhGqNRiPGxsbw2WefwWaz0UILUsz0+j0hv3E6nRgeHobVaqUV1y9fvsTa2tpbPf77Ap/Ph0ajwdDQEL744gu4XC5IpVJcXV3RYqbX5eLxeNDpdOju7sbw8DA6OztxeXkJn8+Hb775BouLiw1X7lwul+YqCSeq1WoAP3Li63KR1ERXVxeGh4fhdDrf4MRIJNLQ9gjCiTabDZ999hnGx8eh0+mQTCYpJ94WjbjJiQMDAxAKhYhEIvjuu+/eCyc2TAmSHjGz2UytAqfTCaFQiMPDQ4RCIeRyOZyenr5xaCKRCC6XC8PDw+jo6AAArK6uYmVlBdPT0wgEAg1TFKRHjFg7RJkplUrE43EEAgFkMplb82ZcLhd2ux0jIyPo7u4Gn8+Hz+fD5uYmXr16hZ2dHRwfHzfECyRhJ5VKBafTSUvlDQYDstks/H4/0uk0SqXSG++dyWSivb0dIyMjcDqdkMvlCAaD8Pl8mJ6exubmJrLZbMPkEgqFkMlkcDgcGBwcxMjICFpaWlAqlbC7u4tEIvHW/kWTyYSRkRG43W5oNBqkUins7u5iZmYGa2trvypM82tBesRsNhsGBwcxMTGBjo4O1Go1+Hw+Wthy2/NpNBoMDw9jcHAQRqMRx8fH9H4tLi7SEG8jCJX0iLW1tcHtdmNychLd3d1gs9nw+/3UM7gtv0QqXL1eL1paWnB2doa5uTksLS1hbm4OoVAIlUqlIdxBONFkMsHlclEPUCQS4fDwEMFg8Cc50el0YmRkBJ2dnQCAtbU1rK6uYnp6Gvv7+w3nRBLaJcpMqVQimUwiEAjg6Ojo1vfO4XCos9Pd3Q2BQICdnR1sbm5ienoaPp/v1nTZL0HDlCCfz4fZbMbw8DC++OILuN1uSKVSRKNRTE9PY3V1Fel0GpVKpe5DJpbB+Pg4nj59Co1Gg4ODA/zXf/0XFhcXEQwGfzLRf9fgcDgwGAzo6+vDF198AY/HA7VajVwuh6WlJSwsLCCRSKBcLtd9yKRoZGhoCM+fP4fJZEImk8G3336LqakpBINBmktsBNhsNjQaDXp7e/H5559jYmICBoMB1WoVGxsbmJmZQTgcfuOiMZlM8Hg8OJ1OvHjxAq2trTg9PcXMzAz++te/NjwMymKxoFAo0NXVhY8//hjPnz+HxWIB8AOJvHz5EgcHB28YH0wmE0wmE11dXfjwww/R1dWF6+trrK2t4d/+7d8QDAZpIUMjQIino6MDz549w2effYbW1law2Wxsbm7i22+/xe7u7hs5GAaDARaLBavVig8//BAulwscDgebm5v4P//n/2Bvbw/RaPRWIr4PEKOlpaUFY2Nj+P3vfw+73Q6BQID9/X28fPkSW1tbyGazOD09pdzBYDDAZDKh1+vx/PlzjI6OQiwWY2NjA//2b/+Gzc1NhEIhVKvVhnEHj8eDyWSC1+vF73//e7jdbshkMsRiMczMzGBlZeUnOXFsbAxPnz6FVqtFMBjEn//8ZywsLFBPqZGcqNfr4Xa78cUXX8Dr9UKj0SCfz2N5eRnz8/OIx+Nv5cTBwUE8f/4cZrMZ2WwW3377LV6+fIlQKIR8Pv+rOfHelSCpeNLr9XA6nRgYGEBnZydkMhnK5TJisRjNN9x0j1ksFkQiEWw2GzweD/r6+qBUKpFKpbC1tYXt7W1ardYoa4fP59OE7+DgIGw2G1QqFc7PzxGPx3FwcIBoNFpnQZPfdXR0oK+vD0NDQ9DpdCgUCtje3sb29jYl4UYoCtIvJ5fL0dXVRfNJWq0WV1dXSKVSCAaDODw8rAu1EOVnNpvhcDgwPDwMi8WCarWKvb09bG9vw+/34/j4uGEhNS6XC5lMhvb2dng8HjgcDhiNRjCZTKTTaRweHiIQCFAFeH19TXOier0edrsd4+PjaG9vR61Ww8HBAba3t7G7u4tCoYBqtdqQcDzpEWtpacHg4CBcLhesVit4PB6y2SzC4TD8fj9yuVydXGw2G2q1Gna7HU+ePKHe1eHhIba2tuDz+ZBKpd4g4fsCqQI1m83o6+tDX18f2traIBKJUCgUEI1G4ff7kclk6rjjZlUsiTiJRCLEYjFsb2/D5/MhEom8QcL3BcKJOp2ujhPlcjnlxEAgQAvHbnKiUCiknNjf3w+VSoV0Ok254/DwsGFpBpLPUyqV6OnpwdDQEOx2O9RqNc7Pz5FIJBAIBGgL0euc2N7eDrfbDY/HA71ej+Pj4zvhxHtTgqSkXiQSQavVoqurC4ODg+jt7YVcLke1WsXh4SH29vZoKJQc3E3FSTxAq9WKs7Mz+Hw+rK6u0oquRhw2h8OBUCiEWq1GS0sLvaAajQaXl5eIRqPY29tDMBjE0dERtVzIR6LRaODxePDRRx9RjyIQCGB5eRnBYBD5fL5h4RnyEVssFppwNxqNAIBkMom9vT1a/HHzgpIKMFLt63A4wGazsb+/j6WlJQQCgYZVqrFYLFoibzab4XQ64fV6YbFYwGazcXR0BL/fj0AgQFs+iFykeIbkevv7+yESiRAIBLC6uoqdnR1kMplb81F3DVJ4IJfLYTAY0NvbC4/Hg46ODvB4POTzeQQCAezv7yMajdaNFCSKor29HR999BE8Hg8UCgVisRjW19exvb2NZDLZEAVIDA+JRAK9Xl9HqGKxGMViEaFQCH6/n5L+TUUhFothsVjw7NkzjI+Pw2Aw4Pj4GJubm9jY2KCFMPetAF/nxM7OTgwMDMDhcEChUFBO9Pv978SJLS0tOD8/x87ODlZWVhAOhx8EJ5Kc+U1OjMVi2N3dRTAYpPeFvBPSljM0NEQrXAknLi0tvXdOvDclyGazYTKZ0N7ejp6eHjgcDvT29sJoNOLy8hLBYBAvX77E8vIy/H5/HUHyeDxYLBb09fXB6/Wio6MDxWIR+/v7ePXqFVZWVuo+kPsEk8mETqdDe3s77HY7ent74XA40NraCgaDgcPDQ0xNTWFhYQE7Ozt17Q1sNpt6xMQTOTs7QyAQwPT0NObn55FOpxsWxlCpVGhra4PNZqNn1tXVBS6Xi3g8jvn5eczMzGB7exuJRIJ6dEwmk/aWkfj/1dUV/H4/ZmdnaeFSo+Qi+aSuri709vbSP2QU2NLSEmZnZylB3iywIk3IpH+Tz+fj4OAA8/PzmJ6exsHBQcNCuyKRCFar9Q25pFIpjo+Psba2hlevXmFjYwOHh4d1xE8GM3i9XhquikajWFpawqtXr7C7u9uwHCBpreno6KiTS61Wo1qtwufzYWpqCqurqwgEAsjn8/Q5BQIBWltb4fF4qKFzdHSEjY0N+i4alStjs9kwGo3o6OhAd3f3G5wYCoUoJ+7u7tb1PXO5XOoRe71edHV1oVQqUU5cXl5uGCcyGAxotdo6TnQ6nWhpaQGTycTh4SFevXpVx4nkzpDBDC6XCx6PB06nkzo7hBNTqdR75Y57UYLEauns7MTExASGh4fR29sLmUyG8/NzRKNRrK6u4ssvv8T29jZKpRKtgCKWQUdHB8bHx6nnODc3h9nZWSwsLCAQCDQsVMjlcml+Ynh4GG63GwqFAkwmE9FoFFtbW/j666+xsLCAUqlEvSUSZrRarbQtRKfTYWFhAfPz85ibm4PP52tITonkT4xGI4aHhzEyMkKtOIFAgFgshr29PXz77bf47rvvcHJyUpcjIsqdhGgsFgvW1tawuLhIlUupVLp3uYAfe98GBwcxOjqKgYEBGI1GSCQSJBIJBINBvHr1Cl9++SVN1t8M06jVagwMDGBoaAjt7e0IBoN0HuPa2trfNLvwfYDJZEKhUMDlcmFiYgJDQ0NoaWmBVCpFLpfD/v4+Zmdn8Ze//KXOCyTfokwmo8VmXV1d1FMiuahUKtUwI1MikaC7uxvj4+O08EMqlaJUKiEcDmNxcRFffvkl9vf3aWEWkUskEqG7uxtjY2Ow2+1gsVhYW1vDzMwMlpaWEIlEGsIdpKXhJic6HA5IpVIaPVpbW8OXX36Jra2tWzmxvb39rZzo9/sfBCeOjIzA5XLRKT7RaBTb29v4+uuvMT8//wYncrlcWK1WWmym0+mwuLhIOXF7e/u9c+Kdj00jpedGoxF9fX0YGRmBzWaDUqkEi8VCNpvF0tISFhcXafMt8ZRIeIeEaZxOJ/h8PhKJBDY3NxEIBMBms6FUKsHhcO5alDfkEolEtKdvZGQEvb290Gg04HK5ODk5wdraGubn5xEMBnFyckIPm8lk1uVtXC4XZDIZ0uk0fD4f9vb2UKvVoFKp/uZ5eL9GLlJ6TipVXS4X9Ho9BAIBtbzn5uawv7+PQqFAFeDN8I7JZILT6YRWq0WhUKB5wGq1CqVSCaFQeO9ykXaczs5OjIyMYGBgACaTCSKRCJeXl1RR+Hw+ZLNZ6vmQfBnp4ezt7YXFYkGlUsHBwQE2NjZQKBQgk8kgEonuXS4OhwOFQkEnDHm9XlitVkgkElxfXyMcDmNmZgYbGxs0p3fTYCG57O7ubnR0dODi4gLhcBirq6tIpVIQiUSQSqXvNIrsfYK045CJKSMjI2hvb4dMJgODwUAqlcLs7CxWVlYQj8frCuJuhry7urrQ09MDFotFw7vhcJjOQ73v+cI3G/zdbncdJ5JhH7dxIuGOn+NEUijTCE4kuc3bOLFYLGJjY+NnOdFqtdIq8kwmA5/Ph93dXdRqNajV6vfOiXfmCRKtLhKJYLFY0N3djb6+PnR3d0MsFqNSqSCfz2N7extzc3PY3Nys66cSCASQSqX0sLu7u9Ha2opyuYyjoyMUi0Ww2Wy0trZCIpHg7OwMFxcX9xKu4XK5EAqFMBgMdI5db28vLYIpFAo4ODjA4uIirXIlVhmPx4NEIoFMJoPZbEZ3dzfa29vBYDAQj8fpGCqz2Qy5XA6fz3dvlXhsNptOqSC5TafTCYPBgOvra2QyGcTjcSwtLWF5eRmxWIx+xOQDJqXQhFDFYjGOjo5ok65Op4NCocD19TUl47vOMZECAqVSSeVyu92wWCxgMBjI5XLIZrNYXV3F4uIiDg8PUa1WUavVwGKxqFxkykhnZycUCgXy+Tzy+TzOz8+hUqkood70Ru4SxJuQyWR1uei2tjYwmUwcHx8jn89jfX0dc3NzCAQCVFEQ41QikdAcp81mo0ZLLpdDtVqlsvN4vDqr/S5BDDGxWIyWlha43W709fXBZrOBy+WiVCohn89jc3MTc3Nz2NnZqSuTJ2uRZDIZuru70d3dDZPJhOPjY2SzWRSLRepJCYVCVKvVe+mfu8mJ5O4TTpRIJKhUKigUCvD5fJifn8fGxgay2WwdJ5Lzamtro5xYqVSoXGw2Gy0tLZBIJDg/P783TiTGr16vp0V+JGRNxkQGg0EsLCz8JCeaTCbKHSwWi3Iig8GAyWT6/9u70qc083R7UDbBBRRR3OPGkrhF0xrjku7UTGZqKjUzH+YP7Q+Z6p6a7qp0XKMRRREFUQSVXRAFVLb7oet5GpKYm+4rCjfvqeovvaR9fN/3/H7Pdg5UKhULiZd8T7CyshItLS0wGo2s9dbb24uqqip4vV44HA6YzWZsbW3BbrfD5/PxgqpIJOLb38OHD2E0Glk5JRQKoaKiAjMzM3j27Bmy2SyXUC8vL4vet6CSmMlk4ttpf38/VCoVQqEQ9vf3sba2hs3NTdjtdhwfH3Ppj2rlIyMjGBwchNFo5P+WFo9HR0cxNDQEAHC5XLi6umLPtmL30Orq6mAymTA8PIzx8XEYjUZotVqcnZ3h4OAAFosFZrMZdrsdHo+nYABBpVLh8ePHePToER49eoT+/n40Nzfj4uICsViMDw8ACAaDAMBEW+y1D4VCAaPRyLfuhw8f8qSqy+WC1WrF2toaK9fkN90VCgWGhoYwMDCAhw8fMvFkMhlEo1F0dHTgX//6F3K5HKLRKH7++Wf4/X7E4/Gil6NkMhl6enowODjIpfju7m6k02kcHh7ygMT29jYPItHvWiKR8O+E4urp6UFFRQVisRgaGhrw97//HblcDvF4HAsLCwgEAjfu390mpFIp2tvbee9tZGSESZGG58xmM6xWK++n0u+adlKHh4c5LpIOIxWqly9fIpvN4vr6mntn6XS66NO8lZWVPLBEPWVSP/F6vdjb24PZbMbm5iYcDkfB0r5IJEJbW9tHnKhQKFjndHp6GpOTk8hms7DZbLi4uEAymbw3TlSr1QiFQjg4OPgiThwYGGBOpP82mUzi8ePHGBwc5BmL2+bEoh2C1PSdmJjA1NQUhoeHoVAoWCfO5XLxmPzFxQVkMhkkEgmXMQYHBzE7O8sfQFVVFVKpFE+/NTU1QalUsuKFWq2GRCIp+rg9PfDR0VFMT0/jm2++4Uz04uICHo8HOzs7sNlsfDOjHqFUKoXJZML09DSePHkCvV6PmpoaZDIZnJ2dsQhwbW0tMpkMlEolFhYW2PammCBVl6GhIczMzGB8fBwajQbZbJYdHsg6h25mlKlLpVJ0dXVhcnKS1SrUajUTjVwuR2trK+rr65HL5XBwcIDV1VXIZLI76XkqlUqYTCbMzMxgYmICLS0tqKysZOFdh8MBi8WCcDiMXC7HGRI16cfHx3lxubm5GblcDpFIhCdgGxsbOZO32+0c16eUPW4TMpkMfX19mJ6e5lKhTCZDIBBAKBSC0+mExWKB1+tFKpWCUqmEUqlkHdGxsTFMTU0VZMX0LTY3N6O5uZmnZU9OTqBUKu/EHFgikaCzsxNTU1N4+vQpjEYj5HI5zs7OcHp6ioODA2xtbeHg4ACXl5eoqqpCVVUVZ8YjIyN4/vw5hoaG0NXVxd8Pyf01NzdDJpPh/PwcsVgMtbW1CAQCEIlERX1eYrEYOp0O4+PjmJqaYvWTeDyOWCyGw8ND5sTz8/OPOJG0aYkTFQoF0un0R5xIl5S3b99CKpV+sU3RH0U+J05NTWFiYoIz0aOjIxwdHWFnZwfb29s4Pz9HZWUlVCoVc6LBYMDU1BS++eYb9Pf3M//FYrECTsxms6iurmZOvK33sCiHIKX9LS0tGB8f5wdGeplUnqJRexK5pZpyfX09RkZGWGqMHJ8rKyvR2tqKVCrFrt1UshKJRPxXMSEWi6HVagtGtCUSCVKpFO/GNTU1ob+/n0sRVN5Rq9UwmUyYnJxER0dHgeNzU1MTamtrWRswkUigsrLyzvowNFgxODjI9fj8uIhA+vr6WPItl8tBKpVCrVajp6eHFUnUajWkUimy2SwaGhogl8shl8shkUhwdXVVoJta7OdF/RfKcKmnkN/DVKvV6O7uZoPOXC4HsVgMlUqFtrY2ViRpaGhgJ2uVSgWxWAyJRMIedmKxGBUVFXfiQ0fDEb29vXjy5Al0Oh37OgK/qY+QtRCtbFB5t6mpCc+ePcPg4CA0Gg3kcjn/uTTZXFVVhXQ6DbFY/Em9ymLFJZPJ0NnZiYmJCXR0dKCqqor//7Qv3NbWxhdj6ilVV1ejvr4eExMTvG+rVCp50ItEsquqqtiNPJ87ih0XCa2T0tWHnEjanwAKuIM4cWhoiFc88jmxpaUFGo0GCoUCIpEI2Wz2zp4XUDhsZjQaP+JE0gvV6/VIpVLIZDIFPXqj0YjJyUke5CJO1Gq1qKmpQVVVFcRiccHzuk3c6iFID6WxsRE9PT0YGRnhhXEic9pH6uzshEwm4xIZgIIH3tPTg56eHvaZog+YPnS6FdK0EQmoFuMmRy8pDR+QXxzdlAEwubS1taGiogKdnZ0FP0tVVRXUajU6Ozuh1+t5gII+YJlMxjfxaDQKr9cLi8WCYDBY1IxCLBbzzz06Ogqj0YiWlhb+eWgAiPqCWq224GehQ5B6HGq1muOiyxDF5ff74fP5sLOzw9lJsW6oRJbNzc1cQuro6Cggexp0SafTUKvVBT0GOgSbm5thMBjQ1NTEmQIRWnV1NeLxOE5PTxEIBFiy6/r6umiTlJQVNDc3w2QyYWBgAA8ePCh4XjKZjC8stbW1BTdmygIbGxu5V0aDIXT4K5VKJJNJBINBBAIB7O/vw+l0FlVOjAYjtFot9Hp9gV8ccYdEIkF9fT338vI9GvMPQb1ejwcPHvC3SdyhUChweXmJSCSCYDAIt9uN3d3doqqpECdqNBrmRFoY/5ATOzo6eKiOkM+J3d3d6O3tvZETY7EYc6LVar0TTiRNYOLEpqamGzmxo6Oj4GeRy+Wor69HR0cHDAbDjZwYj8cRiUTg9XpZs/Y2uUP0uV+QSCT6Xb89IoZnz57h1atXXPOWy+V8QybR3kQi8UnHbrpdK5VKNjPNZrPIZrNIp9OIRqP8YVqtVqyurmJ3d5f7MMV4mWkycGRkBP/4xz/w9OlT9PX1oaamhm8mmUyGe5IkBpuPyspKXiClWxxlU+l0GrFYjOvnNpsN79+/h9VqhdfrZRWc236ZaXVFr9fj1atX+Pbbb9HX14eGhoYCYry6uuLn9WEJgsiLmvZisRi5XA7ZbBaZTAYXFxc4PT2Fy+XC7u4u9waOjo6K9pHSAdfZ2Ym//vWv+POf/wyj0Yjm5uaCTO36+hqJRALJZPKjPhcddHK5HDU1NZwBUlw0xOB2u7lHtbGxAY/Hw8u/xTjg5XI5mpub8ac//Ql/+ctfWA0m/4acSqW4F/ThUBVNuspkMlRXV3NWRN/Y5eUlotEoKzeRJq/L5WId1GLERapEz58/x9/+9jcMDw+zNVo+d9DzojZIflzkvlBdXQ2lUskrIFSWp8vl/v4+LBYLizaQgHMxDnjissnJSbx69QpPnjxhAfNPcSKV0fPxJZwYDAY/4kSfz1c0TqRLxdDQEP75z3/i6dOn6O/v/4gT87njJk6kIchPcWI4HC7gxK2tLfh8PlbB+VLuyOVyN6aPt14OpV5Ra2srtFotZDJZwQgymSNWV1ff+GfkcjmkUimcn5/j9PQUkUgEyWQSiUQCPp8PXq+XG+RbW1sIBAK3HcYn46ISLq0L5Ns8UebxuRF5erg0GXt6esovSCAQ4LgcDgebe94FiFhbW1tRXV1dEBcdKAqF4sYXLpfL8QsfDAYRCoUQj8dxeXmJcDgMn8/HEmRWqxUHBwdF3zmjjKixsRHt7e18QOdDJpNBLpd/Nq5sNourqysEAgGEw2Ee645EIvD7/XC73XA6nbDZbNjb27uT3q1EIkFDQwPa29u5LJtfIpJKpZDJZKirq7sxLrrchEIhnJ6e4uzsjE2sfT4fjo+Psb+/zys7d+EbSJlFW1sbNBoNJBJJQTuASry1tbU3/hkUF31ftMJzcXHBcR0eHsJms8Fms93JXmcxOTGZTMLn8+Hk5IS5Y2trC36/v+gxESfqdDrodLpPcqJCofjsOhRxYjKZxOnp6Sc5kWT+rFYr3G73rcdyq4cg3bgodW1vb+clyXzQB5svbkugD/Ti4oLT3+3tbf5Y6aZNL0B+SaRYyGazSKVSiMVi8Hq9CIVC3Pf6PXEBQCKRQDAYxObmJjY3N+Hz+fjmfXJywtnkXTiR0wtIpUq/34/a2lpUVVV9FBc9l/y/l//n0EGxu7sLs9mM4+NjnJ2dsaM13eDvQqGf4orH4wgGg/B6vairq0NNTc1H/+6HwxAfxpVKpRAOh+F0OmE2m3m/ye/3szUNxXUXQz6ZTAbJZJKHVTQaDa+cfBgXxfCpuDKZDLvDr6+vw+FwcEZxdHTEh0c8Hr8TWyGqpJyensLr9aK5uZkt1X5PXLlcDrFYDMfHx1hfX8fu7i7C4TAbbdNEMr2PxcaHWWhnZ2dBe+j3xEUHOXFiMBhEJBJho23KJu+SE8/Pz+Hz+RAMBqFSqf4QJyaTSQQCgf+VE4sV160egrlcDtfX13C73Zibm+OMh1J/AFxKoonOhoYGbsyT27rH42EtQIfDgYODA5ydneHi4oL3Ye4SRIY+nw+Li4vsgExLu1SeSCaTuL6+Rl1dHcelUCiQzWbZFd7lcmF/fx+7u7twOp1886Fb613qMtJhEQqFsLq6CgAIhULc/6ID4vLyEpeXl2yl1NDQwAcKTcRSRuRwOGC32zkbpJ2zu5bbojLRxsYGO2u3t7cXlEOvrq6QTCa5N6HRaKBSqSASiZBMJnF0dAS32439/X3s7e3BbrezAwjtnN219Fsmk8H5+TlsNhsUCgXOzs7Q399fEFcqlUIikWAhCXpmFRUVuLq6gs/n+yguUpGhEtRdKxVRKdbpdOLNmzc4Pz9HJBIpGA6jKopIJCrgDolEguvra3aFz4/L7XYjFotxBnUXl8sP4yLxgfn5ec54aJoV+O1iQ73pfE5Mp9N8gLtcLo7L5XIhGo0W7E3fJW7iRPp+PsWJ9I0plcoCTqQq0e7uLvb39xEOh++UE289E0ylUuwoQIMQNJYtEomQSqU4ML1eD71ezyWps7Mz7OzsYGFhAZubm+wVFY/HuRF6H1ZCdHP2er2Yn59HIBCA3++HWq3mUhTVsC8vL9Hb2wuDwcDlnHg8znqg+ZktSSFlMpl7EVwGfv0AQ6EQlpeXOS6dTsfkQ329eDyO9vZ2GI1G7gPShWdhYQFra2uw2Wzw+Xw8Rk89i/vQm6S1k/X1dYRCIQSDQbYSqqio4P238/NzHhIxGAyQyWTIZDLw+XwsQWWz2XB0dIRYLMY7V+l0+l60TzOZDOLxOLa3txEOhxEMBnF4eMjPSyQSIZFI4OzsDLW1tTAYDNDr9VySCgaD7Au4vb0Nl8uFWCzGF9NMJnMv3xgdgnt7e5xpe71eSKVSjuvq6grRaJTH6ikuuuSQpdfW1hY7lCQSCaTT6XuLiw4Lt9uNeDzOFZdPcWI2m2VOlMlkzIm7u7sFnBiJREqGE30+XwEnkurNpzhRr9fzykcikWBOXF9fh81mQzAYvBdOvPWeIJELPSDaO6JbKhlitrW1cYkqlUrB6XRiY2OD/zo8PMTJyUnRGvG/F5QRBQIBvrnlT67RlCWtdKhUKmSzWXg8HmxtbcFsNsNisRQ4E9yXi3o+KHsnwfJUKsU7PMBvKvyNjY08pSYSieDz+XjQZWNjA3a7naWr7kIt5UtApXl6Fw8ODrgXQ1OvGo0G7e3t0Gg0LFm1t7eHjY0NXjQ/OTkpsFO6b6TTae7hAb+6edBBQT3c+vp6NDY28opKLBaDy+XC+vo6NjY2YLFYcHJywtlsKXxjxBf0zUej0YJ+J8mgdXV1QaVSsdoLPS+Ky+12s1B9KcRFnEhxXVxcFKyzECe2trairq6O9UP39/fZGNdisTAnFnvv70vxISdeXl5+khObmppQXV0NlUqFXC6Ho6Ojjzgx36T5rr+xouwJErF6vV6Ew2H+OMmYdWJiAgaDAUajEY2NjTg9PcXa2hq+//57lgqiydFSIB0C3eqCwSDOzs4KHrZarcbo6Ch6e3thMpnQ0dGBSCQCq9WK77//Hu/eveM0v1RIh0C3Osq66aCgEWdSdCfVl7OzM9jtdvz73//GmzdvCm5wpRQX8BuxkuUT8JvcmMFgYJUKg8HAWqD//e9/8dNPP3FfkzKJUgKVmvb39+F2u3kXTiKRoLu7G319ffyNAcDx8TF++eUX/Pjjj+xQTnGV0jdGg0gejwc+n4+5g3bsaJzeZDJBqVQiGAxiaWkJr1+/LjAJLlXuuIkTyTmdVJryOdFisXAvsxTjopZKLBb7iBMfP36M3t5eGI1GdHZ2IhqNfsSJNMF6X9xRNMUY+uVQyUgqlUKn07FS/dDQEGpqajidnpubY8+yu9An/L+AMkEAvIRL3m2jo6Oor69HJBLBwsIC5ufn+dZdKje4m0DlMIJOp4Ner8fY2BjGxsbQ0tKCRCKB1dVVzM3N4f3792wSXGqHRD6IWClzamhoQE9PD0ZHRzE2NobOzk5kMhlsbm7i7du3WFpaunc37i8BXTZp9Jz2bx8/fsz2OpWVldjd3cWbN2+wuLiIvb091jstVdCBQWU+msom2yCyvXK73Xj79i1bPQUCgXtxXflSfMiJEokEOp2O/SyHhoZQW1sLv9+P+fl5zM/Pw2q1li0nGo1G5kSNRoNoNMqcuLGxwdrD982Jd2KlRCU1k8nExpZ9fX08TfjDDz9gdXW15D/OD0EOyL29vZiensbU1BQGBgYQiURgt9vx008/YW5ujqdZywV0Q+3s7GTDzuHhYVxdXbHv43/+8x94vd57cxn/I6BdMp1Oh4mJCczOzmJ0dBRisRherxdLS0v44Ycf4Ha770RQ+bZAcZF01fPnz/HkyRPU1dXB7/djbW0Nr1+/htPpvDfvvD8KWpsYHBzE8+fPMTExAZ1Oh0AggK2tLbx+/RpWqxWxWOxeemN/FLTcbzAYMDs7i2fPnqG/vx/BYBB2ux0//vgjVlZWWKu1XEBL7j09PZiamsL09DQGBwcRiUSwt7eHn3/+Gb/88ktJcWJRD0FK+Um9f2BgAIODg9BqtUgkEtje3mZPr1gsVtK37g9RUVGBuro6vskNDQ2htbUV6XQaDocDKysr7IBcbge7UqlEY2MjTCYTRkZGCswwl5aW4HA4cHp6WvK303xQr0yj0UCv13OZRiaT4ejoiC2U6OMspwMwX9JuZGSEpatCoRDev3//SQulUkf+wU5OLQMDA1CpVGxTtr6+/pGFUjmgoqKCOXFwcJA5MZlMMie63W6cnZ2V3cFeW1vLnDg8PMycuLe3h3fv3mF/fx/RaLSkOLGoVkoymQxKpZKtNciWJ5VK4ejoiIcq/H4/Li8vy4ZQyQ4l/2AnAWKPx4P19XW8f/+em73lcvMmRZvW1lYYjcYCAWLyK1teXubp33IhHlra1Wq1MBqNGBkZQW9vLx8UNpsNS0tLcDqdZZVRUG+zvr4eBoOBpavUajVPFeZbDZUS8XwOpLVbW1sLvV6PkZERmEwmvjwfHh5idXUVW1tb97LO8UfxKU58+PAhO8mfnJzAbDazj2MplAq/FPmc+OjRowJOJINg4sS72BX+PSjaIUiCzA8ePMDz588xOTmJlpYWXF9fw+FwYGNjAwsLC7DZbAWWPKUOUn948OABJiYm8O2336K9vR0AYLfbYbVaMT8/zwM+pfSw/zcoFAp0dXVhdHQU3333HXp6eiCXy+FyuWCz2bCwsACz2cyyYOUCmUyG9vZ2DAwM4MWLFzAYDKirq8PJyQl7t62srMDr9ZbNQQH81lMyGAx48eIFhoaGoNVqEQwGsbu7i/fv3/OlpdhKNrcJsVjMme13333HAuHn5+dwOBxYX1/n/uZd7/39X1BRUQGVSoXu7m7MzMxgamqKOZEmXOfn57G9vc3+m+UAkehXb8p8Tuzo6IBIJGKll7m5OXZqKTVOLMohSDfvzs5OPH36FDMzMxgdHeVe2eLiIpeffD5f2RyA1APU6XR48uQJv8jxeBx7e3tYWVnB0tISNjc34fF4yuollkgkaGxsxMjICGZmZjA7OwsAODg4wPr6OhYWFmCxWOByuUruJb4J1NtUq9V49OgRx1VbWwu32w2LxcJ7Snt7e2V1ANL4uV6v57haWlrg9/ths9kwPz/PHonk3VYOoPkB6inNzs5Cr9dzxj4/P4/V1VXYbDacnp6WDXcQJ3Z0dHA/emxsjDlxaWkJi4uL2N7eht/vLxvuoB6gTqfD2NgYZmZmMD09zbvR+ZzodrtLMq6i+PTI5XI0NTVhcHAQL1++hMFgAAA4nU7Mz89jaWmJVc7L5SUGfk35GxoaYDKZ8OLFCwwPD0MqlcLtdvNLTCrnpfiwbwLZCfX19WF2dhbffPMNamtr4fP5sLKygvn5eZjNZpycnJTNAQj8tuLR1dXFTXqNRoNIJIK1tTWecHW73WVTAgV+Oyja29sxPj6OFy9eoLW1FfF4HBaLBW/fvsXKygqcTmfJDB98CfK1KB8/foyXL1+iu7sb19fXsNlsePv2LZaXl9n5oZy4Qy6XQ6vVMicajUaIRCLs7+9jYWEBi4uLzInlxB3EiUajkTlRJpPB4/GUDScWJRMk650HDx6wErzH48Hm5iY7kxdb4LUYoMO9q6sLvb297AhNzuQ2mw3Hx8cl+7BvAg1WdHZ2ore3l12dd3Z2sLa2xmLe5dJ7IZD1TkdHB3p6eqDVahGLxeBwONjNgvqb5YTKykrU1dWhra0NPT09aG9v551BWoanoaxyApXVWlpa0N3dje7ubqRSKXg8HlgsFqyvr8PpdCIYDN73j/q7QYf7h5xIS+N2ux0+n+++f8zfjQ85sbq6Gl6vF9vb2zCbzcyJpXx5LoqLRE1NDVpbW6FSqZBMJuF0OrG5uYl3796xUG85goZGGhsbkUql2LpkcXEROzs77ExebqASL3kGejwe2Gw2lqDy+/1l1QMkkJlna2srxGIxexmurq7CYrHwnlK5gaYm29raIJfLEQ6HYbPZYDabsba2hsPDwzsRUb5tUM+sra0NNTU1iMVi3CujzPauNTJvC8SJarUayWQSBwcH2NzcxPLyMux2e9ldWAj5nEgqN8SJNpsNoVCo5JOComSCdEulhVaLxYJ3797BZrMhEAiUVYkmH+RoTaVCl8vFGowkrFyuh2BbWxur94TDYSwtLfFC6/n5ecm/yJ+CVCpliygSUCb91sPDw7JbyyGQykh7eztSqRRPga6trcHpdCIajZZVeZdAqwMkdE49pdXVVdjtdoTD4bLq2xJomI44kapiy8vLzInlNLiUD4VCgba2NqhUKhZmX1hYYC/UcuDEomSCSqUSWq0W6XQaFosFi4uLWF1d5d2yUk6NPwdyIheLxdjZ2eGBkVAoVDRTzruAVCqFVquFQqFgA8u5uTle8Sg1qaYvBU0ZqlQqnJyccP9lf3+f9W3LMS5aINdoNOwkvrCwgJ2dHcRiMVxfX5dlXFRF0mg0SCQSfMm0WCyslVqOlzEAzImZTAYWiwXLy8t49+4dIpFIWXMHlUPFYjF2d3d56j8YDJZNXEUR0A6Hw7BarZBIJKwK4/f7y/J2mo9YLAabzYaTkxMEAgE4nU54vd6yLKnlI5FIwOFwIB6PIxAIwOVy4ejoqGxLT4TLy0u4XC5IJJICO5q7tqy6baRSKRwfH8NsNuPi4gInJydwOp0Ih8Nle0gAv8rbBQIBWCwWZLNZ+Hw+2O12BIPBsiDTz+H09BRWqxVSqRSBQIDnIv4/cOLOzg68Xm8BJ5ZTZiv6HBmIRKI/xBRVVVWorq5GRUUFUqkUkslkWS3D3wSZTIaamhpUVlYilUqx2WO5xyWRSFBTUwOpVIpUKsU+e+VOPOTYTb5sFFc5lkDzQZJbCoUCmUwG19fX7NtWzqDpUKVSCQAcV7lfMoGvhxOvrq5KUkoxl8uJbvpnRTkEBQgQIECAgFLB5w7BouwJChAgQIAAAeUA4RAUIECAAAFfLYRDUIAAAQIEfLUQDkEBAgQIEPDVQjgEBQgQIEDAV4vPTocKECBAgAAB/58hZIICBAgQIOCrhXAIChAgQICArxbCIShAgAABAr5aCIegAAECBAj4aiEcggIECBAg4KuFcAgKECBAgICvFv8D7YPcVeozSIkAAAAASUVORK5CYII=",
+      "text/plain": [
+       "<Figure size 576x576 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot some training images\n",
+    "real_batch = next(iter(dataloader))\n",
+    "plt.figure(figsize=(8,8))\n",
+    "plt.axis(\"off\")\n",
+    "plt.title(\"Training Images\")\n",
+    "plt.imshow(np.transpose(vutils.make_grid(real_batch[0].to(device)[:64], padding=2, normalize=True).cpu(),(1,2,0)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# custom weights initialization called on netG and netD\n",
+    "def weights_init(m):\n",
+    "    classname = m.__class__.__name__\n",
+    "    if classname.find('Conv') != -1:\n",
+    "        nn.init.normal_(m.weight.data, 0.0, 0.02)\n",
+    "    elif classname.find('BatchNorm') != -1:\n",
+    "        nn.init.normal_(m.weight.data, 1.0, 0.02)\n",
+    "        nn.init.constant_(m.bias.data, 0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Generator Code\n",
+    "\n",
+    "class Generator(nn.Module):\n",
+    "    def __init__(self, ngpu):\n",
+    "        super(Generator, self).__init__()\n",
+    "        self.ngpu = ngpu\n",
+    "        self.main = nn.Sequential(\n",
+    "            # input is Z, going into a convolution\n",
+    "            nn.ConvTranspose2d(nz, ngf * 8, 4, 1, 0, bias=False),\n",
+    "            nn.BatchNorm2d(ngf * 8),\n",
+    "            nn.ReLU(True),\n",
+    "            # state size. (ngf*8) x 4 x 4\n",
+    "            nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),\n",
+    "            nn.BatchNorm2d(ngf * 4),\n",
+    "            nn.ReLU(True),\n",
+    "            # state size. (ngf*4) x 8 x 8\n",
+    "            nn.ConvTranspose2d( ngf * 4, ngf * 2, 4, 2, 1, bias=False),\n",
+    "            nn.BatchNorm2d(ngf * 2),\n",
+    "            nn.ReLU(True),\n",
+    "            # state size. (ngf*2) x 16 x 16\n",
+    "            nn.ConvTranspose2d( ngf * 2, ngf, 4, 2, 1, bias=False),\n",
+    "            nn.BatchNorm2d(ngf),\n",
+    "            nn.ReLU(True),\n",
+    "            # state size. (ngf) x 32 x 32\n",
+    "            nn.ConvTranspose2d( ngf, nc, 4, 2, 1, bias=False),\n",
+    "            nn.Tanh()\n",
+    "            # state size. (nc) x 64 x 64\n",
+    "        )\n",
+    "\n",
+    "    def forward(self, input):\n",
+    "        return self.main(input)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Generator(\n",
+      "  (main): Sequential(\n",
+      "    (0): ConvTranspose2d(100, 512, kernel_size=(4, 4), stride=(1, 1), bias=False)\n",
+      "    (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
+      "    (2): ReLU(inplace=True)\n",
+      "    (3): ConvTranspose2d(512, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
+      "    (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
+      "    (5): ReLU(inplace=True)\n",
+      "    (6): ConvTranspose2d(256, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
+      "    (7): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
+      "    (8): ReLU(inplace=True)\n",
+      "    (9): ConvTranspose2d(128, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
+      "    (10): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
+      "    (11): ReLU(inplace=True)\n",
+      "    (12): ConvTranspose2d(64, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
+      "    (13): Tanh()\n",
+      "  )\n",
+      ")\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Create the generator\n",
+    "netG = Generator(ngpu).to(device)\n",
+    "\n",
+    "# Handle multi-gpu if desired\n",
+    "if (device.type == 'cuda') and (ngpu > 1):\n",
+    "    netG = nn.DataParallel(netG, list(range(ngpu)))\n",
+    "\n",
+    "# Apply the weights_init function to randomly initialize all weights\n",
+    "#  to mean=0, stdev=0.02.\n",
+    "netG.apply(weights_init)\n",
+    "\n",
+    "# Print the model\n",
+    "print(netG)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class Discriminator(nn.Module):\n",
+    "    def __init__(self, ngpu):\n",
+    "        super(Discriminator, self).__init__()\n",
+    "        self.ngpu = ngpu\n",
+    "        self.main = nn.Sequential(\n",
+    "            # input is (nc) x 64 x 64\n",
+    "            nn.Conv2d(nc, ndf, 4, 2, 1, bias=False),\n",
+    "            nn.LeakyReLU(0.2, inplace=True),\n",
+    "            # state size. (ndf) x 32 x 32\n",
+    "            nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),\n",
+    "            nn.BatchNorm2d(ndf * 2),\n",
+    "            nn.LeakyReLU(0.2, inplace=True),\n",
+    "            # state size. (ndf*2) x 16 x 16\n",
+    "            nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),\n",
+    "            nn.BatchNorm2d(ndf * 4),\n",
+    "            nn.LeakyReLU(0.2, inplace=True),\n",
+    "            # state size. (ndf*4) x 8 x 8\n",
+    "            nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),\n",
+    "            nn.BatchNorm2d(ndf * 8),\n",
+    "            nn.LeakyReLU(0.2, inplace=True),\n",
+    "            # state size. (ndf*8) x 4 x 4\n",
+    "            nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),\n",
+    "            nn.Sigmoid()\n",
+    "        )\n",
+    "\n",
+    "    def forward(self, input):\n",
+    "        return self.main(input)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Discriminator(\n",
+      "  (main): Sequential(\n",
+      "    (0): Conv2d(1, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
+      "    (1): LeakyReLU(negative_slope=0.2, inplace=True)\n",
+      "    (2): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
+      "    (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
+      "    (4): LeakyReLU(negative_slope=0.2, inplace=True)\n",
+      "    (5): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
+      "    (6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
+      "    (7): LeakyReLU(negative_slope=0.2, inplace=True)\n",
+      "    (8): Conv2d(256, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
+      "    (9): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
+      "    (10): LeakyReLU(negative_slope=0.2, inplace=True)\n",
+      "    (11): Conv2d(512, 1, kernel_size=(4, 4), stride=(1, 1), bias=False)\n",
+      "    (12): Sigmoid()\n",
+      "  )\n",
+      ")\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Create the Discriminator\n",
+    "netD = Discriminator(ngpu).to(device)\n",
+    "\n",
+    "# Handle multi-gpu if desired\n",
+    "if (device.type == 'cuda') and (ngpu > 1):\n",
+    "    netD = nn.DataParallel(netD, list(range(ngpu)))\n",
+    "\n",
+    "# Apply the weights_init function to randomly initialize all weights\n",
+    "#  to mean=0, stdev=0.2.\n",
+    "netD.apply(weights_init)\n",
+    "\n",
+    "# Print the model\n",
+    "print(netD)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialize BCELoss function\n",
+    "criterion = nn.BCELoss()\n",
+    "\n",
+    "# Create batch of latent vectors that we will use to visualize\n",
+    "#  the progression of the generator\n",
+    "fixed_noise = torch.randn(64, nz, 1, 1, device=device)\n",
+    "\n",
+    "# Establish convention for real and fake labels during training\n",
+    "real_label = 1.\n",
+    "fake_label = 0.\n",
+    "\n",
+    "# Setup Adam optimizers for both G and D\n",
+    "optimizerD = optim.Adam(netD.parameters(), lr=lr, betas=(beta1, 0.999))\n",
+    "optimizerG = optim.Adam(netG.parameters(), lr=lr, betas=(beta1, 0.999))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Starting Training Loop...\n",
+      "[0/5][0/469]\tLoss_D: 1.3327\tLoss_G: 2.9109\tD(x): 0.4710\tD(G(z)): 0.3334 / 0.0759\n",
+      "[0/5][50/469]\tLoss_D: 0.3975\tLoss_G: 18.6086\tD(x): 0.9795\tD(G(z)): 0.2794 / 0.0000\n",
+      "[0/5][100/469]\tLoss_D: 0.1952\tLoss_G: 5.1273\tD(x): 0.9312\tD(G(z)): 0.1027 / 0.0077\n",
+      "[0/5][150/469]\tLoss_D: 0.0890\tLoss_G: 5.1653\tD(x): 0.9807\tD(G(z)): 0.0640 / 0.0084\n",
+      "[0/5][200/469]\tLoss_D: 0.2651\tLoss_G: 4.6875\tD(x): 0.8998\tD(G(z)): 0.1069 / 0.0145\n",
+      "[0/5][250/469]\tLoss_D: 0.2760\tLoss_G: 4.1801\tD(x): 0.9559\tD(G(z)): 0.1915 / 0.0223\n",
+      "[0/5][300/469]\tLoss_D: 0.1293\tLoss_G: 4.3041\tD(x): 0.9312\tD(G(z)): 0.0502 / 0.0233\n",
+      "[0/5][350/469]\tLoss_D: 0.2458\tLoss_G: 3.0678\tD(x): 0.8304\tD(G(z)): 0.0361 / 0.0767\n",
+      "[0/5][400/469]\tLoss_D: 1.5231\tLoss_G: 1.4075\tD(x): 0.3113\tD(G(z)): 0.0038 / 0.2935\n",
+      "[0/5][450/469]\tLoss_D: 0.8433\tLoss_G: 1.8634\tD(x): 0.5897\tD(G(z)): 0.1559 / 0.2040\n",
+      "[1/5][0/469]\tLoss_D: 0.3977\tLoss_G: 3.0405\tD(x): 0.8880\tD(G(z)): 0.2193 / 0.0712\n",
+      "[1/5][50/469]\tLoss_D: 0.2656\tLoss_G: 2.1538\tD(x): 0.8446\tD(G(z)): 0.0739 / 0.1483\n",
+      "[1/5][100/469]\tLoss_D: 0.2981\tLoss_G: 2.3471\tD(x): 0.8163\tD(G(z)): 0.0750 / 0.1179\n"
+     ]
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "\u001b[0;32m/var/folders/l1/8_qbbp7d7hbgk9kkn4tkz2nh0000gn/T/ipykernel_35921/2435757670.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     59\u001b[0m         \u001b[0;31m# Calculate gradients for G\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     60\u001b[0m         \u001b[0merrG\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[0;32m---> 61\u001b[0;31m         \u001b[0mD_G_z2\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0moutput\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmean\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitem\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     62\u001b[0m         \u001b[0;31m# Update G\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     63\u001b[0m         \u001b[0moptimizerG\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;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "# Training Loop\n",
+    "\n",
+    "# Lists to keep track of progress\n",
+    "img_list = []\n",
+    "G_losses = []\n",
+    "D_losses = []\n",
+    "iters = 0\n",
+    "\n",
+    "print(\"Starting Training Loop...\")\n",
+    "# For each epoch\n",
+    "for epoch in range(num_epochs):\n",
+    "    # For each batch in the dataloader\n",
+    "    for i, data in enumerate(dataloader, 0):\n",
+    "\n",
+    "        ############################\n",
+    "        # (1) Update D network: maximize log(D(x)) + log(1 - D(G(z)))\n",
+    "        ###########################\n",
+    "        ## Train with all-real batch\n",
+    "        netD.zero_grad()\n",
+    "        # Format batch\n",
+    "        real_cpu = data[0].to(device)\n",
+    "        b_size = real_cpu.size(0)\n",
+    "        label = torch.full((b_size,), real_label, dtype=torch.float, device=device)\n",
+    "        # Forward pass real batch through D\n",
+    "        output = netD(real_cpu).view(-1)\n",
+    "        # Calculate loss on all-real batch\n",
+    "        errD_real = criterion(output, label)\n",
+    "        # Calculate gradients for D in backward pass\n",
+    "        errD_real.backward()\n",
+    "        D_x = output.mean().item()\n",
+    "\n",
+    "        ## Train with all-fake batch\n",
+    "        # Generate batch of latent vectors\n",
+    "        noise = torch.randn(b_size, nz, 1, 1, device=device)\n",
+    "        # Generate fake image batch with G\n",
+    "        fake = netG(noise)\n",
+    "        label.fill_(fake_label)\n",
+    "        # Classify all fake batch with D\n",
+    "        output = netD(fake.detach()).view(-1)\n",
+    "        # Calculate D's loss on the all-fake batch\n",
+    "        errD_fake = criterion(output, label)\n",
+    "        # Calculate the gradients for this batch, accumulated (summed) with previous gradients\n",
+    "        errD_fake.backward()\n",
+    "        D_G_z1 = output.mean().item()\n",
+    "        # Compute error of D as sum over the fake and the real batches\n",
+    "        errD = errD_real + errD_fake\n",
+    "        # Update D\n",
+    "        optimizerD.step()\n",
+    "\n",
+    "        ############################\n",
+    "        # (2) Update G network: maximize log(D(G(z)))\n",
+    "        ###########################\n",
+    "        netG.zero_grad()\n",
+    "        label.fill_(real_label)  # fake labels are real for generator cost\n",
+    "        # Since we just updated D, perform another forward pass of all-fake batch through D\n",
+    "        output = netD(fake).view(-1)\n",
+    "        # Calculate G's loss based on this output\n",
+    "        errG = criterion(output, label)\n",
+    "        # Calculate gradients for G\n",
+    "        errG.backward()\n",
+    "        D_G_z2 = output.mean().item()\n",
+    "        # Update G\n",
+    "        optimizerG.step()\n",
+    "\n",
+    "        # Output training stats\n",
+    "        if i % 50 == 0:\n",
+    "            print('[%d/%d][%d/%d]\\tLoss_D: %.4f\\tLoss_G: %.4f\\tD(x): %.4f\\tD(G(z)): %.4f / %.4f'\n",
+    "                  % (epoch, num_epochs, i, len(dataloader),\n",
+    "                     errD.item(), errG.item(), D_x, D_G_z1, D_G_z2))\n",
+    "\n",
+    "        # Save Losses for plotting later\n",
+    "        G_losses.append(errG.item())\n",
+    "        D_losses.append(errD.item())\n",
+    "\n",
+    "        # Check how the generator is doing by saving G's output on fixed_noise\n",
+    "        if (iters % 500 == 0) or ((epoch == num_epochs-1) and (i == len(dataloader)-1)):\n",
+    "            with torch.no_grad():\n",
+    "                fake = netG(fixed_noise).detach().cpu()\n",
+    "            img_list.append(vutils.make_grid(fake, padding=2, normalize=True))\n",
+    "\n",
+    "        iters += 1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -1211,7 +1706,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.9 64-bit",
    "language": "python",
    "name": "python3"
   },
@@ -1225,7 +1720,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.8"
+   "version": "3.9.9"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
+   }
   }
  },
  "nbformat": 4,
diff --git a/README.md b/README.md
index 57884980d12716147ef767baaee44c3afe0e851a..fc329382890229ce09e35e7c9c44ba4e26f2a2e9 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,23 @@
-# GAN & cGAN tutorial.
+# Part 1
 
-We recommand to use the notebook (.ipynb) but the Python script (.py) is also provided if more convenient for you.
+In this section we will use a GAN to generate fake numbers using the MNIST dataset. 
 
-# How to submit your Work ?
+## Changes
+- Following the tutorial, the first aspect to change was the `nc` variable, the variable that determines the number of channels of the images, that should be changed to 1.
+- Then, to import the dataset, use `torchvision.datasets.MNIST`, and for the same reason as before, change the transformation `transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),` to `transforms.Normalize((0.5,), (0.5,)),` to suit the number of channels of the images.
+- Now the variable `device` was defined adding an `if` clause for ARM mac GPUs.
 
-This work must be done individually. The expected output is a repository named gan-cgan on https://gitlab.ec-lyon.fr. It must contain your notebook (or python files) and a README.md file that explains briefly the successive steps of the project. The last commit is due before 11:59 pm on Wednesday, March 29, 2023. Subsequent commits will not be considered.
\ No newline at end of file
+## Results
+The plot of the losses has a unexpected behavior: the generator loss increases in the first ~50 iterations, while the discriminator has nearly no loss, then there is a peak in iteration ~250. That said, the overall result is pretty ok, with some images turning out recognizable as number.
+
+# Part 2
+
+### Question 1
+Knowing the input and output images will be 256x256, what will be the dimension of the encoded vector x8 ?
+
+Since this parameter is hard coded, the size of x8 will always be 512x512
+
+### Question 2
+As you can see, U-net has an encoder-decoder architecture with skip connections. Explain why it works better than a traditional encoder-decoder.
+
+The standard encoder-decoder architecture has a limitation that the decoder may not be able to reconstruct details from the compressed image, leading to information loss. Thus, the U-net introduces skip connections that allow the decoder to better recover details and spacial information from the source image.
\ No newline at end of file