protein_fcn_prelim4.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Trying to make a FCN to predict dihedral angles. Some of the code adapted from Jeppe's openprotein."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import torch\n",
    "import imp\n",
    "import re\n",
    "from torch.nn.utils.rnn import pad_sequence"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "aa_id_dict = {'A': 0, 'C': 1, 'D': 2, 'E': 3, 'F': 4, 'G': 5, 'H': 6, 'I': 7,\n",
    "              'K': 8, 'L': 9, 'M': 10, 'N': 11, 'P': 12, 'Q': 13, 'R': 14, \n",
    "              'S': 15, 'T': 16, 'V': 17, 'W': 18, 'Y': 19}\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def aa_to_onehot(aa_str, aa_to_nr, mask=None):\n",
    "    if mask!=None:\n",
    "        mask_ind = np.asarray([x=='+' for x in mask])*1\n",
    "        mask_ind = np.nonzero(mask_ind)\n",
    "        aa_str = \"\".join([aa_str[x] for x in mask_ind[0]]) # because it gets put in another list\n",
    "    init_array = np.zeros( (len(aa_to_nr.keys()), len(aa_str)) )\n",
    "    for i,j in enumerate(aa_str):\n",
    "        init_array[aa_to_nr[j], i] = 1\n",
    "    return(init_array)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def read_proteinnet_file(file, stop_at=1000, verbose=True):\n",
    "    protein_dict = {}\n",
    "    with open(file) as input:\n",
    "        lines = input.readlines()\n",
    "        curr_id = None\n",
    "        for i, line in enumerate(lines):\n",
    "            line = line.strip()\n",
    "            if line == '[ID]':\n",
    "                curr_id = lines[i+1].strip()\n",
    "                protein_dict[curr_id] = {}\n",
    "                protein_dict[curr_id]['primary'] = lines[i+3].strip()\n",
    "            if line == '[TERTIARY]':\n",
    "                coords = []\n",
    "                for j in range(3):\n",
    "                    coords.append(np.fromstring(lines[i+j+1], sep='\\t'))\n",
    "                protein_dict[curr_id]['tertiary'] = np.array(coords)\n",
    "            if line == '[MASK]':\n",
    "                protein_dict[curr_id]['mask'] = lines[i+1].strip()\n",
    "            if len(protein_dict.keys()) >= stop_at:\n",
    "                break\n",
    "    filter_seqs(protein_dict, verbose)\n",
    "    return(protein_dict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def filter_coords(coords, mask):\n",
    "    mask = np.array([x=='+' for x in mask])\n",
    "    mask_stretched = np.repeat(mask, 3)\n",
    "    coords_filt = coords[:, mask_stretched]\n",
    "    return(coords_filt)\n",
    "\n",
    "def filter_seqs(protein_dict, verbose):\n",
    "    re_chainbreak = re.compile(\"\\-*\\+*\\+\\-+\\+\\+*\\-*\")\n",
    "    keys_to_remove = {}\n",
    "    for key in protein_dict.keys():\n",
    "        if len(protein_dict[key].keys()) < 3:\n",
    "            keys_to_remove[key] = ' missing structure, removing...'\n",
    "            continue\n",
    "        mask = protein_dict[key]['mask']\n",
    "        if re_chainbreak.search(mask):\n",
    "            keys_to_remove[key] = \" has a chainbreak, removing...\"\n",
    "        else:\n",
    "            coords = protein_dict[key]['tertiary']\n",
    "            coords_filt = filter_coords(coords, mask)\n",
    "            protein_dict[key]['tertiary'] = coords_filt\n",
    "    for key in keys_to_remove.keys():\n",
    "        if verbose:\n",
    "            print(key, keys_to_remove[key])\n",
    "        del protein_dict[key]\n",
    "\n",
    "def new_dihedral(p0, p1, p2, p3): # COPY PASTA'D FROM STACKEXCHANGE\n",
    "    \"\"\"Praxeolitic formula\n",
    "    1 sqrt, 1 cross product\"\"\"\n",
    "\n",
    "    b0 = -1.0*(p1 - p0)\n",
    "    b1 = p2 - p1\n",
    "    b2 = p3 - p2\n",
    "\n",
    "    # normalize b1 so that it does not influence magnitude of vector\n",
    "    # rejections that come next\n",
    "    b1 /= np.linalg.norm(b1)\n",
    "\n",
    "    # vector rejections\n",
    "    # v = projection of b0 onto plane perpendicular to b1\n",
    "    #   = b0 minus component that aligns with b1\n",
    "    # w = projection of b2 onto plane perpendicular to b1\n",
    "    #   = b2 minus component that aligns with b1\n",
    "    v = b0 - np.dot(b0, b1)*b1\n",
    "    w = b2 - np.dot(b2, b1)*b1\n",
    "\n",
    "    # angle between v and w in a plane is the torsion angle\n",
    "    # v and w may not be normalized but that's fine since tan is y/x\n",
    "    x = np.dot(v, w)\n",
    "    y = np.dot(np.cross(b1, v), w)\n",
    "    #return np.degrees(np.arctan2(y, x))\n",
    "    return np.arctan2(y, x)\n",
    "\n",
    "def calc_angles(coords):\n",
    "    N = coords.shape[1]\n",
    "    angles_all = []\n",
    "    for i in range(0, N-3, 3):\n",
    "        psi = new_dihedral(*[coords[:, x] for x in range(i, i+4)])\n",
    "        omega = new_dihedral(*[coords[:, x] for x in range(i+1, i+5)])\n",
    "        phi = new_dihedral(*[coords[:, x] for x in range(i+2, i+6)])\n",
    "        angles = [psi, omega, phi]\n",
    "        angles_all.append(angles)\n",
    "    return(np.array(angles_all))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_proteins = read_proteinnet_file('/Users/Deathvoodoo/big_folders_msc/data/casp7/training_70', 2000, verbose=False)\n",
    "val_proteins = read_proteinnet_file('/Users/Deathvoodoo/big_folders_msc/data/casp7/validation', 200, verbose=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1246"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check how big the proteins are, dont wanna pad a million zeroes\n",
    "keylengths_train=[len(train_proteins[key]['primary']) for key in train_proteins.keys()]\n",
    "keylengths_val=[len(val_proteins[key]['primary']) for key in val_proteins.keys()]\n",
    "max(max(keylengths_train), max(keylengths_val))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.7/site-packages/ipykernel_launcher.py:35: RuntimeWarning: invalid value encountered in true_divide\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(805, 20, 1500)\n",
      "(805, 3, 1499)\n"
     ]
    }
   ],
   "source": [
    "max_length = 1500\n",
    "sequence_list = []\n",
    "angle_list = []\n",
    "for key in some_proteins.keys():\n",
    "    sequence = aa_to_onehot(some_proteins[key]['primary'], aa_id_dict, some_proteins[key]['mask'])\n",
    "    coords = some_proteins[key]['tertiary']\n",
    "    angles = calc_angles(coords).T\n",
    "    if max_length-sequence.shape[0] < 0:\n",
    "        print(key, ' exceeds max length: ', max_length, ' , skipping...')\n",
    "        continue\n",
    "    else:\n",
    "        sequence_padded = np.pad(sequence, pad_width=((0,0), (0, max_length-sequence.shape[1])), constant_values=0)\n",
    "        sequence_list.append(sequence_padded)\n",
    "        angles_padded = np.pad(angles, pad_width=((0,0), (0, max_length-sequence.shape[1])), constant_values=0)\n",
    "        angle_list.append(angles_padded)\n",
    "print(np.array(sequence_list).shape)\n",
    "print(np.array(angle_list).shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_onehot_angles(protein_dict, max_length=1500):\n",
    "    sequence_list = []\n",
    "    angle_list = []\n",
    "    for key in protein_dict.keys():\n",
    "        sequence = aa_to_onehot(protein_dict[key]['primary'], aa_id_dict, protein_dict[key]['mask'])\n",
    "        coords = protein_dict[key]['tertiary']\n",
    "        angles = calc_angles(coords).T\n",
    "        if max_length-sequence.shape[0] < 0:\n",
    "            print(key, ' exceeds max length: ', max_length, ' , skipping...')\n",
    "            continue\n",
    "        else:\n",
    "            sequence_padded = np.pad(sequence, pad_width=((0,0), (0, max_length-sequence.shape[1])), constant_values=0)\n",
    "            sequence_list.append(sequence_padded)\n",
    "            angles_padded = np.pad(angles, pad_width=((0,0), (0, max_length-sequence.shape[1])), constant_values=0)\n",
    "            angle_list.append(angles_padded)\n",
    "    N = len(sequence_list)\n",
    "    have_nans = []\n",
    "    for i,j in enumerate(angle_list):\n",
    "        if np.isnan(j).any():\n",
    "            have_nans.append(i)\n",
    "    sequence_tensor = torch.tensor(sequence_list).float()\n",
    "    sequence_tensor = sequence_tensor.unsqueeze(1)\n",
    "    angle_tensor = torch.tensor(angle_list).float()\n",
    "    angle_tensor = angle_tensor.unsqueeze(1)\n",
    "    inds_to_keep = np.logical_not(np.isin(np.arange(N), have_nans))\n",
    "    sequence_tensor = sequence_tensor[inds_to_keep, :, :, :]\n",
    "    angle_tensor = angle_tensor[inds_to_keep, :, :, :]\n",
    "    return([sequence_tensor, angle_tensor])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "def split_inds(N, train_fraction, validation_fraction):\n",
    "    indices = np.arange(N)\n",
    "    train_to = int(np.floor(len(indices)*train_fraction))\n",
    "    train_inds = indices[0: train_to]\n",
    "    val_to = int(np.floor(len(indices)*(train_fraction+validation_fraction)))\n",
    "    val_inds = indices[train_to: val_to]\n",
    "    test_inds = indices[val_to:]\n",
    "    return(train_inds, val_inds, test_inds)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.7/site-packages/ipykernel_launcher.py:36: RuntimeWarning: invalid value encountered in true_divide\n"
     ]
    }
   ],
   "source": [
    "train_data = get_onehot_angles(train_proteins)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.7/site-packages/ipykernel_launcher.py:36: RuntimeWarning: invalid value encountered in true_divide\n"
     ]
    }
   ],
   "source": [
    "val_data = get_onehot_angles(val_proteins)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "from torch.utils.data import Dataset\n",
    "class proteindataset(Dataset):\n",
    "    def __init__(self, seqs, angles):\n",
    "        self.sequences = seqs\n",
    "        self.angles = angles\n",
    "\n",
    "    def __len__(self):\n",
    "        return self.sequences.shape[0]\n",
    "\n",
    "    def __getitem__(self, idx):\n",
    "        return [self.sequences[idx, :, :, :], self.angles[idx, :, :, :]]\n",
    "    \n",
    "class proteindataset2(Dataset): # needs to be fixed\n",
    "    def __init__(self, ids):\n",
    "        self.ids = ids # should be np.array\n",
    "    def __len__(self):\n",
    "        return len(self.ids)\n",
    "    def __getitem__(self, idx):\n",
    "        id_sub = self.ids[idx]\n",
    "        seq_string = seqs[id_sub]['primary']\n",
    "        sequence =  aa_to_onehot(seq_string, aa_id_dict, seqs[id_sub]['mask'])\n",
    "        coords = seqs[id_sub]['tertiary']\n",
    "        angles = calc_angles(coords).T\n",
    "        seq_tensor = torch.tensor(sequence).float().unsqueeze(0)\n",
    "        angle_tensor = torch.tensor(angles).float().unsqueeze(0)\n",
    "        return [seq_tensor.unsqueeze(0), angle_tensor.unsqueeze(0)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_dataset = proteindataset(train_data[0], train_data[1])\n",
    "val_dataset = proteindataset(val_data[0], val_data[1])\n",
    "#test_dataset = proteindataset(test_data[0], test_data[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "id_array = np.array(list(train_proteins.keys()))\n",
    "train_dataset2 = proteindataset2(id_array)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "trainloader = torch.utils.data.DataLoader(train_dataset, batch_size=100,\n",
    "                                          shuffle=True, num_workers=2)\n",
    "valloader = torch.utils.data.DataLoader(val_dataset, batch_size=100,\n",
    "                                         shuffle=False, num_workers=2)\n",
    "#testloader = torch.utils.data.DataLoader(test_dataset, batch_size=100,\n",
    "                                         #shuffle=False, num_workers=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "trainloader2 = torch.utils.data.DataLoader(train_dataset2, batch_size=4,\n",
    "                                          shuffle=True, num_workers=2)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch.nn as nn\n",
    "import torch.nn.functional as F\n",
    "import torch.optim as optim\n",
    "\n",
    "\n",
    "class Net(nn.Module):\n",
    "    def __init__(self):\n",
    "        super(Net, self).__init__()\n",
    "        self.conv0 = nn.Conv2d(1, 3, (20, 1))\n",
    "        self.bnorm0 = torch.nn.BatchNorm2d(3)\n",
    "        self.conv1 = nn.Conv2d(3, 6, (1, 4))\n",
    "        self.bnorm1 = torch.nn.BatchNorm2d(6)\n",
    "        self.conv2 = nn.Conv2d(6, 12, (1, 8))\n",
    "        self.bnorm2 = torch.nn.BatchNorm2d(12)\n",
    "        self.conv3 = nn.Conv2d(12, 24, (1, 12))\n",
    "        self.bnorm3 = torch.nn.BatchNorm2d(24)\n",
    "        \n",
    "        self.deconv1 = nn.ConvTranspose2d(in_channels=24, out_channels=12, kernel_size=(1, 12))\n",
    "        self.bnorm4 = torch.nn.BatchNorm2d(12)\n",
    "        self.deconv2 = nn.ConvTranspose2d(in_channels=24, out_channels=6, kernel_size=(1, 8))\n",
    "        self.bnorm5 = torch.nn.BatchNorm2d(6)\n",
    "        self.deconv3 = nn.ConvTranspose2d(in_channels=12, out_channels=1, kernel_size=(3, 3))\n",
    "\n",
    "    def forward(self, x):\n",
    "        conv0_out = F.relu(self.bnorm0(self.conv0(x)))\n",
    "        conv1_out = F.relu(self.bnorm1(self.conv1(conv0_out)))\n",
    "        conv2_out = F.relu(self.bnorm2(self.conv2(conv1_out)))\n",
    "        conv3_out = F.relu(self.bnorm3(self.conv3(conv2_out)))\n",
    "\n",
    "        deconv1_out = self.bnorm4(self.deconv1(conv3_out))\n",
    "        deconv2_input = torch.cat((conv2_out, deconv1_out), 1)\n",
    "        deconv2_out = self.bnorm5(self.deconv2(deconv2_input))\n",
    "        deconv3_input = torch.cat((conv1_out, deconv2_out), 1)\n",
    "        deconv3_out = self.deconv3(deconv3_input)\n",
    "\n",
    "        return deconv3_out\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 149,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "epoch: 0, iteration: 4] training loss: 1.346999955177307, validation_loss: 0.6612606048583984\n",
      "epoch: 0, iteration: 9] training loss: 0.8109584212303161, validation_loss: 0.6653778553009033\n",
      "epoch: 0, iteration: 14] training loss: 0.6761969804763794, validation_loss: 0.6693404912948608\n",
      "epoch: 1, iteration: 4] training loss: 0.6468740224838256, validation_loss: 0.6719595193862915\n",
      "epoch: 1, iteration: 9] training loss: 0.5975839495658875, validation_loss: 0.6658914685249329\n",
      "epoch: 1, iteration: 14] training loss: 0.6096521139144897, validation_loss: 0.6526800394058228\n",
      "new best validation loss, saving..\n",
      "epoch: 2, iteration: 4] training loss: 0.5670120000839234, validation_loss: 0.6318108439445496\n",
      "new best validation loss, saving..\n",
      "epoch: 2, iteration: 9] training loss: 0.5541205763816833, validation_loss: 0.6133136749267578\n",
      "new best validation loss, saving..\n",
      "epoch: 2, iteration: 14] training loss: 0.5646921038627625, validation_loss: 0.594924807548523\n",
      "new best validation loss, saving..\n",
      "epoch: 3, iteration: 4] training loss: 0.515029352903366, validation_loss: 0.5749236345291138\n",
      "new best validation loss, saving..\n",
      "epoch: 3, iteration: 9] training loss: 0.5508701801300049, validation_loss: 0.5621587038040161\n",
      "new best validation loss, saving..\n",
      "epoch: 3, iteration: 14] training loss: 0.5344243049621582, validation_loss: 0.5516715049743652\n",
      "new best validation loss, saving..\n",
      "epoch: 4, iteration: 4] training loss: 0.5097227811813354, validation_loss: 0.5428355932235718\n",
      "new best validation loss, saving..\n",
      "epoch: 4, iteration: 9] training loss: 0.5289572536945343, validation_loss: 0.5379088521003723\n",
      "new best validation loss, saving..\n",
      "epoch: 4, iteration: 14] training loss: 0.5144637942314148, validation_loss: 0.5340955257415771\n",
      "new best validation loss, saving..\n",
      "epoch: 5, iteration: 4] training loss: 0.5065475821495056, validation_loss: 0.5306398868560791\n",
      "new best validation loss, saving..\n",
      "epoch: 5, iteration: 9] training loss: 0.5123748123645783, validation_loss: 0.5285604596138\n",
      "new best validation loss, saving..\n",
      "epoch: 5, iteration: 14] training loss: 0.5050772964954376, validation_loss: 0.5269206166267395\n",
      "new best validation loss, saving..\n",
      "epoch: 6, iteration: 4] training loss: 0.4980649471282959, validation_loss: 0.5249199271202087\n",
      "new best validation loss, saving..\n",
      "epoch: 6, iteration: 9] training loss: 0.5256168603897095, validation_loss: 0.5235904455184937\n",
      "new best validation loss, saving..\n",
      "epoch: 6, iteration: 14] training loss: 0.4918351650238037, validation_loss: 0.5225203037261963\n",
      "new best validation loss, saving..\n",
      "epoch: 7, iteration: 4] training loss: 0.494488400220871, validation_loss: 0.5215032696723938\n",
      "new best validation loss, saving..\n",
      "epoch: 7, iteration: 9] training loss: 0.4877139151096344, validation_loss: 0.5209525227546692\n",
      "new best validation loss, saving..\n",
      "epoch: 7, iteration: 14] training loss: 0.5252194762229919, validation_loss: 0.5198981165885925\n",
      "new best validation loss, saving..\n",
      "epoch: 8, iteration: 4] training loss: 0.4988790214061737, validation_loss: 0.5191102027893066\n",
      "new best validation loss, saving..\n",
      "epoch: 8, iteration: 9] training loss: 0.5115679919719696, validation_loss: 0.5182817578315735\n",
      "new best validation loss, saving..\n",
      "epoch: 8, iteration: 14] training loss: 0.49419012665748596, validation_loss: 0.5177737474441528\n",
      "new best validation loss, saving..\n",
      "epoch: 9, iteration: 4] training loss: 0.49383376240730287, validation_loss: 0.517259955406189\n",
      "new best validation loss, saving..\n",
      "epoch: 9, iteration: 9] training loss: 0.49391084909439087, validation_loss: 0.5168090462684631\n",
      "new best validation loss, saving..\n",
      "epoch: 9, iteration: 14] training loss: 0.5046696245670319, validation_loss: 0.5162144899368286\n",
      "new best validation loss, saving..\n",
      "epoch: 10, iteration: 4] training loss: 0.48302615284919737, validation_loss: 0.5155754089355469\n",
      "new best validation loss, saving..\n",
      "epoch: 10, iteration: 9] training loss: 0.4865092098712921, validation_loss: 0.5151577591896057\n",
      "new best validation loss, saving..\n",
      "epoch: 10, iteration: 14] training loss: 0.5178297340869904, validation_loss: 0.5147886872291565\n",
      "new best validation loss, saving..\n",
      "epoch: 11, iteration: 4] training loss: 0.4790602922439575, validation_loss: 0.5142053961753845\n",
      "new best validation loss, saving..\n",
      "epoch: 11, iteration: 9] training loss: 0.5076931416988373, validation_loss: 0.5136858820915222\n",
      "new best validation loss, saving..\n",
      "epoch: 11, iteration: 14] training loss: 0.5008448958396912, validation_loss: 0.5130979418754578\n",
      "new best validation loss, saving..\n",
      "epoch: 12, iteration: 4] training loss: 0.48840609192848206, validation_loss: 0.512675404548645\n",
      "new best validation loss, saving..\n",
      "epoch: 12, iteration: 9] training loss: 0.49735626578330994, validation_loss: 0.5122693777084351\n",
      "new best validation loss, saving..\n",
      "epoch: 12, iteration: 14] training loss: 0.49498059749603274, validation_loss: 0.5119542479515076\n",
      "new best validation loss, saving..\n",
      "epoch: 13, iteration: 4] training loss: 0.46592167019844055, validation_loss: 0.511542797088623\n",
      "new best validation loss, saving..\n",
      "epoch: 13, iteration: 9] training loss: 0.5025590419769287, validation_loss: 0.510959804058075\n",
      "new best validation loss, saving..\n",
      "epoch: 13, iteration: 14] training loss: 0.5156817674636841, validation_loss: 0.5103561282157898\n",
      "new best validation loss, saving..\n",
      "epoch: 14, iteration: 4] training loss: 0.5192355275154114, validation_loss: 0.509874701499939\n",
      "new best validation loss, saving..\n",
      "epoch: 14, iteration: 9] training loss: 0.48019376397132874, validation_loss: 0.5096330046653748\n",
      "new best validation loss, saving..\n",
      "epoch: 14, iteration: 14] training loss: 0.4767816424369812, validation_loss: 0.509228527545929\n",
      "new best validation loss, saving..\n",
      "epoch: 15, iteration: 4] training loss: 0.4649089276790619, validation_loss: 0.5089921355247498\n",
      "new best validation loss, saving..\n",
      "epoch: 15, iteration: 9] training loss: 0.5267461240291595, validation_loss: 0.5084768533706665\n",
      "new best validation loss, saving..\n",
      "epoch: 15, iteration: 14] training loss: 0.48178269863128664, validation_loss: 0.5080975890159607\n",
      "new best validation loss, saving..\n",
      "epoch: 16, iteration: 4] training loss: 0.48239482045173643, validation_loss: 0.5091326832771301\n",
      "epoch: 16, iteration: 9] training loss: 0.5053368628025054, validation_loss: 0.507610023021698\n",
      "new best validation loss, saving..\n",
      "epoch: 16, iteration: 14] training loss: 0.4931576788425446, validation_loss: 0.507934033870697\n",
      "epoch: 17, iteration: 4] training loss: 0.4902017593383789, validation_loss: 0.5071439743041992\n",
      "new best validation loss, saving..\n",
      "epoch: 17, iteration: 9] training loss: 0.4767883360385895, validation_loss: 0.5067136287689209\n",
      "new best validation loss, saving..\n",
      "epoch: 17, iteration: 14] training loss: 0.49375555515289304, validation_loss: 0.5062928199768066\n",
      "new best validation loss, saving..\n",
      "epoch: 18, iteration: 4] training loss: 0.47918136715888976, validation_loss: 0.5059241056442261\n",
      "new best validation loss, saving..\n",
      "epoch: 18, iteration: 9] training loss: 0.4803157866001129, validation_loss: 0.5056039094924927\n",
      "new best validation loss, saving..\n",
      "epoch: 18, iteration: 14] training loss: 0.5065808713436126, validation_loss: 0.5053128600120544\n",
      "new best validation loss, saving..\n",
      "epoch: 19, iteration: 4] training loss: 0.4951210618019104, validation_loss: 0.5052552223205566\n",
      "new best validation loss, saving..\n",
      "epoch: 19, iteration: 9] training loss: 0.49250327944755556, validation_loss: 0.5049687027931213\n",
      "new best validation loss, saving..\n",
      "epoch: 19, iteration: 14] training loss: 0.47267706990242003, validation_loss: 0.5051653385162354\n",
      "epoch: 20, iteration: 4] training loss: 0.49590388536453245, validation_loss: 0.5043779015541077\n",
      "new best validation loss, saving..\n",
      "epoch: 20, iteration: 9] training loss: 0.48716883063316346, validation_loss: 0.5048913359642029\n",
      "epoch: 20, iteration: 14] training loss: 0.47564520239830016, validation_loss: 0.5041435956954956\n",
      "new best validation loss, saving..\n",
      "epoch: 21, iteration: 4] training loss: 0.5026917874813079, validation_loss: 0.50424724817276\n",
      "epoch: 21, iteration: 9] training loss: 0.46554137468338014, validation_loss: 0.5036471486091614\n",
      "new best validation loss, saving..\n",
      "epoch: 21, iteration: 14] training loss: 0.49307848811149596, validation_loss: 0.5034626126289368\n",
      "new best validation loss, saving..\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "epoch: 22, iteration: 4] training loss: 0.5004382312297821, validation_loss: 0.5034646987915039\n",
      "epoch: 22, iteration: 9] training loss: 0.48504036068916323, validation_loss: 0.5033885836601257\n",
      "new best validation loss, saving..\n",
      "epoch: 22, iteration: 14] training loss: 0.4726028203964233, validation_loss: 0.5033047795295715\n",
      "new best validation loss, saving..\n",
      "epoch: 23, iteration: 4] training loss: 0.48551304936408995, validation_loss: 0.5029894113540649\n",
      "new best validation loss, saving..\n",
      "epoch: 23, iteration: 9] training loss: 0.4808096647262573, validation_loss: 0.5032849311828613\n",
      "epoch: 23, iteration: 14] training loss: 0.4950728416442871, validation_loss: 0.503052294254303\n",
      "epoch: 24, iteration: 4] training loss: 0.4899945378303528, validation_loss: 0.5024398565292358\n",
      "new best validation loss, saving..\n",
      "epoch: 24, iteration: 9] training loss: 0.4932475030422211, validation_loss: 0.502608597278595\n",
      "epoch: 24, iteration: 14] training loss: 0.47263681292533877, validation_loss: 0.5028032064437866\n",
      "epoch: 25, iteration: 4] training loss: 0.47182021141052244, validation_loss: 0.5027539730072021\n",
      "epoch: 25, iteration: 9] training loss: 0.4914246678352356, validation_loss: 0.5021182894706726\n",
      "new best validation loss, saving..\n",
      "epoch: 25, iteration: 14] training loss: 0.47892066836357117, validation_loss: 0.5024779438972473\n",
      "epoch: 26, iteration: 4] training loss: 0.491371089220047, validation_loss: 0.5039166808128357\n",
      "epoch: 26, iteration: 9] training loss: 0.49435281157493594, validation_loss: 0.5021312236785889\n",
      "epoch: 26, iteration: 14] training loss: 0.4617341697216034, validation_loss: 0.5017249584197998\n",
      "new best validation loss, saving..\n",
      "epoch: 27, iteration: 4] training loss: 0.4667428731918335, validation_loss: 0.5016334056854248\n",
      "new best validation loss, saving..\n",
      "epoch: 27, iteration: 9] training loss: 0.4764394223690033, validation_loss: 0.501309335231781\n",
      "new best validation loss, saving..\n",
      "epoch: 27, iteration: 14] training loss: 0.5075423121452332, validation_loss: 0.5011447072029114\n",
      "new best validation loss, saving..\n",
      "epoch: 28, iteration: 4] training loss: 0.48105337023735045, validation_loss: 0.5010120868682861\n",
      "new best validation loss, saving..\n",
      "epoch: 28, iteration: 9] training loss: 0.49137344360351565, validation_loss: 0.5008224248886108\n",
      "new best validation loss, saving..\n",
      "epoch: 28, iteration: 14] training loss: 0.47264094948768615, validation_loss: 0.5005571842193604\n",
      "new best validation loss, saving..\n",
      "epoch: 29, iteration: 4] training loss: 0.4792173981666565, validation_loss: 0.5006679892539978\n",
      "epoch: 29, iteration: 9] training loss: 0.4924949109554291, validation_loss: 0.5004515647888184\n",
      "new best validation loss, saving..\n",
      "epoch: 29, iteration: 14] training loss: 0.46983044743537905, validation_loss: 0.5001583099365234\n",
      "new best validation loss, saving..\n",
      "epoch: 30, iteration: 4] training loss: 0.49892979860305786, validation_loss: 0.500320315361023\n",
      "epoch: 30, iteration: 9] training loss: 0.4657665312290192, validation_loss: 0.5002361536026001\n",
      "epoch: 30, iteration: 14] training loss: 0.4718664288520813, validation_loss: 0.5000958442687988\n",
      "new best validation loss, saving..\n",
      "epoch: 31, iteration: 4] training loss: 0.4604755163192749, validation_loss: 0.5002015829086304\n",
      "epoch: 31, iteration: 9] training loss: 0.5012663841247559, validation_loss: 0.4996822476387024\n",
      "new best validation loss, saving..\n",
      "epoch: 31, iteration: 14] training loss: 0.48343409299850465, validation_loss: 0.4998071491718292\n",
      "epoch: 32, iteration: 4] training loss: 0.4843004643917084, validation_loss: 0.4999304711818695\n",
      "epoch: 32, iteration: 9] training loss: 0.487815260887146, validation_loss: 0.49961698055267334\n",
      "new best validation loss, saving..\n",
      "epoch: 32, iteration: 14] training loss: 0.4649656772613525, validation_loss: 0.4997778832912445\n",
      "epoch: 33, iteration: 4] training loss: 0.47398620247840884, validation_loss: 0.49969884753227234\n",
      "epoch: 33, iteration: 9] training loss: 0.4738982915878296, validation_loss: 0.4990682601928711\n",
      "new best validation loss, saving..\n",
      "epoch: 33, iteration: 14] training loss: 0.5026348173618317, validation_loss: 0.4994540810585022\n",
      "epoch: 34, iteration: 4] training loss: 0.49185510277748107, validation_loss: 0.49923205375671387\n",
      "epoch: 34, iteration: 9] training loss: 0.47463876008987427, validation_loss: 0.4987659156322479\n",
      "new best validation loss, saving..\n",
      "epoch: 34, iteration: 14] training loss: 0.4656851887702942, validation_loss: 0.49974244832992554\n",
      "epoch: 35, iteration: 4] training loss: 0.46637882590293883, validation_loss: 0.4996001124382019\n",
      "epoch: 35, iteration: 9] training loss: 0.4994216740131378, validation_loss: 0.49942880868911743\n",
      "epoch: 35, iteration: 14] training loss: 0.4764419376850128, validation_loss: 0.4997628629207611\n",
      "epoch: 36, iteration: 4] training loss: 0.47648765444755553, validation_loss: 0.49882030487060547\n",
      "epoch: 36, iteration: 9] training loss: 0.4813313245773315, validation_loss: 0.498587965965271\n",
      "new best validation loss, saving..\n",
      "epoch: 36, iteration: 14] training loss: 0.48403599858283997, validation_loss: 0.4986107051372528\n",
      "epoch: 37, iteration: 4] training loss: 0.4923750996589661, validation_loss: 0.49835872650146484\n",
      "new best validation loss, saving..\n",
      "epoch: 37, iteration: 9] training loss: 0.4635396242141724, validation_loss: 0.498025506734848\n",
      "new best validation loss, saving..\n",
      "epoch: 37, iteration: 14] training loss: 0.48689464330673216, validation_loss: 0.4979023337364197\n",
      "new best validation loss, saving..\n",
      "epoch: 38, iteration: 4] training loss: 0.4849988043308258, validation_loss: 0.4978974461555481\n",
      "new best validation loss, saving..\n",
      "epoch: 38, iteration: 9] training loss: 0.4776779353618622, validation_loss: 0.4986623525619507\n",
      "epoch: 38, iteration: 14] training loss: 0.4744838893413544, validation_loss: 0.49757346510887146\n",
      "new best validation loss, saving..\n",
      "epoch: 39, iteration: 4] training loss: 0.47605844736099245, validation_loss: 0.4977160394191742\n",
      "epoch: 39, iteration: 9] training loss: 0.46251508593559265, validation_loss: 0.4993892014026642\n",
      "epoch: 39, iteration: 14] training loss: 0.49186702370643615, validation_loss: 0.49761858582496643\n",
      "epoch: 40, iteration: 4] training loss: 0.4773275554180145, validation_loss: 0.4970800578594208\n",
      "new best validation loss, saving..\n",
      "epoch: 40, iteration: 9] training loss: 0.48622019290924073, validation_loss: 0.49782881140708923\n",
      "epoch: 40, iteration: 14] training loss: 0.471829479932785, validation_loss: 0.4969726502895355\n",
      "new best validation loss, saving..\n",
      "epoch: 41, iteration: 4] training loss: 0.48319717645645144, validation_loss: 0.4970480799674988\n",
      "epoch: 41, iteration: 9] training loss: 0.47348284125328066, validation_loss: 0.4971213638782501\n",
      "epoch: 41, iteration: 14] training loss: 0.48242889642715453, validation_loss: 0.4972487986087799\n",
      "epoch: 42, iteration: 4] training loss: 0.4507832944393158, validation_loss: 0.49749138951301575\n",
      "epoch: 42, iteration: 9] training loss: 0.4862228870391846, validation_loss: 0.4969576299190521\n",
      "new best validation loss, saving..\n",
      "epoch: 42, iteration: 14] training loss: 0.4975566387176514, validation_loss: 0.498769074678421\n",
      "epoch: 43, iteration: 4] training loss: 0.49077885746955874, validation_loss: 0.4974975883960724\n",
      "epoch: 43, iteration: 9] training loss: 0.49233049154281616, validation_loss: 0.4973609149456024\n",
      "epoch: 43, iteration: 14] training loss: 0.45482433438301084, validation_loss: 0.4968091547489166\n",
      "new best validation loss, saving..\n",
      "epoch: 44, iteration: 4] training loss: 0.4828857958316803, validation_loss: 0.4964400827884674\n",
      "new best validation loss, saving..\n",
      "epoch: 44, iteration: 9] training loss: 0.45955321192741394, validation_loss: 0.4997650682926178\n",
      "epoch: 44, iteration: 14] training loss: 0.5007183909416199, validation_loss: 0.5071926116943359\n",
      "epoch: 45, iteration: 4] training loss: 0.48735268115997316, validation_loss: 0.500004231929779\n",
      "epoch: 45, iteration: 9] training loss: 0.47106282114982606, validation_loss: 0.49745526909828186\n",
      "epoch: 45, iteration: 14] training loss: 0.48237246870994566, validation_loss: 0.49694979190826416\n",
      "epoch: 46, iteration: 4] training loss: 0.4724901854991913, validation_loss: 0.4967430531978607\n",
      "epoch: 46, iteration: 9] training loss: 0.45143691897392274, validation_loss: 0.4961390197277069\n",
      "new best validation loss, saving..\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "epoch: 46, iteration: 14] training loss: 0.5050410389900207, validation_loss: 0.49605792760849\n",
      "new best validation loss, saving..\n",
      "epoch: 47, iteration: 4] training loss: 0.4673293709754944, validation_loss: 0.49649402499198914\n",
      "epoch: 47, iteration: 9] training loss: 0.4764802038669586, validation_loss: 0.4957585632801056\n",
      "new best validation loss, saving..\n",
      "epoch: 47, iteration: 14] training loss: 0.4908961355686188, validation_loss: 0.4963066875934601\n",
      "epoch: 48, iteration: 4] training loss: 0.49053635001182555, validation_loss: 0.49575427174568176\n",
      "new best validation loss, saving..\n",
      "epoch: 48, iteration: 9] training loss: 0.4770037353038788, validation_loss: 0.4955501854419708\n",
      "new best validation loss, saving..\n",
      "epoch: 48, iteration: 14] training loss: 0.4772158443927765, validation_loss: 0.4957979619503021\n",
      "epoch: 49, iteration: 4] training loss: 0.48567832708358766, validation_loss: 0.4958939552307129\n",
      "epoch: 49, iteration: 9] training loss: 0.48113142848014834, validation_loss: 0.49604126811027527\n",
      "epoch: 49, iteration: 14] training loss: 0.4627821326255798, validation_loss: 0.4963013529777527\n",
      "Finished Training\n"
     ]
    }
   ],
   "source": [
    "net = Net()\n",
    "\n",
    "criterion = nn.MSELoss()\n",
    "optimizer = optim.Adam(net.parameters(), lr=1e-3)\n",
    "#optimizer = optim.SGD(net.parameters(), lr=1e-2)\n",
    "\n",
    "prints_per_epoch = 3\n",
    "\n",
    "verbose_k = np.floor(len(trainloader)/prints_per_epoch)\n",
    "#print(verbose_k)\n",
    "\n",
    "train_losses = []\n",
    "val_losses = []\n",
    "iterations = []\n",
    "best_loss = None\n",
    "\n",
    "for epoch in range(50):\n",
    "\n",
    "    running_loss = 0.0\n",
    "    for i, data in enumerate(trainloader):\n",
    "    #for i in range(52):\n",
    "        #sequence = train_data[0][i, :, :, :].unsqueeze(0)\n",
    "        #true_angles = train_data[1][i, :, :, :].unsqueeze(0)\n",
    "        sequence, true_angles = data\n",
    "        #print(sequence.shape, true_angles.shape)\n",
    "\n",
    "        # zero the parameter gradients\n",
    "        optimizer.zero_grad()\n",
    "\n",
    "        # forward + backward + optimize\n",
    "        predicted_angles = net(sequence)\n",
    "\n",
    "        loss = criterion(predicted_angles, true_angles)\n",
    "        loss.backward()\n",
    "        optimizer.step()\n",
    "        \n",
    "        # print statistics, should add validation loss\n",
    "        running_loss += loss.item()\n",
    "        \n",
    "        if (i+1) % verbose_k == 0:   \n",
    "            train_losses.append(running_loss/verbose_k)\n",
    "            true_iter = len(trainloader)*epoch + i\n",
    "            iterations.append(true_iter)\n",
    "            net.eval()\n",
    "            validation_pred = net(val_data[0])\n",
    "            validation_loss = criterion(validation_pred, val_data[1]).item()\n",
    "            val_losses.append(validation_loss)\n",
    "            net.train()\n",
    "            print('epoch: {}, iteration: {}] training loss: {}, validation_loss: {}'.format(\n",
    "                epoch, i, running_loss/verbose_k, validation_loss))\n",
    "            \n",
    "            if best_loss == None:\n",
    "                best_loss = validation_loss\n",
    "            else:\n",
    "                if validation_loss <= min(val_losses):\n",
    "                    print('new best validation loss, saving..')\n",
    "                    best_loss = validation_loss\n",
    "                    torch.save(net.state_dict(), 'best_fcn_parameters.pt')\n",
    "\n",
    "            running_loss = 0.0\n",
    "\n",
    "print('Finished Training')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "torch.Size([161, 1, 3, 1499])"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "net.load_state_dict(torch.load('/Users/Deathvoodoo/Documents/random/best_fcn_parameters.pt'))\n",
    "\n",
    "net.eval()\n",
    "\n",
    "validation_pred = net(val_data[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "plt.scatter(iterations, train_losses, label='train loss')\n",
    "plt.scatter(iterations, val_losses, label='validation loss')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "432"
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import PeptideBuilder\n",
    "test_protein = list(val_proteins.keys())[13]\n",
    "print(len(val_proteins[test_protein]['primary']))\n",
    "print(val_data[0][13, 0, :, :].sum()) # sanity check, but the keys should be arranged in insertion order anyway"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'30#1W26_1_A'"
      ]
     },
     "execution_count": 108,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_protein"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_angles_read = val_data[1][13, 0, :, :]\n",
    "test_angles_pred = validation_pred[13, 0, :, :].detach()[:, 0:431]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_pb_structure(seq_str, angles):\n",
    "    psi = np.degrees(angles[0, :].tolist())\n",
    "    omega = np.degrees(angles[1, :].tolist())\n",
    "    phi = np.degrees(angles[2, :].tolist())\n",
    "    structure = PeptideBuilder.make_structure(seq_str, phi, psi, omega)\n",
    "    return(structure)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_structure_real = make_pb_structure(val_proteins[test_protein]['primary'], val_data[1][13, 0, :, :])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_structure_pred = make_pb_structure(val_proteins[test_protein]['primary'], test_angles_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "metadata": {},
   "outputs": [],
   "source": [
    "import Bio.PDB\n",
    "def write_to_pdb(structure, prot_id, identifier):\n",
    "    out = Bio.PDB.PDBIO()\n",
    "    out.set_structure(structure)\n",
    "    out.save(prot_id + identifier + \".pdb\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "metadata": {},
   "outputs": [],
   "source": [
    "write_to_pdb(test_structure_real, test_protein, '_real')\n",
    "write_to_pdb(test_structure_pred, test_protein, '_pred')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 148,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnMAAAITCAYAAABsRJpUAAAYPWlDQ1BJQ0MgUHJvZmlsZQAAWIWVeQdUFE3Tbs/ORmAJS845R4kLSM45R5Gcc44qioAKKIgKCIgICIgKChJUBAETgiQRVBCJKkFFBBQT/wDq+/7fd+695/Y5PfNsdXV1dXVXV9cOAOzyHuHhwShaAEJCoyOtDbR5HJ2ceXCzAAXoASXAA3YPr6hwLUtLU4CUP+//XdZHALT1fiq5Jeu/2/+vhc7bJ8oLAMgSwZ7eUV4hCL4BAFrRKzwyGgDMEkLnj4sORzAW0RIwRCIKIlhgC/vtYPIW9tzBpts8ttY6CHYHAE/l4RHpBwD1ll48sV5+iBzqLKSNFOodEIqwliJY3cvfwxsAtkmERyIkJAzB7FQIFvH8lxy//yXT869MDw+/v3hnLtsFrxsQFR7skfD/aY7/dwkJjvkzBj9SqfwjDa235rxlt6Awky2M6A49CvU0t0AwCcHDAd7b/Fv4jX+Mod1v/q9eUTqIzQATACgqbw9dEwRzIJgvNNjc9Ddd3TdA3wjBiO1RtgHRRrY7fVHekWHWv+Wj4n2i9Gz+YI/I7bG2eDJiguy0fsss8fcx+iPzVqK/rcOOnqiB2AB7cwRTI3g8KsjG5DfPQqK/jvkfnsgY6y2dkTWHgW+kvvUODywQEvVnXrCKf4CR+W9sGu1va7jTF3b18tjWjQXBgT5RjqZ/9PT20dXbmRec4hNq91t/ODc8Wtv6N39FeLDlb3641SfYYIvOh+C+qFibP32Xo5HNtjNfNAiPtrTd0Q3NEOhhbLmjA1oMmAIdoAt4QAxSPUEYCAQBfUvNS8ivnRZ94AEigR/wAZK/KX96OGy3hCJPG5AI3iPIB0T97ae93eoDYhH6z7/Unack8N1ujd3uEQTeIDgEmIBg5HfMdq/Qv6PZg1mEEvBfo3shugYjdavtv2g8NH9oWD2sLtYQq48VRbOh1dGqaFPkqYlUWTQZrfxHr3/4MW8wg5hpzDPMJOaFW0BK5H9ozgPMwCSio/7v2Xn+e3ZoIUSqAlobrYbIR2SjmdBsQBItj4ykhdZAxlZAqP/WNebvjP+x5W9ZBBkCisBM0CSI/KcG1GLUCn+lbFnq37bY0cvzr7V0/rb85zx0/mU/b+Rt8p+c8FG4AX4Id8DdcCvcDHjgdrgF7oXvbOG/e2N2e2/8Gc16W58gRE7Af43n8XvMLatFyVyWmZf58bsNRPvER285i05YeEJkgJ9/NI8Wclr78BiFeklJ8MjKyMoAsHX27xwtn623z3SIqf8fWuQ6AKpPEeLQPzTXYgDq8wGg+foPTRAZjS4PgA5Pr5jI2B0aeuuBARSABvEUVsCFnF0iyIxkgSJQBZpADxgDC2ALnIArYmd/ZJ9GgjiwDxwC6SAT5IAzoBCcB+WgGlwF9aAZtIIO8AD0gAHwDIwhe2UOLIJlsA6+QxCEg4gQPcQKcUOCkDgkC5EhdUgPMoWsISfIHfKDQqEYaB90GMqEcqFC6AJ0CboO3YQ6oG5oEHoBTUHz0Ar0DQWjqFAMKE6UEEoaRUZpoUxQtqi9KD9UBCoRlYo6gSpAlaGuoJpQHage1DPUJGoRtQYDmBJmgnlhSZgM68AWsDPsC0fCB+AMOA8ug2vhW8hKP4Un4SV4A41F06N50JLIfjVE26G90BHoA+gsdCG6Gt2Evod+ip5CL6N/YYgYDow4RgVjhHHE+GHiMOmYPEwlphFzH/GdOcw6FotlwgpjlRDfc8IGYpOwWdhz2DrsXewgdga7hsPhWHHiODWcBc4DF41Lx53FXcG144Zwc7iveEo8N14Wr493xofiU/B5+Bp8G34I/xb/nUBLECSoECwI3oQEQjahgnCL0E+YI3ynoKMQplCjsKUIpDhEUUBRS3GfYpziMyUlJR+lMqUVZQDlQcoCymuUjyinKDeoSFRiVDpULlQxVCeoqqjuUr2g+kwkEoWImkRnYjTxBPESsYs4QfxKTU8tRW1E7U2dTF1E3UQ9RP2BhkAjSKNF40qTSJNH00DTT7NES6AVotWh9aA9QFtEe5N2lHaNjp5uF50FXQhdFl0NXTfdOxKOJETSI3mTUknlpC7SDD1Mz0+vQ+9Ff5i+gv4+/RwDlkGYwYghkCGT4SpDH8MyI4lRntGeMZ6xiPEO4yQTzCTEZMQUzJTNVM80wvSNmZNZi9mH+RhzLfMQ8xcWdhZNFh+WDJY6lmcs31h5WPVYg1hPsjazvmJDs4mxWbHFsZWw3WdbYmdgV2X3Ys9gr2d/yYHiEOOw5kjiKOfo5Vjj5OI04AznPMvZxbnExcSlyRXIdZqrjWuem55bnTuA+zR3O/cCDyOPFk8wTwHPPZ5lXg5eQ94Y3gu8fbzf+YT57PhS+Or4XvFT8JP5fflP83fyLwtwC5gJ7BO4LPBSkCBIFvQXzBd8KPhFSFjIQeiIULPQO2EWYSPhROHLwuMiRBENkQiRMpFhUawoWTRI9JzogBhKTEHMX6xIrF8cJa4oHiB+TnxQAiOhLBEqUSYxKkklqSUZK3lZckqKScpUKkWqWeqDtIC0s/RJ6YfSv2QUZIJlKmTGdpF2Ge9K2XVr14qsmKyXbJHssBxRTl8uWa5F7pO8uLyPfIn8cwV6BTOFIwqdCj8VlRQjFWsV55UElNyVipVGyQxkS3IW+ZEyRllbOVm5VXlDRVElWqVe5aOqpGqQao3qu93Cu312V+yeUeNT81C7oDapzqPurl6qPqnBq+GhUaYxrcmv6a1ZqflWS1QrUOuK1gdtGe1I7UbtLzoqOvt17urCuga6Gbp9eiQ9O71CvQl9Pn0//cv6ywYKBkkGdw0xhiaGJw1HjTiNvIwuGS0bKxnvN75nQmViY1JoMm0qZhppessMZWZsdsps3FzQPNS82QJYGFmcsnhlKWwZYXnbCmtlaVVk9cZ6l/U+64c29DZuNjU267battm2Y3YidjF2nfY09i72l+y/OOg65DpMOko77nfscWJzCnBqccY52ztXOq/t0dtzZs+ci4JLusvIXuG98Xu7Xdlcg13vuNG4ebg1uGPcHdxr3H94WHiUeax5GnkWey576Xjley16a3qf9p73UfPJ9Xnrq+ab6/vOT83vlN+8v4Z/nv9SgE5AYcCnQMPA84FfgiyCqoI2gx2C60LwIe4hN0NJoUGh98K4wuLDBsPFw9PDJyNUIs5ELEeaRFZGQVF7o1qiGZBLdm+MSExazFSsemxR7Nc4+7iGeLr40PjeBLGEYwlvE/UTLyahk7ySOvfx7ju0b2q/1v4LB6ADngc6k/mTU5PnDhocrD5EcSjo0JMUmZTclNXDDodvpXKmHkydSTNIu5xOnR6ZPnpE9cj5o+ijAUf7jskdO3vsV4Z3xuNMmcy8zB9ZXlmPj+86XnB884Tvib5sxeySHGxOaM7ISY2T1bl0uYm5M6fMTjWd5jmdcXr1jNuZ7jz5vPP5FPkx+ZMFpgUtZwXO5pz9Uehf+KxIu6iumKP4WPGXc97nhko0S2rPc57PPP+tNKD0+QWDC01lQmV55djy2PI3FfYVDy+SL16qZKvMrPxZFVo1WW1dfe+S0qVLNRw12ZdRl2Muz19xuTJwVfdqS61k7YU6prrMa+BazLWF6+7XR+pN6jsbyA21NwRvFDfSN2Y0QU0JTcvN/s2TLU4tgzeNb3beUr3VeFvqdlUrb2vRHcY72W0Ubaltm+2J7Wt3w+8udfh1zHS6dY51OXYN37O613ff5P6jB/oPuh5qPWx/pPaotVul++Zj8uPmHsWepl6F3sYnCk8a+xT7mvqV+lsGlAduDe4ebBvSGOp4qvv0wbDRcM8z82eDI3Yjz0ddRiefez9/9yL4xaeXsS+/jx0cx4xnvKJ9lTfBMVH2WvR13aTi5J0p3aneaZvpsRmvmcXZqNkfc6lviG/y3nK/vfRO9l3rvP78wMKehbnF8MXvS+nv6d4XfxD5cOOj5sfeZcfluU+RnzZXsj6zfq5alV/tXLNcm1gPWf/+JeMr69fqDfLGw28O395+j/uB+1HwU/TnrV8mv8Y3QzY3wz0iPbavAjBSUb6+AKxUAUB0AoB+AACKPTu52e8CI5cPFPIWB/cgUSgWmkAi8CWYBy5C86OvYDQx49gsnBESw+YI7RRXKa9QNRK7qF/RYunkSGH0jQw/mPSZz7Gss1myX+bEcrlyN/AS+Xz4bwhihByFy0QWxMji+yTapYC0jkzari45WF5HIVWxVWlVWVzFWTVn9z21dQ1hTQetdO16nXE9tL6ogZGhr1Gy8RmTy6Z3zPrMxy0+WFFZy9rY2cbbFdrfdnjp+M2Zc89uF6e90a45bjXuXR7jnp+9KX0EfJX9jP3tAtwDA4PCgxNDDoYeDjsSfjQiLTI1al90VExgrHucdbxOglwiS+KnpHv78veHHtBP5j0IDs4c6k6pP1yaejItLT3hSNTR0GNBGWGZp7IWTqhkH80ZymU55XT67JmhfFyB8lnfwhNFt4onSuDzwqXmF2LLiss7KmYq8VXi1eaXwmtyL9df6bu6VEe4JnRds35PQ8yN7MZLTQ+ap1s2b7HdVmg1u+PRFt2edjev42Jnbdetew/uDz949XDu0fvuucfPe+731j8p7DvQ7zqgOsg4+HGo6+nZ4dBnmiOkkdnR2udRL+RfrL6sG/MdZx/vf3VoQnZi9nXepMkUPHV7OnZGaRbMPpnLf+P+VuTtx3f18xELUgsLi2VLTu+J79s+hH/k/zi+fP5TwIrKZ9Ln1dXptbH16S9rGwzfNL5H/bj2c2VTcHMTWX9OcBiigxygZhQXKhY1CZvCHcjNvx/jhUVha3G+eGH8MqGPopGymqqUWE7dQPOEdpXESm/IkMB4nWmeRYTVk62M/SUnM5ct9xGeO7yf+AUFLASThCqEe0Tei9GK75KwkQyXOi59VebRrknZr/I0CnyKKkpmZC/laJXDqqd2l6nVqrdotGt2ad3X7kLiSqteo/4VgzLDYqNy4+sm7aaPzUbMpywWLVetgQ2lLcmOzZ7PQdhRyknOmbxH3UVvr6GrgZumO9lDxlPYi9ubyYfoi/bd8PvoPxvwPLA3qCO4OaQmtCQsOzw+Qj+SGDkcVRIdHEOOxcW+jKuLT0/Ym6iYRJe0tO/x/poDx5L9D9odckjxOBySGpuWnH7kyKmjJceqMq5ltmY9PD544lX2u5zPueAU7WneM7J5Wvk2Bb5nYwvTivKKK8/dKGk/31s6cmGqbL78Y8VGJUWVaLXppYiawssdVxZqaevUrgVez69/0PClUaTJpTm7pePm6m2eVp073m2p7cV36zo6Onu6+u4NIKdT28Prj8q6sx8n9fj12j3R7pPoZ+jfGHgx2DiU8zRoWPcZ57OvI09H65/nvoh+6TymMy79in2CYuLb66XJyaln0z0z92c75tretL1tfXdnvm2hfbFr6cn7uY/YZflPkSutq0xrh9d/fk37xvK98afDr1/b628PMUA+iPfLo9JQb2F9+AqaE30CQ4k5hiVhK3DquAl8OoFMWKdoojxIZUOUpCZSr9BM0/bTdZE66J8wvGL8yIxmYWEVYdNkt+bw4YzjOsJ9hqeCt4Gvnb9b4Knga6F54WWRr2JAHC+Bl9iU/CT1WnpA5u6uOtlzcsfkYxRcFfWVxMk05I/Kgyq1qsd2e6tpqLOqL2t0a5ZrJWu76Wjocumh9Gb1HxrUGB43ijS2M1E15TQDZtPmnRbllqlWvtbmNqq2AnZUdh/t+xxqHFOdHJ3FnH/s6XUp2hvgquJG6fbK/bpHhqePl5jXnPc5HydfNt/XfjX+CQFmgYJBUNCr4NshZ0Ojw8zDhcN/RvRE5kTZRDNHv4wpjt0bxxM3HV+e4JUomPgmqXKf337h/e8O1CRHHTQ/JJNCl7J2+GVqW1oZsk+Cj1oek81gyFjPHMm6cfzkibBsqxyFk1y5lLnfTr0/PX1mNG84f7jg2dkXhZNF88Vr5zbPE0o5LmiUhZafq+irhKrkq/0uFdV0X165ylSrWGd5zft6dP2hhhM3yhvbmkaal26CW6TbfK3yd4zaPNsP3a3sGO6iuGdw//iDkUeU3QqP3XqyelufLPeLDngMlg5NDHM9cxkpHn35guWl49iF8fUJp9cDUy4z+Nnnb4bnCYvRH0jLbz/PfOH8Fvbz9db67/xHt1WwigBcpEM2BJKDml8GoDQMyTNNAaC1A8CSCICtMkDFdAIUVS+Asnr/xg8UICK5piwwQrL1RHAayR4fgWnwA2KG5CALKAg6Cl2EOqFJaBPFjVJHuaEOIlndfdQ8TA3Lwy5wKnwVHkXD6F1oN/QJdDt6BSOEccacxHRjYaw6NhHbjF3HKeHicbdxv/B6+OP4UQIfIQKJSDQU7hQ3KAmU7pQtVPRUYVR9RGliLnGD2pO6j0aNppaWj7aAjkR3goQnJZPW6MPoFxj8GN4w+jMuMoUzrTEfYKFgKWAVZr3JZs42y76fg4XjBqc15ypXEbcB9xpPJe8ePlq+bv4jAvqCFIJPhc4Jh4noinKIfhF7Ln5HolLyglSddKfM0K5Z2c/ykAKVIrMSF1kQiWxyqkq7d6tpq+toiGgsabZopWnb6Yjo/NJ9qdeiX2BwwDDAyN7YyETLVN2MbK5moWVpaGVl7WjjaRtml2x/yqHK8Y7TqPOKC+1eGVdbt/3uVR7DXihveZ8g3wt+YwEsgXZBucFDofRhDuElEe+ilKNzYubjDOOrEqmT9u9bOOCc3H1IO6UtVTlt6EjcMdGM11llJyJyzHIVTvPl8RSwF/IX7yrRLQ0tu34RrvK7NHcltA51vfSGWlP/Ta/b79ts79Z3cd3PfkT1+OwTtf4PQ9eepT0PGXOZkJ2cnomZ+/TOeiF/qePD0+W+lVur+ev+X6U3lr9f/em3fX7AgAbwA1VgC8JABqgEXeA1svqsEBmyh2Kg01ADNAytoZhRKkhun4KqQvUhWTwXbARHw6VwP7yJlkEy83x0HwaL3DmSMDcxG1gV7H5sBw6Ps8IV4ubw8vhU/AhBjHCI8JxCluI4xSKlKWUtkv0mUM0QLYjt1LLU1TR8NCW0nLSldEJ0dSRZUj29PP1NBk2GbkY7xhmmKGaYOZ9FmuURqxcbColVeuwLHCc5lTnfcBVwW/FQ8TzmzeQz46fnHxOoFIwR0hNmFf4k8li0XOywuJeEkSRZylQ6TCZ313XZEbmvCiyKykou5GTlCpVu1Q9qzOraGns1PbS8tH11QnTj9dL0cwxKDK8bPTQeM1kxI5qLWOhZ+lgdta6y6bZdtKd1UHF0dzrm3LJnfi+7q6XbUfeHnlgvE+8cnzE/Cf+kgJ4gbLBWSGzo9bA3EbyRzlFF0aOxdHGW8ScSniRR7TPbf/zAk4OkQ44pJYcX03TTK48SjoVnzGV5Hp/ODj2Jz6087ZBHk99/Nr8o4Jz2edbST2WDFbcqr1Rfq2m/8qx2+Tpjg3yjY3PczTO3r97pbO/veN31/v73R5jHtL3sfYIDYkNSw3Ij8s/VX2qPG01YTzpP284qvSG9nZg/s6i9NPUh+uPap6iV2VXLtaYvjF/DN7q/8/yI/dmzvf4QwAM2xP/NQQg4DurAEFiD2CANJKZkQTegcRQOJYus/BFUA3K3oIbV4XC4DPF4IloPnYy+jd7AkDEJmDuItxtjT2EncBK4JFwvnhsfhx8mKBAKCZsU/hRPKbUpG6hEkPsHB7GImof6Io0cTSetHe0iXTqJj3SX3pX+F8MFRh3Et08xazAvsZxjtWDDsrUjfq3OieJ8xJXJbcrDwDOJxKRs/jABZ0EjITVhsghZVFFMWVxNQl1STcpV+qzMgCwsJyVvqxCneEapnjykvKLKvttQLVG9SZNaK0R7QFdFr8aA1TDXmNYk24zJ/LyllFWHjYFtrT21Q7TjM+fde6r30rumuK17RHi+9w732fDLCGALrAqWDbkRphTeFCkXdSNGIrY0nikhI/HHvrD9E8kWBx+l7D5ckbqarnsk7+h8hnJmVtb0CXJ2ds7HXLtT984o5DUWkM8+LvIs3iwpKZW50FZuW/GhMrNa+tKLy6lXJWqHr8XV0zVUNyo03W5Rv3nztkTrhTax9p6O4C7qe3UPzB6+607uYe2t79PtHxuMeEoYrh7RGp1+cXhMeLxrwv711JT39Ois+ty5N+/eCc87LyQt5iyde1/wIfNj1LLdJ+kVzMrg5+JVlzWOtefrp78Yf/ny9eKG1caPb1Xfzb5/RrIO1Z8Tv7q31j/KV052O3xAVNoAYCY2Nz8LAYDLBeDnyc3N72Wbmz/LkUNiHIC7wTvffbZjDS0AxU/+T99f/geb/d1aF8i2NwAAAZ1pVFh0WE1MOmNvbS5hZG9iZS54bXAAAAAAADx4OnhtcG1ldGEgeG1sbnM6eD0iYWRvYmU6bnM6bWV0YS8iIHg6eG1wdGs9IlhNUCBDb3JlIDUuNC4wIj4KICAgPHJkZjpSREYgeG1sbnM6cmRmPSJodHRwOi8vd3d3LnczLm9yZy8xOTk5LzAyLzIyLXJkZi1zeW50YXgtbnMjIj4KICAgICAgPHJkZjpEZXNjcmlwdGlvbiByZGY6YWJvdXQ9IiIKICAgICAgICAgICAgeG1sbnM6ZXhpZj0iaHR0cDovL25zLmFkb2JlLmNvbS9leGlmLzEuMC8iPgogICAgICAgICA8ZXhpZjpQaXhlbFhEaW1lbnNpb24+NjI3PC9leGlmOlBpeGVsWERpbWVuc2lvbj4KICAgICAgICAgPGV4aWY6UGl4ZWxZRGltZW5zaW9uPjUzMTwvZXhpZjpQaXhlbFlEaW1lbnNpb24+CiAgICAgIDwvcmRmOkRlc2NyaXB0aW9uPgogICA8L3JkZjpSREY+CjwveDp4bXBtZXRhPgrez1ReAABAAElEQVR4Aey9B4BnRZnu/XYO093Tk4cZJpGGIGJOCKiI7roYQHAFw+oGdYXVVXfFb1UYA+515a7srquiV9Sra0KvAXOOKAgiSIaByTl2zv09v/dUnTn9n+6Z7p7uZnqm6t/VdUKdCu+pc+o5b6oyMxtUTCFRIFEgUSBRYJwUqDm+xpovbLbGZzVaRVOFldWWWXlVuZVVl1lZlaLSipoKq62vtZmNM22ufnP0a9avWr9e/Vr02xt+rf2t1tHRYd3d3dbb1Wt9nX1WXl9u5XVZrKqrsgb9KGe2fvP0m68f2/X6DejXqt8O/bbpt12/XfpxrEs/6uvv7reB3gEb7Bm0gW5d0aXYOmA963vsofMfGpYSNSfUeBsqZlVk7anN2lPsp/c39Dlut/+m3cpqRAfFipkVVtEoGpGnMotWafn2kGMV4XyFzhe3y8vMdKxihtoxQ20ItIHua167xlp/0jps+0d7sO6MOu9n++/aR3tJypco8KhSQI+Q0NxVV1nZe94zIQ2ZyLImpEFTXAj9Hy6Mhb6xjLFcM1ydk3Estq207Klq61TUH+uYqj6V0vLR3o/9j+0YKx3i9WO9LtY3lpS6SuuJ9cdySs/H46TDXV88P5rtWMbe7+y1pnOb/BJBELNybSrxyFF9Ng8OCjgNCjCV9Tio6rRO69evT78e/QBZbPcP9HvewYFB69nd44DFywtlevkqkuvb9AMQxl+VVVmNfo36DepH+ZQby2cfsDdQOWBlA2U2WDGYAynqAEwtet8i2/TuTbR6SOh+qNvqTq8zXW5lZeqc/ugT5ThbANbAMLHh7AZr+3Wb02SgTfUKmAHqDhgohxBTNkUP6qVfnvZqK8YqZewzW/aJZXbX8Xf5pcP9i/druHPFY7QxhUSB6UIBB3OPRmNH+0A9Gm071DoPNHnEsg/Uf67n/OEaRtO/yWz7ZNc/2fQ/0L2PdBtNnph3ItPh6h3u2IHqnGz6xbqHa9doj1EGeScydN3TZVs+tMUWrVq0r9gSPADwAaj1VGRgDuAFuOLXrR+Ay389+q/Yvr7duU5lcKIikANEKZBPPC4xtYb+ODZTP8qeoR/cP8qGI8c1DhapsUKAESAHaAFXBdAEmKucdYCpQfkG+wWiAFaO5rQPoBtUOQJ5xC0Nb7Bjuq7L9ykbDiB9GCwXoAXQiTMHF3O4sHb7a23Zwk8rcygb0FkW6su6nwHJCOT61B7Fsv6Dg8Q4Pkd6j9SeXOtAse03Ap8pJApMEwrwenhUwkgP0qPSmEeh0qO9/48CyadVlWl8TO7tGg70TUSNiPc2X73ZgU4ENg6SACUCP/39Am0Snbb1t9lO/Tbpt1a/dfpt0G9zx2bbtWuXtbe0W8sDLc4lc6AlzOOALgAZACGgDJDWoR/cOUS0iFIRrbINeANs1enXpB8AD9FsrX5w8YCA5ZUSBRc5UGon+Ayx6UgBICcs6OAp76MAHP3zKGC3YO/H9u2H4y0/anFAB+hCvDvQoSjxbh6oO8Slc653IEh5xTrYjse8LkBcBHSklN0+YLNeNisvdjwbHX/sGM9l6ZpEgUeNAsN+fpV+sU70xBLLH6nceD5SpTTfgc5zjvzFPGO5njqL17Jfej3HDiXE8sdbbrw+tmG85cTrJzo9UPs4R3uLeSay/bH82KfSfY4X62Z/LPWXlle6f7DyY90xHa7+eG6kdsXzXEso5uMc+8U8xfPZFeP/f6jlx+uLLRjuWPH8cNsjXTOavo507XD1DHeM62MYrr69T32L2XdjDrPHXPLVnCN163+eb0/+h+9YX2+fdZR3WHlZuf36mufaM97yQ+vrEzzr6bM/XPeifRdr6/RXfW0IkBvoF6IR1uqvkvi0rFfMruwHcPvkqsX2jlW77O2r9oGRz686wcWuADmA36dWLRlS/hPfcaNz1u68/sL8eHEMlfax82VX5PnYmH3Xf2YgDFymuG3uG/38wraPDwFiiz+w2DZ0/60133Kt7T7jzZ6Hf4t6P5EBygDk1u35az+3dO71+0S5Qnn07+GHX23Hnfh/bfX9r8qvP/GJ/2OD1RmQA2je+Rn14xSd1m2K/Sjtw0jHKbTrvq687LSRKDBdKLAfmBvuRTfcsUPpYHyQhitjuLqKx4rb8frSYwfaLz1HGcVjxe2Ryo/HR0opI4bSlwjHD9T/eN1I6aG2r9i2Yh3DtbN4vrhdLKP0uoO1L/a9eN1w1xTrK90+UP2leYfbL9bN+bHWP1yZxWMHKn+4/hevZTvmKT3O/nBtLT12sP3hyh3LsckufyxtOVjeiW7rcOWVtiHe/5oVNbb0Y0vtgS9eao+59KvCOaAds95O6cWVS7mrEDpaOlx0ecdnLrDTL/ma9W4VSAuK/Xd97iI743VfdwDnRcAVk8hxoGzAAR2iU4AOv5evus++tOpku2JVp3Pi4MZdtuohu27VMQ7orl3VbH+3aqNzBTGG4Hfbqhfa4y7/hrfm1Bd/xfq29w0ZZ6V9pn/ozWHEQBv3PuMtNvs+AboA5uZv+ahtWyhAF/Zj6hw11bLnKf9ozbdda+XBeGLHcZfb4oFPep/g+C2Z8Slb3/43GffPWXV0PROz0siHH8wAHSJbuIqrb3uVnXTmFzz/3TdcbKe/8mtWs7TGbqu5bUg/vIPj/Fd7aq0hRk8hUeBwpUAlD+rhHuLLMbbzYG0uzR+vI+VcvD7mi2nMF8/H/bGmpeWN9fqD5T+U9k1E2yaijGIfx1reWPMX62L7UOhXWtZw+5Nd/nB1Fo8dKn2KZQ23PdnlD1fnWI/FezDZbaX8WFds45D932ZHu+7uMnSxCFiRCptoIPqu/+vvlP6aRIqnXXyD3f3Fi/3YqS/5inP0Hvua/5dxqASOAHF+rYpwcEg5+iQH7BTDbtuNVpwbPlyzqkFZOlVdViHcOzNiIWQ40wHYg89/0LlahbNDNof0L55Re6LeXQRtnhYAHfpshHhPml/UbAMVWcX9bf1W0VCRt5F8cNkcxIV2xz6uWPZZB25FgId4lRiv693Z69sT8Q/L1s47OieiqFRGosCkUaByuJfRpNU2QQXHl8F4i4vXx5dS3I/lle7H44dLeri379GkE7ThvhbTYnviudJjxf1D2Z7s8g+lbYfjtfEZHGvbRrq/lDPcPSiWX1rnwfIXrz3Y9nBlcWz1hauzS6+6yDZesdFw8VG1uMrW7cxEij2beqx/rxCR8MjKs7/oHK97v/GXfs1jX/v/HGQBjnIL0gDqBvoEhoSRot5bBDy4OQHsRb069OQQxhLesmqvbQ6/jr4O6+sQJ649A0L3PulezzPSv2L/ADm4Bmk9722ut4bhROTC+fUFIOc6dnROWRZfvdg2vnOj7fnWHmt+SXOWVS5RMIgory7fB+icHEMBHZmdDjIIyY0uOChGJ+DvlL/4st37xYxudtUFOXAkSzEU+1E8Xro94ykzrP2W5J6klC5p//CjQPZ0H37tGtIiHrwDhYOdL15bzMuEECeFYp7S7eI1pecOh/3DvX2HA41GasNk02405Y8mz0jtn27H4/NGn4nsT2Q4WJnxmY8pdR9KGw5270rPU9eux7zJNte+3oFcrPuBZz9g/S399tAfX+mAB9x12kU32Omv+Jrd+ekLc6V/wFKR4wWAgSOFYUUEbvQJgwgA3Z7wg1OHSJWAOxPO4a4EMHj7v7/YgZCfHMM/uFUAOQKWqs4doz0YLXBMqUeOKQLo/DjbIQx0Bs5cq9ylCNB5viCBjty2/NosqwrWxUWgqN2Y997v/KWd9lLRTXqGK8/5YqxmXOmMpycgNy7CpYseFQrspzPHy2W4F9BYWld6PdfGl1bxXNyO52K+eDzWOZbz8ZqR0oP172DnRyp3tMeLfYvbxf7FY5QXt4vnJ7t9o+3HSPmmon2RLsU2DEej4rGYt7R9pfvFsuN2sZzS/HE/5on7I9XH8eHyxPyxTvbjdiybY6XXxmOkExEOtfzYZtoSt4vt53jpPsfGE2JbS8uL9RbLLM1TPDeW7VhnvGas+1w3UlvguqHM/+AvXhGL99QNIHDNAQiCC4eftcCZc1Gjjkd9PBd16ioAmyCUi1oBefidw1XJ61ftcf05s4V5HY+7TPpy++wl/PiIbSyZH2L/B3qErjSb7DntH/Nyc0OIlo9n7eWM8tCPRe+VH7srN1nLD1rMnqZjXWqrOJNbZ/+9drIiMJYgLGn4VHZ9AHP70UF53KJVoPbk537J7vvay/06/3fV/vRmfIzUv3hhwzPkF++m5Jok0iOlhz8F9GqIj87h39jUwkSBRIHpTYHhJtLhjk3vXo7c+uH6yrFl8z+drYwgv2vljWFFAxkIIHp0nTgp+vvKCLgRESBCrOquSnBZErZJcTVSUZH5ngO84YIEIMcPVyTt+sGhw6qVlSV81Qe5CLlz8Z0jN3oUZxqe2TBkFQZWZMhXeFAfXAxMW1nxgT6I80j7N63KHBPP/IuZfn1Fs9o+tzLLh9g2XhOvi32njOK28qFz9+Btr7BTX/gVK28ot7rj6uzW6lv9o+Jg4C12sfHcRneZ0v7bJFqNNEnp9KCAnogE5qbHrUqtTBQ4MigAeCmG0U60xWum83Zp/4+t+T8GiPFlrgBzWLFq2a58iSzAEMCmBLw4iAPUAHgEjHxfaQR0OA8G0MVfFMPim663R0BOPt72fnevVcypcAX//j39VrVIAHBZtXX+qdM2vmPjqMk848kzMufGdao/WKlGQDdiu5l9Qmy/Sc6RBcC4pnK+/N8BBgFwpSAOOkSAF/se8kE3aHj/zy8Z0u7Rji+WYsP3XdKRG0K+tDNNKMCjFJja06TFqZmJAokCiQJHEAUW/+viDMwJyEV3Hw7k4rqugLkA6BzUAWYEZJzDFYDccICuvELgRj84coRo3br+XeutcmGlVS2ocgC17dptDsB8PdkagSjWUFXdDWc1WM/anlGDuhlPFaALa8eWRVAngOXtLAWiAp0RyHnjtNvxhw7nrjl3brYu4JoI6EKaA7m4H8vVfgRzTkNxN+nfH2f90Ys/0L+m5zdlDozlbBi9RZYsSyFRYLpRQI9CCokCiQKJAokCjxYFXAcsVI6eG8r8bniKeRqYB+Cj7aKeHNnJK9iVpWG90lCMGzZg7TlYmenNebnSVVt/5XqrXqTVHxZUWs1xNbb9v7f70loqJFunVXnK+wXApKPX9ss2B0gn/ewkw0DjYKH95nYD0BGwnI16fM5lo51qj9ejZb9YRsyDukZAD7D+sfW+3bOuxwZmDLhDZdrtgXyRFhyiqLiEWJbDj8XjnvaGa+P5khTR7mC36CMA56tRCMwlIFdCpLQ7bSiQwNy0uVWpoYkCiQJHGgXmXTYvs/IMlp7uYgOgA5BDrwyQprVMHchomzQHdZyTIYTnEXqJwM5pFMBOtCxd96Z1zv2rOqbKKuaKXyf9MsShbb8TYBM3jVDWpxIUsTotHxAYG5DFgcrZe+NeX7yelRG2/vtWzzvSPwd0TxOgUzGsbjEwmFmo4nIEzpmDM5Xp1qh0hz4pFEEbol7qBeT6+Zi/kOZAjmMhRuvZuI8YGcC29zt7vQ7+4QrFLV8F9Fj2y0GcLGoRK6eQKDCdKZDA3HS+e6ntiQKJAtObAuAlXHgIuHiMXLkAdBy4gbXAPCFG8EbHI4ArTTkXAdGGf9pgFbMkbp1T6QvbA6wQpbbf1p5ZgQoQskQYTn3dsS9Wo4pw5+AKDtYMWveabqteXm2L3i8r1HdlRgtexzD/2n+XGQ80PrvRy4DTR/mAqCh+9fIBo468VEiG6YaWJr+/nEfs6tkE2py7R9vE3YvHSB3c4ZQYUBxo6kAwlNt8gUAcAE7AzS1fxZHDnQpgrvPuBOSGEj7tTUcKJDA3He9aanOiQKLAtKfAzBdKzAd4Cw5vEfk5Fw6OHCAKjlwJkIugJwKV4ThzDuwkglz39xk3DjAEVwydONfFQycOMCexqFvLCit5PYAgAE7gyGFIEblYtBEDiQrp9S345wW29UMH5tBxc1p/1mqN58ioIALFwPmjn7QDUBn7M+LNFAl6t4XVHLRNqF2plTTU1gjaHBgKeDq4A7wpbrl6SwYepWs48/yZ+0Ac/vAE6ogdt5X4Y6HwFBIFpikFEpibpjcuNTtRIFFgmlMAQCJOkuvMAegAc4hYwSXBj5yDHQBKEdTRbY55knG3HMAJzcR0/ZvWZ9axrJ+KixMMBODIYVShWCkDg55HtKYrhhVYhVI+2Crq50WQSRrbCNgTB7HusXU27/XzbPt1270NB/rX+ovMUTGWol4X9fcqdpf5Ul5uyMEx2hD65KCMQlW1KOJpfkyHO+8SJ02HPXAaJ8VFcBfa65zOANwcMLOt/iB+TctzBfql5IihQAJzR8ytTB1JFEgUmE4UyMEGAAOnu3DIFF3XrFwGAOVCVwFk5UAndjACH+0LCjnoien6f8iAHK4+4MDlVqEAN4CTUuru2SgwF8BbdAHi1rKaFUgRXTpnTu3L9dEElFipofnCZuvXqg27vrArtuiAaevPC6AugjfqwSpXwM6tVAF06r+3KYA1F6tG4BZrYD/E/HwAmhF4OsczgjqBOPzp4ZS4+8FkqRrJmNIjiwIJzB1Z9zP1JlEgUWC6UACwEbhFUcQKZy6KV4dw52KfAHHEYtB+1KPb8Gbpx+GzTgYODtyCCw/nigUuXARLuO7o361GBPDmwEr5833lpy6An3O2AHVsCzj1buq1hW9fOGowF5sbQV3D2Q0ZaAO8AegikCPVX5FL6PsRwFGQtnMQx/EI5EpSN25ok5GDgFyyUoVwKRzJFEhg7ki+u6lviQKJAoctBZwzB0BCT02iP+fCwZ2DIYclaFngzgFuFKKeXLbHAXCN0IzS1S9ebTUn1Lihg+vHRRAXU4BZKNvrUXXov2HRmXPjiqAK4Beupb4hnC7arIjhwMpfrrT7z74/b9JoN3B7EgNroOaALnAiI8eQvu3X73ghKcCO9gRxKmlc1WLpR5fag897sJg7bScKHLEUSGDuiL21qWOJAokChzMFHIRgyYquXJWiDB4iZ24Idy50wjl1JR0S5HIwV72iOlsGjJUjIpcriFAdvCkbWYux4cwG23Pjniy/QFR+HaAugkBSygM0AZgwICDSXsXerb2G0+ON/9/oV4so6YKVLp1V/6T6DMAB7EKbHdCFC3OuHJw46BfbpXTpx5daZXOlVS+tto3vHH+bStuY9hMFDncKJDB3uN+h1L5EgUSBI5ICgDh0vOAkuY4aIlbFAenLDeHOiUsHqMEJL854I8CJ6YZ3SLSqZazc0CECuULqYAxgpJCDIlUx6+JZtvd78sFGkeQPKdsx5tw88FwATej3IcL1fR3DUfDsV862XZ8fnf5c1pKR/3fc2mEsD0afqhZrlQpZ4pZXCaTCLQzRRcGRe6i0XCtX+Jquod/Pnvdsu/aT145cSTqTKHCEUSA84kdYr1J3EgUSBRIFDnMKoNMVRYSIWWN0Tp2AHvtsexo4YgO9wU8awErixfX/uN7XMfW1XCOAgyMXDQmiThrHFJyrha6eOFr9bf028wUzMy5cAHAO3qI4VpcIPmXgMdDS2xa5cyHt29lni65aFHJMTOJ0kX4eaW7UwH6I6MkNicxkoc+IaH+27WcT05BUSqLANKFAAnPT5EZNp2biXBT9HfxB1Z66L3IshUSBRIGMAqw64NwtdL66FBG3RtAWgFx+LJ4D3IkzxnVr/25txpErilaHA3S85YnCRREYkRLnvGZObtHqnLmwyoTODg0ZFvRjQwAmoFIR/bkVn1sx9JpD2Ou4XT7g5K7FcBw8EoCLYlYBU+ckAljVT6x4d31xYriEh9CFdGmiwJRSIIlZp5TcR35ldafV5e4PXLGaSaAwEVQt1FI9ITAJIGI63H0+Re5FbuUnPaLRumSIfU1posBwFHDOEz7m0JcDsAUxK25JOOZGEBhDRBErheh54hxrnvq6pxHAkQrMuPFA5MwB4sIz6NwugGOMAkl92/rsmPccY5vfu/nAhgaFxrueGqCyWuLWHolbq4USBaxqTpzYjzXaCXBlaTHKd0tauIaRKycw6n0FmNJPos7PPm62bfjFBu2kkChw9FAggbmj515Pek9xJhr9WLluS5xc4td+AdRFgCcnCoaLBH9Z6wubNLovmPQGD1NB84ua3VM+Ojj46Mr7w1d/CJoObf6b59u2/9gWD6U0UWBcFHDOnD5qACHR11x5hYBcdFGiYeeATkglAjtAy/p3rLfKeZX7dN0Yn/wF7pTrxgFuGLbEELy+CObgAqoerFrdHx2csJLAWM+Xzorn1FwHhFyvsiLQws3JgrdpdYj/ffDVIWJRB0odvFGXQCd9dr2+InDTMc7xjDqQC/3vsR7b8/U9Byo6nUsUOOIokMDcEXdLH70O8VJ1EIRTUCkl+wsYIBcmFZ9otFucXIZs652NKIhljhCxMLm1/iRzNjoZvcKajzUrmchy7/goVYf2++QRORwxpf0hHPNucTTetznupjRRYMwUaPtVmzU9tynz7SYg5mLWAOQwhMBFCc+Ic+Yih05cu+LHUunzNeQ5K4xXGpeDsADkvA6Vd/znjrfVl6zOns14TXgeSzsVAWMEcQ624JzpY2zuX8+dMDDnYmEqB8Dp+YugzvvLOwXSiGbxvYPeYP3p9bZ21VquSiFR4KiiQAJzR9XtntzO5oAIMCRRpL9si1w5Xr7FfSaNOHEozS3tQjNZoJt1FVGwLnVfMJ6eYCGXi6ZYp3I4EFcqsorcxZgGDohPNJrsRrPw+Hjamq45eijAR0tFVYVzyfwjJvicc1FrYVkvd02iZ2iwUtyo8LHE8zOECwfIic9VfLYiKQFnCgBG1Bt4PqM4t3N1Z+ZiJLrzCHnz55VyC9EBHXkQeQpsRUCHq5JZfznLdn95t04cYqBs1eFll3Dk/ENL50hxkIzFK9avPZt7bPN70gfWIVI+XT4NKcDjmUKiwCFTAPcErlOmlysvWI8AH31RE91vFYAobhf9WMENixwxRJtEAUK4CDgX7bqra9ztq3tMnc142gxrOq/J3RxUzq+0itkS7urFj3ipvFF6R1KYdpAXRKsRlEYuY77P2pYlbSXPsf927Ljbly5MFBjslLgSQ4Ig/vTVFuCcAbowdgjbfp582neOFB9GBL3FI6DLwdcIQM7BUdBVHegUv0+gLlrNApqOedcxeVkRvMVnOefIFUCdc+eCekQEdIuunBjLVre8pX8AuRgBeArR15w/u7gukf7g257wNtv8/gTkMgql/0cbBRJn7mi745PVXyYUwJpGVOTK+SQTOVmFCSdyDnxyYNJRHDJR0EaJWRGxIroZT6g9pdZBWsWM7KvdfXBFoBgBGWkAng4yI9gMIDS2KaZ5O2ObdUBTq3MPxtPGdE2iABTo29WX6WlW6mNBY88dBmuMRRFoXNbLOXL92UeOU45xSCAFYIVxmaecI/AIEQWEAFxeB9az4vq54YXSaGDBh9SCt0rv7T+l91YEbWGba3PAqGP+fFJuBHRKx/vM0tQhoZQzx7tlUJ0M/XHOegByPO9Xf+Fq2/mZnUOKSDuJAkcLBXhEU0gUOGQKOCgK3LY4CUQQVARMETQ54INLB5jiugLAwkHo7q9lYpp4DhcnYwlwMSpnigsH901f7WX10ovD+k96NXkKJw6RcIyFNnh7Yn9iOwPwo03lmnjh2FVUi8NXU2HLP7Z8LM1LeRMFcgp0r+42uGQ5d06AC9Dl1q3RFUng2uXcu3i1gI2Dq7gf0wjgStMgEqV858zBnStEXKTA7QLQOXAL4C0+y8VnO4I658hRD0FYa0DroU5EcBpAhwAUXaRLPQHkuTPhYNGLqPWRVzwyEdWmMhIFpiUFEpiblrft8Gs0oIwXfZ7C3WI/pPGc7wOOmCS4JgClyNEDJOUTRgBTgCdEUbUnjx7QdT/YbfiqcqAmbkMUlfo+oC2WHQEc+8XjhbY54NS+X6MUa0PaiZ5TVW2VVdfLr96MGlv5f1cefjcmtWhaUKC/pT/zNSfQ1nRukzU8o8EBXe4wOII5gRsXww4q5U8i15wTp8fJgw5F7lUxdXAEMAoiS4ChL0Yv58VFQIfoFfWBJf+xxPr2iEXOLKGy/ZmNz7Oe2/zZpV5ifN613fySZh04xABoizH0yYGdtrGAr1pUZXWn19ncZ8+1Te/ddIiVpcsTBaY3BZKYdXrfv8Oi9SyUnb/Y4wu9kBZf8vl2YYKI1wKaAEptt7ZlILAwQTCpwWkbS8BwAjcnGFHkQA1QFoBZrNfbpGN522K9wRLXORChP3FCo50VlQJzVQJz1dWecuxp33ma/e4vfjeWZqa8RzkFll+/3EEJwKn7gW7r295nfTv6/Jg72hZ4afuNFqYXrnIgJx9zWI3u+X97Mn03ATSNav85KQPwcSAnMOQACACn44gpo9jWt3XtwID8xQ1o0EeO16DcoAwOWM/aHltyzRJru7nN2n/XnoG6yKXmYwxgFz/MioZNelZYhutQAx9etJ22eaq28+xWH1dt1cdWux5s7+Zee/AND9r267YfanXp+kSBaU0BptQUEgUOiQL+UgcABRCUp4wuQFB80bPNBBDyxm1Sj3pRw/HqulcGD+Faz0vrdA1+rNCNGUtgUtz77Wz9ybxMymYSitw5UgAebQttLG4Xj3E8ArmKColYBehq62ptZvNMW7BggS1dutQuuecSO/bfk1HEWO7T0Zh36UeW2kk/OcmV+bd+eKvt+PgOa/1Zq6+mALDrWdNj7b9ut44/ZGuV5gYQ4qit77o8A2kCeIhj81AEctqOhgIO1AoiVrhzuRgTg4h2cedihFMXuHV9uwUqZUT0+H97vPVtlW5feEb8WQpAzuvmsQ7POemMJ+kD7xADYlTnIgJCeTdIpFpzUo2vLnPJxZdYy09abMsHtyQgd4h0TpcfGRRgWi28CY6MTqVeTC0F8Nfma0PK3QeGBvFrPYIgf/EDknjZK/XjcZtJIIAqgFxldaVt/pgs0lB2BsExQkn0MucY4h9ES92PdI+6k9VLql3civ86F7ciTkVPTvXmbaWeYhupk4krpGxHIFcEc5WVlVZTW2NNTU1ZnNlk9fX1VllR6dyNj8z/yKjbmTIeHRRY+PaFDkpYGJ7nZfMHtPoC45vAeNPYdN1O9DtR8FfEkKfq2Cpr+3WbVS8TJ/jqzbb7zEa3xq6cVWmVC+RAmDEd1QZKVQYonmcvjGfS/cY7gImlweqy59iNhnimo26pypx5wkxb//H1NtAqNp6Yb/HZrWjMLMSxDnejI6V3n3y3KhlfgCOJKDX2v/6J9YZroeZzm62vo8+2f2K7td/Sbru/MgEuUMbXxHRVosBhRYGxya0Oq6anxhw2FGBiOFiksTFP3I5pOB7BEhwDjCA8cI6gFDCIuKWiWSyBMYSe9T3GerF8tkidWkXFQrNyffcAQC4/HwCdAzvAqP4or7e311paWpwLgniqr7fPqmuqnWv3+k2vt+sWXTeG1qasRyoFZl8625e8AqQwhnGPs/uru61/DzJQBYaUABNgyC1NcR7MUllw38SNg8vc8PQGNw469tZTbVfQo0PHzd2V6FoNx316ZkHfjDHqZWMJShY9Qw7kEF9KZOunw7PVP9Bv+HeMnDu2qbu8VyBP5e+5Z481PqfR6o6vs467OlxXrel5cnqscgn5B1u2e2j/9ZjzAdZ4dqN94LEfsH/507/Y5g9vtt5tvdZ1X5ftvVEc9xQSBRIFnAIJzKWBMGEU8Be5zxfhzT6GkvNrA0jySymmJDqgk1iICREHpaMOmrP2fmuvNV8UFLOZw6RE7sCupI796gTExXaFvEyQXI++Edt9/dJ36u621rZWq6kRV0G6dMTKqkp70W0vsm898VujbmrKeORRYO7r51rlnMy62rlYuMwRV67nkR4XaTqHS4Y6BDdMkH851xkLgI0PHAAW4s85r57j+dqv/LI1XnNJll/H3T8jHD5lRazqoA2cqG0+QCKIY3znunPK6zppgDqO6+eWtQHAYWELkANUFrl+HfdkxkXLPrrMzllwjn37q9+2nZ/bafMvn+9AEV228YbFH1xsDU9rsNlnz7a+gT7b88M9dvmPLncXLqwli/i55cct4y0+XZcocERSIIG5I/K2Pkqdyuai/StnconnituFnM490H5Mc5FQCYjyclQG7hNsDEtAoswNdw4/VHP/dm42wUWfVd48n8m8RQ7cOBbr9qNhn23VnwM5rArRP+Kn7c6uzkynrlyTNUYS6NUppnAEUOCWW8xOOcUqG2Rpqnvdv0kWlHfeafaCF4zYOThL1YvEpdWycXDccKFRJtFl1Nl0Dpk4Xi4iRbwaRJqoA3iIoIw0ADs4eb1bBJa6u/wY46+/rT8HW64fB4CD86Z2OpBjnPIMlgC7HMjF4+QXIPT+9YlLB5AD0EWH2VGUi4qCZg+4gj/e+mPXZV3y70vsvMXn2ffv/b7t/t7YxJ+LrxaAO6vBTjvrNFvTtcbafttmmz61ycW5+OEjAhB5jjtu6xiR3ulEosDRSoEE5o7WOz8J/ebL3516FsvWHDIskOM4gTREB0Tacf0hsJW4CX4tk1BJRN8I/1xjCqoHrgiTH5NpnPS8fsonlKbxmI4zwZGX1PsK2FPwfY6F424dqHMujlUfVv/Vas833n/NL2rOXEdo4mQtzxQeBQr85CfS2XqysbbBI4r9u3ZpDGkQPfaxZrffbvb4x+/XqBzISZyK7he6aM7dgtPL2Nbb18dI0JHzc+iPRsCE2JQhxseCAFUeqwYd1Cy1t9r6H223xhfJJ1yvOGry78a1+FZkbAP+KN/HrfYpy/ejmDVathaAnD8L9ETjnGcZLl1Zj8oo4czlXLqodyoA2NPeY9/d8l3nzM35qzl2wgdPUBcrbc+ePc5FB4wBQvt39lvdGXUeL2m8xL6t3551e/x5vv0Lt7shBuB0oEUqCwA5WaX3bux1MXPnXZ20LoVEgUSBEgokMFdCkLQ7DgoAcCKQYxKRyMZBnY7n4Chuk5JfP01bvs2+B6XonLnIKXLFmMyYhEr2h1jwhcsPlvBVX3Ncje35xh5rfqnErSWAzidYCqFOQkzZpo3aZ2IErHngPH3RsZhCh5gnb3OWe0z/0a9Cr8pBgPruyzppQsfXHj70cLmSwhRR4EtfsopnPcux/4P33Wf2i1+YbdxoNlcc3mNltUyEa/f975tdeaU3Cnc4cOR8uTgc28JxA8ARSBRdz01cOjh2DuwCkHMumESubqBDPhznFsEc26zPKnBo/fJPJ4OggQqNSRVT1qrrBALdUTZgLQA36tsPyEVQp/Hl+bieazSePS+iVxiEPNMChl4GbYSTGGMBzHn99FHlsHrF9t/IXYh2PXC58kITW6ry5DcSdyuf6P5E1n65HhrsELcTECdQCvcREOdgTrqC/Xv7Myv3UFxKEgUSBYZSIIG5ofRIe+OgAC/lxmc3ZhyECOr08o4AJ3LrHPDxstfkwCThgA7/VoW8PqmwzyQQ4kigCO4cSuFjDqqbhcBnXzI7m6w0+cQ25ZMPhcZ2KKWtnie2y0/7Cc/HBOigjokPcKcU0Lf+TespadRhzmvmuD6gi+IoQxNb795eFzcxqTMhVi2sslkv1WLmYZWMUReeMmYU+PGPTRYrEtNLTr9e9+cDHxiZMh//uNm55/qC9J3332/2v/6X2Wc/m+U/4QSz5z0v48qddJLZn/0ZN91m/v7Dfo/cKjSITaPaQF6RhggBFx57t+3NwJHuba73Vhz7yhdFrHnKWNDSXif86vH2yM/2Wt25M/0jChAFMGQcAyAjGMuBnI7nQC1uazkv8qn2DMgFQMcY9rycpz0KDurEEOeZBNA5CBVXzrnpeo7In4M6lenX0dcQ/flWuYDT6BDZdfQE7vrbBeRkJYs7lP5d2parFEAc+90PjZELT2NTSBQ4iiiQwNxRdLMns6vOPQDIAc4U/OtekwITgoM2OGt6ufvLnImDfOzzlmeuIK9vqoygCE45OZDT6TihcJxtBzy+M4Z/oRx07qJSuYtdw8TjkxETjzdHbWFi088nuqyBmdNVqiRfaLP3M4C4CObWv3lsQG7BPy8w3ExQJpMYVnv49mq/td0nS4Ac3DrAHLRrem5TUgTnPowlXH+9lZ18ss1bvNg6ZbDS29NjXU9/utkLX7h/KYC1Zz5TtC633nvuMbv22n1AjtwPPZRdI2tmOGSm/DNv/rBVzpebkIJLDx+3hfHL+IhjBD0x/KVFMOQFFvLm1+oEHLhBiViLgK5nY481vWKu7Vp+kTWt/1rGoZN/X8aj6fvKRbtw3qKBg8BW/gwWtyOA4zmIkXaE58Lbod1iCrc4Btof+1AEdDw7/pyQlXcB3EClOZAL/uzcr52AHCth+GoUOg53jv0E5CKVU5ooMDIFEpgbmTbpzFgoAIMM3Z7ImdOubwdOHK4WAERxMsj3mSx432uC8/PaxsqPl33M66lfuu96mlY1VxatG8ZmNYeenTseVlFYxOFWwScf7Xs9tIenQu0ohnxSKh5kO7Q9Tlg+WXGMSWuUYf6b52c+tdRvuBPoFnU/rOXIft/hoqZiMVW9Vdbf2m/VSyXCk/guhTFQYMUKs6c8xWbMmWPbfvpTkzKX2YknWvWZZ1rP5z9v9spXDi1s5kyzujqzdqGjr37V7JOfHHqePQAdIL6jwxpv+GerkJW1LwCPwYD013IwFK7MPyA0vBkzrDkcxanFD5d8m+vi2OSSYAThHDI9bzxzGPTsqnqtPfWsDXbz82/2jw23shb3rqJfonr5jsvbwZAhUj8pZcdjSnkWHPjFbcYxeQhKvV3a9OeBlL7zR0ogCWXGDyN/FlRfniI21hqwEbShMuFqBOLO+TFx5HCa3HlH0o9zmqZ/iQKjoEACc6MgUspycAo4Zw6F6z5NBqT6Uuelzks/Tkw+Afhh/dNkwcvdAVyY2JgQiIAUXu7xOp8cdEkewva4OHMqhEkmxtYft/qyQHkdsWxxwQje5mwja2vJMU45x4HJLE5Y2tzwtg1+6kD/FvzTAgdxlTMqrb870xECxO36gpTrRwi4Y8EtCy4aWJuy/nH11vHHZN03ArmGHhZgq16yxNp37jT7xjfMbr7Z7I1vtB6JRsvOOccGv/hFs0su2XeN8nro40vlAGH1amtYuNUqdT8cyCFahbscxlJ+pcaFgzHADKBMKc6vURdgdZMcXHEB14boz0g8BoCLH04B2PWs67E5v7jAfrTn03bxD5rtB8//gXOUy7UsVz86dcoXdS9zoFbKrYv6cRKVMo5zUBf7ENtDO0IYAuAAcSH6cbbj86A2O5AjjX2POoBwGwFzMu5xIIe+nLjSnX9KQC7SOaWJAqOhQAJzo6FSynNQCrTf3G4Nz5TLBr2knbOlK/Iv8yjiYXbSn17fSrQBR0DZHdQFMSv7rry9N8sbJzgHduTX4TwwsY0nUAZlKaL3420ulkuZVA8gJTAxeRI2sh0dpvHaiWAULkaYwOZdPs+2f2T/9SLnXTbPrQ2r5lfZ/GPn264du6xnV48hLoNr2PKDg/vPyjk+an9R1EWzUhiBAk96knPZ/IPh1lvN/uu/sowztOzUbOlOiltXIUA3ZEitXGnyCK3xrNfkAQAdqxUAyHIghy5ZaWCcEKlAYCyCGvYXf2CxrbtsXTYeUUcovZz9wjEHggEMejkad/ie2/nEczSk/8daGs+zxj0/9Lrc9YjOM8ZxixL12Xx9Vp4ByiVVZLw7EIvHYr2hbp5BH/PKThgRzPEc0FeeBYG3mPq2+ktbPGK4geEDYE5Ws3Cc0ZlLFqtO3vQvUWBMFEhgbkzkSpkPRAHX6ZGVnWn+8y97uFVMEgA1pUwEEeD5y16nmRD8fARE2mdidD9aTDK6tAjkcm4d58YbwiRFW4gsCzTjKSOsJTlSPWp73ocA4tgHmJ7/ivOtra3N7jjzDmvZ1eIWeoi66mfW24rlK7zPa9etta2PbHUQh+PYPd+SyG+0gTlZ7i6cxpoQUyihwFve4vprhh+4vVol4CMfMVuxwkFZ7275P8OVSAw/+5msK5fa4KJF1nzGGbbzhhvMLr44OztvnlmX1glG1AroGyGgwwiQcwtPOLqlY6Y4VjS+/eNBz0jkzsGJwuoVa84ctKmYfKyX1OsADpBEueTTGO7b3mf/pCXlrrnpTWZt77XWd33L7LjjrOl1p/uKDi521Vjx5bEkzvd6SCKHjjbzDHJM5UUdO69adeTt8gPZPwdzhb75+OeZj89yAcgBWr3dgNAI5gJHDpErunGAOV+XuVBH2kwUSBQYHQUSmBsdnVKuUVAgB3MCG4Naisg5W8w54sw5J05lOKDTXky9WL7gI6hT/trH1Ppi40wgRSDnE0o8xoVMMocSuJ5JTGn7bQJ0TxxmwlZfmNyGBCYwBRcdsU37A6AjvfEzN+Zra9bU19jsJbOttbXV2ve2212/vytzvaAJHBEbblLGGnBdgb885yoyYaawjwKPeYwZlqWzZpmtW2cmB7+GReratQymDJw9/PC+/GzhbkTH9srFSIX052CeefihuFtPfaosTZqyMuPxQgpXzkWYWKIC5DRehgRuT4g+xnHkG8FMBDYCWcs/sdweedUj2ZguGW7+HGgM+vOkNzb1+HOhonPAp3F8w6eWW9mrHxQolNhd4w2uYsu/3GhN73+hW77C0XVAJfDkTrcZ+yHmAC4eow0xarP0WXMgx/EA3HIgR1+LzwPjswDknCup/vsSZAHMOZDjeUgWq1A0hUSBcVEggblxkS1dNBwF0N1iQWxWPgDMedDkAJArgre47SmcAb3wozgILt0zznmGfeeG7+ybqMKkkk9ccZIhHWeIk2GcsNin/TgzRdfIJycBs3yCjpN06JZP0HHS0jH6wCS26cpN7ssOxXbEWh2NHba3Ya/71fJJSxwIRNJwUsYbypukkyVrSSZguHopFCgAkAPAwVWTpapt3+6cN7FKtWKC3FtoqTX3EVe4xHXnZBDRd+qpdvppp9mfMHa46CIHeH69LF/t+OOLV+TbOOjlPuRcuXiGcVKIEcgBnhgrrhOKM94A7NCVnP+m+bbto9t83A8BbliKAhQjkGO79BnQft1pdXaslpBbj9XtI49kwFX6gC0f/Lk1vu0c12dFpzWu9eoWt3Dp9JdHymV/mPJ11IMDuULf/FmBI8exAO7846YI4uJ2BHIYQKAnJ2OHjj8knc9A2pQkCoybAgnMjZt06cLhKID+C0DOnZoGnbMh4M1nCd77AkoAOQCTfkVAd9ttt+0DcmFiKQVy+f5wjRjtMSYshWJZKF7XnV7n4BI/Xs5VwEErE2roTz55MXFFQAeQu0piPQUmZuJkBQAEPsQcQE5WJdO1XIwb6uszzhy6cHDdsEZF5Ir+G9w5Vm3AmrUYWJZLlqmb5bakXK5KuLVuqYofOrh9AMRhgo8JFelgi/PDgRwV5q54wnjz8cNzEuJAlTLoTVy5oNLqT6/3ReSLwG0IsIMrB5iLHxfUSbmKuPJoeWGz2X+rL/QbETG6fl/7mrX+LHMy3ficRgeQLNPFqhGIOF3XrwjqQnmxXKog8MyGjSH9zMEdRAPT6ZnOuXGRMwcXkhhBnHTk2E7GOxlJ0/9EgUOlAFNlCokCE0YBlJdd3CrRUeRWFQGPv+jDS99nzLiNbIttxe7W7sw1SRHIsa3oIs+w7ZPNeFrOZBVDycQFsOu6W2texklH3AO2XUkbZW0mJCYolNjjBBXSWORkp/n6ntAshaEUwBkwgK1RTtYAYd/7XgZqAHmAG4wZzjpr6DXs3XSTW7fukDj2sdKfs7/+6yzPhg1mO3Zk1wkU7RcYizGAdQoxH+thXHs2nec4Y8jHVBxfYYzN/bu5mcoBoC1+QKjJADiPfFAIyOXgkfEbnwsdb3h6AJ1wIekvAPbqq7MWyoK39b3fy8T8rLQgrphH/LsJCOKgGn3XyC30lOd4hAh3kZiDUj0fbtBQfHaiuxH8yWGpGuvVfgJy2W1J/xMFJoICxVfRRJSXykgUyF7wUS+ISSt+nfPFrvnCv+RJ2Y+TW5jgIqDDOS5gzblmjFImrRAjJ83TcdDbOR1wNpgEmfgJsfyw3fWgAF2ciMRFwNouAjyfvApADmC3+X2bvZjJ/odbEhexymISMVUKJRQAzAFiJG50MMdp1lHlGHpk3O8VK0ouCrsYRgi4CQKave1t2cFvfjMTy8LhGuE6B2cCPD6WMXBgLIex7uM97DPucy4WjwJiRsYWaYg4ij7lc6dkHy2MUR6DAOpyDl3cR5eTP1LGso43/bn0+zDykLsUB3KImuFE/uhHmehZdGl70/XWeuKlDqwAV3mUAQLLZ6EOgBPfYUFc5CYGK9T8Q0ftd3AanhV/XuLzA2gEzIVzGBx13plcj2QDLP1PFJgYCiQwNzF0TKUUKOBgh695AboIzuLkNlJaFMsA/lhcPoK2CLTipMXExTE4Y+MKTHzoOcHl0F8sr7Q+/HehkxYnIU+ZlMLE5JPdFHPlUFx31yRqNr7mUiihACAGbppC2THHmL3znWZr1ph99KNmcOcAcyNZprK2qpbs+qbEsrXoyREeeMDswQczq1jEtlpBYr+g2+AcKfTGwNcMS1LFON6Lx/JzGuc+luJ4EvgBHO25d489/eNPz0Gcj88isItiVo4xfhnGAdC5g2AMPBAPA+Tg0H3sY5n7FWU1xMn407vuOmv7VZu1/rTV3YFEfU4sSn07rI2K/zsHd3zM6Jl2blwByNFvgKgDOdLIlYugjmNcpz5iod5xa9KP4zakkCgw0RRIYG6iKZrKc39p8QXvXLkwscVJLKZxoiN1YKZJ0VOJDyuqYUmImHGyYhLmr5CyEPd4gk98TIQBFBbLjcdiPZzr3aS1UZmcgliqv6MgotLxLR/cMp5mjOsaXyoKP2ai6bjWpR1XrdPsop//3Kyz02YB2p7//GylB+3bFt0nABc6dSOF3/3OWjdutJew+sOHPpTl+v3vM4AIOGKJr5Lg41cghg+SCNqcCxe5c4C7GAPAy58LgGAJ54qxtvre1XbKf5ySc9z84yMANsZo5NblTdGQYKwiymz6xGvMZJXrRh+33JKBV7iSiJI/8xmzr389v4yNtpvarO2XAnY/EbBrkSgUNyGyLs1jAHaMt/6dOq59PxdFpjwbEdDF5ySIbjH0wYciRj/JWnUI2dNOosCEUkDaGCkkCkw8BfxrXF/t7glfxYsPpvksGDuElFqLx3JAJ4MDFpfnWufuhYnKgVYBgI2HM1X/eE3k4EQ4c0yO/AWAyPZw+xwDOJLPl9CK+XQ9nImpDJVz5JxWnBkm/J4NAhcp7E8BOFMSl6I9tusJT8hADf7m4FZJXFomoDb4hjdkLksKVy+/frm4nt+z8rt/YL++URyti35l9s//nIEf9OzkusTmzi1cIdsKnGWfnTnL5p5UVFa4WkEcUw7aGLMMkxDdGELbfo7SdBsBdPEaDhF23LPDVnxoha1555rswwMQF8ctZRILIV5fvaRahQs9btuWrTn7299mHDk4dAcJADsCK4vUHF9j3WtEB+otPiOlZQBUFZxTHaxV2U/gDSqkkCgwNRRIYG5q6HzU1YI1Z+3KWhe/wEUogrYisIMw+TlNBAAVQB3XzPyzmbbn23uEpUBc+yYUn1g0wSASGnMAyEUxFZNhAGYxHTJpRdBWmMjgQDCh5iCzZEIdc3vGeAH+5ZhcXVl9jNceNdmx5Lz3XluvVR+eIu7cLX/zN5m4EV9z4lBVrlhhvW99aw7mlvzXEgcuGL4w3tzpdV2ZLdz2dKv44GLbeMXGTNx6ijhly5eboUf34hfvI6e4a4wHABliTsaQAzWNHx9PBSAXAR3n43PgBUmlr79M45kxV+DitdzdYiuuFqBbtSY7x3hTzEEdF4f8ro+n3aZzm2zHFhWIriBOkEstd7nmICHqrOLuxPuEU2RF1k3mg6LqmCqDS9z8rGZbf9V62/zezQcpMZ1OFEgUmEwKTPFUNJldSWUfbhTwCQ79GgwgIidimDSeA8RxjacAOkAXk9twkQlyHCGKpyg7nxCHK3+kYzwxOudGCPL11vK9lnG0YnyXsBar00R9R1E9hQNQ4NvftkFx4gTDzM4918FcJZwp6dOVl+smyg/dMe8+xpZ9cpnWa6221h+12u4bdmdWnQLsjMmuh7rcTciKz6/IDAjQx8Mh7/z5QyqGmxXHLsYEcby72JVxGiLHXSTL8yDclqsZcJwonbncGKFdokxFdM32/mmvnbjqxOw5GFJz2IngL+zi69FFrIiVxwHk3BGydDOHPHfs6gMLkAeIY5UWgNyW67YkIDfcPUnHEgWmmAJMTSkkCkwKBXyCky6RG0TECauQ5iBOx/JtwFwAdH17+6y8auikEjlnXQ+I8zDGUP+Eep+QELO6iCoCNqqI4qt4LKSxvjixFffZHhd3cIztjtmdK0fbBQ6Svlykygjp3XebKW7E6GHBAhev9uFv7p57rOmN8+2Ya0517hLgBAthXOr07e5z7ppzuuKbUUOz/fftduxlcur74HszUS3uTT75ySEV+5hl3GLEgMUn4zxasYbUQR0gLjwD0b1NbvyjDxjXn5O+GWuU+nbQp9txxw5b+c6VQ+qMO14PYtUA6ljqzV2yfOITMcuYUnwY+nhXMZGLTUq5rCkMkJv9nNm29f9stXVvWDemslPmRIFEgcmhQHxlTU7pqdRRU6D5Jc025zVzbPals23WS2cZ+zOeLgXuaRywBnXuHMrRBcCWA7c4qQmc+HkmugjmQjr/pfOt654uB1tFQDWeFRTgLOSuHgTEiuXF7QjyAGoO3Ar0z4Ecc90UAzmaUTE7rMeqSR8rwxQOQAG4aFie4m4EQHfiiTb76jNt3rprnLsELXG+DECunFfpS6sBhljJwccAwIgAqBep+7b0OYhZfN9lmeuPUu7cb8SdC2MWjlopVy4HbDwHOp0DurAdgR0fQIC4aF3qoA7/bCpzy+1bbOUVK103zdsW/wUQR/vd8EJl2G9+E8+OKT3pJydZ5AA7LQKgg06AXoDc3PPm2pbPbLG1f7d2TGWnzIkCiQKTRwG+81dNXvGp5INRYN4b51nTs5ucS4DbCRTsfZLRRFO9uNpmPHmGL5GF/hmrE0y34NwkNdqBlOMnZkfmyEKquSfu+0nAkjhlZOnvle8rWdF13tFpvRt6fRms6mOrrWft2JT/4crBcUDvx5deCuVH/SNvTgBpXjefOUSaGbbj8QjqWr7bsv/E6h2YnH+sDsDYQNG8/SZxmVI4MAVwK4ID4Npam/Ppi62yudIqZmj1jBl6xmYJxGmf543xsPsru10fzMeI9nH/4tt8AHD/ATV8ACidP/sHttueb6blv+xnP8vbgB4Z48XHiY66CxnGT4h+fcjt2xr3eWCb50DL2TkoA5AJ6LGdR330tG1psxlPmmF1j6mz7geCcYLGMm1lzV7q5FljwfqxrkKy/DPLbcPbNzj3DT25WCZjrmpxlVUtrLK5LxCQ+9wWW/OaNWpYCokCiQKHCwV4TaXwKFFg4dsXur5OmZStEdf1bux1v2ZwtPDJBPcJFwBM3rxQ571hnvtfe5SaO65qe9YH7pws/SJHwrkQBQ5FfhwuhSYxt4pTn52rJ52hxmc35nVjgND6y2xpovzgKDZcR45JGl25yJXT6M+3NYcWt/MJWBMlk3Mew7XknSoRK+AVvS5ACO1CjyqFQAEAFX7gCqCqSJvm+66zOTe8xheWdyCvZ82BSnH5Kl0AjaMeJEr+3G8fh4hMGYtKfbUDcd8ASst3vznzPVeorP237ZmIlWvwtxbGfBzfjO3htotcOefu8Qwocp8jhy5PeU9s7vX3w/Mue57179L7IYpzg6iVdroBQ6Fto9lE1656qegQnxOl0KXulDqb8cQZ9oHzP2BbPi0g9+o1oyku5UkUSBSYQgoka9YpJHaxqoX/zTG3cAAAQABJREFUstA5A7yw+cLu3do7xCs6X9eAvMrZUjZWZHF1FwktlJhDS/7s+KSWGJomoWdNj1sL4sbDuRXwgwlwItTP3Cs+nxZEHR8s1z/lI0XscyjBdeU0MbHeZc5ti+CN+rRdPJ4DuQj6yMv9CKCOtrTePHZAyXVjDa7/BL0EdJ124AH5+UohUODyy0UYrXzwrGdZq3TiBlm+66KLrO6MOqs5rsYBsIM4OG1wm7A2ZSzovvv9ZPwJDCE+JOU++1hgXCg4uALMVSmG1OT5g3swe/OnTfaiQ0KbxK24KmHsOjdPHw8YXAD+VYLnhfuWj3kOURcxjsPCtotj4wdOndrXrWtrlYrD/Ktf/cpmvmCmLTljiW24b4Pt/NxOa2ZtVoprDB3wvYP/W/nrlbb2dWv9oxEaYeSANKB6WbUt+vNFtv327Xb5my+3lh9PncHPwVudciQKJApECiQwFykxhSlWdAA0vtyxmGv5UcuICu0AIQI+n6qXi0Mj0Sscmrl/K0D3f6Ye0DHpATAAlnAyfAKigdk8laXF7XAOsDpQLo5BhcSE4iD4hAZgC5NZBHVxogP4MQkC5uBSNv1Zk7V8f+wTSd1j6/ZxGopcOSbOQizlyvl+mFSZ9MsrBAQU2SagxzfZAW4s9IFT5PpyAhrQJfnvKlD+l7/UfZRVscbUYjn0nffSl9rqcxuN9WujmNBTQBwido0BB1rFe697Wv/k+mx86Z47cI+gTvkc0MFtq9bNgHscOGEz/2Km7fpCKZyTKFQOeOEmD1Zk+m9ep5rsY5sbypiPESYr44x61Q7/iFGdvl2mTDrugC6srMBYcDCnZ2+wJiv/4e0Pe7/m/vVce9vxb7N//fm/Gh8wOz8tXcFRhBN/dKLVnlzrzwnPNyCu5sQad3HCB8TqD6y2zns7reO2DudKjqLIlCVRIFFgiinAK43XSgpTRIGF71jouidMEIhrdlw/NkCGDl3NyhqfrOAUjPX68XQTXRnELw4qqjKAMdCvWUgjxxWuNbnlQZuaMn3XAZG24n7nhs59PqvCZBk5IXkKWAoTqnNRglis/rh6W3/l+rya0W4gOnKODGI1fbo4GAsTZz6JCgz4thI/T/NDpA/llQJT6nelrBgBmJu+uGlKXIOg14WxCNwR5zJJpxLl+D1fly+0FDIK4MwXdyGkL3uZNVzxvIy7JF049OH83uvjhw8gH0/4SkO/TJzuyln7PkwqxfFe88o1GTeNMSjSDxHNi5vnZagcB4rot2obo4DVF64e9m40PqcxawN6sHz8wBGkXI39ON59P4y/ODYZe/k41Fj1ffIQNIbjeI7gNIpF8zarfEAZ4+asuWfZH/Xbdfcuf9+4pS0cRr1/1r5+rZ1w4wmuf8rzXX1ctdUeX2vvrn23va/zfbbrhl3GOqrdD3Zbyw/H/iGVNTj9TxRIFJgKCiTO3FRQOdTRfGGzv/x5OaNLNh4ghpsEXui1J9X6BDGZHLraU2pdGZqJJ3Ijett7XZ8n1/PBgg/9t1EEF1OJ0+blwZ2DExHTIOJyzgQTmEAMnDy4YRzreLjDZl08y32BjaIqz4IXe1cIF3fBASITInNijLGguF+S0j7aCpCrrhagqqnRcpc9UwLkaJrTR7RFf4p+MAGzVmwKBQqw9iirMnR1Wd3fnWvlS+SLT7RygANoituBI+cgSoCqyBljbDOec7AfARecXKJAmAOxQrV+vcYoOq0jBdY9bRSX0MebqnBjC7jZPC661sHXgO4rHGrGHuM+gLfSVKMg0+lUO/u75H+uJlNZyNtHO9XfCBZZsQT3Pd/RL453nP06wNWHDYDw9DWne9pwZoPn7by90/beuNfe2PlGd0rNMnZw5DA+SiFRIFHg8KZAAnNTeH8antHgkwsKzB23j3/BaRStmVxqT6h17sDsV862XZ/fX9xzKF3DLUpFvUSimugQ7QHEmLh6twvMCVQ42BqHIr7rv2nCYpJl4vGJLU5iTHKcA+RJRGWapwfKNOsx10nPqGZFzai7hOd66nALPyY5JssQc5EqdUWAx+m4TXZtMzlWVkvsJGvIGVpJAEB357/fecA2zHntHOcMRVF0w1kNdt/T7jvgNcOddBGr2oHuU7SSRKm+44/jHzfD1TPtj7H2qJwC1/z401Yu1QUHXhG4RSAHGAPYwXGL91xjqugeBGMWVBjcfx95SoCc7zOOFFzfjQ12lXfZp5bZ2r9Zy5H9AuudOqADvDGO+zUmBaR87DO0+bihXaGsUhAXxyzpoMSu6oXX4c+gyvP+hLY6kKPvsY9kzbJ73bhXceAa2uLbwqLR2AL9XTe6YF1Wub7pXtvtXDmvMP1LFEgUOKwpkMDcFN2eRe9Z5OIZrNI67uiwtl9layCOt3r0cpgUADhM/LMuEtfqq7vHW1x+HVaTiPSYFJkwmORYA5UVB3jRH2rgax83B+VlmnGYjCgSUKfd0m3nSAVXDeWD5cY6kYuv0vJK79mozCMHdH6cIwNgjCM8TmpxghsppVjOqU2sswk3rrGx0eMfv/JHp8ecv5rjdK9eUe3GGc5xYUIuhjDRFg+NZdtFaCqT+4A7DXS14LakMAwFtA6rgzjAG4BLYwln035M9POxxfjSZg7YAVIYFsD5hLOs/flvmW+br9qccegAgICkmEbAVCxDZQLEKuYygEcODuieJQ6d6ojrsjqgo02hXXkbi/uqy8ciKUEpHLohgV0izxH51BQHh9rcL6u44J6v2HdogD6enm23mBWQw2I8ceMgYAqJAtOHAnGqmz4tnoYtRdyHAjtf9AASRBkTERDVoouDThvlH2oAxGFkwYSIcQYAbjIU/XHBgssDq9PEg2UfYi4mMboQJ6U4qQm/uH5emAg77uuw2ZeIE/nFkTmRDoQkzmIi9qAkn8Q5wOHiMbY1KdNnFMfdPQNcPYFlYnetrI3re23Zecuya2MZTKICWbiCcK6GUhc/B50kaDmeADj3tqs4dLKcO9qiCfbuJO5yet55p5UtXWqDe/Ucbd1qtnmzlb3r5TmQiyAOMOb3GaCtvzxSiO4dYM7vVwB06ItFPTQXuQYAl3PpKI83JmNT0ccU27pPBzPQaf15qzU8s8HK+3SBxjR1lwK6nEunLM6FK3CKVUvWft8I/xh/ITq3UO2gLQ5QeabgugWgyhW+Hep2IAuQC2DOVSD08QYXHl3eFBIFEgWmFwUSmJuC+zXrL2e5yBJwxLJBExUAWq4Dg4K1lOUR8Y3Wgm24NlQukJgqADkAV/cjknNOUgA4+RqZ4B0mxgjqNF/6RMYEHCe1PgE+TUrl/TqgCQrdnwVvWWBbP6yJvBAAT4Bb55QFIFcK4ny/cA2TGZaHWBdDQ78W7g4cDqWR00P9tBlupU98AmzsR2/9cM2IA/LW7/kAdIrHXHlMobbRbTLJAy6xFmab8vAndlSu+vDRj5qdcYYGhcDJ619v9q1v2eXHHWf/3dIisepsM8XBk0/O71MEXv5hwLgqADm/90Xw06tiuZ8B1PRs7PGxBTB3IKi3YywvphHMebkq3wGi0nmvm3dQa+u2X8vh79NmZEBOoI56McYYrBxe1DoE0DF0NCzzUOwH24A4AFwAczmQC4Au9jGCV88X+s04dR96sthNltI5hdNGosC0okACc5N8u/gaByjwosUjO+LRiQwdt3a4mLW2LjOIGKuRQGwLOmYAIRetStQymUCOOgE+lYPBA7+4YExcObcDQMfExOQVonMVmJiYeMQ94PpT/vcpdu/b7vUuwOkD+EQg5Af5FyfAQlkcY2InLxZ/THSIk12MXMhXBIKIntAZBFT17uh1YAVw8+uUrvjSiqxtAgL3P/P+vPq93x0bFxZA6fqEkEP6cg42OjKObl7o0bLx9a+bPeEJZr1CXX/4g9l73uNLc/1EYG7wkUds8D7pIs6aZdYs32oAK4ZMAOAOwgv3MpLMOVjkQ3zPeBKYswjqtL346sW24YoNGTgsAXMO8OHWAfYpO4BFxknlotG9Stt/l63c4Vy6Ht1f+Y4D0BkfNSpzCIAL+3G8eh+oV8GfDzXdOXMRyGk/f07gNmpcR/Dmx4tALwI5nCFrbCcQ52RN/xIFpi0FRvcGmrbde/Qbji8qXHr07cmWpJqMFmE1h8I9CtwAx/EEnIQyacAFmqplw+BU4nUVMXHUEXNQx4TF5KzAROnHNPH29/RnunByL4HPrw3f3mALr1ho6OF13NmRcVPCZJddrf9MeMXA+RABZ6y2UbZV5cGh0cTmi61LpMlk6ZNhgbOx4vMrspKKdYQJlWupi4l55S9WOuDb9dldtudbY3MjAmeQvqPHBPfEOX+AyKNtLdbly81mzrRKxb7f/tZszZrMBcm6dbb5yU+2qtNPt94LL5QDxhozgTsP3AvGDeL6cI9j6uNI3D0HceQLEY5UWY8AWm82BvCHWP+keuu6S6JGHokA3nJOHWARcSt/UQyqOrlPYwnOpZObIep2QKd3hK9AIU6iRt6+ouiHQv5c+A4HFAFnUQ9O+0OAXBCvFo85eAXEAfQ03vl4SSAOgqaQKDD9KTC+mX/693tKeoDlpi+roxcyYsu2myaWK1fshOvPSdcKUDf7FdIp+5+RdcqK17GNCxLX0RJwwUHvVAfqxC8WnDKffEnksoFtn9jChEa7AFhlXdJvq5SYVsCp9Retfu2s82dZz/aeTN9H/cgD14YYJ9+YArDhrKH43SgFdRwzext0Ccfg/gH24MBRxpYPbtmnJ6V9t5ZlEsZ3GVxBATEsTwHUTPhYGc946gzb+M4DG2zEtvp1iIfBBXoyHSAU5vWY76hIHSjpPvcJ8CNOffzjRRMR5ZOftD0bN1rT4sXW+9OfZjpzT32qOHj12X0WvaJo1e8zxALoCJznQA76Kjp3C64cInE4VNUCdqI/xkSb75EeXgGscf/zfW3nge0Y84Oj23A3Q8o64ykSvbK6Az4VGU8Y7owUGA/0pwDiclDHhwcc7fAB4scDeIt6eg7iEiduJOqm44kC05YCCcxN4q1rem6Tiy5dqVg+nyYzIG7FCao79hWgG0uIemK0M644MZbrJyIvLiFQ/C+XM9Yhk2NxogxznHMpmIThhik7wCuCWQwYmMx6t2nFCXFLmKj3m4RVDmCrZlmNtf1WVsGaQDv+0GGtP2vN/Iap2LEuUh5pgE4UoltfCkmOWMdimOL3QQAiGnwg/nLxrkS7R10ArEi8WlVfb92AuXvuMTtG+odbtpj97nfWcvbZ1rhsmbUigr37brNXP9lJ5NzUUmKpqMjJykGcwJx/MIi00DgaTQxUDfgHzfHXHG8PX/HwvpLiOIwpZRaDjs88f6bt/fbYxOoUgWNeViop75bYVas6uCW2QKWDOo3vIaHQlxzQRWBKCkcOMBc5cEoBcjzbALnEiRtCzbSTKHDEUIBZf9UR05vDrCPz/m6e1c6utZ5tPdb641br26636iSG/vZ+d/ILIKp7TJ11/nF0xhbOkRKg4freDVPPmYskce5IqwCMoovKOKHNPIJpiByLExaTVeCuwEHrebjHejb1OIes9rha53AB+JyLVp1xPeLETYoFL6CueoFcsiypsc77Ou1QAC3067q7KzdgAGBD3/abM10ptXzYgJgbUAlnZWBvphNIRraPxrD4ihnWWnu2DQqwNYoL1/3+95t1ajw/85lm119vNmeO9TQ1Wfm8eaLZgFV98SPOqeWeskIDYN0jYlEB5Mitcw4bxiXhmB/XEPJUn7aknOtp6bHZL51tLT9vyY5xnIi+HOOJbSyexR128KVt9CnbbzrwfR7pXvZt7fNnr2etLNT1MeZif32IAMQAoqrNx33kvPn4D8AtfxYE1uKzELmNc141x8cVS+HRvhQSBRIFjkwKJM7cJN1X/L85aNBLHz2cqXArwYSARR5gDi7PrJfJ99xXDu57zjkAooNzuiaJHmMttlRHzMXVFKI5rZTT5py6eI7JVvOpG5po0kXUDbeOa+BOOIdGWWI5VXVV1rWly3Z9f9eELmDPpIzYFMfL7vSX9h0gRPEukzicRoKD2gNcc6SdWvBPC/Jly1gH1G75sg0sX27tslatEIDrf9zjzBYsyADdddeJfdptA098oq8A0fmTDTbjxUtzA5mK2swVkAN/YRxS58SFbQCZAyOOy5EvuqI8rwMVHFB+xa5Huuzkq0+2+6+UQQvXKcINc2AF8cMxNgkYNWy9ZqiFdXZmbP/72/qN5euwfHdd0gAavV0URfsIIXXgh684cRjZnvkC6Rrq4wDgyVJc26/bnuVP/xMFEgWOWAokMDdZtxbKBurylTxVAc5A5cxKqzpWulviCo0paB47XEP/noNzFZyjwQxbmOxQ8oZbx73w9TEDZ4U8cFew2j3QkkzjpQdiWkSt6ORV1lRa03lN1vKjlmGLcwMQtQvRGHp6R1uY9/fiYGt5OtZH5Z5s/8R2F5E31v7YWr95svWLAzdj5Upr//GPBbz6bVBiVvvGN8w+/nGzZz/b7JxzbPCkk3LOlX+URKDFmC7ECOBycKdz/jEgsgPoAHl5UBnbH9hu57/3fLvhghuMdZFHDBpPY1mhZMRydAIOLSDOLV6li+kuanRs15eG14M9/b7T7dbKW73IOa8WJ05rxmJA07ur17Z/LAG5A9E6nUsUOFIoMMbZ/kjp9uT3IxfxaHLia3kqA46JmQAwKjiY7zle/Dn4mcpGTkJdBwNlvcigpjAADrj3cEhcl2mYugGg3Cvn+ijv4cQdHaa5E3oI58+IueEiVc5TlP/ATVducnGg00Rkwa+cnXCCtWsVjtmyWt2zZ48N/vCHZh/6kNkFF2QGEH/8o9lFF1nbR39jjW99ZubAWVxYVvCIQC6COLhwDtgCwOO+RE4vnK2c2xbAINy8m+67yY77wnG29doSrlvhsYZbBzd8IgJAbr+gugBq0AVH0lXzZVyllScue9JlduXLrvTsGPH4MnDqRs/mHtv5mZ37FZMOJAokChyZFEhgbpLuq4tYpbdTVS0P/lMM5vDg7ro86A/JqGD2y2XdOsJXPd33yUyThStUTxI9jsZiXX9L9CcMq5iv477aA4AfrpyMQI6GgLse/AICZPngILKMHBw5LJvhzrn1pTjaDc1rre2zn5W8vMp2PeUpVouPOYlcu2+4wUycOnvuc80eftgMn3OvfKU/azxviKjhcDlwE1PXyxTIAdw5sAYvKQLCcjG9noGBQQFw3NKE6I6qdVu6HuoyfDhyT3d/LaguUF4R0Ol5n4jgy7cVyvUyQ3vhuqNyUN5UbsuftNze/9b32+4bsva4sQ3DTXndZ+JENCaVkSiQKDAtKDAxn5LToqtT30gmlTlS1B6LReNEtZIF2d2thiw6+ZpvvqB52KJZuoqXPyFNABkdJuy/JlaACi4nquZV7VcsunToKwIcIhdvv0xH2IFZL51ljDnACA6SY0SvNK5X7AYF0nF0UCYOW8OAHAazEsRXvyr/b3dZnwwh5lx6qdny5W7Z6iQC0L33vdbWfVp2ncTr7tpFQA7wVow5t47jon3RmMCtQNE/C4Y4pNExNLqMbL/jre9w62c+fvz6ALwcJB7i/ao5QWstiy7+TIbnMhYJFx0gxwfArGfMsj998E/5Kii4N4nW7Kh1jEZXNpab0kSBRIHpT4EE5ibpHnbe2ekKyfVyrYAz30cj4G2+d3Ovi+7QF2t+yf6Azq3zNBkxiaEsncLEUQAdKlZxgPad9wy1LAbkuVgO2mvynWxL54nr1fhKQv8LDjHiVEAJfXcDEQET6LPrC7ucQ+z6YlGvkbcTnDR9FDXW3G1Nv/43s//8T+u//XbbqTVZTz7+eKtmhQj5nsvDzTdnfuN0DcDLARYcNFQuiZQXwF085nnEffM0gD93CQN4CwAuplhM//cf/tuWfHiJsWpKFMsK1nm9eTvGuRENYeIHViwG0StgDW4muntbPrvFNr6j4L9Q48gNmQQAcXydQqJAosDRRYEE5ibxfmOR2def+U+bxGoOWDQLfMOhw0KOiaL5xc3utiReBNjAOMAtPePBlE4IBQBziMwAI8XFy11MJroj3ubckQ7kWPvW180VEAHEMQ4BJQ7qBOwAeKy44JabADkYU0pdNMobKnxsIHqduVNLfP2bQJ0cBt/3wAPyI1xpj/3bv7WyXTIOkN4cAUfS6B4SAV8RvLnoVECuCOL8nD5k8pTtGHU9hjceWYUjRgG8rvukyqB+XHDpBW6p7h9FE/A2dcvnyJEjVZmMF7iZVYur7AnPf4Lt/PxOW/OaNXQ1D7QfETBgeDgucJ4xbSQKJAockRRIOnOTeFsRHe3YscP11+rOkN+3O4ZyZyax6iFFt/2mzZcoQnGar3f8nmHt6gGOhADFgJawSmFsFFh23TIXFzpACSDFuSOiKT77fB1X6YCx3FgMgBgmZ3Qpe7t73XoV+h+pofHcxowbhz82cZc8SuwPEIoRzlwEcJ6iMycQk4M5QJIOIdYsLyu32TN/Z7s+LCtN+Zzr0JJed554oj1ZLkvWSI9u+y9/6datfJwAbuDOldWrXgFnynT9OECSouvLCSm6gQouR9BdLIfFpT+2QZEK/nzImAWgNFirfGq/O/dVf77zm+/4B1Ltilpb+8a1nn+8/xCxEqg7GlC5PqGAHM/ss57xLPvWu75lm6/evF8VEbDGj7P9MqQDiQKJAkc0BfQWtVVHdA8fxc754u8nllvT7CZrvb/Vuu6f3FUgDthVzUu5ywZwG/twIAQkBtvFOXqwa0LERAdswxFycvEHFtvsl812sABIADQ4+AAFCDBEESJK/XWn1lnD0xps/pvm+zJRtSfXWt+dchArIIdO18EscKczybCuxEI1gjbSijpx5EgRr0ZOXVW5GxU4N67AmXNgF53/6iMEOnvU9oyle62h8i5r//pDQj9ltknqDANaKeK1K1bYPe9+t3VUL7XqW7/jQI2x7sYQIqZKGJ6k4LZi5BkpRj56pEvHM+PGGYV0sENuQATa5752ri34xwUuDmW95LEGX1tZ9AIsAvhrT621+jPqrelcrSQjDu/vr/i9bf33EovaUElls5xTL5Xz60XVTiOcBKeQKJAocPRQgDcbr7AUJoECOKud/+b59hcX/4V986PftA3/tGESahlbkUyurn8jh7bOcZA7BrgXyTv8wem44K0L3JilXCtJMKm70YJEcZHjhAWxc+mCnhzOm1mNgGMotZMS8CUHl/bhlz188EqnaY6GsxtcJy6KUgEjcdvBrnQGoYnrgQnYbXzXRl+SLXLjotgyX8lBQG7va6Qbt3BhRhFWgyD+6U+2yD5mmx46zwyjiFNPteXHHmvPV65PdXVZ/YsXeL1w/6gvlpcDRbiAiHVJuT1KfPtAdFd+1+2Dwxg4jvlKEAKfuFq59PRL7X9u/x+3NN3yr1qCbBQBLiYrt9Q/vt5mPH2G/etJ/2pX/OEKXyKse3W37fy/B3Y1gusSJACAwodffuSOrVGQMmVJFDjqKJDA3CTf8mP/7Vg78+Vn2i2/vsUeufSRSa4tFT9WCiDaQjQKQCNg0YuI1FPpPMaw4G3iuAgAo3uIMjy6WHDVAGbubLbA1XGuE1aHs6XrpIm1coG4JsvFNZG4jInel5sSB6pvb58v87X6JatjNUdECkfJjT8AsyUgzsEu4BZxs+gDR4ltdDt3fV56b9wGxShqRJ+zZfHFVv72t9sCgbSOjg7bu1GK/0ptr9ZBRXzKtvzPGS5Mzj7b7HnPM5MLkyWLFtnuc+R7jTYgBgdkq64hgC6AuBzMUTdlloTh3PbAJXRQJ3Grp5FzGLiJtB1nyE84/gn2HP0+p9/Olp3Wt02cWXHy4JQzJuDgP6/uedaq301tN7mOa/ut7a6Xh7sa1h0eDaet6c+anAvs1sIzy+3hlyZAV3Ib026iwBFLgQTmJvnWzv2buTbvgnlWXlFu6z64zietSa4yFT9KCsx42ozMAlAitIGegUysFvjU0eUEotDmFzU78HAAJy4m668yybbd1DZsTcuvX261j5E4VcurrfuHdQ4eWFYMcRlAp3qZlNnllqRqjnQYBeq613b7uFj7urXDljedDtI3HAG7kQeuNCKYA0yF6GJEcSwjmANkAXpXXyBQyxsJQBUA0d7dp5q96EVmZ51ldscdZvPnm20Rp6tXeojivJnEq7KCyEAdIExLfLmjYfKfJ27d0qXW+FePyesGaFMf5Xs9iHUDeIx1D0vvMC6GO+cfA9Kny8XAtF3ALnL/vNwC2HcVB/0DAGIkhTUzOn5usKHUPyS0jio6t6wTzLJeowno1TU8o8EY1xic8NGBRfu2/9g2mstTnkSBRIFpTAG9BVOYTAqwJmvXs7vsOS94ju1+1u4E5iaT2GMom0kP3S03VNCk57qD0h90EBH1tsS1aRRnB3Gpu6bQxIurl73fEUdohIBYnUkVfSt3gKtJvbm52fZs2GPbPrLN14rFTQcRfTq4KPUnyn2NuDN1j62z+5523wglT4/DOWALXCqTnU0EZjmAEl0dLItG0YoUcFx3ep1zoyIIclErotRZs8zkhsTmzrU5HzzTATBlbb9rpRZEbTDT6hA2b16W1taaybmwbdpkdtVVbgzR+px/tsafasUI4asYuadw47wdAnMAuhzMlQK30v2SW+EgTP7ovN30O4A5TxlLCs7Zi4COfuOUGH1VLG4jkMM3HpxhcXx7N/Y6F7j7odG7C0IUC5DGOhoOMPpzNZfU+BrNiPXXvXFdScvTbqJAosCRQoEE5ib5TvJl3Hdpn9XU1ljNiZrkU3jUKdBwpoBUs6yLWzqtb5dEXutljMC6nApwSyKYgMOB1S9clsHdg9azocfz1p5Sm+nMiWvHZJwHbaIniZf+nq097tC1SeuK7tmxx31/4eKCiZaJteUHLTbnVXNsxlNnWP/Kfp945zx1jp2x4wxjfd2HXiTF/mkY4FI5iAHQhIi40WMETBm+2WeAA6hRXHLNEnvwJQ9m1wVA7eJTOG7iwJUJtO183JU27573O/ia/6QHMo6bQPmmG481E62FnHX/pNTWJ3Yr6UOio0Bg64kvt8YHv5RrCFMfXDoHcbFdMS3cUr8FpfscDMdy8Sv7MR9DSX2m/w4Qyc+xAOJiikEF/uwAcDFyjA8MuHVjAXJUQWD9X8YrABEVAjjA6CWiw3jafae5WgDcvq4HumzzezZnF6X/iQKJAtOeAgnMTcEtxIr1F7/4hdXNkmWjXqptvxxePDcFTTnqq8DRa2VjpXX3dPvE1v3AUM6Hr88ZqIQyuovLtN+3p88n11wxXxMmokQmcLdoFeCYdeksw1p1oH/A3ZEwIbd0tri4jMm6GJioN121yRrOarA5r5HiutrVd3yfzZg7w2a8cIbVPlRrWEROJ9Gr68lhEAB3igiYEyjziG4af6QhAIQ9VitV7F7f7cDDaSXSct3sp7XYLolTofGcGTNsB1w4iiACngJIOvaiTbIC3WzrPysxbI0+muDYAeba9KzJPZCtXm2tdcdZoz3stTtHUPcHTiJi3xzUcTaCsrCdAza/cv/zfphrFHMOHIbrgLeCg+J8WzjTLclVv4tYEfFzTAATnczxgDhvQ/i397t7jci7pv5x9ZloX5xfF+3LPVHNshoX+c9/w3zX2+SDpm+LPmrkQqdnY4+N1mCjWGfaThRIFHh0KZDA3BTQv+MPHdbx9A57/kuebzfeeWMCc1NA85GqwKJx6ZKltvru1dZ1DzPu8AFwBVgDfDDZcQ+j2DS3XIR7JG4Ovsuant9k9U+ut4qaCuta25UtGC9x2cGW6WIJK+LsS2cbS131nSouribbhccvtNpltW6deN9Tp0b0umjVIrf47H6420EObUdncMcnBYZGE+BGCRgNAXGBRn45ACwGgI7AjPuDEzdvoDrzC3fCF06wBy54YB9g45r2dhuUkcN8AbkI5txIgXOUg8hSsWywzJa9boft+NQOa/9hu9mKFVltjzwSa5WJgXDeORKx98kiuUbXySq5rEsGDEHsGoFcDsq4MoK7mMbSAG+O4EIeznNMbfFr+pWUgjm4kKoT4BYBHNvobB5oPMYqx5Ly0UjEOrZ2Za3r0sFpxqI9rr5RPbfamlc0W3N1s0n4L3IO2OZVm61le0tm5Q43WUY+iMEx3GB7ywdHZ507lramvIkCiQKHRoEE5g6NfqO6uv23WlbrwsyBMFaNKTw6FKhaWOUK+Rs2bnDF8wO1Ar03xHDuC04TWnGilT2rX+oi2QBQ0MGrnl9tvbt7fbUHLBDHEljOqv2Wdpv3unnu4Llvpbh0i2bYSU85yepa6oy1du8/+/6xFDmqvHNfP9dXDIiGAbSh9SetGSBDZKoIhweH03FB95EKjly4nMsVxZbFCwA8gWMFdw3A6Fw8AF3VgLU/0O5uOTpukYUqtCX+4Q++usODcgxsdVpCKx7XKQdxAxQUyhWQmvcP86z9VQJzBRCns3lo+0XGGadf7gRY1qgAy8hR9PJpJwFcJofC+4V4iJT+kCds54Augjl80sVtVqAIXDhAHBG92skMHbfrY1Jx15d2uesTOHR1j6tzLjKgrr2x3XY27sxcuNTLwnhGpc2aP8uWLF5iK/WbrV+Lfmv0W6ff9iu2W3dLd2bZrWfDV8aQwYaDPn34bH7v5snsTio7USBRYBgKJDA3DFEm4xBrtd5xwh02a+Es58Ds/truyagmlXkAClSvqJae/DzbsnbLkOW1hrsEa0DAmosBmYyHCVEke+w1x7p+Un+3RGRa33bImpnDXDfSIcRrG96+wXC2ixV072m91nl8p81vmm/Lz1puDT0N1nFnh3Py1r9l/UjFHPQ41rkoyLsfPPyv4SYEK0+JHNHxdM6RQEf5IGhMWEXK/T29PTbntXNs56dH9nXmOmKAKi6LUThr889PMjv/fLNzn2dLfqlUecoAYAAcRI3ojgnIcf1gxaAd85ZjbPWlq6k6C3ffbbZhg/XOnJlZqwYwl7sQAUwJxEVgR5mjCVHdwUGduHTOUZR4OOq7uYFEEchRbCw6bO8H4sgPDWhTCVfO+wtXDo6kOHGkhypSHU0/i3mwjCWiW0dw0bjuOytNVC2tstoTZW0to5y9DXttY/1Gu6XuFjcUguOK+56i+BzdUKIHdds5kur3nFfOcR1A1oiFm40xx+HgYzNraPqfKHBkUiCBuSm6r3x9957ba895yXNs+z3b3eP9FFWdqgkUYHLu6u7KjR0ORBiczDJxMbFH0DZcfhwJY/RQrlUMulZLqfx9h86VwOcacfYrJHq9eJb1nNBj25ZssyVNS+ysJ55l33ziN63xvEa75zH3DNekEY/NfMFMF6NG4AZ48225EHHDBXHHHIhoYobL5iGAkrJ+uVCRtSS+zEb0eSYAB7iBzsQYjnnWA7Z5s+gyMGC7Ll9ncz66zIEOHDDlzO4HVq9Bz67zoU5b+I6Fdu+PXm2z/yQr1B5xOeUc2LBUbd1/ZQUHcRKxeqBMDCbGECKoc1c1wWgjtsWBHeOAAIAjkIa4H5hDxApIjWkAdM6FA7iiJ6hjUw3ivN3D/Ot+ZKjOaDFL/KBx587yB8g+68MC/HJVg+hjjzTqS0JDjaWq+XK/I47u4OmDdupzT82MPaJ/RvT0ZAy08V/kMzCFRIFEgUOmQAJzh0zC0RWAzhVWZLfcdou/5FCuH63/qNHVkHIdlAKaZ3t7ekc12ZfVgQr0J1Cy+8sjc1HrnyLrVVkL9u7oNdbAHat49UBt3vU/Er3e3G5Y38JNW33Calu/dL0d23ysXXbaZXZN5zXW8vMWe+jPHzpQMcZC93FCzl2HqH9DOC0AqRg1GWPR61EAzYFZTAExBwgAKQcyAf/kWb/5TXcZ0r50qc0WmAHECdZ4HQAck1Q0F9OqbhwtL9h1rW1tPVNFCLRilSoDCAwZHKwFzp+DztK6dEXjcxrdgCSvfxQbcCV5LhGxd6/pzjl1OV0CfSKQI/W+QhNALwAugN+cCxf04zr/NLmi1FF0b8xZeF8dKADuCO74GQfQeg7g7gHi+BhyJ82k+lhwLjdcS903OMJVNQKF4g4f/83jM04lIE8i20PhOB+orelcosCRToEE5qbwDvNC33SGLBibpV8l56oJzE0h8VUVXJQ+XFaMIvgELu4CE9FIYdH7Fhnrr6L3hVXstmsn3jkrHBwiQBHLRDh1D6982K456Rq7sO5C2/tne+37a7/v1ovr/n7dkKbi9sQV3WXI4ROqXHi4gUIwUsjBmrhwLmKMXCn120GSQJUDOcBSIY4kbkWVAOtcdMLyEIDOotdo7F97rVuYIsYlRECH4QIWrEUw17+z3475/46xvrfeZDublpo9+KA4XmJ5PfywmaS2EWACDvI2xkrV1pl/PnPMYC40ygEmtMYPoYsXJW7f8409+8AuXMtIm5A6hw6OXBSjyuVI170jG9jEpk7nNIK9Htsf9CG+5d74ChcCffhRjNxOF8fzWBE1FADzvl6vAOHyzyy3Na9ZM53JktqeKPCoUCCBuSkkO1ybvs4+O+kJJ9nW07Ye0PnsFDbr6KlKXJN+AQKfeA/WawESREXiKdi8N86z7R/dPuQKAA1ObgEgPWvlzuF/Ta6FXwR1u7+622b95Syb81dz7MunfdmalzbbFUuvsI+84SOu0P7Asx/wdqIHhgjVxagCJXBGWEPWRWGAN2IUh8aJVSncFLcwRUzKcSU5cNE2XDFWLRgxaHIG3JZrOSlAGtwqUjhVi85fZ2UP/aNYOYErR/HkkZ6cAzpZzjqIVL3Uw/Ny/PXH28AlD9ru1UJNcjEy/+nrvD20LQdxtJNAW0Nwx81xZ4ypgw2uyTCnp9DcaScgjDWoc5/mVtgjlzzipR8uYtMxdnXSskfxLaL5GBzgaYcxBg3R1fQgOjvnOBxb8l9L/P6vk0g+hUSBRIHRUSCBudHRaUJyYSkIB2L50uV284qbJ6TMVMgYKCAwN9AnwFDQ5xrpajgsgDkAAqLJ0oC7B1+rVe5H8CM4keLV0rpK9xH7dtwmVx1vmm+9T+61a06+xk5vPt1qniUnsfdW2bo3rLPyJunDacksB3Fw4gTkvD/Mn3QnRgBQ2IYucBoRd9Fvp1PgPDmgEwD0vEpmvXyW7f7SMOJnaIwjXAEzX+9WEzU6Yl6e/rloVVWqNdk27dFpynWQLXFrrENb1vanNrvwSxfapz7yOLObbtI5AUIBPW+brvGUPsQQtkdrBBEvG5LSHqLKcpFugQbQ00WI4tgClHHn8sgrHxlyedoZngIR4JWeZdUKXKZgKME4ha6sabv0v5fausvWlWZP+4kCiQLDUIDXeApTSAH8NW3ettn1TKaw2lSVKADIAFgg0jlYcDAn8AI3plTUOv8ftWSXxEgoteOTbdOVmw5W3ISfhxO0/k3rbdOqTdby0xa7/eHb7T79zjv5PDvuhuOs+fzmXKTqunGIUOHECQgBUoZEdsNxlhT7/9k7DwA7quqNn+29lyS7KZue0CEgiPTem6AgIihV8Y+AKKgIKIhYEFGkSJEmAQSko3SQXkILJIRAsmmb7b2X9/9+d/ZtNo3sZkt2s/e8TN7b92bu3DmvzDffOec7q+WIhfPnwkfQua1bP/xct3tXwSkgDJhz4VSBO1i5oplX24qpKmYQ4xlexz0m5Mpznffh/rfuXp0QGOf1D1+33/xQHTMSnraSuFNWgb3wXLqD887nesS+dpt3+KFjBhmDj0jn0h04wiqR88VnIndargdyYcf14Z7vEEUoVNgiXMxnmypYmLsJN03ow8h+U++BkeOBDZ/VRo4vBuVIYXDmzp1r0YnRrgpyUHbqd+I8QF9VABgnaTo1fJm56kMS9TuZgu7rus4Qep5G6AORJ9d9Xxt6TFuw5Rcut5qna6x8Trm93PiyzcyZ6cKw6UcJ0IXBGACl07qAGM/JHV2mvwFzjpECIHUHM10rrXpAf9k1jYIN5zvlQQHIAG4rL5S0yNSprisDoM29jsYaj9dctD5SKPTCdffqiEBXhLvn3G1jfz/WJu30wCpWrjNczDxd2LgzdNzFIq45uR78DaPpgC7Hjn86FwAdAM6xnbqHOfr4XB2Xt371AIViiHRz4QWYi9/6y7+n/bpzP5j3wDD2AD9Z3gbRAwhshkNNXOF7GzwPwIqGZUY25Pv2WtFJRBtVwUiVXthy/y83aDkloEI+UMp+KS7cSWFC+jHqC7oJDCaDnL3SG0ut7o06m1c6z1LjUi3niBzXZL1rSmFwoie6AF13MKfnY3LQCGGFYAkzdvorAH7d1qdLxroMloUwJz4sGXN+ULyQn2/2ta9Z0Xdf6WLi1gXqwixdGNAB6tyisfA3Omj5l+d3AToH5GAcwyHgzpBoV97buia4nucoSgJAcMzhJewHAGKYkSPszlxKru3/gpf1TG1EPc3nmUIaLrgIuXrzHvAe2LAHPJrYsI/6dQ3ybRKkYt8hza1QY7czY7/uxQ+2Pg84nyv05/K51reSnofxAmyQZxZO1EanjRM+bFLLkqCCD1kGTvjobyXMTLC8K/K+ZNSBe4nQMbl7K69caXWv1FnZojKpZHRY7tdyLeukrACchXcPUMN078KRfAw7l3BHhi4Q0w3UrRa61PoAY1e96gZb/T+KKJzkyM03m/3lL2bFxRaflWXnT5pkFVessKKTXg5YORg62NLOUGsXU6fnXGcBXfyQw9f1WKAO4eRdr9jVge0we9jFznUyioDw3poLLxNuxvhlBBgSntZnAL009NVo8far7X5ln2zXO40/N6b/r0ceGPXjUZayu+R0VN0KqPfmPeA9sGEPeDC3YR/16xqEauIT4l34CRV4b4PrAdgi53dhsPiZ6w/hwA4Q3oPxCYM5gBzsDGEgZCcAGeT7uBwfhXBZH50xOkLk/1ZM1CAagMPNVWBj+c+WGy2r6ubWWUNzg+Vsk2PZp2WvPRsAHKY5d+ml6bnsU4J1u1i5TkDnAB8fWdZHM0z/kD9Zl9FvFrCXNr3MMpqfMrv8cmt68EH705Il7kImf8qU9YK4LkAn0OxYOcBcd0Antm7ua3PdMeX+MDcQ4OWXrHNxuYEbAeYAa04kmIIR+ZN8ScKqyGsA1uOnxFviVol25jfPXNch++f6wQNJuyY5sWz8zcVAj/sC98O+/RDeA8PZA3DYlw3nAxhuc0/dR+GvLXOsqqzKSq9bXe5iuB3LcJwvDE9MdkxQ3SmgRgXd+ixlzxSnes+JHRkS2CqAgttGuI1+rYQ1+bu9TIBDkh1UOwLYo1OjndAvEiG1z67dtWB9+9zY52GOwoLA5HOV31XujtMk99WR2mHpo9MtaosoJ6NC+yzHOnWGJwGBXQLCAkFjdh1jK++T1IrAURjQufvOSz/W78rFE6PGeiSur2nokKEvht8SYwstecWTrgq3o67OaiMjrW7/n1jSy38LNtOUwuzgaveARw3tWD72Jb8D9riHtaEfaNaJWQ5stS5pDY4DJi0lxsruKAvG7uH/idsmut69TvMsQSK46luKCG5sfqzRexctwcXfW2w1TwWtsHo4rF+thx6gQnzC3yc4wBwZrdZy79Z7EeEe+s6v5j3gwdwgfwZyzsqxLbfb0hbNWWTVj1cP8t797vAAYIsTtmNf9JhcunUZrBOyCbAzHdUCDloPMFj3Qp1rRUTLLaotWQBygDrClMjPMD77mTBzgqUfnm5xu8W5/DsAwUBYW3GbxRVoH0iQCJDFT4+3tioxiAKchILbk9stJSfFoqdFOxmV1UR6AakwUWpJBkhramiyhrcb3LG4Ss5OEBsGs+HwIydc1qcTQMNbDUE49fvfN5s9u+sQHaATGHImUJYcOdeSCgXq3pcfGhosadl/AxDHCgA6rDuwCzOBFEZQjdwJ5MJhWe5bSwK/Zx2VZW3Vba7XK63VegO66BgBA0uOFvIsAOK4KXEGwDh/h/Ptqeufsi+O/6IrvB5M1P/fXx7IPj3bCm4rsPGTx1t7lELpSxvsi298Ye0VQu3evAe8BzboAf1Md/2EbnBlv0LfPDDqglE2/ujxVl1ZbZWPVVrpTZ6Z65tHN37rhG0T3Ikbxgf9v3UZfVfTjkhzArGEVakYhQlCuHdDBgiI31KAQK2hYALzJ+bb+HHj7Y3X3rDW8lZbcXH/y5msJhQsCY0wg0YVb/ap2cYxJ49OtobqBqu4tyLoukBOmMAfwNPppym5H4YvY2KGzT1+bsDOiYlzLB2MHI8VjXQMJELECkkCXEumXWK2/fZmS5dC50mILkMoS+hthY7z9NMNlpNxIxIDHTGXi0Z+WzgvjXF5HL7nNf3rzg66v3ma+QKWw0LInfcAWRjGmfvOtPmvzXeM6IpLN+znpK8KtOt9IowaN1X3AsITZ0205eXLreKuCmt4r8HK7yzf0FvuX99ID0y4dYJlfjPTjkw60v6jW82HNbbytyvdZ3Qjh/SbeQ+MOA94Zm4Q33JYua133NoK5xQ6QNBWsm5GaBCnNGJ3FZUkQV3YuU4gsy52jlyppFlBSyxy7WqfrnXJ905UdwOeQyeL9lZOL01sXk21JERKlltSRpIdcMQBVrtdrSXsmuC0tTYwVI9fjhmj8HEYnMGydYIvqnGr/l3lhFktVa2ustMscrIKJsTacSnncsy6hVzZrrmh2TFzLnxKuBWQ1XkfzknDd25/eq3+gPMCAPfKK2ZVVdI4UVg6W7l3VLGedJK1bLGvxbz6cHAsYtvYrjsD5yq8w4xcJxvnXtfjcM9TcvVcvp7YOVg6x9TRvL5zceFYFU6ULix1+Xj0tD39utOt6rQqV5yClEragWldPs/7VZ6rRM46JctyTs2x3+/ze3tj7BuGPEbhLfqO/qvSYF97w/D1+M0a4SuStjBp9iQbf/1423bnbe2bsd+0e1rusapnqmzpuUvdhdMId5E/fO+BXnmAa19+Qr0NsAcm3jPRttplK5v34TyrfqbaSv/mWbkBdvkGh+eEQmjNsXNvr83OEWYbf8N4x9QgRbHsvGUKDyqcuJGWemCqY4DII4vNirXtdtjOCgsLrXRpab/lBlFd6sKFKoQgPOxAE2ojAk+N7zVa7nm5lrRjkmXnZlt5ZbmV31HuQqywYg7gEoJmEdBNGJNgn5+pxvYAOVizMJOmv8PsGMxcWdU+ZmeqKGDsWLO77jJ76SWzWbPMttjCTNWrlpOjSgkVSjSqd+tZXw3GhwHUfsJgcC1WDuDI/nTfxcjB+Omfs/A9LwPIwywh9woZu+NmzoBbzTc6JzrI3wuP1wkcAatNC5qcZqALlwt4c5HVslyt93TP++6t/zyAfE/+FfkWPznedondxabrdo9uDcsbXP9b38Kr/3ztRxpZHuAn0YO5AXzPYUvGXTPOvrr/V+2Nl4Or/qLLiwZwj37onnqALg6c5AEDMHNIe6xpU56c4hrcc9Kft+O8NV/eqL9hiAjrUR1LCDZ3rNpytbVaeWG5LfvJso0aM7wReX5U3LrelxkBmHOAppOxa/xAgE4dLBJ3TLS8zDwrqiiyslvL3DYub07bOlAH2BKgQxgZ/bq1AJ3GC4c6S98XYPvDHwIW7tVXzb7znWA6++yzFqiLSEy0xOO37CrWcKFXwFd3wCjA1QXkeBwGcfxadYI491z4oDvvHYijEpVj7Vy6QKLGcayecu/C+XYweuQOUoUcLqZoK21z1coexK3h3D78OebSMa5Cms9kckqy7aFbkW4ftHxgzUvU/UGVz1WPVLmlD7vxm3oPjGgPjDgwl7J3irHACpBMHWYbun7o9XEIh236ArqQp6C8PjE3UdGmbFv22TJXnUUuiLeh4wE6HpD0TuEC/U7XtMn/nmzkVHXUdNjcacoh60cDUFG0EDdNwC4v1qbMnGKFiwutsaixTzl1gEUH5qTT5RirTiDnwqICrg0fNNioc0dZ4qxEm5I2xRYULbCqhxQaFZPlAJoAXbgyFnZv2Y+XueboDnABrjqBl8ubI1QtAFVy4B0BcGtXwvo//mH285+v8lRBgdnRR5vNmGEmSRIbPdqSTvlKkEOXIFAIcJQMiAvjhtk49sNjfqF43B3QMTLPr8+E18Jz7LrX9uE2Yu77TYcKaeERBicPknvCtk3z1wb069uNf379Hhj989GW+4Ncp8uXkpRi43Sr122Fbi1VLda8uNlqn6+16kerrfalga/2Xv9M/SveA5uHB/hJHDHM3KjzRrkG5ITVSPbmJMTJyrEDSp52V/awBJxEwibvuJwdpBAQQpWsg8vX6axaBARyAozgpNQZ4uF+7JSx1tzSbOVF5dZaqvypjxqt+Jri8Kj+foh4AIbMsXMCKFRFNn+2elht0n2THPgHAHw49sN+m3XKvqqeVN4eny3y61C7p4KSDgxZuVlWUlhiy87fOJYuaZckF2p1IreEWslt67ZQwEA+H98HQq5bJmxpcz6d4woGWM+FWcPhVn2WT9z9RLv6iKsdQOoCR/KXKzjgMw+Yyzjb7KCDzMaMkYBfvHRbBIpOO83s6adX+aygwGz//QNQN22aY/KSzt69CzjyPQSkaeQArOlP9zAM6sJfy273bt1Ve1illxfOtePXrfNx+CIt3HkiLGzM8zB0aAZ665sHkBZJOyzN4kbFWVpkmknt0JrrpNkobcCWZS0uT5OcRNq+ra/wqG8z8Ft7D4xMD/CzOCLAHNV8NMnmaAmp8YMOCItSKApmxrED+tsBsu7ArvMk6GQYdAKLitH60VEWEy1dL2llMV5SYpIK9wQEmtQgWvetLa3u6pOTNCcIcnKqH6semZ+wIX7UvN/htkEUOVC52N0cmBPwAsRXPlTpmtt3f31jHpOLB+ACZNCrF4AEIIL9i99KoE7AbsrWU+zzTz63pT9aujG7cJ0ZAHMs7iKFz3GYoesMQfLZpD1Z6qxUm6Hbm2+9afO/uNQm1F8UtK7qDLXiIy6ASv5Wshrj5cKynd+Z4v+NM9t6a7PjjnP3yeTPyRqkKYeunH3wQQD2wkez225mu6qLw/jxlnjbT7u+f/jBsXSs1w20uc06/+4KsYZfD4+p76ITM5Zf+V7CxK0G5JA1Uc0R332Eox2Ioy2bB3FhD27UPdW/Y/801qUjxOZI1iUmXqozDa5qu+njJnchWz+n3irv3XAV+EZNwG/kPeA9wDX6yDBynuKmSyYiVyKgSkAnT6b81kBugEo6ThAO0ImRQDfLJY93nljcCUYnNBeCgoUD7GnhpMMJsqy5LDgxdLJ1XOUD5Mr+3jvR0pHxTgyto4Rlba+X2C/ABWZoTdNTMLWhSH1GBLr6w1zhhZhhQrvowxHeRKCWJu9tK9vciXBhx0LLm5pnEddF2MYkhZNCwOeQhYsPQE33BaADK4nWIce9dOZSm/mVmeq0cIk1l+sbEaUlYtXivgOkJgjUdYU8hY0ATdjo/RSKTVYQ7S/KBz34YKvbe2+zzEwdU6oEixVy01KhrhFVLS3WrhN9SMUQVqLepvfeaw3lKpDY6SBLfOcudzHVES+dPr5bYsm7AF2wG/c/39e1rHMuXZWv+jv82IG6ThAXZuXaG9S9Y4A0/9aa22b8xJhLlA+nC2VyP5GFaauVdE9Jpbsoqn6y2km7bMaH7w/Ne2DIeICz0zp+GYfM/PptIuQnxYwWkKM1D2r56HCJrWgvb7cVl21Yi6r7RGLytL1AHeKi0bnRLmRFGMHJOHRf0T8eFh5w7NwWYsTS462xrNG9n+GJT3pgkqXul+rYHPTllnx/Sfiljb7PPiPbXSzAyiF/wWeIORDuRUbEXSgobw1ZlJT8FKsrr+s1I8jnHZBG7hzjul60unQLFwY4YMrfAqh8njnGrSZsZct1Wzp7adDNglCrxvjijaNs2iGPW8L4BFty8RKrvOpd/WqELOvXynvj4oaLHi52tHR9l77+dTNCqTNnmqtoHTPGItLTLUbgLjs62raU96Zqga8WZ2efabzmlcon/dGPLGHe46uNiz++1LoDOR53hlXD4DUM4Bwj5/PivtSVPcqX3SQAAEAASURBVH0RdhnWmiKiqMQoJ1BNGJXQac1/aqzqUeVgevMe8B4YNA+MGDCHR6ke5EeI0BMJ567qTydS4OzSczYunDVo75Tf0YB6IF5gLi4nztqa26z+jVUyJYC5tAPSHMtTeV+lFZ5Z2Kd5wPpmHJ3hcizpslDzzKrWUA7MiaEDgMHSAZQo1skem21Ln1jqqk57s3MKN0ghYFzuHZCDXewEcfwNK1jxzwob+/uxhi7bN3K/YQ+1PmQlNyqkqtdd/pwAHXNZOOM/we4pRsBU6JBTetOqfFGBrop7KtbKO7T99jMbNSqQKkF3LjfXLCtLgndpZikp2j7BEiUyfICGXKTlQ0KzZWUWf+DMIEQcZsLF/Di2jn13N8AbvWI72ccuRk75iF1ArjHk0h26b+Yfb5wHxlw8xrJOznJtzsI5n7XP1br33hczbJxP/VbeA331gH7WR461FLa43pScUNuntLt8ubSpae5El3FsRo+U/UeOt0bWkdKmqy21zZLTkq19RntXVaMLKQrwhJmsvnqFcKoL0yt0SxVld3OyGJLG4PMZ3RiAOro32Fj1NhXTZrd2X3s9j/8jwAVYGqfqQem70RWCSk1Ys7BxTIQqV+52i3tqjJ1uVG7nX5VvD3z1Aft5ys/tNyf9xsr+sSpN4IvXjxLLJhAHaGIB0J1yipXert3V/T08tGMcu/4IPyA/jo4QCrG6wohK5U7xeJGg27PPWkisXf1WW9m/p093BRQJmv/U5GT76K2Vlnne5K5+q4Ttwjl1HA/ALgzcuCDregy4UxiZnLjGuQrneus3D0z850R3gQGDTKoKcj6V91dayV8UMvfmPeA9sMk8MKLAXNjL9ItkQT4EaQjyigiZehu5HqCvKoxt4phEq01eJZXg2Nv4aGutVv9PgaK+mquiJmwo8IFI7bqMzya5aRhVp+V55bbFrC2s4fQGK7t5FcBabdvrrjM75BCLVOFBVIxUgmWCgY6ZqipWqPP2p8zeestyHj7RvVYSdbLZhAkqxY6U4tfNZnNusuI/vmSRl0Ta73b5nV2afqld8vVLXBh4XXlrbpBOhq5kV+07Vt8fqlgPCtg2JxJMFwieD3eEiBIqZqFwSEsE6x9xhIUokBATZxdeaCZQ16i2YB9uKS06AdLyS9+1nKt2crtLPyrdAThYQoSRS/68bgDRvMhXpTqH9fN/E++eaKn7p7oq7JYVLVb3Up1j42qeXcUu9/Mu/XDeA94DPfTAiARz+Gb0haMda0GiNewH+R7eRrYHAPXl5eUWFS/A0WmAr/jIeGtubN7oytLwWNyTq8lnLiyT0f217o/5TMLgUSTRUtRipaWlTkZkvWCO3DSxWR1vvGEdKjww8s9k9a8rZFzzX9tL4cwmyYK8sbXkVd58U0hSQJJ2W9XKWgMIFhdbzd+fs6g/HuBCq1dvf7WdPP5ku3XPW21ek5i3rTRYOLwKM/fII258x7h9qDFPOCEAbsqHM8AkenMs9do/66vowd3zHLIlYuZCMIgKtUZpvqPEIq588EGL3yXdYj+OtapZ51mHxozQ86WnPmm5/zzUsaNdoV8Burwr8yx+XLwtvWip1b0iQOhtwDww8a4AyMWkx1jz8marmF3RJy3EAZuoH9h7YIR6YMSCOddAXd0ZOGlyJU8iureR7QHaN5GvlpaVZq0z1OZJArIwc5KZtsrm/vl8hCtiKb7ZEIMEQ0cuH224ygvKLT073Up3LLWGdwSMutsllwTdF2C9BEbtjDPM5s9ftca//20v7rijRSmMeaKqSp898kgrXrjQFSSEBOJGbfGe5ESE5yQfUnVHkcVdWuAA3WvTXrPpO063lkdOsc+zbje7554AtAHkwsAuvJfZs81OPTV4nhAq1aoVFSYUGizNYst4jgUWDrApBg5dunbNacU229huyqd77Y0qi/1GrmXM+7NVPp1locMPd+3AnPajfq3I/QNgA4oTxiVYyW0lHsiF34MBui+4vcBS9kux+FxJjixtcOkoKy5eMUB788N6D3gPbIwHRhyYo7VM5rcynUQJenOcMJdftHxjfOe32cw8QN4cjFl7h6RKOnPMKADI0q2wubBfjhb2L9zRgNw4Pn9fZu1VqpKOa7X2pnbbbvvtbMWOK9YGc++8Y3b88Rah/qchAF13IMfgJyukKpar/dhj7Z8AKFi0Z55RgUO0hQoLXScUVzzwwgsWOuww2/6qIpt350RbmLTQds7f2TIOy7DxN55oS0Knm4k9c2FSxgXQsZAPpzy4SwoK7ArpLHY8+aTZ3LlmL74Y5MV9/jlrr20PPBA8R1eIc86xV7Tv+IkTreqmT5UrJ6YRI1QrwEmhRhjEAbAn7TrJ5vx0jlGU4m3gPJDxzQxD4Dp+lC4q1Jmk6t9VfW45N3Cz9SN7D4xcD6zKih4BPhh37TjLOTPHEiYluORdkqOX/8wDuRHw1vf4EAlrNjY0uhAnGlrk0QHm0KPrDwvnyREuJO9rQ+bkboSX6B1K4QLV2GvZF1+4EGZMnF5jWZeJOUv6w3fM7rpLum+fWtY5Ey3zLGmEPXGqy6tDTNcAXWL2qvVw5W9WOq2wtyvetplRMy3jGwJshEth3QjRrmkCdL8W45ajEGu8mD+qVSPuuCMQEV5z3TX/Fktof/mL2W23WdMSSb+Itas45V5XxAHgtJqaoD1ZesDKHXfCcfbOD9/xQG5NPw7A32N+NsbiRsdZc2Wza/m2sSLWAzA1P6T3gPdANw98KTOHqjfthRAgbVneYiSJl96gsMkwNHpspik5Oyk+yaqLq13oatkFy8w31B6Gb+YATtkJBLvqBBFOx2TY7qm72yvtrxhK9v1hVAAyPHl5aB7S+H5D1lah5u9ikefNm+fYqbXWbxMSUy5aC7lws2YFoVaAF8+LKXMAbPJkJ7mSFPF7a1e+GQaYLN/tj0GI9vnnLWeHW61UjNq7W2xh6Z+q/dzeqS7M/PFXPrb8nHxrPvAem/+0CijIe4ORo5AhzM6xP1XSFmv/0eTvSWcudM01AQDsPuGPPw62Z17kzrEoDGyAOIVpD1FHiCc1fpzGyBUwXC4gF6qtdfIq8ZPjXQXw9btdb3Wv+hy57m4diMdTHp9icZPiXJUwfYs3Rrx6IOblx/Qe8B5Y2wNrgbmCOwssboKEINXmKizWSWiI3B0q7NKPTrfWZa1W9XDVsBGGnPHWDBu701hFtyJt5fKVVv9OvWse7oHc2h+IEf8M3wjhktSDUh0LRpur5xc+b4u+vahfXON0zySbkZScZPXjVBzQA2MbqgdLS0otWpW1tE9CEqLLYLYkxpukdlqCb6bApIlHs9Fa8rTka3lAYGuFmLP6BQss6ccH6BkVmR7yO7Oddw7AnsKzpUcrJ075cM0HHGCHS+D3luidLebWOa47RdU2VZb6lVQr+ORWW1x0RsDOAeSwMKCjo8Pbb1sbwA49uaOOslH/OsKKg7WC/5eLCVehhv3yl2baDxIqhnSJKltjCgpUWSs7+2xrvvFGW0p4VfIlk2N/bqP2yLf5l813mnjdh/OPB8YDybslu9/8+JR4q1tc537vB2ZPflTvAe+B/vDAamBu+kvTLXaSxHR15U44CB0sCgTobuCkErgYVy5RlMIdmd/OtLQj06zw1ML+mMeAjDHumnGWfmy6HTL2EHtLt5ULV1rN0zW25GyxAN68B9bhAQoU0CvLOC7Ddkza0e7QDVaiv6xpXpPrrtCWJz25nsrhiAhDI7Gtoc1yxuZY2ZSyVWDu0UfNvvpVtVPKdm3AQu+9p8bmOvkq3LoI6Q/CrgqBIlmyrdaJ1jLnuRILEZrVuk5CRGHTUVdcYaVixDquvNIVLsQLzMHqVVz3haU9vr0Lc2bmZzqQa7d0MnNhdg7nhIHdH8X0UZBBRasAXXHbCXZA5Se28NmFrjtA8RNPmKkYwy64IGDoKIwQ+ItSvpz2aO8VCc5961su5Dp5u7ttqwO3srevbbT3f/W+Nbzff+9Df72fm+s4+b/Ld5XCTXVNVvNcjZVePzwjMpvr++OPy3tgTQ84MAedDvNGfz0aUNNmiJOOO4EI0NU+rzCHcodiVP1J6yEeh5vTU+m0+JTFa467yf+e9sI0y94r236k29W61X1QZyv/qFycu1Vh5817YB0eiBkb41q8jfrJKNe3tNmaxWTV26IT+4eVC++SC6SmiaqUVWeFnhh9fmm5hbUoZy1cEeueoLm9QFsrYcp337UpRx9tCxcvNlMhQZf97GfWId22DxQ+tYICSxa4K5Ce2zz93S6mji4Mxdo+RyHOMoVKQ6+9Zg9MmhQUHmiQ4quLXZizKqXKkkcn2/S977ZPXz55Ve4cRRcYgO6UU8zuvz8oiqCwYa+97OlzK832PN7sUI1JDhzMHVIlVLuiQad5xyksW7psmdlVV9kvrku3e+69R90x6uyFG1+QskqNG97/NzgeQLaJvr2R0ZFWN7fOCk8rHJwd+714D3gPbLQHoqe/Ot1o/O2aJCsvp/GjRmuYI3FSqb83L9RV8xrmmoQrBJuwRYLLp4Clm3DLBKe0vj4RzzWGGNA/x98w3hAXPWX0KfaxbleWXunmVnhG4TqPZ0An4wcfVh6gWhKBXMKYOYk59lHDR1b/Ws9Cob05UC6W2pvbLT4t3lIPSHVs8ZdtH5Mf4/oJUzRRX1tvLUtUhIAhFUJbLIoSyDtTnhmn3eSCAqu7+mqzH//YrWa//W1wj8zHgQdanYDdXAGtqLw8y5sxw1Yqt67js88cmMoUg1ehUGnxLrvYFsrR+0Q6dA0vrLCK8yY7di56Wwkrb5toY9+63pY1/SAAcBREdM+f01hOekQacdZZqeoAHCwcAsF0gCAkK9BoH31kE86pswjpmC1+6zDLqrvXrjuizdorVMUr0Nv8xdq/QcHB+P8HygN8JtGTa6lsseonKIfx5j3gPTDUPRCZtL36NyoZu3lxszupoLe2/BfL1wt8AHt1L9e5kEfdG3XWWtKqcInaDW2TaIQ1N5Xl/TrPZrw9wyacNcHOG32ezW6fba/Pfd2B0gX7LFjv8Wyq+fr9Di0PxE1VnqjAXN5leRY7NlYVnSqS0Wd98XcX9/tESV9ABiVDDBnttjZkpDZEjxIbHhvlQGBXuFHsWiShVIR/zz3XTCHXVuWZ7cuA9ENd0x57LAB+p5/uqlrb//tfWyEWLyQwliIgiEBvBQUKr7xiIQGu7dmellvKYSv/0XPW9JnY+tIWi06KtpQ9UwKGDSDHAtvGgp10ktn77wesG38TWiV8qmpVV+ggMAlDlxnxtGVsucL97lQ9WGUpcxXSfq/BFYVQ4OCBHM4bXKNamouHqLgoJ6RedIXeN2/eA94DQ94D0TByDfPU8FuhDKo7e2rhZuQkZyfNSrKYcQrBqqF36oFiGgY5LAK7mLpzqh0bdaz9T7driq5xbNySHyzxIK6nb+gIXi9xh0TXVJ6qUVg5Lm4aljVY3f8GpmKy6ZMmQ6C4TixVVGJniPJL/I/WHWLGMbESua7RxRN26aXq2Rq07uogPIkJnKEh94ya2mdIhLcSuQ/pt61mCqkmizmD22uZOtWFRUPbbmu1gDkJ+MYJaDUvXeoYNBdco5vE+ec7BrD89nKLnaC+sekqwpgab+PfuMmWVJ+1CtQRbhWgG6/1l6i1mH3ta67Dg6uwBejRrgvdOMKxBx1kJDwk3nKBq5ZH3492ab4Ty2rv1qD/MeYXY5yCAcwxreS8eQ94DwwPD0Q2fNLgqPTeALnuh1b9mMIwSkwmJEJz66zvKOwzSDbtxWk2q2mWnbTrSTYmaozNrpxtC99eaKU3ltpnB3zmgdwgvQ/DdTc0r0/aJcnlyVH0MGn2JJcT2lbb5ooelv2k5xc3vfUBoKW+pt4SMxJdvuqXbU9uHekM0WKznOgwK6ubQ6REglvJOdtjj2Bzqlrvu88alP+mGlVXTRq80O1/gbkk/dmGvMhPfxrk1tGVQW3AQs89Z82ESDuZtkXhzWi7pXVqbptnzfObxf61upZkyV8TqwhIC7NzjClR4iVi8lyYlU4PhFYVCp526KEWDXjUnJ0cyVNPmf3jH664ipAq3TY8kAs7fNPdx04UWE9RL+Kq1n6r4N50R+P37D0wcjwQWfVIVZ87ICBTgl5WW7GEEfTbPvEeCZKeqCv6AbC8y/OMqtvt67e3E/Y8wSbHTbYHqh6wz+Z85voFLvrWIiv6tQ8NDIDrN6shk76aFPRIFbNM5TZhelgnmGaKfz4/6vNeHW/MaInlzoy3lL0VfuyBIe/TWtZqqWmplv3d7PVuETcxzmnMwc6FBJzQm3Mm0NWhIoIUqk5/J4mRsP31r2affmpPKw9uFrIf90p8t7tJFkRbWIdad9nBB1vEMcdY1nHH2XYnnuiqYgmxOnCmdVypEEANMWEBLxMgK7tdubSfN1t7Q7vz1/jMm4LRyYHbc09RbYlmCtWeN2eO2YoVQY6c1lhwxBHW9vDDZi+9FIRg997b5fSRl+tBXODCTf1/8q7JxucYrcWWLzrzMjf1pPz+vQe8B3rkgegVv9QPbj8YuXb0m0yKVchVPwgUIaTul9pvOUfjbxxvKXukWOrMVDtOtzm6PVr7qDV93mSN7zda0W+KPBPXD+/jSBgifka8qyQFuNEua8wvx1j8tHgXaqXjQu1Ltet0Q8I2CU7oNzoj2rWXclWlihjSmYHCiajoKIuJjrGULVKstVltrVo7ghCi9lN5v5L+uxlsdtz0OCvOKbaErARLnJW4TgkUQJzL50tS6Le2wQFNN4yKE6gG3VFg7gWBMRfCDI9/3XXWMWGChaZNMyPcSdEBAsIs551nn6oXqmPMFE4NiT0rV+izQiHboyVb8sp3v2ulCrvCuDnYGM6H2247x87VnXizNb9/rNPg43uesJXCpi/rCk7bGqLFbKvw7jWqYrWCgkCGhNCqKmW7jJy5hx4y29dl93U97R9sWg+kH5PuhKTbWxVinSe21pv3gPfAsPGAzkr9ZxX3VFhEbIQ7MSGlQCLtlEenWO2LtVb8p+Je7witI04W5DRtNXorO1q3m3W7s+JOa14i4YgFzV9arNHrHfoNRoYHhD0IXcJAwCYDpAhjtlW1Wf2b9V0t3gBR8VOUQ5clAW1dqFBN2mU8FGnF0uHCjMimtVtzW7OTDnHrS7POifzGxVv8WfHWXNNsfEfC1vxpswORo2eNtsYTVEW+Dj07wBwgMi45zhpLG1dVF8K4nXWWfSgJkQiBMx1SYKpqjVA+WkhFB+9J5+0IhVUfVQh1jKpTi773PTP1Z3XN7gF4sG319UKhURb6znfs34AssXmRyrfrEBvnjpbQ6eOPB5IiyIqowIILN6ra6Q5Dh4Dk3X4uCYu5wXqqTjUkUNCrI4eOBRkSxhZgdIbG3Q47BMyd5maam7dN7wF6BTuN0eYOc23kNv2U/Ay8B7wHeuiBfgVz7JMkaSr1OEHSSYKiiLRD0iztiDSX4Ew4FhFi1iG3Dcs9N9fp1qFdF77aJ3djXOo4+7puDbrdpdvlyy+35kXS/nq93kr/XuqZOOc9/19vPcBnDxBGw/aJsye6zxzJ943vBdWrhEup6nNSJZEaXesimk04lrxQkvVDjfpbfVzp2epe457n1fouMk69RjQ2QIylKbHJMR6xybE25swxEvVtdr1Wqx6tcvtZOWqlpY1Js9qDa636qdWlINhfzCjpP7Z3GBXnq5nYuUoJBqeK+aomxCnh3wJ1UxCHZg9LvDekFl7PilHbU2DpJcKnkiKxtLQgZw1m7w9/cPIgkdJ4myCR30VUuepxh/LxTACxBWCmdlo2f77rMAGrRxVqzRXPWnbh8Q7IwVKO+vcUq0u4Lhhfrbfsk0/MpHfnGEG2j40NOj2EJ08FLmCSdb0NGQ9Q2MJnl/B/f0VshszB+Yl4D2zmHuh3MIe/qv5d5cJXrTNaLXG7RIserUq8XFW7SmyYkyTsHT8a5Cmpw5a7GnQMRmS82hBlWK5uFbot0+2a8mtcnlDL4hYrv6vcMSfr0r/bzN8nf3j96AFEeAFgueflui4MADJkSD7/+ucu5w1pEqy9Xp1PmgTa1M6OXDVCsh1iLdpKXQCyxzOi0wOf/bZRbQb4iUmW9EOy2L5jI5zcR9w0fScyIyzjqIzVwBzhYCrFE9ITrLGq0WpfWAP8iA3rKC21A8TAPaBK1lh1e+AL/TByIgAz9UZtkNbcm2LadhbIe5OiA4CU2DUn7Ev4U8xYh8Kd20uWZJFCs06T7vvfN9M2RuEDrNqvf20RYtZCSIuogCFJLF7jE42WsGWCRaeqslXztDnlZvvs49qBOcfAuCEKTO9VQrSwemFDtoTiiJUrzU4+Ofysv9+EHnAXL2KnEQpuL9fFjjfvAe+BYeUBxUDssoGYMeCr4Z0GdzLkx8GxFjqBKlgV5BgJxJFr5PKOxHzQeaK5vtmqaqvUk3GpFX9WbHVz6lwvRgoaSq4tcSdcKt+8eQ/01QMFdxUYjdtdwcPHTa7LCQLBidsr5Cq9ufZKidaqahMmmYIIpERglLuqSXsxAbYDQLqLEMUuYdk6YjosLlUq+2mRQUFBcruljkm1xP0Su0KpgMq0g9Msf3y+VS6pXLt7icR9EeX9RFWiv1Rhw/OqbK1Ac45wKk3uKXJQNWmb1qkUMGt98kkzOjvQaouqVYoU1B0C204Vp3PF3EX+3/9ZSIvrrQrYQ5QY0IVcCbmBGrdV+W6tL8+z5N2T3YVaVFqUxX3whJ2z1yWW/pWv2KfMSyyhvfpqUJxx8cWu+tb1Yn3hBbN33jH7+98DYEm3CG+b3ANJOyVZxjEZFp0WbQ0fNaz9WdvkM/QT8B7wHvgyD5AWE/qyFfrrNXcVL3YC8VPaghFODbcFI3zVXqcTZa1yNUpbXRgVYVXPwPWX9/043T0w5bEpLg2AvLbGuZLceKbGASgAW+rBqe4Cg8/eWkxY90H6+DhpZxUKKacUZotQKuLbNDfPnZFrlWWVVvj9QidgnLNNjlWVVFnV41VW/biA2pqmsKgdf7xFqLfpCWLdZgu8hcrFktHoPmywdIgK//nPZkceaYZ2nJi8/MsucwLDd8KivfiimSpb6eMaIfYtRLcIWDPy3wjNAv5Uzersf/9zYdgJL+xnqfunWkJBgtW+X2vzSq8NiiAI+SpUGysAqS1NWXnWQJ6cwr52111BUQaMH9W23oaEB1znnCPTnYZg+ezyId1ze0g4zE/Ce2CIeaBb7GNgZ9b4sa+OGlgP+9F74gG05QgLwr6Rf0mngZiGGJcOwAUEItqwxAMJ5JgnhRZc4HSM6wjaZEkUmLlg+VvnW9136yxxkipc61XBqortdQI5Vp440cmPhATCZkukd6wA3cli2J5SNep7ql5Fmy5Fq6l+1T4ml41QaGqq2a67Womem60lksb3s2YphKycPOWyhQoLzf72twAA0vSe4gXacj3wgNlFF7nK1OmqTl3+vXInxxI7JtYViox/7TRrurjQkjWmeDxra2210ksuMfvFLwKG78Yb3X4jxPiFFB72NnQ8wPeB9BeXRqCLGm/eA94Dw8sDUZruZcNryn623gMb74Epj0wxtNsoXqh/td4q7qywUGrI8ibmWc3KmqDoQZF82koNtLncO/HidIGIkvQIhRYthS1W8mKJpR+SbqPzR1v54nIru7HMFQ+tcz77729GGPP3vzdTJ4gaMV4vq0/qShUdpCqHTkNag6ptSwBqYvBclwhkQgSoOl5+WWBynIo22sQO6qABcYRIyW8TODSFTF04VB0lHDv3k5+YPfOM5asqFbDWdNezllJQZlSup2SmWFtEmy0b8wOrUOsudOxC7BNB4xtuCLpBMOavfhWEX5FJeeSRdR6Sf3LwPYDYO5XJfC8WHrJw8Cfg9+g94D3QJw8MGjPXp1n6jb0H+sEDU/8z1RXgRMZEWuPCRseONS1ocmCkPEWhSeGpiLgIV5HaD7vr0RAI8FL5yn6RS6G1XvZp2TZz25n2ybufGB1WjnjiCHvrlbds6TlAqDUMcKQerfaDH5jR2J48NzFhIRUdVMPaUU3afXn++UAiBD04OjLcfLMZYI2wJzl1Cte60Cp/v/56AL7If0Ni5I47LE6s3wrJmYR4TftCaiVhZoK1jm51LF3etRNs6R3KswMQUv1KKBVWj6IH8u8uvTTo2Yqg8NVXO+HgNY7I/7kJPEDVtdKZrb1WoN6b94D3wLDzgAdzw+4t8xPeWA/Ejo91laH1K+ut7rU6K7mOQGPAwnEyc9IjEvgFVA2mUWRBmItc0qyTsyxvyzxbMG+Ba3GFxA9ADnA348UZNv/D+UZx0Wq6jffc47o52NZbm0lXzgEy+qJKUDhG+W9tqigNVVaa0aUBfTeAFQAOqRJJmzjgpZy2CIVRDxGb94QeH6tCiQcAX4yHHh3dG1Tt2gqLB3tHGzExfjXx+1j24g+taWKTjckaY017Nlnmue8J5GlOyrdLF6iMkzNhBkPLlwfAkiINwqzMydsm94CrZIUZllH44817wHtg+HlgcM9aw88/fsabiQdG/3y0Y+DiBC1aFrVY917ELUtarPkLtZUSSEInDrmcdCWDD6Y1fNDgBLKzZmRZeWm5NSxUrtxnTVZ8taq6X6qzj575yD796FMbO2ms7Xbibjb+b+Mt71cCY5iEgk26cvbYY0HvU9p0UeTQ0mKtKlwIoTF3/fVOZNhVsJL7ppZbBqgCsKH5psKEkNiymYwn1u0BvZZOpwi2BQBKqy5KFbMdMGqPPuqqZCMefNBMeXHld5a78HCt1VrS1kmWfNMEByTjBeTEE1rx4sUWUkjXVbHSJQJgKJbP/c3+vG1SDxAmj0gQLaePPnmj3rwHvAeGnwc8Mzf83jM/443wQMaxGZaVlmXVHdVO4mbNIZAfSdknxWnJIV5Nn9bBtNxzci1jiwyrr6u3xkWNVnZzmcVPj3dTqHyw0nVBQaGfzidLRy+1pOwky5uaZyl3pNinsxVOvfDCIJxJb1QxXrTpcgzc00+b3XefpeyVYsn7Jiuk+0+LOjvKltz1z6AQAg04QqFoy0l+5DqFZvdWn9YX1EO1RkUSVKWGQ7HtsHFUsi5UTtX550srMs7aVShRrYrarM8qrW58nW2TvY017tWo9l47mwK/9ickTci1gw3EKIYgREuOHnlz3nrlgZwzcyxmfIzLr0QNABYZALbs/GW9Gqf7ylRWR8ar96+qqnurodh9HP/Ye8B7YNN5wIO5Ted7v+dB8gCgCPZhH93uXXGvwYKtaXSFaJjT4LotIJvDSTLn7Bwr/dvAV12OumCUpW+dbi3NLda0tMlKri+x5F2Srea5mq5pMjcWLPWgVGuZ0mJ1Y+pseeIFKmFSqFQyIDBxpuID1yNVTFvBySXW8bUOi9yjQK1Ts23c2HG2QsxaicKtY08osWUAPcAf1arkz112mTUp9JpCjpsYvQ406dCr+9GPgnksWGD24YdBeBYgRweHfwoUirErvXmBxU6OtcLsQsuanmUFd+9o1xw3X31bxcgB3NTz1e1LYV8njaKqWzfn3XcPOlEEe/D/r8cDaYemuYprmOPW5RK9ptuIUgL4rNJXeOK9E23R8YvWs/WXP01BEJWsjIk8jzfvAe+B4ecBEiUuG37T9jP2Hui5B+jxm757uvK7I6zw7UJb+n9ii9ZhADrXiish0uWwwVbQnaHxfTFNA2DpR6Q7wJg+PV0RrpDVL6l3QC5tnzQXtiTsuy5DA6/+rXqrzTvS7IgjApAEa4b0iPLbxo+9z9K2kcSI5EkwGJeashpbOm+pVSyosMZPG63xw0aLXDzf2qJVNEGVKQvFE+oO8SmdIBgPVk2SJS63jpCswrkZKoZoeu+9oNIVkKYesFS8ttyhytbJ2kaR2X2T9rUl2Uus+KNtzG69NWDgAHFo4hHSRTR45kyzMWNcONYAld7W64HUA1MNUd9QR9BCrnWZBKglq+ME1BUdpd0boC5131TXfWe9A63nhYxvZBj5pAhif37k5+tZyz/tPeA9MJQ94Jm5ofzu+Ln1iwdoCp+nW6FujZ98OTAjdw6WgoUTHM3k6S1c/aTATD9ZwjYJBtNCB4qYhBirr6h33SZoV0f7rugYfS039M2ETUOcF3BEhwZ1W0j56Fank1f9jAoTo3SWV+5fRKS0w6SbR/iMlmSrCXHvvbcZOnDk22Hbbx/0S6UXK4BNIVdXIUtLrnfftWO0rmphA0aNe5hAihoAbMceqy4tvzRCwS/mvGi75e1mjR+fZp+d+/dArHjatGBsuk8gHEwHCEK4KqLwtn4PEPonRE7FM+8dC5qdYaAfX6jPEK0SpVMYNzXOJtwywQpPK1z/gGu8QvGDK/jR28Dnw5v3gPfA8PTAhk4Zw/Oo/Ky9B7p5gErR7XR7tOHRrpNgt5fXeti6otXoDgFLR5cGwFdrUWuftedS9kyxhO0SXFgsOina2pvarXF5oxuXnD1afgE8oyJFmAek2lpz63pip53MGgVM6azw0UdmEuSt7Xqxhw/QqKOPq3qtOoPJKygIiihOPdXsuuuC1l8ANnWMeIh+rewPFg9WDh25c84Jer0KXNafdJLV3rCtxebFWnJBsqXskWL5f/62LY/eJQByrM8+YOkI7zKO9PC8rd8D6YenW2SK+qXSXk7h1eonVr+oaPqkyYXfyZ9L2CrBCVGvf7S1X6EVW6SYaEK2fO69eQ94DwxPD+ja3Zv3wObrgfiZ8eZkRySf21rRurqkx3oOm16qLUtbVvUCFv5IPSDVcr6vkGQvjRZdWd+V3MgVeZZxXIYlbJHg2LOWcuXHqVq19OZSq5hd4XqcwqKxREX3AMwBjArFwMybF4QvAXQUJnyuMNkJJ3z5LOnHKqbNjjsuqGZVRaoDhIRSkS8BvNHpgU4R5MXRYxV2jjApmnUAMVg5wORbbzl5kwjy6yRzQmVr4/xGe7bxWftx3I8NMGLkxwHiKHhgHMK3jEObMEKt3tbpgdEXjnafC2UHuLBq5QOV61yP5xvebbCWZS3uImTa82JBe2hJX0nq6vzAZ96b94D3wPD0gGfmhuf75mfdQw/ETVYYSblv7+vWtrLnYaT2KgE6SZYgJBw/JSigiMqIslHnjbK2yjYrv718nTMgLBad2dmDWLlMhLBg+TBaJYWqQ06YlWKGmqeDAoeUvVMsI1+VrFH1LjQahUCvwl5farNnm33ve0FnBUAS20g7bryKEXKl8faeChPaAWZUn6qa1bXiQlgYxk36c259if+SI+eAFoLBMGUAOxU3uLZfADbAIQLDVKRi3/ym2U03BTlvrKeuExHabwhwprBp85UPWunFezh27oFtHrBpW0yz5m+9aQsX7BiweQBAcvsIDZOjh9AxunUwjd66PBC/RbwTYaYzSFtx2wbzNukvHJWlTiJioaNHR9vkhyfb50fpvduAueKHaIXiazrcBcwGVvcvew94DwxRD3gwN0TfGD+t/vEA4SeYjVLd2ip6DubYO5IPLBRGxNfEu3wwZEuojB190WinSUd4ivw0Oji4XDseayFfjVBpqFngTUwfyeWAQ0Bc97w1KlPHTB6jeoOqYLsA97mCiA164LbbAiaNDhDk0IlZWyLttyUUMMCeRWgwRH/pr3r00WZ0f7j//gAEohc3Z45rz+XafCFRIjkSB7To3EAuG+uofZcDc3vtZU6UmJZgt9wSiA0LOPKcEwN+6qlgDmIMq//6gWU8v5d9MfoLOzT3UIs/hF64N9qnU19cdUjozWkuEWIJQ8zX22oeyDlLEiS6GKC9FnmeiFx/mZHrycUBFxJJCmMjrVNwR4EtPnnxejfjwoNcPApk2L7kzwL/3rwHvAeGpQc8mBuWb5ufdE89gNSCax7e0eZOXD3drvt6zZ+pclA5S+117e4EC9vmFnWNCCePO7FhpZGFIgLJCGQeKDwg1w7w5oBhN9kHOjvE5sfajG1n2IL5C6y1LMjTI8zaBtOmsXpkjz9uxoLtt1/AvMGwAdQIkSJZAhNHCJXKVEKeVJN2Mnku1IowsHLu7KCDAuBHCHbx4gAQFhS4kGrKCy9YpnYxSstbaNqhYwdQ5PVLLzW7+269Itt7b2nMZVvxtcWOKXp8x8dtp7yd7NDdD7XI9/exeaMFKDHJnETee691SPYkTb1bq1Ul63rMBq+O6P/DUjpcILR+0Wplf5eve2AN7zRY/NR4B+jipkseW6z0+ozCh9T9Ut1FSEet+hS/IZbWm/eA98Cw9UD0sJ25n7j3QA88QIsulvaWQHakB5uscxUq/epernO9XWH6YsfGGiwdbBwhUWRA3H7E4sHEtZcrYb143Qnl5N/FZsba9BnT7eMPPnaVpnWvaGw1OofRc2BOY/bann020HOjVRegihAqVaMAOpi7coWGAWAwaoA5cuIEvKhEtaOOCgAfBRGICC9ZEmxP71eFQ2uVL1en8G0hAJEQKe24WA/gGAZyTFj6dIROG2e/a8uP3sHlCr6101s2ecJkO3674+3+BfvZx2NeN9txx+DwxBZ+Q49uPuMMD+YCj1j2mdmuOpULhA1VX3du0nVH/mX4cxk7LtYmP6Rw6zGfd73OAy4kknaRULAKKzByN8tu6RlgdBv4/7wHvAeGnAf0i26XDblZ+Ql5D/STBwhVwUBEp0dbW1Wbld3Ut5OW0/YCo+k86MKqVL0qJy8qXrlKydHuREpuHZImsCQwIDAkADXuk3ZMsq132trKK8qt6Isil8dX/3rAisDUxY6JVXQ0wpqLxOYpV6rHpj6oLj+O3LfJkwPwRlHCzjsH4dJPPw0KJGDUKEBQrpsrYCAUC7AD5AH66NdKhwbW++lPg9w4KlcRBwbA/etfgQYdIsOsT94czB/sHjZ2rOvhCgBs224va/jZHa7nbH1KvZVmldrRWUerxuI8K9n9BgsBKsUIfqy5xyk02ApwHOFGeJRuJaQHUF26/MLlvfYI+Z5sH5WsSlWxxwC3mqeC/My0wwLxYb4X5ONxIVL7bK01L2ju9X78Bt4D3gNDxwOemRs674WfyQB4oKNJrFytmLIGAZJ+MjfePBVIqHoQho4Toyt0UFgsMlZCwylxlpKXYjHR0v+KVjGEFooaIiMihaOW2odvfejCtg3vN1hH3SoKDomIyMhIpaspT0qivj22114LGDKKC+h7CuOmStHIGTNskoDSYoVB25AUgVUDmBHGXbw4aK1FcQNFCIRgAYT0Y5WeHALBEWLPYhWWbQYIUkjBEjbW1fhufTpGhI3iBiRMCOcKrDXPOspW/u5hl6/YcUiHPbzVw3bMuGMsomgPK7ssz1aImWsuKDBDh45tGXcEW+aJmRadq5/lkCpYNxJgNX/e7HLsotIF1mR8ByjcgTFGagfJHXI9ySGtfqTa6t/2IdYR/JHzh76ZeIBv+2WbybH4w/AeWMsDsFuwESSGw6Bxoqx9XqCmH8y1P1L4FQFXcuNg7Ugmb62TJl1Vg9WW1lp1cbVVFlVa+fJyK1teZs2l6t4gJo48Orbvbo7Fy4qzjjaBuY96AeYAYHRUwChQABA98ogKNNqsQoAqW6zX4QqHfqKQaqihwezFFwNJEEmJOHaNqlUkRpA7gS0TaIs8/XQ7Uazbe+TaXXyx2dy5bviu/2DzAIKwcgC3O+8MXoL1Q26EUC/SI6pwbT/sW1Y7/TsWed8/LDI70gpzC23/1P2taMsii174ntUWic3DGEf5cyPZcs7IcRcIsGuFpxZutCsotgnnc5J7B3jjYsEV5Sh8C7CrerCqd5+zjZ6N39B7wHtgoD3gwdxAe9iPv8k9kLBlgqvucxIhIsIq76/s9zkBzDhBIuzaUtjiqgOpEFxz4SS7JogLT4ZQbPKoZGtplMbd3F6AORizHXYIQqPkxcHOqc3XCeoQMVfFEfUCSXPFeoUE8FxYdJddAuFewBZhUkR8DznEYk880doF9CIlX3KROjVcD/BjLAE7O/xwszvuCE81yJvbddeA1UP4l8rasNE9ghAs+XTsA9kSsYX1Dy60iC8WOumMZVnL7GupX7OyLcss5t3nrGaB1gVUomX30EPhkUbUPaK/6UenO3mRpo+brPpxAek+mGP2dL1AdbVjkyni0dL4QaMDchTlePMe8B7YPDzgwdzm8T76o/gSD9DTMnGbRJfPxmrr04j7kiEG5SVy7DLHZVpdVZ2h7N8re+yxgD2DdVMnBhMQm0seG+FLZEP22ceitISQHIGFo60W4Onaa4OqVYVo24uKXHVqqLLS/qfFCfySf0dYlnXpGPHAA6umxWvk2CGDAhuIjEnYAIiEdLmHcUPg+JprrOHtBifXEjM2xlZmrbRZqbOsema1RX3witU2byukrf1SyDECDbkbNA0ppqHYJpxL2RdXwBhzYRCdEW0u/KpCG3q7evMe8B7YvDzgwdzm9X76o1mHB2DkYOcItcJSwID1V6h1Hbvb6KeQpMiblGflReXWNL+XYI69VlQEXR3Qk6PiFOCGMDAAbI89pI+XZ+2SGHE5cYgBKz/PVb2Ss0aolhArnRoAeiyEUvlbodRIacFFKReuA/Fg2n995SuuxZdRZEGOHuuHgd4ppwRVtNdfH+wDMKe8QbeeOlXADFH5GzMuxsqyymyL1C2sfka9Rb3+rNXGfS0I35IHOMIs66Qsp2HYXtZuS85e0q9HDyPsinf6dVQ/mPeA98BQ8YB+Yb15D2zeHiA/jVZFiP1S5UeLryFp+jYmJCY4MeKNnh/ACaYMEKcwq/3ud4HkiHTdWsSkxUqGpAXQRTUqIVYAIHlxAD/YNxZAHECPhccCch2SIelQHlxMVpZtozy4j7S0ENolV45KWPZ5/vlBVwdVwZ4pgHfrc89Zm9hAx+zB4CFu3GkV91aIJQxZ7jm5Nm+7eTYpe5KFTpNG3w1XW1HpgeHVRsy9u9jI0sWGqosBXt68B7wHvAd64wH9UttlvdnAr+s9MBw9QBP7+GnqRKDG4uhwJe6Q2CXXMFSOh76teQWq8PxsxWpdIno1P+W+uf6qhEzz880OOyxg0WbPNjvgAMsS8KonJPr004HunDpPGN0YEBImLEsf1n33DQCY8ux+8stf2msHH2yG/pxCsR0KgxZJdiRN41ygvLhXtG4IAEjhA2FVsXaJYvne1HMdSJwAHMm9AxQCGtlPp5EXFmoMWWxBrNVn1lt+Zr61TW2zkpM1txFma4VYX/MVpiPsI+AP13ugTx7wzFyf3Oc3Hi4egJ0jdOk04EbHWFxB3NCbusgxZElcO7CNnR35ZmLPHFv2xhsBu0aIc/58t7SLIUsSmKvnuZNPDvToYOfoj0oXhp//PAiZInOijhB/bGqy70kI+DbEgMm/Q4ZEXRsqtt/eLlcF7YTMTMuUhMl74Rw85dc1zJtn9sEHZgKCzsiDoygCpm8NQ+SW/re5Z+da0TZFNmqs+rx+FrK5U9eonl1ju83tT6qsI+LV/aO0zYr/WLy5HZ4/Hu8B74EB9oB+Ru2yAd6HH957YEh4wLU7UojV5c7pxJm8e3KfKwb788DipsZZVn6Wla0os6ZPNyJnjsnQuYEQKmANEEUIlNArRRH33WeNqkD9gUKib9KLlWpTxIPVVivm7LOtg4IGwrPo0anbQ8Rll1lIrb2+GD9e+DDLag880OwPfwgKKmDwtH21AFqlmLh8LTx2+nVPPGF27rlBCBegCEu4fHmwr3U4LKyph2ZfW1abZYzKsIQjEnrcxmodQw6rpxJ3TLS0QyWfkxJtTfNUxfqYGExv3gPeA94DvfDA2pfKvdjYr+o9MNw8QJUociE0vkfsd+yfxg6dQxAz14zWG5dYfTFCmhQl0M6LBSD13/8GbJlYs79r7ERacf35zwHAOu00U8abba8wrOvPSjhUosFxCqcSOq1Wvp1gnkXutFMwK4Aa4JAKVYVrm8XqLdd66WLrXCHFlVcG6/Xi/7Jby6zywUpr/FRN5VvrLHOHTJv2rJjAEWBZ385yof+ORukL9kaSZgT4xh+i94D3QM884MFcz/zk19pMPFD1SJVjP5BsQOAXNijv8rwhcXQUBLS0tvQtzBo+EqpTb789kBcBhH3ve46Zoy1Xo8CdVODMzjsvEPitq7NqMWgfUrkKo0eOm7o+tBLypWpVodf/qb3XRbxWUmKmjhJ25pnBAlAUoGufM8eqFZKNo5OEgODGWPEfiq32hVprXNhoLaEWS9snzSb9a9LGDDVstokdH2vROQqxRkc44emSa+Vfb94D3gPeA730ABzAZb3cxq8+xD1AMnXaIWmWsleKOzkO8ekO+vQa32+0uIlxFp3a2b8yMdKq/l016PNYc4fk8bXFtVlHhBgayXdstP3+92Yvvyy12Aizo48O2DJCoPRWBeCpErVaodNIsXehm28OChcIxUoTbpZkSIp23tnOVG7cOypiCBEypauEwNqrCsMer7DtXFqDYYA7gCKsHwUQ2rZDXSYcKwjrtxGGFhoSLRHJkpDJjDOKI2LGxwypcPhGHNZ6N6EPK8U49PmlrdZQlMxZ7+T9C94D3gNDxgMezA2Zt6LvEwHEoVXF1T5G78W6/9X1feDNcASU8Ek6p7I1MjnSUvZOseonFF7chBZSm6WoUVFWMKXAattreydR8f3vm6kQwXbbLahEJWSKfhxsGzlw5Mbdf39Q2frii4qpbm+RyoMLUdSAdhwMm/LtisYq7Kzih3evuirQqkMwmLZdKqYICRwW6/VI9XJtEbhzRRVUw6pQwiRD4gyRYFp50V6M7hG9NLTQmj9rtoSZCvEq3S8hS/qAk9SKTT1vEdLd3Cz7tGwnmUOP3tpnxEr6MOvm9hb74/EeGBQPeDA3KG4e2J3knJVjmd/KNHp70n801KT+oJLioK0U/Rm94vva/gc0xOTEuArCqBQBOvkpYUbCJgW/7dXtTtA4OTvZ6hrUBaK3wsF77x1UmwpsOQ05gBbFBwgF33ij2e67m919d9CDVaAsRA9V9OG0XsQllwTdILbe2uyMMwKH8TqLcuNmffvbVqQwasMNN9gBEiBeQMUsIVUYP9aBAXzyyaDgAv06MX8uJPvxx2s7fwPPtJW0ubZojqFLk+BzdoJF5UVZ6d/ELG5GBiOXun+qRaZEOgC78ncrN6Oj84fiPeA9MJge8GBuML09APsac/EYi5umkKG6G5iiajTopvE7VXH1b9VbuFJwAHY97IekYjQ2XzlL8h0MHVbzlPqIbkKjzVVTdJNFxkVaw/vKXeupkdtGnhwsHIty3EyVqOTI2YoVgQQJRREKoTqhX4okEPHlOTF422jb4kcfDWRNZswIgBkdIRD7FVgrUuHERQqpLhOQe0sFEa5P6003BX1bGQsA+eCDZmjLfU1dHJAqAdTRZmwjDOFcukTQ4iwiI8Lix8Rb0teSrOLuio0YbWhuMuo8iTDr/YaRhXWk2tqb94D3gPfAxnhAl9XehrUHdB5FNZ7qzNalra6nZ8V9FQ7QDevjGqTJNy1ostYVrdbR1OG6Q4y+UIBoExpsXHtDu2XnZlvKnoozrmn/+EfQAxWmLWzSdItEnHevvQI5EBrV/+1vZoRT6crAawj6traaoRcncJdCyBWRYAoalPv24eWXm511ltnChWZq2+VA4EsvBf1eawRwBdau+s9/bPGf/mQ/VGi24Gc/C0K4hGMBjBRL0JsVAIemHGCO8CzAbiOt6uEqF/qm+ri9ud2Sd0u28TeI8dsMLGFbsY2Z+vLKWr5osdIbNy/WcTN4i/wheA8MKw+IzvE2nDyQOCvRGt5ddQVP7ldrZKtj5Bo/UmK/Qq2Ep5oXNW98F4Hh5JA+zhU2JGHrBIupinG5SyTcb0prXa73sq7dagSgYiesMRdEfmHWCI3Cuv3qV0FlqeRM0sWOVcRqfdpyHXmkGY+pSqXdljo1kAfn8udg2wTs6pBAIfyqYghDpoQQ7V//GoRHqXIVW2cKrdr//hfkwKFXRz6diiKu4zly8CRJMkHgrvCpp8zuustCc+eaffe7AUtHiPePfww6SvTBoZUPVVr8lurcoVB43Pg4Sz8q3ZZ8f0kfRhwam2Ycl+FC+7CP9e/UD41J+Vl4D3gPDFsPcGl42bCd/QicOJIaMDax42JdfhX5cQC3+jfqLf2wdJcnB6OBkry3nnkgQvFpJxGhcCuJ9lUPCYhsShMei1CuWGJGokXmRa4SEFaf1ehddrEOwqgUHMCCUfSgCtJRYsuqEQEWqHJADjAHACOvDeAGaFPOm9uGClQKG6g4pYoVsEdlKgAR9g5WDTaPMWDuOpk5B+YocEAIOC3NFTlUq+WXA5i0AFM1qwOahHgJuwIK+2jkNvKZp3cp3Ttis2Ited9kK7+9vI8jb7rNU/dLdRWskQmR7vvqOz5suvfC79l7YHPxgA+zDsN3svalWmuv1UmuuNUaP260UeeOcg3LyTOq/FflMDyiTTtlctMoPgg1h4wTbO6PBG42odF6DMa1sabRYnNiLemrAlCYOjuoZjUAV7TnAnQJ3JmYsaVi5CIBd+Sv0U6LcCndIJAjAaCp7ZbtuWcA3BSWd4Dst78NwqiwbLB4hx4a9GulspUwLLIkMHSnnBJUriImTOEDvVgBeYA6QCFsH2PymM4QMH3c95PVv1lv5XeWW8uiFhduTZqVZPlX5ffT6IM7DMwvuX8RcUqNECvXnWUf3Jn4vXkPeA9sTh7Q5bi34eaBac9NC0JwOn8Slmt4r8Ea5jRY+R3Dl63Y1O9BW5n03ZR36Hq3qjPEpjbeT3LE0B+LmxRn9a8rFCdg9sqkSRYl2Y92ABQLbJiqTdul8xZJsQItuX796yDvDRaN0OiECUFxBAwcOnDkz7F8+GEAyj76KGDhBMjSH3nEqq6/PpA4wQmAOipWJSxsFFnAuCFn8uMfB5WzjENoF+MxY7ENYLIfrfL+SoPRQmA3bmwQbl1+kUDnMDLY34yjFV4V+8tnjbQIjsub94D3gPdAXz3gwVxfPTjI2898b6bFjFEFXIvkR5S4D6u09EdLB3kWm9/ukG+hA4PpHxWGm9rQCERANyImwklXZHwzwyqVk/a+pEOSlTNXSzutt94KcuHopypA1wEzR+4bLBv5amGjDyutub7znaD3KmFQgBdacYAzqlMBemLvqq65xjIVHq1ATBitOlWvuopXdXlwhQ1UwAIgYeEOPzzY9thjgzAtY5Kbx0LIlpy7frSKeyosdmKsRaUH+XMT/znRFp24qB/30POh0o9Jd10beH9Mh00LtogoPdbnp628zaqfFIvZzRK3S7SEbRIsIiHCdR5BS6/s73ofvHkPeA94D/SDB/QTZJf1wzh+iAH2wJRHp1j+lfkOyNHDkRN93Wt1tuzHCpF567MHorOjXV5WTK6AnE7IQyFcTd6jEzWWBh76gY1visURO9ZKvhrATZpvLqQJqEPXDZkRwqBbbBHk0iE1gq1cGRQs0ILr/feDbcIhUbXtcswb+XGEaMWybSPh4Qbl2jUhOMx4hGnJzSMcK626CPZPFwhYPl5TlWvcYYdZO2OSlweLx1i77mr2+OPBHPrhfyR36KfrundkRbvHxX8q7oeRezZE6gGplvSVJEvaWYyncBu5lhSrcGFFiJ6KaJ6PTJJmoYAbBSwut1XdRpwGpEL4sHLIB9W+XGttxfKXN+8B7wHvgX7wgAdz/eDEgR5i+qvTXcJ0dFq0tVW2uVZP5M0VXVo00LseMeMDEjhJE2aNiIywitnKBxsCRhjdiRuL0UlKX2mNcWLGCKcS+lQOnStUoPsDEiH5yiOjCILCBzTn6McKgwdzxrr/+leQZ4fIL0CN3DakTmjFRagUMCZ2bfmzz1r2gQdah6RFWihwYH1CtYRQ99rLkgQaW2H1AIIAN4Vz2xEMRqCYNmJUtcIOEuZV2LY/raO6w6jojgbMZcVY4o6JVnnvwIcqqT6FETe5naIjcixh4DpqO9xj8t9C9Z2ATq4l59EBPoWuqcQ1uRcGj3B+7XO11ryguT/d4sfyHvDH1XhqAABAAElEQVQeGOEe8GBuiH8Atpy3petMEBmjyreVLS53ilyh6kdWD+MM8cMY8tOjY0bGNzJcCA/2pGVZi0u43+QTv/BCa/n+r63p2AutcaLCnsiAAOZg4WDj6OqAKDCP0ZbjeSpTCavCtsGiEUrdckuzgw8OCiYobGAdJE522CGQKAGI0a0BkKicuBqBtxiFXSMVVm2niIIxKGpQ1eoWYgWLKa5gHEK27Ic5wQjSToxwK9W23KNl14/mqrQFjBK3SXQ6beSh0QoLgeyBsqzvZjlh6VC7wFpVh6sUB8g5cW7pAlJtS8oDQM9atGh+rBsREk3H49aAueMzBZBrr5FfvHkPeA94D/SjB/SL7m0oemDqf6cGoZrsWGtr0IlDlXx1r9dtFhpbQ9HfzIn8J/KxYFkckzIUJvqtb9lPJOL7h3IVt8Ccff3rAcO2335BsQOhTvLayJWDiWMdqlQBV7BzhElh6qh8hX0DYCEczHOEQmHnaPEFYEM/DsHh004zU3uv+nPOcSAwUlImHYsXu5BqhLYZhV8AiQC6Qw4JgCLFGBQ+kGf3+edm++8fsHkUTdDqqx+NooG0w9MCXUB9PzJPzLSS60r6cQ/BUGkHp7nwaES88txg4ySTQu9UOoesy8i75IbFTQ5a6/GZaqsKgN+6tvHPeQ94D3gP9IcHdOlIhpC3oeSBme/MtPhpEkpNiLLW8kB+pO7VOltxiRgYbwPiASolR12g9kp5MS6n6dM9FEIcCqaQ5RixakUUFFCEQAN7KlR/8YsAxCEiDKAjpAkbRy4d7BoGeEPEl9cBbiy8xj1MHFWpAD6KHwBnjIHuXHiBvWNhGxbGq6y0HIVfSwnPAubo8IDsSZipg91jTHTt9torqHgF3Cls62RU3njDTa2v/5G/lv/bfEvaJsmxYIvPWOzkS/o6bnj7rJOzLCZfvXsVJiUvDua27sU6JwcUXsffew94D3gPDBUP6Jfa21DxwMTZE12Cdfy4eOto77CmQvVXlTr8ouMXDZUpbrbziBkf46pGOcCWpcTKhoDBaIkxKyKMWlzsCg2Mzgq027r44oBdO/vsIE8O8EReHIwcoC4MyK68MgBhFCagDweYmjgxYM0UwnX5cEiZYOro4F4j/Eq4VmNECuCliNXbQi/vpCVG4VzxejZXIHGp7lsRFIbVAxySX4cWHSDutdeCogkqXwGgF10UzA1JE+ZG9wl1j9hYq3m6xrJOyXK9W6OTJPasIpH+sOTdky1pJ+VOiqElVAobh+5f9VM+raE//OvH8B7wHhgYD3gwNzB+7fWokx+abIk7JbqG4q11rYZ0AWHVpedwyvQ20B6gBVpUkhgrkU/o9g0J+/e/zQ46SPFfEeiEMf/v/8yOO85MoVcH6ABJdHEAfAGqxIBlP3aqlb3WybTBtpHHBgMHe0ZuGyzcbbeZqfrUAHNTpqw6VCRFnn8+YNbIkROg61A4tlqA7nUBsNfZHqaO+RCupbME2yAyTH/WsBQJ4A6GkIpXAbsEhXIbjzoqmCtzRwuPKtg+gDk3ab1XLjdNBSuIPffVCN0mbq+uG6pGDTWGXG4cEiPkxnnzHvAe8B4Yyh7wYG4IvDtTHp/iKvRiMmKspaLFgYm6/9VZ0RViO7wNigfip4iFErtDcnp/JtMTvo3KUhuqsbFWfLXYtd4YVagApsceC/LOAF6ArddfN7vllgDowdLxPGBNenJlefdZZuNxAjclhuBwRMscC30QstJC8Wrks8G4KUxqP/xhcC+GLVLVsLECak1o01G4wFisRzgW8MY9OXcAtO5hV0AdC/l6AE1YQ5i5Z54JCh9GjXKixPsrb+9RKm3Rs0PehP3TueKXvzS7/PKeeYR1yb8DjNJ9QmOF2v7q8hyRCEG/rS+WdZJYvpnxzmeuu4oKGspuLuvLkH5b7wHvAe+BQfOAfqm9bUoPTH16qiVuG7ABLaUCcm832LKfLnOhnU05r5G075R9UoL8KLVYQjOs7uW6fjv81tJWq3lWrJls9EWjbeVVK3s+NpWmABgYNiQ+6H9KQQOgjFApLBc5a/vsY4aYLxWtyler+KlCmNKWy7jleCeL4YAOOW+ALaRLFi8O5kAIVAxbh0KwLYAyctvCnRskV5Ki3LxamMHOkKvTqzv55IAlXKTQP7l4zAeZE7TsGJ9cOiRLMCRPFB4ugUEMF1wA5rR+hPYdokfsvfcGxzZ7drBN9/+vuCI4PrGLYwXiBFvtORV4NCN9orFDbWq/Fi3tNt0cq9p92148zvlBjuuygZQIkiIIcVc/7sOqvXChX9V7wHtgE3vAg7lN+AZMe3GaJcyUKrwYFKQN6EG56CSdJL0NqgcAc4gGU3nohF/7ae/kXtW/Xd81Gon0vTIYN0KS5MEBssibI6xJAQRSIy++GOTAkY9GdwdYOoATunACe5WXveJCoKl/FMN3sIAg7JpA1MTpb9ki2DQAHtWv6iDRQdhT+nJdpv3VEo4FfMHIEVYlfBoucIAdY3/ozFFpy3oAuTAYPOGEgP3T33M0aKRCwR3k5AEOFbKNVl5fK/NRezI3h/COqdKlR+xeezkWLkpANllh3iLtZxm9YPEBuXn0n91OxGBUhGXotjxjeXiEXt3nnpNr9Et1nRukAVf9aLXrd9yrQfzK3gPeA94Dm9gD0Zt4/yN291OfmWrxM+J1NlJeeqFkR96Q7MhZS0asPzbVgacdlmYpe6YEIVaBrfK7BEz6yZC0SNwh0fXNpQNAzX8Dhq7Hw6PhphDnXso5exGQA/iiapSeqoAgWDa048iJO+aYYFjCnbB0FEPAnGm9mhveC4oOAECyuuI6G739PFv5jrYjbEtXiEsvNZs/3+zaa4POElTLhvPswnl7ADiAFKCKylaAFYUPt98etPpyo+s/JFLIx2N+KnRoEdiLoFIWJrEzZKtXrITH5OZRmEG1LuuE2UMAZK002ZSPVw1gBEQiTAzrRy6eLFbfoYToBKvSjSKF1QyBZKpq0eFbj406X9XLtG7TobQWt7rexm0lArfevAe8B7wHhpkHPJjbBG8YrbmQHoEN4CTk2nJdsGwTzMTvEomLuAIBB53Q21a2Wfk/+g/MkUhPG66UvVNcH8+aZ3oJ5tB8U0usFQJFsdKSa3nwwYB5I3wJywVgg6WjkpWWXu+8Y/aDHwQ5dBQ4qI+ry6cjFCpwFKMwbet//2s1L9RY3HgdM8AJwAaQC9uPfhSEdimcAIxReAGAI8wLOwegg6GjGILHd9wRhH8BkBgg7txzLVpAqo0qXMCn1guRP3fKKWZvvukAnTLorARwSg7eN74RdJdQCzGXc0fYFsAI+ES77ogjAuBIKBggp1zChIVPWMzomICVa11uTRLvdf1o8YXYzOPFUN7bCV6ZVncDYKfsm2KxebEuVIvsCCDeA7nuXvKPvQe8B4aTBzyYG+R3a9J9kyxumk6kMqrkav9Xa8svXD7Is/C7wwOZ38q05N2SDQaNE3l/9/mkk4TSuVwYnVy8Xhthzw8+sAXKWYsmR26ffYIOEOSawWLBiO25ZwDYYLgInapPqmPbfv/7APiRX0crLoGrVvLW/vpX10rKtZPaWnMClJGbhtQJButHdSwAjgIMjNAuQIp9Ek5F5kT2TYkP3ydAGKeQb7Pm6Vp5qaJ1gkK5hVTXMn9CsIA/8u4AbwqbEnJ1PBpjwrqxL8AjxQ2EiAGXMIa0KQPIsU+OiyIIBI3FCkb99T9OPmSMjbGlTUut+scPOWAaobEjFL69F3DLnNYwQBxt22iRRmcGujeU/9MDuTXc5P/0HvAeGGYeiB5m8x3W0y24vcCQwKD3J6196l+t90BuE76jqQemukboJNITZqt6WExVf5q+XVHJUU6/Dr2yjTIKDm66ydoodCBsCtsGA0fXB0KqZ50VgC4YKUAb4VcAEfl2Z5wRsFvr2zG9VllmzAhkRQBTO+4YFFwA8sJGZwhCnLBohGIpxBCQ1B5dvl0zgA3mTQUbXxeQe1DhUXv0UTPmDkNIKJaQJ8ye5jVNYGu+cvQOFzh9DL05Wn4J6EVKdiVerzUQNuZ4YA4XLzbXZQJQBxiUaDEFFLH5sU6OJNMyXY/UcLg2pPVZXH9Y5tDNMo7PsIStElxIvaOlw+Wpllxb0m0N/9B7wHvAe2B4ekC/zt4GwwN5V+QFFXNRYuSWq2r13aBqdTD27fextgfyfpVnKXsoV05h0JYlLVb066K1V+rjMxRURI+KdpWW7VUbCeaYw5lnmv3hD2aEIWHgkPag0T0M3Z13BgDv8MODKlfJkzggBNiD3QLYkMP2ZQZACxthUcAgId7uJpA3Y8v3raIk10rqBRoVgtUMgrAnla2AL4AcXSoIr0ryxNn11weh0oKCQFtOIdBD9MJ85dutIERMyJjiCwHTnwjI/Q4gSD4ebB5zp7CDv1Wk4Rg8Cj8UNo6bqnZZ0par040LIysUo0jxBQtMH6wfOXmypK8mudzF2HGx7kKK94L3vPx2gVBv3gPeA94Dm4EHPJgbhDcx94e5rlcjVattxW0uIR75EW+bxgPZZ2Rb+pHprnk6unJNC5us9kWBiH42wEZUalQgDyJg1yf7yU/MfvazgDmjnyosHGHE7bcPgI8AVIQYrWNUKQqEeU2gb7lCsyFYLtajcAAR4nVJgHSfGLIfLHSW+NvfglcAR2LlKkorbFTeKCsJTbEohTNf41WFXCO++U0L3XxzENYVoHMFDeS6iXn7noDXbTB35MARnhVQdCBQhQ0fAuYKC83+8hfL1Xz/yniASAAe9+TjoX130kmBBArFHrCDYvgoWslMzLQPdWv8QGHgH36brdey9KPTnX4c7wMMbFtlm9W+UOu+g2ut7J/wHvAe8B4Yph7wYG4Q3jgqGaPTo629WsBBidoeyA2C079kFxnHqaBgYqzkODqseVGzfX7k51+ydt9ecmBOQCI6sx++ar/9rdnppwcFCmGh4FNPdZIg0ZIJYQ8PkqsGuwbDhewIrBYGo3fiiWZUxVI5CmO2LgOUEd7UONEqfmhD507hzdiV71lDSawtG7dMYd2plizmq0qMWqRy9k5RSPY2CiQaGoKQrQAlTNp5AnJ/plKV8ajM1frJypl7hf1ecom1ImWieUWIbQvpqQZAJO3GXn3V7KqrAlBIVa0YOxeiJXdPwDD5z9+x+NmTbDfdHm141Koe1fhrGLlxCEHHjNG2ckxHXYfr6FD5UKW7X2N1/6f3gPeA98Cw9oB+5rwNpAdyz811Gmbt9e0uyd6HdgbS2xseu+COAkualaQoXJC3OKByMMJRYTAXlRGE/DY8ww2sAdiC5SK3jaIBQq2yNlVutiHci/Dv734XDELBA8wc6/CYnq0UN+y1l6uSddIi9ErFVBiBAHGUwrTt99zjQGCb2LloCglkiAojoePsggLL1oNqAb6DYN6YDzltyIEAuACOqp69BmaP6lNeh50TsNtK272heaaoqraWkKzafCUL/JUC9ugjS3iWXLvuAI6cO4ogCOdqoatGdEa0C7ECxunTGjZCqnETVbmbp1676uhBblxHWYc1ftJotc8L4HrzHvAe8B7YDD3gwdwAvqmZJ2Q6+QQX3lnaZk0LmoZO388BPO6hOnT+b/MtdV+110qMsuZlzVZxf4U1zhX4GCgTfnPyJCmBREm/7QaJEhZkRKgwveGGgI0jN07gyvVeJWcOUIf+HAvFE+TTUeQQlhwhz+2ll9zfhGiPFAB7V5NcCptGqFPh1TZyz7rb/vu7YodmnhOY+w/M3913W9ZHv7Hyqx41IxxMXhshVMAXuX2wiOTAqTXZYrbT87UAS8mrRKvatpYWYPR2veCCgE0EEAJM6fnKGIu1FQUZzF/7T0n8xHIScuwt3WqfE0CjiwSMpABjvXLxkmNnS75RKQ3lba6jA5IwbaViKb15D3gPeA9sph7wYG4A31i6CkTGRVpbRZu1LGqx0ht0QvO2STyAQGz6MekWmxtrrRWt1vxZs628UoBhAC0iWg3gVWBB7hwsUb8bAr/knHU3GDhCrOTIAYAARkiEdPZJdWAPto5eqQUFAQMGYFOF6MNhcV7A3HXXdR911WO2VfhVPJrlKCevFBB2/vlWrv6xUeq3eqBCpE+if0d3CMK8VLEC+NCkU+h1JcANsCcGMeK886ydwgbCqgA1QBssHPcsDzwQMHWwkNoXBRYpvz3O4u6daAfqdlf9XUGI9WjNhiIKgK3mV9wgQCmmL/axP7lCB03Vm/eA94D3wGbtAQ/mBujtzTg2w53EadoNmOu1YOwAzWukDoumXMKkBGtvVN7i50322cGfDbgr0JZDw84VQqT1U5j1y2YNKEK+g4pOFSW4PDVEf8mhw+iigL38cpB3h4wJsiQqSgj9P3vXAdhWeXWPZMvydmwnsRNnOAlZBAgQ9gyr7NEyCi2z/LTstkChlL0pu2WUUSDMsqHsWcLehB0gZC8n8V6SZUv6z7lPz3EgQOxs+/tenp8sPb1xFT+dd+4958ruROICiQ1+aohl43otrI+L+hYkEiowRbs59/2sGDUxhmorRrBmTKBYs3//GyPIGn4rMYbUspMm2TpJKWnlK0dzZDvOzTf3gJxamF14occ0CqDqvAgIC/YsQKgwhCpOLdNa0BAf51mbCLjKAFlpZNXscV+x/zvbavN+6nTcay4CLgIuAt0hAg7MrYRPMX+XfARzg0jGPVNS9V01h/qVsC+3yZ+PwPAXhiNnA69OrmUGU31HzPj5N62ANQTmxMyuVDAnVavMhOVDJ3BGgYGxXGLDyJAFwmEkVa8mECVLE3+oFi5VD+c/tUxLpU/J5CXFsE2c6NmOUKzQn6nbt/XcSy8ZQAwyzdufBsRzxBx++y0KCK6mSM3Kx0qJBtjaKyngR8uVnMBkBD//xsyV6yt4PgJ76gKhcxAQ1HbJ4GWRaSug6faG4Q3xP05KsfYqmkflBDUWY04Fnn7aqw0UC6lZ4E6iEamA3XARcBFwEejGEXBgbiV8uKqT0lDNjmp16p7hl5EbqyUC5feUI2/bPGSFslAzvQYVl1f8sI/nSjoydRiQHU0gm+wc6+ZW2pCfnEQG6gAhUYTAUMqHLsk065/Yaus6MW9i7ti1wdpqdfVgBJJk/ivzXtmHcJshpkDnS8kqxo+vS+E6mAKG6QJyrMkL7L8/224Rk6kOTylWeuMlBTwnTAAotmCi1RsSakg8IesV1coJ+Cl9ynPJLpyPAtrJyCtuI04fVHyA6vur0bQH6+xUDyhWUX58AozarvrGajsCnwJ0b78NMBXshouAi4CLQHeMgANzK/hTzd6I7YRYKyUrhDgbt/+gAfgK3p/b3I9HQMbAvfbohZKsEsxbOM8a3QsArLJBcsnq5kJk59Taa2WOTz7xWmOJxbrjDm9P6u7AcZ0sP/S8TIe/X2PnrblsP+XzJoGFAJbUpwJRBG8JMmhJ9VwlgAuMH+91eBBwe/BBs0PZmLVsH0kAcfvtXu2b0rACVhdcsOR+1W9WDKPq+ZR2FetIxi/84ZMUMrBkjjWPw3KG4UFO9c/Vo+nA8zwmTuydtq/6QKVZ99jDOz5tT3WAqrdT2zMH5paMt/vNRcBFoNtEYCV/w3SbOC3ziTRPakYi6gE5tXDKHscvFzdWSwQK9i3AsKJhWBBZgMjkCGYdN2uVHkcyQTSnvzCWy4mhW+lDtXI+kPv+zqRiFVsn5kpAqytDdWmqv5PKVPVyYukI4OICdgSMAnJjuc7Xel29VHfbDSMJzD7WPuVtJ6AmCxN5yYlFW9rQa2LVlGKVITK313LR7SjYu8A6qPwCVL9WN6DyDu5TilgBObF4YgUFNMVMSnShfQoQ+uyeQN7f/ra0PbrnXARcBFwE1voIOGZuJXyEiSYyFayX05d5MppE0aFFqL53FTJCK+Gc1rZNlt9djoKxBcjn1DKrBTP/jym/VT2IRwTmAmlMtS5vB4jlOXYxZOrMIGHA961GOrNdGQOrbZhq0cSECcwJNBG8BdgHdmvW572pOjh6yMnbrhcVrVwLSdbOGThT6zEpTmkY/KNDYE7HmJ9v6wYp0EiQcSsaWoTS/FKPlXulHo1HXucpZAXWlFZlX1fVCNr2lUqW2IOtw4z9E4Mo8Cnmzg0XARcBF4FuGAF+1bixoiOgFKu+vNNy2MqpV5q50Pc9icyIG6skAn1P7ov8X+TjOE6T6ieh8vbK1ZLuFpiXObGBOabeV/lYf32vb+vFF3spRpn0ihlTLVlXB73izABY2xDoSrFyBwjIyX7kueeAbbZBEa1GmriPaqlVZXVCLzrzkZMxsNK+PzXeecdjGFnnl+D2e1+9PTJHZWJfTlX1VR4rx/2Z3YmAnBS2rMsz5az2xRpBtSILX3EFiikOCaqGUGBO68kQ2Q0XARcBF4FuFgF9wzAX5MaKjkDOZjnm/h8aGLK+rGrnpebeFVeQuXBjpUZgxMQR2Hz7zTGX0/yP52PyuMkrdX8/tvGCPQpQdnkZMgbT266iFV+OJFu0tg+lRwUSVc8msYLYLs0SRUhJS3Ysg2nOmJg7dqXA0UcDMjA+7jjg6qs9g99ljYFAGUHa0PXuQb8D+hnLOuW5Kfiu6TIPnCrNKt87pX/FEvKY0phOXq+8HOQO8fqMGYgr5avUsMQae+7pAT6lmY89dlmPwq3nIuAi4CKwxkcgfY0/wrX0AJveb7J6ubQiNviOkKEpCSB7k2wMunEQZp3ALxc3VkoE+hzbB1mjs7A7p8vmXIbph7KeajUNq5njviWCEDvXLcYttwASQrAeDmlpXspVNWpKi9LTLsDnYmLjJMiQwnXQIIApWClYrVNDZ4JABi8rOBVZv6YdCaf3Wt9DzUM1KL/zAMxiPV3ilVc8QKkUMuvlAgR3cQLLT5WqFWBTazPNAnuqpVP6VQBQx+uGi4CLgItAN4qAA3Mr8cNs/qgZsqdQFwD15lRHiMzRmRhy/xBM/83qAxkr8ZRX+6bD64SR0TsDj3KSLUx0cnT1HZM4b39efUex4vesVKrSq2oHpno0iSuUyiRTl5TBr1Skqlk76SRvnWef9Xq/duFIlF5N75OOUZzerH0TVXvejCq1IJOgQfV3GlKs0irF/PQkniAjFzz8cCRkRyIVq45R4hCpWcneBWiLkrzkEuCss7z3u58uAi4CLgJreQQcmFvJH2Dkswg0F/22yGu6zk4A+oJa5+l18N1e/IJxY4VGIDw8jN7B3pjROgN1T9OOY3UOATkNf+n91j1+CrBJbXrqqZ5Vidg4tQ2T2EGp2C239OxQxJKpk0MXR+42uUgvSMe7nKyP7l//6jFr2jfTqaZk9ZW18+d7KVX2e00Q4OWQEdyGnSg+IrjbhkziF4ceiu/YAi0p82R58rnhIuAi4CLQTSLgwNwq+iCr76uGOgIUZBUgKy8LmSMzMeq9Uai8tdIK9FfRYXT73YSHhNGX07yaeai6u2r1nq/PynVHMKfI3nqr51s3bZqnHBW4khBBPnTz5gECeOec0/XPgPVw2RsH0DvUG99xqqeKFadwe2LklDrVLAUr7VFsVssvDXWP4NzEWrkXZFtC0cYTb77p2ZioByy7SZQS0FWo5Zl6yH71FaAes264CLgIuAispRFwYG4VfnA1D9P5lN8zQZrIZo7JRMagDJT+tZRfWNmujm4FfA5SDCuV3chJ3TfWBMPmpIBFYAWc3Jq6CdmQjB/vKWRVi1Zb66U9VZ8msLccI2/AfP6NlEPTe/XvofF1plP7veb5yalGTyldATulXFULl5npzVK6atbzUtzqM1B9H8FegMBvEwK6SRRnBJgGTt58s9eVQseptLBsV2hUjLY2LzWr191wEXARcBFYwyPgwNwq/oBqHqkxU+HiI4utxVSoJGQpWIkjah6swYJrWPPjRpcikGimWXNdHHX96hDMTrE0XdrSCnoTMYQN4olumWpNnR4mTvRYMtmCCEBJ/CB7keUcKkeQvU8Vp9iMGBoPuwbbHXkkXqffXR8ycrVsYdZ6yikecBN4E5hTfZxUtjIQFigTyPNZPC6TPMYPVHPHGjr1h8Uxx3jiDNXP6f1qC0bmzmoAVW8nAYczG17OT9K93UXARWBlR8CBuZUd4aVsX7VciUgCvY/pjez1s42hK9iswFKvOVvmYNqBTFu50ekIyE+u+HfFYEdca27f6Q2s6Dek8KS85ro1O6e4ycNuBQ8D5CTUYpzaqsmUkVWbLZUqwdYi7U/gS9Yn6jlLq5GRG2+MbwTUVEOnzhAa11/vATSBNM1HHeUxelS9JrUtWZr86leAetfKwkTMosCfti3WT/V1d97pvc/bovvpIuAi4CKwxkXAgbnV9JE0vNIAzTK4LTywEImRCZT0KUHvA3ojd04umj9rRtO7TZh/4fzVdIRr527jNeyHyykQJoBazUMp37RcWtOwG4jAuxudi0Awi2iYH6PAnIy4BcYqpFYVWDv9dKB/f2+DrNNLI/CaIl87CTLU+UEgTTV07ERhSzJ26Xvthbann/ZAnUAavfCyaVnSrJSqBB1i8Qjs9jz4YDyzyy7eeyXkGDCgcwfu1nYRcBFwEVjFEUhxB6t4r2537RFY+M+FmPvXuah/uR5zv52LukQddirbCUfsfgRGXjASG8zbAOs8sw76nUfrBzd+NgJicGItMaRlp2HgPwf+7Porc4WMgRnWkzXRkkBsemxl7qpbbtvAHM9MYC7eEDdj4hZ51ykNqiGRhUQMBGpZ9LhLKM0rQ2NZp0yY4Bkbl5d7vnh8X5LGxjkHHOD1cVUvVzJwfWWrIuZU6dmdd8b4/fbDs08+CRxxhJcuJoNXIoPka6/VHt1wEXARcBFYIyPgmLk14GNpfIsl+5yLflOEPsf1wUv9XkKobwh98vrg8H6HY0G/Bfh4j4/R74x+aK1sReu8VqshapnWYp0FBAjd8CIg4UM8Ekd2r2yoC8fqHBK4yCxYtXyNbzauzkNZK/e9BJhjLSSCLUionZgYNA31Y91jD+Cbb6hbKEKjuj08+qj3mnzvlEbddVeytGEkCQATBHNZrOlrUk3dww/be3MpotiULb8+UI/Ziy7C++wFm5TRMH3rtmLrr7cfeQQJCSjE9rnhIuAi4CKwhkbAgbk16IOpvr8amvN3yUfB3gVoHteMCaUTDNiFckL8DstC1sAstA5sRXzDOJmIhM0lp5UgXh9HvCqO2JwYot9GMf+Cnpmejc2MoXV+KwK9AtYTd3V+vKH+IQIQ9pivd2CuK5+DpcqZXW1JEMQ18UEGgZxsT5Q+pX8caAzci6xZbUUFCtQFQoDMH1KmcgT5fIJCCbUbs9pFPal6OKVjycjVs7YurlZkqo/bems0ExhCooo//Qmff/651dE10rMuQPUsIZ0bLgIuAi4Ca2QEHJhbAz+W+pfqoVkjf9d89PplL8g/LZgT9GbWEqmrRCDE9BC/1wIZAaQXsT6LhsQZQzOQu1UuCg8oROvcVgN2s08mQ9FDxsLrFiJ/x3y0rNOC9MLV99+71769kN7X279ShI1vO2aus/8FxTwnogmk9Uqz/9N4i2BOqVT5ytGIOEDFqoCcbEcSCYI9zRqqpVOdG1m8EIFbi8AcQZs6QlQK9KljxJAhBuZi3N6sjz82Vs76tcqUWIMp3Ab1l2X6dTj97j5TNwk3XARcBFwE1tAIrL5vuzU0IGvaYdW/QGDHWUOtqgRQxPjIpy48OGxtwgTmBOyUllLbMBXdp+VxHpmG8IgwsjfMxjfbkXHoISM6JYrYpjFkl2Zj1Puj8PVmX6/yM88el22flYkfGlIgY5Ufxdq9w+hXUUjQklbKm5RyKkyfpk+jvOzU6YHChaSEC1KhclToOfnOHXQQQFWrte5iPZ35/EkwofZjBQVeupR2IwF2iVA6NcqaOAOIYuPE+mk7GgKAYvpYUzeW9XifdWT9vDXcTxcBFwEXgTUmAg7MrTEfxc8fiExwNdn47+L1BfLS8tn7tTjdDIjDwzyQp+f0JZgxJAPrTVkPzR83Y9qvpy1+Yzd9NOfUOcgbn4dAaQAZZQQBq3gUHVpkAFqsaVtlGxb9iwyPG52OQGsF60M5R4dG7QaleN4tqBpFIcLAgd62xLDdcw/Amrcasmghsm5FZ5xBDcT6eJngLMDUaUx9YcXGCbSJuVO93CGHICkhBdOsUYE01eFJBCHGzx/atgyD6THHSjzPQNh/zS1dBFwEXATWsAjw68aNtT0CAnkCakrNVvy9AjN/P9OWVXdVIfpF1Gq2ApkB5G6di5GvjVzbT3eZjr9lagsitRGE+oSMnVumN62glbLWy0JoQMjqvGR2W/MoGSU3Oh2B5thQRCdH0VrTimA4iLwdyLxdc43ZjkjUYGpW2o1gzhzrxTqAIG/BTTfhZXWloMVIkKKIIvrQjT7hBGz0xhuk75iS5cgbM8ZrNcbHbQJyAnpi+SSsULsvDfWUFYNHwYS6RUDtwNxwEXARcBFYQyPgwNwa+sEs72E1f9hsYoo5Z8wx2xOBCqWcwiPDGP788OXd/Br//qYPmxD5ksawbTxnMpXDHl81akS1FMsczgJ7Vsu3LmhFxeUegFjjA7YmHiCFDrpJiVfHzauvYI8C9B1POxICLLXlUqeJLKZV+1x+OVBXh1ymQ0FwN4ZMXRGBnQQP1VS4Tqap8CT5yz3/PFBVRf1DJvqo8wPVrgmlVgXmZE2ibWrpD4oscsjq1fE9VEP4z7qli4CLgIvAGheBNB7R+SviqAr3L7S76BWxLbeNFRcBfRHWP19vPUtllREqDVk9nYQC3Xk0vdWErDFZSCtm3WBpmAxLACvbwqX0jFJkjc2yjh5SX4odrLyFtVpudC0CNAiW2bIxnf1CCBVxHhTCosodPPUpa+DaCMaaZSRM1i3O+raIukMQvEW++gqJr78GPvoIuOMOFLJDRHSjjcy6pJm2JdsR7M2gsCGuNK1AHLcVEDOnmjnV4clUmOzeUDJ1i779Frjxxq6dg3uXi4CLgIvAKojACmHmSk4tQXpJOooPKzZLjVVw3G4XnYzAgisXIPJ5xCxMMkoyMHoSrR26+VDtXOSzCFqrWqEeuGO+GoPBt9EAdiWMssvKTKCiGj35yskLcNZxs1bCnnrWJqNfR1F1J8sFaLcjK56s4VkYUnMS1qEAwtKishmhbQiN5lBDUJem+jilRMvLkbbZZgD7q2ZNmIAm1cgpXSrmjQzd859+ivHqEnHkkYD86fhcgV6TQbDGBhuYWnbWzJkuxepFxP10EXARWIMjsNzMXO42ucaABNJTisr0oCkoo1+ysNiNNSoCalqeNSrLhBKyMol8EoHq7brziHwaMVsL1VylFVEQwq4MEkfUPLD8dWxFhxSh99G90Ws/2pBIZUzAqA4UYuRmHeuA3Ir6f6X/o4ptaGAIGX0y7PrS9skNqMqgafCMGaZizRk6FGWqcaNNSUSAbOFCJAn0+hKUia2LiaFT31aZDF9yidXDTSNjhylTPIXs8OGIKuUq6xO9n2Axk2nWiFSwSuOqZ6sbLgIuAi4Ca2gEAjyu5PIcm5rFKw0iP6hkJIl4E81saZKqZfW9lPe7sUZFoP+F/VF8RDEyB2YiOiuKz8u7fy1Q0W+LkP+LfISHhs1IWBYuYs5aF9F8mUbLUpzqsZbqAZpsTVqtnertQAGkblQyBlMVPCDD0tXy+9NfjV6XJYxe5zvQtohAjsBjwVVM+7mxQiOQuW4m+p/fH9mbZCM8gBY9Id6MzI+g7tk6zMQ57fVugcJClBHYbU3WbTqP4H217aLHnEyB82hr0nDrrcBWW1nbrzB/z+Hz2UyzSvNMfs9mwfBZqqejsAJk8CzF+sUXfNYNFwEXAReBNTMCyw3myu8up7s6v/ME5qJeQ/F4YwrQ0SxViko31qwIDHtsGIp/WYxYXQwzjpyB2ie6P+sg+5a+J/Y1Vidczho6qnsF1OQDp/+/thRA6/i7nlcrp9TrBu74USZb+P9cHQlS68sUOM52U0pjuxuYlfd/PXNEJlTSkb1ZNvS4ILsADa0NiE6NGoj+LotWImTmbKhvqwQR6qm6zz6A6uXUh5XPBQne0qiGDbNGLk4Vq2YJIRJcqn8rP3QkCQAPWG89/RfBY599Btx9N3D11Svv5NyWXQRcBFwEliMCywXmdKecuR5rVvS9RpbCB3OqGTJAR5ZDbaYqb3NF4MvxGa3wtw65dwj6/rYvi8fbMPPEmai8ted8Pnnb50Fsstg5M1sO02yZKVhrHUXCzYBbgoybfMc4zPSX/5+TMQI41mwZkOPv6gGrDhtSrMrYtv5Fsj9urJIIKL1dfGSxlXdklbHFHSfCaTRFmE6dFzNgJ+Z1xjYvsqSgGBuynu4bpk8PzsiAeOgZnGsJ1mJMv/rgTQDOZp0BHytda6bEfLwfmT7xclOefBLYd1+t4YaLgIuAi8AaFYHlAnN5O+ZBfUF9hsPSU0y1SoEmpk4pK7EWCTrgL7yhe6sn16hP9WcOZvAtg9H3/2ihEczE1EumYt7ZZDF62BCoC+Z67dFUPygBj9qhGYjTX4WAnYfnzBrD0rBMo6qUwG5W+P+66b2mHha1Ned01WGj5E8lCA9n6pz1dDLMDueRbePUxikao2CiJXUd8m8uWf6hmsbYbLbwajkFULuujkM9XwXi1ad12DCAqld7TOuSMH/fi4bDj7FrRPKWW4Arr+z4TvfYRcBFwEVgtUYgvat7H3DNAOiCqlST5SJS7FwilPAYD6axrH8ol/GMOEpOKUFsFg1UH1n+wvOuHrN7nxeBthqmleIJ5AZzkdFf1UI9bzS8xhZPbqy1EWj+qBnTD5tu6Vb1Lta1SG3uBOwkdEnLSrPrT3puOoIBIXNdqgjE+f8+3hxHQe3taFtIYDc3htY5VB7POgSgnYl86qSExQUXeN0iZDBM8UTL736HR0eOxEG0LHmIwgg3XARcBFwE1qQIdAnMDbphkLEWwQxeJHWdTNUOBeIsBmef0GQG0xQtXIa5FKhjGiueGbdUVuHBhStESbgmBXFtOxYxp2khfuFxEiPlhovA2hoBWZao6wlefBHho/ZGr70I7DbObmddg9lkXzUzrW43l0qr87HY2FAxexyPzLQsQu7cp9D0QRNm3st0+S9/CZx5ppkTQ4IJtQCT0pUWJs8x5Yr+/dfWcLnjdhFwEeimEejSN7kAWuboTANngTSmJQTmWGdk9UaqnQsRxPGiqfqiQCxVk8T36DmBvaLDilB9j1O6rq7/U7KTGcVpcmIymt52qcLV9Tm4/a7ACFDM0HLXq1jwwAO0FjkAuZtvjsZZsxDefT3r66rOJzmb5rT3MDb2rhdvZ/LI4BHshcpCKOhbgNEbLmTXiWsxcxrTsLQrwe67e1503BbOPRdR1tkt0cN1BZ6C25SLgIuAi0BXI9BpMDf0gaFWFJ6WS9UY/xmYI54LJAjeqAQUO2diCAI6A3WtHRi6TO/uWHfG8ueqvL3nFN539QNaGe/LWjcL+3H6rO4zuHTjyoiw2+YqjYDSoum8lEnEwK4OGDAAjeoKMWkSWm56CrjwQjSHylET3hzBUWNZ0xtB1sn7IXc7zyMzvTdZOnVGKSS4Y91k7va5WOfb6/Fd3UWeAlbbF1PHrhGt9K/DM8+s0tNzO3MRcBFwEfi5CHQKzK3z1Dq8XhKwtXkMmwE5AbogAZsUgB0BHYGdCSLk2SWmjoycrxq0lAcBnfpYLrzeCSN+7kNaka/3Oa4PQr1DVPV9bsq/xjcbV+Tm3bZcBFZ9BPbe2wNy7PSAQw/lBYl3l2rBxdRoOjtCtJ19NrbZdVe00Xbkfbb6Un/WSGwQIjd+Y8dqNid7FiBzTKb5EFoKdkAIQ787C9OuKgduu81LrSZYGMx0Lq65ZtWfo9uji4CLgIvAT0RgmcDciJd5t8vro4ZAm8xTfbNUY+d48dRkgE7MnICdlmLnBOb8WaCOJquJTIokVEtHpq709FJUXMGaFzdWSQTERvTN6ItXOKl/qRsuAmt9BGg5AnrEQe27sinKEiunLg/jxqFNXnOc32S7LuvuUFfnsWxq4aUxahSiRxyBKLs+hM89ylKx+htRH+P0vukoP3waZrJOLqnOEG+/DagtmBsuAi4CLgJrWAR+FsyNfGukMW86bp99s9Zdat/F2cAcmTmNQHJJhk4qV3PH7wjqUoBOTJ2BuqyAObvPO3+ebcP9WHkRyN85HwW7FeBoTpc0XYK6Z/jF5oaLwNoeAbXaOu884OSTAdW0TZ8OvPqq91jtvmQgrC4QmlX71nEoPcu0q9p/tWx+AFruu888MvW3InWsWLqi8zdD1WbnA7QlwXXXdXy3e+wi4CLgIrBGREAojIUmSx+jP6QEP5VG9RWramVk6VKCMQNzUrNq1tCWUrOAn+8/1y6M8Bk6LeWiLy+6lB9dy4wWzD09dbdsG3M/VnQERkwcgXW3XxfNnGa+NRPfbOOlmVb0ftz2XARWeQQOPhg45BBALN2ddwIPPbRsh7D++gAtR8COECCQw847A0zL9rpmP+TtkGeATtey6S+O97brb/VXv/I6S0jdKoCo9K4bLgIuAi4CqykCS2XmBOLEnCklKqAmI1U/dWoAju9qX4qV84g57xR8QEdWTsBOdXX2XvWvTCeI0yymzmfouA9tSxYBA68biNl/mr2aQtG9d1v611Lkb5WPnTndtug2z86he5+yO7ueFAG16lJNm9Ko22+/7GBO7/n6a0C9V594AhgyBBncVuv8VjR/2oxsTmlUvRZF/wvT32+9NXDCCQBr8fANb4ZkU8I+sG64CLgIuAiszgj4nFr7MYyeNBrGvomBo0hBs+8VZ8DOT68K0BGoCYjZUo9Ts7F5qfXsdQE2gUPVyaW2aUvtgy78sgdIy0+D+mcK0LmxYiOQvVE2+hzfBweFDsKEtgnWi7XuKZdiXbFRdltbbRFYd10gLw+IRoHqagT23BN45x2AooefHeXlgEyA33wTwQ03RJjALMaau6ajrzZA11bL3q3s9pGzWQ7Mc+4f/wDYsxWZbGOo9C4ZvaxBg352N24FFwEXAReBlRmBdmZu9Edk4wS2aATss3ICZ8a6kWGTiEEqVgNqPnATYEvVy7UfpJg5DS1505sM8n2spbMuEXpO8DHF7ImlE9hLpFMQwaVGxuAMx9BZJFbcj9K/laLPwD74iFNkSgQLrmGBuBsuAt0lAurcIKPfBnb1oAAiyWUmLUqi11/vCSMI8DBzpldLV0k7JKpZrcvDllt6EaD4IZ92Jg18voV2JpBY4n//Q6IwgZYpLd4NKI3PsdNOvB7yOiWBhVStv/89TuX7rta23XARcBFwEViNEUgf9d6odrbMFKo+iyYgJ+AlIEebkXhV3GPpOjJuKQBGSOeBPp1IRzCXer8P7Gyp5+KctWQ9noBdMD2IZBpTr/KJ4mvyfFK7sDmnzOEKbixPBMouK0PhPoU4kdOFtRdi4T8XIvo1GQw3XAS6UwQkeDjySF5TeFF5/XVEqWQN9O6NMOc+ZN5CTI/WUYnaRruSVs7NWpcMXgaBXIjsWv20aYBsS556CrsSzOnyNHFsNhK9WdfL3tKarQuEgNsbbwBHHYX/Y0r2WvV3ffzx7hRJdy4uAi4Ca2EE0pXetFSq0qACcmLdtCTjZuCK1zAbvEb6rJy/9Fk5a06ulYjpbCEmjsM86aRwFUjTdgT0tNSVMrW0/QjIBThLNEEwF4yx3U60nTTkym50JQL9zu1nzcjPyjgLl7ZdisY3GrHoZn75uOEi0N0iINsQ9VEVeyZRww03ICnbEQKu2WrHlcM0KbtEWPcGsW9XXolhBHnTZ8xATL8//TTA/quyM3nh5ZetT2uujNE5Ei0Ec828YD37LFBYiABVs8dwm3cwzZoQAPzzn7tbNN35uAi4CKxlEUhXvZq12RKAE+vWIbVqViNEYHx2yXo4riM2TeDNgJwP4pSC6DAMxBGfaWkiiJR1iQE5H9QJ2GnmesEEHxDMpbWlIRkV8nOjqxEoOa0E/c7ohzMyz8BlictQ/0Y95pzmmM6uxtO9by2IgMx9ZTWy6aYGzALs2JBG1q1tt908wYK85e66Cxm77IJxpaV4Z/Jk0m8TAQI6Y90uv9xTtf7pTwhffzrS18uyVl/JGJX3jbxgbbQR8sePx3iG4tY5/Ft6/31g//352yoYqgPUuf33v6tgZ24XLgIuAmtbBAIb1myYtBo5MnHGtPl4TFhKQIxsWXRq1BNFqGG1WnKxfiQtgyBQ4M3+Gdxb6rkTxtnzWmpbPrBT6tZn4tT+KxFLeHYlbAKfaEpg8jheaN3oUgT6nNAHAy4fgD/n/hk3cqp9qxYzfz8T0a9cerVLAXVvWrsisMkmgEQRYuqYUrX5sccMyK1PQEa3Ocx8911Pvfr3v3vnpvUvu8zEECGyb5kHDDXjYClZNRae8DrWp4UJq+0wTyDwllsAiSFW9pB/no6tuNgzPVb9n4Qe//d/K3vPbvsuAi4Ca1EE0o2NIygTkFsCzPEkjE0TK6fXlH5NrRNMo0hC79H8I5MfA4E4wjNBORND2JJp1USQzwncKb2qFmGqv6OJux0PWUI3uhaB4qOKUXZpGY7JPQY3c6r7sA6zT5rtgFzXwunetTZG4MMPAc3+KC8H7r8f5QRyU1jjFlVqVD50//mPtwZTrlK+psnehKOVAod8CrFUu6ua3ta5rdiPQO5p2p60ycbk8MO9dmHeu1fOz7/+1etoIaWsylQk3FB9XkuLlyoWyLvggpWzb7dVFwEXgbUuAumW4mR20wdqxralTsOAF8GWv44JFnij6qdifSBHrq598p/T0h/ajgCdD+rsURp/co5zUk9XvmgiCO2r5tEa/61u2YkIFO5fiAFXDcBB+QfhP5xqP63FnD/OQfOk5k5sxa3qItDNIsDUaoCWIzOZTk0qrXrUUd4JCjD9+tcIFBUhg9YmLWK9vvsOuRcegPStcsxfTir+2IwYnpAxsADiqkirSoW71VYeG6euFRJnTJ8OvPKKZ4kiy5Xx4x2Y62b/Td3puAgsTwTS20FcinXrCMIE3ho/bjQvOFsvxeBph/56WvpQjm5x7Y/95/yD86CcB94E4PQ7dWWeibBSrpyN/SMDOP+C+f7b3PInIpCzRQ5yt85F3vZ5yChnv1zGrm1BG+5bcB97SRJAs7tG/4v7I17PiFfH0bqw1UQQro3XTwTVvdS9IrDPPrxRZBZAogaNP/wB+OMfgcMOQ4CpyzSKItqocm359lsPLJHBC48Lm++lsgSxOTE0XE8mTyzYHXd421jaz9NP99K68p6TGOPBB5e21s8/J+NipYkl2FAbMtmuXHop8Nln3nsJPs3j7ue35NZwEXAR6EERWALMCYAJnGkyVo4/+dTi9Kv/mAHS6/66WvrgTYAunZOWHcGdz84JyLWlJtsPmT8xdAKL8qT7fPDnPSj8nTvV7A2zUXR4EXrt08u+bGTuHMoOWZo60UZ4zLpDKe8kHpH6ztLXLYwyY6vPkR+TtSfq3F7d2i4Ca3EEVGumFl9UtiJOdZXAEUURofx8tNKPrk1CBlmNKO3K1lzZmdMRKsv3hA+8wZTPHPbd12PGOoZBoFCtvwi8AlS2ZhB89eXrO3H+iGrXL9hSLEnPu2Ue11xj2wswnauRFBMnJvCII5bchECi9iumUOydgKMbLgIuAj0+Au1gzgdjWvpDAMwGQYCAgM1cGEhI/aJ1/PV8UCcQF0pNPrDTdrWeGDkBuhZOGnocT4sbkGt6m02y3VgiAn1P7Is+x/VBel8CZCqPc8I5KOKkUcWpuaXZgFu8iXGs40w/QC3NuT71WABPDIMUeW2LWJjohotAT4mA7EjkDUe7kgBTqUmJB1h31jp7NvDBBx6DRoNgnHsu8NvfInzes0groLiLdbttlW2of0lyCc0cqpWT9ckWW0BK2WxumzDRrmRRCi1mMyU6IRbjdZJXQooolnk8+qi1IFufwFOyrza1FlNdn0DbjBnGLELbrWH5iernBEhpioyDDnJgbpmD7FZ0EejeEUgXJgsGPEbOB3QCZRo+SOsYAgNyrHEz4QKZtO9PWtcHdQJyGanJB3X+62r2LmAX49QabEU8GMd3+3zXcVc99nHvo3uj5NQSY9GyCrKwCadCTp9yms9pZv1MxGuYNp3XipZpLYjNZQz5uK2arYeYThWYk0K46d0mFP22CPFagruqNuviIaWwGy4CPSYCN93kdWwIkcEmG2eMlnzlNKvll8Y99yCwxx7I3GkAwnsUmHKf95iLzbWleN1xR2DYMAQJCEO0CGlta0MTBQlN6iaxcKEHsMSSKa1LJjApsOWPzTc3/zqss44HzNQPVmlZCTDYQiyHrOGfuO6lBJlJsXFi5/beG2D610CctiMz5CFDvI4WEmGoJyyPxw0XARcBFwFFID0Y9ICcnxbVUmBMIG3Oq3OsCJgPFw9ehwzkEe8ZoJMalZOAmSbvt8VvEEAUkAunJj3O4lTPKcqpkZPWafqwZ7NyEi/I5DdjUAayemVhPU5lnN7h9HbL22itYYUhm38LvKmDQ/SbKGLTYljnqXWQU5iDhgUNqLqzCnPPnNv+WYnV48dpIC4YITPK9GvzR/yCcMNFoCdFQMyXZvVUFevVcbz2Ggq32w578LlnhrBWTr6bqj3ljVHtUXcB1401o+Age7EmCeASavnltweT0bBECQJXGqeeCkh9StbO2DM9t802lr615wTmBNAEzORRR3CWxw4VNE/BJRUVgOxSVC+nFKs88aRcVRpYfWfpiweua9sR0JMwQks3XARcBFwEGIF0qVd9Rs4HdPrdhjCZj8tSj80bTi8SzCUCRHa8Lgn8aRKYUz2c3u+nWvWchp4TkCvmlMdJadhaTlrqvd9s+42t19N+FOxdgEH/HISMsgxsFdoKAzm9yunj2Md4r/I9A2+RTyNo/rTZAFzj640WIjF3/S/ob+mghnkNqP1v7RJATsBQX0rxxrh9QamGru5/dT0tvO58XQQWR+D7QI5tvwZtuy1vM4H7KIAoGRb2auXIake+ilAosT0vXLwWRiJISIwwf761+7K+rF9+uXi7esRuEiC7pw4RENjzW3wpzauesernutlmwAYbeExer14GyBpU+6b5zDN5EPd5adOzzvI87IYPB9Q/ltdoHYP52u23HzB2LApY31cnwFdWtuRxuN9cBFwEemQEqNcKGPAS+BLY0uSDOQNuwmIdAJ1UpzZ4fdEwVo4CBn9oewJ02p5SqNqefmfyz9YVkMvnpNcyOen1+impmhR/Iz1gmb9rPgbdOAjhgWGMyxiHXpxeTb6K1xa8htj0mIG35g+bUXl75Q+iUXQIq+Y4BzOC9MRin8lPmjHreH4hcBQfWYwsOtfLCNpq6FLp2LrnHJD7QSDdEz03Aq++igEEcsymYgoVolmTn0LaQWzVJVautg01133lgS75u4lFk/DAT8t+P2pKdyoV6wMrbhs33ghLqwoMKhUrlavA2ZAhSGeHirb33oN1n/j3v72uDlKsSqkqYQWtVEC7FANxAoG0S8FLLwEUVRgo/NWvUPeLX2AYU61TxeiJtXPDRcBFoEdHgE25vMkHc2LKfDAnEKcaOQN1ekwgJ7AmAOcPn3kjdrOh1zW01NRx+7nItWSr6ui0P3/dL0Z8Ye/pCT+yNsjC0IeHIrM8E1tmbGmA9vXk64jMjliNW/0r9Yh8wsfvLz3tnLttrtXByXpEBdrR76KYdw5ZAw6ZBQdzGXF26JAtiWrlYrNjqH+h54HlnvB/yZ1jFyNAtamA15xDDvFEBuytmnHhC0hjL1a1NrTLm0QRYtceeeTnd3L++cDgwV67LXWHOOmkxe9hrZ71g1WdnNKyQ4YgyXWDG2+MhBS26iMrteyBBwKq7xOIo9rW2DwJN6SyffjhxdtTuliqXNblTWNbsr/QP+9K1eylDI8Xr+geuQi4CPSkCLQzcwJxmnygZUEQ4aZZ2E1LXkME5ATCfgzQiYX7/tD6mpRi1fsEAMXUUJtOnAAAQABJREFU+Wzd99fvrr9bv9Qz+2FM0RhoeoJTZA6B2ztNkPdb1V28g/+ZUXx4sbU7a6lhsTSnytsqkTk6E33+0Mf7IuL75SsnEKe6Ogfkfiag7uWeFwEpWeknB/Vs7dfPGLD0EmrBMnmV4hVRN0pSti7TSLUAg2xItN2OXnRi526+2XzhAhMmIKnauqeeQnzcOBxH8PUviTAkglBbMKVdZaEi1arAGWv5jO1b2kHIi46pV12WryKgO5bWKDcrDSxRhBsuAi4CPTICxsyJJfOBnIQK+t2GrhapWQydAJ1q7H4A6OyllPiBrbo0fLCnpT/JJFiiB7F1EU5Ktb6y1Su2fnf/Mfy54cjfMR8HZxyMlzg9MO8BY+Jqn6414cKynH/hwYVo+a7FUqhi3sTgFexegLRCMgry6eOXUOsiiiS+bUH1f1i344aLgIvADyOg1KnYLb/PKdcw4QNLE1SeYGDuh+/64TPHHgvssAMglaxsQ+67b3GtnMQOZN2OZU/Ym5lmTQqczZgBENSBAOwzMWkSZMgSRUBMdXFKmX5On83nnwdYz/eTQ6yhsiZNTbiZdiklAwZggYQTQ4b85Nvciy4CLgLdMwJLMHNi5QTmVMemYfVxxGZ+mlVgTsBMLFvHZXtoBOqSXIlv1+u2DXuUNLAoINfASSBOalYBOrFS3XmoS8OwR4ahV1kv7MvpgcQDaPy8EdV3VWPBtayH6cSwL5yU/1WoJIS8HfIQzGRNDkMdbyAbN4ts3Fdk48wbqxMbdqu6CPSkCIj5+uabxSzY228zNdrXyhOC2RRv9UrdzP5UTKQk/c1vvJZbBFQgaIPq3/xxww3IJ+t3m35XylY1ckqf3nuv7futdddFLtWpjc8+64E4CSX++1/glFOAv/3N38pPL8XQSR1LMLhAqlkCOusUIZGFGy4CLgI9KgJ0TEq3uq0ceJMEChImGGBLEJJxNlwmIOfXzNGOxF5PLfmLQTaLHB+rG4HIvbYAvc04Ka0qkNjEqZqTQGMdp0+qP+nWwS79WylKTy/FJgWbmAjk3oZ70TCxAYtuW4S6pzovSDBWjgxcMI8ATnFWtwd+JvF5BHIUTcgYWN5ybrgIuAj8RAQE5DR3GGLjBOTUVeVnwdxGGwF/+pMnPJAJscQJl1++eGspVm5nPvOYaugI7KBOFKzNQ0GBB9roLxdVvZxUsFtv7dmRyARYoE4pXrF8yzJefBEQmNRxiCXU9sUYKr3rhouAi0CPiUB6H/RBf04lnATnBOQEwC657RKk9yHFRlzGXxcDOf7SzsylUq6Klv+cHzkTRugGl6BDQ/VxMgqu4aQ0rhi6yZvzQtdNR7/z+qH0tFIcmXskHudUNbsKtY/VYvafZnf5jBtebTCBQ3phenvLLqVV1Y/1xwQTXd6Ze6OLQA+KQKKVLQXJev8sMyflqpSnqk9j1wfzhvvLX5aM1JVXIouvP6lnVRf3y18CVJ9aBwmlRz/91MBkG8ULZvyrFKwEFPSUUzuvpGrolhXMaR9i5dSZIjfXS/c6IKeouOEi0KMikN4P/VDOSWBOQE51bWLNxPjYLGYuxcoJmFnNnBi5DrVzipgMhNsBHdfTMB86kkhpgTQDiAJ0SrFqKMUqpqk7jv4XERz/uQS/yfkNHuRUM6nGLEYW3bhouU9XjF7mSDKnTJCz9BCRzyPLvU23AReBnh6BZITXu1ayc1lk5mgc/KPj6qs9Y2DVuMm37phjfrgqa9na+Gxcpr8y92VXiGz6wjXX1VlKdJMpU/ChLEikXJVdCZm+kvJyLCDLlmQdXxGNh6uX1UNOrJ+YPfaGNQsUdZBww0XARaDHRSCYjWxjysSkqaZNzNk8Tvseuy+22n8rUWpmT6KlPSbIa1+KtRPQ8wFfh6WeExhMUJIvpk/bl9JVYE59WT+Z1D1TrGWXl6HklBIclHMQHuVU81ENKi6rwIoAcv7/TqlUI18SDjsg54fELV0ElisCEgypbEHWJKF+oaVvSzVxQ4Z4FiRTpwK33rr09fhsQgILAT4yZgH6wDWz9RduucU6O0zia6P0WOlZmhXLEJiQDtli7+hHV0PQlyvm74ILfnT7uO46Tywh1o9qVjMVVv3dGWf8+HvcKy4CLgLdNgJBdWFQv89pnL7lNIXTDE4CdIs45W6Ra/VY6ptqfnACdwJ0PpBLPfafM2CndQTm/DkF5nxmTmBu2kHTul1QB1w1ACUnl+Do7KPNdqT2A8b2svmoebim252rOyEXge4WAfU1VsYhvW86hj3BdGrHoa4M9IYzCxKpT2+/3Wvl1XEd/7FUppyD8pijyCEp418Bt2uvNSuSOAUYB2pdiSjUDozA8E3amjBJiuMpXkjSaLiRzwdUY9dxjB8PCLAJSEp8IcGDQKM6SNx1F3DRRR3Xdo9dBFwEelAE0h8/+3HzV1IDdjVrVxG9VJE/lgL9vsHvBnN48fFTrP6S4K09DcuCfQ2fmVMaV9OPbX9tjX3vY3qb19vJWSfjJk7179Wj4vIK1D5Ru7aekjtuF4EeFQEZcOdunWupVvVIbh9qoaVWXfKCk52JTHylXv2xQSAXICALEhjG//UvTyjxwgtea7BPPrHauJepdM3YaivEJJB4ktV1XC5kuvQmgrkx7MU6n4xedWOjtz+la6VaZU1ckO3Cksp2KH0rUPnyy55Xnfq6uuEi4CLQYyOQPv+S+V0++bLLypCIJaytVO2ztZh59EyMrRzbXjunGjoNpVk1iZkTkPviOdaadKOhGrb+F/bHtrnb4nZO9e/UGyPXFcVqNwqLOxUXgbUqAguvXYiCXQuQMTADof6pVKsEDyee6JkLqz+qPODUqeHHhsAbU6VxArFN6T/3Luvf7D0CY3q/WnNRAPEO06iHsAvFA4ceiqRAm8Ce0ra0JfmS/ViDVMRmErzpCso8iCpbEKfgIqG2YOoM8cEHnqedGD83XARcBHp8BChX7drI2TIHeTvR54yto9pqWA1X0WYb+rT3p0tscFx0nAE5n5kTwJt98uwl1lnbf1GP1cLSQqsHrJ1Vi4X/XNgl65G1PQ7u+F0E1sQI9Nqnl9n5SK0q4ZDmRCSx1I4rLVNboJZ74ZIw1v18XXz11XnAwIFeOlPs19lnL3mK6vKg2jj1X5U6lZYjkLqVCtNimQlvvjlw2GHeewQCOQcJEBNsy/WfHXfECUzD3nj44R7rd/HFHstGli4xZgyiZOhMoZqZ6bUEU93dG2+w7cNVSx6D+81FwEWgx0fAv/HrdCAGXDsAvfbqZRdGXQDnnDbHGr7/3IbGJ8djYmDiz6221rxeemYp+p/bHydmnojrG6/Hon8twpzT56w1x+8O1EWgu0Sg8IBCKD0aKguZV1x6UbqJGSRokFL1B3MbswV1cej61fxRs4E7tcvr/fveyN001/wyJ303wQNpX30FEHwtMSbwNfVXpVundXeQNYia3kuJSoPgXKZKY3xDTGBPfVkJ8DakD9ynbNmVJFiDlLH0hjuBoO1GAbXnnvNMhdPSPKUrBRBnkqG7jJYlBiiX2Ln7xUXARcBFYHEEugTmxMgpxRrqG0JbdRtqHqFi89KKxVvtIY+yN85G88dMn3BskdwCVc9XYcruU3rI2bvTdBFY/RHotW8vA3ACcUqP5v8iH1mFWWic2YjYTNb+TmuxOuBAGhk5MXP+nGrdpWuY6uTizXFEv4gasFM3laJDilDSvwQVsyvweZAgSz1XxbyxXs36p955p1c7JwD3wAOAbEfY1QGsabN1lAY9/nhAzB17wGZtsglOYLiuUkr1nXc83zmZC9NaJLDtttiRvV35DtTLl+6SSwAydwKAJXvuiUVMzybU+9UNFwEXAReBH4kAbyk7P3QBTctNMyl/6xz60nWhm0Hn97rmvaPs0jJM2c0Db41TGrHwpoVr3kG6I3IRWFsiIPCjDgiy62BD+p8aAm0yNc8cnWkgLm/7PMsSVN5eidaFrZ6pNlOpYt6s6Ewb062rZuIxqU0l0lI3lbpn62yZPTYbBXsXWIu8po+aUFNSg/yB+Rj8760x82DWpqnTghg61b3ddhuyCcaap0/3LEIkRlBaVDYhSsvKIoQpVLCrQ+GIEaB0AleJYVPrsF//mr9xHHwwcOaZSDJ1+wq95rKGDMFoLidz2/YafewWUsFaQg+5il139erqvHe6ny4CLgIuAktEoEvM3IhXR1iBcLwmjqq7q7DoJqYIetjIG59nrbn80+53Tj/Mv6jrYhJ/O27pItCjIqD6LwEgASECLCjFKPZLlhtqXv/73y8RjuwNs5ExmCzckAwzz87dNhcZAzJQfV815L8oJb7q4eL1cUur6s0CbTZSCwN33I2xdGToghlBBLICZhYczKVpcE6a+c31Pro3xg4eiy/qv8An9x7jWYF89JGnZKVPXCbVqDxKtEpRKgCqJVk4szChMTC22AJBihwSUqMKBFLsYEDQOxpg002BI48EBNSuvx7Yf3+A6ddCmgkTNiImlo5M34bl5fhE22d3CDdcBFwEXASWFoFOg7mi3xSh78lsSs0+hkpjzDt/ntWbLG3j7jkXARcBF4GlRuCyywCmHq3AX+CtshJoaPAsOPQGMXRKWcqjTf5pM2ZAoqtQSQiZIzIRXicM1cg1vtVoN1WxuTFEv4p6u+LmfDZOXpfRyd7zmaNSnVOYjwjQMkmpVzqme8sglwJ26gCRn2asX+6Wuei1dy9skb0F3pjxBj7/nOlPWZOo/6lacE2bhkP++1/8R31eVTunoY4Q6siw2WbeuclCRJ0ixo4F5FWn81FqVr1duV4wIwNBAtg2rXPggcB5FFxIREEAl8YYxLW+vOhkKKx6PDdcBFwEXASWEgFeynD+Up7/0af6/KEPQgNCSDQnEPksgqoJVT+6bnd9IWeLHCi97A/1YW18rdH/1S1dBFwEfioC6h2qpvACJ7LrEBgScyX2SZ5rSmeSpes7+RwUZb+JkqPCduMoQUPWulSaDg+j9xG9UfNoDeqeqbNuKLHvYhhyzxBkrZ+FjP5k6h6oRtsiquwr29qPRI/bFnrK+9b5rUjvvbjKhNDOA4Ci2kgQJmNJtM5uRWhQCC1lLcjslYn0yQ+jJns/gGlTsWkBGvd+ISAqwMZ2XcYq6rz0uobYubY25O61F5JMuSZ4fhk0900jQzeaKdo+FEksohgiIcHEhAlealm9WwUYyVTKPNgYSwI7vP++V5un7brhIuAi4CLwvQjwCubfw37vlaX8qoJ/pRPTS9IRr2KK9Z4q1DxUs5Q1e9ZTHYUQPevM3dm6CPwwAuGhYTMiNxsQmYbrKsNZatLI3+4w1iqNBrxxdTKQb9u557ZvJH+3fISHhSEWLWtMlqVSp+4/FQJymetmQnVtZYeWYeYNMxH5JGLMXN6OrJfjftKK0+x13WypLVfNgzWYdfys9m0v8UA9UVP+cdmXHmnrW79jMXW0Lglm0vQ3J4isDbMMOB5YdiAea3oMn2a8h0x2dohEo0hKqCBVKrs3BE85heldAlOxa+oUIfZN/VKVPpZFiXzmBNLEtFVUIEDhQ1J+cTIfPuCAxcyef5ASR/zxj56oQp0eNJR2VZ2dGy4CLgIuAt+LgC6zvA9dtpG/az76ntDXLtSS88867kculMu2ObeWi4CLQDeIgJgygZ92pai83Aim/OdAgklgq2bffyCwyy4oIyM3R0wcVaAFH/3T1lX9rSxEBJ4E5Ap2KUDVfVVYeMNChEqZWqXQQazbwN8NxPQrpiP6dRSNbzTae7RfH3wJgGmWQKvot0VWP/f15l//MMqsZ8MRR3gpUx5L1lNXm2emnQOPX+lXf5uF+xdCoq8/ZP4BN8y6AZ8nKc6QWIN1cwHWtwVoTWJ1cbIXkSBCtW1Mn2oOqKUXXy8iC8c9Isz5Y84zBCRVM0e7EksvU/iw1KHuE1S0gh0jIKZOnSjccBFwEXAR+F4EOpVmzd+Zd828cCsF0TKlxaUWGcyczZlynbs45fq9+LpfXQS6bQR0LcgoY80X62et1iw7zas3K0xHWhHrznqlW5/TzHUysTBwEPDb3+IoCgJeZ60Z7r4bvRfcjPBgplBZ76alOqnIYkTXmblnz0X1PdUI9Q5BTJ9eKz2WIPB6z88yMiliYMt6QjOTqmuSSj+Szd4SfK7lmxZjA5V+zd4ke8keyWLmVJsmyw8yZG2Pv25/xwKOYhGtHaEEGXyslKxsTyrKKpBfkI/Q1BtRucUVSKMVSYIp4iSBWphM40jW+A1kunUBGbmk+qVOnOiBRdqWRCiCmML08WQydEm+3sL0qoEzgTQZDsvqZGnjawJRsXnch7F7FF3Ydpe2rnvORcBFoMdGgLd6yz5kxilZv6nFJPl3A03vsb7HDReBHhSBjPIMS4Gm5aV5QI5gLp0ATuUX6aXp0Ou5G7AVFQUF0S+jmHt/AXDCCTiGlh0TxF6xt2m/tDvQ+Gaj1bvpvWb2y1rc/F3yseDqBYh8EUFaAQEh69oE5ooPLcai+xdZna4MfqPPTzUAZ0bANP9Ncpa0NNHCXjONCbRVtZm/XOTTCBZctcDA4IhXUrVs+qzEnPmASvVuqdH0QRMSUYLC1PaSERoLkzWsf6kec+fMxW6cxBKqLi6u1lrymNt7b7TQ8Pcrihg+JjAroqDhWKZf89TZQSBM4oZjj/VEDKwXrFMMJP7wvePkUfdTQ2BP6VilpB966KfWdK+5CLgI9NAIdArM6e472eLd+eoC54aLgItAz4qA6tl86w5LpfKaIMCV3pfdFnizlzk801j7hXcuRO0TtaifWmzF/WVUe96jOrNnn8WQAbeg9rFasxhRStTv2lCwF1OrqsN9rMbAmGxCwiPD0PPyfRMw081TdMLrSNLXLXL3m4hc/BAiT04xENcR2Imlk8ecWDUxf7Iu0Rj1dkp1KoAkA1+pZlXX1mEILAoUiu0TqDOxF5lAKWfvjt6NE7JPwPotOwNsu2Uq0/PP96xUJOCg2W8lW27dzLo4jVMHD0bvX/0KuPRSr1WXmDZ50glMqnMEY2JKXlv7R36otlD2JvK3+/LLH1nJPe0i4CLQkyPQKTAnmb/uWhNNCTPm7MmBc+fuItDTItAubGA9nICcmDlj42jeWzCuALEZHmiqfbLW7ECsWT0bzwfJfFURtERpsbHeRldh/oXz7X1Kz8r4VylM+TbWPV2HhpcbDETpNQFH7VNWIU1vN6H502ZE7n8fUI9UdmQY8Nq+poZNMtUZue5ZRF6eh5PebsSRr3Mbat+l1CtZunitB+rqnq+zjjWjPx4NfPihV6smkYK87b43mg8414CcwJy2pWxE/Qv1aP6sGY9w6j+wP0aHj/EMg2WpIr881eH98pfA+uub+KGBadWrOVeKiZP4QS29mGo2Dz1ZsVDpakrYo4763t6X8qsAnWY3XARcBFwElhKBToE51aEYmOOFzZRfS9mge8pFwEWg+0VAqdNAJoUGMthl+tRSoGTjwkMItgjqFty9AI2ve2lTnb1q1Jr/eDMwaBCStO+Isr3V0OaTMWX/KQbgBNYE0mQjovo6sf71z9Wj7vqPTLyg1Ku12qIpcMOrDYhOiaL+8tdMYLDtSSeZR9uc4kuAZ57xVJ4vvogdqBq9nIDnhs8+Q+M/XkPDL85E/d+eWALQNUxssBZfY74a44E5GQqvt57nZacD/5jyBFqN/IIdHHTTamAuTjBHpk6g0E+37ok9TV07gEKGLWj2O2jiRBNDGNO2cCGgFKwsVgjYMmmKPGq77ZChrhCyLVHaVaygjJG1rhsuAi4CLgLLGYFOgblEjAVzvP6Y5QAv6G64CLgIdP8IKA0aDKfUqgJyvdIMaOWMy7GuC2KsVGumOjUNs+rZhbYastQg65WUwpOCh+r7qw3AmWCC6lcBNoHCnM1yzBeu+vgnEN59jIFGpW4F8iRIsB6rFFyZUIDtr96SgEIpR7FbMt9lyyzNr1x7LUIy9KXSNPPQrQ1IgmrT+jMft1SppV0pVmp6iyyfeiqLKRM7Jr+7ww4D6AGHf/4Taaxle/GttxC5+nErKxEzp+teMkprlc+9dOuE6AScnH0yCmdtgHfvvx+zXmfqd+ZML30qs2MxcfKMYy1dlB5xX5OdY0IXp1N4MUa1dD5bJy86N1wEXARcBJYzAp0Cc7qYST2mWXfnbrgIuAh07wioDq7dcoQWIJZaTQkWGl5rMEGCxAr+ULut5pLtvVSjbDlUH0aRQN7UB62WTnVwStHqhlCgMJhPJSyfk19laPRoY+W0PwG5rA2yrE6tZVoLmu7+yNScu5DVSqgjBC09AhRV5EuRKtWp+p6yDq5VIIlAzLo+yNBXdh4EZ7oRtTo6tvmKzYsZ+Bx2Dd83Y4apRYP9+6O3QBY97+Kqhbv3XhbYjcJmH5NdE5BTqlV1dKwZ9tOtT+JJZA/K9gDh/PlePRuZvSCVrfKYO/IPf0CJfOG4Hdx0E+rY7usKAtsogxWS3UgrVfCuRZf/X8ctXQRcBJYjAp0Cc6byIpCTojUY6tRbl+MQ3VtdBFwEVlcE2oEcwZdSrAJfAmHxxjiaP2yG/Cb9IfDVnLmB55+WmekxZy+9hNz3b7NUaXuaVkCOKVZj5TbJMTFE010fYSy7JBiQo0ecWLt+O/czUFZ1LBk0pUPJYr2kbhE05s3ccUccSKVovWw7lBoVQ8dUrmrhSs8g06YhlaiEBgRWsRcI8gTKJGrgTakEXE3vEqhdfbU1sE9QWFBDUHj6kCHAO++YbUmAjB0hJNPEvOZp8Lqn2jmlXyXEmF4/HQdwWm+bK73uDdoWgWMfgViKKibQnmQRmb+hTP+OOu88BMePB9j+ayqZxTJtj+nZnH32MfCpX91wEXARcBHoagQ65TOnu24p2XRxUyNreT254SLgItA9IyABg9KrBuK4TCskyCpOR/YG2ah7rm5xL1SevnqlRnttBLA+zDoeiBFjU/rCWXeg/vl6ZK2X1e5HJzNebVsedblb56Ly9kr0/t0VmMGOD7q+yDxYjKBeq3qkCk3Pz7WuCXjiCWubFaBx7m5Ugj6uNlhqUO/Xp5ERK/j4euRtl2fp2WZQ6CAzXgKsDL7WNKkCGQs/ITojNqSJseaiHdpQtvOXqLzgCyT79sVbUpj+/vcAWbUCArt6pktbt9oXoecmWA9X+c8pHq0LW61HbKx/DA05DZjf90ygmMpdij0K6aVXL5Xq+ecjSaawhgxhJYFniF0hSimSaCBDV8t1C7i/hs8/x2jalFSqa4RsTtxwEXARcBHoQgQ6Ra/FG+ImgFCKRGaebrgIuAh03whYbSyb0Rs7J/Uq2TTVsNW/zBo5sVqpITWq6uAgNk4pT9W0scdqn8QD7Ua9KstQY3vbJoUUYuXE5Cm9GvnHDNuSiSuYYrV1CZpi0Zh5xZlAYdw4r4k9e5/mERg9LSCndlfqhaq6MwIoCQrEGApo5m6XCyj1KZEB6+gi//631xqLv4qhM69MqVwXtCJeHUf5fgR5O+0E/PnPxpiBQM74OLFt5eXGyiV1bhy6mRXIbfqwCVMbp2KjjI0wpu8JAFt0KQbkED0PO3VrkO2JbElYixdjjd5cpXX/9jeAIg0DfAR05A+9ThBauuEi4CLgItCFCHQKzKmA2RRerB/RxVgtbtxwEXAR6H4REGgT+AKJKmttRbAmUCcrkcjkJRn5QFYAkfoSr3ZMNh0UAgw7YTqa36fI4OijLTgG5ATmOFutHLcnhaxUqgeTsZpNhkrbt9ZfSqnyn8o6BLysz6k6JYhloy9cvQDROecgcNttsG4IFDnIsy3r62cshdq2qM0DmwJzNTWs0Qt7QE0ALVXz69uNCMip9q/X3qlr2dlnAxQpBMjkNajXqt4rzzjhOM4CdKZwpWVJ0/tNlmauQhUyBjCdyzSxwFy9zljpX/VjVap38809Tzp1bxCTKBsT1vclqZpVGngeH2+tc6BYwg0XARcBF4GuRKBTYE47kAmnXWD5ODwijLydeOfphouAi0D3ioAKMDgbCCO4MnZOrBlZebXy80fGYLJyrJ/N6ceaNB+8MIUogNR0wo3Ar39tKVZty2Zecaxna0oEIf+4OygKUErSgKM2TCDXDuaUAJCIQua+aj5/660A1aNn0WcuyQb3Mu0tv+Yaj1ET2OKNpgCbFLDlB34JiMEToyagJZ824sN2YEYxQ7yJbB5LRur/V4+B1w70eqAyVZrB/RnYuuceQH1kNXRcGgSY2o+sU5onNWNG8wyU5pVixGXVBv4atT+pbSWiEHDbcktvlh2JavtYR2iWJEoPq76OKtxPudkA6wDdcBFwEXAR6EoEOg3mrFVOTZvdoap+RrYCbrgIuAh0nwioNs5n0nxgZelRArnWCt7MdRjtIE9sGsFK2SGLMOz4aWidzfWk1iSwaU/XskZN2zM1K9OuEk80P8yULL3iMr941vqh2v6IhWxJ4KX3YtIkS1uq7g277IIArUfe1TFIDEGQJrynfSv9acwbgZZYvZbvCDrZcSHJ7gkh2YX873/e6wJb2oeGgBlZNhkeiynEaadZypaPPHuRQw4xANl0w6t6xhs8JGPpCBqjX0c9U2K0GuMocBYXaON+D+V5panjg+oIpbYVa8ljSWPK1bzmlAKW4pasXCPZuZ0l1iBIdcNFwEXARaCzEeg0mJO7e2x2zIw4VUAsQFfyF6ZY3HARcBHoFhFQPZjSnQaodEZi6AiqZEvSOueHYM7W5fp9xlfDrEnYDqtmEsETGTSw60NHVs6EB9xWqE/IPOriAjtMPVqKNRU9vzZNgEmgEjIJZsqTVXBASQmKCepeE1DUe1kPV6XnKbYw1o3YyNg5sm7RbyhCUPsrpjrLtc7llxuY03qWLiWoE/gjDrMaOrGMxv4R+PGdHrv2n/8Af/kL8OCDBuAkgDBAqhpAzvKuUy1xhJMYR7NCkVkwj+1eznFZk6imT31glXKlMCIuOxL50AnISSgh4QSBnd0WL6UbhQ7FDRcBFwEXgZ+KgC7ZnR7qq6i7XhUb6yKcPTYbA64c0OntuDe4CLgIrIEREHgTaOHQ0tgxPpdemm6CAf+IpTj1QZ8ZAbMOLnNwpjFVUPH/7rsbI+UrRw0c8i3G5rHOTiIEbLstoJ6mqSuR7ZdPC3CJIRRrJoWoujIIRqYRzG3NZZuYLtazyeC3TunKu+/2LES4up8Gte3rNQKmjfi0CTS0bRJi7elWkWP0oBMAlMBDYC7AbbaKRVPNHAUKAozZE/+lLXhDeI5ATunlPsf1sfNtY3ucdkBKli3nvvvwW/rLhR96yJg3E2IIzMmkWKnV447zUsdi5wzwpoGOdTxBHoMbLgIuAi4CnYxAl8Cc9lHzSI2pwHShV5Nt2QiUTyjv5O7d6i4CLgJrWgQEvtpZOR6cpVz5nNSmsVlkmFJDLbgM7Om1HFqYcI5Oj3p9mwVY3nsP2GCDdsDns3Ji3BINCQ88+RvrsBSAU5q0KLvILExMAMG6uSayW6O43n9vvNGrfxs4ENlk6SytSaNgA3Fi2zQr5UqAZp0dyJRZ2pTiBHV+0GuWZtVCggh5z3FdSyFTFWuCCQon8PzzngJWilRhW81apACuwJtafOmmNt7KG1ulhMUYssau6Y03cB/Zt9Fc/1QaHO9P0+ANBW4vvhg47zyvNk/pXu1DYgmydAXauOLmhouAi4CLQCcjkN7J9ZdYXY2v1Wg7o439Faluzd0qF8OfG45Fty0yI9AlVl6Lful7Ul8svH5h+xEXHVqE6nuZFnHDRaCnRCAFXPzT9dOSYuNUJ9Y+UiBHKcbMkZmmdG1bQPapmOuonZdEB6l1bCkARbAm4YEEBO1Dz6eAmICc5sqFldb71QAOwVFi331RKCGDbEho7QHalRTTz04N7TUEyowdE7lFwstYvfJyq1WbrhV8oCR2jvtrn/Uan2tbyOPOiVEYm44YZxx1lLcfmg4bgEulWHUeAm7BvKB1ldCxxmMEc2Tr0Eg2T6bDEycC7PLwCWvuPrniCs97b/31gbPO8hSyVPCasGOzzQzYZbOu7mEdh5SzbrgIuAi4CHQyAl1m5rSfxjcazRBUd7ttFEXIoiB7XDb6n98fxYezDmQtHL326bUEkNMpOCC3Fn6Q7pCXPwLEJh1ZrHZA03HLuoJwtr/9jbMhWxApWc3jTXYbWzMpyu34Q+2wBLLUhUFpVH9Y7Zp+EcgiuZWMJKE2XmL9LUUpsQPZsq+1jgCdwBKXxrhJcPDoo+ZJZ9sRMOQ+GnJ3tBo7pWhn6H0pMGf799k5Pa+hY9S5UKAQV+pTnnlKeeqxlLR6PTWbDx7VuOlF6aaEVd2wwKBq50zkICuSCy8EttvOq42TglVp1fHjuQ/uRPVzbEtmtXj77QeUl4M/CV55AynvPDdcBFwEXAQ6GQFdvpZrNL7ViHlnz7N+ha1sYq0LXtaILJT9vcxA3XJtfDW8uWCfAoz+YHT7nrPG8kLuhotAT42AgJFEAgJZPqD5fiz4vFKxltbUehpizsighS/+g7Fa9l4+bUAqBegyBhGKpWw/lKK1fRAUaTuqd5PaNaM/15EfW2WlebNVCwixhs3YObbJ4rOe+IEpVxsdj5c1awExYJwtOUyg5q8j8CUm0PbpPesJGMjyJZQqlb+czH3Zkksedu3nznO1+kCmmNXVQn1p03unW4yMkZw+HWW0YwG7OhiwU82dDwpl3aKUquxVmH5Of/11bx8UQHygY3j//dSRuIWLgIuAi0DnIrDcYM7f3fyL5qPqriq0TOedbSSOvNI8lJ5eipFvjVxrWLr+F/e3Fj1iI9Z5bh0UHVyEyKdMm7jhItCTIuADMi07giPFQICu4xCQU60Yh4CaL2SwLhBktFqenGSvidXzh6VRCdakjpUVR4C1Zc03E9iQ2LJaN4LHRHPCmLaMIRnoc+suwLnnGqBLSNCgbREoBilUaFSKVUpTP4Wa2okxigRzSTFiBFSWiKUwYYnhAzo9yU2qBlDAMUmRgh2v2DmliQXuUoevuj+tp7SyWEMBUpWYCHxazR2NjeeTzVuPfV1Lf/UrQHYqElKIWVS9nJS5VNWGmIJue+QRgL1Z+zLFOkXsothGN1wEXARcBLoQgRUG5rTvRf9ahAVXLDBLgKaaJhRmFWLAVgMw6IZBGHL/kC4c3qp7S9EhRcgZR3MAfr+0VbWh8c1GVD/g6uRW3Sfg9rSmRIBJUEsbtrNWLCUzdi4FaDoeJ7WuBvj0XLua019BbBoZLr8WzrYncEhmTmAt+lUUg4Y8hAJagQxl/ZuBQQIssWbqNCOAVEpQpK4Tllpln1PrwypFKDtCZFKY0Cowxz6qxoJpv9y+D7xMBTt4sAGqiFg5sWxaRaBT62loqZmnYS3JpKwlsCohUIRaeTG1m7XrMG+bXEfnaGCO9XLGHBLM6XcZD08r+BfVDqci8eyz+ILgbQFBXAmB5ADWxRXuvz+C6r3K2j8daxtfCxLshcnKLRRAfewxb386JjdcBFwEXAQ6GYEVCua0b6lc5545FzWP1mDBtAWoi9dhfN54DD5kMNaftT7K7yqHBAVr0sgbn4e8HfPMgT5RT0ZgWgw1D9asSYfojsVFYJVFINlMOOenIIV7lGYlayaApVZcPxgpQGQMXUfAR5NepMQJHdOaMh7XtpSizFo/C7W075hBgGMpWKlLyYxLzKB15k2bZ2w5BK5kR6KODkpXEuT1psluUqyXOkGoddd117WDs8gG+3uK0SFDKGrIQVJWI2ec4R26jtcfAmjysuNzBuakwKU/HE1EEB4zxlg9nZev8FVtoObM4Zloeo8qWfalFRDUDaDVwakmTqld9nhNsj3XAhoez5k5EzUCbNomwV2GFLM89gQtU1oEMGVfcsQR9rr74SLgIuAi0JUI8JZ3xY+GVxugufCAQvNhemXMKyguKcbuA3fH5MMno+LQCvQ7px8aX6eAgk27Vzdwytkyx8yPxRaogLvqHqaL5R7vhotAD4xAW3UbMvIIlFKALpDw6uFa57V6LJkfE6VFhYL0T2yXgJF++EN1czLH5UsCcz6gS7QQzBHQaT+FBxai+LjjURW7DpGnv0bOAet66VbWzcn2o/6FervRKrroV6jOOcAz4GWtHIYMQT9ucpaAHcGS322iPc1L5aua24OMmA1Zjdx5Z7tVis7NBB1Mm5qggUpUgTRIecq0bYTGvjuT/XuZ/V8Dvygzxl7rGytHJm7WSbMw+JbBlmoVK2ctztSmS6BN4FItvNR+TPsXO3jggUiQhWuRQbBq8MRaSrkqEKqes264CLgIuAgsRwRWCpjzj0csnebSM0rRdlgbXih9AVnFWdg5uDPWG7EeHh/xOGb8bgZarmiBxBNSr0W/5d0qgVT1/asmxSmWMHNEphVdx6vill7VHbcbLgI9OgIp8GVAjUyZAJgU65mjWEeWGjLbDSY9cl+iBd3AZY5Z/DqmT4fVznFbBp6SBEup7WpbUoEKCEkBXzVihNXPtbNzBId6LTaHbbbYxF5tA6vf4DVhxgxAvm9PPAEobSkwJ0CkmjnVtvFworsfD2y6qbdv2ZgoPcsOEdkEeM2XXorAwxf7p2Dr+2BOLb2QwQMUO8fOEa8w/Zu5eSkCPE7z2iPYMz891sv1v6A/wuuE7XzUaWJG61nATgRyO+yAwOjRyCeT+Evu5Ut2f/iQx5jUMaqbxF13Adtv7/WS3WknL7263nqLj8c9chFwEXAR6EIEViqY84+n4u8VZmOStUEWCvYowFOjn8JzvZ9Dbq9c7B/cH2MGjUHFoAp8uOWHmMapnlPsXzEzJdYFXXfoSmO0VbaZIakYNCuWVvpHXxT8IjFWQOkSZYG40Otav+ruKv8wfrAs2LPA0jz6whJLIBApEYcbLgI9PQL6G0sL8Y9J4It/H7ISUa1buH/Y/CQb3260GzDZc2gYO8Wbsd7/1xuFBxWi5qFUmcJFFyEeihujZ6IE/l3q71P1cG11bah7pg652zMtWTIQePttNI/aFzkznjSmT+vob7/h9QaEhxE4PU42S+2vZE1y/vnW1eE9pU8F4sS8UWzQss6OnhGvQJzSpGLKmDbF2LEYQoD1pUQJj17spU11KEqhkpUTsLT2Xw+eDZxzDvD3v/MY2rzUK8OgWjmda3ohz5eAMWtMlgk4Wma2YMp8vuf+CejDtPJO3KbO/A3OE9TxQWlhijz+ctVVCJx9Nho538SYmMJVtX9S6sr+RPV5rLdzw0XARcBFoCsRWCVgTgemi7/mRTcvQu62ucjZJAf5u+XjvnXuswum0hfp2enIDmVjMKcB+QPQmt+KuZyqOUWSEbRF22gbwG8XXgNVx2N38Urv8Fpov3cAd/oy0qw0joFBAcH5rYjNi5lvnGrkrB2RNsfX5BFV+19e+N1wEXARsJunYC47PEipyr8RU6AqPcq/v7TitPYI+X93dXtdgTrabSyYypuhXRcwnUkmisBF7FyUvVdz7vsrAvHUzZYAIvFXvDoOpW7Dg8Mou21TzL3oUWCLLZDcJBvJkAcedZMlprzsnDIMnDIVs/88G1BvU3ZMMA5QwgalctnmC6xDgzzedt7Z+53gDR9+iH7zL8L81ovxJVOrWUx9Nt/2JnL/uJ2BSp+VCw8NY8o8WpGMn0mwRrRGc9+sk/dgay/GgGBPBsECc/LGU//ZUGnIjI+jXxBcUuwwlkDuK57WAzoWze++S/D5OHDaaVYPd6VUsb53nX+sAqEEc0GmYRMUgLjhIuAi4CLQ1QisMjDX8QBlNqx5wbUL7C5fXw7hIWFL4eiiWtmvEpNzJ9vdsBUn89rqFyAbSyAgJ+AmEMcUkC0J6sTQ+a157HV/p/zuCdDkM5jPC3I0HRI86E5cBc9i/MQA6HhcnZwfMLd0EWAEUjdJxnbzBkqChKb3m5CzaQ7qnpJEgETZMZdZp4Ohw4dbOyr+NWIumaZaMmWttN0wUQCBUSIn4alduR1jzoURuT2lW+terPOU5PJkIxBLVrxFYMa/bf1NU4yhOtbK+yuRt0seSk4rwYJPBvJFPq8DkB+c0qgy9hWIYp0baPVhzJc87NiNIbguLyBHHw3cfjsiBFABrtN46XPIv2hPq4ET65ZRzh025nuAUKIKMmrmJ8eUajC8GMhllGUgPJz7ZFa3ZXILpn91MHDIwfhUXR9UIygAp1SqAKXmDpYsOPNM77jUj1bAU2COzGJCtiSqq3PDRcBFwEWgixFYLWCu47GKrfv+UN2N0hnybxJjl1aUZuBLAEzPCdAZqBOQ45eCPfaBnPosEuiptkUA0ACevhSYImqrJTtX0WoXaTEOYuT0utoTRT7jBdwNFwEXgfYIWL0aQY7PqJlogX8z2ez0UPQbtrhTXStBXICM0zTWmBmoEvskRoxgJaN/fwTppxYl6xShqCD3eYoLiKs0JwOsw2MbLN1MtXzN9Ow5vdH/km1oQH4/IuPHI5vsXDCd7bJS68jvUalNtQxsrfgY1QRqN1HRaubBAlBk6gzY7bor8OKLXl0dzYWLB3zC60eOnVPm309A9C/XIykTXwI6XUvsGqObOrXy+u47q5UDa+VyJpzm1ccRyPmsXKhfyMoyBPJaZ7fi2zu3IANHNlEmwazJwy9+AeyxB/DCC8YwGpATmPMBnUyId9sNUKpXIgj2m4XEHFrKCFmvs6bPDRcBFwEXgc5GIAWFOvu2tWf97I2yraG32D+xfPpyEOMgEKg7fzUOj05mqsQNFwEXgR9EQNYbYrXFXmmZ3iudhrchZI7OxLxPt/HMfAXgCKDyHj4DDdOp1pSKU2rSYcOAQYPYIaE30gjugtuVGXiybalWLbVNlTvkbu2VXpj5+PyNkLXgLSjN66tHZYkSLg+j9G+lqL6vGjOf2RA48UTPkFfASK3DpBBlWjfn3r96f/O8CVQHCdXzVd5eCdXspuWmofGIq5H/+F9MWKF0afam2ZbKrXhxgNmKZDe8bzeTgUxPvSqfO90cFu5faMegm8KGiQ2Y9dT6XupUrKAYwsMO885Zqd8rr/QAm45N4FGpWx2fjpP9WkGgi2ee8YAnla6WOqY/nQG6H3wK7gkXARcBF4GfjgCvNN17NE9qXuIEpcZLy/fYvaYPmpZ4zf3iIuAisGQEYrOpJhU7J3GR6twa4whWM+2Yz0uH+q5qkBXLvv00JMmi99qgFhlDP0P5b+rx/riFwPHHo42grk1pxPSRyGmb4rHpuo1MzWLI9Xcq0CQBRfJfZN5ejhgDmEwjqx4ki9dA/0fWuy66cRH6nNCH7/0EM3fZxXYvtaupTLl/A4gCYWTPNOvYZ/9xtilP9bsAmoCcz8rpWiDAWHFpBbdVYarZNGYF/O2ll6SbhdKAqwZAzJxuBnWss46dxfU1dxjrrut1fBBQk5hBCl1Zk5SXewycGMRrrvFYOAk2VFf38cfAVlt5TKJAnxsuAi4CLgJdiICuHud34X1r7Vv0xSEbFBVeu+Ei4CLw8xGwkgWBOYEvVjaojEHp0WiEaU4V7pOZa/1iAUKVrHNVSpHrRBdG0e9kMlYvvoTILRM9duo3v0HwyYetBs32qu1pJlmucod4TRy5W+Yi1DdkatjWUy5F6IuJXr0stylGXfWtshApPrTYatdUeqG/Z9W1mVAhg2UZSp+yVVh6Aa1P6uLGuqkmV6yclW3k8DX2U9V7c7bOQcPLDWZJJL9JCRwMCJIVDPUPIdQ7hN6/6+2paXm1jHwZQc4vp2LhXnsB9KBbYii9u/HGXt2eFLcyAlb6VGlXtfUSwFNNn5g8paWV1tVjraM0sdSvEycusUn3i4uAi4CLwLJEoMeBuWUJilvHRcBFYHEExIoJCPlMmsCaAFislkCERf4B1pjJXiP0LtOEqSEhkhTrQYKr5v/NQ25iElruex3xE89C8PWXFgM6/w0CdCp7IBNY9NsiA2p165+I9CfuMbbN9k0wJyAp5bkAXPEhxaZYVwpWNWxKAwvEiW3TrNq+eWfPs6WeN1BKrzilVsUCqi5XqdsZR85A7ja5nlo1y3uv0rNZo7NMuap15JMnY+CmN5oQ2fFUDCX7tkB9X2k5ssRQR4fyclPTppGRHE5LlDqlX3fYAUnFidsxUYi6VUj4oPSrOlv84x8OyC0RSPeLi4CLQGci4MBcZ6Ll1nUR6KEREMMlQKQR3fQgxE5hTdhTTxlISacQIUG7jfT7b/JER1Ka858EFH0OV0qUGVoKj7L60Rz8zqfR2nc0gvWLlgR0AohtHqBr+aYFRQcXoSj2pAGwyCSKk7gNY/0I6MTQmd0QRQutC8jKUXGaOZLsIAGeavoE5KSKb3yn0fbhixzEyoVKyLZxFisne6LJG09G3vYpdbteJ9DT69ljsxEeFbbH8tjTMUzdZyoaN/09Glj3tojnexDFC19JoXrkkQD7r1pHB1qhWP0clao6pSqaGWeyvVdM5sZSyQq4XXaZB9zkhffKK4BsS9xwEXARcBFYjggoyaFrjhsuAi4CLgI/GQHVjLVuwfTi+edjU3rKUcuKqXysgv502oq0qcvCX/Y1hkypSoGivB3ykMFm9DWP0aqEpQ0yCbYxZAjCafOMDTOvN4khOAtwCWipVk3q1YK9CkxsMP+C+VbvJqYP6SS0COAE0swmxNui/YzNjFl6VGCv6d0m6yVraVOur9SqzkHLnM1zMPO4mbavNKZdlV7V8YZHEsAJ0HE9pW4lnlBt7ay93/ZEDVKtUqFrtXDjx6OI6dSB3HM953mcW9SLVkbAsRjBKdGpQJwsU9S6S8/JY06CEVmTqEZOqVW1//rd7+z43Q8XARcBF4GuRICXRTdcBFwEXAR+PgKtG1FwcO652JJA7l12VUiqvksze4smWBOmNlbNA3b8f/bOA0Cuuvr+d7ankRCq1KUKCqhYQLCEYhepIiAqimBFsaPgz/hHbNgLFgQRUUSwgB0VIyCCBZAqPYCUkN62zsz7n8/35SWzm012k2zC7O756uzMvHnl+84b8s6ce++5Mf6Rq6LaINsRDH/lS9e2R1tMfvnk1Id5+VFUddotQhfzROjoqrDsJ6VsiXPvRxUaYIXSfV93bPSKjWKnK3aK+w65L6qZ/OrUK7ZaqSZPyVoyN3HfidG5UWfabv4f5kfL9i0pPEzP1aTGkSen8OpGL9koHj7l4VTNSoiW42OHhIccRBIrEgYm40uuXRKPHHtNbCcVrVeh0fkiaN3qKpHRWUI5c/Ne9KKYRx6cQqgNEyZEmx7j9GAPnJJExOjWQ7QuKvjKaXs6S6ROFhA/wq689zACRsAIrAMCxE2mr8P23tQIGIGxgIByvuKzn42nibjdqsb2VfVFbT3nY9Hc8UiUlzZFptywSapY7VFP1N6dnhfNV1+eFzYo5Aohwx+ODgrN2zYnxSxBJkKUukC8/ePRdPs1if1In8u3U84dlaMYC1PwQMh2u29uF7PPmZ3CrapxTUyJcGox8Kaj0AElkHy5ZEWkjhVUu0LmKKxYcOmC1B4My5XqwmpSDiGBvIfUoRJWZlei4z8dsfjPi+Pxz0pR23HHWKjQ6lLlBTZJVdtDvWFfqvdby/x3kqxXHsOQ+D//iUwEtSwD4y4ZAXfOnRudqljtlvJWllJXpe0YKh0kcNasPNw6c2bEP/4RIQ++FH4tTsTPRsAIGIE1RMBh1jUEzKsbgTGJwLe+FU0yxM1UdVmhOvPtb0/t8JIViMKj3e//SpTU8WG8wo5LyQNTpeb4C05LlaGoX4QtNzt5s+i8szM6/tURT3xNtiW1g20f/lMiU8nXDh86VdBi7k2YlJBq0+ZS1kQICZE+fKpCk/opyjq0BUyqmpS3VI2KYbi2g+9RJQshLFr6YUDOfDAU5zipKEIVuBQ4QCzpz9pxc0fM+e6c2tlFUL3a3h6x226R/PPId8NbjgIGHlTxFg/CqcInhVEJpRJWpWqVIZKXSB09Zsmv8zACRsAIDAMCJnPDAKJ3YQRGNQLPf37EN74R47bdNjpRk0j2rxmoWj17KQT7/vdHi5S5ssKJVdlwtN3wk9zmQ7lnKSdNVh+bn7J5KobovLkz2XzM/YHITc1o3VkWIiJb5MQlb7tlhK0gdSn/TW35KMZY+Gvlmy37fPIhk6Pj3x1JASS8Sl4c+0gDriXFDeJJNSzdYNJ7EToIHy3F6ALTcWNHzL2g73xqptb35bRpOVmDyEHYeJAHB8EjDw6yxoM2Xx5GwAgYgfWMgHPm1jPA3r0RGPEISDVrVL/TLhL7CQn2G9iJNHX+Ico/2Sp6tN6me+4Zc848M7r+fVi0feSYXCGbJxIlIkU/5nF7qLBB5IuQK2HS7ge6E4migT2EiwIH7EeKYgeIXAqZ9ihfbpFez8tVtXHPVEcHbEhE7Ob/dH5sfPTGUe2uxqwvzEodKsbtOS7lyLFOIoEqrkhKXUeez4fnZHlWXhGbWpP1O6/VviVX0MMIGAEjUCcIWJmrkwvhaRiBukVA+XHj1W2hg6rLZz5z9dNUXl0cc0xsp/y5h+6+O7a65ICYe+HcFM5Mhr3L/N4ImU584cQgX41qUaxLsD8h1AnJotNE1plF7xPyj4PMLXugxJFWR5g0PROKpd2YlLek5qnDAzlzhFVZhnfdkmuWLPefY/JUqC7+i3LYPIyAETACowQBK3Oj5EL6NIzAekNgWU7ZkPZPPl17e/xP3mpT1c7q0ed8LybfcGxMOXRKPPHVJxK5aljakMx+F8xdkIoh8HSjwhTiRc4aTe8hdqhomA+nB7lvUt2W3rA0D78SOoXQ6TlUFFqQO+aIuW8qJeUNnE+Ej/2VZ5ej8zZ5vXkYASNgBEYZAiZzo+yC+nSMwLAjIDI3Tgn8nST4Dzb+8pfUh7SqAoHqC14QLbLuWPjnt0bvt7+VLD9Q4MiJqy4LmdLCq+ehnuQlR5EDoVGIHaoavnRJsZOSRp4bpG78XuNzAleQOU0JX7i23dti6b+WxmOfeCyFc7vvFaHzMAJGwAiMEQRM5sbIhfZpGoG1RkAkbsL48TFvdWTulFMipMaFPNZS9ebFF8cC2Xfspebzt6pLQsett8ZuuzwU9//m/sg6pLLJLw5TXror0C4M1Ywwaff93bHoj4vyXDgZ+RIybdutLdp2acvXV95dVTlv9GhN/VwVju26vSvmXTwvuu7sSsreWp+nNzQCRsAIjFAETOZG6IXztI3ABkNAHmlz5Y9WEqFT8efAQ6QtNYt/7LG8cfyBB0b87Gdxiwjea+XFdun3vx9PvHfPmPTcSTH30r4Vo1SfYhGChQhh09S2i2cVQ1ChWuTLlZQPR0/YIvQKqSPfzsMIGAEjMNYRMJkb698An78RGAwB9Q7tlN1Gq7ocdB10UN5PtHabs9WnVVWsccstEddcE7HPPhF0RaCN1e9/H5cddli8WY3pv3/2v2PHzxwUXft0pdy3Yhe04PIwAkbACBiBtUdAv389jIARMAKrQUAGwJlsSbZU2DTkH7fSUBuvkGqXfNX++tcIHoyjjoq47LLI/va3uEitq17Q3h73v/HC1I0hX8F/jYARMAJGYDgQMJkbDhS9DyMwmhHAW05tqjbmHFHcasd550WbSFoyzVX7qjSeUHeHjTbKDXR32CHiBz+I3ptuivv0YZsMhxc89aR8Pf81AkbACBiBYUHAZG5YYPROjMAoR0Aecw92d0dpypQVJ/r1r0ejerKOp+hBZI/G82k89akqMW1WzltzhPLlgg4SInSP3XFHbMOyU0+NjV4qsudhBIyAETACw4KAydywwOidGIFRjoCqUeeJ0O2ECqc8uPj856O0995x0LOfHfPUZD6OP34FAGpAnypbaXWl1l5x7bXJey5+/vO498EHVdDQFIv2HyBcu2IPfmUEjIARMAJrgIDJ3BqA5VWNwJhFgOIGFUKUAWDHHSNE4k7eb7+48s9/jrjuur6wPP3p0Th5cmSodZ0y6X396yOkyoVy52gun9FJYuedIw49tO92fmcEjIARMAJrhQDNcaav1ZbeyAgYgbGDwP33Ryh8ulDK3Pzi338AAEAASURBVKYKnXb84hdxI8rb1VdHfOpTK3A466yI5zxHHRnkISfFruGQQ6JRBsIhtS77zW9y+xIpc6n6ddttI375yxXb+pURMAJGwAisFQJW5tYKNm9kBMYgAjfckFS17SBjImnZ9ddHfPzjeV6c+rcGzeflN9ckVa4qVa7pxS+Oapfacz3ySFRvvz3i8MMj/vnPiDPOiNh0U3nK6Z+fE08cg0D6lI2AETACw4uA/lX2MAJGwAgMAYE3vzni73+Pm6TM7SiV7v7//S8CtW2LLaJN5KzroosiXvayqPTIN052JuXbbotA0XvooYgDDoh417sivvCFiFe9St3uKxEQQOXdeRgBI2AEjMC6IWBlbt3w89ZGYGwg8KMfRZty4VDfsrvuSv3tS7vsElOUO9csG5KuWbMidtsttfLK1AWCnqwl9WZNZO3SSyPe+c6ID384EblNKKKQYhc77ZQXSIwNBH2WRsAIGIH1hoDJ3HqD1js2AqMEAbXiKomodVGVetppEVddJeHt3jhECt0CqW69FEH84Q8RW24ZgSonstcjz7nsH//Iix+A4U1vinjjG+NY7WcuSt3550fI6mSflr/EpIMmDQ9Qqpb1MAJGwAiMRQRM5sbiVfc5G4GhIvCd7yQrkuzxx6NR1asTUNWOPDJCxQ03ax8N22yTF0Eo1Bpl1boqPy5Q8KhwPemk/CjKnYv3vS+O1PKf8vlPf5pCs/RynaeWX00br2O2B8Twv/+N15GTd/fdUSI/DyXQwwgYASMwRhAo6TxX2Tt7jGDg0zQCRmAgBL7xjbxNl4oapmy/fSwS8arKJ468ueD5/e+Pp8s0+HYsR/CaQ5nDgoTChtNPz/f4kY9EHHdc7LrXXvGgiiK6C/UM4ifSNXX+JdE2ri1m/3Z29M6SJ92aDvLuVD37BoVsf6gcvZftsUdoJvG4LFDSPBQG9jACRsAIjHYErMyN9ivs8zMCa4PAvvsmY2Dy4Jo32SQW3HNPVBVejVe+MuLMMyMuvDDiyivjdilhQc9WFDqpY7FkSU7kUPBQ4N7ylthBRO5eect1E46lA0RbW1Lwmq/4XlQ7q9G+Q3uMe8a4NZ+l7FEapPqdtIzIxde+Fn/QMZYqH+9kETxaio1T/l786ldrvm9vYQSMgBEYQQisY3xjBJ2pp2oEjMDQEcDoV31Yx221VXRS3EARg9p39RnXXJOTOAyAFy9eoca94hXJfqRB/nKtIlQPEPbET46+rrItSareZz4T6HCV3SoxZ86caJiwhr8rFf4l7Dtt883jXFTByy7L24kpr2/x9Olx7j77xFs0r/Ol1pVE9hx+6HPl/MYIGIFRhoDJ3Ci7oD4dI7DOCNBLdbPNIhobo4cODjfd1JfIfehDyQS4edddo6Iihuqdd+btvCB1VKxKFWsSyeKzTrYlp23//fN9otyx/rJRXVyN+SqWKDWVikWDP1OIUSpFRZW1f0Z1w7PuK1/Jt2Pfr3tdZCrauOAlL4ldFXa9W/54gSp40EGD79trGAEjYARGIAL8C+ofrSPwwnnKRmC9IfDe9+bttiZOzO1DZDOyfGASLMuR8SJyncqhy/CSo1L1lFMijjkmQiHZhnHjorpoUQQk6tvfTuSK7hEUPMS//52HadnhuefmhsPk2PFZR0eeeydlbZWDvrAofCJwLTpWW2trLBVBrCxcGPHHP0bghVcM5dM1KgzbrPl0kUN38MHFJ342AkbACIwqBEzmRtXl9MkYgWFA4NhjI6RqSTKL8UcdFR0qfkjj05+OUGhzYxGz+diLEN6kowM9VrVOSaQpw5qEilXls8U550R84hMRypmLCRPynLpTT03rxpe+lAhjk8Kwe7a3xwt1gFv1uEEh3Q6MhnWclQY9YcnbU1iWHq/Jw05VtE0idk8fPz4atcHNInapSIP942Wnc2mUUlhZujSCnrCYF3sYASNgBEYZAiZzo+yC+nSMwDojcMQREa9+dQRqlyxJQubAIaIWCqNuLSL3iMKYicA961mp2rUkopZRnbpgQcRf/xohg+G45ZZ8O1Q2bEsoREBVY18UJ1D5qlApViIxST5zImOpMEJKWyKFkMWXv7zvqfzpTxEQOnncPU1k8w752cVnPxsxbVqE5lJSjt4uUuvY6vt6LIZUfvCDqeq2UX1gK8xJHSo8jIARMAKjDQGTudF2RX0+RmBdEYDwYOmhfLMg1Arh2njjCJGlmDIlJ3AiXRmhUUgcqpeqXePiiyN++9sVRyeMusMOEeTdkbOGakfeGvtiO+W3NX/mg6mStXGjxpjfuX+kcCydI6iQhdC94Q35/siJo5KWoTy5qbJFmS+yVlJbsCp2JxDF5z43gpCwCCdq3U4iiPeqMKPC3LQ+1a4hKxUPI2AEjMBoQ4DIxPTRdlI+HyNgBNYBgfvuyy1EKCxQNWtS0yiIwFIEha6pKYKcONQ21DKMhSFbkKZi8F55dcnrjXDspz6VmwizH9Q+8unOOCOqS6rRuoPUuJZSNM25P3oukbIHgWQoBIvilkKrb31rXjn7xBNJASyrQrVFit5UEcOlVNveeGNeaPHDH0aoZ2xVZHGuFMOSCF2zzqECQcXIWF0okmVKfgT/NQJGwAiMCgRM5kbFZfRJGIFhRuCBB3JyRuECyhvWI4RRyWcjXw2rkY99LPVqTQpa7eHPOitizz2D8GtADCmOoHCCECmhVYomWGfZaGlviYaWhuQ51/OQ1DsqYAnDtrTkpBI1kGpYlpEvp31m8r/bXerd/RddlJNGSB9K4a3KvMO4mPnNnRuZyGdFJLREKJfjU2zx3e8Wh/azETACRmBUIKCf2B5GwAgYgQEQoMvDe96TFxpA5mqVtwFWT4tEsmL33VOYsyyFLLARwbNOSloicjNnRnzyk8u3bt6qOb3OKlmUZyv0WgwIGeRMuW6JgElhS1WyWRZxxRWRKVz7HIV9b8EGRXlym+mxSN0mlkLaqKBl/PjHeaj2ec+LDO+79vbcHoWKWuxVKKbwMAJGwAiMAgT0M9XDCBgBI7AaBAhhDoXIsYvTTovm7baLMuTv+utViaBSBIoe6PwgK5P4whf6HAh/uVJDKbLeLLru6lrxmTzqkgqHGkhIVjl6rSh9VKhSVSt170JV2+6kVmNlkbLHpObtLhJZOv74ZJ2yfEeQSQge+XKEWQkPo/SdffbyVfzCCBgBIzDSETCZG+lX0PM3AvWCgCpL6bbQQm4dytrnPhdxyCERMhBOBQ/k2KH21Qxy5TKpbVmPFLfawT4gbypwSEUQ6v/aiZJG8QT7UzVrWdW29xHyJbdO4dd//e53sSk5fv/3f7V7SgUbzfSZJST7619HqEds2mbGjL7r+Z0RMAJGYIQi0DRC5+1pGwEjUE8I0JtVIdZ9VIl6PRWt7353PjvCq+S+oYgR9uw3IHOhaOqAZA5FjRw7fOoUTn2WvOx0lNCSUMlDiNLFzu3t8bCepbnF4zrGbHL0sCShL+zRR2uphkK0rXr04oeHzxytvyCZRaFFvpb/GgEjYARGLAImcyP20nniRqCOEHj725Nqdm9RIMHUDjww79aAukbhQk0br2LmhFnJl6t2i9HVDpQ5rFBe+tK8ilYE8SZZk9xE2BWrE8ghlbUoder3WhIxG6/Xe6oQ4g49FkHqMC4+/PCk8E2UyreEKlq2xZ8OrzvMkCF2Mkb2MAJGwAiMZARM5kby1fPcjUC9IIDKJaI1B5JF1wcG1iTKdQv6sdb6z+WfRvMWyqNTdDXryqIyT4SvdijvLp75zLSkTZ53vVLnKgq10i4MS5N0DDzlqFCVHx4FDkulDl4vY+NGPe8kRXCRHrMpwhCJ3FjE73GKJ6hmPf30iKuvzgsiOI6HETACRmCEI2BrkhF+AT19I1AXCMgGJBUWPPpoHr6UNUkiWqhy5KihgPUbjZMbVaHaoO4R/Yof1E81tfNq1D9PsiMpK89uM4VTX6bHnShrhF4hilTJ0rbri1+McYcdFhV88d7xjmRHMl8GxR3yw5usPq6TRfgepIoWo2Jy6qiSpaiCwgwUQNqOeRgBI2AERjACJnMj+OJ56kagbhCAxFGwgBLX0ZEraKhgmPxSfFAzGiY2RNPUpig1L6tkRZmbX6PM0X1CJCxVoULoVOCwVITwTgooCLPiJSfiVlIlaxx3XPK6K6soYgspcUshef/4R+5rJx+6bnnkLVW+3MYK2Vb0WZVQKzl8dJfARoWqWfvO1VwdvzQCRmAkImAyNxKvmudsBOoRAdp+UVlK4QJhV4jcD37QZ6ZNmzVFw/iGIFcu9K9PtasaySi4di0KFfbdN/eEY3+oZyJkqcUXfV6f//y8ohXSiGXKhRem6tYOhVEbRPIyCBsWJZBLcvlEDLsghZrXZOXJdaHM0XeWnDyGlbkcB/81AkZgxCKgf1HJWvEwAkbACAwTAlS2Egp9+OHlO6T3asMkkTgtlxGJKlJzb7neWb3L10kv6J0KAYO04VWHioZ69qpX5Yobih1FDyJmDSJ6JYVSK5A6FLsZM3JfO1mkpAIJlotQbin17vG3vS0Ckqjw7ziFV7u0fnbNNcngOIVb+87C74yAETACIwoBxUE8jIARMALDiABFBzVErmkTqXEQOcyBq7mnXHlhOVYickxBlalJUXv601M7rjj22AhIF10bpNaVZAycwraqVK3ecktUlKvXJAXuqVLZdlIOXSu9Ygmf0oZMn6PKjUPZI1+Oba+8MjpVzdok5bBEAcW99w7jiXtXRsAIGIEnBwFXsz45uPuoRmBMINC8ZXPKjeNkkwVJZ7Vvflx/FAir0i2CECmEjHHeeXnRAubC++wTjeoiUaF3LK3GVMla3m+/uAvyp7y58SJpL9PjuXpcpN6xM6XOPUD4V4UTLaqELb/61VG99NLofdnLokE5dtnee+fH8F8jYASMwAhGQIkkMX0Ez99TNwJGoE4RaN5aRK5V4Vb9n3Zd1SUicgtrCh0GmrfIWlLWVMWa8u8IqWIjcvPNyrHTP1cie5ny4ppVlVrFAPgDH8jbd33lKxG33x69ype7Ty2/rlY4d5HsSLZVQcYUkbjFRxwRZYVrs8KjTh0qsr//Pc+9e+97I775zYFm42VGwAgYgRGBgP6Zdc7ciLhSnqQRGEEItGzTkhM5ZeRiCAyJg8wNOg4+OGLbbZMXXElKWwaJIxxaO+juoGUtyqvrUX/WkAIXvcq9o7JVFa6bigjOee1rc3uT5z43ZDoXJZHABkyGRfJSjh35dNimUAxBz1isVDyMgBEwAiMUAStzI/TCedpGoF4RaNlORK6N34n6pdidRe8jvSu361rV5CFYCp1SuTpRodOyVLWMoohanzqFSSFt+MpB6Cp0msA/7s1vTl0dOmSJ0nTiiTH1hS+MDoonPvnJ5HWXKb8uw8BYyl0if7NmRfznPxHXXptbodx226pm5eVGwAgYgbpGwMpcXV8eT84IjCwEIHINbaqr0r8s1Q7Zjjzcs+YnoHy21I9VBsDP3mGHuE97WHDddRH77993X1/9aoRafDWp60NVJJCCiPjznyNuuikndiKDm6oAYq6UtwzCRiHFv/6VmxtToEEFLIPWXx5GwAgYgRGMgJW5EXzxPHUjUE8IJCInD7lE5BRaXck/bqiThVxRfarK1scUGp2y2WbxCoVe76DjA0bBv/lNvqff/z5ZmFSnTIlGhVYbRdyqKnwI+sOefXbqQEEXiFZ9Nl7b9ZB/Ryuv//43AgNiQrQ8PIyAETACowABfOb8MAb+Dvg7sNbfARG5rG33tqztaW1ZS3vLWu9npX+Ljj02Uxg0a1y6NHtflmXj9VD3hkyeclmce25+nI9+NJMalzVVq1kbn99224rjn3FGJkUuK82enW3FZ//854rPfL2Nhb8D/g6Mku+Aw6yjgI37FIzAk4lAy/YKrU7IDYGrsh4pzy5HZXFl+Kak3qrx5S9HyEakRerbPqpqVYZc/FqPpXjaqXdrXHFFxDHHROMznxmtKnLouPPOXMVjFrIuiY9/PEra/ukqqrhNVa8pL4/PPIyAETACowABk7lRcBF9CkbgyUKgZYeWaByvbA1y5NSaqzxrDYjc+edH4A+Hr5zCocl6hOIEChHe9KaVT4nOEC9+cSpyoOChScUPe8gQGDc6dWuNOz74wZzQqbdrmwjdUiphVfSQKlbpEytS2KyQa1WVrxXMiT2MgBEwAqMEAZO5UXIhfRpGYEMj0Lpja+qzWhQ79D7RG9XFsvoYyhBhK6lwIVu6NCdxkC0RsBJecpgDF35w5LSddVbEz3/ed69vfGPEK16REzupbbT4mqAK2KWnnpqI4JRnPSsWKe/uBSKJ0u1ClC46VMlapV8sxQ/40v3yl3336XdGwAgYgRGKgMncCL1wnrYReDIRaN1ZRG7csmKHpdXovk8WIEMdZ54ZjfKGmyoCN1vmvYFFCD1YsSWhSEF2JHSAKEl1K2mdKmodpG727IiTTsqrVWuPtddeESefHKFCCbpAJKsR2ZTsoRZft6HM4SNHQcUjj+Th2K9/vXZrvzYCRsAIjHgETOZG/CX0CRiBDYtA21NFsujsoFFdUyLHRspv2+SQQ2Ke1LcMs95aaxB6se6yS8Suu0a0t0coLAq5a6C9l5S76uLFeegUm5G3vIW9DTxoASbj4C0nTYrHTzkl7+c68JpeagSMgBEY8QgoUcXDCBgBIzA4AqWWUqTQamuDIqFqz6WQavcDa6DIFYdQz1W2yh59tC+R4/OLLy7Wyp/f+tYIdXGoor5tt12UsCHBV2777aP6mtfkXnGETt/97ogbb1yxLfs56KA4QmTuHLpAeBgBI2AERjECJnOj+OL61IzAcCFASFWWI9HY1iiDXrXnWlSJnplrYQhMyy2FThMFpBvDYON734vgcdhhESKB2XOeE+Xdd08dG0pS6xqVJ5dJwavMmBGBakdbrx7NS2HbiSJ8qluNEKHzMAJGwAiMZgQcZh3NV9fnZgSGAYHGyY3RvHVzNLU1RaVcicoCEbmH1oLIFXORNcg4mfh2ki9HNeuajte9LoIWX5A6bEtkV9Kg6tQmEbgW7WtrPRS8jev1+N9dd0V85CMRl1+udx5GwAgYgdGJgMnc6LyuPisjMCwING3WFM2b50Su3FOO8rxy6rW6TjtXu60t5Qf3+N13J7VtnfZ15JERCrumzhDqEhHjx0e0tuZ2J+z/iCPWaffe2AgYASMwEhBwmHUkXCXP0Qg8CQg0P0UkbpOmaGptinK3iJzMgHtnKYy5NgPT3wceiPja11IYdBz7GI7w589+tjaz8TZGwAgYgVGFgJW5UXU5fTJGYHgQaN5KRG5qUzS2NEalu5JIXHmO7D3WZijnbbMTTwwZmcScRYuiop6qLUcfHZWqcu/wlfMwAkbACBiBdUKAf189jIARMALLEWjZpiURuVJTKcqd5eh5tCfWmsh9+MNROvTQ2E97nyWft3ETJ0YoZ65nzpzYBaNghVw9jIARMAJGYN0QMJlbN/y8tREYVQi0bKeKVRU8lBrl6ab2XL2PqvXV/LXss4p1iHzjttt007icHqrylltCZeq0aREPPRRyjlO1gsoVTOhG1XfIJ2MEjMCGR8BkbsNj7iMagbpEoHmb5miYpH8S9P9q5zIit3AtiRxnqC4Mrao4fZjuDeeem5O2t70t4sADI/7739RPdZy6NjRRwHDVVXWJiSdlBIyAERgJCJjMjYSr5DkagfWMAMUOjZOkyNFlAUXuMSly8pJb6/HqVyfLkB71Xq1KhYv/9//67kq2JD1q43WMlpYffzzvsdp3Db8zAkbACBiBISJgMjdEoLyaERitCDRtoUKHjVSIoHKoandV5KoclcXrQOQACv84mfpmyo2LX/1qZejOOivizjsDPa6hvT23FBlovZW39BIjYASMgBHoh4CtSfoB4rdGYCwh0DilMSdy+lmX9WTRvdO0iGOel/u0oaiR41Y7Dj4493TDYmR1AzNf9V6N2bMjPv7xgdf817/iwWc9K46S4e9lrKeQq4cRMAJGwAisOQImc2uOmbcwAqMCgYbxDdG0cVMKrSYit/neERttlJMwdVWIzTePENFKJrzqcxrNzXkv1IpUuy22iDj99FXjgCLX1ZXvq1jrjDMidt01okn/7HAcbEnuuSdmqUVX7LDDyn1ai+38bASMgBEwAqtFwGHW1cLjD43A6ESg1FJKhsAUO2TlLMpz5SGnsGgoxy0efDDvb/rZz0bsJ1MRVaQG3RX4HCK2YEHETjtFfP/7qwaHHqkocxA62mn9+McRL395BCFVFLgsy/d3443xN/VS3Q/Lkm51bH2eVEEPI2AEjIARWCMETObWCC6vbARGBwJ0dggJY1kli4oqVum3mpQyiNoBB0T89a8Rv/xltPCaTg1PPBFBtwUti3/8I1mLpPUvvHBgQGQInJreq6Ai5DMXqG/qnRoqesBnLu6/P+K22xIprN53XzyVveyyS8Tznz/w/rzUCBgBI2AEVomA/jmP6av81B8YASMw6hBIPnJS5vhfdakKHlDlGIRAyYmDoH3pS/Fa9U+9DVsRqWfxhS9EXHBBxL//rYoF/QaE4OERR7h08eIULk37KP7ssUeqZk3rXXddrsjhJ/d//xfxk59EqAtEqBtEPPZYInm3av391Vf1IVQ71EBIo4cRMAJGwAgMCQErc0OCySsZgdGBQENbQxBiDUU5U+VqQeQ4PdQ0lDSpaKUtt0w+cNnPf56HRT/2sRUAoMzJJy7Ii2N9+cmtNCCACxfmahy5d//8Z8RJJ+X9WYuVr7km4rzzUri2IqsSBXEjdtstjn/TmyL+9rdiLT8bASNgBIzAIAiYzA0CkD82AqMFAUhcqS0ncllvFtUlIm+1o8hj23ff2FoFEHcTEv3KVyI6OvJCiEsvXbH2H/+Yh0vJc5s6NeLii1d8Rn4cyhrKG/vcbruI//xnxef9X/3lLxFS767UcQ5XXt5FhF9/9KOIr341AhKJR53agnkYASNgBIzAwAiYzA2Mi5cagVGFAH1WsxcdFJVjT47ym94b5ZM+FNUPqroU25D3vS8/1yuvzMmXQp5HaUmVECvhVFWcJtVu++37YoKqRrEEhG2bbSLe//6c1L3sZfEG1Djy4sjBUzuvFL7tu3Xfd9pHJhInGhclwr3aR0yZEqF+rqkwAkL47W/33cbvjIARMAJGICFgMucvghEYAwhkp5ya90SFFEG0UNOwHcGChPy2Cy7IQ56EQ7faKpQZl6tpN98cwQOVjfy4Sy7pi9a11+bFEa2teSWqSNjHtO8fUjCx//45GaNCFhPhWmWv716SgXBoX/fMnRsHUiihcGvMm5dv/+ijObEjR8/DCBgBI2AEVkLAZG4lSLzACIwyBChewBcOkgRBwqCXECqq2v/+l79mOXYiRxwRITPfv/P+m9/MgUBZQ6XDlgQiWDsuvzzPb3vggYiXvCResvHG8Wn2TRj2+ONz8sd7BoUNteHYfGn+lzmh7mFVoiUNWJ/Q5utPf8rtUiCLqIQeRsAIGAEjsBICrmZdCRIvMAKjCIEPfjCajjsuqlSNUrRw662BAha/+13EDTdEtLXlFaWoX0uW5AqYih+qkDkpdKEODUmZ4zVkSxWncc45KwCCsGFfMm1aTFUl6u10jSAH7g1vyNd5+OHca+4Zz8gJJQrdC16Q+84Ve6FbBPlxP/hBUgDLO+wQG0vd60QJpAPFaadFPPWpauJaXr23XbE/PxsBI2AExhgC+qntYQSMwKhF4Kc/jfLee0fsvnuee/atb/U9VRS02iHiFzLxTabAz352BN0eIILkze2zT4SUt+UDM2GsTJ773ChJOZuH9YgqUZ91yy1xU3t7xAtfmK9Kz1Xy3045JUpPe1q0vPKV0U2RA+Fdxrnnxq4ijXerV2vcfXeyMZlHzhzzgORpmxg3bmX7k3xr/zUCRsAIjHkEHGYd818BAzCaESg9JmWM/DW6MQzW+/SYY3I/OCpRCY1CoOjI8KEP5SQLZYyWXpAzxotetFwxy1D5qDiVEnibiN9hqG940p18cr7uD38Y8cUvRnbvvVFRscO+KHQcQ8dskxWKamIjvvvdPNT7979HYImidYMwLgqdcuni61/P9+W/RsAIGAEj0AcBK3N94PAbIzB6ECg1llQaqvMh3w17EUKq/ceBB+YKGmFUihwgWJgAUyCBOTC5duTDKfRKzlpJZC5DgSM0Sv4c1ap33RVxwgn5nrVNr8jaL7Wvp6ijw6z3vjeqdIB41avy/Dm19yp/4hPxLylx79P2X1ZFbJeqYB987Wujcc89o2nGjOhGSVT+XQoDUzFLPh1Ej/CwhxEwAkbACKyEQKOWTF9pqRcYASMw4hHAjiTQ3rfaNgJbEQogyHtD+aLS9F3vyi1AWAZxg8QRUqXQQeQqhUZBAUJHLhzh1Eb9k3H22TnxIwwL0SI8ev31OV5qzZU85pR/t0SmwhlhWooX6MuK2gbxmzkzqiKHN+ixn3LwHp42LX2WadsKYVZCvbT2IqyLMfH55+eP/Aj+awSMgBEwAv0QMJnrB4jfGoFRgQCiXKHMlbO8VVdRDYrtBwUKVIyi1mEdAokTyUp9U9/4xmhTmLRMQYJy7Uoy8oWElRQOzTAJPvXUXO3bViSRggjIGvlx9HMtBoUW7Jfw7sSJefj0iivy/q50gnjnO5M/3cOyRikRRiXsCqlEAWR/hHQpyiA8q5w6DyNgBIyAEVg1Avxu9zACRmCUIZCIHOckHhcqSEihVogVhO6ww3J/OQgTprz0SaXTw9e+lpsDS4F7H+oceWoKmbZR9KDHxptskqt3hxySo0X4FWWOcOtee+U9XU8/Pf+Mv7TrQtGjMpYQLlWuUtta2A8Ebeedk8qX0R2C1l+oeFTUUgGLJclLX5pXs67Yo18ZASNgBIzAAAjoX2wPI2AERi0C1WVnRjECyhdkjge5cfQ//fSn+576UUdFk9SxL0P0rr465cJtoxDsPapGnUdHB0gYYVcG9iYieykcS7UqpI7PivAoyhy5dyhtdHWAxGn9nre+NXWdKD3zmdGgAosKhRQohKxH0UX/Ctv8aP5rBIyAETACq0CgUcunr+IzLzYCRmCEIrA8xAqZQ50jtEmxAtWoEDnMe/Fwqx3/938Rr3tdTBIpW4qhMLlsGtNkGnwnBr7f+U6EPOBSTh1Ej0HFKWoaZIx9Q8YIvULu6CbR3p6HcwnVovTdcUeECGOJThRS4qq8RzH8xS9yFQ/C6GEEjIARMAJrhEDDGq3tlY2AEah7BGpDrFlFTO7ooyMw7aXwAeJEOJP3teOTn8yLHkTKFlLEIDVuaylnFE1Ib0vh1+3pjQphQ4GrHZC2z30uJ3tYlOAhh42IwrWpXRgK3U9+kodaValaEjnMFFbNCKW++MV5eLd2f35tBIyAETACa4SAw6xrBJdXNgIjAIGS5shDnC0NctxQymQBEn/+c17ZinrGe2xL8JKDuJW0Ee29VNjQpFDsI/KMiw98IJJWppy3J7A3oZr1wgsjLrssD6lSIQtZQ3WjAhZix/j1r3PTXxS+9va84ALVTi3D8JqLK69UTGA6a3oYASNgBIzAOiJgMreOAHpzI1BPCCwPr0qQy8hnw5IEIkc3BexDIFu09aLDAnlx++6bf45aR0EDnSJE3MpUoyqkWpJSdzMnqBBtF2FaLEwUni1pn60ifM/Q8476+KcKw1auuy7it7+N+NSn8k4RqlRtFjHMqtUoQxoJ1bJfWoB5GAEjYASMwLAhYDI3bFB6R0agDhCQuFaSwpbCq1XNRyHN5VYfVLVSdYr9BwqbyFoKuZJDR+h08uS88hVVjfVUwdooMjcX5U02JhnPqHcamZS4LpG/GxS2vYHKV/YnQ+BUZMEKIoXbaPsnRBJ7aQV2syghIVh3cQAdDyNgBIzAsCJgMjescHpnRuDJQ6AwCUaRS6ocU4GUodBR7ECeHIUIVI3iF4dlCKa82IsQXqXtF8oZZsKodqpMHafQ6GL83hQeTWQNZY+QKpYjdGUoxpvfnBdGLCN7VML+D7sRwqwUVngYASNgBIzAekPAZG69QesdG4ENjIBEs8aGxqj0KmSKKsfAhgQ7EXLiIHIQLBQ21Dhy3/oPGtsrPJq6PKilVq9CpBgGN0hpqxKmJdcO6xE6OdQOvOEgcqh+DOXaBYUUY2WgctISDbsXDyNgBIzABkZA//om44INfFgfzggYgeFEAFWOfLmkytHxoSBzHIQcts02yxW1G2/MixdqD/7610fst19e0EColbw4lLcDDsirVyl2oF8qJA8lD4NhvOHo4sCgapVerXjKQRQHIon5mqP3LwQXQkduIm3LPIyAETACGxABK3MbEGwfygisFwT4SSb+FTxLlOtD5I48Mi+CoAMDIVRI2tOelhMzecql4gjabVGVyoCMffSjESh05MJRFEGrr0suiTjiiLw117HH5m258i1yEkNrL0jg7bcXS8fO80c+khNZOmVQbGIyN3auvc/UCNQJAiZzdXIhPA0jsLYIlJqlyjUsU+WqUuVqB3lyEC3y4RRmLUk1y7AYKYoZCKOSP0ceHNWmkDhactHJgfXwjKPlF4oepE/9WVM4FTWOXDw+R5GCxOBhV5gJ185hNL7+2Mfy85biWRKJa9P5T1WHiz223jr+QA/a17xmNJ61z8kIGIE6RcBkrk4vjKdlBIaMQKHKEVqtDa+yA5GLFP6EsL3tbTFZ5GMBBQ2obliNkOtGbtvMmbltCSoT3RkgeZgMv/3t7CUfqG5Ymuy/f14gcdNNeYEFoVmqWalYHS3jBS/IQ6aQYLApxqmnLq/0TaRWJsqZSGynumA8IjweEd5vkK/fD3/844jjjiu28rMRMAJGYL0iYDK3XuH1zo3A+kWg1CJVrqgg7U/kOLQ+K6kiNaMwQblzC8h1w7S3UOcgHbvtlhc1ULTAelS7osS95S0rT/4Pf8h96viEsCI9VymsQOlDkRrpAxJHNa8KRzaVHcsiEd424bfojDMiXvrSnOhChKn2hQijZqJGkit34ompAOKHwmBbdbZ4+JvfzAtHsGyh8ITqYbD/8pdHOkqevxEwAnWGgMlcnV0QT8cIrAkCySRYylymogceKw35vLUqBNiFtcill+aPYiUMgyFshGLpzoAnHXlvd96Zm/8W6/V/xm6EAbmh6AFVbjT0VD3ttIiDD46SyFqDFLc5smuBKPd85jMRr3xlnnuIuTJFIKiZZ56Z48BfKlkJVdNNQ/g9LEwaVEFcVVi7QbmJVQg3JBnie/jheS/aFVv7lREwAkZgnRAwmVsn+LyxEXjyECiIXCp8GEiVY2rykOtBhYNonHBCrihBvqhMRYXDaoT39FylSIJQ6tlnD35Ssi1JhRSF3Qk+diN9YJyskCk5hRUMloVF8ut79atzM2SIHMoabdBqxyteEfHGN+YtzJ7+9CiJxGXKM2x+6lOjW6pn9eKLc7KMTQxqJnmHv/hF7R782ggYASOwTgiYzK0TfN7YCDx5CJRalxU+qOgh6x1AlWNqyo+rUqRAVeoee+TFC4QJUYogcUUBBL5x5Mj9+99DOyGsTFDlyMW7/PKhbVNPax11VF6woQ4X8bOfRRx00AqVkfc//WnEq14VceihOZGj2AM1rr19xVmQj0j/2p13jk1UBDL3i19MhLhRJLks4tZLQQiWLe97X77Ns58d8axn5d5/K/biV0bACBiBdUbAZG6dIfQOjMCTgICioX3sSFY1BUKiF1wQqeKUUCphVGxIIGHkctGnFbUJwjfU8aY35fsjbEjI8a9/HeqW9bEehApVEqLFub/nPRGLF+defJBciBwDn71ttsnVTJHhZoWlK8qNSyKoihzita+NBhG6cSoAmTtzZgQKnUKsZW3TqJB1RXlyTVJAyyedFPHHP+YhVtRPCLSHETACRmAYETCZG0YwvSsjsKEQaGhtSHYkHC/1YV3VgX/1qxWfUIlKyFWVl6lg4e67V3w21FdYkpAXttFGeVL/N77Rd0s+I3+M8CsDj7qrrspf18tfijUgtahy5A1CtCBxYIPFymc/m7c4UwFEWo43nyp1e1XssZvO778qbIAMNqkyGHK3lJDs736Xq3a0O9M6W+2ySzwsojheZG8Rvn4Q6OJByNvDCBgBIzCMCJjMDSOY3pUR2FAILO/DSuHDqkKs/SdDJeq6jpe/PPegYz+YEJ98ck5iUP0gK4RuGeSXEa5E/SJPjNf1MiCx5McRJiV3EE+4H/4wYv78/NzkF5c+I58QMvrud+czP/BApRYqt1DbNirEXKY6FfJ21ln554Rc6VErNXSOwq4NIoMlSCPEV/lziUSzv9GQX1gv19LzMAJGICFgMucvghEYYQikwgdxJiotV6vKDfd5iaCgOr1NBQHfIecMlY48PAyGRdgapWptKSK0u46rAG5cC4GB8H372znp++53h3tGa7+/a6+NkHqWVERMlemGgQIHCYXMFQUhn/50fgwKPlTUcB95cyJyFVW6JjUOa5diUDGMwqe8wy5VCG+DOgfBI+8OUofy9/WvF2v72QgYASMwbAiYzA0blN6REdgwCDSMz0OsmQofqp0bMP8K9U3eat+B1NHai+pMCAxKFwRHuWOPqEvEIwpflvQ8ub09Fuu5iuUJBsMyLY7vfGfDgDSUo3z/+zmhg4xuv31OPMklpLDjT3/K8+g4N3rXkg+nApEOqXHjRFw7UeP6h4/ZFjJ3zz2RKZR9sFS/70vNSyFnrFtok+ZhBIyAEVgPCBATmb4e9utdGgEjsJ4QgMw1NDWk8GrWoyrLDTVkc5LCjoQfKSBAacLKhNZWKHAoXazzox8lgtctJSujyILwK0QQVYuwZD0NQqV77RUNOp8MUqd8ugaRzwwTYM6LLg5SIkuodddfH7H77vEUhY4Xodz95jd9z0S2JEGeHcbDMhtukUXJo2CEKod1iYcRMAJGYD0hYGVuPQHr3RqB9YFA6sPaKPVHY0CT4PVx0Np90hlC3Q0SaaNSFvsNBoqUSNBEFQks+c9/Iv7f/8uX0w6MitBZsyIoHFgfg/3j3QZhpLiBwgaIJWbIRx+9+iOiGKq4oSoy16Zwa5cUuSqkDvXxmGOSWXAJcke1K7l/UtwmokjyqB0vfGF+bFmYYDqcSZ27RYURzVImy5rTBtRPa2fl10bACIwRBEzmxsiF9mmODgRQ5RqbGqNSrmzYEGstfKhvkDdIEyodY9n7fUXm/kRxQTHIl1vfA+IFoWNglaIihI3VX7ZViuDjVPNiI7K68ctfpty/sqpTS8oJzHR+Tdq+rA4XJZ0LIdOYMSPPr5O1yBLei6Qlc2X858izo70XIWdZvJSkzGVar0dEt03r9eAzR5HFaGh3tjoch/oZBSEUnkCaec13BwxRQwvLnHpTcId6bl7PCDxJCJjMPUnA+7BGYG0QoPihta01li6QAvVkjTvuiOCBCW5hMozdhkKLM7DpKGxJaucH2aLnKTduBuvzGt+1dSV85OTxgGTRYkwq2nxCupArSNdFF0Ucf3x+3IH+EgZWpW9ZytwmUvTm/utfUYFoKGSaEYbFR08kLxGOJ55Q0ev8/BwJtVK9SxiVZ85HqlwVsqs5ZCJ4qW8u+2ddj/x6oKLyIwCfQjz3wE6PBmFH9W+mZdX29tz6RnijnHoYASOwegRM5laPjz81AnWDQGFH0tPb8+SEWPsjURC5YrmaztP5YLlax3J6mhKupKiAQQ4ZRsV0oSD0SiUphQH0P13bQT4bIVCIAfuHUCrMmexF8HiT4hYXXJC3M1vVMf72t9TxoYzKJ1PhTGRznF53UrhADhyVroSUFTLtFGlsEBmpchxCu5ASCBsPzhO1SetlUpuqzAlyazKXE7k991xB4mSqnMLiqJvgyXcCnIRjSbi26AdAWeHvCvY2kOoZM1Z19bzcCIx5BPSTKKaPeRQMgBEYAQg0TFCItVUhVpGEygKFpeppqJI1uFFDbsgvI1dNnSJKInOT1O6qh0IIFCs6LkC0aB+GwoWippBmuql/4hMRIoRYgKzROPjgfB+E6ES4tlL16WL2C0mEXKHOQahQ7foXLXAgyB5GwapW7Ra53FLzXXLDDZFRFAE5/cIXclVO75lbplDyJG3TzHlB3CCQ552Xt0zjnHgPQVEBBN0heiCKEL0XvSjiH/9Yo1MbVSujtnE9ILhYuwjj9Mxr2s2hpuLDB3ETXhUpm5mUujZhOF5h2W7hnfwBWdfDCBiBPgg09XnnN0bACNQtAihzTc1N0dOh3KInY9AtAUsSyBEhRR6oUhA48udQqiAyCp2+4B3vSH5zv5g5M+awnGpXWoZxQ6bqk+KEc87JlTuIDgULhUp32GFrdnYQLkgVoVupO4/K223c6adHJx0vCLEuI1aJSHz1qxHvfW/f/XMeDIiees4mJUiEjXZcG0udm898REZ3VFXr/RBHec5N1HwfJfz34Q/nBITtCR0eeWQcfsIJ8YsvfzmahNMSCKywYB6T3/KWWMi5834sDnAm9M2DMP1Ag1A5Dwge11WqXJdC3l0i483yMZysyuM5EHU+v+66gfbgZUZgTCKgZA8PI2AE6h4BUrIaSlGtVDd8iBWPNQx/3/nOPJyJQkX3hPb23J+N9l3nn5+TJpLYpaxc++c/x7nq+jCHPqeFsS4Vn2wHGaRggG4J7KvIOVNospncut/+ds0uB0SONlzc/AnViXS2QazoVsHAKoUqXIgV5PPzn8+XF3/ZRnPYhEIIFVAsEhktsU+9nsx+Rej2futb4wGqdzERlnrUiQpIaBfT5GKgPmr5L1AoRUKYQ8q5Q4nifDV2AEuKIcg3HGtD1zf9ACCUKouXQQcKL5XRV16ZFM1eqaJzHn00NtH3bSp5d2tK+gc9oFcwAiMXAYdZR+6188zHEAKlllLQj1XNu1IV6wa1JTn22LwdFaobhIVQGPlOKnhID0gSDwgQxIyKUtaB8JDPxo2bUCYEi+W6ISd1huWocuSjobLoJl8V2ZsiA98uSB3GvUMZeLixPuE3CINUnC72y/EuuyzfA6ogFZQQPsgkChvHxzsOUqoQaFVEryLykEk9bNU6ZdmWdGsblj8qdbFVxG4b5eAtVEFEt45H3lxGTh7kDOIIQSPMClnZf39dr9YoX3ppHgIWIelWuLBT21RQISGG5A4yICX77JM/6KqhAoxROcAF/Al587wm4VKIHWFYqXudIsadSjXYVeruXL5XkHHyLz2MwBhGQP8VeBgBI1DvCEDkoiTxq7KBuz6Qz7bbbjkxohsC6hWtsGoHihs3VPLmCJGh1BFSI/QK6YPUcdMlPAbhueaaPMwKqYLYoWRBrCBCer+9iNCCoSpXzE+EsVW5WN2QTW76qGnk5UlR6zPovwoxJdRL7hZdHz7ykTw8LBLayzy1XVV5d5N1Dl0iXJ2qpnyB5nOtCFb3jBnxIEREc8xEZLdWTtz/CCEXFi2Em1EBZTY8RdsvJP/vd7+L2HvvKOk42cUXRzfKJNiAUzEU0k0EEyIKJnj0gcu6VvkW+6+XZ8LgfA8gchDtV70qr2bm+zDUASmHCKtI5W6RuqeK0N1FNSzfv/4FOUPdp9czAqMAAf1XENNHwXn4FIzAqEagoUUtvJQzJ2Fuw/rLfeADOQGDgBDyKkKmtWijJkH4IE/kvUGUIHyoYspBS03sudGi2HETR82CFPGeogeRopCKVSJsKdI0R9tPkSLWBVHixr26gYWI+qrupnDnbPKwKDBgHsyBuTKfWgUIMgDpRCWChPEaAgUpRFUU4cIUuV25bWl/Igl7ab53M1cGx6PnrIgXJsNLFVbGi65F5G0zYbBEimCDtu0RMaz+4he5aofyqDZoydqE8+a4KIdYnih8mwgOVbOQHT6HFOLVJ8ISFE+MpgGOnJ++By1ScqdK4ewg1A7JA6OhDEL5fC+0/Vxdh+1FhhdB5sjL9DACYxQB/evlYQSMQL0jQB9WiNwGH6geDIgOFZ8DDYgeN+iChEDW1Lu0BFlR0UAqQvja1yKOOiovfoDQocKdcUbEqadGKLcurr46MkiXctsqCpkdgXpGccEppwx0xBXLCPtKAZvEEtQ91DCWof5wPEK//QdGwhQvQLJQ8yB+UodS6zHCtSJUC1EUUfn0mMv24MCcCRNDvBSCfULkcQsRt0wkokfvH5eiVlK4VGhERWRj6okn5pgQToXYsg+R1vTMMRkQT5REyMhPfpKHWJkX7yE5tYP3UvlSiLh2+Uh7DemeOTN6VMQwWwrk5sIcYpyqjdfkXAiR6zvzoFrKbc32fNc8jMAYRYB/qaeP0XP3aRuBEYMAqhytvBjVzuqGmzeKCQSFECmJ/AM580OcID6EDlGWULtEoiYrpPgckZYOqUzkOaU8OdYj9wlig5qH+gQZJNQKkZJ9SIPIzU0QGtQzQpCE4wjl8ho7i9oB6dL8Htc8t9TniyFazIObOyTpzjsHVmwgjihyBcFi3tilKLG+UWbBC1GJTjgh4tBDo03znMecOS9IGOtyPlLSOnSMNh23zL50LjuKUM7DfkWf92j+TZpXFZKL6TCKHhgSAia8y/5ZBsGD+IrgJKLIvghVk2/Ief/xj/kZQ07BiVBt/1B3vsbI+Yv9CBgLo6UKa5f1Y2GSvmPkE2ZcO/AeyoBca7tFqpAtgRskmGUeRmCMIdCo850+xs7Zp2sERh4C+i819WWV7rNByRzERe2wmhQCrUIgBiJz+MIddFBOPCBm3/te8pPr1s36YalSnYRYUae4QfMZtiSE23i0t+ekRVekQQSGogHMdslJS6SMmzNkByIF2YPcQCwJwRZDpKqqvLaXSs27k+0uvzwPDROqRFH8/e+LNfs+Q54gABAswp7ktx1wwHKlLhVgHH54dIvA9UI8WB+CibIIyWVb5dSV2VbkDSuSueS6yRYlVMWbUTyBMsjcIadshyJIRSxD5KxZ51wlvFqbH8dxwIXzZFsIMEUe4MY5kez/ZNpyoJZCsLF+ofADY2g8/HTd+oS0OcfBBoUzhEx1jXtEyDKR6xb9OKhSJELoG2JOLuHqBthCfvmucH0g0x5GYIwhoG+/hxEwAvWOQNarGKs4R4ibYB5cXcqbDTAgEiI7hLEeREkbaBAS5eYL6YKYEI7ES0xea+kmzw0WjzrICN0UCIPiE6b1m3QTLhP2lLpVRWUjlAuB4QERgkxCmnjmPQQHEoFKR5gNbziqP0W2fo8iwxwJXYrENWvdXipYVzdQxCCIkDBsRpTPljEP7DBOPjntp5P3kIof/CAnWdhisF8UN2xOCH/qnMpFIQR5hhALHn/5S37ekA0I6Je+lM/muOPSPmhflTDrP0fWRYEDWwimFL+JOp8l5IWB75MxmAekjWuAoskDIoyPH69pmUYfXHBS2HnAAQ7gBlY8+M7MnJkTNkLkIqs9XG/2CTnke0NhCoRuoEIJCB8qKT8MINXk03kYgTGIgP618TACRqDuEYC76d6WlbKgP+sGG4QpdTN9hg74qAyDewkRfv3rfQ9/4IGJDJUUMswgN9zQ2Y6bOyFaKWr03cSENxEXSBcKmm7A5SJvDjJF/hpEQUSudMIJ0SqFpot9kDunHLykAkEGCD9CcriRQ3jwwBP5WtreHk0iA2UqVhXG216k7l6Un8EGc+FBzhXKIkoPRRkcC3UNkoF6RPEEj1//OuL5z8+PzTbMgeINyFtBclDfCMkSzoWYsM7ZZ6+YiUK5W6iadhYq0qc+tWJ58Qo1E8Iq4lOSUe4BMiq+ipw6COyqSHWx7fp4JiysOZekLmYQJggYJIrBdaMwRGplSXhl739/HkKlsrcgbhAtkfoG4cN3oQmcNLpQdcGc6054ldfgxY+B4gHh44EayLG4HhA9lE72zzNkn2OsqUdhmoX/GIGRj4DJ3Mi/hj6DMYIAtiSJyOl+t0GHkvevkFryPCXf36wWWT2QFlS3YnBjLqpBi8pWhQVbRGC20/IHRWgwfE1qHGSPPDnCrvq8SUUDzbohd8rOI97znijpkalLA8UI43H+pyUXhKzo3QpJErFJyhikDqUIZQw7D6l+5F6lEKjCn1WRgpIIoajB6gdqF6FCqnUhKTINTrlsqG+Eht/+9pW3V+uvPmPatJxwQDpQnMiFg3AQFiWPD4WTylX6u9I8XqTjKarCnbW69l4icSURt/1VXZuI3FVX5ecOyVkfQ2QtXZsiNEwuJCQJTCFZwiUDG45fnAcqHIPrLgKcodBCbCFm8s+bKmI8Ufsoi/hhxtwpMlbWj4My2EAGeYAVg+Owb1RQbHAgwKiQEG0GJBKCjaUMOBfEj+30HWzUj4AKJN9h1hwv/x1TCPDzaPqYOmOfrBEYqQiIlRRkjm4QG8w4GMKhm+wjImaH6Gb9gMKlFXzgUKe4eXIz5eYt8lXiBq78tf203kNS4rD3qBIG/dCH8jw2erayLTdsqXFVEcRDFba8E4JIOI18sJkzUyFCg0jR00XQSjruEsJsKDLk7GEfQuiWvDWKHNrbc9XuzDPz+UBCdGNvk9qzGDLAQxWPqx0ojhBS1B1UJhQfVDXI5KoG5057LipMmQehYYgccwMTFCbCzpBR5spnhBDZv9TKxwkbokiyLWpgMSCRkFspcxOk7t3HeuqoAbkBi4QT6uBwDQgSnSm4nryGHEOUC7ULLHhdKGGQNeYI+cMwedq0/LwgW1ipcD5sL/w7VVSyUNdzsa5rjxTZTOH1VEwDmYMQol4Sduc9pA0FlOKIQm3jWoIzBBNyx3u+B2ANEWRb9qNHMpsGE66lhxEYYwg06nynj7Fz9ukagZGJQFVkjqpWEbnQ/7MekYUNNUjcl7r0X5GJnaWkPEtVlVPlIderG3lZqsweej5SpKpDN/BHRFDuE4mrUIUJiSMXDfJGEYHaXDWL+LUp/NrLDV838Kr2N5cbMsQHAgTBEUEiGf5REcGlumnvpH2URIg6UfWwPvnmN/ObODd43eg3lYJVVRiuTDgWMiJC1SVCkIgk5AqyWVs0MRBuVLPS9otCD7pPrMrjDfJG/h/ECmIDSUOdLMKDqFfkBEJMICGQGxQn1DmeeUBEIK8odxA84ZJC05AkCgz0HjLbg0IFkeJ4Cls2CucMLMkVHI5ByJYHOHIO5MBxLTgGJBwMOIeCFPPMvFmPAfkFB0LCECyIF6oZ60FiyS8UAZ+sdapcD9aBgEHIuP6QeMgbCiiEDqwgdXwGAYbkKlyePodUQv44JstRVAnPsj9h3q1tCQMnhTWfnf8agTGDgMncmLnUPtFRg0CDzkRkboOqc4C3LPl+rgjH/bpRP6obdpdu7M0iHf+T+vJPKSKzpeJlmPVCcFCgKFbghksOmsKGGAhXpehMkAK0h1poPap150O+IBI8uFFDgkReElXFq03L54sIdqLOcUMnZItSxXo6LiSiQyG3cbr593CTh0iJcFUhHeeckxMEyMVg6hznONiAmEJ8mAfqG6QGRYr9My/mQ6UpxJV1IW18RkEF/mpYi0BUIG+yK2mAGEKmwIj9EkKGHInkZBAcsITIQhr1GK8QYy9kZ7jIHPtlLoQsIXEQOIoJODahU4pDUEshSQyIE9eB3DQIH8QUsqf5N2o/GWQL4s8yritD+HSLlFYhZ+QcUhzBMSCuVCizDdeNbXgNMYQQ8l3gXEXmthRWS9hW84XUJ0IJaYYI8r2BKGt/hOyrEHIPIzDGENDPIg8jYARGCgKpqlX3riLcukHnTXWniguaddPtfdOb0o0XYtaJuiSycqQUGGkxcbVu/BN1Y1+icGizwq693GhJXIcskOMmA+EFb3lL3ATJ0SChPoMUQL5QZnQjL4lcpGWy7DhWIcCLUdbYlopK9lUMcu9Q4xTaXfza1+ZEAj82SAc3em74f/jD8BA5jgmJg6BBaDgGRR2Ql4EGJAOixPlDZpcRskRaREhaRD4oBuhijmABOSLMCUGE+H3yk/lehXmD1MWKyNEU4bOU9YZrcC6oY5AmyBOh02nT8opUcIZ/ZaBgAAAnGUlEQVRUgTuqJaHdGTNyYsf5oF5CwCBiIn4Vkc5dFKq9B4WN3EYUNaxLlPOXwqOQWIyd6frBdQY7iDD7JsSLaieVsknfnybNifZsyXNO13EJZBeSDpnTeg1ScyvgyjWGNELU9R2qcD6EvoeDuA8Xxt6PEdgACJjMbQCQfQgjMKwI6F6JMscotYj0bIhwq27AJd2Yd5WydL8UuJIUr1TVCAng5q2b+c+42aNWieS8SmrTJcqN60VNgXxQXKCbdoliAqlt2Re/GJVjjkk5Vxk3YIgeYTmIIYoWSpFuzhuLDP0EAgERQh3ihr6MBCYAij+EA1HqICMQEJQfKj8hXMN5Y4e4MDfIHEUT5GdBJgqljpBu8UCd5IGSBFFiOduCmcKMPRA25sdcUfIgo2AJZsJn+dCxqAKtQJwYFFD0H5AkCgnonbsmg7xADI0hS+wfpRCCRUUqc4BcQqQheO3tuTqrdfCCa5GCuATcmS+ETGHue4TD8SJvF3GOKkRARcuYLwSLYomDD45QgUsiuFdckePHMcCGoXMt81BouVXz2V7n1avvwQMQZtaT6lYVEdxRc76fa6A8vERGwU0/BpJBMyR6oCElOIXCB7I4GWh9LzMCIwgBvvXTR9B8PVUjYAQk3EDmUK8Y6Zll62soP61FRG5rhfjuV95ZFeNfSAO9R4sbMxWG3ESpKpVycgckBlJFGy9y3CAtzFfEoMRyCABGuYTZCCuK8G2mm20HIT0RwuTmL1LRK6JXpegBosZ67JdcPIgHOXa1A1LF/vgMgoSFCvsbzgGBwCKDqk0Gx0JR4sFrEvTJgYN4QuAgt6iOqEiQVZHRvd/2tniM1x/84Ip8MwgVpBaCV1spzDHIO4NQaV8dwqmKbQnkmOID8utOOCEvYCAsCiHEwmRNBmQTPzfUMeYMWWZ+qKAUm5AHJ5K9sUh2l8KuDQqTVkSeaMeV1DXOkVxGsBfet4vQtehaVERYdxQJnA9hhGzxOWQYjCDnM2fm1xDFDjLPefG9IBSta1zRfueKrC3QOU+WitnNNsxP13a+vktbi+gvBi8G15uwLd8xbHH4AVE7UBL5HPWX7xHz8DACowgB/VfoYQSMwEhDgHArViVp6P613oZuxhCXfXSDfYh8KgxxIXOE2IrwIkoORISbOtWquhFn2HGgzkAwGNzAVTBBcUOGYobKQgUlxIftdTOffeml+c1ay7JvfSupNBUqackbI/8OQgDR4GaPEtR/UCzAHCAPn/tc/0+H7z0KJNYkEB7IHUQVMgJRKEhbkT/HPDEmJi8OkqHCjxbIbEE2UNMgU+yDnMSvfGXleYq0ol42iiCWCU1yTOUeNqqv7bR3vCMZF09A0SQ8WyhcK+9l4CWEqLlWKHNcI5QuctbISYQovfnNEeedl6xCFoioHamcvqoqfJd983IvQal4zVIpd0X5UvFIRd+LXkK0UkkJCyf1kuvGa84bjDgWlcoHHph/dyBhdBEhZ5D8Qsgyy8Ba81uoa8qPFqxa0lwVXn0CxQ9iRocPMOX8wZFzqB2QUYgcPwSYg5W5WnT8epQgYGVulFxIn8bYREC3N930lp378jvsMGKhG2yjFJqHpMJk+KShnPQfkCcKHSBm3KwpAIAcoKKQ/6RQWZVQJzdSbrrcyPkctY0qTdaD4CkEVyJcSR4cIcyrr85bbEH8IDzc3DnWJZf0n8GK92wLKVqfAzJCxS3VsaiRkAqUIZ7pZsFycIIMQeZYF+USsqEikCUiHF3nn5+bK5NTx3KUNgjsQANVTspSlZxFbF1QKkWUIXgzRbBKMi7uQa0k8Z8iCvkCDjpkAB2nnRZtePOhsKHMcV3Yh6pym+WBV8X0F5IIyUKB1b7/q2twBFYykFCR+y1e//rYU2HXR0VeZ1M0AYmbOTMvhFCo9DHmcuGFuSpHVS7XHbKFiorSBhGDZEGGqQbmGvOa7wZ9ePkBAGGDgKF8kt/H94iCCvaHAso2kFi+f6igzKN2QP45FjijJnsYgVGIgMncKLyoPqUxgoDufTmX082M1zyGeyivbUclwM9DVerf+aH2WKgyqGfczLl5EzpDDdFNtnrBBXkiPCobRAgljhsrjx12iCB3Su2tttNNdyGGr9OnRyMKX3t7vk8IIjdpVKmhEJXaea3v1xA1HhAiHqsaqJoKUTZJWerkfKhGhQBDoCCCq1ISIT0QOIge4V1UM203XgT7EBV67CGivFBq5FQRrAWQGYiQ1L+knNbOBUJEGBV8yVVUAcsWUk31zYkurhnkDOUTFfFnP4uq9jFZ16R7xoycbDEH7GB0Xe/UNlO1v06FXZdK2fufzqWKoXFhFYIay/cFAsW15vpDyAlFo5xCXCHxEDBILwQfAsx3AWWNOXCtGSh0bAcOLIfIQf74rlH8wA8Bnjl3vk8oxrWD/EsIblHkgQrpYQRGIQL6meNhBIzAiEVABC5D0VhfQzfY7UQ47oOwrG4Q+kOl4kbLQH3hJosSQ84XN1uKBcjxeve7c6UK2wuS4hW224owLp+TY6cbfWXmzBXFENzAyQO7/PK06xH7R0paVY8M0kQbMAiv3icValUn9c535moSFbqoVFIuSyJBHSKAP0dlgvQQ7lVeInmGqQIY0tx/oE4RboTUad0GHXsW6hdKp65vSSpXVpAiVSBDuBaJRG2hUO4sCDQKGIQdQqdrPU9zoao0te4i5Ayp4lza2/PzIlTKNUdpZRREjzmIoE2Q0rqUvDWIHASPnEHIWH/lFxLG9xtSyHcKIgixhCii1EFeGZB9iGD/wfePYxACR730MAKjFAH9V+RhBIzAiEVA97/1psoBisJs83nmpri6AZnjpouKwiBExs2amy3qEyE7tfh6uZL2J0HMIDKoN+rN+hTdnOdSzIB3GeHVk07K/eEIUaIaofBhhTIKRiJykB4VA5QgQBRorCq8Sk/a73wnD8cSBoUYaf1MylmcfnoEoVJy2lhPhQoZRrwQasjYG96wAi2sQfD4I1QNcSLvjGtFXh/bQ4R4z3WCtLEPhSozhYnxEUwVrnxOxS3E+qKLUm5cxtxZn/1B4vGIIzeOUDf5kiiVHANVjuUQMb4fInObMRdUQtQ59g1p47sCuSwG3znmwud8v9i2+N5g58JnEGMGx0P9rB2ojWxDGJbtPYzAKEZA/zXE9FF8fj41I2AE1gUB3RAfl2LyEoX27ic5HYUH37b+g+XkhXGzRzkhFwriQM4VJIH8JpGye6WO9NCfFQsRqU4vmjYtHhAJ6SIPbObM3MIChYZtKHwoKkRRVzj+mlpv9J/nk/meik8wgszpfCYJjx4IDbmB/Qf5iRApCgQgS+CBMkUFMBjwunagfLE+5ArSh3JVXCdUPSpJIT4K0zbodRXyzHIGyqmuc5uIUplwJ6QMVU3H6FZ4cw8RySe4PgzmgUpG5SmvuT4ckzxJcgRRBclZg5xxPLppUM3MORB+hcTp0SniVqG4gevK9YZwoTLOnJkOk/7wnUFJhCiiGkIKWcbceM9rjg0WRTHOiq1zTztwgKwOl8ly7f792gjUEQL619bDCBgBI7AKBOhNqnyoPyrEOUk39nFUoGJXgRpUO849N78Ro7SQ10UbL5z+UdcgDty0UVhQSiBlUt8Ol9HvdSIAHb/7XV7FSX4UN25uzj//ea7u/fSneXEE+0DJGqjas3Ye9f4a4kKlqAjXBMgI59R/oLpBUiAgy/IOk2I1Y0aOSf/1ec967A8STVUvIUesTyiawIMO4gXZUq5ZCsujmBUDBVXzmorqVVSaQv64zgqvT4IcUqjBMVBcyXdDNUNJ5fqSA0jIHNJUFClA5CBcVD/rWrcptL63QrabYxEikt+Nyoe6BonjAS6oa/0H35niwXcIIgxhJCTP+rwndNt/8GOBHxZW5foj4/ejFAErc6P0wvq0jMCwIUDiuW68PSICJak2O0upmcfNHNUIAob6wkAFUY7dBN1ceyEpWI1w06UaEyUHoici0KB8q5eoAvK3GMASMiQPi6R8EuAhBFS+QuIYhA4JtRJSg5Cg+FA1OlgOX751ff1FlQMjkZ8GEawenWsFkopyBUli0DmB84OggCHhUQgLOWiEqlc1IC+ooFwPyE4RtsQrDlIDcWI/mPfyTNiTylsGc5o2LZ4nwvYA2IO3rnOTOk9Upfg9JmI5RUUEXcwLYocyBtnjfJg3BQbMFQLK9hhDU4Qhsk5uXoO2KWufjyn8uhSiSe4axLIIwTMfHrUKpaps048A9g3BR7Vjzlx3SCvEkvlwbpA8vhsQxGIQYkVhhFSiAHoYgVGOgMncKL/APj0jMCwIQMpkH1KV6jZXN9YG3dDpAFAhDHbIIXm1KsqOqgV7IXcoP7qZJ8KHqiOyVlKS+ziFyhqkzNyNooNfHTdh1qNaESLHTZ4wLZWe3NC5KUMSyLcq1D0IBarfSBucM+FoKUqZiHGDSEmVPC/ULIoLILSQIUgSCiQqKKQFIgaeYDDQgFhB5sASwgypIZzJ9pBulDOsUBRObdB6ma5fCXKMmoYqilqqvLr99NmtECx52LF9FdJGLp7UtKNFzv7DXKki5RiQJPbLfLkuEEKuE88ocsxZx8lEVsm9i89+NiePhx6aX2PWo3CDOaPKce3ZN+SW4gpeU6BBaBUyhwqHfU2RN8eymTPz8+P7AIZF8QT48b1kOblyhLI9jMAoR0A/cz2MgBEwAkNAAJKgnqqQhKoKGbohESILJdQT3XQzbsrc5AmLFeEzPZPoX5JSVBVR6MQagpsy9iVHHpmrLNzYCQuS90VVIzd2btaoPZAS1Bj2ST4XuVfc8EfqwIaEllkiGL1gRJ4b50jrLKljSZ3k3MEEggKeFAVQ9buqwXWAeIkkJ2y5RlLgGrSfKiSIghPUVXWeaBLB6UEZFCFrlvon1HOSKGL1G82tTWS9i7AreXmoehAhESKhn8+nIH+QS64luWooYJBOVDL84GjxVQyFViGRhyqP7gqFzjNCxxA4yCSqI2obrzlXCOAysjZeRFc0LL/uxfeK7cAFZQ5cII0UWXDuEMpi8MMAYonax3w9jMAYQED/FcX0MXCePkUjYASGCwFu8NyUqVoktAdBIdcKQlbceHlNojwPkbhU+Yi1CNYkkBXCiNzIUV9ImEdl4UGojTAfN2tUFR68Z7/sk+OM5Bt0QUi5FpwXoULULYojIHUQE86RSl8qWAmXgnP/Sk22Z2BXQhgbFQpclZs2RYS4WWSmmxA1RRDf/37eqUHqWouIV1nXD3XuSIVRb4eAsY5U1S4RuZdJCb0HdQ5yhrrFvEQSJ+j5f5A8CBUhc8ge+2dAniBZECiIJcSR8alPpbD6a3WcX8pLMCO8Sr5g8R2BoC9TDifo+FOlDHbpuJlIbi8kl+8FyhxErSjuYL6QP1RBcivBC9xQC1mGoscc+CHAe76rHkZgDCCgfyk8jIARMAJrgQChztpwJzd/iAXP3OhRWrihirQ0yqusQicBVByMXSFz3PwLs1zChNy8GbXhxGI9SNBoGXjpQWoJM6IeQT4gYxA31E8ICEQHQssDojLQQNmEXPE5CugJJ8RxMga+VApnD6FNerwWuXgQHqleZY534okp7Hkj66CIMVhPfV21tzzMTViWeUGeRC7vg8hJEWuQMloljK7OD8tz+PCZa2/PSV0xV13XkvL3jj388PgxPnWQOCpxCTNDzlD1IIAQOxG4pQrjL9X8GkTCJml5m/BYKuPoDogsWPBdgaChZvKdolMFA5IHRgz2W6hy/IigGMTDCIwRBEzmxsiF9mkagfWOADd8HrVhNnnLkRNXKfKjyIeD8EFauOEWoyByxfviebQqK5AnwqKQMUgKhAXigloH0YFEgc+qyBw9WSForE8HDdm97Kbcth+BPaoZpBniVgyt2yaS1A3BZsgj7l6OR8iSAVnWsl9J7WoVse7mPSFv5idivkjbUcjwMi37HWFvwqtUNKPiUXlckE+U1G98IxpF7g5Vx4ofYy+D8kdYnUEonfOFyPFdYUD+KX5R+Lwq1W+xzn0xx2Vu7A8MILpF2Bniq64ky7tu8DmheZazX+aCuulhBMYQAiZzY+hi+1SNwAZHgJs4D2783LS52RImIzxWqCsbfFJ1cEAqTlGRGEW4Mn+X/yV3rFZ1Kj6jpReVohSbQKR4HH98lLSvu1HaUKMgyxBFwqHFUDh8BxWi3IkfHEM5b4Ral5M5lsmCZqmqbPcQ4b4N02FCvdiQiBRWRJbIs/u9QqXjFI7tJDyMqgYxQzWDWEKmRPR2lx0Ktis/J7yLfUltCzYUWIgb60LOKHKBuEH2+V7wnjw/bFHIxWQdcIDMQW45L44JUSVEy7ZsB3krqmohgLQX8zACYwgBk7kxdLF9qkbgSUMAo2AGnRwgAShEI709V35Ga/93IBJX7A18UN0KVYrlJ5yQ1LJm5YX1QsQgQOTSvetdiWilFmiQO4hgrerJtiJ/+4iM3QnRYUCACImiYhUD8qd9drKMXDlCreQpKm+tqnm0iICVpaB2EfrmgbKG7QcKHsSKMKfUvbtFAisocKedVux5xTPkC4IGYYOY8ppzwbKEECokn7w3lEdyMSFl5M2xHcbFPHN+5AdCItme+YIXJJbzt0HwCrz9aswgYDI3Zi61T9QI1AECq6vKrIPp1c0UCGVCclDgUKKUP0ZBxCFSzH5NT1bC1NOnp/Aq6lqF1lr4+klZa1aYshciVAxadkkRFfXKi054JgwLmYMsFoPQqhS3mQptN0jlqqLMQShf97qoSplr1X47RfAyLFQgVZByVEIIH2FO5c6VVElboTCBwpaBBueyxx4px66ReUPCUAshmYSXKbwouoaQs4eVCRWyqHkYDotQtrGd5t3L3DguxBQ7EvZhT7mBUPeyMYCAydwYuMg+RSNgBEYgAqhXEBSUJ4U2mxTK/BVmyihoyktLBQoiNkmFQwnDguQTn4hdVJF6B0SwGArBlrTe1VTNKiSbBmQMEkQIs3aIOFW0/XipXB1nnZX3gBWhHCcitwgrEBkCN4hwVSlcgZRhQgyRhJQpRIp/3W7yCPyvjpnReQL1kRw+1oWM6Ty2VGHEBKlq9zFnVLQLLsjJIW3FUPfwiyMkX4RR6RhC5TN2KAqvdkHgRAoplqhyDpA6HszPwwiMUQRM5sbohfdpGwEjUOcIQOao3EQBE7EpQ4wgPkWfVIgPAyJDeJGh8OpDqGK14VOFLSE+ZfLcGOTBtbfnZA5VrXYQtj3ssKgS2qTylKFjT1T4swM1UHlwVbz+UMwgXCxjjuTqXXJJVNVT9k4Rye0Vpn2KjJCvp3JZr0tS1DYXQdxf3nK/Uuj0cYovpCSWqIpVBW6GQggppNMFc6czyLRpeR4cYVWIHcshrJhQ46FHqBUyV+CRJus/RmBsImAyNzavu8/aCBiBekcA8iVFLD0omCAcSQizGBRQoKxByIocOT0vIZeuIGkYFEtZq/J5QeZe/eo8fIvCRaVp7aBKVdt3o+wVnm2aQxUihfKFLQlkkJAuIWCUOcKi5LgRQiV0K2L3oOb5oIodpihUupD5KB9ulkjmz9k/xE9ErPGEE6JZ20wRWZskpXBnkciblX/3uELMGQriOefkeXOEUCmcAYvnPtfkrfZ6+bURWIaAftbEdKNhBIyAETACdYYAYUWqPlGtCFWigNUOFLKighMVD1sScuFQuCgmwICZll50WuA9OWlUgWI0jNpFAQNtw/oPFDmKCTg2c5C1TJfmkNHSjf0ofLq38vAeo/sC26MEUsDAM8eGdDHkF9hFtw7CphgJY6ECEWQfCptmUufK2maJ5jVPeXr3ah9LFFYuiRBio1ImNEuOJaSTcDPkknmtykA5P6r/GoExiYDJ3Ji87D5pI2AERgQCkCl6ug40IGdYfaCQUdmJgoU6RugTAkhlKMSMQgJUOaxCjjoqV9JQ9HjPuv0HeXjkt7FPttMxMlQ51DLlr00VibyfMCn9Vhl8RsEGfXRVEDFe6tkzDjwwHoU4EiIuSCYqHmFSSKQ+hxQm3zlCqCiPeO8RMpYNSRklkHNgHk972opzw6KEdnAeRsAI9EHAZK4PHH5jBIyAERhBCEDeKGZARYOEoYqR7wbpIdSqgoP0GvKFQsdnkCzIU63/W+0psx+KEdgv++A9xBFyJUK2g/Y5m84fRXcJtqVi9uCDYzcVQXSIkD1AHhv9ZiFl7e15mJQcP9RECB55byh0KHaEZvmMdWfOzP33UOFEODcSId1Er7eUIrdIeYFV5mMyB+IeRqAPAvov3sMIGAEjYARGJAIQGwoBUK8gXZjqkh+HwkWeGQQMgkShACFYPqOq9atfXfXpErKlehQjYMgi6iDtx447LsZJRbsDIkdLsmIo1w2vuSkiXP/F3oSuHVTCMniNIoc6yIN58AyBg5gxN0gcr/GM45isw3E110XK0VvEupwHRR4juS9vAsR/jMD6QcBkbv3g6r0aASNgBDYMAjNmRPBg0EEB0gMZQ4kjBEreGv5tEDnI1Re+kK+7qr+QK/LhIFeoeKhyDO23WySxQSqatLV8HHBAysFrkIq3gJw5+q/W9tZlLcgjD9Q7OkKoWKIkspZxDAonGIR7IaRsK1WxpGNknAe5gh5GwAgMioDJ3KAQeQUjYASMwAhBgGrTYhTWIeS+QYz4DJ+6oQx65VIkAZn7zGfyLRT2rGo/mAcr4y7vAiEjY3LrqhBGujX0J3LFsci3Q6F74IGcJLKcY6Amap5NsjF5iqpzH4aE6jglKYwZCp2HETACQ0LAZG5IMHklI2AEjMAIQwC1jrZbqHFrMihQoOMC1avnnbdiS2xFFE5tlWrWjR0JNiF6nfqiUmE6UHs2Wn1BJlEICQmjForAZapQbZg2LaaoeOPZys/7h/LvHj7zzLzThYopIHMpZLzi6H5lBIzAahAo6TNp6h5GwAgYASNgBAZB4N3vjpKUtOyCC1J7sZSXR/cHVDRUNgoxIHjkvLGMQgzCpnqdTZ8e8ba3RUnFD5l86JpECMvk9vFAscN+BN+7978/NlKl6yKKNj7ykUEm5I+NgBEAAStz/h4YASNgBIzA0BBQu69MIdFU6Yq9CeHV9vYoKSdvH3Vy2ERFFo/La44uFIsWL45eFTZkCtWixCWih0rHUDeLMoUUqHUieKkyVj1gkymywrhVKl5RBj2MgBEYEgImc0OCySsZASNgBIxAyomjKpbqUogclaaqQM1E4K6nuAESBnHjAdmjMnbOnLxHK1WsqrzNKLBQwUOjerhuq6KIXeVPd6WKLEqyIMkUlm1R6HUp233vewbcCBiBISKgxAQPI2AEjIARMAJDROAvf8k7T9CNAdNiwqmQN4osIHCQNSpgVdCw98kn5551Rx+d+81hoyIi2Paa1ySfuZlS365EkVNYNfvoR5N9ylbywiMM62EEjMDQEbAyN3SsvKYRMAJGwAiAAMUOGPviC0eRBd0nUOkgduefH/Ge98RWMhe+ke4PED2qVOn0wFDotYsQK4SNYosXvjAalD9XffGLk+nxAlQ58uU8jIARGDICJnNDhsorGgEjYASMwHIE6MPKg96rDFqHMQ4/PEoKlc5SXlzKe6OqFp+500/Pw7CQtaJK9uUvT9vtpFDrPQq9ThA5XADJu/DCtCv/MQJGYGgIOMw6NJy8lhEwAkbACKwOgVtvzbtMbL11NKqqtULniG9+MydyKpJIViPk1NHvlbHLLslweKpsUO7Byw67E1p83Xln/rn/GgEjMGQETOaGDJVXNAJGwAgYgdUigDqnatTywoUR06evWJXwK/l0qnBNxRN8oqrYkkjevBNOiHjGM6JJ2y2dPTvv6crnHkbACAwZAZO5IUPlFY2AETACRmCVCNBxAn+5ZdWqfdaj2wM+cpgB01kCe5O9944XHnhgxJFHpmKJpMrddVefzfzGCBiBoSFgMjc0nLyWETACRsAIrA4BmQEnIkexA31a+w+sTDAWVrVq7LFHbL7bbnH1Bz6QF1BMnBhlLEw+//n+W/m9ETACQ0DABRBDAMmrGAEjYASMwCAIqOghec9R4HDZZSuvfOONibg1yUuurPy4J6hkPeigvCgCW5Prrlt5Gy8xAkZgSAiYzA0JJq9kBIyAETACq0WAEKm6QCTjYEKnKHQQu403jlCHiNTv9U9/irIKJPaSYXCPcujuUiVs8pS75RZXsK4WXH9oBFaPgEqH3Jt19RD5UyNgBIyAERgSAscck1e0TpqUh1TxnlMIlVZejRttFOMUZl3y4x/nBsJUttKXFQuTSy4Z0u69khEwAgMjYGVuYFy81AgYASNgBNYUgZkzI5YsyQsaIHIicdHTk/ZSUSh1iQyD46qrcsPgNd231zcCRmCVCFiZWyU0/sAIGAEjYATWCgG6Q1DogFUJJsAURNx991rtyhsZASMwOAImc4Nj5DWMgBEwAkbACBgBI1C3CNiapG4vjSdmBIyAETACRsAIGIHBETCZGxwjr2EEjIARMAJGwAgYgbpFwGSubi+NJ2YEjIARMAJGwAgYgcERMJkbHCOvYQSMgBEwAkbACBiBukXAZK5uL40nZgSMgBEwAkbACBiBwREwmRscI69hBIyAETACRsAIGIG6RcBkrm4vjSdmBIyAETACRsAIGIHBETCZGxwjr2EEjIARMAJGwAgYgbpFwGSubi+NJ2YEjIARMAJGwAgYgcERMJkbHCOvYQSMgBEwAkbACBiBukXAZK5uL40nZgSMgBEwAkbACBiBwREwmRscI69hBIyAETACRsAIGIG6RcBkrm4vjSdmBIyAETACRsAIGIHBETCZGxwjr2EEjIARMAJGwAgYgbpFwGSubi+NJ2YEjIARMAJGwAgYgcERMJkbHCOvYQSMgBEwAkbACBiBukXAZK5uL40nZgSMgBEwAkbACBiBwREwmRscI69hBIyAETACRsAIGIG6RcBkrm4vjSdmBIyAETACRsAIGIHBETCZGxwjr2EEjIARMAJGwAgYgbpFwGSubi+NJ2YEjIARMAJGwAgYgcERMJkbHCOvYQSMgBEwAkbACBiBukXAZK5uL40nZgSMgBEwAkbACBiBwREwmRscI69hBIyAETACRsAIGIG6RcBkrm4vjSdmBIyAETACRsAIGIHBETCZGxwjr2EEjIARMAJGwAgYgbpFwGSubi+NJ2YEjIARMAJGwAgYgcERMJkbHCOvYQSMgBEwAkbACBiBukXAZK5uL40nZgSMgBEwAkbACBiBwREwmRscI69hBIyAETACRsAIGIG6RcBkrm4vjSdmBIyAETACRsAIGIHBETCZGxwjr2EEjIARMAJGwAgYgbpFwGSubi+NJ2YEjIARMAJGwAgYgcERMJkbHCOvYQSMgBEwAkbACBiBukXAZK5uL40nZgSMgBEwAkbACBiBwREwmRscI69hBIyAETACRsAIGIG6RcBkrm4vjSdmBIyAETACRsAIGIHBETCZGxwjr2EEjIARMAJGwAgYgbpFwGSubi+NJ2YEjIARMAJGwAgYgcERMJkbHCOvYQSMgBEwAkbACBiBukWgqW5n5okZASNgBIyAETACRmAEI9AwoSFKjaUI/s8zEpoepZJeLxtZ6H89WUQ5orK4Uixeo2f2pj14GAEjYASMgBEwAkbACKwrAg1tYmvNOXkrNYhmNep17fMKHjfgoaqd1SjPEbNbg2EytwZgeVUjYASMgBEwAkbACAyEQMN4kTiImxS4pML1J3F6nxS6/E++i1pih7SmR5bxR//vzqLaXY3K/MHVOpO5ga6IlxkBI2AEjIARMAJGYAgINIyrIXFNolW1hI6Qak14dU3IXIqbitRB6LKuLMpzV63WmcwN4UJ5FSNgBIyAETACRsAI1CJQapUCJ/KWlLhmPS97hKoRCKvWkrgUZmVjkbPlo1aVY2ES5NKffD3WrerlMqWu2lGN3kd7l29e+8JkrhYNvzYCRsAIGAEjYASMwCAIoMYl8gahK4gcxK5GmUuFDuTKSZ1DkVs+CkLHc/HgJaSNUSxb9pyWi9QlYldW6BVS93hfUmcyl5DzHyNgBIyAETACRsAIrB6BVNygMCrPKHMNrXoeV4rGSY1pWbVLIVFVpibVDpIHmWNoG3Lglo+Ct1X1Qilxhfq2XLmrJXK8hszpOWN9vaZIouehnuW7M5lbDoVfGAEjYASMgBEwAkZgYAQSgRNx47lpk6Zo3KgxKosqKacNclVduvpihdadWqN159ak0iViVxC2Sk7QCqJWELo+BK8ItxYKnUhdKpDQMXtn9Sbhj915GAEjYASMgBEwAkbACAyAAASucWpjNG/ZHKWWUlQWiMRB4BTyLM9edWHCALvKiaD21bZrWyJkfcKoInbLSR0bF4ocIdji9TJ1jvVQASGRVuYGQtrLjIARMAJGwAgYASMgBMiPa96qOZGwykKROEKpCplmyl9bUz+4/oBO2GdCNG3aFFmvyBr/h6gRdl32nJb1J3JaZfk6KHba1mSuP7J+bwSMgBEwAkbACBgBIYB3XOuOrVFqKyUFDIuQao/InAhU+Yk1U+RWBWjTZk0x4XkTVpC5IpSKSifCmMKukLZlVa0odAXZS896bzK3KnS93AgYASNgBIyAERjTCIx/9vi84ACvN9Q4hTUhWInMrWGXhsGAbNmmJTbad6P4/+2dzWrCQBRGLzYJFKLYjctWpM/RVy102WUfoND2CcRN6V6huChSFwERer9xRtNCcaNR8QTCRBMykzObj/u7qDxTVdY5iTnF0yVLnUSetF1ys+peFHaIuW10uQ8BCEAAAhCAwNkRKK4Ly3ruAlUnBrlW5QqVsPLxb2mQXcIp70rLuj5vcrkmC53mji7XdC+JOVU/4YAABCAAAQhAAAIQiATkXpWYSxay4OrUPddz6+v47K6H+evcqo/K8ktPtkg17DzpIlyrm4Q6TKSixLHbBGJu17vA+yAAAQhAAAIQOGkCipML1rjoykwiTpaxYB3b89dV75XN3mbWv+3/FnQqTFwXcrEoMWJuzxvC6yEAAQhAAAIQOB0Cqh+nM5QCUZxajFULXyDL3G7yHrYCkSt3dD+yvMitlXtxYgk5WerUZcLVWyhIjGVuK0cegAAEIAABCEDgzAjIvRri42JygdviVgSii1WN75s6ll9Lmz5OQwbtv4LOhR2WuaZ2hHkgAAEIQAACEDh6AvlVHlyp61IgUculhatIb9PH/GVuZVluLHSy0il+LlroEHNN7wjzQQACEIAABCBwlAQuut6ia6G0UV9eXcSl3/X/GvyC5ffSxk9jGwwG1spWLlfLfAFScX4i5hrcDKaCAAQgAAEIQOB4CRQ3nsGahFs9Vk5LPpCQS7Tkch0+DK3T7azi52rWOcRcosQIAQhAAAIQgMBZE2j32hsxl8SbjyGL1dVc6MhwQEKLz4VNnieW5Vlws4akCM9o/QH6cR2kX+SGPwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from IPython.display import Image \n",
    "im = Image(filename=\"/Users/Deathvoodoo/Documents/random/pymol_prot_fcn.png\")\n",
    "display(im)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Work in progress..."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}