diff --git a/notebooks/session12_inclass_rdkm.ipynb b/notebooks/session12_inclass_rdkm.ipynb
index 78ad264b..c915eb96 100644
--- a/notebooks/session12_inclass_rdkm.ipynb
+++ b/notebooks/session12_inclass_rdkm.ipynb
@@ -16,7 +16,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:30:49.911274Z",
@@ -70,25 +70,14 @@
     },
     "tags": []
    },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "(1797,)"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "y.shape"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:25:46.040606Z",
@@ -133,7 +122,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:25:47.359743Z",
@@ -176,7 +165,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:25:59.086486Z",
@@ -186,128 +175,7 @@
      "shell.execute_reply.started": "2022-05-04T07:25:59.086419Z"
     }
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "# Tuning hyper-parameters for precision\n",
-      "\n",
-      "Best parameters set found on training data:\n",
-      "\n",
-      "{'classifier__C': 0.1, 'classifier__penalty': 'l1', 'classifier__solver': 'liblinear'}\n",
-      "\n",
-      "Grid scores on training data:\n",
-      "\n",
-      "Run 0: 0.967 (SD=±0.018), using {'classifier__C': 1.0, 'classifier__penalty': 'l1', 'classifier__solver': 'liblinear'}\n",
-      "Run 1: 0.966 (SD=±0.022), using {'classifier__C': 1.0, 'classifier__penalty': 'l2', 'classifier__solver': 'liblinear'}\n",
-      "Run 2: 0.971 (SD=±0.024), using {'classifier__C': 0.1, 'classifier__penalty': 'l1', 'classifier__solver': 'liblinear'}\n",
-      "Run 3: 0.97 (SD=±0.019), using {'classifier__C': 0.1, 'classifier__penalty': 'l2', 'classifier__solver': 'liblinear'}\n",
-      "Run 4: 0.933 (SD=±0.045), using {'classifier__C': 0.01, 'classifier__penalty': 'l1', 'classifier__solver': 'liblinear'}\n",
-      "Run 5: 0.969 (SD=±0.019), using {'classifier__C': 0.01, 'classifier__penalty': 'l2', 'classifier__solver': 'liblinear'}\n",
-      "\n",
-      "Detailed classification report:\n",
-      "\n",
-      "The model is trained on the full training set.\n",
-      "The scores are computed on the full test set.\n",
-      "\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "           0       0.96      1.00      0.98        27\n",
-      "           1       0.92      0.94      0.93        35\n",
-      "           2       0.97      0.97      0.97        36\n",
-      "           3       1.00      1.00      1.00        29\n",
-      "           4       0.97      0.97      0.97        30\n",
-      "           5       0.97      0.97      0.97        40\n",
-      "           6       0.98      1.00      0.99        44\n",
-      "           7       0.95      0.97      0.96        39\n",
-      "           8       0.90      0.92      0.91        39\n",
-      "           9       0.97      0.85      0.91        41\n",
-      "\n",
-      "    accuracy                           0.96       360\n",
-      "   macro avg       0.96      0.96      0.96       360\n",
-      "weighted avg       0.96      0.96      0.96       360\n",
-      "\n",
-      "\n",
-      "# Tuning hyper-parameters for recall\n",
-      "\n",
-      "Best parameters set found on training data:\n",
-      "\n",
-      "{'classifier__C': 0.1, 'classifier__penalty': 'l1', 'classifier__solver': 'liblinear'}\n",
-      "\n",
-      "Grid scores on training data:\n",
-      "\n",
-      "Run 0: 0.965 (SD=±0.019), using {'classifier__C': 1.0, 'classifier__penalty': 'l1', 'classifier__solver': 'liblinear'}\n",
-      "Run 1: 0.964 (SD=±0.022), using {'classifier__C': 1.0, 'classifier__penalty': 'l2', 'classifier__solver': 'liblinear'}\n",
-      "Run 2: 0.969 (SD=±0.025), using {'classifier__C': 0.1, 'classifier__penalty': 'l1', 'classifier__solver': 'liblinear'}\n",
-      "Run 3: 0.968 (SD=±0.018), using {'classifier__C': 0.1, 'classifier__penalty': 'l2', 'classifier__solver': 'liblinear'}\n",
-      "Run 4: 0.929 (SD=±0.049), using {'classifier__C': 0.01, 'classifier__penalty': 'l1', 'classifier__solver': 'liblinear'}\n",
-      "Run 5: 0.967 (SD=±0.019), using {'classifier__C': 0.01, 'classifier__penalty': 'l2', 'classifier__solver': 'liblinear'}\n",
-      "\n",
-      "Detailed classification report:\n",
-      "\n",
-      "The model is trained on the full training set.\n",
-      "The scores are computed on the full test set.\n",
-      "\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "           0       0.96      1.00      0.98        27\n",
-      "           1       0.92      0.94      0.93        35\n",
-      "           2       0.97      0.97      0.97        36\n",
-      "           3       1.00      1.00      1.00        29\n",
-      "           4       0.97      0.97      0.97        30\n",
-      "           5       0.97      0.97      0.97        40\n",
-      "           6       0.98      1.00      0.99        44\n",
-      "           7       0.95      0.97      0.96        39\n",
-      "           8       0.90      0.92      0.91        39\n",
-      "           9       0.97      0.85      0.91        41\n",
-      "\n",
-      "    accuracy                           0.96       360\n",
-      "   macro avg       0.96      0.96      0.96       360\n",
-      "weighted avg       0.96      0.96      0.96       360\n",
-      "\n",
-      "\n",
-      "# Tuning hyper-parameters for f1\n",
-      "\n",
-      "Best parameters set found on training data:\n",
-      "\n",
-      "{'classifier__C': 0.1, 'classifier__penalty': 'l1', 'classifier__solver': 'liblinear'}\n",
-      "\n",
-      "Grid scores on training data:\n",
-      "\n",
-      "Run 0: 0.965 (SD=±0.019), using {'classifier__C': 1.0, 'classifier__penalty': 'l1', 'classifier__solver': 'liblinear'}\n",
-      "Run 1: 0.964 (SD=±0.022), using {'classifier__C': 1.0, 'classifier__penalty': 'l2', 'classifier__solver': 'liblinear'}\n",
-      "Run 2: 0.969 (SD=±0.025), using {'classifier__C': 0.1, 'classifier__penalty': 'l1', 'classifier__solver': 'liblinear'}\n",
-      "Run 3: 0.968 (SD=±0.019), using {'classifier__C': 0.1, 'classifier__penalty': 'l2', 'classifier__solver': 'liblinear'}\n",
-      "Run 4: 0.929 (SD=±0.048), using {'classifier__C': 0.01, 'classifier__penalty': 'l1', 'classifier__solver': 'liblinear'}\n",
-      "Run 5: 0.967 (SD=±0.019), using {'classifier__C': 0.01, 'classifier__penalty': 'l2', 'classifier__solver': 'liblinear'}\n",
-      "\n",
-      "Detailed classification report:\n",
-      "\n",
-      "The model is trained on the full training set.\n",
-      "The scores are computed on the full test set.\n",
-      "\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "           0       0.96      1.00      0.98        27\n",
-      "           1       0.92      0.94      0.93        35\n",
-      "           2       0.97      0.97      0.97        36\n",
-      "           3       1.00      1.00      1.00        29\n",
-      "           4       0.97      0.97      0.97        30\n",
-      "           5       0.97      0.97      0.97        40\n",
-      "           6       0.98      1.00      0.99        44\n",
-      "           7       0.95      0.97      0.96        39\n",
-      "           8       0.90      0.92      0.91        39\n",
-      "           9       0.97      0.85      0.91        41\n",
-      "\n",
-      "    accuracy                           0.96       360\n",
-      "   macro avg       0.96      0.96      0.96       360\n",
-      "weighted avg       0.96      0.96      0.96       360\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "for score in scores:\n",
     "    print(f\"# Tuning hyper-parameters for {score}\")\n",
@@ -380,7 +248,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:27:16.494482Z",
@@ -390,18 +258,7 @@
      "shell.execute_reply.started": "2022-05-04T07:27:16.494424Z"
     }
    },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "(64,)"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "X[0].shape"
    ]
@@ -417,7 +274,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:37:00.550732Z",
@@ -465,7 +322,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:37:01.152919Z",
@@ -498,7 +355,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:37:02.161634Z",
@@ -540,7 +397,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:37:03.207961Z",
@@ -569,7 +426,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:37:07.974515Z",
@@ -580,16 +437,7 @@
     },
     "tags": []
    },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/opt/conda/lib/python3.9/site-packages/scikeras/wrappers.py:290: UserWarning: ``build_fn`` will be renamed to ``model`` in a future release, at which point use of ``build_fn`` will raise an Error instead.\n",
-      "  warnings.warn(\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "grid_result = grid.fit(X, y)"
    ]
@@ -610,7 +458,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:37:28.170707Z",
@@ -620,16 +468,7 @@
      "shell.execute_reply.started": "2022-05-04T07:37:28.170652Z"
     }
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Best run: 0.924 using {'batch_size': 5, 'epochs': 10, 'optimizer': 'sgd'}\n",
-      "\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# print best results, rounding values to 3 decimal places\n",
     "print(f\"Best run: {round(grid_result.best_score_,3)} using {grid_result.best_params_}\")\n",
@@ -652,7 +491,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:37:30.648754Z",
@@ -662,22 +501,7 @@
      "shell.execute_reply.started": "2022-05-04T07:37:30.648698Z"
     }
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Run 0: 0.896 (SD=±0.062), using {'batch_size': 5, 'epochs': 5, 'optimizer': 'sgd'}\n",
-      "Run 1: 0.878 (SD=±0.068), using {'batch_size': 5, 'epochs': 5, 'optimizer': 'adam'}\n",
-      "Run 2: 0.924 (SD=±0.061), using {'batch_size': 5, 'epochs': 10, 'optimizer': 'sgd'}\n",
-      "Run 3: 0.914 (SD=±0.066), using {'batch_size': 5, 'epochs': 10, 'optimizer': 'adam'}\n",
-      "Run 4: 0.893 (SD=±0.074), using {'batch_size': 10, 'epochs': 5, 'optimizer': 'sgd'}\n",
-      "Run 5: 0.869 (SD=±0.058), using {'batch_size': 10, 'epochs': 5, 'optimizer': 'adam'}\n",
-      "Run 6: 0.909 (SD=±0.073), using {'batch_size': 10, 'epochs': 10, 'optimizer': 'sgd'}\n",
-      "Run 7: 0.901 (SD=±0.064), using {'batch_size': 10, 'epochs': 10, 'optimizer': 'adam'}\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# get all means\n",
     "means = grid_result.cv_results_['mean_test_score']\n",
@@ -711,7 +535,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:38:23.367733Z",
@@ -759,7 +583,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:38:27.500519Z",
@@ -769,72 +593,7 @@
      "shell.execute_reply.started": "2022-05-04T07:38:27.500463Z"
     }
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/vgg16/vgg16_weights_tf_dim_ordering_tf_kernels.h5\n",
-      "553467904/553467096 [==============================] - 10s 0us/step\n",
-      "553476096/553467096 [==============================] - 10s 0us/step\n",
-      "Model: \"vgg16\"\n",
-      "_________________________________________________________________\n",
-      " Layer (type)                Output Shape              Param #   \n",
-      "=================================================================\n",
-      " input_1 (InputLayer)        [(None, 224, 224, 3)]     0         \n",
-      "                                                                 \n",
-      " block1_conv1 (Conv2D)       (None, 224, 224, 64)      1792      \n",
-      "                                                                 \n",
-      " block1_conv2 (Conv2D)       (None, 224, 224, 64)      36928     \n",
-      "                                                                 \n",
-      " block1_pool (MaxPooling2D)  (None, 112, 112, 64)      0         \n",
-      "                                                                 \n",
-      " block2_conv1 (Conv2D)       (None, 112, 112, 128)     73856     \n",
-      "                                                                 \n",
-      " block2_conv2 (Conv2D)       (None, 112, 112, 128)     147584    \n",
-      "                                                                 \n",
-      " block2_pool (MaxPooling2D)  (None, 56, 56, 128)       0         \n",
-      "                                                                 \n",
-      " block3_conv1 (Conv2D)       (None, 56, 56, 256)       295168    \n",
-      "                                                                 \n",
-      " block3_conv2 (Conv2D)       (None, 56, 56, 256)       590080    \n",
-      "                                                                 \n",
-      " block3_conv3 (Conv2D)       (None, 56, 56, 256)       590080    \n",
-      "                                                                 \n",
-      " block3_pool (MaxPooling2D)  (None, 28, 28, 256)       0         \n",
-      "                                                                 \n",
-      " block4_conv1 (Conv2D)       (None, 28, 28, 512)       1180160   \n",
-      "                                                                 \n",
-      " block4_conv2 (Conv2D)       (None, 28, 28, 512)       2359808   \n",
-      "                                                                 \n",
-      " block4_conv3 (Conv2D)       (None, 28, 28, 512)       2359808   \n",
-      "                                                                 \n",
-      " block4_pool (MaxPooling2D)  (None, 14, 14, 512)       0         \n",
-      "                                                                 \n",
-      " block5_conv1 (Conv2D)       (None, 14, 14, 512)       2359808   \n",
-      "                                                                 \n",
-      " block5_conv2 (Conv2D)       (None, 14, 14, 512)       2359808   \n",
-      "                                                                 \n",
-      " block5_conv3 (Conv2D)       (None, 14, 14, 512)       2359808   \n",
-      "                                                                 \n",
-      " block5_pool (MaxPooling2D)  (None, 7, 7, 512)         0         \n",
-      "                                                                 \n",
-      " flatten (Flatten)           (None, 25088)             0         \n",
-      "                                                                 \n",
-      " fc1 (Dense)                 (None, 4096)              102764544 \n",
-      "                                                                 \n",
-      " fc2 (Dense)                 (None, 4096)              16781312  \n",
-      "                                                                 \n",
-      " predictions (Dense)         (None, 1000)              4097000   \n",
-      "                                                                 \n",
-      "=================================================================\n",
-      "Total params: 138,357,544\n",
-      "Trainable params: 138,357,544\n",
-      "Non-trainable params: 0\n",
-      "_________________________________________________________________\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "model = VGG16()\n",
     "\n",
@@ -857,7 +616,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:40:04.278636Z",
@@ -868,19 +627,7 @@
     },
     "tags": []
    },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAOAAAADgCAIAAACVT/22AAEAAElEQVR4nNz9d9Bt2XUfiP3W2vucc8OXXw6du4FGaoCIBAmSIEVREj0jjcKoLMkTPE5VtmaqNK6yymX5D3vK/stJ45nxlG3JKiVKGksUwQCQlESAyEADaDTQAZ1fv9cvv/eFm07Yay3/sfc593z3+97rBghSLO+69d79zj1nnx3WXjnQd778JWZmZjCIiIgcMRExs2MGQGAiByYAzAwAABEd/Zfg4nd26K6gbezSnTAfX0Qs3ePpnrb/Y1/UNTJ2IDIQm5kBsN7N6QupCpi98fJZM2vv0faSjz2AQhzU8iekMZi67sE45vhrerC936h7rHvjoa7a+9G/CAAIK1dIj/aQJgDA2l8VwhyHkQYjsDh9s6YdFQNQVYO3tsFcvF+5aYeQeoh9p7vMADhNX4yQHm9fpKqAsWHZMwBqxyxlXDSL+2QGle5Ohalq+gqoapDUTyCKVxTs210BgwhEOAQK77wREeztbzv6VB+qVgCxa93WdjeYGQxYAtw9hnQELNo/afm3GTP3bmLcr7VQ23XbgngEBQBgPea5e/dA3YPLV9uRK/GqxWvxWYIzgxmUDAmwujll6RFNi9AQzEDEBgMlYCLz8TZpjxshnkCj5aGi5fvTB8t/SYmI1ASKwxBgnGl6i6Yl6rVer2nQTFBTwJySqjqACL6/5R3e6tqxYNd/5BCGI0UCsvYGCPVa+3ic5BJ6ul9XQIqI7L4geGwjZpiZEsBm1O1Z13nEr/2DYWbEq9B8X/juX6HeFsLMRBKWPbKcAKCaXm3arkkHLl03tDw//Ze225zeqBFXEazFoLYccwteh2fU9iDx1c46xJkeZAOlHVKDIb3KiMigRDBVANxRj4gmDAwCkZmZpekrO403qyxxcJydAYd3mZnR7hRU45p4mEcLHwSjRBzvicl+PC0t66F9je3o9v8oLdGa+yJC46Nvb9tRNLbyIIAlIesT/XgHWcfYdD0scSrBtTuhLRprl6I7Mx3bkPgGCqpoca213VqHjO9Bvfoci0fCkAl9JUIS4iBdi9iIqIVz6nq5R8+RE1MTBYHS9lm3Mty9pnfyjqIA0hZWKU7NGBQxPZn6FVjsAPRHglFFOnHuyJX+xXu2DqG+81f2edAjjU0JiQftSFX8cn8qHBHtOxxCy0ESAyACqe+6OXp3h8acy2wVQbZwCWvH4Nov/dF0R0jb/9j67yIYNfFdrOn8+PZ3USFyLXfYojEjjeeFvJmpqiFyoQbieOjb1ykAaOSGFQC34KyJWnWzbxyzqnbMT7zb2j07JDMAEU+nW1I35pla3pMAqJkRt+woXFx2IkV6R+R2CHFcRID5jlqTIxAMkVwSEZmDIbG28aGO2yOyIwjb4g3WyRvg5SGk3nVVAgjcTjLNLx7htJ0EGChtARMBpukwG3FaAaJu7zviqG1n7fKx9PiloyyHQ/d87IHCyj2qfbQRetONO9Ud3bSRgkOYMhHdZQ+6QmqcHTlvLWeTkK51TKo5F4FeiagjCGQBiY2WyKS2Ql/HJkUSm/bDWFQV7DqKnhAzEdCSFHJmcHChPW8wbomCKQUzMyTmCoATYZjBBEoEJpC2QlIEkiRbdxB7iH+MgyNQBxMdmVhdQ7Llhh1tHTj0YQuJ321J2n17uFc7fCLt8E/p31Uh6e26eofX+zccZVT+kFgmOkIHfAscnQwS7s01RW448aAGBbUSVYs8D0lIiatpkZ05RyLSrTO1/K4iERDlmg1mILW0s9Ri5XgyIswkRcQqQqUoJLl4LlqS1pdLVrBFQr9oOXccAuHuNmZeeSo269jhqICyJaR2h5tBUOuDLaNdRGtR9uHxJES4PBxpg46oIzpp7NCfPbEUy9Vfbcfu8Sqd7XVynKzZ786MiKyPH3tiUH+fup2zxIMepolHpNVOzlh2zsccGCzlLWvfwqZR5OmQZBxAEmrNjEy7Bzs8QljtP0KdmZFq7KTbbAeySKbbIxSlscQZt/NNujMzM/MEjchSKQGWA0XC2tcgcm9M6QofAs0OBQPodDZKh9a0v4jdKneot8PTcQzxzkiqObF3h7dZDXw8QAFLIWbl6n3//MNqR0FEVTvlpR1/AA61Y3EwdzyrpQNpLW8gHXP5zjq0SMCtLyDKfR4xCAB2PUWBWquTEABqSlErpD02A1AzBhlgpHGoHU7tr0Lslom8JdgjUmMmwpKDjLQ+QQmDzLhFF8zc16+kL6REHBc8gaNntIeSzBKccUd/tcVhrX6+ZTdbakLQRGjoiMrpMBlf4rNVIms9fNZumx2jU7u/+vM+7Z6otNP1mPLR+82kRz+AiPYjjuh6IgGWAt6KvokoAjqIW3NDOwbX9qpIW3CEt1ne3zJX2rFAZhqlGRBgQmaeSVpNqXXauyi8twg2DTkxqSBjAEZmLbtpZowo21sUxSLH2rETTF7NgqmomYFhnby5xGdHd+AdslC8VLS0MNsJBwTHvMp9tjhVOwb3cDMz/kPi3v5Q9Wht08N0+cfYOvYmHrOjGHhpilrqz1fuMkSauxSpGWhPArG2anXH3tig2ukBDNAlN79kC4/lJVZG1Q3FukH2kUmfOwEAHALQFW7y8FqstuOuW9QUCIwIzOS7U0XgTjfesg4dr9oS+Q4cE9Vwzq0oYo57Y5r7PW744dpxQvo7egrAEeQEZodjBn/PoVInjLdyZ69P7fechITOXmur5LjTd7hWy7gyivQnJ/D1RCLLVxjMEUVFvaqSmuuti5oJLYfSLZreU+XHLUx2HP+S9Y+bHWm9wrTXgYL6UvwhMnosvMa/u+srdzIlliAjJhAZ+ZZSt2qsaMVZSlEdk9/21n0hIJqQ7dhjc6T1VAi903yfB4+w9mmCfcTwdi9dLguApRJsqWY/DE+JLLYafqxKr3wckmsfPPTTCq0/pmm3/UkEocP8OqGl1FEuaYlV1MUaDJEEx41lg1onWhBoCWhm8U9VjXjmPgDaVw9EuTdqqTTyXmRKMCJr1QtmLYlfEWXeyd70wTR9JwURM2eWNFXtnGyp8KR2nHHgkX0+LPZGea63kvcZRIdDfmQO8o9jO+Z0HSfzUcf+dprRdh2y5cIkYfkYwOmrypewnvAoAVGAbvU2prw8FZ0qPdn134EJ0Mzuv5nHPELcI/FxNMQRm3Tja+HQQDCOah8iIkeJoBvDRe6TGJFodLpSY2qVRAJ2ziWTbFqXaGNgOjq7Jcjed+ZH4DJqs6A9hNHb2vRrlCU5STDdYNI9PTHsfq/uhrBEk+nPpW6oNXm3Y4jXXTuxljtsbSsrNtNuVJFsde9aKqggqfv29dbNorOHpHfZMYvcjqidbhyHS49FJWiLFDt82T7Y+jDRKvHudkyRTPBQJ4AxtwqmyAu235dWDI7I1AgwOCKOps4lBjwsuxzb7seSHtYiHXnkDyor/Ajc4R9NV0e4BVr58rZ/rv704xpcv/+3Q3J9RBhp8NGprT7yzgaq9DZ45j7Nr4Dj0cXteNO37SvB9z2u/yEs+x/3RkSd71Kv9TB6i3SPPzDvYM3f+VB+KBgxMwlhxeZybNNjxJ+ki018Zrx41OrVvav9HPsmf6/V6YtBdti80f6bxJcO+SfXASQFLRG1OthD4L6insAxVp8lE3Z0AG/fDgv+qw8mSeWQ8eaY236YduwJt75R5LiR/FCTeicIAr396mA/Pa56/zf12JL03TkXQgDArS4Fve3TqDi11YFFdWbH5sQr1l2474w6jQ0RtTxG6w9KvRP2zoWke11/51tOkd398WGKP2D70dRMP2TrM7udzuVwa4H8367wd+xSWCtGLIWpw0h0KaNHbUDUx8Q79RhxquNikwNGawSOsOGZhIgI6iIbCuXOTwSuYzNoqbVUxDOSZB1yka1uhRJrQV3NOAoECVw1KqEcCOmURNA8Vj5NCGCpGzGo8VGX6qMLmHpYqgGOow/tGminw2uV6j1tUYdUjI7Yse7bOqcKO/z+41VFq6M6dCmZvyMuemdvT70f6uYePKi1PMZSD0AAkakZmDx3qDDqg6z1CNSlYoBUO4f5+HxaLlMHqLaqRlMNDqRghSMiSwtklgJClJSJIBqNlnFQ3rUiEicRfjX2gwBmdpr2TVLoEhjJGB/lQ4JmUZQ3E263p1UuEoE6r9p2w8zeIZP9B2rvEJ3/2BHnfQD6HdLrP4LWUVW05ur2ynLk2p5eBeywIh1vM5fI8iFEVRWT02QuXcFJrfSSMJezTtInz+3QHBMRWvYRcTCR2JMpGVNPVGdiH3sAlFx6h1g8qempHn8KOoRJjtm5YznFI9f/4PziyhvfGR8S1wrouQ3cq/WV6sduXv+NR6ezAtY9tc47hel3pJJsDZV6CEb7NyQKri1BB6CSghz7j/Qf7P9EREJgKLdOLYkPteUc4/2OQEQiatCoemImM6iamnomi1AX/e6ita1Fn9F7xAgw0ohYXRSNTJcece0jRi1vnmCeepIZcRsI8UeBNv8w2wpU/bBs6x8H9Lk0zy+N44cRARANnwa2FMvWMyvbO2SNlczYdNjaZCvyBgSCwly7aExmpq6NhTUDq0bAdeS9ayk7GZha93UAPRRIgLRe99xJUZxsA3Gs3T0AnEUfuaX0c7z+6Y+k/RjQbV/H/cNDVwfBPUn5GMSJP2Z6uKX0cxhT/rAHjJkLEQCqWhoJDO4Y8E4SEIEN7NjMVBWhXpo6pfX/j77FAHf+nUTk4Fo3+3Z8ahEEW6OP+daj2JgMMEYvmNd0aYNuMav5nn9FklqW34+bww+1NG3H99MyUvfSZesCg9rxHsL52qHOdlSwoxEXvcarHuPcmn+0Q8JLQtMDZRw+Gu+w0WGldReTvpIf4Misl/CXFGTRVSBpjWIMRnTAIwOkGyFclCWEArfzyAweFgi5ydAELLWIGOfSVELICpfBgc3ESC0GmQAeEFSgzFkwAerQVGE1aK4/T2cU/aUJiL6e/XtXHozsaV9F1S0u9RQqf3zaEmj65+FHOgMrUPV27cfjePXjavcefNLBx5Die86OWn7BHKBOkaPxTGwqBkdCJt2TZpBg7MQRM5oY2eyMUrQdBUdF04C8GiyE0DTi0eKYJWB1Eo5FszqIk9s/kFyRun3sUCyWg1jV6q+sxb1+RR9W7oFKf4xI9D5otT+GY5RBh1XxKxjr2Lcfup/b8Sy9kld1QOlsM4MA/VEA2lq9mFiKnV+ZwlE7RYc70zapRMZMjkyOiFyLa5Pl3IxhTtTDRgBMGCpqDIOpgk1JFXXQ6HrhTCkF4Csbm4GIVLNyoU2jxVCTAsB6inpr390hO24j5QkW8+G0SqXEA9xrdZYhbz9Gror5R8568uNtR7mxt9UtHKK5ZsysbbxOurQCoMl77UdXWSjM/mDiaEcAXZtpQ3uD5Nbjrot5GsA8msyEU/CJsSqYlJyKqULVzCjLckBIrKmVGUTUmAEcmnAwgzTsMuKKm7qGQAJ5iu5JUDJhYhgMhSemqE0ligZZSkiWkhKpC+oAYFAYevRfkZLJHLtArRrqmB+WmLmL7uzcmo5yTe90oS11jmVMRX9o9wKvY9Tmh37upm8dRo3X0f8zdRW5e0W0VJMxJy8eMzPRvtqFiKDGqgCJwnleYUW7P+JTYurIHUbnMTyDYEtXRuoxyl20DpmQgQ0NdxsY0yeRJ0kcZ6fA92oCislIKFnblSAqbHBSO1ayyFIamSml+I4QPZHVHJw1jaqFOQmJ8x5ACFoHiLpaiWBo/KSuyTKTRgzHhHxQl5wK94CkP8L241R8/njbMXJGe/3YFqGTCNQArQ3Qe4QQYwus1zidKTODirCjfvSI9c6GRSFMl7i8FXFS0+MEOG7ZCwGYoEBmZqJmxk5NyQwcIGYWXSsiyoeCjCBsKT4ZMAhx0MinslAbEGoGUyhShjAKqmoIIbTaUPZ5RsxlWYqYmouZDlTFDCIKE6gSke8NOhmQ4thdDJrrkvP8W2p/bAH0XsqBpQB+SKJsLZYMkJqqRTuwBmKQJxAgSpqYUdPW1U0jKHOim2pIRuWIfWFoTSzt25cID8A9+LA+bofBCC5IAlBRM1NB5C+NUJM657z3ICEDkxmrQ0p90VRNCtCLasfkXw8AggCwmImxGauiUwERsaqG0DCzmagaEbEpOHISzlSZnEL7HvUt60nGUDIiuASdZsdOdEUe6n+/v/r6/qofdAv8h4DBV7m94yxVR6/jyFFZFf/v0WHvWQMURDAi9lAF3BINJwtgl8wkyWeRw1pdLk2IVgE1c+bM8aoyqx1bF0YivR467oXVIt8GlaROUyElCyrRyM4kpiZWl3WWMzOIW9u2oa5qgJRAakEMAHPC2WoqgClUWRRqZCCzkDgQETNSAxGYmYzabpTimB2piPWjOrlFlm/jmPX/X+0+AviPFXnbMo+StNpQeAAahEkAmCkdTl9FRAxGzDGWVKcAAEkJQAgu8w5MCl1xPO3FD6W5qGnn3xnlblUlCZ4YauYEalAlg2hQtdpIzdTA5lQUQF1S5sxlzsiaWgCEBoGUFVADm5gY2LeKfTEfgpp6sRDEOtkjHcbosUfkc6pD4HhoyRgwbyoNo1FkS4fl7ouLRk2mVnpzRMtAbW5v6zY2AjQZhDobK9K/h1Sh3OrF76OXWaZriz30Eff9sfI7aZ2wYXTIurO8oSc7HasjO7b1OyFmO6wYiiJmmpoYLzPfBqixKMjBYuBMO4jIRzJFsFaBS9p1BVQ5hliSA8EZyJy5GLwtMCJiYSDEfgSl44xqcmSkAU6YyYRMxGlUyQgAEkDM1MRcENWIn4mIKLRaSJPQgBsRZhcD9pWdSqKvpA0TJ9zsWEHSQMBCJpIZTK2FFAVAEqNGAQgROVMxMjBJACtMnYKgPQx6aEHvvRnaCq3anemWo/+3yqz+0O0d69V/yH7etttWs62CGNez6g97pAczU/UxTQcA59qTpDA1A4iMCKbqDNA5OEcih8nNw8hFjExEUDFRUltyFIBZioOPyU2Z2VEUjMhIiaAqAEc8HULgLl+jJc7YcccBs4TE0JqpLdM8RacQSSF3LZg1TRNRjwm0MYiJWevB18vNRIddLanLphRFztYXS1ttZGcItdZdslWzrGZ36rPwXedvs4vt/Yc4qiMxwX9wKtz1c6+x9efytqPt+893vR2axaGleKc+psxswUTA3OZjVAVgYgYWA7TOCw8zFUM1WzST4eYWswOiKObErKwaxxgOcyhBBGox8VLSD8SYDEnoSVUdQdtovsgbSFguRRRrVKPfKBFgRgaCUTBRY0nAm5Twadba7VeflnJE153FWBRt3Kiuhh13O2GW8v0kSr1i40GbPgTA26GMH1f7g5P4d/iWt71ybLsf65KEpNi6MJ63T5ja9awmRESruahMRETZu/RqMckyN87WLPIJzBAOQcqGRIzBzbz20UXJDGox/h1Rb7A6ePUEY+I2N70enmD0UybqZUammGgyCl1IXE0LTljism5VlnhBVSFEaqakoMgSOIAp5Y1avjhNVZb57pcgGylB6z7Rf8EfQVsZzx+3dqxCo9/MEjTcn4k6tmefs8sIrKBw+EcG2BGbKBnI8WI2feHF14nMTGCymDaLudQNYGxGUBAcxUxKalFUiqpKldag0HIDzJxlWZZl/QnGxVeBKfWluggZsbNo0Tw08eOgJe2lEoxVoG2LBlRViIjXKDCAFUpEzKzGRkxMAkrJw5LPKCGKh7p0SQYAd0hmstb8QNEOFm1uRF2eKjPXmjGO6LqNQGakRDHZKR2KamdwVP1FD52E4O+x04dzOtwL+y4p+zEwf9ylI310sfaw5BNuUECJU8J3BIsR30QKg5KLevk0/f7ixUCHlSGYobVWERjgyN/Fl5OpJ43UUcGe7Hb1nerWOpp3k0GMGiBoAKyxgrkxUsBRdFIiqLk2CLMhT8E0ZTiIiTKJIApHBiEwWTBYTFprao4UJqSeoYAJozFVOEYARWMSRcKf4FCViYPGPCKWkLha+y97gWowKFmAmSMDU8yKZuh5rEYvaAIxkhc9EahVqNnhrIvLfSJqS020MvjR7U23arujR5SrHIE4Ai7FlMjLH5OTnsKM4lb+qBSfelSmm8AP92D/9tRJj4iTAkbstG7IuM0jTIigKgK1WPjncO8p79sxp0WX6vfusKm22WlCwgDq5dnP/b3Xvnfu3Z/4KWYfNEiq32EeEv1TDEZGqlBha7lMimd/qZY1GAfVYELCZNGfPSrLki+lCWJakaUKTFOyWiTsiGOpXUsFNUItGZHGDORJfOS21oJX89Qa1uM5IjWKXjQRcQJJW9Vpl4y4faQ1eEStdZcUHJTSliYk1ooIaXQpeg7tntJhJ5CYpSTEsR4ScM00OVV1Tx+RbHpXuoU+LrtTuxXU+36v1peTOi3aCgzFJW9zzQmzgwmCxFViJvRiEMjaxyPtawuMcNT4UF+QZ8RcRccBaDdxAamamhH81ubJYn1b4UStFsQ8R6oGDVlGRGQJJAAmazPYJ2SR0D8idCnB1CwoOzYEx+TAQTR0hzoV+TAisGmXK2VFKRtjmV0SyFZJP5BgOlFlNmpzOHnWY9RMIG3PhGsFdqxgx37j7qcOcvgIQBzey3ZxD205kAJLKCkNFEQrZoNE2M1AxPfOBfD2rWUHO27kPjDaST/Wi660I0BPbLHsTqx9kQ6fHQFlaaGtuwKoqnNONfGXy2RAK0TmGBWBAmgsungAUnz8z/wPF3kIYgoyuDahPZGJ50zUGhViiCjA7ijHslRrwKKZlRybMpEzjTUpvEUtK2JO7EPPWleKqGM6jyG2/am0+WyNCNa62cWXC8QzOOrka/aOzJk4oTZehLvU9EqNqWf2nBQSMc+9GpTNRwofeUaQQwrrTL4o8cSrCXtSDYwMYmQMjnn8DQaDkCPh4F1uEmOeSFXYimPQJGlExUhQsKy7c0izp8rMYCfxCwCNj0bbiVLwyBoyQqRgDINQAgtKmgwiIMSnyLiXm05jHSQjAgmxQbxqIBdrGiiccet6Jom2A4gp3Ah9i52Zz1hhDJ/iJznx+sYKjTC+JBEpeVIkw85CnQVYUDZwLc1zLy7+8fPywZ+kitRbvp6HWQ0iDIdF3UiMJlLz0MBkMeBRVX0qtAdqFU+VRauXFS4x/ESOAGYDlEJiDZ1JWtuokoUzC+02RZVVRJEGQOFVpa2/0y1IdI4hBcPIzBR1hFDWbNXUebh1CDli1Gj71VT9o41HanEGLEXPmWmIWtWupB8zwRLpX4oEnc4fxo7jjCKb0b60LaF3+PBFwCRLaVSPxdYRJ8V1g1rsPOpVyAzRRUN7QxExA/U0P53GgDv4WEkxFxc9shCeIy+BVnGoka2Pb5A0mLhtq5JQpO+tPQ99zvi41tSBWVXVDTLnXG3BkvRoRPTaiy+++Hxj9CcZNQAzcd7BqArNklfRlPLZzETEuWX2zyWtSGQqQe2SbUwRoUttYwxE7mmpIn+s1qW/oUQl1HpOW70gE+aYxYR68XwAoH1bvLNAK3QuyvGI5K8ttpIq8jBJW1HTtz6HAYRYO4cTY9cpZjWicJeSlq+eBVUjdsxwbRbethaKdWisD3NEjtNYzEips6uSWqo0ZxZxFBmcAaJgVlWKFjQnLnMx4gAtF0pJf6ZIg7TWaLmks4f4E1WKPl9MCEnYMMBEuUP3BCW07mpAzJ4elYQ9IFRROI5x3seSxUPbQllSQaoRkQNpO31G3SzKnbVNQQGUDBMRciwm1Kvp4eLugxwZxyQKHRvThv4CyiBus4S2+6TgiGJ7CqbELLUp91NGBgYopjmPfZqSaIqe67BOK0kpAEGICUujr7YZyMh33D1rAPsUVJyQgeswaFwHUMg8N7VEaxmzZrnvWMFOQrJYV4nBmspTRH94awJFySvGtBLFQ28eLnNGSgFmAZqQKIE7L+7uZAMgRZDA3nF0s4/SVFJ+UTyEBI7pDBUNM4MZpuxidn0yJgtC5pfHWInYTNrzoUbMJhFtsHOOHGJK424v03yZLYgKiIg9waK1reV4Wtmmg+xlmqQeJ8qOLOaitBiUl054q3degoK1WpeoAlTRzOdVE0ePYXP31qR45PTOZO7GQ2UIqBALAhcTc8Rz4iJvxxQVAdxiULNoZlQAjpij/GZLSEpUaLkjSV4xMw+2VBw26fXUgimJaLCI4DuCEnFWNEAYtcmdDa7Fua1HqfWq8A68y9yS6qmqBOo+dV2bSZZ5SGCDBa3VarUyBJEGUBzJQg2zpduEWdQDIhFcmKiJQBUasbq2qAuk1Oab6tTIq+kMIqvUlss1iGoQExUR7ZkYACAjZARn0esmpQkK0EAInY6OoCm/71J+Slc46Y1Fop3aurw9aaUkNKpxAQJSkbC2KYH9qsVohW/pLq0u4BHVBBL6Eecoyxyg1rKAcVRreT3n7RHbr/365wrvHCOoE3OmHJXhMIZxcmvqO0G3TZJKNRZws66mTJ+U9YcUF8eMxNQIYho/QUUFItrfyg46icgRdUUN2im49pP6NDi/AZlxQbCyboiIjMrgQC5oTTon54MxOZ87HeaZYs7iVUMgkGQEtoYAD4rlsSXWZyYSQgYlayNFzLQVrqLuiA1kakJsAGuDqNSOsV6iLRZXT5mqkBqxEkDG0StGgjHnKgEkgJl6gE3JyBge3MTi085586YmbMSIlXwNEDNiISMjJROYQSBRccyUEweA1EKsK67iVOPyscuiT2dKzmJKItF/TgUOBoaRMiQm6ifEl7V7Y2ZsiiiW9eq8WMSXS2IaYtZsjhycslDDxqTshBtQEORCljkjqZtGCQLntZrv75XT67PiA4M5l/VwwAtiyYgCNQynBJgNyDsLplG5GMMs2ow0ZkYkqo44S8g6ropaW/2YlyW7op6JAsy34SsatIEDKVlnUTUSirmRiZKywcyUGgUbkykJUWAnympqgLEnVVhgrn0pLNowae6RZTmMJw0I5p1trA1BXNYqZkVWkChTxCiJaegwWdM0zjlSc7FwoplFZbxxqwU7hqsyM2ITFc8c2bTej5yoSo+VJiJTNYtyCXdKGfRoR4QZB+OoyU/xPFHeOsbTNbHrLddnZkFCXpBqT0XYEoejwljEqc45VaUU382AxqjKVgcCWyrEDKagzo34vq1DnJayD6gZSF3k5JuaAzGcETkVFSImynQ82tk5e3r/ym2XFWYzb3Dk+pH7qtplTugKZbeaQo0WHCM9xHknKSctkeqypIO1XKSRqUX/qBgBghhVTEyBkjcoRxbTFLBYS1zNEkTp0s/GoAoQ+aFf+DLAJPgcjjxUzNS5QkQGRcaoYTx0DqAmCMHgvJiJEWwZpUXEqkZksUQzLbm0ZDyxFkITH5nKMysRiQixMTsLq/UtE/SoEoOJVGPABDobYQs3DPAylsAADjzIYhFdkUCOOTE1Sw3CkmimISMd7CRuRrRBiI5nDgBCCMw9248hevcs2Yklw5xGQq3Sm3vnJwIJ6JCESuhVxzyuxXKhBjUylxMRSajNPIgAZRFn6q1sdHHh1AM3dVEMfFXVPocDmWry32wBVDvv9N5o479mZNCB89ZKMl26QmnNstoVrzFTYxAJlA9xKdqpW5iZnYpEE3unuomrQgCpmYAUkbuNppiobmEYe8/OOTQGUobCFIGFTXNH5AhByQgCNTQNeeNgaAJCK4mrqrTymDoQ4Jg55kHVJQIhkKhEbzRRgTHAZshy5pw0VhsXi+mjqLVUx7OJNt1UW4BXDWymzpPPOdQaGumqDxKRzw0sER6dI9Poh5MEr8RLWSdypnBYaxOn+MyRS47CAACJTGQe4VST2Sk+7lwWz4nPMrCqwNTDKcWSFxSN0aaq7BzSeePWFrrEka27wqqCycw0CBlDTAHO4LIMbGbqMq5rbRomrwDmuzfOn9XGF08+uD558+Ag7P3u7375vY+fft+7zqrEJDAUaQgzRydhM6uREE3SOoGDamYoPFX1ciQGSHJ4SocxJSwBgKjBZQUbkcEclIm8IwmmZiYCY6booNSiWzMFa6xcS6yR1+eWAQA5ajzMxHtHlnk3WQQxI3LOeYradgIo1nkiFWkYxL6sg0UnCHLxNCyPOHNDEkKTc56JUasB7jJ6dqois1RKIcs8KJiasQ9B/NLIhY6nJgMnw1xnsGIDMRMzgdVnpLI8uxQDrw65jnHCn8tCeUtjo0QNhfNBhQg+y0AEq6N/bNRYdfJfy9oAQLSthKCqTZ7noWnEwOxV1EgIcAT2LBIJBSilyWSB+oySOrRTTZF1pRTSCHsLGzO7MSnYVAPBqxqDhVWIzWpyPJveRdns3Zwc3JoWupPnvLc73b2zIQQlGBlJMhAyswIqoqrKWYKy1m5O7AaFQyoCmIYYeVBpyx4bgFYTJEtGhM2U2ZE1caN7pCmLZ00IkcRHE1VEmVEhoTEzXTLHq2dbc9KY+EbENBclNfWeVYMDZwWZUxKoKjELG5tTYVET5w1GJgLOHDGJAXB+HmpRNmMRrZkBVbHgkBNypsJnRAHwMGdR12FgpzBAnYu+gzG3jhIUITqGscKREWtnACNTNu/hcw+O3gYu974ObcRPZnAE0uRHoC0LbKqmDBdZjpjXgJmZjYjNNI+uYkHYM+ATJU/saaDkIhClWpJgCnVM7InVJz2Do7IRVd/lfvOCVl+4tDgQsdVG5IZZcI5BisyglNwm+LBDkzkjUzNiMiMEInIGJZAKFWAhC5qb8fnNyZf+9YtvXrlx4aH33rn2emEwL9/9zjMf/+TDUSw1ipySViQp7RwShUUiDExMO7kAEYiciDA7YTGXaSAhqCLV+2p1SakReQrErGbQjMgtFiVleV3XZjYXq8pGFSoNMzvn8rzw0KQiIHKOISbJARCsXBRFzjUr+yC8kAa5YxMmHXrPQEZEQgjKxgDDVCyGRC2PtTPNnXdkRj6YtQZtUlVJxnQ2UAODQqXJmYiius6IOOpv2/2IcrACUVFMgDkiJlaCmURXbXCKufGeYYYQpQ0xS5VtzaJbBiHqs3DIL2WlMTMx941Dqur9ki/s2KzDbg/JYdG5GOSgahxCIKKMibwLYsFcBNlIBNod7HpxUfVdCg8dXFScayCwqSQ1nxYJ6CM1jCd6qXzVKDG1ncO0vL17/cVXXj538sJcbrMfZmTOmtu3b5E6wAyVc4VFLlBUY3kgGEKSzrX1UpsFqquwWMisLr33zrl5MBUTMYBVolrGiZbx7TE7iHPOmsDMVVVVDcXNFRLAmVkTADgRNcvi3OWgIaqGw2IwKKSpQmiaOlTCTdOoaq0ycLIzzqSpfSOkbCpN5mVjvJalpRSrjSiG88eiQ6xqLeoGMxeOPGmETNVYLy8BsET9BAiRrSAVc47YA6JNlnFoxPtcRDyzKahNu99CgzkHMoXFgkYeIBDYk/ceRIiaITCUmMmQrOKc8AsbpWRSZom0os0ymfATEyWJJ2o2GEQ+8y3VTd5YMKNkPOfW3E9MDo5BQVVFRNRHO5REraqotrWt2gNNh3gOiwgVITg2GeUcao11171zcdQhUETDlBRArov7joKEGRgkIDWFKsFP9g9OnTjjzG1vn9y4M+CCINisUTdEpPmgiNZNYqeqjZFj14QmA0Wcsmi0qioAIIE5lbyhzIJZY4FaU4uZuciACSgdIQsNERCEEiXJLTMzEkn5DFWVPKmAHClgSpoYpWJSysFiRtYArIKgADKFKrl5aMq9mkno0pe+QhzObo58rKWpQTMjc9pQoxCjAFKOCkgA3MZbkiPkmWeogutAjXTJ96CksBg+E431BrbCcUZUeEcZqUSh2JtJjJxpcYwjAijwiEFOK4UJk0/oOY8GbuLoWQYmIZAqJRs6EcECMNDo+mtExEfLSsMsBdIQAc0Rt9T2z06MbcUpU7LW+MCGqIWQZfILUpiCozCx+tJjG6lnakSZPACH4JwTEUGqXkw9XrB7yLX5j4QQRbwg8/0X/vH3vn5pvRh+6/Lk8sH62vooaOBs5DL+63/9rzehilk9IlSJpczvQboMEdYNKS5IZ4+UlHVCzCQuuymI3NJKEp8zTlEYqM2A1rGmu00FimReAUCSDA3KkGCqkJSGxDKTaOJXVQ8H7+FCrSYAuHBKyiAFByUxCcxG3nUhJu0WCyiIMsFMRMjMdY5lbCkjLhkbqRFMUJs6RyGIZ0dg7gyGcGpQNec6JGExV6QxOWMQt46pUeaLsYIcGUKDEbd11Ci56lF0q0o6nT78KSLFJDh2REBk2O1Qco52xVu3lSg9gGEWRNqDl5Kna6tWE+sE2/S/0groxxZaOGNVVAY1R4kjsqYxgNWllJncSdk9HbFnSiobpIRKLl88+r5zmJbjIh9efOJ7by2GjZTWDNZP/uSf+nenZRUNDXGFRCUSGFUDeQPUtPXKi9KKqAY2j/TqAlADS0onx4AZmpQ+rD3eolV0FGLLox0oig6UiKuZGRmTqossImoRMZKq7YGjKY9pqFqbqKFW8sPcjR0dBNEIVYJhppkvJKCx6FkBaMziFOGp04xwGVoIMEIv+Vnrpyyx8Lm1mqMAIvYuqopMsyEDmQXzBWkT461EyVzGCGymxCZwTgymmjErOzMolDxFtUl02CNKwTSGmAY16euOtvbEsyK56KW0W0v9KHVf2iLvRBx10oBx0t6ZWa3gYEpwUQRD650Jjt6CzrWauP4QmBPMacwdqPBkpqFbNwAc0FoOkJjolNzBAFTS2ieTLw6znMWJD554NJfpbFyxyto+V1qbNFsqPQV4yw3bUgMjccodLjREPUnW1TM2VGiV2a1TvZkkL2u0uieYNzNYpHJmMIlA70CQVI+2bqK2TqRRQCiGpMKSmzQRDCYLY4nsEpk30bmEqAgEQIRF5YKSBBgjRpcaLS069/U9b9c33tmp+axViAKqGgwx14+J1fXCu9yBolERBHKePGtrxmGRZMRoCIcCo5NMFhd+6Wp+ZJSHqG27DR2+JEt5FpYUrpW1ew91fkDGiYNiYnWZR4CqscuELZgzDVGGCkFVQtS1xfRDaIN3afn2NuSXD70OPUen5aE37g+7lQdMRIigodpq2NE6suHaBja2i8l837ge5L4n6vVZhSW5eFtupHOOWWlm7+RpAGBu+QGi0FJ8MxKDKtRILBYPiZlUzNrTa6ZeQx1iPaRleTgfamNmldBBpSRHaUrOf2/jfy7pa3QAjRWRKCXFdM6bmDaNcyTBsiwqxkDOMTmLubVaTpeSutCIWFeKkABL20viFtCh7+56PzuJdX4J0S9Fo0cZukesE9MMoUM8yURKiKoYuKYR7zMxp0ZVXZdV2ahJTIZNZNHUSa63e73QP+ogpruh5y3aC1BZGkG68SelemfISV/Y9JXnX7j10pXTpx/en0wCTrtitCjnszt3uqf6J/MoVPWx7ArX2wfD+0Dq0etdExGiWMwjajaip0oM4YkMm0XjYNwjNVJiA0TUQ03IETS6fRO1mdQ0sMaEmnGBUxx8xLSEWO34+EatoNzl42wlEgPQqDjnwKRKRVGwd2qVy/Lod00EcCrTDUDYHNNkNlvf3iJ0iHyVX+zR6KVpoL3h0DgTeW11NGj32DQ5hmqL6aNllfrpKAEwmaGstZ6GoJUaCQTs2vCY2GVSAPRgoj+k7r5uIq5zK6C+qgEUTFt4XfqdLbGqSfuK/OGL5zeF/jf/u//mb/2t/+ytF64MBjuPPPzQ7q39lYl3W3SPrVvFl0uOvBf3Ei+0cHl8V3Hl27UFkYpotPCamYhYslFaTOgjRhz5VYuZJTSYguBrI1gwpPpcZtDkuUyCmICUSKkXNxejkyntVcvxUeteYG2BuejB0p+tGBlxAYuetkzKMeeQh1IDBzafXtWiRscUGNVkNjqx5XR1FdoTGW2KnedUtBspcIiSASA402iDTZ6RYtAElNFrgchHi6CLvopBQNQQHMGXZb0QTZo8IDJbUYNgEFvWHl8C0xHIWIYo3ItJBtCla2T4aHuh1udFtY2JBdQ4Or2aqed1X9wpRhey4dobl37n1NaHzqy7W7M554O6nDjK+njxWJyXlqhz62ljP5JGxABxaJkoIUnBl5oY9BZYu557xnlrdZShcc6JguFqViIy0RhMQDBSGFgRs1Qwq5HBKwht9ps0Um1LzhxaQ7MUtZgUEz02rl3xVult5JgBauNHASKoSXRCBMw5z8wEJWYjI3KU8qhYDIhfHksjNsynsx0itHZG6mjc0pVwFRQ6EG91kARAY2Ig7UNPO2kISAyERswIxmA2sBI3tYk0VTl3zkdWp5UUElzjcF/viC+7d+tj/fvTVpCIMhkPfDO9feWZrz9XVs0z33sRlInp1evXT1546M1L18+d2Y6e7egBaNftSs+2JARYucdoSTSX/bQcpaH/NfFl8XdONlJ2mVeNLsEKuuc5UUsewJ40SV4dOK4A3+qTqsxHFquF0A4mDIHIExu3ujQCOe9UNc/zzBkzEVNMz0YgE0EyLkWP4dUB1HVNyzCBhC+RhIk47CMcR//PZQLiaLg/1H1aXCTqSeCYIq4RUrJFuajjuXBeWvbXzHqZf5basZVhdyT+ENHslu3ewgdas9zRnw6hBqiaIxMr71TlLNNxNhhunnqA80sBdurMuf3p9Npbd0+fOOVcOOYth+H+6PdjIaH9qcVpXT/UEf3lUGPTaA4x62WCRrI32DKy3ig6pILb0jkM8xKVHQZH3RApkhHm5YCAjnlf5aZdktFJKO1HRkSmDDjHzNG9KRo12XnubCKAtsk3GG08HaWs/Z1ThiPD7GBiZm4pcmgHFN2VlSXuRJCW9HQbn6bQan9amzJxVD4TkQJ1FeqgYqZgoix5hLUbA6ScALGHbolWNEpHN/6dXO+N6pibqaO8gBk7tmGYjLl887VbAN/e3TtYQMjf3du9c3d09qHz3/rWM9JUH//4e601WPQHeYSz7FRLfbfJtHqKqHWmDr/GL0nnj5h9ucWLHD26TE2dplAnRVTgAuSihqubXUTG/fGYWW29zCJHV6t/KSKtSOJXjlf0eiQQW0xnzgMX7bNJO9l6UWpSbC85geiv2oUUrjJmZhZ34+rVq+8LsozB7lGa/pdDABrV+GZYOiBF15H40XYWMTG1NQ0vFnNmX8agPzApjL0oHAtMUniopURFuqzz0KGNd0TZO9bjfsWH2umvfF+Vr9VDJjde+dpmIdNdtzfbnZWLp7/7wmReNnMS0HQ6HQzzV1557SMf/gC1SHTlpff/89hRRaqrqtGynK60JLvDox2wSvwVCUxTB2h1/m1KC20PT+eBIEaek4EBFpOFtFk22u+txo5AZJqymTpqnf8YGuCZiA2OAxPl7JPfAThmi04EMYphHHnclISFiWIhaGZv1hqcLZ32KAy74O5OJ5kKWqNiT6zupKA0zq48ALSJmF3MAWAoFEQx/YVmojUgxMR5XdcislASsElXWMJiRSNKYVpsFpF760a49IrXVkS7Z7a6wyenvXho/Evksfyxd0N725IgACBXlm799ObQqCFcEZiz6cNPPnDt2t7VReXVZzUgBwezHOSjvh0AMVvPGNvyNtaqlhEnaN0AiDXK4W2eJYCMLOqEqZ0dJ2/dhKiX47QUhYHo/ZmgMzmUJVSs5gDrjp+SGSmYTH2fdqysaf8KtwCfgnMJBnWpEJ2RqnMuzzKKYbjLai/Rc5MUxtGnP3KaROiRMTK2IESsR06vAay4e3s3Zlvo1m+VN+rAcrmuabHYakt2dYM5A5vRAkUVZFpWlrLNkLS6W7svIuyWpQ9MR64c89R9+uxueCc9HLrHfE4CcmObn9neunnr9S2zUbFVN4VgghzDjZFcys3MMeSQosru9a7jXtTdTP3bYruXvqol2i083ntq2oFpixCNo0+JAvBd1POxDD6SZpTNJAZcOJfF4GaGEbnIzjnP0fLlE9ZpTdvdzlGbWV0lahX40KYmCgaVpaqofTuAcr6AplTZ8fKRCR9aO7SmiJZRZCNqVIOyGpVlVakYkcC3CWGtlw3vmLXuRnLs1h67+m8LlIdGf3gL7gOv/cVRc9n85nT3xmBr+9pedXeOD7/vPSr00iuXdy6cffPy7VmF7zz7QtXUt27dOnV2M0ZQHe25m+CxU6M23UhPYrflmnSDiSJOixrB1KbtuN9JsNZF2WxZ/ziBfiLRvQfus6aO4Yg9u8xxnrm27JwyJZwYTTK09M221Z7boN8oj6uIaYvmFVBKYbsB1hgJxQ80pmdiGKfvSil2OVWOSKq7Fnw6LhNipEaKorJs2vCdabg7DXemzULzABJlmE/MR+zfOPorrWzDO1mfH63ZfdvbPi6EK89/9eCt5yYH0ys3dr/xzPcfeOD89194fufUzuUrV65cv/GD194sIXcX+//sVz8jslyc+4zkXj+9/VzaTLP36vBtO+keiZbPmBHgkH/usdql2JxzzhFxjGOMlUPIOfaOy6YhMuKIhCJPkjCoxlgHglEMegVizLVCZFl0wixFT5MldN5Zg0yNUrDTqtcFjsP6HVlROIAWi2peqRgHzgWDqGAn8qwLqDKxQRDZ+7b60L0NZIdW6V7L1W1Dfz/6PEAfUb2TPcMR3Na9moge2PFPPPjQN77zyusvPPfh9z7Kw3xj/cTpc/XaueGZndObW9uPfOCx6zfevHP1YDKZjEaj+2xxH57sOBT7DlsK2jDjwyTe7LjQXqSQUcOy9F4aDIwAr4CDMUgowRdgMbsuMbMpkzqm3CWtUwMyqJEb+hg/oY48p5BOlmTWccl2b4ZWtSPcDYgsBAAmyQxuSfmK6MkLQKSlIGwsNhwM1ETaZDtGYDjWCFwa8+uKiCqAvFaa1bqoK1EWZIh5RePimERfGhDIwRAiygSQ8uQcMaJGAeDQBuihXeytesf/tvJPpxhuGZZ4V8unEA4zrysd9cFFaXmFAVWos0138NDP/MTnf+0b7/nQQ3/l3Y9ubK4PTpz7R99sPvmx8yfPnN6dlvObN8898uDd82ffOnXj7/6TL/ylP/fz504OJfp0xs6j7iwZDGOoY7I+cCvZBEpJa/tHl9pSY4HaeF3lVKKOYvByKq1nRG0sE7XRSLEUh1NVWCrHACCwRQtzShJoIA0egIKI2UUbcjyZBgciRnRiZrJUEoWimz0ABI2BLkgnBABSqpzoi0RE1kuy0WHQ3o4mTVhUT3V39rGUikBpfWMjhEDIu9Bss9qgor61wJLQcFqFRVmJQciZcXSPPYwzOhF6FThWWCU7Rhj64ZrZ/cWtQz23sH7vG3rXCVLToJDZTn7l2W/iyt3RC689v3f92p//qfdePPvk2fP5F/7lbxYS7pb1du6zLDtx4fy//MY/d+S/9eW1n/35nynW4UlxhNCv0OTuj6WY32NCCccjxYT42uQJkYOj/hx7py7ROkpOW3akCcgPHAnIAE/w3sVcU0lQUWFi74iTSb0TxwiAqBkhphLTmKR1GXLUreohapj+XWqvNFYFEEtJ93uBDS3rDSLQaH1DDW6pEmeQa0wNeQhUNUHqeh5qpQFcIaYwNlLoqurnOPJ6rE/xPdtReD2Oa0tvu89Txz4orTEvnututNR6msZ1mwV/gu+cbm586+tXb8P92uc+M/TFCQ3fsmf4PZ948Xsvv/ri99YHfuoGe+X+i9977j/9m//rP/NLf+LX/8U/uXrl9c/86t5P/eInL5zecQ6dxf+YSS0zFVpnGjgEO0mtt1RdLwH6MKRHWcda18HOpt29U2NFeqALhu76EWIeeR04zdg8I3Pk24w8RLGOKDhyaoFNs5SbsjegbgUBgAQkMZtK/Hgjb5STy2mZ4I96LV7h9nPMLrJT1YODAzheHizT2rJSit1JuHVQ7dduZk5cpkAQA5igCqfGK4vV24n0zqQ9OOwfeZ929J6jW3vsU++83aeH+H3TLc4Nyi/8/peb4clvP/vdNVucHeDRcX3y7Nk33rz+za99bT1HriEz2xj49Vy/8Lu/s1YMt7d3rl97uS53n/7ytzQMzFznDHX8e7vyGscJOikk47jBogukbZu0KZ/usYZJVO6/Iv7rDBwLnCmEyEQaIvMwD8sIBcObkWhM4RWCSGgVjSpmZOAAgknOyCkQAqxhkgziSZjMWKJvBpiYED9OwWIsyYs3hj0FUGMwE4UIxRmJmAZXZ00zPHFhUAuJBhssZP32vLixr7emMg0k5FXVgrcQxSxAzZQ4JitIwEfaVnDVmFThuIXtf4BY6QqGWBFw+UkcfffptiGamwjCrc8eQQnxYveR7tNejw8KrDs2Es86SImVOEbjkRqpC+Iecte/8Jlf54s/893vf/vOyy88MOCLmJ4fuAff/fDMisndtxDqNdBYRANoMH/5xWdPb576d/7yX6yl2r179crll/8/f/cf7e8hCLGx6iC4Rs3FjxHHzxJqleInorr4byzxkZKrKZmSAEqkMeVPOvytRUBAStT2E59aIssuaVsXB0tsxAoSBYul/Aj9s2NGqlHng8asuceZTne3iNATe2I+gi+sjdVKG0kaPy5GTJp0A1/2rrmaNzhuOHh/PhvOPabid6fl3f39ui7j6e8PJr0I1j/ZOEzC7DAqOnqafyhU96O1o68+9qcjjRv2oZ6cH5T/3T/6lcGJC5cuXfrW018/sTE8ubkxyD1I3/Phn7i7OyGjohgE6LDIM+c3BjtFxt/4ylecy3yelfOFzKu1IX/3O98mHjVioMbpMTawo+t2dLRvO8H7r8N9Hk9zZuagFoPNg2kwFSSEHFRr0Vo0GIItEcDRgXb0euWV/Y0XEW21W6KqbYkHi3gYGj9LlWTqQVHZggfXv/H0bkZX9suZQIiNTCBiYfmC6MZ3TxXKD9GOAu7RhbvPmr7D/o/d8qN3Lr/DK/HWoLn8tX9+Ym2HNx968fnvXdheH2s1DE3hADW4fH3zZJHlGWXFqPDOHGicbw69Pvv0l6tF/Zf/6l9lBzTVpZeeee3lF5555iXyY0PJobj/OuA4eDoKiEcfudcNwJKArNCiQ/2IckMmqe6sAzmNkSIgMZg6U6fCMC+K+Gk1vXy0O0arQj9uAhFpK0iMFS4oNca1UkMuwDXGQj5qQs2oloM6lHWQWvjgRjOZXf+v//f/l5wKbQIzi3ETEIRUUkUpaV/UKXiPrsj929GlXLmhY5rtSDu6PSu/dt+jVuE49e09dzo2Vhk1d7Nbr9x54XvFiUe++q3vYe/ats2ePD3e9DbOeVQM1PuNzROZSlMuSMVr45wjSJH7gbNnv/CdixceFrK1gjeG7ualH7z4/ee++pWnCYN+xED3xmPHubJQK9a1FRHn6LMdIrOojmoV++0r0b8CgAAf1Bhsy9h8ELUq8fhvdLNPfkmkyzvbhNxmIurYltr1lIYvBSElWb4dHLuBqBJ5JTJCzAkVY2FzMgDsWHXoae36jdl/9f/+P09eLI2ezRcn/4sX//Of+tmf+aVf/mXKx46JQJ7UORdCiG5xkbJ3C3d0gY7+1Acv/KG1Y9++sq/xWv/+Qzdr/eCo/o2////98JMfvbR57ttf+/XHt/yF9ZFN9zznJqGsq8C8qOaEMB6NM7NgUsMtZJdsbTwe7129tb+7+5f/g//+7/7KvzCjzTFdee3FzfWNxdRl48rB9V99+NTdE4mu3Lki7B+9c+U8py+tmimKbH1UCoMPqg7kiE1JVYis8S46tTtjxPhFI2qEHAmQZUHVB2OLKe4AL6zEwTmOqbKJTJqYyE7hmoB54xa1LAKZkYiai78u9SaAkjns3rl9/fVbN26cPrn1rae/f/v2becaXty+eHG4Vrz3w0+9/9svvHLwxrf+9t9+fSJ+Z+fk448/8ckPPnb3YHLhwbPGA7QO7kCM9O6UPYe8hNrvS00YWtg59OeRxV0F+mX/3DqJpRimeKegrwc9pLG3VlXXquG6Ly1cJiaHlGqnzpFdXLv1W7/yDx7bzi6f/+Tnf+0fnD11SqgerrtXrrunTvovvXT7I4+dDJTdvHqNjF+4vff4qdFmNv7mD17/yKMXFs3iWskDeuPlZ19+/EPve626/oA/uz+r74Q7u9ff/P0vfv7Tv/gnnGsMM1i29HNIivqlIil+ixINC6JKUdt1ixKitUpxi+kRksgZ1abaCaCAkUmsGGAW02OlM6CqDBcVmsTqOYwQzeAZszlAsxDV7CxUo9VEMoE4I+aF5FVtoghV7r0PIcyj5541LvrTMRM0pvUJIRD7WoXz3EulCiIHYmmLK8SlICKH5swOcvHXL4cv/pvPvPeJR3k+XV/LZgf21FOPT/YPmmrvepWNs5MH5eT23f3c8Xee/saXfvvX//P/1d+8dPnaxQcfOQwKvVoih6AKK1ePQt7Ro3/U0hh7SATuiIbfjvTzo+n8zcwbasoHYXegB81b++VP/Km9/ddu37ixtrZ2hgWUz/YPmpNnTqyvCXQyLS9dfdMztkZjKZtaqwcevMDMRe6LRgvoF/7V5z7xcz/9S7/07z392X9lyjvj4RuXXj517uy3vvb0Jz75FA7rjI9yHf1fNZ2sPkFfnaMtW7qeOE4zg5EJIYa0GwBT7Ww1XSdq5E1DVDSRRJcPF1I0txMboEUJVVPXM5otSpAz8iBHlMlcmGNZJSIiYTYzB0dki0ZZ2CMjI3UxTZFDVPi3FckPzdnq2d2XiuHwTpl/5JM/+bEnT23/8qfu3L42n82qptw4sX76zIM3Tm/efmPv/Nblj37w5CMPPzadzmezxfe+/+KZCztHuaKVze6gsAOvY9f9WI+eY+982+v3acdQ8FVQSLNwRuaxSdPf/9XPXjw5uDY898xXfmuUsUxuvuvBM9cP9t71wAOzavG+Ry9Wze7+bHb95rXMu4FlA2IHUtWDg/nm2hBNVeS2NXA/eP6F9zz54S9/7ndOro0rU+ft6a9+cW3nwruffHRzawQKR+0LS9+DI7M4lhNYPrt0G7qfa3br/GtiVFZN9NBIBn2wF6tEHHyRCWrBwbz0w/WqaqqqbFIqM2JmI2fkiAZAYO/giK0hR0rqW+9dUiIiiIDUM8MkFvdwYgCUmYhBLBCkfH+JGrJpANbHo9qKMDo5PEsbJ3KANk+eOH3+wXm1J+YnB3bprZtnt08WOw8N4KbT+WAwctlwXs7m5exokpll7oN+qti+WBxvOwY4jqzgPfQ+/d3p+ryXNqN/5V6n6CjgNq7Im+tf+JX/6tFsMProT750861bl3Yf37BHLz6wky/2Sz0zdq/fnG+SbF3cub0/37t546z3MFLyoQkD5vFow8l8a5AVzmWiX/iNz/xHf+NvjobrTRnEdFBkaxkGA/fyS298/BMfMZr2mZBOoOm76cTJxNs6mt2fztH5dn9K24+aGWUCalQbJREpy7KqdT6fq2oQ61I4+WCDMrj93aaqmwAXKOdFTURmWQz+pZTahsUaUJObCyFEJqQD9lQrAUStPORighdTgDxlANhibkFjlwjrEu3BDPl0Fm6+9vLVSyXNpqfnw63NkxpqhW/CwXA4Wsy8LGy3mpZVAOd5Prlz5+7Gxnpt1Z9878+sYNB7tw6OjwkeOra9PTI+DKDoEf1jB3MMO3vvtlB67+nRzVxG/sbe6IMvfe0fbq7r2GTLNFBzanvDzWej4YBC6ZyrRcvpzApXh+Ay74nGRa5VcIzCMeeFLRZWl1ZVf+HP/+Xf/Cf/LM+dg0Gmt25eyV47ffGB82fOjZf6mRbO3pZE9NHk0Uf6BIGIYoIxVd1f1JPZoqyapt2LJliMXFBmhYqJI/PPXl547wlsPkfk3SLX2duGmCg5WkCFlIkhxsykxu7QUJK1Xc1MiAhwRKQpdUz8MaYNIVF0AaIKDl63T2zKwdrmSMZWjavB3uXL453N3GfzvWb32qvnH/rY7pvP+a21sxcfuHPjxsnNfO3E+mTWTCc3F5ODtc3TqffuHLejYqWujpYuHXLS7OTI4DstLLsUhN4htsjApBDvzsG5LW3WqbY65C1LSWh5HhxSEIkedcW3NsiAhI0NOE2XfvXv/L33B3f5/J89eOUHB3s3Lo6bC9uj9fXmxh1rFrcGRf7AzmZ1gIceevcXr96Eq7UaFOOCF03pG2/EuTkMvTahbm7XzTrVr33n2fyB9auLa4/ZhUA1DdZ9Wb750ncuXTh/8eKnmjARmTtXWBt2FfPMclfhEDH6OBWdE4TojpuURIj8KUeWoFETtTI0RNQ0zZ2DRV3XAEII5jJVEyOL6ZyAVGI+mvvI2JEYWNhXyg25qFOMaRrFKLQqz6j1DKrR4bizyyWznpkYxY+C47OtpWtp2jLt/IgPmRnbjTQWQHIP0mb+rscezwYbWbG+Nt45mNv1G5OtE+efe+7Vk+fPUpHN64q9D6aD8eiRhy6cP39ykOe4R4uc7srrcIh/X2I7O9z0cKToCtb/sbRjRwXATEQHzsrzWye3yX/7+rxZO/HNp58+UbgH1kfzvT3nR7XyxUcvnjizzZmoozMPXgzayKzkzJdVlQ+pcI6UprPFvKzZ0Vrh1oY5cfjs7/zahdMXf/bnfn6hcwCZ80WeeTS7t29+/t98gcg7l/UWh1LlIhwy8LKKM3WmhJyQh4ZVnONBU8Pg6kaJs2kls1qv3T7YnZTXb+/f2Z+H6GZp5r1fKZvUb9w2IvJCTOQM7BGIYtbCtBlBk09xh0IiKo2V1NQQlQx942a8WWC8dPFMTE3GMUlTW0sZ0VuPgKhUoJt3F3/v7/939tCnv3fpdnF27V9//qs/9amfvnPjyv6d/TMPnf7OM8++NXp8czS4eneSmdzev1NXtrE2yobSiNhR0hmTXArAJLB0OnvjbFOSHMMyrlxfSuVm1EvU2N6ffE26oO8lVj4c+9Z2mB4/ymR0bmnGIOMC9f/t//C3t8pb4yc+Otjcunvr2pObWM/WihOnrt6ZzAPf3g1VudDQeIZfG2/tDE+sb85mM82dDXg4yOua3rizt3HmXFPX68MBBc0zWsuyyd29pz700e995WueRuV8qgpH+v3vfvO9T30C5utKsyxL1huwZ4QQDA7OqapzrmmaRc11XTOzNgsmP5+XwbQoirIsm6YCUBTFtGzqRhSkdVvEFhKzP3SEzrmUXdBaF74ol8S1YsCTCQFkUO6YyPSFQe3qE9jENNZIXbpgxCnESI8YBRoPRIruXUIDgKCdh27ro6mtUyapELud8z//S7/0K1+7dOXajeoaPvUnPvXsM9/lHE88/vDn/vVvvu8nPvna9xfTA7l5d5Z7FANPyF++9Lry5L/3V/9jaYns8rAss0j0zs8RmLhXs6TLA1Jun/Qwtx3SEnw72t4+3NZ/75VOXHbRwaUeGY5bxv4N4Sa5VKHan4XhQ+/7iVefefrcuh9keOXG3nCUO0dNg7vX9wqfEdgWUxtsNjIJIRSZ397ayhx8U4mFzROnggKMg+kc8N7cgPWtN1598KkPBOd8xgSXCSiwIbDVX/ny1z/2ifebRRkWKjoPIQjtTadlWZtZURR1XUvyqySHOvOFMRG4rCsjKGcA9mdlJPSirU80oMvYz5Sm5Ngg/eWCEPvILNqhHW1XiRLkpRDJdvk7+Iz4PqHVvpdxW8HKOh10TzwxarNxL/MAsRHuTBc/+/EPvrLIL5z/6M88nEkTPvDE2Sll9XT+0GMbd26Zc/V4OD7rx3DqM/JueO7hByfza+ZyaKIdfZV8O50fJ1H+g7QON69cWbkIwNTBlf/8n/1TCWVDOyfOnfuV//L//sEnHvAadH1YQ6rFZJQNUfC0mmWOIcbj9TxvIolsymowHmWci2vyIvcgP3BWVSNeHwgWtf7e7/3r/9nHfpJcISJ1Wa6NN3LOZ7P9F55/9v1r2yLmHBQoy3o2mzW1qXFNDpQzk/ODnHKWWeSDAnETKgkpqLJpmiAEQBSEAEvh/y15OQZFUC/ybqWpqhdzEbQI7CwlpEsIgpOzKrUFt1URo3oOf5JGAC7ScGJlgzGnMm8tiLhW1dPmZDMXlRmBxIQx3tydv7mY6NXbMj+JoIvf/O1X//yfe18+5OH44fF4//GrJ0fjPM83SUoTmOqsWeycHlDk19v5pj1eVkc4lH7xCNAccUNdrmGX+XflEQMgrW1wWTSufbCjX3wkQQiAVnwEtY7dFo1uqSw9s3rKy6svv9rs7xaBT7//Pd//6rdObQ8mk8nOaMD1lDgTy7yJqlsfrk32dh/cFqOF1bk1oRitZ45dKBvnykVVZE40DIIFMi335uQ8hVyR2fA//J//R7/+3/z9NU91My+yfCcvduvJwfXXn/n25qPvfmhaxwLOmbBRckRXM5tXkzhbVbMYmSguBAFDgzBc5OXJ2sy7BgUj8lSHvUs1FvPpxGfi5H5qMLDBiMV3jHkSYQ9XxejjRaSD3jn5LpEVEAvW0H1MJsuLxK1VspNeyYhMkef5yPE6qMjdyK+XZTaZzHfWNwfsZ2qXX3r5wtntjW3dGA/u3L1Npl51eG6t6YoWduT4Hu2oK+BxQAscR266qSU5pvd8sm0eYV7R4kXtvYnsPrarSFi0Kavvf+PrmE+Ii/Pvefdv/Ppvn8gLgpqJB01n9XhYoCo9yYB0POCL2xmxTWcLNnUWMlhVSZZleZ4H5sI5QxNrmMQCQJk21cHkxv7dkuYn19dEtDbyOdWGN1976ewjT85qagwmVjgfYkltS9Fw7SyQYnJhROyci+5GJhpTgxPDiDTaDI8o/4/y/RYBc2VZYr2wpIKJtTN6EZ8rUu3SokDU3y0iFz8wMoW28W6qbVHGXjhqTzw8LNZY3GO3s75eEFFWi86feN97gmW3btz+0u99cXowef+737W9uXb37t2XLl9pMi52NoaZH+UZmAgxQ6cz8NKp9shHj/ng2E9X9Ld/pX/xmPU9HHfbn+xySVO5qsSVtvvCfXWHSDPdvbNugetK8jHlo1tXLg+Mm3LBjjKmfOSFw3jdb2W6U9C5reFa4WBYX18nIu8IGnLvmqpkmDahqioJqgpmHxoFaDzwv/+vP3d661ypYX9yIE2oqopUPZnn8uZbl669dU2NQK4JqkYS8yArNLpNG4kC5Ih9FLedc2TQIG14HBGlGmzWBup01Lg77f0Df3Q9AcCW/keJC+0cvI8WXl1dzcOWg4TXe4okAL0rPbwSnewPbXIkhXTnbqnsb00nly7vvvrGtS88/exoe6cWvPba63cPJpPJwaKum9F2yDZuz8KtabVrXIeYNfpQOzyq49sxy7E6nePvv387blneeSMzY8bzT39xcf3yyOcnn3yPr/nMeD0nrK+tTSYTFSma6YZM1sP+Rl7ND24UGc3mJfxgMMxL5emi8d7XdZ1qPqmQYV7VSJmOyczmoX7m6a9trq1/5BOf9uNtydeFc2V2LtvZGF167lt3Ll9yxo5caCfSSTOdAig2bZuJRmhtkyyFEGRlescu1FEY6zcGO7CLzppRQE+yuEYG12mq05HyGnSYoItP0JQQLKqjNRWbJcRIj/jFCBGxaatYjdl0ovuoACCr4S6cOzWxYuvhU0VN6xtDLct/8LkvDsfhw5/4SZL8269cfunWnvfleDw8d+r0uNi5uj979s3XOBsoc/yQpc8ys0Mv30N0yYvj6SaSvrDGTx/bdTf0P+1FipEJMV4loHcUW8/X7qcu0wTUuouNQYglMTwMsBIpY2eYH7x1rWgmXLhFsfHNr30JvJiUB5PF9AGHR7b0Aw899OEHTzy4c3p7ffTg2iO1m+3NhpUuJMzj8GYLnuRjBqSWgcwPKN8svNfgc0xGa1kO70Zntl055/d88EN7+9M5CtMw4SIvRlScK3I/27955+Z+SFQ9xRil+pFxIqRqQbQhY5VUyDNAGxNYJuqCugQzbTBMSOQHzG1dIYMzKDjq0Xv4ioii/UP4PjC+AuZvi1R6vsyrTs1ve1DibcPBOll9cmerKRo/OPE3/sb/dPPUhdszXds5731+4eypExvrIvKDV35w8+b1u/t3z506dfbkycVica+xmVlcpm6xjg4jfe/CZY6M8F5jTpjjHu3orN++kRH0ztXL5f7dta0tWts6e/LE97/73bXCPXD2fEFy/tT2mRMbv/G1r9wUZ1w1bvMzNy/5g8F4OAJld+/ePbM28tb4zK7duFmr5aNRNiiuXL1spAqX++LGW9elhkfDUl1/85VXXnml0mo62XXE8/1dacJ8dke0fuvya7u3rmp9KCHeygRbOk4GqpsgghAsBGuaJtZkWlmHYy37/dZLK5kepMO1LFaXdXWn79u6m49u6rE3H72BmV979RLX87vXr1tx+u4+a/Pq733hy5pt8mCnKnU99+9/12M3b9yYL2aOcenyGx527sQp158F3fdz3wn+sIB1r/tXMG7MOd59+i9KG9beBsBr+Md/57+d7918+dXX37y198mPfHgIy0M9IMVsf3PA5WL6sY99fDYruakPZgen14ahrkMItejNa9eHpltrQ2LdXN9S5jt7+2Jh68TOvCpdNqjL8tT2DikX3q8Nsme+/pVHHnrUD7MiR8buxPo6qZEuBjlnFF76/rc31sb3dEQylmCh0RBCMq8LEiKIi9Ar89XxA3HK8aejXR5lTBXsuy66fom7NGg99Nnron2kLWYc/eSZsVTssypiLcz+dnZvaUXdpeBlgKpWtdUHd7KNjUtTV84m507sP/7A2Wwwvn631Bphuq/z2bsee9fDhryq7m7Mm3J2++ruIx9Mrox2SBDsIK/PlR9/3szsPn4k/SXqPXhPlUX/jvRrjwU/vrgXAEBEbDF91/lT+5hnGHz8z/65Z77x1fWcNzIZhun7HjrdzPd5Lb/6vRc+9NAZCTrM+edOnbhT7nly+weza9euNVVJSur8MBsxwtpwEOqpNMFFpZTTZjEbbAxnYe60uXXt8ni0vba1g8ki89msnG2ubcriQLMsa2j7xPiNV14+efGBFVemNoQhKdxjFBCx5847WR0h6eeTrHzc7i+P6BGERUTEFDMvHEPi3yEiudeDZtY0Td+0ffSRe3XIlHtrzp7cmVRXHn7ozP4be//pf/LXXnvp5f1Zkw0268k+hWpjbX2tyGlRzvf2xt7Xk1n/5B2HvQ6Feh47+PsM9T7TvNcNK4K/mIlpH4uvtG54zLh74+r+9csb42J9fT13+q9++3OZyYlxcTqTs2Ofe3f5+p2LF3dcuLk7HM725lfLgzJQVVW7e9NBUWieOZ8z/AACWQw9Rt6v5YPN4VjJPMLGONdQgXwQEzGt3b/z5/9SOa/uTPazgbu1v5uB55NK6+bG5VcLl2mblLhb5KZpJJby1lhPwnmfM3siBSQmXyCi6LEOoJOourVd0QLdCzziyqxUN7SApOQLKS9I+iwVLhqlACK4KDbBOIZIkzIps7l6etBoo20y4nbbluFsaSCtMEEGjfyylE1e296d82ffvx7KEyc39eYz5Z4p73qeTEfroV4MDHvXb5XV/lPvfkQVocg8Ulw0EbXB99wpvxKrdPiNXfR3dyUOT0yP3tDJkYefaoVFpv7HCN1NpOl7ykceGbZWeoMaIzJxSqhJiUP4+u/+Tp47glDA6OKDt268Kcgf2MybgFDp1ISDbuYF55t5WXtq1ocDpYBBVVYuTHfnFcogQaVhNR5aljXsN1yYKhUU5pJlaNTZ0DnO1oY0lVDenEyEOPfkKht6zkgH4yxz7LV8/flnnYYYtw5L3kKW3C+SyBvFYIIyOEqORppSArQL4cg8w5GxI2aohgSFTNrzkYim0y4hJhExY1mJDD08hBYP9z1F+l/6qurlIej007aR5aqhWXm2u7+vUkWH54ETp9ZURnk2fOXF1y9+hKsmoBzlLF/4/O/9+z/9vu+/8sbizvWqeP5Tn/jUnSt3m0V47oUXh5u0aNRlq2M4VgNvdh8l+T2v3OuGe955+LKZEUt3OyWqBTOEJhAR2DE7gyM022sDd0cI+uC7nmJ168PB0Nv62gDA3nR3kI83N8fSlLXMsmKcbay5zOWeN7Y2X37l1cVikTOsqYejUSBisVBWEDERKevKAjxnzlk9W2ijzIPBYP/6rYXO10a5M4Lo+vpYy5CzelYvWTWb7N++u376hBxJfbPMwNxrzCwifUDqs45AmwYnUfWOuHfgQe2dFnlV4zb9YlyxBEmHjcUryLm9GYdNTgnEYzqxy5fubNrBqROPcC+9IzpIpfbRji0DAIjI3vT23d368rWbZ04c+NFHubmzUfhf+sXH7ZsbZ865D370J7ek2cXdYUaABZX3fvjD88VNyvLjTsIxZ4N6TkzHThA9sHtbUL7nT4ePLhGZCcDRhDFZ1ADquu6cxmGZc2QID+3g7puvPbqeS6h2yV35/a9s5m6d5uuj7Tt7k3Pnd8y523emO5tDp14UlOXT6TQj2zmxOTl1+ubNr+7kzgXVck5ZUficzBErQx3xeG08LZvxcFDJomqCmWtC+OJnP/fv/id/7RvVv2TNdgaD6WTfY1g4BJK6KoPfzyDMzgxN0yiWCCuCqffeVFNeXJXupz7buiISEVGWZU0jkdG0tnp0AqpE6xRqlED0R21HEUnHW5w5u5XnQ5i/58PHNSJqxG2d3Frf2Dx5YvP/9Q9/7+/+s88551585Xtrm+e3T51+9KELH/vw+y6efvDujet7t65uruenNjff8+ij0lQrIzk6yKNj7tgdO9z6Nx97/diRr0Dzyq+RGygXOjmoZ/NqNq+aYEFgcAYHcAgq0jz9+58/Oc7zjMfra+MHL/7gu9/OVS/sjLWZ7uxsEZEqVDAcFo0hWNib7BW5P7m12TRVLPjeNE3miyzLmFFVC59nQcVl3mVeF9OCbDZbBOPxcOiIsizbu/NWCJaN1somjMfj3LFASKWczjLS2cHtV158QWFBhRxHv+/+aizP2OFFtpiqIzGpq+c8QnbfVbetA8Md+oiMr/f+nqrKH6rFHjqF+Btvfn9r8zTheD/ifpKS/qBDCGfOPLwo9za2t77z9ekbt69osfEvP/Orjzz+gM+3706ql77/vb3brxcYoq6n+7evX31pnbB/7Vpe/Hhm8bZzXIHX7ruIpFLpvRZCqOu6ruvpdBoam02bciFVaQov5sRc74uIqXG49OLzThojNAYp8snd6+uD4tEHzs0me3Vd53nRNAL4u/sHQjwcrQ2HRZa5G9ev+sJfv3Grqio1Vwcz8nnhsyKflHPKvBBmdVmgLhwWZQU3cM5tbW1ANcvE5aM//Wf/PRjv7+8XeeY9eeYiGzgg9wQJ5aKGsUoyRPXXpK/v7DBl/LMzMvXzjq9AdncnpTTzFoGSiJxzScaKsmUUcVfUzv28VgkEU83alKF+xSpt6r3VBH/rzecXVrNa3Ib4EWKJhpY2fdThQTN8FmAnBrw3O7jd2KntjXc/9eE3Z+u8OBhlJGGxA26IynJvUd151/ueWls7sdAQHNWhZ/RfjuY4ReiRX1P6594nmWF7zgNiUZOZkq6LQSwxVXHdkhymMGVYNlvInd353n5zMLHZQb1TuMW8KVPBhtD5ojNiXiohQ82cLw6oXowyKhfNnvC7zz2SjUc23i7cfN5kmrmbd3cX86quJqPcVbMDmIRKVZEXReZPeRuIzYByQZoNsvnUyrKUUBZsozwrslx5WNf1eOBCU3KeLZpgjgbDoc4PQE2eSVPPQxBrgjINBoPx2mZBtJhdv33pVZAGv+SF4ml0zLnzHS4kotGgKDImcswsJsmtmCgGaIjF4lksIiJNhCVVZWMRi2VzzcSscYECNFhAl6CwrxU6iiqORSQrSCX2rkYMtRCOtY8f20k6UgQzk3o2zPLnvvXdfDx84OF3j4Y7H/zQT7Ernvnu02ujnBZlM5kPQRcuPELZcL90i8Vie3vHuYyOOB+97eD7FwXL6yv39P8kwDQ5nphZ1EqkhFNBAa6qZjqZl2UZcYBJZYRbUwmmxhRMjV3XOjzBzDnb+sB7C01Vg+yjP/2J29evFq64eumVZjHLskw05HmuFrz3ZVnGkIksy/b29nZ2djjzb731FlSY/KgYaBM4L0aj0caomIkFELFUDCF2xJvDoYfNpzMxmIpK2N2fMqMoCgkWB+a9r0OTZdne3ZsXz55x0fDYtkN6vQ4XEuZVaZYUQZnR2OU+uumJOkMsOxiJfkrw0SLa2K0GMVGoqRNozIhHPirbVbXzA7dWvNAYhhd75FhOaan07jAHWt6ZSY0YIouDXZj0ISCN5rDblXIrj0UBi7C5sc5wn/z4x7/4zZeG43NKg3yY+4E88cSjzs+uHdzh/fzbz//Aq549f263HGd2PVyePPCxn3VtjGz/jStgSkRLb9FlBGZKldFGpvRWPznJxczYACGIwOUMIVgwZpfNpnPnycxCCCILCUbEoiAWODjHcG4uzAgAk3MAJEjKCdAVdFTk3Nx+46V11o21DcrciQcufPGL33FN/Z4LW0OPubLUTV03hR9C4L3z3puZiKyvr9+6deuBD++oXmOEWiQraz/MRaogjTEag/OEpsZoDAoFEUQmB7P18XBe1vNqsXvjxpmHH4g1m9k5MxPTpg4BVjeLDO5rX/z9j/3inwa7Nm8yAIqQiZgtJInnZKZlEwwMtUFeOFBZV3HJ19fXJ5NJBOeOmkef9hgdpLDIcIoGYuSmDK3LZplyZAW1RLzS8YvH4sI+1kmPGMGkKmdF5vv3rzy10kPX/1u3bjVB2duTjzywP53uL+YBzmV+Pp9boE/+5Ke2Tp49ee6BjfMXXr966dFHH22aZjwed1zOypCOQ5ZdGODb6Nsjpogf1zklis7LWoOxWlnWTS113Uiw+CE45zzBMXsmb6ZwLBI8bBkqqIeczdLJMTiz73/ra+Ocm6YxszfeunX75q21oTu9MWyqBQCVxhEx2dbGunNuf39/f3+/qqqyLNfW1lzm19ZGg8K7vBjlhdTV0CPWuTi7tV4wOZdpMCKazGelVIPRmLUpUG2MRy8+//26JmIzIjFi5rIsARjTcDjUZrExHFlTd54VaWlaFpPalhChwokRkZjOtBFCtDXuHxz0LI6HW6tkjxkOHchZGBINQJuF595tRmoQ7bnbdamPuSYLKckqOoEgPdkq8ZVAwuS0KuumKgMnJqOlAqQg6enGTR3Mwzxp0jU8fOqCUTYZ5NfeuPT6S9ev7V15/tkvPf3KM4NBM8LjV669uAl3Zudd3/nes1VAObnz0CNPbG2sZVneZXztAkqXwaSHXFj69s90JymxUNdDIBNGIAsktUpjsEZJMJtWk3mo583eZL5Qq0s72J+pYNHYvNZauQ7UCAmInYAU5hBoa7OALdpyOUoIyk5hZuIsOFUKQR15Kx86ue64FE8zmeb54PJbVyioLC674Xpu85FtrGdOOKtv3rp7MBtnxXBrdGZjuDXOKPecZ+tbm95nHJrQzBpKmWbrxia1yxf1RDOfsTb1oMiYeVLVbEJE1Xz/zVdeqZty5/Sp3cW81CBGdT4wojxYXfLmcCAyn0wmaCkSp/wx5HqVBeJ1Yq/E5ADPJUxFiEhiGDKRqUbCHiOZY8gDEQUSIRLKjChDWEe1QVKgGVjwhBVJZYmE0oE/TomwiqtWJBDTg8l+lr9NTtRjrwTTpmluXLsOpsFgsLW+Mch9U9VbG5su2fzFeQyyHKRZlq2Nh3ZEtmsxaPqsjvbInautV4HJVKcHk+l0WjVNI0FEYgGK2bTqEAlUoq9Ulzq9a97nTa0refLZEGtUKJk5g+OmaTLH+7t7LrhCXE7F9vZmXdd55h9//NGQbUwaVGvZXjW/U2N26vR4PASTCvbGDy5QnNrcIKI8z6uqkljQh92krNU5hR3U89rT3WpWL0pLqbno+u50LtzwcDgczuaTQV4Mh8PCZ6ySOTJpAPhRduvg9kIXt27dLDLvmCPXCyBykP1JpT+1KVg9gLoZOAdiMCOWw4yflijpMkcmO0Vm4utypGHMbuALxxmipUrDahb3Y8H0Pjt6CLLJlMChYtO3Lr26UnHomGdbV0sBiUXf0GTqUifDYZGzGw+yar6o5ouMjB2auhpkyswMkqbOSB33g09+6LZy3iLUmVEIqoro9ls1TdMIkweTIaiahFgvCswcnWm7D0g69rdswmwRRH1/6ZiMVBzDCKIqpsSyMcxCWfpspER3J3NHHOpmmEPr8Jl/8zW/cXqCan1j56Ch5w7K3HmfZWb4x7/5r0qh6d6+Iw5VbaLEzvncZ8XupCyrxnseDHNmnlVlVS08u1A3Il2AoamG0SBXxflzD3ozBkkoHWAQR5Kx5Y6sKa2pcybvfSSeIqkKm8JUg0ijGkSkcDi7ORp5HnjKSBtDUCgokMSPakzpyUQOxmRwpl6tCPWJHCOvMCmbIGYgjvIaR09SbRn2+8Nifzu7KymDQ+RagSzMRBa//Zv/AghHOzn6CqJU5EGJhZEznT6xOXQ0yLLFwbSc7XEI4yzLODDzeDBsyr0izxjqmav5fkarOL59y6p7/8oYOr3diraZjbXRUIXFdCa1sHGeD2L0ghIx+aRGdgCpQRxZ5ihz5L2POrzl7NjUenkAkkjUkAXv4GEkwioMmdy+OvJ+ynAbw4/84s+V89n6cFRw2F5f+9CTT4xHWbYI4WCSVeGx7ZN54SeLEuC/8NHzI1vcXdSOKHM+9z73VDiQ1BdOb48Lz0434VxZnVnfGQ0L0zAYFJmjh0+vb/hmnatQL0yq9dHmzqkzm2uDEMLAYz33zjme1ydH67SoBxlefu67TmJmbEvOdWaaQorNOSaCY2yurR/MprWJMdWhUWsMwZl4wAPOLCPN2Vgb1iY3GbOtUzPMufAOKgf17ECqGaMqm0UT5nWzCMZLr/J7kLwVeD0O5RxqQ8ch1FevvGYa7tVPguz2gyQrm89yz+53f/tzHGTg3WhtLE1Z5PnLL70Ehywf5X4gTSjL+WKxmM+nN69dXVsbHcLi73i0x05TVeu6LstSRKKfvYiKInk9pmrSalQTIbr4hEajkFSVoa5EZWlNJYohFody/DvH3rMjG5AfZ8U4ywd59q9+6zeYjMvKZtOfeM/7RBoTHRfZYjbz0xs0v7Mx3PCjXHX/jMwYcHnW1FKWIc+5qiYikmWZ937kzVszzhmzXW+N927aLMTRnemEmYsiN2maprlzMEc2nNU6HOTE2Ns7QFE00tShUalyxyGEBaFhztfXHeuNN9+8e+v20rrTc1Aaj8fxZA6K/M7+QSk0CzptZK7wrAiVt+BApOZAGUKGULAOnI08hhTWHOq6XIQwEWQ8HLlRIXAuA1iIK3MMJYplMFPFaV7ink6jbmxGAgogBUfZvlPjOzUWdRqDiPVkc4uItopzhCJFdKiJWseriqUyDs55IgZIkGKfZ7PZlb3bGzpSWDEcBNP5wt64fuVsfvLZq8//4NKbX/z2MwubqzTm2OeDzA+/8M2njUhU04cghNA7b/1cPQJRUiVtONXZiDNdLCqppV7Ui+miqUUFEkyFAFJVMbOINaEMUkchmqeZGlUsS4hYRDCiJAoxrRoSMTIWjUJyyMkKtsIbrCZOhxQyvXnjekAYZDAb7t387md/96sntoqqCTI+t/A0m+PKjTeHo7ycV3uTpqoX2xtDH3R7YzOUujXcOJjt3rx+a2O8XYdQs28MnOXe+/l8kVuGgfcKx6IWyGUuK04O3f68GflBJTrIi4xpzW2oM28NqRuxoa6HxWjA1dBluVbDjWI7zx2nEB4mIzbvkOeoFk2oNdQ6bWr1vlYqoB4uD7Ll3RNnt7ZHjlVObW/lTDX5QF7ZGbhRmavbrZ3nbOCykXOZI3bqc6JY3d2ii9RxlPcoTlrFNL2L/ShQUg2zXWLvyDdheiwGPR6ZxVqdLjt/7szjjz8eOTzv/cmhPrg9Vm2eeOTR9z/xrqeefI83t5ZlMZvvZDJ5/LFHrBeAdyx27LUuHCWlbYqaGhGJhuxO7Zym1iP9Ma9QIGMxr0IanJlrM/H2ddfdI46MyByZp8ZD8sxnTOSgxmo+qEanNFZ77OKDBXGWySAvnZusr69PZ5X40as/eOnU1s7m+uCBCxeqRblW0NYgZIP1G3emL7x5I99co8z8EG60uX3yLOVrnrSc7XtqoNV8tu+gk/27Vi1yElWdTw4KCl5Kn4m5uqYFqTjnvv2tp597/tlmPs9JfcElacgLNvI+m88XqMPAZ9/+9rfJMTlm79g7sBczFVTUVNTUHDJtKFSsDatoqDK2eR3u7M0FvpJwa/duGRoGVITUVBoHs9A4khwwE4FwA6vQ1G4OnoMruHnfnyPmoTFYrARnyQNuVWmXIhNS5ualxt7MUjD04o46WstHo0GomkMAmr61GvVlDApYCWS0tXNCQzObzaqqcoUTkergymAxxjjLjaWu8vEai40ciwZmNpHCj1aOwdExH72B4VRsMVukipFtImqYdVmDV6xT0TSsphmxM8Q6DjHUvp1IC/etzytUmIyICg/mGCkOOA5BTb1x8mIb+OzE9pa/fX3/7oKsfutKPh6/S4zvThYXNjNWlVAv5mXOMhgOgyyGlj1w9syi0iuvvXF63a9vrH3r6a++fmMjZwSQI1cHdc4ZD1xelBrm1ZworwLgCyFvzrLR9tBn0929zW1343p18eLFwchuvFAYR1OnW1vfycs7xJJn2K1lMZt/7JNPVSbalgqKwSuA5hajy7GWsUhk7m3gvVRzy8aVVCohK/IQApg8DGyeIAaC5hmZgURioexg7qBqAlgcmUFEnbFfOfSHN6anY++QChEB0lMrxfR8BBBhIMqT641ZwSOyPdWNDrus4JhOmIiYTAzMmM7LtdHg0mu7Hs7M5vP5iVM7VM5v2dz54XBYlOVMGh2aTpsmhOAZBZFI03dM6ZxujkKqKQEUHW0siCmJhv7A+vg3ImbrcbEAmDEc5DlTKbxYBKfeeMlqU+/smVlOlmUZk3h2jUgDCiECpplJLIoHcHUwef2NVz+ww6br62vFhQfe9Q8+/1pTNRWFwZkNI7s7qaxqpln2i//xX/9v/6//p5/Lh0V5cP7k1uU3y4M5ru3v/4W//lfy55qvfO0b37s9GfpBtVtur601lGeuqNf9GhorUY94Z+fE3v7MuUyz8cbZ82V2rcrqE+sDyrJJ1Vx88qOvvfz9iSi7omnY1Ix4EWpeG97ePwgqJIHNVNUxF5CYeXPAmYg0TeMdKiEBwTsRUJarKos2QRpLmimWxjvHMEdWs0uOduwXVemKfM6kGRwZhWAS1n0+dIXXNrONdd7zS3g9BkDR6rR6OkZOacFYoWb1FOSI3De/+aX3PvVXcKStEGBbomIGA6Yf/ehHb1+7dWmRh1DenNcXcjfcOgkhhYmG2WKeM9g0y7KLZ083mJqlJDJm1jRN3svGuHL2RDSEEEIAOBVOY9f3EDUzQvLoxnH6AQ9bLGZzswAVykCel8qKNmqxNQJ7JpWGyBZNo6AAViM0FjlzocwUgIamvn7jxodOn17I/siv788O9vYPzm9ubvv5dD5pGhkOh83uQXbm3F/7z/63jzx48dXb5cWt9Zdfu/TGW2+954MfeOzjH37t1vSVt6YnHn7POXdqvSg4ozM7O3dmdV1XG2cuTi+/UmTr2eIOjTdPntm+dXefc9l+6OFAvlgf3741qQWbJ87zeP2la5fvHhxUB5O5TDMRVR2urdP09qTKq7peY980TeFzM1sfOJWmqhZzY2a2nOoqKGV1owutaiFPljERdFTk8yo44qqqBoVHrJelVsZihUaNCjjT2jz7AbmcdcE6HA+8YiILb+BoRUp57SgG5lHnkZxWX4k4XVciBWIpBiZmS7WNSW3q/XbuhoNc8+rrv/fV9z31V5BYha5gKBxIoQxHJN5cRUrGBCHTfDBwzt2s5gf70yZHJkNajPYH+wOeL3SyNXDXS+9YhYN3LMZlsNHWumpnY6fcFyJqTEAqyQolIqqqysw01HF2RKmqtoXQgWYCYhIAxBRh18y4RcZEJCYEFw9zpmZYVCCXlkqj30JBMVEgBVWAxdAg0RAmCMHMAc4B5MjMsoxHG8XzN/etKM4PwMOtOaqt8WDt5Mk7swNXMK+PF+zu1gUGGxe38r0h3difbj/w4AOnzr33o0/eXsx5cnBr2qxtrT36yEPssoPZ7vrW9gOPnLh+6/awcPTBp0Au4w8Nx810Oj9/5sG1nfndu/quJx6bzw+2BuONreL2zVvDtXpz8xy7vBpVZ4piujc5ceLEYJA7/5R/87nPf+F3/tJ/8D9YYwA1fCGL/ccfOvvNH8wXQhu5Geq9OoYlYS0r1AUzs3KxYAW5PPdsGI4GZV0ZuDEO0KpBMGXPjpilGmYEpwX7RagzcLWo95nM3GrQ3PESzArC6/3Up4CVuW05kNy8GzRVGerGOe6Kj/SeC6QZLORBVJq+Ov/GjRtvvvnm9evXQwhbo2zTy+a5hx998sOf/9K3nnvplc9+4fe/8+IP9kV2Nk8+eOGhYZb94PKl3/vG18ivlrjt/oyp1SJNXzHZd26IR9EkIlspQqp0xDl8ZWVcm9UqIxsX2cAnA+DR2PCEX9smbfvMv/iVn/6Zn/qTv/xLH/7Ix3/xz/zCr//a58vZ3fVx9omfeOKDTz1x/tzmfHbrUz/3scce2momVx6+uHlw9+bJ7fEHn3rPiU1v9cGTj104f/rEqdNb165dHq75EzsbNy5fLtYGn/2dz169/tbazsY//af/6Nbta/nA/z/+n//1ydPbv/Fbv/bZz/zq9nj4D//e32lC+fVvfHmxmHzvO98123/iyQ+9770/8emf+6X3vudDH/jQx85eeOjUuYvDteKhB8+f3FwvZDKgSqoFEa2P1+7uV7U4UasbCvCDIsszR9CyCVWQWoLlA58NPUlDVpNNJASfL1SDAULr3rYK3sgwzjkrhnN1B6VOSp01NBOaw81qndW6FJL6omj/YvdTt9BdVtv+RSLK8sHW/PaEZXN969bdq47ZOp8mS1n4iKjhItNcnO7N9l976613P/UUV2JAMSjOnDlz8eLFZy+9cu1u9e4HH3nkwTNrA3poc1F84+673/f+X/jZofjTX/7a75+/+MjDT7znG8+8+vBDF5/ceKRQm1vykYnSm4p48jA0dVPXdZyFI9JIHIyVE5N6NJ1YWwqbiRI7m2o+pTqnDsQq4JgDm4igDqAob4aGzJoY6ZXcR5dGjW55+55WRJRDNnc2z58/WfNuPvYXzz3Kl6/YcMdtnKxvXd7eHq6tXfj+c9995JFH/tb/8n+8+/qzH/jAE/u7d+7cvLJe0O1rl7bPnYbmW5vjL335i9NmcXLzzBuvvf7QE4/tz/avfu/m4+9/byP1v/n853/5lzZ3d+9cu35VTb7/6g9+MdM7871bt6/t7++KVrPJtJzvXrliobwzHA6bplmUdZY7kZB5vnnzyuQWjzM7efLE7lxvTSuRWua1srdglYoZzOp0HMkRO9VA5MVqr5ZDRcSz964ZDVxMQNOIiYkENdFKuTReVIGHxf6iZKUgEgxd4fnjEee9UOm9MCtLuTHYvplnN25ezrw4KZwnIMaOLhHVK9/59uL618Odt77y9LNv3dr//X/z5Zdffvn1118PIZRleeLEie3t7emifOu159989qsbNK92bz/1vveDyZqqnO2vD4u9eajNb51Yv3v7zj/5F/9SHYlqE0KH35i5qZrZbN40ocORSVpvSx0fxZrx7HUwxGQwIXTOLhH/mbSYMV50IDJ4dgpfB4i5LtPLvV7U2a7iDePx5j//57/2+kvPSXnw+svXTm2OT548f31P/tnnvlzPKhY085rdYPetyy9/80uYz8J8vpbnd25cHw6H4/H6+mh7fTB2jqbzRVmWPBjs1XL+wUd2D8rbe1MebtzaPXCuGK6tH0znsc6lMpvzB9PZaLhx8uRpgA/K2Wa+vbnmiFCWC5HgHWkIBB0N1/NiuH7ixMINn335zat39yvjmwu5XYZaBRSEsBCpxWqxWVkvqtCoNmrstJFAfnT29InxaFSLWiAz1KIHdbhTNbfm1X6tn/70p51zVVWB3d39A7AzcA1YUGnqJQa1t1PQ9O88epuZhXIxM39zOg+hcWJaZrFMAhFiEv74VDHbfc/ZU5eu3jm9dZKLgc6bsiyz8Xg+n4/HO4vFYnNz86l3P/Snfv4j2eJ2o9XWKJ8eTEIIu/P9K7fuDLbXdq/c/N5zzy+aanN9y4aDvVAWPOq2HEBZlmhAakYx278xs8a6DSkP8z2zr0SWIykm2ql1cBZdypi9qSSDipljSN0oe0R9iSU3R11mAz/mGHRatr39qQYlmKOmXpg2pasXw7UtEHmfM+VZlltlwwFfOHVqtnurlvr0iZ0iy8uyvnD2xNrWtkohcvDpT//C9snt7Z1Tf+JP//JsWv70z3x6tijfunHrL/7Ff19qCo3+2T/755zLnnzyvU9iy6bVn/rZX1hb29jY2CK4R971eO6Hp07lt29fzfN8sVgU2aCqKu+5WtSqVAadNfTg40++duny/mxf2FlTB1NvLog0ZCrOzEKA46YKFRFlirKq5tNqfTOXAU/3KrVh1cikqhtTn6EWhdlvfe6zNTIyUyURIbPQ1MlLj50nKOA05XM0M1MXox8li1F3cGJwh0urWOsRGD1VIxcQQNMrv/W+cx9n9+oIg+kQV65/98TGBxRCgFeW3JmEpx4YD+9+91tf27t8d1FXlYmyy2js3vs/+p9gfnM2s5K0Zr+/f+2EOzi5fX6R6ZazYsAPnvuAX6e6kmzGDz72LjMrwzT7QbnGjizTpmkacU6bhbIFkI8aSuWOP4m4MzjnMqKoeG9L8S15GGJ1nDUhOCUjNKqmDCYip6pE4mEkjWtLUgigCjhP1p7eVIcNuWUKAVTZadJ9aJFxCMF7PzMlg4g9/tiDb377soa6LKkczrLC75VV0+xvFTvXZzfHNttYH57dPnXnzrXNnRGKM7TA3el8fbyWe2mIDhZBGXfv1g+feVQHstjbrw/23iynBWWF6RvPfPvE9naRZW9dehEVrr7xpud5np965Qfff+TMqWr3Nqo7V17DusMbb+6S1c+/+M3pNOxsbqxv7Fy/fn00GiH3F8+cbPane2Vz7aU3JFhQAUIjasSVKEw9Q60GmNhUoxOCu1XCLFet37i2GxoJweblgYIkOkjU5pTJaMIDs6AgDxO2UC6YvFdV0sY0xsVbjLpxkJFDaQAo854NqkouFoo7ZHNqc98DbaZwAiyj4eTq3piSvaTG97/z9V/4hQ+KGhkqdtTgznNfu/GtL71xYnrplboY8HqWj8eju/uLer/8lb/9f/zUf/G/0OpgsMY/8dQDY+yHpq7qhTXzT330gb1Lz16/sZjZ+rjIJwev7u0PtgegBbb98NrtqydOvBeLqsHCk5c6CIFcZxBaRfYtro3nDZ201AWFxdQuDdiAIAjmPBFL48gcs2MGQEYxgUp02qLWXd9smbS+gSODJ6sDIIGZY5Lf+IqimakbBPZvvPHG2mj87DMvv/bmrZ98/8nHn3zv/GAfO9nNG289+9UXt7ZHN65deeiRd108d3Y+vTbdnx5Mr6mERx5+8P1PPvHlz37uP7xwvhieCpPbG2vb+we3N8dbDzx4utHFsBjc2T/4wGPvvXHjRlnOTp8c37g9ZQgVmbeZ87J380q5qK2p7969nY23w8Fia3N08fTp+amcKR9kw0cf2xKRSnQ6rUODRU0GR6iH3qaVqsbSFM5MTdk5U1GoMTNYRcwMpOaIo38JM5uRJ4KagEBgdiLCbbLmSoIxiUjGajDz0Ea8c65uBATnHESLQVYHWAiZz8BsFtQCke/DZUI2ETP1oNbb4ATJKzN1piKS58O33nhhkPNBqWTmc8vffE1f+PqpM7OvX5+f3jw/yg7IIPVkM8+VfMDizdef371z9/UbB6M7b7z3XWfJZQeTifeS8Y3zj11YW7vJkp0e0o2t0akRmjDLA3/yYz+7le9gMRXAj8bldKGOSuVBS5dVlRDTA6bMM8wcI4uiiBMhJkr6zKn0nKrFqhJQI6sJ5Mkyx0RQiJkFclR4UfUWUwpSiJl7mRQWQmBmcWoqwWQukqHJfV4ruaqKY3jo5OjqbtkIzp49u//q7fe85/3F+ORgMCnLcnNtvRIbDPI/96c/XeSoF0/lw5E2qie2NzfXpwfXJNTj8RDZ2k/93M+/8vLzVaAbVwOP1ua7C8rH4yLXZirEMLpx+TX2OXP+0uVXOM9LcUHZwmQ8yIYDz5o39ZyBM6dPXDi7U872ND91UHtyzrFlWWZmBue4ee65H5g6CbVnBtQ510iDGGMEEJEHk2chUZgS/f+4+u9/y7K7PBcdceY5V15r51C7cq7u6hzUQa3QyhEQyRiwZRtwwMY4XHxswNfggAn2wQLLQjJIIBSROqlzdVd1VVfOVXvXzmnltWaec6TzQwnu8Z1/w/jMMcY73u/zYKiAUhAqqtG7z35CKHx3TlEKgjGEd5vvAkgFFRI8l3/9XAcFl0oqgiCQhDGmFPzhQQtjP+GOZ2OIdEolwp12F2CCsFIA/x+rE/z/AvcfMushLEpJyfbtlZBAICHQqTHs3VZKIIQRV972RvONL8/YsYR2M1TVYogEJAgjRCSQEulCil4w2LHvUKu52WiIfhgihCxbDjpJqWyM8Krp0LzXLuQRNIxxI23Zk4XhrQspsOMkWXjpRNPft/fwjcsn9x851hqAPXvv+5u9GwKA0F0d1f8/Mepv3ingX09ySXX3cAnA3fEDBHSQE0IMxxFC8ZwljEmgiGRSSoPSNOelUmkwGAhMMMby/9XyttgAE50JhDGEWeqaNJCKUHo3gfJgHpoki0GSZJaNEWbjk2UxGOi6nuYyFVgpvrVyYWZ63NaMJGkb1Ml5SkCcRb6ukV1TU5sJKBdKays3yuNTlTbUytVA73fSPE4yAzuG52CAHUPTDHOrPciJxlKh6zqWyiiMmJrKEp9TqzTqDYcZ9bxepIgqVxpmtN0pFhxdN+/O9KWpZMKv1ovN9bVqvZKLu5MeGCGkIKQaVEIhJCRnGFMglQQSQqkEBFAhiJQQCCOWc6UgghAoSRAUUlKlgFRQgpRnSmEhcyUg0iDP89nxsbWtTcY4zBnhd38AUAEIBUAK0SgVCKkol0whpNlSsLu3jFTlNrtbZqIQQgQQghIBCAASUBEABRCxt7dz6aJh6owrSiGmuk31vplVN4o3v/svDhYhc0ihMOKuxljkCpkY5FwRZWCZSipJpWJtDoA7srs8ecffdBul8ZBnlclVFjWEOcAWm/AJSK6902y+X/cWBoOnjTAeZrYERufG5u1kSxr5yhYf3VVub6udDyHCoAIyZ1jTBIBSSSqYhCqFGmEpwSZUVNeA4glWkCMjlgwCCAEmEigQ60oVQAapIaiAmAyjULPcQZpPNqogbBEIunFSLTvrrd7o2FwYSiADIRRCCHEcE73Ih/fuHj9z7Y7u1XmQzOyqrc+ntt7NY1OzDUukEgMmkQj7rmv6HR5lGQe0USwABHKJDKxKrmNwvLS4RTHRMQDAD6NcgDkpsqGfLqwvjc1MUix27JgxKhODd69qHZcSOlY0zVFTMzUENcJzBKVWHhmZ2t/vrhJFgcg0KvthXnHVUM5ZhHaCTre/WnDcWrUssK1TWqiNeuVKa23RqYykWVzAdm+wZri2V6wBFefSiLA0Ra5BglQqmKYQlkKlEOo5Z4grQNndiAPmTCKKMM2whEpIJqU0EdIEkwhyJQCHY57NqLE68CVPcQCKqFnS6epqVjaxn6Q9wchfB0DobySKSvC7vxMFiISS3K2wQIAEyJCgEgAiAcRcKgkUhhJCIADACN++ufSlP/0zZ2KnrmthFhuEDDdiBoZO6i2c+ouJEveckpRgeaOlaYZEgAAOEZYKIykVQgrBdmfglQ/JNke5fuXmrfKDZa+g9wee6aJeh3uOl/OBSqLdOkZCPXFkpnfm+3OFHXoyHyhpIBR3Wx5QvNdFCBANCsEKjpsxhhCJk4xSDASSUlCEXQcrxaXgFEKAketYWCts9tqcSQgYVrBcdNJElLziMEgNKjlAlkbSNLN0I89zBEASwzgG0SC2QGnp5gLPFQQYAcFVDqiuUuHVa5tr2wXLi+O8VC5vbW1Loww1jmUeREnKsjCIOHKhQlEsSuWpYnnm1OkzpV0lFkMqGQVka+nGZ3/6vXkGIJB+fzNjwg/i6enRzQ0+NT2X86TVaiMEMYD37b13x868OwSapt11J+R5hnVTM61M5u3Ad03ps4xgxCQQSZ5LsLnRzDSVd1rEJEgzOp3W7du3iVsdxOEwDLrdbtnQyuMzRNPLTlnBeHV1tdqYBqABUEAzTUGSK0QQ4QBIqSRUFGHbNYNo6Ogo6G5rRkFyAKGiEAoAmORMSkoIyxiFSCnJOdexpukkk1EwTF2WHKiTqV27e718486mjh2LEpGlBIi7aE0EkYB370v4r/NkpOAPeYFCwwgrNKS5VBoACgIBoX6XDS0Rv8ss2z73zioZqaVwTBNhmhQ1zRHVrbV3xqP9NfyOVigwhAsUX7mxQdw6pxphkYIGAFjnGUcoEnJ7e7C7CIumM1hl24Gwq64/XHvlpZXH3jth6rsLRL/SXC33Nz8zNoMUdxfPQaKNwCFcfpGYtqlyc9CxRdi5dRXu3iERcykxsAKMx1GkEwqVVBpyief7YRL5lm2M1KuQiUxoaTDIsqEUUnJg6RzmWBNgvRtT4A6HgVJsZGzUQDCJBkjX/SCulQpMCU2qsXpxdTuFWFd5bJhmlkYEk5zwAsdRmA7jcHRsatjx270OMe1hOgQCV/PesC+E0JGuUz7UCF24c+Nzn3h2yJJnP/mpcdeHsDR6Jdt7eHLEvccsahaXhbIr8c6VtY1dheKZt1//8Ec+srq+PTM+19sejkxOx1F3ZWX19vwStKpufQIjTABhSpmat9xcP37k2LmXX3jg8L5SuXrl5oJTqq02gyeeeubEi9/hpuh0+3ESWEC/t1iojc1ww2kuLuzfOVs9eiBs97pRbrnFJIkmp6uu7RSAF+F1GE4W1DXGS5hoTCYEmZiIKGMaS71KCfIBGyafOj59ZbE1FFjyNE14uVyL+xHFOkjSu3EGB4wopGE27DaRaZaRenp3ZW4MfP3Nt7bVRB71KaXbm/2JiSpSQCgg7jICwf8JtVNCAiUwhhQjIQREwuLBXbwAkEqKTMkcKgaVyuJYptmD4zakXGOJJtUPefp5vnjh7Nbbf4HTTpoa28NtaROuGVSJIEowJpmQEAiDYCAVgZDoGkWSpT7RraeffHw4wP4gn9wxo5tVCaKoP4AGqZXrXhq3owHMUsyoBYkuoa5T13VdAqlGaoZu2QbiHDLRbXfSNC0WXNe2PM8L/GTQ79qI2WYBCK215Q8HPSGRpuuWSQuuRSCoVIuGYSRJhChRRNMtqzIyMRhGgudFx7It3bLMbsfXbAQxUCSNUD9jqaHpfuJjwpEGWBhaGgIiZxj3w55pE6IJomDN5mWoDuyZmaw5tYJpa2CqZrsO2THTKNUsaogo7dbGXd2U03O7L9y8k2vOneWlcrXUC6I7LfS7X3z+N37nK05x7vsvPJ9z1my3hsPgz7/2F5Dgq5cv2IXyzJ6Dzd6gUK2fv3KtMTYKMdp3YP+pV97cPzFx9tWXb527NFkuqih67/2PdJqtpx59Qpfqx3/ipz78kY9lAlxfWMk4ynk+Ua2hLJo/d97v+KOuJ/xganpMozhPUsnc9z0263H+I5946IHDo0VtuKOGRx345NG9KAymCgbNg4YOjt9z37uXbt179JhE3DLVg4/eO2xvNQpFkmcFDVlAVDyLAu4QOFaxJ6vurEN+8oPHG2PmC6euMWAkeea6BYCQbdvdoI8oAQgKghUC8C6u8m4IAiEUgnGeKy5YlveSqB/3HpxqyDzjaabyTGaByiLAEpGlOgR117NBClRkYB2kmUkJlgjReO3cjXtGO1yr2zTa3bCa21C3HQsp29QlpBAiA3KhlJKcQiCVwkg4FvUmivtmGr/9//3fUFY//MlHXn35Rte/qLIwQSJTOJaQjJT6yoJEbqeDmOh5nsY5p6YlLQ8pcGv+OuWQMHB3gsyPkyjLmu0OJYZGYNkFAKc5jxUAI6Pja81udxgqxAZhzyk4OZCJkOWREcayzqDvll1oWoM41UxDtymmQCOIStpvh2lqLq8PQIgcEY9pm2AwAN1m88ZNGMRbrZU8aI6ZzlyhmK6tUj3VZD5lRd5wY9BqHpytH91Zfezw6D17y9MzdVNZ9frY5YtXNtZahGga1M2s8+zTj0CV3//IAynLukH2G7//xb7yhso6cfbK/v37syyLgtB2dE3XsYHjpG+YjoR6EoRFx1WM51mcDPsXTrx1YO9st7VmuhrR8I3r58sevnz2rb6/rUASp52g04lCP8liptsJExoShkuD3Ae2nthWhMQwG1KCEAIIIWGtbJ1N3/tA6yv/4/SF65txYmJQ2mp3X/rBiZzbPiNOY4oT7/WT564NzFdPXq477lixeObN14fD4cqdpeH2Rm9tibIo6mzUHH3v1LhD8v7W0tGRpta//Jev3txk5YpBd2pdO+ykWzeePNT4pz/2AcSFQHmECIQScpFjmRQAQypneWrkGZJKcGYTXgGsaDm6inRMNZ5bQlLBsFIGwZCxPROeTLmWX3VBKvMkl0yjKEkHutQhjolh2zUtNiw9Z6fWtwnjCcSQp4JlWGQAYgQkQlBAWqiWMSUvvvCDpTvdf/Ob//njH9lx7vKd//VHX1hfvemWJ4ZQG3fdF67dYSNlyKjE+okbq19/8ezpq2vNVG2uXL924+r25nY/ioDKbRe18jQTEPC+lDmQSiUp4qlGZI9r2CjlgihMemlGiZFjS+m6ledFx826w1hqy5u+jlHR0G2lzHzoWnqYg0EKlEAEYU0nCilFMj+GCY0btto7XmZJa9/eKdO2hmF30G6tr270187dWNsYnazfP7vXq5ibfbR719R6XzgF27DA9GSx5prttW2mAE+jSqU27CQAckzyVoZ0kWmGHfYGUqVdX5XcYhHKxYH//cutF97deOPt5wjVKdYQVErgcqFaKFpEtySgEgJEDNO0pa7ZheKdxasLa0svvvPu26ffqY/v6nSTXbtnNeo6esFAWgopJDoAKMsjBVLBMZdweWv17Pnznq5FnGRhkCSxyBAAcdyOWZGWhHAmLaiw6RmmDQquYZcKtQJ2nTKBULN1oJsalLsqoEjiXtCtjrgdPGQp90mxYBpmuWG6JX99hcE7hHmTZXyrI77/1vUxzwqHrTQh7zk0uWPU+plPPvPIQa9Bl4jiWbHgDqKhDm2v6CiWBkO/UC0rSLVkwJGM4ogBzXWLDCo/TXud5ZJXsAzAQx1BkGeyXGmsbm3aolqvuUVAICdIK+oIqxxomoWhLnOmIeSnmdApFwJhBYQglCD5w5wSIcR5pihduD1/YOaJD7znqRvX39114FilUbq83h4bbdTqaNBp2va4H1TsyuTSlpDEHPi5Ud9DYr0d6o/uPWyda1KAgnhITIxJsdXedMpjUZiFoJhxJXPGhAzW7tRHajlKMg6RyMNhq9PWM2LUDSgyUjRkvnXToUQzVL+34enuxuKNpFgSWdJP8h279wmWtUWGdCvy85wr0zQJAFNCnyjEJ652PLvUavYsDRt6iekZhsii0cr6FoqsK+cuIcfLQz/ZWFsfJsPtlYSJXpoVMM2lLmSWZZmmWxDqQMo0SyjCEkCq6zoFhNILly56xfL6YCVIhWeWXj557Q///c/4rTDP86JXUFwEvk9cnAkmpdQ0DWNMda3guFXLane0GyfeRU4jDPpbW1uN+ihCBELEAPJzJoQwTRsh5JqWlDJI43LJXVxaoQpZlhWHrFyq6pZjGnYuARKCx+kAk1p9ZP7KtciHSRtBAYGEcc62o9bKAtNJYbzqwNpoAjLDCItpQVhiRHMKBQyGwch0OQPJRq914PChN15+jbB3Jqf3r7xze2bneD/rmZp97MD40XvG7n2i9M3vvPjOydOViVlSss00il0NZXHYbQ4LniMRHrZbBJGUYKEE1uxunAk5HKR8nGhlu+oPE1cjgd/VkCKmt7S8BklUSsW9e7zSi6qrW4E7Oj3VuHTuNDEw8yaGKNe51nC1VOkx6+uYU0qRUJjgv1FLIYRSxjAgGONus1Uoj24nPd0tlEbdq4una1jTIAOS9UAhFfTIwamAscXVPuHRA4dHk1RevnppZGwyj8PGxEiUy8r0vZcuXJ7ZLamh44zqALkm0Ipyq5mmra7ERr3kEiSzPOqEORzVxg0E4o6C5I3L8yZMmTAef+yeG/MbSSaavQDmMaDW/M15rLhTbfhxmuXSwkBmUbmk577qdTbCYHdxpLy0ucDv9muBhiDycy4ARlC36zMRY1a5KDWsJ9umW1UAeUlKsE7DJlQ5pbRWn2ittgVjAMgkjQ3HW1hdenTHSBxlQpqMJVEGFHVMuyyoVZvZkwcLSb9DMfZ7gwMH9p0NYK/T7nY775654DjOWydPHjt2PBtE/c4GhYASqpcrly9f/uTHdipAeJ5+8/nnEqFOnjzZ7jQ5zx978GHDMIYZS/1+kmSmUSdUozokhNcao0ihpZXVY6NzIOhuc7i8OL9z3/7m2oalG4d2jgfDUCsWVpd71QYBSru+vKq6SyN29NZCt6FtZmSMxXYHDTxYXLi1gDVbEhol7Gc/8sHHnm38g3/6FyO7DqRA1SfmrEG3gFrYmmKY3FwLixOPN/ZXSH/oy5zXyiaBCGjEDyJCTVNDgMtmmHmmZiFDIAwUJ4QkWe4PeazQIIwhVKP10iAFY8VGJ1hzONocLJcx2FK5n/jB1TaWHOpZLKhdt4INv2RAXJpJWFe3kJQSY3q3oHk320II5WkKuCaB0m0L9oN234d0AsOIc46oQQAwkdQM94FDB4bb16mhH9892u0EnkmSVJFifZvL1CYUEyoEJUaWsYvnLzzz1GO+30Icpr3ArphVx/Y5ykVW4Hmr3ROKiEz6dwZwT1WkPvUqo+MTdQcMOtGws2UZVEcAQkV0M5VQKq4DCf1O0StmPKkYmu64rsb7WrKyLTwUr95ZL1fcPMnyNFUQKAQ1E1mI4TxHDBZNfdgfpprhUU64rwOggdyCRFhs0BvmeZ5z5nlOlmXNZif0g7MXL03MTC7OL4yNzyGi8bQLIQJIMwzDMit+HGJKXNc1TYcgdOXipRNrS6k5/fjjj5qmQynKeASlghBur803yl5nGIVSUkqllJjomp7bpiZSHoWJFAAASUwdQbS1sbG2tKCbtlJ46IcKG47jXr96uVap7929a3yk4GG2vNqp207S2Z6pYK+gnTn1uq7QII2wKG1v9GsTO0ar5e3W9SefOqbw5pGDOzY3q0zSjpt7uXX1xgJIE6yJuhHfvHFtqyuoyHbvmZ6/tWjrXmHWGi8uf+2br84cfo+gVcZ0hADhEuZMBEEEgSERkIgqBJXgMst1oBqWDrN2yXBiBMd3zMHWrbGpxvXVzY7fRdDY2lwBVrnX6zEtBpk8fmzXO2R1k2CjUUW9bjBomTqjiso4maqMx8Pbm+GWUyzfZRVxzjXy/zKFSgUhFDnjUvYiv3p31lvTdRRolCilOMssLBzbMjaDkckZLqPXXnwuEeDjz75HM2icdXhGbt6+OV4dkwZ+66UX53YfQli++K1vQJfsG5uGwWDQJb0c5MDw+7284K90WYhckqRS6i/Od3SrIPmAQn1oub1mdxEnvRATlWtQSEyDJAVSUsAhJYmUnEe60JluCpCT2IeokcsNIg2sUSSQrWOuJFOCQJEx5OI8FlghxZmg2CAyRQBKrLJcGTKOqDW15zgAwHKMK1cvWOX34pXAsqzRsYkgCAqjhSxjukV1qErFwkp3mGeJhnPd1LbCoKLRQa8/Pr1nfGLsmX0PRHTinXfP3H/8sRNvvfrIkw9Z2AR5tu/ovc89d4oBg4Ok5DiCccvxoubKIw/e94MfnDh67PBIY/yLf/h73/zud/bNzEFA7zl6LMzaSU9KKYlBm+3tXfv3uJbOkogQWXPo0DVF5uuSlcRwyq0tcVYjBmHZWH0bFN3N7sAytzwUP/fGmf17rTfe6BEpRr3uNsPrCy1cGNsx4jx+385v/uAvr67qfHOk5MwQZNbKtk57J8/ffuLpSiYKLR8yTKO4nbMxMlH21lfCfpCPjpQ1kIdA53EAojsWQqZZi5ffGa/tWF5fTXAp6PbrVubhkXvLDk8jPxi2BwMILb1glrMgdCJo2u/7uafSkxi5nrejceuGc2x/LZB10+ltb1+fsOzT6xmO+4bldnNQNRQFvCPMoo4ASw3EY6J8JjUCYKp0gmW4WTETCXsYKMlTA40zsxR2V8ZGvcDvQdo/dSepV5xOxh0kPG+kxfo/st+90dlskSOO0+51FhXLLYzkVvb2rUWIOAASIXK3xLmGdAihlE2AMVKihxSGPYSQhADnGwgDIRimdi5kAiREEiqApFAKSME1hJC0AYIozQhCiLhKRRYpSQQ554ZjZXmOECWAIqiIZLEyMMUIIYyElJJopmK5BpGmAwVgQUnXghQiGPvVssUjAYCb8SWDIp5mXqU2aA9rtnElznTTMwQMEfVEDEVImMzRkMN84LcGWwNo8zBlnEGAea3oOFkWUVqsVLpdC6msYNntCN13/8PEMDOW+/1cTamCpRGFw2HTNQuu4bT7A88uGI67a+rAhtzMJSoC1suEbXlChnkuWu3emAOfOo6ff7H19KNH2SDSLPOj95W1snn2cjg3vbOIhhtGvLW0fnj/7Fu3Fm+eH+wslliyxMP4YGVqUZd7RvipM5tXVu8srdQ0LbW1nm52N8+v37dr0lAbLd55+XziZ6XNG7fKJcMFjWi4TFbX5wG0KdS3wsARPsGWx6LDu2dnd07+tz957Ym5Qn9zoza5rwOJZxWN7tXm7XdYKWsNBEKo4GpRb0tyB1cnZqwwd8zZI/u96zdzzcxYXqrUmMIIgUzzvGIlGrQ2mwHGBEEgpRRCpQTlikVcEgClkgbWoeIQQk03iaAIQAIRgFQCTDSdA4gokRIooS4uNvfsIJ6rP3zvYdcpYs6+ceLKMDUfPaaB9fGb19sEopF6o99uSZZRehdIQYSQCGKIFELoLvwTY6wQQohwADKsKZZiIKiSFFKkm0pwqhMg+V1trwIIgL+eqAcAAYkJghByiQEEUimolGs7WZaRv9aSAwUhwAhBJXIAMMVIQgCkIAhjBIjkBBCRpxhjKSXn3NR1gjUgRTrsO1Rn1ILQpRa27LRQcIFhNSpOe9AbrZsb8yEiUAIaRj4meqaohnQYc86ZaWi+HzAhc5WeuXq5bGpPPvb0mydPTdVnisWK5DyIIs/zdMOimuGZtlM2MsFSKatugUCNpxlG6OGHHhr6IcBgYnJM04w0iSjRZ/bOvPeJibff+s61VjQV57Cz8epzp3/syUNn394cPXL81cs33n9s9sbS+YfvOVIwxYcbu0GU2IbdGfoaSnTTfmDn4cRdObtS6MbF++8pZ7xd9Ap5MvS7WwTmJUuvwMCwR964vuL327VS2aU5iCNywDbWmGbOjDgq2+G4N2/cWW9vbNaPzL/VPnpk7tHjxfXl+K/Or26nhT0T+bFd3qW4PXH84OJrS//4o4ffevVFuzp5p9syimO91/7k5Rduvn0H3pGFXBiarhCwFxCDSLsB47/7zA5dtwZRv1BylJCOaWmYIS5rhCCRBxBQTLMgVVJgjE3bQWGHx2meZhhjTdPUXTkTQgrAzsAfm5rDeLtUdiZqrpIkDvpjtpPa4xtb59PArxTmsizqb2wQJCEUgGcYEQCQrmlSSvBDlO4P0V8CKiklIcTkiRI5RRwY9g9reEBAIRBQImNQowBCREiephghSinL4rtLXEp1t4PjWWaaphRCAKS625SVAkHFOdcxVIKxjGOMEYYsTw3ToADwPNOwlmWZaZpZlkHB//LPvlZ0ZmarTnt1qR1Ef3jxYqFYGoRwenL/MIgPTlTIrLmjrv3ul06VysQi3tZWv7GwVCiOljU3T0Vv0MUS2JarmW4uxM7du0acwpkzZ973zNOxz/I0HZmaWN3cFrnUDZvaXuD75RHPsCysuGCZZRlKqUP7D+QR63Q6lueFUZIkiRQqz3mnF7z08uvbG0oh8/XvPbd3117u1gb2iFMoXjq1en0rxHAYZuX/8VZvpmGtrS2NmQJI2IsSoyQ37lx66ulHDs4eDtD1BGF/GO3eVe72/Up9yq01vv7iS7saXsUrFwj4yF57cSUymf/pH32GKUBMRxveaRYalkiiVi/a6EZKl2udrbif6EL86YZ/aynygb1jZyXttxYLlTzSy5n2if007lyYGrcCRKZtE2rtj75vVKY7W3gr6g/zFCGSO1Y5Gvrlkhcl1NY1pLgEGuecYAgVAEpARIBiCiklQZqlmmVkcUtJkXOOCLYNs1ouY9DVIJRpiCQ3NSoBVLo5WdCkJDnPSqXSMMpNpKZG7dvLYRhHlco0TagOBZJcMq4RACDGGDCWIgGB/KGJhmBICIFQKQQQkJINdQgVlIJzBDOlBKFISamEpAQhrCBUXAIhBCEEQJjnOZQKIcRzRhCSjFer1V63rWmaUupul1kIIWSuaZoCAAMFIMAUY4yVkAbVRM4wJdDWopxPFApSylqtJk1raqR29fJyxcEmkUiySr2mGa7CMBSsUnLoINA01d4W3sh4kIhByiJcDNspHWT3jyGTonKtvL25Ram+2eo0JkYuX7j1jTOn/9ZP/sT66mK1SBvjY2+dPR/EvFyqvfnWO6urGzzL3rnwtkm1Zx5+uFSrvvHWyQuXtk2djNcnRkdHby7d2Ld3f57zgmc7jgPz6TPnl+/ZP36PdWJzbfLNc+0nHnvwzp2eTdD+fUdzY+31d6/93c//7f/yx19tdgKjMLpz9/T81euHjj2itFhYyauX1m9e7Y7u3uvxgovV+dPPRwxk+drEWMV0aimHm8Osh1JHqpFZZ9Thr114/aXTbZKpcKxR7PWD2O93emHaDcxSadCNFGAGwe3EwcWCmWfpsNvM4vmWKiO8U/UbO3bUR0C23W81ZW9Njrvgy2/cHLa37AMf4O22xEbOEPO7B6Z3nb5+oWZDPXdTjSIsswQrDxIeSoE5EVxJHWJXiUBwgbJiiSqW3r59ztk3cmTP/QPmssg8dmDXhbffbEXMAb6ZU7+1bRYa892mg9Dq0k1ZGkmxWRhzCktZdWfh9koqguY4zQlkaRojDhzHyaOAUhozoeuQceWVvBhbQ8gPaFomYp1ApRHb1BljmlZQSt1lbeoGsixL07QcsjitbKrx+0tL0DDzlOmEahhKAQFAQRJYlsF4bppzlmVhjC0CLq9G3N11T2lTQgQRCTNhWnq33fYcS2leEGbdznBjKK+t9ZHiuTQQNitFp4d5rVantCc6/cAGMMtNl8QApiLpN7frEzur4xO3bl6XQKlM40J61XIetiXA1WJRbi1r1WrFLN28fcu0tOuXLy3emQ/CsDY6+rW//MbO6bFUsHdu3C42Gszf6g4VxphQ5RkOIUVCyHitEUZxvV4HSLMUxpRgig7vOywBKKPM7/pTUzOblrTL5dG6N4rfe2ZxAM3+g4+PvvVaFnmT62uLuyqEPvDg5cXVpx48bquwH+a9Vn+s4S2vLGBq5krVy5Vf+LmxP/zWrfZgLGK86gTlbRmWjf66TmyrG0YDTAf9IRR4tlY8sqt2FLZvrekEQsxZcuvWbUrtkbFxZTjQtmWcaPoP+RyMZQ41QiYAhBnrdYvW1YVw6XYcDXrUsLXiVM+/s9JKZu3aL/7s03/18qYGCNIJREJxvraxOjM9HndWEVKU6hLcFeHgH6IiIJRCEl1PWIIwVog0N7hjV6Zna4nfOTA5paFYg9Hs+MSpKLJt17IMiHqTE3Pr6zdn987eWAwjZI+aZMLgPZZ4tiGgN2SabsPPfvzB9ubq3StRzoXiGcY4THIFOAaQajjXqn/58vzHni0zViAKYstgSV4ul/1heJcpDiE0LWoYBoSQAxXE+upKPL5jLuVMSWFQjckMY8pyWTXqECrHse6S8Sil0XCwf9/k9QEGruvaJgLAhRgh5JYKhBAqosglVY8U0FhhRzJaLb584t1ccn+7Pex2Tq3f5hAN456WWgkPO5tNrldhEkom/X5LDLo6ziQ2gzTjEvn9XqXg1kZqRFHqeqZdPna4WquXsywBUikINNNIk1wjBAElszSTOM0ySz8axrmU0jCMOM/yPO90Oq32ulTQdXSWxNHAHwb+jUzkeU4p6a0vVhojG61ukL5z75gWzB42HbLv8G6YafO3+muDYb06547W281FpzRmFlxidSg3zHIhZsb1yxfCNDw6MR70u3OzXv/2FTMY0gDmYTy+76hRFbAE5tehUoEfChoB2ySCg26YvfLmmR99cvZWnxNNN2seeOLeAxdutP1B30Z6r5uINMYYp1nmuS5BVCcUw7CgS2wzRyW7y7xoR92dRhLHhrkOaG0tzL1O4+bZN1dvD/oDXeqRlFKnJBFR3A9lNGAsyqmDNN3ElBIEgMg5x5jqus45R4YGUgAUAtIk2IzjsAJU0fJVbJT1sGKr8UbVMiyEAVdxnAqH4sXF1TgVFPBhlFl6CUs+iIZv3YjfurA2c/jw5LS3d98RSizOAFeQxT6EMFdYKi5ZZhCYoMY6n5k6oKquG/txKsGg1SJEq5pOlqflYq3b7RLD5gBEYaQYyYmIlby5lvM8xkgAmSdJ4nmekrDb7frBoFgsRlF0d3G7hVI0uHq67y3QtmnoMvbjIDAsd5DkcZKl1OZKSziRCnJilkzUTcn2n351tmg888Ahg7jbPhd3WilnuRQUAp0qkkQbK80501rfXOUsssyCxCampob0qYJHRa8dwDPzV1ytmCOWZonneXmaY0Ja3Y5b8ApeaeDHlOeablaqBZZlvh8AAHRdbwd93/cJIfVikXMZSr61uqxBrCDohwJwhqGiUjLOh2FYdMqf/cyPBv15CSzGU4QMAKzxHXv7aWpBbWrPwfWBzLhaWbyJOS9Xpzb6W0T3Cp61FfT7fqQUdHTN1UC/u2xB8vaNcNS0S6kq1KZcSua3aNpcx7bZ80PNLqwNh8I2pqqMCKGAEJpiFdcNeRCHseEVZndOdbvDfrtVr9biKBsG4a56quetKMwlFj84E4SAjLpQAg/wDjCqS4jXZK0246DTL6Jy3cFY12kwHOiGZeu0WMKuSTa45AgTAliaQQgVUECIPM8sonWCzDY0LIWgHS7DK5fuZEZkCrqAKgCLS2dPzM3WWD4wXA1A2h9suzbUsLa81X/utv/v/s77nay5ntZ8yJ97fdCo0CCIzp24ZTsahOTa1Vu79h/sNDdt2z574bJhao1S0dTpUNhfeeWdd79tHporpGHCACwUqGGYvd4ASV6pVCCEUirGWBRFmBi9nJ/qmGvaYKxkWyYulQtpe2BZFhesl7EgGDZGWK/X0zSt1+tVyxWIyPmVFq7nFINawVWMpCETuawVR3bs2nFnafPmus+w3WwHC71twdIDc/UBxRdvnGovr2rGXMnyZMwLunfh4nWjlExVbMstplzYrgcYKWggTIIjB3Zvt7ojNkBYLffD63eum1CLM04IkUJpmgEJFlKubm3wlBdsTyHFeaYIRsSA4Ie0nyzw7wYIg0LBMqwwyzkpJVDlaebYWKaxjZQOMdGwjl2pyPfffHfnzh0WMLPtq8y0VoV/5vxQYHff7M6TL583K3XBhEqColfa2lpVWWfnrl1L3c75vk8Y7p/furXZv7bBIlCWLPr93//Nr/z6HxuwETebbQGYANPjxUGaolo9yuOJnfWvvHL2yuaQmKYJlERQc0x/enLn0s1mn+UEqO21LRvxzcWF4sgEE/nkzFjZ8N54Zbs4VR2pkV6fH9jPewOTM7S9rXRtqItiFt34wKMH3/5ujxFFKdI1S6OWQbGjcV3XUUaxbrA8kFIapimE0DRNcYgRhsSBSOaZbziGEOzxJ+7/6H2NmpUmoUk1ixpxHGROUa21caU8VjRHUGcFSZIwUdUUD/vt3He9hg6HCNkpS1jid1rJrWu9QqFQsI35W+ctDWdx27WBpQnTkFImllmoV3Z+/OmpER1srqw+8PhDF69cLpeqYRjZBgYAeJ4Xx7FhGJTSWKWCjPGz3b/15ChN+yJnEELPKSRpICUXUsMY2rZ512BEKZVZpArT8O31f/D0WHfQtywrDH3Pc3iec87Ltra3btx/3F4LtVvrvfZ2DQ86w8Fm5pVD2XjP0/vXFpeDNKk0RoN+94E9O7rS0AwDGoia5TTILGr2BctV8trJc26lkcthoVJth+lIdTdAzJPS0C1Ns8Io1jQt4yzJg6DX05QwkJYpnjLsVSZ0xCGEnHNll4UQnU6nWpvUIE277UZtrJdFjGbRsOcQHfPUpAgKQIBUKr515fLawspkY/y9D4v//dLpZx6+P1J9JNTtO7ct3Yr6XQo0otHeYIiA0qFTGy2fvHEDM8Mg0WjF2OzRQaAiHhDEfu0f/+ohVDn4+CGOSpdvdh+YrSqcP/eDE6tbg/Eq9qOVhTaJY4e8cubSyPis32lGmeGDTjeOhih9372T0/be0yt5OVh2zGT20MNWcCUCiTOyG+GwMVrsD9pR4iqAg5hlLtmbVZQ7vHpt6d59h12NLmwvNNyibdoGnbi08u5H9o9sUZXFdh5uEMOxDJIhpIDBpQCAMKQMArCSVPdEBsJOc/XGwjnkPzBhMpIRVuROYuSltmqmWbndG8K4p2GS9/uP7BnZX3dtQPJiSUQBy/h7S5u3YqHI2JNPH3Ww2Y0yqulExxATAHWECIE5S3PHIRkzLxv8oXtTyNmOPVMIoWNHZg2nMej1TdOUWcQkKDYKkZ/0uy29YKk8ziQKm0s8DommY6oLmFNpbPkdDRtxGNiuk+Y/pOtoGYvJ1pWl/OVX37VtO82laaHMFwpBrWbwbsaEc3N1dSNyVKFoZQERSajZ7XZbU3LuqX01J755tQXDzlTB3c7zmcbomTtBpTRGFB0tjoTDLgNKYU2vjPgKAqarXNe9Kh0MsFkY9PqMpa6rEQxikfWGQz3JStR0CSSSWZbBEPU768CrM8R0iDKFqAEyAF2vUqwUnWpNWcV8c77d7dSdQj/Y0jEkCnAIJFQYQ12JOO1eX+0fOzxpQu/Pz95hIUZ66DCITRcwP2EJkFgoaGANKvCN535QdsZcjZZQjrPtXktYGEgpMXGzGA68buD3NR1NTtaU0GMQdLvR3PQ+DLc7XZ/SBqGYUICG/f52qzlem/BXLkFYIyA+fWm11tgzGZNLKwswGGSrr6+bidewzi/cmWyYt5eXqTn2/Ml5qpk7du7tbzVxlmZa8M7tq9O1mThlhUojCkJTA61+F2k68dx2QjcHMMDlDKq1ABZNT4mhpBBhYrvlnFGBeJzn02WPYTK2c0+lCFKRbw96BsvTgBk8N3AaZwHLc4RtoBLT1DnnrleI8swuGzInHNu7x0pVd+RWADlAGwxQCJSESRTblqNQTiFM0sTUjMGgX3CteqXsGH1KbIyolIBXyo5uUd3kWV5qVAZ+DJCYHJttbrkcA00bnYuE5SyVx8aLpcpms0UsY258wlp1MyZ27Nhx7folkuTHjh27du1aAaNWmj/5xBGv/5JT8EYse3272ZgqFovl+TtLhap9z72P8JdP0cSrlL2V0ydjznVMDAJsTXAl/CQnulYo1jqdQGlmIqmABNgqVVksBahWYKqCbtcktuSoUKpT04iHbQCAlIBzblkOISQFKk/CkXIp397UCQFAYQiE4BTikqkRHRK7pBQYBH4SBiLPwyRMmwIjOhyuzd+4Pjs6xvzQQohIAQmRUgAEJecQIQ1hiPHzL74zuePBteZ2g2odAd26jQRETo23u5pBHDzQ3bnWduBWankmoRpwLAQiepEgyTiDQZy6jruUdM584+WjUxPFonNoemR275RvuKbGTGSHeZlTXUmJhBD94VA3jCRqT1cozMOiUq+dXe6JzNY5tG1J9ZKhZI5Xlvp7D+x0qxOpMEamZgqVWaC55drE6MgMQujY0fsVqgFFM8Y3N7ZrjVEIoTJQ1w9vbaxN7X/f9a7aed+Tx59+3/s//blqY9wpW/WiYxq4Pjb74FNPHX308crsTq82Qm17feD3+8P1bpgpPU6j5Q1/q9fZ2hqapo6BSjOg67rr2XGchnHOFMjiSPA8kXCqYoG4B6AcRumVG9dH6tVea3N1ozWM0uFweOKN1y5cuuhHYZplg3673+mcfOvtJM2v37x17cb1MAxF5K8u3273Bx0/KZZLN+dvN7ud0Zlpt1CoN2qLSwtxnE7u3RfnTLessZH67Ts3rl+8OLdzj59me/bu37VrV5qmhw4dGpkcO7h/Xxgk+w8duu+hh4fDIOn37n3kvoX5W2HTf/jxx7c6a4cPHd23e27z0jlPsKJjawg1bP2BIzPdfqcbZH4QLSytAcN1ylVsF3NJZVbhcQGB8UxOxbCc0UqOLY4tP1dhJnMuwyjLhEAKKQV6/lBAIrj0O21Lx5ZBqGYIwYCSgKUoT2U0SAY9DJFBqWubBCLd1A8fOTY6NYFB5upU5RFRuamkRaiCSCjAuCAYAyEIUIgJgOuDQeJqdg51gMypGpB5W0JSL5mY9Q5NWOFgyzJpkjOBVScbLA38JZ9tBHKtHYexEBJvNXuGiVxdH/r5gdnRJx7aVXC0+5761OH7PuFL1I0LvYEEAJCVQTvPgEXRQKqOH0yNH+23ehnX/Dzc2txySzTww5Gp8ezOHUEBi32FLaxptbEqYvjOysWKh1laWsuDcrXWTC1FdUrA0dmJT336Y1//068zkDOFV7vt7Wzy9vbp5s3v2hhqFLzvwQcYmvV77apDRhzr+1/9X5ynfi5P+osffuJJiOjq6kLjvvua/RUU9uaX85/53AcEyHWzSnB/YnLWb18wAIeAEMMyS4Usbbp2lQA/YXKmUbmyoXbu2pMHwbvX1sfrIy995/kPPzu2e+eOfrcFIRwfH0/SQWt9wBV03IppmrZtI0gMAP/wa6/df9/cq6++8pGPfryggITI8QppmhXL9SAIkywm1OVRkGYxQXR7dfWlt1drBfP//qMvfvrHf4IwxngmFcc5ZAIEUTfnrq5rQImMZw1PvXPi0u0WfOzB9/yXP/iTj3/yU0Ck57/1jX0Nb5DhgHHfH1hAPPneTwy6A9OqHthtD/w4y6Bnk8U2s6vjQOMOBpOTIxud4bo/pperUTiQRA1THuVCAOyWSti0mR9puu4Ph3tmJ86cXK3oJnU0wQUEEmqWFAJLACFI0gQwaFTp2iAolk2AaJgJbLr+9tKta2crhgMSHwNsIoURYJzfBaswwSDGkgtN04axHqa9Qq2+nTYJrDy6y7xiTLfzwvGqzg3z5qVVqHLX0A3Dttyy6vkyRYOgk4RirlxuGMnoWHFxxf/7P/WR7fX+C6durs3f+OrK1c9+/oHvf+v3srSOJTIVIgQxDEg/jwnQRRBhszCAdt5qutCzbcxFykgtbi9amrO4FoxTmrIIMKqyABOEsCCazZRid8U3kFmWkUDqFgpKLI4VC3/03363WBhlPMOAHLvvOJOFMEgdGpVhBZoyU9EPTiwoHTx8cPzk+fONUimOwzgLRsbHPFPLo+TJp54cxHmhNqpY/4PPfjhKuhAjqgFDx1utLZyljiGyLOt0OmXPvevvoYBhuxoEA9sZQVC1trunm+zyl7/6xd/9j3cWbgrBlOCZVFyIu7QMTM1cIIipgpjo2uJqt6Pv/NXf+qNvf+l3Lly5PlItpyxP88w0HSWBlBJjjBEVLFEstYrWZqhdWMV3ll956Yv/9fz1W7unqncNgoVCgSVKMl/XaRi3LEdHCA7iuKfg85c63zr9x9/+/d98990rWbTy4K7RpLmVMdobJhICUyc572uGAQWP0zwIAlMzIUuSkKWZ3mPVggwQjG8tbMJyVSiKlUqgyNK84BYBZnGa6ZqOMa5W61axfO70qaJXQLli0JQgMwDDuoW5QFJCISGCeZ4vzN/GXlm3XK6aiOiFUnF4pa9hiIAigkukhORKKQgNITimlEMGJMMAx2kikZUnEewOd5abvcTWlfAst5Pk+ybtFb+5spUaVZTHzUCYUZLrrAUyq2DhCsgPVpPPf/y4aWTPv2s+//zzwiwanuPVSvMbmy9+O/jEQx9bakkAcqJCxvHN1VWCMpkpZWEyVaA32nJo+hYRGcD+YHq4vRIlgYscxMEQYhvbS63FUrWQcE0Inckg4VkqQGNs/Po53A98jamCiKCG/vTFszkffvCBEYhzCWCW4Gb35i//vc8NYl9JCVCUpOWc3kJSvHb61tMPPphGLccotuMhJjbLfZ4auWhNjhb/6juXP/jYfeV9hc//3B/83n/40DCPY00vAY8IGTEzgq4oVZIsLREYywQDYxBsYWVEcXDqjdPV2V0vffMlYu/6p//inxD96GMHYZoFhw/c8+1vfeuJJx7LYqZYSivk5RdePHToQHNjdX4Dff2Fs6Xi3E/+wi/PjOxycDpSKNqU3rx6ZcfcIV0jk+O7Fdw6c+b8nj17VpaWbnfN80vX6u7Mz/zs5zL38Oc/sne0Prp3966FWzcnxqfGJufGcztLljbWNvft2m3s2/PHLw83o16Z1P7hP/9n//wf/RO9vepMzL1zWhBPH69Cr7V23z0733r+naA33GjGEzv2hmGIMdYte35h9YXzbdsrcakUQJCQROQASAAsqZlFr8CSzLQdx6sUy8XFVntte7O1uTo3e3ByYgwKTnTHMvTWxlLB8yilURiXy2U/9OM4ybJ0dbsJhZBcvP89j/v91vrCTSChriREUIccYZrn3NCBARBQEikpJVBIKSAUyJUGo6T53373C+nqO7ToXPnLWzgpnFiyCD5w9J7KrStXCtSb3D0SdalGrLVbtz/58c8M+GDp1HMC6KY3fnX9By9euTlSnto5dU+QZVIrtYZZYWTUkj4S6NqVNa9gWcAkShIAlIRyx0R1obMhFWqliUHtMAy1gumnvSSNeCxMT+MSuoVinmcI6VzI6kjNWjKhgNt3torVmsgpIWi71c0k0uqjLDUGmeBQQUCba2sT5dXh1vqp8+9oFCMEHnn67yaZ1DFHVDtw8OCbr3yLQjQ6Urj/6DHbNvPED9PSn37hC5/84GcvX+t943/+8Uc/84nmRqTXRLfXd1i/mA6kVhqkfGtrMDtWMMokjJCUcqPd73GT06Juaq2uVAbNFcSwNjHd0K2Bpu2I4qBcLq2srHW2emlWDQch5/n2dmtpaVm5+6BmSMQLxRHLqflhsr26urLcLJXdM2fORFmyvt54887bhw/uSTLW6vRyUDc13RDQK4y0IFfCuHHrTrFQHvTjOLodC9hRh5u8SQgRYvuVU6d59QlHKxoKY6r9/h/9wX/5Jx/t9frTe/TBHaEpsm/OfvKhar8/unqr56Fma7tZLZVGR0dXu8Gzjz82PTvEIEOExrnImUy5SHP+2o3e4XuPX7p2nUvBWNYf9Lr9thSCxZlp2pTSMIwR4DxKN9KYatBfWxMiGxmtr20sKIAYY55XLBQKjuMopdrdDtL0JEng33wESyERQilXSCkKFAJAISWVQEBZQggIpFCf+5m/+6s//9k6d7bXO0bFfO3EaUsCnUqKPKB0NWTx1iYHCKboz7/1vKo3wND91S+8ppTi9g6rdqwTK3fQ8/NEDuiij3c7uqsRxdWhQ4f6gT/cigiABkUql2nU24RCcgYlQjzKrly5xqAyMMC6BQnKpZC57CSBrnEATaXwVms7zziUUBl0GPdymSsh3FI5510+bCGAqUKAIC5SJbiIBl5t2tEtijlAMuMCEsp4hiRz3QLFEMtMCoYQwo7tWfpwmJXHdx6+/8iXzrw1t+84pPlEfSY0HSGUjjHSLGFXhL5xa6lTr5UXt3rlQiWFxhKdy2VkGfb9Tzz65oklYuh5phA08zz7yEc/9OYr85o2PHr0iBDCJBtwQeq6+eRjH1xeXn1y9r3feeMWJZgAZiCSZeL++x48lbHdu/aNjNaURFGWvLi59tA9D9177GCv13vooYdeOLEiiR1Z0sZGniT333t/PxwESXzsvvuTaNgLkuubeN++A6apX712+aljD722GCgFc4PLFERKaw2yYrkxOnfg1tb5Eb1weGcDEzHI+DAjTrmIaFivF9vt1bpXksJf7fVqiClMATV7wxBhGSYMWdag23NsE1INIZgkCUBqrNbwyqXbNy5DIC3T3thcrdVqEFthHNg6dVxLiJxSur65tmfP7oJXHURZlmUAgJdff+1jn/jU3TKiEAIgmLJcUwQirADKeKYRIpUSQDEhMCVAilwoBdVWX/vKNy5qOul3U97so8wyi3qexUrIVhLiIEZ8OKQ2cTwocd5JQa5jOh6GMeZ5QQO16WmCqDdrvfri6ffcc/TmzYVciuHQ5wqnUumaRgAASAGutMnJMby8oThXiEIAuMqhZjAlYgpqlRpKAwlVmkUQZAcO7wWIAi50y2QKcpTMGmlv/eJd/ZWngz/79Z8H1f3/7b98ARCpCEqFBAhKoEOgI8UBhSljSAqACcEEEgwFEjzXMMozwQKhskyw4Ssn5j/60Xaxbl+b5zP1IOm0yY7d1NCHG+tMDSAjTxyZNBVP/c19Rw43N7ejmCO9tNrPDjooZmHJzinQDMpGRlWa5iLllLYhwpqmMcZ5LhCCGgVcMcOywiTdM1p0mF/W5O6qBiw7l6mQGeMpJoplPySM2raNME0zphvWTBEXlF+U6iNPHJ2VdarzqBfpGlVQQoyTPMs4y3MmJY8iv6IVJ0vMCKOyBX/yY0+cWcnq0/edPvXGWy/91c/+4i+uLaxdu/Nufere19541XLmdlRLcQr6kur1yTAIBwN2/sZ2rToSpjwBGQe641gY6YN4Ux9mQZIQrHTDAkBKKfKMcy4Jpptbq/XGBFNiaWVxMBh86H3Pbq/dXFtfShPxnsc+vGv37pd+8PzB/fczxoqeCwDAGv2hxf6HBimJdEoEZlJxkAIKGUJpJolGBYW5VBjBWEiASQ7IYh87jkl0AwPuFOmQsVJ5XELeG67yIaGU5IogKSyERNYTQsWZUEAhFY1VirdvX0LEJGthloszZ04TISRWXEl515iKFWE8kwACjNvdDgCIQgAUwkoqTASHSCNUMzoDv0a4ZFIIJSG4euV6qTxiYJplzPIK/iAYx3D11mUloWFoPPGpbOsO4kAIwQUQQZJ1BsNIbXOVE5VlmYrjGAomsYIIAgUJ1lguASYAICaERnQp4n4/y4WEOE1SUfJKNiWBwpqmGQasEYNYqMRzCji27GzQrIxMNza2eRTcVARCRDWtsz3/noceu3DmzX/1L/7+y68OdaxRHCrl6ZYVd7pCKCAkoYAxRilFCIpw+MQDx9fmz//yL/2dExealGKhmG5qTORxLBW6C16TWZYRQnRdD4OlH3nmoWT++txkdWL3hzS8bJp6EkUQAwhxnnFdM5VShFAhRGKJyZnae4+VqGw9cO+MGrX6QbC4vI6QoxkKofDwfYdLO/f+5Gcnzl5d3TE7nUyjKIrq9fq756/NTk799CfvSbxGdxittnxiulASzsDkjsG5KxekgoxlWc4ppYhoWZZlWVatVi1N37tn/8rmEsRA07TW5lah4G5sSsv0lCCjo3XLsre2mrqpt1otAADVNC4FhJAQQjABMmeCUwEwoYpzTEmYZ5qmQ0IRgFmeUQEIonkuchWutTbumTpSaIyjOA/SjsYLszv3JFk0XB90m1ES+gWoOBRDInKVSYUBABiBPEeORN0cMH/xv/6zX/rt3/ufqQRS4VRyLoRSimAci5xAJIDmyTyLOSBZN6JV3RSCGqWSlSoIOMw4N0wAkMGzZKpejYKOqGANLUXh+mQtzbNmResFeWRgwWE3iG0ECn/4vdU++zKHdiKFjRjR9TQyfBHmuaYANdw8GObSg2lIJI+4yJKUa1gIxjUdYoxSIDAsMpASlStAAYt4LoUmTWRRHSoJpWFinQCGOv5wbLyBEAjCFpQwVnRSR4YOr5+8tGt2Zs9eFz/+9C/+0r/7lX/480sr2436Pmp7ayurumXuPbB/ksF9Y3nuRw2vIIAafXL3rrVN+9nH/t2v//av/fr/Rw56H3j8g7BkJJvdYqUEiX3sgblDexIOOuPFOofyqQ8+dfPCNXfvjvO3uh+5JwWptmOmmiS25AG2Skd377y6NlKoBCYBTz31PkAQUJbHTs1V9/733/vOL/7KLw/zvg7p6Gg5HITRcFBxrBPf+/746H2lakl3zU6nYxlASl9TmJalv0WHty7BQhUIxhMMgBJKYkIsW+MpkAiHYV+zDQMXpEr7/b4JhRKQYKVgyiS17KKAiCVqdmpuOPA1KljGPbecpsiydKGVMFk8vuvg8s3rJqVJmiCQRAIySSnBmCUSWipnFgFccpbmQggMgERYikxBRAG1TLJv5z1nr5w+uv9+U3mdtbbAEFJSNUdQZQXSHUjTZRYhyQJIEANCCIUVFeDTT71vbvzM22chBD3DNSAuEMiDoag0xqIkNC0jSAekAI0sE1KCVnM4Nj6SR1LTbeHEnDpGGJvlhqVa41p3ta+wY5GCRa09aez3txYGW4uDGG53v3m4aGW24/du//6//+TX/uI1X1ApnIxLDUvPRI7mDvPNhz7+o1FGBONvvf68H12GwRoO0BjRAZKS5wDe3e+JkpwLwBiDUGmEQKAAhAihUqkkQKIhoBQEhAKF2+22oduVSkUppeuG7zOINY3ykYaVZM0DBw4wV0Uhdwz8H//t3zdU8QdnLz78xD2DWPeK5XTtyqByyA+7G3ga5WdjKRSEel7gbr2TBz/9i//86mLze3/65c995kduXUwMap/8kz975r0fuHkleXU9aseJXqvzQexWSVHTe/325Myu5944o5smzFtFgxqQrS4tQmPk1GB2dHJoqbRu6EF/3R2ZLdTGFwe9Ts+/fO2tnbseUAjVJyeo6UDTJI5zYMfkq98/PTU5t93MN5Y2PdclGl5YOBeZ9375+8u6awNtg0vJU+4WbCZ4EEdpGjs6NnQjiiFPckQAkCjNQ8c0IBFCCYOYelnHAAGES/VCsxVJhKGGBBQCAkTB1tZmNxjGSbS2vhSxZDgcuhoSAkGMhYJCCANCojjnHBM9BSJnadE0lMggxJlSAitP0DyPg7g9PTq5cP1lnqF+nM3tmqYaoEg5JbvZHTZkWnbMRKAoyRGFUR5ppnd8qurQ9TuXT5WC7K9+54sZhZmMwzR58NFHbqxsJFmaCGYMe6S2e3Jpq4UIXa7IMtaLGiqbblMmJrUzyuvhpQINLyz2ATWgXlY8L+L6vTUs/e0Q2EjR0E9OtJZz5c1y/dJbN3JmWBbmQZcqrEHJEiyzLBRxCKlAIgb5Y+//wCt/4c9Wioc/9JBtjxsWpEhqhHKgZVmOlGRCAYwk5wAozvNUMKiAqRtY4zzPmOBxmmEbeY5rGPb6+nqlUgRKAGBAiqNuUKnpEJm3b965vj3ChYK8/+CeALKo1YnWmtHJ+YHneXvLYwWBraR36uR6c3no1Qu6RjS+eObMuUceOm4XF5QSG5v5zfnVoWaLNKqZNRCJGZyJQXLx+vLEftuVlEk9kRxLz9CATPNEIJCVUSTtojlVRQNYqfh0/vZq886NuVqVQ7H69vz+448gzVwL3MV1Up/ZxBBNzU4hqFxa2Vxs3Td5+FOfmoVIA4Dv3HsQUpJk6T2PP/RbX3rhF37tX+gQK4oxQkiojGVMCiY4AnB5/spzL7yRJInlVrkApulinUrBAYKvvPJKd9BWUKeIUGKGSd73824vyiWEWE9Sbli2CayqrgEmp6amivVqa2NFJmGusAAYYpqkiabrAOsI6r0ohUaJaAVFkQKM6Bb3QylRhNDEzvELC6skjlN/laYqgejky99hishsKHgshVpUwPcMszjCo8DvbmENJkP80vq5l08yDGc+8lijiq5de60FOLEQufTO275QplnJkrBMCWGDjo0ENTQ9JSLq5T7rpvM/8guf/+bXT85UNsLuWo9DKXAi0LC/oRuWVh/sbZh+P7OA5RfEy+eX9h7Y56fA31odmZhxCtbJpUUFCVAUUarj3HVcCnIJIKFIU5pS5OnP/tSJb31r91S0tbU97HUmd86maQoMBBSCQFLd0HWd5xmCKhgMU5bfpcpKCESeY4xdr0RJK03F9kZHp5rg3NS9wFdMCMdxgJBJCt4+cb673fWq1XZrgwwP3r5zIkXOu19+p+5qi8Ngudq43c9LBtR10ytPzK+3ipqMk3z28BNrYW7kw81uHzYOvrVGIF9KhsCqNm6/s6ibVpsLOjZ5Z2u7UCmBG0HRq7RjfTrJAn/ARJ6gsYKp3dgOCkX79lb/wP2PXnzt6sjux9aSkOo2NvhG4uYROnT/YxT3K3j66Sce6QzYysLNdrdfLXphjjvba+VSI0nDcBDkBA/9uDo2EvrW288/V7C0fpb1U1Us1PM8LZRLmqYZGvnqn33VLUyFmahNjJbtou1Z3eGGiKJBkCJKdA1HcaabWi5knKuJqT0QbzGJV1aaszsOjIyNhoGfKaEfJoDL7c3+Qw8+Mez0DM0emZjoBR0dENt2iU4YY7bj+VE4GAwc282yTAE+HmWuW0AaEnm8tLY2u2dva9ncvnGCCsDbQ0mdyf0PpvH25vJtouFg0O/02P6H33/m7e/peUyxUWvMbrc207z3tde25+rhj332p8fq05srTZ/7J0+fS4YCQyZFThrJlbI5trDYU4ibZMazulp15LvPXRgmr7EFpynBXKGmg4GfRBbHJilRXvj+5a2DFUUxdzh7ZHelzfwr660JUBwpKVXiSpMAY0fXZc6IkiGLABQZYwSbGsQ8DZCB3vvJT/75l/5nw+sC2b91VXGqtppRwePSBFQFaRTnXv2nPvSTO3ccuXLurYeO7CI2RXkhhIthENUhTDOt7NlhvN3u9/fW9+dM2I5ORR6xNGO5TvnkRHlkaurSxetPvu/Da+uLe+47fmD/sT/63pXKnr11jV65cuWR9x+WUtq2bTqu/+67u/fuZYKvLs7P7ZjLlHz0eP3VN99x6mO79j5y9dLFw0ePb29v27btOM7a4ioddnbP7dQO6JvN1j0TuzyzsLm0lgaJZ9kj1bIUKYL0PfuLSRRN7dw3PTW1sbo+s2tGCBEMB4cO7FtevvbYPXPBwnZpZMLzGMsN/YHdxNFVYq5jp8/k2GhNM71YpF7BLtbqtSml6aOJicsQ4uHQ8zzGUwihZduaDgoFd8/ctB9tU0oUQRgQzLBu2CIilu0MEzhIugIpr2BMT08Xi8Usj5N0YOpUs1StUTcsA2EguMoYAMNtvz9IWc6VXF6ZNzRsFopx7Gvc6nbbQXzLNE2hxHCwGQWhEmaapwYiQ5gYBGytLetsaC6f3+mYZa8RDNjVsLl87c1cMExRylBFZgzuBqXKox//++fe+h+sCbprG1iBHDEEjKUuuPLlF80iODZ934ce2/1y/uJeLV4fqF3VmEwXR7hVd2ApcB0gvIpbv3rpRqWYmlptcmR68frlbT6s1SuKJfVque/3++1kVUShrJQdEwHbGJsuDtTOkt6ALOYGhSrJMyVJGuauqQGsBmFkFqBuaihOKKJIpxIiLtT7nn32zBsvYiCwHueD/PChYyfeeetbX/vfT+6bS9JA5eV++04Wzmk60mWUR73ErVBMHdsuUjfYXBSZ0jSt4BTa7ebEZGMYpUJA07DTLB768XYPN+z+3nGTJBsNi9Qr9s13T0BmXLp2g1KMKVlaWtF13bKsMFsemxjf3N7SDLNcrbc7Xc3Ue7xLEJQq7zRbU5MTeRqaOuVZPsgGCqbjE3XLpv2eXyuWh81OQkMIQavbImnBMYhOlITxsB/5/UHBxTwPHAe3NtcghBolVy6eb7eWP/DgvdsBv7V8tlx0wqC///49umYqWMZYgxivr28RoAEdsZzxLMziPgBaKwClUikIAl3X4ySyLCsMIxuQIAjm5+e73W65yvI852buOBaQSbFaYZx3wx7FWCnV6XTebTbL5aJp6t1mz7SMeqNx4eyZSsm9qyJ3i/XhoBcM+gpwTdcty+R5PBz2HMerN4rEUHtLs6+/+mqSZVJxz3Z27G2cv3xlZmpnBcJOe6vgOZubG3vcooBqGHUEz8YL7nLEMwGkgHma9UD1Rz/zsckdxQuXrrY2tnTubhMhIIASIhZBIRRW/RZLemd2T7uPzE78kx/RlreVH+4gX7+5LLR2EDCL2hBCqhKMsdy4hJ3G5I4DP3b0we3Flem9s5eudBYunHz84SO3by11h2ShDeLlIcEKwu6Pf+h9M1OzI4bxlW/+56N7SxLJT33is+994ol/86/+JVNpDHIgZZpnLsESEajhwVazUCxXRsaf/dGf/4sv/08RL3aGcefy+QJiD+7ftXLnhpBp1h/85GfuTbvNNGs+eWxnO+2p0dl0MARMBIN+qawPewNTR43aSLO97Uc+pNU497lkQElMzFYve+d2GyNLW9vYObvjq3/66qFj9715p1M301Kxura55Xne5OTkcHFJIdg5/e7ExESSsfb2+jNPvue1F1+6/9gDb7z5WmNk5NChPdevXJ3dMVUqli+cvzI5OQ2RWFhYOHz4cJ6nm6ub9x7e09zuUse6cPlyodQwjXs21xaHg870xGQSxavra5MT41sb65pB9+/bd+7M6SeefHxzda15Z/S//M5/d6vFT3/yY65TwWGAsQIW7PWDMXNsba3bqJfG6hO3b93SoK5T4hXcrXZwl4kJIbwrUCSECKEwJUQjuq7fjTAZTwZ+V/Go22sTSoXI0jSmGOmEEpF5lnH9xtVWa5sDWC5Xi4XSxmJaqTS63SYgZhiGuqGCMO10OpTSOPF37969fnYzF7xUcFmehGFIAbIsp9tt3Z6/0ouS7daWTPNyubi6ujJWrV/q94UCB8f1n/2ph71y7Rd/4zmMIUTYouYnPvPT3/3mH33yQ58aNFeAVh9C5UiokDQYTmwMEhKLlg6oZfELVy53xNJHzU/8o//0x//obz1AzMzhHNjUo1YKiGcbNjbdsD9kcffShbPFiYnm0ursromg18qFPH3mbJzJPdPjxw/vfPv0HaQYYhHQhoBgSivLG8lnPvIoPnn+PU883OptRkluWpofdw3X1DCOU2WQTKZ+yQHUlDxjTpF85LM/9YXf/e3URCDc+sg9U1ut5uzcXJKtbq+vvvvW7WCgBmH/TLrRzqOV+Y2n3/+R3nAZtwe1Gb1aH8vjQMnccbxSubrUznImCUVA4mKBTtapgZlpeM1m08k7B3ZOTdr8R46YKSz1mA2NolewhRDjM3NxmtiFsuM4ZapXalVA9bm9h0yvWB+fKJQrulOY23eoVqsqpQ4dP27bNlDULo7rum7i1LRLnSjcuXd/woW4drtcH2EQzu7em2WMZfnIZNksTkRRsOtAA6BMs539R49euTm/a+fhr33vzYMHdoZczc/PV8rF3uJWcbR28KFZACTVDdOwHcdpdXuFYhUhTXCY5PCuwcIwDCFEEme25QKFEKFxlo6NmuVy+e5sPhPKMMw8ziQArlvI+72C52CAoVJMcD8MRsfGGqP1bpB4tsfzDAKgFPWKhXa33xgZvXHrvJLY8zzGGNXttfW2bngl13Jsc2NlsVyv6ZLkGSem0e0mo9XpTPD3vu+Js+fOeYUywpo9Ng2k6vDo5O2tKL7CeAql0qVSlPoXTnzmfce2ErX74L6Fte2N7mpCACXCp6oojIcff+Ttc68XMQcStDc2BsD4/Odf/LVf+w8Yb5En3v+A5gAqMYPoa395xa6TZG1VL01NTflHJ6dOnb+Yb/dOP9eDys2SACto2bDT6799/hpBQCOpAZO101cOvm/XsVn7OaPgOpZMU2rmM7OjBa8EFceYIgUoVw5mqxdPDLcuv3hp/nM/94/G6vuziBNL/LN/+X/9zm/8ctEpXbiyToy82Y8OH3xgX7l1cIIOhtmzk4VBj+tlV27cyVVu2gWie8NB68b87SN7Jgyd2La9sLhujcxlLEAYsVwglH/s2WfjZAiUHkXR2dW8lVSa0fLf/bEjSSzeXAFdOjbsb919MjFMyzTNKIoUBBpFeRw9/szRW9duTu85cOjwEcuhBae8vdEkBJo2XF9fqddrE3Sy2+k7hSIEOM4HW4ubXqH01Hs/BAiFSM7s3jlM+51Ox6vX3PGRQb99+NDeSxevF1zn8IOP3rhxY/euY8214nvH4+ZQOZb20gvP756bePfSuYl7n6EGdjzHLThcCt2wW9ut0d3m869/44kP/C0h6F+rhpRp2pxLCIWmNAjh8vLiIAxsd1xKKTjCxJAAI00TEokc5CLXMEmzGEiwY/fepaU7hw8f+uq3vnfs2CPra4tJlrrViTffen56onHg8PHrd67ZujscDimljz7yZLfbTdPMcA2s5Ac/cOTCwhVHGTtm97x5/uzUzl35sPPMUw8PhtGRe+9f29jMBlGOJc7iIdFfuGAY1uHcuTVsblZMRFBfOXsm90+sXuwVDflPf/zT//vP/pPJSx969IE/ee2V93/8x8d3FMu7G2sXTzU3zV/95Z/8+V/5CWqO/Oqv/w6RDmltxf20ee/unTdub2llj/Lkgz95b7nf+NaVGy1+40iphKfqnkpGDz5mafW//N63xqZLOImUNX5x4dL7799JO34zJhuvXf+tr35bU3EeBUCal8/cmNw5meQNFl8HUuUsjdMkI2JSSG1230eq+4Zr10em7tWyCEEc8+FP/b1/+f0v/kelRVNj5alGtWz3Hrh3rx/jufKSMN1JHN0a6IcPVjohT0XmWiYSfP/cJKF6FKaY8ol6SaLUwAoqwAHWTbiyka9uLO7Yv/8rX/uL4/c8OYLx2voNaT/21a99cSGq7Hn42TfeerlWHsmTHLv03nvvPXHqxGh9vF6tvP7aK4898sA7b787ObcrAeL1H5x4//vee+bim+VSaefsjpMnT9/z8MNlr/TGqy/uO3BoevdcLw7XN5edYXt8evd6cyPy29Wau7a2sbq6qg5jU9defOX1Rn387VPvNGr1PGc3bt4emWzcmV969vD+73zrBz/x6QePPvy4JcATT9cN3lGcxNGQGFimoFzzmosbr1+4CvyBP2gCc0yjNMsYl+ju0DZCCCjmupUgHOqYAAQFFBjrPM8FEErIlOWAQpBLQxnUFgcnZt4+c+7Rh4+/dPHqsx/+EFIEaNquHTu2t7effv+H42HQSnyC9EEc1msVpcwLVy8HwfC+e59AaNhut985d87WtFDxi7dvPf74oz94/ntlUzt78szErv1rt9YLFdoOhpVimWGqmAQgu7168/gjH9m8+H3V2Y6Ve/XK94Zk1+KdrdtvDy0K4gQAsfTkB37qP//VN7/6Z79TLrm9bO/D73+vVVz/wre+XixOSJ8jgyYZQ0ePHZibPpDlOYvTwO91h71MGDEUSdyZG6vYlrYxGM4cOX7p6qXuxrsffP/TixstvaAbOlWShv3w4K7ZUms+573/8OUvAWI0m32N0n/1734LahDhgGpKQQkhdBzHxaUuv7MxWOKZbxTL2F/mIIUY6ZpjOsaD7/045FqzNb+yfOfy9YvvXjz3hS9+Y32ze/3mzbWt1re+/dKFC7e31zeXby/4wyGhQEqe55lt24SQu/TGu+czzmQQRMtL8xBZUaSwOb7du96o41LR8gMhpR4IjbOEUB1TQg1dA5YObZFA6hiaY2FTtxwPISK4RFISoABnPT9RxJTYUMgAxATUVNTmUEeaC6CRSSSQJrEpsd4LkpQBRI1BEA/DBBg2NGxBDWh4nTjtp5xjUwpUrYwIRXbs2pem0Z5dU2HiS56fOXk6TyESuO6WY5ZyBLFjvvrKouXu+Mu/+obrWgpKSCBEQiEBsGQye+H7X4v9poaA4bh3OTx/IxgnhGCMKaVaych0QLRGYdTdtW+fociBkfGtpVWLaFgopCAXUmC0vLqqJNANc+fOPVEQaJqaGB0/ePAI1UzNKtx730MHjxw8cmz/ocP7dkzPKgFylpi2yXnW7bYQhcMwqI03et1tG2VVHRoyKMo4XL40XXMcC45CscOzl6/cSodBlGT9MImV7EH3x37p14GiRJlRP7Dx0s2z37t84tvXT78u2lsRC/I804ggf/ylL8zO3lf0kvGxxs1Wz3Ot11+5ONho6ga8eSO5cafdt+wbN24/eN+9iN359pe+v4mqneYNXVUNHV85cXMq7pRr5O/8+q8la/0syxynwPl6joo/8/P/8OD0AakAxCRLMwikhvT7j+++9kd/nk0c/to7l93kz4CF/u2//Y+aXoJQNfbf+9GS9sIrf1AqTJcaaHS24N2yDNer6WpEtxhsRtwgvl8tlkoW1vVBsViP4ziOY9O20jSVHGmahgjWGceA1qtmdziUwcaOMq5gzwm6JRXoROQ5SoHJeFIqlDWKKwUvS2MCkp0zjQI2Krp5ZMfOcqE4PTk+iKOqY02N1EUSPbB3DgDQMPAjB/fUHKyT7D33HKxWq56mjKJVO7yXEOKn/tHZif1jzmTJ9JBde+iI53mUsocP72L9jSM7xwyd1gvEmK6wJLYNG0Lsuq5jAw2ybievVqa3Vjcdoz/NE6gSA0Z+a6tRgv7G/Gz14PqwzwQHHMZx6BVLQkmhpKZpnfXOnpkDp85cgi4pjEiEUMZyjRKIkBCCUiKEMIiXsmHeuonvWHk6JWr1Pts8efLN0ZlpZNFus5umOTUtw7beeuMtkacHayObi7fW1hfGx6jhFPWGeeb0O5/78c90+5vf+e63kxQ98cSzt65e91xTQCgV395c3XP0gQuXbkIuZeRbOZFSKMzGsDGOtodxLGQKMn/gc6HbVFJFbAGBhDJhmWHXfvSxh6/MX1++uaHnfrTaK0ihK3T/sSM/uL1wcNehq1cukEGUXr5xUYKAQkSd+mx1uhfmA9KVKTu7sKWgk3P4Kz/79/7Tf/33bwVr//hnP/lnr21tRlLivuSUCf2FM1cnDuz/tFE0yMA280q5gLDGRJoklThnUBKILKByjNXtE185f/MHn3nP8RcuLxHJBSRanv7mv/mVYqn8sz/3f0EI7LHZ9zz7+VRKgbR+wKFjpIxnkkVAM4teebSIs8Lw3EZMckllkqRCAF3XAQCapjGINQ1zKSDiQLIo2LgwH+2LBmUzmyhPQMBd1/3OS6cPHjiQ9IxWszc7PkkQKBW8NAuG3eaeuelokKkkGa9WIc+PHdh3fWGxvbm2c3oyT6KSjg3DYH53ouIpFiGQjleKBMuos0UQahTdYDgcNjtlixY13F1bdhyHaJQKjjNe0XHWbdqAe4Yx2FzVMV6fv+oQsrHU2lzaeGTfodZ2j+p2mMJOTHKf+YycP3XhwUM7k5RQGjzy0OGLt1KCTYL1jPEoziFKgiBkudI0/pkf+dlBv/v0R3+C2OqP/+R/6YmpUZwqFmepjiAhWAiR+BkmjPvNzz7x7HduF66trGz4Wxqh75w6pYjaPzHnr3VuXgyTQeBqlEH67umTFCoMVRh2GVdgWhKYt7ZWl+ZvD8MASDNPAkuHpmnbToEq0Ol0Bv1urVDw+xHwyjGLhGRJns5OzSTx9mIzggpbpuezfMCHiFsCU6xRKYSBUZbEb719ajts6VoxzYGAUEGQSnzyxq2MwbPnzxOCSaoIYH1FSK3oPHr/feNU+/6rpzTN0LnWA+TAnsOzOyZe/+5f8Tz7qb/9U3V7bbaAA1DPxXZKSrg6AQqkw61//au/9fDBff/6V/7O9u0LAtHZ2RmQT6V83cJoZGQCi42h39+LLmX79/TEwtOzzo1mJ3eKGrCIAVPma5ggyDb8bHT6yLX5Pz13ZXXG233h6vVDtUoOUF4oLq8v31jQinhqbWPjSKHAucgztnv3vo31O1wKx3Mh1IRIqEZlPEBQ7do1/pXzWSnOnto367iDVNKjez/+299cfuBA/fTSbeWMaIAE/a4JESAGAgBKMwVJr9tCSlopJgqLNOx1OhoCGIFMEp6pNGcEY4Sx4AoyAAAnRBv2hgXHlcRZ2b7tlCqep1FkBDnhHNjUwnkqpEYgJLqeJEJBw4+Ssaod9wYappt3rr/z5jAMNd1zRuYOHmHHbq+RZl8P+Mh8T0sztaNOiyP39i+f/+l/+OO3bnds29Z1SzcdJqRmmEIIt15yq3au5a32QEEppRQK0v9TPSpdmUuwq3YUF/1X3jr5/g9/fu2vrh6amEHUjPNwa3utXvJ83zc14CJzs9nkghMskzijxOeSDMN+lnZeeuHbGiYQEohQs7kZhQOBqUEFhUSmEU/TfqszPjoTAWCILIg6nlcbJPmnP/vBha++Md4Y0yU7vnPyz1963qiPcKD7vq/yLIPEtvTQKNOYIisd9DohUxgLCLReyFypa4SwXJKqa0BoY0zTjG3ePK+NT3/m73zSJiMC6e9cur64cT29tvzP3mdfWbfW3pm3HyGHD9bPvO1vp+D4jhEK2KAzKM/t0LimiPXcd/77vgP3wzylMDW0AeFAo4QGQQdHDQwF8hAbwqyIDWOoB5awujDVuIE1HVOUx6JqWVE8fPToo68sbz5woNBLSnumsDIzwrV9Bwold+PQPc8cjm7R4cVuyIlBttZuQKRDgjbbsWGTIAk0YSBFYoFeevG5O4uFRoqD3Q+e/cEljGgfLb47jx8vZBuD/e3tKwjgWrHcYXESppZr6utKCTAIk1LBDNMgT+ntlY05CEU61GU0K+7kTBiOl0uBga0QePNGZ+8DD15/59TInsPLOdN0TyTBoD3MEygA1wBIEwE1QDiLBRAyD6KEMZYlEc+zgucZhvHMYweLpWorpCVvxIXD//F7v/vYU5/bTgkc5j62+il1XMtPwy995Qu1kT3f/e639+49QOxRl8Wep0WxqRUsv510h8HXv/bF3aNTF27Mlxsj2E4L1ORcsFxBnTFBOVTDsF0VdDnexnRv1gydims3Rv/WTz3z7dcWe9cXO70V1ywnUTLw+0XHHUYx0qlAugIiZtDVPSXzPNFJwVQ55LJHIcqFEESXadbf3mKAe16hoNO0VDE0FAzDGMHET8b0BIUZUtPtrc6BMf3Mm0v/9ufuWekcBtzdAnTl5IkRkCJgsBiheCNKYhKxKgQRzAy9mOVqd6mSEKBDu1yQpFAo3b0TpIPh1Tvrt7eDT9+7Y6PL5uaOrra6Obc6ra0vP3dr2kwAQMvbvK6aSZjYmL59/uwHn3zilbdPzuwcYypRGO3dNW1Q4OoaU8KCGkZAEgQ1pMMUytQf9jTI40ELF0ewBJplqzjLc24hgSDQdZhliUfEjfmVQbfX7KTrK4E4MHnx9DtPPfSE320e/eij/U6HZ7FmmBs3Vg4fO4JlmmRMSTjsDw3boZQihAiiGMr7Dx8811E12n/n5Nlnju/BWI/o2NlkOFWXlWzC6Pq6ZiAmTMtyRysZSz3DDIIwHwxHjEqtXkkTGKw5c7Krh/nSncVLkGsaNU0Zx4kpUaBgg9DFU++OmTJt356aODjTcF9dB7YUDc2uFuuRSgk215ZXCAQ8jt1iYV+1USwUkigSkiGiC6QahdK+vXtu3FjJs5Y3Uw47ZojJIMoKTAmkcQQ9mNmQTNbG6vXRZjdtMVBKhg3ZytOwyEQ5M6mMR2XtZ559Wkb5e+556MXXv0nTqILcdsYzLoVkUOIk7KZJnOkOyZgDw5HSoLt5tYbz5sb6yu0zhPOqaU9MzMSR3+2alu36QZfzHCGCEMKCVx3oqXDclqmmHnns8a9+7zuAsV6nmbC8bpdKbkEgCVS+vHwlzqwk8F3LiIEN7CJC/h//wS/9+RsniG5tbLU1w41TtrC2XtCLi/2QscgoGCOGsRiRmcP3RXHv1uUzkWB75+YKbvnareXpqR23tjcYgzMzO4kCSEipIJgcmRidfPDVd8986UsvJSm37D9jUh8pjGGPTT323one/Le+fT1q8y/805/+/uollgMNRNffvTRVrF2/fj3pNi/OL/3OpwyTYqgEIBjbBmcsSSMHOFiBXnvdqo0FfjQ2s98q1MHF04bnGDLlTBEZrZz+VpYlnPNUJTv2HHKtTGjCLOBm0I0gCFmEDZxjlaWi4tq8Bx576AHGEw1bw6jDU7FjsgFsKgXSNU0hJZliuYKWyXF6av7OfXvGvJIz8AMRpWdud4PSTqiZGcamoQ1y1o23JBChaQdhPMgzJw0dVSmPVs2Sd2Df4MG9uzg8aHMoRYoUkoKeuNOKgT5aIrpRP/Xqa+MHnqnv3vXf/tNvzt7zVOYhNeq1M67bBkWmUytGsb+1vjy5d2d9ZtwyzDohmk5kJpMsAlXj/FuvFN2xQzsmhXH4X//2h//vb99ySnWJjYSD1YEwCKrUq8fuO3Tq/M1nf/QfvHvzDl8711v4fs/BUBYF4AKjO5JBiCFjGeF7dOwk0uLwN/75v/n8v/qPPaPBsZ2j1NO0FPEZI/3cL3zHx3rr6984PF5ZPR/+yHtmPcP82ss3KUS6aZTLVbdY3Oqut7c2pIjHHQ2CIFx7c2GdVZVc951Xv9V65tkPvfy97x86sF8oTqUOOIMaqjXKvTcWM4S2EtYZNJWCBsqjXnDq1dcE1MKcZIIywQgxGJdD0Yt6PRurfhCu9ROsmefPvRgQRxESZilfXivu1qUEpuNqZtEueZdXukRKiTEhhN5/9Ogbp95GaSwEoRARFtse5cNejPwEHjL0/P2PHJJuqiSP84wKJ+cSYSGU4DmGyBHAw1RmkodxapW84XAopVQ4x0ZR5RJB2cr1xUH+9vKiXhgA4kiZY4zzjKdpqKsBy6NkEDGiNgfK0L3nnz/XjPU3ooE1Md5nZgq0TNCEqzxPhRB5EpqW1ukOxsfHJZdJ6kugDMMUQpq2FcXZ7mP3xScvNfbMBQvD8V0PVidqY9A9xJufuq+x+tbK3K73tbrrMxNTNxbnD+7bf+nqJaLAA8d3ffe55zshPzY+defOHaEbm3EOqKQaVEVHKT2VOE30wmrSXtvI9fqd7ZPH3zMLylY36v74P/jH126tvnXhdL/f2L17v6ZbhJjlKsOJcdTzbi4sAccrlbFBpYs1PwpFFi+cnX/kfR8drRZvXbs+cRB89flTm9saKetJkgAAdIhTpFVqlofh7qnR//6Hf3DPg89mMhv2Nzt9dHYYelkObC3JJIFoul64s72pmPH8l39jxkm2O+tf+PVf/of//vdyWPIZp5xkOHf0sKlmtGzz0N6dtSlTI5plmSnntxdu5ws9oUuRimq1quu6bdv76iMP7i2ur3QDv52GgSFlL7JrY0c8isqWcfn8JUWx7RYmR0c4yzu3b5laQWBk27VsoD0+oR0pi4ePTg67UFHtcz/5+RE9MIDLs1UdAa4QSxKKiQIIadQ2sEYlTtJMMc0wds1OZEmsEMyyJIwSiMjq6i0CAMaYZln2/Itvq2TFtA2NKaREnmlmatQmDicqXlkxHxmDH/z7xyxqr1y9rSk9wwbVFELQMsuGTop7Hu93ZA5uebqpqEYQ0/WKVAMGUAwJ5dkffeP7mgZ21It2Y9die93SZAKZUJmpU2TWzHLBdEpFhy/zoT/MeNa7trztlWffvJ7uG5s51RTCrp1ewr5fLVA+Nc6yweZwo18bdReX1gEfjo6OcoHTqMeRG0jkatl2ZM+UGwsR/NvPfjQ0zHfevv7EQ4/gaPtb57jstDakyhDU0iQiZgYhS7PEb200JrIsGzFsnnbefOt0icLCLNtM7DlLS3t9Kq3f/U//qxXJkI4agPkXL2pcRh+YIsPB269c+7Ef+2DDYnONmoGMpDPsLd02MbVs2y/KijC7m70VZ1WNMcPSmQDUyM7+4M//5MqKKUYG6aWZiWM/ed8Dy50OMWlvbW2iPpI05ws7yqBHAZ47s7y449BHPzehtePUtacfevr+t68x27/jFj1O8tHRMQHJxx7d//aFbeKoQqkojSzZGCQD8Wuf/+lOP/zaC28vtZtr+uwjzzw0MQb3l6Kr22k7c7bXWv04s1zv+N4iyXW3WLqy1J6oo0zoGx0qZXrP8X2P3O9XbTJImS76X7lGyhDmovS3f/xvcxFGSfv5E1dW15css0JguuvoPRffvbi9vvSBkcaDD+xJeuJ/nmjG0lwBedm5Wdq7ZwgyplegyAHA2xF3dQytimZQoiHc2ZrywCCSqZR35luIJADkOVPRcPvJJx/aWLpGDlhxlvWpSQmRWJpnlWNCTTIuMHzifR+9drM72hhBHC+vZv1Xb7FANkpYSABhKiQCCLpOqeQaBGPbhlhxCAFSKk6ZZnLJgcxzx8McO1ksDcuNGN/c3ILEivNcSwEEBoeGiOIX3l4sWNKFgT/cqs5ajZJddItVtWF7eO3muT2lfZpAUYQMWllv3VpQm2XIx0Z3+jAdm50CSHElkxxklAiC414z9eyBtF9fv/yRgw+cOH3yhXf7jz32ZDv233r37Zm9xzbvXMW9sQSwqandnfnvLYsujwdh6LPb706TYbK19OrXb01VpymJdVqJBomviSCWsztK/+o3f+nijcXf/R/fR7TiaqM5DF986eTTz37y07/wC7dvnfur7z4/OV7npsnZ8MF775saGfvmt/+flv7639K7PtuHP3r58rW2+97jkrGMxD2BEAIJECAkuJUibbG29OZuaWkfSnsXWopDgKBx90kmk3HXPbPdbflal3/s+YHvX/F+na/3eR7HE81l1rluW75gJwiMQwbD5r5Hf1ENazlkJGO9HLo4lVuqh//6rf+SKP2+970X9KyE8YG77zAXp5YWppafffipc+cWynF29ZY9DS2NhKulWmy9aFsGJbjWcIUoe7Gq1zsvDF+kCRAEQcr4//I7576dwB/7yL3P7z9eO3EJhWkpc382/kAITQtALLzIR7pZqdQLnS1tHY7vl8OYppSK6lUZy/m6/9S+l1YqjS9++v3Tw+eOXzi3/vr3GZ5v27oXSMHl/4czL3QhDrf1dqRJx86NcP9Zdw5GwMrOrNS2btrxxCN/spO2lci8fGS8wWkCxw4FuzcPNWNVSJpu3U8le9f2mcdPnBMyKrO4HFCTmBMXjzkYvPzYbynCZMjwpCY1DSDAHWUcW4g9IBGATKiKH61Zv/nihcPNlbKm+EuvvZiyO9/1tjUSYyKYIkZLV18q3Tpx/C2r0bAsR8MYYmIZhFFNoQjqtuSx77suTV159VXnz52qR1JgaiAYQs2MfKTbiiZzGTyy5Fvllf/6hwcf+/0jF4dPvPvuey4d8o0saSzWi2OLp/lycb765kHrb7/4pWdPvs5722eqK3vPrcRY0+vlwErp1Ngw0OoJwmJvS1/2jcnGYk1sz+V/vf/5NogXXDZVebW6OL+0PNcQwWdu2/bdX70cajq99e6VqeHB9laxNJaHvg0zfX3rJ+YX77rm6khP7X3xN8tzmblTx3d87kOZlAZQDFW4bcPQLbfdeOz4iqYlsrYRLy8eOHzGWb19qVRKOfn60nIDAc7DxcmJsOkJoDDRF7ItrruYTto135w48mohni209mFfE9qiC0A1VJoK4yC6994b4qWxmamJam2hPiZ3rd1YjUq18vRga0u5OH34lem+ne9K4wY0EinbNykBSuqmBhBJph0FkG7buo0AQAAASmkYAglgLGLlV2++6sqDb77Ym+wNFJdSAiARBgLKcr359ItPFZc8R9PmiyuJfDLyXIqTKAyZUgDjJqchI4ErYkGMqLGhuyXmUlMgCLkQOgJY000d0ER92uZ4a3deYjm7pEYbYT2GmbQJfA/Q9rfd844Dhw9v3ny9SLdpmU5Rm06n0+sHOyfnFnf25984PrJp97Xb1jvbd2yZvnz+dy++xnjhho2rq6JxeXomhUgIEVl2QSKRagRxgJLpsAY4Z9AkCAmg3DhWnt/bN4Q7Bkb2nQuSLQCkLpW5QJqGSSHTDhRdWZjPZDLtbanLoyMIDHkxIrxeYokCrNX0njis9BXoXEgri+dS0fJIiV+/pmN+adQHuRtX2/tHxpaa4p5371ysLVtKHzl64Xizc6Y5rv3h10O9g4/NqA/u2lQ/dL5cLN21a+ePT8787Hs/WNvR+ubF5VU2Uen85KK/KZGbBIm0okFN1oq17lxqqJDYe2F2+MJFpOmpkHR2Z6oRg4JwX+aSrUq5XRlaMIFLHH7s6Wact+zkVVftXNcKcU57+fXJKJMEfb0wRgmlTYxPZ2uj//x/v5fWPK6n4xB7SytrPvi1rXdchUhAIj0xP9fanv7Nv/6DjWRGTwTQQgAgQP04JpRCAFpbCkePHmduKcbmwLrW9Ts3vve6d733899sy6T++IsvnTkGXz556q6rdvzkdw+vXd/95vP71+zcc+D1uUqcDs01DZq5vDS+qk9Ds9VU2mkZfeTKKze5poNxKUbEBFgELjRo0/NXKrVACKqQ2/RUWv1Z3gdipCDBAsugWEDR0uxMKpNBCFiWtVyJJsaLB468waH14H0P/Onxx1yfVGcqSCoT1JCjUDrxkc9/5b53v82yNYo5xYFQLNuWX9FtPWEJITCybr/15pdfffKa7TuFqAEjf16qlWJjsTrC9HQhHXvekuPI4uKkZdUcQxYXLuvmoFdZaPpBYWDNky8foKY9OnzZyg88ceDE88eC+vJyggjFcykbbdtc+N2rE67AChGTcCQlX1paYCyiHAmCfBZJKZWQSkhT14I4Cpio+cwTNtYcTcGIcQWQG0vHsuulYmV2NPDrly6c/MbXv3Lu/NJTz7y+caBnenF+MGXOzE/3JZ0thSSsrLSFxTU5EQY8H6+s62oHcZyMGo1SZV1/X+nckdrYOKyVVi4dHzl7TioYxPiFC5MdOiD1WWFSYOlJB3oSm4ZmatJsbcFYhxA6pgOApIYR+83FZpPaukHB4QsLhu4EQl5YXLDNrDRxImlIoIZnF0Ai7eQGf/niMZwfRBp9+dwkhaFlJS/Ms8fPR4+9Hi9EQ07XlUvzpZlibfvb3lFUgCTTFdVppQaWKukYZoc2dImwaOjUxLrP/bmZyT/89me6TmMC6wTFMIqBUJRISCHWFdbm6yXFVRhoY+fGgrn51kJrBWYrgLoo1Wi0KCOBzZSGYyjYy28ca+3fsvets0EULDYXH3n9+Fg9BslErIUurxmALVfQk8++UWLW5OxsLYhDDnRie0EYRMzzQy5EvdloNpt/dphIKXlYRjDQTBA1i7l8ux9pjUaj0aw3mjVN006cPhF6deXX82YzDOYr9eVm06s3655XLM3MXTpzfs+Wa4e6VteLXhgIXUKmtz13YLxYrrmBH3KXg8j3Gh/76P1T4xeRDs6eP+J5U0SXl4ZnU7Y/OXx0afrS3PSlpfGDo6eO8XpxYvjNseOvJHipo2DNz44ZhkFoYjkEQCMzs6NhpR65ITUS1SgSbnml7K/vbfMbVc+tNGt1sgIN7FgcESusyKTlYC9ijBMkEIA0A8JgdrmcKuSlltHcqtRiJC3mVV2q7+kq7FzdgZ1s2mkLLjxTOfSiRaK1A0OLVe32HZu25dnJcllJcM2GzJNnLq3rEJQn+MhSZ96WmY7o8uXWTMpQE970VNsVWEcqit0Nq9aJU8OYy4apW4Zt10pXfOCWF2aPJhpmy+a+wiE3ZEulkJq6VolsJSVKJcthOxZCWsmZWGBqjiyWm8zL5VoOnh5tetww7HNj1a6u7kajfnm5mUpAt+nNC0RpbJrJ5WaQyw0Uco65ep2DYIwIB1wSvVEFz//uR509Lbfe/6Hw1EuL5OrW1vjiC48emp7a0p/vvXLL6Pgo9pYyWseabXNPilWT85d9GHdAtiy4aaTbWnMIyNVdbWlAyoFWxzKtqd7B1U888vvxy4fb2v7CUBk30E7P1JXUhNFSk3YMretuukUsTAyzUT/QEgIvVKe33zB4ftZaEmsPj+1Ndq++6a4duWxXMHV64/atR587FYUwZWYaYZDRlK73U7aAQPLc2HxCS/7wF3/40F0fI5rDlP+lz//dV77w8flS4DjR9kE95DbifgjpNVduyudzjKA33jj611/8zJ8eP6ZhoiNiogblBPnNBz6wM4kTm7tuwMpqNNHq/o62jTch3Tt8eO/YmVNJklAsghxi1bTCrXPzJ9uocXjEvu+d9z3x+E8IgFBZlhaWFy5ApCsZtWqAT13s2NA9PrdMIwKcvBW73YW89EON5D3Gc7kCpoDLmCD9Ty++wQXIUkgUVFKQ0VJoGIZkfgBELo5ErGOKCUIyjpsL5xRX7sp8W35dyS1LoEQsXddXSkmu9r75p7ff+tGJg29dva43nUfTxw+m8smufB34CClsOzaUKyhsXJ6YK0fm0QV89xUdNlrUjXQhZzpxqVEKCOMsaNj5VZjPmLpJ07ZjGABpLudQJ8rUfvX4awQk6kD/+Z9eUTw9FwbzvuvkBpuVegonpIirQTPdWpAxC+r1lEEgNahSGOkx55pmIqjZdlJJrOsWC2NNMwFkFJAw9BP5lhqTQoj9Bw+uXrvDRCiK4+OnzyUy6VNH9iKATUr++NTe9w5Crzlv9fcnWlbRJnUs27bjDU6lMfZyx213tyYzZ8tqdrJqYdBVKMwWS+VGvRpFWGozDfMz9+4shNZoOV430MmlKjdiqVjNDe562x2CAyAVwXZB02Npv++DD/z7f/7Ho//7rzdcf6WucYJx05VElyy68+CIfcstf5EwjYd/+7XNWzeuymjtfYN/+5Ubci2tSEZEoxRLGHgf/cg7I45VuHRxYWrdwI56ZdLI9Sug7FTyrdPnB9Zt6OrKnzs788zYJWKYuc4er+FNzTaWau6N26+ixLYcU8UAEZrLtqql2XTGFDLkEFBVj6IAE4NGs1ocnDp8sri8oAssJGAIEYNBRkWzXmvGmg+729Y8/vRThOomQpLHggEzNCDgCBm6Xrdp/KnbNr5xOjPnCoG0JALHhkf7V3UnbKtNVMx0HjD0rnv7K42VZmwVyxyjwPfqMAhILYhJJDBEDSl9r44ElrGQXGAFzh/cC7mUQBVJJDEDAmCoQURNEzd8KQAUll1cPNe3u+Oh5567uXdQ6flkIhAuWpdJRJXxHQN5PZSER/ffuE0LSwbw7905lKRS1RfevrV3Q69xu7CJaSVS2kfvunlq/pLnNTUAAomqIcsmzGK56Tf8ttZMk9JK1QPKJ0bGSiUcYPFcwUo4IiSN2DM1i/Ew0i2iGbHX0DUHKGpZBtVNXbNWioucS8t0/Kara2bMmGEYGMNquawbtkKYYNSezT70s58+8MH7F0fG6ra2vdB9cWpaNBtd/T1dBfeKJKr71UxH+662AQFOIYqbpO+Xb1W+e6dNQDprtcT8TUw0P/QyCVWquAYhkVEodO92q83ewVZV931EoNI0K7u4OBELeMX6NZqmidBXejDUlQoBwIgSoDSNaygEGCnAElknihagakN6TWJcY35vwl4ZP28WksPTkzA1lsxmgfCkVLpJiRCh34BYb21pX6hHHaQlncVViQwAuRTHzl9O5twTp0/AwCOJrKh5C3NHPYmAUdhx9a2prL68XG80GqaWUkJIonMuT10+pwasASt75uCTLCacI5KyGSdXdGwe7B96+fA5jHUYlQBigENm20d++Y/f+MUL1QuVe97z7icfe8iiupNGC8sit/uaLFgaO312a38eu0wEvqZgwTaL9UaxVu1w9LQmKnEph8DU8nTYDL/0iU8zUj96rnZqJNCt+PhLT//r/3kvgTKWXEGEMhJJpCRmQBKKMRIKMIgBAopLFoWNOlNeLOLZBdZWaKOR8BuJRx//U1Kwl87PV2Tr3vlkI642cIGxjKieW92GU41KKq/lC47RnCWwTkVXZzSNYieda93YSiqNSo8VdvQkEOB2VB5Mac1K09Y1ASwGOIEE22YC2YVCdywWDNiCoWRRjEJlpVE9RqaRDGTUls7RWEJMqK5LHhYKhWatGcdxJpPiUgGoHMeybbtcKWoa8QMXKBmHASbQNHWfakEMZy5e0puBrePnn3pED6q4XupaszZMYr+50hx2X12ulJvepbJ85/V76tWwlHBXAZlXtCXyG7GwWg2px740W00HCOkoYUHNVMhDqD3rqIhPLtSUYWoGBYrcc997Lpw57nlhyqRQCgaVpQNsJcI4NhD6wPvfwwCjRAKFoAZA3KCUYmKaxPZiCaS254p1xy6OUNzS1tvyzJuvff4vPv/iM7/54Ic+ObM835ovHHvl2d171h88Mw2VwXL5b/3PTz795a88+rNf9La2LTa9oLRkGjp0NCkDjMH77/vooy8fGtiwbbm41J3MhyGx7QyLQN0Punqy56vxlk1XlhUdTPbecc+Dly8vCcbuvn33xQuX68m1I/PVj39oXVhZaLXQwy+8EgvXyiWuveMvb/vYvVg33zp2UFOUAoBihVG8oT6fVhM3Xnvt4dFXfdf89h/2I+rEQkBCNYCwiEZGRvLp9Hi9AfMtFdi87S//lUUroaDK6pYw5FL7xDdfJAwQjKECMKKSKEIlRIBBiASSfy7tKMSNBOnMtXqqFrgsk0shLALfwwaFWKVbrjlTi3V7sJFYX+bFoxXMUecQmgmozOQN2w6WQ1X3YeAa23pTuXTazGUXFxejULR2t3PoxpxB6tAkSBjZxWqIFNB1DQmoIaiA0ABZKtWzDmzU4nLgdvV2CTdeYWWqUK1cEUBJzDEA9cg3sE6Q8n0PY2iYOuOxZti+7+oGDcKmaWou8wFABEMAFEEYKBHHseM4pBaPnjlVJwgo1mbSD9x1a8Ke/eItX/zk577dbILTvnSAlKhw6ejxkNqVAduNS+dKlrrqE6cuhtbsqB9f2ZLOrusqXL+28+mLs71mHnPZgdE7btkY1SvKM+aX5+MAEMM3DQSBwgAKIIRSEiAArLNj5XUD7RlbualkpISOKFK4WVtJ2GklLQSxYCVNM5GEPowi4tRxmiVSCyv1MFJe3fdXloJySVhmXFruSpClyYuD/Vc0iLrqbR9ThHZ1dLGIVBq1BAUCcJ9TC3Kp6Oyit/nK3aMTMxh6XqDPF9lA/9qVlVKwsmyYNrLManEp29fuI+ADke1uLyQdaiorY894tUsjp7/6qQ+rxeBnv39kuVrr6Ejuf/PwF26+7Q/Dy10Dq88MX1jV1n39ro1RvX7wwvFP3pxeqaX/5fHDsQ6TVg6xWkSggFCTQgrJiY4gbc236a327JLe0rNzOWwV5fkk9YRfQxiHnCgZwyvau/5MM6OIaAoopSIMEUJSAFspLk1Gqus3bVxaYE6LP31J9AwkANTPDE8nW9rtTCrjZEREzWwulcyEXgAhZIyp4lkZNhKZdLlctAwj6SQAAF+8Ohe5NZmGkCALKG7kAHUAc80o4KrmYoOJtn9/ZBTboOJDR4sR6BTUJUqXUioolRI8FrquGzr1A0Yw9CEkLCRYA4YNBTcga0RKApW3NQH0WEAKFJMMAp1SWanMWwaCMI0hDJlPke5KrmU2G1NH/ajIbOuOTQOf+sTdT752/Ibr7M7MVRcvn5u+UHz8sf2iJxfNTUeUxgjJOLrt2nVgzW3Krz//5MstWqlhdalqJWWQ3iSRVnoyMLnXtCD+3JffHzF7sYwr8yfzg30JoSFQfO6JxzasvbrQZv7Zhexk09O+3mXznETFysLWdT2tWaCgfMd9//bs777JsZRcPzgmEXCiUFD3+IXx8+fPlGwdg0R+zUAPYe5KvdiWyKYziXp5BNaj3LZdp8YkSWUAKx589k8WSf7tN//hJ//y1f6OvqpML9RqrFrMZhJmIbfMdEwtoehgnz4+XzOQk8/277oydfL06c1rux778Y+bTIUxBpStS6RcFlKNEzO9UHWRj7BaMfRkHWhLAuAAr2vL72ppn+7O7TtyPlzx3nH7VWkba5aKub67Pf3Ys/8+s9DKsSewaUUgIkZsRlogY5KmnN5129aZ2dPD81528Eqd4vGarwEwdvqtJuNbBzdfGDlqxIogTIUQGFMBZKiggkSXSAmBgAghlTBCJOGFzKTE0dIaXOnI52fmK6lEJmzWg6Dq0VJ7a1+94jdri9Vy8c+SHoxalJFZqfpCtVcDtRCJdNL5+n/8um/VugcfvO3I7ES4svjsK48AvWAi/q5brusfSj30+zeX6pVM+01Qmqmk5gd1AiIMMYeQQCm4gjQhuQuUcmPAJJAEWUjGxCY6DbwmpppPLQw9TEE5lrYFuRQEm0oZBIOYx7rTBgni3OeQKKhRqomAbVvX4tXZznfc9+2fPPfez9xE06lfPn16Q9v6/K6VT/3Lo596h3nr/bsefn2kzq2engGN0872gUyf/doLTyldb2stlEvS4Kh7aH2xVpkJ4ht3bB4/eNoB7Jprtv70f347Xyl/9nNfOLjvYOm1Vz73uY/++Id/FKEkyek3Ti8GQVAsFr/zb//yw//79Uym83Of/qCgTrXZaM3ZCtBsywCAEksgFRZSYxIxJB7bf/Di2WMDyVVZbDXOHzx+6ZBt44CbCxIlEs700uwN2zelZKzHblCsvrX3eQ4g46zS8Kej9lJZW71r0+SxvSz2g+VAL1WqlCSsFCFEtvfu33/gpts+uOzOfe+7/20qdebNJOBmbDoabFCYKqzZPXXyDSVR5AcWYkhLMZYPQqcRNwwUGTC16/obxpYaQPH2pHHrnXfIuFxx3Ycf36eF4aa/+aRu9b/jxivyZLZ70wZH02N37siCzDGoxZdqiesrfm3Rl68PT9uztRSVoecWCPr8u+7ae+zYiUsnsMLXrU2SMHABgLGEACAumYIAmJqUMo7DFE5zVS0khhhjqaSjA7ht8yrIYqIUVBJKnDC0fKHN0dILlRKEQsN2wkorhS3LKFcrjp0Kw1AKroQsl6qW1bPAkm+dmef5Vo6V5gxwlA4jf3zaG1i3LlW4YqZ+ikKhkEX8ZQpwNWrmGKOGiakRh77OYwCgYkDTCBIegI4FAWIehMQCgmIgAUNYQiaITm0MAhSYQOiGHgjhMc/kEVaYCdVoNqBwkW6aHI7ufTodlF559I9XJDPf++YPU8m8oSd/+vBcz6HpPB04d6IC9RXNdTZevRMS5CJ8sto8/fihDlkrSdGVb81ZpoyDVgM3EYemcez0hWa1RJB49oXnTL1AsP7d//xWV7K3XKwe2vv60kylr2fg7IlTATUcx4mUzoGeMm2qZxqx/N//+vEv/unTQGEOpEZtoThBWDc0AKRSEGmkmsrPKkDDJjXZHQ9+7pHfP64CtrZD5wFuRNFte1ZPLU7varl2+JG9Vd9XkPb19rTl2g4cPtk9tDmRT41OjbmlZsZJhjLyhEIsYt7KZz/38ThuTG7soHFRYHTN1l2tpuExNT41fWG53FC6zlX92BGuUCwJgLIY6rofP/iOG6ZHZuKqV6w1rrr7wQijN8fGu1NgZHxubOJXBIYAiggkiIJ/9d3/SUFj1epM3FF49sz4xnQKp/k//PS5B269/T3XbZw8Ndm+aujsE6P9RtLMDEQcZkz29isLBizdvHXVyYXljNP5mTsz5AP33pVO5wSHxWV3fHks2+rcun4PUBhjfe/ZM2s2WGePNRr+hIYCyPQ1q9KLi1XHArfesuPQiXKlNNm7c1Ntua7ZJqEwnSo0GjXDxF0t2ZgFuoZa2xyv4UaBtmPrjrGnRm/Z0RvE9fPHTwA37E6mvEaltSV37aq2ueP79Xpt0EQorC8T7dO78oeGq8/NNrcnwj1bV//ohdOmjt6xJVeG2b3nZrbk4Ob1HT9++ZiZbL2mn0540XzZb7MSeRIcm69Smt3WJ2LMhmt125CbvVAkOQAAUH1JREFUO1pfOV/TpL9jQ5eJ4rfOLztIrW6zEtmW4xOloazW37PxjZPzFDU3d6zy4ua3/vWLVT038/wvbxjAO275XHn+zO6Fhbq1Opi/PD15dqC7pZRcXzvwamvGXFqYTZh2kUNy6tSUX7KcgkI6kypGqMR1h3uKYtdHru5R0zl3fEKzTTtrsTBbqTQsE5tG8ut/903GcTqq/uJ736MRHj893FHYmcppOnOVUgDyenWaghaoZCyxt39hT3odrzVBpclrc1/664/+8Wffm2/Guc4tm3Zcc/VQsXvbls/fc1cWFur1ShilF8bq5YW5XPcWhWwZeBPnztgAeo0oQEhJxH3+b//4RSlm61XvA3ftkjgxOVOMFnzMgvZEZnDPui2uv/foJdjWffrocZcHEhrQd1f1dg2u6s135pK51KDn9GQHjgezTw9XG7Ojo8sKQyqBYshRPLB5EEBopDuYxAcvjGxK3MAzdkMTWbnYl0+XZxYOHtDnS+BDn/rE7598zqhjmDI3X3WLApItvlJzI4GJBuDqbTt+NzpNLIM4ps5i0JJveX7fs+655d3br4SALC+WXn355VPn61du+KDvA4IVFDKZ1NymA6tL5cpCS+tq01S6kcBaBUYRNXTNIFGlOTM+s6rvPcmW9oWZicsT5z/84McWZstQS9x/6y4aL/KEtePuq8fOj1YjuyXlIK4KerWlw+jvWzc1Vz0/hWajIK2YETeYiK/ftsFdHBeMY4Ncva7w9IkVwThqLgXzFU1FhMN1LYbycGklEG65NS+jRhW3ZfvazCa2jk+UJYHzk5frjXRSF41KafOONS8eu5w1jPZ8yswawSWPC9bZll+o+9BQkVpas3HVf/3o343IfXsyNeVNPDZSyfClWzr7f3Ly+wV38bbB9uKJU6/5Hb0Q61C5SjelCIxcRyG3PC8V0G3bdsOAS4HMDAtKCTOhx6LuuUA3V+qR1qqdnx5OIcc2rVqlms1ma3EgNUNyL2XQfGvf5OXx9dvXpVLOP/2fr0E0w73GL37+k+4rPpwrDCCIkoW2sbnjlo5xhibyq/508NRpweKJ2dWpTTPjK/e+6+r7333rtx64xzZzR0YnaqA/lyvMrjTePLcETUiwPjiwxkqQ8ZGLKWTfc/u9TcwiLhRv7j189t679kRxfVW3AdPttm5UVvznn3/0ttvv/MjOtc+vBIXWnqA6wSKQTzr/5zMPjo8uNTgfWSz97PXxnW2LUc+2U6dPpST1OdUUlwBpNOEK6QCPpFs1CuMw4CLUyxWsRSERP/ndG80YnR9bPHW+mcBAcD49epni5Lae1lMHH8l1dKjliaxVCM2GErLmNYvTy+gPT77SBFVloVxLPydtykhwbhpE8chWiU6uGUISDXMWAMvUbMMMo4hKw4+AW58QVlazycJcvVJcmp8Y2ffqozNj57jnHjyy78LpF+uVccEDAAIm3YbfKPSgTLvTm0GpIMhiA0dBqxP152RXm2WlulpS+u6Nfavac10mrAbQ1xObM4kVqUqKtrRmujL2/NyiiPwWByqkPKWyukql5MT8vLdSSjrUMAyJcHsuldNhHIQJisJgAVj2mtUdCFSBEjJmUxdOQqkHCvUN9F8YHveYUJxZQG9W5xTDWTuBAlY+O7o8PEezqsXuGr58IlyYXwyHvbE57ho4lfZilDNN30iu+MTQk0VOsOdNB4Fm5MOYLxTLVDNLAUtZxHHyRT/QiR5KTcXShwILO0lahdA13QbUijjV9FzSTDEG04UcsfV1V17T2+rEYTLTeiFsuM2YtbWvfvat3wnIKNIf+PyXHKMdW6l60YRIzp87kudw27rVOzYM5An6q6/9dxR1vHns0P/748sHj5WaAQ0juGEobZmAKGVrgOuYR4l6xGY8WNKMABpEuUxSL2xnoVBIxAB84z9+5YpkBNVMQ3JEYx13ppPAMJMwnyTIl3LLFYk3zk82PHl6rihbEk+fXzl5doqztb0b3tu//h4fIy61/nU7NKwYNgfTiDBfj8osCManp46ffvM3P/3ZwnKo+QFTTaTbPk7UmBRa6/YrrwqDoKMlXV2YHlq7lWZSuUTXvddtX0VKqhkQW7POn7qwaeMWaXoIC53T3/zusY9+9FaJYz8IjBCdHj5rJRQGMeZCYPjK0Yu9fZ1LpQrS0kA0p0YvBfFi5DdNaieTGcdxsun2kdFhSFh71+C2gXU//dEvCwmrXqs9icUzX73eqywR32XJzgvjM5P1hoGIiOuJfP7YkQlFoY5RUyT/WGw2uGFg9cLr84SaXKpFET8uM0Ntxk2rsKY0r+a/c1PPilfNpFrWdxSAhs4cPZNr63xn5+pLE+PKcIgiW1vzvR1tjfLF737pg8169dSRfVs3b1ypD6/a0DN1YfS2PWs6hucSKTl8/vwdVw7t3LVj/vzRpVppfV4jkoflZZvptwzm21EMQrajXevOZoBXv+Omm46/crkacj2TcojuVQIpVLnhQkJbe/rLtWojipVmIK8c+9JMpcMw1hMpKfm1e24YGb7UqNUtyw4wACDoTptJG63US4m+ruL8pYCDgNRmZoN0pvO//+uhv/zkvX988czp4csVil87+dqaoW6no/uKHS1XXLNlcnbsqWd/k3D9hqEZeiGRykRJ7eKhqdiLHn4rumL1xr/7x8/++Lcv3dTJixOHdei4KOPFkmqmW3VjKXjgTk9d1m0nbtGFhEJqQiIsBaGp3s6hJ55+6Zrt62+5/mbFEQe+H8ZTC3Np09KwE3Ox762xTFfXVLXRrmLZKN51ywdOnj/8xQc6t29Wv35qf1trQheNaOmNHcmwFqh/v2/XQ3/6w6e/9J7vPLx/4szs97606eqTI612nUeWgRCElYiaX/7Sv1639bYA1DEkCFEdkEf2HtiQ7xOIu5LVWTwyXyOVMFiuhx2BL5szCMRbNmzFNH/qwohJnY7Owvata5lnnxm+cN21V54+fHCuVF+/fc/C/HgUyiSs6pAbXPa1pnOZVaaZeWLvk5jwhksUiBRkugFrFS+Xzru1RQtDRfSR4cvrNq8bXQh/8MS+GkxQgDBEFIGP3bg74P2XZyaL0RJwIyRshBEBkdIdBqguPWrocy5cuVBqMVhnV3tSJwODq9pFXSJeq9TmFitXbNl1OQ523HJHX2wxJBTju9fWH/ntwx/c0T5++Wx7a6azq2VqccVEIptAg9uvOHzs8Jb1V4zMT6zbtKFy/OzEheMpyxwcGJosHWrN5KViGgG0XE52pWOG+9qwAfy+3m5Fo9bWVgkb0rbLpXIynQoDETJOAF5cLgIoEUKU0qC5vH3bVW9cGskkc0tLC62thdOnDniel8tkWdSkEGPgs8pEY77hmLRUn5KOWQ5LlxbnDhw8/cVPfRZZ617Yf+zEWLkcspV6Y3bsiYsj9kqDkxo/eumwjVhPfhWn0DNz4zAFJkq5TCFsVjN25+ar7gmVPz872W+49aY3foHHLkB2rIRkHHhRiInOAYhiP2Ack26s9DgMFARSKIOzO2/cBZQgkLenTRm5TIOFQishYwBAxdGq/tVvnnVrLpwZ3v+56zZNJ9T4xPm7btnaQXgwPnXV4M2jg/qAf9LGgWPYnYWImuMf/+SNwJ9Mi9rdt23M6vM1CVlVhdy3tfrmdfbITOPKm985ceky1i0c1jiT0EZFtx60ColkDGQEmGNqcE22HSGEiWISUapLGPUNbbo0NnndnjUHD1zu69S6e1aPzYU3Xbfp9Vf22Tof2HzdyaOHfF9S1FyzekOmpatUrbCmxIZzbvgSV1UEjRiYAHhAKEfP6lRdtWvH6PDI/btSMPZ+8/IbUu8QEikQIawgIFJFH3zvu5MSEi372z8+J3DgMpEkmIuYUuTHMmVpLAwU1iUgACOiIqAE0fCtm9YTLerpW7X/xOlEIqFI+vDY5Ps/8zeUGUqJsbGRwweP3di2BKCtYR9ChfTU5KWJQk7DWBE9GYpmWs8L6TOJMcCmpVXrDdugGsReHCaSGciIJPVqSRo2IkqzHOH65A8XGopTYOumk1EscswUF4FpO9Vaw/ObCKFyuWyRiPliRcq8lQFQMhZjpMVxnEomDaqVanVIZRa4WUf3ms2KTjiXsQpsXV+/9q6vfurKv/nmf5cXJni21VKh16z1dLaY2WBpHiyvcMzkg5s3vzx7buPqa2ZYMmxGBgHr1wwWF4v5QmJmenjN6o3Hnv21CUTIku+756oqdk5dnpVabmq5ggAt1WZQrG9e2+PkCtet0gNe9WrtycwM1U0uyKn9b+VyBdNKACaUUgCgCFk/eOIQAkpXYve1twhZvXXHLUcvnVqnF3/9+qGsje/ZuZpTkkD8jNexavc1/oFfZjQrYZDr73nfwad/PNSebAD85HPnt3R1iHz0xT9OO4BjkxLetFmk60bP4Nsr7uWevtWLp/Y33XAmDCUjEjOiMAAIAMQBJPffe4tCQkJucAdiGXH88qEzLTadGa23OXG9WcAzcUNNHzhaLhdryjBHT49PLBQH27oMpAsPHzhyqaezYFuWK0Ij1dLS0dLd2SNia2H5MiVWe8fmbD6dtenSYvnZ80sL87MKtRgKYhARpDViBaDUac42rYALqrH3fOK+R379RxItRdKAIlLIElAGjGNkSqhz4UMFY8FNAkQonzx6DnDI9Pm2ts5Lp8785fvvzM23L82NEmwYmcEYwkjw3x0e03R8y8b1oi119rXj883mx3ffVJuYefX4RMa21wyKbT0DP3vmxdYkufPe968xxP/94SO9rebH7r1zZHL5laOHs2lr59XXpFPqmWdPXrN719CgT4erJRbEy8paqAsaThJIAmClk5pGPDdOZtLJdF6WK04ShKEo1RfzRiatJRRMhvE04mxwy3V0ZD/0otjIyDa7zlzfjzzMkxrknAvV+J+fPBnGGd25pl4bcXW/FSTTCXn2cj2R60zw8d09rTV2uaVjywsHTt501wca2lJxaqG95fqOFuOPT76Y1hOXL82UABNV8tHP39vdK1OxtrG/e7pY/tXZU2Zbn03a03q5Fpebp4fp0Ltc3MgXFpUUv/vD7xOpzkJ7b1HRfS+dzhfWJ1oGsKxTJ7X5il1AeW15G/OVWr340v5Htu7YffTispXIX7k6+7s3RhPplJQyY62cP/5a3k4aWtW2VfdM+fFLLDMR+BH20psWphbZSp6gCVMGLci67EZ3Wr1LqTDdDqrDNa80X1wqdg/kNZSYnSsxpgBEgEIFlSYxIYgqiLkCEoaGqWVTmXfcsHvJjR2Ld7TsXqlxQ9DzC6hSqv7FX34WgmJpRS/FnmXRlkwiaaVSEUBQ4xxgpA2sKRw8+tzqtWuffPQFJupbt+yAYS2s+aOTpYWpS5REEBGMNEUhwigMZcI0hGBS8J//9kmoBKXUbTST1NJ1MxaKQCilREjjjAGIOecYQ9syPU9KTEQsFVTEpFCnlVq5u6MllPz86MiK33jXu27L6+jhV59Ys+oqr9mcWynOVw0Y1QpOoRJr584VGw2BnLalekPNVjHOhWbnxeVFuv9sh4NCmLy0FJ6f9fYfG/FhojJfk2cn4nB5tsieeunAJz9xm1CXEcK6TgMR6gjYCjMiG7U6xBhJGRGo63oRxAaHsdLact061t7+jnftvHLD6888c/rExdXtHRcPBbZDSnHdXQh5jDE1cgbTMXLrbPjyxfrSaDq/5rvf/t6BY0//6mf/vtje1BpEKzsbQDi05iq37s6Mrcxo04Zmikg1Su5Ve673/IiSJJQoX8isXr9mdn5+w8aeZCbvewtHjp66/oYNZXfmq994PyyvTMzXC3q7h5MKQ4GrSEk/sh7+/avVqD+YbpijFxlvcEIb7kKmOyMg8qWbbHUcaUyMnK3MT+k6DVl8+fKlgYHBwC8dO+kl8+tXqjMJW59bKpYDHvgNjARYkr+sPbl/XqPyYtJM10NvdU924vzZFqSts5w5wVuT+fu++uXZubHji03g4WQGrl63xVe8Wl1ZvWZjrVadX+FQBkgEiAAyOTkDIKw3G7097aLR4Esr6wY2/vCJ/V/58nU//uFjEa//9Ue+8NajYzdcs+YnP/6F1tK4/7YHNIkhVlwEkKZsA0ngAUAowuPnDxeIduSlF7sTGKJkfXo0mBiVggEeUSUBtgkxINB1CgQPKIKYx5JFCTPd4FDDGMZxxjSogYHKNMMViInlWHEAksmE33QxxjoQUcMlQIWxryOCINLtZKVchhCWY//CNOu94gZTac89/8rywrN6CswXSzd/6FMbWnse/cUP/KU4jFLIsvzlOtZCg2aRKWql6rHGhZ6O/pmIz1yecgsZXXBltb74zEt6uoD0HPPU4nIkRdRaGKhWq/uPjcHAa7NMqWjEmQatcsM3Uw4C2E4WllaWk6mWKPYM28iZhsnsFk1u2Lzp1Mk3pi6+Nny++Nm/+ed9p08EjLzrxhufeP7Rtd0Dk5cv2Smnpy9/6uzlPVtvPDNyxnQSGmQq75kZjAHf5ibWtQ94PbUJSTdv3XN5dFJfv5OfOMNDPDFfKy0Xd16TSPd0TI+PGalCE6ROXprJ9K1ZVNZ85Pzjv/6vaaQYzV44VXzi0R8DhaQFUOxvuub+rBzv6dbrTfj4o8986dMfyDjpZnN53/mZt86O+16FkHB65FDFVxBChEGrZtfKizuu2PqBBx74my9/QUVBcX6BwkymY/umW6565InHsYa4JqHkC3MXs4X8mlXoMx+77gat92//7pus6XVp0dBAL3LlyvxigiSqgK0zO48vLJaqS9yg3IJ3rBIvna8t1Uk2mcVBONCenyhXBlqSwltcqodkcPUqCYFlOkEQlCsNz62NLzcRgXUXx4q6MVjywYqyEvkODGdqJW1ubhbxZtiUxYZYWVxiXPN4GTFBdd3k0FJIBR5UTClBicYgs4gGlJRQsiBAJgYIRNXQ0KFOTKXpAClEqCFjwGMERKyInUwEQatlxVD4YRQTYkVRQDUY8VgpQSnRDWoLiaBe9KNc26o7337P6OilVNcq6BRwORgZm37bnR9+7ZWDCAcQ0fHxEy/88N/f9s63aXDLqC/C+uKVqUa37S765PihQ2vX9nQPrB0+fXHntVcYcTXT30/96hzLd6FKqqP/P379golBS8IRWAT1oLe7++KlS2nbWb96oL2jf/zcJNft186fJAyaRKo4GFy1TnGAGlz5YkNnR2vPxoITJDPpJx75SSbZf81td002ljOre6tPrOx99qk2qNcmR3NIxrXK2JlSkhjlqakUhpl8e32h+JuP30c1+75128emR2ZKiZ5rPtA4+vzecxMaAqhSJImWL336w43I7+9+29z0JEa11avtpelUz/qrW1ty//ytj23Z8f7plQCYbYLoL7+8L2WkERAObkMUMj5x8dgLaR1NTarSipc0SU9yJUsumAP2+GIQhWHOyeoS8pC1WWkkuYSgXlpGELpcMay7QprU4spJF1Z1DvS74Upbe0+hkDPxBhB7eMGer9Un69P/+A//z4dBi7RbdAex0J1dYZVm34Y1tUZoMbx1/WY7YpXJERo2NqDabddtOVlcdjHJ5vuBFwkDpFN1QuL12zeYsx68cdOQaTlhxLHymTCpaVUrfoKGEpqeX0O6vWbjNebWLWdfGOYzb0YosKgJVJOCpGAKayIOoxigBNGFEBy5BDpISYgUBBgAAAkFMdcJZgSiMAIaNhJ2KCBnvm04QQwYjyi2AFYsFgJATcgb7711YaFr7vzjSLgQCaJZInQ1AphEWAEIFYQQ6oUGox3rrsx1dTQWZ+YXxzt710hi21QWq83+zsHFYonYWoeTmRgfSSXznb2ZZNU/69XrMFlANXthcmd3lUhJQLAAW1qovRTwq9q8Y4uVHW36U5Whxvk358txlOgMqmWKNWYEhGdiLrQsTjk9taVJoifffs97TZr43WMPX7tt96WTbwUKdPUUpAdSSbjQqG1bM7AQiImJ86lkpjZVrIjsjj1DLTnnpecOBtWppE3imGKIDAw5QIBx3YBCKA5wPfCTEtyxLhckOoyuVQ1YSyY2TI4fZLFV8yMjUfBCViyOl8YvcllsL3QpzyNUYaELIe01O5yh1YeefmHT5rXzC3XcmIg5S2oZrDyEDWJEQWhbwg11IuKmYyWjsMlCjmQNEQyUNPQMZ8iFUsMglrqZ6WtWliIW61BoqaQP9OtuvOGJx/8QuvD993xKT9td2fx8af7k6fPtPX0J25gvrXzzg1ff84lPatJsMfGv/vOrX/u3f5+fq4WG4cVeSlmRoTMMk64qam62XL/j3TcefPPRBz/8nu2rEv/2h5OLiw4yM/3tQ1Uq9j33REbX69yPJIHrW9qAVEAhBcGfN6kUCQGx6aTjZoxguHrj+pGZpVzPlpWRUQ0sSaBMRYFtMg8RySiQBqZlGBoKCKBMCDmQDDEsCUAUQMyQQoRIFmBgBATBSAhMZYgEUJJSBFmC5hX1dAKTZqpZnRscHJybmyOiGSETcXntztuPnHgBSB0ibkjIdWgZuWZE8+t2IwCxaURh4DXrXX39PEKUYikwJ77fLBMd22ZeKRQ1GulcivrMtbTQ5RiKJCq9v6/6q6eODm1a21T2lit3sepsorn08xeOfuXDN/38udmpZl2vehETkSYcs6XhrSiKEYAWIjUX9m1Ys23XdfvffOu9t9/2vd/98K5bbmwb6nvkZ88ov6gryVUAJA4AEyJWCnEEdu/Y/uD7P/GDh743fmlWAwElDmJNAQEAREEpFXWo54VCBySIYbaQL7S0rcuJk6UVappBaOpG2o+xk9cdzxRO+cS+yc41g+7M+aXy5aSeZECmLQdJRgihOBlaLRKoWm3MUlRSk0Vx0rAx0TjRPKXr9XlkmAaMl9yGlFIpZWDFAcIShZDbumEDEkkOZaSIxgEMufBChuPkVbfffObicZPqiBqtHf2WmWQwzrVlY9e7MHyx4gmTOjFr/sUD7/31L3+9bvUqw1/5u49fLc1g5CL75ne+BcJ0BTg6LgvNZgpyZHKAOlu6Zex7bn2gbwhyQ2lJacGWjv5mrbw0N5tCZU9BNxBwc6FdCSAlUJD9mTCNIYUQSgkIIRQKgKBCekwojH0TqyYkNjawZck4AoJDxSIBkKYzwQHUMZdScYYA5lJCpQNNSIkpIbphQVKLo/ZMgVskbTi2k0zpDreY7WQuDY80akUeegIwSiljLIGBL5EFINDSXjhPUALi0OYUJa3Il5v3vH2hwQ2dZLIFjODU+ES+Nd/e3ukHDZ3o9aZ/4exhPwyu2n1zo9EMA9nd09qZyI7Uqo5jERgPH3mez57wZRYZCjIBdAexJpaiAtNJsbR7z21X3XR1DuuA6s2w+NIze0UsvCgMPF+G8dZb3ltiam6pVFsZeeBtd/zkN4/89Pt/d/v9X9iw7sqVSy8l04UqUxaCgUIIWSByOeYEKQm8B+77wGOPnShGrueXiESYWlKJTNaq1WoY5IBYiZSKQ7R9bc+7br4qp+b/dGDk2NmLut22dsOVgNgaivoKg4v10ZXTRa2vZctQ/tkXX6bUCyJma46Km7HShHICUVY80ZEtCDaPdMdt1FozehDGimp6usUMoFnoHr+0j0PCOccYKwEEklgBBSUiBIRxez7pNWsSEYAQE1JIKKRn5ntWlnwKOERIKJDK5DZuuWql6q4eWiuYUQtmI2/uzEj9Y/e988XnX9pxzTWv/P7Hv/3uxwkLWOTWeTnErV/6+v+LYiuOpZASOxbjMtUx1NbW5vuenU5tWLeVQeK7ZRHjiHE9bZSnRqaK460pRGIg/2xWVAJjjKWU1NAQQjyKYiqFAFApQiUSfqQCCTORYFgKr1KTkSAYGhqmBBkKJey0kzAINrAGCtm2rKVJ3UhkHUMoAPWI2rYKLk9MDHX3Pfzqvuv3bBc+WQzVa/teeM/Ntw/1r3/8qT90tFAUYcV4ynYWivWKO9+VTCvgc+HqlALkM04bQZi29Qa0OnuzpcVZCZFtmgOrhpJWJoxDCHUfqFhqF8ZnvvLlr1fKruZkCTYNS9WrnkbtiUvHxi+eIrxBSFZIA8ZMk5SHCgC74TaJxjnJ4HQaiLAE4v/+2a8/8aFbV2/dePHMsfvf926NUgDAb56/0KTJ9vb2XDIdEyaB+8fvf3vb2h01pYxc/3XX7t7/8rPLy/NcBz7zHN6iQCRN3dWyr796LFZqyy1XTl6+fPHSwo1X3fmOO+/95jf/ZuOmrcqJjrxyuaVn25atG5LRkhfP5cBKOpEVwmQxMoxUEHpSjy8unR9fqd17+01NsdyzKv/pwa++cviiImTXlp0//o9PvP/BT3f3b2i68ZuHXvjQe2/61pf/vs2iqwaHLk6OAABE2DTcSm9+y67r33764is21ZRSUkoJdUiA4BFSKIhiHZOlasNy0g23ySVTQkRBGKooakzdeMNt2/q6Xnj2GcHC2vKlAy9OX3XD2/zGIk20Z/POH555HeoJoqoGdXltzq8tYaiMJD5y4NWpebRcJN/47PvPzTsepEzyldripZFLK41Ff65OKa3VV9YMDdRZNLdQ7M8VdDsrFAO4kEo1Tp89TiCPIUQKSCwVhhhKKaOAI9rwY0gUlgQhhLEypC2xBk2Sg1aSmFYu3dnZC+I4qWu2Y5KEAQOfABlC7ciZwwMdacTlqeniyVce/+Q971EK/eDnP3rgPbcI7ksV204y9GsoclaqVarpUTOIMJQQXX/99UZk/Fm4e3p0ZnKOvee2OxbmF9vac9OTld6BNAKJnz7+5Ec/+5ETU3hxdkYKjok2NjllGzqWQCDgR1IBkXWIRaQGAx6U5uZm+rvzGKva4uz5mZXy3ISlQ4ook0yDElLCGYRQKQUo4kZYkmaitrRsb+opKWIkO4JQxChRjYIIAcaZhIArKZSyESMoFDIdE2aaNq8FiCbveP/nsWgmW0d27bnyt4/v1/Wrdu7pEsxP5DrfurBYDn07Tc8cfBMFUX9rFoTl44d+fvsNhddf+UMyV2hN2Lm4Hl061Lu+rzubwbWKYWM7k0maSdtAzYXpXFgayGQ3rtq1c/3A5/7tf19Wzd1X3V2tzjPAZ2Yq9UY1YeELZ/dV3JnjJ8+szJeXG4GuR2vXd9dOjSkgpFQJgk4vX7j1QU0IIZAghDDGtl95xbFTJ4iECgAEMJGov6/vzPBl06QSgGuvuWpldo6a6dePHd23f++JA8gBiGCINMMAALPaW3vfTLW2IWpQpAFW+8WPvpvNt/zpjXhg97s//b8vPrCjUmpWf/v0HCGrP/fpwZcvXYKU6KYeBO742CUpY08oIAQF+LHpkZvuuntmaqJfE/1DAwdOnGpWakwEgFNy956rFSUTM7ODvTmEEMbY1uxGKJc9YRumhq3pxfn2VZ1ahA4ePX7VtWtw5HAvBob+yNMPf+S97zWFr2DiB4/88pN33ilC6hHtxOjY7i1bMdIio922C15DEEwAyASMSGmEIRifmLp6Y7sK8Vfe9fbPfOuQp6qRpwGIO9q7kNQRQlLKngjNLh1f29+NTGAY9LaNO4SqJniiq601lzRNAuxc1kmlOdH7+/uB4DyeR4Qm7UIyEOdPP7utz3nmN98FihRLi4sHqGkFeakZOJVFQSaZazaVREoqKCEFROqYx2GYSqW2dbceHlu0vaV9v//pxnffp3FBwhjGxLZTIAIEE4Eh1c2WXDanx6XF/Qn1ARVgI5WvjE9qqfTkysLwXDG15o5kIereMr37pl7HSvR1rbPTAzsWh4DpyaZ45bFfL8/uW1gaKwbu0nlCZDho9fGqrwP92naY9Op0fCyQYOdNO16bO0QSlkW1wC1fu6XnY5/5tD+3/On/fOWRP76WzLbxJfHWG6/2JNsTCXroscc7W7O//eX3IQwIaysYcHHiwF99/R/Wdg4888wjP/ruf8dhGIduI4KJFPnxI78GAgY8IIRACI8dfhNSDUjCAAdM3P2OdyRwlTVKmzesmiwud6dIFylw4Vd6kuWALEcR4jCpJXweilCcO3WBhW5tZNhjEcUYYpMxvxwu2uHEYmXUE9WbPn/fT377eHffqhm0xkt7v399X7q+gBAaHBxsoZpQuhaHOpbcMpjQjrx1lFH9wEuPNQFrxur85LHWfFcqGZHuToQBqFXcwfbcn96a/cQtg8Syjp5bsqwUlVxAj0NdwBgzHAuguCGEzowm5CmWyEnAXOwoEYvQkQgBorOIS6WrGDLAdMQCxgFRAMRQCp/HcST9WCjOPA6okt/47n96gdsMZBQ1FYiQnoJM5wogiupRxY9Ak9q+6n79jZc+8eErMQZ+SKWgdkdveH60kGsDQANKOAn96CsvgPJIqckAW/jjr76htt3xN9/+JQpqgmgZqtuWLmWiQWkcNiWBDCpp6A03RirSORzMoLESSED69XftmJ2cNXo7py6ehsq7WrrZ5llDZtpVUK+M8aUTQqcmxN1kzmHVHjF9eXg2uKKUd2w7mTHlrIyKGdxj+eW0rarztdzK7KlnqREWh21t23XXX1x40l9ZWGrA5fFRDKIde25GIpJSKsBzXnHJlx5jUoPrdq7qWzfU1XfjP/3bj2aWTkTLmXk4T7254XlWvWN7ZtXAQMvQwsE301armUkGTbfsLtxxw53LpfmwWm/NJyGiEvtMKWXpD/3wO//4T//ckksIQ8VaMFGvMbdp54YwNRJpOw5JzDw3CKREazr7Iq/BpHIj+tz+V2+4foNKGDThZJgMYtvMYoMVtm3U3QrfN6MC4dVkAKAw0rRSXEBIE4TqUITcxApa3LjzvXdfnl4+dOacJu2XX9zvlqLOtnVnz56onPVwkyVxkNTbRVAHhhX6dUGxkbTq9TJzo9auJOXmqKa9p7/7hYd+i5XjVxa8Yp1IhSAkEFAPWaemFxtwnQloLBCDUgClJNLNBOeEA7B9+1bhM4XgyXOn1665FgIsOMSKhQpJKSIRI6FD+GfgKJIAXb5wTnHBlJJQcsV5CDlUMZAJJ8sFJFjRZL7T0qHAkDcHB3qjmCuZxNhTChdyuaGBTbGiEMKO9t4wohIgJAyLZtyiKFgaAnakiQSQL/zpl7g2VcckC9kP/uHBfMYnLfTOW694+JnDAmGpw5qMbMNYbjSpToQbh3FJt/Mw4NzK2hr59H13/PfPHrEQPvLim5/66/fvMQf2PRYlkdCa81tSfBWdsQqpp+cWRp94RkppSqQ0O/bBkbBSD8D5H3y/p9D2+osvtJmZ0K2efWnckrK+khu2DMJREvJyjSW1wvC+fSZBwPd3b337bCLv+NOXzx/8y899HBORNdErT764Uq3j2E+b1g03bBxZqCHbyHdede7S+bzG9FQ28NwKBH//7R9+/Iufz7fmzWQ+9kMzoemOkST08P69jo5wNiWBtDGNkcAAAQ4NCL/1998Asdx63U0xUNNlLwlUyMXyyooKYxtJimEunUAIIdbcunl9pj2Vab2iulSSwUhrobXe9BBhEYhf23dwa/dQttXJYK0bW6n80NT4xeJcza25mm5wAYmmfNfK5Tfdc+e1c+Ul7JinTr2YzbdADi6PV1at7Tl0brG9oBeydg566/MparXoeWtp5iQ0NA7UQKatHFQxos2m7/qIxUghPZPMAeZVl5cMyQiEWEEEILKgg4RlEptB3Ns/dHamqHEBOUtrDqwHEcYSShErpskYYaEbUmkMJZCKpbSHBjdykGlyCIDW2b6GYSwVuunGaz2/pEyn6sYf+NB7ieIXzh6xU05rJnXuzDCKA0oxJKiycnlkYSmCkmmARIIrzmKWLaRu7LzbCzhCzT1Xb4tkKIBvEP3jn7mfYugrswW5l/c/URobM61UA5kZBQf7QM9QSKChcO3++7f91+/fKhR0pphjFNqy+a4OO9vRSUpjmZSWa+t5Yu8ZYJiF1vyLj/5p0FE60Rm1/FThO//zrDs2lcEaOLXQk+n69cNHXJUejvKYY8ilBlAyIQSLQ6NDQkUx9v0QYRO7ngIximTGouXIdUWU15NhbWnL7TsWFiWK8o3mMoi80om9lvJQuj2bSv/293+IIdVYEEOHqhYOvWPnqyc/9ivoaPd8pBBa4ZIXdjsO5AwR0ohVCwM/+vf/ZgqDchnbKc93DaphIBGPMUS+jDlCkiusYQIRFqwso2TGFkxGtQAaWLloJaquGkRGMu35DmIuIkkNxhKSamn53AkPCeiJZy0H16uhoZFsNm87KNdheaHUTAvqWtLSJ/e+xXhkUZgVKoRIKihERDyrMLAhu2GX6urjara8MA5Cv7k46yQK3Oi128NsJWnNuJmOAcSePlRque7WO1L63Ku//WSoeTOTI97Ews5KurkAZ5vLLYNbf/jwr7WwKn2vUZmlEiGAiIISAiigJBBACKVkRCENaFwqgDWpGhiGCEZAYmRCwMnSykK+rZNa6aFVVwTKjEWosNtaSAcxl4iZUOzcvrHoVoqlarnSaNRKEkgGiOsJx0QmYFOTc5RSIQQWQYGCfE/v1Nxi1Aw4iC8dO3rFxs2nz06s3rgxRoGKLB0Jtxn6HrMcLKCQUsU8AsjUYPjKc7+Ni0uZZCrgXNOJAcWlSfLz3z76ma9/c2liqT3TcuPNt81NnlpenI19rxmUvVDGkXvznvW2BiFJQL+RbM62tOYXlmutDgliT4nam08+oS0s91mSCKGl7QV/hmJrJVYO90xsAKwIIdC1idRMoZeBZ2gOgkwpwKSIAcS6seDGli2MMBa6YeJo8tjx6UZ8/fV3nj46WdB1rJSjkUgwpAAChlaLgZbMWmZJhUknxWOLY0Ew/NOvf+dCWEgkAYiigANCMlYyCD0lsWGKnFNQFHMlMcJBEAioCIQ2oU0ZBwBgBoUQRIkI5/0I26ZTqkXY4D3tecNsrVQqHBFgZDetXXd0ug5IyKBDFBdxiEkin6AIiEBDhoZXSjXSgKOTRzDiR46eLPQW5i6PS5AwDWpBoCJfAqggp1hKxSxZ7dGXK+OLIwf3Lo1fpjitKeEIoz7Pwz76yhNH7FwGxWrbuiEXGlz51UaxuTRa6J2z2xosK3tckIYtJNejeOZrn/lePVT//qN5k2Yl83woCVSxUlg3CdT4+latIUgLA5M8WmlUhy8cz2QyFGPJhYhioIjt6BFHrtm147buU5eP9m649ifff4JFsY7QMVMHUBKvmk5mXU6klEIIphG/6WKIbNtWTNlJQ6rGhr7ehVoTVOINA73nZ2bSjrm5r3PD+hYVE3/i3LV79jTiXGnlXCabjTCCZp6BAuNKKB0ZhhRCSvnqE/8vGztmT05z25di0JJRutPllkZ5QwG5WHOt9tYui04I1VB1FyeJXchlw+rGTT3QtCTBOkY53tgy2HV6UfZ2dmdZtOTDwNZePTaTNrOYKjeKTCxaPHAxlR9rVmxkQ2wowTGE0OScC03jlrCwknEMMPrzJ1c6DtQSRhxGiiqgK08RAslAWitNnjD1yINQSC6xVhCxqSQLY2KTkPuzKyXDzHp+WTIYa9SMkZkqqDjIJwjz/UAQQmjkuzomHKogAkbSbqwUdceKBRMIptKpRt0jGieKeG6Yx3klqYMq6zZtZXquUas1q0BkCGSehyBUsYk4swujdSlkPBfJe997zwuP/9BVRmu2ZbY0bxJSliqplObkgiiqkph6pEJkbXxRKS1oMqGH0IQEQwMoJbhlmYHfrM5dvjA/0o+SWatJjFSIGORSd4uT2sLn0uv+5qrVp4cPR/Nad1cydgUvvhbUoY9vgMxr+KHOHa0ZlNy5vJuEiWXfG1PZljXr+loyPRNj4wK6ZNnjkjOPa6Oztda+7mYIkFSHT56eL7oONkQjhAgppTRCuVAyinddfdPeo8NP/+6h2sLi737+C8FkyHwd48hDAMaQiWatKYhlmqYA0EIkn83HYZQwbcK5ASgglqZpURRkrfTcyNS6gd7x2flJtjQ2M4MVgbbxkevegT19wLnqzdff6O3pIrqrhBdLogAPotg0jccf/xNWCZ4zMhXvS1/d+sqpZAV0Y1PriXcNJKd+9e2fkuSWNQM7dZpnnp1L9oC4gpsActySaAOahoAAGOk9PbVEcs+ePc/8/MzWFsZRWW92WqYWNktlZGrAil1Ztuj03HzeSls2kZyZlua6bs7MuMwlQgogFJe2bmAEIsZNSwecNxtuJpVmjYA16gnT5DwkAAoW2EKaphkLFVeCRRsgQrFpevUy1nSYtoFlutWm1BWHcRBLUQl0S+eSAgIARtjSokBIhJjgbuAbQMYYY0IrlYrkUcWt85gLJSMFoULYLgEMIsWdyGWQ1JsLC/WT1DB5s56iKcDZ1MSRWFLfTHsB4wgePXR0fmpCRUFX2nJYGaJkszQXAg4UBgBEBFGg9fb2Cq8uldJyOI0o8D1KdVfECKq+9jZZJYulSsG2aRZWlpmdyOuccRht37pFGlYyvdy2auKLH92d2oRWfjTfmI6qtZmhvv7QnZQptzi3sq7fifyco4OYch0gACSUqlmrCqYPrFnl1gn57UuHkFSpZOZAfdxX/olTx5VS0MgCpgyECURKSIyJRNgPvY07tjT8EEXNtpyFTFJoaam6tbRhrCsU5n2H8UbabPOaPjYcpZSu6whKICTQNKUUhTBtp5rEmJyaMUwtasSuYTcqxci0BItbcpuqtaU73nGX5AIrX8HaLTeudxA8eGY6n+mImQQECQDr9fradQMjFy9QVv7233317//vN/7q33/6x/PFOKwrHE+Hle1r3/UfP/7j6uvuyLRyIV2MGwk90qkPoAs0N/JtalMm5YvHz6zfvq397L6+XTv90VFVAzzFSqVqLp0yVRxHHsB0lGumaacNrRH6GIJGo4ExDqNYSKW4iECsa1qIOIi4RKAZuLZmQcushYHVnS8tLIUGiGKuUyOQUkEWNJp/1tdGdRdTEnsBIdivVYSQgMzbOCkIw0i5rm/qRnm5iCGKfe+KjWsKrZmXD4wGIraxRoSoKg4xDYI6VCBWypcKc0EQcN0mItbUBJA4HOzZcunQ/ggSqsnJsyeYhfUo5kCaSAfCwJrVZGXPjSXW33br2/zZg1TWarWV99x69WNvDm9e04O44kpSipaK1RgQWStrSkAWJQhPh6qjrXOqXgcKZFKp2tLC1racQ0Bve9sTR/bls6swlGsHVvUO9ZbqxYbCINu9Iounn1OPfeZvHKMtpayE5dTKtTdeexNcmeMor2QUs0AzcAwFARpSisW+4mEQBRPzkykrSTxGEUIolAE2CAJMYYVw1Gwmdd1VAChAEUZAhGHoS35yaiqujJhUMwFuHepZKXkxAKhWv+7m3T9/cTSVNRmXViLNhPwzRjWCiuiUIKyEkIZWYqGiCCkMGF6/ucCWkB9Wu4au80kzn1sPaSQabOLUeYUsYhkaUDnbaO/dFMQ6oFiyMJDypz/+4V/91f21sPZvn7u746bW+8a/9nd/9ReBlbEjUkf8oOI/h9whmb/5v//1mQe+4rktADsNYlOjBYiaC9c5+iJj6tSlSYScRoMXh9/aff2e+z99vVp+eWXELZYTy5ON8XJNy+RXEi2oXDIds4lDCUwuGMIoFqImAiGEhjUQyYrfVBCIMFZKKaWkKHEEoALG/AKmpF4uO7YpZKhpGiXK0bBlJg3DCqQngDKzGULNIPAQgALJuFFdCWWpySHWuxwzmbYAVEolNbfc9KqYK0gThuQ7BrsJjBUVUAEM4P7xUggtSzWvHOhpBE1OkjpSADTWb+5r7bzt9NkzXuhhIqhtr27tqkPu0CRRpLWj/Ze/e2j7pivzbR1hUFy1atXUyMmpsjvVkIGWaU3J5XnPZ03dlG3Z/GLs43ITIpRPWKvNBAfx2YUZzzYNwVIJp1pcOc89X4K33X3nSFGsHerMtyYbbn2+NhVL/saZ0aMn680allIaeo9UvIoCwYEhMs++MatwzzOHX/+7L79zbZYkkeTCllBhIAmQubRTDYGJFYsbJEE1hgTBEkOuSQ0iiAmhBtcMqisFFSAIE0JsAGgEwzrTgbQTqbHZIrC1QrIPJ7zu7tazh99ykgOcxwrCmHONUAAAQEgxRSCJ/cg0Ta4YESIKmhCKBEl/7e8fbM2uAoL//OGTINULMQUURlwlMG94mqVrAImG8h0de24cxwEiEZe64FLTYVuiY+c7b0ESv/P+K779UH/kC2BnCRVJLcn4fALgxdgzTPdDH/mwk2QqgkonpnSrAijAKLZ0Mx8LWVucsZBx8OCZM3v/9NorfwMqjagRhCV3pSJKxegf/usZbnQWA6FDGLuhphGdEgyRTiEhBCusaYaZtgUCECaTuoUV0AiAlo4AdIiz0qx5ihOlD7S16kAw7gMALTONkfarA/sVQZt6h9Z0t7AohCKWUKsUz4CqPeM1oRJtrZkMkQAAJrmFRGdv/7HikWaMkwhks5aOACK2kFIhmC1GZY/c8653De/bF8nouz/67gv7zhEV+bH31qkjAIDplZVGc7mza+iuG9/x+W985YZd1167a09LwR6bnS5WqwoAI5MNS0syjHSAnnnjcHvP0JsnLm7beCOC/tGjL7/nuhuXK7OapiFEOOeXy7UKbyKqF5TVubFnfGyk0N5WLleRZp44Pdox0AptsVglY3OTZ85dRNiEEOJEh2bM8yhGSHEOsEoJXrvy6g35FlVanEXp3LOvF8nN7euzHsVMAQiRgoJjKBWLEQBEN4kJKBJxq50ru6FKa4CFRDMAAI6TYJJQ4CUgxswITWgQvlyXEYaGqfEl5nQbu7Z262B1h/BOvOau05Vp5Fe8+oLvqIQHANI0g0euY9uBAqHnJ7I2hYDVReA3E9qkzWPRmDl+fE5vWedGWCIQ85gZGlN66EClygRAmzWe+NNDG7buKbR2jI9cumLVUNJCP/+fZ2655ZqDp/TRF3+yCLpWXbFb6HFauqGWUiGuzYfzC8fNltWaVE7G0wBitqdh5Lnu4tSZgdVdxNCWJmfuf9+7nnn2BR9RnQeuM3Tre37z0u/u09MttHUqFUTdia5X7/38lx98nGV6bQz1pBlhIhruYCotNV0CxaRIWImTM7VFrtxmtGfrFu5VBSIx80wzYScz85MrB06cBnG8e9uWSCEzCCSCJJkAGq28AjkEWqrFzrdHsQsAisNmQfaWuEdlxJDKZtrTWALAhYwkFImW7ihxXqvHpjJashlIOokuhESQKYDrXLCWnNX3gXc//cTxB/7ir4nACIsoqicSpmRAYp37TmUqrDXELbvupQaaqxSNFo0jY6Xmm1QrN2d1DREJCUIG1cozE22JLCTWrqt3Hj5xrOHWdJo0AZAW13CyVZYzoZj3PdBReHNsKZHqEkGVWOmOtkRuXf7Aqenyqdq2d9155OXfFHAaWjpTcSGHlxYIpljFyLZyAIjbb769sjzaLGoxA04itVxizxxaJDetWmdPShpH0gYOIhgnE2Zfh+MjQq65ZdXyNNi+Oh4v5w8dOiSgkjpUEvhNX2EAUHjjnbdXFmuXZid71w0sl6Nq3ZsdHzO5bGsYO3v7KaTliNz9metqLLQhRBr+zRP7yvE4UIhzjnS8XF4xNE0gyRmsFqf7h/phOf7R/3zr65//t/3zc9e//cGedUMKuFTKwwf29uQSs3MLrus2y4sKoGZlOZVI7pt6hgtFoDj+2t4rd9984sSFOTpwxkv85PWJq6/rqTTnkwGZHD+UWXuFy0Wz6hKU8husCkrlZjQzNrZl1abh+TnLsl4/tPfYEXOhOgexpV9OpjUYcU4gQsCQQXzL3f+995Vvzh5bwUGp4/oBgMJVa684Prlw5Z7d33/ytRiBnqS5a8f1CPI/9xIxxC0ideTwsd6ennRrnvBEJASEEiGqadROenEcYqXCOMi2dIK0KRSAVMOECMkFAKZjOwnTBkRwJZNGImfLjLfv0hLEqKevxzAAQojz0G7UkrGXEqKGKYM0294pBUSakgoThXL5BVRe8QKxe3NX6n0FDzSee25fvV7NJ7LV0FMSCBUbWDz4sbeNlc4bffVaKZw/zzQnqRTAmAqFNWwoKSAAseRAMASBEuHU2Jn12zpRFPUPrl8cvjjQt2HYndo7s6BZXFX5Hf197xjs/6fKlAi9YkQY4loznjozdeLYqTQ22tORLQVNEhl6tpOplTwFk5wKBOXGK68olibmqgsSAqCgR+jU8nRPQWOs75UDk0td4PYtPRhWwhAXHEqYvv/gUcghOXB4WEP2UHdmuTR/y+49b548hTERkvu1piQa18RvfvuohrVYitn5pThGpm4kEyYI4jnfPTxytqOrQ8O9y14UAt5UIAFhpVz1sQ8BjmNuJkwZKUSIhjEL4g0D3YwVH7hne8IqhZ5GE6tjvXV28sz5cyfrS7MgbE7L2EnYUArKVRDHgIvIj2zTcJlnOmYQibPnzlvJ1NZ2+//89YP9LdaFczMhm4ubjTziy2fPKoCgFivm1bzST3+ofB5bGt3/8hFNt4SUAfMdGEbKNpOtGNAoqCONMh5hAIMIxrL3ve/724e+9vFSsYSgqRBI5Nqj0YVUvi1EVqg4tVNWMiGUjAXHhGhQM5M4ZHx0fIS87VoUAQKAAjGCFGNs2WbEY8ViM2EpAhTEigukJAYwZlwiDADgSkolFIRKCaZAMpWKldCkSiaTCERCCETMPz30vx989zszRmLMbQodK03DkkrCEUAI4XQ2gfns/v3HNq1vLzXj//7Rv7Rm2x/40EftRPpHD/9agAgqxHzR0Vn4+y9/W1EYNuT73/3BpeWi4srQTUop4IxLhgkWUjLOMQJEMgQazz/xx5ZMcv+h0yilVQE6P7GopVud2lwT549UvMaFUzojKPKYSlPEbrjpbRdOHkokk5iz7//n1/tbu+cajYFc6603X/fKiy9EsehZs9Gv1eZLi57nRkiXwr44Nac0qxGikamFdDKrO8nxGjg+u7xloxlDA2BNAMPIdrRlW4jdACVQfOo1F0B26dwly7KQQjrCZtLyhaaUlNRWGGsQMsUphQCoiHFqmC5gT728r3tV33tubnE9jjQikMkBpARjhAAAtm1GUZhKOpEfAABAs/n1f/jcoeOP33BzP0Dh+z/xLuvEwqtPPeSgUCe6ITlFkCEjiCEAhAGkGSYlPJShjCPdcCJpZAtJQlLvfOd95RAA4rz9fV/ocDLf+f63AAhWUFJHOo7jZpxJoIyTpLGYBqIhBcVOO0J21HQhwy4yzURb/8AWJ0mPvP5oGHpABEKULGrGQfPhX79QP/prESgJdQiVmSukMmnNskEcEcwRVoaphQpqQkgIpDQQDTo6OqbGhqWUCiHJZHdPz9JSUUmIsCYVApguLhW7rQxXSimIAeCKh4GUCEipRQwACKWAjAUYo5hFMIwRJrGIHcyUFEpB4uRGmtp8Q6Y4JIiHcUABlwpoBDPAqtVqq62XG7Wp6eLp4UaqdUiy6Ac/+VmhvaNUKbemstlsFnfaP/qvnxa0QsSMnINPvHUoDCsFM4MIURAAjSqMI7eJAYQIQSkU0KQMQIBs01i//eqpycOnVuZDCNoEsvryqClJM+pt3VqqHejp7Tk3s5jB2v889AupE8mpUphY9uVaBJQ1VvXmn3xcA6q1u2t6aSXnWJFgiXTrUkPUXRYzgwcCI6tc8iPgHzt0FPr8aWEpXg6JBbHughWsxHhjkvz0/7zvs996bgU0pIDC0riIdKJJwTEmhHChkAIYQBTLmGMJAVACS0QDBUxGhS8nLswMD4625jYihm0KOecKMN/3hRCaplOEvVoDARDHcQrxwfZE2x27Q4AqU/6L+17ef7bpoNCgmhQx1HVPABvKkAuIDaBhHtQNRHWsUQW3bNx5bmS+XK1+9MEPQ0HShH/2/e/OQhyo4P53PiBrl1C2txFHZVFLJLXBlo0zxbni3OAbe5/WNBWqmcGOtaapJ3P6lTfdX67Obdg4ZMB8vHDcDUoJM0WAopSWq0U9PYt1CyCoIFBCcqAwRVjHTKoYowjgEOtQMPnnE49A6LkzkxMQKMEkVAIoMDU5iSBVxFQSCwEJ0TA1I6YQABJAiSDgACCdUM11A6myUgopQCKROHv8eEtX17b1GylGtVpFazcixRCkt73rvek11/z9+zuHX35akwIjn8dMScWYGJ2buHx5NKlnIgT/+IufInuz12xwaiEj4XOpa2YQBCuLC25cyzpt7bZFDaqUXii0jk1KxmJCkFAKIhILhjVEJQ59HxEogQFhoCT2Qg9Qo7Q8w2CnZWkMhWKFWLxCKZuLlkpNsRSWOBDl2GNGppBqr5VmAmHoAEjgZyCOhN8EDoj86siCMmhlmXcUMlVe92nSZ4qJWnehsy6E13QbXpjEekJ3GPZN2r3CQj+IDRBmNVEPAenYoP72o7d9/vsPy1SShBwSnQGKAWIKQRVJBmMmNB1kzexKuIykvO7qLe2JTpCwC5ouuXlk8nyr3U1FrBQEUMWU8jhBpVRAMhYqoZhUCkCl1Be+tMttssTQalBvvP0z3xAkZel2HEcCIl03/MDTCAox5sAlSommghQwKCDEFMtAliWu3Hv33UpLRtKVDOVb2jHBAolMe9KFWWjrcRxXF1cmzi+H62V5eVlKvm7V+iCoCp71isXB3o1bt1+faLWGL06uGyowKnfv7J6dQpaNMSa+j7O5Ag+ZqWsRVhgxpjIAu5KhIOIKQSnQ0mIJYCE4gYSK2FMOV1iWXGYJyjnSgQqAklwpAiMgfKbuXt2T6uqB1EEICGlI5SGFpLT/8hN/iaDkkBGFmIScNGYvHD9/aZ5dGs2kWkK38dRzZ4hGQyZ9Bj/w/vdlDP/X3/76Bz9wu/CagQslBDIIZ6Lmy6+N2laKxaot39u7bufE1HgsExZQDcVn5uZb0lmqIyFlysiGgQcAUBFpz0jIqoaZYNGiEBhpJkQMRlxx6SmgdCWhAThTQqeaTBLn8FtPAkZ1wyUIZzJ2o1lu96DvNmcqMuAyhkIhKhQWofC1xZpUlqlqzXo+mfBZAATkMNCJxDFJwnzbqnxR6BTxsdOXB/tzY9P+ltX9jZURjdcqpdGCtd7jEwQkqky5zQgQRJUKYtxq2STTZb/tnraB38Algwz0dQ11dbemsnbCogRRTQuZtlIJnXRmaWry0KWDFEUbelYVG1pbQkM0QYClWY4QShKBkXCR0cmXl/zJcn0FIQQgFAhIKQnCGONNPe3CW1J1VK3ZparJNKUjrhkwlIEfB4RoCGgr876voMINSLAQESGGVAAyN1PobckNZNM9ArMgcjEkjUYlk3WggrZJQqyCICwtLedSacxlcXFJMbY0czGSEcWZ99z16fbuNqmpOou/960vf+oLfxmB7pHhQ+dPvrlq7aa4Guk6TlqZxVoQKQTaVqfSDpAKCGAQiqCyDP3OK3cjzWxNG1qglMERgL/+xS8+9rGP7H/m8W9/4QsKpQAWnsBU+hRpTBGp5MZVhQ0brv2XX+1LZtJKKak8RY2LU43OjoF0qqphHsbWsldRZnWN1zhx9q18mJy3urHrSZxAyAbAV0CYhvmn3z358U9+8pY77zh+6tym1T1SxkKouh+8evC8sgyOgWVrVpaeHzsBlMQgjkPpOPbqbf3TU/NEMahkhIgkSCkV8Jq/IDRsdfSuroTFhltlXtnmDiYAAI4k1LQEBASZGEGq6YQpkCJ499YrgVvkkiHgzs5Wbn3HdY889gx3F2TbYFRb0YBLoaGg3vT0jowV1yt7tu4+PzatUV1QJL2Q4zAkIUZzLXY7hsbLB16/557733j9lfs+9Onq/Fu9VvnKPV0daU1EJN29RfjYDXzXdWeKrqlRyeJqrUQUTsGk9s//+I2v/fi3a9YPttopEcp9x94EQK5es14z87VYAebEQHYMDFW9hQhY0M4oHQhlBgwHAcRQcyOgQZnQIVieNFGcSiV837cMk7l+IukAKShB3/vOT7762S+lnfYsU9/91rfeGr5oWx1I86AWC4kwRIVsAYr8t7//P54sYqoRaEmJNM2WPkxmWjes3cMi8sbR56YnJh+4/wE7YcVSMC/UUjYHiivJGGNVT0oQxUzEATaSrlv88he+gq1ExALl1+PS4uc//SnQnKOV2p4tV734zBMXp451dua4FMILu/vXm5igLkv6HTMXT/as2qr0WJFIkvD2t+8BEEMQU6yCKFRSfuhDH3zj2KHNu7Zlso4GdBm5kWJSAkoxgBgSM5YxEo25yeGtm9dIoKRUZy5OX3XzfRMTxQzmCAYEgjD2+oOV19945D9//m+vvrj310/Iy+Ux29ZQ1FAYQUI1RKCVeeb5F1s7W44ePApEuGGwb2FqKZtMX3PldVjxleXFwG+mTToRAg1KBA2P+oZOS27VRyBkTEHQbLoAACEEx5xwE4mw7J+LOS5kejZu3sLDwHZMhBSWUKdZBZjQOQAIAq0Zy8XZqZm52o4t27zIDRsjwkNTyysDG66te/7MxdO6lqh4HCu5efPWJqea8KFm16q+RaWjo2Ls1RDWGW8hFGv0uj03PHf8vFIqEAIaDtYSQ6t3HHv2QGN8bjhtriLmxAwJwpBgBSQPYyERhIKnkUP6d3yNSKBDJyBWd19rMpmcGFtYaDZsxyz5cVfGaMxNpdJoqLdj7Og8MJyV5nTG9OqRkzAFUKhaH9NgWtezELJas0LrpWQ2g2qV7VdsKi6vtPX1pmxj7PJwKqHne3onGvOozNusDisrU60DqUTbt/5/XzOSBOtGvbLylb/6fE+hJ9vSPtCSOHt6hktf1wljGlQRNoGZdAhNHD+5/ytf/EcVAwCjWDGmAo8Rj8MYC5/Hsd/QrZSRtOrV0DDtBKAmDlW4Ui7Xpi9eDqvFShjJyvznPnbfw7/4r40dPS29g7WgMbMw29OTI8n893504KVH/lCLg7yVWig+ZGbbFbBOf/+n0mdCCEQwNXTAoYQAsxDqeqalrTA9kutdn7c07IYx5JquRXEIuWQwYnq8pSvhKFfTtJlZz0r0nL144YZrd7758mRHnhKjojWmD7zxq/988icSB8fPxffebP3iRRppWqAQhkRIIQLf6Vh9aeJyuV4iJL3/6Dk3JJn8YM+GPtNbbnVyNa/X1PREoXPtmuWIL586e+bE8LBjpjiLFosehhwgSBSRUiJEFNAUbv3oZz72+puPXnHFDVOTS1dsuX6+dm7//oONunv99df39GxT0P/5r74juBLMvPveB/VGE+rJptPWMpjNaj0HDg+jmVIicz1vc3fKYGapyTkvJFsLWsCDxd62PFUpk6Jsvv/N51/0Gq6Tyju6BZueFM4ze58v6SkiaBwpgLHr+lC3tt/9l/P7//D88MVtqzLjJa9eL/UU8rlkphqWYiYownPMJwy3NwKeTerJpL33zX3aTWZXS++b595ECKwd2M690FBRhnAjEkGpHhhx+85u26/89E+PFqsrhBoAha1GvW3dNWdOn0/1tB/a/8aisTYP1OjF8xknOTo2bBAERCiZe/hg+tyZvdtuWPOpjxa4QaWVx5oeQ4gAggIKDKGGpApTmeSOLb2Xzy4p0UhYJpOESyBErCBXCnpe3dCdhtuACMWchSLA3AoFEEgigq1koulGNT9MOabizZRmzl481pieXGyEK64LFDd1SJOd3/nFw7duXH98eLo8HdRiCOLghl3XN5z+X/3qx46/KSLlyZKRzvcLEANoeEx0WvnOzvbRiUkMTa4JgKHmKN6MSivVY28d3NSxlgCiYxIz369WAbVK5XEtYyzH1SSVBuK/+tWvbrv941U36syn4qh87Q23//6h/7w08fx2O/m3//33CkXIQ3tuXHv9tVddPve9w8u8Bm0TBoQQqMBKpbp246aVyQtAYUysQGpLEys0xevBJOjcYORMN2YaBgnHSFtOYh498L73eZ5++dSp7Ru7LQqppkkiLMuyLEtB+Orei3oic+zcyfPzizdecyfKWL/92W82bthOrcRjLzz/d1+9PWKSScYl55xgSqiucYKDyG/6uq2iiMK6X9cSuI6FjTOb1/XnS1MJYq/rtDWwNJTHFBMM0b5jpwAjLclOwWKElTA1TdGz4ydHPZ5QmYWFpY6OjjgOQ0qxlih59XYrhQGfbZSVB6IsTGcLT56YWtOVG+rpXTpwkgwkzF1XbSbYPD56qRav4TARJ82KR51sdPT4kcXy7J6rdvi0qxqVevPhvrO1Y0cvXx4eCZCey/dX6kGbEc4ug1dPPmbaFrh0mSAbszkXAkgMPxQciELH6kwKXTw/lTBAI/SffGH/7uvuopwatCEFpQLHcSyiCIc2gaHEGlGREJABn+hEAkgRbO1stywHo3lOMhZJKqscR4X1tPj4kZXjx954//1/WW+UF+YnCDGsdFeV6+vXrFo4+4IQIUHoyReetB1D+riqhBlFMdI5XUmF4dOHz/V0b5J2+M7Nt/7PM796+KlnhjbvMWgy1BYoNiQMm7HQEdFopGMtleqgekJiJZWrBEXMC5WjQwGlVmrWD7/4yEGv3J3QZkpq99ZNz+97PpUkOEYv1WpYo82J5c9+/quNkNeLtUZQefXNs3fefMPNt1x18Tv7hn35wU/8Zu9TXyHSZzwbisVPfuHuU1/63zzNcOVUuZv0VtZsGro8PgIUhMoXAlUqJc3Qzx1eml4ZWV4Dd+1cbycQj9wF3uiFMiqzh/Y99clP/V05Pp1JldopuLQ0yaONFxsnCKwirYsHUssmeZixmNaW7KEajGPtyIETElDbpFRKTjRIzdit6BrVDBtgjrgMQjeKaQOK6dkVN52y7dMtoYhEpGtam67SGavmN0IpG0GjM2sGVfe6KzbQt1+LkEQKCCEYEwQH4xMX1emX5ku8tlJav3Y7l56MEliFvLDtXx684hf/9c+DJoopqBSL+0tFgsFysxzP8QsKkDVDPTiBpIYWKkU91T6zUuVBU6OYB8qDsYTGwdMX9x05nyDUCeu9vbvmagFTpuDQdRuOk1lqsrZcBtNQsBhjJKTUESUSICSuWLfh8NjZKsP1qjByq+uV8xqP0k7im9/63kc++tFIJk2s/owPoLrGA86VVAoSojEu44hTXTIeJ02MJB+7cGlhZHjP21qDKPzdH/5wy22f7m7J5PTiO+97bxjUzdj1x0dzvR0WTWQs7dKZfXq9JLFkLEinUndft7Ore+ujJ84TIGQIaBrftnmjpTg2+x5/6/kt67ffOH7KaQZLXBCKeACAVBomTAGCoBRKQrn5tu3nT18gdo4glEQoDlW+pV+3oA70oL5yYbqYNPVag7WlUndcdfWBN/eLCtDNBLL0yF28eGnYf+rhsBlESOMICOY9NHHh+OnzBoBxRD76oX/7p//fTz98b2ut1jYy3vzBdx76zje+8C8/eSLSC36Jf+lzH/veQwd0U08m0gTDRrNZ9hpRnSWsDoYTZ0enzl8+YdoIIwMDkYWRZRTuvWWTWHj1829PJ6HosHWc7v/FI/MrjSbOty6ViK0TBWKsCa5kMpXiUgKAGGMQU66kUkoq+edV7Z9HyRBCCGEQBJ6nWSDS7UTnwJDiVcSbjZiMzU8lNVZa9P3IX2q4R0aXLcBtjG/c6QylkgH3QyCVwkpB10Vmtrta9zQtEwQe5zHnUhIJACiWS5fq7rY1uT7oS0yTmWzEYhJrhBDDMMpbu/7/KehX3mCp2H8AAAAASUVORK5CYII=\n",
-      "text/plain": [
-       "<PIL.Image.Image image mode=RGB size=224x224 at 0x7F0C483539A0>"
-      ]
-     },
-     "execution_count": 47,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "# file path - hard coded paths are bad practice!\n",
     "filepath = os.path.join(\"..\", \"..\", \"CDS-VIS\", \"img\", \"florence.jpg\")\n",
@@ -903,7 +650,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:40:08.824616Z",
@@ -913,31 +660,7 @@
      "shell.execute_reply.started": "2022-05-04T07:40:08.824559Z"
     }
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/imagenet_class_index.json\n",
-      "40960/35363 [==================================] - 0s 0us/step\n",
-      "49152/35363 [=========================================] - 0s 0us/step\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "[[('n03220513', 'dome', 0.44513726),\n",
-       "  ('n03028079', 'church', 0.30873805),\n",
-       "  ('n03877845', 'palace', 0.049231548),\n",
-       "  ('n02930766', 'cab', 0.026441267),\n",
-       "  ('n02825657', 'bell_cote', 0.024402618)]]"
-      ]
-     },
-     "execution_count": 48,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "# convert image to array\n",
     "x = image.img_to_array(img)\n",
@@ -968,7 +691,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:40:16.363836Z",
@@ -1004,7 +727,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:40:23.802519Z",
@@ -1039,7 +762,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:40:27.719653Z",
@@ -1049,20 +772,7 @@
      "shell.execute_reply.started": "2022-05-04T07:40:27.719597Z"
     }
    },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 288x288 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "heatmap = np.maximum(heatmap, 0)\n",
     "heatmap /= np.max(heatmap)\n",
@@ -1080,7 +790,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:40:39.659719Z",
@@ -1125,7 +835,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-05-04T07:40:51.362071Z",
@@ -1135,18 +845,7 @@
      "shell.execute_reply.started": "2022-05-04T07:40:51.362014Z"
     }
    },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "True"
-      ]
-     },
-     "execution_count": 54,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "cv2.imwrite(\"florence.jpg\", superimposed)"
    ]