{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Using Tensorflow 2.x Transfer Learning to classify breeds of Dogs 🐶\n\n### **About the competition ([Dog breed classification](https://www.kaggle.com/c/dog-breed-identification/overview)):** \n\nThis compition is to predict the Dog breeds. It consists of a collection of 10,000+ labelled images of 120 different dog breeds. \n\n### **Kind of ML Problem**\nThis kind of problem is called multi-class image classification. It's multi-class because we're trying to classify mutliple different breeds of dog. If we were only trying to classify dogs versus cats, it would be called binary classification.\n\n### **TensorFlow/Deep Learning workflow we will be using:**\n![image.png](attachment:45ebf86f-9bea-48bb-819e-8289c86f70b9.png)\n\n1. Getting data ready import dataset.\n2. Visualize the Dataset. \n3. Preprocess the Dataset for Tensorflow format.\n4. Prepare Tensorflow Tranfer learning Model. \n5. Train the model. \n6. Visualize the model results. \n7. Predict on test model.","metadata":{},"attachments":{"45ebf86f-9bea-48bb-819e-8289c86f70b9.png":{"image/png":"iVBORw0KGgoAAAANSUhEUgAACyMAAAI8CAYAAABY55V6AAAgAElEQVR4nOzdebhddX0v/vd37XOSkzlASMKQMItzwRkBvTjW2jrUQgdFkTpURQFBq/fepzdtrRaHgspQrFar7bXFttf+vLZ1qKgIYqu91qF1AIMikJAEMnHmvb6/PwKKipCEk7POSV6v58mTuM9e6/veMd992Gu/z2cnAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACwbyhdB4C9Sa11YGuyeGTL6JI5A82itM3iyVoWl6a/uNZ2QSm9gZIM1pKBtO1gTR0sNQNJUksmS8pEmmai1EzWZKJpMtG2dbi2va0DpW5N024tvTlbm6FsXZxsLaVMdv2YAQAAAAAAAAAAgH2XMjLshlprb/2W0dW9ZvAhJf2H1loe2jR5SK05IqWUpDZJmpo0paSk7vi91pT8eN/99O/1p38vJbXW1JS0taaWpE3SJqVNrbXWuraU8o005Ru17X9zsl+/sXLp0I2llP70/E0AAAAAAAAAAAAA+zJlZPg5tm6tyyab8YMm0hw00NZDauoDUpoHprYPTimrkszrOuM9qclwSb0xaf4rtf2vNuU7vabcNJF23fx2zi2LF5eNXWcEAAAAAAAAAAAA9g7KyHCnWuvApq0Tx6eUp9amPqXUHJqUhUkWJnVBkqbrjLupTcodSbYndXtN+8NSe5+qbf3UN5YMfvWUUia7DggAAAAAAAAAAADMTsrI7JNqrUNbtoweNN4bWFVq/1El5Yk1OamUsn/X2aZVrZtSmi+UUj/Xr+UrbX/yxpElQ7ccUcpo19EAAAAAAAAAAACAmU8ZmX3GFbX2njo88fB+vzyjpn9SKc2RNVldknldZ5sJajJSkh+UUq+vaa5qJ+onPvupj37ttNNO63edDQAAAAAAAAAAAJiZlJHZa9Vae1u2bFncDsxb1ab5jdrW3yolh3WdazapbdaWUj/cNPnrsmDOjUuTbaUU5WQAAAAAAAAAAAAgiTIye6Hbb69LJ+f0T66T7VOaksel5OFJhrrONZvVlJFS69dqKV/s1fIvWdS7av9StnSdCwAAAAAAAAAAAOiWMjJ7jU3D9dDanzi/1pxRSpZ0nWcvt7mWvL80k+9YNn/+TV2HAQAAAAAAAAAAALqhjMysduuW0WN6TU6ppffLqfWUJAu7zrSP2Z7Uz9Sm/b91sly5fMnQdV0HAgAAAAAAAAAAAKaPMjKz0q23jx/X65X/3pZ6SkmWJhnoOtM+brLWbE6tn+n15vzR/gvL17oOBAAAAAAAAAAAAOx5ysh0as3lH5ufdvQxpTf52HYnphoPzZkzb/XKlU9YvGD+I0qT3nRkZBe1tb/1jju+8v2b1101Ojk5cl93L2nG2tSvNKOTV695zQu2TkdEAAAAAAAAAAAAYGooI9OZWmv5gz+74p1JfWFNlnSdhw7VDKfJx/c/ZPHpr/mlXxrrOg4AAAAAAAAAAACwc5SR6cSOIvKH31DTvLnrLMwcteS95aYVr1iz5pTJrrMAAAAAAAAAAAAA922g6wDsm978nr9fWUt5+V3/e8X+S7N00YIuI9GR4dGx3Lh+Y5Kk1Dy7OXjTRUm+2W0qAAAAAAAAAAAAYGcoI9OJ0XZ8Za9XftQ+fspjHp6jVx3UZSQ6cvvW7XnX33w8SVKSodqOHxxlZAAAAAAAAAAAAJgVmq4DsI8a7DoAM0UpXScAAAAAAAAAAAAAdpcyMgAAAAAAAAAAAACwW5SRmXa11uZxD3rgL/R6vaGuszCzlKYMHnX4qgfUWs1LBgAAAAAAAAAAgFlAGZlptWm4rtqwZfwjhx9y8IWDvd7CrvMws/Sa3tADjzjsTZu2Tf7NpuHhQ7vOAwAAAAAAAAAAANw7ZWSmxdrbb1966+axX6/txOebXvnVpilLY/Yt96BpmqUp9dR2svf5TdsmT73tttuWdJ0JAAAAAAAAAAAAuGcDXQdg73fbtrGHtjVvKaU8rdbM6ToPs0Mp5Yha27+sg4v+edO2sf9+wKK53+w6EwAAAACw91lT1zRj/zq23/jk+JE1dXXbbw9umubAJPuXUhbXWhcmmXu3QyZrrdtLyrZa6u2llg1t2lt66d3Y9tq1J5xwwrrTymn9jh4O7FPqmjXNTRu+t1+vNkfWpq5uUg4uyYEp2T/J4lrLwqTebf+WyaRuT822tuT21GxomnJL2y839tvJtYduGllXPvIR+xcAAAB2kTIye8ymTXVxnTNxelvq25Iyr+7meWpNJtqa3T2e7s1pSsruTMIumZPUZ/VTn7px2/h5ZXzbXx1wwAFbpzwgAAAAALAvKW/8/BuXjQ+MP6Jt24dvvXrrg0vK6pq6OMnCpmnmJ5mXZCg1g0kGk/R+fHTakjKRZCLJWEpGmzR31NQ7Si1br7362nXnfuHc/0yTr/cmel99+xPffkPiEjdMhZqUda9+8bKm5hFtrQ9ft+GGBw+UZnUtdXFJWZhkfk3mpc1QSgaT+pP7N7VNMpFSJ5qUsSSjpdY7StPeMdg0W9evWLBu/ate/J9J+XotE19dcfGHbij2LwAAANwnZWT2iHVbhh+XZnxNUp6UWgbvz7lqkrG2TetSz6xUkgw0vbtf6dtlTZp5Sd6ZwQXP2njH+O8tWzDn36YoHgAAAACwjzj72rNXDEwOnFhrPXGsjD0sNStLygFJ9qup8+7pmHsck1HTZMek5Ll3lh/v/rUkGS8pp6RmU9u0t5531XnfTsk1bdNefeHjL7xuih8W7BPWn/2SFWknT1yXnFhqfVhNVpaSA2rqfkmZV/JTE1F+/oCUO/dvmZtkYe5sGt91fE3Gk3pKSjbV9G5df9aLv31rzTVjdeLqVZf+pf0LAAAAP4cyMlOq1trcNjzx4trm0prM6ToPe5XBWppfTM0pG7dP/s4BC3ofLKW0XYcCAAAAAGauNV9eM3/L+JaHlrY8PZN5fE09vJSyopa65M5S8Z4wJ8ny1CxPyQNr6iOTPDltbnztVa/999rUT9T59V8vOv6izXtofdgr3Pyyl80vc/sPbWr/6ZmcfHxbcniTrKjJkuwoFednSsj3U0nmpGR5UpeX5IFJHtmW+uTBMnDjLa8649+bpn5iTq/8634XfcD+BQAAgLtRRmZK1FrLpu3jD7ztjonX1ZrfiiIye0rN3Jr2Tzdta0/euHXsbcsWzfl2SjE3GwAAAAD4kd/91O8umZw3+Zhto9t+paSckGRVkmVJejU19zTweA8pSRYmWVhSjkhyXKnlqeWO8h/nf+H8j00MTHzunY975/ppSwOzwG0ve9mSicHxx9Qy/iup5YSarErJspL0pvnNgJLUhdmxh48oJcfVWp463s9XbznrjI+N9AY+f+Q732v/AgAAQJSRmSIbN4/+t/R670tyRNdZ2PuVZG5Kzqy1/LcN2yfPPDD5XNeZAAAAAIDuvfLKVy6cPzD/URNl4tdKysk1dXWSpV3nulOTkqVJltbUo2rqo3sTvX9/7dWv/buxkbHPXvKUSzZ1HRC6dOsrT13YbxY8aqKM/1qSk0vN6po6c/Zv7ty/NUel5jHz+5NfufnVZ/xdf/iOz65630du6zogAAAAdEkZmfvl9lqX9rdPnlVq+79q8e+J6VVKjkzb//TG7RO/15vYftl+++3nY9EAAAAAYB9Uay3nf/b8Y9vB9kU19ReTHD6DSow/o6TMr6nH1lJXlVqOnzs09+rzrjrvA4v+ZdE1a9asabvOB9Op1pRbXn3GsW3yoib5xVpzeGbODxHck/ml5NhScmhTy/HN/PlX33TWiz5w8MV/cU2ZzrnrAAAAMIOUrgMwe23duvWA8Wbu+1PL05PM2ZVjN9y+Of9w5RcyOjaeJHn+Lz4hR6866B7v29bkjsl+WpdvZqWSZMFgL72f82yzedv2vPOvP54kGRwYyDNOflxWr1y+q4uMpdZ/HmlHz1y1ZInpAwAAAACwDzn/6vOX99v+M1Nyakl5VJIDu860G7Yl+VpqPtZren/7thPfdn3XgWA6rPud05fXgeaZTZpTa+qs3L8l2drW+rWk/H9N2/zdisv+/HtdZwIAAIDp1nQdgNlp09aJE8Yy59rU8ivZxSIyTLmauUl59rwMfXHdlvHHdR0HAAAAAJge53zunAe1tX1jKeV/lJQnZxYWGe+0KMljU/Kafu3/wbnXnPvErgPBnnbzK09/UAZ7bywp/6NNnbX7tyaLS8njSsk5tdf+4S2vON3+BQAAYJ8z0HUAZpda68Cm7RO/U9O+vqRZ1XUe+AlNecBA6t9s3DJ+wdf/ffA9p5xSJruOBAAAAABMvdd/4fWLJuvkE1NyZk19Qkk5oOtMU2AgycE19VmllkPO+8J5f5mJfPQdp7xjY9fBYCptOPPMRf15k08spXdmrfUJSQ6Y/R/lWgaSHJzUZ6XXO2TdWS/60PxaP7r4kg9u6joZAAAATAeTkdlpa9fWoU3bxv8gybuSoojMDFVWp8nFD3vU5P+qtc7tOg0AAAAAMLXOvvbsFf3SPyMlb0rJ0/eSIvKPlJSFqTmhlvq7dU593bnXnHt015lgqqw/+yUr6vz2jJTmTTX16Un2qv2blIVJTkjyhpFSXn/jK19g/wIAALBPUEZmp2zfXlcuPnD8kpRyXpLZ/wPq7O1KLXndxu1jF6/fXld0HQYAAAAAmBrnXX3eYb2J3itqreel5GGpmd91pj1kTmqOSs2LS1vecM7V5xzXdSC4v25+1W8f1vYnX9FPzkvysGTv3L8lmZOUo2rKi3tN7w0/fOUZ9i8AAAB7PWVk7tO2bfXA4XbsilpzZpI5XeeBnVFqnZuUl5TJsb/ZurUu6zoPAAAAAHD/vO7q1x3V1vZVpZSXJjksda9/j6MkOTA1z2tq87rzrzr/sV0Hgt21/tUvOqrX9F/VJC8tyWHZ+9+jLEkObFKeN9Dkdete9WL7FwAAgL3a3v5Cn/uh1lo2bhl/zFgm/qEpzcmzeSDytq3bsvb6tfnWf34r13/3+my5fUtqrV3HYg8rKWl6zRPHysRHN2wef1Stdfb+IwYAAACAfdhrPveaY+4sIr+wph7cdZ5pVbK0lPLMWuprz7/6/BO6jgO76sbXnHFMrc2rai0vrMm+tX+TpSXlmWny2vWvOtP+BQAAYK810HUAZq4N2yZP7PXywVpzRNdZdletNVddeVU+9y+fy/Zt29Pv99P0mgwNDeXBD3twfuW5v5wFCxd2HZM9rCQnll7+5raRydOTXNN1HgAAAABg573u6tcd1aZ9ea31+alZ3nWeLtRalyT5xba2Ofuqs9t3nvzOL3WdCXbG+le/6KjU8vKa+vxkH92/qUtS84u1Sda96sXtykveb/8CAAA77cq1dajf5OCUHNIf7x+Qkv2bUvevJfsnzf6pdf+UDKTmtpJ6W1tzW2q9LU1zW6/pberV3DI+Lzc+fWW5o+vHwt5NGZmfUWttNmwbPbFp2r+qtazqOs/uGhkZyf+54qO55vNX/8zXhu8Yzhc++4V877vfywvOfEFWH766g4RMp5ocmX774fVbh39r+aJ5XyyltF1nAgAAAADu3Xn/ct5hk3XyzFLKC7KPFhnvZnEp5em90hs/5+pzxi468aKvdh0I7s3Nr/rtw2rbPzMl9m+yuNQ8PSXjP3zlGWOHXvoB+xcAALhHa66sA485NCvnNP3j+qUcN5H2IenXQ1PKgtLUoaTMTWnmptahpM4tKXNralOTsZRmtKSO1VLGSspo27Zj/bTDzXC5+ZPfm/iP1PKVybb3tV86OjellNr1Y2XvoozMz7h18/hzegO9S1Ozouss98fVn7smX7rm2p+4rZSk3u1p9Oabbs77L39/XvTSF+XwIw+f5oRMv7K6V3p/u2nb+CuSfLTrNAAAAADAz3f2tWevqP36G01tzqi1zurr1VOmZklqfrk0Zfjca85924WPv/C6riPBPVl/9ktWlMnJ36glZ9TYv8mdE5KTXx5oyvCtr3zB25Zf+pf2LwAAkCT5x+/Wxb2BiQeVfo4rTfvwWuoD25QVpdZlqVmaZO6O0ltJktS7FeBqalKTksxPrfPz43tlx59LajKelJNSyoZe01/3ybX5VnPD5Ffbfvsfm0c3f+u0hyzfPr2PmL1R03UAZo5aa2/Dtokn9gbKe5PZXUQeHR3Np//pU+lP9pMkc+bMySGHHJRjjz0mxxxzVBYtWvij+264dUPee+l784O1P+gqLtOqrEwp77ttZOLkWmuv6zQAAAAAwM9ac+Wahb1+7xmpeWlNPbjrPDNKydJSy3PS5sVv/NIbD+g6Dvy0DWeeuaj0J36plry0JvbvT1qa1Oe0pXfmzS/7zWVdhwEAALr1j9+ti//5uolTes3k75e2XJKmeUNNXpCaU1LrQ7Kjwzd3Cpaas+Nc9aEpeVKSF7Zt/kdKc9GS+Qf8wT9fP/GUT11fl0zBOuzDTEYmyZ1F5M0TLyy9vCslC+/7iJnt2quvzfbtO35gY3BwIIccclCGhnY8Lw8M9HLQQSvS6/WyefOWJMnm2zfnQ3/+oZz+26dn9eGrO8vNtNm/nawf37Rt4tW11r8spfS7DgQAAAAA/NiWwS3Hl1penJIj4kNDf0ZNPbCU8tyx/ti3k3yw6zz7onrFFb2sWzeQubf1NkymKdvnlSSpC0fqgQNpM7Z/PytXTpbTTtvnrj/XBe1x/VpeXJIjus4yQx1YS3nuwODQt5P8RddhAABgd4xe+pYj234eWZrmAbXWg2rKwiQpqdtLKbfUtv1O08tXhl75xu91nXUm+sfv1sVNmXxkKZPPSskpJWVVkv13fHXPXggpOwbYLk6yOKWsLsmDkjyxTf9Ln7ihfuyOkfzrrz6obNqjIdgrla4DMDNs2DbxxNT6f8s0FZE33L45/3DlFzI6Np4kef4vPiFHrzroHu/b1uSOyX7aXXievfSiS/OfX//PJMn8+fOyevWhKeVn/7nfcsv6HxWSk2RoaChnv/7srDps1S48Gu5NSbJgsJfez3m22bxte9751x9PkgwODOQZJz8uq1cun65425qB8sz95w1eNV0LAgAAAAD37rxrzntgbev5KfnN1MzvOs8MNp7kc6WUN73jxHd8vuswe7t6xZo5w+vnLWtKXlSTlyc5bCcP/X5JLm9r/mL+ipGN5bQ143syZ9dufuXpD2pK7/yU/EZi//48NRlvks81pfzRge9+/+e6zgMAAPdl+LI/OaTtj5/fpDyplBxRaxbtzHGlZFutWdumfqbpzXn7/Fe89qY9nXUm+3EJOfdQQu5QSZuabbWU7yf1y6XmHwaHeteccnDZ2HU0Zo+m6wB0q9barL997Feb5P9MVxF5OowOj/7ozwMDgxkauufrXcuXL8vSpYt/fNzoaD70vg/lxu//YI9nZEZY1E7Wj27cOvacWqvnQwAAAADo2PlXn7+8tvW5SZ6tiHyf5iR5XJIXnXvVuUd2HWZvNfyuCw4dueSC94zcOm+slNxUkzdn54vISXJYTd5cSm4auXXe2MglF7xn+F0XHLqn8nZp3e+cvrzp9Z6bkmdHEflelWROTT1hsq1nrH/1i47qOg8AANyTWmsZvuSCs4YvvuDG9Cd+0KSck+ThO1tE3nGOLEry8CblnPQnfjB88QU3Dl9ywVm11n1uiOonbqqrBnrtWaXJhaWUF5aUX8hMKCInSU2TZEmp9WGpOTWpvz8xMnn+p26oD+o6GrOH8t0+bsO20RN7A+XSmrpf11mmUml+/P2qlJIFCxZl7tx5P3O/Xq+XlStXZL/9lvzotptvujnvevu78/2135+WrHRu/5Rcduu2kRO6DgIAAAAA+7p++seVlNOSLOs6yyyxqKY+OSW/1HWQvc3YZW976PDFF1yXJjfWmpdO1XlrzUvT5Mbhiy+4buyytz10qs7btVpTmjm9R6TNryc5oOs8s0NZmOTJtZZfrmu8ZwsAwMwyfPEFrxu55K3DqXl3kkMzNT3DJsmhqXn3yCVvHR6++ILXTcE5Z4VPX18f0Iy35yb1VTOqhPyzSkkW1ZSHp5QX19r/vU+tnfhvV1xRe10HY+bzwnYfVWstt26dOKlpmr9KsqLrPHvavRWSSylZvvzALF3640LyyPBIPvS+Dykk7zPKyl7p/e9NwxOP3xd/8goAAAAAZoLXXfu6Y0pbfq3G1J1dUnNISXnWa6957eO7jrI3GLnsLYePXHzBl/r99utJ9uTE2qP6/fbrIxdf8KWRy95y+B5cZ1psPOuFx7S1Pq+WPLDrLLNJKeWgUuov33Lr6fYvAAAzwujlbz1q+OILapK3Jhnag0sNJXnr8MUX1NHL37rXflrIFd/85pxPfGfiCW3p/2GteUGSg7vOtDPKjl7p8lLLM9u2/N7iR028+ONrt6/sOhczmzLyPmrT1olH95r6wdSyquss0+XeCslN02T58gOz335Lf3TbulvW5b2Xvjc3fO+G6YxJZ8rq9OuHNm6ZeGTXSQAAAABgX3P+f5y/oD/Zf1It9TlJ5nadZ5YZSPLY1Pz6G656w171KYjTqV5xam/44gvOqf3mupo8ZtrWTR5T+811wxdfcE694tRZOWnq1leeunAy5cmp5dklmdN1ntmlDtS2PLZpeqf98FUvNFEaAIDO1MsvHxy+5IIr2ol63XSv3U7U64YvueCKevnlg9O99p70j9+ti5fMP/Y3y2BzUZJnJvXArjPtqpq6qJQ8vpfe6wbaub/78evHHtZ1JmYuZeR90LZt9cA0uajWHNF1lulWSsnChYvvsZDc6zVZseInJyTfftvt+cB7PmBC8j6iJkeml4tu3lp9BCQAAAAATKPJLZPHJvmlkjLr3pibCovmLMoRi4/Isnm7fWlycW3rSWMZO2kqc+0r6sVvPmDk1kd/LsmFSbooBPeSXDhy66M/Vy9+86wrpJay8AGlKc9Iskf3b+/A5Zn36Mdl8PAj9+Qy079eyaKaclJJz/4FAKAT2y572/KRic0/TM2pnYWoOXVkYvMPt132tuWdZZhC/3zd6NG93uTrS83/TK3HJ1nQdab7YW4t9eimNC8YLL3Xf/r6+uiuAzEzKSPvY27dXleO1LG/S3JC11mmSynlZ26bP3/hPRaSSylZvnzZTxSSN27YmA++94OzckLy1i1bc9WVV2X7tm1dR5k1SnLiYMY+sn57XdF1FgAAAADYF7z62lcvbprmCal5QtdZurBozqI86sBH5blHPjdPOPgJu11ILqUcmya/fPanz3ZtcxeMXvyOBwyn97Wknth1lqSeOJze10YvfscDuk6ys2572cuW9Ev7xFJz8p5cp3fg8sw/6ZQseMZzMv+Up+/xgvB0r1dSj+019Znrz36J/QsAwLQae/ebHzjQb7+TZCaUgJcP9NvvjL37zQ/sOsj98U9r6+G93uBvl1pemuTorvNMiZqmpi5L8iv90j/7UzfU47uOxMwz0HUAps/atXWol/E/qqXs0QtCs0HTNFm4cHGSZGxs5Ce+1uv1ctBBO671bN68JUmyft36XP6uy/OKc16R1Yevnt6wu+kb//HNfOA978/o6Gj+5i//Jm96+x9mydKl91jO5ieVpnliaUffVGs9q5Qy1nUeAAAAANibzZmYc0xt6pOTLO06y3S7q4h84kEnZr+5+2Xp3B1/BZ+/+fPZOLJxV0+3IDWPGZgzcEKSj0511r3R9nf98S+0mcyw9pAAACAASURBVPxMSfbvOstdSnJwm8kvbn/XHz9p4Wve8B9d57kvo3NGjmlK78m17rn9e1cxeOjRj0+zaHGaRTve3xm+8hOZuOF7s369O80vNY/O5Pjjk/yfPbUIADtn7dq1Q3Pnzn1UklOTHFJr7XT6VyllvJTy9ST/96CDDpp9U9SAGWv7u//4YZMlXyjJ4q6z3KUmSyZL86Xt7/7jkxa++g1f7zrPrvrEdcOrmrRn1ORFKTOi4D3VlpTkmbXtT/7T98b+5BlHzv1a14GYOZSR9xG11oFN28Z/r9bygq6zzCQLFixM8rOF5CRZvnzH9Im7Csnbtm3Lh973oZz+26fP+ELyd/7rO/m7v/7bjI6O/ui2t/7h23La80/NcY/0gyn3qaaU0jt94/bxW668sv7BKaeUya4jAQAAAMDe6GVfftn8OlYfkzYnZR+bo/DTReQkWTCwIMctOy7JbheSH5BennrOled89qJTLto8tYn3LtsuvOBBTZN/yQwqIt/N/k1T/mXbhRecvOjc3/2vrsP8PDe/7GXze2Xi0an1xLqH1vjpYnCSlKF5mfvghyWZ+oLwdK93dzV5QG3KU28/54wr97voA/YvQIfmzJnziFLKG5KclGRBkoku85RS+rXW25IcdP3117/1qKOO2tJlHmDvMHLZWw6v/fKZzKAi8l1KyuJS8pmRy97y6HmveOOs+SGMf76hHtSr7Qva1Jek5qCu8+xBS5M8q5eByU9/v/7JUw4r/9l1IGaGpusATI9N29vfyY7/WJ7TdZaZpJQdE5Lnzp33M1+7a0Ly0qVLfnTbLTffkgv/+ML84IYfTGfMXfLt//p2Lrnwkmy4dcNP3L51y9b8+Z++P//4D/+UWvfUZcG9R0nmlpT/+bBHTby06ywAAAAAsLdaNLzo8NSclLJvTUW+pyLyXe4qJD/h4Cdk2bxlu3TekjK/re3xafKIqcy7t6nvevOBvcHyiSQHdJ3lXhzQGyyfqO9684FdB/l55s6dODy1nlT30FTzeyoG3+WugvD8U56ewcOPnJXr3YP5pTbHjU0W+xegQzfeeOO8JMfXWk+ptS6ptQ4kmdflr1rrwiSrkzxmaGhoj30jAvYd6972tgVpm08m2bUXndNrWdrmk+ve9rYFXQfZGZ/+YT2gTE6c2ta8LDWHdJ1nGuyXUp9b+/2zP/O9emzXYZgZlJH3AZu2TpyQTL4+2dfmSuy8BQsW3WMhOdkxIfnuheSJiYl86H0fyvfXfn+64u207/zXd/Lhv/hw+v3+PX69bdv808f+MR987wdz26bbpzndrFRS87vrtow/tusgAAAAALA3akt7bJKTu84xne6tiHyX+1lIPrZpmn3q73RX1Cuu6I00vb9P6qqus9y3umqk6f19veKKXtdJ7slkW46te2j/3lsx+C5TWRCe7vV+npp6bEm1fwE6NHfu3F7TNAuTzO86yz2YW0pZ2HUIYPZbPL99X605pusc96XWHLN4fvu+rnPclytvrQvbif7TSlPOTOphXeeZNjX711KeN1Ha3/nkD+rBXcehewNdB2DPunnr1mVt+h8saWbBRbU9Y2eGAJdSsmDBoiTJ2NjIT3yt1+tlxYoDU0rJ7bfv+FSsW26+JZe987IcdMhBWX3Y6inPvDs23Loh133nugzfMXyv96u15stf+nK+d931eeFLX5Sjjj5qmhLOUiWHDdT6F5s3bz5h6dKlGtwAAAAAMEXOvvbsFWWyPDrJPvOG1c4Uke+yYGBBls9bnnm9ex6kcS+Wpslx515z7tEXPv7C63Y77F5qeP3aN5SSk7rOsQtOGl6/9g1J/qjrIHe3/uyXrOhPTjy6SZny/bszxeC73FUQTpLhKz+RiRu+N+PXu9fz75gyfdytr3zB0csv/Uv7FwCAKTd6yVuf1tb6613n2Gk1vz56yVv/fOhVr/9k11F+ntFtEw/qleY3k/Kg7GvDQms9oNT6tLat/5bkf3cdh24pI+/Fbq916eS2sfeX0hzddZZu7UQbOfdeSG6aJsuXL0utNZs3b0mSbN+2Pd/91nfz3W99d2rjTpFSSurdmtgnnXRivvGNb2Tz5i2ptWbTxtvyvkvel+ec9pwc/6jjMzg42GHaHxsZHcu24ZH7vuP0OnZiYuIv3vcPn3ndD9Zt7CTc4OCcesf28dG3vOa0DV2sDwAAAABTrTfZO6LW+uhSyoyc+jrVdqWInCQ333Fz/m39v2XD6C5fEmxSc3Sp5ZFJlBnvZtvFf/yQkqzpOseuKiVrtl38xx9ddNYbvtl1lrvUdvKIpuTRSaZ0/+5KMfgu96cg3Fs2vevthKamHl2bQfsXAIApVy9fM39kvH5sttVl27Z+rF6+Zr/y8jX3PqGxA1f+sB46MdE+NzVPSOqcrvN0opQjm5LnfeZ79ZtPOrL8R9dx6I4y8h6y5tK/OrIM9p5Xa12eNJ1k+Ou//9SDVy7b/ymlzLzvICNjo5mc7Hcd42fsKCTv+FSTn1dIvvuE5Jls2bIDsmnTbWnbNkly4IEH5uSTT87/+39fzQ9/+MMkydatW/PhD3441337ujz7156dBQsXdBk5k/1+rv3aNzPQm3nvPdTUZ2y7Y+ShKe1oF+tPTo7VuUN1dM3lH/5cUt+85uW/tbGLHAAAAAAwRUpt6+GlKcd1HWQ67E4R+bM3fTbfvP2bGZ3crUuSh6Xk+CRXZGcnduwDeqW8N3VWvjc20CvlvUlO6DpIktSkrG9zeJocN9X/upqheektX7HTxeC77E5BuLdseeadvGtF5LuvN3DgrufcuZOXw0rq8TW5oti/AABModHxeeemZPYVZkvmjI7POzcz7BNjrrmxzts+Nn5ymoHnJnVJ13k6NJSaEydL+6tXrq3fP+WIMvOLdewRs/GCy4z3++/56+e3yeWpWbBj8no31wnWb7ot6zfd1snas1kpTRYu3HHx6KcLyb1eLytXLk8pJdu3b+8i3n0aHBzMoYcenOGfmi5cSsmiRYty0kkn5qqrrsrNN9+SWmsmxidyzVXXZOOGTXn+i5+f/Q/YL10V2Gut2XbHjPshprsMJDmiu2r/nc8jpTwibQ5bc8UVv7nmtNPGO4sDAAAAAPfDqz//6mVNr3lITd1/b6/adVBETpKFqXnAOV8857CLTrjoht09yd5k5JILTqk1j+s6x26redzIJRecMu9Vv3tl11HWvfrFy0rbPiS17D/V557ccGtG/+3aNAsXZ/Dwo3bp2F0pJN9VRJ63G0XkJOlvvDWjX/7iVE9F3qFmYVIesO6cMw7LRR+wfwEAmBL18svnj0xsflPXOXZXLXlTvfzyC8vLXz5jikVbJ/KApvSem1p37cXL3qhkWWp92mTt/2uSj3cdh24oI0+xNX/214+rNReVpNsRs9xv8+ff84TkJFmx4sAsW3bAdEfaKU1T7rVMXErJypXLk9TceuvGTExMJEm+861v591vf1ee9bxn5xGPPn6a0rJbSnlONrdnJfmTrqMAAAAAwO4YLIMHp+bB6eqjBadJR0XkZMeklFVNv3lwkn2+zFiTMlrLpbN+yGwtl9bkwV1Py21SDk4pD657YP/W0ZGM/efXkyTzT3naHikkT0UReeSqz2Tk376YdtvWXT5+J5Q27apMFPsXAIApMzJ52ytm+0vwHY8h7+g6R5J8fG1d2aR9dq15SkkGu87TuZpekofVkl//5PWj33naUUPf7ToS008Zecq1lyfNsmRHKbQpzY5LfvyEWpN+vz9Nq+3e/wFN8/MnJCdJrzd7v0GXUrJ48aLMnTs3N910U8bGdhSSN27YmA+8589z26Zn5ZSnPim9Xm9ac/V6vRx37FE5YOke+FizWa4m+a/vfT8/XLchKWmS9vdrrReWUmb51XMAAAAA9kU19aAkx3adY0/qsIicJCmlrKy1PiDJP97vk81yd1zy1l9oan1g1znur5r6wDsueesv5FWv/2qXOfr99qBScuye+pDFPVlIngVF5CRJk2Zljf0L+4LRS99yZL9tXpLUR+24pXy517TvHXrlG/fA6HUA9mm1eXvXEe63HY+h8zLyl79cBze3/Ue1pTynJPf9gn/fsSClnJgy+KQkysj7IGXkKbTm/e8fKhPNw+5qBh7/oGPy+OMf2mmmmWrD7Zvz0U9/IaNj43t8rft7MWzBgoWptWZ8/P5f/J1p5s6dk9WrV2XDhk3ZunVb2rZN29Z89CP/kB/+4KY863nPyv4HTPmnrP1cvabksENWZPXBK6Ztzdlk87ZtO8rISUqaBa9597vnJBnrNhUAAAAA7Jo1dU2z/ZrtB7W1PbLrLHtK10XkJKm1Lk9y9BX1it5p5bTpmg4yI5W2Pfd+v1kwQ5S2PTfJi7pav65Z06zb+P2DkvbIPTmNZ08UkmdLETlJ2tTlTZOj66mn9spHPrJP71/YG125Zs3AYw+Yd2FKzmrbu55Nf/Sc+tS2bd44fPEFSc3FX9o0cu4pa9ZMdhYWgL3C9j+7aEXG9o56yfY/u2jFwpees77LDLcuGVs9mIFnJPVBXeaYkWo9tCZP/cTasc89/Yi53+o6DtNr9o52nYEW/NQY2YGBXnq9xq97+NU0zawZGF1Kkzlz5nQdY48ZGBjIypXLs3z5gT9x+1f+9St5x1veke+v/X5HyQAAAACAvdHoF0aX9Gt/VZJ5XWfZE2ZCEflOc5Ks/PLVX96npz/USy5ZWJrm9K5zTJXSNKfXSy5Z2NX6P1j/nSWpWVVS9vj+vauQPHzlJzNxw/W7fPxdheT5pzw9Q4963KwpIidJSeakZuXGFYv26f0Le6Oxd739wY9dNm8iJWfd551LznrssnkTY+96+4OnIRoAe7FmbPSyrjNMlZnwWAZ6vaPaUk9KMtR1lhloTkl9eJPeCV0HYfopI8NOmS3V6d1TSsl++y3J6tWHZu7cuUmSWmu23L4lf/quP801V30xk5N+4BYAAAAAuP/Ghsb2a0pzSNc59oQZVES+y/4TzcShe+LEs8Vwf+sxqXXvuchfaxnubz2mq+WHhob2a0qmbf9OVSF54S89Z9YUke9Sa9l/skzu0/sX9jbjF7/5sf2m/81dPa7f9L85fvGbH7snMgGwryjP6TrB1On2sXziurq81ubxJaWz12V72g9vXJtvfO0r9+MMZVXb5imfuGHkiCkLxaww0HUAYOZYsGB+Vq06OOvWrc/27cNJkm1bt+Vv//dH8t1vfSenPv/UzJ8/v+OUAAAAAMBsVifr0ra2B5W9bAjEDCwiJ8nS0paVe+rks0Ez0Pu12tauY0ypZqD3a0n+Xydrj9el/dSDpnP73lVITpL5pzwtg4cftUvHl6F56Q3t3iDn/oZbM/yFz2R0movISVJLlpY6sE/vX9ibjF78jgdMZvLa3T1+Mr1rRy9+x7FDZ533nanMBcA+Y296Ad7tY2knjigDzQnp8NOeRkaGs/6WH+bW9Tdny+bbsnXr5mzbsiWjYyMZGBjI0NC8zJ07L/vtvyyHHXF0Vh68KosWLdmpc9980w9yzVWfzuIl++WhD3/k7kYcKqU8vKmDj0mydndPwuyjjMxeaXBw8Ed/rrWm1ppS9qbvq3vO4OBgDj30kGzYsDG33745bVszPj6eL3/pyxmaN5RTf+vUNI2h6gAAAADAbprM4lLKgVN5ykVzFmXZ0LJsm9iWjSMbp/LUO73+DCwiJ8mitm2X78kFZrra1ud3nWGq3fmY/kcXa0+WurgkU7p/d8b9LSTvji6LyElSkkX9+v+zd+fxUZXnHsB/zzmzZyULCUvCvgqICFKRi6JWa63VLtHbRUWqgAtWrdWq2E4VrNjeIuIC1CruFbxdbHu1brjLDrIl7GHNvmfWszz3j5BAIGQ9k5kkz/fz4WOYOed9nwRnJuec33levUe/foXoThh6h28iOT5GnAXlCCGE6EGqn1w4Ito1WK36yYUjEu+6f1dnz/ufrzlOsZsTGJgI7tybXivKS7E7bxuOHD6AosKjqKooRyDgRzgcQjgcghYOwzB0kKJAVVWoqg1OpwsJCUnolZKGrAGDMWzEGAwYOBRuT9O/ThQVHsUnH/0ftm1Zj3PPuwCGoUNV2xsv5SEMXPbeIf7ssmw61v7vXHQlEkYW3VL2oGzk7cwDAIRCIQSDQbjd7bshxeerxdGjR6AohOTkpB4RaiYipKenwe12o6ioGJqmg5nx1WdfYdiIYZgwaUK0SxRCCCGEEEIIIYQQQnRVCuLASLFquPog8Dnp5yC/Jh+fHvu0UwPJMRxEBoA4UqjloropXrbME9AqB0S7jggYwMuWeWj2bH+nz0wcx4yUaHQ278xAcrSDyABAxHE2Unrs61eI7iTw9MLrGejw8rMMeAJPL7zefcf9r1hRl2jajh07giNGjKgAoCP2MjU+Xdcrol2EEKJrsdlwRbRrsNrx76nTw8j2BPTXmL9BQKf9nl5RXood2zZi5/bNOHJoP2praxAMBGCaRtM7mCYMXQcQQsDvQ2VFGY4dPYgD+3Zh25b1GDBoGMaOn4TBQ0YiPiGxYbfSkkJ8/vF/sHHdZwj4/aitqUEwGERcXHx7S3cDNB66MRHA2+0dRHQt0t5UdEtTpk6BqqoAgGAwiIKCgnaPtWfPHhQXl6C4uBQ+X+ef14sWIkJCQjyysvrD4ajrNK3rOv668q/QNC1i8zIA5h76J2I/VSGEEEIIIYQQQgghYocK1Q1GYstbtuzkIHC/uH4YnzYe0/pOQ5o7zYrh2zR/DAaRAYZHIcWSn3VX5NOruu33Hq3vTYXiJlDUfq71gWT/6veg5e+LyByxEEQGAGZ4ovmzFkJYh4HfxOJYomnTp0/XmXk96oJTerTrOcke0zTfdjgcsty9EKKtzo92AREQle9JM43BBJ4ERP7uzGDAj683r8WqN57HO/9ahW1fr0dxUQH8vtozB5HPwDAM1NRU4fCh/Vi/9lP862+v48P3/oGiwqMAgIqyEnz52QdY+9Vq1NZUwzAMBAI+hIIdy8kxcxaBxnZoENGlxNpdXD2Kpps9NnyoR/h7T+udhomTJ2Ltl2sBAIWFBUhMTEBaWttXDgsG604IMzMMo/k3c0VR4HK5oKoqNE1HKBQEW9SWn4jgcDjgcDhgmiaCwRAMI/LHPk6nAykpvVBYWAwA8Nf6UXC0ANkDsy2fixkIaQYC4Vg6pus8CgFOuw09oPm2EEIIIYQQQgghhOjJGE5Qx5cYbyoIHGeLw/i08QAQ8Q7JMR9EBgCCE9xzl3O3GYgzu2lbHpsRnX9XhukEUVw0L3BFskNyrASRAYAZTkbPff0K0c1Y2co9cm3hRQPTNPNUVZ0H4FUiSjr1+VAodK6maf/NzKc9115EpNtstk9dLtdfTn2OmQ1FUY4R0dbMzEyfVXMKIXoIwrBuF1AjDOvsKf/zNccppI0AlEGR/nH6fDXYuPYzrP7gXygtLYIWDlsyLjMjGPDjyOEDqKwsQ1lpMcaf+w0UFx7Dl5++j+qqyvotEQ6HEAwGOjplLyYMXX2Ak6cPosqWNxddnYSRo4QZ0AwTpkVB1a5GM8yIz3HJ5Zcgd0cuqquqYZom9u/fj/j4BLhcrnaPeaZ/LiJCWlo6+vbtB0UhAARmhqaFcfjwYVRXV7V7TgBwuz3Izh4At9sNOp5UZWYUFxehsLAAphnZn6fbfeJnZppmRDtEM3OPfV10wo1TQgghhBBCCCGEEEJEHTM7QR1bqry5IHBnBJK7RBAZAAgOZu7wsvBdlQbdqUKNdhkRoUF3RmNeNqnDr19L6ohAIDmWgsgAQAQHqOe+foUQIpqysrICAHJXr169Z+jQofZTnw+FQgFd1682DCPFqjkVRdEMw9hls9nePPU5Xdc5Pz9fnz59es/s6iWE6BhGarRLsFwUvifqhSTW1f4Atz941grlZSX46vMP8dXnH6C0pKjJbRRFQVJyCgYOGob+AwYjMTEZbk8cbKoNoVAQfr8PFeWlOHokH0cP56OyoqzR/qZporqqEls3r8Wh/L0IhYKorCxvtI0WDiMY6HAY2QZQhqGgLwAJI/cAEkYW3Vbf/n1x+Xcux1uvvwVmRjgcxtGjRzBkyFBL57Hb7ejfPwtJSckNQWGgvpOxE4MGDUZJSQkKCo62q0tyenpv9OnTF6ra+IQpESEjIxPx8fE4dOiQFXejnJGmaSfmVQgejzticwkhhBBCCCGEEEIIIbo3IlIY3O6EaGuCwJEMJHeZIDIAMBSgm6ZxW8FBitq2xWu7DgcpUfp3NRUgWnM3ZmUgOdaCyMd16L1SCCFExx0P/54WAN65c2eYmcHMlq3BwMzEzPrxILQQQlipO64X0+nfkx4KJ9tVNTOS7RVLigvw2ep3sfarj1F1SjgYADxx8Rg4aBhGjBqH7AFD0Cs1HfHxCbA7nLDZbCBSYBoGNF1DOBSEr7YGZWXF2L83D7tyt+LIoQMIh0MN4wWDARQWHGmyFk0LIxi0oFklmymmwf0B7Oz4YCLWSRhZdGtTL5yKA3sPYMPaDQCAoqIipKWlIynJmtVSFEVBVtaAZsdTFAW9e/eGaZooLDzWpvGTk3sd77Z85s/QuLh4ZGcPwP79+6Dr2hm3ay9dN1BWVtHwd4fdgYw+GZbPI4QQQgghhBA9QfWyP6TZNXM+gy8DkAwgDkR1HXaYNQA+AJUEek+zK/MSZ98bubXlhRBCiC7KrtiR6kptMQgciUBylwoiC2iGQYqte14K0wxDltpDXSDZKCmCWduxAHHDOLETRBZCCCGEEMISzKgiQv9o12ElBjq2RH07kF1JYhOZkRq/tKQIn338H3z1xUeoqW7cRNjticPgoSMxfsL5GDx0BJKSU+DxxDeZJ1MUBTa7HW63B0nJKcjo0w8DBg7FWWPPxc7tm7Bh7WcoLmo5v6ZrYQSDVpzHoBTm7vX/nziz7nkGRojjVFXFt676Fg7sO4Cy0jKYponc3J0YP/4cuFwd75ofFxeP+Pj4FrcjIqSlpaGysrzVb9Q2mw19+vRtNohcz+PxIDExEeXlZS1u2xbMjLKyMgQCdTUTES791iWW/OyEEEIIIYQQoqcILPn9IFbMhWDkQDNwWueEE6voOI7/6cXg2TbNmO1/eiFAWEWmcr977i8PdGbdQgghRKyqCdfg67KvkexMxqheo5rd1spAsgSRux67y6kbevfsjWx3OWWZdgBqem+4Jn4D9gHt74p8YpzzYdZUQ8vfb1F1QohY99SG3MvYxA2s4CJi9AVQC2ATMb1Z7nO+6J0+yJIEjgVjCCGEEO1GxPsBOivadViJgE4/V25nJJlEmSedz7dMVWUF1q35BGuaCCLHxcXjnIkXYNr0b6F3Rl+43J42ja2qNiQm9UJ8QiLSe2ciK3swvvj0fWzfuqHZ/TRNQyhoQbN+QopClL2SWb2WqHseoIsGEkYW3V7vjN64+LKLser1VQAAXddx5MgRDB48uFVB3+YkJMRDVVu3QpbNZoPbHdfqMLLb7Ybdbm/VtkSExMQky8PIpaXlqKg4cTPR8FHDcdGlF1k6hxBCCCGEEEJ0V7VPLshQbPYtDDPz9ARyGzBymMwc/9NPFJq6Nj7+roeKLCtSCCGEiA4NjBAIznbtbGrIr85v+HtnBJK7cBBZAxBqcatuig0t3D1XJK7/3qIwL1QN4BChfa9fK6npveGZOh2uSVOgJCR2aCxyueEcPRYA4F/9n5gIJBOgAdRjX79CRNKi9bk/UoDXmQEQQCeO2RMAXMjEF/aKDz67eP3OTwyt8op7pkxpYxKH6fYbfz1aJ/OfBBqkmQy7YlkmWe5wEkII0SYEZQODr4p2HVYiQvNJ2oiwJQGm5Z2RTcPAoYN7sWn956iuqmj0nNsThwmTpuKyb38fqWkZHcq5KYoKm82OqqoKFBYcaXF7TdMQClkQRmZOgkJD4/KRDqCw4wOKWCZhZNHtKYqCaRdPw45tO7Bz204AQHFxEdLS0pCcnNyhsZ1O92mPMTMMw4CqqiA6cVBJRHA4WhcuBgC73d7kh4hhGFAUAlHj51yu02vpiOrqGpSXV4CP39GTkpqCa3Kugd3hsHQeIYQQQgghhOiO/M888XcwX40OpZBPxZmKzVbof+aJf3huv+8aCwcWQgghOhcjDIIfHQgzdmYguQsHkQFGmIj80S0iegxT8VM37UdpmEpU/l1JMcPM1KHXrxWsDCLXi7VAMgNhAnrs61eISFm8PjcfwIDWbU0XqvZe1Ys27My+e+Logpa2vv76e+M8qutD4ofPNQg2Ot4UeVO5jslprb9O3GxFjDcsGUh0iM1m0wzDCNls1kVuiMggIln5QIgIeHJj3jgYyCHib4DQF4x01N2A4kRdB/swgFoGyom5AMB2Jvztrkmj349m3VZh6O8D6m+jXYeVWKEPOnO+/3zNcSCzH5lIsrovcmlpEbZuXndaQNjpdGH8hG/gsm9/H+m9+3R4nmDAj21fr8enH/0fykpb7neia2GEWtlwswU2NjHVTubv3t9v7DXAhxVV3RcwsPfqwSSNV7oZCSOLHoGIkPPjHDz35HMoLiqGaZrYs2cPxo4dC5fL1YGRG3/EVFZWYNOmTaipqUF6ejomTDi33eOf2tVf0zRs3fo1jh07CqfThbFjx6JPn75nrKUjwuEwSkpKYZomAMDpcuG6n16L/ln9LZtDCCGEEEIIIbojfuqxdL+i7gFzUuQm4at9Ty+s9JjGMLrzwZKIzSOEEEJEiAkzSKAaAC0ne5vRGYHkLh1EBqAoNvIow7+zeH3upQAyASQDcBERwBxioApAMYB8ELbDND8c5xv9yfTp3SMI41EC1QG2tpFHrPD7URONeU2Tg4pCNeCOvX47IhJB5HoxFkgOmibXRrMAIboT7+rVtpT4PqWMNh+v2xSmY4vW7T7n7vOGbzn1yVmzZtkpmP44KXQzgLo3pVNuhPnfg8G1k9Psk9tZeiOujMAcK8YRHeNwOMqI6JCiKEMtHDbAzFUtbyaEaI0la/MmgzGwhQAAIABJREFUsoqFzDweJqc0vDc3Ha1xAEghIAVEQwH8FwG3Ll6fGwBhNwzziZ9PPuv1zqrdavdt9LufODch2mVYyl3k/6qz5vq0gNPDQeNi08RlsDhrGQoGsSdvO7Zv3QBd0xoedzpdGD12AqZd/G1LgshaOIzcHVuw+v1/orDgSENjymb30TWEghZ0RgYAcH9i+gEAnwKqJdOsdjPv/uCA/i409bNLh1P0l6YRlpAwsugx0nunY9rF0/DWG28BAEKhIPLz8zF8+PB2t7EPhU6cTK6trcWrr76CUKhuxay9e/egoKAA3//+D0BEYGZoJ31wtETXNZimCVVVAQBfffUl1q9f1/D89u3b8OMf/wSZmXUfOkFr7kaBruvIzz8MwzAAAKqqIufHP8RZ48ZYMr4QQgghhBBCdFf+P87vF1DUI53RfI+ApICiFvv/OL+/5555RzthSiGEEMIyJpt+lVRLghaRDCR39SAyABCcHjslnfZDOX7h0XX8TwaAsWBcBVIe2Bqf53tqQ+5aML+UeWD7a9dee63RyWVb5rYvgvZHz3OFPDaKahffCChOu//+6IRUSfUjikGpSAaR68VQINlPCiqjNbkQ3U1KfObadgSRGyhkbF74eV7i/VNH1ni9XqXgoP59Yn4WYUpH05eaD4L4D0tfXPAMAH5iwuP3guj37Z0fAEzmX9K13nBHxhDWsNvtIQA+snYJBp2I5N9XiA5asi7vJpP49yY41YKefm4wzoaivLZ4fe4ygF+t+PfK271er2lBqRF1880PZth0WgbQdJ2RyDjtXpmujKkT/g3e3RscSop6TSjI5zPzaEDpa+1KiEBpaSF27tiCysryRo9n9OmPyVOmIyt7UIfnMAwDe3bvwAfv/QNHDuc3NKZsiaaFEQxZdm5DZXAC6jqS1zXoVGgkA5NMm5H7/gHjQ1KU9y4dQDutmlBEh4SRRY9y/tTzsX3rduTtyAMAVFRUoKKiHKmpae0ar6amBmlpvaGqKnbs2N4QRK6Xn38AR48eQf/+WdB1HT6fr9VjBwIBhMNhuN1u+Hw+bNq0sdHzzIytW79GRkYmAKC6uuPno0zTRGFhSUMQGQAumHYBzpl4TofHFkIIIYQQQojuzP/H+f3gsB/q9Ikd9kP+P87PlkCy6Gqqqzk1pGoDCUp/mHwegMkw+Two6FCbFmJUM2M9FF6rM9apJh0JKcH8/omJZRaVLoSwgGpTa9jgMqvCG5EIJHeHIDIAKLBDRZtX74tjxsUAXVwwaOwfF2/IW1VRM2Kut8t0S2aaPfPhmYqJWxg8cUOZrk7LsEe7KIvRm2T1VfBWUhXUmCbKohFk6Iwgcr1YCCQzU61isvwOI4QFntqQexkzJnR0HAeFP5szY15GYb6eWfc+eNq7YZiBZctWzL/z1Cc8c3/1h8AzT9zGzO1KFZWHTMzf5vut1+v9Y1cIwQkhRGd7cvOuSaSbX5rgSGXh4gGa0+vK62YtuvLaB+6eNPqJCM3Tbjk5OWpq/IhfsYlfkw7Hyc8VBkz0cbevUWOsYVBuJMd/d0dViuKMu5AVXKcQTWU20wByRuIQrKy0GIfy94JPCggnJfXCuPHnYcTIsbDZOn4sm79/N9575684uH8PDKP1h/WGrkMLR/AeGWYPA0MI6G8yj1dM48L3DugrA6x+dPVgKorcxCKSJIwsehSny4mbb70F8x9+FJUVlTAMHbt378bgwQbS0tIauhC3Vm2tD7W1NUhKSobf7z/DNnXNCUpKiht1Um6Jrus4evQIhg4dhkAg0CggXC8YDIKZEQwGUFXV8UYEpaXlqKk5sbLbkOFD8b3rvge7vbudqBVCCCGEEEII6/BTj6UHFPVIlKZX4LAf4ace6013PlgSpRqEaBYzU1mVfjHbzBkK0xgGDQ5DSyQTAE66hm7B9RAmJIJwCUCX2AiACrjgQmlNuJqB/US8DaysSI23rSaiqIS4hBCAznq1jWyWXliyMpDcXYLIAKCQAyq5OzJEKpjn9IrPu/HJ9bl/vmvSqLlW1Wa12T97aBoZ9Bvg4UkwkVD3Jk/YXK6hG4aR34jWzAylmmB0+oXhzgwi14t2IJmIq6CochFeCAuYjNesuIlCcdjPJoXAZuNDCQL+CkX/5XMvPN7sG4Xr9vuG7F74WHlWnJrclnn3Vut4dncAADyF+fpRAB1fr10IIbqJP3552K3aa9dAN8d10pSKAlq4eH3uQ6rK4+6YMPpgJ83bpBkzvC4nhy8gUt4AkA4Gmrrv97UDAdw7Oq7T64sEOykzIjX2u3uDQxXFfhOA7xE4m5kj9kOrranGofx9qChvfIN0n77ZGHv2JLg9HZ86f/9uvPvvVdi3eyd0XWvTvswMTQtDC4dhdzha3qH9nAT0Z0YqQCPdbFz4nwP84uWDaG0kJxWRIWFk0eO43E5c8d0rsOq1VdB1va4d/Z7d2LNnN5rqxHF8ubrj/+VTnjNx6NBBZGcD2dnZ2LJlc6N29nFxcejTpy+Ki4tQVFTY5lpraqpx5Mhh9O6dgYyM3igqKm70fFZWFgKBAA4dyj8trMxsNtR+8vfRFGZGVVU1yspOtP3PGpCFmbNmSBBZCCGEEEIIIVrgV9Q90V7izq+oewC06WKmEJHCzI7yQKC3qavPEtFVZbUaoALEdPzMSlQywIkEjAfTeICvL6vVUFoTBjO/TTbjtlS3u0SWwxWi86ikVhDTMbb4/cCKQHJ3CiIDgAInVPJYMZSbgDsWr8/9AZP5vbsmnhUTFwXvmHlfX91w/IEJF5OBjKa2KQ52v+aRbkXPi9bcNlWr0E31WGd+nnc0iGyUFkPL3wc1rTfsA4e0ad9oBpKZUWknPtZpEwrRTa1cuVItANq3TG4T+lx8Po598CUArCHTfOS5lx97p7X73jrj4euQ608e18uGGwa7obR8MsGAif9+Zq8/n0DrUNeKOXP2jHll7CjOXL58edtSRUII0c08uWHHZGLfagAdugOznRINg/IXr9sx8+fnnbUCnfgL8owZXpdDCwxT7I7/AfRvglq+w/+Yv/scFzluv3d9JMZ9d29wKEi9Fcw/BaF3JOY4WUVFKQ4f2t8oJJyU3AsjRo9D337ZHR6/tqYa1dWVyB4wFCkp6QiHQwiFQgiHgwiHQgiHggiFQ3VfH39M08KNcm+aFkYwGIh0GLmeG+ARRJQJNvp8sI+XXDqEPuiMiYV1JIwseqTzzj8PAV8Ab//17UZvos0Fds/0vK7rOHgwHwkJiZg2bRrWrFmDYDCI5ORkTJlyAUpKihq6I7dHaWkJfD4fzj//Anz11ZcoKiqCzWbHOedMQEpKKvbv39fk3SvmKXfkBoNBuN1N//4VDAZRXHziThtFUfDDH/0QiclJ7a5bCCGEEEIIIXoC/zNP/B3MUT94IiDJ/8wTf/fcft810a5F9ExlzIlUq/3EAN9SVqudA9ia7MISa4jouzBs3y2r1VBSFdpkMv2pd5L9NSKqaXlvIUQHlAM4HImBOxJI3lyyGQMTBnabIDJQF0a2UbyVQ/YhVr5cvH7niz+fNPpmKwdurVmzZtlJS3+AWPmZbnJ/UPNZroDB2FapY2xy97gkxox/020PVERr/gAC5XbER+T12xQrgsiBzz5CcNsW2LMGwDP9si4TSCagrBzhaK3AIkS3UZB91g1Wjpc4NLvo1z/9dmZb97stxxtvQn8DALZW6Pjlxupbfz8xcZ/CWAjCQAD15xaqwJyvMN/nuvOBhgDOrBkPjFag7ERde60UCveunDVrWfLy5bMlkCyE6JGeWrfzVmZ6Nko3vZ9AyguLN+ReeOe5I2+K5CpcXq9XKTiIkQqMm0xTv5Psdkdbv/dNZRompHb5hoQrIzHou/v5bIWNuwB8uzOCyABQVVmOosKjjR7rndEXw0aOsST863S5MGjwcGQPGALTNGAYBkzDgGEe/+8pX9c/p2kawuG6sLLL5UEw6EdCYqddAiEGJwO4hBUj4b18PeGygba/ddbkouO6x5kXIdrIbrfj0isuRb+sfnjv/95DcVExgsHgaUvqAEA43HJTHMMwUFlZAUVRMGXKFOi6DrvdjmAwgGAHz0EzM/x+HwBgzJgxGDFiBGy2updueXlZM/udWmPTdzlpmoajRwsbOiu7XC78ZOZPMGRY207GCSGEEEIIIURPU/vkggwwXx3tOhowX1375IKM+LsekqWcRacprQ3fCObHuFbLZEAhdIEE8hmQQhNU4LmyWu2Z0ppQIUx6IC3J8XK06xKiO1p0/qLgvV/ce5TBRUDT3Ww7or2B5IEJA+GxebpRENkBG8WDYPnFZgWgny1enzvhzokjz43kBfeTzZox7xoCLaQwDwTQpgvvqwvC3SaMTAo/Fs35+y9aFSy8/cajRBSR1+/JrAoiB9Z/BbOmGmZNNQB0lUByFYCDQ596tQZLXov0XEJ0a2RTrmihH1Ubx1PbtSqR6dHXnfgb739uxYKlz60AALzfmv2Xr/hd3i03PjxWJd5+/CGPoh0ugaySJIToaZhp8cZd85j5kWiX0oBx4+INeQO8Xu8lXq/X0hbEs67/TbZiM68pzDd+QeBsBtrdAOB/D4W6fBjZrSTMsXrMD/aFJ5ls/AqES3Di5qCIYmZUV1WirOTEqXy73YE+fbORlTXIkjnsdgfs9raHmk3TbBReVlTVknraKI4Z54OhvrdfNy4bbHs7GkWItuseZ16EaKdRY0Zh8NDBKC0phc/na9Qlud6fnnkeoeOJYmrlJ7rNZmuxy3J7MHNDELklp9ZaW1uLtLTUhvqAuq7Ox44VQtPqbphVVRWXfOsSnHPuORZWLYQQQgghhBDdk2Kzb4l6541T1NWEPtGuQ3RnTKU14ZEA5gP0/bqXQNcNIJ+BAlBfKHiptCb8EoHfYsbDaYnOvGgXJkS3QWD+hAuhYi8iFGZsTyA5zhbXqrG7QhAZAFRyw0YRvY56zlPr8/avZB56LZERiQlmz5g3jEAvAuZEAM72/u510GegWmMk2rv8Z1aRuyS4JpoFEMDHgEJC5F6/gPVBZADgYAChndsAxH4gmYAiUrCns8L+QnRrjHSLx3O2dZfZNz10HRgNv4xoPvuk9kz9p5ce3THnZw9NhkFrj9eSNGfGvIKlK+bLeQAhRI/x1Mbc+5gpdoLIxxFwUa8rr3sXXu9lHR1rxgyvy03adaaJm4mMqVadgg4abB7xGYf6x6kDrRmxs9G/6LbbLF0l5t09obMMUm4n4HIArTspYIFQKIia6kpo2okGmS63Bymp6XC6ml71vrMoigJFUWCzRT247gJwHgE//s8B3n35IJJzs12AhJFFj+d0OdEvq98Zn7fZbAihPtzbdU5UKooCImoIRe/atQsZGb3hcrkQH5+AyspKlJaWw+8PNOwzYtQIXPqtS6NVshBCCCGEEEJ0GYElvx/EMNu8LGvkcWZgye8Huef+8kC0KxFdEzPTb5f/5WUQ+jf1fGrSOyP/9qEjBv/fj6gfAvjhkjf/XVhWVd30SW+mEgzP+LF3+nS9c0sTousy7eYxMikPwAWRmqOtgeTW6CpBZABQyQO7EuFmiYSBhRvy9nm9PNjrJUs6gM2a5fUoIW0xQDMA2OoCyB07N88A3joYxMyh0b2o21EKYxZZ3GmtPWxsO2aSEbHXbySCyPW6SiDZBAoU09wVkcGF6GFM8BFrV3ChQMvbnLIH6NX6rxm488+rvOXtnX3pnxesu/XmB89mnbYc742ZOWfGPF+Zz9Zr1Spvy0v+CiFEF/bUut3fZzYej3Ydzfjm4vV5f/75pJE/a8/Os2fM+5YC3MLQr2Ime3s7IJ+GsN008axTMd7qG29TwVxg0cidyiTcYuV47+8LZJtQfkpEV4G504LIAOD31aKyoqzRY25PHBKTW16pqYdxMfBNYr1o9RH+/fT+dCTaBYnmSRhZiG5KURr/VlJeXo6PP/4EGRm9ARCOHi1ATY2v4fnho4bjxltuhN0e9TtbhBBCCCGEECLmsWIujLGmyA1YMRcCuDbadYiu6ZHnVxrNLQ1VVlV9pqd6gkyAmg5iE4A9RTnMrEgHQyFa7SgxbWNiHRG8VmFlILkrBZEBgg0JsCPyFzIZGNDryl0b+Tc8ob3vgV6v11Z0QJvJRE8jrNvbve5w0/UFifk3tz/p/X3g6YX7AXTRLmA44Lzjvn9i7v3RrgMhZ/VRuxa3DWAdIEtfv5EMItfrAoFkQwHybYqxw+qBheiJFIP/wSr91LIBiYta3uiEOTPm5YEbftepXrZi/pKOlvDc849tnTXjgdEK1J2oOxrxpMbpFTk5KxNXrbo2IqsViNMpisKRWC1ZCNG0P365qx+TsSradbSMb1q8Lnftz88btbw1Wx9fDeZXAF8JIMPCd5UqZv4jk33l8he9u3B8mZklLwL+JY/fD6KF1k3VCZh/GX/H/YVWDfd/e9jJZngyqbgGzClWjdta8QmJmHrRt3DWuHMbHnM63UjPkMUOmpACKN8Nh8z81Tv4T9PPotpoFyTOTMLIQrSg/pRn3YFE+z72q6urkZu7E4bRtoYFREB29gD063fmzs1ncuqBDzOjoqICFRWnr1iQkpqCa398LeLiO/VGHyGEEEIIIYTouhg50S7hjGK5NhHTHnn+zQtMkym9VyK+ed74rrRAVNR9snEHjpaU4bd/evM6AH+Jdj1CdAWLpiwK3PP5PXsA7AUwMpJzWRFI7lpBZEAlN+xKLyjUWc0nePySDXmvAfhxa/eYO3eu06hJHmeC3yrM17OtDCCDOQDCvxSPfeazz3prAWApAD+MH4NsX4C5a33KETEM/nGs3PCStWhVoPjOGXtMkyx//SouN9TeGRELItezIpBsS29fnS2ODRSZoO2pS17r0XeBCWGVOyeP/t/FG6xb1dvU9f+0dttZMx4eC/CI+r+7fT7LVplZvuJ3ebNuenCiwsrG4w95UuO+LgDQ26o5hBAiVjAzPbU+72sASrRraQUC0ZNPb9r5nzsmjD7Y1AY5OV5Hapw+D+CfABgEWHZ8YjLhdZPN/yHHgB3Ll8/WmtrIXRZ80p/mvoGAsyyaN6II2La/LPiUtaOGh7CqfoeAwdaO2zoOhxP9+g9Av/4DojF918PcnxR8R/PomwB8Eu1yxJlJGFmIFnji3KitrbupwjTbt/pZUVERfD5/u/fNzMyEqqpt2s80uSGQTERQVRW63nilULvdjqHDh+LbV38bmX172gqrQgghhBBCCNE+1cv+kAYtthsNVS/7Q1ri7HtLo12H6FpMg+NAQJzbhWHZ0oWjLTbv2o+jJYBpGnKntxBtQCbls8KbEOEwMtCxQHJXCyIDgI0S4KC0Tp2TgR89uX7nu3dNGv3ymbbJyfE6EhO1Pg5DWaLV8FXtbQByBgEAuxWYM5596bEtTW3guePBr/xLFj4Dwh1WThxpJvOS+DvvXxPtOk5mMOUTrH/96iXFCK5fAyU+sU0B4bYEket1JJBslBYjuOGrSHRFBhPyQbSx5S2FEK1CxFifuxvAcCuG27Vs5ew5Mx6+wiRcu/zFR9eeaTuv16sU5utfn/TQ4kWrFgWsqKHe8hcf2zTnhocmQ6HjdVD6nBkPFZf5zu4jHZKFEN3J4vW7/kiE1GjX0XrsNg16A8CUkx+dc+Ovf0CK+T9s6v0A2CzsBLBLIZ5Zo4e+fuWVP/ha2pi83rD/mflXgO37EePZQYOBx7f7ArvLcy37XPu8hBP8PnM6DP42CA6rxu3qamuqceTwAVRXVTZ6PL13JgYNGXGGvToJwcaMc8jEVZ8d5K3/NYBO78QpYkJMv6EIEQvSM3qjuKgEAKBpegtbNy07OxtlZaXw+9t2fElEGDBgYJuDyACg61pDGDk5JRkzZ8/El599icP5h6DabOifnYVJkycia2AWnE5nm8cXQgghhBBCiJ7KrpnzY6IlXTPsmjkfwJxo1yG6lkH9M7IPHG3TisPiFL17pUgXMiHawLSZBxRW1oDxfQa7Ij1fewLJXTGITFBgp2Q4lM4NIwMAMS19em3uv++YPKqs/jGv16sc2YO+qs2YTaTfD4PsbF0IWQPoMJH5yHMvLngZrUg3ux377gloQ64A0LZWuFFSHjL15/eEFkS7jlNl2moPlGhxa0zg+wAse/22JyDcniBytOZrCQEam8jzazWbLB1YiB6OYPtvht7h11XN/sNA3fXXbIWx5tYZ80rYpMuXvvzo5lO3LTygvwpqSJlVL10x/66Ozt+UpS8vWDdz5n0j7YY9l4gIoPTUuK3VOTneXqtWecORmFPUMU2z7kcuhIgoL7NCG/Ii8h4aSQycv2Tdzut2Ll25nk1tFYjGgU0bM6zKIGuAOavM53i9Pe/3ntvnHQ4s+f3lTOaHllQTIct2+1EWMs9LjRux1uv1nuf1etvXRfIkgWoMBPGFIHT+QXMM8/tqsHXLOmz/ekPDY8kpqZh64eXRDyMDICAZCi4Imvp5AFq9UoXoXBJGFqIFg4cOxo6tOwCgzWHiek6nE+PHj8f27dtRXV3Tqn0cDgdGjhyF1NSUds0ZCJw4MT5s+DAMGjIIg4YMatdYQgghhBBCCCFOYPBl0a6hJV2hRhE7mNldXqu/e6igcJqEkTtm3Mghj5XWaJcHKm1XZGWRpV3PhOiOFk1ZFLjn83u2g7EVhPM6Y862BJK7YhAZAFSKh5N6Q4lGgyeC21DoWQDX3XzzgxmqhssL8/XHbXZY2XKfARwC85vuFL930aK2dZmk2cu1yiWPftNBjq8BJFhYl+VCBuOZXQFbRdjcMOtHv5iw/I3/iZmVL2jRqkDBbTdsJ0XZClj7+m1LQNiKYHBnz9dsLcAhKFgzZPmqKssHF6IHu3PSsM2LN+T+C4zvdGScQ//65AFFpcdwPEbGQDoU3jRnxjy2Kbb+T7/gPQYAs2b9Jhth40f1+xmmMamp8Rigypn3jGOV5zNwCeoG/pAMmpf8wh+3UiuXEHjhhSd2zZx53yiH6cg7/pAnNU6vACArtwghurxeG3I3WthBuFNpofBfwAaA1r6jtygA4tdMu/3ny5d727c8+0ncc3/5UWDJwplM+DNi7IfMAN44EMTemoaGyOcW5Gsbc3JyJq5atardXZJXHmY368a5BJpS3+BR1AkE/CguOobiomMNj7k9cfB4YubXCQLTGAZ/+/M8/nLqSGpdAE90KiXaBQgR64YMGwKnq65zcCgUancg2eVyY/To0XC73S1uS0QYMWJku4PIuq6jtrZu5QVFUTD27LHtGkcIIYQQQgghRJOSo11AK3SFGkUMKK/Vf1pWq/kZPC3atXQffKE7WfOX1IZ+Eu1KhOgKwgjvYvBnnTlnfSD5k2OfILcit8ltumoQGQDslASnkhm9Apiv/cVDS7bZdKWQSHkJsCyIXAzCG5qqD1+6Yv7ApS8tuL+tQeR6yXMfPkAKXQkgZm8c0Uxg+Z4gKsImAGQpTvemm256ID3adZ3Mpth2MVNEXr/1AWH/6veg5e9rchsrg8GdPV8zdtkYnfqeKERPUfGvN68mwrGWtzwdAWxoof7LX1nweJlvnJ1Bt5+6iW7qR+fMmHdo1gzvSCVsbD/xFL/yp5d/t/vkjXfk5DjKbrn7i/Jb7jZNlbcw8B0AbgBuBr5jqryl/Ja7zfKb7/58R05Oq+4ueuGFJ3YpoJNvDvHMmTGvoD3frxBCxIpndhTHAzQu2nW0l+pyImFIdscGIdQC+BSqOXbpivmepS8uuMWKIHI999z7XySTZwNod8DXaiYDK/ND2FCmNXqcQONT4oZv8Hq97c47JmihbJi4kMFRPGiOTX6/D1WVFY0ei4tPQK+UGGogTYgHaITPhgHRLkU0TTojC9GCjMwMZPbJxMEDB8HMOHasEIMGZUNV1YZtTNOEYRgwDBOapgFguFxu2O2NX2IeTxwmTZqIzZs3o6amtsn57HY7xowZg169ep32nK7rCAaDYAZsNhtUVYWqKqfVcuxYAUyzbmWC1PRUZA3IsuAnIYQQQgghhBDiuJhpBdCMrlCjiKJSv78f6+qnJpuDW7O9TzOhS7cQAIBChAR7y9c8iOnV0pqQlxX9wvS4uHaFHoToCdK0tOIqW9UXAK4EMLKz5m2uQ3JXDiKr5IFT6QMbRbfhb+q5Y8b4LOi2T4CPwV+Swouee+GxdyworYH7tvs+8y15/AcK0VsMeKwcu6PCJvDi3gAO1OonP5zlZHXjTTc9cO6LL/6uJFq1nSwtLbu4oGT/FwQlIq/f5joWRyIY3NnznYqAYwx8VkFFByIygRA9nNfrNeH19lu8fue/ALqytfuZYQ1VeQf6e3929TEAWLXqWgPAswCenX3jQ78mot+etHmWAr3hTicCfBkD7TNOHq/iZ7+4xlTMv7VmbiZckJncP1R28105qc8/+VZL2z+74tH1c254eAIU3lg3PTLn3DSv0rRnpS9fPltraX8hhIg1RqD8RXTxRpvp3zgb1fsOAW05r0bQwdjKrPxh2YpH3ohcdXXcd/7qT8//4rc3XTvAdb4tyj9tzQRe3BdAXpXe5PMEGl+Qr230er3ner1es63jq4aaySqPICa15a0j62D+Xmzbsg5Olxuu43+cLjecThfsDiccdgfsjro/dV87YbfboSjWl+7z1eBg/l4UFx1teExVbUhOTkVKSkzdEwuAMgjGMADbW9xUdDoJIwvRgviEeEycPBEHDxwEAGiahrKycqSnp8EwDFRWVsPv9yMcDkPTTnwYxsV50K9fn0ZBYQCw2ewYPXo0tm/fAZ/P1+g5VVUxcuTIJoPIpskoLi5FVdWJk1w2mwqHwwG3243k5ETY7XZUVFTC5zvRzGHs+LFISWtfh2UhhBBCCCGEEE0gsrfp5HE0ENmjXYKIXeW1oR+xSStAaFWHLdERNJRM+4HiytANvZOdb0a7GiFikXe6V7/3k3u3GKrxMYE6LYwMNB1I7spBZACwUzLcSj8QontdNS4rE87UZITKKtuxNxsEZQPzBKdGAAAgAElEQVSYXwmQ7c8rVngj9g8RN/dX71Q8s/A7rPMHLpViIuQQMBgv7A1iX02TF9+znKxunPUj74Tlb3hLO7u2U5HXqxfecf0WBj6mCN1M0FRAOJLB4M6er9HchFyT+P1hT70TitgkQgj8fNLo7yzasHOCwvQegNQzbsjMZZt3UvFXW8DAHjRx0++ylxY8AuCROTc8/DsofA9w+jFW0SF9GIBdAFB2810/NMlc1eaiiVaVz7r7JynLF73e0qZLX350860/nTeKbZwLEIGRpIQPV86aNSt5+fLlEkgWQnQpJvM3KdpFdJAjKQHO5ESEKqpasTXvBOgvZbW+P6xa1b5VYNpj1o2/vnJDmXb+7moDd4x0I80ZpUMjxr4F23y9qjWz2ZATgcYX5utf5OTkTF21alWbOjqzSukEGghE//x+aXEBvvzsA5imCVU93pDyeGNKRVGhKApURYWiKlAUFTabrSG47HA4kZjUCyNGj8OQoaNanqzFWgqxd/cOhIInDr8TEpPQt182XO6YuncXDM6EQkOjXYdomoSRhWgBEWHaxdOw5vM1OHqk7g6QsrIKGIaBmhofDKPpzzVN08BnuDgdFxePiRPPxYYNG+Dz1a2eoKoqxo07G716Nb2SLnN91+UTdN2Argfg9wdQXl6BhIT4Rh2X4xPjccVVV0BRYuIcqhBCCCGEEEIIIaKImV1l1dpqk/GNaNfSwzgUlf5SWhX+eU2i/eJBRF0v3ShEhMWnxR+trqz+AIyL0IndkYHGgeRjvmMo8hd12SCySh64qB/s1PQ55s6WPGoIij7f2JZd9jDhLTLwzHMvP3q05c2t8eD62vNTnKTMGuZGuiu659JLQ2ws3e1Xy0PNNvjKUpz6phtueOCcl1/+XVln1XYmZUXBo2kZng8YFLHX78kBYefY8dAPH4xoMLiz5zvuGEz+0HD4d0ZyEiFEnbsnjt4EIG3R6s3JFO/6KcBzCDQahFIG/m7alN9W/314QXH+6wYAEOCZc9OvLl764uMfNTXe0pcffSAnZ+W8FM/XGhE15OYYiIOJvDkz5lVdZQveCDLaHkSuH4vxWsnMu3env7BoQ0vbPvfq/F233vDgeFbo6+MPeSjcuxDNha+FECLGLFq/81ICkqJdhxUShw9Eydqvm36SUAST31RMWvrsKwtym94ocm7LuS3eJPPPAFCtmXhsmw9X93fiwsxO72HwpGfu/XfPmuVNU9jMBSGthe2/kRo3YnVOzsrpx1ctaNE/NxzzMJv9CUo6YiDlTqRA13VUV1W0cnuqCyirNqSk9sb5Uy9Benpmh+vw+33Ys2sH9u/Ja/R4r5Q09MsaiJN+tYkJBKQSMHAls3otUZvC6CLyJIwsRCuoqoobbr4By59ejrLSunN7lZWnn3RyuZwgUgAwEhMTTuuK3HhMG8aMGYNdu3YjHA5jyJAhZwwi19eQnJwMZsA0TRiGAV0/0RmBmVFdXdPw98SkRMyYNQNut7sd37EQQgghhBBCiDMyWYv5jrLM0u1INFJcW5tZVqttgYKMaNfSYyk4P6E2fKCotnZ8Rnx8UbTLESKWeM/yhu9Zd886aHgP3LlhZOBEILnIX4SwGe6SQWQAcFAK3Go2KEYu/SSPHoriNVvAerPXBqsArITJzy99ecG6Tiqtwa0zvYPZ0OeVhRhP7PDhBwNcmJxmj8Z1aZOBF57J8z1ZFebPQDh9+cTGstykbrn1x78a99zrj7fuynWEnLVqVfjYndevV0z1fUTwZoL6gLB2+CA4GIh0MLjT5wOwXbPxv7MWreq0DnhCCODu6edUAnj6+J/TzLnhoblQaAkAgG0fAFBxhlaKqXHbHgHOmNZJmkTG3ztar6riCwDO1mz73MuPbZ1zw0OTodBaACAgZfaMhwr7DLT39Xq9Ju/wOqA5lgL4EQDXaQMw7wPRb2n8g690tO7uSlEUPlNzMiFExxFobrRrsEqvcSNQsm4rGlbbI+hgvKmy8mL6QGW11+tt9m7ESGJPyjNA4/OF/zgSwpelGr6f5cSIpMgeXxLze0T2ua47frEbAJYv95bOnHnf2Q7TuRng3i3s/l+pcVs/uOgi7zc//tjb5NIyJ4tP7ZOomWYfEMfEQbPD6YInLr7VYWRmhmEYcHviMGbcuThvykVITGrp0LFlRQVHsGPbRvj9J5pfqqoNvTP6ol//AR0ePwLsTOjVpwqJAKJ6PCxOJ+1ShWilvv374orvXnHa40SEAQMG4PLLL8PkyedhwID+GDAgCykpvVq8OyQuLh7jx4/HpEmTkJ6e3mINSUkJGDCgPwYOzMKQIQMxZMjAM85z4SUXYtiIYa3/BoUQQgghhBBCtA7BF+0SWqEr1Cg6SUm1fpXCjmOABJGjjzJVdhSU+/RvR7sSIWJN7ebaQmJ6F0CL3f4iQTM1VIeru2wQ2UYJcCvZsFPsNA5T7Da4ezfZgNFk4O9MfM3SFfOTl66YPysaQWQABNZfAsENAAYDK/ODeG6XH6XNdya2uAjsJVa+GXfH/bcs/NOjO0wypgAob3E/Qn922LbNnHlfQieU2axjQXeBAvMdBkf09cvBAIySos4IBnf2fPsVhd8Omkm7Ij2REKJtlr684Gkw14dcaPaNDy1taru692J+sP7vzHzh0hXzyWQsAGBMUjScuYVV6zHgqLj5njtbu/3SlxesM5jG1KffCJRRmK/XGJsfuxeaIwTgJjQVRAYAoiEAXuYtj/l4y2PDLShfCCHahICx0a7BKqrDDtXlAIAvmJRrwhROWbpi/k+feemRD6MZRL5t5oPTmfDTpp4rCZpYtieAp/P8uQz6h+WTM/7OijnRNfdX36oPItd74YUnjum20LkAilsx0kUjB+rvX3SRt8WAsU8LeQCOmYNmp9MJjye+TfvExSdg0uRpmP7Nq9CrV8cXPKisKMPWzWtxYH+jfwIk90rBwMHDEZ8QMz+uxpjjfaWy4kMskjCyEK3k9/uxad2mRo+lp6fj8ssvx5Qp50PXNRQXF4GI2tSivq6FfusPP+vb7iuKAofDgYyMdAwZMhCJiY3PN27ZsAXlZS2erxRCCCGEEEKITvGHDbvSnlyfu3Tx+tz9T23ILV+8Pjf01IY886kNeWbd17nli9fn7l+8Ie+5p9ceifWTSJXRLqAVukKNohMUV4d+R2S+DcTC4oPiODJN89/F1aEF0S5EiFiyfPZyzeayfUmg18HyOdYWBBtcSj94lMEgS6JO1onL6tPwNQNriegW06GlLFsx/3vLXlxg/QXtNrh1xsOzmTH11Mf31hh4bJsPf8kPolbjSAYDisikn7luv2+4e+4vP6p/cPmK3+XpBqaiFYFkAP0cpiNv1iyvJ3Jltmzi8uWaz6Z8pTC9Afk9tG3qbnT8EDr977AlS0LRLkcIcTrFpAvqvyaiWTk53tNWSnKYjn31XzNz0bKXFnwKAMtfmj9v6Yr5tu/atEKr6jGI72vL9n966dEdpNMoHO/o/OhNbo9C+H0bhvAA2MVfPza5LfMKIURHeFezDYzsaNdhpX7TJ1+0dMX8qctefOQfL7zwRE3Le0TWjBlel2kqr6KZ7CAR9AN+43txd9x3jUnUh1i5npl3tndOZmw3ma83ifp45t7/vbjbHthIZ1hx4PnnnzgCkycAKGnF0BeNGKB9mJOT0+wBsRPkBCGuPbVHgsPhhMfT+nI8nnicO2kqLrn8GqSmtdQ0umXBgB9bt6zDmi8+QjDgb3jcZrMhe+BQjBx9NhQlNqOlRIiHoqVEuw5xuphoOy5ikx70wVdRBEVR4UnJhGo/fcUXU9fgKzuG6uKD8JcXIlBZirC/GnrYD1M36oK5NjvsLg+ccclwJ6XBk9oXujsVXW3Jknfefgd5O/MA1AWCzz77bAwePAgulws1NTUoKrLsGLLN7HY7+vTJQEJCPAoKimCaJg4fPoLXVryGO+65I2Y/HLoCPRxCbXkxQv5amIaOM/wedEaJ6X0Rl5wWmeKEEEIIIYSIcUvW5g1ihRcykIOTchz1h4MnHRc6mOEA0AvMcwylZs7i9bkA0UpT5fvvPmdUfmfXfiZzZjz83xvKtMSJqfZol9IsAt6Pdg0i+oqrg58oRNOiXYdomkL0YHF1cErvRNf0aNciRKxYOHFh1b1r7v2Qdb4AwA+iXU9X4aBe8CiDoJI72qWcJnFItlaydsuvFdX+1rN/9u6Ndj31br7Z2591/YnmtllXqmFzDY99fJxriMI0l4FvWjE3A+8D9JTn9l/+m4gYd56eKXv+lfm5t10/b6qp4nMALV1g7auE9X05Od4Bq1Z5w1bU2B6DnlxReWTuzA9VNqeQvH5bjU3sVFX8tffTK6J3kUkI0axnX5mfO2fGvE0AJgBAapy+E8DQ+ufnzHh4JsD1S+Cay15akHnqGArzaY+1FwH92rrPc6/O33XrjQ9P+vkPHRvSktp5nypjDW967Cya8GC7Q2jdjWma1JYmZUKI1kuJ3z2BEWN3WnaQe1D2OQA+iXYd9ZzQHwHQt7ltGLR06QuP7gKA+NvvKwTwKoBXy57yJnooLlWHfp4C5RJSaAIzDyYgCQCYUUkKHWDmjSabH9lgW+fymKX0s/vbFMJe+vKCo3PmeMcgqO8Emu+CS0TTUuNGfJKTk3PhqlWrjCa/Hzs5AcS1MfYTMQ6nC5641oWR3W4Pxp1zHi665EqkpXd88TvTNJG382u8/+7fUFFR1ui5tPRMjD17ItJ79znD3tHHzPFkmrHe1KZHkjCyaMTQwyjZsxn5699B+cFcsFn3/mxzutF3zAXIGHEe9HAQVUf3ouLoHlQX7IOhtf3cluZKgZZ1KaCeHnCORXk78vDxBx83/H3EiOEYOXIEFEWBYRg4cuQQDKPJz7JmmSYjGAyC2YTb7e5QaFhRFCQmJkDXDRQVFQPM2J27G599/BmmTZ/Wpm7NPZEWCqKmrAiVRUdwNG8zju7agqIDeaguLQSb7W9+YXe6cc7l12LqdbchPiW95R2EEEIIIYToBp7ctj9DCYa2mOjgxTbmaxUd1y5ev7OQDWP8Xd8YW2RRiW1Bt/3MO8Q09NcAnAcw/n4ohFgPI+umMS/aNYjoYWZ7Wa22HUCnLqUbCoXw2UefYlfubgwfNRxTL5wKtyf2gnGxRCHlotLqUF5+gmPsRCIt2vUIEQsM09hDRG8Q0xAGj492PbHORvHwqIPhVDp+MTISnCmJtiF3X7vkl2ef7Yt2LSezadpyECU0vxW9sGSZd+cSYCeAf9Y+80SmYvAUUvBdBn8boNad8CUUE9P/MYy33U7zS7rlobrfae9ovrHls6/Mz50144ELFKhfoOVAcmZqnH7wiivmDnznneh112VbzW7WPG8ooCEMyOu3ZQcVopUqh7+MdiFCiOZlDrRNLszXg6gLxg2Zdf3Dk5e/8ujaW2/9VS8O8J/rt2OiG6NXZfOe/bl7UIfXzVawg1d77TTdq1tSlBBCnAmbZ3e3Nb5U8H8BeDLadQDAnOsfHAPg3hY2K3zuhUfuXPrio6c9kXqntxpANYADAN60vsITli71Fs+adf8QNWzPZyC5hc0vSPEMX+P1eid7vd7Tgj66zmHVhkCs/K9lt9vhdLZ87tTpcmP02Am48OIrkdm3f4fnDQYD+HrTGvzn32+hpKig0XMutwcjRo3DmHETYbPFcKyUSFNtzmC0yxCni+H/a0Rn04I+bPvnUhTv2QRDa3yuSg8FcGjjBzi08YMoVRc9wWAIH73fsEIa4uPjMXr06IbgcHFxEYLB9r2/1dbWoqCgCMyMtLRUpKV1vIN8cnIifD4famvrzu2u+XwNxk8Yj6TkpA6P3R2Fg35s//if2PXV+yg9vBfVJQUwdOuu/WmhANa9/RKqSwtx9S9+D6cn3rKxhRBCCCGEiEWL1+/8O4Khq61tLkCZpNoKF2/I/dvPJ476vqVDn0FOjteRGmesBJuXmYbe6Iyg34iR1gnNSLjzwdYsXye6IWZ2lvnCBwDq1NYVxYXFWPDrBQ03a+fuyMXb//s2brvrNowaM6ozS+l6iEYMrA3n79nDg4cNI1meXfR4i6YsCty1+a4PlVqlHwgPALCsk2B3o8ABt5KNOGUoFMTmjVLMII9u6wMgZroiz7nx4WtBfEXzW3EoCNvtJz9yvBPYXwH8lQGqWfaHVKemZ5imkmKSGQ+QHQBUhcJswKcrZjnbbUUJs+8tO9PSwy1ZvuJ3ebfOnDeFTXwFoFcLm2cO6J104Ior5g6KViA5a9GqQMVdMz4MGdwPTPL6bd7/s3fn8VGVVx/Af+feWTPZFxISwr4jKgqI2rpVbW3d3raxtVYJqCEuqLGLW2inNWq1WlBUICoE0Laa1rrUulD3urGJ7PsWErLvk1nuvc95/5gQiCSZLJOZCTxfP/hhZp55npOEm5m59zznNBDxvxXV8lLSgmWN4Q5GkqSuOZ1O/ZaZDziZ6EEAUFT+Misry4QW06dHk+V465JlBS+GIp45M+fdwIqx2UJ6eUXT1Iri4msCV80i/D0oiydY5gOYG5S5JEmSOsEKRkRK9dpgYcLkcMcAAFlZr6hQN34AdJnuzSYD5xBRRPwUCgsfbcjKyktPcjjKAcR2NZaIph7er61zOp1nfjsh2apaXAYbdf0abA+YTGZYrIGLeArDABEhKsoBRelbwfDGhjqs/vJjfPLB26isKPtWPCaMGTsRM869CDGxgfK+w4zhEkDE/Cylo2QysgQAEIaOnR/+HYe3ftF2n2oywWQyQwgDuqYd2z63DRFBVU1QTCpURQUpCswmM8w2mz9ZlwHD0OHzemHoOoQwIISAUAdON4XK8goc2HcQgP/rnT59Gmw2GwBA0zTU17f/3ebz+dDS4kZ0tCPgLhGPxwvRWnW3OwnNhmHA5WqB2WyB3d7xC5KiKBg8OA179uyFEIyyQ2UoLSmVycjHYBZwN9Vjy8f/xkcrF8DdVN/pWCL/z723O6MM4T9uSratQ23pPgweExHvLyVJkiRJkiQp6J5avytFGPoutLZi6xeM/3tyzdZajdSxv546rjrY02dlOS3JDv1OZvwWpCcD8H8o6MDXtRqmJEZm0g+Af4Q7ACk8SkpK7DXNWilAgZKVgm7BY0/CMAzYbFZkZmagoqIKjY1NeGb+M5j7q7kYN3FcqEMaYCg9MU0vY+YMIpJVPaST3oIpC+p/89lv3tJZn0BEN4IjNNM2rAgWZRAc6lioFBXuYLrk0SgZEZKMnHOtMxmKXhgosYEV5cKipc5Ofx8TwJjz62oAQX9P+m2LlhbsmJOdfxaA1RSoEhhh8LDUuD2XXTZ3VLgSkhMWFNVXzJ35FoAJAG5kyOO3AwYRvhIwrUhdUHg48HBJkiLBouUPFeRm598HIAoAkqLGbmDCpCOPe2A+M1SxEPFyYgU6W5Dk2Ijc7HwDgMFAOYFf1A3txedXPrbtyHj+5pGLwBysC/S3QyYjw2Qy2Q3D6DIhrhfMzBxbUlJiz8zMdAd5bkkaUAhIjogs2CAiRka4YwCARMc3dwbu8kKvPr3ywX2hiah7iovnu7Oy8tKSHI7DCHANgkCnd5SQ3KLBZbVSLURk/OsymUywWAInI+u6hh3bNoHwV5x+5tkYNWYC4hOSerSWy9WEfXt2YuOG1dj8zRrU1hxfy2TEqHG45LIfI3PoSFAn10UiBRFcCstk5Egkk5ElAEDFjjU49M3HbbfjEpIw6cwZiItPgMftRkVZCarKS+FubgaIEB0bh9j4RMTExcMRHQNblAM2exTMFivUjhKNGdANDT6vF153Cw43ePBxpRm+44riR559e/fB1dwMAIiLi0Na2tGN/B6PBz5f+yq6Ho8XPp8Gr9cb9JL1Pp8Gj8cLwxCw2Syd/vI3mVQ4HA40NTXDMAxs2rAJEydPDGos/UkYOhqqytBcW4mWxnp4W5qh+7xgwwAIUE1mmG1RsEfHIiouCbHJabDHJnTrxVBzt2Dtf17ChlX/QNXB3cC3kuxVheCwqrBbTbCbFZhUgqoSlF4kJLt9BvZVtgAADE2D5pPFjSRJkiRJkqQT01827MhgTT8UmtNTlGBmUbVk7f70OVOH9/nC/QUXOE2TR2lnaAa9CeiDGOi6JkSrtw75IjYZ2aeJe8IdgxR6JSUldntcWiXAIW/J425xo7GhAQAwYsQwAEBGxmCYzWbU1NRi4RMLccudt2DSqZO6muakx+DE6katiplTZEKyJAEN1oaD0b7olTAwBITLwx1PpLFQImLU8bBQ37vt9TdVRUy4YzhCseoLwQEvXBcvWvrHL5fg+HbE4bKkqGDXTTfln2HS8TUCb/7LGJYat2fu3LmjFi4MT0LyIK/1YJnF+6LCGEJE8vj9FgZvZEN5ztNibAx3LJIk9Ywg8V2FlXUAAKJTjtxPgrOLVnS+iSUEVAAqAUMBut+kWu7Pzc4/8hiXVhpaRooStMV4jXMkTXPuDdqEA0xZWdkwXdevAnBakJO14gCcD+BzAO8Ec2JJGnAYgTM0Bxhu3cwSTjm/vH8wgZ7oagwB7kVFD/40VDH1RGtC8uBuVUgGnX54v94uIdkdBZfFh7pIybNVTeZuJSMzM5oa67Fxw2ocPLAHg9MzMXrcJAwfMQaD04fCEd3xR25d11BTVYl9e3Zg187N2Ld3J+pra9DS0nzc2JGjJ+CyK36GkaPGw2SOzOse7TBc1hjUhjsM6XgyGVmCq7YcX7+6wJ/oCcBms+P8H1wJW5T/2lVMXAJS0tL7tgj5y8ubTGZEOaKh2Q0o1c2IlN0mXdm1fVfb3wcNar85yO1ugRDtu97Y7TYQEWy2dl18g8Jms8IwDJjN5oCJt1FRdjQ1+V9Atm/bHvRY+oOuefH2oj+gfO17x31fu0SEuOQ0jDzju5h03g8x4vTvgJTjP1BXl+zBX383G/XlJcc9ZjUrSE+wISnGAlXp+zsPIRh7WxORAcBqd8AeLatTS5IkSZIkSSeev2zYkaFq4mCo1/Ww+9CStfuH9DYhefbs36ZbhOUNQJ+iGdTjK3K1PoEmjRFjjpAzl0dVxufdd9JeEDxZMbO1tlkv5TAkIgP+Tk5HmM0WaJoPADBokL/AeE1NLRY9uQh3/Houxk6QFZK7Qgqia5v10l27OH3MGJK7mqWTWuHUQi3v87yviWgRCDFgnB/umCKFmeIRo06ETckAIfK7ECpMtnDHAAC5s/IvAuPnAYYZbqg5hMhoR3ys558v2Jdz/T2nKqp5EwJceAeQoTWFr0IyFRZqJXlZ6xWfQx6/38LAdmIsdunNq0YVFcvNR5I0wBQue3j9nOx5XxH4rGPurlq04qHlXT+TGgAOyoVCBhogeJE/GZrHg2gkgK7Oa1B8DFmCsXYbi/kmAPcHdc4Bor6+PsHlcl1JRNciUMeCnjMDONNkMs0sLy8vTUtL2xTk+SVpwGCw3q2KEQOLL9wBKCbly4CDhGlGCELpteLi+e6cnJzBim9QCYAud+cScHrFfv3zrKysc4uLi42tL8B79vVcyUAdASHvLPdtJpMJNrsdqqq2O79qsVgRExsPw9BRX1fTdr/X60FFeSlqaiqxf98uxMTGISExBYNS0xEbG48ohwOKaoK7xQVPiwu1tVU4XHYITY31aGqsh8dzfNF9RVEwaswE/ODyazBm3KSBkYgMtAjmynOT4Qp3INLxZDLySc7bXI+NbzzblohMRJh05gxY7Y72A1kAAa/NMpgFWAiABZgZAKOt3RkRCORvcduDPNNwKy8rb/t7dHT7a3oez/HnicxmM8y9+uUc+NwmESE62hFwHOB/0SIiMDNqqmqgaVov4wodoeuoPbS3Z4nIAMCMhqrD+PrdV/D1u6/A5ojBsFNnYOSUczHitHMQl5qB9e+8jM9eXoTmuqOtBlSFEO8wIznGgtgoM4KQg9ymvMELr3b06xhz1oVIzBgWvAUkSZIkSZIkKQI8tX5XCmv6oTAtr3jYXfb42h0pv546rlvtsXN+ef9gMin3EXAbRJcX6rrCYH5NKFwwiGylbnjLAz8ldATRaeGOQQotZjbXuHz7AAr7CXQAiI1NQENDLXTd30lq0KBkEBGqq2vw1OMLcVvebZhwyoQwRxnZGJyYkObbu5Z5+FQiLfAzJOnENf+c+W7nFucnjfWNdgBWABF9UTQUTBSLaHUCopThUBDcvKL+wiSCV4qxl27NckYL1l8LNE4BLi8qctaHIqbeKFz56MGcnPvHK5qyE4xAm5AyhqWGLyE5c36xu/LWWz9hdtkZJI9fAATaDeYlUeB/phUWN4Q7HkmSeknoeVDUz4/cZDIuCPwkLgJwZzCWJ/ALi1c8dF9Hj910ff4IVeGfkEI/hsBwADEgREdZg5zQJzA1uBMODMysVlRUnEFEPwOQ0U/LOJj5e0KIkoqKiidSU1Mr+mkdSYpoxFTHJ1ouMqMynMvnzMy/BcDQrsYQ8OqiFc6I795RWFjYctsN9401SN0OQnJXYxk4K8kx7uOsrFfOdzrJePcGrYRAWwGcG6JwO2UymeFwxMJmj4KruQkAoKomjBozAeecdwnq62rxxf/+i7JDB9o9T9c01NfVoL6uBmWHDmC3zQ6z2QKzyQwoBEPXoes6fF4PvN7O9z9GRTkw6dSpOP+iH2LYiNEwmwfIOQagghRlBxGJcMciHU8mI5/k9n31FuoOHq2aO2zMeIwYO9FfdZcZus8F3eMCswCIYLI6YLLFtO0/YkOHoXshdA8MXQOY/X8AcAfJtdT6f69HAdiKgbCTqbnZX12YiI77xatpfbsepOv6MXPpXYzsOVVV2pKRhRBwNbsQnxDszZmRyeNqwo4vVmHnVx/AHhMHqyMGjZVl/n+jrewWFSNTo+CwmhDsFgw+XaC8znvkUEBi+nB8b9Y9UE0D44VbkiRJkiRJkrpLGPqucH+qMwuxA0BSZ4//+vo/O5rVph8DYjl6/yGUARwEYfbiZQUfHLmzEEDL0396E6ArejlvkNHr0bf9NqKSo6X+V6uyIngAACAASURBVNOsbQZocLjjOFZcXCIaGuqg6/6CLykpSf7N0jW1eGb+M7j1rlsxcfLEMEcZ6Sh9eJNvE4Dx4Y5EksLNOcnZPPfLuatMPpOZFFIBTAt3TOFioljEqBPgUEZBiYxiw91CRME9+d0L7ND+DFDHvWuPjlr1bNFD74Ymot4rLHz4cM61vxqhWO0HELjVc8aw1Lh9l102d0Q4EpIHPftsc83c61ZpwmxmQCU6eY9fAHsBLIFh/DV28cqagKMlSYpcpHzW7iar6+D/fdxp5anEjLi7a0sbgpKMnJgR/5vOHnt+ZcE+AI+3/mnFtOiuR3R0XT1Z6oaDBw+ON5vN1wOYgn5MdCCiJAA/NAxjIzO/RBR5HRskqd8pdLAt4eKEwTvCtfLc65yxGunPBBjmbjY8N4QkoCB4ZsUjNTm/vP9UxaRsADAowPBzk6I3vn/BBc6LVdV0iA1jC0dAMjIRwWqzwX5MMvLQ4aNw0aVXYuz4yfD5vEhMTMbnn/4Xu3dthbeDysaGYaDF1dyjdU0mM9IGD8EZ087FGdPORcqgwVDVyO+6dIxDJMSWcAchdUwmI5+kmBmHt3yOPZ+97q96DCAlLR3Tzr0QpChgZvhcdTB8Le2ep7U0QHM3QlHUo1WQe7Lukf8PoPcM1C5TtX3gzAzDMFBf3whVVREf374zmhAC9fUNUBQF8fHHd97hY948CdHxN6WpqRlerw9xcTHHVTZubnbB4/EgLi72uMeOe18W7gyB7iAgxm5GYoINNosCq0mFWSWYVIJC5E8aZkAAMISAbjB8uoBXE2jxGdBhgiALmhobwMxgYaCloRYtDbVtS6gKITXeiiGJtm/9bNtTzVbYYxJhj0mEIyEVUXHJsNijoZotoC6qhHs8Hvz71b9BM/xFDWwxcbj8zodhjQpLp1xJkiRJkiRJ6jdPrtn6GoCgtBjtE0Lik2u2/ePOaRN+euzdc2be/z0i5YVmNAxFH5KQiegGh+7+1+MrH++w5VfU7fde6Xr60XoK8/fCa7CecOc9V4czBin0Kus9HwMYG+44jjj2c3ZcXEK7hORjKyQ/u+BZ3H737Rg/KTR5trU1tTiwbz+mTD0jJOsFDdG4ykbPh4NibReGOxRJCreFMxY23rPqnrc1u8YA7sJJWGHVn4g8EQ5lNFSyhzucHmEoLYFH9Z/c6+8/hUG5AYax1cTXY4BcvSj82xPV1103d3CMOa4CQKDM9MHDUuP3X3bZ3OHhSEhOWvhSY21Ozts+i8Ygvgt88h2/rRWRF8GkvpT29LKwVsSTJKlvcmfmv+5vBdyOLeeG/N8Vrij4Q2fPI6dTVN981w0EWtGX9QnKL8np7GEVQGLg4QYEsx29grVBm2uAqK6uzvD5fD8HcDkCbwbqE2ZWmHm0oii/qKqq2g/gf/25niRFIha0BSdaHj7hy3AtrZn1/yHAOXIGfryyk3PgkarwxYcP33TTb8806ZZ1CJSQzDh//HB91YENO64cOnnkJvg/p/br7/PuMJnMsFj8H+kyh43Exd+/GmPHT4bVaoPVasMpp05FSupg7Nm5FZs3rsP+fTvbEpd7s1ba4CGYfNo0jJ90GgZnDEVMTFyXuVMRyKcQ7fKqqkxGjlAyGfkk1Vi2B9veW96WiGy12XDqtHNBin+ng9ZBInIbZggj7IUMQiYmJgZNjU3+BG1f+0rISmvithCiw+q6/mRl0S7puP3jot3YjgghWv8c/7hhGBDCv8a3cpEhxNF1VVVFTEyAog8RwGQyY8SooTCU0i7HqQDMqgoc8zWbrVEYffZVIEsUGupqseWb9di1bSPEtxLmCUCc3dTpi6nJYsOgkacheeh42BxxMFmjuv3Cy8z4et1aVBwua7vvlPOvQOaEAXaxU5IkSZIkSZICWLBpbyo83qvCHccxfvLU+l0pG59cMVQlzifgKvQ+AdkA8zMKmR95tsjZrSrDQlXGqoYIa9vMgk0uU+7M/DWLlxdMxwBJopH6prLR+4hCdF644+iKPyG5Fnprp6JjKyQ//Zenccudt2DSqZP6NYb1a9Zj6eKlAIAZ39mKX876Zb+uF2wKKRdUN3gLkuOs+eGORZLC7dFLHm2Y++Xcty26RWPiO8A4P9wxhYqZ4hGjTkKUMmLAJSIDgArREK61s7KcFlb1LwO+MVSU6598vmBAtUF/6aWFjddf/+tkh2qrAWDtejSnDUuN25+VlTeyuHj+8eW0+lliYWFDzdzr3vbCrClEd4D5pDl+GdjOLJ4mQxSnPVMkE5ElaQDLyZ43GeArj97DN6A1uVhR4MzJuWdBYeGjnb7mJT+3YGX1zXnXkD+ZtccI/Ebic0+81JvngrAPHMRkZJ/2fNDmGgB27doV6/V6v68oys+ZudPuXMFERFZm/o6maTceOnSocsiQITtDsa4kRQqPj1fbArzDHWgExNvhWDf3hvw5AE7pchDhjcHDTO+FJqLgev75xw7l3vDAGVBoPQJXSL5gzb9e/Hf6xN8/rKq8A6ApoYixKyaTGRarFRlDhuN7l16FSZPPgNV6dL+p1WZD5tARSE5JxdgJk3Ho4D7s3L4JJQf3obK8FJ4OqiUfyxEdg8yhI5GeMRRp6ZlIzxiGlEFpiI6JG2jVkI84zIz1PxqK+nAHInVMJiOfhAzNhx0fvQxPk79arKKqOOXMGUgalAYA0L0u6L6Qn4uKWOkZ6Sgr9SeXNjY2tnvMYrHAZDIhISGuw2q5qqoiMTG+02RWn+9oUrc/sVhAUdrPExMTDYdDwGQ6/nA98lhHLxA+n9aWjJyaljogXkRIUZA56VxU1OyAu7E28BNaKaoJo6Z9H4mDhwMAEpIGYfjo8Wis/wG++Pi/2LtzK9xuf3K9Lhi7yl0YneZArN3clkRustiQMHgUhp1+PqxRvStoVlNVgY3rj25mi00ZjPOvuxOq2dKr+SRJkiQp9JiuuGKOvclm6rQNgL1Z1cJRSUmSpMiieLwbIi3bVWtsrDT1vlqGAGO9T/VdtXTpY2WBh7cXc8tvKlsWFQyBYT6IELc9ZQB//MYFl84AYWruzPyNi5cXnAqZkHxCq2rUryAS94Y7ju6Ii0tEY2MdNO1ohWQAqKmpxaInF/VrheR1X63DssJlbbe//N+X2LtrL+513guLZQB9VlfogVqX/lmiwxSWi1aSFEkWzljY6NzifK+pockFRiODL8MJfZ2DYKVkxJgmwa5kQglYADcyeYVRFa61kxx6PgBHl4MYqxcv/WPvkrvCbOXKx13XX//rpO4lJCMtOTp69+zZvx2/dOljvSul1QdJC19qrLz11vdYcbuY0QjiywA6gY9fGCCsVwQW2sH/iV28sibcAUmS1CekgFcfucFCvLhkxcMrc2fm54EwBQAUn/kdAGd3NUnyc/OvqLk572UA1/RoceDvic8tuLY3gbfO8BuA3+/987812zTn3mDNNRDExsZO0nX9WmYeEeKlY4joYlVVd9bW1j6bmJgYtg1ekhRq93xnfNOTq7eWgygt3LEEi0k17Qv1mllZeXZS8AR3VbiDoHth3OR0FvSw8n7kWLziodKbbrr/VJOhbAYjOcDw895ftDDq4ltv/0QhmgwK7zkFk8mEYcNHY0jmCJw65SzY7McXayZSEBUVjaioaKSkpGHUmAlobm5CXW01qqvK0eJqhsfjhtfrAYEQGxePmNh4xMbGIyY2Do7oGDgcMbBHOWC1WrvsBh/hDAI269A/JbLK6x8R6kT+kC91gIWOre8WoWrPBgD+9pmjJ0zGyHH+TTBs6NDdjZDXLI8aO3Es1q72d5qprKyA/3vjf5222/1VKDpKFD6isyRgr9cHn8/XdlsIgeZmF2Jj21cwVhTluATl7jzW0nK0snWo2p4Gg2q2YOzZV2Hje8vbVY7uiiMhFXGpw4+7PzY+EZdc/hOUl03Hui8/xZ4dWyCEgG4wdpY1Y2hyFAbFWRGTnI5hp56HuNThvW4/oGsaPnzndTQ3+j8D2qJj8eN7noQjPiSbYyUpbC66KudeEGaHO44OMdys0BMf/mtJn9qeSVJ/+t7VOV9zoIui/Yb3q7py26p/L9l15J4LrpiT1GzCSkXTJ3b2LK9NXwTgTyEJUZKkiLTwq+0jBDjiTgKbHFEwxzigNfWok1wFVL6ypvG0dcXF1xh9WT/qlvzSlr8UDIXFfKgv8/TUH79xoUE75rMT4ZTcmfmrFy8vmBbKOKTQaW7mNA9rr4c7jo501vUpNrZ9heRBg5KhKISqqho8/ZenkZSchKHDhwY1lsqKSpSWtO+8pCgKKisq8atbf4X8gnykpqUGdc3+JIR4q7ypKS0tJkZWVJROes5Jzua8z/M+ESzqVVIPAvgpgIFzQHeTQhbYKAPR6jhYlVQoGECbKI7FrGfu39bjzV7BkJvtHA7o87ocxNAF8IsQhdQvjiYkW2sA6jIhmZnTLWzZlp3tPKWoyBnySlKDnn22mfOyPqnwRdcz4yDRiXn8Amhg4L9s4Hm37voitbBYJo9J0gA3J/uBfwH+XUEMblqy4qEbgIfhoeaLbIiuax02Y871D0xdsvKhtV3NlfTc/J/V5uQVMGMd2vWB7ZCmaTgzrWj+pr7ET6fd9wFveFhHcPJDng7CHAPGoUOHxhqGcQMRzYC/gW9IEVGaEOJqj8ezDcBroV5fksJKUXaDI+88dG/VWI3qUK+ZHB39FjMH2JzJs5cVPRK2DaTB8vzzD1dkZzvH2KDvBbruBtBSXz913b/+GTvtxz/dANDUEIXYIZPZjJGjx+OUU89EVFTgS8YWqw3JKWlITklD5tAR8Ho80HUNhmHAMHQABIvFArPFCovZArWLfLYBh+iAwcY7NrLIbgER7AT6FycFxij95hOUrP8v0HpxKCFpEMafeqY/AZMZ3qZqCNGn668nnOEjhiMuLhYNDY1oamrGgQMlGDbMf4HMZrPDZDJB1/UAsxyvurrmuIt01dU1iImJ7nVC7BGapqGlxV/d2mw245TTuu64EGkcCamwxyahpaF773fiBg2FydJxVRBFVZGeORyp6Zn4/KP3sO7LTyAMA4KBgzVupAweiskX/QKKKdBn/c4xM9Z8/hFK9u/x30GE0y/5KTInhL2jgyT1P0IygDHhDqNDBBfA8eEOQ5K6wsBoANHhWZ1Yt4p2V7NVEipYSWOg02wgAsnjSpJOcqzwo+GOoTODzj4dpe991vUgRjUr/Ghts/mp4mKnr+vBPXPH1hY9Hirum+yAXe3b57pAvAb0gk3NJpfeQfKnv0LymsXLC6ZD7jYOO+dzf58BxvE7aHuBAPXrPbufUFWlX/6B1dT3X55MXFxiu4Tk5OQkMDOqq2tRU12Dmur+KRZotVqhaRqEEPi//7saH3/8Caqrq/HgAw/i6qyrcPEPLgnqept27cX+svKgztmKdM3Y6Sx8+YPgTSl2xsarf7j7mmtkizRpwJl/znx3ztqc9THemHIGbwFjDoDTwh1XsJgoGg5lDBzqaJgoBhT6vJfgUejDa67p26av3sjKekUFNnaZDAYAUHFv4dKCPSEIqV+tXPm4a/bs36ZYhKUcwPGltNrLsJGx6cYbnae98IKz+y0Kg4TmF7s5J2f9YbNRDta3ENEJdfwCOEDAChPw16YW7B9VVOwJd0CSJPXNLbPzx7HAVUduM8R0wN+aqahoQX3urPyHwHgAAEih9wAkBpozsXD+JgCW2py8ycx8m4+VK0zE6QCgM5VZSLypET2TVti3JOT26BqAX+3zNHW+vCAEMyBUVlamCSGyhBA/QZjO4zOziZknE9ENZWVlh9LT0wO/v5GkEwQzigj4TrjjCArmV5yTJgX1XHQguTPnXcPMFwYY9unioodWhiSgECgqctZnZeVlJDkc5QBiOxsnhEDVgQNj96z+qmLUWTNaEPgzVL8ZlJqOxMRkOKI7DbdTqmpClCNMl5lDjBk+Aq9V2PzuhSNJfsaKYDIZ+STSXHMYu/73alu1WavNjilnf9df4p0ZvpYGCNHzpNoTXfKgZIwYPRIb1vmrSa9fvx5JSYmIjo6GzWaD1WrtcTKyy9WC5ubjq3X5fBoaG5sQF9fzF5kjDMNAaWl5W6LzkKFDkJ6R3uv5woEAWKNiu52MbI8J+Jkeqqri3Au/j/iERPzvg3fgbnFBCMaW3YcwqrwM6UOG9TreirJD2Lj+q7bbCWmZmH71LJAygC8SSJIkSZIkSVInGMgKdwydiR0zvONkZGY3oLxT06L+PNgJyG1LgOkWfd7WZjAe+LoZs0fZcUpCf512odcT7vzt1bkz89cfaQd7/BBMzZ2Zv3Hx8oJTIROSw8ZZ+PfXwEcvWvcVA3j/q3XBmi7k4uIS0dhYB03zH4YpKcmIjY2BpvXP+ShVVWC327Fjx+7W2youvfQSrFr1HqqqavBa8ev4Zv1G3H3f3X3eGH5EVW09qmr7rdBkHID/C950hMY6MRvAoODNKUmhUzi1UANw4K6v7/obNdMhAl0P4FIQ4sIdW28RyGNV0mwOZSzsyhCoFLbrocFjiL4nPfVCsmPTXAYCta3btHhpwV9CElAILF36WNMNN9w3NEpV94MDJEwxDzEb+oaca51nFP7NGfIKbVToP37r7sr+m9fAIWZcT8ClwAA+fgkuFrSamVf4FOW9oU8vDUtFcEmSgk8Y2Hjk4wKDXy4semT7sY8vXvbgvNzseXcDsIOQkJN9/28Kix7+c3fmbk1Kzp2T/cBGAj3TusZDS4oeeja4XwVwxwtl/7nlklSeMLQPm1sFJtGFzpMioaCsrCxKCHE+M/8cQEo4YyEiO4CLiKi8pqamIikpqSSc8UhSqNw5ddzSp9ZufwZAl90/BoL9r67KuiV73uummPp/Lly40Nvf6+XkOKPIpy8JcFLYZ1JMP+/vWEKtuHi+Oy8vL81d5ziMLj5feFtaULptW2pCekZTYmZmCCNsz26PAuwnwGf/fkZE28jQ/5kwWt0f7likrslk5JOE0L1Y+7c/oaXWX5lFURRM/e5FSBo0GABgaF4Yvh61sj1pWCwWfP9H329LRna73di0aTPOOms6VFVFcnIKXK7uf++EEKiqqoYQrUnhgmEXjHqTAmZGVVU1oqMdUNXeJbLW1tbB7T5a0Oa8i85DdMzA2wnDPbhW3lkb2G9TFAWnTJkOV2MtPv/kQwBAS0szPnnv37j62ln+xPxe+OzDd+BqavSvoarIeuAZxA/K6NVckiRJkiRJkhTJHl+7IxmtG1wjlWqzwPD4Ex0J9JVP1375wot/2oN+Tsi9JTv/HoDadkou3eNGjJnw64kOxJiDVsS2UhCdFn3bb8sBYPHyB8+ck/27rQQe3+Fowim5M/NXL15eMC1YAUjdl/XKKyrqxVUmVcWgpC47A0YMr8+HmvrGfl0jNjahXYVkq9UKqzW015SSk5MQFRWFgwcPYd+efbgz5w784dE/IiGx7z+n0yeMxrDBA6Pb/KrP16LF401xOj80OZ0XnhQJBdKJacGUBfV5n+f9l0C72OCPQcgGI6xtVntpH7H6SoJpxj0mioUCS+BnDAA+r+fzUK+Zc60zmaHP73oUawb4Bpxgm7ZWrHik5tZs5xgBbSdAMQGGZypWff2sWfeduWxZeNoyJywoqi/Jy/qvXXPsEgp/LISSDfBAPH73grFSYX5NVbW9gxe+1L9vqCRJCqorFr1zDVS6FcSTAKomxr/SOOn3hXOmarkz5y0EcduL8uDh5l8cPwOxgvvPEVC+BgAFymM5Oc5nCgudLaH7KgLTmuIqnnrVQ7+/wYa0RKXnExBm0Bn3bw1+ZBFrIjP/gpnHhjuQVnHMfKnP59u0a9eupWPGjOn3ZEZJCjci4idXb9sMwpnhjqUvDK8PnsoaYvBLWlPci7fMuv8GW7P7n/OL5/dbpyrFqxcyoctOpwT87umlzhNyA938+fPdWVl5g7uqkMxCoL78MPauWxNji472RCUkdNyOXYoAvItAz3stllVTibRwRyN1TSYjnwQM3Yftq16Eq+boa8iIsZOQlu7vvi10H3yu2m4ndJ6MModl4rKLJuK9j7bAEIT9+/fDYrFg4sQJSEhIRF1dHRobA7cy9Xp9KC+vhNvtrxhvUxSMdGswC4bPbEILC2iajv37S5Cengq73d7tGIUQqKtrQG1r9R0CcMbEVJw5feC9L2NmeJq63x2uua4cqcd0cRNC4KvVa7Br916kpqbg7BlnITbmyHlXRnIUkBpvRUW9/zNaxeFD2LVtMyafMb1ncQqBNZ9/jAN7dwHwJyLP+PGNSBs1qUfzSJIkSZIkSdJAYWJREO4YAkn9ztSa8vc/u+3ZZQ+9HKo1c355/2CAHvn2/U0a4/ffNHvvnhAzZYgDfwTw014u8Q+fJu6Jz7tvb/u7iZcU8cTc7HlrAZzR4TP9FZLXLF5eMB0nWLJNpBtd6Y6HxYqEuBhcc9kF4Q6nWw6UVeBfqz7t9fO7W104Li4RNTUVvV4nGKKi7BgzZiT27z8In0+D814nZt48E2dM6/hQ6q6UhHiMyBwcpCj7l91mRYvHC8fIEisAmYwsDWjzz5nvBrD9rg/vKlfMylYGXwbgSgKNC3ds3XAYjLdZ4TfIwl9ZKfkS7ux1fYDRGpqw+8U3Xr1l9u/mpu5VVjk/Ck0lRcWqd6ONgPLEc0UPbuj/aELv2SJn+a2zHpgkGJsQuNJwppXVdeFMSM6cX+wGsL3uruxyj25sVUi5TCi4khgRf/wSUMbE/wHjTRK0etCzReXhjkmSpO658oUPxkHobwDHJpoSACSDcF851dx35XPvak0H9ptjDvmL0AqiGU6ns8Md2s8WPbxhTvYDGwh0OgCQT38PwHf6++voHqbcWfMOgv2vCX9Y4cGD2fYHk+NpXjcnaAEwhU67f2f/xRhZKioqRhqG8UtmvgCIqB1imcx8TVRU1G4Aq8IdjCSFgqJYZgn2fYPWX9IDUdWXG8Ci7eWDmJWVbofjuVtmzZtrmNW/Bnvzyi2z8y9mgesCDNu4qKjg0WCuG2mKi+e7s7Ly0pIcjlIAHVYg0H0+lO/aBVt0jG38d8/TTVarzKOMOFQL0JtWQ3n5kpFUF+5opMB6seVNGmiq9mxAyYYP2m7HxMZj8plnQTWZwMKAr6UeHOGVrcKNWWBKzGaMT3W33mbs2LEDn3zyKaqrq5GRMaTLKj7MjMbGRhw6VIqWlqPvI85KTMEg1YQYUnBRytELVT6fD4cOlaGmpq5bSeI+nw+lpYfbVVzOTPDiguEHoAzAa811ZXvgcQVO7j6iqboUPndz2+3Pv1qNl/7+Cj774gu89sa/8c9XX297zNB9aKwqwdBkO2Lt/vcRhmHgy0/+21aVqbsOlx7Eui8/absdnzYE06+c2aM5JEmSJEmSJGkgaW2dHNHixo1oDGUiMgCQSfmsiwd/OPaee7ZF3X5PVtTt95Bd2Acx83MA9gGoA+ADEYOIAfha79tHQKEhjEFRt99DUbffk3V8InLbAry4qOBMAOs7jwFTc2fmb8QAPmkvSf1BVVWMGjUCUVF2GIaBpYuXovCZQsj9+pI0cC24cEF9s635f2aYFzA4DwILCLQj3HF14jCBlgPIY/BDdb66d/88/c/lgsSt4Q4sWKrXbgYBo1iI/xwebmzJnZV/eVZWVu9aAnbTnJn5NwIYGmDYrrThancTsAakZ5c9VKIbmMJAfTeGZ1pZXZdzrTO53wPrQsKCovpS3fY/hZQFYJEHwgImROTxS0AZM4oEcx5YPJxKse/KRGRJGjiufP7dFyC07e0TkTtkbho2HOXTz4JQ1I2Fyx78qqvBumr+3pG/E3DunNnzTutqfCg4nU4ld+a8MjCGtN7FAsaElAse+B3MPiuAZSB4Onwy8x4AN9Dp9zvo9JMnEbmsrCxZCPFjAD9HJ9U0w8hCRFOJKPvgwYOnhDsYSQqFuVNHbQKoNNxx9JbQDTTuOtDRQzZmfk716aW5sx64PS/vL92vVNiFW291RrOglV2NYcAnGD8OxnqRrrh4vltTXaNBqO5sjM/txsGN32D36q9Mhq7L5LnIogP8gU/XnjlvDIVl86zUczKj/wTXXHkQm95YBMPnrwBrd0Tjuz+4Ehab/3VM9zRD6L5whjgg+Mo3QPGU4dLxKlq8Kg7UWyEEUFNTg1Wr3kd6ehri4+Pg8XhBRCDyJyALIeDxeFFf3wiP5+jnOKuq4vzBQ3BpajreLquCAeCc1MFIjI/FP/fthkvToOsGKiurUF9fj7i4OERF2aGqCogIzP4EaZ9PQ1OTC01NTW1JywRgUIyGH06qh93Q4Dm8BraMGeH5xvWCp7keB9f8B2CGZjA8moBPF9ANhmAGgaAqgFklWM0qbGYFLQ1VqD6wFenjpwEgfPb5F9A0f2KxEALr1q9H9g3XgVmgdOuXcDfWQCFCWrwNzR4XBDOaGuvx9erPMO2c7lWrEoaBNZ99BHeLCwBgttrx/Tm/R2zywKh+JEnBQoAhgF63wiDA3OXjBCEYRi/n1oghPzBIAx0D0PsjH4YAXdEVmWojSVKPECE+4pP0ArSfC7bcmfm/AjCik4c/XbzM+cGxd9Add1QByAl2HIuLHpyaO2veFjAmdDiAcEruzPzVi5cXTAv22pLU3YrIkWrYsEw0NDTg8OEKbFy/Ec/Mfxq33317uMOSJKmXCqcWagDKnFuc1S2VLZsEibcY/B0Qvk+g0xkcztarGgi7wXhXIeUjAm1uqG04XHhFYVsFCyXOsoHr9WYA0WGMs8+ET0PjnoNttwk8Fow3kxzjt8+Z9cC9i5cVvEGgoL6znD37tzEk+Lku918RdAia5XSGpkpzOD2/smDfrTfeO00YptXopBLYMTIVq77+xhudp7/wgrP7bQuDbGqh//hlZ1Z1bU3cJh3iLUB8h4HvAzgdQNiOXwI0Bu1WiN8VRB9pLDaTKbEsc37/tdeWJCno6Krn3tvHzMN68iRhtqD87HMmX3zWqrj/zrmk02pKL7zgrM2d/n0HYAAAIABJREFUmf8ECL8CABL8MRDacxTfdni/sY0IaUdus8LTC5c+sh0AaJLTB2B26x8JwK5du6zMfDYR/QxAarjj6QgzRwO42GQyHdi9e/eC0aNHV4Y7Jknqb6Sq32dD3xLuOHqjZt1mGN7Oc7IYiAfTQk9d7e/mZD/wJ0tM4zMLFy709nY9o0V/mHD0935HiGjBkqIH9/R2jYHmhRfm196a7ZwsoH8DYFBHYzzNzdi7dg18LS3KiGnTXDGJSY4Qhyl9G1ENM7/KhvHk5WNtnRRqkSKRTEY+gXmb67Dprefga2kCACiKiklTpiM6xt+VS/e6oHmau5pCAsDCgPvAhwAAh8VA1pRabK5Lw7sbCIYAAEZZ2WGUlR2GqqqtycjUmoxsQIj251PNioKfjx6H76ZloNHlavfYBemZiLNYUbRjK5o0/xsSn09DVVU1iKg1GVkBwP7sPKN9fh4RMDm9BReOaUCM1f+Y58DHsA6eClIi/3Bnw8ChrV/AVd+E3ZUtqGjwwe0T8GoCmvB/zQRAVQgWE8FmVhFjUzEsxQb+5lMwC6SPm4YRw4Zh7959bfOmpw+GMHSUbvsCpduPblqOjTLBblHg8vq/V9s2rsepZ5wFqy3wprO1X36Cfbu3A/BfdD3r6lkYM/X84H5DJGkAYAUvw8A3vX0+KVjJ3HmnBmasAeOp3swtQAaxckK225ROIoQdEPQYwL0+8dDF5E1k4QG7m1ySpPBgRuSfhAthjLNnPxoD0dRpOzthMf0gVLEAxIuX8aTc7Hlr0Vlrd3+F5DWLlxdMBwZgGx0pYtns/rwgZobL5YLD0fVhuGbNagghMHp0Z3n8oeffCO7A7t17sX3LdtTX1iM+Max5A5Ik9ZHTn2BzyPmhs7zZ0ryRBb/J4EkgnAfGOSCMQWiukRgAygj0hYD4VIW6TjEpJe5ad9XCHx5/kfmOMWO8T63bnsuCXwxBbP2mduMOCK2jfF8eT0yv5Wbnb5+D/AeWFBW8Gqw1LcLyKQJ0giDQ0kXLH+y8q8UJ5tkX/rT7tpvvm2Fo6hcAEgMMzzQL45vsbOfkoiJndyoq9xtyFvsAHGKns7yifM9GYVHeJMYkYjoPoHMAMQagkB2/IPpCGManCpnWqaSWNHBp1ZiFb/fDuRpJkvrTFc+98wKjZ4nIxyC7IsoBdHkRsaZlxz1JjnG/ar0ZNyc7/54lRQWdnjfoT7dk53/Jx1R/JqH8cHHRH9eGI5aBIjY2drwQ4jpmjvSqw8lE9CO73b4JwN/CHYwk9bc7zhiz9anV275gwtnhjqUntOYW1G7Y1q2xDKQQ6AmtOe63c7Lz5w8ebvqz0+nsUdGt3Budp8DQ53Y1hoCqRcsevKcn854Ini1ylufe8MAZUGg9OktIbmrCgW82wN3U5Bh37rn18YPT5YnBMCGivWAsY0V96QcjTfsCP0OKJJGfnSj1CjNj/+p3UFuyve2+jGEjMWKsv0CS0H3QWhpw9NojQ3Zr7ZhoqYRWu7vtdkqyDddOJkwcCvztU6CyHtBac4K/nRx8LJuqYmRsPGaPn4TkTpJdFSKcmZKKiYlJWLZ9CzbX1qBF9xccZWbougF0UCBUISDGauDckY04fYgLyjE/Sq1uLwxXJUwx6T3/4kPMMHSs3V6Kbd90voGTAeiCofsYLT6BWpeGAzUebDjQjBn172FC1SFcev7ZOLh/D0oPV8IRZcMVF5+L7Z/8A/UVB3Ds9XZVIaTGW7G3wl94pLmpETVVFUjPHN5lnGUl+/HZB++0VaNOHTURUy//pT8bXJJOMh+8WrgeXbUED+Ciq29e0cXrDwM4+OHrhX/t7fySdAKobBD88ro3j1bJkiRJCiciMnOEl0Ymoi47LwSThZu3Auiw1TgDPyosdIb49zfx4iKcmZudvw5dJyRvXLy84FTIhOSw8fgMGCLyvv0eX6+akkBVVfzo6h/hrdfewubNmzB9+lldVkv2+TquCGO12pCQkAgiQm1tDbzejrsFf5vFYkVSUiKIFNTV1cLt7l2BQrPZhNTUFFRUVOH9Ve/jJz/7SY/n8Gg6mj29bh7Tb1SFYLfIU8HSycl5oVMHUAmgMu/zvK2qqn4qPGIwmWgUC54KwmQAExHM6neEBmbeTqBNIKxng7cailFuc9vKH73k0U4rKh6hex2vqubmGgBJQYsphIRPQ+0327scQ6DxAP6ZOyt/GwO/W7Ks4B99WTMne94vAD4twLASN6t39mWdgeiZ5x7ZmZN937kK1M8QKCGZeYgN+ubZs387YenSx5pCE2HnyHn0+C3Jy9pq1uI+JcUYDNAoNmgqgMkgDu7xCzSAsR3gTQRlvVCwVehU7jHc5aMKiwMev5IkRaYrX/hgHIQ2qy9zEGC7ovCdZW/m/KDTeYqLi42cWfNmKMxf+p/DDzmznPOdxc6QtirOnZn/IQNntd2h0M8WFf3x7VDGMNCUlZUNE0L8gpkvRRgr8XeTwsxjFUW5rrS09EBGRsbn4Q5Ikvqbrtd9TzUnDKhrZYc/+AJC7+G5NkYqAX8q36//Kndm/pOLlxc81J2n5eQsMcN36P1A48wWdWrPAjpxLF7xUGmghGTN40HF7l3QPJ74kdOmlaePG+8DMDS0kZ7UaojwKTO/qpFn1Y+GR5eHOyCp5+QZ6BNU2caPse/LN4HWi8SDBg/B1O9e5K+qywytpQHM/k00jQ0NOLB/H6KiHBg5evSAb60ZbL7anTBc/uRYUghJybEAgNOGAyNTga0lwKaDwM5SoLy+7VvuHw8gymBMSU3DjIwhGBOXAKva4XXqduyqCTdPmIx9TY1Ye7gMX5WWoFk5Pg053q4jI86HkclejEjyINZ2/BsZo6UaWs32gZGMLBgVDb37LN7o1vHp9lpY1K2oL9uDc0c64MrIgNUENO3+FCw63jSWEG0BWpORfV4vGhvqkZ7Z+TpNDfX4+N032xKRSVFw/nV3Ija5y04XkiRJkiRJkiSdYHJnPnAdmId08nDJkqKC/4Q0oGMsLnpwau6seVvAmNDhAMIpuTPzVy9eXjAtxKFJrbj1v0jTl5guu+IyfPz+x2huasaePXswevToHj0/M3MokpNT2m6npaWhtrYWBw50Xfxi8OAMpKUd/UyempqGhoZ67N3bu26TmuZPJE5ICNTNXpKkgWj+OfPdAPYB2Jf3ed7XJOgj2JAIL5KJKB2EEQweyuB0Ag0CkMjgWGKKBsF6zFQagZoZ3ASgDoxqVrhMgVLCBu8nEx0kQdUkqFZRlerHzutZUufd52S6F6zZeS3BeC+IX37IVH31DQxPN4vGMiYQUDwnO3+LAv7DoqKHinu6Xna206ZAfy7AMMEQNxYVObu30+UEU1j0yPabrs//jknF/xC4QnKGla3bs7LyRhcXz+/dDp9+kDm/uO34LcnL+lrRoz8yqZSoCZFsBqVDoRHMPJRA6cw8CMSJAMUyEE04evwSoAFoZkITMeoEo1pRUMZACQzsJ4UOKqqoNoSoVaLU6tTHloY9KVuSpCAwtJeDUZeLiLLBPBtEnX54Klz24FdzsvP3EDAKILXcof8XwHl9X7175mTn/x3ABUduM8QdS5Y+/Eqo1h+IDhw4kEBElzPztQAGyodBG4DvArixpKSkMjMzc3egJ0jSQHb3Oee4n1q97QImfBTuWLqHX2iqqL5XYf49iG7vxQQpIBTkZuffzcBjgarsq1rJH7iTBNujIWHRU4V/ONiLWI5Tc9OvLoHCN4P5NABxzIgm/2fmI3mIOgAvgGYADQA2gJXnk55/YlUw1u+txSseKr0123maIH0TGMkdjdF9PtQcPABXXW1axa5dO6ZcfsUrAH0X4MGhjvckUs/AaoXoNZDyka7Xlv5oTFJjuIOSekcmI5+AGsv3Ycs7y2Bo/qROmz0Kp04/B2azBQDgc9XB0P0nAnVNx+YN36C2tgYA4IiKQlpGRngCj1Ceve8D7E/yjYqywmw+mkwcYwfOGuv/AwCaDlQ0AB4f8OGrGtzVAgqACyakYHRih69jnTIrCsbGxSNGF2jZvR8+XYemAKdf0gATMRKidFhM3bhIyAbc+96HffhFPVo/XPpyKdajCazf24D4KBNslnrYzSbYrSrsFgVRFhUWkwJQ+xqsJoVgMSnw6QLMosvq1vV1NXi5aBFcTUdf887NysW4GRf3IWpJkiRJkiRJGjiYWQNgCXccXWmNsf8RrejsoRqXqWdZmEFHvHgZT8rNnrcWXVVIzs5fu7ioYBpkhWQpSB7+y8O44+Y7UF5+GMOGDYPZ3L1C5dHR0e0SkY9ITExEdXUFXK6OC9+oqtouEfmIuLh4JCQkoK6urkfx+3waamv9XenP/s6A6vwpSVIvtCYmlwAoAYOcHzmt3jhvjMfliVEVNYrBdghYhSIsilDMTNx2YpiZBVRoBhsaBLxms9ltCKNFMSnN3MxNf770zy3URZJSd9RPHfN+4tptrzHo6r5+raHkrqhB7aadPX4eAZMY9Mot2flb0MOkZDsZ/2FGVIAV/rWk6OGwXvgOt+dXFmzrbkIyM6cnORx7L7ts7vC3317Yzczy0GlNTC4BUMIA7c/OtibHIKbFUGLYTFGsG3ZVVa1CsIUBM/jo8SsYQiHWBENToHgVk+EmzdxCMJpFlNE06M8r+nz8SpIUgQiBqud325XPr8p/A3iwqzFsyZxAvpIjFZi+m5N93/jCoke6bhsQBLdk5z/PwM/a4mD+/ZLlDy/s73UHMmZWKyoqpgghfg6gs03nAIAmvQk7XDtw0B2UXL4uJVmScEr0KUiydN4og5ljiehik8m0vaqqanFKSorcQCOd0O6YPuHjJ1dv+xMI94Y7lq4weFv91Ak5hdOcAsDcW2913sct+gIGbuzFdIkE/OmW7Px5AnhgSVHBk98ekJ2dbWPGfV3GxGwsWf7Qbb1Yv03NTXf9FAr9BYw0QJiPPaPcQc1LU+sfB/xdTMaCxDU1N+dpIJRD8N1Jzy/oU3ec3nq2yFl+441548y6Yzeo4w0ohq7DVVeHg80bx9WVlXovuPnmXxPU7xHxFIDGAIgOcdgnHALczLyXVGU9DHxBUP5nIpRcOJzqwx2b1DcyGflEw4y9X/wbmscFwF+1ddIZ05GY5N8Ao3td0H1HL+A0Njag8ZjESiiBq/aeTLT6ffBWbQYAEBGio+1djjebgCGtnwdWK4xgnqEjAFZmZMT1vHKwr3obtLq9MCeMDGJEkUchgkklGILh8hhweQygqf3jFpM/+dhsUmA1K7BbVHTVGVcIA7VVldizcyu+WftFu0TkSef9COdek9uPX5EkSZIkSZIkRRYiuJgjOxkZ4H5v1zcnO38zAKXDBwl3F4e4/WrHiBcX4czc7Px16CwhGTjzluz8TYuKCiZDJiRLQaAoCq7OugqvFb+ONWtW4+yzz+lWB66kpM43cA8bNgJbt27p8LGhQ4d1+ryUlNQeJSPruoF9+w4AAC669CLYo7o+ByRJ0gmGwE44PQA8AKr6Ot3jeLzPITmJxNNfbbvJUOkCMMf3ecLQcBGMaQScycDj8F907hEGJgH0Sm72vK1M/Pslywq6vEB926zfXWWwOL/LSQnVLt09s6exdOSVrCz1e3FDL2JFXE7AJDAyACQzEEOtm/YY8JH/zHQ1CKVgbAYrb73fcPCDa4qLe9inObieX1mwLSf7vnMVqJ8hcIXktGGp8fsjNSH5CAIYRUVBO37x+Mo+TyFJUmS5fPF/rgjujJyNAMnIhYVztDmzHigkphwAUKD+D+i4AmOw5M68/9ljE92Y6I9Ligr+2J9rngjKy8vHCSGuJ6IzgM7rZ/uED/vd+7GuYR2a9P7P+T3sPQwCYXr8dNgUW1dD04UQP/b5fDsAvNHvgUlSmN05fcJ9T67ZNhVAhFaM47o7p06YdOzmtmefdTYDuAnATbnZ814B+Kfo4vdNh7MCDgIW5GbnzwfopsVFDy5D6/lcG4YErCBr0jAKvTj/y1lZam38kCcA3HkkkD4yg5EJouKam/MA4gWJ6fG/Iqez41bn/eSFF+bXZmXlZSQ5HOUAYjsbZ2ga6svLT/33Y4/ee8kdd/7YarcnKqBhzDxFIRrLhGSAkglIZuYERHghlzDRQWgEczUzqomompn3gsQ6Umi3oSvVKqHqklHUEO5ApeCQycgnmKaaUpRt+azt9ugJp2LkuFMAIrAwoLnbvwbVVFdDb20/GRMXj2HjT4OvuQZs6CGNO1K5drwOsP81T1EVREVZAzwjQrGAa+friD8rL9yRdImIoHZ8Ob9b4qMU2MydTyCY4dEYHu3o+xgigI95w3Rw7y5oXi90XUNjQx1KS/ajsb4OPq8HfMzAsdMvwuV3PAxrlNzwJEkDUVaW01KnHxplEI1hgREqkweECpBeAeg73//Xippwx3hB1q3RpBujFFCmIUSGQrAzi1oVpgpd1bd89OrzpeinpCFmposvv3EEmdWpAkoqsUhmIgdIqQOLWiYqMxnamlVvLC3rj/U7c8EFThMSD6UpOo+EoowkII6BWoAqWOVSjxK994swtw/NynpFrft/9s48PIoi/ePft3uO3DcQ7ktukVtFUSMgiMrhMairQEBIAixKWHVXDT/HJYi6rqKsECJC1L00rud6X6wuusohiBwi95n7nElmprvr/f0x3EnPkUwSwP48zzxPJlVdVZ3pTHVXfd/vi8/as0fuzLLmrFSwc+N7uU0uijufsdvt0lffF3eE7O4Os9SNmWNAVADh/VxT+rfbZW/mRQgDAwN9mFGBcz1dJTdt5PzsaQuHMLifTnFNzprsZ5uy/2DJyVs0NGP6wm1g9KmvnIF+GalZ63Pysoc299gMLkxGjRmNdf/5BsVFxdi9ezd69Ojh9xhZ9gbHa5qGt99+C4riweTJd0CSJBDpP+ebTKeWNt9443VomoZbb70NJpMZkhTcAsO+fQcghEByu7a45fZbgjrWwMDAoKn47WV9Spdu2HY9QfpfS48lIARP+f1N1+wAsMNmy/xXQlTEJGJaBkDf0k8X7kuM/IzUhTshiYdzVi9+6+wadrvddGy/upr0gsSON0QC97z66tPO4MdwivJZ81MFpFkADwBE5Nm+uXTmz1Z4X0lg9AYwCiTuGxXXwVk6a8EWhngx6cWleY0ZT2PIzVuyc+7Uh4ZrJP9PzwnsFJzcuU3svnHj5nU9lwXJBgYGBr6QZPnWEDdZNz1LPbTtbJ5dsF9NO/42MWNa1uycl7NXhHgsAID0aY/8H4hmn3jPoOUr1yx6tCn6upA4dOhQe2a+g4jGA76zLBR7irHdsb1ZhMgAUKvVYm/NXrSytEKfqHqXdE5gIqJLAEw9cuTI4fbt229qlgEaGLQg5e+/Njbuxtu/IuDKlh7L6RBQmbzvp1Y0rK/u/m1O3qLJdrtdKtyv/ZPBExG8eJUAfikjNWsVmKcIQmcA/lKTvfrC3xcfCKYTttnk0vj2aWVMy4McX3AwzS87Ujm/LG1BRnz5oVXUjMGb+fnP1qam2tuEQS0AEOurrur29P/oT3/Kb9PFNMT26KObi/bjaw8QR0AYAWGapobLMiwsyHAAPQtJYkFk8qgEF0NxyYpweWCpcoShdHJHatF9fYOmwRAjX0AwC2z/aM1JIXF0bDx69hsAOi5EdjtKwOLM7+3y0lNaq7Ydu0CWzTCHxcDjLMcJfZNHUbB+4zZ8t2krFEVFj26dkDJiKBLifX4Xn/dozmIoxaecd8LDLLBYAv+XOd34R9Pqv9cwyTJMsgwhBEym+uckIQSE8OpvfOy/+UUp3g6tphhyRN20p+cKJpMJV195Bb4oO4qKisCDXkwmE4YPG4rLh1wCZ3UVqqsr4ayugstV633V1sJVWwNXbQ20s4T2pwuRmRk7tm7Cjq36z2hRCa0x9Ma7cNUdc0FBbmwaGBi0HEPGp0VEk9ZOkuS7ANxZqhztCUhE7N0s4hPf2WwCYFZHTkr/lpnfYlX71B0Rs6chAtdRE2a2YUl6AED3+soZKGJJLFr75qrDx39DI26cExduwSWa0O5mRZ1IQCsGQzo+PiIJAgKykDzXTkr7UWb83WIx/aMwXi3dmJvb4JT0drtdWrt5f4xJyF2FJE0fdXP6eJjlzuwN2QCfmNSOB+gQMzTJhJGT0vYQ4X1Nolehhe9eOzCuCqETjVJKaqoVVaYkWZNuZMIs4GhvCCnyxBbj6bMraYRwzVk4clLapyC8C5P0TQFKi7fn5wftTJlimxMle9S74HVCqAMDNQD944u3c74HgOG2zPAIzXGxEFJqmfJZKgMRIA0QQKwMbeSktDdlYZn/6bt/aVbx9rnK+PFpEU4ZbcF0MySe8p/NR/uQBWZAAgRAXk8jAAzSgK9+OFYwcmL6exLzO6rq2dgq0lmcH+BixMhJabMBTNGtIPDdF+/mBhWtlWKbk0yK+hgB/esUMm8psFTcF9R1Z7dLI384lgPii/WqMPjPX7794r+CGaeBQVPBwCcEpLf0OHwi0WdN1XRKit3EpG7QKWbhrtW3aW0xiHPWcL+M1IUb4MMhOSM1a0NOXvYwGA7JBo2EJELmQ5l4OPNhFBYWoEOH9ggP97mni/LycsTGxuGdd97E/v37AQBvvJGPyZNvR3Fxke5xx44dQ48e0Xj//X/jwAHvnspLL61CevpslJeXBTzmffsOQFVVhIeHI2vRIwEfZ2BgYNAczB/a77vnv992N5P015Yeiy+YeOH8y/qeFAzne9dS/mGzZb6dFBlxE4NehJ8NXp2We0PQmxmpWb8Q4/4VL2efdPwr3K++Rn7cfZl5Xc7LixvkEsgpdlPZRZWriGiCAMeH4DYpEuArCHRF6azMZwB6J6Hi0Mzm3HA/wQuvLNk1554/XKpppvUE+HPebtu5TeyeefOe775s2b2GINnAwOC8g0GdKbSPur4fcI5jt9tF+rSHRxNJn3nHwS8ACLkYefa0hWlM/NiJ9wR+Lycve26o+7nQKC4ujvZ4PGMA3AE/gVPlSjm2O7ajwFXQPIM7rd8djh2INcWiXVg7X1UjAIwEcOzw4cNFHTp0ONw8IzQwaBnsdrvgRx+96vn1O98F4aaWHg8AMOPIvcN6d6RhffxOOMcNeCanpdkjJEVdBcYkAMGm6CIQ/TUAxUq1R/IENScUp81vW8q0mRitgxxTg2HmnNK4Dk+WZ8wfGJ+zdH9z9ZuXZ3fZ7fbkgv1qIXw4JAMAAwML9qub8h97bLDdbi8A0LyTgoHBeYIhRr6AcJYeQ+nerSfft+/cDRFR0QAzlNoqCLWuRsnh8EbuSZKE+ESvSFU2h3kFzMdVmjt37cMna/8HVfWKODdu2QFFVXHLTaNgNl+4l5BafQjCcyqyMSExOqhECeERhBOLk47a+g0Ro8PDMWrIICiahsSY+uc1j6qcFCNbrA3XdwnFAbX6yDktRpZlE0aMuBrDenXBkiefQlV1YJGlAy65BDOmz0BU1CmXYiEEVEWBorjh8XigeNxwu91wVFWipKgAJcUFOHRgD4oLj53heKyHOSwcA0bfimHjpyCxfVdDiGxgcJ4w2pYWyxoPY4EbCfKtDHT0fxSbAFxFhKvIZCqIUJx/u3ZiWn6Yx7o5GAcY2YoIVeEUgIbUVy4BxzQ2LQNwOMU2J4pExtWkYbbGfBPI95TDgIWAoYIwtFZRZ8QUYdloW9prn+XnBp2+5MoJM6L/s+XYSImt0wTxOADH830FNOl1Z8a9ksYzQDVfXLul9mXZlvZ5Q8ZxOn1tNktbNeEaUcGjiXAzEy4KcEBtANwNxl1QxI42FJ/XdmL6+5+/s3J7UANwqWFswigw23RqVIPxI4DvR96U0R6qYx4zzSJwQj0zigygtZtd52l6hdAx4sbZ8RazermTeRxAE0DcGRzAB0ucDGCWIMyULOb1pUp8XsqEez5tZa3a50+ULBG2CsZw/QrolmKbs3Bt/nJHoOchqaIvgLEA6goOiZLaqAl9tgNbAm1v5LaCtiAeU297AAjwCJJ/DrQ9A4OmRiUpy8zinBYje9ymJlMS9umivqb39MCM5bn/+HNJU/XdOIhz8jAkIzVrI3wIkmenZm1dkZfdH4Yg2aCRxMTEYMJtE/DuG+9i48aNSE5OhiyfWkNiPjOIu7y8DMnJbeFynbrd1jQVbrcbRUWFuv04HNVwOh0n16wAQFVVKIri87jTKS4uhcvlhtlsxsLFC4M4SwMDA4Pm495L+/3tuY3b4yDoLy09lvoRz8wf2i+7vpLjouT81FT7e2GSMo4EvcpAZAM66cGEdzJSH9lPkjyHWbiZMdHXAQQ4ncJ9fQP6Qknagr+UcuUMAsK5aW6N4gFOLYvrMLksLXN1Qu6z85qiE18sf+mJ3Rmp9kGAuhn+heLtleqiPamp9ovy8uyu5hifgYGBQaggIPBIxcAI2Ihg5cuPf56RmlUJIJaIKH1a1rcrX87WX68MkvTURzIYfErgzOLdFS8/7nN+NPDidrsvliTpDiLq6muvuEarwS7nLuxy7oLCDfaEaRAaazjsOoyfqn9CpCkSsSaf03U8EY0hoh+ZOY+ImnewBgbNDBExgPHPrd/+JJh+B0KLOdLWHC6Ae0txN7rUvxD5dHJz7TUAfpOaao8LJ/U5MGwcvCjZJwzp1tWrnwrY0r101oJbwZyPoNRRoYGAWKHR3vKZmffEr3p2TXP1a7fbXccdko/Cf1bIAQUH1O9sttcvz8+f3OxBpQYG5wOGmu4CouzAdvAJx0IidO7eE0QETXFB89QvhlUU72aNJMmwWL3aI5IkkHRqnt66ffcZmzoAcOhIIWpdF3YAPCu1gPCet8kkIzwiuOwIia1Pzc1HT3OgPh0iQuv4eLRPSoKsI249Vlp2cqkzKrYRc5mmes/pHEcIgS6dO+PO22+HxeL/b965cyekz7wH4eFh0DQNQmgQQoAIMFssiIyKQXxCElont0fHzt3Qp/8gXDVqHG6+Yzrm/X4R5t7/GAYOHY6ws1yaSJKQ2KFK7ZyRAAAgAElEQVQbug2+CmPSsvDbl77ADXP/iFadekCSL1wRvoHBhcSIG2fHayoeZEFrANwXmBD5LIiTGfgdEVZ7LO70MWOmNGSzrF4YCAdrppSU1DBZVR+SNM4B+MaghwhcTMBiVuj3KXZ7UF9QY233JFgl8yICvwDiSaATQuSgiQJjAjEvFwotGnfLzA4NbAcpk+bHJXvi/w/MLxHwABg9EPwDLwHoS8AfmcSakZNmTbHZbKFbhGCYGSJ89E1pndgsVoGRCT9OTL92xtyc0dpsVrPAtBpE86AjvPUDAXQpgGclSVpZrCZc5+9zNbus6wk45qNKjMnl0XUkPhubzSaDuR8BbXWqtCamQYG2BwDs0S6G7434n8Nd5oPBtGlg0JTcP7TXOSq2PcUDV16kb6PaCNJTs3owcItOcfnKl7N/2xT9hpKcvEVDQdihV85Av4zUrPXNOSaDC5cx48Zg4JCBAICCggIcOXL45AvgOoHBO3Zsw5VXjkB4eDgkScKVV47A9u0/+e1n166fMXDgQFgsFpjNZowfPxE//fTjGe2f+FlRztyLdbncKCnxrtkseGgBYmJ9GqAYGBgYtCj3Den7AoNntvQ4zkYIPHbfsH6/81cvL8/uylm9+C1TdGUigycAaKBAhrqwEB8A+BjwLThg0MxXX33aGUzrxbMW9CxNyzxGzHMpxEIAHSKY8dvSWZkFFTMyhzZDf2eQk2ffbzaZLiagKoDq7cOg7p437/lffcC1gYHB+QWDPw5xk0GtjQiLcnItlAiX/3aG3afFbaBkTHvkLgKdFCIz8FGOIUQOiKKioh6SJE0houHMrLuvckIMvN2xHbVay+yze4QH+2r3YZdjF1RWfdZl5i5EdHthYeFVzTQ8A4MW575hfX/PMm5EkN/NoYA1DYVfb8CBdz5HwYEfcxvaTl6evWLFmuxpmqW2E4hXIYigF9/Qv1bm/fHTQGuXzspcCvAbaAEh8mmQIKwuS8tcyczNNo68PLvLBVM3cADXEWNoUuSPX6WkBLcvb2Dwa8EQI18gMDOqC09pFCKjYxETnwihqfDUVOg6v+oJYE93fbVY6n5/ypIEopacf5oeMlmB46Js5rqbZP5I7ijhhGb1WEkpiiuCN4l0KQp+OezNokIEJLRuRACjJHvP6RyGwaipdaKquhKX9O+LCTfdAIn0v6Y6duiAe1KngllDVVUlqqorUFVdiWpHFaodVXA4q+FwVqOm1gmXuxYexQNVVU9+lgRCcrsOuPmO6bhj2my0anNKV0Qkoffw63BXdh4uv3kGohPaNPn5GxgYhI7hw23hFrO2kgQWAOiAxj809WXCY1pkRLrNZg8uOkUHAkcQk1WOsz7HwILjYumGjjOJmTPlzYdnBHrAhAkzohVF/geBZ4PRvhF9n04bAqe7hfSSzWYLesPuqlvS2kqoeR4SftfIv4cXRphXvEpLS9T4BePGzQvNREgwQ6ZEYaI/EeN6gEJyTVyojLalxaqsrSHQXBCSQ9CkFcC1ErCmRE3wubj+4YfL3AL8tY8qJiFLAW/2liM+CuBhDOh95jEAD0xJTQ1Y2C8R+RYjE38D4MKOAjQ47yAgv6XHoEflrn3ISM3ijNSsV+bY7FH+jwgMe4rdBPAPeuUk+XBhP6cgzlmzqB+ATT4qDclIzdqAll10NrhAmDlnJrL/lI0bJ96I0dePPvnyrinVvcTKykoxfPhwpKSkoLQ08D2ksrJSjBgxAldddRVKS4t1650Iyvf+rGDfvgMAgFvvvBUdOwcfu2hgYGDQ3Mwf1vclZvkaMFregYkZzqOFczIv62MP5rBly5a5V+Ytfk9YOkaSJG5AQzMysJ/Mn4w9OXmL/hlMk6VpC+wy8TZwSJ5dg6WNJuO7spkLljd3x8tW2Q8TTL1ACCRrUHulumivIUg2MDA4n6g+Ylkd0gaZNwRTPTf3yUqA/3XivSa0bY0dwuzpD10Dor+e/AXhp5V52eMa2+6vgX379iV7PJ7JAG5j5mhfdUs8Jdjm2IZypTykY5BJRqQ5EgnhCUgIT0CEJcLnnrhTdeKXml9woPaAz3aJyMLMlwkhph87dqxvSAdtYHAOM39In4/LHWEdAc5prj4dew9hz1/fRdmPxxNbMqalpj7QqOeI3Nw/l+SsWTwLmqsjAS80fpS8PdD79tKZC14EcF/j+wwNzEgrT/vdm2y3N5uuMS/PXqGaxcUA/JqdMHBF7y7q5/YgjcIMDH4NGGLkCwShKXBVn8owk9QmGQSCUlMBFvrrktbjbshCaPC4T2kcZPmUvmLIgL6wWMwn3xMRunbpgIjwhponnh/IEa1AJq9brqYJlJc5ghIkt+tEiIrxbqxpQuDrH7dCUQNfIxZC4Nut21Bz3IHabBVIaN3wACjJHAE5olWDj28umBlghslkwnWjRuK60ddCkupuUFosZtx5+21o07q197jjrkpCCGiaejwtqwcejxsuVy1qapxwOKpQVV2B8opSlFeWotpRBY/HA0mScVGvfpiWvgBJrb2CZKGpWJe/Ekd3BZxl3cDA4NyARk5K6x6eHP85AFsjnH7rI04wP1HmOTodaPyDD4MsIDzH4DSvaLaREMIYtGz0xLT+/qqOHXtPgkOS/w5gjA9RZYM43t6YMjX+k1E3z00M9LjRN6V1MgvOBXB3SP4eZ5JADLs7zJ0ZjEjUBzIJpIGDd7L+dcE02pbWX6j4H0A3wCsiDhFEYE4m5jdGTUxLHzIkzeyj7ufQ3dxmE0BDAv2fFpoWB+Ay3wPDAFSEBbTgZLPZLAD3AXSvecFC+u7DD58PURS8gUFoIEG/b+kx6FH4340nfpwiItXq9GlZ+aEQJRd0UZcTqP7AAaZVK1Zn/9zYPpoP4py87CHwI0ienZq1FYYg2SAExCXEYdyEcZhkm3TyJUkSmjPGXToedL9u3Tpomobw8Ajs3evdxB12+TBcO/ra5huMgYGBQSOZf2nPr4TTlcSM/S01BqGo2PXSGzj49ucLGtpGbm66smL14x+WOi8xa40RJesMUViL+gRzQOnMzG/A/Cj7Ezk3LRITzy6Zmbmem/k+bHmevUCRTJ0B1J9m80zaKdVF+wxBsoGBwfnCWvu1KiGggIuAaPvtugkZqVlfpqWt9LEmeSY5eYtvw/G5jsFxGdMeuauh/WdMfeRSZnntifdEtDtnTbbffQED4OjRoxFhYWFXS5J0BwCfG+eVaiW2O7bjUO0hiOPZqUOBRbYgKTIJbWPaolVkKyRFJqFddDu0jmoNi1z/do2AQLG7GNuqt6HI7VcjFwVgNIA7qqqqAt6jMTA437Ff29V137C+s2Gy9ATz603Vj/PQMex97QMc+vArKI4zb53DYf0mFH3kvPp00Yq87N9CM7Vh8NJGNLVQcRQdyJj+yIO+Mo2WzMp8BXTuZeFh8KSyI5X/aM4+V616vBCCBwMoDKD61QX71c8MQbKBwZkYYuQLBNY0qJ5TqUEio2IhNA+E6lu3EBsfB8ArfK04zTlGDosCHY++69yxLW65aRQu7tMdvXt0wairL8V1KZdBli/sy0eObg9zYq+T70uKq1BYUAG3KzB34showpArTSc314orKvD9jh0QIoCHFWZs3bsPu48cOfmrtp3ciIrznXrFF+akPjBF6WUUP3cZc91oDBo48IzfxcREI33WPejerVuD22XBUBQPHM4qVFZVoKbGiejYONww8faTm5QA8N3beVA9hhmhgcH5wkhbRjuAl5JvsWCDIcDMxE+MnFh0eYjaC/E4ycLg+70Cx/pJSUkNU8PlmQClBNBgOYCfQLSOQGsBbAFwFOQ/lSozrmCoDwy3Zfp1SE6xzYliE54B6CY03WZbBBgPyGXmSSFqrwPIh5utAUZOSu8mVPwFjF7+azcYYsIfY9rzON2FFMYWeK/l+g4ngLuOubkgKaDehNwLQHdfVRh8sVlC+0Caq/S0asMkdYL+dX+YoO0GKJSb8gYGjWbeZb33EVDQ0uM4G8VRA632zHt3ItwmItXqjOkLP2hou3OmZPUBMKu+MgY7k7vK6Q1tuyXJyVs0FIQdeuUM9MtIzVrfnGMyMDibsrIyrFu3zufrwAHfzlBevFNpeXk5XnvtdWzatBlCCLRq3QrTZk1r2pMwMDAwaAIyrx1UMf/S3t3AeKC5+y79YRt+zn0NmtsDMF+UMf2RexvTXn7+ZO3F1Y9/mJOXLYMwHiEQJRPx47m5uQEt5DNAZWmZm0DnTqYLIgwtm5W5h22v6woGmoKXXrKXSRGmNgAHsiDeVqkuOmAIkg0MDM4bWEwNRTNmpwPkNa9KkTyHPOnTsj4MfAw85dQbygOApd/tGLv0++0/9Mn4zZN95vwGfeb8Bn0yfvPk8xt2bPzLpp9Hnd3EnFT7QEj03Wm/2rNizaIeDT2fXyF9hRB3Aejpq5JLuLDbuRs7HTvhEaHziTBJJsSGxSI+PB5hpjCYZTMssgVhpjDEh8UjPjxe1yFZYQUHag/gp+qf4NScPvsholbMPN7pdNa5hgwMLnTuG9T9l/su7Xu7LHMXIlqIUASjEAkGvXTkk/8uOvjuF3CX1L/lxEDXjNSFdzS6v+PkvGovWpm3OFOCqS0IzzaoEUYbMD2ZGNnr6OzURx4+u7gkbf6DBEyp79BzhMklszKfaM4Oc15ZfASChyAAh2QA1xQcMATJBganc2GrSX9V8BkOyLIsQ1NcYD9RekmtTgX8HT6wBzju/EuSDHN49Mm2+ve9CLffPBZ32W7AtVcNQ2RE0JnXzztIMiF2SBrI5D1XZkZlhRMH9hehqKgiIJfkPoMk9B7oXS8UQmDr3n146+tvUF2jby7gVhR8umETvt22Harm/UxjkxT0uMTRYNcgMkciZnAaIJ1/819UZCRmTLsbgwcOABHBarHgztttuLhv6DLLCKHB5a5FdXUluvXsgytSxpwsO7htPapKzjmdhYGBQT3YbDYLq9rtAF3D7Oceh1AA4D0wPQ1gjiTwIDNWgvEVQLU+jwXFEalPptwys0PIBn8KN4BPmPA8Mx5hxiNgyiHQxwCVBtIAEw0vURN03X/kGFNPBu6GNzpejwpmfgUs3SMETZclTNdA0yWhTQcwHQJPAdDPf+1FYubJkUqtP8E1kaLMYyAQkXAVgE8APEZMcwlIB+EhBl4GcDiA4xNYoidTbk4bEUBdg0YwfnxaBECpYAyDP4E5wwngPQCPgXg2A+kALQSQD6DM57FeWpFED5d74uu9OWCSCgHylfowWRGiawD9AMB4AP42gxM1IYYF0phK7rZgdNKtwNijkelQgGMzMGhWRJh1oP9azcv+133s/zGPy0jN4ozUrFeCdUoWEr7SK5M1Gma320Nnj9OsEOesWdQPfhySM1KzNsBwSDYIMVarFcwMTfOfQcrtdvt8BXJ5CsGQZRkjUkYgPiEeHTp2wG133oZHlzwagrMxMDAwaCmI77u0z9P3Du0twfus3HT3JMyo2nsIO174G4q+2XxWGS3y5bIVTC85a7L/nZOXLUHi2wA0WPnDTFkZ0xfWZkz9wyBm1p0ovrTbTWVpC35kxqCG9tWEdC2P+9/PnOYrE1DoWb7c7hAWcwK8a1T+aKNUF+1PS7NHNPW4DAwMDBrLO2nj3mLGL41tJ37Hts9Pf0+E6zNSszhjatbf/K035Ly8+G8nAj6iL+pkWvr9diYJHxHRQJKlKBABRCBZimLGYE0Tnz23fofnufU7JwJARuofuggoJ5/hGShM7mLyKao1OEVhYWE3AHdJknQNfGSMZDAK3YXY6djpV/QbLFaTFdHWaJjq2bOXJRkR5giEmfSTO7qFG/tq92FvzV6wj/gtZpaZuTeAuwsKCkJirmNgcL7x28F9D9w7tHd2GDkTNEX0YOa5AH4IuAHGYYAXA9w/DI7o+cN6z6wt+HEx/OyPErCikUOvw/I8e0HOmuwFJKE3B5PO/UxaM2hxRmpWSUbqI38AgPL0311NTI+HcKhNAgEPlt2TOb45+8x5ZfERCaYB5H8/HGBcU3hA/dLWzMGkBgbnKuefMtEgYDTFj5YKQExsLMLDI1BbWwNndRV+3Pgt+g++HCRJkK2RMLGA5naChTjDLfbXghSWgLjhD6Dqh1xoDq8glZlRXuqAs9qFuPgoRMeEw2Sqf04hAi5PkVFTzTiwW4CZUVRehvwv/4OOrVujdXwcIqxWgAhujwclVZU4WFAEp8t1so2YOBX9hlZDJwjSL6aotogenA7JGtuwBs4BTCYz0mZOR1VVNaxhYQizBm62oKoaqh1OmEwyoiIjQD4U3UIIOJ0OXHnNWGzZ8C2qqypRVVKAgj3bkNCucyhOxcDAoAkpFvHdZKb5DI72U/UTWDBHuCNK3ZYj7rH9+rnXroVksTisWmRtmBDKWCJ+AaA4vQaYMVRiugPA0yEavgbQhxrh8TCT+rPFJbuOtvW6Dyfur7FQrMWqeiz9mLSlAAb7aSuZBA+D18X47JGTJmUMk8C+IjoqBOMP4Z6wf3z44bKqs8r2A0BKaupX1jI5T5VMrzNYd8OOgM4CIsVms32Tn59f7yZiyqSMaySIeexP4Mn4AZJ0v9mkbI5BR0e/flDt9kd5SFq6KaxADbPA2o5Iux+EKQB8TRSdZMYzV06YMWrdu6urffbZMKrBOAgJpWBEAkgkhkOSTb8qZ1uHWRpEQswG4DOCjZk/ZhPNhxZR0MocV5PfDyrsdu5rs5nbIT7cI6i1SeMnANzioxkCMFQQ39PXZntw+1nXmiXaWaxWh/8E4Cqd49tIEncF8J1OOQDAbrdLX20+MikAwRMxYSwAv6mzJDK1Fcx6YmQGeHd1a3FEp9zAoEWZ379b4XPrt78D0MSWHgsAVO85CLXW5b8iMEVEqlPSp2W9IdeYpi/Pt/t0xkhPzfoLAB33dM5f/upiXWfh8wPinDwMyUjN2gj9e4whs1Oztq7Iy+6P0KZPN/gVExsXi5qaGjgcTsTGxujWS0hIwNChQ7Bhw8Z6y3v06ImOHX3HCDqdNWBmxMXH4Y4pITOnMTAwMDhnICIGMNZuZynupp0vEcMGhCiTD6PWVVa+f//rH/ZhoXsbEJMY2fsfACaHpE8AOasX/wuANS314d/IkFcwWH+y0IM5DJJp05zp/1eVMfWR60prd23Mz88/GQXDdrtUdqTiA4AuDtW4Qw2Du5dx5Fdse30E5U/2H8ETInJz7TVpafYEyaOWwfcaCwAkS25197x59t7LltnPXkcyMDAwOKc4yon92lNZJcANct1iaMNXrfy//6Wl2SNkj7qOgVOB2hJ+IyLV32RMy3pdqjHdo7fe4II5ueeklPLI9m0C7dYM8Nt/Xrflq19ezL8KxxcnCagodf7cfqU9/zwNkG5ejh49mqSq6i1EdCcz+9w0L/WUYlv1NhR7/OvPZEmGVbaCiODRPFA034kZZJJhlvXjjEySyVvuo5kqtQo7HTsRZ45Dx7COuvWIKIyZr2HmwsLCwqI2bdrs9XtCBgYXIOlDhyoAdh9/LV+5YYO5IioqTHaQNVyoJreqyEA4yKIJWTKrViF53EXCde8NPeoE5y1btsydMeXhKZClj/T6Y3Dc7GlZL694OTvkqbhY0CKiRptGJAK05HfTH3lYiFoz/BvwnAsQS3jj2PR5HdquWeb/yzlELM+zF2TeY+9dq6m/AEjwVZcZIxIjt3xjs9muOP25MxiY7RI2W4ZDotFgMQygLgBiQRBglAL8C5i+hap9SMMW/tyQPgwMmgPD2SaE/OmVVyJrXJZqPv53vWxAHwwf2K/eusxArUeFaHDQypmo7hps+OeTKN3vNX3rP3Q4OndM9nucYMaWjRtx5JDXcE2SZVx61Wh06n4iiJIhNBVKTSU0JaCN3YAodUn44GA4XJr3Erzr+qtxUce2OmMEnKoG/bXOJoYFtJpiOHb+C7X7vgCEerKIiGAyS0hKikF0jL7Q1VUDfP2xgp9/rPs8KB2PchWibllcKwUXX1qN8Mjg5yqSTAjvOhqRvW+GHNEaDbZVbiQEINIsQ9bpvqLagef++T4AwCQBI5JUJIeF7sN2uT2oqKiCLEtISIiDHKCo/uN3Xse2LRsAAIPH3YGb7m36gDCJCOEWk+5HtW7TVqzf6r2nIIBLXEXhy+69NxCHCgODc5aRk2apAOk95DCAN754O9fvZlZKit0kxR17C+Cb9GtRLSBWmc3C/nH+Sz7dVq+0pXUKU/A3Bq6E/v3Sh8JjmrH2g+X12qePsc3sqiqUD9AQP8NXQJxHsDz0+Vsv+HQ/ttlsllIl7t8AXeejGoP4KVHePmvtWrt6esGQtDRzbCH9HcS36RyrMmgFx7kfXJuX53fiHzVx9lVMWj4AXyunnwizadra/Lp/p6vGTW9lsZpeZNAE6P6dSQXEJ8Jsvn1t/nKfgrGUFLuJ4o49QMz/B4K+fQBQLRHP/+ytF9egHlFVyvi0JMmE5fBu4PqDGTgM8HsWDcs/fu9FXw68dRg5Ka0aPlyqGfgvI2J8uFvzH2UWAAeiCnh7/usKQPVOtqMmzGwDSfrojIX0syCiJz9/a+Uf9MrHjZtndVvd38C3cN7NoFzZzAs/y8+t9DVmm81uKVGO/l4C/sCAL7elSpLkwZ+/uaLOouqoiTPnMklPQfd4Wigq2j5x9v/M6Vw7Me0yIvzP11hPo8Yt1GRfgveUFLtJij96PxhLdKo4ADz4xdu5IY+iNzAIJUvX76ggoKUjH8t+XvNaZ+HUXgHxzUEdSfRhzppFN9RXNG/6Q60UlguhM0ft3G8y+/re0KNq7txExWNdDPAYAsUBHMmAGd6OFICcDK4A+BMzyVkxuX8uCbaP4GHKmL5wGxi62RUAbMzJyx7a9GO5cHjoLy8nWi3WklYJcbhr/Ogzymo9KrQWW+jQ53BBET76z7fo0q41pt147RllTkVADdE61t5f9uKZJ56BJEno1esiAN4A4dpaFzweD8xmC6KiTk3bxcVF2Lr1pzPa6Nq1K7p2PZXcoKamFi6XG1arBWFhVsiy9zFj9+69UBQVU+6Zgsuu8Je0IzAkIkSbz1xfeP2zddix7zCuGjYQvbqdewHNsuRdczidV9/5BKUVVYgM80Q9MHVqaC2/DAwMWpTnN/00gIX8FBiDAI4DKFB3XRVAJYi2sxBZ8y/t+xUAZKRmlQGI1zuImVk2U7/lq7KbJFArfVrWPURY1ahGiEokiImtO5u/t9vtaumszEUAskIzwqaFwCvjX1w6m5o5MCwtzR4hedRSwOcaywmOUrh68YoVT9Sfs9rAwMDgHMFuZ2lT+0/KEORahtA8Pf+dMf4MZ+XUVHtYGNTNAHqdXZ+Zv1z58uKRZ//+uQ079oHRJdhxA4C7rBJ7//FvgLl2RV525PGAJAM/MLPlyJEjYyRJehSAz3WNarUaW6q2YHPVZriE/haJTDKirdGIC4+DTDKICJrQ4PA4UF5bDlXUv1wUGxaLttFt63VGBgC36kaRswiVLp9L5rBIFvSI7IHL4i5DgtmnPg4ADgB4vry8PLdfv34+91gMDAwCY3Zq1scMjPFRRQiL6JCb+/ixUPWZMTMrBSq+DFV700wu9KRmi3cMEfRp4ovP+Pq7NwmZmZnhteWRBQACCZLdktzFNDjQbIr8w5JhIM4D0AfBazgZoLchi9nU/5HCII81MGgyDGfkCxQWgU0aEhF69u6N4sJCeDweCE3D5u//C7PZguSOnUFEkGQzrNFJUFzVUGqq8KszQiIJcmQbxA6ejfCOV8Ox/TUo5bvBSi2YGYpHw7Gj5aiqqkViYjSsYRZI0plzRFgEMHKCGa3bqdj6vYqqCkAIbx3B7JUxneiOgLAIDcmd3ejauwbBGimSOQLmhIsQ1fd2WJL6tpgI+VzBYjYhKioSJpMcsBAZAGLjTj24Fe49z83ODAx+DcQVjPAtRAYI+EomOfvj/Bd9CpEBYF1+7qGRk2Y9TqCXGKg3WoaAgWRWBgAoROMmx3xRbl6wdu0LfheB8vPzPSMnpGdDwmCAE3WqEQR1luOLYwGcIW5ufcgqua2e7j66cILweSBCZACQax2btMjw15gxD7oPSNxLVpUYAHXEyGaraSiDLtc/FkzEH5tMYurHfoTIALB2rV212WxPlSrxFgAPQd+9J0ow3XbdhBkfffru6qP+2tWHVIA/lSR+9PM3X9yAJrhJIqATUc3va60ctNitPpKVuKLWtrn5a/Prfh6hwmOpHQ9Ivh28md+zyFjysR8hMgDk59s9o26euxysJgM8E/op9GJZaItsNtvUs6OOhUQ/EaMI0FvoF30jIwujAehvmhJNDuIjjjDLdAuAl/UquFtVmsMVHqR3+RNQDY03BNqhgUFLIcmmHqypRS05Blmg5/LldgeAW2bMeDDaIiwrANwV0MHM4zJSsxjAq5LTNOd05yKF5Z+h808qE10ejBC5cEZmN5OMJwDYFA9w4vvk7JSaDFgAtgCIByhdYZFeOisTAPJlln8ft+rpfYH2GRzEOWu4X0bqwg3w4ZCckZq1ISdv0TC9oBYDg0Dp1qMbYmJjUFVZhf37D0KWZTgcZ2ph+/Q5lW24VavWGDRoIH74YTMAoHv3i9C585nJBQ4cOHTG+4iIcBARFEWF2WIOmRDZwMDA4Hzg3sEXbwEwFgDATM+u3z5AkuRrhBCDZKLODIoDMUFwFSQ6SERboIivvz740/r8yXUdeFniMSRovV5/RESayn9l5qFNIYySiGJ9pSIPCOYkAVpXsF899uU9DzwDqOeFEBkAGJReNnP+Z1i19I3m7Dc3114zY8aDrS3CUgDfwcEA0I5rTVvnTn1owAuvLPEZbO8LZhDWPRmFCESDRQTC2AIXm2CWGarQIDQ3wq1O1NZU0VB7TUP7MTAw+PVit5MAEDd+1Se/J+Yn/B/BP2iKOur9OePrrBvm5dldAHqn3f1wW0mW8kG48kQZEV2bkZrFDH6nzDng1vz8ydrS9TsfAHODhMgAYE2IRcLA3nQ1P/kAACAASURBVErJ9t1JhhA5cI4cOdJHluW7mNlnNgSP8OBA7QHsdOz0KUQmIkRZo9AqshWspjO3ICwm79J1aU0pBNfVoSmaArfqhslSv0xHEQo8ar1JJuuMdX/NfsSYYjAkdgjCJP24ISJqx8y3JCQk/Azgfb+NGxgY+IWhpgOm3dB3FZYkRfoXgCtC0V9amj0CHuUjX1pVBjMBaiCBqMkkzkMhMgDwdUWz5g9s/eLSzc3Z67PPPlubmmpvEwa1AP6DmQYU7Fc32Wy2IXoOyfzjkngIzgEQzL5jfRDAN0Ojm3nz44Cg+yHcK4znJIOWxhAjX6BwEE41kVFR6D9oIDZv3ARNVeGqceJ/az/G0BEj0bFbj5P1TNZIqG4nWAuJFub8gwiW1hcjPrEHPEU/wbH9dSilp5zvnQ4XamvciIiwIrFVDMLCztTJyDIw4DITuvQg7NpejUN7CVVlJrhqZDAAa5hAdLyKVm09iE1QEB6lBa0jtiT1RWSfW2Fp3R8k6+l0zl80VYUky7oO1PUhSRKiIoPPtmQN925aMjOqy1pUW2FgYBAAMmnTmX19N5Bbg/bE52+tCvQfmgWUb2WYPwAoFfU8TDI4GcBlQ9LSvtiYm+s795Y+m2CWHly71r/Q9gQk124TbP0vgSbq1WFCK0lRInGWGLkiqkAKV+J9uRgrRHzIR/kZfPLJq86RN6fvALgW+o6zCRqkOpOS1+WZLiWglY+7lgMM8czH+S8F7KqTn5+vpdjm/FlSlQFg0nPHJABDhWy+BEAjxMj8b5il336en3Ok4W34pRMYf5BCldCEsY1U7SvUIw4PDXZJ0JGZfkZbJYH++PGbuQFHhH/+1gulo26Z/Wewdg0Y9ace8XJruRqbDeCMSCLVpW43W83F0BMjE/WrtXpioCNGHjNmSqQKHhfoeAFAgjwNPsTIkXBaBGiQjyYKI0BBOW0bGLQE9w7uUfzM5p87yIo4CCDw6L/QIMIovEP6ZV1OznerVz9VDeBuAHdnpC78COCxAbY1RUSqU9KnZb0h15imc6Q6m/Xc/xg/vJC36LtAGnXMvK+Ni6QfCWgd4Dj0sGmk2UrTFhRYhTYwatVzTeB0QJyThyEZqVkb4UOQPDt14dYVedzfECQbNJZH/vgIHsp8CLW13k1eSZIQHh6OiIhwRETU3UiNj0/AkCGD4XQ60a5d+zrl3bt3QVlZBZzOGiiKgpoab2IJIoJ9ib1pT8bAwMDgXIaIM4HN8L4axMrVizfMnp71EzN0RTwEGjxnxv/dAzTSwfgsMlL/0IXBT4WqvQhw2z6S+qdQtddcMNErVXMf+jLmhYYLfRvC6tVPVc+d+lAnjeT9IP3MTsdpr5K8efr0hwavWbMk4PTJ/OOSeIB7Q+BObMHtiNJO3TsrAGQChPA+bUgyoKiAyQL+YfEBSPQ3ML0Bs/sX6mc33B4NDAwC5r2ZY54E8NRNL36USsBUAvUHkAigloA9AvgszoqsV6de7zeDSO5fHz8GYERamj1J8qj/AnD1iTICTUyM/FGdPdP+MoGnNXbcba4cYrZcN0hFrvGMEwhHjx7txMx3MvNY+HH6L/GUYIdjBypVP67EsgXRlug6QmQAMEtmRFmiUKPUwOmpe+m4VBcqXBUwy2ZYztrL92geVLmr4NYCS4pbo9VgT80etLK0Qs/Inrr1mNlMRAOZedrhw4ePdOjQoVlFfAYGFyI5eU/sz5ietRSM3+lWYgzPmLFwcs7qRa83sjuSFeVZBukZMHkrkfx4qaN6cWJk5GoCJjJQr0iGAEyTA/KkOieRQB+z3d6WAnQeDhV5eXZXaqo9OYzVQpBfh+QBiZG9Ntrt9jMckvn7p5JhVV+E8G2w1mAkfhqS5WnesiQLivtZQ5Rs0FI090ahQbMR3J5gctt26HbRRZCOO8cqigd7d22DqpymrWL2Lvj8yiHZCmvbIUgc9QRihs6FHNUWIO/fTQiGw+HCgX1FKCyogKLUFW7HJsjoPzQCA66owfCx5bj25hKMvLkEV44rwyWXV6FtZxciooMQIpMEOaodYob9FgkjH4e17ZALUoi8/ceNWPH0Y3g1dymqKit81mVmaFr916qvsrPrnfzZuO4NDM5prpswox0zpfiqw8QrW5krvw6m3bVv51Uwy+8DpPOlQ0QSBkaX17PiFDjvfRGkkLVCDaslpr2+6hAQIUyoE/lqjYxkBnyF1ZuhUV1lh8++xBeA9HvSfSE7wiTVSS9/rCYpEkTXsf79KIPp00pV+h+CvLFZm7/cyQIr4XWt1iOJwQNTUuwNDc47IAQtDvbzu9BJufVoTwL5THUHSM9+9s7Kn3zXqcvnb67YR0z+3EqsGuQ6ouGvP1xTQoJ+1D2K0Usi/Xx2SljkQIDrdUn30eaIkTdl6P4/sWpuA6Cb7vGEr957L9dYKDA4L1gwsNcRzSx18l8ztAjiDulDu+gGNuTkLbpeijBFg+mtQNskwm0iUq1m4Em9OsldTX6+57yUzVrwdzdJBSEQIp+COdlNUkHJrMy3Q9bmWeTkLRoK0HbdIQD9MlIX6jojGhgEisdz6ra0Q4cOmDzZhj59eiEpKQEREfXHucXGxtUrRAYAi8WC5OTW6N69C3r37oH4+DgA3uf76urq0J+AgYGBwa8MzVzkOwMOADA/PmeO3Z9gNWBsttdlwJQHfcexoBkre+oumJwHEBCuKK4WEVG/8MqSUmEVPQFU+atLhA4WIW/KmGL3eQ/MbJd46xNX8ObF/4bgMgh8A2Aegrl3JuoMxsMAb4JireIflrzMPyweyMGnNzYwMPj1wv+edf2a92Zdf+27s8YmvTtrLL07a2zEO7PG9n9v1tjMV6eO9StEPp3cXHtJTl72NTl52RIRnWGWkHzVkEYLkU8Q50ROqNq6kCkvL48jopuI6E7oBZyfqKuUY7tjO465j9XJYnU2ZsmMMJO+rtkiW2CV6982EixQ5a5CkaMIDo8DqlDh0Tyodlej2FmMKldVvY7K9cFglHnKsL3aO26fdZkjmXmUJEnTDh482C6gDgwMDHyS3Nn0B/gz/hG8NNOWGbxz3mmkpS68mJnSfFZilOSs+WNWfv6ztTl52XdqFqUtgFcB1J5dNY4YMeexxwQBrcuOVPZpib7z8uwuF5naEOBbsORlQME+dYPNZpN5m93CWx6/Hxb1GBhNI0Q+HeZsmCzlvHnJmCbvy8CgHgxnZAMAXpeYi3r2BAHYtXMnAKC2xgmPxw2T2bs0pym14ABvfn8dECK6XQdrm4FwHf4GNXs+gOY4pXmqKHfA6XAhOjYc8XFRMJlPrZeGhVnQrn0ijh0phaI0PP2BHJWMiO43IKzjFZAjkhp1Nuc6X336PjweN0qLCrD3520YeOmVunXLy6ugqiri4mJgsZy5tFxRUQ1FVRAbGwOrRX/ZuabGcVKQHBGjq00yMDA4BxCQr4XvhSQBqKv1UqH4gsA/M9gJryNCXVjqK6sOK4AGOa8wOLAQ99OIrm7nQfzRIp/rYYQICaJOZEorZxdRiqMHoOcOC0QC4oYrJ8xYu+7d1QEpNj5/68VdAHYFUvd0TGa1M5h85MrmSpKk/2x8Z2VDxJhsYm2rkEwbmHGjTh0C05VKzMEXAASvTiH+JFxxBn3eFzqyxmMZpLvxTIBHM0s5DXTT5O6t+bVfivAUAfrCYBbjUlJSnl+7dq16xm+JvyDgHp2jrJomhgH4od5xk7gKoPoWjCqJ8QsTLgFw9v+cmcxiNHTckTWhXCuR/oY6CekDvTIDg3ORBQN7HXl+0y+thab+Qv5TlTUKzeXGkQ++vvnPS+b5dVhfvtzuAHDLjBkPRluEZQWAuwLspl4Bg0R8h92P60LV1LmJSphlCzMHFeATDARMLJ2VWWFR1R7Ra5YF7DoXYOuck8cXZ6Qu3AAfDskZqVkbcvIWDTMcks89qgr2Y+PrT0Pz1CI8NgmXTlkIZ/FR7Fv/EUr3bYWmuCFUBSw0MBhEBJJkSLIZnugOQJKPW7QQsuiRRRBC4IorrkCXLp1RUHAUTqfv2+oTz+mBZExKTm6N2NgY7N9/EE8tegrP5z4fknE3Nz9/+yk2ffRPFOzZAaGp8BWnRyThxnsXo9flo5tvgAYGBr8acnNzldnTspYw4SG9Ogy04hrlSQBzQ9FnYuTmKYB0jc9KjBIAT4BwH4COvqq2JoGh0nmc+ZExvSzj/mcScp4OOsC3seTmPn5szvRHLhZMW+Hnfp8IHSCrG+ZNf2jIsrMckpmZ8OOS8fgRuWDRJnS6YSYQpgI0FVse38nMc2jgI1+GqHEDAwODYOEVaxb1nTv1oURNkr8AcElsz64ha5wg3QlgRsgavEBxu929mXkSEXXwlVW6RqvBLucu7HLugkf48nI5DT/Tl69nVk1oqHJXwaW6IEuy10iLNaiaCo2D28ZSWcUh1yFEVEUgIj4CsSb9KZqI4ololCzL3wH4Z1AdGRgY1MFut6sZ0xbeB+J/Qv9boW1tVOQjALIa2IdUsF9d56+eWdL6nv4+N/fJSgBT5059KFNI8pMMTMHxPaw7zmNX5BMw+C0A+pbwTUhent01b569s1Kl7QGxb5EWYVDvdr2/hWoNA3P/ZhriCSwAf8ybH38NZL6HBjwQVICVgUFjMJyRDU4iyzJU9dRCHIHOmDHVWiPDVX3Ika0Q2WsiksYsRUT3G0DSKYGroqgoK6nGvj0FqKxwnuG2Gx5uQXK7BMhy8P+GJJkRcdGNSBqzFJG9JlzwQmRmRs3xDUlmhtvtW7unCQ1Cx81YsICmCZ/PiEIIlBadEpa37tIi9zEGBgYBkJJiN7FEVwKI9FHtoNmp7G5I+5pFPgiQD9cX7ipJ4c0asbB2rV0lQjkA3VUpYlhUmOqIHIuLIZiw00fzJhDdESaZH7pu0qyBQ9LSmswsSAJNhM/AOCpjFv9raPtXDu5UwMw/wJvQUwe+NFK2NDAiWdJqo2KNKK3TGDdunpWZLkddUe5p8Dcp/VoXNbSP3NxcRQL9w1cdAnUWib3qrO6zLL4C6V8PEtPV9f1+woQZ0UQYivrPq0QDVjGjXodsZoxKSUmp9zqXJPalEqqsZc83PsoNDM5J7h3co3j+sD5xAL/TVH1U7T6AXS+9AeexQp/fBWezevVT1Tl52Xfn5GUTQB83sPsjy9csfs1XhcNT5yYqVksJGE0mRD6NWI/JVFSSkdkEfRHn5GUPAbDJR6Uhs1MXbgXYcJ47h9jx6av4euX9qCkvgNtZiYqje/DJk6lYt/phHN36FdyOcqjuGghNgSQRTLIJRAShKlDdNVBqm8dBeMumH+HxeBAfH48uXTqDmVFQ4H0OF4J1n+l37vwFO3f+Um8Zc93jwsPDEB0dBaEJvP/2+6E9iSZCVTz46T/v4anbBuKP47rhtT+m45fvv0R1aQGcFSVwVpTqvhzlxXjtsTQc3lFvfJWBgYFBo2nT1ZTFgJ9NTEqfNW1hv8b2lXb3w21Bkl/nRwJdn/Ny9p9z8rI7QfA8AIf06l4r+VgiOE8QmrakpfpevmbxIdWEQRyYE1hHj5A3paXZT25e8Jbsy7FlyR4w3gGjTZMNlNEboC948+JvefMfG30tGhgYGDSUF15ZUpqTlz1AqKId1V2ubzgEfVteAwDAsWPHWgkhRhPRZcysuxmvsoojriP42fEzarTAfFE01qBo+vcU/soB7361S3XB6XGiRqmBW3UHLUQ+gVu4caD2AHY7d0Nhn/0SM19ERDcWFBSETh1vYPArJuflRa+DsdFnJcYfZs+w62fJ9EHBPuU5ANG+6hDw5NkBgCd44ZUlpSvysmeaSesAiZYD4A50/m9tEqhHS/a/bJm9CkLuB5DP/c6eHWQ8Oi18WAsIkU/ndrD6A/+wRM+ozMAg5BhiZIOTqKqCQwcPnnwfG58Ia7hXnyNUN4Q4jx0DmgEyhSNm8CwkjFyM8K6jIFlOmQIKZhQcK8ehgyWoqqg5uTkWEWFFm+S4gAXJkiUa4V1HIWHkYsQMmgnykQLmQqKivPSM905HFXxFsCYmxCExMb6OKzIAxMfHIimp/rITuGprcPTQfgBeV6Gel41s4MgNDAyaGjWyMJrB7eDjnoaB72Q5rkGT2Nr85Q6C2OOjioVV0aAHyMbAGjQQgn5aXLvWroH5UwDlPqrFMXGmAK2JK+KlI2/JuPnqiXM6IsQpLhnwl0KnuvIQDvqpo8tx18o9qCcF0Wm01oSfqFWDgHFEOWJAnAgf14oAttvtjzbKQVOT8L3PCoQIM3OHs3+99s0Xj4D1RXWC+Gq73V7nu6RaNncD0B31nhf/rMl4l0j3Wu2HuN51xpLmFfr7cPeiLwN1JzcwOBe5b1jfSRxmTSZ/aeqCoLaoFLtW5ePIx/898auwjOlZSxvSVk7eouulCFM0mN4K8tD2GdMX6rqWF868r0241VKoV95UkIaDTSNIBnLyFg0FaLteOQP9MlIXrm+Kvg2Cp3TfVuz9xhsLcNXYibhx8jRcPGQ4YuMT0Sq5HQZcNgIjb7oN4++cgdumz8WtqXNwy7QM3JY6B7elzsFNd6RiwKUjmmWs7/zrbQDAoEEDAQBVVZUns3FVVztQXh6IxulMqqocqKysG0fYqpX3du+br5svzsdZVoxfvv8S6997Ff99bQX++9oKbPzg79i76Wu4HJW6x3339hr8afIgvPnEfXA5veeSEGVG9zaR6NshGv07xfh8xUZ4Y6D2b21wTJ+BgYGBT+x2uyCmsX6qyTLxisYELNntdolM9CIY9ec4Pw4BL614edHJzf+cVxb/JScvuxOD5+IsUXIMMS45n12Rj0PATYVp87q3VP+rVmXvk2XTMIDK/NUlQgdJUX9Y/PDDbXjz48+B5W8ANKP4iS4HTJv/n73zjrOquvr3s84t0/sAQy+KgKIgWGIjiCVqYkEzeRNjdEQdBgwaSxQV4k2k2N5oYsQBFOfVmF/ixBJbYkeJXUFQpEmHAYbp7dZz1u+Poc+9dzpTOM/nQzLes/c+68CZe/bZ+7u+S5fNvkf1+TZUAdrY2Ng0jwV/ndNoZSebtsUwjKEiMkFVk6O1KwuUsapmFaXB0mjNDsIf8lPtryYURjthqrlPYHw4qTarWVu7lq3eiDlZe4kTkTGWZZ1+OOKysTkSMAy9nKjGSDhUQ/Np5j7rdVfeMxCRXzfSbLfpLp7Z2FiPPT13d/6i+268zVnbIofmzsju3Fsnd+T585/1FDsNx4lA2P2AH4xwcstPY2iBN2U7oEMRvtAV93ekKNrmCCKKG53NkUZZSSnBwP7SI1n9BmIY9eszoUA0HY/NPkRwpR9DSupRBIf+hKql8wmW7Deg9Nb58XkDxJS76NU7ldhYN0nJ8YgY7CgqxbIia3PcPUaQfGIuzuQBYBxZ62Yb1h68972zaCuWZeFwhP97MAwDwwj/VDdEMJzRv/o+XfIu3rp6g4+Unn3oc8yoFkRtY2NzODCcvkTBlRi1jZDijfH/+uxLc1uW6inSiygJECpGjxaN2zGo0zI/sRzOj1X5ceRWxCqMBjkey7rSKVbdhImTVyv6H8X4N+VZqxcv9rRqB08aKZ2KaPFXXy1slWWRqlEsolHt9MWhg4GIIiubpuM2Y5MUM5pLOQI7WqtrN6zQRogyF1KJtVTC/F6KinXD82pI2Nrzgvb7YOmWocCag4azzKEqRtiNXhF5Y8mLC3ZOuPSGL0TkLD0kMUKgt1Gf8bzpwM/Xl1oj0MjfHRbma5GO2dh0FX5z/JBdQO/HPls9WA19QCG7JeOo6j/WP/PSxGCNt6E7uTJt0qQ7Zi5a9GCzxfvz5nlqgMsnTbojyW25nwB+2cSALszLmaHAs0atc+q8Qk8NwO5JdyQZEmwz8XUzMcRkW/W103omPf1YWBeMliOaX6Aj83JmfgmMidBobF7OjC/zC+47GaRVCSc2LScU8PLZs/cBcOr48+ndbwAAx44+iWNHnxS+0wFzXMMwiI9PJCU9Fna0f9W+yop6QW6PHvWPw8rK/QLdlJSohi8RidQvJsaNiFBVWZ/YHK1cblvw6qPTqVv3WaPtnO4YLsi7lxPOvRzU4n9/cQr+uvqqUE6nMLJ/MjHOpu9Y+IMWlXX1U/QxP/pZy4K3sbGxaQJPFPzh4ynXzvwKGBul2Vl5Ob/7n/yClpUA37E5eLEgkdct6inz4rw93IH5BbPneTye/B2bgrmC3A30HyNdX4i8Fyeua4DfddT55z3l+f7GGzynmcHQJ0DUimHpSdJv8o8StgFO6JCpohORWSxff4EunXO5jLm7jefLNjY2Njadjeeff95hmuYQIOoGb1WoilW1q9js3dwsV2JLLar8VYgI6XHpxDjrc6eCZpBKXyXlvvKwQuX2xFKLYn8xK6tXkuhIpGdMz4htVXWgiJyoqv8Q6UYTJBubDmLe07O3Ts6Z8YzAdREbKedOuXbmuCeevu+Dpo7rcssnjbUxsc5fuGBBk/dS0w3u7JgpedtjqD4AzO/IGP6yyFOUd/U9YxFZirDvi/eMkU5+eU6UIrIdgmZi6n91xZxT5YS7o1VRtrFpNbYY2WYf5eUHJ7L37jcQAFULKxQI1wWAz5eu5P0ln0csoXko7pgYzrvwAmBgi2Pt9BgOXKmDST97Dv4t/6Vu/X8IlK4GtVBVfL4AmzcWk5wST0pqAoYhuN0ufL5D/p7FgTtzOPFHXUBs/zOhnTfMOiPeuhpWrTjYxHDXju1s3fQ9g44a1sZnU7Zs/J7lX+x3SzpqzJkk9+jdxuexsbFpKwynKwFTk6KJG1W5wIALWqp/jObEDqCQ1rKRO4a3X1lUdM7EG/KBkSCNPYwdQCqQimofgQmC9QCpRevPmZj7Bqb8Wy35JkGs8ldfXdDcVP8BUY9abG/meA1wOik2LQLRXqwtSw67s3VzENiqIv8QtdqmlqywKyhELRvUUkwrlGwgUcXIqOyklbuPFmaxoQ5fxHKEqrFqaFihb4zTesFnOR4krJpZBHGdwwFi5AsvnBYTEN8YDV8GK6Tieg1QC9404GYOESMr9EQYlZ2d/UZhYeH+Fe2QnBnpO0nB6zBc74c/amPT9Zh26vCNwM8AHv5yTaZTrVkC54uQqkqCiLgAVDUoQq0qFaBv1loy4+5TR5QC5F4z4yhD+D7M8IbbdH8MtDijf4+Q+arcSb97yrCs95rR9VdWQuhXk6+Z8U9HnfNaw1G5qqUxtBUBp3Md9c/tNkY0v4CxeTkzviK6IPnb/AIdaQuSDz9qWfx3wZ2oWvTq25+BRw3DMkP4q0tQK4ThdOGMSQQUM+jHCvr3uRAfir/WAcS1e8yhYAjDMPYlGfv9fgKBIA7H/s9M08I0Q7jd0Rfvg8EQIuDck3hsWRbBYJCYmP1mmoZhYJomPp+PuLj2vj4h1m0Q63LgcgiGCApYlhI0FV/QxB+0CAX8vPbnu3ntz3cjhgO1TJyGMKxvIomxDZdsXTHxJKT1whVbn9R+KK+/swSAM7InE5+S0c7XaGNjcyQjIjo1x/MTi1B0l0fRR6f90vPGY895GtrWR+G66zzpmMHnGg/EurLgaU9EK/09FZPyc3Nzn0oI9LhhvCPweHPi6NSo3rpu2rTZQx97LGoCdnvy+ELP2tycu84wcHxEBEHyUX0c/PoyN7Fu6QR7kXomBl/pV/f9SMbO7PC5u42NjY1N+3HmmWemAccQZY3EZ/lYX7ee1TWr8VvNf5yGrBAVvgq8QS8uhwtBCFpBAmaAoNk2S/nNJahBtni3kOhMJN4ZT6Ijoo9PvKoO2bRpUz8OMdGwsbFpGWW1J0zOSFhxNRC5PLfy8rRpf8567LGbGv3SybtmxsNAdJGKyp8X/t+cr5sVqIbd6+qqRHW+P1zkPzN7e27u3aMdAWO5Qo9jBzq4coK7c0q7hGQsPtXlDx0jo37bLnvFNjZgi5FtDuBAMbE7NpaYPZszapmoGTkpbuu2HVRVN8M1p9ZLSVlleElHN0PEIHbgONxZowkUf0PNN38lVLN/jbaqso7aGh9Qv8l2IM7EPiQe/0vcPY/HiOkUz9EOYeXypZTsPriygVoW/3n5H/x80o2kprXdBltVRQWL33xtn/DQHRvH6dmTcTgjzxltbGw6FldQEk2DqM7I7Y9GdYDpjLz70sLXJ1ySG4fBg8CgZnYX4GhVbsLQX6thba7FeOXsSye/5XbosjdfXNCo2PTY7Gw3AbKiCsTF2NbMuBqgfi1WJ4Go73titUtZ+7ZChY2VIb33q1cXHt66bi3AKZJoaZTfR1UFI2y5oubgshIDphHYSaR7V3AbERaaTzmh/9YlXxd9pxGEi4boecC8vf8diK1MVGLPiHBHf/7ei49vAcDt+pRAqBjh0PvJAXpiZSgjA/aLwFU4M+IFwldOR6D5teltbLoAt580rATIa26/Bf83a33eNTNWIYxocFAYecO195y+8OnZH4fp2iSysz1uwwq92ZK+Ivz0Fym1P23puduYlJIbbnk5c+Ejl7XH4PkF952Ul/O7b0GPDd9Cjs3LmflFfgERbHgPRpfO6YGhs0DOo/57O4E94nRUg0AtUAH6FnHBGTLMU9ImF9INWfGvx6ktLQJg3I8uAVV8lfuNuq1QkECovKPCC4vT6cTv92NZ1r7qRjU1tbhcTpKS6qcTfr8fr9dLRkb06bbX60XEICnJuadfgLo670FiZMuyEBFiY8PnMrUlo0Yeg3VwoYUGHHv2lUhMIovffJUNa79Drfqcpf6ZcQ2EyIPHnk/PQcfhdEeO/fUX/4ZlKYnpPTnn2jtafxE2NjY2jTCvwLMzL2fmHNC7IzZSeoXcoelA5DYNEVco9AQSPdFV4B9PPD3nraYMuGDBgmDp5GmLsbrVdlhCmtcxBOhQUe2Cgrmrf53jOSNEqIEgecRAB3kXx+DuXH/t/XE6lujS+8+RMdOXd3QwNjY2Njbtg4j0AoaqasRSMxXBCjbUbqAmVNPi85iWSZ1Vh4TqdyAaM7Y5HHgtmD3H9wAAIABJREFUL5vqNtHL3YtjkyIs34Coam+32300thjZxqZNKCz8mZl37YwLUN6N1EbR1GDV7puBB6ONNTXHk2Vp6OZGTlkVl542vTkxbs2+JY7Wli7tXMi6adNiOjJBcy8LFszZceONc0YkiXdN3iUxGRGKuHcWUtDgN/rl/H5y0uSOyZ6x6fZ07l8Bm6Yjghj7Dd7MUOsqahgHfjvqvv8JywXnnsGAfllNKnPpdDo4ZcxIRo4IW+m622LEJBPb/wzSz32IhOGX44jPZO9zvt7pZ68QWXDEZ5Iw4grSz32Q2P5nHLFC5GAwwKoVy/jovf9gmSZiGKT27I8rpl4kX1dbw9uvvkBFWev3o03TZMe2LfzzrwspKa4Xi7vjEph4x6Ok9e7GDt42Nt2AoCGJ0NFi5C6ZXqPvvTL/n4pcj+hLKL4WjmMIMhj0ZhF9OmjJggkTc386PicnqsqjHyl9kUaS4iyr1c7IRsBbKhC5vAMA0tnq5HRZFE0l+u9DnRpWsxyxwiGOUEgg2gRA0PD3l8fjUUUWR+k69sJfTts/+bLieqERXUD/yp5J8uLCeTUIL0VoNzYYMvc5NY+/LCcVjIgrwaCf+xPMTi8+t7E53JTWrYnofuxQebU1Y6fHB/9DNNeKKCSiHNuJKloKXFpz/c292ml0zS/4w0hgaZRGY/NyZnwJGnaBQL+YO0SXzSnUr+coBsUgucBg6itNuFEVVAVw7/lsMMhkvO7d+vUc1eVzntflDw1u6yvryuxev4JtKz5ARJh41Q2IGHgrW5370+4kp9Q/bnfvrq+UnpCQQHp66j4hMkB8fNxBQuQDk7i93v3T1+TkJJKS9mvW4uJiycjYX7zE7w+gqiQlJzVp7aq19BpyArFJkQXUGf2Hk5Y1kNS0DC77eQ6/mXE/g48eDsDG4jq2lnjrxzlqFGf84i76HDM2qhB5984i1nz7NWIYXH3/c0dkVS0bG5uOodb0zpH65KGIqOodUybNaHJ5u6nX3nMaUl9VIwrVTjGn0ZyqO5bjgia37SKIyPkdHQPAXwo8qy2cZwD7Sm8e3bdTCpHrUTIwrPf06znHdHQoNjY2Rxq6vnOOdWRSHaqmJFiCtq6IH1AvQu4MQuS91Jg1lAXLGm9oY2PTpuQ/Pes9ILobgOgDt9SLgiOihN5pbA/VtLjikUdu9TYnvvg0+Ulz2ncFMn3Oizo6hr08/vjdpXOui61whanL2gnpiau08WpENjYtxBYjdxMMhwt3/H7tR0VZ6WE7d0J8HL+44gKOGtI/ajvDMDj9lNFcfME4HJ08FaS9MNyJJJ1wNWnj7iVxxBUY7sSDjiUe+1PSxt1L0vG/OujYkYSqsmP7Ft5+7QXeeq0Qc48rd9bAoVxy01x+fN0dON317kZbN33Pv/7xfyz9bAk+b/M1O5ZlsWPbFt574yVe/vvT+4TNYhickT2Zoaec3XYXZmNj0y4YWG6EjhWTSledT4m+//L891xO63pwTFOR6OVVG6cn6I9RFhgV7rnZ2Z6I/y6mv3EBt2E4drcyHgLxDheNzHdVsbM+2wgLw000MZ9IjUOcrc5QNs2QaHTRoIKYEY9ZukSEsLXpVTUlUBc4bv8H1nmET3jwWoZ1sPjR4OkI5+yPg31jOgzXUI3sqO43MJYtLijo8ExuG5vORmFhoQn8PsLh9LycGTNbMu6N190zTkTCT/yFkvyCWQIS0TV5qrNZa76HBb/haF55vmYhml8wayyNC5K/PVCQrJ8/mKVfz9mFS9cjtNxJWslGgxt0+dwd+s3sdhJddx38NeV8+fe5AIw57Ye4YmIJ1JajVucRyEfiokvr9wqWL18BQEpKxOq5+9i8eeu+n7dta3reWklJ/SbsyT84pTkhtoqso0ZHPNZryAkH/bdhGEy8chITr5wEQFG5jxpXb44+pWn7Kf/860IATr3sWjL7H1nJ/zY2Nh3Ls88+XBuyrOzorcShFvk0wYErN9cTb6m80fiZJfexp+c2c81Armle+86PKp3mmhYUeFaLwelAWUaKwZRL3J1TiLyfdJT3ddWctiu7aGNjY9MojkhrGh08VvfDMAyvqkY1xYhzxJHiTDlcIR1WEhwJpLnSorYREa9hGJWHKSQbmyOGZCPQqNOdLyE+YoW/KTkz7lT27yeFQ5X/t/CZWe80NzbF+mFz+3R2FO00gh79eu4fRaTrLMwp2frlg10nXpsuRedeDrBpMobDSWLG/qrQxTu2E/CfgDum7fVZapoEfLW44xL2uTEnJyXys0vP48lnXmR3aTmHJv8ZhsHYUcM5b/ypB7suH6E4k/uTePxVxA4+l5pv/goiJI78Jc7ErI4OrUMJBYO88eL/o3L9sn2fiQipmVlMnv0kFXXK8BNG46su5e2/5WOaIUp372Lxm6/y0Xtv0n/QEDJ79SEmJias21EwGGTDulWkZ/REDGHbpg1UVR6cnOZ0x3JGdi5n/fxG203IxqYLoIgplprdqqjM4UXfLHyqDHjy4otz/1btkF8Y6CRgGEICSnPrWAv1ZdZ/UxracfJZ2dMmLil8rMEGoUPc5SGii2QsrJ7NPHcDDNwZNOZ0KbTagdlmDxY+DPxRzCQSsbTVtdE1xukkYGVG+b0PgFZE7G9YG1SNzVLvxHkwBm7QMcAngKjI5WHHUD5KChoH2Uu89+KCZWdfesP3InL0oaMKxoXA8/Wd5ViJ7CC9RdXaQHMcvmxsjiDyC2b9Pi9nxr0RDntycz3/u2CBp1lZiqYpEct7uwLOo+rPe98FU6d6Eq1a8xlEJ+49noCSIp3w11U1q+L62wenPvnwxvY6RX7BfSfl5fzuW9AITu9ybF7OzC/yCzhJl899GQ1d2qYBqGZhyk5dPvdfMuquy9p07C7Eh/m3YYWCpKRncNSI47FCQUL+qAaVnYaTf3Ayzzz5DCUlJezYsZPevbNwu2MIBMLn41RVVeP3+3EoOFXxh0xKS8sPckAORzAYpKqqfg964s8O363ijIk85TEc+6ene92zRITBRw/np1ddxz//+hQrv/uOk0uKSc+MPiV+/cW/4a2rxeF2c/4N97RN8DY2NjbNoMI7+q2MhBWfA9EyPsbnXfu78/Of/kPEBC8AIxB8HCS6Kkjl31mDHc83J8aN9dWbTmi0YRdDhBN12rQY6QRliQGeWDRrzV3TPGfdPNG1Ij5GOr8fmNAHP//S57N/KD8rjJTQbGNjY9Nm3HzysGf/9MWqfCC+lUPV3XzysGfbIqbuimmaVUDUkkE93D04Le00Nns3Ux2qPkyRtT9xjjj6xfajX2y/xppWqmrx4YjJxuZI4sFFD1bnXXPPk4hcH6mNIqMn58wYOr9g1roDP5+a48kyCf2hkS3vSkeCM7dFwamMbFG/ToyFdIr3vPqqK3pLR8fRbJyh72lC4rCNTXOxxcjdiB5DT2TtB/XrcJZlsXH99xwzYkSbl6Cs2L4BX005yb0GkJCxXzybEB/HdVdfzguvvMO69Zv3CZKdTidnnDKKc20hcgOciVmknnZ7R4fRaVDLauBwfPwZ53H5lHvo2W8QFWs34nA4+HHOLaRmZvHmXx+nfHe9kWcwGGDDutVsWLe60fPsKtoW9vOso47lrF/8mhFndLuqfTY23RZRy4tIZEtCIYiyVJWSdovB4Lv2Gvtw8uqrC+qAp84///a/W/E1J5uWdbqIjAIdiDIIoSfNeCER9DRX0P/H8y6ZdOfbrywqOvBYjBUqDTW2LaXSaPZw4xgZYLqjhW0oW1p/HhsAQ9Wrii9KkwTLMKMrhpqA1AVi1O3MiCTXVQigRKxDJyHnTpy6CrShGFlxq8qo7Oxsx24zpbdanBbm7lED3q+u7hNo8LnwisKtYbqcOz4nJ7ZHbW2wNMBwJKzbMqCbgg5pN/GgjU03QHHIGEwN58prSDD0JnBWUwebknPPKwox4U+kjz72nGefi868eZ4a4PJJk+5IclvuJ4BfXuQ49Gug82CK+QA0WuK8FYjmF+jIvJyZXwJjwrVIjJOxvs9nB1Ftv7Un1Uv16zkVWAyVMXe3uqpCV+Lrlx8jUFuFy+3mRxOvRC0TX1XUvdZOxy2Xp/Poi6W8//77jBw5kmHDhvLddysbtCsrK2PXrvrp/DnxyYS8ft7DT3HxbkwzRI8emWHXvsrLK9i5s35v9YYfJbTvxRzCru8jG5SXF31PSq8B1Hm93D3zXvz+APfOuJusXj3xFa+ld2oMOyr8vPL8M+RMjbxmtHtnEWu+/RpEuHFBsw1xbGxsbNqEwsKfmVMmzbhaLaIvyqr1t1/96vYBzz77cNismdxrZhwF5DRyOn/A4bje4/GErXQTibjYzGTM7qk13RWMSQE6jZBozvXu36B0fiHyfs5g6InToPDRjg7ExsbmyMDh4kQzyJrWjtFW8XRXevfuXVFUVLRKRLYBYVW5MUYM/WL7keHOIGh1n+KJTnES54jDKVGXYsqAlbW1tTsPU1g2NkcUAUfwVrfl/iUQF6mNqC7ngOQUj8dj7Ngc/JuoRHObVEGm7lmnbjYG9O2EthqtpW/jTQ4Lf+roAFqKLp/9Wxl1z0MdHYdN98IWI3cjUvseTcag4yjdVL9xs3njRnr1ziI1LVIV6JYRk5hCoK4KZ2zDxM3E+Dh+evG5LNzjkAwwdvQIzvmhLUS2aR6JKen87CYPJ583EcPhwDxgwdgdG8fZP53E8aefy7MP3M7qL//bqnPFJCQx7sppnHLJNTic0Q00bWxsOheGOryWWNHro6vMD7kDrzl8rnZ5x3IlJ3e++uyt4K23Hq4FFgOLx16cG5/gtAa6LMdAFYYCY1A9mfqfo5ZfUMUALg0ZziXZ2dlPFRbud5l59dUF3nMuy63TaC4QYg1o/dWYGSBRv9jVsMXIbYWpltcQwxfN09cypQ/16vCW/z4ajoxort2i+MWQiGLkjLjS3aXBtFXABcChE1QD0SFl/pRMwzAuJryzdplgfLV4saeBvbfCO8CNNBQ39pOKmDOqXI5liAyBsMI8E1id5SjvNBvJNjadkfyn7luWlzNjDTDs0GOinDnl6rtPeOKZOSsaGyf3mhlHKVwc7phCYH7B7LBOBosWPVgNXAVcNfuGWzrz+m0jJdPbAtH8Asbm5cz4ikMEySkJBvffEAuHZ90pBYNi/XpWPxk944ioeLBz1WdsX/4BAOdd9nMA/FVdT4sdX7OcnFPdLPq0J99++y2rV68mNjaW2NgYRKC2tg6fz49l1WvO7h37A9avW0+5L8CDp57FHZ8uobS0nLKyCmJiYkhMjEdEqK314vP59vX7nzEl9CJ8UnJ7ULV7K7WlOyitCbBul5eymhAGkJnk4pjeCciaz+k/8gy2bduG11ufx7V02TLOHXcauzd+y4Ae8eyo8FNWUkxVZQXJKakNzqGWxT//uhCAH0ycRGqvRl2vbGxsbNqNJxbNWjMlZ8ZDCr+N0iw9wYj9DTD70AMej8fYuSkULtnsIBS5ddEiT1Fj7Q4lNkSC2U29nmJDHN5smyjo8rkTUL2uo+NoNsLDumzuy3LiXZs6OhQbG5vuz69Hj1j76JcrfyBqfNqS/irWD349+ri1bR1Xd0NEQkVFRetEZLmqRnxZcoiDREciXSqNpm3YAnw1dOjQTlFdwcamu7Fo0YPVk6+951pR+XvERiJxU3LuufuJgtlzAHZtDv5KVM6OOrDy7hP/d9/fWhqXRhFHd1V80Ccv5565KsZKUd2msF3dzu3NrZ7YGvTruSeCdl23Q5U/qOrDIp2xBKRNV8UWI3crhBMuvZGPF92Dv7qcQCDAl599zrEjR9Krd28cjvAzacuyqKyooLqqKuzxQ4lP70lcWo+IjssJCXFclX0BL7/yJomJCVww4TQcDluIbNM44nBw1IlnMfDHP+Po0acz4viRGBHuW4DMPgO48aHneO+1f1G6ZSU7Nq6lrroCtUxiYmLYsWEVvroanA4h3u3EFzQJhCz8MVCWqvjjHZSmWiQO7UnO+RfZQuQjjOlzH/cgco1ChYHMmzt9ysKOjsmm+YRcltcwifxCobgQ+mZRU1b4ql1ysbl8Ve+WvApYlZ2d/XaRPyneFRObYFjmyZg6HTi9kSGSQC+qIesl4ECFjFqiW0RleOSubeGMTCbRRdOmIxSys//bCIfhqEK1JtrbqkOk1VnK4jT67y1pHr4BfsvS8kiHCwsLA+dOnLzCUq0CGqp70D5q6EBFL5fwrtpr1DDDuhc7HMb3pslq0FENw+IqtRzbER0cQYrtVdUvDxTu29g0xpE6n8mqdZ6wMyEUdsNEDeN9IKOxMQyJXNlAlWMb61+dd3vPQCd32KvKvS0zecH/tlt1iL3kF9x3Ul7O774FPRYgNcFgzvURc0baEWOLfj1rQHcXJAe9NXxV+DAAo089k8SkFAK15VhWCFVt8+pY7UXt2lcAOKq38MzNcO/fYVNxiJqaGmpqDjZ46Z+YxN1jTiHO4WT9ns96xsXz5A/PY86yz9lYVYnP58PnO7hAQ0ZCiNzTd+Ew6h+8tateIGHEFe1+bR9/8jnL/9tQK1dcHeC7onpD0O93zWLC+T9mQJ+e1NXVMayXiy/+9fi+tv0z49ha4uW/777BRZdf2WCsD995HW9dLa6YOM6/4Z72uxgbGxubJuI3Ave5Lfc0iJw4ivCHvKvvKch/ZvZBz+odm0KPCiRHP4N81HuQI78lsYUIxUZ4t+vyhAh1xKSrAaoIX+t8pEHCb1fAgeg/gFM7OhAbG5sjg9+cdNxnf1668jg1jYZlYaIgDuu4m8cc1y2qNB4O4uLivvd6ve9Rv4fR6mp93Yha4EuXy9UiQbyNjU3TWLPR9cLwQaFvgOMjtVFkRm72nY/HpThifSF5vJE3luqg0/k/rQpK8Xe31yKvSjzIdNmzZyiABELkXTNjB8IaYA3CGsXYoKobvKZ3Q6RqPS1HZ7TteIedWJbffyPwl44OxKb7YIuRuxnxqT05+oyJfPf2/6Gmic/rZfnSpWT06MHQY4aRlp4GezamTNOkaNt2tmzaQE1NLaFg00uQNLa5tW71KrLS4hBRtm3ZwpCjj27VddkcGThdMYwcdwnJMS58IfjmmzU4HAYulwvDELxeHzt3FlNSUo5pmgSDIUIhk/R+R5M54BhGjjdISU4gPS2Z4m0bePy3VwPQNz2OzGQ3G3fVUlZjsbOn8s2xiumoNzSM8W1ha8UmeiX26cjLtznciNwLe+05dcGd988b/sD0qbd1cFQ2zcQRtMrVMCI6oNajY2tqspzUu47atJA9AsnqPX9eBV49+9LcK0V4FOgRqZ8g42sD/iwOFiMjKu8DkcXIQvr4y3JSF79cUNHCkEWQ3qrERHm53hVUZ6CF49scgjvRvc1f698RrY2KNRg8Ap4WZ9iayrBG1kv8IkQV34laK0BKCStGlt6KY7wII8KIhlWQVWZKIKyjthpaLCZfKTQQIyN6SRApFLUGEf6mrFPL+Dxa3DY2DThC5zOeQk9gcs6MhyS8+1563rUzb8p/+r4/R+qflzPjUSIlq4j8a0HBfevDHjuAgGU1cPXrbATVnAXktf+ZRPMLdGRezswvE+NkzNwbOkwTY4CxTZfO6Slj7u56NsFN5MP820CVzKzeHDPyRMyAl5C/fk3nrTfeoE/fvow+6aSODrNRate8BEBGZhIi8IdfQJUXVm6B7WXw/UoLX7HJFaNP5Ni+4XOZnIbB78b+gC2lpTz76Sf4XDBgmJfMhBAD0/0kxx48/a9d99phESMXVzVuLvXR2koMXmdYmkFcViybv/2EGOd+/VbPlBi2lnjZsG51g76fLnmXrz5dAsBvnv2o7QK3sekkHKnJVl2dRYserM6bNPMaLP1HlGaGivwdOGvvB1OzPYkWoWmNDG9aZuBKj+cBqyWxGYY4o+WzdmUMI3oN9sPG17OvQejKm0Cn6PLZI2XUPd92dCA2Np0V+/ncttw05rjvPO+/70pNzHpE4NfR2ir8paJm5y2es89uUKXNJjJ/+tOfqq6//vp3HQ7HKaraOgFfN0JEvjEMozAzM3NXR8diY9OdWbzYExp+9cxrMDRaBZg4I8H5j0DICAjaWMWT2556ytPIfngjCDuAIa0ao5NRFSkXUugN9AbGoyBYCJDgiNW8nBnFAptU2SywXkVXiZrfxab7v3vkkUeaVQ1Zlz/UEw1e3uoL6XD0Tmwxsk0b0jkWKmzalAFjz6OuopgtS9/BDPgwTZPinTsp3rmTmNhY4uLjMUMhamtq9pWsPBS/z3eQo06groba0p3EpfUgJmG/SYG/tgpvZQkJ6Vm4YusrrZumSXVlJQCqys6iooPEyKGAn+qScixrEPYtaHMghiEMGtyPGFVqaurIyEjdIziu/1N/OwoOhwOXy0VSkgOHw0FRUTHHHDOEhIT6yhKhYICPXv0b3poq4twO0hJd9bWWQ4oKVCaDeYDhsj/k57+b3uekfo0ZfNp0F6bPfWz8oZ8J3Dr9/nnDUG66/66pGzoiLpvmc9aYfruXLCtap8L5RC6mNcZKrEsAjuiSU2ddntvbaTIg0nEH1L3zrwXfNGdMrQy8SJq7lyj3AikRmqW4HGQ27KxvIzIl8uD0EImZALzYnJj2Mv6ynBQVTiSqK5N8TKzDF/G4TbP493OPVU2YOHkNyoWg4Sd5KhPGX76tz+IXW1YrPTs721ES1EZURLK2sqeGFQvvJdaUtbUG2xGOCnM4BfgFGk6oTC2GfrG4oCDsffNO4YKqCZflLgPqgPiDDipJYumvIMzvQ32DTVT3/T5a3DY2B3Kkz2fmF8y6Iy9nxq2Ee/6r/nHatD/Pf+yxmxo8+3Oz70wBbg4/qvjyn77vsiYFoHpuc+LtGOT8w3guzS9grO/zOUE6+kXfYB1hk026PmsXP4+vqhTD4WDCRVegauGvKa0/tmYNlmXhDzQ90byjCFVuwfKWYxgGCQn7p2rJcXDasPqf39hqsmG7Raw0brAYIwbpQQuXWIwfGrnql+UrJ1i5GVdKWxTgaD3FleFfTwRIjGtYuamqopznFv4Jr7e+MMz//G4+cUnd8la3OdI5QpOtugP5i/5QmHfNzOnUv4uHRYQzJ0+6c9T8RQ8sBzATQjubYM41a8GzD0R9x4uKZQlNeJ50Rf4cjPtySs6MoApbVHnHUN4pqSt7r7BwXk3jvdsGVYTlMudwna/9kJehSwuqbWzaF/v53ObsERdPA6Y98sXaIYaY16vqSQAi8qWljidvOfmYbr220554PB7rmmuuWSMizwGDRMR2wIf1wHPl5eWf9OrVq0VJXjY2Nk0n/5n7lk3OmfGUwHVRmp1fr2CJgrAq/+lZrU4CEtFvVeWM1o7TmShq5K8uDAL0UuiFcOpeP2UVJ95yJ3k5M0pRdiCyA3QTwjJRXRablrH8kUdubShU1tDZrb6IzoDQR9fM6ivDunfFQZvDh60E7YYYThcjzvsVKb0Hs+rtZ/HX7DcU9Pt8+H3hNTei7HvMqWXh89YSF58IQF1FCd6qUjCMg8TI3ordeCtLMQwnrqwB+84RrXS2r6oUX1VlG1Vft+mOGIaB2+0iMzN9nyDeNE3Wrt1IVlYPUlP3691M02THjt04HPULygGfl388OpPP33oJVSUrNQa308DrD+ELmJgOqAgjl3tz3avcdPp0DCOSltHmCOHHCMPuvH/ebx6YPvX1jg7GpnE8Ho81fmLuUkPxAokRmvULhhxTgLZwMKxfb+2COFVOA434d2AJZR6P5yyPx9PkRajFiwt84yZe/x8HxiSJLEbGUh0MvH/Qhw5rKZajksj9UsXSn5ybnfvuO4ULKpsa0/6TxhyNoRE3QIGgWPpOD3Y3K8vVphGUpaABIr9n9BRLbgFatFlRGUg7SYTR0VtZL3y1YGFUJdarry6om3Bp7sfAuDCHReAEwtsXVxByfBJlaFXLXCaGYycNM8ydKD/ZV6ak4Wn/vXixx3Y4sWkLjpj5jBr6A7HkizCHHMHq4jeAcw49YCS4IroeCzRHvNvpFYCCHNYY9es5L9E51plSdPncl2XUXU0TlncRVJWNn74KwNkXXQ4i+Cv2Gxnt3lX/80lnnovTbRDyVQPw+ptLWP7tGn50zhmMHT3i8Acehtq19deRmBg5Z8ww9q4FHDw1jY9xEwge3M/S+jZNeZ2vW/c6KSdNbU64zebM007hpe8+JxQK/1iPjY3l5smTqCwvoaykmKqKcioryqgoL8OyTBSo9tZPZQJ+H3/8wx0H9Y9LSuXnv3+S/iPGtOt12Nh0BEd6slXXRxSdfh3ijOb+hVjOL3JzcxOMQM+7gagOYAor5xfM8rQmKhWj21bKUnAruFFGCIxQYVpGQjp5OTP2HAZgl4i8JZb8RxKDbz3++NzSNg3i69kX7XEe69ooR+nyB/rJqDtblDxtY9OdsZ/P7c8e0fHdHR1Hd2Pw4MG+0tLSD3w+nw/IAS6lkblHN8UPfKKq+T6fb/Hw4cOrOzogG5sjhTict/sJ/Vwjfvc0UpIeLMuVeFqbBGPKhxhMbpOxOgnrI/gitYIMhAzQkQAoKIK3vEzzcmZUgZaDlClsMuBTf8C6LsbdbEF050MxqDNuB27p6FBsugedYZPIph0Qw0HfE35Ij6NGs27JCxSv/YqgtwYz6McyQ/WFy1WQQBAjYNJ3t4/kmiDfHJ+xb4ziou0MPLrekiYxIwvUIj6t50HnScjIQgwHCRlZ+z6rrKzENPev75mmSSgUwumsv93i03oR53cg1UYXlXPZtBeqiq+2htiESHrCyIQCfnbs3Mw///IHvv3kPQwRslJj6JESgwClNUFCllKXAJXJDW+84pqdfLp1CacPbLCmYnPkcbTAa3fdP++2udOn/rGjg7FpHIclX6hoLZHFyIYod0+4ZPKS916Z/2FLzzP+kuuOFofjWrfwlzdfXLCjpeN0FIZouQrDI7dQ/WDlrqHAmmaNWx7aKCnusrCyzT2ISsyhn8V448v9MYEloD99NUCEAAAgAElEQVSJ0M2hwngzwHDgs+bENH68x2kYRT8huqPNJtOylhcWFnbbTcmOwAr43zfc7moOdQU+AEGmjLt06qMf/mve1uaMPTY31xUs1t8LElFqJFBnEny5KeOJ8pYK0yMcDmubpbDJqlr1XbRxNSZmuQSD20EOFSMLkb+nwOCVaOPa2DSTI2I+M3/R7C/zcmZuAA1XXm7C1F/NGDHv2Vmr9n6Qd+09d6BkhGkLyLtPFNy3pKnnFojv/K+zjZb3a7szfTO7FyadR/yreql+M7uXHH9Ptyk7WrFtLSG/l7iERDJ6ZhGoLsWy9otdvXX1brlJqWmAEvJVs3Hzdj7+YjkAL772bqcRI/t3fA5AVp+0iG0GHyN8vxK27i5maP+++z4/feTIBktJxeX1Sfg9+jZeCCWw48vmB9xMjj9+NGPu9XDXzBkNjhmGwYNz5tA7KytMT/B566itrWbVimX859XnDzrWc+AxnHfDXQwefSaGw06ktjniOGKSrbo6+c/cv2xKzsx8RfMitxIXoR43AjMbGc6yLLPVJW8tJGh0042IRrJZ967UZKnq1Sp6NbWOvULlepRyEXlPRd8WCb0dW+3fsY0UE1aaTV4vEfl1y6LvjJi/A3I7Ogobmy6E/Xy26fRkZGRUrVu37sOUlJSSUCi0AbgMGNnRcR0uVHWbYRivmKb5otPp/HTIkCG1HR2Tjc2RxKMFnorJOTPuEXi0Jf0VmbZgwfTmGzaFwcxwvWqUd/6Kas3he+uwrY8JkAKSAgwSGON2cXm3ECLvxWBCR4dg033onrWpbPbhTkjhuAuu5fRJsznpf+5k1GXTOOHiPE74SR69qxJI+2w7Az/extANVfQo8RHv3b98tXXjOkLB+oeRMyaWlD6DccUdvJfpik0gpfcgHC43UC8m3VW0A8va71zj9Xqpqd5fJtNwOEjM6I0Y9u1nczABn5dXFj7I28/8L5u++ZTayvKo7S3TpHjrRlZ/8h+ee/C3/HFaNt9+8h4i0Dcjlv6Z8QjgC1oUV9RvSq4aplgRbr2XVv4d7aYL0zbNR+F/77z/8QUdHYdN47z7r/mrFP4TrY1CPIY+OOEneX0J73YalfEXTc0yDGO2KHcHLf51/qVT+7dknI7EYQa/hyilCxAhaF6anZ3dvDe3dGcmEl3sZIhVdOhn/z41owasF1DCl2wABAZjcMmFF05rIGaOhiNlxzEoNwKRrkUR+TYmVtc2Z1ybxln8RsFOhCcbaRbnEnNKdrbH3dRxs7OzHcm7yBbkB9Haqcrzi18uqIjWZi9mVeAToHmlay1eWbx4cdT93sX15XA/aM6wAjvGndDn62bFYmPTBI6E+Uxp7epjIh2zDN7d+/ONV9+VgcoDEZoGS2sdFzXnvAqu5rTvCBRckybdkcThmLOYRuf7DrM6YUytoGxLva6+d79BmCE/oeDBxR0OFqfW/5O7XJ3Tg8ARmw6AZUYuyDHshPrrWbNla4PqW4fe0J+srM8TGja68T1VIy69GZG2jNq6GtLTk8m97toGx+647RZiYpyUlZcc9KeyqoI6by0Op4u09EzOOPtH/P7hhSSl1BucZw0ZQV7+fzhq7A9tIbLNkczeZKtbOzoQm+j4jcQ7gLpobQxLHiHyOzsACk8sfGZuq9/bDXVGjaUrE2ztNE9IU/QKlHy1nOu9CQl1GQkhf0bCsNCUnBl1k3Nm/Dvvmpl3TM2ZeXJuridz0qQ7kqZNmxbDnsexLp3TA7ig9VfSSVBu0JVNX6uwsbEB7OezTRdg6NCh/h49enzrcrnmUV+xby7wJrAKqIrauevhBTaIyPuq+rhhGLcADwWDwY+ysrJsIbJNm3Pn/fMunH7/E0/fef+8abc/9NCR6DzeKPMLZv0ZZVXjLRtQPb/gvnltFUePBx+sppvZRXZkqdGEuC4lE2gKgzs6AJvuQ+fclbBpY4SYxFRiEvdXaA2WllK59iG03EtqTL2+x7CUoesqWH5CJgA7t29h945t9OrTr8lnKi8tZfu2g03uAn4/27ZsJTWt/Td8bLo4quzYtI5NH6/hk9ee4x8PQlrPPvQZfAzJ6T2o84eIi43BCvoo3bmdoo2r8dbsryQjAvExDoZmJRDrduwdki27vYQsZXeGsrNn5PnVd8Ur2FVdRFZS34htbI4sBLlh+v2PD7OEvAfvvLElLwk2hwdVB/eLySVAZHs1ZZS69IFzLr/hT+++uPBLmvDCdeGF02L8rsCpaoRuArliz8cnhyT4z7OvyL0p0yj/sqs466a4a4pKg2lLgbGR2gjcWhpM+9rj8bzj8Xgiq0P2MH68x2lY285CpW+U/a/akOnY3uBTj8eSiTd8rLAMiFhiSJRp/hj/ttOybyn4pPARb6R2e8Y0zv5614mK+TSQGbGdap2lvPlm4VNlUcezaRFB4XGXcgPQM1IbFa4tDe1Yd1p29t8/KSyM+u/q8XiMD77eMR7Ru4CUKE1LxQg2WXS5eHGB7+zLcl8X+J8mdglBqEnuxSLGG6ra0A4xIvpGU37nbGxaQnefzxQWFpqTc2Y8LnBjg4NC77ycmZPyC+5bZBrOL6M8+s8vLPQE2jXQjkHclrsqL2eGCVSCVAisVPTVkD/ulSf/X9u4BuuyuYNAw9u8diSqWbr8ocEy6rcbOzqUtqCmpH461TOrD4Gahom7SUlJlPr9VJWXkZyWjhgO+vXpxcQfn82qtZsYd9qJhzvkiMQfcwmVn/+JDet3ktUnnaSkuLDtho9ysHq5yQsffMgVPxyHhKlc+e9PP0dVSc0MYhiN76ckHHNJq+NvKmPHnMj5m7fw1jv1eRFXX/ULBg8aGLataYYwzRA+9k+LYtwx/HbmQ9x7x2R2bljF7i3r6DFg6GGJ3camM7Mn2Wr4A9NvtN1LOymLFt1ZPSVn5m2KPtHyUXTT/ILZbeK4WxUK1CS7ut1GMQD+dpQSKMQJXIDoBRZgBEK4cROsdpOXMyMAfPrCR8HdV5zV6XP0moc/LhNokFRvY2MTHfv5bNPZEZEgsGPlypWlCQkJ3zgcjkwRSRSRBMuyuk0iisPhCAF1hmFUq2p5KBTa3b9//+j7KjY2rUBgHugggRynmfCz6Q8/fuv9t9/4RUfH1clQdTivFiv0Oc0wjagOOpsu1Go6Jt1EJ2iBRb0e2UkHGLH2yehm5ptKkq6YO0ROuGtDR4di0/XpFl8yNs3Hu2YVoYpynCLEHeBQnFniI7PER0lmLJZp8vmSdxl9ymlkpieH3fTZi6qys6iIFcuW7XOscRpOTMtEUTZv2kRCQgIDhwzBsB2RbSJgCGQmu6mrdFHrNwmELMqLiygvjrz2JwJxLgcJcU5S412kxDtxGPvv1ZLqAFXeIAEXrDsq+vkrvGWs3r3SFiPbHIKMM1Tev+OBx6c+eOeNL3Z0NDbhWfzCgtXnTMx9UpXfRmwkxIrqz1Vl5PjLbnjanZTy5FvPPhw+E9zjMc5Zum2k3/Blg/xC4JBvEDnJCMmjJY6M20E/Bun0maSFhYXmhMty70Z4DQ3v5ijQQ9FZHyzdHntsdvZ/vissjCbMEknZcT4YdyLaK9L7s8IynObOcMcqtsjG1P68rMho0PAqFEhCuT8uWHvM+EumPr74lXnrCaMmG3txbnzysqLLDOEWheOjxA1ivBkKGs9HbWPTYpa8uGDHhIm5f0b5PZGcrlSzAE9sMG3w+Mty/hjJzTg72+P+cEXR1SJMQzkuymlDKAsrejqbVXvdUPmnijZJjCywbNyYAeveb4Ic2UzxL5Ny90aRpmUSC/y7Ke1sbFpO957PzC+4b1pezsyGYmQA9Im8a2akgQ6K0P3j/IJZi5t7ToGgQqferDogW8oBpIOmKwwBLnbGeBccUKLbBFaqsgJDl6OO5WIay/Of9RQ36USi97dt5G1J8AHgZx0dRVtgmXu8PgTUauj70advP0pLSvjyo/eZ8JMriEvJoq58OyedeBwnnRjtEXr4iRt0NjWrX8Ss2krRtlLEEIYMycLpOnjacM6lTraut9hdUcnCV1/nzONHcuyggSDC+qIi3vtqGSHTxOlUxo5vvGKlM2UgsQPGtddlheWKiZcyfvxZOB1OUpKTI7arrfOSEH/wdNgf8OMP+Llq0jSeffJPLLotmzsLu5Xht41Ni+nuyVbdgScK7svPy5kxBTih+b3VVMOV3VaxDHr6kcqy3Ft9QGxbjdkZ8AH+jiva5QbG9UrthiJvR+ga6h0zbWxsmon9fLbpChx33HEBYMeePzY2Nq1g+tzHxgMHrrmeSUjenD73iVvvv2tKQUfF1RmZv8jz5ZScGW9qE6uKqOjM557ztLlzu8LvBe5r63E7AkP0tvyCWY8CMjlnxtEo4wwYpyIngaYAiQgJaPvoIocP6Ia6N5OxgC1Gtmk1thj5CKVm+ddYdXXEGgbuA0TGonDUhkoqUt2EnAZ+n5cvP/qAPv37c9zIkThdDbVLwWCA1Su/Y9uWLZhm/XanIQYT+k/g052fUeWvRC2LVStX4vf7GX5c59oEs+lEiJCZ5MbdOwFLIRCyqPWF8PotgqaFpQoCThHcLoN4t5OEWAcOQzBEOFQvX+s32by7DtNStg6EkozoWkFfyMeyos8ZP+T8drxIm66J9jJUXrjr/nn3zJ0+dU5HR2MTHnUafyKoY0EnRGnmAEYZyJxgVVXehEtzvzYMloYsXYYaFQ5D+1nKYFm+40I1jBOAVCAmzDiGip4ilt48PvvG5YsLqWmXi2pjrNTAh0aF622QsKXoFQyQsWJQkBVI/6T3pTc84jAcK04flVWy17X14tzc+LpdjrGWEbpNVM8C0mjwDbz/lAa8n+7oF1bM9NVXC4IXDv9lfqA24TyFcyMGLiQDNxpG6JJzJub+G0tfxmCLKVqnSG+nKWNU9JcgoxSSov4lCLuNoN7y39efaGgpaNNmOMzQ05Y4T1Phx1GaDRDht6j7qgmXTn5BsN7E4dygAfWbLh3gVD29NFj0C2AYkBj9jPKJGNbTXy1YGGxOnMmG8/1KDVbT2H0DqOrzTXUvXlxQ4Dv30ty/WXBPE5oXW4itLLI5DHTn+YyoZdx7lmGZS8IcdCM8HKmn5S4e38Jz1oJ2ajFyM8QpDuAEEU5A5SqwwGFxgFjZAv6L8gpO602nussCTioWLPDsLXneVIf5w4/SZkKmzoIVRogMMGDIYFZ+s4KSXUWs+24FQ489gfj0fgS9lQS91WH7dCQ9LngM7+b3qV72FFaghvXf7yAu3k3vPum4XPXLlSJw7W1uXiwIULTZ4oPlK/hg+YqDxklKDXHqueVIlPV/w51I8onXEzuwhb/urSSjkUphlmVRW+slPi42rBFAamYPAIJ1dkVdG5uD6d7JVt0BI6RTLKd8SKQk1UioFM5f5GlWomk0RERLb7jlZeDnbTVmZ2Cl1fHbe8cNbt4/bZfAYjK2GNnGphXYz2cbGxubI5w0RJ++8/55xz0wfWpkA6kjEC/OibGEyoBI5kx7KSqrcT3YHjFkLHxkdtkNt3QLMXL6gkf/tOdHnV8wax2wDnjq0HZTr/IcbTmCp6rIqQKjQDPBSAfNgPDmXU1hSO9u+C4Ex3R0ADbdg45frbDpEKo+qt+jjXc4MA7Z6EiqDnL8t2WsHpaKN86JaZps3bSJoq1bSc/MJDk5GYfTSSgUoqa6irKSUkKh/Zthia5EzuxzFn0T++Lo7WTxtvfxhrxYlsX3a9dSUlJCSr9jsKwhNHcd0ubIwBDBEHC6HcS7W3aPVNQGWb+rlpAqRb2V74Yp2oS9+I82L+Y3Z9yNRNvJtGkzps+dNxaRmaDn0/jEu8NRmD39/nkjauND1z92003+jo7H5mDeK8zffu5lefdZaH+gsfrF8SIMB4Zbys8NERBF2SOr1UaNjhXYYGDMe69wXpdRBSwuKPCffUXen8U0R4P0JrydsUH9YsFFilwUUosPv95RPuHS3CIV7Vm3mwwV05CmfKnCMlOM5wsLPREdlv/93HNV4y+8/lojxvgEiFZyyAUMUeVGRG5EwdgTQ/3/NSEexScq0955bf6WpgRv03LefmVR0dmXTX5E0OE0cBY/ACVWYDCitytyO5YJTnBoGPvryJQJLHj3pYVrmxtneUptraPC/VlUMXw9fjFogifyftTQZ1CZTiMTXhWWaojG7Ry7MF3ted/d6a7zmQWLfv/fKTkzixTt09Q+il6yYMGCZiUxHNC3AkhrSd/Dhbft6jYYwDiEcZjGwyFCGAHIy7knGBcrYZ3tOxO6xpMpwzwlHR1HW6GmGfZzAc744TiWvL+YZZ98QCgYYMSok3DFpWAGfVihFt3q7UrcwLOJ6z+Ouo3vUPXVE3jrAmz4fieJibH07Z+5r93lOW6Ktvj47AM/u4vcqEJGryADh9WRnBZenL2XlJOmEjfoHDA6bv1JVaNWGzMMg549IguWXW43TqcL04x+rTY2RybdOdmq6zPvr7M/zrtmxvMIv2hGt935/zfryraPxigAq3uJkdW5gfrE3Qw6YKMlLkZIS+yGzsgiA1Wfd4j8LPyky8bGpgnYz2cbGxubIx2B26ffP+84p+GYNuuOyes7Op7OwKBBBHZu1ipUou6RWJZ1b7R91dYgoCWqu0WkR3uMf/iQImniNuK8v3q+B74Hnjt0kNxrZgxxCqMsjNGgxyLaB6WPQm9ppCpiz+5YJUas3h0dgk33wBYjH4H4Nm7Au3YNAKnO8LdARqmP478t47sRadQk1ieDmKbJ7l272L1rV8Sxk9xJjO93Nj3i6p9dfRL6MK7vD/lw+wd4Q14AKsrKKKlbR6j/AHDYYmSbtkUVdpT72FHhI2QqxT3hm+MUq4na4s3lG/hu9zcc13NU+wZqs0eYxBLQriZKuiqhzjnit7Mfv/6he260nSw7GWmu0iWlgfS5oB6EAe14qmJBfh+qWP1fmqWZ7HA0ts612B9relBmAT2b2C0NIU2QJui091EC+qfFL+WvbKzh4n8/ue2ciZNvQPWPCsNpkrK42ZSBLjTdztfbYWybMGhF7w+MlKKHFDwIWe10mjKFxzNc8S+0pHOP2tpgmbiWoBJVjKzwhaXBsA7fkXj3pYXrJlyauwLhxGhDi8VXsaGYzmdZ2UZ04ed9d6dbzmdMd+BYI+BqojhWNs0vmPVqy8+mb4FMbnn/9me1tveSj7h+fKq78y9ce12zgLyODqPNkMiTsZTUNMaccgpLP/+c1Su+YsSokwA6pRB5H4aD+KN+RPxR51P+0QP4iz6jpsbHmlXbyMhMJiMzCRGhz4BYfnhRgN3FpY2PKUJMnx+Qdsad7R9/E3h01nRi4+KZcvu9B30eCplUVdWQnp6y77PdJeVkZqYiB0yH/z979x0fVZU+fvzz3DuTnpBG6FWwY8Duz9XFssruKrircYstKFJFxQahuPOVbsMVhUAowbprdl3LWsDGWnZt2BuC0iEEktBSZ+Y+vz8CKJCemUwyOe/Xa14vmHvuOc+k3fac56gqPr8vKCfILZGZxGQ0RrhOtgoH4vWN0QjXb4B2dTYGx7GcPxCE+yyO+L+w6jeputUYFuE9Kz57ZoHH47F2bPEf5690+gtWf62aFNxRoaMIadTxEL2xEmKC0WsLsTbfBYQ8GXnC7EfvR+XPgEkKMFolc3w2DMNo837tc/xvZs2ed8vM8aOfC3UwoZa/wXc/Kh3qamfZ1iNjr/I8M/dJz55gxGGrXuGI/CcYfTcbv3NFAHrRhcum/QD8AByymoPH47Hy19NdrMrjVK1jReVoR7W3CL2AnoA7Jiq8ri8BEKljlVrDqB9T+rMNKn59Ber3E2VZRFo1/wgk7KnktI8K6LFuD1F7KxB/DatSqxBjx9IvtR+X97mCtOi0Qx6adI3ryvldLyAlKgVbqpKPtVXlbRnNyedv3M+G31H2lvtYvXUfmwrLqEDZ2hFWpTtUNOB2q6MO72+sbnVnI+BEptB6HyyeYtvy3oSZ838X6kCMQ+Xl5fnzI4qeFJURoKuCM4quVZW7Iioi8lauXNnqypO98srcilifPCnCPaIE5UIW2Oyo3BRZEfUM9XyI6C/u9LrCrcCn9d2nAXYJck9ZhHPvyrx5+wLct1GDlSs9vuSI4qXqOCNB1wZhiB8EuUUTK2fk5c0pa0wHeXl5frA/AWr9uRDlP+3dPUsb2L0CL9fRZo9Y+tUrr8wNyiz3FqF1H+/DXdidzyxcOHu3Kkvr0VSzc6f2bspYbrEnN2X/5vCm494OGtQHvif1bg0TjOWiUEfQnKKjogAOrvajGvI8mnoSks6eQNrgx4jsfDoAhTv3sGb1VoqLqg7TySlVycm1iep8OmmDH2sxich+nw9Vpay0BHWOvK9m2Yfel3PZ9hFnwrt3FYEqEsLqzs3lZ5OYhmDOH4yGuzq21PXendMf7R/qQIyfzH9qVrE6zKxXY9HlC5fMeCsYcbRf+NA24PNg9B0iH8Zn318A4PF4nEdzpn6dvWz6k/OXTb0ze9m0S7OXTTttwbJp3Tr2dEVbPldfgd8BdwNPobxN1QP38qYEEBcdhg/fD9hdFPKDbtasea+icjsmEdlo/czx2TAMo23rrsq/Jsx+dEqoAwmlEUOzjldlTL0aK5Fet3dOsGJJ7Jb0X2jVq3UWJXdP/CiYA3g8Hic717N+/pIZr2QvnTZnfu7UUQuWTbs4O3fa0dm50yIs0e4i1JBAZxiGSUZug7wFVZWNY+pRldh2lD4/7iH943y6vvoFKR+sJX5NPtGbi9E9bpziGHz5CUQVd+KExPSDycaH6xjbkUE9f82JCQPQkghwwvhGldFojqNsKixjXUEpxSVenDrKbypQXumQv6ucNdtKWL1lH7tLvfhc8PWxyifpDl53w+Oo9JkJ2s1DW3tSQIwI94U6CONI3+TlVb7xwoLl6vivAl4kcJVMfCh/8/m8v0mNKHrylVfmtto/Fi++uLA02VWc44hzPhDI2a8KukrU/vPKAZ3yGvI1WrnS40txF78hjjNU0Q8DGNNOsTQjoiIi+395i4sC2K9RD3l5eZVvvbjoBbCvAvmQwCWaf2XhDEt2Fz29Mje3SQ9Q8fs2IvxYS4vdoKsasyyWWM5/gJqTmJXNlt9aS+uqsN5Arf54H+7C7nym0wbX8LraqOhdNPH3LmHhAzubsn9zeGjp9I7ZudOjynFFW7g6OfiPU2QMIstFJCATqmIiA9FL0CWGOoDmtO6HqpUv+x5ftdpPxd7WdfpjRcaT9IuJpF32BFZUEqpKwfZdrFm9hfLySlLbtyOhmlKMVnQyaZc9QeIvJmJF1p6w3Jx++P6nRUJ27Tr0e+Fy2SS2OzTWpKQERA69Z/buG68AcNL5Q4IUZQtiJjEZTRd2k63CgaDf16edo1ZQZ5JYyN3B7L85CeqpTzuPx+PMe8Kzdn7utOeyc6dNzc6ddlX2smm/zM6d1ic7d1qMJdrdUS5WuBVlPvCywNdo7RN2AaIiwvgZT3Ron51OmDn/eoWLQxmDYQSYOT4bhmG0dSr3jJ/16N/Hz1pQnxVTwo441t+lQSuWyPXDr54YlElp4vH4UCsjGH03B1XNEI8npMXC5i2dvgmo5wqNrYiqKehlBESw1+w0WqCIzl0A8NZznXUB4h2b3sSx88Mf8Xurlvfcdvxp7Oh9AoiQv28Pr334MecN6E9sdDS2bR+sjayqeP1+dhTt5duvd+AtS8RXGo92FQj5/HKjJVGg3OewZ3cFBbsrECA60iY6woXbBksEVcWvUOlzKCn34/1ZxW6fC3akKp+fpA2qhny4Y9uf2OTPYrQNin4T6hiMGulbLyxZPTAz80p2uy+3VSYpdBOI0YZNxnKAEmCHiPXXGL+z6MV/5za0OmqLlJeXVwmsujBj+BC/l5sFrgdSgRga9jVSoExgN8oTfkfuXfni/J0836iY/MAXHo/n/739ef4NqHM70J2GJyRUADtUec3vkplv/3PhmoZHYwSQvvlc9ocDL7v1YpuSUSBjFZKpuvFS36eXKlCmsAv0n47jPPzmC4sDU23ZjtwCld+DnFRDix8cy27kz5BsAL4GTqt+MxutCF9tidCGEXThdj7jWenxjbh20hix5NEamvgXLJ1+f4CGywNa5I1bVZ468O/cXE85kL//9R0w7+dtR/15QpJGuNIROQklHTQd6Ec9bpBHultFEkpsqANoTjsKCgA4YUDVocfxHzqX5n8ffcG/l79d4/4XXXY52H2DF2A9WRFxpA1eSmXBl+z+8K/4S3eyYV0BLpd9yNmDHZNKu9NvJSKt5V3HO47D26//tEjCq//6G3+64aYG9bFl43q+/+YLLMtm8G1hNXekBmYSkxEQByZb/SvUgRhw/fV3xePIvLpbgoW+RNU9gKDwusvftL2R+4BWvfSswp5kKQ3ExHLd/xB9E7Di8I3D/jSxgxUtfS1HjwbpC9ZRoL2B3kCSHc6ljopDXfZZB4Z2fMMICnN8NgzDaOMEuRLxH5917/yRM+8a9V6o42kuozInTVSkwTeuLJf1EdA1CCGRvHvjm0WJ3VaBnhKM/oNHP3hz95ZAFtlqih+petYZPtTaFuoQjPBgkpHboOSLBpGfk82+igr2uVzE1aNCMoA7Koqkbt0o2rgRx+ej43ef4LhcFHU/GhWLbYVFPPPWf+iUkkxSXDxRkRGoKiXl5RTu3kNBcfHB0lOWz4+o1qsUlQhE2VY4l4sLe1Y9b905NqzvrqijpBQJURVQWuGntKLmoqYqsDsBClKVgvZKcSI4TbgR2iGuE2f1OLfxHRgNICv2L73aeimPhzqE1k8+prbEV+WHpvS+v2LqkxdmDP83Xv6gyFmC9lGhF0oqRyZDHkh43AdsE9XPEes1W0pXrPjX4wUNGVsroiqwKr+BmpdpEexGndSrJTtwWCWi1R7EFdZb6pTVp6/X8xbuBqZddOmwJ3wueyDoOSjHo3RCiAONAzmYjCSCo0o5sIOqpKaNqryL8NKbzy9s0vfrAI/H4xnYAQ8AACAASURBVACLzr9s+JsiOkSVM0D6AN0R2qEcVvdeyhDdjbJHYSPwNn599pendPl2f18NY1f6lIjNonxdUxNVZ1t8uTZ9CR7lE6SWZGtHVsfvrWi2pX5KI9Ub7eUbwFtTG1XZ3Ji+Vz730C5g5gW/u/GfIBmiDFClL0IPqhLFfn5tolT9Lu5G2S0iPzqqr4vtf/bNZxdvaMz4NXkjvX3x+Z9tfVPRVFE54u+RWryLy1rfmL7L/f5tkZb7BVSP+H1UQS14Y3ne4uLG9N16hMHxPtyF2fmMZ6DHlW/5akpEBrBHXuNJy37c06DjerUdqT3eL/4WmYwsETKhvm3nPzWrGFi5/3WE4cPHtxOvfalgXQpyMo4mAolIVV5oiyfSiPVyWh53ZNXpQmV5PRcEOFBd97CJ6KeffCLvf/wFOwuPLN5xbN+eHNWzK99valKoARWR1o/2l+RQvum/7Hr/AXy+/fcHxCbxzNuI6vb/qP/cpuajqvxtyaPs2VVMSsduVJSXsm3LRl54ZhmDr7yuXn188v47/Oe1fwOQMaVeeXyGYewXbpOtWrMIJ+JRoGM9m3cbed2Um7OXTX04GLGkzZu3b+fw2yaJ6l+D0X9zsSBLFi4M+kT5RU/P2A5sB949fNuoP09IOuekqGuAVv21NAyjeZnjs2G0HVkzso93LOcGUT0WK5xnMLV5yYffd6qTcqLCOxNmzxs9a/zo7OCE1XLcNGxyL5+vfquaVKPLjddNHpyzbNoLAQ0KkLw8f/HIW69w/LIu0H0Hk0jklVdWFbYKPWUVcGqowwiweq1qZBh1McnIbVBEl660G3g+xctfYUtFBV0iIohz1e9HISo+ng59+7L9++9x/H46ff0hikVRj6MB8Pn9bCrYwaaCHbX2k7xhNftO648TWfeargK465vNarRqasG2LsrmJMVylIS9kFIsxO+FqPKfHi/6bCiNgeJE2JGi+FxV2YNNJSJcedK1RLnMiqDNQnUqwkW0wiVYBbZEJtlHe0aMCIsKuaGkfr2htu1+y7cnEOPsT7hdOHBg5mMk2F1t29ULcVLUkTjQRMRqV7UEpRY6onsE9lqOne+LtNaszJvXqCVJEiO37yzyp3ocr6/Gn3Gfr6JRiVDeSuvtSJezxvFX/9dPxV0R7bUbkjCqK15ctA5Yd1ZGxt9ife16qmN1dFTjEYkTSxKAOHUoBacUkRJLrR2W7eQ7Fttez1u4hyYud19dTG8+t/AH4MGLrrkm1tkT3Vst7eFXK9FC40VJQrAd1UJFCm2R3Qi7ccnGN/OytwC89WIjR97Vc58kbn3U7+jTNTWx3U5BVMSeikaOcJBlOSP9viMTYA9w45SuGNizsvr0sMCL3NFtD4lb71a/RtXUxhLfzqaM8ca/cr4HZgy8LLOdS6N6Ofh7IsSJSIKjJFuigiPb1aIIR/eA7LId76bXXuieD41ILq+Lx+M4l2U+7fhdr7od/xG/U96Y2L3v5M1t1N+B915Ysu+C342Zj7fsqcO3+SxLvY57F4H/3WlZWvHxPtyF6/lMfk/v3+pMTLR9bwPHNnWsxEX3ryscfls+qvVNsGkum1PmPRiwdNKFC2fvBp7Y/zrojmvui0V8e9FAXI0ZdUnpcTwbPl7BujWr6datS4P3ryzdR0R0LLZtMW7U1dz/yDKKd+09uL1Pr25c84dL2FwSyKgDRYjqdjYdu53Nvm/yQCDuuBY5DwCAd15/hec+fwOA+MQUxi9+jcryUqZe9QvWfvc1D95zF916HUX3Xn2xrZ8y+isqy9m5fRuVFRVsWn9gjp9wyc0zOObMX4Xgk4SCmcRkBEiYTbZqrUZdP/lCdbiqQTuJTsvM9Czcv7JDwKnPtVRs719ovRWsdvrcFY+FOoj5T80qnnfH9PBdhSqpLMTX6bIS9JrQxmAYQWCOz4bRJmTNfvT3qs4/BaomSjc0WdUIf1X3EudPmDm/36ysUWNCHU4weX08LTS+UIIN/4TDCzQFRlL2Q+uLb7ztBgddHIz+A00dMlMWz94Y6jh+om+CjAh1FAFlsyrUIRjhwTwwCqD7HnsstrQ8Yq/u/7qekX4cZ/U/odq2qlBW6cMJ0clX2ZrVrJ8ykbI1VRMbEmybJLe73lWSK/bupWjTJvxeLyrC7s69KOxxDCXJHX6qvnMYy+clvmAz7X/4Cn9CHJ/fOglvXDwAVw06lz7dOgXmwxmtyq69+/jr314CwCsVvBK5iC3530NlHTsGmMty8etjLuPWX0wiMSqpeQffzxIhOsJV068Q733yJR99uRoAAd1ZXhA99+abm5wIF0oTZs47BZEp+5dibS1JSk/MmjDa3AwOHzJwoMeOji60CwoqnFWrFvoI98TAxvB4rIErsQYOxGlUpeEgxHPK1q127+JiyTvhBB8tISajyTwej/XM11+7TgDM9zW8tNLjfbgLy/OZG6+bcoIt+lV92jrKxQuXTTtiOeqG2jfslg4VYuU3tZ9A8paXdej4eHaTKz/Xh342o4KqlSZaskrpP7HumdBBkPXIspTIiMid7ZMTuerSCw/ZVlbpw+/U/7TT761gxexMHL+Xc84bSLvE6q9bl//733i9Xq68YSwApUVV89MK1nxOQqeeRMW1q+rPccheksfW/B2ceFwf/nT5IAA2l9i8sjGanp3TuO635x3Sd4nXwWceIgJV1+/x7kPnkz3z+nt8u24zu977G6VrPuCcwVfx5ztmsndfGbZtExXpYuHkEXz+7vJ6jdH56HSumDiXxA6BWZHTtqruOfzc48+voHDXHmKjKuPuvPbakKeiV50z8A7mfMFopHCdbNUaZWZ6oqLUtxqhe0P3FeTZ+blTLw9GXACFw277A6J/C1b/QaWakbLooX+EOgwAXTXjHGzeDnUcQeGrjJVTPSH9O5I1a96rCheHMgbDCBRzfDaMtmP48AXu5N7+zUBaqGMxWgnlHcfixnvHj14d6lACbcTQiVeLWnVNxCkEUmpvonnZudOvDFRch9t5421PCNqwSaTNTNDHknMeqt9SY81EP53ZE9FWVVm6VsJeSZ+YEOowjPBgKiO3UdF9jqbP3PlsmXM/xa+tYI/fzz6/nxjbpmNkJJE1ZUPuFxkfT2qvXuz48Uccn4/ELT8SX7CZyth4irscRUlqJ7xRsaAOkft2k1CwmYRt63GXl2H5fexNiGumT2q0OpHg9HSw1lm1LBAfWGmxHbn9nCn8otcFRLlqLARpBMGsrNGrgMuae9wJM+cOROy3GrqfCNfPHD96aTBiMkJGV670+ABfqANp0TweZyU4K5upOm+dPB5nFTirAPLyQh2NESD7E90rvwHzfQ0zoTrehztzPnMoj8djbV/v+6C+aZKW8HxGRkZcXhOXdYtb9NftO28c97xAS6nk+c/mSkTer4SWn4wc8gTLQLDdkfQ593K+f+tvvLvyP5xx9tmktm9/SJuNGzbg9VV/IZ3WN/3Q/iyLq68YxJuvvc5vLz0/aHG3RadfOpSenbI47fRTsH426d/ljmDUrCWs+mgVxdvWs+m7z0lJSeTlpQ/QPiGSPWU+dlt+PjrZYW8czLpsVMASkVuLWVmjV02YOe8cM4nJaKQnZobhZKvWKgrfrMYkIgOo6uBR1048af5jM74IdFwAyV0T8oq27BkK2toSPV9O7pr4bKiDOMi2iiBM5xC3Sw750s8zJ4weNGH2o/ej8mfAVPIxWjNzfDaMNiTlKP9vVU0istEAwjmW8jBhNglr5DWeNHW8j9VRHrS0sGR1h5TYY18BrWVJLPn9yGs8admPe4Jyzzc158GrC4eP641yVjD6bzp9t6UlIgMQbRVSHvLLhkAKn8RqI+RMMnJbJYK7fRo9ps4kadBv2P5YLqXffsO+8jLWlZWR7HLRzuUi0qpx1XDc0dGk9OhRVSG5shLbW0n0rkKidxU24wcxwpIbtKMiWySo9zO7JHTjor6XctWAYSRFt9aV+YzmoKAq/tPvHT/241DHYhiGYRiG0Rjhfj6Tv967GCS2AbtEpcQccx9wW1PHTs2Zc1nhjeN2Ae2a2lcTFafkzLmimcfcBYRmaZn62xXqAAKl77lXsGfrj+Sv/pD3330XEaFdYiLl5RWUlx1aZExVEREq9u3C8fuIbpcKwO5t60jo2AMRi7Xfr8btsvj+2285MT0dVaWkMB/oFYJPFz6OPfFEKC2lqKiY8vIKSkvLEBEiIyOJjIwgOjaBU4dcgQ6+nPtGDcG2hN4dYlj14y52tleK9v9GPfv10wzsfVFoP0wImElMbZuZbBUeRmVOOlPRmxq9MKfgUrGeAE4KaGAHuvd4nH3DbrmuQqzvgdZS+WmX17aHSktaQchXvh1XS5+T1kh9OraIogWzxo+5A7gj1HEYhjk+G4ZRX+pIMmJWVDIarI7KwK2Lx+Ox8tf5nhSpvQKkiozIy8vzj8z0DAff94C7hqY2tu91gnR9BJBcvPmcwsQuHwhySrDGaAxFP0rpkvjLUMdRHTl2/F79fMYXaPC+L83K4c1Qh2CEj5ozTY02QWybducO5KiHHqHn1BlE9+mDX5UdXi8bKyooqKzEqWUJzsi4OJK7dcNymbx2I7A0XnE6BefeamxEPDecehNzhyxj9Fl3mERko1aCvCFKSrgm7hiGYRiGEf7C/Xxm2DWTjwPJrHajsI+q5e6q2zZu5DV3BKRaS4TP1zcQ/TSFW6yjm31Q0eXNPmaD6YpQRxBIp/zxLk75w13YLjeqyq7i4oOJyHF7KkkurgBg07o1APgqyvFVlFftrIq3vBT23+fZt3cvAI6z/9pbHfyVFc34acLTgdtoaWmpdO/ehU6dOtClSyd69uxKx47tse2q27EP3/ZnfvjyY07snkClz8HnV7495qd+/rfhP1T6K0PwCQyj9VBQR/ynmUSnlsPj8bgc5AkQu46m+XVs7zcic8roQMV1uLhFf93uqLaUlS3q5FcGd8y+vzlXv6jbKZ5CYHuowwg41Q0iV4ZViTPDaG7m+GwYbZeo/+tQx2C0Qqr/DnUIgbRtve8ihAtra6Pw9YKlU58AyM71rAdm1NFtv9FDJ/0hUDEeTvLy/CldEk9H5I1gjdFQir6WkvPQGS1qQuYRZFaoIwgIwSHGuT/UYRjhwyQjGwDYcXEknn8hxz39T7rcejsRnTvjBXZ4vawtL2e3z4e/hqTkyLg4Unv1wnbXNFHHMBpBgETQNG10EY3DxUXEc2b3c1h6xT8ZfdYd9EjsjSXmz6BRC9X/mzlh1IWzskYXhzoUwzAMwzCMRmkD5zNuW/5b0zbL8g2oEP9xNe5sR78ciBjil87doTZdCc1a1Y7j93ZJWPjAzmYfuVwmN/uYDRXtbfkxNlDHY09n0KSn+e1f/sFv//IPLhj6AJ1eWM0ZHxXQ+8c9AHzy35UAxKZ0JD6ta9WOIqT2OgGxbEpLSti7p6pt/tatVZstm4ROPZr/A4WZx2fdzisL/sLOrRuprCjD563E562gsqKMHVs28I/7xzHi7M5899F/6N+rHVFuiw07ynAsKI3+6d6bow6bd28I4ScxjJYt3CdbtVbb1nknCBxVeytd7453HYNSa/VZUZ2WkeEJWund9oseWonqiGD1HzDqDEtbNOedUIdxOBEUCMi5dItisSDUIRhGa2aOz4bRts2ceNMHCs+FOg6j9RBhyKysMZ5QxxEoY8eOjbSEF+tqV4Hr1J//v7CkZDawpbZ9HJWHMjM9UU0MsUbi8TgpCx+8UFTnBmuM+gejD6XmPHSRQMsutV7mhEc1YWWrHDO51p8/w2gIU87WOJRl0eHq60g873yKV7zKjr89hbewkC0VFcTYNokuF4nVVEGOiIkhuVs3CjduxPHVvYKVOIceM8oqvHh9ZrJ5W1Ra/lOVH0Vx5NBn95qiSKU0aWFdQfhl719xxYlXcVq3/4fLMonzRt1E5NqZE0Y/Huo4DMMwDMMwGqstnM+MyJwyX9HEajcq/5i3eNbaqnaTXhTk0moanTJ8aNYZC5fO/KCpsaRmz9myc+S47uJnc1P7agjH7+3WfskjW5tzzAPkjImF+lldhTtCS47xNH+SdjPbNOMeIi2rak7vrgpiS3yUAB+sXEG/k44/on1lZSVvv1l1r9xluaisrOSbL7/k+H79mjfwMJUU52bHN/9jUsaZ1W6PjbTplRZLWruq/Lp95X6K9lXyxnlHzmX4y+u38/iVLwQ1XsNolVT/b2bW6LB5YB0uRgzNOl6UOr8vts3AuXM9e0YOnTwbZVKNDYWklFj/AmBoIOP8uZRFDy0suvG2JEVbaEUrvTNl0V8XhzqKGikvIMH7/oSE37Us1CEYRqtljs+GYQDR5dF/Ko8uy0UJWhVXo/VT2Gk5vuNnTrx5R6hjCSTv3sTnQevIw5MbcnM95T9/Jy9vTtnI6+8ei+M8W8uOHaPENwO4remR1ix50UM3Fw277VVHNE8gJphjVaMEhytSFj/0ajOP2yhy5qTt+tn0f4JcHupYmkZmhzoCI7yYZGTjSCJEdu1Ox+uHk5rxJzbfO5Ndry+npLKSEr+fIq+XLpGRROx/0HVAZHw8aX36ULB2bZ0JyZHFRdgV5Xjj4gF49q3/BfEDGa2FVyrZZx1WsM0Cp4uDeAUpaViJZEssuiR0I2vgNM7ofk4AIzXC3DeK3jhr/OgaK+wZhmEYhmG0cG3ifGbo0Kz2Uks1u8LSk/544N9FJaV/SImNLa2unYX9ekZGRmJeXl6TZ8imZs/Zsnfo2LRKl2sN0K6p/dVGkGKXyNEJSx4JdbLtM8CVIY6hekJeqENoDns/+pBOkZEH/3/6R9t5a2AXNvywmq2b1tGjV086depMpdfLj2vXsLNgB6pK73ZHcXbns3n828f4ce1adu7YQfeTBwLRofswYSApNoKu3RNQBb+jOPtXGrNEsC1BfnZro9zr8PWmPazuq5RW82X/ZvsXzRS1YbQebWGyVWukqjLq+in/AOzaG3LHo4unbwDIXjptysjMSRNAatlHrx0xNOu+BUtnfhPIeH8uOefB2TuH3VYmon8N1hiNoTAmNeeheaGOo1ZW5X/RoBWvDo3IslCfWxtGq2SOz4ZhHODxDC0H/njnvdlT3I7TRx0nQGsgGy2NitUPocGT+gR5ZtaEUWGXrD7i2ilngV5cWxtFvuvU086tblv2knv+NTJz8tvAubV0MObGa7Oycx6b+X3Toq1d8qIHX9Zr7kgrjnZmqepNwRzrIOHhZNplyWJPtffwWy5rOmhrTkYuJ33Co5AV6jiMMGKSkY1aueLj6eG5h5Qhl1H43LPsfnslZSUlrCsvJ8G2SXS7if5ZUrIrMpLk7t0p3rQJv9dbbZ9qWajbptN7b7HhN7/HqabSstH2KMrX+95hb3khJHHEHCvtorAZpLR+1ytHpx7P4OMzGHT0EJKikwMfsBGehDzL5x47Y9KN20MdimEYhmEYRqO0ofOZKLU3KFR7gWCLc0pe3pUHk4vz8uaUjcyccgPokZXllLiUmGMmANMDEVf80rk7gMSdN457TmBIIPqsxr+Scx78fZD6bpgI5y4qrZaZjIx7fKgjCLbSb74GINH+KY/L9ivnv7WFj05NY288rF39PWtX//SMQhD6pZ7E6R1OB+DS3oN5ed1L7Nm9m1UffgjdLmzeDxGmRMBlCzX8mWLHnkp+3F7Cls7Kd31rXnXy060fMqDz6UGK0jBalTYx2aq1GjV0yjDguFobKTs79nL9POFXHdwnWvi+rWUvC7WXANWXmw+Q1EUPPlx847jPFd7QuhKqg8/vV85LWzTnnRDHUSdJ9xTo5zNeRRkU6lgCQsiREzyVdTc0DONnzPHZMIxq3XfXyDXAmlDHYQTPhJlzSxt86qyMmpk1Kjs4EYWWWPp6XW38LvtXHo/nyKWx9nP83mss27UWpKalviNsy54PXNDYOOtLHr+/BBi7a/idD/nVNxsISsKtwj9cLsYnzp/zYzD6Dzbpn/WpfjrjZYTfhDqWRhG9W0RqvjFpGI1ghToAo+UT20X8qafTwzONPo8sIKpHT/yqFPt8bCgvJ7+igp8fLaPi42nfuzdWNUnGvthY9vXoQVlKCkmrv6Tbmy9h+Wuvomy0AQJfVa7k032vwy6wNljIVuGQHyw3aGet869WlCuam8+ewKLf/50/pmeaRGSjWlGR0UeUl1J01qzxo69sC4k7hmEYhmG0fm39fGbE0El3aE3lW4WvHl0645PD387OvWcpUFzNHiBMGz3aExfIGFNz5lwWqU5HRPID1acq+T51OqbkzGkZiciAHD95A7A11HEcQSRf0u9cF+owgm3vh+9ji2DJoQmvlqOc8eF2Tl65npQP1xK7YSdOSSS+gnh+mTLoYCIyQFp0GlcdezVJ/o6gpmBRU20uKqNgdwWqR97H96uytbicT9bt4oeCElalKx/3r/1+/7qitcEK1TBaDyHP8rvPnz1hjEl0aoHGDvN0BRbW1c5GBno8nkMeBizM9XwHbKhtP4Ezhg+ddF3ToqxbUs6c/5TEEQ+E7FxalfzkLu3iWkMi8kHC3FCHEDj2PaGOwDBaFXN8NgzDMBpAsX45K2t0WCYij7xu8vMcUW7vMCK3LFrk2Vxbk4WPz94owtI6hjt/RObkZkt8TVx43w8pOXOuiLDtDipkKZQHoNsyER3vte0OqTlzMlprIvJBLtfNoQ6hsSR90n2hjsEIP6YkrVFv4nIRe1I6x/3jeQqff5bC5/5F6TdfUeTzsdfvJ8XtJsHlwi2CKyqKlO7dKdq8GZ/Xiy86Gm+7dnhjYkAEd2p7Es/9Jcf/+RrKklPZVrATr6/JK+I2K7dtIVLzQ7pPvllNWXnVJPqeXTrRLr5xz7V37d3Hhi3bAIiOiuTk44+usa2jis9f40SqFsmyLTqlJnNNwiBe+f5Mnvv673yZ/ylSLMg+QVMUTVBwA5Hg9HCwNltwWOHt9rFpnN3zfK4eMIxeSX1C8lmM1sNz27Ci8bPm3SzwMMoXwNzZWWMWhTouwzAMwzCM+mrL5zNjfz020qtS000yJ3vptH7VbxJVJp8hUO0ydk6p71XgF4GJskrcor9uBzrtGnZHL7/4ZwMZjezqGSvCuivp0QdqTdYJGXEPQL0tKwnecvqHOoTmEH/6GWxRRam+/m6y30X0pn0UvvsBlTFxfHdBBiveX0Vy/Gp+e9ZZxEZHUbR3Ly+8+1/KKx187ZOge/VjiZiqBgfUcjuI3bbDroJS1hVUv6qkCmzqonx6Uv2KjlzY97eNCdEwWqWoyOgvyisPLUqq6KzZ48eY9UJbLvH6vM/XVAX+IJV7H1029evqNjkRBX2tyrRaq9FaKnMyMjxP5+UFt2pttzlzyoCOhTeOu1uEKarN9AxN8AniScl5MCArdTSrfhNf4fMZW4HOoQ6lSYQfJH18rckhhtFWmeOzYRiG0STCO7ZX/jR98sgtoQ4lGEZcPyUdx7m01msiYUPhvu8erU9/HXq4R+Wv82UgJNXcHU9lZHjSgn199HPx2fcXALM0I+O+oo4dYylzXY4lt6F6Yr06EPnK7+iDdrTvn8n5+SWSl9e6EsRqIf3u+kE/n3kfqneGOpYG8blMYpURFCYZ2WgwsSxSL7ucxIHns+edt9ny6MN4d+5ge2UlRV4vKW43SW43kfHxxHXvzrbSUnxRUahlgW2TMug3pF17PVE9eyIuF1FAUruEUH+sBot2u7Dtmk8ovl677mAycreOaXTtlNaocTZu234wGTkqMoLT+h1TY1ufXyn3tt5K00OO/wO/7HUR7298m0f+dy/5e7ci2wUpEjRZ0aT9i+TZHJKMPOjoIWSeMpJeyX1xWebPmlE/syeMngvhVLnDMAzDMIy2pq2ez3g7Jq6lmoqjAIJcU9u+C3KnrRmZOekNkOqWsjv7xhs9R+fkeKpNVm6KxEX3rwOuBNgz/PZUr/qngVxUhvSKQA8uaOgHKhGi0XUCy10RlZMTHn20MNDxBJqk31mgn8/IQxudbB1YIs9Lv4ktKzk6SGKOPxF3SirfFxXSLTKSGPvI5TGjExNJ8vsp3ryZ3v99hfVnXETR3n08vuK1Q9q5Kstp/9X77Dnz1OrHcplU5Pr4rr/yXTeH2FJI3CVEekGBikgoSlTKo+rf1yldziQhsl3QYjWMlqYtT7ZqrYZnTh4CnFxbG4WiCrH/UtP2hQsXekdmTpoFMqGWbpJSYnyzgNsaGWqDpOTMuUc9nmlFW3YvBwYSpGdpAl5FVyZ3ThwktSzX3JKJoPq5ZqGyLNSxNI1eFuoIDKOlMsdnwzAMo7EU7p89fnTrStBsGBFHX6592jrqUrk0r57Jtx6Pxxkx9O6hos5ztTRr1z7OezNwf4OiDYD9ScR7gKX7X4zMnFzrjPvs3GlhvxSbpGfdpZ/PuBTl2FDHUi9Cnpx61w+hDsMITyZrz2gcEVxJySQPvoyEc85l25Icdr2+gsqCArZVVrLb5yPSstgNODExWNExxB5zLJ1GjCL+9DNDHb3RQglCUnQyvz7mMk7rdjZLPnqElT+uoKAkH/JB8n86R4mwI+nXcQDDThvL6d3ODmHUhmEYhmEYhmE0lxGZd1+KOl2r26bC5uylU5+qq4/CktJLU2Jjqy1Zant9HwNBnS2bsPCBncBIqPlGbXbutN7BjCEYJH3ilfrp9B2IpIY4lN2SntWmkklOePFV1oy4nnVffkGkZdEzKgrXYc9AYlNSsFwuWL+eE159gr1pXSjo25/yuHbE7NpJ2vefEldUQNFxNRQWN+pNExX1KiUIJTH1q35cndFn3s7QU8cEMDLDaB3a6mSr1mjMtVkpfni2jmbqx39Zbu60WpfyLSxx/yUl1ncrUPOUDWHcqKsnL5j/xLTVjQi3wfYnB/9KPR6raPPuJSJcqpAckL6hSIXnkzq3G9Zak5B/TtInPaafzZwIWnMllZbtQ0mf9FWogzCMlswcnw3DMIwGU0bNzhqdHeowgmnEdZPmUccKIQL3l7G58AAAIABJREFUPpI79cuG9Ltg6T3Pj8ycvAnoVlMbR+W+4VdPfHLhEzO2NaRvI3hyXqy84bpB7vciXC0+97oAb8pVoQ7CCF+mpInRZK6kZLreegd9Hp5P2tXXYcXGUuo4FPt8OEDMCf3oec90jnp4nklENuotNaY9d/7Sw18vXcKf0q8nwq66Dy0I/ToOYNagudz/2wUmEdkwDMMwjBZDM4jQW+mkN9FZb6KzjqajjiM61HEZRri45po7YgXnhRo2+71SeXx9+snLm1OG1FhVL37k0MnjGhdh2zZ6tCfu9gVl8aGOA4e+oQ6huVmRkRyT+yT9XnkdTevA6tJSNlRU4D+sgnh0u3YkdeuGOA4J+Zvo886LnPjKE/T+36vEFW6nporjRsNpN4XIhu9nicXZPQeyaux6bjhtLJaYW7eGYbRMHo/H8luuv1PrWsSgqksW5c58p67+8vI8lYL/orraObbO93g8zfrHUTweJ2XRnMzknDkptlqnKvoCyiaBinr3ARX793neUf+pyTlzUlIWzrk+HBKRD3JkONAaP48flT+EOgjDMAzDMIxwofCDI85Fs8I8EXl45pR+IjK89laysUNP1+TG9O+Od51YVxtxy5PUcU1mNI9hwyYf98la3+sPP1uBv2VfFe1G3P3k1BHeupsaRuOYO9pGQIhtE933aLqOu4NjFi0j9qR0Irt2o9uEyRyz7EkSz78QOzY21GEarYwg9E09jtvPmcLf/vQyg44ewm3nTCHn93/nl70vMkuVGoZhGIbRsnSlP8oP2GzBZgtuvsDhN6EOyzDCRZwr6tUaNwp3Llly79769pW9dNocoPr2yoMZGePMRIIGGD7cE+Mv9RWWlhN518IynNDktDrgdJWTJ+4IyegtgDutAye+tIKjHp5HWUQE35WWsrXi0Dyp2ORkkrrVWFTFCCDnKAci6t/+tK5n8fy1b/PwpbnBC8owDCNA8tf7zgW9oI5mRRE+d00TwI7QoWfke0CtFcNE5Lz8H71D6ttnoCUuemBVas5DQ1IWzen+cJd2MRY64AV/BB84br5Tm3X7X9+pzfuOmxf8EfjRAQ93aReTsmhO9+ScOZe1X/TwqlDFH0xy8oS3UV0Q6jgaTLlDBmStD3UYhmEYhmEYrY+1uZo3X3Lb7l/dO/6m15o9nGY0fPgCt6BPU3vOnV+Eaz0ej68xY8yd69kjwmO1tRGV80ZnTkxvTP9G4IzInNzX7eN9IPqHrQ6LX6lomTUflD1YnCnpdxaEOhQjvLlCHYARfqKPPoajc3Lxl5TgSkgAMRNxjKbrkdSb6Rf/NdRhGIZhGIZRTzqOLvjpcfANm0oq+E7msa9J/WYSRQInH3zDQhE2yhy2NKVfwzCC79IFb6UildNEuAhIBGIRcQOg6gVKgF2ovu51OZNeuf43B5NKR2Te/StV5xfVdizyY/bSqXMaGo9YnKYO31W3LSUu9gXgVw3tsy3KyHjGtiq/KGR/2uXeUmX8wjLuG9Hc+dxOd+k/2RwLgHZnn0P6Ox9Q9OorrJ90F8U+H50jI0lyVd0GjE1OxrJtCtcfmXcTu63qS7hhawHTFuc1a9ytnbP/KUORa//qmAJOXwfr69prQUS6Innh2rdJje0Q7BANwzACIjPTEwW+N+pqp6LXz33Ss6e+/Xo8HmfYVXf9xuWO2Eht1b0sWXDHNXesuP/x+0vq23cweDwexwOfjcysvdDZ0CWzP2umkEKvf9+x3lVrf+V20SfUodTTe6z5dG6ogzAMwwgX5z69tlsE8isVjhGHbTi88frVR9U60cgwjNZrVtaYtRNmPvokIlcBoPrwrKwxt4Q4rBr9Puetrn4tP80R6xSBdIS+ONpJROJUEJQyhAIc1qnwpYWu8vl8n7w06pKvDu9LvBvHC3JCbeOp8GT20qn/aUrMHXq4huav9/2RWqa7O2q9A4R+tbo2amTmhJ7A/xQSDrz36Ro/81+oYPSQRiybFjSyE1vOl5MmVPs8xDACyVRGNoJCXC5c7dqZRGTDMAzDMIw2SD1YOAxCyD34cpiDm95N7jye1EP6VRbi57cBCNswjCC4NGd5r8E5y58ZnLNcxarcIcIIoBeQBESgKqgKVTdUk4BeiNzo9tsFg3OW6+Cc5Xm/m/PscYLzYk1jWGqf3ZjY5i+ZthrkvWo3KheOyJzctzH9tjUpsV9sA6J+/t6+MuX2+WXsK2uWEhC7cUgzichHSh70a05e9SVpV13DNr+fb0pK2OP3AxDdrh1JXbse0t4XHU1FYgIpX36CAn7HMa8GvFSVzb7V7Ph+I1L00/0w59jq12ZMjk7hwd/m8N9Rq00ismEYrUokvroqgAHyzwVLpz/f0L4XPXnvZhV9oI5m7Utckbc3tG8j+MZc//kZd+eWdispb4llwA6jbCWSIXJlnj/UoRiGYYSDc59e282Ffb2qTMJhmMLtalm3XvjED/1CHZthGMEzK2vM1aj/PDtCurbEROTLFrx81JCcFdMHL1r+nY/KTSrWswKTgEtQjkEkQQ+UvIEYlJ4I5wncrMgy2+X+8tKc5YWDFy5fPHjR8nMBxlzrOVoc+UutAwvbK9Q1oqnxezweRywy6hgrbmTmpAlNHctouNGZd3YE1/+AlMO3fbnOz6yny/E2qi52oMkalNPkpAlmgpDRLExlZMMwDMMwDMMwAk9JQvh5Il8M1qHJao3s1w2H9FuOkNTkfg3DCKjBOa93AP9nQMcmdnWFPy72ivzTziDts0+wvN5DNgpMmJfryW9s51aMPcgp9e2tbpvAB6ApIK0gm6L5DRzocR3X07dDq6pcH6G0QrljQfmo7HHRF6BcEZQgRJ6X9KzLgtJ3GOl62110unEkm2bPZNMr/8YtQo+oKGJTUrBcLnZs3kxJ5844EREknPn/uPT2W6iIjKbisN+3YIqJOPQW5ZsffMLW7YWccuKxpKXUfpjfXljEJ1+tpkvH9px3ev9DtpVWNt8df7fLRUz0JXT7JIZ5/7sfKRC0s6IJitPLwVr3U97ezEGPcGGf32CJqRNhGEbrMvKGKQPwa13H3mL89ujGjhFR6Z7qdfuG87PKUodTFc+wayY/vujxaesaO44RWKOum3KKqq7YtY/Ih5+tYNwVkURFtNhiNUUI58lxEwtDHYhhGEa4cFuuPvid34AeKEaRDP6BKnwAmOQnwwhjs7LGrgx1DIcbsuTVC9Wx/uKo/gIUmnB3VyAZ4XqU6wfnLF+7a9OmyvhN61219Kmq1jW5uZ7yxo/6k517V7+UEnvsN6DH1xLljLFjx86ZO3duRSDGNOo2PGN8Owf3x9Ty/GPDdofJS8oY/6eo7cnxEqpKBH9HXDdI/ztDurKQ0baYZGTDMAzDMAzDMAzDMAJmcM7y58A/JJB9OhER5J9+JlE7d5K8+tsDbxfNy51673ymNbrfefM8+0ZeN3kyUm0nSTdm3j00J5cljR4gjB3by79NtfpEZABBx2XnTstekEu2rr0vjRLf56g2NTl9f+eSj+X0l34TtwekvzbAjk+g57SZdJswkdWZV7N23Y9EWRZWRASlPXvi7tCRE596BldiVeKvC4glutnii4tyH/J/t7vqlmVsdBSJ8XG17ruvtAyACLeL1KR2h24rb76E6gNuOPUmbjj1JkY/dzUfbv4vqlWVkW2xueS4y7n7gnubPSbDMIzfP/52J19FeW+gs6omWRClVatTVIDuUuxt/krv+pd3frQJj6f6ku4Afn2/7tHktuzHPQWNjXXuk549I6+flIkjz9Y2iMvWBR6PZ5CntniNZjE8c0o/Rd8AYgE2FjjMfa6SsZdFtLyEZKEQv3WBnDzh+1CHYhiGEVYcJwW0+6FvSrKg3UITkGEYbdHgeW8eg9v7jPo5qUkZyDXrs7dbN0o7dCBh/Y9E79hxZAvljQXL7nktUAPm5eX5R18z+QrH5ptamolvX7s3gUatIGg0zPDhC9xW5aavgS51td1Tqn9Ljk69FikcgzKnGcI7oBLkUumftaIZxzQMwCQjG4ZhGIZhGIZhGIYRAL9e8nJ7t99eA7Srs3Ejlaemkp9wBmmfrsKq4DgJQNXiwtLVs5Jjj84SJPbwbTa6ODPT81SgKlmEi5HXTf4S1dRamtw9P3f6Qwf+I33uLAA66Ucze+PS2UgjKyULeeAeL+l3miqIjWTHxXP8P56n9JuvWDdpPJW799Bn5n0knHFmqEMLO/Mue4Ktezbzf2/cSfvYDkwYOJW4iPhQh2UYRhsxePGKzvidwYhchPALX3lZ+wPbhP2P5UUOviMorkgXgzuftYec5f9F5TXHzYv/HnrRmgP7jRg6+XGUiNpHljeyc6fmNjX+wr3pL6TEfPExwqm1jPWr/A2+gcCbTR3PaLwbr8062kLf4rBrgB+3+nkgr6pCckxki0lI3oTPf7GcMvHbupsahmEYASBYZjUYwzCax+Cc5c8I3ssVgv6Hxx8RQfHRx7Kvc1dSv/oC8fsBUKiMSNh9SaDHm/f4tG9HZk6ZB1rjCjSOo2fdmDnltJzcqR8FenzjUFblpg1Ap7pbymvZuVP/lF11hfyQfjn9aXyyEGFwUAMUmYy3Yo6c6ikN6jiGUQOTjGwYhmEYhmEYhmEYRpNcMv+NLpbft7k5xnIiIsg/4yzsCtvP403vLy8vzz9m6JQL/Fp9pb8o8f0dCGil59bK4/FY+eu9a4DeNbfSJdm506dWt0VOy/oRyADQT2a0x2Y6yoVAIhCLSFV5XFUvUALsAl1BtHeyHOPZGdAP08bFHH8iJ/zrpVCHEfY6J3Rlwe+eDnUYhmG0FaoyeNFrV4EOx9FzDiYbN2TqlpAADEJ0kOXjgcE5yz9DrMVdVn34tpaVXVXH3ntxnOsaGf0h8vKu9I+8YeJQ/Fbty7orTw8f7um1cKF5yBoKY26Y1MPvt/4DmlLd9s07HP7vsXJu/X0knVJCnYwm7+Lo7+WUKdWUrzMMwzCaSlRVUadq2tP+9xBHDywVYxiGESSDFz/fGSfqUyAtKLWQa+GNiyP/9DNJ/fwz3KUlCFw8d+7cimCM5ZRUTrRi3TcC7uq2i4jY6D+AHsEY36gyMnNyPtChzobKquxlUy/++VvSb9J2YIh+MTMJR7OBKwManCN34FTMN0nIRqiF+urfMAzDMAzDMAzDMIxW7JL5b3SxXN6NzT2uP9K//fcLXq1HBYK6Pbp06gcgq6rdqAwePtxTWxXgNiN/ve8zkBoTkUVkYXbu9Bvq05ecPHGHpE8cLv0n9pb+E5Ol/8RISc+yJD3Lkv4TI/e/11v6TxppEpENwzAMo1YyZMHycUMWrdgC+jhwTgD77o86c7emD/hsb48etZe3Vf6S/dj0LYEaOHvxjK8U5tbRLM2u9I0J1JhG/Q2/emInv0/eBe1YW7s9Jcq0J8pX+VTmEKS1suvgQ3Uy6UcNlJMnmkRkwzAMwzCMMPLbha9eiBO1BUgLVQxqWewYcDL7unUrzM6dtjJY4yzMm70bnJF1NOs+auiUycGKoa0bmTllHfVIRFbku+xlU0+jhusfOSmrWPpP/IP0nyionA6yuqa2dQ6F/AtbO0r/iSInZz1gEpGNlsAkIxuGYRiGYRiGYRiG0Si/XvJye8vl2wwSivsLts+Srb9++OWEgPTmL/tNTZssr7/NL+U8MnPyS0C/mrYr/H3+0qkjmjEkwzAMw2jzBi96ddDgnOU/qMWDWq9lYhtHbVv2du1O/hlnUta+uuf8sip72bQ5gR7XZ7s8wJ5aY4NZZuJY8xr+J0+q7bLeQ+had2v5xud2nesekHUbLjkD1R+CH+EB+j74+suASdNFrvQ337iGYRiGYRhGsA1Z9OqfbZHXQh3HAXu690wZnLPi/mCOkZ07Y4nA17W1UdWsO+64IzaYcbQ1GRnP2CMzJ38I2rPu1vpdp552P5B6JRfLgKyPpH/WsdJ/okV6pY3yC0T+D5WXUL4BNiNsBD4FfQZlHF7/sdJ/okj/iZb0z/r9/orLhtFiuEIdgGEYhmEYhmEYhmEYrZPbb68JeQzR1g9A+6b2k/34/QUjMqc8JOitR2xUTR157aTfZT82/V9NHac1GpE5eTlwUS1N3luQO+2PzRWPYRiGYbR1wxd87M63di5D+QPNWHTGcbkpPvoYytq3J/nbb0AVoNxb6VwejPEWL/YUjcyccgvo0lqaWVLhfQa4gNBU3m1Txl7lSfC6/P9T6FV3a/nRHW+fNXduVXUuOTHrI1X68sWsS1Anh/osb9wYwneojpb+k94KSv+GYRiGYRhGSA1esCJDVZ8MdRxH0tsHL1ye9MLwi+u1clxjOI7cKJa+S83XgTElO6OXAlcGK4a2xDPQ48qP/fzfIKfV1VaUb8vEfbLH4/E1ZiwRjwO8t/9lGK2WqYxsGIZhGIZhGEbY0tvpobdw0sHXOHor1L688IF9n8HWWzlOb+Hcg69bOU4zsBsVy3DcOo4T9GaG6i1M1FuYqbdwt45llI7lTB1LZGP6NYxQGZyz/DmgXajjAEkdvGj54kD0VFTy3R1AebUbLXmWev79CCcjMyc/LbUkIovIf7Jzp/2iOWMyDMMwjLbs0pzlvfKtwtUgfwrR6hSUJyWz/dTT8MXEANy3+KnpG4I11nfr7SeAVbW1EZHzbsqccmKwYjCqjBv3YLTX7f8A0T71aL7Vdnynz53rOaSytQgq6RNeJL2yM7Z1NuhLgYlOFJXHUB1A+sTjTSKyYRiGYRhGeLpk8etnYekzoY6jRsL1gxe9dlOwul/w2NT/KZpXWxtFM0ZcO+WsYMXQVmRkPGPn9/I9CXJxPZqvrrArz8jN9VT/bMEw2hCTjGwYhmEYhmEYRvjy8RdgxcGXn9lk1PM66GNigNuAZw++lHG0J7qhYehYjiKGPBxeR3gYmALcDkzE4j4sXsBihd7K+eox12lGyzc45/UOwJBQx3GQcn3GkpebXB05Ly/P72jNn2tk5uSnmjpGazIic9IcoOaKx8Kn85dOHdh8ERmGYRhG2/bbea+eI+jn1KsqbXD5IyIp6H+ybvt/Zwe1atPKlR6fhYyqMx54OyPjmUZNHDXqlpHhiSgrLv4Y9Nh6NC/0uZyTH31sZmFNDUQ8jvSb8F/pP+kSLElGnbOBR4Ad9Q5KdQPCDJCTcVckyICs62TApM/EVMg2DMMwDMMIS7975NkUy/G/Heo46qT+hy5Z9MoFweo+GvdIYE9tbcTSBZ6BHlewYgh3Ho/HSon9fCFarwrTP9iO/+wlS+7dG/TADKMVMA+5DcMwDMMwDMMIZ+2oWvr1wCuRHfWsbFqGoMQDKT97xRHXgMqoQpTezEgsvqYqwbEjEAdEAW4gEogF2gPnovybXWTpcGLqPYZhhIT/s1BHcLgKxxWQRJiFy6atAFbXsPmPw4fPagHVoINvZObkewS5tabtAuuyl047uTljMgzDMIy27JJFr1xgu60VIPGhjuUgEVHLemHwohUZwRxmXu7Uj1RZWlsbRRNT4j4fE8w42qqMjAw7Jc63CvT4utoK7MHR9EWLZmyvb/9yUlaxDJj8X+k/cSzpEzuwz07Asbvgl77gOxG/pmNZJ+FwAj5/H9yuTvgqY2XApJ6SPnGS9M/6VE7w7GvapzQMwzAMwzBaNFVxIuPeAVpBgq3YFtbfL1v6VmIwen8o17NLcWbU0azf1h7+64MxfvhT2bbe9xBIfb5+myxc/5+9O4+Poj7/AP55ZvZIyMGRg3BfWvCu91EPECQFBY8WWlTMhiNZsKhtrf5qFtyaoNVaFVByiJBAUSG2Fah41Aqtt+AtBAUEhJBAuHOw2d2Z5/dHUDmS3U2ys7NJnvfrlZcy893v9xMIITvzzPO9MtCDmEJ0NFKMLIQQQgghhBDGsEOHA4TZaCg6Pp7WxGtiwchFJzzA98CQC1VCtNaYZ18fgIbC+ujCfProRa+EJ5dmubqpU4q3piwsa0SxrAzXnWjo4N6UnfnFeYMilUcIIYTo6MYUvXmxwspqgGPMznIKhg3Mz48pev0GI5ep8VvuIaA2YBQdT7ndbrnvFV6UFD94HRhnBx0IHGX4zytYPLu8xYsRmK68v5ouuH83XfjHLfTTWRvowpwv6Nz/+5IueGAjXTRzK511XyVd5K5r6RpCCCGEEKLtuXHBv6cz+Ayzc4SMkaT7vPlGTV9Y/PCjAHYGGkOkP5E1wZ1sVIb2ypk5688EzAg+kvb6fZYr5he7K41PJUTbIRdlhBBCCCGEEMIYCSBcC6AbGraJ3QxgLhouYkwCYxaAZQBOvlFLYNwFYAKPg2wzLKIOAY+anaEpFr/1L+GYp2CJey+IFjRxuocz02VosY2Zpt0xc4pCeLrJAYR9+2vPHQDZ/loIIYSIiBvyV/Ui8r8DwGZ2lgAsRHhp9IJX+hm1wNKl7iMa2BVoDBFR5Xb/B0Zl6IimOWZ+CMb5IQz16cB5BcV/3m54KCGEEEII0aEwMzG46euV0UrBr8Y++/p1Rk3PCo1h5iav0RIoTrH5HjFq/fbI6XA9COb7QhharZB+0YKl7l2GhxKijZFiZCGEEEIIIYQwBuHH91xPQcEwHMUf0RXzaQ4WoxsehY4sKEgHsOGk1yZAhwNpGBzZyEKExNBtuFuHbw/XTGnb1GkAvI0vg1VDh7rbwJaAzTNt0qxRrPCzAYYcTttm6VFaOr6p7u5CCCGECKOh7jUWxWp7H6BoLkT+nt3Clg/HLV9uWNai4tlz+NT3Tie7eMqEB7oblaEjcWa61jL44hCG6hrT+YXFeZsNDyWEECI6MRgg/aRDTAS9qZcIIUSoblrwxr/MztAiDALwpFHTFy7M/ZxIeS/gIKIp0ye7TzMqQ3uS7Zj5OwDuoAMZfq/iHTJ/0eyAnamF6Kja3Y0zIYQQQgghRFRSoKMrO5HaynmSwpImcrwg5NFTyD35BLnhRUOh4wa+B9cB+Bt0DAOBjg25GAqGshubyC0X7kV0GFO4Jrmp+txocfPTbyb98zcj9rd2Hvdat39ahmscE1Y0dn5If1/hWmBya9eJFtl3zLycdf2VAEM8uq1Pintttj9ioYQQQogOLrG39yEw+pidoxm61x/uUgzgVoPmZyg0FToHvOFusavbAcQalKFDcDpmvgzma0IYqrPGlz67JC9YkbgQQoh2TCN9vwLlOwC9jzu8H4AUagkhWsXtdiufACPNztEKZ41d8PrVK6ek/8+IyXVb72GKd2fAC/aaX1vjdrv7ud1uuc/UhKzMnAxi/msoY62K1rNg4WNVRmcSoq2SzshCCCGEEEKISEgG4ynYsLpVHwoWmv2JNIMOYDW8CNRlFABAT6EChEdBqPjxIAjAGNTITXQRRcibZ3aEYDS79nC45sovyVsJYGvjZ2lSVtb9ncO1lpmcDtdQUvg94IeHIU7Cml7rSysqyvZFNJgQQgjRgY0peu0sMP5odo7m4wlGbkVcuDD3fTBWBskQ48xwTTMqQ3s3zeFaAPCNIQzVdEUZUbhk9nrDQwkhhIhqtjrvl6TgbwB9e+zQXiZeoau2100NJoRo8z7tdVkh2nqjTTauO3JRUbaPgXsCjSHi3hXbvcONytDWTZvkGqswFYcytk7XkuctekQKkYUIQIqRhRBCCCGEEJFgBWEICBe28uMcsz+RkDGqAfwLqdgb0ngFn4CwDgAfd/RKEBKMiCdESxC1iS4UYS5+8Y9o6ozitW4M71qRl5XlGgRgTdMj2KfUWrsUlT56OGKhhBBCiA7O7WaFiFaZnaMVSrIKC61GTa7bLRMA1AUcRHgiKyvLsAztVbbD9RiHsPsHEfxM/IuihQ8F+DlSCCFER/H6lDMPWhX9JTBn60wZDJqiQ33mrXG9d5udTQjRtjGUm8zOEAYXjF7wSj+jJi8szpsDwBNoDEF5w+12S43gSbIds65jHS+HMFTzW3Dm4sWPtHpHRiHaO/lGI4QQQgghhBBGIHgBHCI3Qtv66q/YD8YrOPGmejy8bWpbZtH+dTE7QAjCmrGg+M/bQVjexOmezoyZPwvnepHkdOb0Urz4JtAYvdafMr/UXROpTEIIIYQAPu/x5hUABpidoxV6VCj9M42avKjIXUdMjwYZFqP4urflgu6Iy3LkPEDAH4KNI4KfmScVLpq9IhK5hBCioxr1t82Jw5d8e9Xw57dlDF+6fdiI5VujeHcm4lfHn17VzTpwDXtp+eHqA6+tnTBgO4g4+GvNcfnynbHDlm65cMTSb+8YtnTr6OHPf9nd7ExCiBONfe6NiwBONjtHOFhgMbQzMZPlwmBj9uzwLzIyQ1vjdLiGEvTX0ORugQ2I4CdowxYsyCuLUDQh2jQpRhZCCCGEEEJEggbCXgC7WvlRGfHkEUIAg/AVTn6CnTHInERCNCrO7AAhCHtGa/zhOwB4Gz1J/A7AAS9YRqPpt//fafDQLgS4NkSKZZB0RBZCCCEia9zy5aqm6qVm52gtAmZeaGB35PyS3IcA/jbgIObrpt/+f6cZlaE9yXbMnK6AZocwVNOZ7y4onr3E8FBCCNGBjVy8JdVLlkyo+hxAnwlFe1zX+N6RL5RHddOC0vGkrc0c4Pk4+yKf2VkCGV5SlhSn+W5XCPOg8ExVwaPMne6/9sXNch1WiGii8e/NjhAuzDQLbNw15MJF7o1EFHDXEmbc4ZzoTjUqQ1uSNTHnSgBvIHjdpObX8Yv84kfejkAsIdoFi9kBhBBCCCGEEB3CXjAyUY9PWzWLBX2hYl2YMkUfDXuhwH/SUbkILqIHkRUctU1tvmcL94Tz5s2rdzpmTgP4ucbOOzNmzS0owYxwr2sUh8PdRYd/c4Ahum7TexcVuSsiFkoIAyhKm3tOwDAKye+FEG1F/b6E02BFmtk5wqB3b6X/jR8DLxm1AEFxMHgtmr6BrGiq5Q0AA43K0B44HTMdAD8dwlCdgZzC4tnzDQ8lhBAdnG5Vz2TWJxDofAAAgwlKDz8djRn5QvncNyb02mlyxDZreElZEuy2X7HO9wBA5+TRAAAgAElEQVQ0iLnh5wgijmVd3Qhgq8kRhRA/Ctrtt60gcL+bn/lnt38C+w1bg9VbGf5dANQmB6m+99HB7zllTZx5qaLyvwEEe3hWZyLHs8W5KyORS4j2QoqRhRBCCCGEEJGgQ8FBKsDe1kzCv2kTXVlbowqAdsIRgnTyEqI5DNoCtKA4d6Ezw5UHQo9T1+TfjBs37p7S0lKtkZdGlUmT7kuw6f6A34v9Fpy2oOhhKUQ2UKxNLslFQif5fRZCtEFkoT9H/aNfIWIgCwYWI+cX5749LXPmf5l5WFNjiDBg2qSZzvyFuQVG5WjLnBkzxx974C7gUyvMzAqUvIKS3EcjFE0IITo29qcCNPC4b88E4jQC3e7HUYwo2TrvzYxB35kZsS0aXlKWBJvl16zhHiIMwgn//lEKgeUBJiGixLjly9X6w+hrdo5w8lvjUmBgMfL8YnflNIcrh4E/Nz2KBjonzRxfsDB3uVE5oln2pJnnQdf/A1BM4JHMIJpeuCj3b5FJJkT7EazduBBCCCGEEEKISJmHajCOnHCMpRhZRBHmqN5mE4ChGRUdw5s6lxT3k2+MWjdc7nG4u9h020EE6PpAoKsXLMjbFsFYQgghhDhm3BPLY5noJrNzhNF1oxauTjFyAYtXvQnA0UBjWOOHJ068t70/2Nps0x05Y0D8PILfK2QFyl/zS3IfjEQuIYQQAOnKfgKdWGzMIADdCXS7buMZI0q2tqsiPaP9UIisK40UIgMg2s8EKfAWIkr4DnU5B4Dd7BzhRMRDjV5Ds1nmAdgdcJDO+ePGLW+6e3I7le1wnU7M/yVQ0PeGDOXegkV5hZHIJUR7I8XIQgghhBBCCBEt3CDQSUWCBK9JaYRoTK3ZAUJQZ9TE85fklQF4q/GzNHDalJlRu3Wge5zb5iF/JZrepo91osvyi3PfjmQuIYQQQvyorkunU3dgaOOsusXQG+7zlrqPAPRkwEGErnFqjNxIPk6244HrdNDfEWgL52MYnJ9fkvuHCMQSQghxjN7J/hnp+BsBO084cUJBMklBcoiGl+xKgs3edCEycIAY/1JUrDYjnxDiVLrC55mdIdyYyPBi5KIidx2xnhVkWLekuC/yjc4STbKyHuhBwIdgdA42lpkfLCzOfSISuYRoj6QYWQghhBBCCCGixVEkAIg96ehXZkQRogmHzA4QFLOhGa0JqaMBaI0u7ecPjVy7pdxut6Uyzl8FbrqbCENJL1qUG5X5hRBCiI5C0dSpZmcIO8YvjV6ioDg3B4x9QYaNd05+4Gyjs7QF2Rk5VxOUlQiwW8aPaGFh8ew7DQ8lhBDiBP+5udcBNVZdxuCnmy5IhhQkh6ChENn7a9a56UJkwjJW+OkrNy7ZZUZGIUQjmAaZHSHciPicSKyTX/LwagbeCDyKHb+Z6BoQiTxmGzduejx5lY0AugYdTPhrYcnsh4xPJUT7ZTE7gBAifIgAhU5+/yTaCvmjE0IIIQTqkAzllM5Um03JIkQjmPEGEbLNzhEIE940cv558+6qd2bO/B2Y5zRyWnVm5jxasGj2/UZmaA73ULelcpt/LwiJTY1hxqTCkof+HclcHYE9NbYah3RU19bh801bzY7Tpuw/eAQAYLEE3zEy1m4DAOys2IslK+TLuDkOHqkBAPzhjjsM6ygvhGgummx2gvDjdLjdCtxu3dBlLNpN0NS3cWqB0fes0JQSAFG7k0UkOO/IuYSJVgOICTaWgOfzi3Pb4dekEEK0AUT8OnNl+j92LPHX+0Gg3zDQ54fzDALx9x2SMaJk67w3MwZ9Z2LiqBRyITLhqf/8auDm/5CbzcgphDgVMVK5vdVPMPUJPig8K6nEU3Sm7WiySSlZ/SpKAFwdoUymSerUrQJAfLBxzLyosHj2vRGIJES7JsXIJiECrBYFkB9n2yyKwr7iqkLoZJe/1kIIIYQQTSIQhgJYa3aQJijohpPfpzG2mBNGiEawzQXyRnUxssVPOUavUbAod67T4XoQQLdTTjLd5x7nnukudXuNzhECquzv345AXR8IzsLivEWRi9RxuMeP9z5Y9Px2T723/5oPPzU7Tptjt1mR0jV4w5KkLp2RltwNlfsOYP+hwxFI1n4QEQOYC7lCKURUGOpeYyF4U8zOYYDOY3tdmbIS2GPkIgXPPfKu0+H6BIGLjS/IznBNLizJe87ILNFq2h0PnMsqvUGMuGBjGfhHQXHu7UBeJKIJIYRojBQkt0pzC5HR8P5ICBElmPjkHSTbg4RILTR/0eyd2Q7XPALuDjDsquw7XL8sXJz3UqRyRZrT4fIihB1hmOmVwpK8SRGIJES7J1WLJrKqUVjNKoQQQgghRHvCOHzCZWaGDfvRCcARsyIFcToA23G/ZvilGFlEj1XZw/aNffZ1s2ME9M9p6XsjsQ7p+jBWlM8bO1cZ5/8CwJBI5AjE6XBtA9Cr6RH6rIJFDxdGLFAHRLstg5Ve7NR1/SctnSPGHhN3er9ejnDmakpN3VFsK69AXGwM+vXuccI5za9B58jcm4212zFkYF8oSmgtcIZddiEOHqmG1+szOFkDIoLdbj/h2CcbNqGyaj/OH3I6+vVMi0iOTTt2zNj07a6NLX09E75zT/2V/JwhRLTot90Cf0+zUxjE1x0GFyMDgNVnudZn9R9C092RQYSHJ06898UlSx6vNTpPNLnzjj/+RFOUNWB0DjaWiF7dX3POeECKsoQQwnShFiQzJupW+Ecu3vLkG3ecFpHrItFs1N82J3pV701g/i0RBkIKkYVoc0ghjfV291fTH8nFCovz7nE6XBMApDY1hgj5WVlZK4qKiiJzUS1CsrKyrKo3tYJDKEQG6D+FJbk3GJ9KiI5BipGFEEIIIYQQ7dnWE35F6HSs+3DwYuROIHhOKAxuLiuAOG7YGCXoVTOehAQAo4ATulQdAGN/KzIIYYRSAOPMDtGY2Kq9cDpcDGCJUmuZPr/UXWPUWvmLH/7C6XC9DeCqRk4Pnu5w/3R+sfszo9YPxulwfQ6gX1Pnienx/JKHcyMYqUNyu8d70dB5tlX2VddfCdBpYYgU0M6KPdhWXoHEhHhcccG5J5zzeOqhaZrREVqsa2LEmstAIUJspxMb9Gzc0lCc3LVzAnp3N76xKTN/89PTej1t+EJCiIhJ8CYrTW2g2+aR0iUSy8xb6j6Snen6MzH+GGBYapxqfwzAnZHIFA2yJt7fV1MsbwN86q4ep/rfvhr1ptLS8dH7j74QQnQ0oRQkA90JlK7blA8ArIhErM2bN9tjY2NTiCiVmbsqipLAzHYiUplZ13Xdq6pqDREdIqIqAHvT0tIi8jCQh+h0ReeboNBAMEshshBtEOvc7ra/YsK+iK+p812k0Ato6oFNQrLiTX0AwJ8iGsxADoc7RqnXvmTipBCGr03rr440PJQQHUh7vbQlhBBCCCGEEACd0lW4CwJ2CT2OF30ReIvfYBIApOP3COWCB5CAMwFchBPfp70NDfWtyCBE2DFwv9kZmtJ527ff/+9EPc5fnZ3hKp0+zh1v1Hq6zfJzAHqj5+D/FAG68hlpWqbrbQDnNnWeGX/LL8n9QwQjiVZixXYNAK/ZOUTU8KLeP9TsEEKI8Irxx7fb+zWsn/DApaEKF+U9QBS049hU58QHzo5IIJNNmfJAd0W1fgBwk93QfsC83gNLemmpW37mEEKIaEPEr9/Sr9Jityxh8NME7Dx1kJ4KTR9oVITdu3cn79q1a3h5efmM8vLyeXFxccsURVmqKEo+ET0B4GEADzGzm4j+pCjKbGZ+nJmf0XV9sa7ry3fv3l1UXl5+X2Vl5Q0HDhzoa1RWhdQUEAZIIbIQbRnvMjtBuBHwTaTXLFw8exkYwRpmPHjn5Jwmm1q0JQ6HOyaG/W+DOISmDvR2Wn/LdW63u9Hr+0KIlpHOyEIIIYQQQoj2i1EOQj2A7/dS7wvGMM7CR1SEJredYgdiwHgUx3cZaT4VwC3Q8B6AZwLGdKMTDuIOAKf/cLDhBvoq9ISnFRmECLtVU9O3jX329UoAaWZnOZ7qrYfiO/GvNRF+qcf5f+nMyHm1oGT26HCvWVTkrsvOzHmQmBrtMJzlcM0qKs47oavEYx9tSLMT5RGUa/319VCsFpDSUHvEmg7d78ecO2/7FuDXVT3R9ZtLezerO7ozw/UeMy4PMGR1YUnexObMKcyXEke7qw7XZxzrZCI6OA3Krd1T4irMziGECK/6mCMEPcbsGIYglULYGjd8WOOfQaEPmx5BVqg0H8DVEQtlgnsc7i4ev/9jAD2Cj6aN8bpnaMGS2fL+UwgholWwDsmgA7pKYS3e27NnT3dN064EcAWAsxVF6Q6gG4DOaNjdTWVmENGxiD/W/h7//8foAI4qinKYmQ96PJ6q3bt3f0NE76uq+k5qaurJTSVaTCffQVVXy5lw1nGHpRBZiDaEmTae+m2kjWNeZ9K6YwDaDmqyRpD8GhUx88+pDX9vnDFjht1X7X8FhIuCDia872F1pNvtDvYgqxCimdrtk/ZCCCGEEEIIAUIVCJuOO2IFcDticCXPgJ2P61rKAPG9iOMZOBOd8SoYo9D6rqYxYMzju5DDM5DCWfjhJjwziB2I4XuRioN4FsB0NBQwN8RhfAjGu+RuvOuqEOZSf2p2gpOlfBagwQPRKKfDxdmZrpJwd0ouXDQ7D8CBxs4pgNvtditzPth4+pyPyv4xZ10Z20mpAGgygweodtsPhcgAQKoC1W4DgAEAOTWlet+cdWU8Z/2mZU9+WtY/WBZnhqsU1HQhMoFWFRTnXd/8z1JEg5TO9heh432zcwhzMePt7gmWv5udQwghmkXTIrpcweLZ60D4Ksiwq5yOmb+OSCAT3Dvx3jgP/F8ghJ2BCNhm9amXP77k8doIRBNCCNEax3VI1oEnAPq64QTvZPAyn6Ktbe0Sa9assVRUVJy5e/fuP2qathBAHjNPAjACwHloKIBOxI/XMUOlAIhj5p7MfBaAawDcCsDl9/uLKioqHt29e/eVGzZssLX2c/B26rqRgcUAvgAAAlVAoUVSiCxEG8I2cwp3DUWvm7FqweLZ5aRgSaAxBIx0TnFdFalM4ZaVlWX1Hen8EoBrgw5mfBzv73xdcbFbHsQUwgBSjCyEEEIIIYRov3RsB+MlAEePOzoYhBehIgd34zaegTF8N36BuzEJfjwBBa+CcU1YVgf8aChozoWCVYjFH/gu/Jrvxg24Gw50wSz4sAINF95/xDgCYBG6YnMYcggRdiunjtgDYIXZOb4Xs38fFF/w3aSJcYce5692ZrqW3TvxL2HbLlwjHtPYcUunWHQecZMfKn0Dws0tXoB5vOLHtqfWl21++sOypMaGOB05z4Hwy6amIOCz/OLcsS3OIKJCUqL1WoArzc4hzMHgipr95SPNziGEMIbdk9h+i2IUCv6DWngx/J7hQUcRz3M43O2uHfWMUTPsNUrsRoSw0w8DFfD6L5y31H0kAtGEEEKEw7GCZB3+vymgbGYarxBlqmRb9Pb406taM3VFRUX/IUOG/B5APhHNADASwBAi6oLw15YQgHhmHgTgGmaeAuDJrl27PlxeXn5BayZ+98aU6npYVus6TwfROKiUSQrPlUJkIdqOVdnD9oHQqu9p0Ya8JzTOiaj8RXmTiQI3viGN/jFj1Ax7oDHRaNy4cari7b4UhBuCjSVgg273DX98yR/kQUwhDNJUC3bRAnsAHN9eiXWAWX6W7aiO/5NvzfYRFvXH93X19T5UVh2AoshzBB0NM+Pg4Zoff63r9UkHDjS5tbwQQgghGtA81PPdKAXhl2Ccd9ypVDBmAvBCQQ0AGxhx+L4TMgEgeMHYC6B3C5evAPAhgBEgJAK4FMClIBwFUAsFiWCc2umDwQDm4iheojnSFVlEr5VT028a++zrh9CwNadpCNiV/N3mMzRgCQE3hfQixvga9fB4p8O1Ohydgp9dNPs9Z4brKxDO/v5Yn+uvQXz/3scihgcxTtMU7Ju7rmzxXRefkfH98WmZrmJmZDT5QuYt84vzLsgvzgtXFGESIvLsqan5qcq2CoTxa0u0CeyH7bwBAwZI1xYh2imPpUanRt4etA9KdaRXLFjy+N7sDNcjRPhjk4MYyTHQZgLIiVwyY40bN071xXX+GuC+IQw/wPWWc/NfyDtoeDAhhBDhRcRrgX1uN7+9qsfH6piKCzW3m1p8HXHLli2pnTp1Gqnr+i8URbmEmdMQ2cZ2CoBuALoCGAjg/F27dv1L07QV/fr1+7YlE75zW7+DYH5v6FqoKVXg0vEU2a0ahBDh8C2AFLNDhEvXTjYzi6uZdIxiQqDuzEm+tMS7ATwWqVCtxWCaHj+zmJnHhTB6O2K1q4ryHz1sfDIhOi4pRg6jv0ycWPfQsy98wlAuBIANW7Zhd9V+s2MJEzAzqmsaHqSxWS2w21v+8FB8XBziOsWitu4o6jwevLj6rXDFFG0YkfrnB91uKU4SQgghQtEVm3EAvwehGKcWFtvQcKH71JIuxpNg+EEtvjF9EAoeAeMTMB7CjxfwYwHEovHnFj0gzIaCv1LRCd2chYhKPlU73aqpe83MwIrnzPnz3TUAbp406b4Em24rwMndxps22ulwMYCSeM1zZ2u2pvaq3itsuu2QGhujDLptDFS7ccVEDNwxZ13Z9UfJNmjHvOLfMXPThcjAFwUls88rKJltWB4RWd3j4/ccqPWP0XX9X2ZnEZFDRKN6xFO76ggkhDiRv17VrLFmpzCGynTAjHU71dXmHo2Lux8Bi6n4/7IdruLC4rx2sStNt7jBmwH0CzqQUOP36GcueMG9z/hUQgghjHKsAFn/uIWvX79+vTU1NfU8VVUdzJxORL2Z2cxdAwhANyK6ioh+QkSXVlRUlHg8njUtejCzoWjbH/6YQoiI0Gk5iC81O0ZYEF4rzhxm6gPm80vy3nA6XN8BaPrBRaY/Dx3qfmLtWneb+N45LXNWERi3BxtHQJVXtV74XP5seRBTCINJMXIYERE/VPRSBsO3HqCY2qMe1B6VZiUdXVKXLuiSGB98YBMSOsXijIH9sP4r03ZsENGGsYa70iNmxxBCCCGCqAdw/Jv6w+AwXPhl6CfNWw9GwB+6yQ0dwH94Os6ABXNAGAMgBoAdgBUNF7k1MHwg1ALYBAUPoTPewmHcCR0/3pwlVKOmiTLihs9v/7G5AWAvgAp6CrN5BlaD8NdjXVPjjq2rAtCPFTzXAdgMhhsV+DeVQjp1iDbh1Umjq27I/09vxeL7DqBIb+GiqX70/Oe0G3/otLdw4WPVAG4DcJvTMfMNgK8Lca6MGjUmw+lwvVireaYsaUFR8sKFj1Xf9bvHXhg0YcxtzX1tCyXFsveQGmeHv67xb4MEVOUX553X6EnRpnWLs7yy90j9wwrRA2ZnEcZjhXKT46yBOtcIIdqB+LQaf/1hUzecMIzXF1NpxrpPlj55NHtyzjDS6L8BhikEFAAYHqlcRnE6XFsADAhhaL2FLIMLXnDvMTqTEEKI6LVnz57umqbdCGACM59HRF3NznQcK4DeRHQDM58WExOzYufOnS/06dNni9nBhBCRY+/S6+n6Q7seBbX92rbkDV9e6syY+bOCktx3zcyh+/XLFIuyO8AQGtLP9/FaIOqvKTszcuaAeUoIQ49afJbT8ovdRwwPJYSQ7RyN4F7w/BTo5AIo+NPnot2yqCpSk7ri4nPPQKeY1j9Aur28Elt37EKdx9NE9Uv0UqjpbzU6M2rrGpr+ERFi7XZYVDVS0cLC4/MerPf6Dhm9DjFqAfrIovofck25bYfR6wkhhBAtxQBhBgZCwRk/HFTgAWM9PYVW/ZvJWeiEWFx73GI6/PiG5iOkC9H8W8TCj/NAGAwFA6CjDxSoYFQD2AXCh6jDp1SEw8wg/B694T+uqxShCruxpbFiYb4PCfDgHHzfdcuCauxEGZXCCwA8A3YoOBfApWCkAegCggeEvdDxMfz4kOajphW/PUKY5ob8//RSLP5dkVzTTpxUOuXnAbvsTZp0X4KN7UvAfGNz5mbQK4XFuTc05zVzP9/cm73+HYjsNqZgZmxe+BI0j/fkUwf3156bUlo6Xh5uaMeqjnjWEClDwzXfzoo9WLH2XfRITcb1w352wjmPpx6aJl9OQMN1jthOJ7YvffPdddi+azeuvfQCnDmwf9jW0lh/q3tiTJsvkBNChGbMs69vJBz3PqodYEb5qqz0k3eoiSRyOnI2AjQk0CCd/elFJX9+o7mTH9tlo0kFxXkRuQ83zeH6lIGfhjDU69cwZMGSvG2GhxJCCBG1ysvLBxNRFoCbj3VDtpqdKQANQBWA/wAo7Nmz59sm5xFCRNDYBa9/A8bpZudoFWb0+OA9kK6DgKMa6NKi4twvzYrjzHTNB2NaoDE647SikrytIc1nwnsi5x2uh6BgZihj99da7KWl7lMungshjNHmnx6JSrt6FKPnnv8B2gU61O5Gl1Xa7TFxF5552iyFFLvBS4VNTd1RfLXlW/j8DTexhgzqjy6JCY2OZWb4/X4wt50SXCJCl4R4dO2cAKslPH/N+vdKQ8/UJHh9be/3wm63QVEavx9fU3cUq9c0PPxlURVc/tOz0DM5KZIRW0WDXvvpps1jyr7daXwXCVY9OK1bpWvYsDaxJYYQQoiOiwDGPGwFENKFimbNXYQ6AC3elp6exFEAHxz7ALsbigaPdU8+cSyBAew89hF87sdQDeC9Js/PQz2Adcc+hGhX/jVtePmohatTrZq6GYCxLf0Y5XaFzw1WiAz80Cn5phm3uRN9Nn8BGBNCWYLA1zdcROXiWq3+N8E6JT/1wZfd2esP6XtFuBERfjJ5HL5ZUAqt/odrqnsKivPSzMgjIislMWbYviP1m0A02OwswhBlUogsRMeiEJ5mxjNm5wgnIl5lcgTWmW5QCJsRoEGPAkvpjBkzUufNm1cfwWzhQM5M1xvMwQuRGfBarHRBQXGuFCILIUQHtW3bthir1Xo5gGw07AqQ3AbuO6sA0gCMBdC9vLx8YXV19b+GDBlSHeR1Qoj2YQqAQDudRL3E77aD9IZbUAzEKuAvpjlctazTVWkD1c/dbvcp96eM5CXv/XbYpjI3XTOoAJ8BaLyIy2TOjJy7QCEUIhP8unVvp9LiIl8EYgkhjpHOyO3EvmrvNABz0LBlSdSrOngIK9a8A8+xG6XpV1+OPj1SGx3LzPB4PND1qH8jJBpBRIiJsTdZjFxdU4tlr7wJALBaLBh11WXom9b410K0IcALxp1JibYFZmcRQgghhBAiWox99vWXATSrE3Ho+IWVU39+a2tmcGa4/g3CiGa9iPBCrd8ztami5Dnryg4DSGxNrtbSjtbjm4UvAcDRtP6W+EhfxBbmWc9s7V/j3Q5Qz9bOJZ2RQxOZzshcvv1r24CLLiK5YSJEBzJq4eoUq6buNTtHOBHo+hVTR642O4cz0/UEGL8NNIaA+/KL8/7SrHlN7ozszHQtA2N8CEO9OtHVRYtyPzQyjxBCiOh16NChrkePHh0LIJuZzwEQb3amFvAQ0RZmflHTtOI+ffqUmx1ICGG8G599fT8D3czO0SLMSFv/ERRvk415K1mnW77+Tl23dq07Yk3pshw54xTQ8kBjCJyTXzz74cbOzf1gcyKRlgQLXXLgq29ejEnpBmtCPNQYGwBA83jhPVIDT9UBdDn79PGs8jpvLe2//8rWPUgyLXNWJrO+MISh9Qrq+88v/ktla9YTQjRfRLcOFcYhb/VSYv6P2TmE6Eh01t/U663LzM4hhBBCCCFENFk5Nf0mQE0DEM4LfXsBNa21hcgAUFCSd51X8SaCmtFlnTEhTo2pcWa4TunsN+ejslUwuRAZANRYO/qMvro+tmu3JClE7lguIvIdrLQNBOOg2VlE2BxIircNlEJkITqevb6dh8BoP7uiMaPLpi9q3G636feidKvvTwDqAo1h4LEZU9y9IxSp1ZwOV0Gohcik4HopRBZCiI5r9+7dybW1tbczcw4zXwyDCpE1TYPX64Xfb9iPMzEAziCi6aqq/m737t39jFpICBE9CMovzM7QUnEVFYEKkQEgjRR+74z+/m+y7nhg2Lhxy9VI5OrZ3/p3gDcGGsOgnBm3zfjhuveT6zf2mLO+LGPOurIyVv2HdYW/1XX9xS5nnoaYlG4/FCIDgBpjQ2xqN3Q96zQQ83LFj20xdj4yZ/2mL+asL7v1qQ++7N7czNmZOROY9eeCj+R6Ju0CKUQWwhymXwAS4ZGUlHSEmR4Eoa1tISZEm8RAPXRlVkoKyRZAQgghhBBCnGTl1BF7Vk5N78HAQAClLZ+JSjXVN2jl1PTuK6eO2BOufAsXPlZdsChvjNVn6QzgxdDj4Aanw8XZma6FWVnuTo99tCENhBvClau14gf0sf/kl8Ojcvs8YazTT6f6pARrT9ZRY3YW0TrMqK6Ot/YiooB3qoQQ7dPH2dk+KGhWZ95oFrtvH2L3H/rvnu3+L7In5lxkZlFyUdGjhwmKI9g4r9//bDQUTwczbdKsPwPIDj6SfdD51/kL8940PJQQQoioVFlZGQfg50R0J4DTAVjCvQYz49ChQ9i4cSM+/vhjfPHFF6isrARz+Hc+ZmaVmXsCmMDMmTt37myb3VKFECF7eep1awFsMztHcyl+PxK/2xHSWAYGKIryVlL8FxucmQ+kA2zoDitut1snVu7gwN+oO/lsXV58Yt2GS+asL1ulMO0GoxjAkBYvzHwOGEtJtVQ+ta7s73M/+fq8UF7mnJRzMzH9DUDA3xcGvArh2sJFjwQstBZCGCfqL6iI0CV3tn1EOqYBUpAshJEY8BApU1K62D42O4sQQgghhBDRbNXU9G0rp6aPXzk1nVi3pTCjEA0Xjg8C8IKIQcQAvMeObSNGoWpTk1dOTaeVU0eOf2XSDd8alW/eUveRguK8CQ3bZ4e+2xAxMhWvv9bm06LuIrjXZvvM7AzCHETkSU60pkiH5DbtQE2CNXUAkb0EBtEAACAASURBVMfsIEII8/jr/XPNzhAu8bsbdk5n4CxSaV3lDv8nWZkzLzWr2De/+E8vAfg80BgCfr5nu++SCEVqkWmOnAdY1+8POrChy/bkgsWz/2l8KiGEENGKmS8hojuJ6DSj1qitrcV3332HXbt2Yd++faisrMSOHTtw4MABo5YEgO4AblVV9ZdGLiKEiA51unK+2RmaK3HbVpDWzE7xjMFg5TWnY9ZXzkyXoU0w8ktyPyZCSVPnbV07o+/Ya0epUD4Eh78hBwG3sKZ/Nmd9WemT75f1b2pctsM1GhotR7AaR4afSBk7f9Hs98KdVQgROilGbme6JVhLiLDU7BxCtGe6pi9JilOfNzuHEEIIIYQQbcmq7GH7VmWlO1dOTR+4cmp6t5VT0+0rp4xUVk4Zqaycmm4/dmzgiqx05z8zRuyPdL6C4tkjqn2WzgysDmW8NSEeZLPGGJ2rBXo8/clG2aa0gyIiT1KCtQfAFWZnEc3F5Unx1h5SiCyEWH3n9ZUgesfsHK1lramGteakTeUY5ynMH1Tu8K+fmplzReRTEUOnTAB6oFEMemXGjBn2gFMxU+H6r5Pt3TqjU89UxPftiYQBvZEwoDfi+/ZEpx6psHfrjKfLypLA4etq5syYeReDZocwVCPiGQXFs5eEa20hhBBtz3fffXe2ruuTmfl8ZlaNWqeurg779++H399QdKdpGo4cOYJDhw4ZtSQAKEQ0AMCt5eXlI4xcSAhhvjezrzvMwBSzc4SMsbTT/qoLQPRqCyc4E4xVzgzXl9mZs24Mb7gfqbp+L4DDJx/vftVFGHTrDYjrnWbU0j9i/FKxYNucdRvzTj41fdKsYUT4ByhoV38NzOMLFj30ukEphRAhkmLkdoaIdNb5L8wwrHOUEB0a8xZFweNEFPCCtRBCCCGEEKLtWbrUfaSwOO963ebrwoRlgcamXh7SDnKm8GvUbrZ3F81HRPXb4239wPy12VlEyMqS4m39ichrdhAhRHSw+jHJ7AytlbBzZ9MnGeerTO86Ha710xwzr4pcKqBgce6nAJ4NMqybr6bL1JMPPrl+Y4+n1pX9Ys66TYufWr9pr4f1qoETbkC/m69DnzHD0Hv0Neg9+hr0GTMM/W65DgMn3ACtBvvmrCurmLOubOG89V/flP/5ltSWZp+e4ZoM4qdCGKoT6L784tkFLV1LCCFE21deXt7HYrFMADAaQOCHbFrJ5/Ohvv7EzZv9fj+8XsPf4lgAXARg8s6dO88xejEhhLkuLH9/EQgvmp0jBF+X8/bMgudyPy1YlDtag34+wP9u0UyEs4n1l50Zri+nO2aNCXNOPLP4kf062P39r61xsRh0+1h0O3dwuJcKAeXMWVf25cOffJICANMdMy/WdX01ONi/YczMPFF2hBEiOkgxcjuUlGD7GkSToOvN7PcvhAiEwF4FiiMlMeYbs7MIIYQQQgghjFNU9OjhwkV5vy4oziMAbzU2JvH0JneOMx0B48zOIMx1EZEvOdE+RGd9rdlZRGAa628lJ9jOJCK5jieE+MHfnSM3A/QPs3O0lK36CGIOhLTRxYUM/p/T4frQ6XANNTrX93SbxYVGun+dgHmuw+Hu4mZW5qzbcOOcdWVvKUy7CXgJ4IkEJIe8IFF3AJk66//0en175n5U9trc9Ruvb07H5OzMnAk6oQhAsNcwET2YX5z7RMj5hBBCtDuVlZVxANIBZBBRV6PXIyIoyqmlJ0Rh2xwgkDgiSldVNePQoUOGf65CCPO43W7d11NzAPjE7CwB1Kj1tT/7ODvb9/2BZ4sf/qygePZIRcOZAN5u0ayEs3XoK7Mzcr7OynCNDFdYAOjZ3zoX4E3x/Xpi0MQbYeucEM7pm+vsOC12258Wrpygs/5fACHsTKhMKSyZ/YLhyYQQIZFi5HaIiDglwfpfED0IQn3wVwghQlDPjJndEq3vmh1ECCGEEEIIETkFxXnDrT5LZ/CPW+qpdpuZkULy+PqvQy+QEe1WamLMMIBD2cpdmIDBud0TY4abnUMIEa2U6UAbvL7PjM5btzT3VZcAWOPMdL3nzHRda0CqExQVufcx+P8CjyLqc9nZ/+yyftMeQHkZwLBwrc+EdGb615z1m8rnfLxpfLDx0xyumwi0GCHd0+NH8hflnrK9sRBCiA7nbCIaD6BXJBYjolMKjxs7ZqCuRDSypqbmukgtKIQwx6ujR9d77Lga4OhrIEfw+lRt4D9/c0ujT2bOX5JXVlCcd7VP5f4ArWvREkQ/UQivZ2e4dk7NzLmidYEbuN1uve8t6f/off1QkKqGY8rWiut81qDnEwcPiA06kvnuguLchRHIJIQIkRQjt2OqVjcfzK+ZnUOI9oFfUfy2QrNTCCGEEEIIISJv3lL3kYKS3NG6zdcFhOUpl55ndqSgrLouBagCAJCcYHcpijIaAJudJRhmwO8D6j3A0TpCXQ2h9gih5jDhyMGGj+pDhOrDhJojDee99YCuRzho62+oMxH9PCXBPisccYQQ7dPKqSP2EPEks3M0V8zBgyuttbUhtUU+BeNyMP7jdLjeNboo+UDtN88C+Lyxc3F90jBo4lgkX3jW0GZ1QG6+HtB52Zx1ZZ8/8eGGqxob4Myclc7AMjAswSZj8BMFxbNzwh9TCCFEW1JeXt6HmW8hosvMzhJJzHy6oijjKysrzzE7ixDCWG/ckV5rLz9yDkBfmp3leL46LfHVSaOrgo177rnZOwqKcy9RYOkB4IuWrEWE3irTu9mOnCPZme4zWzLH9576cOPkuB4pf4zgAyRBkaKg14grENe3R9ODdLgLSmbPjVwqIUQoouc7iTDEzsOHu8Ui5n0o9BOzsxyv6uAhrFjzDjz1XgBA+tWXo0+P1EbHMjM8Hg90PervmYlGEBFiYuyNbs0DANU1tVj2ypsAAKvFglFXXYa+aY1/LZiGUVatWa8Y0JUOmR1FCCGEEEIIYb456zZtBXig2TmC2Hb3xWdEe0YRQZXV1akWxHwGcJNX8XdW7MGKte+iR2oyrh/2M8MzMQN+L+D3N3x4aoHKnYzKXYzqw4SjNUBdDaOuFqiraRhriwHsMQ3/TewK9DsN6He6gm6pgNUOWG1AE5cgDPXmu+uwfdduXHvpBThzYP8mxzG4wg/beT0SKOjNKSGEcLvdyie9L18Kxq/NzhISxqsrs0ZeP336n+K0o5qTmB8A0Jrt0t8FYVbBory3whXxeNmTZl5OOr+LY/fKSFGQds0l6HLGwHA8eNI8DA2EuT22ffmH8ePHawAwLXPmNdzQcCaErYlpfkFx7p0GpxRCCBHlNmzYYOvates4Zn6MiHpGat2Kigp89dVX8Hg8PxyzWq0YMGAABg8eHKkYAHCQmQt1XX+oT58+RyO5sBDCHGMXvLYCTGPNTcEV9s5H+pQe+zm+ue6e8kD3ek19C6yf0Yo3InUq0yXPlDy0EaCQi6ueXLdxhAL6dwvXjIhtpa/Cs/fAiQeZni4oyZ1hTiIhRCBSjNwBVB72XmZReBlAfc3O8j0pRu442nwxMvMOqDQuOc7Wom0yhBBCCCGEEO3PnHUbDwDUmsIawxHh4F0XndHN7Bwiumxjjkms9r3JhEYrjSNVjMx6Q/fj6kPA9m8Ye8obipD3lgM+b/Pns8UA3XsRBp0FDDmPGgqTbeHPHUgoxcjMeLtmf/nIAQMGeBodIIQQjRj3zPL4envnd8CI9q0ZvoXi+enKyTdWf39g0qT7EmyabQoIbgCJLZ6Z8b7Oek7R4ofXhCPo8ZwO11IAt1oT49F3zLWwdUkI9xLNw7yxHjz826ef78sKvUVAXNCXEBYVLsqbjDawC4IQQghjVVRUnAXAxcwRfZApioqRwcwfAJjZq1evNyO6sBDCNDcWvpHNCs8BYI/w0hqBHl0xdWRYdie5a+KDfb2qthLAOQBa9Kg9A3tU0Jiq2k2flJaWBiyOfmr9hr7EylYg+C4sZmK/hi1LXoa/ruHfGGIsyi/Ja3O7CAnRUZjQJ0REWlpn2wfQ6VHIhSghmouZ6BEpRBZCCCGEEEKciIIWhZiNOXjhiuh4BhB5khJtVxKU8QBaUPbbOpq/ocNx5U7g7VcZpUWM1S8wPv4fo3xbywqRAcDrAXZuZby9mrFqiY4N6xm11Q3rRQmvBuWXKYm2q6UQWQjRXKV3jq8Bq+kAfWd2lgCqFF0beXwhMgAsXPhYdUFJ3pNexdubgLsA1LVodsLliqK8le1wfTDNMfOqcAT+nqprd3XqnXZk4PhR5hciAwDRmTYoX8b2SP53SIXIwLIDNV9Phdz/EUKIDq+qqioBwDBmvs7sLGYiorOJ6JaKiooUs7MIISJjRfbIQrvXlszAR5Fak8E7dJ0vCVchMgDMXfKn7wqK836q+C2DCdSiGhUCuuvgj5LihnyTnZFz9bhxy9XGxrk3bLARlFcR5YXIAEAWFX1uGAZSFIDwfH5J3mSzMwkhmibFyB3El59YiwCazUT1ZmcRoi1goF6Dlpscb11gdhYhhBBCCCFEdCEiq9kZgmkLGYV5khIspaxY+4N5c6TW1PxA5S7Gm/9gvDhfx3tvMKoqwls3pfmB8u3AGy8xXlvG2LGZTS9IZuZv2OPr3z3B8ndzkwgh2rKVU0fs0f31VwDYaXaWUzD2+sl/8cvZo7c2NWThwseq84vz5nkVb5rO+A0RWnSfgoBLGfw/Z4ZrXfakmZe3PPSPhsxwXNJv7HCbYo9wS/0AiJDc98YRibFpyQHHMegVtu2dGKzjmRBCiI7B5/MNZuZRAJLMzmKyeACXM/OVZgcRQkRO6Z3DalZNTb8UhGsAfGbcSlTOjLtWTf35gH9l//wTI1aY/zf3lvzi3Et0WM4A8L+WzcIDiei/SXGffzVtkmuE2+0+oT6w21H6LRhnhiFuRMSkdEPKJed+mdbPMhHyIKYQUY3MDiAih5ntVbX1zxDTZDL5j77q4CGsWPMOPPUNLW/Sr74cfXqkNjqWmeHxeKDr8u9JW0REiImxQ1Eaf/ahuqYWy15p2CXHarFg1FWXoW9a418LEcQM/dlD8fa7TpcCfiGEEEIIIcRJ5q7fpDNzVF9TISK+66Ih8hC6CKqq2v9rgv4CABw8Uo2lr/wbiqKgS2J4u0NqPgsO7uiOyq8GgvUI/PUhRnzyYXQ/cztiu1WDyNjrSkdqauD3a7hx2JXoc+y6BkH5VVKCZbmhCwshOpRRC1en2DT1LQbONjvLMXv9Xv95q++8vrI5L5o06b4EG9tuJWA+c8ub5jDwmWKhKfkLcj9uyeuf+mjj1UT0GoDYlmYwku71Yfvf30D9gUONnf5vWq1lpLvUHfGdDoQQQkSfvXv3xvt8PgcR5QHoHOn1Kyoq8NVXX8Hj+XEjGKvVigEDBmDw4MGRjgM07MawRNO0B/r06XPAjABCCHPd/Nyrl2u6ei/AowHEtHI6BtG70Llg5dSRzxt+kekkzskzz4fOj4ExosWTML4iVu7LX/zQq89s2Jbmr/NUhDFixNhs1u7Tzjttr9k5hBBNi+obZyL8amq4e51ev0wh5Rozc0gxcsfRFouRdU1fo6u+X6clJMgPMUIIIYQQQohTzFlXVg8getrnNc5798Vn2M0OIdoGZo7ZX+N/FeChK9a8g52Vxrwd9tcm4MCGC+CrSWwqCUjRQYoOEP/4X2r4L5jATAArYF0BaypYb3S3SQAAKRpiUvYgsf83sMRVG/I5HS+1W1eMTx8GAGuS4q2jSB5wFkIYYEzhqk5QrAsJ9CtTgzBetfts40vvHFbT0immj3PH63H+CQAK0ar7VbSRdG1C/uKHvwj1FU+u+2KgAutnAML79E2YafVefPv8v+CvO/rjQcJ6D1uuKi52e5p+pRBCiI6koqLiTGbOAXCrSetHWzEyALxHRK4ePXqsMSuAEMJ8Ixe/HhdTr6QD+mgA1wIYEMrrCDjAoLVg/TW/1b5qdeawZj2AaYTsSTkXKTrNZmBkK6b5YnDW+H2K1Xpt2IJFFK+4++IzbzI7hRCiaVKM3AEdOcLJ9eR7mYCfmZVBipE7jrZWjEzA21a23pyYSPtNCyGEEEIIIYSIanPXlx1gRlezcwRChIN3XXRGN7NziLZlz4H6c0nl9Ydraq31Pl/Y56+tJqx7y47P37eecFxVAXsso1M8o1uqhs5JjLhEHXEJjPhERlwiwx7L8PuA2iOEmsMKDh8glG+3oHKHCs9Rgr+JuHGJjJ9e4cX5V3mhNl233GpW1YLkzgleIlzYLcH+lXErCSEEAGYas+D1sQRajsg/IKVD08etdI76R7gmnDjx3rh4xX4bExWgdfetttqAUXOL8zYHGlS4nq0e3rQJwMBWrBUx9QcOY9uLr4CZAUKZbrVcVFTkrjM7lxBCiOhRXl4+BsATRHSaGetHaTHyHiJ6skePHo+aFUAIEX1uWrSmi+739AWU7tD1LlBUu0IgZvaSgiM6qMqv+Hatzhy9p+HJ+OhzZ+YDF2is/AUNxdXNothtGDxlnAGpIke3xHT97fkDGt0+RghhPovZAUTkJSbSvqpD3ntIxTJuIxfbhIiQrapivScxTgqRhRBCCCGEEE1jxiEguouRj2UUolm6d7N/AcBWdcQ7lYieADg+nPNrnQHfRTq+/kyDtx6wxwCxnQjJ3QlnnU84/SxC1+TQa9CO1gLffsPY8ImOLWWMmiMMPuk2Ue0Rwt7vYqB445DW27C+DDXEuCcp0facUQsIIcQJiHgVsGLsc+8kQ69dAuDGCK38pZ14aKlzVFi3O1+y5PFaAEW/HffEkqOdDjhAeAYtK0oe5AW+cTpcO62MYfNK8rY2NsjDm55EG7o3Yu/WGamXn4897328Pd7f5eLHF/1BCpGFEEL8YNu2bV1UVT1L1/W+ZmeJMknMfG5VVVWPlJSUCrPDCCGiw8uZww4Bbfu66TOLHv4EwHDnxAfOhqoUArgi1Nf2uPpi44JFCPk982HSTgBCiOAab1Uq2r3kztaPodJEgL8zO4sQUUHnHaTSxM6d8KnZUYQQQgghhBDRjYE3zM4QTFvIKKJXSqLt2aR4SyIR7mGgPlzzqhYgtSdhyDkKevQhXDpUwS0ZKm6dpuKSa5RmFSIDQGwccNb5hLG3qhg+RkFC58Zfv28v8N2WUwuVW43IA+CupHhrohQiCyHMsHLyldUrp6bfpFhsXYnwoVHrMGgH4ElbOTX93NIpPw9rIfLxniz93dGCkrz8/bWWGOg0A0BLv3P38RE2Ox2uXb+Z6DphG+anPym7nIDprU8bWd3OPwMDb7/ljseX/KHW7CxCCCGiS0xMTE9N085F5HdLiHYWZh5QX19/htlBhBDCCAVLHv6qoDjvZ34NAwF8EsprEn/S3+BUxiNggtkZhBBNk2LkDoqIOKmT9T2NtVsBrjQ7jxBmYnAlkTIhqZP1faLo3GpDCCGEEEIIET38pLjMzhBMW8goohsRcVK8bU5yvDWOgWnhmjcunnD5cAXjJ1uQfrOKQUMIdnvr5oyJBc44j3DRlQR7zKnnDx9g7NjKqK0J31t+ArLfirPEJyfY5sm1BCGE2V7OHHZoxZT0y+ydD1ugwI2WF/GegBmF9urDnVZNHdl/5dQb94RjzlCUlrq9BYtzn07rb7GA8Du07PMhAL38Kr6d5phZnjXx/r5gJk3jF7hlXZdNZ+vcaaHZGYQQQkQfRVF6EtEQs3NEIyLqSURSjCyEaNcWLMnbVlCcd6FFsfQiYENT4+zdukQylqHmfPzFhWZnEEI0rk1ecBHhw8zK/mrvWCLlOQZ3i9S6VQcPYcWad+Cp9wIA0q++HH16pDaVER6PB7ou93XaIiJCTIwditL4sw/VNbVY9sqbAACrxYJRV12GvmmNfy0YlHA//PrkpC62VUSkR3BhIYQQQgghRBs2Z11ZVL9JvfviM+Sajwi7qhr/rdC1XCKKyq3tK8sZb67QseHTU9/e9+5PGHGj+v/s3Xl8VfWd//H359wlCSEJu4i4gAJJULSCEKS2qQKWOrZ25gfV/tpqtWpb6zpd7Pw6HbrMdJl2utipS7VauyrO1C7WClRTFQkitVWWoCha2QQFwhKS3HvO5/cHi0kI2ZOThNfz8chDz/d8l/e5uQFy7+d+jyac2qkfjZeCyP91SFHOLzszCQD0lPfe+cilcr9JshJJgUnmZib3/X8Ymrm5u+8v9o0k/d2k79fvC29/+Lr3dNnO+F3h45f9v5vN7CvuSnZ0joKxozOj57wz1ZW5eppHuvCGaSW/jzsHAKB3cHfbvHnzhyT9UNLAuHJs3rxZK1euVG1t7aG2VCqlMWPGaMKECXHFkqRaSbcfe+yxN/IhUgBHi09eNn+kK/yzy8epQV3gmHnvUe7wwTEm6zrmvvq6qaUT484B4HAdftEG/cOB4ssHt+/LvOlZPSSpIO5MQE8x2S5L6qIhBTlPxp0FAAAAQN9i0gKX5sadozkmLYg7A/qn4QOTv5D0izd21RWb6csu61U/A4MGm0afZFr17OHndu2Utm32DhUjm3RfndfOH1VYWNUFMQGgx/z2Y+f/RNJP4s7RFW6759+/LunrV1/6r18MzG92Ka9dE5hp5Dun9ulCZEmyQHfMdx89n401AACSduzYUSjpBEn5cWfppXIljdq6desIST12lwcAiNMP75m/RdKEj334C2OSSf1WrlJJQe6w/lGILEnOrvdAr9X8VqU46gzOTT4l17WSdsedBegJJtvlkV87ODe5NO4sAAAAAPoei+xzcWc4kt6cDf3DsMKcqqEFOfOGFaRN5h+W2Ubt31EzVqkcKb9AOsLNmdojkmyjm39oWEHahhakL6YQGQB6h9t/8pUv33rPVwdI+ora8X5G3jFDlRzQvvrlXurYYc+umxZ3CABA71BfXz9E0mhxR+wjMrMhYRiOjjsHAPS0O3/61fW33f3V08IoWSKzZ/vZ3xQ2f75T8wj0QvxgQpJkZuHQgtTPItk/mGx73HmA7mVvWlIXDC1M/dzMwrjTAAAAAOh7rp1WvN6kLXHnaMqkLddOK14fdw4cPYYNzPnZsIGp0V6bGuRKfFymZ+LKkkhIA/Kl3I7WmpmWh9LHvbZ60LCC1OjhA3N+3qUBAQBd5rZ7vvrF2+75aqGZviapurX+Q99W2gOpekYYZj8fdwYAQO+QzWaLJB0Td47ezN2LoigaGXcOAIjLj+6d/0LxNRd/Iu4cXW3we6rK4s4A4HAUI+MQMwtHFKQed7crnNuUoJ9y+RZloyuG5KWepBAZAAAAQGdEuTlnxJ2hqd6YCUeH4cNt9/CCxO3DBqbPen1gKkeJ7Gi5/29P50immi9GtkAKEs2NsP/xIHPc639P5QwbmJ56TEH69uHDh3PnMADoI269+6v/cts9Xx1k0jdc2tlcnyCdUsHY43s6Wne68DvPrh8UdwgAQPyCIBhoZkPjztHLFSQSCR4jAEc1k82OO0OXc/W/awL6gWTcAdD7DC1I/Hbr7vptySDxC3c7Ie48QJeJ/NXAgkuGDEouizsKAAAAgL7vhtPGvv695at/I9n74s6yn//mhtPG8uFixG6iWb2kjZL+SZLc3d7Yk32neXS5zE6VbKzkRd2xdhRJ2ezh7Tk5CtNpvaZIjycC+/GggcnHzcy7IwMAoOfdes9Xb5Z088cv/ddvSH6lTIMPnssZXBhjsm5SX1siaWncMQAAh3v7z18dnBOEp7pnR0dubdoczkyZlCVf3VtTt3rJFcXt+XDkAPfu+d2qH8mLoqhdj1H53etzc3KyJ4cKirMe5bZljLm7zN60VLTy0XkTNnYsKgB0D/NgiqufvQxmmhx3BACHoxgZhzGzSNKSN2syl1joP3VpbNyZgC7wkqXsQ0MHpCrjDgIAAACg/7j+rNKLvrt8zU6TYn3zz6XqG84qvSjODMCRHCj6rTjwJUmqrvYh9Z45SUE02tzOUmDT5Joq69zPUt0+1dTsVY6kRvsgb93slQ/8JPOFd88pqDjCUABAP3DbT77yOXe/+RMf/eJ/SH6VpCGFp5wYd6wuZwm7WBQjA0Cvc+6vXjzZwszl8mCOKZGfMFkbh0ahR9V5uamHz/npK7c/8eGTNrdlkLvnBEGQ797PCsy6Vo6Z5be1c/mv1w8KanVRVonL3X14wpq/x85hzCVZrbLB8nf98oU7HrtkPJtjAehFopPV5r+S+gqnlg3ohShGxhENyUsufaM68wEl9F2TZsSdB+gok55IBKkbivL0bNxZAAAAAPQ/QSI5zsPs1rgzxLk+0F5FRbZd0nZJf5H0266Y89o5nlNXWHO5m37Y9JxLu931RlesAwDo3Q58CObzV111+xeD+g3zC8ed9C9xZ+pqgXSx5DccqHwCAPQCc++/P/FmNpiqQJfLfWQHpnA35aST0UpJD7RlQBRFKUm5ZvEWmEVRpDAMW22LScrMctraOajx8WbRB6Rghklt2tl6v0PfgxMSntha/pivqHiXNXPfHgDoea6gSP1uZ+SgH94CB+j72vGPJxxtzMyHD0o/k+Opi6Iw+rOsv/3NhKOAR2H0WMpT7x+Ub3/h9qsAAAAAusN1Z47bFqaC0ZKiGJaPwlQw+rozx22LYW2gV6kfXHdCZD6tuXNm2p1IBW/2dCYAQHzuuOPqzGmXXvy1ZH5e3FG6nLuP+O9Vq9u8yyMAoPtt2j1pgEwnyNWRQmRpfzXrSHM/pa0DEomEqRfUfARBoCAIWm2LiUVR1PYgpmMkjZO8o+GL3H2MNr8wqIPjAaAbeByvW3ez/nhNQN/XK/71h96tsNDe8GTOByKP7nKzurjzAG3hUl3o4Y+iRObiwkLjzUYAAAAA3eqmMyZsDFPBCT29bpgKTrjpjAkbe3pdoLe5do7nRFH9qSabethJV43cNuQMHrA9hmgAgBjVF1hB3Bm6S1SXYCcwAOhFarN7agPXVsl2dmKaXTLFeueljkin0xowYECrbX2BK9wl2esdnsBUI7MteYOC3V0YCwA6qz/WzPTHMMdCCQAAIABJREFUawL6PIqR0SbHDLTXhw/M+ZQ8+qb63d796Idc8q/vej33upEFBX3uF3YAAAAAfdNNZ0zYaInkCJequ3stl6otkRxBITIgXXWVp/YW1ZwmBRdLKmly2mVaKfdFt9zCh+wB4Gjj9d5vdw/OeNj3KrwAoB9bcfWUTBD4cpP/uoMFyVvd/DdRIv1IWwcEQZCxXrCZWGFhoUaPHn2o+DgnJ0cjR47UiBEjYk4mScq25zFK19Q/b4F+JtnL7V7JVCP3J5TQ7x9+z7jYvy8AcIj7i3FH6HL98ZqAfiAZdwD0HWZW99hj/uXTpmQ2y/Q5uU6MOxNwGPdX3exrwwam7xw+zsK44wAAAAA4ulx35rhtkgZ9b/nqByV7X/es4r+54azSi7pnbqAPqq47ITBdKQUXHf4Zet9lHjxVW599OpZsAIBYJXPTaQ+zccfoHqFy4o4AAGisfl9iXSodfU0Kf+NmI93M2jTQLSvp9UjB8xVzR29q63pRFNWb2V73ePcSS6VSGjVqlPLz81VbW6t0Oq2CggLl5ubGmuuAOkk1be38yMdKd8y5f90D9WHwYhToBJPSbR1rCnZIvia0ge0vZAaAbhRZsDSQz4s7R1eKLFgadwYAh6MYGe3yrndZVtKtb1TX/0XSTxRoQnevaWZKp9NSzL9EoYPM1NbfszvNtUZulw0vTPMGIwAAAIBYXX9W6UXfff7lY4Laur+6NLIr5jRpS5Sbc8YNp43t+O1CgX7mqkt2DYui7FyT/V/Jm75JHEnBc1EQ/u7eXxdy60YAOApF9bVJS/TPt8KCKErEnQEA0FjFR8fUSnpx8u3PvFIwOC9HGt6mcenazf7mvkz9iqunZHRJ29czs33uvqtjabtWOp3WsGHDFEWRzExB0Gtu0t3Ox8j84XnaNvd+f+zlHZtzCgYn23gh25Q3MJ1hR2QAvZHV6WHl6Dtx5+hKVqeH484A4HD98xUYdLthRellO3funJ7xvLstsHfLu/cT+IkEr6mhRXWSP7Q7TF8xZnCHbnsEAAAAAF3uQNHwsbcsqxrjgX/DpbkdmcekBRbZ566dVry+iyMCfdoVc32Ia99HzPyzkvKbnjdpq7svjmpql8cQDwDQCySSSY/66T4niWSyn14ZAPR9K66ekpGU6e513H2PmW2Pe2fkg8ysN76vvyeRSLT7w6kL5lmoduyoDAC92Q1vL177veVr4o7RpW54e/HauDMAOBzFyOiwQYMG7djufmm0N/sJ8+jLbpaKOxOOPiavd9cXg2z69jFDrDruPAAAAADQ1IEi4nmS9K1n1g5LevRVk2abaZC78u3A79PunjHTXnftdGlh1oIvfHrKhDdiDQ/0Uh+7ZM8xivZ+xN1uMmnw4T18h2S/lRK/+vFvh+/u+YQAgN7As1GoRK/ZmbFLeTYK484AAIhXGIa7ksnk1rhz9HK7zIzHCAAkl9RDtzXvdr3jUzgADkMxMjpliFm1pK9v35VZ4u53y3Ry3JlwFHFfJwWXDitMPRV3FAAAAABoiwPFxR+POwfQV5WXP5YsHnnG6NDtCjP7jMubu1vXdrktcCX+60f35b7Q4yEBAL1HMqqT989iZCUjbgMPAEe5RCKxQ9LGuHP0cjvCMNwUdwgAiJ3pQbneH3eMLmF6MO4IAJrXT1+BQU8bUpB80hVd4K673MULYOhWLtWGYfQjl18wlEJkAAAAAACOCldd5alxx06ZECr9OUlfOEIh8huS/SJKZb9FITIAIBEN3Bt3hu7Sn68NANA2xx577E4z+7ukfXFn6Y3cvV7S5r17926JOwsAxM1zsp+IO0NX6U/XAvQ3FCOja5j58MLctcMKUle5dLWLgmR0D5fqzIIrRxTlfHx4IW8qAgAAAABwNJg7d1Xad+ydaAr+WUfeXXyrmd2dCPX1u35WtK4n8wEAeqdkkLMr7gzdpT9fGwCgbcws6+6bJP097iy9kZm9aWYvjxs3jtoFAEe9G0477fW4M3SV/nQtQH9DMTK6lJlFIwrTP1Got7tHD5upPu5M6B9MqneP/qBQM4YNTP7MzKK4MwEAAAAAgO537ZwXc4YkTpqkwG5010eb6+PSFkl3pFLZb9y2YAC3KQYASJKunjKqRtKrcefoBq8euDYAwFEuiqLN7l4Vd45eapOZ8dgAwAFu+nTcGTqrP1wD0J9RjIxuMXxQ+hnV5XxArmsj88NeELMmx+7UlR6tIvdD/2/W/B9KkUd75bpGdTkXDx+UXtFz6QAAAAAAQJzmzvV0beGoSS77tEwfaaaLS9oo6Zba1O6v//e9hW/2cEQAQC/n0s/jztDV+uM1AQA6JgiCDWa2Mu4cvdSG2traVXGHAIDeIk9Ft8adobP6wzUA/Vky7gDov4YPt92S7nijzp9QffZrkr9bUo4k5Q/IU246rdq6/RsnV1SuUE46J8a0iEt9NnPo/1PJlAryBxw6dqnO3B8OlPP5oYV8ahUAAAAAgKOL2+Cg+nhX6gqXf6CZDqHJXnXXf48uyfvu/Pn5fNodAHCYQNEDruBf4s7RlQJFD8SdAQDQO1RVVe0YP378SjPbKOm4uPP0Itslrdy7dy93zgGAA66eMqrme8urviD5V+PO0jH2Be4QA/RuFCOj2w3LsTVvun9E1fWzo0DfMLOxeTk5mnpqsRZVrpC7qz6TVX0mG3dUxOy0cWNUODBfkuTuL0Vh4rPJqHrx0KFDd8UcDQAAAAAA9LDLLttZpLr0TLkubOZ0xqS1cr/lR/fl39Hj4QAAfUZigF4Ma+R++E0b+ySTPDFAL8adAwDQO7zrXe/Kbtq06UUz+4u7U4z8llfdffnEiRPr4w4CAL1JrhV+p9arvygpHXeWdqrPtcLvxB0CQMuCuAPg6DDUbNfQQTkPWDL9Do/8PpNtH3/SCf72M0/TgLxcmfWL1wDRAWam3Jy0JpeO15SJxW5m203hL1WXfccxg5P/SyEyAAAAAABHn8su89zUvrzpUeRXShrV+KzVS3re5d+8g0JkAEArrpk4cY+kn8adowv99MA1AQAgSdq3b986SUvMLNNq56NDKGlNXV1dZdxBAKC3uXrKqBqzZj/436uZ6UJ2RQZ6P3ZGRo8aNsA2uvslO/dk3xHJrjntlLH/OGr4sMT26t0KozDueIhBYIEGFQzUiMFFoUkPhLIfDh+Y+4QVmMedDQAAAAAAxCO9r/q4SMmLzWxyk1Oh5FWm4Nt3/CrvF7GEAwD0OaEnvhNY+JG4c3SF0BPsBgYAaGTs2LG7Nm7c+LSZPWNm0+PO0wu87O6PjRkzZlvcQQCgN7puSsnC7y6vus/kH4g7S1u47L7rpxQvjDsHgNZRjIweZ2Yu6c+S/ry1unbOiCGDbh0+eNDxYqfuo1Uk99csCK4aOjDFPx4AAAAAADjKzZ/vwca1taPNfYbU6LPKLmmDAvvxHb+gEBkA0HY3Th33t+8/s7bK3YvjztIZZlZ141nj/hZ3DgBA72JmvmPHjmf37dv3e0lTJKXizhSj0N1XhGH4BzOL4g4DAL1VJl13RTqTPlOucXFnaZHpxUyq7oq4YwBoG4o/EasRRbkPR5aZLrd/kbQq7jzoWZF8pdz/JQrSZRQiAwAAAAAASfr735UvRRMlP7nxGd9pst9kMyGFyACAdjJ3ZT8Zd4rO2n8N3FUQAHC4QYMGVbt7hZk9HneWmFUlEonfHn/88ZvjDgIAvdlnTj99b5TQbElvxJ2lBW9ECc3+zOmn7407CIC2oRgZsRuen795aEHym0Fmzwwz3ShpZ9yZ0O12SLo+UZ+eMbQg/c0RA21L3IEAAAAAAEAvUVs93KSph5+wda7sfXcvKOBWuwCAdrt+yqmPyVUZd44Oc1VeP+XUx+KOAQDonczMU6nUc+5+n7tvijtPTHZIeiQvL++RA3drBgC04Ma3lbwSms6VtCvuLM3YFZrOvfFtJa/EHQRA21GMjF7BzHzIkCHVQwemv5sMwzNDt29LekESt07pPyJ3f8Hdv5XIhmcOK0h/f+hQ28UvggAAAAAAoKFkmBoUuU1s2OZSveTrM7Xh6rhyAQD6vlDRxyRl487RAdkD2QEAOKIRI0bscffHzWxR3FlislLSr4uKirbHHQQA+oqbppQ8H1gwzaTquLMcZFJ1YMG0m6aUPB93FgDtQzEyep1Bg/LWjyhIfiaRTJ3vHn1OYtfcvs5lm83sM8lUevawgvRnBw/O45NLAAAAAACgWRZYjsmHNmqT3nAPnrnnwcHcUQsA0GE3TZ24SrL5cedoP5u/PzsAAC2rqal5xd3/R9IzcWfpYeslPRAEwbNxBwGAvubaKROqUunUeDNtjTuLmbam0qnx106ZUBV3FgDtRzEyeiUz88F59srwwtxvBQOTxXL/nOTPy1QTdza0WY1Lz3kYfTaRSZYMHZj6r8F59io7IQMAAAAAgJaEbkkz5TdqdN8ZBP5iTJEAAP3IsesnfF3yJ+PO0Xb+5P7MAAC0bty4cXV5eXmPm9lPJL0ed56eYGbV7v6Hurq6+0eOHLk37jwA0Bd94vRTtuZo72iTLYgrg8kW5Gjv6E+cfkrsRdEAOoZiZPR6Q8yqhxXmfDO7t36mIv+QzH4veV+8jdpRwUwZd/+d3P9vVqmZwwfl/ueQIdZrbucAAAAAAAB6Ocum3DWwUZNZXaRgV1yRAAD9x7x5Floi9Y8mey3uLK0x2WuWSP3jvHkWxp0FANB3DBkypDqRSDxiZn+IO0tPcPe/SfrlmDFjuOMyAHTC1VOmZK47q3ieWfKUnl7bLHnKdWcVz7t6ypRMT68NoOtQjIw+Y+TIgq3DCnN+PWxg6sIwo8kehfdJto3C5PiZKSPZtlDhL63eJw8vzHnvsMKcB48tsG1xZwMAAAAAAH2NJWTKbdjisvqERxQjAwC6xHVnjtsWZjPnS3oz7iwteDPMZs6/7sxxvM4OAGi3bdu2vWpmPzezx+LO0p3MbLWZ3R1F0V/izgIA/cV1U8a9dP1ZJWayz8pV220LuWpN9tnrzyqx66aMe6nb1gHQYyzuAEBn7KytPbm23s9NKPgHk50ra7xrDrrdbsn/lPXoodx07qODcu3luAMBAAAAAIC+7fJLdk1PRMEPG7a5BSvdw2/cdV/ByrhyAQD6n28vW3l6Mkg8KmlI3Fma2J6NwnP/edqpf4s7CACg79q6devAKIr+IQzDz5vZpLjzdIO/S7otPz//9qKiou1xhwGA/sjd7XvPVF1j0udkNkrundv41CyS+yaXvnH9lOL/NjPvoqgAegGKkdFvbNvro+SZmwK3y10+OO48/ZnJtkcW3SXLfnd4fv6muPMAAAAAAID+46Nzdw9PJoLpDdsiZfamwnTVbQsGbIwrFwCgf/rBsjXjw0CPSRoVd5YDNiUivetT00peiDsIAKDve/XVVwen0+lL3P2zkk6MO08XesPM7k0mk98ePnw471cDQA+49a9rj6vLhJ82s3PlGiOpoI1Dd8u03t0fzUklvvWJMybw+h7QT1GMjH5n+/btRcoZ8PYwCmaaq8xNp5uUF3euvszNaizyv7lU6YlocWJAzpNDzbg1KgAAAAAAAACgz/vBsjVDo4T9xt1nxJnDzJYEob/vU9NK3owzBwCgf9m2bduxmUzmMne/xsyOiztPF9gu6QF3/6/jjjtubdxhAOBo9cPlL4ytt2iyucZLfqz8wN3sTXsk2+ymF9IerPjkWeO5yzpwlKAYGf2Wuyd27lRBndcfn0oF86LIP2iBxsadq09xrbOE/cKiaIFl0xsWDdLueWZh3LEAAAAAAAAAAOhKc++/P3HOmFOvdQXfkjzRs6tbaIo+/cT6lbcsmDeP1+ABAF3K3YNt27aNCMPwn9z9GkklcWfqKHffFATBT7PZ7J1Lly5dP4+/NwEAAHoNipFx1HD3YOfezGmh7N2u6BxznSzZCZIGxJ2tN3CpxqRX3fwli4InwiD644j89Eozi+LOBgAAAAAAAABAT/jOs2tOCrJ2n+RTe2ZFezpK+gdufFvJKz2zHgDgaPXaa68NSSQScyR9UtLZcedpL3d/UdIdubm5vxo6dOiGuPMAAACgMYqRcVRav359bu6gkSMTruODVPptUvRO9/AdZsGwuLP1KI+2yeyJSPbnpNtfLJV8bVCutphZXdzRAAAAAAAAAACIy/eWrz5VFjwo95O7ZQGzl+TRRdefVbqyW+YHAKAZL774YmF+fn6Zu3/UzN4jqTDuTG2wT1KlpDvNbNGxxx67Le5AAAAAOBzFyMAB7p7YWZOZlAl9dmA+292ON9NAuQ2Ueb5kQdwZO8Q9kmyvzPe4a49F9ncFtjARJBcOytfzZsatawAAAAAAQK8xd64nBid3Dw4jG2lRkKMgWeNR+vW7Ftj2uLMBAI4+3698cbSS2S+668qumM9MP1I2+eXrysaxoyMAIBbr16/PDYJgbDKZ/Aczu1RSadyZWrBR0gIz+0V1dXVVcXHx7rgDAQAAoHkUIwNHsGuXD81a/bFufqxHwSiZjZNUIvcSl04wU37cGZvjrr2B6VWXV0laE3n0YhAkNwYebUl6enNhob0Zd0YAAAAAAIDmXHbZjkE5delzIvcZksbINcAt2GXma82CJ+prcp+950HbGXdOAMDR5/5Vq9Kv1yWGZbN+aWB+tWQntm2kvxq53Z5M2k+OyQnfmDdxYn33JgUAoHXz588PrrrqqiGSzpH0IUkz1bt2Sd4n6ZkwDH+aSCQeOfbYYzeYWRR3KAAAABwZxchAB7h7Yvv2faPCZPpUs+yppuBUdz/VzE6WySQFLgVmZnIPJAUmmUsHmtz01s/fwf/6wf+ambu7THLf3x7JLPL9AyNJkVwu1zqZVrqilUGQWFlbl1k1akjeRn4RAwAAAAAAfc01H9k1tL4+MVdmV8v9jMZnrUbyv5rr3jDKLrhrQRG7JAMAYnW/e2LLunXJnOrqRHZ3XrAnlTBJGpgJPVmwL6orKgpHnnJKdh53JwQA9GKbNm0aYGYnSTpX0qXuPiXuTJLWS/p5Npv9zcCBA18cMmRIddyBAAAA0DqKkYEu5O7J6moVeI4KPawvVBQUZt0KE0FYGHqUb5ZIupSySKnALBkqSplHKUlyCzIJBZnIPeuBMiZl3MNswoK9YZTYlTTfpSDaZYn0LqvTrqIi7TazbNzXDAAAAAAA0FmXX+4FiZq9F0n2b5JObq6PS27Sapd95c5fDbivhyMCAAAAQL/k7rZz586i2traM6IommNm75VUHEOUzZL+kM1mfxdF0dMnnnjiFjPzVkcBAACgV6AYGQAAAAAAAECsrrxk90R3+4HJylvpWifTbxNZu/G2BQM29kg4AAAAADgKPPPMM6kRI0YMN7PTE4nEeZLOl3Rqd6/r7hvM7I/uvjibzS4/4YQTNppZXXevCwAAgK6VjDsAAAAAAAAAgKPXVVd5yqtrxpjZWVKrm17luKskG/gUSRQjAwAAAEAXmTJlSkbSJnd/Y8OGDc+Z2f+Y2URJ04MgmOLu4yTldXYdd683s9fM7JkwDJe5+7OpVOrVKIpeP/HEE2s6fSEAAACIBcXIAAAAAAAAAGKT3KGcbKDjXJ7flv4mFSjQcd2dCwAAAACORmZWr/0f/ty4ZcuW5+rq6h7NyckZHobh8UEQFEsaJ+kkMxstaYS7D2xhulpJ29x9UxAEr7j7OjOrSiQS67PZ7BuZTOb1k046qdrMWv1kKgAAAHo3ipEBAAAAAAAAxCpSwk1hm/ubJXijGgAAAAC62ciRI/dKelnSy6tWrXp28ODBFYlEoiibzRZKypc04MB/B0rKjaIoEQRBZGZ1kva6+x5JNWa2N4qiPalUqrqurq561KhR+2K7KAAAAHQLipEBAAAAAAAAxCY7WHW+M9xspj3a/wZ2y0y7PAo3dn8yAAAAAMBBEydOrJf0xoGvQ9w98corr6Ty8vISyWTSoijyTCYTjR49OmNm2XjSAgAAoKdRjAwAAAAAAAAgNnfcYZkrL9n9spR4Wu7nttK9Vm5rstKzPRIOAAAAANAiMwuldtzqBgAAAP1SEHcAAAAAAAAAAEe33GDgaya7V7J1R+pjUtakNeZ64O5fDXitJ/MBAAAAAAAAAIAjoxgZAAAAAAAAQKxu+bntymSzf5CF33f5s5IyjXvYHpcv8Si8tb6ublEsIQEAAAAAAAAAQLMs7gAAAADdpXjqeUMDs5JIQamZ8t19lWWD59eseGRznLkmT56ckkal2tJ3xYrJtdL8qP1rXDjgraNNmRUrVmSO3LvrlJbOTefl1SYlqXpENlz38MN1PbEueq+Gz8WCgt31FRUV2aNpfQAA0D6f+ODOwZkw9Q6Tna3Ax3ikXJPv9cBeMvOKVCa/8ocLbE/cOQEAAAAAAAAAwFsoRgYAAP1O8fTZZ5vrVsknNXfepa0mu2Vfbv23XqmoqO3xfGWzXjNpdFv7m7RE0rOR2/PuWrT26YXrW+pfWjZ7jsv/0KBp0ZrKRbM7mretTpkzJye1I7NNsgJp/+NcVbnomO5eF71XSdl5M6Xg0M6FLn2/qnLR9T21ftOfBZP+a3Xlon/uqfUBAEBHuX1y7rb8bLJodOjZvGSQ2JPJzdny4x/b7riTAQAAAAAAAACAwyXjDgAAANBVysvLk6/Xpm6R+8db6mfSCMm/kleb+vD46eee+8LSRzf2VMYD67e5EFmSXJohaYaZy0wqnTbry8l99s3nnlu4t7n+kfkg80ZNBR1P23ZFW5OJmlT20Fr7H2cczcyCwd7guWhSfk+u3/RnwaUBR+4NAAB6D/MfLtAeSVVxJwEAAAAAAAAAAK0L4g4AAADQVbbUpf5FUouFyE2MT3jw29Ly8oHdlak7uOmLmQH++5PKy3PjzgIAAAAAAAAAAAAAAICjG8XIAACgX5hQNmuGub7UtN2kH5jrw3K7RNI3Dx9pZ6o2dV0PRGyF7z78q0XlebWpu5s7YVGTfZEBAAAAAAAAAAAAAACAbpKMOwAAAEBXCExXq1EJru9WEJy9+qmFKxs0/urUs8+9I4wSf5A0/mBjJF1fWjr3W6tXL6jvqbwNuam8auniPzd3rnjqeUPNbJzMbpQ0r8npiydMnfXttU8veqZhYzKVeiQbZt5/qMG0rstDAwAAAAAAAAAAAAAAAKIYGQAA9APl5eXJ12v9IskOtZnZFU0KkSVJK5969KXSqed/zIPo8UN9pREq2jFR0rM9k7gxd2WPdK7q6T+9KelNSR8onT7rAXfd3/B8EOh6SR9u2Pb8kw/tkPRgd2QFAAAAAAAAAAAAAAAAGgriDgAAANBZb9QHJ0pW8FaL7x6Rk/n1kfqvfvqRJ8z0cqPGSCd0W8AusnrpogWS/ahhm0uz48oDAAAAAAAAAAAAAAAAUIwMAAD6vJVPPfqyyd7jpn+T6SHJ/r2iouKIuw1LUiS90vDYzYZ3b8quYZH9tNGxNGLSpNn53bHW5MkXDigvL+8Xd9IYPX16Xmnp3HTcOSZPvnBAe3KUl5cnJ8x4b4Hmzk10ZY4JM95bMHny5FRXzTd58uTU5MkXDuiq+Q6f/8IB3Tk/AAAAAAAAAAAAAADouH5RXAIAAI56vrpy4cOSHm77CJ3a8DDy4KWuDtUdwlT0UhA2acu3YyWtO3g86ezZIzKhPu/mgSSZ29I1yxb+qrW5J8yYNSoI/ROSzZR8Yo1qC2pqUyoum7XVzJYGkX6Wm33zNytWrMh0xbWUls2e5q6LD+YMpOzqyhmfkeZHnZn3pPLy3AF16Q+6q0zycS6VmmuEF+5USdnM3ZJelOxVl91dVXn2Q51d76CSaTPL3OySQw1u91YtO/vZ0mlLPuimj0heVqPaAqVq9z+mUkXkwW1rlz3yWMN5Sstmz5H0oUg+8/VajQi0TyWv7ZPKZlXI9WCU1IK1SxZtak+24ukzTzO3T0o+VbIzFe5TTWrIwRy/C6Tfrqpc9DtJ3rYZ5welZU+dL/knIultNdJoqfbA42ur5PrZvrzMXaprT8q3TJgxa5SFusakcw8+FyWpuGzW1kC2ODL/fdXoQfdrwYKwtbkAAAAAAAAAAAAAAED3ohgZAAAcdUpnzDzBQ41o2JZOJf8aV572SNQHgz3RuHY2SCTfbHicicJJsuAGO9RBJ0pqoRh5flA6bclXPdTnpYOjDo2WSSPk/r7I9L6a1JBFYyfPnPvyisXVnbmOCVNnTXF5peytlVx6uDOFwafMmZOT2pG53GttvssPfX+tUS8rkHSmpDNN/v6SsiWr3WZeXLV08fMdXfeQwN5jruveOtaGkulLrnfXh5smMWmEpHmBRfNKymZduaZy0Z3l5eXJLbXp/3L5tYfnliSVy1QehP6VCWWz5qytXLSktUgTZry3IAj3/USu9zfN0CDHFZF0Rcn0mU9EQfLKtUv+uLalOcdOnlmUm1rykEszmpmxQFKZTGV5tan3udl9ba5vliTND0qnP/XvHvrNjVI2yOvyD5rrgyWvVd/s02ZfXrVs4Yp2LAAAAAAAAAAAAAAAALpYEHcAAACAHhfaZxoemunl5598aEdccdolCKc2PHRpQ6eyz52bKClbcoebPt/GEbNyUvbUpGlzRnd0yVPPmn28BXqoSfPqjCcv7uickpTaGc6R7IcHCmzbqtQ8+NnkyZNTnVm7We7f1KFC5Bb9qLhs1k2v16UfsAOFyC2zgkB6snTazLe31OuM8vJBQbhvoXSwELm1vHaOheHjE6bOHnOkLqOnT8/LSdkfDxYit2KW3O9s09rSW89Fb1iI3BKfZBY9Vjp95tvavAYAAAAAAAAAAAAAAOhyFCMDAICjSmnZ7Gkufapxq90fT5r2OeWcOcPd9L2GbSYt78ycJa/tuErSFc2dM9PLLm1t5lRpvWU7tBvthBnvLQgT+n3DgmGXtiZCe/e6ZQ/v6sicB+Xk1FdIvrtJ82pJv5b8O5LuctOjh4/0STXJIZ/szNpt43+R9EJzZ0z6ttzf16T/bpOWHOF7IJm5i66MAAAgAElEQVR9vaXV6upS35dUdlgKaYOkiuaymDQiCPz35eXlzd5BpdAHXtrcnAfm3XrErG1Q8vfqq9XMc9Fcj5j0A5PuOXx+K4jc/jhp0uz8jq4LAAAAAAAAAAAAAAA6h2JkAABw1Jg0aXa+y3/csM2lrWGQ+x9xZWqr4umzz05lMn+UrKBhu5s3U1zbNpMnXzjAZfObtrvb1SlPHr966aKTqyoXHRNaOFre+HEz6XftXa+8vDyZCPf9XPJJjecK5qxcvvC19l9BY3+tqNgp219obtI9gQXj1lQumrimctE/rqlcfNOaykUfq1q66LwokSjW/iLltzKYndPZ9Y/I9UXbNShnTeXiyWsqF03wKBomacGRu2urFM1aU7m4cHXlordXVS46xs1mHCgibthvRsnZs9/R3Bzjp88ubrors0tbFdg7qyoXHb+mctG71lQumqDATvPDC9pLt+1LX9R0zvLy8mQk/b+m7Sb7UpRIFFdVLjpm//PFSiR9o4VH5DCTJ184wM3/rUneDXKNX71s0btXVy66dnXloo/mZ7aPdlOjfiaNyORHV7ZnPQAAAAAAAAAAAAAA0HWa3fEMAACgH7LsAN0hqbRRo9nVVUt+23Q33R4VSB8tLps17bAT7mkzO0XSRLmXSdb4tLR8ZE72tqoOrluTrP2nhjsUH3Bz1bKFdzRseGHpoxslfax02qwNbvqizG9cs3Txd9u73uu1yW9KurBhm8veW1X5yF/aHf4I1ixdfO+kSbP/57nnFu49Up+1S/64tmTazCtktvStHF7SVRkaMvl1q5ctvqVhW9XTf3pT0ryS6TMflx9eBB2G0fQXl//p5UZjli58auL0898VefRiw3aPfIqkx5vOkXS/xptmCWzumqcWNuq75qmFK4vL3j1Pyj7XsNDdzW+Q9EDDvq/X5kwyRaObXOBPVy9d2Kig/YWlC6skfb6kbNZ4Se9vmq05Nel9/8fcGj8XzT6wpnJho+tdsWJFRtJXSstmTfEGzyV3+7ykdj8nAQAAAAAAAAAAAABA57EzMgAAOCqUTJt1ncs/2KT512uWLnwwlkCNXWHStw/7MvuapCsklTU3KCm/tKKiItvhVU1nNz72J9YcP+hbR+jtq5ct+rcBme3pjhQil06fdbVkNzZe3q+rqlzY7h2WW9NSIfJBx+Rln2nSVKqm1d6dZKaXR+Rmbz3S+SAMDtuV2mRfalqIfNCqpY+sk3RXozmkMc31dWl2k4m/0rQQ+aCqyj++Ig+uajJ+xuTJFw5oPEU0tUmfrXX1fm1zc0pyj6IrJW9bob9box2eXT6/aunCp47UO5vJXN5wbpNGlM6YeUKb1gIAAAAAAAAAAAAAAF2KYmQAANDvlU49/xxZ411TzfRyMpm+Iq5MnfSCm8pXVi5e07lpvHFxqduPtWBB2NKIAzvTtktJ2Xkz3XVbo7Vkt6yubLxjcE+qqKjIurShYVt5eXmiK9fwyCtaKhYP0qlnDxuj8MkW53R7utGxHV6MfNrbLxgsaXyjtRTc29K8x+TVP9C0rSa5b1LjbH5aw2OTfvfyisXVR5qz6uk/vSmzthb7T294EESJR1vq/MKKijfcbHmjPKGd0ca1AAAAAAAAAAAAAABAF0rGHQAAAKA7TZgxa1QURg8ctuVtNnjv80sf2hFHpo7z3eb6snYP/v6a1QvqOz2bbHTDx8UUPNfZOZs6tWxmSSj9b9P2IBEdaQfmLjVx+vlDQoXHeZQYlgiiQx/Ec49M8qIu3gy5MbO1LZ1+/smHdpSUzdwtWcGhxsBfbGlMIgj/Hvlbnye06PB/z0dhdmjTtlVLH3mppXkrKiqypWWzlrg042CbB8Gwxr2ssOGRm/+1pTn35/Pn3Fp/jF0a1qhXIiotnT4r3cqgHG9wGLqNbHUhAAAAAAAAAAAAAADQ5ShGBgAA/VZp6dy0wp33uzSiYbu7/581yx9ZFVeupky6R+7N5nGznRYFawPLvrBy2Z9e7+J1Gz0uUeRdXpydlS00qaBpu4f2DUmXdPV6klQ8bfZkM/+0pIsjj2QymUXyhpWrPXCDEJPva62Py/Y1fHwsE9W12D9M7lUQtTJnWNCwyPrADtB+5BGHbG94ELiKGh6bVNRwkiCyna1NGJmq21Lu3fS52HQn7bYIFBW23gsAAAAAAAAAAAAAAHQ1ipEBAED/Vbjz2w13epUkc31tzbLF/xNXpOaE0p1rly1e0sPLmuSNduVNeH2rxbMdWGT0EU5dXFJ23l1rKv+0uCuXK5k2806ZX96Fc/Y9kfIbbvhsUk1bhrm0t9E0rvxGx6Z8a1CNHLWh2Dpw2+etVSPPnZvQa63WNbcqCoJUpycBAAAAAAAAAAAAAADt1v1bwgEAAMSgdNqsD7n0qYZt5npkRF7mi3Fl6mW8YSGyJAVK92gxp1lw++jp0/O6ar7SaTP/WWZHdyGyJAWJ+oaHZm3+AGJOoyPzxvO4Gu3abGpL8a+33mfBgrAt4VpfKnqjS+YBAAAAAAAAAAAAAADtws7IAACg35k49fzTI4t+2rDNpQ1BEHywoqIiG1eu3qfxzsj1ycY74XbpSvJ/kgVbzP3QDtDuGjvQBn5G0pc7O3/x1POGutl/NmleLek7USLxRDLybcNz6nZVDB/uklS+bZttqU1tNGlEZ9fubQIPd4cNtkZ29+FtHDqw8aHvanJ+d+OFWn++uGxAWxZ2aWvD70WUSBSvHVWwri1jD+mqomYAAAAAAAAAAAAAANAuFCMDAIB+ZeL084eEHv3emrS7Rxesqly0PZZQvZZtlnSoGDlwjZNU1fXL2Gerli76X0kqKZt1l6QrDp1yfalk2qxfrlm26MVOrRHYaU1aVtdl/OyXVyyubq57haTS6bP2uPe/YuR6i3YlPNGgxQpOe/sFg59/8qEdLY1z6fSGPzfWWjGy+7hWw5ifLDX9aWymm7RTDYqRLYqGasGCta0OBAAAAAAAAAAAAAAAsQviDgAAANBl5s5NRIruNWl0o3a3S9Yu+9NzMaXqzVY1PAjk5V2/hP1ozdKFh3YsDjOZm/fvyNywi/6706uYzmh07H73kQqRJam8vDzprrGdXbc3emHpOzY3fYyjbP05LY0pmTZrXNNdolOeblSY7qa/Nxn2zlaimBSc11reA/7aaKD7e9s4DgAAAAAAAAAAAAAAxIxiZAAA0G8Uv7bjC3Jd0LDNpG+vWbbwV3Fl6uWWNTxw6aaJZ5931pE6F0+feVpp2axbJkydPaatCwzIvHlNw+MXVlS8YRbc0KTbrJKy2R9o65zNcVdRw+PILGqp/5Z96dObtlUMH+6dydB7zI9kwaMNW0LpR6e9/YLBzfUuLy9Pmunuhm0ubXhu2cMbGnWMVNlkaFlx2azLjpSiZNqsT0o+qU2RXY83afncqWfNPr6lIadOO++Y0ukzby+ZPvMjbVpDkkz5be4LAAAAAAAAAAAAAADahGJkAADQL5RMnXmByeY3bHPToyNyMzd3Zt7isplXlpTN3PXW16xVrY/qG6JE4sGmbe7Br8ZOnlnUtL24bGa5uZa49KkgiP5WPH1Wa7viSpJWrFiRadq2eunZ90iNC1td/v0zyssHtSN+I4E33rXXpCtKy8sHNtf3lGlzCs383qbt5du2WUfX73UiNSrAN2lENlt/u+bOTTTturU2/QWXZjRu9Tub9ksEwTNN20y6e8KMd09o2j5h2nmTZPpBW+OmlPxN07Yo6RVHKnwvnXr+OVkLnnO3q+T2k5Jps/61uX6B284meWeUl5cn25oLAAAAAAAAAAAAAAC0jjfiAQBAnzdhxnsLFNb8smm7uUZvqUs9Ujx9VuuTuH+lqnJxxWFzSCdIVtCgqbRTYXuRtUv+uLa0bPYvXP7Bg23uGpuTsp0l02c9JPliV5AXuE936cK3RlqBuf9OUmHHVp4fmc38pLv95dCM0oja2tSXJF3foSkD/VWN9zUu9dr0kpKy2f8h97+EQViTMhsVRsE5UvZzkkZ0LHvfcExe/QNb61L/7q6xDZrnlry283RNn32nR6o2ecpMl7i8aSHy7lQy5/tN51y19JHtpdNn3uFuVzVsD8KwqmTa7O+a+VrJRko+8/Di5pY9t+zhDSVls26T9PFDKVxjg8BfLi2bdY9LS8wskvvbXH62KzqzUeW46csTps7+2dqnF65v2Bx6uDGwtz5/6a6xW2pTG0vKZj5gFqxYvXThj9uTEwAAAAAAAAAAAAAAHI5iZAAA0Od5VHtck4Lhg8aba3xb5jCz+yUdVozc3wWhbs4mNNOaFue6LpDsApM3qfE9eFr/3Jl1Vy9d/GxJ2czvSHbjwTaTriueNvveqmULV3RkvuLpsx4117kNUk6S9CuZlPCEIpf6z9bHLauoqMgWT5/9YZMvaXJqvNy/aQceiOa/t3bd808+tKO5eU2J/3RFVx1+wm/wI87YNhZmvqRkanaTAmq5dJmky9wPzt3sd/EbTQuRJWlgdsC6mtS+3Q3/fNj/XLdPuvsLkihGBgAAAAAAAAAAAACgk4LWuwAAAPRuFgQdr4A8yq1cvvA1TyTe4dLWto4x2XuqKhf/qLNr12X0pcPWNb9Vc+cmOjJfOkpe6tKGtvX23fu/+q+qpQufUuT/0J7rdOmjVZWL7jnS+VVLH1knRW3YalySfLdJP2jr2quXV2yJPHFe27+HB9lNayoX3dzcmRUrfldj0v9r33wAAAAAAAAAAAAAAKA9KEYGAAB9Xk7W9nZ2jsh9W7MnLNjV6ND0cmfXalqAm/So2V1oO76A7Wl87Jtb6r52yR/XpmtsrGT/2krh6iIzP3N15cKHmzu5b19utuFxa4/VyysWV1vklzcaI51V/Nru41sadyTPLXt4Q9KjKZLd2lI/k+5JuI+T2eMH21zaWlFRHnVk3UPzRt7oueIeNP+capzljQYjdtdGyX2t9G+8hmlLS/3XPL34IWUSEyTd1cq89yiw01oqRD40Z+WfFpv5mZJ+3cKMz5npnWbRQ43ySq+3NHdV5R9f2WN7xu/febul5+KBQucgPGlN5cLvtDTn6srFPzDXh5spuM82OwAAAAAAAAAAAAAAALTL0XKnagAAALTJ/KD0rKUlCqK3uVTkpr1ybfKkVq5dsmhT3Onaqry8PLmtLuckeVQauY73QNs9CrYk8uqWr66o2NP6DP1PaenctAp2THXZGJPczTJmtt6kdauWPrK9I3NOmjZndOjh+DDwEwJTjiLfoiixbvXyR1Z1QWSbOP38k13R2yJX/v4WeyNQtHFETvb5ioqKdhcTnzJtTmE6io43UzKbirb1pec0AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACwuAMAAAAAAAAAAAAAAIA2sfLy8sSGDXmJ9g5Mpwf66okKtWBB2B3Bmpo7d27i2Wf3JCWpqOj4aMWKO0JJUU+sDbTP/GDy5E2J6urXgp7+OUF78H0CAKA3oxgZAAAAAAAAAAAAAIA+oOTs2ad65JcFrlPbO9YDZRXZH9YsW/jD7sjW0IQZs0YFWZ9nsncfWHuruy2oqlz4u+5eG2iX+fOD4keenBW4XSNXWqb6yO33VcsW3hF3NDTA9wkAgF4vGXcAAAAAAAAAAAAAAADQuiCrER7oHW46q92DXW5BtLEbYh0mFXpRaDbZpfMlyV0bzKK/9MTaQHuUV1QEWz01xl0XyBTIFUm+Ke5caIzvEwAAvR/FyAAAAAAAAAAAAAAA9AFREAZS0NH3+c3dgi4NdARRGAYKkomD92o2yeTcuRndr3ja7Mmy6NJAGrW/JXi8Jrf+jlcqKmqPNMbdApnv/9kwBSYleiQs2oXvEwAAvRvFyAAAAAAA9G1WWl6eb3U5IyPzUUGkolDB7mym/rUi5W9eseJ3NbElmz8/KL1/VbK+fk+n3mwcPXpfWFFRkW1p7nVvG5jVggVhZ9bpOfODyZM3JaqrXwvS6YG+eqLCvpMd7TV37tzEs8/uSUpSUdHx0YoVd4TS/2fv3cOruvL77s9v7XOO7tzvBsxFBklgfJEBCflyBpCw7PFlJiPPJck0mSaTpEmbNk36vG3ftnrap2/b9O2bSZukuUyTZjrJJEMyM5mJjbmOxhhkwPINEGBjGxuMMdggbrqcc/b6vn+cI+lIlkAYCRl7f55HDw/r7L32b6+191prr/Vdvx/+03L9m57mZlf+7T1x+NSXnyWTyeDEiaIAYOLE076trS093kZFfBLp7yNhfPv3/Pbzo3JT9/N5Y61EolTt7YRwE95HhFVXV8fOn5/hYJhxdcQniQH1fXRuV8iNrO+o3RhPzgJvAiMZn3UbemWM7YmIGF/M32rY44LZAMJ3T4JvAcOKkSMiIm4wH/O53fLyxoKS6T3TMhmb481mKHDmM+F73oXvZop4/0qbGyIihuTTM1aO5hDz+DTOzUc7DyMiIiIiIiIiIiIiIiIibk5s+f0NczNp/xiyegdTBcWgAmQpjEugDslesMA2Htq9pZ0bOMlRXf1IcWe85xGTfv66MzN7jjD1h+37Wk4BVFVVJTRx7kPm9cu9h3hjy+F5k3734zRpPSTNza5i87P1TvariARGysv+/vCeLX883qZFjD4Vq9ZNxdnnneynAHB6y4vvHH5uW8uNuP6S6kemxeLdX0A8nks6psD+8tDuLc/ciOvf7CyqXj8xEdfjTu7LAN44iemvD7du2zzett1oltVuKJf3PwusBsDZi4b9r4Otm4+Or2URnyQWVa+fWJDgMZP7MpIByGzzoee2/C43eKFmaV39HJfRE4Y9eL15jdc9XA9DjLUuAn/Xvmfrt8fTrohrp7Jmw93gf9HEQgCZdsZiBX+w/9knz423bRGjT+Xq9TVm9ksoJ74zflycLvwfN2KDatRu3Fgqa9atB/fbwF0AiCfl7P/B03O1c51XGCY4fWTX1pNjbWfVys8sk4v9a4wv55LeAf23Q89t+52xvnbEp5uqmvVPyNzvIU3PJf2VM/erB1s3nx3q+GQyGXuvK/F1TL+fl/zNQ89t/cWxtzZipET19MmhYtW6qVjwUw59HkCODN6eOrRnyx+Mq2HNza58yzML43KfN9l9ggmIEqAIB3i6MC4Dl810IvQ8Fwb+maO7d7zJTfS9F3Hjqa6ujncVTHuI0P8KgIzLwn54+Lktfz7eto02FavWLTEX/KxJK3NJLwTef3P/vu1vjKth48B4rw2MF5Fn5IiIiIiIiIiIiIiIiIiIm4yqqqaEys4/EKb5Rya7G5ijvm986996LPMYqy3U6qqahv/DhYkb29s3pm6Ejd2JVKHJV8hsw3VnZsr4hE0ETgHEYnPjGXx5ft4O3q06SNAOH2sxcrKlxZ1WfKHEwxgO4UFjvggcMT5YTKXI3SHYAGCywyaevWHXD3rKBHdg9L4r7ZKPhMgjpKA4KCYVLlOu/AyOIbdvvO0aD7wPp2GsAVsPYPIJWfD98bYr4pNFYSJYivdfkWkDBoLToGcA3Whb4qEmhmbVve339SB0srq6Omhra7tpFqeHGGudN3h1XI2K+EjINMfEOhm3ZVPssqV9CRCJkT+BuMDN9dIGcp5AgXOXg84iYMzFyFG7Mc4Y72fOBG1Hj266qhg5IiIiIiJinDGz4G5MXxdUAyCOYf7J8TRqSfUj04LNrQ+h4IvAnRKzMFz/PDv57j4lb50G6+M+eLOidt12hcFfHdm75c3xsD3i4897iUWxUt+x2PrnaC8Z+mRu8A+CaSZfJ7PPAEjEQ3PfAz51YuTxXhsYLyIxckRERERERERERERERETETURTU1Ow/0RHrcl+C+l+oGDYgw1nMF3GZxATXNmFbuD73ABPDWGYMRc4NyryIeHiYeB6/5uZkjJ1x92VTumluro63p2Yts4r/DmDGNjF0NmTR3Zv+ZtRsIyK1Q3VmP8HDuZkU9wznYWpP75SqD7JHKas/dk6CkbDloiPHz4Tc4FT0PsaSDKZG9GzOxqEsYxzPhbk6fjMebvu64/1ezUWfBSbw0zaxSwI8pox63t3P2XIOefk+59lzPDhDSuLm/GZi7g2VqxoKEkRrjKz2t40g0Ny/seMgxjZh6HDxYJRii1500Wo/PBYS44b2H/dCG6/9+HJmbDnEROPZlPsLUkbD+3Z9tz4WjY8t61ctyhw9oQz7gEQvGRpvtXetu3t4c6R5JwRqH8w4jKx9CeqLiP6kfcOc7H+ZtPMh+ENaYM+De1GRERERERExPWzpHbtHKT1wPLeNIP9Zpmt42VT+erGCc66PofsXwDzgcRVvuIMo8RgkeBWw1WZY96S2ob//mrrlsM3xOiIm4qZqW67XIDlrcpYb0SoTxrOeydnQf8niSxwwafyu2C81wbGi0iMHBERERERERERERERERFxE7H/rbOLMfuKjHutX4icIet16hnggmCGiZUYy3K/JzDd5dEXKlat23947/bx8lCVAaWv7RQLhZ3zgS73psTOJpQuQWgk2qQ5ca+eSuDzwgy4aF4ngdERsJm/1bDHlfM+Jnz3JPgWMKwYOSLi5meM36sx4Wa0OaKfqP4+6YSFVm6yzwATADA68Npb0lP88vhaNoBrH8eIHmd2dtGiRb6trW2MzIr4KGS8JphspeCxXNIh5+x54GMrRo45m4Gzz0iszSVN8DHbBAwrRo6IiIj4JNHU1BQchKB948Y0I9ms1Nzsqr57MFZU9Iba2tqucS7iqlh1dXWsrKxMLS0tmdHOF+Aj2GzJZHNwevpBN+IyGgeampqCF1+8FJs7tysc5bIba6y6+uuxrq5zNvpRx5pddfXJoKzs1Y/wPDW7qqoxe85Hm7F6bwZdY6zqKeJ6aWpqCg68dX4lTo/TP6991Mv+flYhx8bLpv1vnas1Z19HlA/6+QPgEHAGFEc2F2M+MKX3AIMAMdvQ3DjuZmrTIiIiIsaESIwcEREREREREREREREREXHzYBa4ZYgNQBEAogPsh3L6U7P4MW/pdKiwqEB2m2Q/K+wLQAIoBFuJswcYp3C5Jrab0zdC70bsmdkwifC9znh4ujdtypRUz+nuxDMY/14yJ1Maz/OH2pdlYOOA89PpHiNBDFk8l5QwKc4o4SAms0KkWM7eIN1T8Inf3R7x6Was36ux4Ga0OaKfqP4+2ZQ3Nhb4jvAeRLIvURwBt7Wt7Ued42haPmeB70m28apH5uEcYeiCExs3bhzzqBQR10Ym3RPEXZDAesdwxL19vNfMvFngRAG5tT2hmHMuirARERHxiWBpXf0c522V0ExCcAFHKUjvCdOFt5jP1Jvsnv3Hz810Mqusqe9EOupcsMMFsT37n33yHADNza5yyzPzyLgHMFvF5t1zKVNhl01VRU39u2a2yzL23IySniNXEkJWVTUlmHhumfduJU5msg758EXgA4Kg1ry/38wt6oKSzm6fqVy9/ixm7aELdsQ6yl6+kgByqPsMXdHehO9ckME9iHT3ZWySAypr6k9gPBULEi199ziIJdXJafF4fE0oapzZrae6d09xb8sqa+ovgI4ga00F9vzru7ecHur8yjVrb5WCNcAEvJcRvGlFqdb2lpZLV6qv5avXzcw4VoK7BUDi3bj8ngN7tr83+NjyxsaCxPlMpbx9xsxXHDzeMSsxlYJT3fGeqpr6t4G2MAhaj+x6+lWuQ0CdTCZj73YFVQFBDagWaWLez0u9/C9W1NZ3GJbB+YOHdl09GkJ19SPFXYnUcuTXC26/zLFJLiarXF1/VtDmXGxHahLtRzdt6rlCNrasdsPiUKrDVOi80rjgAAU97b4nXm2yemN3RfZ5imWqauqPoOAHnUXdzw8ZdSv3nMvHkma6C+2ag5iQfc7XnzXsZZN2xya6F1/ZsuXyEPYA2XoJPsjcbgHVAA7OOou9cGD3pteHO2dJ7dpbnNxqzKYTQoC9pksTn73SM78gmZxU0FNQE6AHJC3owiZ1dUPl6vpzhl7A27ZEOn0sVRLc7r2rApDXKZcI9h7aufndK5RrH6NUTxE3gFfeOj/fma8HW5RLygDPZwieGq/NCQfe7liE2eeA2/OSPzBss5d9z7nwDSe6fRg4YpR47ycZqsLss0AtUAy8Cbb1ckHPifG4h4iIiIiPEx/riZWIiIiIiIiIiIiIiIiIiIh+br/34UmZTM8ysFt60wz2mNL/38G50w6wcWPYm15V1XQ8LLvQ40zTQfXZVM0zszuSyWRsPCZ4hd5pb71vCzRflyCnpaUlM7e29pUpVvam96F1xxO++HzYeb35RkRERERERNx4ijrChRmvB7Be71LqAvdCT8bvHV/LBtAtOHR4z9Yt421IRERERETEFbCqZLJEXfHZLvCTnIKLl1P+3Tfatp0fb8OuRixtFaHz/8SwhTjw4sd0J+YGhJ8Xdicw3bAiGQhCMzvvva8PSX1/4ep1fzQl03H28tPP1oH7ZZxVAzPwKpXhQBh0IiUV02une2J/vaKh4a+HE2oWTL00sSvFBjP9UlYaqxPOuU3eiBl6ArPZQhOAGJgwehDnAh8+rgnn/r7yvg1/OpyIcvB9ytsOU/fcDPYE6E5gmqFETpF7GVGXSfe0Vq5c++eH9u14pjefFSsaSlLFrMX0VS+qzJgpU6mJglzQ9zRYB8bjCenFijX133Ydk1o+JBoNY0vM8StI8zAHcEBdCYCtw1ZWc7MLN++sNbl/C0zOJmpXGAZvAPliZKtY9dBtdi7zVUG90BxkkxFFGM6El3EJrNH58PXKmoYfpBx/O5xw+mp0QKlztlbSrwNlZDfm97LUsF9DyoCk0L7DVaIhyJh0Od79hHl9HXMLQVMMJXLlmzK4X8o8njjLD5bVbvizg62bzw6VT1NTk2s/cW6Vwb9BFnjMO/mn1JN4ybx+DdNcwSRyz5OgDgvXFnXFtlWsWvfN/OhmK9Y0zMhs3vU5KWgy/ALJphkUy4iDMLMeRFJmX0pd0K7KmrV/dui5HS8MZVf8tJ+iBPSlszkAACAASURBVA+Z+PncHb/pyfxPYFgxciCrRPbrwHwceHgqXXBpP3BmiMNt2aoNK3yP/0XkH8hFFCsTytaLkRJ2vwXcn3KxZxS6RYYas7/ZK0qH54GripFHq54ixp7q6up4p7E6J+LNatXEETn96OiDq0+yZ9O42GWO+UgrkfV6ar4MbDKF/ykzJfH60U2bB4vY3YI7k3uLi2I/8V4rDavDOO4S9oMhNxBEREREfMqIxMgRERERERERERERERERETcJVpxOufPusDf9BFgO9Ag2zSjWwXwhMkB7+8bUour1LxTGrUWQEyOTQJp2qjOYSDbM3I3FTPDvBM3XndWJ1tauE9A1ClZFREREREREjBPJZDJ2qlN3mdNayCoGhL0KftsbbdsujLN5+cjQxzLUeUREREREBFAUm5F5oHJ6/aPqZokZxV6uwHufTsTsQkVN/QHB98PJsec/rp5BM06lgdmtEgsATHoE417BPKAw/1iDAJiCMdnE1EKs9HJ88msO92Wh1WS9VPYOLXopBhYibhE2L31eZQuSyT8aSjh2OdOTiFkwXWRtAWYK5puIAXMGHW5AIcZsYBZmt1pGpQtXr/vGm0N4CR58n5geMbgPmA8UDDq8BKjErNCCYB/wDEBVMlma6Q4fM7nfBCr7zhs4UokD03N/C8wzX2Xnp9DUtDF//shL55y4CH3lPskbr9DUtGPwPFMvyzftnO5xqwR3YDggYyJ0cTuZXy4VteuXmzL/GPQ4ML2vOqzvXwdMAE1AzAcWF3g/o/y+xj84unPTUOLWK2JhGEexafTXWz7FQsV5Jsy4aobifoM7sx5cNTgCVgK4BTFbxlzkC+68M/kHL73U0jE4mzNnzpj3iUmYFgNYVlD/eaR1GJWDb4OswHsy0B0QPE0uulnlfRtmp9P+Z4FfQczHzNmgk8lGUJgDzDGxEHPTl9c2/PcDrVt2f+j+CtIJC4MZWLa8hGXAJlyxTIxS0AKw+TljZwZkhoxYU1G7frnk/ymexzEmDXFIArhFMAWzO8mKlGfmyuh9QkquaEv/PY9KPUWMPZcKpy8KwnCDxNxsO6AuzO3OdMe20jxuDiZMnjmYLe1P4ZBC++uDe+87PIzjC38s+wy9tLSu7mjg4zssk+g5sHbNOzwT7V2NiIiIiMKGRkRERERERERERERERETcJLyyZU0XznZ4Bb9hxk+b8bU46b8dzsvxG23bLiCdAvo935grFMGVFxcixhurrv56vKqqKXH1Q68tz/LGxgLGcT6oqakpyN5X00hDimfLoqkpweCl5OsgmUzGRrksrLq6Op5MJsdk439TU1NQXt5YMFb5fwywZLI5Ntr1fGNodlVVTYnq6uohF2A/WpbNrqpplPMcIR/hHb0WxvQ9uUY+TrZ8qnnncjDfHPcjm51Lyhjsz8TjO7mOMN0RWZqamoKbs20dIc3NrqqqaqzarGu3ZZza7usl7zkZtTHix2Ps0uyqq79+TW39GIwR+8qCUSyLMX23b+Jn+dON3W/e/iviZ4F6QR3iHsxqzWgw+JqD/zd+Lv2PFlWvnzje1o4Is2nAbWSFyBmynlePAZfyjwLmYvZzzuz/kmkNvUJk1AUcB94hf04EEoilgkdLuuPVI7SmiKxYOF+IfAkY7GHVELPl/ecKnW0YYd7Tyd5nAZDCeNfgRJ7NGYMDcvZs9r/NznfG6oT7Z8AKBgqYL4EdNeMNoLMvVZQCNZi+tuztC/fnXzwWuDeE9UWjkDHRTFXl73wwlKAXgBBbKLOVOTExoHfA9h5s3dwn8KyqXj/P4b4C+kLuHnt532Q7gU0YL+XZGQctEvZz8XT6Zz5KG9TpJ3dj7k2M54G38n8TnAcOyNgHPAtqv1p+OcFyee4+uwUnBtVNr6D6VsFjPQXxNddg7mxETvzY96zmi9fP4dgTxDgAWU/YllEj8GvAgv6yz92bdMSyeeTbNgms0Uu/ULm6/rZrsO26WZBMTkJWL3hsCCFyCtFBf90Xkd10MPOjXGuM6ylilFiQTBYGGV8neLj/+bX2wPjh0Rc3vT9eds2pfqRI2WcoT/xu7+DcgRFE4NORXbsuHmxtOXpg35bjH1FQnZ0PG9054NFnfMeHY11Goz0Pb8lkMvZxGUv3z/Nd+3dD/7fR+H1vj8X3GWMzJxjNM+YRFUJERERERERERERERERExE1Dsz/YylmyC14GzQbNwwt1mpvNb9oZM1msb7pJdCtMXbwR1o4htqx2w+JQqsNU6LzSuOBAe+vmvgW0pXV1ZcoU3ZE2Vpp0X28hCQrNbGVVTf0ve0Pm7XzoeOnV1i2HR3rxZDIZe7crqAoIakC1SPmLuUu9/C9W1NZ3GJbB+YOHdm27YuhPgOrqR4q7EqnlyK8X3H6ZY5NcTFa5uv6soM252I7UJNqvwYuVLV7TMD3u/b1m1CCb18WxSYmz2TwxHYRgT1pu79E9m0bF8+SCO5OTCgqCu8y5JQDITvYo3JuIuSDIsFZQc/B4xzzKKKistW58/Qlv1hoq+MnRPZtO9OazpPqRafF4T61HdYaVd3GshLdlFTUN74NecNiu2AQODBdSdyiqkslSOgvuwvn7BEtOddvMRFfGKmsbukHHFLInLr9n/77tb4wwSyu/q3FavDBzr4k6wfwurKyz22cqa+o/MOkAju3yunT1rD5MeWNjQeJ8plLePmPmKw4e75iVmErBqe54T1VN/dtAWxgErUd2Pf0qN1CsN5rv1ZLq5LR4PL4mFDXO7NZT3bunuLdllTX1F0BHkLWmAnv+o4boHQube7n93ocnh5l0jdADxu5ypNIum6qqmvpTSDvNBc8cbJ3wJgztSWwwTU1NweFjZ28NY5b0srvs6V1zMEo6E5MzlTX1pxD7Q+daY+cnvPShsMrXSVNTU7D/+MV5Tpm1YKsOHu+YTRkFlTVKw/p3wfYGLvbjjEZ0KwMov6txekFhqtorqDR0i+CWLmxSZ7fPVNSsP29yZ8x4A/PPzijI7B9qY81o1d9o2BIxBjQ3u9jmXXfI02C9C9LS6zLbfnTnphsfwWGMqVyz9lYpWANMwHsZwZtWlGptb2m5Yl+xfPW6mRnHSnC3AEi8G5ffc2CQt8WqqqYEJe/fFrpglTmbZ2LeweMdMxAFlbUN3UjvY5yU9FImHt/5UTwODsft9z48OQxTd3soBzDTCWX03OG924erR6tYte42nFuDUYDoUcCBI7u2Pj/sRZqbXeWWZ+aZglXe22JnukVP75rjy24pqaw5l0brz2H2rpcOe6+fvLZv+5sM0Uf2laesWuiO3nTBdEmNFbX1xZAt5yBM723f13JqKHNuZNu9dFXDwsBUJ6kas4V9hQjzkf9iRW39XQDm7Y2LbuKzJ1o3XjF6SNoUW1r34FLzmXqT3bP/+LmZTmaVNfWXQe2C7SVpXmxr23Z+pDbe6LFLVVVTgonnlnnvVuJkJuuQD1+MJwrP5PfRXVDS2R3LVNXUnwG9mJK2H92z/VCvDUvr6soIi1c4lARbfqrbJiW6MlZVs/6SzNrxfmeYCV98ta1lxCKZqqqmhJ94bqkTSWTLDh7vmJ2YSkFldyxttetPInsx413rnOKegyPtb8rLGwsKpvgKOb9Osjv2Hz83I1dnnQZvyng2ZbYLf+0amPEch0SMJpoFzBrmx6ynVbEKs6mJhNJVVU1/fJPUZ0boRYxvyQcHA2UyCtw0wQYTTcAUsvc3XcoJXkUHxhYz+xuZvSfJDCtHfAm0HgDDGdzj4dGqqqZ9Iy4L0QH2E8FTcva2EcrJFsrsQaRGsl5YwdkCPOuX1tVvO7Jr68krZ5q9T+A5wf9COiYzWehuNQsfkFkx2LeKez44ArBi9Z45GbN6wYo8QepZjM0G3w+lk4GXKes593NmPJqzqwCo9c4/trSu7vkju3ZdBDi4obaj8qndL+N4jawo2pCVxxW7B3h9sKHJZDJ2qtsqDK3sT7WjmGsFPGTblQMnOqqRvkDWwy9AN/BjoW+a05uYSxP6UpxVI34GqMlem/mGbeiMT/sJ8MKI6iXHkTkFnZWnep7yXi+7UBvAfguYSDbjfcj9tgKdc15hymdGOA6yi4Z+DPZdHMcFIL8A3Ofz6tyAZWb24NK6up29ZXu1jGVcMNgs+Gtz9r5JcY8qTXY/8IH3+rNX9mw5A5AuziyVgscsK9rt5S2Dv8G5H0s6J/mEQSXYF4EHcsdMkLHOsJeAo9yg+YPCVFBp8BD99Q9ZsfSTHv+sM97DglLJ3wH2sMHKYbIaIWNWTxGjRGlX4RLvfCPq25xwAePZS12pZxnHTagzwouJnniiaIAJko+F/tonQUZAVTJZ6lPB7UZwl0lzJead6t49zZXJqmoaLgn/npk7bsbeoJQ9Q819lt/VOD1R0HOPt2A+gPM6FcZs39X6m975FedsGYB5O+9j7sUju54+MvjY8RwfjkYZ5THkGkJRKnFgNOfhl9bVlVlYVO1wSeC2U91McfGpVNTWXzI4JGnH+XjmYGyUn6qh5uJjCveGgQrlXQNY7f7j52a7MrOKmoYPMH4Sy7DpwL4tx4fKr3x144SAVLU5d595W3yqmxmJroxVrO64iGt4DfnnFdhzIxzbfCTGYA5/rOYEx3Rt4GYnEiNHRERERERERERERERERNyc6IpCZGDxlt3TcG4B6lug6hb+9JwyOl69AQaOFU1NTa79xLlVBv8GWeAxb9J3gD4xsssUz5LRBPqcoM8TdC6c6z2ChSaE6WRM/AkwYjFyB5Q6Z2sl/TpQRu+CY5alhv0aUgYkhfYd4IpiZBmTLse7nzCvr2NuIWiKoYSyAvKUwf1S5vHEWX6wrHbDnx1s3TzY+9IAqpLJUvUk1uP1VWGViBlAqVACA4we5D4DeiJu4Z6q1eu/1b5n225yC4cflZKCYI6cfUmiIXdnLxZaMFcZ3SFjLTBTohTD4eUxLjnU4CzcVlW34ffbd21uX7a6sdJbzy94tAGYJTQBiGFgqMewB4SeSF3kqaV19d+82uRnMpmMne4puFvd/udxfjVoNthEQ0UywMvLuGiOh0Lc4Yqahr+Nx+I/3P/sk+eumGdnQS0u/CXE3cou+pcKxcEEdMtsPWItxk9klkAjXlexilUP3WbnMl8V1AvNQTYZUYThTHgZl8AanQ9fr6xp+EHK8bfXK9gdKaPxXq1Y0VCSKmYtpq96UWXGTJlKTRTknvk0WAfG4wnpxYo19d92HZNaPurixqi3BWJ+JpP+VdAXgTlCEzBiuYWrLnN2v+Qfr1x9/i/tYtP3rmZ31crkrAPHz33OnPsCsMBgGlAsEcs9T50YDYH8ST+hY/vSuge/NdRC0UehKpksPXiio9HEL+CsXGIGojgrashdG9aHYeZ+0CsyG5EXlfK7GqfH4pn1ZplHvdxyoUlkvQyVCCWy6+6kMHVLXEB8+b2e+LbK1fX/59Cera/l53W99TeatkSMPks2PzNbCurMmN+XaNYeC20719knfSwJY0vM8StI8zAHcEBdCYCtw57T3OzCzTtrTe7f0ifm0K4wDN4g5z2vqqopYaUXKr073wSxdZZ9l0uBEuX6j1y/2424bNj78XRmf2Vt/V/Z+UlPjsbisdLd82TuZ61X+CLbi7lTwJBi5Orqr8c6Y2+uxtv/jRQAKTx/AXxYjNzc7Cqefm6+bdr1mAgacbbAnCZIlADFZrn20ugBOg3rCAL3RGVNww/lw+8OFkTLXLnBLwN3Qb+nPsEkkz0I1AKY9BJWcA74kBj5RrfdMaPaG/8OrIys8C6L2VyJnzaRFR8bWwv9pUNkvQEOjVlBkGGdI/yssDuB6YYV5frgDGb3GXz2cpzty2o3/OHB1s1Hr2LeuIxdCqZemtiVYoOZfinbBesEQfBUJpMOBvTR9NVJl7D1CeOBZbXr/+Rg67atS+vqZwUZfUWmL4ObM3AMbhnE/VjwWBBzO5eufvCPj+x5+pWr2bWsNlkunf8Zkz0omIMxOb9vlc89G+bfPtUV21S5Zu13Du3e8daV8qxa+dAsudSXvNmXgLmYphpWKANBiLgINBZIm7y5M9fi8mw8xyERY4PgvEntMjtj2FzQfLL1CoYTLDLZo0w4vw/YM67Gjoy9JvuPPWnteqNt83mA6urqeGdsygEzLivrJTb/e/wS2A8D/H/25ye/fijXx61Y0fB8WBK+I+9CGb0eiycYWqypF6YC747AlgymZ0Pn/2MsER5qb2m5DM1WlWwpJpVox0uYPQ6AKMBY4jK2DBiJYOc55P99SaZ4V1vbjzoB5tY2FU3OnH02pTBekIqfaHulLQ0QuvQyYRsQvR4XU0CLC91/0aUJh47k7nlBMllYlEqcMK+E4NHcsaWgu4NM0R1A1tNyc7MPaxsOB57nMHq95y4SWlPe2PiDwUKskz1uZoBWgPVuyr4s1F6STvSNw18+8cEsp6DOIN+78gvIfifzQeyZo0f78rRF1esPJeKkDJsJLMRwHu5C2sA1ipHZuDE8lK3Ld6tq1i+SWar/W9zed87aDu3acsX5lEGkQFtx/IfOROrwsZaWboC5tbX7JviSN8DSMr6QO7ZEaHFBT9kcYCTtZLfBZgvdvy/277/a1taWBqx8deO+IKatCUunE10dxwGVNzYWcC5zt4n78/xafgD6Xkrxb9x1S+m7GzduDHPnvxC31FlwE8iOdUDMEapdvrLh+8MJ0EaTpqam4ODxjqVCq3odcQrOGzzpvf12T3H47rGWlu5kMhk7nkrsLvAcFfrnffZeO2NZTxGjQFVVsjTE34u0Ni/5gAvth8deaukY9sQbwPtFPT1lSgwWs87JOFWSFdCPClXJZCk98dXq1k8Ztgo0TVAKlBrKzYcpA3QJXfKe0zrPc8trG751oHXL7vy8gkRqNgRNJj4DIGfvu1B/CvzPK9ngMkXLMPsNlHvXTK/FwvD3GPQujNf4cDTLqJeh1xDCpy/Hu/eN1jz8ktqGCpfxXwOrxzRHxkQTBQJMZDAeMKw+nk4/Ca5wNLX3Q8zFv+DN3YK3uw2tF8zq/dYzUw9iTRizhypr1n2nON3xvVzfk91olApWmg9/XrhVJmZhmmhQKAODNNIFwz6nkFcqa+v/qjhVuLl3zDIajMUc/ljNCY7x2sAngkiMHBERERERERERERERERHxCaS6ujreha8V9khe8mmMV292j49nzpwx7xOTMC0GyMrjNCCco5wKTTaLgV5jeinN/WFYTPKDQ0ZeEQvDOIpNY+DCWi/FQsV9x2ZD/V0Zcb/BnWCLQINDjiWAWxCzZcxFvuDOO5N/8NIwk/XlqxsnqCf9uKTfMKPCNCBka+/1CvI8Zy3AbFbl6ob/cWjPlm1cx4xoSFBk+DnkysWMSRIrDKbSK/bpXTjLenCakP3TVIUqrqxt2Bkq/IyhB8meM5gCobnALSbdahlKl9bVf2M4QXLWY1PsXssuat2fvdYgeUbWI9ZEYKKM+SaVp8L0jPLVjX80pMfo5mZ3+qmdtXL+X5IVXBUzOMdsiNFbgKkYy3Iiq5FgFbXrl5sy/xj0ODC9z9oPlZsmIOYDiwu8n1F+X+MfjKaHy+G43veqKpkszXSHj5ncbwKV9IYUHvjUxcmG8Z0OLDDPfJWdn0JT00Y2jszT8GjaPIgZwBdBcQaGaO6lSGIRcAtotso64sBfMIyocknt2ltQ8A9AXxfMy9s40ouRmyQH5hosct5PK1+97neP7tl+1bDCV6K6+pHizq6ez2L6VxiV2UUl8l+R3msvxJhq2L3kvIpdiaqqpoQv7Fhvolkwz6BoCFGUka37AoyJYHMR5eYUL1/d+J/y373rqb/RtiVi1DEjfrvhN9C/TnHMTDsqF0w6eWDfeJo2NnjpnMuKBrP9pDTJG6/Q1LRjuPZt+aad0z1uleCOXB+QMRG6uPX1fVZ2tly4XwE+D0wfsG1gYP9RnPvrbV8nWun588CO6743C4pAfWMAzI47+aLhjj8/47hLnLPJIjuWA6WdbPpQxy7ftHN6aO6LGL9qMBtpqHUtAwqBQjOmgOYBc825NPCn5LXDoaPEvM3L2ZufQUBW8J0VfZs7bS5TwiDGo+32pknkvE4PIDvOm9n/X800n7pyeGFppZmVK9uuFg76NZbzVjfdYJ73vnBZ7YZvXEGQPG5jl8uZnkTMgunqH4/PNGke2XHE4D7alHv+hU0BSivXNCwm1HyZfQWYN8QQOAZMB03HmOcsnFCxuuF3D+/Z0jZcWSxb3Vjplf5V0E+RH2o+v2+13OK3MS/rqTWYVVHz4DcOP/f0saEyXb563UxP6mfA/glD9IUGAcYkYJJguonzoKv21zC+45CIMcI4aJ4/wYKdgTLdBPESvJ/l0aPAl4DSXFt3t8c/SHYz78dZGfEO8HcX3aUfn2hr7fP4nhXONL++dNXuJ51TDbCm7wyz/Wb61oHWbYfJu7dXXtlyeUVDw87MRV+OrIbcuFZmZUEqM50RiZG1X/BnZT0dL7Xtzop3oFntLVxakEzuLehK/IXL9mu3506YbeYruNKmo2y+75tsR2dRuPNQy4+6e1NPtG7sOgEDvP6VlzcWeB8uxum2vOSXDPvm9OKegy17N/bN9RxraemeW1u7b4KVfhuxsM8uMV+BW0GvGBkoSxW83RnrbgO+SHYOotiJpbGO9BJgf74NsTC+COdX5T04b2HWmi9IisEtXizPbtoE4CiyvyjOFOxqO/qjfHGz3mjbdn5pXf2TFvrF4P4ZkDAxDdPSpXV1ZePqvVa0y/QXhxrufYXm5r6xxInW1q7yxsZ9sXPh3xtaQ3+/MyGd8DMZmcj1TRM/at9Xewj68lbu+2PAN0hwITPVoFLWt4kqY7Bbzv3p0d2bThzt31ago3s2XVhWu2GrCOdJdivZTUwxZLcqzm2MorhyONpPXJgItoDs5n0ADJ73nv91ZO+WY+Tezdzc5Ony+xq3xNKZKvuoYuSxraeI0WBiQZWkR6x/U937YD9WcWrvFc+7AZxobe2pqKk/Z9nN2Lk5PlU546tLV687dWTP9v2MQl/pu2P3gP1rg7sZfm4lBlaGKDOYLWOh98SX1W44nT8eDwnPOtl5zLLjYDEXbM3iNQ3DbvirqmpKeDt3u6H1uQ2OgL0mp7fzjxvP8eFollEvQ60hCPuCQcNozMMvqW2oCLz/x5g9AUzL7pEcZK+YLphi2HzQSCMejojBc/GISTLdgZiKMWnAHFj223EB0nTMHfugrOzvgHR1dXX8dE/8fqTfBF9nfc/HAOLAVGXn6281sbAz0TOlvLHx29cQxXFYxmIOf8zmBMd2beATw+AXKyIiIiIiIiIiIiIiIiIi4iamqqopsXRVw8KuxJSvydu/RCzN/ZRBekEuvMpC2CcEZS4adghoBwaHmH4f43kZ+4T2IQ25+D8cnX5yN+bexHgeGODJTNlrHZCxD3gWdNWJ2JxguTwn1ugWnLCsR7tU3kEOuFXwWE9BfM2QGTU3uziZeyX7DRO30y9ETgFHDXvaYPsgmycI1mL6haqV9Xd8ONOPjsQk0GL6F8wuAMcwBk/gTkE8JvSvDD1CvxA5Y3AaOEZ2UaAXA5uF2WOx0OqHu/6ZzoJlZvZ10FryPKoC3RhvA68OsEUUIJY66efjLmxiiHmzqq3PzsW5xxh6sjGVDdvbZ2thTnRzy3A2Dsi7ev08h/sK6AtAviDrfZPtBDZhvJSXfxy0SNjPxdPpn6muro5/KNPR5rreq2bnO2N1yi4wr4ABQvlLYEfNeIP8us569qzB9LVlb1+4/8bb/CGKgFvpX8S8DLyde07zKcBYgfH48pr1SxmCpXV1Zc7bw8CvgN3aH2LZLgIvAk8JduXlnQs/rS/EzX5h4ep1M4fKd6RcjvVUmukriGV82GHFZeB9+tugCcBC8r1xDkP7E8syeKWAhGXLC7Lt2jHEM6C/B9smGyCsMGC6lzXGLL1+QIbXUX+jbkvEqLJ4TcP0wPvaPA98YBwM07GtGz/CxoObgVjg3hDWt+AuY6KZqsrf+WCozU0AhNhCma3sbyP0Dtjeg62b+/qv0MJOmULy+o7ceORFE5sxnrTsuOT9vKyLZNR5p6bFaxquvnFqHEnHSjoxebLizt726hJwSGIH6O8x7WSguCYOLAU9VlW7fsD4RhnOgl4kO77IJwOclLEvN457Wdh7+QeMW9stTmK2k2x49TxP1urC7GjWXtvrzNqVSVxZtGU2DbiNrBA5A5whWxaDw8dOxXjU4x9mmLXEj9nYZaR9dInEvXj9C+DnyBP45t6bY3y4v5ls8IiZmhYkk4MF3AAsqf3sHO/8l8C+SL4QuXc8Kx3JtyUnCJ2D109D+IvlqxsnfCjT5maXsWCVN/uH2JCbci4B+Z7appEVQl5ZkM74j0MixoS35e3bzrn/c+i5zS8c3LO9/eDup/cVpj942nv+CNiUd+wUh1tSsWrdVcd248xx8C+caO0XIvfT7OOxzFtgBwckex1LFKTbGEI49sqWLZcNHcXy+gtRmjEbYTnYkcCCll4vgvkca2npjjl7ibxoTRgzPfbhjSQfzvct72xfrzfXK5GY3DUZ06353/pCL1OY2jnUpvMTra1dXsE+sD7hMWaz5H0FeW17W9uPusxzQOjl3jQZi022Oj+/8vLGAixTKWxF/21yNBHagGhQXrGZZizOu8dj5nzrcB4Uj+yqOyXZPtC7uUwdxrQCyobaAHoD0TFzvi1f4NrL0U2bepz864h+8ZtRijTUxuoPY7wRhpl9eULkYQlSzFD2eyx3KqeAluKeD4YU0x5s3XzOW2wX2Av952imwiE2No0BZunJGrgx6ALSC8GlSa8wxLt5dOfqDwz/CiPzIj4EY1hPEdfNgmRykkf35wThABi8adLhzOWgcunqB1fcfu/Dk/mQ8vCG4V3gXmeAJ3YrE/aQs+C/VdbU/9bSuvp7rttGpx5Dnn6RbYZspJu9wFPCnkYcZOD85wSZHpb8E8lksm/eZmLm4ns4XswbF3PxfAAAIABJREFUp8WA2+Kh7hzu8pr0weycI4xeoelloUNFPYV9wRPHfXw4imV0JUZrHr4qmSwNPGt7hciDfs6Q/aY4n7tmduyf15aPCcYksP65+Oy894BvPUE7ni3HkskUQFdi8nLv+WXDHmCAENlOgW0T9jSQ7yW4SHAn8A8T5/2Do2H2WMzhj9Wc4FiuDXySiDwjR0RERERERERERERERETc5CxIJguLOmPrZPw01lHqYLLEXGAufd/+egXpz0u7L7xxpbzGmNkVNfUPuGD91T0zZ8Arcfrw3pLX4dpFSd2FnCrsdv87kH4i808oG44boFtoc2D63Yw5maxbfkQhWfs4Mqegs/JUz1Pe62UXagPYb5GbKDW0D7nfVqBzzitM+cwIPb7ZRUM/BvsujuNZTwp+AbjPIzWSFRUYsMzMHlxaV7dzsIegyi3PzJMFGwyW9U8Yc1To285rhw+sIwgDZ0E4K4TPm+wrZL2KloDWEtCeTCYPjIHn7KOI70ja5VCnBbESydfK+DLkRGjGJFOfaDmFtEfo2x5eC0QGZ7Nl9lnE53I2g3GrR+uW1K7d9mrrjnfyL7hiRUNJOqY6QhqxvonBFNBqTn8u3OuCjDObLoUNYFkPdtlyKzfRWLm6/plBIdnMh+4OM/9ZZHmTjfa6oR/I2fMmnRFMMM+dcjyEuGckBdTU1BQcONFRjfQFej0yQjfwY6FvmtObmEsT+lKcVSN+BqgBDDHfsA2d8Wk/4VrD2F4j1/NerVi9Z07GrF6wIu/5PIux2eD7oXQy8DKJ+Zh9zoxHyT73BUCtd/6xpXV1z1+rZ6yxaQvslBk/xPuniAVnTYrjWS7pyxg1uYMSwEqPqwcODc4hpsIKb+5xZdvpHHpB6A+dBS/L1Gk+k8CCxWA/jfRY7qApYPVFxnPAd6+lLHpZsaKhJO1Uo2yY3/wJ+/2S/tLBIZxd8iEznGON4GFGumDS3OxtzUPP41NPgX0Z008MfmShXiOwS2SCVOgyAYpNdaYHJL6EaSmAwRLD6oDv9WZ3XfU3yrZEjC5xqVJYPVKvmOYkYmfQWfYmQMWqdUtcEHweuE1IJp5PdKf/ajiPRGOOmIRZfWVNw4gON/NpQr3cvnf7zt60gxtqOyqf2v0yjtfI9n+GrDyu2D3A64PzyHoHsgpDK/NyPoq5VvI8/boL00/6snM7nJEUJATfNed2mzjjLexyLvAhvigmW+C9vgJ8LndqKVBR4FnIhwWbHxuO7Prh5cq69TsVaodht5vpSbBt3oITQUad8qkMsSABNkvwCOiLZDdPxBG3yYLbyS6eZ4l3Hgl9yX+OoSe97Gu5iAxgnDT4397xIwDhLhZc5ES+LePVdjvnnhPhr3u4B+xXDXoF1ocM//ve2StKi4T82bkTU+eGc2OcR0boRYxvyQcHA2UyCtw0wQYTTfRvPpmNuL9i1bpNh/dufzU/g4/v2GVEfXSvN7fsGdl++tvI9pnCbsViEwj1AKYvkRMrZzfZUVPYWXgX0Drwms3OaffdQk02MLrHAYn/bY6XZK7L4csQNWBPCKqyF7dpBuvihC0M8p66YtOeORlTUgO9Yl8Ga0X6AfCmIGPO5oHWIR5iBFEMYHzHIRGjgzxvY/qumbVJhM7pQFzpH7zS2jIglHhbW1t6QTJ5oLg7vkPQSLbtN5mmyeK3AB+Myw2MjLMB9s5wP3YHBRdiPnMmTxnWjeP0Sy3JC9Ay5DneWwemU2DLc0kxbIhoQh/CLoLeOti6edhQ4F2p8ExBnDf7tGqiwLJtjWOYSCk5Okw2IhGmi7uS0Nvkfj2nzpq519pbWgZvKOljspW916Hz/d+1osDkJi5IJhN5AmilXOxIXJndGL3jjnlmWrm0ru6ve7/BYtM0WwR3gnrFSu+DvRgPPxjQX+JVistvDxWTt9lVa+qH8S66C3lmgPULwTxlKfz4CkbNzqcnFpwa7mfvOG8if+NSHG8jeJ7AZOdLFQyb9wCcSpFN7X+0eA+nI0MJ4+k9xHe/C7FXwdZD1gs4+CGjUIw2Ph0vJOZL+2XHdkb4o4faN6aGPqPZy+pPmezY4MgVI2IM6yni+inuLLhdzj9GnsBQsBizfxY457EwzITh+cqa+uMmvzfwbNu/b/sNnbv26Uw7gdtqYhX9m7omgx4AqszTlCF1tnL1+hOC18z0pvfudcO/eXjv9rOMwHNyqsfaE3GeMliO6Q3J/iZw9lImowtB3HXJh07mykz+DrCvAPfmTp0huP14KjGF3DdbW1tbesnKdYeCwNrI9u0AS8x0H7CNIfocR2yxN63qs9TsGOi5AV7tx3l8OJpldHWufx5e3QVLzPyDGihEfg/YatIO4U4gn8CsHONhYFiHGqOOcRDxLby9aAq7vdkMZ7ZGsNDgKStKP0Nzs19a92gZYfd9ZqqnV7BrnAH7ocNtzHjedYH3ElNNWg/202TnB+NId0p6ZPGahtbhPHKPhDGawx+rOcExWxv4pBGJkSMiIiIiIiIiIiIiIiIibnLKMiVFGddzp2E/JREbJC4D2I/nd9OW2HGFxYobQY3JfkfhCMLbGThL/7hq5Zn/2r6PkS3Q5JFbVDu2YkXDmXSJ3YP6LhmaOHlw9/aPHgB+48bwUDaM67tVNesXySzVn7+975y1Hdq15eyVshhECrQVx3/oTKQO9y4Izq2t3TfBl7wBlpbxhdyxJUKLC3rK5jAopKR8bIWhh+id7zHO4PV95xN/1L7vqffITY4nk8mDpy/H3/OBSiw7iQjYVMGq05cLlgIDvUtdBwaHJPu9gPBvD+zdfjprQ7NbvnrniyHWAfabfDiU9m45a3YFmbbeRdXy8saCYGrqsDPXA/xC9oYpwGxBzLuFZEP49pEq8YvMWzLPKzPACzj919gl1/LKK1suA1RXV8cvFU4/bGGYsazIMQHEhe7AeIA8zw/lqxvLjEwVskV5eZ7E9JcZwj/yEwveP7ppU091dXW8JzZpd8bzjplNBsvzCDU0L5/4YJZTUGf9ocaz9sp+J/NB7JmjR/tC3tmi6vWHEnFShs0EFmI4D3chbWCMxcjX816FLr1M2AZErxfEFNDiQvdfdGnCoSO5hckFyWRhUSpxwrwSgkdzx5aC7g4yRXeQF054rG0eCsFp0F9Iwe/NKkqdaGnZlgFYVL2+rTDOKWG/AfR6EJstWD63trYo36NbdXV1cae3e8gPKS0dMbM/8UHRX7Xv+mHfAseCZLK9qCt+GWdTkO7LJS9GtvbOO5NbPoow05cGs/CZO8kXLBkHDfuGvP+7GcXh+ZaWlkx5Y2NB4fmevaF3HWD/lN6NAFdhZqLznXcvFf73WDz9I5O95Trd273vXD/NbmndriMutBjwW2TfvSJJ0/LL63rrbzRtiRg9FiSTk6ybGkx5HmutHTJb23NtgQvcPEmPWy6kuKCsu7DwafiQd/0bg1EMutf6Q69fEcm8Be4vgT4xMs3NPqxtOBx4nsvzCL1IaE15Y+MPBoc3PdnjZgZoBVjvu3pZqL0knTicf1x7+8ZUxap1LUi/rMA5l4kfWTav5MxgD9MLkskDRV3xThkzDOqyhjJJYvY1lcWNx8cvuv2ZUv1LeT/NK37UXSg7eXiQoCWZTMbe7Sp8x+FLMH0VALMpKBzgUTa3iHz4tpXrUnEXrFdO2GOiU46jR3ZtfX4oI8az7T7YuvkscHZpTX2xy3sHBOeN4MCRXZuHtPkK7DXZf+xJa9cbbZvP5+4v3hmbcsCMy4JfI9sWxoBbCYIlwAAx8sdx7HKNfXTWOOxlD7/j06knX21r+QBQU1NT8OqJD15KEVxE/HP6+8tbzIXLGCRGrlq5dwamWinfCyivGfrjWLzg2/uffbIDEM3NbvmmnS95gkuY/y36PSgvM9OGqqqmn7TnPdeZ/5+9d4+O67jvPL/furcbb/AhkqIkkqJIiASaFBULIgGQogOLBChIpuJHaMePOPF689pNjvM4OTuzk0mQmWST3cTxxvGMPXMyO3ESO4lhx45lmxIpyrAlPkAJEsUHCFIQSVmkxDdAgkQD3ffWd//obvRtoBsAQTQBUv05B+egq6uq695bt27dX/3q+0N8qWgehRRcy33FWvyZT/eVno66a0Cramu3lgwVD77uW8ahZN8fg+mehxSYGry7wm+FL/LvfHolNEbWj/cf3N+e9R30VHv7YHXD5pMUTyL1HBNKjbWzs+WfMVAxnzarki4A2IF4jCEMBIQqYwQGxlKapcEQYK4r/f4OB3YCSpcakJi4l3NQHJ0TRaj36ogMblVVSygwJmarO2qI0WHAs2FNWLClHD5mjlRIH8XevW2D1fWbr6XLADAKzU4o5A+rMc/yzp+7HrrrNUIXkXCsKpK4kvHi1UiOe4b+ciWc9VKcsNbuHWlnMlSxMsO8PwyDP5VFDmdUgGClgsqBRJjyRyoO3mq8nu3bc7ZZcT9G1w30UULSBPoTIGJw2bI51zo7J5DZsAhKb6KBcN1Yjjn+xk14IOTrCodbY4vJib3P3TQhG4JFIJKABoxMTkd+ALC0A47MyMgEEyVv16nAzVG1sWW+9bwPUHhkxFdzAc0dHpYEAYiKZpPvoqm6oflrC4tiz+ZBLCEr3fs39tas3/OvkJYB+ATSDskhAPdSuBeAQEZJXIHY7xhcAczZmvrmDhr9oGTo8pGxbO4nOp+/uqau5Ztx+Iesg94ww28OzxHTsKqu5XCIXhyJDXH3A6Cg2cW+nYeAo23Idd/0pQ5CKWfk2QAjNesfX3x0zwsZUfwWNTSU+J6N0DAy/ENATyigaj8T5odTfY7GYCrs8BRRDYuNgcfrdRA7jLV/XuyVnursfCaKbdvMshO95eGw3qRMGAk13XzTJWu/5Bj3W0f2PdcLQJHItrA369K+sEylZ3X+aNLe7tiBKoCbkH7fiQn4sWP9v4osmXUsbVNoNWvqOt6M0TMEfhsJReASgO8rtqoH8L3JNjYfNvwUU20TzOfawJ1G1tBKBQoUKFCgQIECBQoUKFCgQIHbh3hs0JAMAwhncUQGgPtkzKNhLz7di41zQfwMgPdN5E/kcusUZw2FfEchdAn6elfzhoPB0Kyn9+6NxuaGXrbk95EZrrIyHrYZoe8WNTSUMGE0TzmEeAD3eMT/7Hr5h2cRMNy2t7d7uD67i+I3AKQMzwS0yBq/egoPLCrwpeKw03a4Y9ewMzTQag937Drn0mwHsSuzDN8k8C/myuy9QXWnnp7tQ/eU+F0GeCYZki/5E5hFmIWjf9osBZhe7CDfFPX1UMCICSTURO4JDb4J6/wzFFCjIxZD+JlgiL9iZ2g+yWVA0JmWL8bpf+343hfOpJzIOjs744c7dp2j5z5DoQ3IveCawgXug7AaaeGAHohfL/WKdo9YuNaJzuevyOEPAPvNVN0U5pFauXLDhoqRdc8Eqqpaiqw1y4Fh5zsAOEDwb+eXDh0JOt6cam8f7Ff/yyD+EcCh4dzCEjlmDaYZI7wG6mvd+549FVwYO9H5/BVrtYvEc4HsLmHnlg2WzwnWEcWceQRqkDb29wLYHhtyv30ssMADJM5HHO5L8vV1ginFsRIYLB0scbOFbB8XWW8hAtdCwHmI33Wc0He69++6lDqunu3bhw7vef9JEd+EEkqhE6G9vd079sqzx4/s3bjj8L7nj4429ANAqz22e+dZUJ0IbCYgUTbyfN0MM6ktBdKURN3q5IJXysHkEmD39TOaVhEXw4AqlMhTKqDEM3Smo71JCLBCwKKJ/AFYImlkqFZUxIp+CqAT6WdDqRFWun3xFSPzun5oGcGgw89bILOGOO/ev+tS1/5du7v37vxJ18s/PDvSERlIjCeO5aHk76cOqpL0F9z46bi1HDy443rXnp2vH9238YXufc+e6sqirNfe3u75c3kMUNC5dTbIKXG2nu6xewo5A+Df+s21H53ofH7Y6aezszN+tGPDm77lDwAMOzdTmGOsP0qlcCbOXW7wGY1ECF09H4vb7x7vbL+I5Fy1ra3Nf33vC2dk+UMCPwmUmCOO2kQHOf69yXORmiP2gvihkb556KUf9KbqRWurPdyx63zcet8B8J1AFeWSlmNONGNOK2gRpKDTSDfIfxgqje3p6dh+Nelwqc7OZwZs7+yDBv4/Adgz3nm6g/rye5qe7duHul7+4dlj+3ec7N737Knu/bsuYUxlRtOfdDIFAAgqMu60O3qOjQVIk/OYjBsSweD3kjiWAjFAStaOvzl6ZDEwTmMHx8rT1bXKszIZTseCXOfuq+FcZZKVe5bxiW0al0IGQSdPxK0wZrsACGAcgfdSWYRi1zPqQWdnZ9wxfpfA4AaXBw3NeiDhqAaoBonxI9X4k9YvGelOS0u4yBTFmwPhZwCsy/UnoBqBcOcCHMIJYXoRxrivjONaja16PUbNstnma9nwYUIgh6+XAM+zGMPBHSg1oTioQB6GbYaKY/6wPh2AwWvnJTYC5MYVPQGTFU/I33UqcFO4nheh5RMI3Ns5YDLPUglPUvrtswPhJwDcIqfxVsu+Wcd9a74o8ksATuVsY2Ij5woBa5MRB35TFn9z3Z3z+RW1jaPe/wLoYMf2M0c7duw6tntnZ8YcMZCnp2P7VdIcJDj8bkyw3DpORt1HtjT00eJ1pB0wKWC5fDNKhbXCli8i8T6kr8NFCAeCqvYzZH44peco96/cvB1+5YYN5ZRdnOFAS74K8m+PtGzsTr6zC21t/onO56/IDP4YwD+C+OlET8Yk8Qi95gL/ltzQKiCxgfn43hfOHN73/NHknBEAIHCpEuswKV5zPPs/IkvmHst8RrXagx117/g+2gB8P52u+/3EWs/kyYMNP8VU2wTzuTZwp1FwRi5QoECBAgUKFChQoECBAgVucxQqi0G8mDQAZlMSmUvoF+Ca36het2l6w1wWyIJO0dhOtI5WcOrZvn3IyL4JIR1xmyiHlHEdy0z5HIKLkF7w65Psa/cVe6NUAYCEERKOfwRCYOHQLKAxy7LlnyTnIb3+2ovbL2b70i+Knc5wLAYg6S3f4pVcTkaenFNKhNJOlagQM529amtrQ4a6F1QwrGA3HO3IZnRsb2/3woP2IAx/nM6OIpIL342HFqSTOFdS0Kh+lsCenvvuyrZIgaOdDees0W5wtDLDSKzcu8mgmh5P0disDmcAcGz3hrMSXwb0biI7DIh5Rai48ZCmt4DwnOgcUPdDwyGQY4JeR3HsxWxKN6f37o1aOS8DTKsgkwtlbTWm154ZE/WmuTLnWLYvu/fv6rVANwNKLBYoc1yTYbxWyM4DeH8g6QxgOnpe234hW72JhRa9Lmi470uanzDY3ziWnA/igdRnAqdE+2JyoWcErda7EDpO4icAcirTZUFjqdKlmiKpFwiGzGU4VOKW3MDv3G5tec8TiTSWk1gLKKhOehTG7HwvqFB3dj4TpcVhQa+n0kQsp5ih1lpV1VIEejUChzdhEOgJB9SrsmAxTojgAWuvEhoeo0QUiU7ZWGVmEOPey8nFv8sAUhuaQrAqwRQ8O6Z77J5C3gbsq9nvt1Ybcr23AA7Pz0RUis4oh/UZOHe54Wc0iHdIvRp0yg4SdvA2hMOBpFmU7h6VUXYhgKpAygmBzx/u2JVNmU33lfk/JfECgo4u5Dxrh4afzVUtLUWkswDC3FSaBY57nv+joNNEiq6utph13ddB7s52LBkNuHP6coEbwNKPCxzuOyRDFs6dv/F3ihAsoXGc4loBmEy1VYJyQqGxnZ/HcboOEgdgxRt2pjakgdLOwSRkjDO6HrlvAugIpCyQwcNVG1vmD7hz77MJddNSACBwGrT7jnfWjlRmHukkPikIxH1xPEfr9wSELwRCxACANLait/U9mszpj6gJRCmbAoyxFsSwE5sA40NjRmz3fTokpnPjYYEppqqupRJCbWY0HAAJp7w3AHxH0Nch/ARA0G5YCqCBRr9Y3bB59a1qb1dXW6zCv9jl2dhfi/wtiH8hYDfGVp93AS2EsB7kbxs39LuRtY2jBRPSCBN4Z/PjvCJo2DZBoIgWme9sra3Wd9ANDotMgEAVYR6LRLZlbIIxxiwHWR9IGqVqP4Pmh1N3jnL/xE3b4UOxstlgRoShQcge6lf/y9nqPbZ7dz8NXhmxcTYfnAdx4HDHxqzXLUgkEglDWghguM8S6hky4T3ZN8u02qh77RiQtkkImE1hydLGxknNKfNlwx/BlNkE87k2cKcx5kO/QIECBQoUKPDeoGpjy3zX836DQimJnV17d+4av1SBAgUKFJhpRNZt2ShjnxIx4MB8Obn7ucB7gDX3Fg0cPTX4XT+E1wUU08fdINYDeBoYVu+aL+DDME43gK9NU1PPADhIYCJh9iTY3cXFsTs/9C95JT6r6Gyur63BFSpoDEMIlkXBPK41pZY24PBIj0Dp+VhodWR9U/Z6rWYnFLVT9l3NgjSFodp5mdBp5DAgd7U3DtQ07LkIKYZkCERD9SrsnMmWHwDIwauEez4ljkIgpLSDKwAgWlFRpEHMAgLpwkXvbDgjTGGQgwd3XF9V13zSEu8gec9YoMyJmTlIqmFYOCWEKocPhjgvqx7kVDNqtbDN75I6IWBVrt8GAFiVwyBg2JYry3si65tyGN93QxYLAKadti0qYrAzcrOBCZky33JOoK9dJs0bQfXrkcxhxbk+XUkba4Uiysxa2tgYzuaEcysQ0GdkTmdzlk9iYXFJ5FlACwCAMK6ceEYfpQ2Vydi5gSSRmh1Z35RTTYQ+F1kp4ALBCiM7MdWXkXVZlYsI/L7O0/JErvw9PduHquc1nyH0DjKdrSbEtm3bnDcuXKi47jlzHZ9lhml1W4nLpXSoaYH0fS9vDuczqS3vWcpCVZIeB1GZSGA/hFcYjuV7Ue4mUZTAPku2Tyi7VcwYvpytophxj4Xk7QGxNpm2mNTalRs2/Mux3bv7AcCdp3sE52cApVRjLwJ8LaheNQZc1NBQXGbK54R8zbImPWfwLcoELEwPJaCo266f19bWhvorKmaZAWeuhVviugGHHIvFCqqoGaC1tRWtra039ZvTPXZPIZcdMOdca9Apuupa70LAwymETBXOBDNs7jK5ZzQuW5qc99TVcOxqyWD4QmAq6wLMonDKSiHgpEyche8fR445cHt7u1dTt/lt0PQAWpo8gHIGn82XUWQNyhhwpDfAZXN9bs72lg7cf3HAPfnWeBqCd1BfLnAzCDJQQSl0wtBF8p01F5FvHnHtLIVGCHn6sZKSyaq9jsKScQcaCvyG64x4H84CJZmMKFqC55b4o5Rqj2xp6Kt5bs+BpBNWFQAXwoOheOxhwIQN2BB4Hz5uqN1ZHXyEIRADSKtwvmTBr5JZN8/n4rJLdN9A/jsWhyZupfRmAsClY8bsj0Oucdy4F073RsZpMM7GP1Ky48wLDYmxvc1FE4e1gwG7TQnByrGrRRE0UUfCArcDYRNfLuD9yFTkPgOxzYLfC9E/64sejcqt+DCBXwLQmMxXCuAxQzYDOIxxHFOniqRz7ulIZNt5f07fq8Y3/yz68wmziFZLRNwPsAbUCiioiAtD4D6QH7NO0UkAfztum1tbTaS9vRRxd65kKhlw2Kf1lwiYM2xBIwh/9L1ZESv66YAbfRXkx5F4RpWBWhmv7F2OpJDDyg0bKnzPrhqxifCk9YszVO1n5PxwCs5R9obfvB3eNyoGWBG4zJclnji9L/cGa58471ieyGtnJnoteGYCzrfw58wpMj4rkVb5hYSysIkvz/1OBwiakzpsAg6AispYuBIYN1LDKPJlw8/FzdoE87o2cIdRcEYuUKBAgQIFCiAc978i4KPJjyeBkeGyCxQoUKDA7YBoHwHwf1CAoJUAPjXdbSpwa0juVn87+celjY1FxYPFLxLeQYK/JiChQkE9QPHx1XWbnj3csevcWHXmif2i/sjY0ARCUcbgUVcenD+//0D+2zXdeD3bt+cM16W4H6PrBlTmCGmE4pL8EIHiYQswNQfCx2SHDfmjYELBI6juVkxO6eLPkKgs4c9StFrapiERw87IEmNF/UM5DbeMFw3J1QCHl74IIFMRiENFYcAvCVjDB0H2jggZPhrjX4PMZSQNmYYKM2TSiybWDwssGV74tRiw4yymurQDHnCV43iFGKpYYDBM+cMw+FPZ3GHcCFYKuC+QEKZmaKhla8JC2qAL8BrGVpfB3r1tg9X1m69lnDuj0OyEQ9S0OCMTGLRETgdqAEAi/Oz19HqEOPJ+hWPDEILqGg8A+LwsPpurWlElQEZo+CJrJnm/GoZhVRpYMIqGHI7Zlx2D61bom+gSYFVLS1G4Lx6x4NYjb/fVCqEyN7G4EFKGqpwqSC7O59LiTGrLe52qlpYi9XqPAvzZ4UTqGKyeH2tzwsyAVwH9xHPdr0wktzsUs1dxPatC7Czv/LnrobteI3QRwDwARRJXMl68GsBeADD0l0tYFyg2Sr1qZANX121aIDgfsNRmAIvho8iXCcNqeIHNAI6A0cqutwFVdS2VIdp1oJ66LlSbQVtEwyIH1pFN38sS5hEomfKgztM9dk8VVMynzal0bwfiMYYwMF5U7Jk2d5nMM9oKMXnKeS7Wzp8fP/J2X3S8xwJhSxR0shIG3HHmiBYacKg+pae0RQw467iKhYw1xYEZxKDIvqO5na3R2fnf49X1TdeJ9Nw6K3dKXy4AAGhsbHT7+yvCFRX9sWwRR1LQmjCQcd1jvqZnTn2bUkFg/lgZwgsulA5FQ3NGDJ9jvuvfKGE6cSsbfF+utEAuJUAAQG3t1pKoorPFYMMYn53tnaq11Xr1m4+5CdXD1CbEByXzBInzIh5IjKGKCjzqXnO6sv4obQwwaWdk8hJldnfvfTanc1EOCjNzAPJtDMZEh08HVU6YuWOVcYb8cpqMDaiDksaZb6vEZD7bR0HZUsHMGrMWz48ZYwYCF2+ehe7PXQJwgbtELFHhit8xWOEBgI8GRp7LAr5tPPvFY8vmnAk670UaG99AtKiWCj3kAAAgAElEQVRXRg6kjcnkBbJcu3xt86I3X97x9q1se3Jz2zuJv1ZTW9tZPOQOVMCoPO45cwx0N8l1Ij4CIKDerCWENq+uffyFw50vvDmy3m3btjndpy7fH3f5JJ/dvUEI3QWiCFJYgQ1oAosBjRs9pLPzmWhkbdMh6+h1gmuThZc7NOuQdEZ2veLFPvU+YNiZ9m1IexOq9s+kK5sh88OpPkc5uGk7vIENWZjg+bpuoCzRxtK41gwK/tXx3rNuBllEmT1qZpb2lIcEvzjDLEZukPDVcZ6+mfMhKRyHP6moYnmz4QeYUptgHtcG7jQKzshTSuJBlPqUKxzVdPPQY0/N8f2hpYK5n7KLBeMK9i3IvOUYniyop40m9TIPAOfCF/VeCBlYIP/U1m4dfiCOZygqUCCfrKxv2iAo5YiMcFH8X6azPe9VgmMC8E58jAXGAgVuWxY1NJTcHZtHYGqffYW5Whrfi3/dCYX+XwAQ9MmV65q+eGz/zlemu10FbjlKqoaeWlG7tc0JRecCXA6gHEAYBg9amNXICDt1y7jcvXfn4XFEVDI4ns/WzByEMRbZjONajfS4HVWDQiDTqnUJdaSlyb8cjKqREp3kFze/BCTJOM6YSgw+KQM7LGBISlcdN+dv0zgC42PW6VCuZ1kUOLwYofGfDXRigAZTRy7LEALKDIQTEjR8jgV4sBjTOOqLHsGhcbo8LeEy0043B8KcnCUw+gIJcAycUNbM040UMmRxoM1xO77zgwDGEXCokUUodj2LOuOtQ+TYCnIkRSs71hX3YUKGKg5E2i0XUH2DTXEoTOZ608o6JDOU0cxAbEwnCQt4FIYmMjCsaHj8PqfP/6TEnwewVMK8DCW2keRxwXkmtaUAUNwbX+YnHJFT49sghAPGcfZOZ7smiCfgSs+L2cPU3gidnZ3xVes3dfnWeYXQE8nkBw3NegB7a2trS6NQDcCadKnR6lUpGhsb3Qvxoo3W2v9N0hoAi6CU88/oTn07LoHVPNq8WvR+BWAjoSUAZuc6EubpAKd57J46LEDX5J53uiER3ni+QDNx7nLDz2gSStza2Wlra1Okrtne8DxO8Nyh0YqjQSwZpzQUWJQOiek5Tth1HM+34UA/n+B8VjGJgxzDGfmO6cvvbbjm0Q+s8Bz3g+eiWiN3sPT6QOhfAfxTzgLkHEjpzQDCkEOMsXG0wAhKAN2zqmHL3Fzr6F6s5C7QW5JOUZTgFUzhDJPW66fhxYBP1Fxj8EBt7dbSXH4JA0XX58N3AnYBRUFdam9vjAGjAz5UxkveGnCjnSA/BiAMYQ6Jp0FcSdoZQPAtWXRkC6EOACL7KJxFYtMVIC2k7IMAsoYxLzA2npx+Vzof6Eh3A3oQY9huDO3dgKkKfH0FYKYd0AnFJEWZfh7MRsKxK2u9VS0tRej150IqH2tC6RJXLHku9ZwRMIvgmtXrW5Yf3rN9lINmVV1LpWV8JcD7RlVW4LaksbHRfXeQC0xgE6SIA5b2H7s7d/0UI95qutrbr1XVtfwohPgDANcAmIWEgMLCEO0iJMQ3polW29mJAQADSNrSt23b5hw7c+XluHSAFr8mYksycwjEMt8x1QAy+npVXUtl1+neD8rwf6W4HMBCJMbYLEz4sTE66g6xhEDdmubmbx3csWPAAx8k2TBs6xTekDBK1X4mzA/zdI5yFb5JO7wbohRWuhrPpxlz/j9kjedCMU58WeSGIeGRY9uqU2SxnwMJR+MxN1+NRKTjoWhSvqf5suGnmGqbYB7XBu44brvwWzOVVQ2bnqiu3/3uQGjweuqvuq65drrbFWTVui0PR+qb/qfnxS5LfBXSdwR+CdBfEfw2qVes7KVIffO3qhua1093e2cS5wZDL6aua4XKByJrGxdOd5sK3N7U1G/aHBwvzg6GvjDdbSrwnoUG+MvhD8CXD7S33/mh0GcYkfrmluCYMBCa+4PpblOBAlPNqvWb1laofCDVz88Nhf6/qar77GBoT3CuVrWx5YZelu8kjne2XwTwP1KfjcFfTGNzCswAjnc+c8k4zh6Qh4YTpbt8qyVjFCtwG+IZSuDNhtmNCYgCrbejn9JNI4nIUESw8JDeN+PTF5hplpTGtk0DAKHx8ohTYJEkEPfFGaluFgdgdePHaEgDpZ17SMgY57a33hK+gJvVfGKM4GQ2YOXob7NHJwULSdQEfBiXNjbOduB8CNLnAawjsGBMQ38emUltKQDU1taGfDprgeGFWgDoAezzR/Y+N6aC0B2J3DcBdARSFsjg4aqNLfMH3Ln3WeERJNUECZwG7b6EetUo+E7MeZ/17W9J+CCAFUiHRL8jqK5/Yqkc+0sEfhHQGmmcAStPTPPYPdO44+cuN8CknqujVsoBcdTyd35WrAt9+fZn27ZtxnNDj4r4HZDbSDxNBy0rNzRlVQiMrH1yIaQGAItTaST6jG/fvWWNvv2hwPdZa59CFv+KpY2Nxdb69QA2B4qcB3VyKhth++f2QhkhyEOC1g2EB7dky1/V0lIkmQ0gngwkn4f4Zq4Q7p2dz0RpeAjEQQBIzp8fAPBQKo+gHgD7crXTDP/GcIkIiJaVGzbkVN2NRLaFV29oejSyvunTD9ZvrsmVb8KQotJjHcGQZ+x0bmydNAzZCxYKOHJzvgEaa+q3vC9b/hW1jfNo0Ajp0eFE8YKxPBHMF4+Z60YZSp4lIqtWr29Zlq3e4t74MkHrxnunSvRTO9xPCTgANvjyPpkpypNw6nQZfwTiUyln9wK3P6f6UG6E+Qhs1qLV6QENHM5Vpqdje78su5ixaUEVjjEzbq2nra3NP7hnx/nSWPFzgP4FxE+HvxTnyGSoBSMS2RZ26DVa4feU2Jy7BGNFsbgBZnnnz4l8DcDFZFKxpJW2TzVLGz80i+QqKvX8V5QGR4sGeXRkPdM9P8znOcoHpCdoEucr3xYpSZygt7PjOKPs3JOBgFfs+lMWBWIijGfDB/JjE8zj2sAdR0EZ+SapamkpCvd6f2qF3xvZe+jMjBBFjY2N7rnB0Fct7Ocmkl/QRyl8NFLf9AyK45+c+SHy8g+JBcFHic/wpGTmCxRIQZo5wT5FzIzxosB7j+q6zR8BUJ/6TNkJhRstMLVYavaIV4MxQ2EVKHA7Yi1GhG8LhDC9ee4Jfige9G9Lw/JUQeq/SEzN/Rtr1m1+6uj+5wubHN67iL5/VsAJgg0AAKLCIe6a5nYVmGIsTNxhWhEAwDsCvgVy54TrEPyQ/LeA1tva2VMmFIcdGgr4TRZpAo5ZFnKZDlsIgXEG1HsdmLjEoZSfCAHXuGOr+TmU64Pjq4IIQyDSYWyBlyz4VY4T6m0El12i+wby3zIsGXeg4DVxnfEXGinJZBiKBc8tGVtp8HZAxonRaiAdZheHAf69kmE0J1SH5fWQVc+kfh/wMkK4E05/6cCYizwGcJXVdyqTomjR+0D7iwBSqlYegOMCthPoJnHFioMp4z2lVQQ+IyAymWO5XdpSAIgWz7lHvh4NhjgnUWphPlDT0LRiZH4JqwAOb54iUBOS9zs1DU3nrNVp0v1R975nb1t1vSNbGvpqnttzAEIPEmHQXQgPhuKxhwETNmBDwHvmuKFGqVcBQNXGlnlO3N8CaBOQVFUlLkB4UeJeA52V4TUl+j8MVCKrD4L8TF4PUCLk3PSCW21tbSgq/zERn0ZaUfsayNckvADoFKR+mLQKlZEaBfwGptgpe7rH7hnHHT53uRGyPFfd8Z6rHuFSDObxoPQcxxc9ELGAf/KE5rPGokgcO1+hL9/+tLW12eqGzaJYAiRCqkv4AH388kOPPfWVQy/9YNi5cM2a5jLP9Z6kxS8irb4dE/BOrzswwhm51VTX73s/4X+OUGIdVDxiZb/evX/XeyRo0RgQyyB8PFLffLxr347ghiIWx5z3ifoMLJYEXGPOWsspPW9dXW2x6obNxykcQso5WFhJ6FMr1m05cXz/c68H2+X2DdUCzi9BuD/dLp4ElDXaQhIZj8etoz0CUs6sbmCT6GXAHGD/rLdyVeDFvLedUPgQgJ9L/mYFgacdv+xUVV3L3/V0bL8azP/QY0/N8WJXt/oePgfiXlfcG2nY8uWuvc/tn+CpGYUVB0nbD3EBAIhY4MTNciDDmfu2wLl39kWdvnIUUB8Sm7LCEjaK9pdW1206c7hj17DicVVLS5HTG9sk4bNgemcMoTNSqCtY76KS6MC5aLgvsPeFkB6x8D/20GNPfTVjLFnfvMATPgQpq+N7kK6utlhNXXM3qNcApBymF1D4xPXwICN1m1+Ah5/CcO7Bt/rqjeHTSPe1AncApSEUixm+DzERV8aJaCljTB+kdwE9nEhiicAZu17a2fnMQPX6Td0Qe5hwngWhCoIZDtTxyt7lLvgRgA8FbFxvA3gOwgGAlyw1QCZFJizuJfXzAJrGb8PoqDskqjyj+vBANE6DWiChVkzwFCz2ZVO1n+75YT7PUT4Q4IEMztVdyI45/y8JGcf6XuhmlUSmCk/Gs8RQwD8hBvKHCogdTQiLd6+Z2KQiSOXLhg/kxyaY17WBO4yCM/JNUFPX9CB64/8s8JHpbksuIpFt4XODff8A4GM3WlbAVg2GXlizvvmDB/fsOJ+H5o1JTX3TDwE9Ntweqwe69++6dKvbMRN46LGn5sS9WPfwyz9x4Oje598/zc0qUKDAHYAhf2c4NCGw+0jHrq5s+Qrj0MyhZn3z+2Ht91OfKX6xq2PnH01nmwoUKDCz6Nr7/Gs19ZtfReo9xfDzAArOyHcY27Ztc7rfHaiMXrduz2tjhwv3rHxjTHz4mS/44oit4gVue+T5MbmMDod6Jjwj9nTt3XGj9/9t7YgMAL57PS4vFDRAhiVUVrW0FPVs357TkdUIsyywIGX+NEBcblqtT2QcUrrexMLK3LHaErcsM8SccfVkaWOASTv0kJcos7t777M5F3hzMCOvX5hO3MoGF50qLbBgrDK1tVtLoorOFoMnj/HZwO2uoAj4NoZEiM8EwnVJr3d37Jzw5oHhkpNhZAh3oixk3NkActv/rMpBjr2RpbXVOM+99IDEhwOp+wT//7HEq8XX3b5Q6FKss7Nz+BkUqdvcJ/DJ8TWXb5CZ1JYCAADf02xC9wTPr4D7KHwUgD+6hEoAlAcSlkD4BIC4MXwdir+N2znUd2ur9eo3H3PBfUg4IwPAg5J5gsR5EQ8k7nBFBR51rzlZ7TUh378bsKsDmz3fIfT3ceDvi0Phs9EKO9BTXu6hrc0CQKSxsQyDoQfyfnxCsWhzOg7Y8/FihFie6/sU/aiY5VArAaYiFV4T+D0jfClmcHJIs/urii/E29vbh/tQzfrmclhFMdUK0dM9ds807vC5yw1BDEG4jrR6W5kjzMVYz1WYCsLOSwl6CYiBZrh/DVnjufRigSEzLGnM+Wwksi1seaWc0Nhrv4W+fCcgh3rDih0AWgCAwr0ifsOLD62srm/6Ea0uwDEL40IdpJ8F06rIgLolPH96396MeXVjY7s5Gw2vALFNoJNMng/HvACg4IwsFIF4zEJfqG5o3kvYQ4CuQs4DlD4oIKgY6wF4oyTsvjbVzbCwhx24zwNKKRWXCHzcMbYkUr/pOcn0GML1qRUUnwLxaKBdvQA62O/lVCcFgCJ76ex1565XCV0EMC/jS+IErPZ2dbXlVEF8eNn83kOnr3QEnaYF3Q/gd0P0HonUbf6xNXjHsU65oBWeF1uDhMPcAwBcEPMl/2JVXUv3SMfliSL51whzEcDyZMIaOfqTmvqmfTTqtr452N2xYyyn7BlDV1tbrLqu+YAhXhSwFQBAzCbwcZ9mbnV98/MO/XOgU64+7xHB/ByEqsC8u8fC7nxoadmFrpfT9ba3t3uRhqZjAl6Bhp2B75H06158qKq6oel5I/YBujtu9RgSyt8TUqmldQ/Jie9E2hmZAqoo/YbID8HVNRBFBlgg4G4mN1YUuDMwxpGlpBsUA7WQa2CL0o6JihKc1Bhwq6BPgbJIz+niGKEO7MosEvUzTDoFAzhM4L/4ls/5dC6F+8sHj3W1eUjOrVY1bFluhUcnPNWS+6aBOgQ8kUxZSPFRx/g+xIbgWGAcd2/WOqZ5fpj3czTFWJg4ocCcXBWGHHN8ZNyWWXBOnoKf3DC8Go+xTNHh+y2x6ehC9+JZ21P2gwky6QPKlw0/XzbBvK4N3GEUnJEnSXVD0ycgfGMC0Qmnl8q+LyCrI7L6AW4HcBJEjMJiQR/FiJ1FBNbGrf4RifB5t3RUJLFSSrfHhFAG4D3pjKyheDkdLBiexAj5NxgXKFDgjmdVw5YqK7sh9dkK38mVtzAO5RdaasIvHz7uBQPPa6OFY+QuUKDAe5d/BZDaNNm0em3z4sMv73h7OhtUYGpYs755QUzadPjtvk0AlrpFOLKiofkrx/fuyKkoJphKBZz+BPRBphCO9Q5DxeF+xL2L6QQsEGx1be3Wks7OZwbGKHrH0QUMVou9pFIKdSQ0P3TZWwLgjWxlamu3lg5g6D5CQQNiP+Pu8Dn14UcdmKDa3wIjZA1fmsJAd5NcPt5MT2QfhbNILfRKCyn7IG5nR7sAtF4/DS8GFqLmGoMHamu3lubqnwNF1+fDd5amUxQFdam9vTEGtOe/0XmE1FWIwY0k9xraagA7bsnvQwMAeoedF4V5iMeXIoeTSSSyLQz23YMR0ShGsuyZlyoUwj1IqbNCFym+EC2xO0+1t2d1IqdjwpJKp9rqOJPaUiCB4xgjXy4yvZGLMAHF7SRhpBZ5pHmCc9s7LFTGS94acKOdID8GIAxhDomnQVxJhakm+JYsOrKpVwGArJ1H8P7hz0K3tfz2G/t3ZlWwcryyUBxDJZzidQ3BiwtOdLhWowopd0jlUmMqfWrBePebKXHm0uOi4WzCW5C+33X/7FfQ1uYDwOnMIqRsaT4U1KZ77J5p3OlzlxvBiH2C3kVKvZtY4FgtA3KpPrca2T33ikxtRADJq/SZnstfwpCZx2tK3yQEeJdzyb8XwMms1ZZdn0to0XjtLfTlOwOPg92Oyr4L4iFBi0AYAotAfpTgBjgYhFQKaN6Itd+rBH4sqR1Z1n2Z8B0IPJsVcmickfnew8wCUE8pAvASwDihCgkLkBlO/g0Kz732Yt0lYPuUNuDeInvu/JB+IPBRSBuTyXMAPC6Yh0BcsYChOAvAAmjYscuD8DLJ73R1jR0VOZvS5jDCSQd2TCfetrY2P7K28RU47reViHQxC4m+dT+Anwe4kcJ10YZEzEqq/QbndpdFnAhfLZ/0RlQZ511AxyHUJZNmQVgPYDXEPhLfAHBbOCMDgCmJHbOD4W8TNgJweTL5bgAfJtBgZaKUXCWey/MCStj9AH7kFjnb25JzpyAuecjzsVNUWgUbWAJiG4XHBMUAlgCaD2DCkQ5XLS27cOj0lX+j8BCglmRyKLnBbCECm46T/8WQcOKf2s1kBaaFQYSjLvyrTD9mQga4a1XDlrlH9j53OUcxElgA8v7A9KeXVnm3YVfVtVSG6ddYwhksir2ay2aQBRK4WzAPBB6pl0kFX1EIY++h0vM+AIettW3HcggxUn5IMKUTfWPLEnUnTGKjxBokxgkAuCzwddtXnnWNaJrnh3k/R1NNHG40JO9qYKydC+CBSGRbONdmHc/x5sHX0pniY3hw5azB6rd7+4YjvBBG0N0Pnrp8/xvAiVvRhnzZ8PNlE8zn2sCdhhk/S4GRRCLbwhS+Md3tGI+V65ofEPCbo7/RHwzFsfjovp0fP7pv5787unfnH3bt2/lZXp0zT8Bns1TVVN3Q9At5b3CBAgUKFLilWGs/EfxsrHl2utryXscNhZ4D+eHhP8Nfme42FShQ4HbHyVjp8B19IlfOArcX1vcXGvGDAH4BwCYDfsQFPhiJbMsaBmxRQ0MJyUeA4cUXQLhsodPZ8t+JhEJFImzAhwXFoBlXiW/CkKIU8BJgyDO2eKwi+SB8qfwKE9c1ZfAshsz7Bp2h+rHKRdY+ubC6bvNHa9Zvfqq2duudsejT3u6BeBdAQJmPj4D4SFVLSzanN0bd6COAnkZ64/6gpd4tseeGjd6K45KEnwbK3Q3g/VV1m7KGb4vUbl5Cw8cFLM32fRADnIf4ZjpFERAtKzdsyOlMFYlsC6/e0PRoZH3Tpx+s31wz3m8kcXzopkPD3eh9Zfvn9kIZ4XBDgtYNhAezhnitamkpkswGEE8GkpPnqHVSEQ3zPhbcAIw5FyEGnbXuFsyG1etblucshFZTvW7Tikhd06dX1TdtwE3Yda3MhUR45mFqQDxVvW5TVuVjVV5abROqe2M6jRabcElAnRUAoyAv5VzIa201sv49yNjsmv3y3uj1y2dbCkwOxeiByKlsc2MwRvhjhfi9LejsfCZKw0MgDgJAUrXwAaTCrgMQ1ANgX646KJYSgRDchv0J56jsePHYPDIRQvjGoGOV+/khy2sA0o4F4mIDPRppbMx2nzIGrVDCIWhMjDWlSjgwJUviGohLyOJMAwDLajdXQlyITIcwtOb8hfQcDkSYPnM6uU/32A0AJEVweHAiGJKnWz7vBG7p3GXGI/AcgfS5kFaC2BpZ25hVQKB63YtVhnoCwMJAmYtGGu5fPT3bYwLOIfEHACDwsGPwwdra2lH3YmNjo+s78XUgnhqvvbeuL489bhS4OY7t3t0PG/sehP8M4pXAV2WAlkNYBeCBEY7IvaC+Bcf5b937d+VyBiuQnV4QRwC8Q8BBwvm3CkCNgEXIfO68Jdp/8Lz4s5N9dxmL9vZ2zzcD+y3xJWTOEYoBLAawGokQ4/cBAUdk6CWAfzlQHHt9Qj8k900DdIxIPUOh43DLxnHDsXctnX/BWv2TgK8BCDo/l4lYBuAhAdUQ7kHQEVk6RvCLxgt/ayz15fEYQP9btGoHMt5DXQBzJSwDbi+Rl6729muu/GcF/ldkbvxJ3PPAagHVyFSyvgrqu47Ml2vunvUOsnDwvlmXfOlfgZFiRawAsALA6mT9lQLOAzwIom+89ra1tfllsaIDpL6QrHusTfKHBf03AC+PkafAbUTPkvLrEC8ibaOkwIcEuylXmdVrmxdR2qjE2JUoBPX5vjmTz7YuamgoCTHWItkvUvpiyWDoj1fXbVqDCcx1Vj76gRUit4IZm8EuQUzbDrdtM1YsBVA2nEYNdD+5sTdXvb4x8wlNXBSstdV6sscQeCZIWALi4WFlfOEElFvVflrfdW7FOZpiSqN+LwyDfTMsqJazLj+eLX9VXUullXkM5GO3qInj09bmg8qwnxthdcg1TRjjWlbVtVTW1G/ZHKnf8rHVdZvuzpUvCEFjvfhosdw82fDzZRPM59rAnUbBGXkSDCy4kO28tQE8GEygN7366o5j/93INAGfPbrv+T890fn8lZHfdXW1xbr37fw7a7F2VGXC7+SpmQUKFChQYFpoNSJ+NfVJwOmul587Mp0tei9z6KUf9B7du+O7w397dowZJq1AgQIFxuPovoYDygwJ+7lpa0yBKSUup1/QVSSNc4IWCvq4ndX30ZGOpIsaGkoq/LLHCX0KQNrBjLgo+qMUy6obNj9UU9/0f0fqN38r+fel6vrNjXk+pLxTUdEfk02HPCbgCHbByg1N905F/VYcFNWf+ixigRM3Yxhq80PCmOy8ATA9jyBWW6NfW7mu6VGMkF3Ytm2bs2rdlofhxP+DIf8EYms0NPS5ZbWbZ42s+3aEBicBpEPiCgsBfMTt9Zsx4lysatiyXMQnAKxLV6C3AHV2dnbGU0kmXHYBUPDeCQv6QAjOLz/02FNzgnWu3LChwjpsUWLjwLhOQl7MexvEocARVBB42vHLPltV1zJKfeihx56ao/Krv+B7+IIs/sgV/32kYcu6kfnCHBk2EHON4SLcpE3wRu+rrq62mCWOA4FjFFZS+tSKdVseHpGdbt9QLcBfgnB/IPkkoEkrV+V7LLgRGK28ZMGjSDvuhQE87sv7rdVrmxePzL+0sbG4pm7PJmOc/0vEH0n4jzUNTT/X2Ng4qah3IeOeBdATSKok0OIY9yMj66yqa1wkOT9P4GfHPS7XjyVVl1PMF7B6VcOWbCELWf3cS6sEboUQuH+yd80bvX75bEuBycHy2Cn6/HMIT03kj+AfI+g8QrxC4tchPCVrf9fQfTVde6uprn+isaa+6R+G5zF1TX9cvW7Tiqk7AjkAp9qpTsbjcQp7AmluShUZwGXAHGD/7LeyFQYAGgwJSKsmyy6mwepseSONjeUyeBxgS7bvgwwk1BPTzw+hmMC8bM8kADAqusrM949SC2zEoPvkiE1zXLPhiRWuy21A9nZm1Gs1pMC9LPA+GK3J5YwZDqNe4M+NVy8AmLAZBNPnTtJ8UCtyLHpO+9gNABQHAQUduhaCeBDTIK+Vr7nL7Ug8ZN62yDwXAJ6U435iZH+qXrfpLkOzFcDTSDkJCn0Ejtrrs84FsoqyZ0AGoxbcJ+ij0fDc949oAs9cD602wKcgjDvu5asv3+i4UeDm6Xq5/Vy4JPZNin8I8e8RcF7PRFGQewX8iQ/vL1bdW9mNLKrI8+fPF2gz08mY75lJbwDyw/DAYWc0kBgimdUp0QHjCvYhMm485dzIVBr1fVkOv68RGGJgXM/G6M1Rilk6E4kkdI3gM4D+kjlVz3Ed5Isi/kzGfO14Z/vFbJlu9DizcWz37n7fd3ZYmf+TwJfBDMeYIB6BoxT+wqH5D/2m/6WJKn4e2dLQJ2NfBhBcq+i2YDtaJ+Bk3dbmLyz1T/i+/WsL/L6gHyHtmDiqnQB6CP2NDD7vxWP/1PXyD89OpJ25OL13b1Ses120fyxg9xi/DSDR/0kFjktRAlfHKmNFDwrUK8UMzaj+NJm6s3G4Y9f5sOE/GsPfB9CG4EawDBQFsUfAHxtr/7xmScWRbKrIAIC2Nn+oNH6YNH8u4EvIHeHgLQN+hcDfAkpv2gY8meKs57az85mBq7i2h775j1b6TUj/FdD3AewB8RNC3wb4p0AvH84AACAASURBVBJ+jzLPIGNOCw9m9H2Rz+tUYAppa/NBexxi0IbzoIRfrlnf/H5s25ahuB9Z++RCz+DTAj4eeBe6BvAtRt/O2Gi5csOGipr6TR8P2K+/VV3f9LuTsWdu27bNqVDpBsH8FsA6AGsBfM6n+atIw+bfXdHQXJ1NAKS2dmtppG7zY8Z1fx/A04E2e4LODJlAFIu2NkswiqBDvrhwxXN7ss7ZVjQ8fp+stmAC70pBKuMlb0HqRHqsC75XAsSJkMNXshbGNL/r3KJzNJUcPLgjioRTamDjICNW5lMj7RCNjY2uY+x6A/sZZG4YmXaMZ09C6U1tIhZJ+HSkbvPWbO/cq9c2Lw7T+01AXxD1nyzN79esf/z+kflAEwcQmG9wjmPc7Pa7PNjw82UTzOfawJ3GpI0eBQIInznasfMfauqbfghgzXQ3B0jsRpC8X81IJP+te++Ovxuv7LH9O1+prt/8qwT/ezJpnyH+IB/tLFCgQIEC00N1w0urKA7v1DTAd6ezPQUKFChQYKpptUTzvwFKKa2vqKlrevBox86soY0K3D4MlcbeLYq6+w35YSR2XrsQVhNoHQgNfaC6YXO7oMuOWGlh1sJoi4CqYauNdIzA9yviV86PrJuWi0F8UGDKYHYK5GEA7bfm6PJDe3u7V1PX1I+EEk9SnY8b6eMr1XVNnYCOOMZ5/cje53rGqicXkn+NMBcBLE8mrJGjP6mpb9pHo27rm4PdHTtuTejPEI7IwwsUHkm2rgLAFmNwd3V9czuATgN4FnbRobf7VtPoEYARAHMheIJiRS7fBPDDW9LePBK6hpN+GX5ihS0AZiWVQFYT+oPq+uZHjHhAsHFR90m2SeDPMh0O1IP4unHwo2Cdx3Y/cr2mbvdBJBZjUwbvuaD9RS8evytS3/yCqAGKi+XZWhg0AJiQo+vDy+b3Hjp9pYPCISQVMQXdD+B3Q/QeidRt/rE1eMexTrmgFZ4XWwODWiQUNF0Q8yX/YlVdS3dPx/bhhbiYCUVDvn8l4GswW8Ina+qa5xLqZNh99ciL27tu9PxO5r6ysIcduM8DSil+lgh83DG2JFK/6TnJ9BjC9akVFJ8C8eiwggvQC6CD/d6kN+3leyy4Ebq62mKRhs0HZM1PQH0omTwPwid9R0tq6pp+bIw5BilkpWUYxEMg1gqqAlAq4j4IVy5EnWMAbvj6Vaj8nSvo6xTx88mQyACw1ML+9rnBUFV13Zb9hr4DmuUC6iA9iqAyaQ50pfKaKnvPIxXiESgGtMUHrkQ2bPqeD/OmE4tb67rzjTVrJXwY0IbAdc7JjV6/fLalwOToam+/BuBA8m9cauqaQOLjSo2j4llJL2SbzzY2tpuz0fAKENsEpha258MxLwA4PjL/pCDnwOp/qalvGtcxP6MY4Ev22aMdu76KLNI6RfbS2evOXa8SuoiRC5PECdjc6lXJPJcAvQ2xNpmwktBv1TRsniNf+1ziiu8UFRvPW26j9gkSHwJwz3jtPtXeHqtpaL4GaThkK4TmELwv19Q17wPsq0c7nt8/fEzXyy6j/OoRGHsOyVDABFZI/Peo7Kutrt/cQYeD9FkVt97jENczMxx7Vvy400fXfye1BEnoboCfGgjfxcjapp1A/KwfDhnH5+KzUbuRMB8BNXKTC1oxWh255Hp8YKg43Jt+RrJcwMfc3vjCSN3mAzQ6POSGO3te3H4BmP6xGwCsw+vGYy/SOjiLYPT5mvrmWlBHQB6KhmP7byC09KTJ19zldmSRE+19Nx7qoNQFMgIAAu4j8L+He72lNfWb9hDOVUvNprhR0BMA5qfKizgiYkf3yHvdhnuA2D6QG5MpLoBaWfxhTX1TrQW6jcEsWKwCtR6WD4EYd9NEvvryDY8bBaYCHWhv71va2PijsqGiN+Dja5ZYAGqJgLsp+jC4IOC0jN5g3J48vr+993iOa9DW1mYjGzb/QF5aYZvkpWhs8NhkG1jUHzo9VOL/lYH5JgBY4rrrMWvo71jIeSU8FPs10VQAAI3etVfn5lRFPLhy1uDKt658ywhHAIAOB2Px0Ruvg7A8dgrXQ38ug79PpOiya8ITOT5rwTM27v2zCYdeBbiSsotBVlDwBFwQ9TZlukNu6OShl36Qs903epy56OnYfjUS2bYbc3rftHHzHWO0TMADBEtIDFlrr4DmXVqekI+eeRVDFw637/Um/AOtrdZ97Kk9nj/0K8nw8xB4rswrOjrRKtrb2z0AJ6vqWr4Rtt4+62gZYe5PqBIrBDAmsg/y3zUWJ4ycUyX20tmgQ9HNcLTzubNLGxu/WTKoV2R5r6GZLbKCVtY3GU7Wif5fu/mHcPlU8lg96zo5N4QBwHWn/2ylV/k3MvZ7AGCJK0WORs1VJ1N3DnRwz47ztbVbf3itOH7IeP7fJUK/axEBV2BUUi8dc8ahery4PXlk/67eIx1jj7un2tsHI5HIAbds0bvW1fcEVFN4AGBY0ADBdyQc9V0dKRK9OMzrsCoHADp6pwLvjBLBS3F6794ogK41a5pPxcu9FxgPlctBEeHLo4m6XqyP1+dfZsXVDYKdr2G/M14DNMrZOp/XqcDUEiePhqgfEWhIJhUD2iiLWdVv9/3YrGs6IFcDtFwseQ2EPoCAKjKEV33iX491dWXMj8xgeTlC9hEBPxfIKzds/wVAzr6Yjdd+eq0sZPg+KsP+dBeA90usdqAP28orp2oamrph7SWQErBgAINVAFchoXaadkAkDgDmnx+5b9alYPgQWnsRxNsgVybT6h2rP6xu2PQNY3gw6mmoGKYSBqslbAXQBOCGNnN1dj4TjTQ0HRJwEMKjI74+Q2H/web1F7FnR9by0/yuc0vO0RRjaXRMFnsAfDiZVgaghcaUVtdvflbgOYe459ygHibsehHV09jerPTZ8pOznOiLIFuS9sEwgFqR//l6aO7jkYaml6zFFUPOF2y1hR4WUAvoXgiwQBl9520Afx2s19IOUAyo6Gu5iN+O1DU95BOdvtxXezq2nwbyY8PPl00wn2sDdxoFZ+SbgXpRcj/T3fHsmC8200GIsXUjPfUp/NlEy3fve/5vIw1Nxrfm+LGO5340fonspJS5OjufuS12l0UaG8u75s+P5grzdjMkdo7cG5oJ52KmtCXRP96JT+Klkis3PF3u9BYN3UyInpEsamgoqbyyyJ/KOmfKuS5QYBTDi1Spz3o1R8480WpWbni17Ni9RQP5GHPHI5/jfYGJUVu7tfRc+KKSxqjbhpt4dk2C5H2y+3vXkEWt5GaINDaWd7U3DkwmVODKDU9XlA+eGczHOWhsbHT7+yvC0/jczMscI0Vt7dbSaLTYm2jdjY2N7rvxypLJjpWEXh0hZ1MLoGBovc051d4+uHJdczuo7wD49WTy/8/emcfHVdX9//M9d2ayNd0XSgOUUpvMtEQltJlpQUeSSYk8oKhBREUecOFBcf09j9ujT10eFZfHR3FBZBFEUSPCA9S0SYojkCZpCZTQTpLSlq7QprRNmyaZzNx7vr8/ZpLcubOnma7n/Xqlr94zZ/nee88959xzP+d78hHZOnEuMXkJFGQmB4FnApgxKkQm9DForV3Q6o72+GdYEmwaIZ95dK7ATjg7ttWVkHsFRADRVfMEzAZwNQiVAL0qDfwWsV5CM4aF9gbAW8GojAZNQWTb8SVg6iPCHwGcFDHyHG344MFhR4PUqBLMI6KFKQBWAOwk4E0GJIGKGJgOpmLTJJsEcAAGJfOodEbR2dk4sLiy6h9M9DSBPhwNLgRwGcDzmfhNjF2LOaZJTAAUIMjHFp8/bV/s7PkqaYirXtbY1gSwyfsGnRcRwPGVkQ/RPAlEMxCTZ2rq6+sN11LvC9BsjzHoQkTumw3ARQA+ANCVxBhgknYmTIlOEJtFXIeZsMNxbFKM+EjXhvodum0/M41MvtqIsQiCzwPjXVLXH8R4BVFZPlfn58kDvcO8mkGXm+rnNABXMcSlIByVgCCmKQBmg01bCjM2EtHjgYDf7A0y5zbnEtuA2BoqxBMglBNjQTR4FoBaEC6XLI8CECAUgzANzJNMyYcY2OMIOdJuj5yI1tb6Iad75QaA/wnwyAc8OxhlIMwRJK9jBgFyCoimAUjoJdRKIFAfLvP4AoKxkYEVAABGCYFvYUNUCeAYa3YmRgEEzwLjfGThHSSb+5drWxS5h4iYIeWIIxwGs67Zkr6/UKTNNNVVtmsktGTxs4aRF/0wWpo2bkwyMEj0VlRUaB0dHXH2d3R0hBcvrwoYUnuBIgJFc+LXNMiUY4hBR3hnftC+kYB3I9LOFwG4AkwXk6BeAwiBdY0FTwZoHjL3xCSZ0UvAbkS2oQcIcwG8H+B3Eqje5fVujorMEQjUh5zLa16ExD8B3BDNo4AJlxJwgQBdxxIGgyeDaSYyECIDAA3tOSSnnL+JGHsQ2XreDsZigD/HGj4A2AeFAWLiIoDmAhxZrJcBU6fi+IFB2g0xKgQnABcQ6P1M8IJFmyMUPg5gtK09lW03ANgkHzRIvkZjDqLyASwB5HwwHWHJDbahgh0A9o63jEzJ1djlTMTv9+uupd4N0Gz1DHwewBQCNIAWgHEzSFzN4BAx8oh5FtPoQiAA2CeIVtsGEOepbnbR4Jv7g47nom3DyGKuSSC4ASwUQB8kHACmQ9LUbBbU5KguZ9VuKCaO6AKEbQC2u1x1dppybFIY4QLSNLZJERzICw3u9PuHkX5+kQMtzbuBpF52s6azs3EAQGf0LyXRxR+Zt5H19UYP8Bpg8kCZhmwXR5khSN7a4X8Tq1Y95/L7O8SQVgRDOEI2XQqDgsFCY2Cnvzltm5b1eaYgOse4G8De8vKadj3PVmwTbAuHpQGNQ8dF/+DeDSuHgVUyYwWxiaiouu0EzeToopNNXq93cx8waShsLzR0u7A7pIFhPTRNGxxs3dAaxATPgQPgnX5/H4AXAWxaWFtr147ZHVr+MdZ6Z1nnZznQkV39j37b2BL9S2lHtnmnIjp33lNXV7ftpd3HizSbPomlQTZdGra8ouGhYjnY1dAQQhbXMxAIhIDAHqxata+06cUNLI9PtgmhQWjh4KAxWLFg2nGTd+U4Bwdp4GhbkNBzeV1dnbZ5tywBaIEpSb+d8xKVk8v7pJhAts+bcsi15+iTAF/KwLWRUComoBJAKRMfApPOwCQQz8DoomMAoO0A/jxA/XHfrg1HWGhsswM8OuYnsM0msn/3m6L3Dh23T18vmBtANPI+BUR2r5gHYB6BK8DoA4mR9r2AgeIECyt3kcSfpC3/n3GeyIm2AtQC8Mi75HQQ/wtBlLPkwwWk6QA7mDGdIuWOR2TLQqetUuP1jDgx8qsMbknn1f6UvuucnGs0odgm0avh42gG87tMC/1nALiaQJcRMMiMQoCmEzB5wnu4CeD1jqcGp1VW/ZOB1Tw2f14AYIkgXMCSVxJRiMH5IJrKjCkYe05AjP1I8M2RBR2Cgb0mt8ZFDCwDYRGBOuwc/gWi76y5mMPP3Zxg7r4NnG0oMfI42On3B52V1Z45+foLfn9z0hWEbOOTvjXWWOGi1OywnIHerrbGDdnkEGht+k22xZau8J1PBj5NwFUALx5EsBgAyty+XgFqlsRPd5dM/UsyMcWCiuop+Xb6JgAHj3VwEYMM+lGZ27cfAIhwtKu16ZvZ2mfFWbFyLhzy38D0HoDLOQg49/SB3b69BGpgxm/G6cGKXO6aqyX4agLeQoTSQcYCIAinu7ofoD3E2MPAU4V6/oPJBDellVXlROI2A3xeTOZAicvtu1tGVy8LxsZAe9MjubQlW8qX18wOG/gqEwsAIKbWrvbGP7ncNbVM/GkwvyNSP6bD6fZtJeYfFOhHHkkmbHJ5qt/OTJ8GaCnA5TCGwJOH4HT7AgCeJeY/BNqbn8/Uvvleb37hsOMmZrgBfgsDLmLM5sl90euCVwHaxaAHu9uWr85crLVKuNzrVwL8bxJ4+yBQYrrWW8B4ZKggfD/SbLhU5qm+FEwfHzkmxgtd7U2/T1d66YrrioUx9HWODoAF0WCgtfGrmdmuOJeIvuyNIbSEL+ET1A4BAC32VK2ULG4F8FagZREMwLlnCHD7AmBezRB/zpXXwFK3b4UgfIoZZQQu4yAVO/f0gTy+HczYzoTnWWh/7mlZk9QLgtfrtR0I2v6LQZMBgIB9XW1NP0xVrquy+gpJVDdyzCzv72lfFzfxmqzNNMcpc1e/D6B3ErjC/L4imd5d5vaNrjgk5ke72puzmiB0un1fHvE2RWADYe1HXR1r30ibbln1NSyoZvT8gL/0tDW1JIq7pLJqjk50uwD5GFw+iGBxMU8aaR+bmWlNkZ73SLp+aJHnqnmCtf8YOSaCv6u16fFUacrcvlsAvB0AiEmGof1XIq87E913pWaVKHM//40RrxLEeLOrvek7S9zVTh10O4D3EVpKYABOtw8AAgSskdDu7m5LvRDOWVntZqIPjQYwPVykH+occky/VTJuI2ApBwGnuwWg6ueEIVZt2dD4TNLr56m+lJjuAHgZQJfBGMKgfTrK3L5eAp4SwJNb2pqewjgni53uqmpAfIIB74EgZsMe6TcZ1E2gR8Os3Z9LL0kTNcZIdN2725e/5KpsuYkJNwPsHkSwGPbgyLXzSxb3WBf+udw1tQA+IsHVB4KYLTA00lb6wXhC2lDf09L0urX8hDBvBpleCkguA/CnpPEVZwxzC0N7Dup590hd2gF8EKOTtVwMoBgATN7SotB+SH6MIe/vXL9uQj56nUnkadqWsJSNAL0NYxNmDgBzCBRmMhJt0ZURg+jfNVkW+ZmoCmMr3W0ApjNjOizjqFzi9/v10hUrNoKLfi4iQk73iD1R0d7skbg0+g8ARh+ABgL/KtRnO2sWLQwfcmx3zAjfw4QCAP+CETGu5VpY2CxZ/q/DnteUaBvTiKCW/sTM8zHm+QIjz5/lydMB7CRggIE4L41WAvNnHSzbdfhRCJpOwK0Y+xBTxBSZI+HRf0ww9xCJX5Ju/6t1wctOv394sdv3EgjPM+MqAIh6qZvKAIFpFsZJts9VtH5uSFA/8xERmMVt+whAB/h5QPx4MD/08nhtHa/NuaSzs3FgSWXVGh1iBoA7EfGoAyS6HrH3fB+AP7CuPfDSS5WHgIZxlV8YdnQH7cEHZOTD0nIAiIqYZjAwY3QMwQBA/QDvYUI+WebrLHD+UPjlUIH992DMAzA/mudMWASQPHpOPARQCBl4Xs7y/uXUFoUiC4iB1B/G2bZdgNsZMIuR9xGjfXPtlQfRvi5p0p1+/zHXUt/fIfB2JnwgGlyAiBAwIgZkNjcjxwgIcvJ+cBTDMLbYbfQMMy00BRcCuJAZ5w9Zvi/1c//2YlH0MEuaR9EPfhFBZrRdiW3LXkNkC+DYxfIWAoFAaMnSkucMjR8FcAcifeOoOGA0Io8Oa/Tos6zB9JE0EREB6coOZjSDcKPpp3wA8xi4QIiYD+ynvO3eUjL5aNnuvvUgbMDY1rQEUOQ9gDCXjFDK855IcjF2OVMJzJ91sPT1/kc1w5jGwMcQ6UsoKjweFR+bvxoSaC8TPyjseCQq0orB7/frZcuq1rNG9xLTFxHxKg1E6vb5MHvZiuT7Ogi9YCxEjKAnnlzV5WzbDcWEw9FnKs6bqGICWbVKBiK7dZxOwnqZXOzZetKNSUbUU3Jf9O9kI7c1NAwD6b7QnjlE5yyORf8mhlWrZA/Qj8jfKDvG8eVuvtc7tSDoWAnixZD892Te8Tfv7lsAwV5ImjY2T8X9xwqG3hzHGShOF+rrjWMeT2cxF/6cWDiYsDL6iw3ATBDNTPJF6VUC38O6eHxvR26dGXV0dIRLPJ4XJ4tJ32LJLzCojuLn7/IQ3fkFABIIwEIMvEygB3WhP7m15cl+a4TwIdtux0zjrwyUYWT+BVQcWWRJ4PgLMQBC2CRwzYgku+4EAXRL21BaMf6pfNc5WddoIulsbBy49IqqNYYuLmHgNozNJRVi7NqZeQ2EQwk8V59SRubPIWgSeNRhATFjKojGrm/sLQiBuZ2Bn+mwx30/1Y5MfZMnH93AxDtM84h2ALMIfKGwzLvlYA4/Z3OCufw2cDahXvrGSVd7c9t4VhCeLEhQCY89NSDgZUz8akITq4TLs/6/2eCvmKww/282g28ixk3OPUe/wpU1tyYSnBXk8SIp6YtJCrlhbGthAMAJiZGdlTU3guSjiWbDCCgB+BNE+ESZu+a6bC5dVJj1XwxeOjZejsm9GICLCS4AKwftQ993eXy3BVqb6q15EYlqAj6bqBwGPmMa7KwFECcCnEhbsiUsjXKQ+PyojQIXuTy+Kcx8T/RDljn6IiZ6YMA+/dullVXXmIV6b/N6pw4P2x9hHtkWKu5euCLnQLc73b7H7YJu71zfmHRF5sLa2jz7kfCtHKRVDI79ED8KFQO4DMBlBL7e6W4JMFXf2N3a/Eqqc46I6VtW89hkuzVPNwjugqD9PUz051T1ikALYb73BJQtq/p794Z1h1LZIIzBjwD05ZGyJfNeAEqMrEjEO8wHhki8tdaJtkMAsMhTU6YxPyYZriS2uEDkIvC/uzzV9wZD+I8dHc1ZbaWTjNIVvvOFgfsA1I59mBqzOrrwZQExfGQY33K6fU0a+HOb25rjrsfr/Ziq2ek/xzQ76AWQUozMRNear58QIoAEXiAStZmwCAaJ6FYwromTlgEliGkvaB+y91ZwM2Hk/hBglyEAX0mVICLOxqM0InqLJG0DYBUjU5m7+psGaBVhpOUzt5BUDOB6Ir5+wB78xmJP1Se2tK5bk6xcmxSXM5nOlzEdQEoxMoHvBCiyXT0xHIa8DwlWwU9U35UJFRUd+YOgsV1iCSh1+54xgOeTrGZzMeAiGF8s81Tf2d3a/IukmQt6N3FMH7Jz0D7982B8JC5vpiul4HVOT/Vz9gFRa/74FV3g8hB45GXK0rNFXgBvk8BtTk/1c1LYPpFK0J/wpNzVdzLo5wlyLyZgKcBL7RT+Vpmn5uru1sb12eSdjokeY8Rdd4G9Tk/L55jx0eg5jf4UvXY3CJI3ON2+T3S1Nd3n9Xpt+4OO/2HwnbGxR/GC4BUGf6fU7atNJvw3I5m7yCRGZtAV6dIozgz8fr9eUVERGCiY+kNh0CYp6XqKeMdKtNJ6gMAbwPyIweIfcwuNPT1JBqIaKMzM5o8yw8yJvZZkQn7IMIbztbCpuBCDBhPW8CyZNWsW9+7pk2MnwkMESvrxpXPelEOlr7/5iKbbJIM+CBr1sgBmZiIx7q2C97a2DjkrVjawQ7eBxc2R9iu5+CVb2wFAMukEDpk+yoQEiYQLeHpaWvoXVtY2AqFDROK9BFyHxBOgAHCEwe0EeloaWrM2WPzatm3jF4RoTLqMeOCNQBQydJHyw4FGHJJMQ9Exhc6M4KSwSLrwW5eargk9NCq4Zw4ROOG12LatYXh+ifeFosG8bxskXybgBhAWJ8l6H4AGCH7CIfLWJ9tW1+/36/O93s7C4bwfMHgXWF4L0CXxMamfCM8w89PM7AFRZMKRKCQosb2orzfO83p37BvAz4Qmugh8A4FWIHF9ik5mcoMUWG2EQh1bOxoTfahjXRvsFHrhT4gwwEAVRtoKAgM07ro/nudqrH7KQxrJ9zHhOjAuTHR+BLwKxhNCiKf7qP+lvf7WE/acmK3NDkm6QTAvPEvbLjJDJ+aQaUFQyEZawnu+uX1d7yXLax6xGdgtiOtAqEn+IYX2M+Q6YvG0JtHS9YJ733h2uRiho+OpwYWVtX4HGWFm/igRqpKIEw8C/BgxvcTMH0RUXAZCyJBa3PO9aZP/6JLKqid00oKA/FiKOnwYQDMi70fvQqRuAuCwJinhvc72/uXSFkXuYRhhQIyOSwgIFxqJxSOzZs3iA3uOcMwYI4M+KBWGA7owMBEiSV0whouLrd+kxtiy0tPnbHx+IySZt/rsliB/Ou9VAGRopq0r72joh1KK1ymyXfFFiewAsBWMPyEijozMwTNCxIn7JfvA9L009fB9zCQIuM7cRhCRtA0VxNi2t7V1qHTFdc9qCEoG30zAVQnaFR3gTgD3EcQcBo+IkYMgSijqcs6f8vrm3X33MegIEd+EMQ+xVvaB8QQEHQboJjBfAiDETIOrViVOMFg0vL1gyPYzAvVxZMxk2kKV2ZDxfdmpbLtRX2+EKqrbHXbxXQLfgkh7NfqxlIhY0+wx+ceN8YnCQpdJhViFQ4YRzqcwxOgMzjAoSd+Xm7FLRuS6jx5JAkg9+lHaASDE4MTtSn29Mdfr3b4vpP3MplE3QB9E5L0g0TvaYSJ6jiH/Fpb2Z7qebdiXzIDuDesOL6msqtdJ9BP4o4hsdZ4oz9cAvh/AAEN8iRAR0jNg6LAlXESfi7qcbbuhUCgUirOT+V7v1Pxhxw0gfBGM6US4wlnpe0yT9OTMotAb0blN+6B95qUAf5wZ/0KjHv55F0Aboh7dFWcwe1tbhyoqrl1/PD/4n5pBbQC/lwEnEo0VCQcBrIHEn2wavdDZsTahM43IGJBj39PSjG/T2Yi6ulcW7j++z24Yz7HkywXBzUBlkvmqEYIAugj0JAtjrWBbT1frMwnnErdtaxheOKO2JU+EviOZbgHRyiRjrgEAG4moMSLK5ZsBAIyQTD1mBRARV7s81Z2AaOExUek2QPp7WloyWkBzqt51cnWNcj0PXzZ3+q7Nu/vuAeEAgBsRdYxlIQTgJYAeinjg5REx8jCTGPe3F2B8c/FWRubPC4dt35JELxLz+wEqTxJ9AKAtDPl3IWQD5cnANn9zXN0KBOpDSyqr/DpsP2DIT0S/l4wgpRAx4uFczOHnak4wp98GziKUGPkshZljG2bC/pwVVlenOfe0/IYZt2WWgMuJ+B8uT/U7A63NL+XMrhREvEvyo5nEJfCTnFwzGkP58prZYclPZ/dpnYqZ8ZfSZTULejY0ZryV0JlkCwCA+T0cmQxPXjpQQqDRibSyZVUzhoPUIavCEQAAIABJREFUiIgwOBOuD0tccukV13iTdTr2PqMWoF9lKX9wEYtHKioqLk/m/bLE4ynIY1rDY56dUuEDsy9VhH4cX1OMov6oSA8AIDTxAQApPZYT6MOxenP8NgN7FOcY873efATHhMFE2NGTYKXmRBDxqCpbzHU5Fcz0yTw7Fs33emuj28uNG6/XazswzH8C6Mr0sUfxGaCAc/lV87vWP7PrRMo/s6D7AP6fkSMG/tXr9f5n1FNBQg4ENa/1vrIoeDo21irhcrf8jIHPZGQFUCJZNDiXVf9L14bm1ZmZnsPFVuPou04EAWTk4Z+Y7nZ5fOHMd7EYu7fJo+Btw8X5o9t5vs3rnTocHGpAZv0awHQlGcazpctq3BmPIZjfw6CU1zcCFRNzS+ky39KeDU1x25aOh1yMMeJgTrlYwcRvy9y+yQeG6R00tk16CqhYAM+7KquvTOexuXvDukNRL8yzAYCApV6v15bq2VacOUTHpdve5vX2hgfzngPRRUzGXDDNZZZTQDjOLPaQRvtIx95hEq9t29BwLNWKgZBde8ExHPoUk4i07xodl6xvH6+NU6fi+Jsh7VHD0F8EABZs2Jh3YwIWytbX10tXRfXfYaNrAIBBurRpyfvu+nqjp65u25Ldh3+lC20tAXOIMYUZRUTUpxNOaHeGro61++d7vX8pCPILLOl8QWIqExWTZGkIbD4h2wEMaP37J+uT72YhnwQASTiap3FSD8bb2huOuVyuFlFUsk3XxOOAMV+AL2IWUwEZBijIgnvBYheId+blF+3Z5H/ihD0T6fbjOzRZ8F2WdD8AENGhoVAw9UIV3f6cZtc/JA3OF0JKKbS9naVTgsk28S3G60cHMf1hcMS9kxQYcEhH0nq60+8Poq5uc/m+o2+EGM0k+RIGLhbAZAZLFtpxIXm/FHIXG2LrcH74jXRb6+70+4Mul2uTvfii13XBT4PxFjDmssAUYuiS+U0ieo2k9opm73+D9fwWg/EYABD4mODk9y7aRr+2sLL2jw6pt0mNFxDERREP22wHKMREfWDjDSGxQ7C2s0Ae2p9qp4aelpb+8vKaf+p5tAtCXkTA9Ej9lEEII+vtiUcZ53MVqZ91LZh2ZLsMi8eF4AUMXEygAiIMSymPgsQbJGkHG9g2s3j44GZ/68T0XVnaLPunH5GFbz4oNNuzADJqF/OHQoFQQd5XIOVMAJCMXntQJNtClrevb+wt8XhWF4kprwjdeIgIF4JwIQOFYARBGGBJBwh4jUA7C/W8fZHdRBpP+HJsa284VuLx+CfJwu1M2qNE8hKWNBtERRTxCHKACa+ygS02jY7aDH7RiI4rDCEP2grDia4Fb25f17uwsvbxPKZNTMZ8EM1lUAmDiwkYAuiABG+HpvfobD+Sx/LvLGkuAIDE/uNFw4k9+Gdf53JniyLnsMRLLHCn4KjQkoz9g9NtCe9HfX29dK2oXs36yELDDPugFOT12/cOFxj/IyD+Mt48AEAIKdmw7fH7/Ql3CgQArFolbVdcs143hj+B6O45DDpQpCdeOG5lW0PDcEVFxaZhMWO/rsnHBXgeQ5QQMJuZBUCHCbxXCNEDNrYbgvNhaOsAgIkHbYZI2K4FAvUhl6vuZTnp6Pc0jf8EppkkeSoLEhKiq6RgaHCbJU1Py5P9FRXX/nNAG9zOmvYHAZSxxDwmqRFwlIHdxHhFCG2rpHAxDC26m6MIS2kkHA/V19cbqKvbsXD/8fvtobCfBF3AEueDcD4D+UQ4CqY3AONVaPwqhfOHIUKNDJocGX9id7KP4pE+ve5FnnroDU2KP7MQM6XkqYKRJwXts7GRyCv/KW27d3Q0H62ouHZdyDH8apj4N2TQdGKewgQbM796XBw9YI5vHeOT4DfkselJ32s7S6cES3cd/avgyCJu0igYChtJd2jKxdglE05CHw0AHIK90Ubh60iSNlafEjNyLRZUVP8xPw+t0uBLiOgSADOISTDJIEH0guVuYvmqYQvu2dbanG5OdrQvc2j6yyypFOCLwDSTifMI1A/G60JDN4ftASGGWSe5CRyZq9KY9l1YrA/sSJL3RNfl8bQbCoVCoTj7yB+2vxWMjwGRBaQMWgHCAkPwDb1Bx8Eyt69/EJjCkCUEXELAyC43IWZaDwqvRk4d7SlOFh0dTw2iru6l8n1Hd+uSGgR4DhPmMtMFgCxkFgcJvJcIrxPELu6fvLszxc4ZcWNApB/fpqW+3tgGHERd3eG3HTzYORTOX42wnCeI54F4JoDpDCogUJCYjwA4wMBhEuJNIfVdgZorD6ZbRBqdf/nnJFm4Q9O037HAXMnyAgKms+QwEb0J0E4S3BPStH224dA0IvHnSGo+bBPYmsmpFIQKegYcQ98gpnsBgFkeAbAVmT9Pp+xdJxfXKNfz8CPvqot2BB+w24MtLMQilnw+gaczk2DBR4TkPaTxZrBtu8E0mdiIbFlAMqSRLeVOuOkY11x8AqLz550L9x/faxsONWkaLjYgLhKSZ4AAyRwG0UFB2GMIfs2u857NV78jZb3f3L6u99IrrvlrKBR6iTQqIeapzCgigV4mfUMSGyZyDj9nc4K5/DZwtnDi7ogUozjdvr8DqB0NEPTOrvWNzyZPkTtc7po/MPimkWMG3d3d1pjQs+WJ4qysuQPEv7SGE2MtCK8CmCSBd5PFCwIDvY5BWhDrgc93vpC4lyRspq0aRuJvJELEG53kA13tzRmKn2OZ7/Xm5wftu6z2mAgASb13RoqXlFSsa60HDOwl4BUCtjNYgMQ8k3v7MYj+r6u18b2xeVVVRz00OtmyDSYx1rKAHvk/rw20Nd+dS1uyJbrlelPyGNQJsA0x15q/29XW/A2T/X8BUJcgcT2Y9oF4XsLfU9gfEVfZdlsEdAEAPQDvBGgyEy6mke1rzTA+39Xe9LNE+brcvtsZ+HWi36LeU5GizgHA/V1tTR83Bzjd1f8D0BdMQW1dbU2eZBmULqu5WAiOmVfUhLFw8/pnxi0gUZydRL0Fmz1u+Lvamt6VKO6JtEMuV51DTu7bHvXcayUAoDfi6TX+2SDgF4G2pjuzPjkTZZW+LxHhx+YwBnoF8RPMdATAAiJUWM8LwNbCcP7bIy9OYyyq8M7U7PaD5ry625rmIAVOt+8uAP8xckyE2xMJSOPazATtWJnb90UiXAUe+7gataQfRKPjDWb+cXdbsz+VXVZcS73nsWZ/IyZXxsru9qakb45Ot+8+YGwhEgG/C7Q1/WtMvp6aW5n5/vjU3E+gTgYXjHostpCsr3VVVr+HiZ4YDSD8vqu16ebkZwc43dUd5nLIEEsCG9fGeUaeiL4rUyoqri0ctAfTrXhNOSax2RzTEwljnR7ft8FIZVMbAyXmZ9N6v50e38MY9eg7RnQssQ0Rb1GLEtk8Jz/81kRi1/TXN5IeSc6ZgJZAW1NCz75lbt8e8/loBl24eWPjnmSF5GKMkf6684sATULi65Yofj+BOiXwliTtZNLrEWOX29cKk6hckJixpXWt2q7zLMTr9dp6gXxbyFEIQ3NIhMJiSDve+b7lQxl41Dv3qKvTSvbudRSJWba8/qCcPj00PIFCfbGwttauHbM7NPsxRu+s0CnefppKPHX50+loMQzNMWzTpV2XRhCOoZKCocFzbIECzfd682xGQbHQhx0kNDaELezQhoYWz5o1lGBLt7TU1dVpWw4eLLCFHIUyjLyQTZfCoGCw0Bg40cV1QOTZ7gMmDYXthYZuE3aHNHhYD03TBgdbW1uDyP7j3Gj9zOsPSrv9UOhExUCjjO+5EuXlNQV6nq3YJtgW1qXBmh46rg0O7m1dOXxC3iNzZ3NO7XEdPFjA/XnFmmCbkU96GEIvLDAGOxuXD+XyelRUVNgNo7goZC/MF9DtYQcbBQPhQU3rHzihOhI9JwxgkoDDbuSTntc/PHTC+Ubzzur+5dIWheL0gRYurHXkzZJFYYQL8mUeDTowPGXQNtDR8dQQxi/qIJfLZcfs2Q4jPJmMyeFQdKvzpHi9XtshvaiYwrJISoMgjJAsMAYCfv/ACdiBiooKOzCt8Hg+FdlDpEEYobCtaLDHd9nAiY57vV6v7fBhR95ggabNEpPCra316fvaU9h2w3Jfhu3HwhMx/jgRcjB2OWOpqKiwBx0zi3Uh81ka5JCkB+EYmqL3Do2z36GFtbWOvD5ZpAuZbw+RJhEKG47JAxNR/3NQl7NuNxSK04VFnqvm2Vj7Io/sJADsAuFHXa1Ncd/DFQpFPIs8NWUa+GuJvjEA0BkIE2BHvPPEDgl8u+eCqasxjjkaxRmA6b08JGCzsTYUnUMbxuk1ThTzvV4H+pA/KU/LCwm22XRpaHn68FBx8eC2hoYQxm3vKlFR0ZF/tFAvyg8a+SGbLu2wDw1PFQOn3VjplL3rnEHXaJSIzf1AIRycly+NiXoXP9nQwoW1Dtv00CSpcT4AaCG7tBUMBIf2Fw9u2zaO679qlShZuzavSMyyTQqy0XFtRTDNu8uEz+Hnak4w198GzlSUGHkCOZ3EyAkEFj/samv68kSXU1FxbeGAPfiaWSDBwF5iXNXV3vTqWLwK+4Bj+leJ8a2YDIi/0NXa/L+J8nZ5fNvNAjHS+KJAS3OqVeoZkUQYtZUZdzqGqKWzs3HA5fVOomHtCob4ZQKRWkoxcumKq0uFYXSD+DkGfaO7temf1jhly6pmCKH93CwYB4CutqaEz+SSpTUXGBqPnjsDe7vbmi5Id665sCVTkgmOiPjeglDBF0ZEfos8V83TWPssQNPm5IfuGPlotHjZyrdKIWM9NBFW2zTHR83Cq0uvuGaaoYceYuBac1Rmury7vTGhFyanp/pmMD1EwO+IxH9vaV0btxg/eu3+BpMgikCPBdoaP2CNG9lW3f6aVXBJoG8Zmnh0ZMv6RZ6aMo35FgCJnsU4MXJpZVW5IBHrfYOxyPxsxZ5Xzb/HeGEkfq6rtfkdieIqzm0WV1a5JAmzEPPxrram96VKM552KFF7y4RnNIhPmZ47Kqv0+Yj4r1Yvu+nEhOlwVfrWxCxsYX5gqED/tHXg51x+1UWQ4nMj4n+DyLm1tbHbmt+pFiOPxq2suRE05t2fiO8NtDZ/KpUdmeBy1/yVwe8fsyG5yLfE4yko5kkxYm3J4qqe9rX/GM0viRidgX8tCh/+w8jAvnx5zWxd8l0M3GKOl0yQfirEyJn2XdmQXIzM/QL0EWFzPPfK86uPRBZR2dwE+j4sXooJ+Hqgrel7ceeRTBRL9PE5eaGHRuwtq6ypIMGfI+aN5sUE0f4qxgMXA70kqM48tnUur1nCkh+wbK8DwVS3pb3xr3F2Jbu+QAuk+GpohtiwraFh+NIrrpmmGyEvmB+ytgvEnNAbcDZi5FyNMZJed8Y3qX/qXSNCxLJlVTNIiF8jsRg6cq0hP9zVtq559Pw8NcvB/Oe4xR0ZvG9Y31HUQiWFQqFQKBQKhUKhUCgUCoUiOUqMrFCcGAtra/PE0VC5MMTHiHA9Is5NkkPoI6Z1zPxAGLbnt7U3HDs5lioUCoVCoZhorCuNFGcPMfeWGElXBjgra24EpC9dhkz0XHdb0+/MYYOOoQ8QU6ynNqIPdrU1xoglo4Kj77jcvsvNgg5m+iqAhGLkXMHAdXFhxB/obmt+ZeQ44PcfB7Bm8fKqG5lFnIv4VPS0rOkpL6+Z1NnZlNTbYfeGdYcWVFTfkWfHtWaRzaIK78ytHf43synvTLElyl+sgrmtrc/sQ1Sca1Y9sZCfN8djoBeG/NgrrbEeIF95fvWRxZ6Vt0iWXWZRvCD+DIAYD50jdLU2P1xeXvOY2Su3lZ6WNT3OyurbQNQ6ZgM7E8U9EMwrJ8hYcRDh94HWxlWx59rYDeCrTrdvEYDrk5U9akP7uk6nu/pFs4COBT4E4NsJE0SEzqZDeiBdGYpzE53ENBEblBMPmcwcI7xnoNdB9KHO9Wt7zcHd7U2NTk/NzWB+PMZOTd4KWBaxZA4x8XLzuisq0D+XaAVa1/pndgH44mLPyu+GES6ItkvnIvcDGBMjMz5auuK6T/e0PBm3XWQxileaF3AysLfnwsnPot0UaUrfe4itXrH5P7vbmmPGEp3rG3tdrrpP8eS+xWZRKwOfKV1x3dcSlX+SybjvmggI4oNb2hobRo6jdda/ZGnNDYYmt5j7agm8F0CcGDkxfEdXa9P9Znujgto4IbeN+dPW5blWITIAdK1v3FzmvvoGQO8028XEnwcQJ0ZOYle/TvKDWzc0jT53UUHw485l1SEIPB0TXYhrAMSJkbMhl2MMKwT+bKA91mt894Z1hwDc4PRUPwumK61pDEN6Xt24Lmang+7WxvWLPSvfJVnGjLFZ8uUAUoqRCXSETc9rWNemZWK7QqFQKBQKhUKhUCgUCoVCcS6ih8RxoeEFEvgLAIDpdSbefIrNUijOGLY1NAxXVFRsGsqfdoAlrSPGCmYsBdEiQE4ByADjCIDXQHgNkjaESf4jXKC/ttPfdM56klQoFAqF4mxApI+iOBMhixiZiZO7KRe4EUS3pvsjongPjUwxXlcZvKq7tXF9kpJYD4dvBXhUVETAbNeK6guzOrkTg8DyqtgQ/kJ365gQ2cyW9es2EvD1bAtJJXIdYUdH81FiirlWwua4KNuyziRbwPzTTKNKoNp8rEn6UFS8E8eW1rWHmcWNqdJbyeS6zCnQX7AEuZDAozxBLjMfM9A7HOI4b54jP7OUnzA/B6lg4B5LwCeAVXFtt3N5zRJYtrXX2fa3TMpQnHsQUYwQjYCjE12Gs2LlXACLYsuRH+5c39ibKH5Xa+MTsNR3IlSNt/wSjyff6lH12PBwyi07trSuPXwOC5ExOz/UxEDM/dH0ofckjMz8oZhjwm/jtsxixHpmJ35uTr5+V6LsAoH6kEbiprgf9OHLMzA9t2TRd51wUaC7AyYhspnNGxv3gMUnzWEELK2ouLYwg5z7C8MFD2VuB2piAgjfSeZ9t7ttzU6rXQysyMwugBn/muy569rQvBpx/SDHiXezJddjjBGIsGN2vv7rZL8LQ6yyhhHoW1YhssmWbYgsGhjLA7g4nR0M2ReTRsip6dIoFAqFQqFQKBQKhUKhUCgU5yo7Fkw7DshGqevflLr+TSbxMxYFL55quxSKM4mOjo5woKV5d3iq7e86GT8lwZ9nyA8x03vB9D5I+ghp+JwmjO8MDYf++Gpbc/e5vKW9QqFQKBRnC0qMfJbCQMx24cSk5agoj/lASO2ZVJG3dvjfZKKN5jAy6G25MCwRpSt8c63iNGbbE8niA4ChaY/lyh4m2m0+FkwZCXfOTFu4v6u9uS2TmIsqvDOt25DnG4eeS5Vmkv5mjJdEAkrKllXNyN7OMfx+v87AXnOY1+uNe5YYfKml7Kd2dDQnFXd2b1h3CEQp690IdltejGdJAkpK3S0eazwy2LrV+0NqCxtFMsiQMU5PGRwnsj9hNOMy8yEDvV1t65pT2kXiwZgApiu9Xu+4dnHY29o6ZBX9T+ZJv3qb16tEeEnw+/264FjhJ1O819wFFdVTANxgDtMg/miNx+DlMcdMD/j9ft0ab4QtrWu3gbDaHCZILk0W/+SQed81EQhJ9al+tw/hKWvYkGOoNH3OtLqj46nBTGy49IprpsGykEBAPJwqzZyCUJwX5EHbUHkm5enT7U+njiFjxmEMrMgk32SczDEGS/anqvPCYX8pLg2MlF6fmSlmxw6m9GJkQEx8G69QKBQKhUKhUCgUCoVCoVCcrdTXG90b1h3qeeEfPT0v/KOnu23NztNgBz+F4oxkW0PD8NbWZ/YFWptf6m5r9ne3NzV2tTc2dW1sfDawvmnT5vXPbN+5yd8H83acCoVCoVAozljGJfBRnBHECB+YkFyMzDycUY7MMi4ImBmjbtCky+XxOVLngzzzSNJgOi+j8icErRiIddzY3bZmV6oUPS3uV53ulnGX6PJ6Jxnh/HmC5Rxitpt/k+BL6CQOq0+xLa+mjxJBs9njtg8fckx/h8vjS5pmCIh7RdEIcwAk9HRoZrFn5XQDxjyW2kxNyNFFGsySAJ6SwBmyBZpsPmLiTenKJMmdTOm1Qa88v/qIy+37HQO3jIQJ0IcBmCslScKt5tyEpJTCMcW5DWviCPHYA0OguGfuhMsQNMtcJ4moNV2agpBj86A9dtHzIb2oGMCRcRlB4hkwj3r2ZeCW4aD9Fpfb95QEXgF4JyD2a2xsz9f7Xu3o6AiPq5yzCBLi98zym6YgX3llbUlne8Powox8G11rbm4JaIl6bI2BQSUx7RLxy2nLl+hgwjVjmfDM7M5gwsm475oISMOWVL93djYOON2+rTCJhZlEcYokI+xOHyWCNPQ4ke2W1rXbU6Xx+/26y+1rMQuFWYgM7h11bmtoSDkOlZoICItPc6/Xa0sl8k3FSR1jEPWk+vmV51cfcbqr+2MWyglOWec0YeyWPLaelGT69zkCppjNZ9bG16YqFAqFQqFQKBQKhUKhUCgUCoVCoVAoFAqFQpEEJUY+SyFQmGEWmiGpl1v7IN06XMxfsIYLA98AcLspKM7LKgGzzcds8aiYCQJycvpYEwPpcpJZVxr1eptGgrtKAhahSBoWea6ap7F2J8B3cJCKRVQAbS3oZLipO21sIXoj46iCJ7HFUSszUnpUTQSTlvSelVXWVBDx/wNwo2QJAoFIgmMuTGbO460iHyGpL2nkKJJwNNNrzoIehORbxkLkR+Z7vV8c2arGWVldCZOXRwZ6t1w05Z/YEJeVQgEAsLE8YpieeqaJFyMLcDHHNLj8Zro0HR1PDTrdsYJAXQ5NxnjFyFL+AETvsQYzcC0B10ZaPoYkgUH7dDg9vt8T+KeB1uY4b6XnClta125zun1+AN6RsBD0DwL4ycgxE26KScR8f6K8rGMEwxBp20YWfCTGUTeJU+vJOou+ayLID72ZiXeNw+YDkihKl4CBA5nawDCKzaOCzMZK8XYJxpQMSjucLsakYH6fdZHC7n5bEYCkOxCk4mSMMUbLAg+lzQc0RMBoXhSWKcXZbNgGIOLWB6Ypg2PaeJump30WFQqFQqFQKBQKhUKhUCgUCoVCoVAoFAqFQqHIhsyUdoozDgbHCIeZkgtCOjsbB3paml63/jEQis3TIvqoq0vubTkLpBD29LEmBgFZYD4mIKMtyxmUseDF6am5TWNtL4AvZyNgzgWnky0AZe7BMANhVSYY4EQLLshZWX0/Eb8A4MaJKEdSrL0yA/GRYEobZ4Su9cufJ8KOsRAqLhi2144d4oaYvEG/Rn29xY+kQjGGEdYsQjQ5feJLiW1zGJRRewtwjBhTGDTu9qCrvbmNGB/NOAHjo8z0otNTffN4yzwbYMK95mMi3Dry/yWVVXMA1Jp/D+r4W1wmCcYIGofSCzOlsNQTPnP6rgkgQ+/cMc+IZJl0wdkIApy5129LH5z5WAkDsXZl1JenrRMdHRVBa1i+0AsSxc2I3I4xTksYiPFSTaIgrQhcoVAoFAqFQqFQKBQKhUKhUCgUCoVCoVAoFIpsUGLksxTiWC+SDMzLNg8BihUukEWMPFFiR5ZpvWVOGCRixDhEGXsHd2QSqcxTsxzM92VtVw44nWzJFtI4pVfATBEiXkTuqqz+EohuTRR/vBAjxl5CJgJ7zkKEv0oy4zexySMCS6/XawPwcfNPhiYezTxvxblIeLaIEaIx08UTXYaMey4yrfOWhRPCFkoSMSMC7U2PgLGIiO9loDejREwPlVZWlZ9IuWcyRaH8/7OIwl0uT/XbAUCSuD4mMuH3Ozqa4xfsJBgj2ERB2j7XWk8IiBOint2sSj82J86PPRYn9IzEIbSY/LIYK+XFHBFnYlfavBfWtse1HWTLG/c553KMcRpzkfnglbmFcbudKBQKhUKhUCgUCoVCoVAoFAqFQqFQKBQKhUJxIpwxHr0U2cHEe8xbbBPzUozsR59pHuDLY0NoV3wc9Jq3YZeaVtZzfvG2rIw9iR5cWWAApp2tmXlWJumsW80njcf4taXEfkD8ULLxpB04kKf3He5YsGDUAteevvsYuCWTvLPldLIlW3SyHxMYqxYM9HZfMPX8rDKpX8zAqph9zMuWVc1goh9ZYgYA/FRq2nM2yQdn5Q0f88+axQDgPXiQ9gft+zK4/zFeKiHSe11kUFpPlmYMMv6gsXaXKej6RRXemb3D9rfCvL070NLTsqYnm7wV5x7bGhqGne6aToDLAYCAkgUV1VMSikrHC/GxmH4INDl9olUCaInNRur9SSJnTFd706sAPgXgU+WVtSUhoV9CTOcxy4uJ6O0A11pF0EKI/wcgpYdkAqf1zkqAlnHHe5rQ0fHUoMvte4iBz4yEscSHALwE4CMxkVk+nDwn7jdf16AwJqUrm8HFZKo3EkgvmmRkIHQXtiyGQKeM8vL1BZ2dsR6G42AxxXwumkwTP0sEG/2G6R5kOlYCYLm/nIngNa3n64J+UWh1Tz2QN5yhp/V4cjXGOF0pX14zOyzZPI5pU7snKBQKhUKhUCgUCoVCoVAoFAqFQqFQKBQKhWKiUWLksxTJWrcgs0aCikvdvuU9bU0tSROZcC6/6iJILDKHEegVazwC+mASapKUM1Bff9oKIaWOARHjc5CK3+b1Tt3k9/clS7PwytpZCKffpb3E4ykAc4wnTcl8RU97Y2dMxI6O0f+yu2YoF+Ko08mW8aCFgkdZG9OWETDbtQVaIFCfhSfE+vggQZdaQgLDYV6eTIDpB+Dy+I4zZylGZn5LWvOILzELNdOxtfWZfS637ykGrh0Js9ntH2BG7KIBogcyzlRxTkPgZxkYbSfybHACaJu4/MUxc5vCwJJ0aRZ7WhdISzOUpxeesBjZTGd7w14Ae81hCyqqp+TZcS+AG0YDGZXpc6PiioprCzs6nkoqjGTgwnEbewqRTL8j4jExMtHHnJW+3zKwYjQM6D0v3/B3JcmDiA4yj4lNBbAQQHeqcgVRqbkKCEbS/nm0HOBzzBWqAAAgAElEQVSCdHEAeXE2be6pQs+j+QC2JI1QV6dhT19M/85iYsXIIZLHNNZMIVR86RXXTHvl+dVHkiYCwMBbzVeYMhIj82KkWSwXDocXkOXW7fT7x+0xO2djjNOUkJQuilkYgvWn0ByFQqFQKBQKhUKhUCgUCoVCoVAoFAqFQqFQnKWk3wpacUaiFQxvtIYJ4OuZpicWX7OG2QY4kThmU2w6vi7TMk4Fk4y8A9aw4JB9Wao0eWHdk1HesthlCWroaV/XmTByFAKXZJJ3tpxOtoyHwEb/gYhHzTF40hHfieZLhLfFHDM/mMoTrNfrtTFjQbp8mbDbEvTOdKYAoipdvgkS3RdTLnAnwDeYwxx5ob9lm6/i3IQZG2KOCVax/gkh2bBoVLm8fHlNSmE/S+NK8zERdqQS+k4UOzqaj5LG/24JXmSNd35xvDA2aBucnyb7t56IbaeK7vbGDoBG+w0CZoMQ4wWZCL/x+/3JV+swvWQ+FMzvSlWmy1XnkEB1TBagOK2zQfRmbBwuj3jVTkzpCt/5Vs/XpytS8IpUv5fuPrzYGmZjbd9E2rC19R1vWPtgqYeuTBYfAJyVvrdYdxGwsyOl8DwCFS+urHKmjAF2xxwTdqTPNzm5GmOcrhBTbJ2hiVt0olAoFAqFQqFQKBQKhUKhUCgUCoVCoVAoFArFCEqMfJYS8PuPE/ALS3Cts7LmjnRpXR5fHTN90hxGwC86OxvjPe8xnrWEfHnJ0pqUHgqXVFbNcXmqf+P0VN+cKh4zYgROFNampbY8PR0dTw0yECPUJsLd5eU1RYniL6ionmIAv8wkb40xJSaAkHL77vlebz6DvbFpjISeAcMOjtlOm4CUwuFc2nKSYICaY0IEvl1RUWFPEh8AUFZZU+Fy1/zB5VmZUGDOlusiiVJel/1DjjgRoX/WrPjrIuOEPe4yt++WZPk6K313ALGeqzOBj01dYxFQuSwCu0dSeflWKMxoxC+Yjwl0War42bZDcwuMgDVMl3wfkrinXeS5ah4TfmYOY8Y/UpWRjrLKmgqn2/cD14rqtN6JDdgKLEFx9vv9ft0qhJREH0+Wp8tdU4sEouYThUTsvWCmWRNdRiRj/MYSEiMKlUL7Q8rkzM/FZocvOiur3cnio7hvlbVeMYk44WQe23bFhlCx07M+6WIoYeCzqew8nSCSP46Ip+Pxer02jcSvzGEM9Ea9fU8gqyRIPGMOMYDfXnrFNQnHYV6v10aEBy127c3ULinoHq/Xm3C3lvLK2hIQfz8mMH7smRBDcH6Sn3IyxjhdIYrdQUGQ8eKpskWhUCgUCoVCoVAoFAqFQqFQKBQKhUKhUCgUZy9KjHyaUFpZVe50Vx8z/71laVVaj6ypEAb9MC6Q+JcuT833F15ZGydcKltWNaPM4/smM/6SUV4A7LD9nzVM2thfuqzm4kTxXctWXqmT6GSmT4LpIWel7xvJ7GdCjIjF0PjdyeJmgyBaZwlaFC7kH8fHXCXyHHR3OsHdCJJ4T0wA45rFlVVWD8WjeRcM2X4Z56mRtYQivbn2cK81rNTtS+o9MZe2nCyY2SJyo8sG7dP/nEw47nRX/xsRv8Dgm5hl+2JP1dXWOIJjPRgTcJvL652UKL+FlbWTifhha7j34MG466IJ8YI1jIAHS1dcXWoNL62sKgfFLRTIiECgPkQkkorjmfH78eSrODfZ3NbcbRbWMvA+JBEKA9m3Q1GPufeYwxi4tsxT/Wlr3IqKCruA9rC1HRKS/pj6LJLjXF6zhEj+A8CX2aBdZZ6ar873epOIE1cJYRjfNocQYj1Hm07CsksAfSEqOo6hzFN9qQTfOz7r0yD5DYtR1cmEoicCs/HnFD+39bSs6UmZnrS4MQIT1Sey1emuqmbCV81hBLR0t63ZaY3beeGkN6xhBP5JojbX6fFdD+DLqew8vaBiYeB3icS5+4O2rzMQ88wR0JATMyT+ZClntq6HfoO6Os0atTfo+E+rXQDfZ42XFKYrDwzZv2oN9nq9tpDQH7K2CxL4Z6JsCBzTRhFRUtFwLsYYpyV1dRqD328KCWxe/8z2U2aPQqFQKBQKhUKhUCgUCoVCoVAoFAqFQqFQKM5aEnohU5x8COI8ADFiC7vN4t02SzZvbNzjcvt+wsCXzOHM/BV7WP+K0+1rIGC7BDERLwDjGiT2hXvX5o2NexL90NnesNfp9t0D4Pax/LFACN7hcvt+x0ALEUkwv53ByxnyshilG+HbpctqHunZ0PiaNW9ivBZ7zN9zeXwfZ+Y1ILGzq7XxR5lfjTEMA/cKga9Ygm8vc/sqQPwwsbATuJzx/PvBmW/rTv1Td/HkI/1m0YxB4h9OT/X3QaJZEh+GLmdqpF3KWP8fAGXsGdfv9+tlbt9eszBaAM+XuX0bidnPQHt3e/NjJ8OWk0X3hdOecO7p24pYr6LXhwvlG06371cgDkBSMQhLiXAlM2LE+waL3wKI9dItsMlSx10cdLQ43TXfA/OLhjAG7UTnG1JcCehfhmXL+WRsaV172OWpvtfqUVwYRrezsuZ/ibgHoPMAro4XbGWHYPmwAbLWXzDQe15B+JnuE8lcca7BUvJviej7QERsuHjZyvItG9a+nChytu0QAAgSP5EsbzeHEdPdTrfvOoAfJyIpQdMHmO8gtiz8IH5uy4amGO+smVJRUWEfkLyOTG0gMX8vP2j/vNPtawToRcB4RbLNIPBbiFo+ByBmwQYTJ/HKTL8G+NqYuOC/u9w1f2Tm9SAMA/x2MKXdiWC8GCz2CTI3ZlSs66HDTrevgRibILg+0Nr80omW071h3SGXu+aPDL4pwc/3p03ftmans7L6ARDdOmopUKLrw7tclb5fMPEegMIEeleiMgwWiRcs1dcbcPvugklkzIwFwjC6ne7qn4LEFmJZyCSqwPyejE729MJ3IGg77HLXPMWETWB5HKAbAHitEaUc3+KWdMwpCP21d9j+35a+tc65p++t8NTcxxJHCWwnwocYbBUi99tteT/PqkDCt8vcvk8K4AlJ3ENMhb3D+BRZ+naA+4vCBXGL5qKZbAcw6uGdwY843b6PRXbE0H5rFrbnZIxxGuLac/RyNou5iX97Cs1RKBQKhUKhUCgUCoVCoVAoFAqFQqFQKBQKxVmMEiOf5czOD3+lN2ifwcAtCX6uZQAERhIRMgDc09W24mtAU9IIZIS/BZu9xirUiJZ5C/NI5gkdbt6VSIgciU5Pg/m2mDwZCwC6A5E8xyVG7tnQ+JpVQB21bimYlgIcvRzZOQYOBOpDTnf1XQC+a8pzNph+CuaIG3ISo7lnC4HrAfpCnM1ESwVjLYBREWCubTkp1NcbVFl9GxM9F/sDFQP4MphGbxEnOA0NiPO+GmhtfqnM43uGGFeNhXI5gD+BAI01SM72zketgvYjhvxk/A/8+Yh5E3OtN7c1d7ncvpYEoub7op5oFYqMIU0+Cql9f+TYIKMWQEIxMpBdOwQAW1rXbitz+75EwE8sWfkA8jFH+6A4uF8Y2p3Zn1GEjgULpHNv30YwrrHYOhvARwD+CCAgSCbOgLC6q/WKR4DmuJ8CbY1rnO7qFwG6zBzO4JtAuGm0pBzSs2H5Lqd7fWe0/TJTy4RaMPUBOGExMgCA+AEw4oTCNpvjsUTRrWjgr0kib+wYgYojXpAj1ylRX0TA73ra1yYRhAMIi5/BLhN4PKYvgBkMStw5nDFQMYNvilz7xPWJgKd6NjTFeeafCPx+v17mqfkogVssPy0C8w9ppP9NkJZBn33l+dVHsi2TgBIGPkMcrReJMid8s6PjqcEkObQCXGcJ9BHgIzI2ARjzsp2DMcbpiIS8mkz1RwpKIuRWKBQKhUKhUCgUCoVCoVAoFAqFQqFQKBQKheLEEKfaAEVu8fv9euCCqR9nIDsPdRF+2NW24tPAqiRqrQiBjf79krUqBvZmlz19sautKc7D6whdrY3/R4BVBDMhDOWHv0DAUxlFJvw+03OjY9N+BMLqTO0gwo5M42rMdwHcn3HeObTlZBFob36eQO/OJg0DvYD0bWlrejLR7w5p+1jmdZX7M73mW1rXbgPk/2fvzqPjuK8D33/vr7obAEFwJyVxkSgRIonmIlEwCYDU0hYBUJAj77BlJ/bEWRznZSaTl+XNZN5kgpn3ksl5OSeLs0ycxBPbUbzRjm0pMsVNgkSRIEhBlLkAJAVJlERxlbgTS3fV774/ugE0QAAERZCgpPs5h+cQharqW9VVhe5bt+6vZqTrFd59N0sP/zhwWgx97N2uz3xwtW17+nUV+roPi3xyuPmv9DoEsH/7xj9T4Q9HvoSeF+GBoTo0j8jatVFb06qPqui7KGiW3VE684vD/O1TnP8kcHAEKzsI/OjKY7icBq+qvzf6671U6+xJjQOvmYJ8e6TFpnubNx8X3Jor+xsj/9A6Z9KvDDdHW8v6oyJUj3CFP2Jk79eYE/izEc63Na2xX7iWsexv2rANrz93Jee8wpf2b9/4jRG/iOgWRLdcfkZQ+Gpb06a/HOr34zIFX8t+BhiZa/EZ40YjuE/m/fDkga0bj4xhOMYYY4wxxhhjjDHGGGOMMcYYY97HrBh5dA0s1jg10gUFPTdwWibUs1cdEcDatdH+7Rv/oxN3J+jfXm52ha96L3e0bd/4ny5XiNxj//anDl2QC/MVfmf4opVcEaaL5rZt3/DnlwvlnFyoUbThSovfLudQY2NXenKsXuF3LlO48v+1zZ70JeBo/sSoILgw2MytrWvTmUmxT11uP6jwtIje45W/6f+LoY+Zvc2bj/tAFgry7Ut+KaSvZywjotJ/H6keHWLOYbVu37COjJs5gmP3oIr8F1eYmde2ffOl7UxzdjevOxxT/yGQ/zXcygS+EajeichzPdMUTjQ2poY8J9q2b94kovcwbPGh7BbhARHfr1Bc4fhw8fSPzfcrDFTYuXf7praRLm9Mf9J7LRZYvqBi9cBuu72u9DrUY3/Txv8Brpzh2uyj5wX574Hqna1Nm0ahq2+D39+06a8zGpuI8u+5TDGqCK+i8rm2ORPvOdjS+PZw87Zte/p19X4l8PVhZtsYd3IfaEv+xCH/5lzhNXN/88YNzvkVgz+0I5nhlr0ia9dGDl7vt3aJ/vlKVrGvaX17R0FmEeh/vczf3EYnvq5t+4ZfY+3a6HLrbW3auDl3zV031DwKX72pMPMZlf4F1THnBv+MNUp/u96t1u0bf0dVf3/ov9t6HuW/RUFRXXvzuks+O/YQ3/9zpao7+W7iadux6UkywQKGP9YR+AZOlly2EPmS/Sv74hddHcJwx9TBXJHzbzHMMAMtLU90eInuEeSSrt06xDkx2p8x3s1+F8i73uj5Lh/rvMz8/V9DODbYfItWrl7er3u6+r+4XCzGGGOMMcYYY4wxxhhjjDHGGGPMu3VtxxE3N6S5qVRhUWd8jsLtiN4miKryhsBrnUWZNw81NnZd5UvIoqo18xS/zCvF2SnytsO/NaMg3NPY2Bi+m5XeUV49sdAFs0WIRU7O7t/+1KHLL3V5pXV1BbFT0WJxeitebhH0nKgc0XHpHa2NjYMWHY/UglU1M13kk4Ir9dDlkONRoD8bhc50srhi9YwM3BTTmGSi7rcuVzx3DWO5bpLJ+gQTTy9SL4sF1AsxlCMCr7U1b3z5SteXSqViJ7sL5qI+6ZU56jil3h0Lirp3Xu17v7Sibnak0fzI6a1OKMDrMXzQ3rpz/b6rWS9AWWXN/wK+0vOzqvza/uYNf3+16zUfXGVV1c+hcl/ux79r277x10ew2BVfhyB3LY+7lQi34DUtwrlQ/aHx4bj2lpYnOq5uS4ZXXv7IuK5Yx9xIgnlOdaIioQivOY0O7W3efIJhCh2HW2dnvPsBj5/tRJwoRyOC3aP1N2okUqlU7HjazXJhfBLAxXHdB0bhbzkAi5fXzokCfaPnZ4UTNxdmZr3bv+WALKyqXizeLRI0piAE8nqQ4bW9Oze8+W7jXLqydkao+oCqThNx3UJ0xAWFzSPt4DwWyssfGdcR77qYP61t+0YBmF1VVVQiJctVdZZ4pjjkuDp5oyid2Hutz5OhJJP1CUpOr1DkdgFVkYyIvCbQvq9p/dU9wASU3lc3PZYOlyHMdFDoRQ6rj9440Hzf3pE+HNervj5IHjk9SzLBZIB9t03Ye7kC99H+jDHWkpU1/6TwiwCirG9t3vjQWMdkjDHGGGOMMcYYY4wxxhhjjDHm/cuKkY0x5j1kfnlqWhCP9+u06MRNHY1CMPPBtWjl6uXeux09P9sxZXokK2r+WIXf75ui/2/b9k1/MHYRvX8MV4xszNVYXLH6pkhcb8dkr/6uA82bd49lTMYYY4wxxhhjjDHGGGOMMcYYY97f3FgHYIwxZuSCePz/6T9F/9aKRs3V2rdt807guz0/e6+PjmE45gaxYNVDC/oXIkMQOevCbswNLhT38z3/F/iGFSIbY4wxxhhjjDHGGGOMMcYYY4y51mJjHYAxxpjhLayqXhJEbro6/ULPkOs9fBD76ljFZd5fYrHE/xFGmRcVLVKvOy6/hHk/WrqydkZ3qLcGokt8FP3JgF8/tnfnhjfHJDBjzIgFXl6KAv1D57WjK+QfxjoeY4wxxhhjjDHGGGPMKGhocMnv74ul0xcEoH3Z+JC1a6OxDsvccCSVSgWHDxcFABMnzvEtLX8fAjrGcRljjDHmA8CGgjbGmBvYwsrqlCDPDPHr77dt3/jZ6xqQMeZ9rayq+jlU7hvsd179XdZhdfSUlz8yriPedTF/Wtv2jfbZ3BhjjDHGGGOMMcYYY0w/yWQyoRNnPyxev9IzzQsb9s+Z9JdWkGzyLVyxer644AuiuhzAix70kf7zwZ2bd451bMYYY4x5/7POyMYYcyNTSQz22IjC4Xgs8ZVLf2OMMVdBJT74dH7LCpGNMcYYY4wxxhhjjDHGmOsvFpsdD/GlKrKmZ5qDo8l9BK1gxcimTxBME/WrVOTDAALTXRBsHOuwjDHGGPPBYMXIxhjznqMvuij44p7tT54e60iMMR8Ayn9ra9741bEOwxhjjDHGGGOMMcYYY4z5IAqnpEW74m6s4/ggWHLvRyaHUfcjonw0O0VeV9W1bc2btr8XYnHeO3USoD1TRJzzduwYY4wx5rqwYmRjjLmBSej2aNz/saAedUeR6GDbnCnP2JBLxphrQZC/RvUZFb2oIq+KRNvatj39+ljH9X7U0lLeVVa57Q9EdRyAIofHOiZjjDFXpr6+Pti160IMYOLEOb6l5e8jwI9xWDe8QfZbCH23yIwZbSM+VxsaXPL7+2Lp9AUBaF82PryRv3vnb1ciMV5bW9eG2DXIGGOMMcaY96XYqYRmilHUvj5fa6HXCaKyXOFjuUltzskLwHUvRn43sUQi6tTyLMaY9wRJpVLB4cNFAXzgc8UD9sUJ39LSkhnroN6HpLy8PHb27AwH0D67M6KxMbxur56Xf87mc4ngxs0/v1sy1gEYY4wxxhhjjDHGvJcsXLF6Kk4+6VQ+BYDT173ynf3bNzWOcWg3tLKVD9+mGn7eeX0AAGEvgfun1q3r941xaOZ9aqTnajKZTOjE2Q+L16/0TPPChv1zJv3ljViQPL/8kWmxeNenUT4OgOjbKvLDtqaNPxrj0IwxxhhjjDHXQCqVip3oSpQj+rCqOBXNiOeFtuZVT0GDPZQ4iu5cvvqOuAv+k4p+GUBgvzr+uG3bxn9+L8Qyv+rBWYEED+JlPoDi31DvNh3YseG16xW3McaMxMIVq+eLC74gqssBvOhBH+k/H9y5eedYx3a9LapaU6refwGoAMDJLkG+vq9pffvYRvb+UlZRXSkiv4ZyC4AKz4zLFP5VS8sTHdf6tQfJP58HftLavPGxa/3a15t1RjbGGGOMMcYYY4y5AhLT8ai7S2ENgKjsF+X5sY7rRieangKuQiW734CSIIr+bUyDMu9rIz1XY7HZ8RBfqiI9xyYOjib3EbTCDVeMLEF3icJd9J5Lchxlz9hGZYwxxhhjjLlWGhsbw9lVVbunSMlr3kfSFU/4cWejDitENgPNLPDHz593j3fHfCGAxAvTU2MXzx8Y68CMMWagIJgm6lepyIcBBKa7INg41mGNBe+jaQgrQaoBRH1CJbCmA6PMBW62V10D2WJk4PTFoKMIuObFyIPkn88KHLzWrzsWrBjZGGOMMcYYY4wx5gr4MOYCp0HPeHGqKirOjWlQ7wHeOyfOB70DdamKBrbfzLUz0nM1nJIW7YqPybG45N6PTA6j7kdE+Wh2iryuqmvbmjcNPexuLHTOx4KeUSsVBBE7l4wxxhhjjHkfO9zU1HkYOsc6DnNja8wON382988Y8z5z5/LVdwROPuOEDwEovCQZvtXasumNsY7tSjnvnToJ6EncIeKc/0Dmt9Q559T35TARwUcfyH1xLan3DnExeg86ER9Fcj1e+9L8szrep/eU3pcbZYwxxhhjjDHGGGOMMSMRO5VQRPTyc46+0OsEUVmuyMey/6hxTm4fbhlxoiKMSbzGGGOMMeaDK5VKxUrr6gqgPhjrWC6rocElk8kE9aMXa319fVBaWleQSqVGveFbfX19kEzWJ7hO9Rv19fVBsr4+Qe/TwpfR0OCSyfpEeXl5fBTDkPLyL8ezx9Tob3feNo5tTUzPsfheOG/y9J3v1+a9KS2tKxjN89OYD4qYkxni5MM9eSSQ+33MTR/ruN6NSERRy28Z835jnZGNMcYYY4wxxhhjjDEfWFOmpLtPdCWeQ/gfquJUNIPnhbbWRSGsvaavHWa6g7gLEojGAATiXobP2Uad8k4spj9B5ER2ip52yPPXNFBjjDHGGPOBU1pRNyEgXS7O3Sde5h3rYkaiM5SFFWfO42pfRv0LGsj2A1s3Hhl0BQ0NLvnks2U+CFYi4vBewR3SWEfTga1bzw+2yJJ7753s/bhlkeqdAILrFKI9rU2bdvXMM/fu1KSCgmCZODcfAJUjMY12UBAkNM2DHir0qa2zfMmsgrLDZ7u0ovq4E9nlvX96/47N7YAf0fbX1RUkzoZl6uXDIn7hvjfP3JyYSsGxrnh3srLmDaAlCoKmA1ufOghDF1Mlk/UJJp5e5L1bjlMRlTPqo10+GnfKxTvvB3lg35tn5lJCQbKy+gLiWgjl8dad69vyYpVFVWvmRaqrEC10XjO4YG9r0/odA19vwaqamc7LCkVvIgIX0E5BpjnKFM4SH9aIyof2vHn6JqciZZU1Hai2Oxc87YJY857nnzzd896VbXhuDqF7AJEVrN82mxIt7JSpurCy5qiIbJVQts8o7j6Q68Q7EjJvZe30uPf3ilCJypxODk1KnFIpq6g5heg+CJoz6na0N687N9yKrnAbL4K2KmwuzrCrpWXToB2DF1esvil0LEelXNG7eqYrTFfVuoVVNeMAVDkaRJkdrTsbj12yktx+Ew1WeC/znOgsfWrrTF8yq7is8nQGrT6NyFGvut97ffblnZtfY5Bj52piGez8yDiaX9m24cRw+zSZSo2no2AZzt+nMP9Yl9yU6AylrKq2C/SQRjTH1Tfv2bn51eHWM9jrd2u0IxFzQRDyoELlvjfPzElMpaDszdMZqax9TUWfIea2t21Zf3S4dRtjwIsETikgV++naMw5954s7FeJDiHB1/GyBUDxb/jQ7R7ruIwxV8eKkY0xxhhjjDHGGGOMMR9YjY2N4eyqqt1TpOQ17yPpiif8uLNRBzSMqEjhenu15d7zyVTjc64zaAEIlbBjXObiWMdljDHGGGPeH1KpVOxYOlguPvqS4laIcjOiEwUKVUAgg+o5QT6hEbvLqmq+Oy5duL6l5YmO/PWUP/FE0BGbukTQ30IZhziA1yUs/jvgewwowpxdVVUUhgW1qP6uCNOyU/3rqu7vgN5i5OKCYKY6eVSV2uwU3RU5dytpvRvkw8AMUYoRHF69iHQoukYC94myypq14zKF3x4Y6wCycMXDd8rp8IsKNYrORGUyShGCE8WrcAGkzvnolbLK2h+nHT8cqtizYOqFiZ1p1ojor2W3WA8TBE8GrjsmyOcVZqpSguBAQtCVBFpbVlX9kygdPnawpfHt+vp613r49AqBP0Al8IgX1e8AlxQjxzKyMHL+NwW5HQdeeYauxOyA6JOK3A1MF6RIBRQiETnrva+JSP/o9orVX5sSnjl18annV4H7Ck7KgRl4Ha+CA0WgA9WUxvTlE92x7y2trf3e7g0bhv0+kkylxmt3ohqvX1SkDGUGMF7RBAII3aj7MOhn4hI1Jyuqv9XavGkbQxSOX8k2AiEi9wn83MU4mxdVrfm7fU3r2weuU8WVCnwFWAZM6p0Ok0TlIaAKQFRfQgpOA33FyA0NbuFT22+VdVs/pgR1OJkrTieoUgyMEyEGogjdQIcgZ4LAfaassvZx9dH39+/Y/M5oxTLw/BB8SyLiJDDo8ZlKpWInugvu0S7/JZyvAL0FZKKg2f3n1atwXhwPR7j9CytrfxiPxR/vLVwfYLDzs1CC2RrqXSo8CNykyvjc8a6Knkep1oxvTlZUf721eZM9aGvMB8TMAn/8/Hn3eHfMFwJIvDA9NXbx/IGxDswYc1WsGNkYY4wxxhhjjDHGGPOBdripqfMwdI51HCPT4FsbuQBcGOtIjDHGGGPM+0t5eXn8RHf8flR/F/wqQUoGmS0OTFWYCtwmyu0die4ppXV1j7WvW9fdM1NLS0tYVrnmIOgB4BO5ybcgemr+ijVtB3es/1neOmU8JctAfxm4B3BAGqQ5CIKd+S8eERQJfiYwF0CEScBdCFNUNVu4KT1rxQHjQcajzARmdia6gtK6um/kx5ofx8Kq6sWi4X8A/TgwXXp/02+dE0AnoNwKzCvwfkbpfXV/275l3cmBK7wYdidiEkzXXLzATaI6B4gpzOq3boih3KIwA+RtFy/8MfD2yZMnxfvEJETn5bYZ0JsGiZ/Q6fhA5DbV3P5RfQThXoU5QGG/jYUAmIIwWZSphZMtouIAACAASURBVMj4i/HJLzvc5xStAMYNiI/ctNtRZikyJ3NWS+amUl871NjYNVg8pRV1E7Q783FV/W0RFkq2o2d/SgHozcDNwFxEbi6rqP2rtuYNmxikc/CVbGNun04n+17O8d4XLqpa8xcDC5IjR7F4mQM6c5B9NDn3D8SdEBcW58+zeN2W6ZG4zyL8hsAtqA5WhyO52ApFmAI6B5gtzmWA/01e4fXVxDLw/FDlqAvcuEHiyT540BW7V9DfAe4HJgx8sxGcwERgogq3imppOsrMKK2o+9pgHawHOz9VWSrZ60X/8zP7vwnABEFnq8jEsuUPuradTz83WLzGmPeXXGf9s7l/xpj3CTfWARhjjDHGGGOMMeYDQ1KphlgyWZ+4NqtvcMlkfaK8vDw+SiuU8vLyeCqVuiEe5q6vrw+S9fUJLrkzNISGUd8fcIPtk2E1NLhk/ahv/0hd42N97OOor68Pcusd2fGYJ5VKxUrr6gqgfrSGkbxBjssGV15eHmfM4xiZvvfhWuSIr8n1xxhjjDHGXGOdicmLvecrgjxAv0JkOQaySZGngJfzFilSuBv45cRZ/9CA1el5Odcm6HdRbc1NKwBSzvkv3H13qrfja9nKB291qp8CVuaKfQFeEvhm2azxh4aLWZVJqtyh2ttBNgQ9z6UP78WBhap8KnYmKh9sXcny6jkO93nQTwPT8371tqhsAdYhvAT0dFaOg96hyC/GM5lfGOHn3yLgNnoKkZHzIIeAU71zCK+DPluciQ/azfaKiEwD7iRbCBsCJ4FD9N8/AsxG5BedyH9W0ZX0FCKjncCbwFtAOm+ZBMoChY8Wd8UH3Z80NLg44b2q8tuiLKGvEDkNtAvylMBm4PW8pSYoPIjorySX19w1itsIMBXhox7/EQZ8D9KQU6C7csvlC4EjKuxUYSfwM0WO58+QiRV3IOqBm+hrCHgBaFPladB/Q3QL2f3YIw4sAP1Ysqq633ZeTSxX4mRHwSIR+TLog2SLgnt0IbwBHEQ40xcYBSgLnOqX4i6qZwTfJbPnpc5Des/Pc8ChfusFstcbrdYg+FT+tcGY/t6buYa8HNoNW6P3rvN8DQ0umUwmRjHH9y5dqzz4l+OjmTvr289jvb8gm8f88hXlU69FLrG+vj4oLa0rGM186hXfR7kSY3vP4T3hPZEYN8YYY4wxxhhjzHtPMpUa79PBEiFYJqqzVZlzrGvbNFeikqysvaD44yLuTRF2BONpHm5Yz2SyPsHE04u8d8txKqJyRn20K54oPBmFmUpFHxC2laI6vlOmarKy5hiqW8QFz+1rmvAarI1GELKULqubFi8M7xVllcKtnUhJR5cPyypr3hHVvTg2q9dR70a6YFXNTOdlhaI3EYELaKcg0xxlCmeJD2tE5UN73jx9k1ORssqaDlTbnQuedkGsuXdozIYGV7bhuTmE7gFEVrB+22xKtLBTpurCypqjIrJVQtk+o7j7QK7zxGWVLqubXlCYLvcalAk6S2FWJzKpo8uHCyurz4q6kyK8ivjnZxSEe0a63supr68P9r5x5g4RWeFFxwOgejIWuZ17d254c6hl9h86dVsUk5RXWSZPbZ2JUNyRmByWVdYcQ9kTOdcUOzvhpdbWtenB1vFujeaxfgVkUdWaeZHqKkQLndcMLtgbu6j70sXcBVotyqJjXdsmuBKVssqacyAHVHVLSGz7YB2Mesy9OzWpoCBYJs7NB0DlSEyjHVGghepdLUjVnjdP3+JKRBZW1r6D8GwsZN1Q701pRd2EgHS5OHefeJl3rIsZic5QFlacOY+rfRn1L2gg2w9s3XhkpNs+yufqoPuytWn9JUMe56uvrw8OvH721jDmU97L3cLWWy4ytaSsy4dSWfM2yl6PNHYVpfcN7BK2uGL1TaFjOSrlivbeeFaYrqp1C6tqxkG2i1UQZXa07mzsHXZ3qOvh/h2bDw4XbzKVGk9HwTKcv09h/rEuuSnRGUpZVW0X6CGNaI6rb96zc/Orw67n+lyPjTHGGGPMdbZg1UdLiLruE9EasgWzIJwEedzh1oaeoy7wXpWpoloN8vPA7UAc1btV9ZF5K2ubXtm2obeA9nBTU+fSlbWNofdJhd8jW+A62cFHuotiu4HHksnUOB/F1uD0cyg9XV7fwMsPGJfesnbtiD8/vqnKTwW2gjvmRYsclCE8jHJ/bp4YUC7q65LJ+hfyvxvW19cHew+fKUf10/R0noUu4BlF/1Gcvoa4DJEfj5NylF8AKgFBuVWQNR3xac8CL44kWIHDqvIDETbg5YKKliC6DHHLnfKSxt0PW5qe6Lj8mkYkVHQXwrfUB/sCDUMN3DSFNaLUA1OyITFdNVeErZxB2CAiP1CR46oqgpSiPApandsIJ/AhDx9NJut3DvyuXbbhuTkqwRqBRXlF5u2KPua8Pu0DORNEgZMgujmCT4rK54HxQDHogwS0plKpvSPMNYxkGwFuQbl/4YrV6/p9h4p3HIh88Z/E0Ce9yi8J+lBuG48IfMM7nsjuFne+4DyH81/4wNbHL5atqt6ikT4tyBIRfRJkk5fgcBBqh/p0SCxIgNys8AjoZ3PxxFHuVAmWALtGI5aRWrq0tjgT01VE1CE9heekgSZx+k3FvaIQOpHpqlEtyKeAm3LvY6kodWUVNc+1NW98eehX6acd5TuqutWhHRLEilV9lQqfI1tIDkiJQGVXUawCWP9utstcP0tX1s7I4JerymwYPH8x6HJLa4tzeasluUnnQu9/1t68ufWSmXO5TvWxlIguQ7fORJmQzXVWnxLkZ6K6LTbR7bpMrk0Wrlh9p4qsEicJlG5U9uxv3tAy1AJL7r13svfjlkWquePTv+XT0faDLY1v5883VI7ER+NOuXjn/SAP7HvzzFxKKEhWVl9AXAuhPN66c30beR3RL2fBitrbA9FVqlqOyO29Gwa3ov6zC6tqlgGIl1fPu4nPH25a2zv616jl+XLvh2iwwnuZ50Rn6VNbZ/qSWcVllaczaPVpRI561f3e67Mv79z8GoN0tx8uroyjOf9zxHD7+BrkoWTeytrpce/vFaESlTmdHJqUOKVSVlFzCtF9EDRn1O0YLq+ar76+Ptjz5vk5TsMHQVbse/PMLZRQUFapGag+CrIjcLFnQh3dVNlI91knFHd0xcJkZc1J0F1p1c3tzZvbyL1vC1atKiEat9ShKZDFx7pkUqIzlGRl9QUVacX7LVEY7Rp4XlwuNj/x9AKnpFBZtO/NM7ckplJQ1hXLSFX1EVR2hd41zRzXvW/E9zBK6woKpviF6vxqVblrz5unZ/TcRxF4TYXn0yJb8SM+5XqN5T2H9yorRjbGGGOMMcYYY8yoSqZS4+mOV2iXfkqQFaDTNHszabygBZodTjQEOhW94D0n9CzbF1fVfmtv04Ztg62zYOqFiZ1p1ojor2VTYXqYIPhpGGaC3E2cmYpOQIjlcmWd4uR+Vf/xsoqz35bz9f86XDIolUrFTnQUVOGiX0O5R7NDg45XNA6iQJeKVKM8iPCsiiTQIXOpVyyWkYWR878pyO048MozdCVmB0SfVORuYLogRSqgEInIWe99TUT6R7dXrP7alPDMqYtPPb8K3FdwUg7MwOt4FRwoAh2opjSmL5/ojn1vaW3t94ZL0pcuq5sei4fVIuFHvbrFik4CioFiRRMgKpBGtEuVcyifO94d31RWUfPPV3Ajaiiy7/CFpSL8pqKrRMl1GZBnI6d7BlsguTx18943T39CnPs0MFdgGjBOlVju/etAqA3UH/ETzmxesOqhbx3Y+tSBq4zzmhzrI1VfX+9aD59eIfAHqAQe8aLRU+lxvCTKV0BmAVMEjWfjIAN6VoSPxYga569Y8/UBwyL3Ki4IZqqTR1WpzU7RF724WXi5R9BqhZt7jkcR7UZZGcXk4bLK1d8Zlznzry0tLRnIDfmaDpaLj76kuBWi3IzoRIFCFRDIoHpOkE9oxO6yqprvjksXrm9pGfqG+7U4Vwffl/odYMhi5N5jTuTTqMwlO+TsOMnFoWgXIjUifKyoK/ajRVVrvrmvaX1vpzMVVyrwFWAZ9HaIQmGSqDwEVAGI6ktIwWmg92beYNdDJ+5rwKDFyKlUKnaiu+Ae7fJfwvkK0FtAJgpapAJ49SqcF8fDEW7/wsraH8Zj8cd7H3QY4Fpfj40xxhhjzNgIfEcpyGpgYm5SWuHZwEd/lrx14oG+ouAGt7Si+ZW0hE7gt8gWGBeBLCv0Wgk8nr/e3ds2vJ1cWfNjPEmgHkDhDlH59KKVD7VFPix26BdVuSW7hHaCPEMs/H5rY+PIHjBUzgCPR97/WaY4OnKosbErlUrFTnYXPO81PASuGOjp3jsZZXFQfGo20Psg3s8Ov3Oz02CVwNy8Nb+Iyp+H78Sea29f152bJneUV7cl4qQFuQm4HcF5WIbqGkZUjCzHEB6La/A3u7dXHIEGT319MP/VkzviseBHAYlzu7esG7ag7wrtEJU/6s7o1ldb1p8FKC8vj3fEpuwV4aLCvwfyR9S5APJ4gP8Tf3byK225z+9Ll9a+EBVHb6l3kQprcvNOEHSeTj03FTia/6LqY0sFfZieuhThJF5/5Hzia607f3qc3BeGVCq178TF+HEfaLFki9wBmaqw4sTFggXAvlHcxhhwG0Ewn7zvUAe2bj0P7L9z+ep03AXVue/RiNKhjvYDWze+MMxr+/h5tyccr7+v3k/zGm9350qO7B/wvSeVSsWOdha+5fDFiH4x+wIyBY3m5M93lbGMSLrY3yFeUnkdiwFexOmfxi64xt27szmj8vLy+IXC6fslisLcd9gEEFf0LoQH6N8pfVACbary1wHRD/fu2HwCUGhwiyu27IqQMyC/C8zMzX2rKHdjxcg3vFD9LFQeFbgXQOCYxoJ/BL4+3HLdhVrmVH8TpAJAhVdjyN8C/YqRl66snRGu3/oJ1aBe8HNVZZrAOBXioIhIN0pKRR5Nn9OtZZUP/lPb9qcHvf4mk/Vx705Vich/FcUBnSr6GDBkMXImKpwt3v+8iDyYneJ2xgs4DvQruhwiR/Jk4LpjgnxeYaYqJdlCfglBVxJobVlV9U+idPjYSIs4Y0K5F/4wN2rBlN5fiMxW5edFyRYfCxsL/YU26HtQ4arzfI88Ei18avutsm7rx5SgDidzxekEzT5ANE4kl38VuoEOQc4EgftMWWXt4+qj7+/fsfmdwbZpYFyCb0lEnAT6FSNfjzxUMpUar92Jarx+UZEylBlk840JBBC6Ufdh0M/EJWpOVlR/q7V50zaGKShPplLj9x0+UyfKr+CkVJUZKONyx0I2Xw3VURTeD7pbRUati++I9xm9ufNORaoTwgOLqqr/YV/Tpo0LVtXcHIT6eRX9HLiZoFMETWT/JkmIcj8SfCyIuS0LKh76+wPNT+2+XFyLqlKlqmd/QVQeUpiJMDl/n6jP5fDFv3GsM7aubOWD32nb9vTrw60zufzhm9WlH/UijwKzEZ0qSGHPfRSU80Bdgeo6L+7klezksbrn8F5nxcjGGGOMMcYYY4wZVb4r9iGQ/1vgHvpuYg4UAylBKRG4RYXbvSe+qGrNiX1N69sHznwx7E7EJJiufTcFbxLVOWSHtZw5yPqLVLkDmAV6i5aciQP/wmAJwoYGd+KnW6rU+d8HHqB3KNJeQrYr1CyyQ3ouQnVUh1ILnY4PRG5TzW6fqD6CcK/CHLLDjOYHEwBTECaLMrUQGX8xPvllh/ucohW98ffPrI0DbkeZpciczFktmZtKfW1gt1bIdScoPFMtSoPCHIGiQZJ0QnZ43QKEiSCzUUrFaby0ou5/jrQ7xGAWVa2Zpxr+ksIn6Dt+9oiyqSgsfGvg/POrHpyFBv8O9MsKc9BLhokTcoXUwGyBO5z300orVv/loF1XrsC1ONZH6uTJk+J9YhKi8wBEQJFPC7IGstMGiJNNmE4TdLZzOn5hVfWf72/adEmBd0RQJPiZ9JxvyiQVvQtlKsKkfsdDdpjduahOR9yhd0pKfgJkysvL4ye64/ej+rvgV0m/IZ77xTRVs4W8t4lye0eie0ppXd1j7et6b/T3uUbn6mD7EvSmoeafX/XgLK/Bv5O8Y27AOSIgRcAsVb1ZkNne+8nzqx782sGmp98CiBzF4mUO6MwBCwZku7BlO7GJOyEuLM6fZ5Droagb/PhLpVKxY12xewX9HeB+YMIlIxRmu5lNBCaqcKuolqajzIzSirqvDXYuX9PrsTHGGGOMGTOKzCX7sFyPXUHov56cO+VA/+7EDX53c8ORO5dvXRsLKAU+k1vDbZFwNwOKkQHfkcjsL+qOf0eU+Qp3AQmE+7yP/rsgXZr9TgWAIC9G6r55YNuqN+HpkQUv7BTHP77c3NeFMddN79SSez+yIePTs8VzOz0dgEVuDgO9g7xi5BjM8sribDETAO2o/Mu4sGBrS/sT+d9P9NWWTWcXrKp5UiI/D9z/CSREmYboggWrVpXkikmHCde3QfCj3c3rDsO67MS1a6OD2SK3EXcXHKG3gJ+cdxeeOdzS1NspM/sQacMrC1Zse9I5rQRW9gUoe0T0W3ubNu0nr6vl7t0bLi6trd0SnvelqFSS+x6sIiVBOpxOXjHy7KqqIvF6B9L7vSEE2RaK/tPLO3/ar9C6sbExTCbrW6XkzLcR5tHTcRqd7V20kMsXI1/RNooyWTQa7LvLu5Yr3v0ZNAg0DPpdp7GxMSytqzvgTumLwBdzkychcstoxjIi6uYC9/S+vSKvKP5fEnmFyJDdh6lU6pVjmcLvItE8hI9k52cOnrtTqVRs+M6V2qm45wsTwdpdWzac7Jve4Pc2c3xJVe26EF2G8oXc/FMR5gy+LnMjUfGnRIMzebmBmaLu3oUrVv94qOLTbEG+LgF5iNz1w6m+hrh+Hb7L7ltzSybjvwD8OsqtiAzMu/Tko2ZmX5fbETd9cVXtVwd7+L9jxklX1BmbDNyRXZROQacNt30OX+TFzex5QEXgrUjdwDzUcDmSmGbzU/lpmBjKLQozQN528cIfM8JrvhedBJRe8ovsfrip70e9SXw6/+GSq87zLV63ZUok7rMIvyFwC6qD1RoK2Rx2oQhTQOcAs8W5DPC/GSQHNDAuVY664Ir28ajkoUor6iZod+bjqvrbIiyU7D7oTykAvZlsU4S5iNxcVlH7V23NGzYxSPfn8vJHxnV0dv8cov8FoSxbvEr+sdCTr74dYaog9zJ0bvmKXeE+E83mWMcpMgUYX7aydh6R3qoinwfmDLKJMWA66HSEOU6iCQsrav9ymG7jsqiirsxr5jdAs532e3+T9z/JNUMR5mRHYwhuXlj50F/s3/7UocFWurhi9U2e9C+A/GY2zgEvCkHuoZtJCtNFOQs6ov08lvcc3usG7ihjjDHGGGOMMcaYq+O0W1BPXwItBI6T7TL6U0WeQtlH9un/HhNU9COq/jOpVGokD08XAbfRlzy7CLwhAzonkC2WXYrw8cWV1QsGW1Fy4/Ozce5jDF7cmM51WOqJtRDlVnqSydeKyDSyw1QWkt1/J4FDQH5XKAFmI/KLTuQ/q+jKvvi1E3iT7A25/M4PCZQFCh8t7oqXM4jWzywK8ZoGEtIzNC90KRxCeQ7030A2qfTdtM3FMt2r1MUkU/1uN3vBqpqZ3vvP+ezN7NzxI6+gfD2Idz45sGPuglWrSpyXjwC/DnJb37Cvcp7sEKc/Vdiad1zkhp3VT8dFfuX2itVDFpyOyPU51kdMYMaAQuQLwKlBZp0s8HGn8mhpXd2lCfZLVzwJZF5vxyThDAOOR4VWPBsOpVJpgM7E5MXe8xVBHqBfIbIcA9mkyFP076BUpHA38MuJs/6hwcK4Ec7VoY+5XAzwdm7/AL3FxXMR/dVAY7++5N6PTAbQkFOgu8jux3whcESFnSrsBH6myPF3G+/JjoJFIvJl0AeBCXm/6kJ4AziYHy9KAcoCp/qluIvqGVn+eNSux8YYY4wxZmwkk8kE2ltkA4Cg7d0usa1/IXKPBt8Zu3AAZHvPlOwoH9w6N5UqHDj3ocbGriid2YLK94CzAKpMAj4MWk3uu6cIr4J8f3yYaB6qoHMQpxC2F3Wf2scg1TJ7nn/yjAvdDpS9eZOnIcFt+fN5jd0k2ULYnj1wSJxvGmrklgNbVx1TlZ2g2QJcwSFMK6DkckWuoSKvFqUTey8z32h5E/yLh5v6inT7NPh4LHwdpH+xr9dDiYJMC4Psz90bNlwUtB3hzd6JyvhQZEr+fMVu/GRBZtPXIO+Mqt81qzActJNua+vaNEG0D83vVOpmiHN3jPY2qjBBJZgxgvVeKb3ccZt78PYUfd+n43gt4jrW7pSXl8ed6ExEZ/dN1f0EuiG/ELlHY2NjmOjyu3HybN/sFIjIzUcz8cvtxxOo/mzXlnWDFlxGBenDubxJjzheS2ZXVRUNNr+5cciZqUcj1RfpyzslFObjZMlQyxzpdjc5YQl9ebQuRQ5wLt17DCxdWlssodaR7WY+Nz/vonAW1QOSzXn25Tuzeas6r/orZRU1d47eVr4rPTmSXD5KzoMcIj8/J7wO+mxxJj4wbzI05QgiW4B2+uV6tROR9mwOSXY4kVYNE8M+EHOleb5MrLgDUU+2gLTnmn4BaFPladB/Q3QL5P1dyBa9LgD9WLKq+q4Rb+fIjF4eqqHBxQnvVZXfFmUJfYXIaaBdkKcENgP53XknKDyI6K8kl9cMum0XY91lIvp5lEVc2ij2Itki9J73cQL0PjB1rYx0nxWrci9e/y/gF8kr8NXs57dD5D7H5Zks8IiI1g/2GRBgftXPzfTOPwryWfILkSGU7N+JA/mx5PKpM/H68xD9amlF3YRLVtrQ4EIJVniRXx7iIZaBefFpubx5YpB5+xnzew7vcdYZ2RhjjDHGGGOMMaMq3S2tiTg/FViM6Kuq8oPAyUthqOeCuOtUHzkVVyLq7wL5PLnh/IAZCkveTCemcGkibAhyTITH8f6nxIJTohrHs1hVP4dQmZspASz3uBqgbeAKfOTuEvE/h0pecaO8IuiP1ckLonpSYYJ47lbHwygfuordcyVCRXchfEt9sC/QMNTATVNYI0o9PR2dYLoq04Hs0LTCBhH5gYocV1XJdhHg0dwN3p4uqB/y8NFksn7nJcPUNTR4WfnwC/j0T0E+h+izAk9IpC8TyAXCIB25MEBjU53oA6o8iuiC7KqZL8gq4F+vdGOX3Hvv5DDDJxB+NVtUCyhHEb4rPv69Pc9vPD1wmZgWLvTiPq6QfwPtRUX/zknwMxXtEB8mkGAeyM+j+rHcTFNAaoqE7cD3rzTWHtf3WB+xEGhB9LuKaxdPtwozRf39iHs418UDYLLCyvipzDJg+zDr6yPsQ/kWXnaJRl1eZIYTWalwu8BPpSjzHA0NfsGqj5YQdd0nojX0FLQLJ0Eed7i1oeeoC7xXZaqoVpMdhvd2II7q3ar6yLyVtU2vbNuQv29uiHO155ij/zH3Oir/5sU34YOjscDHFbdA0U8AKbJjVRYJjOvM+GwhR7zjQOSL/ySGPulVfknQh3L76YjAN7zjCQDFnS84z2HehaVLa4szMV1FRB3SW7ydBprE6TcV94pC6ESmq0a1INnOJNkEe6kodWUVNc+1NW+87LC7WVd9PTbGGGOMMWMkmjy5wEUygWzxEACqFCdcZl5yZc0lBam986CTexurZgtHSiakExOAS0bhOdjS+E5y+ZrHNfCLJPsdAKAQpKdw5YKqbI4k/GFLy4ZBC4AHD0JPIrRnu+AOPocnPO7EvarZ0UIAilQHdMbzOh7H1LzFYurllqG3fyvqmQHS953aU5LGTx18/l4XQY8OVeR8DZwKkEtGGerRFRSci/kwf9jyLhwnXmpMnYPGQZfxXs4gegxkcW5SDOnfSTLm3TgvfnLfFAkFxp1IxxcnV9YMsV6dJCKJvhponYjqSLoGX+k2xhkwCtVoKy8vj58vKZnoOoIpnlhRLOb7Xt4zR/N7QTpoaGigoaHhWobUq7OkpEC7mAh575nydngs8fpQy+zeveHioora17xwhFwxm4fiIO0mA0eGfjU5JehhBilsB2htTHWUVW17G80+FA+gQlDofRwYpLjc3ChaW9emk1Vr9nnVHb05DXS+qNwHPMtgrVQjuUOdLO+dIPq6qtve1trYWwSbGRcuUA0+Jv27nL4u8AOce0ZVT6v6hEBZrrDxgdw8E1RYLchLZAt2h/zbdT0IHFaVH4iwAS8XVLQE0WWIW+6UlzTuftjSNPK/A8657Ur0Hz18COQ3JDvKAECb4P/GO9mtGSWh/tTsienTIxqKbYR5vgNwsWxV9RaN9GlBlojokyCbvASHg1A71KdDYkEC5GaFR0A/SzZvHUe5UyVYQraAc5RdfR6qbMNzc1SCNQKL8grf2xV9zHl92gdyJogCJ0F0cwSfFJXPA+OBYtAHCWhNpVJ78zvEL11aW5xxWqnK/QOaGOxR1W87aMPJBR8xwzlWKnyEbF70OhjRPuvp9ptdIrvfHkNlp2jUpbHYBCJ9ANFHyZ2nuQfMKgs7CpcBTf1fs8E53XaPovVC/ucs9qryDXG8pOI6Hb4EpRLkMwrJ7IvLNIHVcaJGYGP+Wpeua54Ziqa0f8fwiyBNqP4YeE0hFCdzQFejPMwIu0+P9T2H9zorRjbGGGOMMcYYY8yoerVl07mlFXXfzxDt8QGnE5J4Zc/zT56hfxJYSivq9sYlzJBNWt0GiKKTCiM/jREUaCqcAP0X1eCvby5KH25s3BQC3FFe3VIY55givw1U5Ga/RWHx7KqqovxOOaUVdSVCmEQlv9POEUS/HRJ9zU8seLt93bru8vLyeHds0rbQ85aITAbJ7z57rewQlT/qzujWV1vWn4XszayO2JS9IlzUbIeQ/Cf5L4A8HuD/xJ+d/Epbrsh46dLaF6Li6C31LlJhTW7eCYLO06nnppI3jGqPmxIdbx29UPjVWDzzhKi87jrcG5d2QqLDKwAAIABJREFUx2lwC1ZtPeAiiQG/l4ulSFWnDdzPl1NeXj6uKyp6SIR/rz03G7KF1T/xnq8fGDCEa88yHV4+RP5QsqoHROQffFD03datj/d2AZmbSrUWdcYv4mQKqvflJs9D5cG7705teOmlxjO8C9frWL8iwkvO65/Gu8LNd945/fzatWv97Kqqwok6bqdXPY/w6/QdN3eouOWMrBi5Vb3/auBiP9i3ff1pQJPJ+kQ48Z3tCXUTQq8n2hqzN48C31EKspq+BG9a4dnAR3+WvHVi3hDPDW5pRfMraQmdwG+R7XZcBLKs0GslecM73wjn6qDHHPq2Ij+QIPqr7oQ/fqhxcxfg7iiv3l4Qc20qek7gQw6+Kxp8fdmt4y+2N0Nu2Ob9dy5fnY67oFpzt6FF6VBH+4GtG1+42njTxf4O8ZLq7XST9SJO/zSWN/RueXl5/ELh9P0SRaHAV8geH3FF70J4gP4drAc1GtdjY4wxxhgzdmJ+fFyJCjWvPhKRVar83WXKuab3+0k1kSEaqqOppk+79tg0/R6iCwZ5eLDFod9sa3p6mMLGQYh0iNeBXfr6SUiiIyPh2bxtSbgBxahOtFD7jerCXTj+SD39H+DNf2lkguaPxiIkRKNLhpgf4KIilzxse82IpiPxQxa8+Y5MWuJ05NXGpgU6huvwK45ucBdVe3aoEJBXbAuIRnGBvmNKdDLKZ9STGnK9EAPN7yZYKNJXEDWkK9/Ga6K0om5CXPwKRD9yUVnounyBOCkI8IH6vhdXZZpA0TUOZ0jSXZCAqCjvfO9C5HR7+7ruYRd00QXUnSJXjOxEExJ3lzveu1X0km7LfRq8+JpuFXqLkR2ID0vGaO+YKyHQDn47SLYYWWUKwpLSirpZ7c3r+j1YnUzWJ7w7vVDQu/rORWnHR72Fi6V1dQWcDu+RbBFnj3dA/zWt8b9YNmv80VxOSUor6l6MS/oUuAnAsuzrM1PRqsXLa3+0d+eG/C6915kcQ3gsrsHf7N5ecQQaPPX1wfxXT+6Ix4IfBSTO7d6y7pJc53D2Na0/BZxaUFkzztE3wpXCWSHYe2Dr+ivNI404zwf4+Hm3Jxyvv6/eT/Mab3fnSo7sH9DgIpVKxY52Fr7l8MWIfjG7K2QKGg3WtfaqjFYeSn1sqaAP01M/KZzE64+cT3ytdedPj5PL8aZSqX0nLsaP+0CL+x6okqkKK05cLFgAfR3e/fjgZnx4N/mFr8I+Qf5Cvf/JjHHR2cbGxrC0rq6g8Gz3jsi7MyC/RbbI+Zq5wn2WC1t+5uHPfSb95MGWxncAra+vDw4efuelNMF5lN/J285Z4qJFDChGTi7fMQPRKtX80Sd4WdC/j8ULHuvNpTc0uMXrtrzkCS4g/vfo66C8SETXJJP1z+Y3VQnJzFVxH0I1v/b1Be/5n5HEXmhvrrgADVpe/khRd2HXzyIvGTR3XA7jRrjn8F5nxcjGGGOMMcYYY4wZbbq7ed1bZDujKIN3otD25nXnklVrdqPapuhtAIKM94GbNpIXccou7/Sb+5ueOrQ/b/qrLZvOLlyxerMLZJFqbwItJvgpxV3jJ5PXWaUw6J7uNXaHqvZ0f0qDbMlI+M32bU/3dtXJdVg6Xla+5gmJRber8NuMYEivq/AW8JPz7sIzh1v6kqTZOBpeWbBi25POaSX5STGRPSL6rb1Nm/aTt893795wcWlt7ZbwvC9FpZJcglBFSoJ0OJ1BipFz3RwOQsPLQ9+AbPAHtnKsrKqmBeUtch0cRCgeuJ+HU15eHu9KTLvfo/8B1fnZmw3aibj1OP7mwPYNhwZbrpPJ0wTKtC/heRpYl+6O/bB91+P9hiM81NjYVVpR93wsCv/FObld0dlAEY65XUWxOeQl8a/QdTnWr8AbgnwvjBVt2Nf8+PmXXspOPNzU1FlVX39gz+unvie4UoSP5Oa/WfALU6lULL+DxyBCQXcF8JO92ZsfQG4Y3eyx2q8DlSJz6bkRlLUrCP3Xk3OnHOg/xHOD393ccOTO5VvXxgJKgc/k1nBbJNxNXjHyjXCuZmIzpiDhArT3mAsF2SaR+6fW7RvzO0j5V1s2nZ1dVfV8iZQcdZFM11j0yr6tFYf3NY94qOmrp24ucE/vYSnyiuL/JZFXiAzZfZZKpV45lin8LhLN6z0+hDl47h7B8TEq1+P/n703D4/jOs98f9+p7sbOTVwkipQoCRIBkJJjwSQA0bIxIgmKlmWPF2bs2FlmPDO5M0nGmbnjO1syppM4k8mTm4k9ublOrrPYY8eJYY8d2xItirJhSyRFSZAligRJCSIpkRJ3ElywdVed9/7RDXQD6MbCRQSp+j1P82GfPnXqVNWpRtd33vN+MTExMTExMTExV4/AlAi9lY0SR85jtNh4AmQWhJSV1CB0d28aXDqnbZc5exZUKEZOS9pXHlb8jCm6WRoKzWlcEWXo+0Msma9jJDVSjGzeSNhI/cRsRIGz71hGd1QQOIJk0coF3cFUUuB82fFgCVfynLpEUkaoggqSbPznFjMp8sLG0YtKSczy51iUAUtyr1INjymQLMh9UHpcTP0YLzv172pbLgv/BViroVuAWaXEz+OdtreCIvd72tDEz2YWpEEDQ1dC3pIw0hF7DJJcEIw7niIzObxKna+Y6cvu7S09y5q3/szL9mFaOpRpKUWmEUZmedKsUzeZdz9HftHHGYkX3YU5w3G/4Fx4g0G98ouqQ4Ntcu6vurdtOty9I99c945N55a1rHtcRIslu5WsE28C2a1Kcidw1cTIht8DwXd27th0GDZlC9vbo5fhJNnX1WZKcT7IxpeBF2GjlYoV5wS2+9xpPQ8MiT5nYTYZh/spcTniUItaWirM63Zs+O9SCLYtNP31K6OMMTo6OsKGhg1dVtPztxh3AM2AgRZ5F9VRIEaWD28E7hx+D8dN9t0gkfxO1/bNZ4b6271p0yBsPFDX8tQ3zXMHxscv2wkqwhTPWc4oRFvSGX13f2fH8KKvXGz3jbqmtkedaUXWDRuA2bLsYpVCFEQLTSwnn33jDMajzuubLz31SH5x1saNfhccv3PF6u8kAldL1jABoFrSHTa7/0bg9Xz3tAipYei9wV6Z/a/ByvS2gx0dA0P3Xmfn9/saGjbsdDNPf8PjahlhMjGWaTLncE3jJq4SExMTExMTExMTExMTExMTM2UEeCaYRIwydlbo2NB7gzLzk3C9gbRMr7qzs/cV+3DvM0+c8bDXClxnPVQFCTdiIlHYHEmF7gxHDbZ133xDUQHsns6WY95pKzaxU+glcgj888VdQzf6ZCJ8DWz3iGKvg6myTCdFzvnOzZt7DXVjBYF4UR2azRmnDxrPCWl4r9IZ4Fi+yFLJikQpJ6yRG/vI9SVmN3pFvwa6NzdpEWL2pFz0hQWp9Ahh9YjOJf1csFsLit4At6P7Z5tOFKvfvWPTOTO9KDSckk/SvJxg81K40mN98h0R3VGkjn1bRwZGIRsoVrJql9BTBcUpsHkn+4OJ0ggfx3hh1477i57bQhoaGlJINwI3DpUZ6h50qW0jhchDbPT9iQv7wIbdmQWzTNyypLW1PF929e/V0IdzEbcMvTc4ivjp/KrBot9Dh7dv79+zbfPu3Tse6+jauuX1SdxPl43GxsakMy3EVJhOcC+BNo91Oc9OqqQG/E6c/SRfnTIzu/FIJjl/gt1dlu/jmJiYmJiYmJiYq0cQBMIuPaW9QVieiEoLbTdudBb4uxjlvIdImLnb+5ODd091nx5DCsZVMcqXGSqQgMpkfsTxyrDLcfyZSDYwQbXLsq/pTuhMYgJR88SkBf1Z8dv0pa75wSUK/C8b/CLonly6+usOScYI+3RPyLjrVmOuezb6yPu9ZtpWUHgXZu9pbW0dsTDFkbgDs5UFRfsxv73Q6TRIM185swPIxV2go3LwVNF4w+7tj53xltgK9nx+Gy1QRO0lH9rFEwrbX5FO7bqKfZiIScf5RjFhrDgrsOU0MOSqnMSrgsurT7wscagqVz3bsEXkFyL1SP5nN5eHRWOJXV3taYJoN6IzX+rmm3OFWdzwZvOwEeP4oMw/OUJ4O8xGH55IvmzGT4GSDv+XgSmfM4w3zfT8/s4tRbNPpAIOIQrH+UzTiOwGWeRvhBH35H5hW3bteKJYtkDdXBW9bsaPgHzM12yu94PD57R2/foys2A+Ynhuw8PLYRj9OCtEHklXV3vaJxIvYra12LGM6MD0mXO4ZomdkQtYtnLdOxToY5IsjPxfvPLsE/uvdp9iYmJiLid3tTxwc6DgN8xMhPa1rmcf2z3xVjExMTExMTExMTGXyMaNrqGjo5JMYo7kZhj51Fnmo1sEs4dm4WQYkZ8wOCnocXKHu0algyvA4zkls6Og+QCGSyjIlI2sFFQYmjE8C2gcl1c3RUWTABs9vu2ImfYLlk3Uz0vgdICNcaEYYiAoO5fw4YmCGaABHMdf6Gg9Bx1Ft/HeejAdBVueK0pgEzjY5NiwYUPwyokTNb1hMCeIrMqZBUOfSXaH5CstNx8lzKIonFSA2bB6b/ZOg9acSxLAMbAt4fHU8x3dm0rOaplPVsn5QjG1zDSr4b61P1dym8gWealg6sxqnPzlcye+AmN9KphxHPkDpT7ft/V7Fxqa2w7J1ENuctSgnCBVzQhB+eiGOeOxNyYjpo1mzy5zkc0g73aBRFXKZe5ouG9tyQl3odnDBr4QADUz0qkZwABMk3vVqRryAn7BMTnbN4Fr8FURGfTX1JRpgJkUulSJk+HR1Gulttm5c3Pvsqa2A954k1zaXQ9VQdrNJuv+XZTL9X0cExMTExMTExNz9QjlQm8MFkhk05g9KvjLKTXkOXLBpUuKm5Y+/vSdJtuAadmIX8qGA60A+8Qd97UdeHXb5mIClaIYCqKC549iZBIuSLowlX/mUAZjpJuyGMToAypzJU957EtmFBXhlOB0wtg7cbXrH4/LBJZ30QXeFHwLs8cn3YaIkopeg43TVrzd2NiY7Ff0bhmfhGEn7QuY/UziR6CDSOdxbni8OalV8K/Ij7W3FLlkBj84WOBEXKZJ9MWjhGHDz3HCMiYmEt/HXOdcCPoO1ajqWbANQDVQJag7kim/A9gHWQdaH6keo6Fg0/0Jz7MjGnOqRnbD0NAUHMNpXy4LVjGEHzgCiZfB1kA2Exz4Kbn6X2Z6QUc6O79/JYWll8YU4nylaGxsTJ6vqZnp+oI5nkRFIuHzYWrP4hFW5w42btzIxo0bL63fOS5XHCrhXaU3XyBQttCg8ng6ubzhvrXFG/aaZWapfLhPM5FGOD+bV7WMgpi1jpu3kvrD7u5Ng3Vz294w9CZcGSH9xZ0zTntzh0vU51wqfa5iIHWiIPSZACuSnc5miAKRsnGUKHqZEjHTjo6OsL5pzSHMdYOW5A6g2grP6WnKvKPKCkTuDk673jkl+1vZd+vJvsSB1yYy4Z+Wcw7XGLEYOUdj48OVvW5gs4n5AEkS/+tq9ykmJibmchMouQD8f5CEAn1ySWvrncVWBsXExMTExMTExMRcKhs2bAj2Hjx9ayZh77Mfbl0lkjdglCGlVBAkElYOGpO+ayIMBrwNOywUxzEI9ObDWjJJI8NNPkoJqxiOj3r6/AQTjQnzfSGcs4kiV5eCKR2ZLxm09n2ZtCXpK4jrpg36xgsim2MQXK+GE5MaAb7kQdSuX1+W6sk0eOzh3Yd6GkWyKpEVNiY1wglHNWa2eMqSS+NOyX7VjJvITlYMMVtedyTmpKuB0ql2A59CFDow3wZ8Wp5/WmoTmSpgRLq4Mu8uzZ34So/1qWAwUBn1nBunimT0Is5CVozssSQZXz7ONsjTb0xuAj7hq5MiKh8xRMxWSXxpgjEycqJISmWI8td3GtyrFriUpKr8fAO9ASrianL1scGyFEQVBddhALMz3d2bxk1fjYsuIHea3H3iTClLunEnpS/b93FMTExMTExMTMxVw85l0lalfvIKsARwYu/imZtob5+KWKnkr/673/3u2WEUrgf7QMFi1EJmCt6XlHazYcOXSy88HNP7aoPxsv7gXFRNQR1BBmxkJiLzaXB5MbLZKZPbunf7D0su6CvBtBXOvpUojNJKWP/w85gROll31/bNj0y1qcveucvIeWpmBqalYEPZgS4I+54TX0w7Dgxq1vna8hOZjo6O4fFcf19bNV79XCUxcpTozShMFs4PpyRm1K5fX5ZzNS2KEzM9zB96kHOQUWJCJ/CY65zD27f3N6xct0vmn8d4D4DB7U7RSnJi5JnMuNmbfyf5Mf8mZs/uWjznJDsKGnNWhgridKLXeesZb/8Zl+pLRjqb97735WYj4oxvNb3CpmWsaIipxPkKqW1aPyNpfiWmh3pFnRvwZeasLMAH8vkAlMRcg4orFTq/XHEoU5Q0yMcwTbMRPy9P6zj7TsAI999ys1GxZWcpvCoLhKn9ycDGPd+Bo9eLniv1F+9izpkXaYUqOT+xYt68zO5DPf0TddnwFcJmDBeIvsQEMV2P+gJTT8E0RpnJhv9mJpROOu/KC67ogMx69pQWW9PZ+ReZuua1vQZpoIhoOsc0mXO4lonFyDl6U4OfHhIiG2yN3ULfOlpbWxPnz9cM3+jTeoXQNKB2/fqymccTwcQ1J8ex1EkVT/sbcz2y5+nHnq9rXvuswQqDRRUDqX8F/I+r3a+YmJiYmJiYmJjri9qm9TO6Dp95v5z9c5PdAdwIpIoH0y46wiYzjTshamYyLz/eHowgKTQsxBSE+HEEsEAkCw0bvKJZVT1YwpXcgUskZYQqqCBpgvSnZlLkhU0cCb6r5YGbg57oFyT7KLBEYm7WqaoEF3Uq7Aayk8Gj2610xnuFex/wtVKtR7ikM5WTPwvVgrqp9UGBaXwHrfF4i8b6pBFEnZ2d4+dI9Uqb0Z+P5foEiXECsIAZoY12DStBYEqE3spGTTjMY7TYeAJkFoSU5Z2lp8G9mk1Ja27oWgrCcII+XC2KXIe0oYnjPxakIe9eJm9JmNBB/bJ8H8fExMTExMTExFw9di6dOVB36EzPsEDDcEIL7jx4+tZX4JKzCW/YsCHYfehsM+iXGH42sPPAU2R/p344W6ZbTPbRhtfP7O6CpybVuJhvZrVkny2L/i5NeD9Xzi0peC7rM/kRAjeZ9Zg4CmSd7KQbTf5OCtOEx0walafOkwlP5guYL3xdY+PDFdeTHsBVBHMstEV5vRuvIf2g69ZZzw0J6kfZNJrJVwqreWt7mqcLBupkZ8w0JMgyQ/OSp8NbgFeKbdPY+HBlH4M3GyoU/p+3TOJksfoxby+chS97F2yT9B4AwRK8mhsbH/527n6vxay5IIb3imDr6EUno2N9k4m7VLpkJjPC6dtSXldH6J8jJHtvTVumEucbov5dbctl4b8AazV0CzCLEmrjSYSeL5XLE4eSkpjlDRqyC6WW5F6lWh5TIFmQ+0CAefnAzPLxbhG6vvS4Y8JDaGLwCsbNpnzOzBCEJbvU3t6uhqY2P0Hc1byRsEJ9qggTg9G448+bZUwaLDCYSMoYvlapRBCEkU+NNGqZTNxTackGbBwx8nSYc7jWuaypIK9VljetXmDS7w+9N9mfXM3+vN04OpDc1pcc6B161bW03Xe1+zRdaWx8uDJ5JhwoPF+X+qpRdV/dytU3XO1ji3nrcOKL+Xf+c8ta1o27WjwmJiYmJiYmJiZmKjQ0bEgFFrZ68X8Key9wC+OtNL/KRBYJG6kSlUq7BQ9hXL+OnktaW2cFBP8Y6dPASoP54wqRLx4raDckO+kNgIzbzOyDy5pW15feOBLoEmO0lrbRbliT5Fob68MEMlnh+DVlbAK1riSbqM5Q80Ew5p66GAzC8kQ0PCamw70qb87QiAXik+nDtURWcF04s+IJGV/fHhMTExMTExMTcx3Q3h5hOgIMuwA7sTyZcGsZR1NQ27R+Rn3zujUNzet+fnnT6gWl6nW9fnqppI8Dy/Kl6hT+D4X9jeDZXGESfJPMPrF01drJZpaZAWquu291U7EP72p8eC5m70G6p6D4FM5eL6zn4DiyVwv614CxfumqVSVFow0NG1LLV619V8N9az95Z/Oaks+vb0dSp6rPGjpM/lm/HLl3DgSDzeNt17DifTfWNa35SP19ax5qbHz4KgkKC2INRsoiqyhV03lXKZhZUP8CxqlSzt63N66ZgSy7kLmAjZehL5OmoyPEGHG/g92L8eHa9euLLUa1/kT/vaAPkBeUDXjTkQp/7NQl9yfmmmduRXQK+Z+RH1PlYEt7E4P1Da2t1ZF8A1Jt7rO0sJflyl8a3U6xWN9EcRcfheZG/pmS6ao6qsuuqIPFZWAKcT6AuuYHlyjwv2zwi6B7pGy2tWud0JnEBOYeE5MW9MPGoXFa4vqPf8okmUqpu69tLup8FPlDJBvj9HFl7rOrPedwPRA7IwOhBf/F8o4mx8vDU/9wlbv0duOmwjem6GquUprWnKE/Odpa6HLgA42bjjXm+qKvIvOtioHEn4HVgNV4+f8A/Ier3a+YmJiYmJiYmJjrg8yMM3cksA+D3V0gND0EPIZ4AeyUN/WZ5QJ9noVm+iiw9mr0N8BlJBscimUZJFwiGHfVemBKRNh1u7K9rL/snZj/ReDmXFEIvCzYZLDXjLNeNjAkDDVpmcEvCRouZn+Csya+b6ZuYf8UuBVRJvQezDYsamn5w2IZfeSCtHn1DcchjV1gXxXsmfS+vfUmvbovpt/TcawbBI2NjYnOzs5MyUpySTQiDhCmIn/ZHFtCudAbgwXh4DRmjwr+ckoNeY5ccOkTQ2+nw73qAyITaRseciQscNNSgC6XzDDCGYgyTSIFsEcJw4Zj/sIyJuK0uzExMTExMTExbwNc6A/Iuecw7gSQsQjxyYamNUcrwjOPjn7OWL6ibbG38BeF/RMZZR73g/r7Hvife7b96LXCenUrV9/gnT2EeB9DAkxpH2ZfHygPn64JqyrCMPMN0G3A3Nz81YNBRFdjY+OXxn2+AXLPYyvMu1+qbVp/qHvHpmEj2tra9WWJZP8Dwn6ZEYJRO+blXi1sJkyHh4Jk6iXgg7lKNQYfCKKqg7VN6/+me8emc4X17373Q7PD9LmHo5BPYSxMyLY3tKz7067tjz0zmfN9vdPV1Z6ub173CmgX6F4AjOXe9KtLV649t++ZxzspEBZt2LAh6Hrt3HK5zD932BqJC/3Jwdtvb1zz1f2dW8ZN5345cSk3QETv0HtJ88y4q3b9+rLuTZvGODk6r8EQ+obcG4XdjPP3NDY2/nj02G1tbU0cHaRZsg9OJnvSVPsyFcxxAM/PIHu/I27E+HDiTNQF/ICCDi5rWXeHV/RxYGW+Ab2G1Dnh/RnztqCjoyOsv6+tC8/ToFtzxXfifIsbSPQJ3kleX/iak9/etfV7F0a3E5jLeGk4BjGZuMtgwgWJTJjKq2gsY45xRYAGgSbUyyVx5u1SJYnXOo2Njcl+Re+W8Ulgdq74AmY/k/gR6CDSeZwb/k5yUqvgXzGJONTVxOMygeWzgwFvCr6F2eOTbkNESUWvwcYCg3zC4UwTAEZwvrJv3HHsIKGJM5NdkxQ5H4mJzkdoJExWWCdEeTflSBZipAv+VE0q7uk8ZbLx613tOYfrgbe9GPn2xjUzDf3G0HuH/b+lfjDV39f2Hrz/wdB7k/2Prh2Pf/at6GfMleXudz80OxOm9xrKriQ0Xtizfct7rnK3YmKuCAc7Ogbqm9f+GXkB8v/V2Pjw566nlEgxMTExMTExMTFXj4TcIpl+zhhOQ7XL4P+JvD0WWXAqdb56YF9Xe0gumpOd0OBdk5mEuRLILENBkBujChg3e0jGW5UzZl+XXgUbN7rgsaduk+wdBaVPi+gPvfF8eW+iJ5k8le7s7By2Sm1oWtMj7H0XeT4GHNpiCv4olM450zyMX8t9NleyB6t91dPAY2O2zApo888xolfSi3t3PD7pgPHwlhfBdBzrgsqzfv4s4ESJKiZplsGwY5lBaEHqkiYxR+zgXCZtVeofFsGKBHBi7+KZm2hvn4rbyEgnnGlwrya8Bn3hmDNqEjAts01Fid6MwmShiDglMWOiSWsnZnqYP3TKHGSUsFiMHBMTExMTExPzNqDHVx+YGfQ/idl6sq6HKaBRZr/bm5zzQEPL2qe856wzmyd8nUfvEDSCFiLwUGVRcAj4wlCbra2tieNpe7c8v8LQb2fRg7Mfps2+d7CjYwAYrFu5+hFzbhnwqeyWWiT4SH9qThfwxCS6P0PwkaRlFtW3rH3GpH2RnA8I75bsA0BtwXPBCaHn3bmaNwsbeMft8868dPjsDhMvAXdnu6pbgX+XtPDehqY1P/GONwMfVAvdFYbpe3A0ArcBCYx5UnSytmn93tHC5bctSXYr5EcmsmJkVAOsc44Fdc1tHUCng9DjF710qGe5Od0L1gDMQYRC6bKEvQo8+lZ1uaI30zdYnjqTfyS1asHPJ85kbmxoWvOCOe0aTKQ6u5/cdAIgygQ9lojeHBpfhhaAfaIvdYM1rFj7OGSORqmkCyJbfLTf32+4D2N6x+j9bmSsO/JU+zIVkhc4EFXxUy/WATNzov7lhn6rrrntXid7QfiMTDdLfq2w91pe6BUie9EF/Hiq+425frFU+qAfSD5j8CGyfz9udLLGjNTrzFoKwjyvhM5tp0iATJFP41x/XgSoasONG/sJBqNqc4XxIQ1IGiN0HkXSsMrW1tZER0dH0XRQHl9h3mZMd5PjK815amYGpqVgN+aKLgj7nhNfTDsODGrW+dryE5mOjo5hN/j6+9qq8epnmouRFUZpJazf8l/goZN1d23f/MhUmxrxzpSWbMDy4tuqpEvMAo6XbMGrGrNpGWO8ZIxBRC/5jABVgZjDeOcDV2P4uRpe6EMac8Mx2UHvwoSF6YKQb0rSuHHPhoYNKW9nqw2Nr5W9ynMO1wNvezFyKmkfGlFgVvqHbMRCzPJpWJxuLFk3ZtI4I321VxNpMFNtAfNwmwx5AAAgAElEQVSHJsokbru6PSpOOtWbTqn6sKGZpWtZkVRBOl+yttmJMO0m+jEWc51h3j0i54fdkPsSgx8A/u4qdikmJiYmJiYmJub6wHD+JpPVFpTt8t6373vmiaJpG01RUrjKq6XrjYj6A1yhw858J24fbxuHFpjZHddjNOn27z9VoyQ3ATnnXJ002Y/6K/zjuUniMVjgUpIqLyK8FoI9hXdfmFc5uBvgaDr5PfM0As2AYdxt5j6ydNXal/ZtfXzERLGZziErnHBb6MzXAZun3JOpMy3HusTcIBneSgkx8tJVq6oJdSNmw87Ign5HVDJuMFV2Lp05UHfoTM+w44XhhBbcefD0ra/A/ottdzrcqxnvLiScThZk+5wfQS3ZgNK0+krogoE62RkzDTmPmKF5ydPhLcArxbZpbHy4so/Bmw0VTvSdt0zi5FvR55iYmJiYmJiYmKvLm53f75vdtPongkeEfSJXXAEsd8Ziea0zs7RQOWazJGaSF5Zg4iijfmseHUzUm/g42F3DhWbPofCrr27/0dBzi6qingO9NuebGHUGq8jqGBolPt7QuOaVrs4tr0/Uf4N5YG2IFTJ6AiQPc0zMLchmg2G7TDzW1dU+IkNMe3t71LCi9TmCxLeF3ULWSTkB3Ap8FOx+E70yn5QxMyfYriho4rSM/alz1fFivhwLgsETJwZTm3xgTUj354pnAqtA9QYnBd6wKsEcZDUF18oDx4hswmt/OZk1iwvH+ux1nE4Cc8k+7y027CMyWpF7OpXOXCD33G39h075mQtfMHEIWAwkEctAn1bARyHZ5yJMpiqwm0ALmKROZ6p9mQo7d27uXda0+scy+4Hl7/dK4F7QEplOkr82C2yEqNC6DP/tZQtnv9E11R3HXLd0dXT01jev3om5nYh3kRUHtjizJaBbADB6EC/5WcGBYm2ECs4npOMFAZYFoDsZJ+7izC8AV1vw8VmwY4V1Vsybl9l16EyhQNFA1W+eZxZQNObhzM2S+YWTOfbrGVcRzLHQFhXY/r6G9IOuW2c9R3t7BHB45CZm8pUqqluaXqg8dZ5MmL/+Yr7wdY2ND1dcipGfoT7gDNiMXLtzyWSWAC8Xq9/QsCGF9dwE3HSx+5zOOFmP0BGGnLWN+YHX7cDe4ltsdPLbFsrycXczO2eR5a/VKQbdXLtQEKM1sBuCU9FCoOj3C1W9cwwtmqi/V3nO4brATVzl+sbgl/PvdL5r0YzOq9ebtyfy+gRmH8LsQw4+WJnp+cnV7tN05fD27f17n3588Z6nt8wo9RJ8sXAbg78Zr37X9sfveCtT28RMDyqik08XitQN/crV7E9MTExMTExMTMx1woYNzssqgarhMlPf3vfdf6bUJpFz8yybivWqoAynJAonthYA76ltWt1QrH5D45pbzNkDgiVvTQ/fWspdqmI4UAqA9WN2qpQQmY0bnXx0EyMW9U7S/FZ6FePv+ioHn+3o6Ag7OjrCpOt/1kzfBoaeU6tkWh1EfIBRcSxLByeRHSwoWiDcquX3rb+j9E43urqVq+9qaFr7yWXNa1eNbnPSTNOxbsbdLuAD97S1VRX7OKD65wxbX1CWBp1MDp4q2e8p094eYToCDKdmdmJ5MuHWMs75rm1aP6O+ed2ahuZ1P7+8afWC0Z9Ph3vVmzslU+EcyzwHrQ0r1o5xtYJsKstlK9e9o37l6n9c27R+nGB3wTJ9I2WRVZSuO0k6OkKMEdcB7F6MD9euX18s7aP1J/rvBX2A/MT4gDcdqfDHigrsY2JiYmJiYmJirj8GT6VeRXwJs38oKDaJWZgtJesYfCdiHnkhchrpSaE/yJB4amij2vvXzwP3frA2hn5jGruRvmrnbthFgXKss7MzE5J42mR/CwwtRK0GHlTSPlbiN+wQbwA/I+tilwIWIFsqqDOYP0qI/KL3+v8qMmUvFWuoa8m8E97rG4KvAIVmTlUybgfuFtQhbqJQiCztM+x/uDD1rdEi57czHR0dYZjsfdYbXwSeLvgoYTAfaACWA7dZ3p03654tvm3SH2d6gqKLKa9kn010IraM+qgcuFmw2Jyqhwq7urrSidA9CXyD/JhJAjcDK4FW4L2Id1m2DFA/2QW8l7UvU2XwVOpVJ74E/O+C/oy5Nox0N93l5f8kSJQ93p4TIsbE5FAQBfuArcMlZreRvQ+yWcVk+x1sK+Vcakl/wqOCWJ/Nc9Ba37zuncXq39XYOtccrUjvyvfCTjhvIxbDt7e3R4Y7Rz7eCNiSIBGUaPfhufjo5zCmnUGlmcmw4eCrYUmFKh9vm0vBeVep7CKSoR1ewDhFifv/9sY1M5DdSMFiJRjr/D4dSJ2qPmvoMPnvv3Lk3jkQDDaPt13DivfdWNe05iP19615qLHx4THuz17uBFihILYe46G6lauLOh9rxqnlHtYD4/3WuWYRdszg1XyBlmI83LCitej9VbfyyVpnehAK7j/ppFP+u6G7e1NacIzsCwCDdwSO9zc2NiYZRWtrayIKMisxHpqov2/dnIMFXhrT1+uBt7UY+c4Vq28n++Mvh32z1BdmzJVjz44tT+/Zvvm7e7Zv/u7upx//XmdnZ+Zq9+laxsGI8ycsPp8xY8jeZ/lAkox1d7U8cPPV7FNMTExMTExMTMx1QHu7N6yfEWms7Ma7Htt2V7Hqd7U8cLO81pGd3LgquFTVCUYEuUkJ/aMkwa/c/e6HZhfWXbpqVY0PbL3gYww7B19fWCJK59wbhpgnWL6sZV2xlIhW99hTy4Q9jCg4V5MMN5mdQdFrhULnl556qsei6HErcBowsVjG++ua2kZMEFj/jFMe2wOczhWlgAcihb+xfEXb4tG7W9LaWl7ftG21c8Hvy/isxG/Xt6z9YGtr69Qzh03fsT5X4gPhOf8Qoy7EspZ1dyiKPobxroLiY4bbd7ljMS70BxDPDb2XsUjikw1Nax4uFhBevqJtccrCXwf93zL9jjf3mfr7Hrh1RJvT4F4NK/pPmthLfoI5JXG/EvxKVmiRZ0lra3lfYs5a7/x/w7nfTxH+1rKV68aIll3KDWD0Dr2XNA/TXROILSaFOQ6QFWXkGudG4MOJM1EbQ+nBcixrWXeHjI+TnSTMNaDXQJ1xrC4mJiYmJiYm5u1Dd/emwb6K8DnDf07GZ0E7x6neC/aM0O+b8//eVYSPde/YdG7owyAT3mVSGww/L74pqd0590gxwW73jk3nvNgE+nuGfnOLm5Baynr8mGe8YYwjiK8YfAnsaIlap8z4lkyfS0d6tKTjYXt7dGNltD+K/Bc8fEbox5QWjYZAt6H/Kcenw0z6G13PPjpm/ylvoUbO3w5K+WeAyTBv3jyZqWDlr/oNzhWrG2AZibzQzyzjQhUV/gFU9keRfH4+2WDQbPz+KW0hVrAPlPYWFD2n+7ZuPR9FwWYv/59zploHi9XLcUboh8Bv+Sj4HOdnP9PdPVa0eKWPsa9q8FXQF7JjijdHfipF3o1YhV2/ZOabiC9L9nmgqNA9xxuIP8fsjzA7lCtLS9a3sYRSb6p9CWQhsvyYNUtHoesv1vbQ/e68+x2JzyN2j9t3+DJO/zGVLPvuS089UnRR81T2P7yNKa1sjAUglBiozrhwvG1ipidl/tRRPJ3kBYIpCsTsZtrvk+7ZUtsHC2edNLM9GD1D20vcL/wvj164Xrt+fVmQDFZL/FOMWcP7QG9IiTGm3ZLOIBV8R6sBc/+krvnBEYvYG1pbqy3Zt07YR9H0E4eabABUuFjmRowh9+jLjvMaVEGsWNjNON1TSvCZStEs7INXoi+Xm+xvkeAVsF3DhcZy7/SrS1eufRejzumGDRuCZSvXvYMg81+c2e8h29ifHPzU7Y1rRmS2T7rEUaC7oGiGwfrAJT48Og5d29S6SAo+avDey3+E04NM0h3yI/42Wg3wPgWJj4+Of9atXH2DM/cw8AGGFzHQY7DH984sdDyXyb+BWaHb9M1CH+lPzXnPqC7YG73J5Q4+gSgaux9R+QrNOfRBSOFvF1FuMLe2af2M0W1e60x9suU6IhHYusL3TvbDq9WXmJiYmLcaw34o9Mmh9wnv2oC/vopdiomJiYmJiYmJufaReX8S41DOMQmgOfD6r3Utq//WOdvZH2qwHDcDx3KJh4G1wFULuOzbem9vfdPWncAu8kLROZj/xTCTuaGhue1HMvWZbLFC34ijBbhuU/Tp7IwLmnHmONnJ1hRQDloXwdmGVau/F+FeDdIZ7xOJec67FRIfAq0qdJqa/M4kFwSjbZTVW6l95X18xxw/B9wJJPGswvGxpatWvbxv69bzkA0YN7SseUHe/RTTP85tPxfxC1GgW+qb1v7EObcPKeml2xngbowVQrVApYybEWdP9Af7gKlmFp2uY90Mlgr77Ybmtf8IeFFmR4EbvLQWrJWRjkYvexU41lwmenz1gZlB/5OYrc+lLk4BjTL73d7knAcaWtY+5T1nndk84es8eoegEbQQgYcqi4JDwBeG2pwO9+rBjo7BhpZ1z0vRU4Y9CIAxC/GxZCa8pa6l7dnA84pQOQO8U6ZWsGVAmdBNclFf3crVn9/7zBPDTsMVvZm+wfLUmbwpnFULfj5xJnNjQ9OaF8xp12Ai1dn95KYpp91NXuBAVMVPvVhH3mVsuaHfqmtuu9fJXhA+I9PNkl8r7L0FqXdDZC+6gB9f2lmLiYmJiYmJiYm51jjY0THAhg07a49eOJwYTD8eBNwW4W51Xjdg4KUMZieccShyOpAMdWjXg+85wcaNI57vVF6+z/r7f1u57Dty9CZCt3/Xs4+dLr5nuKkyfejoQPkXTX4TZN3iXJA4EVrqWKlt8MoEge0hY/87cnrCzGq9cRNSpTPrk/xxzA6G2J7yXg7t2fn4uELbjo6OEDhQ27T+b1M+fNoHut1wt4JuzPbJ0jLrQdER59nvFBys8KeOllrE58/POeMrT/61CxI/BSCwC17hq8XqlqK9vd03NK55lIQ9BCAs9IngtWJ108ngudRg+ldlrgbAnI74c3NKZsPZuXTmwNLXzn7L5YSoFthAOhONJxjGqtMH6U3+gRxfzZbodMKl9pWq371j07mGhoatrmpRdxi470C0xKFbJTcLfAZsQE7HkXsN08Gy8qpDL3R8t6dUe1f6GA92dAw0NGx4XrNOHQm8+3s5N9d7zXKizDt7I6HoxcL67e3tERs27K89euEvk+lMhzlbLM9CjIWCcjPOIjsC0SsEesUy5YO49GZhM+QUJcTrsLFomqmp9iVMXtgf+Irfk7e/BDCzU/3pgZLXJne/77rnjbNH0mKLed0huM3BDCEvF1xwXke9868pci8PlmeOHOzYUjx71kXsP7fRk0Ey/LiPVO6c994Fh3cunTnAeEshYqYlnZ2dmbqmti7DPwv2/hEfiiOCZ5ffOOP4nhLbd7W3p+ua2l5wxpOChwEwZhn8k8jcnLrmti2BRcewoFo94b3CfRBRWyAZ7fb4x+9eUnWia5TkOeFsfyieBXJxPKsBPmBENXXN67aY/BvmqGKAJoOHgHFcUK8ePrBeF9oZbDi5wCKcPl3f3NaIaTdmL/Wn0s+UzHI3RaJM0GOJ6M2hc2xoAdgn+lI3WMOKtY9D5miUSrogssVH+/39hvswpjGL8TcyPd2RSbJbIT8ycW+2QDXAOudYUNfc1gF0Ogg9ftFLh3qWm9O9YA3AHEQolC5L2KvAo0NN1qj6zbP0dMr4aC4uCrDE43/z2ECytq5p3TPOogBzdwiacs7eM7lOWRT0nzmSSe4wqQuzBgDBzQa/ljoTLqlvXr3NCM550yyT3S/0IDBs+iBjt4zNe0cvZPOpbkg/jdn9uZIE0CjPf61vXtvoYa9zzMSzDNN9eLsbY0In4is153CwoyNd39J2ASk772I4RFuS8E/rm9qeBv/8nh1bnmHSaSenL29rMTJYU+E7j14sVfNapKFhQ6qiYiBRcmXnZNtpba2eDwO5B69pTUPDhlQicTa5c+fmKa0mvfxsdEtXPV+1b2FZ3/Xgtj2UWuBSx1IxrsQ1W9TSUjHj7KLocqZBamx8uPJY6qQOb98+7srNi+FS7tVLOVY5Xiz8MyazlcRi5JiYmJiYmJiYmEvF7GWwraAhgeYcTO833D3yOl1hQQhKSczJpae8yiu/N/rIPfBioMTjoALXWrsRY4PQ/ZYNLFZjdgMjhZzXHV1d7Zm6lrVdTjwrWAWAWGToVxS51Q7OKUjKRAVO8xALucwu0Qc7Ogbuanngp4ESPwD9WyAn+NRaiyq2k00fCkCi172cruS7GPeYuD1XPA9Yj/EuL38WcBg1GLPRiPSl/YJDqXRqyiLPbJ+m7VgvB5YJlgDrkfrMKBMsAKoK6p0w7Knz7vxUhdgT8mbn9/tmN63+ieARYZ/IFVcAy52xWF7rzCwtVI7ZLImZFKRvNHEUGJWKd1rcq4pc2R4X9X8bqAeG3JsXAA8ZavboHGYBMAfZrGGhvlkvcKwqqhgRV5g1iwvH+ux1nE4Cc8m6riw27CMyWpF7OpXOXACmPE537tzcu6xp9Y9l9gPLX4dK4F7QEplOAt6wKsECG3HOrMvw3162cPYbl32AxMTExMTExMTETH/a26Pu7G/Qk7W1659PzElXh0E2DXyQSfpERe9A/9GavmHX2h1PjGni5Y7vnwSemspuc/PRBxnfPXcMwsLdz24+1NraeuT184mtZQSVgSMRlVtYdj7sT6fn9b08tbk05VyeX2htbd3VA9X9mWRlFCZdMuUjBsP07KCvb/sz2wfIrywsSm4Ob1/udbGoq3PL68DrE1XMLWSc/PNDe3u0Dw6QfU2Kro6OC8ALudfktunqSkPXIeDwopYNO+bY2RqiIDWYkE+GPhrwqf5FFf19k9EkvCXHmL1urwGvtba2Jk6fTpX1VQTBPKoz23e0jxX55e+ZE42NjZ0wu/JCuVUl0xbgonQmUdW3b+29vQWi/VIu3pfUl9wC7p9RmCVnItrbo51wHDixpLX1+URUUePCwZS5QJFzmVTQ33/3vHn97ZPQPVzM/nOO4pM+HzHTm/KK9KuDA4kdwPtHffSKg60TjSNXkd7nB1LfNnwD2JAgeAHwIYMWL9dvUkLZGMrcvBDZzgM/TpQFm4rt4wznX6uxmg6T2gTzc8XzgPcbfgVGr7ySmM01uOFij/9Kk/A6EZk/YPkDLweWg1+C7Iy8NiX6K/YDhy/H/qz/0Ck/c+ELJg4Bi4EkYhno0wr4KCT7XITJVAV2E2gB15AWcUEweOLEYGqTD6wJaUjUOhNYBao3OKl87GwOspoCUw4PHCOyEX+bt29v769vXvcM6CegIZfoJKIOY4Ez/wEJAz8Ts9kw/Ry4LycdHR1hw4rWZwgS7YLfBGYaBGC3I34Jcw8KpU2UmTRPBU7nwBvO7JFEbz4D3xDzq/pOHh1IPWlZ8fLdueJqjGag1kEPnhQwB18Qo50EV2jOwUsct+xvuVoAjJuAj4Dea1h7Q2vrrtxvrGuaa+YL4Epgxv0qeDTYc8us/ewYW6+uec2Hwd5rqLHwScLL3lfXvHbYocWkb+zZseXpwm3rW9o+JekeAEORlYf/dbyBs3TV2oUutM/IlL0JpJ/u3bHl22NrbnR1zU/9Ntic7L45uWfH479b17LmbpN9WvCw6JnfB9Q3rzlvuD82sy/u3j5ypWlD09pPemNFtg3ziWTyd3r7B31Zyv1L5D8Gdq8GsjkUGlrW7vfwlYRFX9+17UdTWq05HsX6UCytxz33tc3PRPynoXNjsu17dmz+u/r72t5jnl/1aI3omZ8B6pvXAnwHs6/a2ZmPlhJqLm1afY+Z+1SEbiwsN1jU0Lz2f/rcigMnnu3a8fjXxjkMW9ayep2X+2fAO2DrXURQf6gfmtd2IT0i3N/v3bG586JO0lvM0lVrF1rErxk8AFrWx0ANQF3z2uMO2+JNP9i7aNY3JxJaX4lrVrS/K9tuc8a/wflGyZaamK8ZPdQ1rz1upn2Se8HJf7Nrx7u3lVpVOprlTasXhGb/h8PWCt3Tx0BNjaqpb15zHmyLZD+sCsu+NrGA+PLcq1fiWK1n5suaMWJR8eh0BTExMTExMTExMTFTJnMq8XpqbvQtQR1wX7bUarJBSkNj5+h6MTIFLgFvOQvL/LHjg/Z3kpYAH8p/ohqgZlSPQ+CgQa9gjMvDdYDK+zMvpiuS/wtxM7AkF6ibm3vlKw6fGPWDpbmMDg7vWHTD0a7Xzv7AB/auoUCwwV1gH1q6su1n+57ZfACyYsvlTat/GOJuAH6DrAAXsoH4xblXrpsjdvEG8HWFwV/97GdNp2DTlPs4Tcf6QeAM8E6gOvdCo7siejD7rqSvH3768i+6BRg8lXo1dUPmSzirRsOBd5OYhVn+HIzsWxpph+ALIckxooXpcK/u2/q9C/WN6x4h6W8w7NeFFuU+SiFuwuym4coFzjx4+4ukBd/o7Pz+iPOdDciv65TYgvGxgo/KgZsFi50bEdCeEkPXQUYF2YnAFJCw7MTb/BKb7fLyf5JKlj0+mcnmmJiYmJiYmJiY6xrlBMeDE9acBuSErGdzr8vZZk/uFXPp6PD29v7DMOZZtLtY7WlAbgyEMLk+5lyyx47Drd97y/syRZRzUx0jto4XqcZMlhc6Os7Vtax+wcm6BA254jTGy4NKvDTR9l0dHReWN63+YWjuBhsZ66sC3QFFV4Ccw/QPgQ/+tH5BzZu7irR7ePv2/rrm1idkia8a9s8L4nOVwG1ANt9Yll7MDiOfKBBETwt2L5pxtu71nm0YzwArc8WWc3quwbjJonRqnCamRFdXV3r5ikVPRoG+AfxrsrHGJFnjhZuHK2o4DBbmYsUBBcYD05WOjo5w6apVz6KqLzqRBJpzH42JndnwP2Rjq7DJ0J+lexKjDBWgMpPaO5Ac+CufFbDel2vAATcIbhgea4KskF6HZJQXCF+vK7qWzDux9M3z3wiiaLbgl8nOI1hOeDwcJ1Y+lophh2X6a5fka8XMLTs6OsK6lau3KbC/MNm/Y+g+zo67hRRmzMu2+ybGcUQtuZh5Ka7UnEMURbuTCfuRZLUFxZXALRIL+68THe/UU2heJ9Tev36eCm5iwbOlhJVm9s8M/s2wI9BQOSwy+DdDL8zGCvmkfzf8OfZvo0z5zWPqFOAyeiem3xxu1+zni9VrbOwsN2xjft/8zrL7Vq8w2U7gUzZiMsFqhD7r5U/VN7UVTmog49fybeg3w/TgfWVJ91OkPwS7d+ShcLuJz0U+6K5rWvOR8Y5jKozuQxQNLilWL+OjewrPDY6P1Te1/Wu8fiL0CzZ2AuVDSN/RjJ7HapvWF3UfMnNrsteGMedZ8Ov5a8cnS/X/rpa2uvrmtbu83CZgA3DXqCoNmH3GTM81tKz589sb10xje/2NrqGl7b+5iDcM/jPQnPvRAoDBfKFfMPG39YfOPl/X1NY4XmtX4poV0tramqhrXvsF57Qf028iu99G/hiYny3Tb8jsyYaWra80NLetn6BZq2te89nI3FHDNmbv+/w5yP3/Q2b6897kwL5lLasfHK+xy3WvXoljzQq+rTDBTcP0Hp8xMTExMTExMTHXAt3dmwbTCrY6878L+nus5GRdL9BhZp8Hy8/GiLS3YMyiv5S3UFCY8nRQYtwMKxJhLu3VEOlEkbY7OjrCvrLBnWbuDzD7E1CJBbh23sweAf67pPxiU7O0M11SJpkAy0gFk7tmGReq5GRvZX8Uydvw+TAYNJvgfKQtxAonkFX0XL/wQsdZ5/13hW0U+jFQarHoaeCbwOeh0J1AmcDbmImrQBYiy7dllo5CV1QI297eHg1a8Jyhr2PDzk8ViOUuGCks3bXjieMZZ1/zss8A3xxnzAF2VOjryP59ENmf7nuu+ZXJLlodzZUa65eCGc+B/++In1L8uoVk5xD/2Cn4kz3rVxUd61O5VqXo7t402FcRPmf4z8n4LGi8BKu9YM8I/b45/+9dRfhYzoVsBFfqXp03b57MVJg7qN9gzP6HPtzT+dhRi5JfkfgM8B1KCx0uCPuxSb+fTPCVnTs2HabInFlf1eCroC8YfAl4c9TuFHk3YoxO5ftw6Do4735H4vPk0hKX4A3gyzj9x1Sy7LvFzAKmuv/8UUzu+zgmJiYmJiYmJiYmJiYmJuaaxjsSx2GEW+zrwI7uHZvOT6aBXTueOJ5y9jXn7DNAO9kYZBHUj7FN8Dnn/R/U31Kze7xF1XcvnncoYf5LiD8YJz5yCvg789Efm6xA8690YP6yxKwvifb2KB1qh7DfI5s9bkRMyswUBMkRcaRLjfPVL5n5JuLLkn0eGE9Q/gbizzH7I8wO5crSkvVt3Di28mT7daXjUPu2bj0fRcFmL/+fBV9k/OwMZ4R+CPyWj4LPcX72M8NZIgro7Px+36ASHYb9HuIblnWfL8YJ0NdN9gV8wX6NdKTgog0k3qLYncCH5GPQaaHifW5vj25KDryaifwXQP8J+AlQqu3TZvYPMv9fMj7xF7t+urmky/feZ544nfBqF/Y54Ilx2jwA+jPQV4QNx/AFUUgiU2yDKzHnkOydc9hMXwa+PHpMmJlP9Fdc1DzFdOO6UFRfDEHaLy9wJ8HgmnCsHQ/vbWz+m1EYftG4FZz9YIJMMtl2zL5V17zmI3uf3vK/J6x8pZA+iPHBiSvSmrTMjxsbG5tzqxAvG1l3W791pFi1NJL9y7Ikdy1pbV2fW1U4fdiwIag/tPXPJT41uQ10j5l+3NCy5r1d27dMLs3KZb5mxwYSn82JxSe5e24HPVrf3PaxPU9v/vuxNTa6huatXxD8+mTaM1jk5TbVr1zz/j3PbHlksv24mHv18h/r0H70vOCeofeplFsGbJvsfmJiYmJiYmJiYmKK0b1j07lFLS0/qfaV+4Mg+Bs5bvLyiw3myCtjZifBDprTvnQQvJEYTM82c7nfrTqdcLw8uk1/fs4ZX3nyr12Q+CkAgV3wCsfN2lPen+5KV18UaZkAAB2pSURBVJT9R7yfC+DF8eSAK5rS9GBHx0BDQ8MLyZpb3wydfoC4E3GTHDNNhF46aWYHzAcvBcnzRxSWb43EtwEMnXPSGAeEqZBOBs+lBtO/KnM1AOZ0xJ+bU1QICLBz6cyBpa+d/ZbLBc4tsIF0Jho3ja1Vpw/Sm/wDOb6aLdHphEsVSxOrXTueOF7btP47ZbIXZNESzG4StkioxqAf7JhHrxKE+0Ilz5TJPyqfc4Q1d/RC1eCYdKlh8sL+wFf8nrz9JYCZnepPD5RMU9u9Y9P5e+5r+04G9uBzzrCBXYjGXne9um3z8UUtLY9UuZkvuTD6ihm3YNwiqEQMZFMt2jGDA4YdrAzL3shmutk83imbkCsx1i8FiZ6MUpsSRN0mNeBYgjQbOQOdNmdvENkrzsKXd61vOlGQHnYEU71WpTjY0THAhg07a49eOJwYTD8eBNwW4W51Xjdg4KUMZieccShyOpAMdWjXg+8p2a+hNi/3vdre3u4bGtc8SsIegmyKZ58IXhvn0NT17KNHGxsf/t5gsv/F0NwdTtwm+cVglcL6zXQC/GuBT+ztjzi4f8fmks5s2WPa8LxmnToSePf3cm6u95rlRJl39kZC0YuF9af6fZi7DrvueePskbTYYl53CG5zMEPIywUXnNdR7/xritzLg+WZIwc7tpSMW13p7+OYmJiYmJiYmJiYmJiYmJhrF4/mW87FOMcrTn4bkxEjZdHObZuPNzY+/OiF8sxLLoz+xszuEFpkkBDWL+mMBe6NwNQdZvyB3c88cWb3DsYV8mWFyhsP1N6/46/KMuFTki31pjscqgFLIzsqR3dg4UtS8owXzyH/RQBccHIwcmNiYxcTI7lU9nduOdvY+PAT6dTgKxnTn1tkc0yaKSMh6ZUL7uyxwvqXGudrb2+P2LBhf+3RC3+ZTGc6zNlieRZiLBSUm3EW2RGIXiHQK5YpH8SlNwubIacoIV4vJsycbL/eijhU945N5xoaGra6qkXdYeC+A9ESh26V3CzwGbABOR3n/2/v7qPsOstCgT/vPmcmk6TpB5RgMSiW2mamNV4Y28wUuQ40k5qL4NJl/LouF+AHLsC1FJZLYYEU9d51UUC9oheWCHg/gGWuS6VqySQtc6XNTCiRkjaTpITa0tS2aWnTfE0yc85+7x+ZJOdM5iOZnMkk5PdbK3/sd7/vu5/37LPPtOc8+9m5eCxSfnRRx9LHHxj8+xmfmDDxvfHgZeWSb+ZU+VxK5StzmZZHSkvT8erRT+cU38j12FGtpBeq9fyv9YmChPWifKa6ZHzO76Pz9N1dHou2gWoaf1MqU+XUuZ7aRGX/f7u2e81nOxbFUFnPr0wpvTIiXpxyKnIqj6Yo9kUuv5Vy+Y169ejje4Y2z3YDw8nfMdorta/nMt0Qkb83cro6p7woRToYOf69qMSuPN42UhTHci2VD0ROSyIiKjk98T3LaocfmWbuVv/mMDKyYayra/3Xy8te+K+VSv585HR1KvOVuUhFGcXOFYtHj1yoT4k4G2n2Lt+Zunr71+ccf3OqJb1/5/DAH0zVd2VP/7tSitdHjjc078kHI6V/ObmV84d3DW8ebOzR2dO/I049eiDKSmXl7vu+OO2Heucta95wPCH4pL/ZObzpZyb36+5+45IjbUenvWshpXikzPHtFHHzqcb85Zcuqr1+4gI/Ed9QnCozP0k+GJF25OMVoE9LYk4pHlm+aPyGxvnmYnIMKeVXT5Xc2tlz25qIYtMMUz0ckQ9Nruh8Uo5f3Ll10/86bc5U/EaK6MyTyt2nHBtzcfwRJynnjSPDm/+scX9X1/r28vL935zqtYnjVYb25YiuKar/Ror42Mjwpl+fYS1z1tXT/+Ec8e6Go/3lzuGBX51tXOfqtW+PlP98cnvKsTFSfCMiLisj/tPk9eSIfe1H0rVTlcWfj3N2QlfP2tU58vBp8Ub6bKT4Vs75moj0qoi8anKfIpc37th692lPk+nqXfvWnPNfTRHIwRRpe468eLpYyzJde+IxwY1aca3Ox1pP6OxZ8/sR6X0nVxrpTbuGB+6crj8AAJy9O4ru7m0dLyypLe04Wu8Yq9bKtmgbPXZlcXjPXadXDbgQrF+/vrLjmWcWV8fal5TjsWisWiuLejp6dEn98AV3Y+n5sH59peuZZxbH4bisiPa2ekeqLTp4bLRSOXi41Tf9tsREvPngomWVIlfrHak2HkVtyeL6ke0Dt47OtRLy7M7ve72vr6/69Gj7r076f/lP7hze9CsRkVb09nZ0VK+8LMZi0ZKIONIex5a8UD+yfft8vgYzStddt669+qKxy8pK7oiIqIy1ldXFh4+OPrXsyFRVRGZzoVyr69evr3ztW4eWVqq1yyqRq7WyrJ/Lue/r66s+91z7oiOLK5WXFJeNDw1tOBpn/oPdbNIr+voWVeuLlxW1Y+2pqOR6UR1vr4yO3viSl4zOVEEIAAAuBCtXr+1ORXlH5PRjERGR81BRKd63Y8vAPQscGsAl7/ruvqurbdV35EjvjYj2SLE/cnxi/KrqB+b6/Vjj9y65rKdqraxXFi09NrqsPLLnrrvGYm7fmaTu7jcuHi3qlxdRaxur1spFlcVH6s8tOXz8CdMXjdTV1dUWy5e318cvT8faDozP93di3d3dbRFXLTnUkZa2jaVKFPWx8erSI7v7X314pgIDF5G0ond9x4vSC8uiXmk/Vq2VbbWyfjTaR1csHj0ylxy57u7utnp92dKxtiUdRdTaxttzffHh8SMX7Pfr50F3d3fb0farl9WKsiOX9dReptrRaB+9orZvdI6vSbpu3br2RfvLpbWi7GgbS5Uyxsbr7Zcfbsl7s/W/OTRdu/XLx8cu1N/LztYlWxm5LNNVKTX8Pcp52mpDu4Y3fTQiPtq5eu3PRsqfO9GeUnxuZGjT2+Y10LOUI+4vU/0nHh6654mIiFWr1i4dW1q+pchpbb1Iv3ZmH4r5YM7xll1bN//tiZbjFYDT56MhsTrnuHbfsbafiOOPRVhIG9qK9M7tWwb2RZz4Ma7tPZHi95p6pXhfRDQltu4cvntzRGy+6ea1L69X8sk7NHLE3p1bN/3ojEe94oVfSLk5ETmnuKcSxdt2DG08cbNCWrm6vz+l/H8bqyfniHfedPPaP3zo/oHH4wLQ3f3GJYfT0Q803p2QI/amHK8f2brpG6f6dbcdbn/Re1KOD55oSxHLx5eWvxIRf3IWh5zzOTsVX/6R5pa0va2I/hNznnDd6nWXt6X6L+XIv5MilkdOPzdlInLX+vYy7//g5Ds0csRblo4//39O/LFbdeva5bUyfyhHvLmxX6XI74qIM04wP5trtdVrbZopxwu5sUp8Kq860zUAAMCZuaPcti2OxPSPyLrgTCTjHZr4x4YN9ZGL6fWYMd5zq4Q8swvqvZ73Dg2NRsQUj8abz9dgRnki4bhlX6peKNfqRBwHJv6ds4nvBGoREfNQDSNP/Ch12g9TM36BAAAAADCD9evXV0Yee767TOnHIkd7RETk9HCR6oPnkmTX6u9dJuTjFUwviO/xzkUeGRkZi5GR85ZAPZE788LEv1Pu+8L5CmG+5b1DG0b3TvG96ly/p5t4zWaspHypmXhNnmvhlHnic+b0z5pWvDdb/5vDeb92z5dLNhk5inhx470xafKH5EUoR+xtP5Jet337PSersE5Uq/3YxL8zmycXr9u1dWBbY9uuoc0P3th7+2vLXH+0Kak2595YyGTklP5h59DATzc2Tfxg8/sre9YUKdIdDbuuv7677+qHtw0+24pD55x/u2k7Yl97Sj+3fcvGxgTRvGvrpoHO3rW/GDn/XWP/WqV8a8SppN6FdKR99KdSTs0VnFP6mZ3DA02PLp34Y/D7XT39P5Qj3niiPef0njjTZOTWnbPuxo2c829t37Jp3+ROe7bedSAi/vi6dev+onIgv2LayuRX7P/xycnlEfl9u4Y3f6axZfuWgX1dXevfli/ff2NjNeMc8c4bXvOm9+6+7wuzPSZgLtdqa9faOFdKzf/Bk4sXzzYGAAAAAAAAFkJRLZ/J9bgnJhLIcpF2RE4zPUYcgHmyfv36ysjeA1fk2tg1I3v3ryqL9AuR46aJ3WORy4eK6rGtCxokAOdNsdABLJRUNlf/TKmld9AsiJTSf59IaDwXfzU5EfmEHUMbn8sRH2k6ZqTrzvF45yTn4jem29fRUfvTyW1Ftf17W3Hczu7br4mI6xvbUpT/eXKl2hN2Dg38fUR8vKl/ittaEUtL5PQfmzYj37FraGDLdL1r4+Nvjcgnk25TxPKu16z5njM6VIvOWYr47uaGPOPdInvuuuvYjMm5OZpeg0j5yy/tqH1oqq4jIxvGKqn4+dN21I790EwxnJz6LK/Vlq+1KZZJN2KkrDIyAAAAAAAAF6bnr3oqxiufL2u13y1rtd9tL6ufOnZlcUE8jRbgUjOy98D31XP57lypfrLMcUdE9EVEx8Tu3SnFxgfvvVdFWIBLxCWbjBwp5cbNnHNaqFBapSjr/3TOk+T4fzPtTmV8tbl7vPKcjzlHOWLfruEvPjrd/gcGB/dH5H9tbCuiXDFd/7NSqb96ciw7h+/ePNOQlIpPNzXk9Nq+vr4LpTp5b+NGUVbumanzw9sGn80p3d/YlurpP8x2kNaes/RY01YUf/r9N9927WwxTB9bvrVpO6dPTVRsntKOoY17IkXTNVek8ubp+jf1O+trtbVrbZRzavo7kMrI0/UFAAAAAACAhTQysmFs57aNT+7+6pd27/7ql3Zv33rX3onHcgNwntXLfEWKvCoieuJ4Qb8lEcdzQ3LEnWWZ7z6+CcCl4EJJhDzvcs7Pp3Qq/zgXccUChtMSRVvHk+c+S/7GTHvLlB8voilve8HeQ0WOr83eK30zIk4mDpctijcX6SWNr0JKaWi2MYvH2h860na0qe3btaXLIuL5VsR0LnLE1U1ntVJ2dfX2t88yaFHjfzHWc/qu2Y7T2nNWDkekhurEeVW1Unyzs3fNl6MstkXkPTnyUzmnxxYdTTtnq0ScI61ofA2KlL8+a6RlbMsp3nBqknz1bGMi5nKttnatjXKUl6do/CzMC/5+BAAAAAAAAAAuAima041zPFmk+FxZbfvrXff+87cXKiwAzr9LNhk5UjT9wUv54k9GfvDefzrnJMJUxIx3jVaL6pEyl+d6mJbIRTo6W58UcXg+brEqIi/LjUnZOT8725ht2+480tnT39RWK0cvjwsgGTlFLG/czjk+frZzFFFePlufVp6zemXJZ4r6kf8SkZY1HyS9NlJ+7fG5UqQUMb4kR2dP/2CO9NFdwwP/GFPceTf5NajXi1kfFZKL/Hw0FlVPxZVnEPpZX6utXmujlIorIzd1ee5sYgMAAGBhDA72lTfesmVXTumzOXI1cjqaUgwudFwAAAAAXBpSpfZsLitfShGHItLhSOnfUyofzKn+lR+45sq9uxY6QADOq0s2GbmSi+fLdCoBr0zpqgUMh4tOc1JojnTkzMblg41ji3pa2tq45mD9+ko8Pmve7azKomhrQTRnbPd9Xzh4w+rbfrhIce9pSbpT60uR+zp7+j/+0o7xXx8cHKyd3DPFa1DJY6OzTZjL4khKTbf4nUkcZ62la50k53xlY0XoHIVkZAAAgIvCHeWxtO6rbbn2eFmvFdW29nq9XlvwG54BAAAAuDSM71v0VNs15efysdo/tuWo5SIO7y+OHNi7ZWh050IHB8B5d8kmI9eL/ExjDmHKacXCRcPFpsxxLDUWxI18hom4kxJJi+pYC8Oamw0b6jGpYvOc5HLW6tCttnvr3dtv7L39FWXOb08pvyXnuPYMhv3a06NtD0XEn59smeI1qBaLZ/18nHzeU8SslZ/nqmVrnSSleHlj7eRUnv/zCAAAwNzs2XrXgYg4sNBxAAAAAHDp2bPnrmOxJ56MiCcXOhYAFt4lm4xcieLBMsqGlrL7fBy3WhuvzLQ/F0WRGjMDuTClfCDiVDZyinT57IPuKCLua56mrB1sdWhzkSP2pYjlJ7bLSmXl7pct23NWk2zYUG95YGdgx9DG5yLiDyLiD37gh99wVW382A1RpGtSzitypB/MEbeniKabDXKK342Iv4hovNiaq1YfLeqXzXbsHHlZangflPP8A3Dr1trYIZo++8rqkh3zFD4AAAAAAAAAAADfgS7ZZOQdQxuf6+zpfzgirj/ekl7d19dXHRwcrM3nccsUL4uIken2pyhXNCa5cmFKURxozO3METfNNubG3qFry0npoItqSy6IZOQUsT8akpFTWb44NmzYvYAhzcmD9/7T8xEx3NjW19dXffpY+29Gzn94oi1FLL9p9W3LH9p699Mn21J6Juc4mYxcRFwXEbtmOl6R0g2Np7TIsf+cF3GGzmWtJ6zo7V0cObpOtaTtu+/7wgXxngQAAAAAAAAAAODiUCx0AAsq53sbN589Wv3+eTjKE82HrFw7U+cUqWum/VwYylzf2dySV626de3yqXtP9Cjrr23cTike2bbtziOtj25OHmjcSDm/aaECabXBwcHazqGBP0opHmlsL4v0sqaOOX2tcbPI+XUzzdvVtb69jFjTNEWkndP1Px/OeK0Trqhffn1zS3nvVP0AAAAAAAAAAABgOpd0MnJOzVVF67n4wZn6pyLXm8bn9JIzOMw3m+ZI8Y6IO6Z83Tu7b78mR7zzDOakxcbbm89tilgxU/9rFtdPq25dK/MnY5qy1tf3vv67c4o/bWzLOb40h1DnR45/mdTy2zfdvPblMw25afVtL+3qXfOJzt41vziPkU3r+u6+q7t6+j+8snftrWfSv8xxWeN2NRWTbhTIX27ajnhX5+o1PdNOuGz/HZPfJzkVw9N1PxetXusJ9aJ8VVNDiq1zDhIAAAAAAAAAAIBL0iWdjFytF19sakj5R2ccUOYnmxvymh/44TdcNeOYlHdPGrNqZe9974v16yuNrStvue3FqVp+epaQmSfXtI3vm9x2Q0//a6brPzg4WIuIjze25Yg3ruxd847Jfbu7u9uKqPzPiLSssb0o02fPIeSWaovqP0xuK6t58IZb1n7fVP27brn9tbVUbM85/Wrk9Nedq/vfP/9RnnLd6nWXV9qqG3PEu1PO93X19H+6s/v2a6br37l67dtTxMnK1Tli3/YtA03nPKfKaa9BTmnDVNd4Z89ta3KK9zS2pYj7dg1/8dG5rWh687HWhpjXNW3XagOtixwAAAAAAAAAAIBLQXWhA1hID90/8HhnT/+miOg/3pJ/sq+v75cnEk1PU8/FE0XKDS1pWa029lxnT/9dKccDUeQNI0Obv9Y4pi0Vnx3P+Y8b21KOD3Y9vn9t7um/M1J+Mud0Q0T8cm5IIOT8GhwcrK3s6d/bWOm2iLh3ZU///SnnwRyxddfWzX/bOKZIxUfKXP5aY1vK6c86e/rfFJH/LqVUlpFedDjnt6c8qdJyyl/e8ZVN98zros7C9q137e3s6f94RJxcT85xbVHkR7p6+j+TI+5LKZWR86ty5FtzlK9uKgGd4vduuGXt/979lYF/Ox/xtqXaJyLSq0/GGvHmaCvf3Nm79h9y5H+t5Hgg5/xcjmJFFPkXIuc3NI4vIv558py7hr/4aOfqNZ+KlN56oi1FrKjVjj3Wtbr/YznlxyPSeIr0uhz55yePr+diXhKy52OtERHXrVu3KJ6v/fSJ7RRx58j9g0/NxxoAAAAAAAAAAAD4znVJJyNHROQUn075RDJyWvbUsfZbImLLVH13f+XWxzp7tmyPyKsm7VqXU6yLnPZHRFMy8vYtA/u6evo/kiPe3XTciNdExGsip2hK6mTBpMgbItJvNrfFzZHSzUWOjRHRlIy8Y2jjnpU9/e9OER+ZNFV/ROrPOSJFjtPlg0W98ustDv+cpfr4B6PatjbnuLaxPUe8OSLenPOJtUz5jv3Q+UpEjojIOX89pfSzU+z48RTx42VEREoRkWPyKcgR++rj47811byVyO8tU+prfg3SsuNVkNPE+NPPaYr4zO6tG7801/XMZL7Wuujb9deUDbXxy5z/unVRAwAAAAAAAAAAcKkoZu/yna1YNH5n03aZf2z63neUOecpE/tmciAden+K9Lez94xIER872/lpjUrOH4rIB89mzK7hTR/NKT5w5iPywZTiR3Z8ZePXzza++TZy/+BTZa7cliP2nt3I9K6dw5t+Z36imtqurZv/W1GmOcSaD0ZKP/HwtsFnp9r70Na7n05R3J5SPHLmc6a/HHn5lb98dnGcuflaay4aKyjng4eKw1NWUAYAAAAAAAAAAICZXPLJyCODg4ci5z86sV2m+KXr1q1bNF3/XVs3DRRFeUuKuO/0vWl8qjF7h4ZGl3eM/WxEen+O2DfN1A8XRXlLLtKGptac/n2qzqOjHbWmI59V8mST5xs3xmv5hZk6l2NxeFLTlPHNSww5HWrezk/ONnE+Xq36pFQpnpmu70Nb7366rKSVKdJnT9uZYmy6cbuGNv1eRNEdEZtmiORgivTBSs7fPzK0+WvT9zt3ZYoDk1qePtOxu4a/+OihdOj645W8Z0rMzgdTxMeiqL9i5/DAH0/fbf7O2Y6vDNzzXR3j3xcpfjIiBmeZ9WBO6b2po/ayXUMDU1Y+Pznv0MY9RxaN3xiR3zfD9RoRMVikct3O4YG3xYYN9ek6teJabfVau7vfuCRH/pWGoP5k79DQ6NnGBQAAAAAAAAAAAGmhA7gQ3Nh7+4vKXH80Ii2LiIicfm7n1oHPzzaur6+v+vRY8d1Fre3KiIjDS47tfnRw8OjMo+4oVvZu6SnK8oYcaUkqYl9E3jMytPmBiMjnvhpaJN20+rbl4xEvreZqGq8fe2K6CrONru1ec0VHW3FrpLgmyjyWUhyo5fLRy2pL9mzbdueR8xF4C6Ube29/ZY7yVWWOpcdb0rNFlE8sX1R7cHBwsDbL+POqr6+v+sThyvdUK3Ft5MrVEbktF/GtlOqPvrS9fGKO8aaVvWtuSmVxY4pczREpKumxynj820P3Dzze8kWcoXNd68qe/jeniE8f38oHj43Hyx/ZtnnGGxEAAAAAAAAAAABgKpKRJ6zs6X9XivjIxObwzuFNvQsaEMA86exZ+/WIvCoiInJ6x86tA3+xwCEBAAAAAAAAAABwkSoWOoALxaF06H/kiL0Tmz03rL5t1YIGBDAPbrz1tptPJCKnFI+kg1d8cqFjAgAAAAAAAAAA4OJVXegALhR7h4ZGb+pZs7ae00/lIlK9rf3JhY4JoNVS5Odyig+kMnLO8fmdIxvGFjomAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAuBv8fsDZcs9mdLvUAAAAASUVORK5CYII="}}},{"cell_type":"markdown","source":"## Getting data ready import dataset.","metadata":{}},{"cell_type":"code","source":"import pandas as pd \nimport numpy as np\nimport matplotlib.pyplot as plt \nimport os \n\nimport tensorflow as tf","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:38.661822Z","iopub.execute_input":"2021-12-11T18:16:38.662227Z","iopub.status.idle":"2021-12-11T18:16:42.794661Z","shell.execute_reply.started":"2021-12-11T18:16:38.662193Z","shell.execute_reply":"2021-12-11T18:16:42.793951Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dir_path = \"../input/dog-breed-identification/\"\nos.listdir(dir_path)\n","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:42.797043Z","iopub.execute_input":"2021-12-11T18:16:42.79755Z","iopub.status.idle":"2021-12-11T18:16:42.806266Z","shell.execute_reply.started":"2021-12-11T18:16:42.797513Z","shell.execute_reply":"2021-12-11T18:16:42.80541Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"  for dirpath, dirnames, filenames in os.walk(dir_path ):\n    print(f\"There are {len(dirnames)} directories and {len(filenames)} images in '{dirpath}'.\")","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:42.807657Z","iopub.execute_input":"2021-12-11T18:16:42.808262Z","iopub.status.idle":"2021-12-11T18:16:49.938006Z","shell.execute_reply.started":"2021-12-11T18:16:42.80822Z","shell.execute_reply":"2021-12-11T18:16:49.937185Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Hmm, We learnt from here two things: \n\n* There are 10222 images in train folder which will be used for training. \n* There are 10357 images in test folder which will be used for testing. ","metadata":{}},{"cell_type":"code","source":"train_images_path = \"../input/dog-breed-identification/train/\"\ntest_images_path = \"../input/dog-breed-identification/test/\"","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:49.943092Z","iopub.execute_input":"2021-12-11T18:16:49.943743Z","iopub.status.idle":"2021-12-11T18:16:49.948464Z","shell.execute_reply.started":"2021-12-11T18:16:49.943675Z","shell.execute_reply":"2021-12-11T18:16:49.947381Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Lets read labels.csv file and check whats in that \nlabels_df = pd.read_csv(dir_path + 'labels.csv')\nprint(labels_df.head())\nprint(labels_df.describe())","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:49.95016Z","iopub.execute_input":"2021-12-11T18:16:49.950682Z","iopub.status.idle":"2021-12-11T18:16:50.052324Z","shell.execute_reply.started":"2021-12-11T18:16:49.950645Z","shell.execute_reply":"2021-12-11T18:16:50.051155Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Ok. In the labels, we have images 'id' and 'breed' which is actually our Target labels. These labels our model need to predict. Great! ","metadata":{}},{"cell_type":"code","source":"#Lets check if images in labels.csv is equal to images in our train folder \n\ndef is_equal_images(target_dir, target_df): \n    \"\"\"\n    This function will check if target_dir images are equal to image list in target_df\n    \"\"\"\n    len_target_dir = len(os.listdir(target_dir))\n    len_target_df = len(target_df)\n    if len_target_dir == len_target_df: \n        print(f\"Both are having same no of images:{len_target_dir}\")\n    else: \n        print(f\"Target dir having {len_target_dir} images while Target DF having {len_target_df}\")\n        \nis_equal_images(target_dir = train_images_path, target_df = labels_df)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:50.053685Z","iopub.execute_input":"2021-12-11T18:16:50.054216Z","iopub.status.idle":"2021-12-11T18:16:50.069558Z","shell.execute_reply.started":"2021-12-11T18:16:50.054178Z","shell.execute_reply":"2021-12-11T18:16:50.068815Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Great, both are having no of images. That, means there are no missing files. ","metadata":{}},{"cell_type":"markdown","source":"### 2.Visualize the input data \n\n","metadata":{}},{"cell_type":"code","source":"#check one image from training data\nfrom IPython.display import Image, display\nImage(train_images_path + '000bec180eb18c7604dcecc8fe0dba07.jpg')","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:50.071068Z","iopub.execute_input":"2021-12-11T18:16:50.071583Z","iopub.status.idle":"2021-12-11T18:16:50.096908Z","shell.execute_reply.started":"2021-12-11T18:16:50.071547Z","shell.execute_reply":"2021-12-11T18:16:50.095855Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Check how many images per breed of dog. \n\nlabels_df['breed'].value_counts().plot.bar(figsize=(20,10))\nprint(f\"Average Images per breed:{int(labels_df['breed'].value_counts().sum()/len(labels_df['breed'].unique()))}\")\nprint(f\"Total no of breeds:{len(labels_df['breed'].unique())}\")","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:50.098499Z","iopub.execute_input":"2021-12-11T18:16:50.098727Z","iopub.status.idle":"2021-12-11T18:16:52.759368Z","shell.execute_reply.started":"2021-12-11T18:16:50.098697Z","shell.execute_reply":"2021-12-11T18:16:52.758746Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"* So, there are 120 breeds. \n* On an average there are around 85 images. Thats, a good number. \n\nSo, making ML model from scratch will not be good option as images are pretty less. \nSo, What can we do? \n\nWe can take help of **Transfer Learning**. \n\nThe process of using a pretrained model and adapting it to your own problem is called transfer learning. We do this because rather than train our own model from scratch (could be timely and expensive), we leverage the patterns of another model which has been trained to classify images. ","metadata":{}},{"cell_type":"markdown","source":"## Process train & Test data","metadata":{}},{"cell_type":"code","source":"#Create an array of train images \nfilenames = [train_images_path + fname + '.jpg' for fname in labels_df['id']]\nfilenames[:10]","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:52.760639Z","iopub.execute_input":"2021-12-11T18:16:52.763192Z","iopub.status.idle":"2021-12-11T18:16:52.774355Z","shell.execute_reply.started":"2021-12-11T18:16:52.76315Z","shell.execute_reply":"2021-12-11T18:16:52.773605Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Create class names array \nclass_names = labels_df['breed'].unique()\nclass_names[:10]","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:52.777534Z","iopub.execute_input":"2021-12-11T18:16:52.777793Z","iopub.status.idle":"2021-12-11T18:16:52.789412Z","shell.execute_reply.started":"2021-12-11T18:16:52.777755Z","shell.execute_reply":"2021-12-11T18:16:52.788713Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"target_labels = [breed for breed in labels_df['breed']]\ntarget_labels[:10]","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:52.790879Z","iopub.execute_input":"2021-12-11T18:16:52.791447Z","iopub.status.idle":"2021-12-11T18:16:52.799511Z","shell.execute_reply.started":"2021-12-11T18:16:52.791409Z","shell.execute_reply":"2021-12-11T18:16:52.798475Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Convert labels to one-hot encoded \n\n🔑**Remember:** An important concept in machine learning is converting your data to numbers before passing it to a machine learning model.","metadata":{}},{"cell_type":"code","source":"# Example: Turn one label into array of boolean \nprint(target_labels[0])\ntarget_labels[0] == class_names","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:52.801048Z","iopub.execute_input":"2021-12-11T18:16:52.801583Z","iopub.status.idle":"2021-12-11T18:16:52.81176Z","shell.execute_reply.started":"2021-12-11T18:16:52.801538Z","shell.execute_reply":"2021-12-11T18:16:52.810975Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Lets do for all the labels \n\ntarget_labels_encoded = [label == np.array(class_names) for label in target_labels]\ntarget_labels_encoded[:2]","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:52.8134Z","iopub.execute_input":"2021-12-11T18:16:52.813965Z","iopub.status.idle":"2021-12-11T18:16:52.912371Z","shell.execute_reply.started":"2021-12-11T18:16:52.813906Z","shell.execute_reply":"2021-12-11T18:16:52.911698Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Example: Turning a boolean array into integers\nprint(target_labels[0]) # original label\nprint(np.where(class_names == target_labels[0])[0][0]) # index where label occurs\nprint(target_labels_encoded[0].argmax()) # index where label occurs in boolean array\nprint(target_labels_encoded[0].astype(int)) # there will be a 1 where the sample label occurs","metadata":{"execution":{"iopub.status.busy":"2021-12-11T18:16:52.913566Z","iopub.execute_input":"2021-12-11T18:16:52.913802Z","iopub.status.idle":"2021-12-11T18:16:52.922038Z","shell.execute_reply.started":"2021-12-11T18:16:52.91377Z","shell.execute_reply":"2021-12-11T18:16:52.921063Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Wonderful! Now we've got our labels in a numeric format and our image filepaths easily accessible (they aren't numeric yet), let's split our data up.\n\n### Split Train & validation data","metadata":{}},{"cell_type":"code","source":"#Import train test split from sklearn \n\nfrom sklearn.model_selection import train_test_split \n\n#Experiement with small data 1000 images \nNUM_IMAGES = 2000\n\n#Split data into training & validation \nX_train, X_val, Y_train, Y_val = train_test_split(filenames[:NUM_IMAGES], target_labels_encoded[:NUM_IMAGES], test_size=0.2, random_state=42)\n\nlen(X_train), len(X_val), len(Y_train), len(Y_val)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:06.075829Z","iopub.execute_input":"2021-12-11T19:00:06.07639Z","iopub.status.idle":"2021-12-11T19:00:06.087788Z","shell.execute_reply.started":"2021-12-11T19:00:06.076353Z","shell.execute_reply":"2021-12-11T19:00:06.087057Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Check our the training data \n\nX_train[0], Y_train[0]","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:10.817438Z","iopub.execute_input":"2021-12-11T19:00:10.817871Z","iopub.status.idle":"2021-12-11T19:00:10.827728Z","shell.execute_reply.started":"2021-12-11T19:00:10.817825Z","shell.execute_reply":"2021-12-11T19:00:10.827045Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 3. Preprocess the Dataset in Tensorflow format. \n\nSince, we are using Tensorflow for modeling, our data needs to be in Tensorflow format. \n\nA Tensor is a way to represent information in numbers. If you're familar with NumPy arrays (you should be), a Tensor can be thought of as a combination of NumPy arrays, except with the special ability to be used on a GPU.\n\nBecause of how TensorFlow stores information (in Tensors), it allows machine learning and deep learning models to be run on GPUs (generally faster at numerical computing).\n\nTo preprocess our image we will write a function to do so: \n\n1. Take image file path. \n2. Read image from path using Tensorflow. \n3. Convert image to Tensor. \n4. Resize our image into fixed Tensor shape (224,224,3) \n5. Return the image\n\n📑 **Refrence**: You can read more about Tensorflow dataset from here: https://www.tensorflow.org/tutorials/load_data/images","metadata":{}},{"cell_type":"code","source":"#Random image and its shape \nfrom matplotlib.pyplot import imread\n\nimg = imread(X_train[0])\nplt.imshow(img)\nprint(f\"Image Shape: {img.shape}\")","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:12.623675Z","iopub.execute_input":"2021-12-11T19:00:12.624052Z","iopub.status.idle":"2021-12-11T19:00:12.961441Z","shell.execute_reply.started":"2021-12-11T19:00:12.624012Z","shell.execute_reply":"2021-12-11T19:00:12.960694Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Since, our model can take a fixed image size (224,224) for our model. So, each of the image we will convert to this shape. \n\nWe can use `tf.constant()` to convert image to TF tensor. ","metadata":{}},{"cell_type":"code","source":"tf.constant(img)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:13.880476Z","iopub.execute_input":"2021-12-11T19:00:13.880739Z","iopub.status.idle":"2021-12-11T19:00:13.892166Z","shell.execute_reply.started":"2021-12-11T19:00:13.880712Z","shell.execute_reply":"2021-12-11T19:00:13.890825Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"As we can see from the, our image `dtype` is `uint8` and tensorflow like data into `float32`. And we will also normalize our images by diving by 255 for values between 0 and 1.","metadata":{}},{"cell_type":"code","source":"tf.image.convert_image_dtype(img, tf.float32)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:14.480507Z","iopub.execute_input":"2021-12-11T19:00:14.481289Z","iopub.status.idle":"2021-12-11T19:00:14.492616Z","shell.execute_reply.started":"2021-12-11T19:00:14.481248Z","shell.execute_reply":"2021-12-11T19:00:14.491714Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMAGE_SIZE = 224\n\n# Lets write our preprocessing function\ndef process_image(image_path): \n    \"\"\"\n    This function will read image, resize the image and return into TF format. \n    Arguments: \n        image_path(str): Path of image\n    Returns: \n        img: Tensor image\n    \"\"\"\n    img = tf.io.read_file(image_path)\n    # Turn the jpeg image into numerical Tensor with 3 colour channels (Red, Green, Blue)\n    img = tf.io.decode_image(img, channels =3)\n    # Convert the colour channel values from 0-225 values to 0-1 values\n    img = tf.image.convert_image_dtype(img, tf.float32)\n    # Resize the image to our desired size (224, 244)\n    img = tf.image.resize_with_crop_or_pad(img, 224, 224)\n    return img\n","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:14.717228Z","iopub.execute_input":"2021-12-11T19:00:14.717821Z","iopub.status.idle":"2021-12-11T19:00:14.723708Z","shell.execute_reply.started":"2021-12-11T19:00:14.717782Z","shell.execute_reply":"2021-12-11T19:00:14.722909Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Create a simple function to return a tuple (image, label)\ndef get_image_label(image_path, label):\n    \"\"\"\n    Takes an image file path name and the associated label,\n    processes the image and returns a tuple of (image, label).\n    \"\"\"\n    image = process_image(image_path)\n    return image, label\n\nget_image_label(X_train[10], Y_train[10])","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:14.933717Z","iopub.execute_input":"2021-12-11T19:00:14.934098Z","iopub.status.idle":"2021-12-11T19:00:14.951351Z","shell.execute_reply.started":"2021-12-11T19:00:14.934063Z","shell.execute_reply":"2021-12-11T19:00:14.95058Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Great, our function is working and processing images and returning image and label.\n\n### Creating Data Batches","metadata":{}},{"cell_type":"code","source":"BATCH_SIZE = 32 \n\n#Create function to create dataset batches \ndef create_data_batches(X, y=None, batch_size = BATCH_SIZE, valid_data= False, test_data=False): \n    \"\"\"\n    This function will help to accept Train Images (X) and labels (y). \n    Also Shuffles the data if it's training data but doesn't shuffle it if it's validation data.\n    Also accepts test data as input (no labels).\n    \"\"\"\n    if test_data: \n        print(\"Creating Test data\")\n        test_data = tf.data.Dataset.from_tensor_slices(tf.constant(X))\n        test_data = test_data.map(process_image).batch(BATCH_SIZE) \n        return test_data \n    \n    #Create validation data\n    if valid_data: \n        print(\"Creating Validation data\")\n        valid_data = tf.data.Dataset.from_tensor_slices((tf.constant(X),tf.constant(y)))\n        valid_data = valid_data.map(get_image_label).batch(BATCH_SIZE)\n        return valid_data\n    \n    #Shuffle and create training data\n    else: \n        print(\"Creating Training Data\") \n        train_data = tf.data.Dataset.from_tensor_slices((tf.constant(X),tf.constant(y))).shuffle(buffer_size = len(X))\n        train_data = train_data.map(get_image_label).batch(BATCH_SIZE) \n        return train_data \n        ","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:15.341662Z","iopub.execute_input":"2021-12-11T19:00:15.343108Z","iopub.status.idle":"2021-12-11T19:00:15.35169Z","shell.execute_reply.started":"2021-12-11T19:00:15.343058Z","shell.execute_reply":"2021-12-11T19:00:15.350854Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = create_data_batches(X_train, Y_train)\nvalid_data = create_data_batches(X_val, Y_val, valid_data= True)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:16.562911Z","iopub.execute_input":"2021-12-11T19:00:16.56339Z","iopub.status.idle":"2021-12-11T19:00:16.794551Z","shell.execute_reply.started":"2021-12-11T19:00:16.563353Z","shell.execute_reply":"2021-12-11T19:00:16.793885Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample =next(iter(train_data))\nsample[0][0]","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:17.678711Z","iopub.execute_input":"2021-12-11T19:00:17.679385Z","iopub.status.idle":"2021-12-11T19:00:17.808464Z","shell.execute_reply.started":"2021-12-11T19:00:17.679343Z","shell.execute_reply":"2021-12-11T19:00:17.807736Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Visualizing Images \n\nLet's build a function which helps us visualize what going on under the hood. ","metadata":{}},{"cell_type":"code","source":"import matplotlib.pyplot as plt \n\ndef show_images(images, label): \n    \"\"\"\n    Display 25 Images with labels. \n    \"\"\"\n    #Setup the figure \n    plt.figure(figsize = (12,12)) \n    for i in range(0,25): \n        ax = plt.subplot(5, 5, i+1)\n        \n        plt.imshow(images[i])\n        \n        plt.title(class_names[tf.argmax(label[i])])\n        \n        plt.axis(\"off\")\n        ","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:18.764766Z","iopub.execute_input":"2021-12-11T19:00:18.765312Z","iopub.status.idle":"2021-12-11T19:00:18.772243Z","shell.execute_reply.started":"2021-12-11T19:00:18.765276Z","shell.execute_reply":"2021-12-11T19:00:18.770221Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Visualize training images from the training data batch\ntrain_images, train_labels = next(train_data.as_numpy_iterator())\nshow_images(train_images, train_labels)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:19.164837Z","iopub.execute_input":"2021-12-11T19:00:19.165453Z","iopub.status.idle":"2021-12-11T19:00:20.826779Z","shell.execute_reply.started":"2021-12-11T19:00:19.165415Z","shell.execute_reply":"2021-12-11T19:00:20.825873Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Visualize validation images from the validation data batch\nval_images, val_labels = next(valid_data.as_numpy_iterator())\nshow_images(val_images, val_labels)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:00:20.828259Z","iopub.execute_input":"2021-12-11T19:00:20.829063Z","iopub.status.idle":"2021-12-11T19:00:23.146951Z","shell.execute_reply.started":"2021-12-11T19:00:20.829021Z","shell.execute_reply":"2021-12-11T19:00:23.1463Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Creating Model ","metadata":{}},{"cell_type":"markdown","source":"#### Creating EfficientNetB0 model","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf \nfrom tensorflow.keras import layers \n\ndef create_model():\n    base_model = tf.keras.applications.mobilenet_v2.MobileNetV2(include_top = False, \n                                                     classes = len(class_names)) \n    base_model.trainable = False \n\n    inputs = layers.Input(shape = (224,224,3))\n    x = base_model(inputs, training = False) \n    x = tf.keras.layers.GlobalAveragePooling2D(name= \"global_average_pooling\")(x)\n    x = layers.Dropout(0.2)(x)\n    outputs = tf.keras.layers.Dense(len(class_names), activation=\"softmax\")(x)\n\n\n    ModelDogBreed = tf.keras.Model(inputs, outputs) \n\n    ModelDogBreed.compile(loss = \"categorical_crossentropy\", \n                         optimizer = tf.keras.optimizers.Adam(), \n                         metrics=[\"accuracy\"]) \n\n    return ModelDogBreed","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:02:47.855733Z","iopub.execute_input":"2021-12-11T19:02:47.856003Z","iopub.status.idle":"2021-12-11T19:02:47.864799Z","shell.execute_reply.started":"2021-12-11T19:02:47.855974Z","shell.execute_reply":"2021-12-11T19:02:47.864053Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = create_model()\n\n# Callbacks \n\nEarlyStoppingCallbacks = tf.keras.callbacks.EarlyStopping(\n    monitor='val_loss', patience=2, baseline=None, restore_best_weights=True\n)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:02:48.154874Z","iopub.execute_input":"2021-12-11T19:02:48.155428Z","iopub.status.idle":"2021-12-11T19:02:49.475372Z","shell.execute_reply.started":"2021-12-11T19:02:48.155391Z","shell.execute_reply":"2021-12-11T19:02:49.474625Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ModelDogBreed_History = model.fit(train_data, \n                                         steps_per_epoch = len(train_data),\n                                         epochs = 5, \n                                         validation_data= valid_data, \n                                         validation_steps = len(valid_data),\n                                         callbacks = [EarlyStoppingCallbacks])","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:02:49.477334Z","iopub.execute_input":"2021-12-11T19:02:49.477587Z","iopub.status.idle":"2021-12-11T19:03:16.299371Z","shell.execute_reply.started":"2021-12-11T19:02:49.477552Z","shell.execute_reply":"2021-12-11T19:03:16.298506Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.evaluate(valid_data)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:16.302952Z","iopub.execute_input":"2021-12-11T19:03:16.303291Z","iopub.status.idle":"2021-12-11T19:03:17.257537Z","shell.execute_reply.started":"2021-12-11T19:03:16.303251Z","shell.execute_reply":"2021-12-11T19:03:17.256765Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Plot loss curves","metadata":{}},{"cell_type":"code","source":"def plot_loss_curves(history):\n  \"\"\"\n  Returns separate loss curves for training and validation metrics.\n  Args:\n    history: TensorFlow model History object (see: https://www.tensorflow.org/api_docs/python/tf/keras/callbacks/History)\n  \"\"\" \n  loss = history.history['loss']\n  val_loss = history.history['val_loss']\n\n  accuracy = history.history['accuracy']\n  val_accuracy = history.history['val_accuracy']\n\n  epochs = range(len(history.history['loss']))\n\n  # Plot loss\n  plt.plot(epochs, loss, label='training_loss')\n  plt.plot(epochs, val_loss, label='val_loss')\n  plt.title('Loss')\n  plt.xlabel('Epochs')\n  plt.legend()\n\n  # Plot accuracy\n  plt.figure()\n  plt.plot(epochs, accuracy, label='training_accuracy')\n  plt.plot(epochs, val_accuracy, label='val_accuracy')\n  plt.title('Accuracy')\n  plt.xlabel('Epochs')\n  plt.legend();","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:17.259105Z","iopub.execute_input":"2021-12-11T19:03:17.259382Z","iopub.status.idle":"2021-12-11T19:03:17.266863Z","shell.execute_reply.started":"2021-12-11T19:03:17.259346Z","shell.execute_reply":"2021-12-11T19:03:17.265956Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_loss_curves(ModelDogBreed_History)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:17.268769Z","iopub.execute_input":"2021-12-11T19:03:17.269046Z","iopub.status.idle":"2021-12-11T19:03:17.748115Z","shell.execute_reply.started":"2021-12-11T19:03:17.269007Z","shell.execute_reply":"2021-12-11T19:03:17.747361Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Make prediction on the validation data","metadata":{}},{"cell_type":"code","source":"predictions = model.predict(valid_data)\npredictions","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:29.78184Z","iopub.execute_input":"2021-12-11T19:03:29.782535Z","iopub.status.idle":"2021-12-11T19:03:31.798531Z","shell.execute_reply.started":"2021-12-11T19:03:29.782498Z","shell.execute_reply":"2021-12-11T19:03:31.797733Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions.shape","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:31.80011Z","iopub.execute_input":"2021-12-11T19:03:31.800441Z","iopub.status.idle":"2021-12-11T19:03:31.805977Z","shell.execute_reply.started":"2021-12-11T19:03:31.800401Z","shell.execute_reply":"2021-12-11T19:03:31.805319Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# First prediction\nprint(predictions[0])\nprint(f\"Max value (probability of prediction): {np.max(predictions[0])}\") # the max probability value predicted by the model\nprint(f\"Sum: {np.sum(predictions[0])}\") # because we used softmax activation in our model, this will be close to 1\nprint(f\"Max index: {np.argmax(predictions[0])}\") # the index of where the max value in predictions[0] occurs\nprint(f\"Predicted label: {class_names[np.argmax(predictions[0])]}\") # the predicted label","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:35.104948Z","iopub.execute_input":"2021-12-11T19:03:35.105503Z","iopub.status.idle":"2021-12-11T19:03:35.113488Z","shell.execute_reply.started":"2021-12-11T19:03:35.105464Z","shell.execute_reply":"2021-12-11T19:03:35.112757Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Turn prediction probabilities into their respective label (easier to understand)\ndef get_pred_label(prediction_probabilities):\n  \"\"\"\n  Turns an array of prediction probabilities into a label.\n  \"\"\"\n  return class_names[np.argmax(prediction_probabilities)]\n\n# Get a predicted label based on an array of prediction probabilities\npred_label = get_pred_label(predictions[0])\npred_label","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:35.260974Z","iopub.execute_input":"2021-12-11T19:03:35.261489Z","iopub.status.idle":"2021-12-11T19:03:35.269765Z","shell.execute_reply.started":"2021-12-11T19:03:35.261451Z","shell.execute_reply":"2021-12-11T19:03:35.268832Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Create a function to unbatch a batched dataset\ndef unbatchify(data):\n  \"\"\"\n  Takes a batched dataset of (image, label) Tensors and returns separate arrays\n  of images and labels.\n  \"\"\"\n  images = []\n  labels = []\n  # Loop through unbatched data\n  for image, label in data.unbatch().as_numpy_iterator():\n    images.append(image)\n    labels.append(class_names[np.argmax(label)])\n  return images, labels\n\n# Unbatchify the validation data\nval_images, val_labels = unbatchify(valid_data)\nval_images[0], val_labels[0]","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:36.341097Z","iopub.execute_input":"2021-12-11T19:03:36.341665Z","iopub.status.idle":"2021-12-11T19:03:37.125597Z","shell.execute_reply.started":"2021-12-11T19:03:36.341627Z","shell.execute_reply":"2021-12-11T19:03:37.124849Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def plot_pred(prediction_probabilities, labels, images, n=1):\n  \"\"\"\n  View the prediction, ground truth label and image for sample n.\n  \"\"\"\n  pred_prob, true_label, image = prediction_probabilities[n], labels[n], images[n]\n  \n  # Get the pred label\n  pred_label = get_pred_label(pred_prob)\n  \n  # Plot image & remove ticks\n  plt.imshow(image)\n  plt.xticks([])\n  plt.yticks([])\n\n  # Change the color of the title depending on if the prediction is right or wrong\n  if pred_label == true_label:\n    color = \"green\"\n  else:\n    color = \"red\"\n\n  plt.title(\"{} {:2.0f}% ({})\".format(pred_label,\n                                      np.max(pred_prob)*100,\n                                      true_label),\n                                      color=color)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:37.439432Z","iopub.execute_input":"2021-12-11T19:03:37.439684Z","iopub.status.idle":"2021-12-11T19:03:37.446152Z","shell.execute_reply.started":"2021-12-11T19:03:37.439657Z","shell.execute_reply":"2021-12-11T19:03:37.445397Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# View an example prediction, original image and truth label\nplot_pred(prediction_probabilities=predictions,\n          labels=val_labels,\n          images=val_images)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:37.965765Z","iopub.execute_input":"2021-12-11T19:03:37.966433Z","iopub.status.idle":"2021-12-11T19:03:38.064234Z","shell.execute_reply.started":"2021-12-11T19:03:37.966394Z","shell.execute_reply":"2021-12-11T19:03:38.063562Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def plot_pred_conf(prediction_probabilities, labels, n=1):\n  \"\"\"\n  Plots the top 10 highest prediction confidences along with\n  the truth label for sample n.\n  \"\"\"\n  pred_prob, true_label = prediction_probabilities[n], labels[n]\n\n  # Get the predicted label\n  pred_label = get_pred_label(pred_prob)\n\n  # Find the top 10 prediction confidence indexes\n  top_10_pred_indexes = pred_prob.argsort()[-10:][::-1]\n  # Find the top 10 prediction confidence values\n  top_10_pred_values = pred_prob[top_10_pred_indexes]\n  # Find the top 10 prediction labels\n  top_10_pred_labels = class_names[top_10_pred_indexes]\n\n  # Setup plot\n  top_plot = plt.bar(np.arange(len(top_10_pred_labels)), \n                     top_10_pred_values, \n                     color=\"grey\")\n  plt.xticks(np.arange(len(top_10_pred_labels)),\n             labels=top_10_pred_labels,\n             rotation=\"vertical\")\n\n  # Change color of true label\n  if np.isin(true_label, top_10_pred_labels):\n    top_plot[np.argmax(top_10_pred_labels == true_label)].set_color(\"green\")\n  else:\n    pass\n","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:41.563423Z","iopub.execute_input":"2021-12-11T19:03:41.56397Z","iopub.status.idle":"2021-12-11T19:03:41.570735Z","shell.execute_reply.started":"2021-12-11T19:03:41.563914Z","shell.execute_reply":"2021-12-11T19:03:41.569991Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_pred_conf(prediction_probabilities=predictions,\n               labels=val_labels,\n               n=9)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:42.157455Z","iopub.execute_input":"2021-12-11T19:03:42.157983Z","iopub.status.idle":"2021-12-11T19:03:42.437304Z","shell.execute_reply.started":"2021-12-11T19:03:42.157938Z","shell.execute_reply":"2021-12-11T19:03:42.436417Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Let's check a few predictions and their different values\ni_multiplier = 0\nnum_rows = 3\nnum_cols = 2\nnum_images = num_rows*num_cols\nplt.figure(figsize=(5*2*num_cols, 5*num_rows))\nfor i in range(num_images):\n  plt.subplot(num_rows, 2*num_cols, 2*i+1)\n  plot_pred(prediction_probabilities=predictions,\n            labels=val_labels,\n            images=val_images,\n            n=i+i_multiplier)\n  plt.subplot(num_rows, 2*num_cols, 2*i+2)\n  plot_pred_conf(prediction_probabilities=predictions,\n                labels=val_labels,\n                n=i+i_multiplier)\nplt.tight_layout(h_pad=1.0)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:43.470251Z","iopub.execute_input":"2021-12-11T19:03:43.471278Z","iopub.status.idle":"2021-12-11T19:03:45.229326Z","shell.execute_reply.started":"2021-12-11T19:03:43.471211Z","shell.execute_reply":"2021-12-11T19:03:45.227598Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Train on full data\n\nRemember we created two list `filenames` for storing file paths of training data and `target_labels_encoded` for target labels of dog breed. ","metadata":{}},{"cell_type":"code","source":"# Remind ourselves of the size of the full dataset\nlen(filenames), len(target_labels_encoded)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:03:45.248018Z","iopub.execute_input":"2021-12-11T19:03:45.248832Z","iopub.status.idle":"2021-12-11T19:03:45.254712Z","shell.execute_reply.started":"2021-12-11T19:03:45.248786Z","shell.execute_reply":"2021-12-11T19:03:45.25387Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Create training batch of data \n\nfull_data = create_data_batches(filenames, target_labels_encoded)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:12:47.546038Z","iopub.execute_input":"2021-12-11T19:12:47.546783Z","iopub.status.idle":"2021-12-11T19:12:47.806718Z","shell.execute_reply.started":"2021-12-11T19:12:47.54674Z","shell.execute_reply":"2021-12-11T19:12:47.805989Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ModelDogBreed_FullData = create_model()  #Create model\nModelDogBreed_FullData.summary()  ","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:12:48.159856Z","iopub.execute_input":"2021-12-11T19:12:48.160564Z","iopub.status.idle":"2021-12-11T19:12:49.42732Z","shell.execute_reply.started":"2021-12-11T19:12:48.160528Z","shell.execute_reply":"2021-12-11T19:12:49.426586Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Train our final model \n\nFinalModelDogBreed_FullData_History = ModelDogBreed_FullData.fit(full_data, \n                                         steps_per_epoch = len(full_data),\n                                         epochs = 10,\n                                         callbacks = [EarlyStoppingCallbacks])","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:12:49.428936Z","iopub.execute_input":"2021-12-11T19:12:49.42918Z","iopub.status.idle":"2021-12-11T19:20:37.713743Z","shell.execute_reply.started":"2021-12-11T19:12:49.429145Z","shell.execute_reply":"2021-12-11T19:20:37.712881Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load test image filenames (since we're using os.listdir(), these already have .jpg)\ntest_path = \"../input/dog-breed-identification/test/\"\ntest_filenames = [test_images_path + fname for fname in os.listdir(test_images_path)]\n\ntest_filenames[:10]","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:20:37.716808Z","iopub.execute_input":"2021-12-11T19:20:37.71711Z","iopub.status.idle":"2021-12-11T19:20:37.733736Z","shell.execute_reply.started":"2021-12-11T19:20:37.717073Z","shell.execute_reply":"2021-12-11T19:20:37.732898Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#View some test images \nimg = imread(test_filenames[44])\nplt.imshow(img)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:21:18.029082Z","iopub.execute_input":"2021-12-11T19:21:18.029624Z","iopub.status.idle":"2021-12-11T19:21:18.291577Z","shell.execute_reply.started":"2021-12-11T19:21:18.029585Z","shell.execute_reply":"2021-12-11T19:21:18.290814Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# How many test images are there?\nlen(test_filenames)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:21:18.613797Z","iopub.execute_input":"2021-12-11T19:21:18.614526Z","iopub.status.idle":"2021-12-11T19:21:18.622061Z","shell.execute_reply.started":"2021-12-11T19:21:18.614485Z","shell.execute_reply":"2021-12-11T19:21:18.621146Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Create test data batch\ntest_data = create_data_batches(X=test_filenames, test_data=True)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:21:19.56645Z","iopub.execute_input":"2021-12-11T19:21:19.566706Z","iopub.status.idle":"2021-12-11T19:21:19.677663Z","shell.execute_reply.started":"2021-12-11T19:21:19.566676Z","shell.execute_reply":"2021-12-11T19:21:19.676956Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Make predictions on test data batch using the loaded full model\ntest_predictions = ModelDogBreed_FullData.predict(test_data,\n                                      verbose=1)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:21:21.359655Z","iopub.execute_input":"2021-12-11T19:21:21.360584Z","iopub.status.idle":"2021-12-11T19:21:45.137798Z","shell.execute_reply.started":"2021-12-11T19:21:21.360537Z","shell.execute_reply":"2021-12-11T19:21:45.137051Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Preparing test dataset predictions for Kaggle","metadata":{}},{"cell_type":"code","source":"# Create pandas DataFrame with empty columns\npreds_df = pd.DataFrame(columns=[\"id\"] + list(class_names))\npreds_df.head()","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:22:27.371609Z","iopub.execute_input":"2021-12-11T19:22:27.37187Z","iopub.status.idle":"2021-12-11T19:22:27.39003Z","shell.execute_reply.started":"2021-12-11T19:22:27.371842Z","shell.execute_reply":"2021-12-11T19:22:27.389189Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Append test image ID's to predictions DataFrame\npreds_df[\"id\"] = [os.path.splitext(path)[0] for path in os.listdir(test_path)]\npreds_df.head()","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:22:31.228342Z","iopub.execute_input":"2021-12-11T19:22:31.228884Z","iopub.status.idle":"2021-12-11T19:22:31.281491Z","shell.execute_reply.started":"2021-12-11T19:22:31.228848Z","shell.execute_reply":"2021-12-11T19:22:31.280645Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Add the prediction probabilities to each dog breed column\npreds_df[list(class_names)] = test_predictions\npreds_df.head()","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:22:34.442447Z","iopub.execute_input":"2021-12-11T19:22:34.442697Z","iopub.status.idle":"2021-12-11T19:22:34.811685Z","shell.execute_reply.started":"2021-12-11T19:22:34.44267Z","shell.execute_reply":"2021-12-11T19:22:34.810908Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"preds_df.to_csv(\"submission_with_mobilienetV2_1.csv\",\n                 index=False)","metadata":{"execution":{"iopub.status.busy":"2021-12-11T19:23:20.654013Z","iopub.execute_input":"2021-12-11T19:23:20.654617Z","iopub.status.idle":"2021-12-11T19:23:22.296843Z","shell.execute_reply.started":"2021-12-11T19:23:20.654581Z","shell.execute_reply":"2021-12-11T19:23:22.296011Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## What's next?\n\nWoah! What an effort. If you've made it this far, you've just gone end-to-end on a multi-class image classification problem.\n\nYou can try using other approaches to improve your model. \n\n1. [Trying another model from TensorFlow Hub](https://tfhub.dev/) - Perhaps a different model would perform better on our dataset. One option would be to experiment with a different pretrained model from TensorFlow Hub or look into the tf.keras.applications module.\n2. [Data augmentation](https://www.tensorflow.org/tutorials/images/data_augmentation) - Take the training images and manipulate (crop, resize) or distort them (flip, rotate) to create even more training data for the model to learn from. Check out the TensorFlow images documentation for a whole bunch of functions you can use on images. A great idea would be to try and replicate the techniques in this example cat vs. dog image classification notebook for our dog breeds problem.\n3. [Fine-tuning](https://www.tensorflow.org/hub/tf2_saved_model#fine-tuning) - The model we used in this notebook was directly from TensorFlow Hub, we took what it had already learned from another dataset (ImageNet) and applied it to our own. Another option is to use what the model already knows and fine-tune this knowledge to our own dataset (pictures of dogs). This would mean all of the patterns within the model would be updated to be more specific to pictures of dogs rather than general images.","metadata":{}}]}