Copy a token from your Hugging Face\ntokens page and paste it below. Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file.
"
+ ],
+ "image/png": "iVBORw0KGgoAAAANSUhEUgAABdEAAAJOCAYAAABYwk4SAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAACDwElEQVR4nOzdd3hUZf7+8XtSSCAJUpJAUCNZYBJKQglFBUFAKRa6gNLFgisqIAq46lpRViyIbZWiFAVRmgVkERERBAGBAAGkGVpIhh7Sk/n94S/zJSRDkpNpSd6v69przSnP8zkz55kz3Dl5jslqtVoFAAAAAAAAAAAK8HJ3AQAAAAAAAAAAeCpCdAAAAAAAAAAA7CBEBwAAAAAAAADADkJ0AAAAAAAAAADsIEQHAAAAAAAAAMAOQnQAAAAAAAAAAOwgRAcAAAAAAAAAwA5CdAAAAAAAAAAA7CBEBwAAAAAAAADADkJ0AIBH69SpkyIjI23/i4qKUvPmzdW+fXsNGTJEU6ZM0c6dO6/axpAhQxQZGalNmza5qOqryzumY8eO5VvuaXVK0sSJExUZGanFixe7uxSnWLNmje677z61aNHCdo658/Uv7683isfTzsuyzui4Wrx4sSIjIzVx4kQnVeYYRuo8duyYIiMj1alTJydWVvHkjVcAAFD+EKIDAMqEFi1aqHfv3urVq5c6dOigiIgI7du3T7NmzdI999yjIUOG6OjRo06twV74XVaVlYDIWeLj4/X4449r+/btatasmXr16qXevXsrODi4yH3L27kA+1w9TkpzXgJlRVkM8T3xF934myd+n/HEmgAApePj7gIAACiOe+65R3369Mm3zGq1at26dZo8ebI2b96sgQMHasGCBbr++uvzbTdlyhSlpaWpTp06rizZrk8//VRZWVmqVauWu0sp0rhx4/Tggw8qNDTU3aU43OrVq5WVlaVRo0Zp7Nix7i4HkMR56Uluv/12NW3aVEFBQe4uxeFq1aql77//Xr6+vu4upVz5/vvv3V0CAABwEu5EBwCUWSaTSR06dNCiRYtUt25dWSwWPfvsswW2q1OnjurVq6fKlSu7ocqCwsPDVa9evTIRXoSGhqpevXrlMkQ6ceKEJOmGG25wcyXA/+G89BxBQUGqV69eufwloq+vr+rVq6fw8HB3l1Ku1KtXT/Xq1XN3GYbkTXvEnfYAABSOEB0AUOZVrVpVzzzzjCTpt99+065du/Ktt/cn2JmZmZoxY4b69Omj5s2bq0mTJmrbtq369u2r//znPzp37pyk//uT3OPHj0uSOnfunG+e9rx2N23apMjISA0ZMkRpaWmaNm2aunfvrqZNm+b7k/XiTAWyefNm3X///WrdurWaNm2qfv36aenSpYVuW9SfmE+fPl2RkZGaPn16vhomTZokSVqyZEm+4xkyZIhtu6LmEv7uu+80bNgwtW7dWk2aNFHHjh01adIkHT58uNDtLz/23377Tffff79atWqlmJgY9e7d2+4xFiU7O1tffPGFBg4cqNjYWEVHR6tLly565ZVXdOrUqUJfj7xjmjRpUqHHXpjingt5du7cqSeeeELt2rVTkyZNdNNNN2nUqFH69ddfS3yM69atU4sWLRQdHa3vvvsu37pdu3bpySef1K233qomTZqodevWGjlypH7++edC23LW+yBJGzdu1OOPP6727durSZMmuvHGG9W3b1+9++67Onv2bIHtf/nlFz388MO66aab1KRJE7Vr105jxoxRXFxckbUXxt45e/nyo0eP6qmnnlLbtm3VpEkT3XbbbXr77beVmZlZoK/ijJOLFy/q7bff1t13361mzZrZjmPgwIGaNm2asrKyinzdSnJeHjx4UJMmTVLHjh1t7/ewYcPs3gV7+WfAiRMn9Mwzz6hDhw5q3LhxiaYaOH/+vN577z316dNHsbGxiomJUefOnfXEE08Ueq6dO3dOb731lu688041bdpUzZs3V58+ffTJJ58oPT29wPaXf4ZmZmbqvffeU9euXRUdHa1bb71Vb7zxhjIyMiT9/ZpPmTJFnTt3VnR0tDp16qTp06crOzv7qsewd+9ejR49WjfeeKNiYmJ0991367PPPlNOTk6Bbe1Nx3B5nVlZWfr444915513KiYmRm3atNHo0aN18ODBq76O7777rnr27KnmzZuradOmuvvuu/XBBx8oLS2t0H2ys7P16aef6u6771Z0dLRuvPFGPfbYY9q3b99Vj9eeq02ncvm83j/88IPuvfdetWjRQs2aNdPAgQPtfq4kJSXplVdesb1nTZs2VYcOHTRs2DDNnDnTtt3EiRPVuXNnSdLx48fzjavL5xMvznlb1JQZRU0bU5xzOu/93rx5syRp6NCh+eq9/LPmanOil2Y8GDnPPEFJr4HO/D5zedue8h0LAFC2MJ0LAKBcaN++vapVq6Zz585pw4YNatKkyVW3z83N1UMPPaSNGzcqMDBQLVu2VNWqVXXmzBn99ddfmjlzpu6++25Vq1ZN4eHh6t27t3744Qelpqaqa9euqlKliq2tK+cqzsjI0JAhQ3Tw4EG1bNlSUVFRtkC+OP73v/9p/vz5+sc//qF27dopKSlJW7du1YQJE7R3716HzK/ZtWtXbd++Xdu2bVN4eLhiY2Nt6/7xj38Uub/VatXEiRO1dOlS+fj4qGXLlqpZs6Z2796txYsXa8WKFXr33XfVvn37Qvf/+uuv9eGHH6pRo0a65ZZbdPz4cW3fvl0TJkzQuXPnNHz48GIfS2Zmph5++GFt2LBBfn5+atOmjQIDA/XHH39o7ty5+vbbbzVz5kw1btxYktSwYUP17t1bW7duVUJCglq0aGG767eoYy/JufDll1/q3//+t3Jzc9WoUSO1adNGx48f108//aSffvpJjz32mEaPHl2sY1ywYIFeeuklBQUF6eOPP1bLli1t6z777DO9/vrrys3NVcOGDRUTEyOLxaJNmzZp/fr1V+3Hke+DJL3yyiuaO3eupL9f55YtW+rixYs6fPiw3n//fbVp00Zt2rSxbf/OO+/oww8/lMlkUvPmzVWnTh0dPHhQK1as0KpVq/TSSy+pX79+JaqhKPHx8Xr11Vd1zTXXqFWrVjp//ry2bdumjz76SAcOHND7779v27Y44yQtLU333Xef9u/frxo1aujGG29UlSpVlJycrMOHD+uDDz7QiBEjivzLk+Kel2vXrtXjjz+ujIwMRUREqEuXLjp9+rR+//13/fbbb1q/fr0mT55caB9HjhxR79695evrqxYtWshqtap69erFet327t2rhx56SKdOnVJQUJBiY2MVEBCgkydPau3atTpz5ow6dOhg2/7o0aMaNmyYjh8/rho1aqhDhw7KysrSpk2bNHXqVK1YsUKzZ8/WNddcU6CvrKwsjRw5Unv27FHr1q0VERGhLVu2aMaMGTp48KBef/11DRw4UOfPn1erVq1Ut25d/f7773rvvfdksVj04osvFnoMO3fu1AsvvKDg4GDddNNNunDhgjZt2qTJkydr69atmjZtmkwmU7Fej7w6H3roIf3xxx9q2bKl6tWrp507d+p///ufNm3apCVLlui6667Lt8+BAwf0wAMP6OTJkwoJCVFsbKx8fHwUFxenadOmadWqVZo7d26+v/7Jzc3VE088odWrV8vX11dt2rRR1apVtWPHDt1zzz3q27dvsWsuiXfffVcffPCBmjdvrg4dOujQoUP6448/9PDDD2v69Om6/fbbbdsmJyerb9++SkpKUp06dXTLLbfIz89PSUlJ2rt3r3bv3q2RI0dKkmJjY5WamqoffvhBVapUUdeuXa9aR2nO26sp7jkdHBys3r1765dffpHFYlG7du0UEhJia6c4d/OXdjyU9DzzBI68Bl5NSb/PlIXvWAAAD2UFAMCDdezY0Wo2m61ff/11kdsOHz7cajabrePHj8+3fPDgwVaz2Wz97bffbMs2b95sNZvN1l69elkvXrxYoK2dO3daz5w5U2gtR48eLbT/3377zWo2m61ms9l69913W5OSkq56TFe2k1en2Wy2fvTRR/nWbdq0yRoTE2M1m83WdevWFXl8l3v33XetZrPZ+u677+Zb/vXXX1vNZrN1woQJhe5ntVqtEyZMKPT1//zzz61ms9napk0b6549e2zLc3Nzbf21bNnSevr06UKPvXHjxtY1a9YUWk9sbKw1LS3Nbk1XeuONN6xms9l622235XtNMzMzrc8884zVbDZbO3XqZM3IyCjWsRVHUefC3r17rY0aNbJGRkZalyxZkm/d2rVrrY0bN7aazWbr+vXrr1pTbm6u9T//+Y/t+A4dOpRv+3Xr1lkjIyOtbdq0sW7evLlADe3bt7eazWbrpk2bCq3fke/DnDlzrGaz2dq6dWvrxo0bC6zfsWOH9cSJE7aff/75Z6vZbLZGR0cXeB2+/PJLW3379+8vtHZ7r7299zVvudlstr711lvW7Oxs27p9+/ZZmzVrZjWbzdZt27bl26+ocbJkyRKr2Wy2PvDAA9bMzMx863JycqybNm0qcO5dzdXOy+TkZGtsbKzVbDZbP/jgA2tubq5t3c6dO62tWrWyms1m68KFC/Ptlzcm8z4fS1KP1Wq1Xrp0ydqhQwer2Wy2Pv3009aUlJR86y9cuGD99ddf8y275557rGaz2Tpq1CjrpUuXbMtPnz5t7d27t9VsNlvHjRuXb5/LP0P79euX7zP42LFjtuO76667rA8//LA1NTU13/E3atTIGhUVZT1+/Hi+di9/71944QVrVlaWbd3+/futN954o9VsNlu/+OKLfPvZe+8vr7NXr175PuvT09Ot999/v9VsNlufe+65fPulpaVZb7vtNqvZbLa+/fbb+d6H1NRU67hx46xms9k6ceLEfPvNmzfPajabrTfffLP1wIEDtuVZWVnWf//737ZarvZZfqWjR49azWaztWPHjgXW5bXXsmVL6/bt2/OtyzuXunTpkm/59OnTbcd8+Xlptf79Wbxhw4Zi939lX1c7b4san/b6MXJOF3WttVr/77W7UmnHQ0nOM6PyxsnVjq+4jF4Dnfl9xhO/YwEAyhamcwEAlBt5d6YV565vi8Ui6e874gIDAwusj46OLtWdbs8//3y+O9VKolGjRnr44YfzLWvdurXuu+8+SdLs2bMN1+Uos2bNkiQ9+uijatiwoW25yWTS6NGjFRkZqQsXLujLL78sdP/BgwerY8eO+Zb16dNH//jHP3Tx4sUCU/LYk5GRofnz50v6e/qLy+/G8/X11bPPPqvg4GAdO3ZMP/zwQ4mOsTTmzJmj7Oxs3X777erVq1e+dR06dNCAAQMkKd8UB1fKyMjQ2LFjNWPGDDVr1kwLFy5UREREvm2mT58uq9WqF198Ua1atcq37vIpDubNm1doH456H7Kzs/XBBx9Ikl5++WXdeOONBbaJiYlRWFiY7ee8c+i+++5T27Zt8217zz33qGPHjsrKytKcOXOKVUNxNW7cWGPGjJG3t7dtmdlsVo8ePSRJGzZsKFF7eZ8lbdu2LXC3uZeXl1q3bq1KlSqVsuq/ffnll7p48aIaN26sRx55JN9d09HR0Ro1apQk++dVtWrV9Pzzz5e4nkWLFunkyZNq2LChJk+erICAgHzrg4KCdPPNN9t+3rJli3bs2KHKlSvr5ZdfzvfXGjVq1NBLL70k6e+HMCYmJhboz2Qy6dVXX833GXzttdfa3qNjx47p1Vdfzfeci+joaN1yyy3Kzc21TbtxpZCQEE2cOFE+Pv/3x7gNGjTQo48+Kqnkn60mk0mvvfZavs96Pz8/Pf7445IKnktLlixRQkKCOnbsqDFjxuR7HypXrqyXXnpJNWvW1PLly3X+/Hnbus8++0ySNHr06Hzzbfv4+GjSpEmGrzVFefzxx9W0adN8yx5++GEFBQXpyJEjOnnypG356dOnJUm33HJLgbv5fX19ddNNNxmuw+h5ezUlPadLwxHjoSTnmSdwxDXQWcrCdywAgGciRAcAlBu5ubmSVKw/x2/cuLG8vb319ddfa/78+UpKSnJYHTVr1sw33UZJ9ezZs9Dlef8Q3bp1a6Hz97pKYmKiEhISJEm9e/cusN5kMqlPnz6SZHcO0SuD2zx5AdGV85jbExcXp9TUVFWrVq3QOW8rV66sO+6446q1OENeiFfY6yPJNkXJli1bCn0vz549q2HDhmnFihXq0qWLPvvsM9WoUSPfNmfOnNHOnTvl7+9v9/XMmzpl27Ztha531Puwe/dunTlzRtWrV883xYM92dnZtpqKeo0c/b517Nix0M+Ikh5znujoaEnSjBkztHTp0hJN3VRSxT2vjhw5Uuhx3HTTTYYeEvzLL7/Y2r/8lw9F1XnLLbcUmO5Kkpo0aaKoqCi7gXedOnVkNpsLLK9bt65t/5o1a9pdb+/zvHv37vLz8yuwPO+z1d7rZk+dOnUUFRVVYLm9cylvju3u3bsX2l5AQICaNGmi7Oxs2zMBTp06pb/++kuSbL9EuJyfn5+6detW7JpLorDPh0qVKun666+31ZYnJiZGkjR16lStWrVKly5dclgdRs/bqynpOV0ajhgPJTnPirJo0SJNnDixwP+2bt0qSfr4448LXV+S+ddLew10Jk//jgUA8FzMiQ4AKDfyHlpY2JyiVwoPD9ekSZP0n//8Ry+99JJeeuklXXvttWrWrJluvfVWdevWzfBdb9dee62h/fLYm9s0b3l6errOnTtXaIjkCnn/YK9WrVqhd/FL/zdHrL1/3NepU6fQ5Xnt5T08sCh5YdnVXvOianGGvL7svZd5IVRGRkah7+Vbb72l7OxstWvXTtOmTZOXV8H7Ho4dOyar1ar09HRbkGtPYQ/0lBz3PuQ9aDUiIqJYv8Q6d+6cre2iXiNHv2+X3w1/ubxjvvLhokVp06aNHnzwQc2cOVMTJkyQyWTSDTfcoBYtWqhz587q1KlToe+fEUWdV1WrVrU9G+LUqVOqVatWvvVGP5tOnDghqfhz+RZVp/T3uNy7d2+h76+99yjvDl576/PuJrZ33tqrJzAw8Kqvmz0lPZeOHj0qSXr66af19NNPX7XtM2fOSJLtzuTq1asXuFs6j7Pmwy7J50PPnj3166+/6ptvvtFjjz0mb29v1atXT7GxseratWup7kQv7TW1MCU9p0vDWePB6GfW1q1btWTJErvr169fX+jy3r175/tLiKsp7TXQmTz9OxYAwHMRogMAygWr1ar4+HhJKvQOxsIMGTJE3bt315o1a7R161Zt3bpV3333nb777jtNnz5d8+fPV2hoaIlr8ff3L/E+JWW1Wou9bd4d+p6kJA/vq4i6deum1atXa8OGDVq8eHGhD9fMOweK82A+e8rj+1DU+e6oQPty48eP18CBA/XTTz9p69at2rZtmxYvXqzFixcrOjpac+bMyTeFg7u44rPJEYp6j5zxHuYpyWdrSevIOzft3ZF8OXsBtiuV5Pi8vLw0depUjRo1SmvXrtW2bdu0bds2ffHFF/riiy/UsWNHvf/++4bu+i7NeVuS99NTOfp8f/311/X6668XWD5x4kQtWbJEc+bMyfcAaE/iqu8zZf07FgDAOQjRAQDlws8//2ybQ7Zdu3bF3i84OFj9+/dX//79JUkHDx7Uv/71L/3xxx968803NWXKFKfUezXHjh0rdHne3b5+fn6qVq2abXnePMz2/nw+7447R8m7S/PcuXNKSUkp9G70vDsui3tHp1F5v+TIe20K46paLlerVi0lJCTo6NGjhf5SJ+899vPzK/QvJ9q2bauBAwfq4Ycf1rPPPqvU1FQNHTo03za1a9eW9HcQPnnyZKcGi0XJC/yOHDkiq9VaZDhfrVo1VapUSZmZmTp69GihUxXYe99cfb4X13XXXachQ4ZoyJAhkqSdO3fqqaeeUlxcnGbMmGGbv7g0atWqpUOHDtlemytdvHjRNp2MI8/3sLAwHTx4UIcOHSrWPNF5fdur8/J1rhyX9j5bU1JSbK9b3rhyhrCwMB06dEj9+vUr9hQsea/P2bNndenSpULvRr/a55+r1a9fX/Xr15f0dxD522+/6cknn9RPP/2kpUuXqm/fvg7tr6jPA3uvTUnP6dLw1PHgTEavga74fPf071gAAM/FnOgAgDLv4sWLeu211yT9HT5e/qDLkqpXr54eeOABSbLd2Z4n7x9Szp4rc/ny5YUuX7p0qaS/H4Z6+YPx8v7RXdh8pWlpaXbnlM47nuzs7BLVV7t2bdsUKYsXLy6w3mq12v5U3Nl3s0VHR6tKlSo6d+6cfvzxxwLr09PT9f333zu8lqLOhdatW0uS3T+Z/+qrryRJLVu2zPdeXq5Vq1b69NNPdc011+jVV1/VRx99lG99rVq1FBkZqUuXLtnm93WXJk2aqHr16jpz5oxWr15d5PY+Pj6KjY2VZP81+vrrryUVfN/yfnFS2PmenJys3bt3l6j2ohgdJzExMbYH1V35WWJU3nmV91lwpbzXrG7dug4N42655RZb+8X5/Mur85dffrE9ePVye/bsUXx8vLy8vAo8ENeZVq5cWejUF8uWLZMk3XDDDU4NMdu3by9JWrFiRbH3qV27tm3qi2+//bbA+szMTK1cudIxBTqYyWTSTTfdpLvuuktS/nFgdFxdKe/9OnToUKHr8+ahv1JJz2nJ+HcATx0PzmT0GuiK7zOe/h0LAOC5CNEBAGWW1WrVzz//rH79+unIkSMKCQnRyy+/XKx9N27cqJ9//llZWVkF2ly7dq2kgn9On/cPqT///LP0xV/F7t279cknn+RbtmXLFn3++eeSpOHDh+dblzfX7Oeff55vPtXU1FQ999xzOnnyZKH95N1xWZKHheW5//77JUkffPCB9u7da1tutVr1wQcfKD4+XlWrVrXd4e8sfn5+GjRokCRpypQp+e46zMrK0quvvqrk5GRdd911hqc8KUxR58LQoUPl4+Oj1atX2wK6POvXr9fChQsl/d/raE9MTIzmzJmjkJAQvf3225o6dWq+9WPGjJEkTZo0SWvWrCmwv9Vq1Y4dO+zOcesoPj4+GjVqlCTpueee0++//15gm507d9rmd5akESNGSJK++OILbdy4Md+2ixcv1po1a+Tr61vgDvy8u0ZnzJihCxcu2JafOXNGEyZMUGpqqmMO6v8rapz873//0++//17gT/qzsrJsv9xw1JzO/fv3V2BgoHbv3q2PPvoo35QDe/bs0YcffihJGjlypEP6y3PPPfeodu3a2rNnj+0vIy6XkpKiDRs22H5u2bKlmjZtqvT0dD3//PNKS0uzrTtz5oyef/55SdIdd9xhd75nZ0hKStKUKVPyhaAHDx7UBx98IEkaNmyYU/vv37+/rr32Wq1cuVJvvPGGUlJSCmyTnJysL7/8Mt+yvLqmT5+e7zzMycnRlClTHPpgbKOWLl2qXbt2FViekpJie8jk5eOgRo0a8vX1lcViKdXDeGNiYhQYGKgDBw4U+OXSihUrNHfu3EL3K+k5LRn/DuCp48GZjF4DXfF9pix8xwIAeCamcwEAlAmLFi2y/UM8MzNTZ8+e1Z49e2z/+G7durUmT55c7LBq3759eu211xQYGKhGjRopNDRUGRkZ2rNnj44fP66goCA98cQT+fbp2rWrNm3apKeeekrt2rVT1apVJf0dWDny4WRDhgzRW2+9pWXLlikyMlJJSUnasmWLcnNzNXToUHXo0CHf9t27d9dnn32mXbt26c4771RsbKxyc3O1a9cu+fr6qm/fvrY7VC/XtGlThYaGas+ePerdu7fMZrN8fHwUERFhuxvfnoEDB+qPP/7QsmXL1LdvX7Vq1Uo1a9bU7t27dfjwYfn7+2vq1KmqUaOGw14Xex5//HHt2rVLGzdu1B133KE2bdooICBA27dv14kTJ1StWjVNmzbN8INiC1PUuRAZGannn39eL7zwgp5++ml99tlnioiI0IkTJ/THH3/IarXqscceK9bUQ5GRkZo/f76GDx+uTz75RJcuXdLzzz8vk8mkTp066V//+pemTJmiRx55RDfccIMiIiIUGBios2fPau/evTp9+rQefPDBEk1zZMSwYcN0+PBhLViwQIMHD1ajRo0UERGhlJQU2xQkc+bMsQULHTp00COPPKIPP/xQI0aMUIsWLRQWFqbDhw9r9+7d8vb21gsvvKAGDRrk62fQoEFatGiRdu/erW7duqlZs2ZKS0tTXFycwsLCdNtttxXrbvjiKmqcbN68WXPmzFH16tXVqFEj1ahRQ5cuXdKOHTt0+vRp1apVq8jxVFzBwcGaOnWqnnjiCb399ttatmyZGjVqpNOnT+v3339Xdna2+vTp4/BfXgUEBOjDDz/UQw89pMWLF2v16tVq0aKFqlSpopMnTyo+Pl4xMTH5psV48803NWzYMP3444/q3LmzWrZsqezsbG3atEkpKSlq3LixLTx0lYEDB2rRokVau3atmjZtqvPnz2vTpk3KysrS7bffbvvLAWepUqWK/vvf/+rhhx/WjBkz9OWXXyoyMlK1atVSenq6jhw5ooMHD6pmzZr53sNBgwbp119/1U8//aSePXuqTZs2uuaaa7Rjxw4lJyfr3nvv1RdffOHU2ouyatUqTZgwQaGhoWrYsKGqVq2qCxcuaNu2bbp48aLMZrPuuece2/a+vr7q1KmTfvjhB/Xq1UuxsbG2uc9fffXVYvfr7++vxx57TK+99pomTJigBQsWKDQ0VIcOHdKBAwf0yCOP2H5Jcjkj53TXrl21ePFivfHGG9q4caNq1Kghk8mkvn37qkWLFlet0xPHgzMZvQa64vtMWfiOBQDwTIToAIAyIe8hZdLfQURgYKDMZrOaNGmi7t27KyYmpkTtderUSSkpKdqyZYv++usv7dixQ/7+/qpdu7YeeughDRo0qMDcuPfee68uXbqk5cuX6+eff1ZGRoYkqUePHg4N0W+//XZ17txZ//3vf213yzdq1EiDBw9W7969C2zv6+ur2bNna9q0aVq9erV+/fVX1ahRQ7fffrueeOIJ291VV6pUqZJmzpypt99+W9u3b9fevXuVm5ur1q1bF/kPPJPJpP/85z9q3769Fi5cqN27dystLU3BwcHq06ePHnzwQYe+JldTqVIlWyC1bNkybdmyRZmZmQoLC9OQIUP04IMPOnyKhuKcCwMGDFBUVJRmzpypbdu2ad++fQoMDFSHDh00dOhQtW3bttj93XDDDfr88881fPhwff7550pNTdXkyZPl7e2toUOH6sYbb9S8efO0adMmbdy4UV5eXgoODlbDhg116623qkuXLg49/sKYTCa9+OKL6ty5sxYsWKAdO3bozz//VFBQkK677jr16tVLkZGR+fYZM2aMWrRooXnz5mnHjh3asWOHqlevrm7dumnkyJGFjuuqVavqiy++0FtvvaVffvlF69atU61atdS/f389+uijxf5rlOIqapz06dNH/v7+2rp1qw4cOKAzZ84oKChIYWFhGjZsmPr376/q1as7rJ6OHTtqyZIl+uSTT7Rx40b98MMPqly5smJjYzVw4EDdcccdDuvrco0aNdLy5cs1Z84c/fjjj9q8ebNyc3MVEhKiTp06qU+fPvm2v/7667V48WLNmjVLq1ev1tq1a+Xl5aWIiAh1795dQ4cOdfmDTps2baoBAwbo3Xff1a+//qrU1FTVrVtX/fr10+DBg13yoN0GDRpo+fLlWrBggVavXq19+/Zp+/btqlatmmrXrq37779ft99+e759vLy89N5772nu3Ln66quvtHnzZlWpUkWxsbF6//33tWfPHreH6Pfff7+uu+46/fHHH7ZfcFerVk3169fXXXfdpT59+hR4uO5LL72katWq6ZdfftEPP/xg+8uwkoTo0t93DlerVk1z5szRnj179Oeff6pJkyZ65plnFB4eXmiILpX8nL711lv1yiuv6IsvvtBvv/1mu6M8Nja2yBDdE8eDsxm5Brri+0xZ+I4FAPBMJmt5eGQ5AAAAAABAIYYMGWL7yyFnP68FAFA+MSc6AAAAAAAAAAB2EKIDAAAAAAAAAGAHIToAAAAAAAAAAHYwJzoAAAAAAAAAAHZwJzoAAAAAAAAAAHYQogMAAAAAAAAAYIePuwtwt9zcXGVnZ8vLy0smk8nd5QAAAAAAAAAAXMBqtSo3N1c+Pj7y8rJ/v3mFD9Gzs7MVFxfn7jIAAAAAAAAAAG4QHR2tSpUq2V1f4UP0vN8wREdHy9vb283VwNPl5OQoLi6O8wUwgPEDGMf4AYxj/ADGMX4A4xg/gHGuHD95fV3tLnSJEN02hYu3tzcfaig2zhfAOMYPYBzjBzCO8QMYx/gBjGP8AMa5cvwUNc03DxYFAAAAAAAAAMAOQnQAAAAAAAAAAOwgRAcAAAAAAAAAwA5CdAAAAAAAAAAA7CBEBwAAAAAAAADADkJ0AAAAAAAAAADsIEQHAAAAAAAAAMAOQnQAAAAAAAAAAOwgRAcAAAAAAAAAwA5CdAAAAAAAAAAA7CBEBwAAAAAAAADADkJ0AAAAAAAAAADsIEQHAAAAAAAAAMAOQnQAAAAAAAAAAOwgRAcAAAAAAAAAwA5CdAAAAAAAAAAA7CBEBwAAAAAAAADADkJ0AAAAAAAAAADsIEQHAAAAAAAAAMAOQnQAAAAAAAAAAOzwcXcBAADAvoSEBFksFqf3ExwcrPDwcKf3AwAAAABAWUOIDgCAh0pISFBkVEOlp6U6vS//ylW0b288QToAAAAAAFcgRAcAwENZLBalp6UqYsRU+YfVd1o/6ScP6PDs8bJYLIToAAAAAABcgRAdAAAP5x9WXwHhjd1dBgAAAAAAFRIPFgUAAAAAAAAAwA5CdAAAAAAAAAAA7CBEBwAAAAAAAADADuZEBwDAgISEBFksFqf2ER8f79T2AQAAAABA0QjRAQAooYSEBEVGNVR6Wqq7SwEAAAAAAE5GiA4AQAlZLBalp6UqYsRU+YfVd1o/5+PW6sQ37zitfQAAAAAAUDRCdAAADPIPq6+A8MZOaz8t8aDT2gYAAAAAAMXDg0UBAAAAAAAAALCDEB0AAAAAAAAAADsI0QEAAAAAAAAAsIMQHQAAAAAAAAAAOwjRAQAAAAAAAACwgxAdAAAAAAAAAAA7PDZE3717t0aNGqXWrVuradOmuuuuuzRnzpx822zbtk333nuvmjZtqrZt2+qVV17RpUuX3FQxAAAAAAAAAKC88XF3AYVZv369Ro0apUaNGumf//ynqlSpooSEBCUmJtq2iY+P1/Dhw1WvXj1NnDhRiYmJmjVrlo4cOaIZM2a4sXoAAAAAAAAAQHnhcSF6SkqKJkyYoFtvvVXvvvuuvLwKv1n+rbfeUtWqVTV37lwFBgZKkq677jo9++yzWr9+vdq1a+fKsgEAAAAAAAAA5ZDHTefyzTffyGKxaOzYsfLy8lJqaqpyc3PzbZOSkqINGzaoR48etgBdknr27KkqVapoxYoVri4bAAAAAAAAAFAOeVyIvnHjRgUGBurUqVPq2rWrmjdvrtjYWP373/9WRkaGJGnfvn3Kzs5WkyZN8u1bqVIlNWzYUPHx8e4oHQAAAAAAAABQznjcdC5HjhxRTk6O/vnPf6pfv3568skntXnzZs2dO1cXL17UW2+9peTkZElSaGhogf1DQkK0devWEvebk5NT6tpR/uWdJ5wvQMmVp/FTHo6hMLt373bqsQUHBys8PNxp7Zdn5Wn8AK7G+AGMY/wAxjF+AONcOX6K24fHheipqalKS0vTwIED9eyzz0qSunTposzMTC1cuFCPP/640tPTJf195/mV/Pz8bOtLIi4urnSFo0LhfAGMKw/jZ//+/e4uwaGyzidLJi8NHTrUqf34+fvr66++Uu3atZ3aT3lWHsYP4C6MH8A4xg9gHOMHMM6Txo/Hhej+/v6SpLvuuivf8rvvvlsLFy7U9u3bbdtkZmYW2D8jI8O2viSio6Pl7e1toGJUJDk5OYqLi+N8AQwoT+Pnymd1lHXZaRcka64iRkyVf1h9p/SRfvKADs8er9DQUDVr1swpfZRn5Wn8AK7G+AGMY/wAxjF+AONcOX7y+iqKx4XooaGh+vPPP1WzZs18y2vUqCFJOn/+vK6//npJUlJSUoH9k5OTC53mpSje3t58qKHYOF8A48rD+Cnr9dvjH1ZfAeGNndpHeXj/3YnXDzCO8QMYx/gBjGP8AMZ50vjxuAeLNm789z/eT506lW95XmBeo0YNmc1m+fj4aNeuXfm2yczMVHx8vKKiolxTLAAAAAAAAACgXPO4EL179+6SpK+++irf8q+++ko+Pj5q3bq1goKCdNNNN2n58uVKSUmxbbNs2TKlpqaqW7duLq0ZAAAAAAAAAFA+edx0Lo0aNVLfvn319ddfKycnR61atdLmzZu1cuVKPfzww6pVq5YkaezYsRo4cKCGDBmi/v37KzExUbNnz1a7du3Uvn17Nx8FAAAAAAAAAKA88LgQXZJefPFF1alTR4sXL9bq1atVp04dTZo0ScOHD7dt07hxY82ePVtTp07Va6+9poCAAPXr10/jxo1zX+EAAAAAAAAAgHLFI0N0X19fjR49WqNHj77qdi1bttSCBQtcVBUAAAAAAAAAoKLxuDnRAQAAAAAAAADwFIToAAAAAAAAAADYQYgOAAAAAAAAAIAdhOgAAAAAAAAAANhBiA4AAAAAAAAAgB2E6AAAAAAAAAAA2EGIDgAAAAAAAACAHYToAAAAAAAAAADYQYgOAAAAAAAAAIAdhOgAAAAAAAAAANhBiA4AAAAAAAAAgB2E6AAAAAAAAAAA2EGIDgAAAAAAAACAHYToAAAAAAAAAADYQYgOAAAAAAAAAIAdhOgAAAAAAAAAANhBiA4AAAAAAAAAgB2E6AAAAAAAAAAA2EGIDgAAAAAAAACAHYToAAAAAAAAAADYQYgOAAAAAAAAAIAdhOgAAAAAAAAAANhBiA4AAAAAAAAAgB2E6AAAAAAAAAAA2EGIDgAAAAAAAACAHYToAAAAAAAAAADYQYgOAAAAAAAAAIAdhOgAAAAAAAAAANjh4+4CAADul5CQIIvF4tQ+cnJylJSU5NQ+4Pni4+Od3kdwcLDCw8Od3g8AAAAAoGIgRAeACi4hIUGRUQ2Vnpbq9L78/P0Vv2ePIiIinN4XPEvW+WTJ5KXBgwc7vS//ylW0b288QToAAAAAwCEI0QGggrNYLEpPS1XEiKnyD6vvtH7STx7Q4dnjZbFYCNEroOy0C5I116XnGSE6AAAAAMARCNEBAJIk/7D6Cghv7O4yUM5xngEAAAAAyhoeLAoAAAAAAAAAgB2E6AAAAAAAAAAA2EGIDgAAAAAAAACAHYToAAAAAAAAAADYQYgOAAAAAAAAAIAdhOgAAAAAAAAAANhBiA4AAAAAAAAAgB2E6AAAAAAAAAAA2EGIDgAAAAAAAACAHYToAAAAAAAAAADYQYgOAAAAAAAAAIAdhOgAAAAAAAAAANhBiA4AAAAAAAAAgB2E6AAAAAAAAAAA2EGIDgAAAAAAAACAHYToAAAAAAAAAADYQYgOAAAAAAAAAIAdhOgAAAAAAAAAANhBiA4AAAAAAAAAgB2E6AAAAAAAAAAA2EGIDgAAAAAAAACAHYToAAAAAAAAAADYQYgOAAAAAAAAAIAdhOgAAAAAAAAAANhBiA4AAAAAAAAAgB2E6AAAAAAAAAAA2EGIDgAAAAAAAACAHYToAAAAAAAAAADYQYgOAAAAAAAAAIAdPu4u4EqbNm3S0KFDC123cOFCNWvWzPbztm3b9MYbb2jPnj0KDAxU9+7dNXbsWAUEBLioWgAAAAAAAABAeeZxIXqeIUOGKDo6Ot+y8PBw23/Hx8dr+PDhqlevniZOnKjExETNmjVLR44c0YwZM1xdLgAAAAAAAACgHPLYEL1ly5bq1q2b3fVvvfWWqlatqrlz5yowMFCSdN111+nZZ5/V+vXr1a5dO1eVCgAAAAAAAAAopzx6TvSUlBRlZ2cXunzDhg3q0aOHLUCXpJ49e6pKlSpasWKFK8sEAAAAAAAAAJRTHnsn+qRJk5Samipvb2/Fxsbq6aeftk3vsm/fPmVnZ6tJkyb59qlUqZIaNmyo+Ph4d5QMAAAAAAAAAChnPC5E9/X1VdeuXdW+fXtVr15dBw8e1MyZMzVo0CAtWLBAjRo1UnJysiQpNDS0wP4hISHaunVrifvNyckpde0o//LOE84XJCQkyGKxOL2f4ODgfM+DcAZXn8+5ublO7dMV783evXud2j5KLycnp1x9VnP9AYxj/ADGMX4A4xg/gHGuHD/F7cPjQvQWLVqoRYsWtp87d+6srl27qkePHnrzzTc1c+ZMpaenS/r7zvMr+fn52daXRFxcnPGiUeFwvlRsiYmJ6tuvnzIMfNaUlJ+/v77+6ivVrl3baX3s37/faW0X5sCBA/Lxcc7lx5XvDTzb/v375eXl0bPWGcL1BzCO8QMYx/gBjGP8AMZ50vjxuBC9MDfccIM6d+6sVatWKScnR/7+/pKkzMzMAttmZGTY1pdEdHS0vL29S10ryrecnBzFxcVxvlRw27ZtU0Z6uiJGTJV/WH2n9ZN+8oAOzx6v0NBQNWvWzGn95ObmOq3twtSvX99px+Oq9+Z83Fqd+OYdp7WP0jObzU4dN67G9QcwjvEDGMf4AYxj/ADGuXL85PVVlDIRoktS7dq1lZWVpbS0NIWEhEiSkpKSCmyXnJxc6DQvRfH29uZDDcXG+VKx5b33/mH1FRDe2CX9OfN8c/W57OXl5bQ+XfXepCUedFrbcIzy+jldXo8LcAXGD2Ac4wcwjvEDGOdJ46fM/J3zsWPH5OfnpypVqshsNsvHx0e7du3Kt01mZqbi4+MVFRXlpioBAAAAAAAAAOWJx4XoZ86cKbBs7969WrNmjdq2bSsvLy8FBQXppptu0vLly5WSkmLbbtmyZUpNTVW3bt1cWTIAAAAAAAAAoJzyuOlcxowZI39/fzVv3lw1a9bUgQMH9OWXX8rf31/jx4+3bTd27FgNHDhQQ4YMUf/+/ZWYmKjZs2erXbt2at++vRuPAAAAAAAAAABQXnhciH7bbbfpm2++0aeffqqUlBRVr15dt99+u0aPHq0bbrjBtl3jxo01e/ZsTZ06Va+99poCAgLUr18/jRs3zo3VA/AECQkJslgsTms/Pj7eaW0DAAAAAADAs3hciD506FANHTq0WNu2bNlSCxYscHJFAMqShIQERUY1VHpaqrtLAQAAAAAAQDngcSE6AJSGxWJRelqqIkZMlX9Yfaf0cT5urU58845T2gYAAAAAAIBnIUQHUC75h9VXQHhjp7SdlnjQKe0CAAAAAADA83i5uwAAAAAAAAAAADwVIToAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdhCiAwAAAAAAAABgByE6AAAAAAAAAAB2EKIDAAAAAAAAAGAHIToAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdhCiAwAAAAAAAABgh4+7CwDgfgkJCbJYLE7vJzg4WOHh4U7vBwAAAAAAAHAUQnSggktISFBkVEOlp6U6vS//ylW0b288QToAAAAAAADKDEJ0oIKzWCxKT0tVxIip8g+r77R+0k8e0OHZ42WxWAjRAQAAAAAAUGYQogOQJPmH1VdAeGN3lwEAAAAAAAB4FB4sCgAAAAAAAACAHYbvRM/NzZWXV/4M/o8//tDatWtVqVIl9e3bV7Vr1y51gQAAAAAAAAAAuIuhO9EnT56spk2b6sKFC7ZlK1eu1KBBg/Tf//5X06dPV+/evZWYmOiwQgEAAAAAAAAAcDVDIfqmTZt04403qmrVqrZl7777roKCgjRlyhQ99dRTunDhgmbOnOmwQgEAAAAAAAAAcDVD07kkJiaqVatWtp+PHj2qQ4cOafTo0erZs6ckacuWLfrll18cUyUAVGDx8fFlun0AAAAAAICyzFCInpqaqipVqth+/v3332UymdS+fXvbsvr16+u3334rfYUAUEFlnU+WTF4aPHiwu0sBAAAAAACosAyF6KGhoTp8+LDt519++UVVqlRR48aNbctSUlJUqVKl0lcIABVUdtoFyZqriBFT5R9W32n9nI9bqxPfvOO09gEAAAAAAMoyQyF669at9e2332revHny8/PT//73P3Xu3Fne3t62bRISElSrVi2HFQoAFZV/WH0FhDcuekOD0hIPOq1tAAAAAACAss5QiD5q1CitXr1ar776qqxWqypXrqzHHnvMtj4lJUVbtmxR7969HVYoAAAAAAAAAACuZihEv+GGG/Tdd99p1apVkqSOHTvq2muvta3/66+/NGDAAN11112OqRIAAAAAAAAAADcwFKJLf8+Lbu9hd40bN843PzoAAAAAAAAAAGWR4RA9z4EDB3To0CGlpqaqV69eDigJAFCe7d27N98zNBwpPj7eKe0CAAAAAICKy3CIvnPnTj333HPav3+/bVleiP7777/rgQce0FtvvaXOnTuXukgAQNmXdT5ZMnlp6NCh7i4FAAAAAACg2AyF6H/++aeGDRsmLy8vDR8+XIcOHdK6dets61u2bKnq1atr5cqVhOgAAElSdtoFyZqriBFT5R9W3yl9nI9bqxPfvOOUtgEAAAAAQMVkKESfPn26JGnx4sW64YYb9N577+UL0U0mk5o1a6a4uDjHVAkAKDf8w+orINw5z81ISzzolHYBAAAAAEDF5WVkp82bN6tr16664YYb7G4TFham5ORkw4UBAAAAAAAAAOBuhkL0S5cuqUaNGlfdJiMjQ7m5uYaKAgAAAAAAAADAExgK0cPCwvI9ULQwe/bs0fXXX2+oKAAAAAAAAAAAPIGhEP3WW2/Vr7/+qg0bNhS6/vvvv9f27dt12223lao4AAAAAAAAAADcydCDRUeNGqUffvhBDz30kHr16iWLxSJJmj9/vrZv367vvvtO1157rUaMGOHQYgEAAAAAAAAAcCVDIXqNGjU0b948PfXUU/rqq69sy19++WVJUtOmTfXmm28qKCjIMVUCAAAAAAAAAOAGhkJ0Sbr++uu1YMECxcfHa/v27Tp//rwCAwMVExOjmJgYR9YIAAAAAAAAAIBbGA7R8zRs2FANGzZ0RC0AAAAAAAAAAHgUQw8WBQAAAAAAAACgIijWnejvvfeeocZNJpMeffRRQ/sCAAAAAAAAAOBuhOgAAAAAAAAAANhRrBB9zpw5zq4DAAAAAAAAAACPU6wQvXXr1s6uAwAAAAAAAAAAj8ODRQEAAAAAAAAAsKNYd6Lbs3v3bi1ZskTx8fG6ePGigoKC1KhRI/Xq1UuNGzd2VI0AAAAAAAAAALiF4RB9ypQp+uyzz5Sbm5tv+datWzV//nwNHz5cTz/9dKkLBAAAAAAAAADAXQyF6PPmzdPs2bMVERGhRx55RC1btlRwcLAsFot+//13ffjhh5o9e7auvfZaDRo0yNE1AwAAAAAAAADgEobmRP/8888VFhamRYsWqUePHqpTp44qVaqkOnXqqGfPnlq0aJFq1aql+fPnO7peAAAAAAAAAABcxlCIfuzYMXXp0kWBgYGFrg8KClKXLl107NixUhUHAAAAAAAAAIA7GQrRa9asWaztgoODjTQPAAAAAAAAAIBHMBSi33nnnVq1apUuXbpU6PqUlBStWrVKd955Z6mKAwAAAAAAAADAnQyF6I8//riioqJ0zz336LvvvlNiYqKysrKUmJiob7/9Vv3791ejRo302GOPObpeAAAAAAAAAABcxsfITk2bNpUkWa1WjR8/vsB6q9Wqw4cP27bLYzKZtGfPHiNdAgAAAAAAAADgcoZC9JYtWzq6DgAAAAAAAAAAPI6hEH3u3LmOrgMAAAAAAAAAAI9jaE50AAAAAAAAAAAqAkN3ogMAAHiy+Ph4p/cRHBys8PBwp/cDAAAAAHAvwyH60aNHNWfOHO3du1dJSUnKzs4usI3JZNLq1atLVSAAAEBxZZ1PlkxeGjx4sNP78q9cRfv2xhOkAwAAAEA5ZyhEX7dunR599FFlZWXJx8dHNWvWlLe3d4HtrFZrqQv88MMP9c4776hBgwb69ttv863btm2b3njjDe3Zs0eBgYHq3r27xo4dq4CAgFL3CwAAyp7stAuSNVcRI6bKP6y+0/pJP3lAh2ePl8ViIUQHAAAAgHLOUIg+depUeXt76z//+Y+6du0qLy/nTK2emJio//73v6pSpUqBdfHx8Ro+fLjq1auniRMnKjExUbNmzdKRI0c0Y8YMp9QDAADKBv+w+goIb+zuMgAAAAAA5YChEP3IkSPq0aOHunfv7uh68pkyZYqaNm2q3NxcnT17Nt+6t956S1WrVtXcuXMVGBgoSbruuuv07LPPav369WrXrp1TawMAAAAAAAAAlH+GbiEPDg6Wn5+fo2vJ5/fff9cPP/ygZ555psC6lJQUbdiwQT169LAF6JLUs2dPValSRStWrHBqbQAAAAAAAACAisFQiH733Xdr3bp1ysjIcHQ9kqScnBy9/PLL6tevnyIjIwus37dvn7Kzs9WkSZN8yytVqqSGDRsqPj7eKXUBAAAAAAAAACoWQ9O5jB49Wnv37tXIkSM1duxYRUVFOfRhngsWLNCJEyf06aefFro+OTlZkhQaGlpgXUhIiLZu3VriPnNyckq8DyqevPOkPJ0vrj6WnJwcp/ZZnt4bAJ7P2Z9pl/dz+f8DKD7GD2Ac4wcwjvEDGOfK8VPcPgyF6L6+vhoyZIjGjRunwYMH293OZDJpz549JWr77Nmzevfdd/XPf/5TNWrUKHSb9PR0SX/feX4lPz8/2/qSiIuLK/E+qLjK0/myf/9+l/fnrIcR57UPAK7i7M+0K5Wn6w/gaowfwDjGD2Ac4wcwzpPGj6EQ/fvvv9f48eOVm5ur66+/XiEhIfL29nZIQe+8846uueaaq4bz/v7+kqTMzMwC6zIyMmzrSyI6Otphx4DyKycnR3FxceXqfMnNzXVpf2azWc2aNXNa+64+HgAVm7M/0/KUx+sP4CqMH8A4xg9gHOMHMM6V4yevr6IYCtHff/99BQUF6ZNPPlFMTIyRJgp15MgRffnll3rmmWeUlJRkW56RkaGsrCwdO3ZMgYGBCgkJkaR82+RJTk4udJqXonh7e/OhhmIrT+eLq4/D2a9deXlfAJQNrr4elKfrD+BqjB/AOMYPYBzjBzDOk8aPob8/PnbsmO644w6HBuiSdOrUKeXm5uqVV15R586dbf/bsWOHjhw5os6dO+v999+X2WyWj4+Pdu3alW//zMxMxcfHKyoqyqF1AQAAAAAAAAAqJkN3oteuXdspE7s3aNBA77//foHl77zzji5duqR//etfuv766xUUFKSbbrpJy5cv1z//+U8FBgZKkpYtW6bU1FR169bN4bUBAAAAAAAAACoeQyF6//799emnn+rcuXOqVq2aw4qpUaOGbrvttgLLP/vsM0nKt27s2LEaOHCghgwZov79+ysxMVGzZ89Wu3bt1L59e4fVBAAAAAAAAACouAyF6F27dtW2bdt077336pFHHlFUVJTtbvAr1alTp1QF2tO4cWPNnj1bU6dO1WuvvaaAgAD169dP48aNc0p/AAAAAAAAAICKx1CIftttt8lkMslqtWrChAl2tzOZTNqzZ4/h4vLMnTu30OUtW7bUggULSt0+4MkSEhJksVic1n58fLzT2gYAlE7eNSAnJ0f79+9Xbm6uUx6sExwcrPDwcIe3CwAAAADlgaEQvVevXjKZTI6uBcAVEhISFBnVUOlpqe4uBQDgYq68BvhXrqJ9e+MJ0gEAAACgEIZC9Ndff93RdQAohMViUXpaqiJGTJV/WH2n9HE+bq1OfPOOU9oGABjnimuAJKWfPKDDs8fLYrEQogMAAABAIQyF6ABcyz+svgLCGzul7bTEg05pFwDgGM68BgAAAAAAiubl7gIAAAAAAAAAAPBUhu9ET0lJ0fz587VhwwYlJSUpMzOzwDYmk0mrV68uVYEAAAAAAAAAALiLoRD9zJkzGjhwoBISEhQYGKiUlBQFBQUpKytL6enpkqTQ0FD5+DBbDAAAAAAAAACg7DKUck+fPl0JCQmaMmWKevTooYYNG2rYsGEaPXq0du7cqVdeeUXe3t6aNWuWo+sFUMbFx8eX6fYBAAAAAABQsRgK0X/++WfddNNN6tmzZ4F1MTEx+uSTT3T33Xfrvffe01NPPVXqIgGUfVnnkyWTlwYPHuzuUgAAAAAAAIBiMxSiJycnq1u3brafvb29lZGRYfv5mmuuUfv27bVixQpCdACSpOy0C5I1VxEjpso/rL7T+jkft1YnvnnHae0DAAAAAACgYjEUogcFBSk7O9v2c9WqVZWYmJhvm8DAQJ0+fbp01QEod/zD6isgvLHT2k9LPOi0tgEAAAAAAFDxeBnZ6frrr9fx48dtPzdq1EgbNmzQ2bNnJUnp6en66aefFBYW5pgqAQAAAAAAAABwA0Mhetu2bbVx40alpaVJkgYMGKDTp0+rZ8+eevzxx3XXXXcpISFBffr0cWixAAAAAAAAAAC4kqEQfeDAgXrllVdsIXqXLl309NNPKy0tTatWrZLFYtHw4cM1cuRIhxYLAAAAAAAAAIArGZoTPTQ0VHfccUe+Zffff7+GDRums2fPqmbNmjKZTA4pEAAAAAAAAAAAdzF0J7o93t7eCg4OtgXoubm5jmweAAAAAAAAAACXMhSiv/jii8rMzLzqNseOHdN9991nqCgAAAAAAAAAADyBoRD9iy++UN++ffXnn38Wuv67775T7969tXPnzlIVBwAAAAAAAACAOxkK0ceNG6fDhw+rX79+mj9/vm15amqqJk6cqPHjx8vPz08zZsxwWKEAAAAAAAAAALiaoRD9oYce0ueff67Q0FC98sorGjVqlH755Rf17t1bS5cuVYcOHbR8+XLdfPPNjq4XAAAAAAAAAACX8TG6Y0xMjJYuXaoXX3xRy5cv188//yw/Pz8999xzGjRokCNrBAAAAAAAAADALQzdiZ7n0qVLSkxMlCRZrVZ5eXmpcuXKDikMAAAAAAAAAAB3Mxyi//jjj+rRo4c2b96sgQMHaubMmbrmmmv0r3/9S+PGjVNKSooj6wQAAAAAAAAAwOUMhegvvPCCRo8eLUl6//339cILL6ht27Zavny5unTpou+//149evTQ1q1bHVosAAAAAAAAAACuZChEX7Bggdq0aaNly5apc+fOtuVBQUGaNm2aXn75ZZ09e1bDhg1zWKEAAAAAAAAAALiaoRB93Lhxmj17tmrVqlXo+nvuuUeLFy+W2WwuVXEAAAAAAAAAALiTj5GdHnrooSK3iYiI0MKFC400DwAAAAAAAACARzAUoudJTk7WqlWrdPjwYaWlpenVV1+VJJ05c0bHjh2T2WyWr6+vQwoFAAAAAAAAAMDVDE3nIknz589X586d9fLLL2vevHlavHixbd3p06c1YMAALV++3CFFAgAAAAAAAADgDoZC9DVr1ujll1+W2WzWhx9+qHvvvTff+gYNGigyMlKrV692SJEAAAAAAAAAALiDoelcZs6cqTp16mjOnDmqUqWKdu/eXWAbs9msLVu2lLpAAAAAAAAAAADcxdCd6PHx8erQoYOqVKlid5tatWrp9OnThgsDAAAAAAAAAMDdDIXoVqtVPj5Xv4n99OnTqlSpkqGiAAAAAAAAAADwBIZC9IiICG3dutXu+uzsbG3ZskVms9lwYQAAAAAAAAAAuJuhEP3uu+/Wnj179N577xVYl5OToylTpujo0aPq1atXaesDAAAAAAAAAMBtDD1YdPDgwVqzZo3ef/99ffPNN7ZpW5544gnt2rVLx48fV9u2bdWvXz+HFgsAAAAAAAAAgCsZuhPd19dXM2fO1EMPPaRz587pzz//lNVq1Q8//KDz58/rwQcf1IcffiiTyeToegEAAAAAAAAAcBlDd6JLUqVKlTR27FiNGTNGhw4d0vnz5xUYGKh69erJ29vbkTUCAAAAAAAAAOAWhkP0PCaTSfXq1XNELQAAAAAAAAAAeBRD07kAAAAAAAAAAFAREKIDAAAAAAAAAGAHIToAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdhQrRB89erS+//5728+///67Tpw44bSiAAAAAAAAAADwBMUK0VevXq1Dhw7Zfh46dKgWL17stKIAAAAAAAAAAPAExQrRq1atqkuXLtl+tlqtTisIAAAAAAAAAABP4VOcjerVq6dvv/1W0dHRCgkJkSQdP35cv//+e5H7tmrVqnQVAgAAAAAAAADgJsUK0R999FE9+uijevLJJ23Lli5dqqVLlxa5b3x8vOHiAAAAAAAAAABwp2KF6O3atdP333+vDRs26NSpU3rvvffUqlUrtW7d2tn1AQAAAAAAAADgNsUK0SXp2muv1T333CNJeu+999S6dWuNHj3aaYUBAAAAAAAAAOBuxQ7RL/fjjz+qatWqjq4FAAAAAAAAAACPYihEv/baa23/nZ2drcOHDyslJUWBgYGKiIiQj4+hZgEAAAAAAAAA8CiG0+5z585p6tSp+vbbb5WRkWFb7u/vr7vuukvjxo1T9erVHVIkAAAAAAAAAADuYChEP3funAYMGKC//vpL11xzjWJjYxUaGqrk5GTt2rVLixYt0ubNm7Vw4UJVq1bNwSUDAAAAAAAAAOAahkL0Dz74QH/99ZdGjhypRx99VFWqVLGtS0tL0wcffKBPPvlEH330kSZOnOiwYgEAAAAAAAAAcCUvIzv9+OOPat26tZ566ql8AbokVa5cWU8++aRat26t//3vfw4pEgAAAAAAAAAAdzAUoiclJal58+ZX3aZ58+ZKSkoyVBQAAAAAAAAAAJ7AUIgeFBSk48ePX3Wb48ePKygoyFBRAAAAAAAAAAB4AkMheqtWrbRy5Upt2LCh0PUbN27UypUr1bp161IVBwAAAAAAAACAOxl6sOjo0aP1888/a+TIkerQoYNatWqlmjVr6vTp09q8ebPWrVsnf39/Pfroo46uFwAAAAAAAAAAlzEUojdo0EAzZszQpEmTtHbtWq1du1Ymk0lWq1WSFB4ertdee00NGjRwaLEAAAAAAAAAALiSoRBdklq2bKlVq1Zp69atio+PV0pKigIDA9WwYUPFxsbKZDIZavfPP//U9OnTtXv3blksFvn7+6t+/foaOXKkOnXqlG/bgwcPavLkydq2bZt8fX3VoUMHTZo0STVq1DB6WAAAAAAAAAAA2BgO0SXJZDKpZcuWatmypaPq0YkTJ3Tp0iX17t1boaGhSktL06pVq/TII4/opZde0oABAyRJiYmJGjRokIKCgjR27FilpqZq1qxZ2r9/vxYtWqRKlSo5rCYAAAAAAAAAQMVUqhDdGTp06KAOHTrkWzZ48GD16dNHs2fPtoXoH330kdLS0rR48WLVqVNHkhQTE6MRI0ZoyZIltu0AAAAAAAAAADDKy90FFIe3t7fCwsJ08eJF27JVq1bp1ltvtQXoknTzzTerbt26WrFihTvKBAAAAAAAAACUMx53J3qe1NRUpaenKyUlRWvWrNG6devUvXt3SdKpU6d0+vRpNWnSpMB+MTExWrdunavLBQAAAAAAAACUQx4bor/++utauHChJMnLy0u33367nn/+eUlSUlKSJCkkJKTAfiEhITp37pwyMzNLNC96Tk6OA6pGeZd3nrjqfOG8BADPlpOT47TPaldfA5x5LIA7ufr7G1CeMH4A4xg/gHGuHD/F7cNjQ/Rhw4apW7duSkpK0ooVK5Sbm6usrCxJUkZGhiQVGpL7+flJktLT00sUosfFxTmgalQUrjpf9u/f75J+AADG7N+/X15ezpkdz9XXAGceC+AJ+L4PGMf4AYxj/ADGedL48dgQvV69eqpXr54kqVevXrr//vs1atQoLVq0yBaUZ2ZmFtgvL2D39/cvUX/R0dHy9vYuZdUo73JychQXF+ey8yU3N9fpfQAAjDObzWrWrJlT2nb1NcCZxwK4k6u/vwHlCeMHMI7xAxjnyvGT11dRDIXoDRs21B133KE333zTyO6GdO3aVc8//7wOHz6s0NBQSVJycnKB7ZKTk1WtWrUS3YUu/f3wUj7UUFyuOl84JwHAsznzeuDqawDfhVDecY4DxjF+AOMYP4BxnjR+DP3NbmBgoMLCwhxdy1Wlp6dLklJSUlSrVi3VqFFDu3btKrDdzp07FRUV5dLaAAAAAAAAAADlk6EQPSYmRnv37nV0LZKk06dPF1iWlZWlZcuWyd/f3zbFS5cuXbR27VqdPHnStt3GjRt15MgRdevWzSm1AQAAAAAAAAAqFkPTuYwePVpDhgzR0qVL1atXL4cW9PzzzyslJUWtWrVSrVq1lJycrG+++UaHDh3SxIkTFRAQIEkaNWqUVq5cqaFDh2ro0KFKTU3VzJkzZTab1bdvX4fWBAAAAAAAAAComAyF6L/++qvatGmjSZMmae7cuYqOjlZwcHCB7Uwmkx599NEStX3HHXfoq6++0hdffKFz584pICBAjRs31vjx49W5c2fbdmFhYZo3b55ef/11vfnmm/L19VWHDh00ceLEEs+HDgAAAAAAAABAYQyF6O+9957tv3fv3q3du3cXup2REP3OO+/UnXfeWaxtGzRooJkzZ5aofQAAAAAAAAAAistQiD5nzhxH1wEAAAAAAAAAgMcxFKK3bt3a0XUAAAAAAAAAAOBxvNxdAAAAAAAAAAAAnspwiJ6dna1PP/1U/fr1U4sWLdSoUSPbuvj4eL3wwgs6fPiwQ4oEAAAAAAAAAMAdDE3nkp6ervvvv19//PGHqlevrsDAQKWlpdnWX3fddVq8eLGuueYajR071mHFAgAAAAAAAADgSobuRP/oo4+0bds2jRs3Tr/++qvuueeefOuDgoLUqlUrrV+/3iFFAgAAAAAAAADgDoZC9BUrVqhNmzZ68MEHZTKZZDKZCmxz/fXX6+TJk6UuEAAAAAAAAAAAdzEUop84cUJNmjS56jYBAQG6ePGioaIAAAAAAAAAAPAEhkL0gIAAnTlz5qrbHD16VDVq1DBUFAAAAAAAAAAAnsBQiN6sWTOtWbNGFy5cKHT9yZMn9fPPP6tly5alKg4AAAAAAAAAAHcyFKKPHDlSFy5c0PDhw7V161ZlZ2dLktLS0rRx40aNHDlSOTk5GjFihEOLBQAAAAAAAADAlXyM7NSqVSs999xzmjx5sgYPHmxb3qJFC0mSt7e3/v3vfxc5bzoAAAAAAAAAAJ7MUIguSffdd5/atGmjL774Qjt37tT58+cVEBCgpk2b6r777lODBg0cWScAAAAAAAAAAC5nOESXpHr16unZZ591VC0AAAAoxxISEmSxWJzeT3BwsMLDw53eDwAAAICKoVQhOgAAAFAcCQkJioxqqPS0VKf35V+5ivbtjSdIBwAAAOAQpQrR//e//2nx4sWKj4/XxYsXFRQUpIYNG6pv37667bbbHFUjAAAAyjiLxaL0tFRFjJgq/7D6Tusn/eQBHZ49XhaLhRAdAAAAgEMYCtGzs7P15JNPatWqVbJarfLx8VG1atVksVj0008/ae3aterSpYvefPNN+fhwszsAAAD+5h9WXwHhjd1dBgAAAAAUm5eRnf773//qhx9+UMuWLTV//nzt3LlT69ev186dOzVv3jzFxsZq1apV+vjjjx1dLwAAAAAAAAAALmMoRF+8eLH+8Y9/aPbs2YqNjZWX19/NeHl5qWXLlpo9e7bq1q2rr7/+2qHFAgAAAAAAAADgSoZC9OTkZHXs2NHuVC2+vr7q2LGjkpOTS1UcAAAAAAAAAADuZChEDwsLU2pq6lW3SUtLU1hYmKGiAAAAAAAAAADwBIZC9H79+mnFihVKSkoqdP2pU6f0/fff65577ilVcQAAAAAAAAAAuFPh87Fc4cSJE/l+7t69u7Zt26bevXtr2LBhatGihYKDg2WxWLR161bNmTNHsbGx6tatm1OKBgAAAAAAAADAFYoVonfq1Ekmk6nAcqvVqrfffrvQ5WvWrNHatWu1Z8+e0lcJAAAAAAAAAIAbFCtE79WrV6EhOgAAAAAAAAAA5VmxQvTXX3/d2XUAAAAAAAAAAOBxDD1YFAAAAAAAAACAioAQHQAAAAAAAAAAO4o1nUthtmzZolmzZmnv3r1KSkpSTk5OgW1MJhMPFgUAAAAAAAAAlFmGQvSlS5dq0qRJslqtuv766xUTEyNvb29H1wYAAAAAAAAAgFsZCtE//PBDVa1aVZ988oliYmIcXRMAAAAAAAAAAB7B0JzoJ0+e1J133kmADgAAAAAAAAAo1wyF6HXq1FFWVpajawEAAAAAAAAAwKMYCtH79++vn376SefOnXNwOQAAAAAAAAAAeA5Dc6Lff//9Onr0qO6991498sgjioqKUmBgYKHb1qlTp1QFAgAAAAAAAADgLoZCdElq1KiRvv32W02YMMHuNiaTSXv27DHaBQAAAAAAAAAAbmUoRJ87d64mT54sHx8ftWnTRiEhIfLxMZzHwwMkJCTIYrE4tY/g4GCFh4c7tQ8AAFwpPj6+TLYNAAAAACg+Q8n3p59+qlq1amnBggWqXbu2o2uCiyUkJCgyqqHS01Kd2o9/5SratzeeIB0AUOZlnU+WTF4aPHiwu0sBAAAAADiZoRDdYrFowIABBOjlhMViUXpaqiJGTJV/WH2n9JF+8oAOzx4vi8VCiA4AKPOy0y5I1lynXjvPx63ViW/ecUrbAAAAAIDiMxSih4eH6+LFi46uBW7mH1ZfAeGN3V0GAABlhjOvnWmJB53SLgAAAACgZLyM7DR8+HD9+OOPOn78uKPrAQAAAAAAAADAYxi+E71Vq1bq27evhg0bpqioKAUGBha6batWrUpVIAAAAAAAAAAA7mIoRB8yZIhMJpOsVqumTZsmk8lkd9v4+HjDxQEAAAAAAAAA4E6GQvRHH330qsE5AAAAAAAAAADlgaEQ/bHHHnN0HQAAAAAAAAAAeBxDDxYFAAAAAAAAAKAiIEQHAAAAAAAAAMAOQ9O5REVFFWtOdJPJpD179hjpAgAAAAAAAAAAtzMUordq1arQ5SkpKTpy5IjS0tIUFRWloKCgUhUHAAAAAAAAAIA7GQrR586da3ddWlqa3nzzTf3yyy+aNWuW4cIAAAAAAAAAAHA3h8+JXrlyZT377LMKDAzUG2+84ejmAQAAAAAAAABwGac9WLRly5Zau3ats5oHAAAAAAAAAMDpnBainzlzRqmpqc5qHgAAAAAAAAAAp3N4iJ6bm6ulS5dqxYoVatiwoaObBwAAAAAAAADAZQw9WLRz586FLs/JydHp06eVnZ0tHx8fjRs3rlTFAQAAAAAAAADgToZCdKvVWnhjPj5q0KCBoqOjNXjwYDVo0KBUxQEAAAAAAAAA4E6GQvQ1a9Y4ug4AAAAAAAAAADyO0x4sCgAAAAAAAABAWWfoTnQAUkJCgiwWi1P7iI+Pd2r7AADkcfY1h2saAAAAgLKq2CH6pEmTSty4yWTS5MmTS7wf4OkSEhLUqHETpaelursUAABKJet8smTy0uDBg91dCgAAAAB4pGKH6EuWLCl2oyaTSVarlRAd5ZbFYlF6WqoiRkyVf1h9p/VzPm6tTnzzjtPaBwAgO+2CZM3lmgYAAAAAdhQ7RF+4cGGxtvvrr7/03nvvKSEhwVBBO3fu1NKlS7Vp0yYdP35c1apVU9OmTTVmzBhFRETk2/bgwYOaPHmytm3bJl9fX3Xo0EGTJk1SjRo1DPUNlJR/WH0FhDd2WvtpiQed1jYAAJfjmgYAAAAAhSt2iN60adOrrj9z5ozef/99ffnll8rKylJsbKzGjx9f4oJmzJihbdu2qVu3boqMjFRycrLmz5+vPn36aOHChTKbzZKkxMREDRo0SEFBQRo7dqxSU1M1a9Ys7d+/X4sWLVKlSpVK3DcAAAAAAAAAAJcr9YNF09LSNHPmTM2ePVuXLl1SgwYNNHbsWHXq1MlQe8OHD9fUqVPzheB33HGH7r77bn388ceaOnWqJOmjjz5SWlqaFi9erDp16kiSYmJiNGLECC1ZskQDBgwo7aEBAAAAAAAAACo4wyF6Tk6OFixYoA8//FAWi0W1a9fWM888o969e8vLy8twQS1atCiwrG7dumrQoIEOHTpkW7Zq1SrdeuuttgBdkm6++WbVrVtXK1asIEQHAAAAAAAAAJSaoRB9xYoVeuedd5SQkKCgoCA9+eSTGjp0qPz8/BxdnyTJarXKYrGoQYMGkqRTp07p9OnTatKkSYFtY2JitG7dOqfUAQAAAAAAAACoWEoUom/atElTp07Vrl275OvrqxEjRmjUqFGqWrWqs+qTJC1fvlynTp3S448/LklKSkqSJIWEhBTYNiQkROfOnVNmZmaJ5kXPyclxTLFlkCuPPScnp0y/1nm15+bmurkSAABwNbt373bqd47g4GCFh4c7rX04Tt55UJa/gwLuwvgBjGP8AMa5cvwUt49ih+gPPPCAfv31V3l5ealXr1564oknVLt2bcMFFtfBgwf10ksvqXnz5urdu7ckKSMjQ5IKDcnz7oZPT08vUYgeFxfngGrLpv3797u0r9JM9+MpDhw44O4SAABAIbLOJ0smLw0dOtSp/fj5++vrr75yyfdhOEZF/r4PlBbjBzCO8QMY50njp9gh+vr162UymRQWFiaLxaLnnnuuyH1MJpM+/vhjw8UlJyfr4YcfVlBQkKZNmyZvb29J/xeUZ2ZmFtgnL2D39/cvUV/R0dG29isaV95VbTab1axZM5f152g5OTmKi4tT/fr13V0KAAAoRHbaBcmaq4gRU+Uf5pzrdfrJAzo8e7xCQ0PL9PeaiiLv+1tF/r4PGMX4AYxj/ADGuXL85PVVlBJN52K1WnXs2DEdO3asWNubTKaSNJ/PxYsX9eCDD+rixYuaP3++atWqZVsXGhoq6e+Q/UrJycmqVq1aie5ClyRvb+8K+6HmyuMuL69zebibHgCA8sw/rL4Cwhs7tY/y8r2mouD9Aoxj/ADGMX4A4zxp/BQ7RP/xxx+dWUc+GRkZGjVqlI4cOaLZs2cXuOu3Vq1aqlGjhnbt2lVg3507dyoqKspVpQIAAAAAAAAAyrFih+jXXnutM+uwycnJ0ZgxY7R9+3Z98MEHat68eaHbdenSRUuXLtXJkycVFhYmSdq4caOOHDmi4cOHu6RWAAAAAAAAAED5VqLpXFzh9ddf15o1a9SxY0edO3dOy5Yty7e+Z8+ekqRRo0Zp5cqVGjp0qIYOHarU1FTNnDlTZrNZffv2dUfpAAAAAAAAAIByxuNC9L1790qSfvrpJ/30008F1ueF6GFhYZo3b55ef/11vfnmm/L19VWHDh00ceLEEs+HjvIlISFBFovFKW3n5ORo//79Ln0YKwAAAAAAAAD38bgQfe7cucXetkGDBpo5c6YTq0FZk5CQoMiohkpPS3V3KQAAAAAAAADKAY8L0YHSsFgsSk9LVcSIqfIPq1/0Dgadj1urE9+847T2AQAAAAAAAHgGQnSUS/5h9RUQ3thp7aclHnRa2wAAAAAAAAA8h5e7CwAAAAAAAAAAwFMRogMAAAAAAAAAYAchOgAAAAAAAAAAdhCiAwAAAAAAAABgByE6AAAAAAAAAAB2EKIDAAAAAAAAAGAHIToAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdhCiAwAAAAAAAABgByE6AAAAAAAAAAB2EKIDAAAAAAAAAGAHIToAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdhCiAwAAAAAAAABgByE6AAAAAAAAAAB2EKIDAAAAAAAAAGAHIToAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdhCiAwAAAAAAAABgByE6AAAAAAAAAAB2EKIDAAAAAAAAAGAHIToAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdhCiAwAAAAAAAABgByE6AAAAAAAAAAB2EKIDAAAAAAAAAGAHIToAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdvi4uwAAAAAA7pWQkCCLxeLUPoKDgxUeHu7UPgAAAABnIEQHAAAAKrCEhARFRjVUelqqU/vxr1xF+/bGE6QDAACgzCFEBwAAACowi8Wi9LRURYyYKv+w+k7pI/3kAR2ePV4Wi4UQHQAAAGUOIToAAAAA+YfVV0B4Y3eXAQAAAHgcHiwKAAAAAAAAAIAdhOgAAAAAAAAAANhBiA4AAAAAAAAAgB2E6AAAAAAAAAAA2MGDRQEAAAAD4uPjnd5HcHCwwsPDnd4PAAAAAPsI0QEAAIASyDqfLJm8NHjwYKf35V+5ivbtjSdIBwAAANyIEB0AAAAogey0C5I1VxEjpso/rL7T+kk/eUCHZ4+XxWIhRAcAAADciBAdAAAAMMA/rL4Cwhu7uwwAAAAATsaDRQEAAAAAAAAAsIMQHQAAAAAAAAAAOwjRAQAAAAAAAACwgxAdAAAAAAAAAAA7CNEBAAAAAAAAALCDEB0AAAAAAAAAADsI0QEAAAAAAAAAsIMQHQAAAAAAAAAAOwjRAQAAAAAAAACwgxAdAAAAAAAAAAA7CNEBAAAAAAAAALCDEB0AAAAAAAAAADsI0QEAAAAAAAAAsMPjQvRLly7p3Xff1ciRI9W6dWtFRkZq8eLFhW578OBBjRw5Us2bN1fr1q311FNP6cyZMy6uGAAAAAAAAABQXnlciH727Fm9//77OnTokCIjI+1ul5iYqEGDBikhIUFjx47V/fffr59//lkjRoxQZmamCysGAAAAAAAAAJRXPu4u4EqhoaFav369QkJCFBcXp379+hW63UcffaS0tDQtXrxYderUkSTFxMRoxIgRWrJkiQYMGODKsgEAAAAAAAAA5ZDH3YleqVIlhYSEFLndqlWrdOutt9oCdEm6+eabVbduXa1YscKZJQIAAAAAAAAAKgiPC9GL49SpUzp9+rSaNGlSYF1MTIzi4+PdUBUAAAAAAAAAoLzxuOlciiMpKUmSCr1jPSQkROfOnVNmZqYqVapU7DZzcnIcVl9Z48pjz8nJcWp/Ffl9BAAA5dPu3bud+h1n7969Tmv7Ss7+Lmivz8v/H0DxMX4A4xg/gHGuHD/F7aNMhugZGRmSVGhI7ufnJ0lKT08vUYgeFxfnmOLKoP3797u0Ly8v5/0BhCuPBQAAwJmyzidLJi8NHTrU3aU4jLO/C15NRf6+D5QW4wcwjvEDGOdJ46dMhuh5QXlmZmaBdXkBu7+/f4najI6Olre3d+mLK4Nyc3Nd1pfZbFazZs2c1r4rjwUAAMCZstMuSNZcRYyYKv+w+k7r53zcWp345h2ntX85Z38XLExOTo7i4uIq9Pd9wCjGD2Ac4wcwzpXjJ6+vopTJED00NFSSlJycXGBdcnKyqlWrVqK70CXJ29u7wn6oufK4nf06V9T3EAAAlF/+YfUVEN7Yae2nJR50WttXcud37or8fR8oLcYPYBzjBzDOk8ZPmXywaK1atVSjRg3t2rWrwLqdO3cqKirKDVUBAAAAAAAAAMqbMhmiS1KXLl20du1anTx50rZs48aNOnLkiLp16+bGygAAAAAAAAAA5YVHTucyb948XbhwQUlJSZKkn376SYmJiZKkIUOGKCgoSKNGjdLKlSs1dOhQDR06VKmpqZo5c6bMZrP69u3rzvIBAAAAAAAAAOWER4bos2bN0vHjx20/r1q1SqtWrZIk9ejRQ0FBQQoLC9O8efP0+uuv680335Svr686dOigiRMnlng+dAAAAAAAAAAACuORIfqaNWuKtV2DBg00c+ZMJ1cDAAAAAAAAAKioyuyc6AAAAAAAAAAAOBshOgAAAAAAAAAAdhCiAwAAAAAAAABgByE6AAAAAAAAAAB2EKIDAAAAAAAAAGAHIToAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdhCiAwAAAAAAAABgByE6AAAAAAAAAAB2EKIDAAAAAAAAAGAHIToAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdhCiAwAAAAAAAABgByE6AAAAAAAAAAB2EKIDAAAAAAAAAGAHIToAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdhCiAwAAAAAAAABgh4+7CwAAAAAAR0lISJDFYrH9nJOTo/379ys3N1fe3t4O6ycjI0N+fn4Oa8+e4OBghYeHO70flMyV55mz8P4DAOAZCNEBAAAAlAsJCQmKjGqo9LRU53dm8pKsuU7vxr9yFe3bG0+Q6kFceZ7x/gMA4BkI0QEAAACUCxaLRelpqYoYMVX+YfWd1s/5uLU68c07Tu8n/eQBHZ49XhaLhRDVg7jqPOP9BwDAcxCiAwAAAChX/MPqKyC8sdPaT0s86JJ+4Nl4/wEAqDh4sCgAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdhCiAwAAAAAAAABgByE6AAAAAAAAAAB2EKIDAAAAAAAAAGAHIToAAAAAAAAAAHYQogMAAAAAAAAAYAchOgAAAAAAAAAAdhCiAwAAAAAAAABgByE6AAAAAAAAAAB2+Li7AAAAAAAVQ3x8fJlu312cfVzBwcEKDw93ah+SlJCQIIvF4vR+XHU8AACg4iBEBwAAAOBUWeeTJZOXBg8e7O5SyhRXvW7+lato3954pwbPCQkJioxqqPS0VKf1kccVxwMAACoWQnQAAAAATpWddkGy5ipixFT5h9V3Wj/n49bqxDfvOK19V3PF65Z+8oAOzx4vi8Xi1NDZYrEoPS3V6eeAq44HAABULIToAAAAAFzCP6y+AsIbO639tMSDTmvbnZz9urlSeToWAABQcfBgUQAAAAAAAAAA7CBEBwAAAAAAAADADkJ0AAAAAAAAAADsYE50uFR8fHyZbh8AAAAAAABAxUKIDpfIOp8smbw0ePBgd5cCAAAAAAAAAMVGiA6XyE67IFlzFTFiqvzD6jutn/Nxa3Xim3ec1j4AAAAAAACAioUQHS7lH1ZfAeGNndZ+WuJBp7UNAAAAAAAAoOLhwaIAAAAAAAAAANhBiA4AAAAAAAAAgB2E6AAAAAAAAAAA2EGIDgAAAAAAAACAHTxYFAAAAABQrsTHx5fJtt0lISFBFoulwPKcnBzt379fubm58vb2LnU/wcHBCg8PL3U7AAC4GiE6AAAAAKBcyDqfLJm8NHjwYHeXUmYkJCQoMqqh0tNSnd6Xf+Uq2rc3niAdAFDmEKIDAAAAAMqF7LQLkjVXESOmyj+svlP6OB+3Vie+eccpbbuDxWJRelqqU18zSUo/eUCHZ4+XxWIhRAcAlDmE6AAAAACAcsU/rL4Cwhs7pe20xINOadfdnPmaAQBQ1vFgUQAAAAAAAAAA7CBEBwAAAAAAAADADkJ0AAAAAAAAAADsYE50AAAAAKjg4uPjy3T7QJ6EhARZLBan95ORkSE/Pz+n9xMcHOySB7G64nUrT8ciue54XKG8vWauOB5XfQaUt8+asowQHQAAAAAqqKzzyZLJS4MHD3Z3KUCpJSQkKDKqodLTUp3fmclLsuY6vRv/ylW0b2+8U8MtV71u5elYJNccjyuUt9fMZcfjos+A8vRZU9YRogMAAABABZWddkGy5ipixFT5h9V3Wj/n49bqxDfvOK19QJIsFovS01Jddj47u5/0kwd0ePZ4WSwWpwZbrnjdytOxSK47Hlcob6+ZK47HVZ8B5e2zpqwr0yF6Zmampk2bpmXLlunChQuKjIzUmDFj1LZtW3eXBgAAAABlhn9YfQWEN3Za+2mJB53WNnAlV53Pzu7H1crT8ZSnY3GV8vaaOfN4XPUZUF4/a8qqMv1g0YkTJ+rTTz/V3XffrX/961/y9vbWQw89pC1btri7NAAAAAAAAABAOVBmQ/SdO3fqu+++07hx4zRhwgQNGDBAn332merUqaOpU6e6uzwAAAAAAAAAQDlQZkP0lStXytvbWwMGDLAt8/PzU79+/fTHH3/o5MmTbqwOAAAAAAAAAFAelNkQPT4+XnXr1lVgYGC+5TExMbb1AAAAAAAAAACURpl9sGhycrJCQkIKLM9blpSUVKx2rFarpL8fUurt7e24AsuQnJwcBQQEyGQ5rBwfk1P68D6f6PQ+6Mdz+yhv/ZSnYylv/ZSnYylv/ZSnY3FVP+XpWMpbP+XpWFzVT3k6lvLWT3k6Flf146pjMVkOKyAgQPHx8crJyXFaP/v37y83x+OqY+EcKLnydCxS8Y4nNzdXhw4dUnZ2try8jN3D6uXlpdzc3NKUWiRPes0cwRXHU56uadL/vTc5OTnKzMx0Wj8lkXeOuCKvzesrLyO2x2QtagsPddtttykiIkKffPJJvuVHjx7VbbfdpkmTJmn48OFFtpOZmam4uDgnVQkAAAAAAAAA8GTR0dGqVKmS3fVl9k50f3//Qn87kpGRYVtfHD4+PoqOjpaXl5dMJuf9VgcAAAAAAAAA4DmsVqtyc3Pl43P1mLzMhughISE6depUgeXJycmSpNDQ0GK14+XlddXfMgAAAAAAAAAAKq4y+2DRqKgoHTlyRCkpKfmW79ixQ5LUsGFDd5QFAAAAAAAAAChHymyI3q1bN+Xk5GjhwoW2ZZmZmVq8eLGaNm2qsLAwN1YHAAAAAAAAACgPyux0Lk2bNlW3bt301ltv6fTp07rhhhu0ZMkSHT9+XK+++qq7ywMAAAAAAAAAlAMmq9VqdXcRRmVkZOidd97RN998o/PnzysyMlJPPPGEbrnlFneXBgAAAAAAAAAoB8p0iA4AAAAAAAAAgDOV2TnRAQAAAAAAAABwNkJ0AAAAAAAAAADsKLMPFgUcbdOmTRo6dGih6xYuXKhmzZrZft62bZveeOMN7dmzR4GBgerevbvGjh2rgIAAF1ULuNelS5c0c+ZM7dixQ3FxcTp//rxee+019enTp8C2Bw8e1OTJk7Vt2zb5+vqqQ4cOmjRpkmrUqJFvu9zcXM2cOVNffPGFkpOTVbduXT388MO66667XHVYgEsUd/xMnDhRS5YsKbB/RESEVq5cmW8Z4wcVwc6dO7V06VJt2rRJx48fV7Vq1dS0aVONGTNGERER+bbl2gPkV9zxw7UHKNyff/6p6dOna/fu3bJYLPL391f9+vU1cuRIderUKd+2XIOA/Io7fjz9GkSIDlxhyJAhio6OzrcsPDzc9t/x8fEaPny46tWrp4kTJyoxMVGzZs3SkSNHNGPGDFeXC7jF2bNn9f7776tOnTqKjIzU5s2bC90uMTFRgwYNUlBQkMaOHavU1FTNmjVL+/fv16JFi1SpUiXbtm+//bY+/vhj9e/fX9HR0frxxx/15JNPymQy6c4773TVoQFOV9zxI0mVKlXSK6+8km9ZUFBQge0YP6gIZsyYoW3btqlbt26KjIxUcnKy5s+frz59+mjhwoUym82SuPYAhSnu+JG49gCFOXHihC5duqTevXsrNDRUaWlpWrVqlR555BG99NJLGjBggCSuQUBhijt+JA+/BlkBWK1Wq/W3336zms1m64oVK6663QMPPGBt27at9eLFi7ZlX375pdVsNlt/+eUXZ5cJeISMjAxrUlKS1Wq1Wnfu3Gk1m83Wr7/+usB2//73v60xMTHW48eP25b9+uuvVrPZbF2wYIFtWWJiorVx48bWF1980bYsNzfXet9991nbt29vzc7OduLRAK5V3PEzYcIEa7NmzYpsj/GDimLr1q3WjIyMfMsOHz5sbdKkifXJJ5+0LePaAxRU3PHDtQcovuzsbGuPHj2sXbt2tS3jGgQUT2Hjx9OvQcyJDhQiJSVF2dnZhS7fsGGDevToocDAQNvynj17qkqVKlqxYoUrywTcplKlSgoJCSlyu1WrVunWW29VnTp1bMtuvvlm1a1bN994Wb16tbKysnTffffZlplMJt17771KTEzUH3/84dgDANyouOMnT05OjlJSUuyuZ/ygomjRokW+O/gkqW7dumrQoIEOHTpkW8a1ByiouOMnD9ceoGje3t4KCwvTxYsXbcu4BgHFU9j4yeOp1yBCdOAKkyZNUmxsrGJiYjRkyBDFxcXZ1u3bt0/Z2dlq0qRJvn0qVaqkhg0bKj4+3tXlAh7r1KlTOn36dIHxIkkxMTH5xkt8fLyqVKmievXqFdgubz1QEaWlpSk2NlaxsbFq3bq1XnzxRV26dCnfNowfVGRWq1UWi0XVq1eXxLUHKIkrx08erj2AfampqTpz5owSEhL06aefat26dbrxxhslcQ0CinK18ZPHk69BzIkO/H++vr7q2rWr2rdvr+rVq+vgwYOaOXOmBg0apAULFqhRo0ZKTk6WJIWGhhbYPyQkRFu3bnV12YDHSkpKkqRC77gNCQnRuXPnlJmZqUqVKik5OVk1a9aUyWQqsN3lbQEVSUhIiB544AE1atRIVqtVv/zyiz7//HPt3btXc+fOlY/P31/jGD+oyJYvX65Tp07p8ccfl8S1ByiJK8ePxLUHKMrrr7+uhQsXSpK8vLx0++236/nnn5fENQgoytXGj+T51yBCdOD/a9GihVq0aGH7uXPnzuratat69OihN998UzNnzlR6erokFfhTSEny8/OzrQcgZWRkSLI/XiQpPT1dlSpVsv3/1bYDKponn3wy38933nmn6tatq7fffls//PCD7YE5jB9UVAcPHtRLL72k5s2bq3fv3pK49gDFVdj4kbj2AEUZNmyYunXrpqSkJK1YsUK5ubnKysqSxDUIKMrVxo/k+dcgpnMBruKGG25Q586dtWnTJuXk5Mjf31+SlJmZWWDbjIwM23oA/3cBszdeJNnGjL+/f7G2Ayq64cOHy8vLSxs2bLAtY/ygIkpOTtbDDz+soKAgTZs2Td7e3pK49gDFYW/82MO1B/g/9erV080336xevXrpv//9r1JTUzVq1ChZrVauQUARrjZ+7PGkaxAhOlCE2rVrKysrS2lpaVf905Dk5ORCp3kBKqq88ZA3DdLlkpOTVa1aNdtvj0NCQmSxWApcPK82hRJQEfn7+6tatWo6f/68bRnjBxXNxYsX9eCDD+rixYuaMWOGatWqZVvHtQe4uquNH3u49gD2de3aVXFxcTp8+DDXIKCELh8/9njSNYgQHSjCsWPH5OfnpypVqshsNsvHx0e7du3Kt01mZqbi4+MVFRXlpioBz1OrVi3VqFGjwHiRpJ07d+YbLw0bNlRaWpoOHjyYb7sdO3bY1gOQUlJSdPbsWdWoUcO2jPGDiiQjI0OjRo3SkSNH9NFHH6l+/fr51nPtAewravzYw7UHsC9v2oiUlBSuQUAJXT5+7PGkaxAhOvD/nTlzpsCyvXv3as2aNWrbtq28vLwUFBSkm266ScuXL883yJctW6bU1FR169bNlSUDHq9Lly5au3atTp48aVu2ceNGHTlyJN946dy5s3x9ffX555/bllmtVi1YsEC1atVS8+bNXVo34G4ZGRmFfpn84IMPZLVadcstt9iWMX5QUeTk5GjMmDHavn27pk2bZvfc5toDFFSc8cO1B7Dv9OnTBZZlZWVp2bJl8vf3V7169SRxDQIKU5zxUxauQTxYFPj/xowZI39/fzVv3lw1a9bUgQMH9OWX/6+9u4/q+f7/OP4olYsSMtlKmJ35MKUz1+2gLZTmosLpsFMfjouOudoI5bgcc7ENc5ZdGELY+AqzwmJb2xSniDUXo1mG5iobktoUn98fTp+fj0+fudhizf32D16v1/v1er3fH+/zPh6fd0//U7Vq1TR+/HjzuLFjx6p///6KjIxUeHi4zp07pxUrVqhjx47q3LnzIzwD4OFas2aNCgoKzOWNUlNTde7cOUlSZGSkatasqeHDh+uLL76Q0WiU0WhUUVGRli9frqZNm6pv377muZ588kkZjUYtX75cpaWl8vHx0Zdffql9+/Zp/vz5d63VCVQ2d7t/rly5orCwMPXo0UNNmjSRJKWlpenbb79Vp06d1KVLF/Nc3D94XMybN09ff/21XnrpJV2+fFlbtmyx6A8JCZEknj1AOe7l/snPz+fZA9gwbdo0FRYWqm3btqpfv77y8/OVlJSk3NxcxcbGytnZWRLPIKA893L/5OXl/eufQXamv6reDjxGEhISlJSUpFOnTqmwsFB16tSRn5+fRo0apUaNGlmMLbsxjxw5ImdnZwUHB2vcuHFycXF5RLsHHr6AgAD9+uuv5fZ99dVXatCggSTpp59+0rx585SVlSVHR0f5+/srNjZWTzzxhMUxN2/e1NKlS7V+/XpduHBBjRs3VlRUlHr37l3h5wI8bHe7f1xdXTVr1ixlZ2frwoULunHjhho1aqRevXpp8ODBcnR0tDiG+wePg8jISGVmZtrsP3bsmPn3PHsAS/dy/xQUFPDsAWzYunWrEhMTlZOTo8uXL8vZ2VktWrRQRESERbgn8QwC7nQv909leAYRogMAAAAAAAAAYAM10QEAAAAAAAAAsIEQHQAAAAAAAAAAGwjRAQAAAAAAAACwgRAdAAAAAAAAAAAbCNEBAAAAAAAAALCBEB0AAAAAAAAAABsI0QEAAAAAAAAAsIEQHQAAAAAAAAAAGwjRAQAAAAAAAACwgRAdAAAAqGCxsbEyGAzKy8t71Fv5R6Slpal///5q27atDAaDRowY8VDXNxgMioyMfKhrAgAA4PFFiA4AAIBKIy8vTwaDQQaDQUOGDCl3zPfffy+DwaDY2NiHvLvHQ15enkaMGKG8vDz16dNHo0aNUo8ePf7ymP/alwgAAAB4vDg86g0AAAAADyItLU179uyRn5/fo97KY2XPnj36888/FRMTo169ej3q7QAAAAAVjjfRAQAAUOl4enrK3t5e8+fPl8lketTbeaycP39ekuTu7v6IdwIAAAA8HIToAAAAqHSefvpphYSE6NChQ9q+ffs9HRMQEKCAgIBy+yIjI2UwGCza4uLiZDAYlJGRoY0bN6pXr15q2bKlAgIClJCQIEkymUyKj49XUFCQfHx8FBgYqM8++8zmHkwmk5YuXarAwED5+PgoICBAixcvVklJSbnj9+7dq+HDh6t9+/by9vZWYGCg3n33XRUXF1uMy8jIkMFgUFxcnPbv36/BgwerTZs2VudkS05Ojl577TX5+fnJ29tbAQEBmj17ti5dumQeU1ZKJy4uTpJkNBrNpXUyMjJszh0QEKDNmzdLkrp06WI+5s6a5llZWYqKilK7du3k4+Oj7t2767333rM6V1tMJpPmzJkjg8Gg6Oho8zU1mUxKTExU//791apVK/n6+qpPnz5KTEy0muP2zzwpKUkhISFq2bKlOnbsqDfffFN//PGH1TEpKSmKiIiQn5+ffHx81LFjRw0aNEgpKSn3tG8AAAD8+1HOBQAAAJXSmDFjtHXrVi1atEjdunWTo6NjhayzatUqZWZmqkuXLmrfvr127Nih2bNnq3r16jpy5Ih27NihF198UY6Ojtq2bZtiYmLk6emptm3bWs01e/ZsHThwQN27d1eNGjWUmpqquLg45eTk6L333rMY+8knn2jmzJlydXXVSy+9JDc3Nx06dEgfffSRMjIylJCQICcnJ4tjDhw4oCVLlqh9+/YKDw/X2bNn73p++/bt09ChQ1VSUqKgoCB5enrq+++/V0JCgr755hutX79ebm5ucnV11ahRo5SZmanMzEyFhYXJ09NTksy/lsdoNGrz5s06evSojEajXF1drY7Zvn27oqOj5eTkpODgYNWtW1fp6el6//33lZaWptWrV6tq1ao21ygpKVFsbKySk5M1cOBATZo0SXZ2djKZTBo/frySk5PVuHFj9ezZU05OTkpPT9fkyZP1888/KyYmxmq+tWvXateuXQoICFCHDh20a9curV69WpcuXdKCBQssPqM33nhD9erVU7du3VS7dm3l5+fr4MGD2rlzp4KCgu56/QEAAPDvR4gOAACASsnDw0MRERGKj4/X+vXrFRERUSHrZGVlafPmzfLy8pIkDRkyRN26ddNbb72lunXrKikpSW5ubpKksLAwhYeHa/ny5eWG6NnZ2dqyZYuefPJJSdLYsWM1ePBgpaSkKCUlxRy6Hj9+XLNnz5bBYNDKlStVp04d8xwff/yxFixYoDVr1mjw4MEW86enp2vOnDnq27fvPZ3bzZs3NWnSJBUXF2vZsmXq1KmTue/tt9/W8uXLNX/+fM2ZM0eurq4aPXq04uLizCF6+/bt77rGoEGDdPToUR09elQDBw5UgwYNLPoLCws1depUValSRevWrVOzZs0kSePGjVN0dLS2bdumZcuWaeTIkeXOf+3aNY0ZM0ZpaWmKjo5WVFSUuW/Dhg1KTk5Wnz59NHPmTPMXLdevX9eYMWMUHx+vHj16yNvb22LO3bt3a+PGjWrSpImkW59TSEiItm3bpokTJ6p+/fqSpMTERDk6OmrLli2qW7euxRy3v8UPAACAyo1yLgAAAKi0hg8fLldXV33wwQe6du1ahawRGRlpDtAl6amnnlLr1q119epVvfrqq+YAXZJ8fX3l5eWlY8eOlTuX0Wg0B+iS5OTkpNdff12SzCVPJGndunUqLS3V1KlTLQJ0SRo6dKjc3NyUnJxsNX+LFi3uOUCXpP379+vUqVPq3LmzRYAuSSNHjlTt2rWVnJys69ev3/Oc9+vLL7/U1atX1bdvX3OALkn29vaaMGGCHBwcLK7N7X7//XcNHDhQe/bs0Zw5cywCdElas2aNatSooenTp1v8pIKTk5PGjh0rSdq6davVvEaj0RygS1K1atXUs2dP3bx5U4cPH7YY6+joKAcH63eT7vzcAAAAUHnxJjoAAAAqrVq1amnYsGFasGCB4uPjNXr06H98jebNm1u11atXT5IsQt/b+3744Ydy52rTpo1V2/PPPy8HBwcdOXLE3JadnS1J2rVrl/bs2WN1jIODg06cOGHVfucb1XdTtma7du2s+pydneXt7a20tDSdOHHinuur368ff/zR5h48PDzUoEED/fLLLyosLJSLi4u57+LFixowYIDOnTunxYsXW9W7Ly4uVk5Ojtzd3bV06VKruUtLSyVJubm5Vn0tWrSwaiv78qOgoMDc9vLLL+udd95Rz5491bNnT3Xo0EGtW7e22CcAAAAqP0J0AAAAVGpGo1Fr165VfHy8XnnllX98/vIC0bI3j231lQW0d7qz5IckValSRbVr19bVq1fNbVeuXJEkffTRR/e11yeeeOK+xhcWFv7lcWVfFpSNqwh324O7u7t++eUXXbt2zeJ65+fnq7CwUI0aNZKvr6/VcQUFBTKZTDp//rwWL15sc/2ioiKrtvI+1ypVqki6VQKnzJAhQ1S7dm19+umnWrFiheLj4+Xg4CB/f39NmjTJ4icYAAAAUHkRogMAAKBSq1atmkaPHq3Jkydr8eLFCgkJKXecnZ2dSkpKyu27PcCuSL/99ptFmRBJunHjhi5fvmwRsJeFuFlZWff1VrOdnd197ads7osXL5bbn5+fbzGuItzrHpydnS3amzdvrtDQUE2ZMkVGo1GrVq2yCOLLxrdo0UKbNm2qiK3Lzs5O/fr1U79+/XTp0iVlZWUpOTlZ27dv18mTJ/X555+bw3cAAABUXtREBwAAQKUXFhamZ599Vhs2bNDJkyfLHVOrVi39/vvvVm+JFxUV2Tzmn7Zv3z6rtgMHDqi0tFTPPfecua1ly5aS/r+sS0UpWzMzM9Oqr6ioSIcOHVK1atX09NNP/6117O1v/bPj9re4y5SVyylvD2fPntXp06fl5eVVbpDft29fzZ07V7m5uTIajRZBvIuLi5555hnl5uZalGCpKHXq1FHXrl21aNEidejQQcePH39of68AAABQsQjRAQAAUOlVqVJFY8eOVUlJic3SHd7e3iopKVFSUpK5zWQyaeHCheWW9KgICQkJOnfunPnP169f16JFiyTd+iKgzCuvvCIHBwfNmjVLZ86csZqnoKDAoob6g2rVqpUaNmyo7777Trt377bo+/DDD3X58mX16NFDTk5Of2udWrVqSboVit+pa9euqlmzpjZt2qSffvrJ3G4ymTR//nyVlpZaXJs7hYaGau7cuTpx4oQiIyPNb65Lt/5T2OLiYk2ZMqXcz/j06dPKy8t74PPKyMiQyWSyaCspKTGX46lateoDzw0AAIB/D8q5AAAA4D+hS5cuat26tbKyssrtj4iI0KZNmzRlyhSlp6fLzc1N+/bt09WrV9WsWTMdPXq0wvfo6+urkJAQBQcHq3r16kpNTdWJEycUGBiooKAg87imTZtq+vTpmjFjhrp37y5/f395eXnp2rVrysvLU2ZmpsLCwjRz5sy/tR97e3vNnTtXQ4cOVVRUlIKCguTp6akDBw4oMzNTDRs21Pjx4//uaatDhw6Kj4/XtGnTFBgYqOrVq8vDw0OhoaFycXHRrFmzFB0drfDwcAUHB8vNzU27d+/W4cOH1bJlSw0dOvQv5w8NDZW9vb1iY2MVGRmphIQEubu7q3///srOztbmzZu1f/9+vfDCC3J3d9dvv/2m3NxcZWdna8GCBWrQoMEDndfIkSPl4uIiX19feXh4qLS0VLt379bx48fN1xIAAACVHyE6AAAA/jPGjx+vAQMGlNvXtGlTLVu2TAsXLlRKSopq1Kghf39/xcTE6PXXX38o+5s8ebK2b9+uxMREnTlzRu7u7ho9erSioqKsxoaHh6tZs2ZauXKl9u7dq9TUVLm4uMjDw0ODBg1SaGjoP7KnNm3aaP369Xr//feVnp6uwsJCubu7y2g06tVXX5Wbm9vfXsPf318TJkzQhg0btGLFCpWUlKhdu3bmcwgODla9evW0ZMkS7dy5U8XFxfL09NSIESM0bNiwe3qju3fv3rK3t9fEiRPNNdLr16+vefPmqXPnztqwYYO++eYbFRUVyc3NTY0aNVJMTIz8/Pwe+LzGjRunXbt26eDBg0pNTVX16tXVsGFDzZgxQ/369XvgeQEAAPDvYme68+cPAQAAAAAAAACAJGqiAwAAAAAAAABgEyE6AAAAAAAAAAA2EKIDAAAAAAAAAGADIToAAAAAAAAAADYQogMAAAAAAAAAYAMhOgAAAAAAAAAANhCiAwAAAAAAAABgAyE6AAAAAAAAAAA2EKIDAAAAAAAAAGADIToAAAAAAAAAADYQogMAAAAAAAAAYAMhOgAAAAAAAAAANhCiAwAAAAAAAABgw/8BYkOsXO62JEIAAAAASUVORK5CYII=\n"
+ },
+ "metadata": {}
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "##Filter out rows with more than 2048 tokens\n",
+ "\n",
+ "We will remove samples with more than 2048 tokens (max context size of Llama 2 by default = 4096)."
+ ],
+ "metadata": {
+ "id": "o8fXqz3DXukk"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Filter out rows with more than 2048 tokens\n",
+ "valid_indices = [i for i, count in enumerate(combined_token_counts) if count <= 2048]\n",
+ "print(f\"Number of valid rows: {len(valid_indices)}\")\n",
+ "print(f\"Removing {len(dataset) - len(valid_indices)} rows...\")\n",
+ "\n",
+ "# Extract valid rows based on indices\n",
+ "dataset = dataset.select(valid_indices)\n",
+ "\n",
+ "# Get token counts for valid rows\n",
+ "token_counts = [combined_token_counts[i] for i in valid_indices]\n",
+ "\n",
+ "plot_distribution(token_counts, \"New distribution of token counts for combined instruction + output\")"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 564
+ },
+ "id": "owyavGGyXvdK",
+ "outputId": "0117ac6d-b1cf-418f-f915-6ce00f193261"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Number of valid rows: 978\n",
+ "Removing 0 rows...\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "
"
+ ],
+ "image/png": "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\n"
+ },
+ "metadata": {}
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "##Top-k sampling\n",
+ "\n",
+ "Only keep the top k samples with the most tokens."
+ ],
+ "metadata": {
+ "id": "TOCspcgXNOav"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Define a function to get the top k rows based on the number of tokens\n",
+ "def get_top_k_rows(dataset, token_counts, k):\n",
+ " # Sort the indices of the token counts in descending order and select the top k\n",
+ " sorted_indices = sorted(range(len(token_counts)), key=lambda i: token_counts[i], reverse=True)\n",
+ " top_k_indices = sorted_indices[:k]\n",
+ "\n",
+ " # Extract the instruction and output for the top k rows\n",
+ " top_k_data = {\n",
+ " \"instruction\": [dataset[i][\"instruction\"] for i in top_k_indices], #dataset['train']\n",
+ " \"output\": [dataset[i][\"expected_output\"] for i in top_k_indices] #dataset['train']\n",
+ " }\n",
+ "\n",
+ " # Return a new dataset created from the top k rows\n",
+ " return Dataset.from_dict(top_k_data)\n",
+ "\n",
+ "# Calculate the number of tokens in each instruction and output in the deduplicated dataset\n",
+ "instruction_token_counts = [len(tokenizer.tokenize(example[\"instruction\"])) for example in deduped_dataset['train']]\n",
+ "output_token_counts = [len(tokenizer.tokenize(example[\"expected_output\"])) for example in deduped_dataset['train']]\n",
+ "\n",
+ "# Combine the token counts for instructions and outputs\n",
+ "combined_token_counts = [instruction + output for instruction, output in zip(instruction_token_counts, output_token_counts)]\n",
+ "\n",
+ "# Specify the number of rows to retrieve\n",
+ "k = 1000 # You can adjust this value as needed\n",
+ "\n",
+ "# Retrieve the top k rows with the most tokens from the deduplicated dataset\n",
+ "top_k_dataset = get_top_k_rows(dataset, combined_token_counts, k) #deduped_dataset\n",
+ "\n",
+ "# Create a DatasetDict object containing the top k dataset with a 'train' split\n",
+ "dataset = DatasetDict({\"train\": top_k_dataset})"
+ ],
+ "metadata": {
+ "id": "iUIy1SGqeyFo"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Calculate the number of tokens in each instruction in the training set\n",
+ "instruction_token_counts = [len(tokenizer.tokenize(example[\"instruction\"])) for example in dataset['train']]\n",
+ "\n",
+ "# Calculate the number of tokens in each output in the training set\n",
+ "output_token_counts = [len(tokenizer.tokenize(example[\"output\"])) for example in dataset['train']]\n",
+ "\n",
+ "# Combine the token counts of instruction and output for each example\n",
+ "combined_token_counts = [instruction + output for instruction, output in zip(instruction_token_counts, output_token_counts)]\n",
+ "\n",
+ "# Plotting the token count distributions\n",
+ "# Plot for distribution of token counts in instructions\n",
+ "plot_distribution(instruction_token_counts, \"Distribution of token counts for instruction only\")\n",
+ "\n",
+ "# Plot for distribution of token counts in outputs\n",
+ "plot_distribution(output_token_counts, \"Distribution of token counts for output only\")\n",
+ "\n",
+ "# Plot for distribution of combined token counts in both instructions and outputs\n",
+ "plot_distribution(combined_token_counts, \"Distribution of token counts for combined instruction + output\")"
+ ],
+ "metadata": {
+ "id": "oUxPB-KOKEmH",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 1000
+ },
+ "outputId": "77c63192-8db1-4338-f015-180a9e5ab9e9"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "
"
+ ],
+ "image/png": "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\n"
+ },
+ "metadata": {}
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Convert the 'train' split of the dataset to a Pandas DataFrame for easier analysis and manipulation\n",
+ "dataset.to_pandas()"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 423
+ },
+ "id": "BoGShCGIrQJt",
+ "outputId": "6370d7c8-d481-4229-fdfb-0f825886253d"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ " expected_output \\\n",
+ "0 AI, or artificial intelligence, involves the c... \n",
+ "1 Machine Learning is a branch of AI that enable... \n",
+ "2 Deep Learning, a subset of Machine Learning, e... \n",
+ "3 AI, Machine Learning, and Deep Learning are in... \n",
+ "4 Artificial neural networks are structured base... \n",
+ ".. ... \n",
+ "973 [question]: What is the definition of Artifici... \n",
+ "974 [question]: What is the definition of Machine ... \n",
+ "975 [question]: What is the definition of Deep Lea... \n",
+ "976 [question]: What is the relationship between A... \n",
+ "977 [question]: What is the aim of Deep Learning? ... \n",
+ "\n",
+ " instruction \\\n",
+ "0 Summarize the concept and applications of AI \n",
+ "1 Summarize the concept and applications of Mach... \n",
+ "2 Summarize the concept and applications of Deep... \n",
+ "3 Summarize the differences between AI, Machine ... \n",
+ "4 Summarize the concept and structure of artific... \n",
+ ".. ... \n",
+ "973 Create an MCQ on the definition of Artificial ... \n",
+ "974 Create an MCQ on the definition of Machine Lea... \n",
+ "975 Create an MCQ on the definition of Deep Learning. \n",
+ "976 Create an MCQ on the relationship between Arti... \n",
+ "977 Create an MCQ on the aim of Deep Learning. \n",
+ "\n",
+ " input_content \n",
+ "0 AI refers to the development of computer syste... \n",
+ "1 Machine Learning is a subset of AI that focuse... \n",
+ "2 Deep Learning is a subset of Machine Learning ... \n",
+ "3 \n",
+ "4 Artificial neural networks are built on the pr... \n",
+ ".. ... \n",
+ "973 Artificial Intelligence is basically the mecha... \n",
+ "974 Machine Learning is basically the study/proces... \n",
+ "975 Deep Learning is basically a sub-part of the b... \n",
+ "976 AI is the broader family consisting of ML and ... \n",
+ "977 The aim is to basically increase chances of su... \n",
+ "\n",
+ "[978 rows x 3 columns]"
+ ],
+ "text/html": [
+ "\n",
+ "