{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import GPT2LMHeadModel"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "transformer.wte.weight torch.Size([50257, 768])\n",
      "transformer.wpe.weight torch.Size([1024, 768])\n",
      "transformer.h.0.ln_1.weight torch.Size([768])\n",
      "transformer.h.0.ln_1.bias torch.Size([768])\n",
      "transformer.h.0.attn.c_attn.weight torch.Size([768, 2304])\n",
      "transformer.h.0.attn.c_attn.bias torch.Size([2304])\n",
      "transformer.h.0.attn.c_proj.weight torch.Size([768, 768])\n",
      "transformer.h.0.attn.c_proj.bias torch.Size([768])\n",
      "transformer.h.0.ln_2.weight torch.Size([768])\n",
      "transformer.h.0.ln_2.bias torch.Size([768])\n",
      "transformer.h.0.mlp.c_fc.weight torch.Size([768, 3072])\n",
      "transformer.h.0.mlp.c_fc.bias torch.Size([3072])\n",
      "transformer.h.0.mlp.c_proj.weight torch.Size([3072, 768])\n",
      "transformer.h.0.mlp.c_proj.bias torch.Size([768])\n",
      "transformer.h.1.ln_1.weight torch.Size([768])\n",
      "transformer.h.1.ln_1.bias torch.Size([768])\n",
      "transformer.h.1.attn.c_attn.weight torch.Size([768, 2304])\n",
      "transformer.h.1.attn.c_attn.bias torch.Size([2304])\n",
      "transformer.h.1.attn.c_proj.weight torch.Size([768, 768])\n",
      "transformer.h.1.attn.c_proj.bias torch.Size([768])\n",
      "transformer.h.1.ln_2.weight torch.Size([768])\n",
      "transformer.h.1.ln_2.bias torch.Size([768])\n",
      "transformer.h.1.mlp.c_fc.weight torch.Size([768, 3072])\n",
      "transformer.h.1.mlp.c_fc.bias torch.Size([3072])\n",
      "transformer.h.1.mlp.c_proj.weight torch.Size([3072, 768])\n",
      "transformer.h.1.mlp.c_proj.bias torch.Size([768])\n",
      "transformer.h.2.ln_1.weight torch.Size([768])\n",
      "transformer.h.2.ln_1.bias torch.Size([768])\n",
      "transformer.h.2.attn.c_attn.weight torch.Size([768, 2304])\n",
      "transformer.h.2.attn.c_attn.bias torch.Size([2304])\n",
      "transformer.h.2.attn.c_proj.weight torch.Size([768, 768])\n",
      "transformer.h.2.attn.c_proj.bias torch.Size([768])\n",
      "transformer.h.2.ln_2.weight torch.Size([768])\n",
      "transformer.h.2.ln_2.bias torch.Size([768])\n",
      "transformer.h.2.mlp.c_fc.weight torch.Size([768, 3072])\n",
      "transformer.h.2.mlp.c_fc.bias torch.Size([3072])\n",
      "transformer.h.2.mlp.c_proj.weight torch.Size([3072, 768])\n",
      "transformer.h.2.mlp.c_proj.bias torch.Size([768])\n",
      "transformer.h.3.ln_1.weight torch.Size([768])\n",
      "transformer.h.3.ln_1.bias torch.Size([768])\n",
      "transformer.h.3.attn.c_attn.weight torch.Size([768, 2304])\n",
      "transformer.h.3.attn.c_attn.bias torch.Size([2304])\n",
      "transformer.h.3.attn.c_proj.weight torch.Size([768, 768])\n",
      "transformer.h.3.attn.c_proj.bias torch.Size([768])\n",
      "transformer.h.3.ln_2.weight torch.Size([768])\n",
      "transformer.h.3.ln_2.bias torch.Size([768])\n",
      "transformer.h.3.mlp.c_fc.weight torch.Size([768, 3072])\n",
      "transformer.h.3.mlp.c_fc.bias torch.Size([3072])\n",
      "transformer.h.3.mlp.c_proj.weight torch.Size([3072, 768])\n",
      "transformer.h.3.mlp.c_proj.bias torch.Size([768])\n",
      "transformer.h.4.ln_1.weight torch.Size([768])\n",
      "transformer.h.4.ln_1.bias torch.Size([768])\n",
      "transformer.h.4.attn.c_attn.weight torch.Size([768, 2304])\n",
      "transformer.h.4.attn.c_attn.bias torch.Size([2304])\n",
      "transformer.h.4.attn.c_proj.weight torch.Size([768, 768])\n",
      "transformer.h.4.attn.c_proj.bias torch.Size([768])\n",
      "transformer.h.4.ln_2.weight torch.Size([768])\n",
      "transformer.h.4.ln_2.bias torch.Size([768])\n",
      "transformer.h.4.mlp.c_fc.weight torch.Size([768, 3072])\n",
      "transformer.h.4.mlp.c_fc.bias torch.Size([3072])\n",
      "transformer.h.4.mlp.c_proj.weight torch.Size([3072, 768])\n",
      "transformer.h.4.mlp.c_proj.bias torch.Size([768])\n",
      "transformer.h.5.ln_1.weight torch.Size([768])\n",
      "transformer.h.5.ln_1.bias torch.Size([768])\n",
      "transformer.h.5.attn.c_attn.weight torch.Size([768, 2304])\n",
      "transformer.h.5.attn.c_attn.bias torch.Size([2304])\n",
      "transformer.h.5.attn.c_proj.weight torch.Size([768, 768])\n",
      "transformer.h.5.attn.c_proj.bias torch.Size([768])\n",
      "transformer.h.5.ln_2.weight torch.Size([768])\n",
      "transformer.h.5.ln_2.bias torch.Size([768])\n",
      "transformer.h.5.mlp.c_fc.weight torch.Size([768, 3072])\n",
      "transformer.h.5.mlp.c_fc.bias torch.Size([3072])\n",
      "transformer.h.5.mlp.c_proj.weight torch.Size([3072, 768])\n",
      "transformer.h.5.mlp.c_proj.bias torch.Size([768])\n",
      "transformer.h.6.ln_1.weight torch.Size([768])\n",
      "transformer.h.6.ln_1.bias torch.Size([768])\n",
      "transformer.h.6.attn.c_attn.weight torch.Size([768, 2304])\n",
      "transformer.h.6.attn.c_attn.bias torch.Size([2304])\n",
      "transformer.h.6.attn.c_proj.weight torch.Size([768, 768])\n",
      "transformer.h.6.attn.c_proj.bias torch.Size([768])\n",
      "transformer.h.6.ln_2.weight torch.Size([768])\n",
      "transformer.h.6.ln_2.bias torch.Size([768])\n",
      "transformer.h.6.mlp.c_fc.weight torch.Size([768, 3072])\n",
      "transformer.h.6.mlp.c_fc.bias torch.Size([3072])\n",
      "transformer.h.6.mlp.c_proj.weight torch.Size([3072, 768])\n",
      "transformer.h.6.mlp.c_proj.bias torch.Size([768])\n",
      "transformer.h.7.ln_1.weight torch.Size([768])\n",
      "transformer.h.7.ln_1.bias torch.Size([768])\n",
      "transformer.h.7.attn.c_attn.weight torch.Size([768, 2304])\n",
      "transformer.h.7.attn.c_attn.bias torch.Size([2304])\n",
      "transformer.h.7.attn.c_proj.weight torch.Size([768, 768])\n",
      "transformer.h.7.attn.c_proj.bias torch.Size([768])\n",
      "transformer.h.7.ln_2.weight torch.Size([768])\n",
      "transformer.h.7.ln_2.bias torch.Size([768])\n",
      "transformer.h.7.mlp.c_fc.weight torch.Size([768, 3072])\n",
      "transformer.h.7.mlp.c_fc.bias torch.Size([3072])\n",
      "transformer.h.7.mlp.c_proj.weight torch.Size([3072, 768])\n",
      "transformer.h.7.mlp.c_proj.bias torch.Size([768])\n",
      "transformer.h.8.ln_1.weight torch.Size([768])\n",
      "transformer.h.8.ln_1.bias torch.Size([768])\n",
      "transformer.h.8.attn.c_attn.weight torch.Size([768, 2304])\n",
      "transformer.h.8.attn.c_attn.bias torch.Size([2304])\n",
      "transformer.h.8.attn.c_proj.weight torch.Size([768, 768])\n",
      "transformer.h.8.attn.c_proj.bias torch.Size([768])\n",
      "transformer.h.8.ln_2.weight torch.Size([768])\n",
      "transformer.h.8.ln_2.bias torch.Size([768])\n",
      "transformer.h.8.mlp.c_fc.weight torch.Size([768, 3072])\n",
      "transformer.h.8.mlp.c_fc.bias torch.Size([3072])\n",
      "transformer.h.8.mlp.c_proj.weight torch.Size([3072, 768])\n",
      "transformer.h.8.mlp.c_proj.bias torch.Size([768])\n",
      "transformer.h.9.ln_1.weight torch.Size([768])\n",
      "transformer.h.9.ln_1.bias torch.Size([768])\n",
      "transformer.h.9.attn.c_attn.weight torch.Size([768, 2304])\n",
      "transformer.h.9.attn.c_attn.bias torch.Size([2304])\n",
      "transformer.h.9.attn.c_proj.weight torch.Size([768, 768])\n",
      "transformer.h.9.attn.c_proj.bias torch.Size([768])\n",
      "transformer.h.9.ln_2.weight torch.Size([768])\n",
      "transformer.h.9.ln_2.bias torch.Size([768])\n",
      "transformer.h.9.mlp.c_fc.weight torch.Size([768, 3072])\n",
      "transformer.h.9.mlp.c_fc.bias torch.Size([3072])\n",
      "transformer.h.9.mlp.c_proj.weight torch.Size([3072, 768])\n",
      "transformer.h.9.mlp.c_proj.bias torch.Size([768])\n",
      "transformer.h.10.ln_1.weight torch.Size([768])\n",
      "transformer.h.10.ln_1.bias torch.Size([768])\n",
      "transformer.h.10.attn.c_attn.weight torch.Size([768, 2304])\n",
      "transformer.h.10.attn.c_attn.bias torch.Size([2304])\n",
      "transformer.h.10.attn.c_proj.weight torch.Size([768, 768])\n",
      "transformer.h.10.attn.c_proj.bias torch.Size([768])\n",
      "transformer.h.10.ln_2.weight torch.Size([768])\n",
      "transformer.h.10.ln_2.bias torch.Size([768])\n",
      "transformer.h.10.mlp.c_fc.weight torch.Size([768, 3072])\n",
      "transformer.h.10.mlp.c_fc.bias torch.Size([3072])\n",
      "transformer.h.10.mlp.c_proj.weight torch.Size([3072, 768])\n",
      "transformer.h.10.mlp.c_proj.bias torch.Size([768])\n",
      "transformer.h.11.ln_1.weight torch.Size([768])\n",
      "transformer.h.11.ln_1.bias torch.Size([768])\n",
      "transformer.h.11.attn.c_attn.weight torch.Size([768, 2304])\n",
      "transformer.h.11.attn.c_attn.bias torch.Size([2304])\n",
      "transformer.h.11.attn.c_proj.weight torch.Size([768, 768])\n",
      "transformer.h.11.attn.c_proj.bias torch.Size([768])\n",
      "transformer.h.11.ln_2.weight torch.Size([768])\n",
      "transformer.h.11.ln_2.bias torch.Size([768])\n",
      "transformer.h.11.mlp.c_fc.weight torch.Size([768, 3072])\n",
      "transformer.h.11.mlp.c_fc.bias torch.Size([3072])\n",
      "transformer.h.11.mlp.c_proj.weight torch.Size([3072, 768])\n",
      "transformer.h.11.mlp.c_proj.bias torch.Size([768])\n",
      "transformer.ln_f.weight torch.Size([768])\n",
      "transformer.ln_f.bias torch.Size([768])\n",
      "lm_head.weight torch.Size([50257, 768])\n"
     ]
    }
   ],
   "source": [
    "model_hf = GPT2LMHeadModel.from_pretrained(\"gpt2\")\n",
    "sd_hf = model_hf.state_dict()\n",
    "for k, v in sd_hf.items():\n",
    "    print(k, v.shape)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x29574e550>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Display the positional encoding weights in grey\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "plt.imshow(sd_hf[\"transformer.wte.weight\"], cmap=\"Greys\", aspect=\"auto\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAiIAAAGdCAYAAAAvwBgXAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzddXgc1/Xw8e8sg1YrZrRkGWR2zE7smB1m5qSBBhtq0yZt2jA0zMzMiZMYY2aSSZYtWcy4q9XyzLx/rCKI5Nhp48q/V/fzPH4ea2lmV9qZM+eee66kqqqKIAiCIAhCH9D09Q4IgiAIgtB/iUBEEARBEIQ+IwIRQRAEQRD6jAhEBEEQBEHoMyIQEQRBEAShz4hARBAEQRCEPiMCEUEQBEEQ+owIRARBEARB6DO6vt6BX6MoClVVVdhsNiRJ6uvdEQRBEAThMKiqSmtrK0lJSWg0v57zOKoDkaqqKlJTU/t6NwRBEARB+A+Ul5eTkpLyq485qgMRm80GhN5IeHh4H++NIAiCIAiHw+l0kpqa2nEe/zVHdSDy83BMeHi4CEQEQRAE4f+YwymrEMWqgiAIgiD0GRGICIIgCILQZ0QgIgiCIAhCnxGBiCAIgiAIfUYEIoIgCIIg9BkRiAiCIAiC0GdEICIIgiAIQp8RgYggCIIgCH1GBCKCIAiCIPQZEYgIgiAIgtBnRCAiCIIgCEKfEYGIIAiCIAh95n8WiDz00ENIksQtt9zyv9rkQTVWlLPsrZfZ9M3nfb0rgiAIgtCv/U8CkU2bNvHKK68wYsSI/8XmDqm1oY5tP3xL/poVfb0rgiAIgtCvHfFAxOVyceGFF/Lqq68SGRl5pDd3eA5jWWJBEARBEI68Ix6IXH/99Zx44onMmjXrkI/1+Xw4nc5u/44oVT2yry8IgiAIwq/SHckX/+ijj9i6dSubNm06rMc/9NBD/POf/zySuxTyc0ZEBCKCIAiC0KeOWEakvLycm2++mffeew+TyXRYz7nrrrtwOBwd/8rLy4/IvkmEAhERhgiCIAhC3zpiGZEtW7ZQV1fH2LFjO26TZZmVK1fy3HPP4fP50Gq13Z5jNBoxGo1Hapc6iRIRQRAEQTgqHLFAZObMmezcubPbbZdffjmDBw/mz3/+c48gpE+IoRlBEARB6FNHLBCx2WwMGzas221Wq5Xo6Oget/+vSe01IqoIRARBEAShT/XTzqpibEYQBEEQjgZHdNbMLy1fvvx/ubmDEm1EBEEQBOHo0E8zIiFiaEYQBEEQ+lb/DEREHxFBEARBOCr0y0BE9BERBEEQhKNDvwxERK2qIAiCIBwd+mcg8jMxNCMIgiAIfap/BiId02ZEICIIgiAIfalfBiIdNSIiIyIIgiAIfapfBiKikYggCIIgHB36ZyDyM5EQEQRBEIQ+1S8DkY42IiISEQRBEIQ+1S8DkY75u6JGRBAEQRD6VL8MRCRRIyIIgiAIR4V+GYj8TCREBEEQBKFv9c9ApCMhIiIRQRAEQehL/TIQEX1EBEEQBOHo0C8DEdFHRBAEQRCODv0zEPmZSIgIgiAIQp/ql4HIz7NmRB8RQRAEQehb/TIQ6SBqRARBEAShT/XPQETUiAiCIAjCUaF/BiI/ExkRQRAEQehT/TIQ6awREQRBEAShL/XLQKSDyIgIgiAIQp/q34GIIAiCIAh9ql8GIh1DMyIjIgiCIAh9ql8GImLWjCAIgiAcHfplICLCEEEQBEE4OvTLQORnYmhGEARBEPpWvwxECpt8LIqdwUrziL7eFUEQBEHo13R9vQN9ocEdpCBsEHHBpr7eFUEQBEHo1/plRsQTUADw9884TBAEQRCOGv0yEClr8QPQqrX08Z4IgiAIQv/WLwMRTce0GTF/RhAEQRD6Uv8MRDQiABEEQRCEo0G/DES0GrHonSAIgiAcDfpnICI6qwqCIAjCUaFfBiJiZEYQBEEQjg79MhDRikhEEARBEI4K/TIQ0XTUiIiARBAEQRD6Ur8MRLRSv3zbgiAIgnDU6ZdnZDF9VxAEQRCODv0yENH2y3ctCIIgCEeffnlK1oihGUEQBEE4KvTLM7LIiAiCIAjC0aFfnpJ1kpg1IwiCIAhHg34ZiIhiVUEQBEE4OvTLQEQ0NBMEQRCEo4MIRARBEARB6DP9MhDRaPrl2xYEQRCEo06/PCOLWTOCIAiCcHTol6dknRiaEQRBEISjQr8MRDRi2q4gCIIgHBX6ZSCiFWMzgiAIgnBU6Jdn5I5ZM5LIjAiCIAhCX+qXgUjXGhFVVftwTwRBEAShf+uXgUjXRIgi4hBBEARB6DP9MhDRd6kRUURGRBAEQRD6TL8MRLoWq8qK0od7IgiCIAj9W78MRDTdakT6cEcEQRAEoZ/rl4GItmuNiMiICIIgCEKf6ZeBiE6r7fh/UAQigiAIgtBn+mUg0nX1XVlMmxEEQRCEPtMvAxGdpmuxqghEBEEQBKGv9MtApGtGJCiLoRlBEARB6Cv9NBDp/L/IiAiCIAhC3+mXgUiN09/xf5EREQRBEIS+0y8DkbJmb8f/RRwiCIIgCH3niAYiDz30EOPGjcNmsxEXF8dpp51GQUHBkdzkYdFIXWfNyH24J4IgCILQvx3RQGTFihVcf/31rF+/nsWLFxMMBpkzZw5tbW1HcrOHJGpEBEEQBOHooDuSL/7jjz92+/nNN98kLi6OLVu2cNxxxx3JTf8qqcv0XVEjIgiCIAh954gGIr/kcDgAiIqK6vV+n8+Hz+fr+NnpdB6R/eja4l0Wi80IgiAIQp/5nxWrqqrKrbfeytSpUxk2bFivj3nooYew2+0d/1JTU4/IvnSrEZFFICIIgiAIfeV/FojccMMN7Nixgw8//PCgj7nrrrtwOBwd/8rLy4/Ivmi61oiIjIggCIIg9Jn/ydDMjTfeyDfffMPKlStJSUk56OOMRiNGo/GI74+ma4t3kRERBEEQhD5zRAMRVVW58cYb+fLLL1m+fDmZmZlHcnOHTeo2fVcUqwqCIAhCXzmigcj111/PBx98wNdff43NZqOmpgYAu92O2Ww+kpv+VRq6rjXTZ7shCIIgCP3eEa0RefHFF3E4HEyfPp3ExMSOfx9//PGR3OwhSV0WvVNUkRERBEEQhL5yxIdmjkZdRmZQjtJ9FARBEIT+oF+uNdO1RkQ0NBMEQRCEvtM/AxG6Fqv24Y4IgiAIQj/XLwORbg3NxNCMIAiCIPSZfhmIFDW4Ov4vFr0TBEEQhL7TLwORNl+w4/+ij4ggCIIg9J1+GYjotV06q4qMiCAIgiD0mf4ZiOi0Hf9XRCAiCIIgCH2mXwYiBm1nICKKVQVBEASh7/TLQESv7Zw14wuIGhFBEARB6Cv9MhDRdQlE3P7grzxSEARBEIQjqV8GIl2LVd1+kRERBEEQhL7S7wMRT0AsvysIgiAIfaVfBiIGXefQjMsnAhFBEARB6CtHdPXdo5XiDDLBq8MtqaJGRBAEQRD6UL8MRAJOP8d59dRqFUrF0IwgCIIg9Jl+OTTzc42IpIpiVUEQBEHoS/0yENG2T9+VAJdPDM0IgiAIQl/pl4GIoeUAEApEGtpEICIIgiAIfaVfBiLaoAsIBSKN7oBY+E4QBEEQ+ki/DETQdA7NKCpUNnv6dn8EQRAEoZ/ql7NmNJrQonc/dxPZWekgLdrSdzskCP8HKbKCs8HLzhUV1JU4MdsM6AxalKCCqoI53EBsahgmq56YVBv2WHNf77IgCEehfhmISL8IRLaWNXPiiMS+2yFB+D9CDihUFDSz5YcSqoscv/n5Y+alM3JGKpZwwxHYO1BVFV9RC55djUh6DRqLDlQwZkVgSLMhSdKhX0QQhP+p/hmIaCVARWovDVleUMfdJw4RBylBOIi2Fh9fP7WN5hp3r/fbokwk5URQXeQgKctOdEoYdaWtOOrceFoDtDZ5Adj6Yynbl5RxzPwMhk9LwRSm/132T/EGcS4rw5NXj+zw9/KIUiSzDkOSlahzB6ENN/4u2xUE4b/XPwMRjRYIIhHKihTVt7G1rJmx6VF9vGdCX2t0+ahq8TI8xd7Xu3JUaKx0seydfOpKW7vdrtFIzLxsCEaLnqScCPQG7a++jqPezYZviinf04S3LcDGb4vZ8mMpUYlWpp49kKSBEf/R/sltARrf3o2/ohW6tATShBswDbDj3l7fcZvqCeIrclDz5FZsU5KwTkhEazsymRlBEA6fpKrqUTtlxOl0YrfbcTgchIeH/26vu3fFapZ+6KdVUnk90kdAUTlheAIvXDj2d9uG8H/LrkoHS/PreHNtMS3uAACRFj2JdjMvXTS239UQ+b1B1n1ZxK4VlT3uyxoTy9SzcwiL/O1ZBb8nyMqP9lFX6uyWXYlNszHz0iFEJ4cd1uuosoprdSWOhSWhinNAazdiHh5D+Ox0NMZQYKQqKmpAQXH5qX99F3J7ZgZAY9URc+VwDEmHt01BEA7fbzl/989AZNValr7vxSWpvGT3ohKaSLPyzuNJiexfJ5z+TlZU3l5bwn0L9vBr34QTRyRy2+wcBsT+/33SUlWVivxmFr+1B48zNMRhtOg49twcso+JQwmq6I2/nv043O3s21DDkrfyO26TJDjpxpGkDY3+1ecGGz00fVSAvzyUpdFGGAmbmkzYlKRDDq8qfhnPrgYcP5SgtIbeX8QpWVgnJf5Ph2bdATeSJGHSmsSQsPD/JRGIHELB2o0secdFm6Tygt3LoHgbBbWtXD4lg3+cnPu7bUc4upU0tHHte1vYWxM6oR2XE8vc3HjGZUTxwYYy9tW2sraosdtz7j15KJdNyeyL3T3iWmrdfPP09o56Dlu0iYxh0Uw4dQBGy+9Ty9Gb8j1NfP/SDoLtyy0MmZLI5DOyMVm7b1NVVdxb6mj5pgjVLyMZtYTPSiNsavJvPpnLDh91z29Hbg+2zCNjiTxjYEcm5fcUkAN8d+A7ilqKeHvP270+xmawMS5+HDPSZnBK1ikiOBH+zxOByCHs27CZxW868Ugyz9n9JISbqHGGDr5PnDOSM8ak/G7bEo5OFc1upj7yEwAGrYZrpg3g1tk5PU4AQVnh+1013PThto7bBsRY+eKPk4mw/B+vL1BV2PQagaJ1/Lh9MmWOAR13DZqYwLQLBh2y9uP34vcGWft5IbtXVQGg0UpMOGUAo+ekIUkSijtA85eFeHY2AGDIDCfq3EHoIkz/8TYVdwDHwhLaNtWAAro4M9EXDkEfb/1d3tOexj18uPdDqtuq2VC94bCfZ9Ka+MOIP3DFsCvQafplGZ/w/wERiBzC/k3bWPR6M34pyNP2UD3AMRmRbC5pxmrQsvyO44m1/f9fVe9XFLSShLafXX3VOr1MfWQZAVklOcLMZ9dNItH+6z0uGl0+nl1WyFtrSwCYlhPL8xeOIcz4f+xEsX8xbHwVHBVQt5v6QCY/tPyZVjkeAC0+zo25lchYA8y5H4ac/D/dvarCFn56dy8ttaH6kYzh0UwYHIF/XTWKKwAacGdFUmnUUlfaitGiJzLBwoDRsSRlRaDV//Yejb5SJ43v56M4/Uh6DRFnDMQ6Ou4/2v+gEmRjzUa+2P8FC0sW9vqY07JPo9nbzOi40SRYE/iq8CsOOA5Q567r8ViDIRF77Gk4jSOoCIaGBSfarYwKtzA8zMzJcREYNP2zL6Vw+FRVpXV5ORqLnrAJ/5tWFSIQOYSirTv58ZV6ZCnAE/bQWjNGnQaTXovDE2ByVjTvXzXh/7v0aKM/yKPF1bxXugtb4ysE9Sn4zSORLWO5OjWOu7OS/r8PSqodHs55eR3lTaFuuh/+YSKTsn69JqGrb/KqumVHPrt2Esdk/B+YbaWqsOReWPMUAC45ip3uE9jhPoGgGgrCrJpGzo6+Hau2pfN5uWfAif8GSxT+oEJxQxur9tdj0msZmhROndPHqNQIEuz/eWaix64qKhsXFLN5QQkABgnGWrRYdRo2u4K0yL0fskxWPTMvG0LG8JjfvE3Z5afpowJ8hS0A2GamYZ+dfvj7rKosKl3E45sfp6atptt9AyMHcu2Ia5mTMafX57YEgrxQVsdHNU00O3dgdi7A6N3R/fWR8Njm4LafjqrpnrG5OiWWLIuR6VE2UkyG/++/w8KhqXKonw4aCUkn4VpViWd35zBzzOW5mAYd2eOWCEQO4UDebn54sRZV8vO4XcZu1uPwBEiNNFPX6sUXVHn4jOGcNz7td9tmX1vY4OCe/ZXU1X9PWPM7SHT/tbfZz2Rc2lm8O2ro/9dXWLd+vJ0vtlViM+r49sapZMT89jT8V9vKueXj0IlicJzEY2cNYljqgKM3cPW0wFfXQcH3ALQEE/mm7XFaPaHC7OScCGZenI0tNhxaa6BsHax7Hiq3girjUK08E38/n9Wn4PAEery8QafhiimZ3DAj+1czRKqqUusP0uAPUOj2kWIy8FZlAypwfmIU1+0pJUqv44Phmdi3N7Lvi/3ktcm4le6vE5lgIeCXcTX5ANDqNWi0EgGvDEDq0CimnjWQqKTf9rtVFRXH98W4VodmCkWckkXY5KRDP09V+ffmf3er/0iyJnHD6Bs4PvV4wgy9Fzh7ZIXbC8r5oraZXx6EJaWN8IZnMXh399yeZCAh/S/sUgb2+rojbGaeGpzG0DDRybY3sqLi8AS49r0tFDe0kRFtITfJjqyopEdbGJcRRXZcGNb/a9nOdoo3SO2TW5Edvl99XMzluRjSw5GM2iNy7BKByCGU7NzLguer0Eg+HrErRLUX4jW5Q9mQtUWNGHUa3r1yAuMz/w9c7f6KgjYv0zbuBVUhrPltzK5lHffpzYMJePZ2/OwzjeDs0Q/zQE5qX+zqYVFkmebqKqKSU37zl+eF5YU8+mMBAJ9eO4lxvyGT4XaXoqpB6usXU17xFhUtKv9Y+2f8ihGdFOSuCU+Saa9m7JgPsdvH/Kb9+q/JAfC7wBwZ+nnXF9BcDFP+BHu/g29uAG+oC2rh0JdZujqBoF/BHG5g7Nx0hh2X3OuQRuuBTfzpjSUsCY7ocV+szUiL20/gF9mJyyZncNPMgURZDQQUlbUtLr6vb+HtqsYer9Gb3BaZ2/d6Ge4IRR+VQZmdbQq+9s2ERRo58fqRxKR0P7nLQYUVHxaQv6a647bIBAtzrsolJsV2WNv+mePHYlqXVwBgHZdAxBnZ3f7WZFmmpqaGLTu2sKB1AWs9azvuS7Gk8OKcF0kPTz/o36esqly9u4SFDQ6C7e9roMXIpIgwhoaZuSQpml0uD0OsRjzBNjRoeHTTo3xZ+GXHa+g0OmakzWZQ2hXs8VpY1+Ki1Nu9kVusQcdEexhPDE7Fpvvf1PocrVRV5cddNTy6sIDihjYkiV+dJQfw9hXjmZYT+7/Zwd+B4gni3dtE6+pKApWubvcZ0mz4y1p7eZYKWg2Jfxn/u/fUEYHIIZTu2cd3z1Sgw8vjESoB4G8nDuGBBaGphEMSbOTXtGIz6fj46kkMTfr9tv2/tLPVzRnbCmmVFcyObwhzfArAmLgxvDb3NfQaPasrV/P5vs9ZUrYEAFfEuZw1+FIezfntJ/ojIeD1UrBuFYWbN1CxZyc+dxsA9rh40oePRqvXEx4Ty8jZJ6A3HXx4oKzRzfynV9Lml7n++CzumDv4sLbf4thCZcUH1NR+1eO+UmcK7+w5lxJnOnajg39Oephw2jBv0mDZF054xDCo8+HNy8M4aBDmESPQxcaiS0zAnJuLcch/0c23rSGU6Vj1OOR9GLpNZwKDFdztJ32tCeRQEXaDZgRf1P+DQCAUcCQNjGDW5UOxRfX+mW0sbuLPn++guCH0ecfTxDW67zg/rhzzqY9D+mQCsoInIPP++jIeX1TQsYp1mFHHK1eO54nGRla3uHp9/V8yyCoXl/i5rjB0Mg1I8HamgZeyDegliatMNgZ8X4uz3ovOoGH6BYMYNLHnWHd9eSurPt5HdWFn+/mJpw1g1Kw0tLrDy/SpqkrTxwW0ba+lStOMLs7Cdy1ruz3Gr/GzLm4dDeZQ8aykSgxvGs5AZyhLMXr0aIYNG0ZqaioGQ+cB/t7CSl4q72yyZpAknhicyunxkYccUqltq+XVna+yqGQRzb5mIBSQRBgj+OuEv2GwTeDcvKJen/vnzATmxdgZchhZElVVj4rv/u9lV6WDOz7bQX61s9vtFoMWi0GH2x/E7Zd7fe7/hVlyakDGubSc1lUV8IsLA+uEBGwz0tDZjQRbvHh2NaIGFJwLi7Fqvydc9zEeeRyaM57FMib+d90vEYgcQuneIr57qhQtPn6IkMhD5uEzhrP+QCNfba9CkiA9ykJJo5toq4HXLj2G0WmRv9v2/xc2tLi4eOcBnEEFrb+C6Nq7UVWZm0bfxFXDr+pxoPlw74c8uOFBALyWSdwy4X6uT/vPCvZ+Ly011Xz12H00VpQd8rEmWzjTL76SnIlT0Bu7n1yd3gDznlxJlcNLblI4394wFY3m1w+0Xm8VxcXPUl3zJaraORyh10eSnn4Nen0kElr80gDOeLmaRo9MlN/BUyufJtbl/JVX7qSx2TCPHIlp8CDsp54KFhv6xPhf3ze/Gyo2wZfXQmvVYW2nIZDO103/wquGvkNj5qQw4dRsNNqeJ+byJjfPLSvk860VBBWVcJOOP88bzJmWPEwLbgBf+wl+9EUw/9FQ4AP4gjIP/LiXt4rrCEYaUZJ79uNJMel5JCcVWVUZHW7h85pmTo+PxFznofXz/ajtDc72WiWeyjSwObn7FZrNr3LRRjcxlaGUc1puNDMvHdLrujXle5v45qntHT9HJVk5846xGMyHTrc3NTWxfv16DuTvp6G1udt9Kiq15lp2Re7CYXSgVbWktaaR7cwmPNDzGGWxWJgxYwbLK2t5zxBBjalzuCjOoOOL0dlkW35bfY2iKmyo3sCTW54kv6mzD0tGeAZvzXuLFtVKlF7HpzVN/LOoquPcJAEP5aRwSVI0mi7ff8UTxLm0DO++JlAg2OABCUxDotGYtBjSw7EMjwGthKbLcEXTe+/j3bULrT0c15o1yI1NJD7wAKrfjy4uDq0tDH1SEhrrbxsicztaQp+dPeI3Pe+XZEXltVUHePjHvd2yH7fNzuH8CWlEWgxo279rqqoiKyoqsKawgcve3NTx+NNHJ3PPSUOJsh49s+QUn4zqC+IrdtL04d5u9xlSbdhPGoDWbkQX0cukC0VBffdspOIlHTd5Z3+BacrM33UfRSByCNvzClnzYhkSQWoi4B0CnD4sgYfOHcVtn+axYEcovavXSh2p58fOGsFZY4+OLMGhLGt0csnOAwRVGGbRYqv9F4XNe5meMp1nZjzT63tQVZXrllzPmqpVADhi/sS/x57G2Ql9MzRVvnsHXzz8T4L+0EknZegwJpx+LgC2qGhqDxTSXFOFx+kkb8kPHXlWjVZH+ohRjD/1LOKzBqLTG7jpo+18m1dFlNXAJ9dMJDvu4Kl6WfZSWfUhBw48hSyHrubDbSNITDqbcNtwzOY09PpQ+3d/SQk1Dz3E6t1V/HXqtQDEupu5e98nZKe24vVVophB65SQ7SpWbzJWXQZqmw9Pfj54vT22Xx89Au+QSaRfdTY545OQugYlnmZ4+2So2dlzx4ecDAEPZM2Abe9D3W4CipH1rovY4T6p42FzIx4le2QUnPd+qINYu4Cs8NmWCv717R48gdDV4bEDY3jsrJGdhajNJfDDn2Hfj53bPOddkCSWNjq5alcJHqV7QUe2G1bOH4Gml7ojVVZo/akc55JQoBlQVXZ7ZNriLMy8LBdjgpl8l4dyr597CitpCshIisqMnR4m7w19dqb0MM6/YRSWXtLKrmYvhVvq2PhtMQGfjM6o5YzbxhCb1vvvPxgM8vHHH7N///7e77d4WJm8juZgKDgx68y8MvsVhtiHoCgKPp+PvXv3sn79egwGAw0NDShdPg+/VseqgSOxD8jmkaEZDLaa/qvCUlVVWVe1jmuWXNPt9inJU3h46sNEmCLY4/LwflUj71Y14m//jkjAM0kJTF9dj29/y2/apj7BiqoG8Gxdi3fb2xD89ToEgNibbyLmuusO+biyXXlU7t3Dxq8+RaPTkjw4l+Jtm5EkDebwcOIHZDPvulsOK0DZW+Nk3lOrOn7WaiQunpjOlVMzSY06dNNKX1DmqSX7eWlFEaoKCeEmnjh3JJOzfnsh9O9JVVW8e5pofHdPj/tsM9MIn5kGEgc/T5WsgY8vpEQ1c+PgvxImu7m/8BlSjvknxpln/a77KgKRQ/hq+R4qP6pBQSUpQuE2/CRYDKy7ZxaKCnd+toPPt1b0eN6lk9L5y/whmP9HvRX+Ex9UNXJ7QTkKMC8mnLn6rTy44Z9ISHxy8icMjjr4kIRP9nHBggvY17wPRRNOa/JjbJk6jljDkWtm9UuqqrJ37UoWv/wsAZ+XxOxBnHzbXdiiDn4AKFi3mu+eerjX+1wTz+HN2mh0GomPr5n4q+sJORzb2Lb9UmS5reO2nIH3kJJyCZLUeSINVFdTft0f8e3tvBKptkTxj2OvpdwchU4j8e6VExiXbqS2bgF79/6123bqtl2NY/8QIhqKsbnKsTsOEN2czy/Vxo5GPulSRl00hegDr8DSf3beGZEWml6bNgmcVZA0KjRc8+llULKKiuBYfnL/Cac7dDVqNzZzWvabhDV2HpwZOBfOeBmPNpw/vr+FnwpCQwYjU+xcNz2LWUPi0Wk1eGSFd6oasGg1bGhpI3Ln+9yb/xhaFLySnpFTvsGhDR3cNcDxkTYOlDmo2lSDFFCZkBnFSxeNJbLLFWWgpo2mTwoIVIU+66agQp5PYcj8DEbPTUf7i2yNR1YoaPPyXlUj71U3klof4IKVrRiC4DNIjDgtk1kzMnr9vRZtrWPZO/n4vTJavYaRM1M55oSMbj1S8vLyWLp0KU5nZzYrJyeHkSNHQkuAHzZ/wQfh3xLQhGbZzc2Yy21jbyMx7OBTIYsam3hkwWISD+TT9bRgNpsZPXo0xx9/PHr9f//dcgfcvLPnHT7c+yFN3qaO2y/LvYw/jf0TGklDUFF5pqyW1/ZWcfduL8fV9z4U8TNdrBm5xYcaUA76mEDlFrzb3kEyWFDdv14DpI2KQp+cTPxf/oxlbOdSGqqqsuqDt9j0zeeH+W4he9xEjr3gcqKSknu9//mfCnlsYUHHz7fNzuHa6Vnoe8kAHsrWsmZu+nAbFc0ejDoNfztxCBdOSO/IpPyvKH4Z19oq3JtrQxmrXwibkkTEyVkAtAVl3IqCRauhyO3j5vwyBliMyK46NjvcRAac7Ld2zggb2FbCYoMP05xzf9d9FoHIISxYs4+SdytQUZmbKHGKx4OH7gWMr648wFtrS6hs6flLP3tsCvedNgyT/vACEk+rk9Id22iqqiRlyDBShuSi0f7+wcz7VY38eV85QRVOj4vgthQNp391IgDXj7qea0dee8jXCMgBzvr2LA44DuAJm0Va6jUsG3949RS/h20Lv2PZGy8BEJWcykUPPvmrtR8/87a5MFqsNFVWsPWHr9mxdCHlxiQWxM8noNFz1Qgbd19w3EGfX1b2BvsLHwBApwsnPv4UMjNvxGjoDIBkVxvO776j7tFHUdyhYQTTyBHE3347usQk3jrg44XlhbS4A2ik0BIoc3PjybQrNFevo1kpY0TMbrIiSjBoA7Tuu53k1HkkZNlp3b6HwKY1GBa81W2/AjoralYUuUM2oTMpYE+FU54JZT66aimD58bj96ssaLmbKn+oQ3BYpJHpFw0mPbd9ivK6F2DhXR1P+5Gp3K25kQa3jE4jcd30LGZOSOGHRidlHh/1/mCvdR4XV33DY/v/zSvJZ/H37Bt7/UyPdUlsW19JUFbJjLXywgVjGBwX1r5GTCkoKn5FZa9Xoc6s5cTrRx00W/EzVVVZ0+IiQqflpc1lxC2oIdoVOlnmZRg47eKhnJDcM9j0ugL88PJOqtozAPGZ4Zxw3QgaHbV88MEHeDyh77ler2f8+PFMmDCB8PBw9jfv57IfL8PpDwUoWd5U/tV4A0Oumo4+7uBX1vX+AOflFbHb5UUnBznTpmdmbSlbt27teExiYiKnn346cXG/zxCoO+Dm3nX38kPxDx23WfVWXpr1EiOjRuAraqHh/XzwdwYXK2O1eMbFcfGYNHQGLd69TZiHRCG1H9uaPvqE+qfeQGONRZc4Gm1EOpqwnvsbrN6GKSdA69IFmEeMJP6O21E8HsquvppgVXWPx0dffTW6c87kq8cfoLm6+3pGE04/B61eT1NlBS01oeHHhooygr7u2ZeRc05k5hXXdlz9K4rKvxcX8PxPnXUyd584hKuOHcB/w+EJ8KePt7Nsb6jPy6QB0bx+2TFYDEd2Vo3cFqB1WRmKJ4h7a/ceM7o4M5JGwjI2nrCpyexz+7BqNTxbWnvYheFdLfYXMnyuyIj06kgFIos3FLHvzVIAZg4P8Ey5xPcEGJ8RxcfXTOz2h/3C8kLe31BGtaN7Gl0CVOAv8wdz6aSMg2ZJWmpreP+uW/C2dT+Yx6ZlMPePfyI+M+u/ei+KorBmzRrWBiSelEIzCU6Li+D5IWncuOwGVlWGroBXnLuCKNPhDbNsrN7IlYuuREXCGXsrT4w5hbP+B0M0+auX8/2zjwMw9LgZzLj8GoyW3z691iMr7Cuq4Ny38vAqGhK91ZxV9x3HnnsR0Slp6I0mWhvrsdgjiEiIpazufhoalgJgMiUzauQbWK3Z3V7TV1hIxU034z9woOO2uDvvpG7+mTz3UyHVLR62lrUc9j6G6V1MTtrItcelkJR8MQkRoYBHVVUaXnyR5g8/JthQj9Tx9VQxJGhwXPwkIy6eha7r31t9Abw2ixLHQNa2XkazHOoMPGhCAsedl9OzLqJyC4XfP8M9xbmsU0IBi9EIwVGxtEX8+ji4hm6L3HY4t+YH9ptT2Wof1u12yRXAsLkByaeQodfytNlOtDOUVSj3utjpCTLw2GwmnZ6NHHBRU7SPyMSUg17t/tL7ZfVs+qyQgftCgUR9uJYts6K4dERyj79ZVVUp2lrPkrf2EAj6cMfsw6PtPGjHxcVx8cUXY7PZcAfcPL/9eb4p+oYWXwsAt4+8jbmrRxCsaENjMxB98RCMad2PS4qq8mJ5PQ8fqCbQ/rubH2Pn1dwMdBoJv9/PkiVL2LhxY8dzhg4dyumnn/67ZEcACpoKuH7p9dS6awEwa838ufRyJrSGfjeSUYs7w8a85CBt+tCxbniYmVeHZZBh7qwpUBWF8quuom3tuu4b0Osx5R6LIecC1C5BjcaiwzopCeu4+G4db735+TR/+BEtn3wCgCxJlMaEsz8+CrlLlmLWVdczYuZcpIO0D9i3YQ3fPvFQj9tP/tNf2G/J4l/f7abWGQpWJmdF8+KFY7H/TksTBGSFDzeW8dD3e/EEZCZnRfPUuaOIC//9+ud0pSoq9a/uxF/s6Ha7bUYqxqwIDAPsfF/v4IDHx5MltT2GRH/pGMcu/BodiXot84ZPw9BQi2n9chaVllFji+ayUQOZf8KZv+t7EIHIISzfVMDu10NRePKoPaSWDOcCXPiA5y8Yw4kjeqZbd1U6eP6nQn7Y1aVZkQoDgho0QFSclZzsCAbE28iOCyM1yoJFI7P6pccpydva4/UAIuITueDBJzCH/bbphYFAgPLycgoKCtiwobN1dJvBRPjJZ3L3sGy+L/6ev6z6CwD3TrqXM3N+2x/Zfevu45N9oQNHc/w9fDbxBCZGHLkF39xOB6/dcCUBnxetTsc1L72D2fbbfuctrS4WrV3DtyvXstuTTZMhiiRPFafWfodOPXgqWh8WIGFsPTmjz2bUpLt63N/0zrvUPvhgx8+6obmsv/KvvL/f1bFOzX9DQuHaY+O5Y/64zkLV2j3IL8ykOV9DS6GFgLszmPDEZpHw7ydJGj8QanejfHgxCw6cT5k/lPKWJBh+fApTzuxZkOoLyjz9UyEvLy9Cbq9/ulS7kLt0H/BQ1h94OeUckCSyLUbOiI/ErNEw3GZmhM2CSSOxoK6F6/K7Fw/rVJnt604nSm5j4fAbuNJ+CoqkJcWkp8IbQOMOcPk6J5f7JVZWf0CzvwaDLgZ/MDTjxBoRSWRiMhX5uzpeU6PVochBxpxwKkOmTCMhO+dXP8N315RS+ekBbF4Vvw5+GGMlcnQ0Dw9KJdPSeXKVZZlFC5axYeuajtui7LHMmT+TwYNDmb8SRwlPbHmCn8pDSwBkR2Tz+tzXiTJFIbcFqH9lB8FaN5JZR/QFgzENDBWye2WFW7bmU7NuA/vSMolJTOTpIWmMDu+ZOWlsbOSzzz6jujqULdBoNJx//vkMHNh7b5D/xIryFdy47EbU9i4lMxzjuSvlT8SfPBRJr2Fvm4ezthXREAgFhtF6Ha/mZjA5MoxgczO1Dz2E85tvO14v5fnnMI8ahS46lF1T3AHcuxpo+aKwx7btJ2RiGhyFLtIIWg2SRkJubaXis0/47ptP8LYP92oUhcQWF7Ouup6Ycw9vaKBg3WpWvPs6rY31eDQmvko8hQZDZ1PCyyZn8LcTh/xHQzGH8t2OKm74INTQcGhiOF/8cXKvmXFvW4DCLXWU7GygrsRJZIKV2FQbORPiiU21da/96kINKjiXldG6ovsMGK3dQGByIq8madjl8rDR0fbLCTIdpkXamBZlo622gHFr72Vyy3YMapD6rAtpzDiLBc890eM5aXPnc/YV1/8Hn8jBiUDkEDYs/o7Nn7cfHHJXcFr9XF7zt/EmfpIjzCy9bdpBh128gSDvrC3h8x8PMLJVIj3Y+TiHpPBlmJ96begjnVO3mEFthahIbBl9GSOHZnPamBRaSgvZ8ubTeFudWOwRnHTlHaSMG3HQP85f+uabb7qleLuKjo7mrLPP4up1V1PiLOEPw//ATWNu+g2fTkiTt4lpH08DQNZGYk5/kNWTJ2M+Al9ugC8e+gfF27cAcNkTLxKdfPi9TIJ+P699/wNNn7+Dwe/jo6SzaDDGYpY9nFf5CWGy+9Av0i41dwR+j4fIxCRmXnEdamEhJeedD0BbdDwPTriMrYaevQXGpEUwLSeWmIYAX+2oxuCSyTfKNGlVMsNNPH3pWLx+haY2Py1uP4vza1m1rwa/3P3z/ONxcVwWWUTcwvYCREMYyimvUvvtTlrefqvjcbJGjzRtOjHx21nZeCF1gdAJLDzGxBl3jMVq73Jlq6o8UVLDm3mV+Hc14Xe1zwKK0PGE/BxnBFZ2PPZAzBhqw9IYcfojWO0J3fbtut0lfFnX0u22WdHh3JAYzsTvr4DiFaF9y5qJ9oJPQKvDU9XCNw/+m6amQtzyfx60RSYmcc4/HsZqjyDo9/c6XPdTWRPr3tmLvSKUvdyeYWDzRDtvjskiS5LZvHkzW7dupbU1tB96jQlzYxZGXzSDJycy9exsltcu465VdxFQQp/RmQPP5K4Jd2HUdglmnB7qnltJoKoVX8EC5IZdNOdkE5G3vdv+RJx3HrrYGEy5uYQdd1yPK32v18urr75KY2MoKyNJEpMmTWLWrFm9Fvf+Fqqs0vjObhz7anku4SOWRKwHIMuexfOznic5rDPjVOsLcPGOA+xwhbJKk7QqN//5RuKbQ/sVe9utRJx1FrrI3mcOqgEF2eHDsagEz46GHvdbRsUSdd5gag8U8sm/7sLfPgwWZrIwYcsejMHOi4T4v/2NqIsvOuT7C/h9vPPe1zy8V09AE8riDbAEee/qKSQlHNmC0rWFDVz/wVaa3QHSoiw8dd4oxrTPqpQDCgtf20VxXs/P4Wcmq55pFwwie2znEJfiDuD4oQT3jnpUX+jzCEpQNi+FcxTHwV6qQ4pJz33ZyQwyQ5rZirrrC0oW3kGt6qPVMpjGuhxq9/UcIvtZ4vEzuODaWw/3IzgsIhA5hK3Lf2DdR6EDS2DAYi6MuoCGwiYuNfmo8wa4Y+4grj8+u9fnBv0y37+0k/I9Tb3er6CyxBygWNPEpRUfALAyagp59u5NoeJ8dcypX0JkwAFoOGH6bQy+5rhfDUZUVeWDDz7oVtW/M3kArUYz87VBHPtDBVo7onaw374fi87C4rMXE274zz67KlcV5y24gGZvI17LJEYNvJOPR2Z1m/r3e9jw5Ses/ugdNFot5/zjYZIHDTms561udPD2p5+QvnYRZp+HoKRlUewsiqyhMeG548OYFKzBodGyOyoRR0sL4ZtWMvhAqFulOdaDL8uMsr731x9Q28yguhak9rTnJbP/Sr21M91v0ms4ZWQS545LI8ohs/y9vbidfrx6CW+4jnXjbezeUo3qV1AtOszjY/GatWSajeSGmTk+IgxHUz0N+a/ywpbOmg8tMs/on2NmTDOmy74Ee2ioxVdURM3HX+P4/HP0bU0027PZPupGVCmULckeG8eMS4ag77KC7Fe1zVy7/QD6Hc1oG0Npa9WgITDIjpJoBknipJhw/lTyFrlbnu5880NPhXPe6fjx05ombuySCTkvIYoHcpKx/lzrFPDA8odh7bOgyrhTZtAQcSsbf1hAqasz0/GzclMydbGJ+GOsWD2tjNi7lcaIWC66+TYi9XpWf/QOZbvyDvq7n3r+pYw/9aweswMURWXddwfY/n1o6NWvhbwBMilt69EpoQO8RqMhPT2dk048md1LGti1ooKqsCI2D/ieSkvo6t6sM/PE9CeYmjy187Xb2mh47TUaX3zpoPv1ayIvuZjIc87BMGBAt6CkpKSEDz/8EF+XGoj58+czYcKE/2g7sstP/cs7CNaHTvgKCi8f/yPf1HwHgN1o58npTzIuYVzHc1qDMn/ZV8HntaEZQZKicNayH7jJ20L2448e9mzBQJ2blq8K8R3ofvJsGepk+fJ38LW1ERYVzZgTTuWYk04nWF1N/dPP4Pj6647HJj/5BNZjj0Mb1vuwbKs3wJOL9/PGmmIArEEXI507Ge3IQ4PKpLPOZ/LZFx7mp/WfWVPYwKVvbCTY3jvn1tk5nJEczbfP5KG032axG8gaHUdEvBlPa4DaYgfl+Z3TwXOzG5icshhdzW68LbFIsgudVE25YSiP59zCF7G9Z6BHOfMZ3LaPxrAkcuMUKt27MGgMLCpd1PEYi0fL+PxIIp0GbB4dGrX7709nmkJ8WBQ75C1EN1ehGzuOm+/8x+/6GYlA5BDyVv/I6vdCUbQ7bSE79CewqrGzhkOvlfj0mkmkRlnYX+diWLIdi17B6/by7dN7aSh3odFI5EyIJ3FCPA+s2kd9o4dRFXJHhqQxsA2r6ycchghKp99IQa2rY4Xfju0oAc6s/opYfyh6Xpp+AXs0drSSxFXj0vjDrGxiuoxBfv3112zb1rnOyRtTTsCvM7B6wmCyLSaWLl3K5q2b+Tj6YwLaABdnXMyd0+78rz6r3Q27OW/BeahoaU58iEeHjefCpMNfm+VQtv34LcvefBmA4y68nHGnHHoIac3+Ij595w1S93WeqLwaI18mntqRor3/tGFcNLH7WiGy7GXTjhsp+G43DbtCAUVAp+eH6WdQkZTBMy1F6F1Odi5dSE5NE9ntV/8NYSa2pidQEpZK/YhTiE5O5pZZOWREW2iqamP1p/up2NtMZZSWb8aH0WDvDASktgCGzY1IXhlVJ+EfHY0a1X1u//GRVrKCNbyz0IOmtbNnSVKYxBUJ8Qx2yowYEY91fCLacAPyhvdY9cRqdkecBZIGg6+FTHM1Ux68HHOEhTpfgI9qmnhwfyXaEhe6olYkFVQJ5DQribkxrJsaqg1xyTIR+vZhn70L4KMLOnfspCdZl30OjxfXsKZLweojOSlcmtz7VWf90lcp+uJN1jT0rClKyM5l8tnn8lCezKL8UPFdeIaNuhxbaDxJVUg0GbkhLY7xdivDbaGsZdW+fBY88zjO+toer5maO4J5191CeGz3AsrivHoWv7uHgCsUfHjMVTREVbA2eyjPzJvOyAhbx8n1xZ/e4IXSp0BSkVSJ01LO4s/TbsOqD50Ivfv2UffY47StWsXBaKNzkBv3AbBrWC7DdvVszf4zxWymZuhQ0v54HQOnTOm4fefOnXz+eefskVGjRnHaaacd9HV648lvpPmL/SitgVAvkEFRRJ03CI1JR7GjmFuX30phSyE2vY1/TfkXM9NmIkkSqqJQc999vFNez8ezT6IqrjMb9vmoLKZE/rbhY29hMw2vdQ9AdzStxBHVwun33IupS28RNRik9pFHaX733c4H6/XokxJJe+01DKmh7Kiqqtz6SR5fbute3PrV+QNo3r6ard93BjNTz7uECaef85v2+bcqbWzjtk/y2FwaCi5O95vIdof+pkbPSWPcSZk9Vq9ubXTT8N7dZDa/3nFbEC11hij+nXEZ7yeeRG+mNC5jWs1nRPhrqNfKfGmz4uhlwoPJp2HCnigyq7sHcaouFr1+GBp9OpImgjOj/0aiYS931Z1HTGMlgZGj+Mtf7/+vPo9fEoHIIWxf9S1r3g/9oipiV/Fh4JhDPmdq0kZmttpwl4/BbNMz7+phJA3sTFWqqkqt08urz20lqtyHqqr4Pct5P2Ygje0nxzCjluy4MC5v1fB2ixOHpBJoK+HU2gVA6Crxq4STu/V3mJAcQY3XT2mjmyHaWoZoazFKQX4cOQFfXCIrxg/uNr323V3v8uiWRzHKRk4sO5GLL7qY7OzeszuH6/IfL2dz7WZkbQya1AdZOGEsyab/vrlPY2U579xxA4osH/IqRlVV9uzYztubthK5fAGGQGc765bRU1lnnkhhdRsaCV6++BhmD+3eJbCh4Sd27vojiuJHkrT4i08lf00lSnvzsaVTTqQhawIz61xkv/c8kytDa8nkJSZTGddzGGDIsXMxhc9k7/pa3FrYOMjEmqFm5C4XHnadluMibWRotPy0pJjCqlYkvYaoCfFUWjVE6LR4FQWv0vkVtMkOArUKSlkQjaPzPb6IheHoMMbsYkt5I0W+yaFtOA8wfOdLGAJtOMPT+O6W23k1MRZNjQf93hYkXyibExdp4uXzxxARYyHOqOvMZPxSyWp460T8ko77BlzLqylnd9x1fmIUj+Sk9LoWkaIo7N+6jQWP/xNV7SycM2qj0EZaiZsxi7Fjx5Keno6qqjy+aB8vLA/Nbjh/fBrjJyVz+/4K2uTO596ekcB1qbFYdVoCfh/1JcWU7tjG2k/f77H9UXNP5NjzL8VgttDQ0MDixYsp2FuAxZWBtS20ZlSdXcPC0VZK4vWkmQxcmmCmpOxFfiwJzTJJdmczteAcogMJzLpsKOkJfuqeeILWHxf26Ae+ecx4Fg8fS0tYOAPDhvKnglA2o1BTzUp9Poqkog0Giaurw22xMCQ/n/TSno35nLGx1J1zNiNPPZW0tDSqqqp45ZVXOu5PS0vjggsuwHSImWOyy0/r8gpcaypBBU2Yntg/DEcf3/2E5A16uWbxNWytCw3tHpdyHI8d9xhtL75OwwsvAKCNjmbfex/zh5L6jjVwHmlvhPZb+ij99NLL1G3Yx5T407rdbh4VS/R5PWfiBWrraHrnbVoXLSZQXt5xe/r77+EamMspz63puJizmXTcMnMgl07OQNc+XFxfVsIHf7uto/eQPT6BY8+/lOxxE9HqjkwLgtJaF9OeDA1JalQ4wxrOg3dOwmD6RYG4osDie2DdcwA06cL5MWYqReZUPkg8keb23kRdzax6A8mzle16Z4+1wX5mVBSG+WSKA4kMKTSRVatF0+WhOTNnUZ2XQkDuvDAYblnAceGvERh9N39fVERMQwW+EaP4699EINKrIzY0s+ZL1r0b+sU3xCzjzeAkbtCbsQZU9mSF8W1Rz/G9XL+WE9wGkBRO/dNQUnJ6XwxLloO8/qcPCPhD6fTGcXZWtLRSVB/qlzAEDa8SRgCVy2gjZ2gsQ60+lE8fBVUmP2wQy6OPJaj59S+O1aLnxKHxpEdbmT4olqGJ4VS6KjnjmzPwBD0cHzyeqPLQH9+dd96JxXLoJj4H0+Rt4sLvL6KitRyfeQyjB97DB6OyDtqMyb15M4rbjSEjA21UFBqLhUB5OfrUVNpWr8Y8YgROr5v37/oTPncbacNGcNbdDxz0IOd1uVjwyrOUbOgsMGwzWUmYfzrH5AzhntVOdlc50WokXr5oLLN+EYRUVX3G3oK/oqoyGo2RUSPfJDJyAj53G9++9CylG1YD0BqM5dzdoXEaRZLYdOKlTPjT1fj2bqRg9U9U7Ok5xNASdzw/zj2ecmvoYKiV4MTYCM5PiOK4KFvHZ9TmCzLv6ZWUN3nQaSQempjJvDg7q/fU8qG5lSZzGZt/MeMkoqYGd5GExhUqJrwy6CLFo+KW49Agk2vWETcunF1LP2LQ+sXoZB+KpOHzobN5K2sGikaLPczA3fMGH3YzPllVeX3zcp5qlmjSRwAwzbGNq0dPZUZadq+vsX37drZ9soSmouXdbo8Oy+T0hG+x6Vv4lBPJJ1THYrfbmTZtGnmtFv75QygYOX10Mn8/PZd/l9byWkXn9y9Kr+X5IekcH935/Xc7HeSvWs7+jWuo3Nu9sVP0qHGU+VV+ju2ys7MZlT2F9Z+U43OHPsclI0xsTduFteUDtHIjGknLH0dex4UZl7Lyg32UbKslvWwRGTXL0XhDmSBDVhYBr5cVw0fy0Lyz8bZ379XJQU7OW82UFhPHBYaiQaLB3EbkBYNweFpZvnw5ubm55OTksHLhQlwbNxLZ3MyAogNY3Z21S3WxsTjPOJ2511+P2+1myZIl7NoV+ntLTU3loosuwmjs2SVTVVTa1lfjWFSC2r7on2VMHBGnZKH55cmwnSfo4emtT/N+fiigywlEc+fztYR7QGu3k71yBRqjkUUNDi7ZWdzxvAv1Co9NHoXqdqMNO3jhem1xEXtWLuvIUMQlZTJ33h8JrG3uqH9AAtuM3lc4VoNBSs6/AO/OUOO+3VEZ/Ov4P+LsUk81Yn4GuyWZNllhoMXIlEgbrUEZbVsrg5Z9jXdr50yfAWPHc9JNdx5WG4DDoSgydX6Zh4qq+biumbQqH75CR8eCkMdOSeXVE4Zh6lJPp2z7hB1LH+el1HPJCxtEsSWlx+uG+ZpBKSTS8RNtcjlauaXb/eFoGRo3iii0zHC2MGb/GrY1JfO9ayKRrgbC2vsfKUjsDB9GWORkcp1dOvnq9nNK3MMYR5+KK/yPtPxQy3OuD4mtL8MzfCR33/3A7/L5/EwEIofwzU8vUv7xIABcMYu46PZ/YPmpgrYNNZQPieD8/DI0ioyiCV01nlW/nmT9dAxIrLe4mTVjG5eedE+vr7352y9Y8d4bGMNPRtIOxBJu4JKHJlPb6mNHhQP9d8UMagnyPX4eJBTdR8sSF9ZtRfWGToKDwsfRmjaDuzK1BJ1+omubcPh6adX7CxFpXyBbN5JuGcHLx/6bV158CUmCc889lyFDDq/u4mD2Nu3l/AUXEFQCtNnP4PFJt3BGfGdGSPH58BcX0/Teezg+69KcqJfVpbQZGeycNJqSPTuwRcdw+hX3EDN6AJK2+0nO42rl84fupbawoPvzo2MZdf0dJMWkMufJUKFluEnHm5ePZ2x694K6ysoP2VtwNwA2Wy6jR72DXh+BLyizoqCeN1YfQLPle04vWsGwys4T4Ja7/s6Fl5zXceKVAwobv9vO9sVbcDeGDrArx89mw5hpHc+Z5m3hxWPHEXWQse06p5dbX9/E6lonWuDvmDlBk0+s4a+owG05d7DFNo2CX8yi0jR4ydnv5owyFS0SsuRjitVIfPtVXqsO3jZXMvvrV0lyhvoulIXFUXjB9Vxxw5mH3YCv1hfg0p3FbG8NnSDNip+/HHiFqys/RQpPgQs+goThBINBFi1axLatW9GXF6Nt6T5kEh42mrpIHYYwF2cbVpDhD/3+8hjC18xGoXN/iuUoVgWzUFSYkBnFM+ePJjLMwDtVjTxRUkNTe5fXuTHhPJyTQrxB361GqbIgn4/+fke37auSRNTkmYyfMZOhQ3PRaDS4nX7WflHIpm272ZD2LUUxoSHOoC6e1uhruX/4dC6yaGl6510aX3yx47UC5gji772XXanx/Lm4loqoUJBr8XmYt2sDca4WRo4cybx585DKvTS+twfVr6BPshJz+bAeC4kFAgH2799P6YED1H7+ORPW9SxQ2jBhPOEnn4zRbGb79u0EAqET3Mknn8zYLs3AAvVumj/d17GYmT7Rin1+Jqacw1uOYuGuL7l3zT9wmVSSG1QeU88i96a/ovp8BBsacK9fT9PX3/Bi2iDem38aAINKirjvpX8T6+isdQg/5WTC581Dn5xChbOJ755+BLl9n0fOOZFZV4a6qiruAE2f7ce7p3PKtC7OTNS5gzEkdw9sFJ+P5i+/4pNXv+LJMefi14b+1o/xFbJx3iT8hl/PyA7P38zsVd+gba/vsgwYiP/Smzg3M4UE42/PjlQ5S/i4dBtlchTfNOto4xffcVVFv6sZbVWoLieYbOGYScnMi4vgtQMVNAZ9eLQ91/mJCJYQbMtD4y/G4NmG1D45XqOqDLUkkRwzhKHl25hRvpuMYLDjeUscQ9hWHYumy7HVrTVzIHk8x0gODK7R+JXOv4O5EY+RPcIOM/+Oo8BGxbfFOIIqXwc/Ia6ulLaho/j7P0RGpFdHKhB5fOHDmL8cj4KCM34Bf/vnk/gOOKh4JY+ZtGKQA/xh5zc8P+pMUOF0l45sWU+V1s8HYTJGnZe3xvuYcOJ5SF0W0vK6XLx6w+X4PR5mXHETWxaZ8LUFGTM3jYmnZSE3+6h5bBOoYLl2OKsdbiqa3Di/KsfmU6kNbMPu+gmQmJ10CdWxSfxlqJ+T8laiVVWCKdPIGpKBQadha2kLW0qbqHF68QcVJHMR5rTXkCQVd8k1yJ7QQk3hkoehYT5uPn0KE4ccfEXQw/Henvd4ZNMjqEhoUx7k9WOOZ1hNJd7du6h74knkhoNXine1LS2O6vYx52Oj55EUPhIAfXIY+jgL+qQwPGY37z72p27PK8odx2lnnsOsIYP5cFMZ9323B29758feVsosLXuVwsJHAYXYmNnk5j6JVmsmv9rJvd/sZkNxE1pF5uqd33BKcSjb4jQZ+GryJN4+4w9Mi43gzdwMSjbXsfGbYlqbQoGjNwWWD/KzKSY0jh7ZUs+Z379LpDNUwDzprAsYf+pZ6NoPlqqi0rahmmC9h6a1lTyAh6WEDip3697jKt33qOZYuPxHiMnCrSg8XFzNjw1Oql0+Zua5GV8YSjfvi9GyIFLmuPoAf8OMAVhKkNfxUa7KTK/Yxg07vsQa8KBodITf+XdSLzubX/NkSQ3PldURo9d1rOB6c3o8VyTHEO+uCrWVbykFSYN/4El87h7HvuJqIutaCThLur3W0BkXM+/qc2hpacFqtWLQSvDZFZD/DQDNlgF8ojmNalfnYWdfMIZ1wQxUJBLtJl695BiGJdtpC8qctb2Iba2dmYMx4Ra+GzMQiVCR5/bt29m5cyfaplqMNWVd+q5AXEYWJ958B5GJyUiSxN7GvVzx/ZW0Kk4kVWJU1Wz81pNYP9hOWFszLz3/MNGVnR2Vq1LHs3jCfFaOjKM0yo7cfmEyoL6SP5lVph4zlvj4+G4zXPwVrdS/uhPVJ6ONMhFz6dAewyNdle3ahfu6PxJsbOw4af5swYkn4LJ1BqWSJDF+/HhmzpyJWuWh/uUdoWZGWgn7nHTCJicj9bKKcm+aP/qImgcepNIW4P7ztTSGS5iDGq5crHLc9kCPx3913GyePv8KIDTl9m9vPseMzZ1ZB1mS2DQgkab2RfViLTZyktIY9/d/ov3F2k+B2jaci0vx7GoPSCSIu2kMhsTQ57TJ0cbJm/ah2+dAVxa6yh9TV8Cdm9/H7nfjsIbx4GXX0zx+As0BmYZAkBi9jqZAELtOS0tQ7hjISK08wGkLP8Dk9+KyhNEQn8bck09l3DHjiTPoDno8VJQgzrYi/rFzBT/6BuGg59DJz9LUYuKoZTMT0O1zoisJZdHkBDOB4ZHQZQLCwJYq4jX5lPjW4vWWIqmdBcpjPQEG+70M8vsZfvzLDBg9H03FFlj/AhT8gBL0sc6ZxcqGARj8nfWGit7IxEQXejmVUv8EGoKdvanCtVVYwxdQkjCWk467mF2fFFLT7EMF9GG1FAbWEF9TgmPwKP71TxGI9OpIBSJ/X/xv4j8fzde5z1AdXsTfJ/2ds7LP4u37VnKvx8VVu77lzMIVNIaF8+TkW5nhj0VBZZGunv12HV7ZzPEpq9hZM52JQ+K44thMxqRFkrf4e5a89gJBezzfZF7AZVFR+LeFrhzmXzucqHInrjVVGAdGEHvlcADqy1r55MFN+HXw5EkRzFn5KUOKdmI3JTEh8TS+MG5DlQIYvDHoHEP4MMxHs1YlI9pCfLiJM8emkBJp5L6t11Ph3kukMpGyglOB3r9g6dEWpmTHkBlt5ayxKYSb9b+pXfHNP93GsrJFBPWptMb9nVceuIfM6p7t8I1Dh+IvLSPmj3cj6cLx7NmKe9UyKuVatmYkIKkqI8rrSAiYKT7zISRJoihMg1aFd+MczF7+BZFNnUVphuwTyQobgTY3mucO1LGzvX/HhAFRPHPeaOK7FPWqqkrRgX9TWhq6sk1OvohBOffi9svc/NF2luSHruCtfg8P5r1PTmWoVbt2xHB+0AcIBgOUJ6SzY+Q5zNovYW8OBQ1mu4Et82P5UvV0NPUaq1U4f+OP1G7qvjqr0WLF525j+Iy5KKUeaiuKmBh7Mla9HT8qz9LMl4RS5ydr1nLLxWeTNWRUt9doqWjkqyeW0+YOXdmszzGybIQFWSshNfvQFbvQNPqQ2schopC4FRNjLFqal75MVG17YfOUueQ88wDaXyw+JqsqT5fW8mhxTbfb3x2eyeyYzgOv0lSC75OrMNeEFgLb6x3FwtJYgkrnwdAalsQFjzxCeEwvV+MBL3z3J8j7oP3BcQTO+4jdjVq++uorABoVCwv9g/Cjw6jT8NAZwzljTAoeWeGrumb+VVhFc1DG5PcxqqmKETVlaLpclUdERDBhwgSitJD347eU797RcV/asJHUzYzllcI3UVSFBHMi86ovwZQfGl7VB52MzHuR8NYyPEYjnmOnIY8czi0x6VRFdAa3CR43Nw/N5LL0hF8N6P3lrTS8swel1Y/GqiPmyuEYkn69B4+zpYWiBx7AtGIldGkzX5idxZ6hQ5EsFtwAKkwPH0V2Q3RHLUjctSPRxRx6VV0AVZap+ee/OpqLIUk02FTuP09LVXToPf3hB5nZ27ufFuL+/GfeW7+VZ089D5fZgj7g57b3X2PWxtXU2q3sSo4hqAsFaimNToZV1KMBzGPHoouKJOKcczGkpaKLj0djMqH4ZVq+KuzWMdQ8OpY3Rtl4Ir8S/a7mjiFJOdFMRngzTz91H+afZxZpNKS//x6W0aMP+l4dgSAf1zTxdd5OJnz2KlZPZ8H15uGT8M8/ixeGDSD+FxmSjc1NfL3nZV73z+/xmoPVAoa6C5ni3UCLZhp1KeHs8JjYqQ7EpYaOQZpqN/qdzUgqKBEGAsMjUS06jK7VWFs+Qts+HVcracgIz+Ti+Inkbn6fQY1lNMkpLGi8B7feROpxT2GKKMPaGsSw3ciKoqEo7asEq8CgyCbGRdSz03s++7zTO/ZRi58BSQ1kjYpkf+oQrvs4HxXICmg4rc2Apv3ckDTxFdZtjyW+upjmocO5/x89m8X9N0QgcgiPr3wZw4cDeHViaN50vCWeRWcu5vj7lqDUlfPy0seRUGm50kh+61V46oay2RDgJ0tnasyo9WAztNHgCc0eSLHpOLXobTRtTlZHTWKbfRSocGNENKZSN8kD7YxzeFH9CjFXDmNzjI6CNi/FrxcQ0RjgkylhlMXpCW9t5qoPn0KryPhiEvHHJhOUzEiO0SS4dTRqVd4N8xLochzU2bdgTvoUFANzwp8A2Y5Bp8Gs16EEfSzclE+NEo7aS3ASZtRxTEYkmTFW3D6ZecMTGJseSbipZ/pSDQYpWfglF9U8glPnwxN2PNN3p3HbB6/3eGxX+uzZ6DOOY0G6Df+215BlD+mNLnIrQgHBPdfcyupR49AGA0zdtJTxeas7nvvl3AtptkfTGBkLfgXD1kY0ztAVWzAzjGB2OGgkRmn1zE6O4oIEHY3F91NbF5qqmJFxPVkDbuXTzeXc8Vno5KTTSJyQGcbVnz2CtvQAGouFpMcexTZzJsXbNvP1vx9EDvhBCkNvnUPAksng+Wm8HC+z0Rm6Op8VHc6t6fGMsXee3FubGtizYhnrv/y4Rzvqn0UaEkix2Jga9x4vKqfyrHw6EBpa+vqGqWTGhF5v9QfbyVsZyrCYNc3UDNlPY24NFaSyQuqySqYniH6/kzNNFq4s8RGphq6IfbJMzb4viSoITenzx6Yz4NnHsY0K1aHU+QKctq2QA57O/Uw3GfhTRjznJXbOinK5XDz++ONokblTfokvK0+h1t1MUPVj00eRnjCV4X84k6RBhzGTqqkY3pgHrvbAZ9INFGVdxqrVaygpKaFN1bMukEGFEgHAw6fnct6EDAB2FRbx+ZJl+Otq0CudfSciBw5i3rix5Awc2C04aK6p4uvH7qes4QAbhjZRlhBKmU8MH819sx8hVmNn61+eYacjE485FkkJkFmygEfPOZb8rIGh4cT218tpbmHKthaS6m0MmZjI9AsGde9s2wvZ5afhrd0EKlxIJi3RFw7paHx2KA0vvUT9U093u81rNJI/91JGaIcQoYb+RvSD7UTNy0KfcHjdh7179lB+/Q0Eq3v2kwho4c35BpYMD4XYN+VcxSlr/KHs7dix2GaEppcHFZUzthey0dFGmMvJBSu/xF7W2U4gR2cha9vujinvv6SNjSHlqacwjxqFpNXSuqIcxw8lHfdXa1XukNsoQ0ExaEgYE8eN49KZFh1OokFH9c230Lp4ccfjDZmZpH/w/kF7nPzM42plxYYNLFu5gvi9oQC91RrO5/Mvpj4mkU9GDqDaF+DmveW9Pv86+z4q9g7AU+unJE5HYVLvQ0Mm1c1QdjG4YTvf75iBN2hGNWrwj49FtehAVYhyL2WW/CknhjUysMzNgNLQMcVj0rB+cCpF62/D15KKpHViinqV5hIJOuvWGRlRTZbdxH7/LPZ7O4eGw02NDNYvJse4HPvpf0UdfSl1RS08+dI2PtN5CEowza/jntmDiDimlLydV/DjtyeRUFVE45BhPHhv7+t1/adEIHIIH21fQMkbXt4fe2/HbY9N+Jxr39rP9Tu/5qSiVZCSwf4rNZSvuA0kSNSs5S+WYR1jlQB6KUCGqieCfP7mfZ2l1VkEJB1vpV6MX6tHQYtdlri6NRQpT7BqSUoJw3HVEGZs3kdKfYCLl7fy1oxwqqJDV8cT7VZuqC0g762XUCUNbQNyOU06joYThrL5s2LCPAp7knTsGWQm3iHjVhop0j+ARteKr24e/sbpHftn0GrIiLEwWd5FsLUBV3gGwYRhtHgCbC1rwe0/eLfRAbFWpmbHMGdoaPhhX62T6e88im/lCnZkSNx/nhYkcEZfx20fb+U0awTGwcfj3ribQOmajqmMP1uXO5KiaBNRjgYaIuP4fP4lfP3n0NixCpRHhbMzNbYjVKqPimfDmOkcGDgCn6yg2+dEW+5CUkDVSgQH2ZFTux+Ac9U8buZxrKFrR3bZbyHbfDafbihjefuCbgDvTQ0j/tG/E6yrQxcXR+qrr2AaNIjaYicbvz1AyY69BNq+RW2/clk5fi55xxzXMbvl6cFpnJvYe8t72eGj5qM8SnfnUd6aT2ugCUeg9yErk9aPe/TJfOnOoMqjISbMyNPnjaT6hzxqd4cCCruughUTXRTmzGBapJkBjat5apOGmrhMlBhjZ9rXKzPVp+XxJg26faH9lhWFKtcuLKvewhBwoUhadBdczo/nn8tL1c00tzeSOjchin9kJxGl7yxu/Ll77+LFi6muribNk4quZhv13hIADBoz05KMDL/1ViR7CvSy/kivXHXw4XlQGWpehz0NLvsOrzmeF154AYfDyfpgOgVyHKByUbZKBrVUVHTJuoXZ2BqZSFFsEo22CIaHmXk4J4WxXYLCgBLg/T3v8/y25/EqXiQFRu2PYGSRndTkNIat3IjkaiOgM5M/6CIaYkcBUBOh5ctJYTSEhwINswTfH5ODb30Daz8vRFUhNs3G/GuHY4v69eJHxRuk4a3d+EucoJOIOjMHy+jD+5zklhZal/1EzQMPgGLENPJCdAnDO+5frdtLub2FOXPmhBbmOwhVlvEdOEDjK6/g/Pa7Xh8T88c/4t2zB9uJJ/J2chGv7XwNgFOzTuWOcXdgN3YflmgNBLntzbcYtPSrjtvSZ85nzhlnEx4Th3vbNoJ19aiBAFW3337QfXOdcRa3n3oBDc0ePljTRvQvRoTkUzJJn9yzqFN2OimcMRPF1ZnhSH7yCcLn98xg/JKqqmxevYKVLz8DAT8+vZGNo6ayecQUgvpQcGH0K+hlBYNZIclgYbc/2OucFY2iEuUKkNFayH7dd1iDtQTkOsySSrpRYabRzjs7r6CqLQmdLoh+lJHm6NDx1KD6eKnyDk4oCrUgaIjUkz/IhlZWwW0gf9UJuOv341dC328JlRhLGF79TAKanrMgddo2Mk78G5kNDeQcCA1n5bmeYa0rFQXYbwjylSX0Ad94fBJjTZchyy5+/O4kEiqLaBg8jIf+KQKRXh2pQOTrnUvZ8lYZX47obHU7liuJXpTPlVtWIgHeU4eyVXMi3uYMBmaFMyamgYan/sJGeyZ/n3xVj9ec3LaZAU372Bc2kFviFpKjqWCa70naMDPfrWeYX4degn02mc80fpRwPWc49BQMNLMty0SYRsPjA5KZHWenuryEzx+4B527FXtECnMjLkBrM1AwPYmdHxSiVWBjtpGy46IZ0voiqyqWEWNM4fiwh1lX5KSkoa1jKXeAOKmVuYYCtJLKusDPB3mIsxnQaTSEm/W0uAM9+pz8UnxbE8dW5WEK+mlN3cCycW5UyYA/4jo+2jKYOF/oT6kyWk9FiszQf4Y+JwXYkRZHVaQNl8XGh6deRYs9mvGNVZz23jM0G7tX9we1WvbcfD/PjR3KJ+vLeHxRAZ72oElj1XHPKUM5vtjLghYnj6Zo8GklotQG7udO7DhoIIbnWm+kZH8C2obOK37VpuPpgT4GPPtv9PV1aMLDSX/nbZzmJNZ/VdTRbEjSSAyeGENT5VeUbg+10M8bcgyLjjuVU+MieWpIWo8Os4o3iK+whcb3eq6ia54Uz7b6JRzYtIbWlp5dEtu0Fr5OOAm7FMtst57w9qxGrGk3zxyfySVjxnNhfBRvrCrmmWX7CcgqJl2QeVkLqU7IYIVpTueLqSrzNUbuWdiIof2bXdvaTHXhx2SVhqZs7kvN4NFLrkUeOJC/DkjilLiIbvvjdDp54onQdyPJl8iAtjCKGn/AFWwJ3RY3glPCX8Gq73LmOOkpOObyHu+tV/42+OZG2NVe1ByZARd9gS8shaKiIpYsXcb2ugDJGidaqfPwFBkZyWmnnUZqaiq72rxcvbuEEk/npeK5CVH8MS0OyV/Gv9b9i7z60EF+qG0QYzcaiXTocDaF6hIMgSDmQJB0WcvaEePZmDWfmXlejEEIamBbjpFFwywo7QXUE+xWnjPaWfTaLrweMNv0zP3DMJIPURiqBhUa3tyFryj0ew+fm45teuph1Wopfpmmj7bi3eOC9mE8pa2e/U2r2RYv4QrvrB+56KKLekzTDzY3s3/S5F5f2zx2LJbRo7CfeSbGzMxu972z+x3+veXfKKqCTW/j1TmvkhuTi6qqVBXks/rjdzpmkKlIfDvrHAqyh3NNaix/yUzs9t3w7tuHZ8sWNOHhIMvUPvwIclNnM0gVeHH8mXybPJHjVD13Y8bSJXMbeeZArOO6d/gFCNTUUHrBhQSqqjpus82ZQ9Ljj6E5RCErQFFlFW8/9RhFtijqYhJpiErBbY3FEfbrmS57m8yoAz7S6oOkNgTR/uLsuSNhOaWRu0nS7ed2RxX1abHcVXwbVW2hZUMy0iqpyM7BpY/AqPj4dPufyJEKqI23YKvxU3wgjvUNnTOJtJIGjXE0GuMYJE33InZJ62NS0nNke/OxaRspSh6Az3UeOS2vUOFP4/vmv6Kixa6VmBBh4MfxkTy1fj9PTLubMIObEjLJ+2Ek6WUF1A8exsMiEOndkQpEFuWvZeHbm1k05NWO2waV2DlnlYbhFfW0mI0UnjwbZ918NJLMHJsRo0Yi2FiIZ9WjeLRGHjzjajYHek49C9fK3Gv5mBP8C6mPOoZz2m4n0yEzv1WPUwGHRuHdMB82VcI6LJr8tNBsGP3WRrT1XiLNOk637kNtqiSsOB8UmaEJUxlmmowuzkLjwAhWfB/qR1CZuY5vEz5CAl43PExqRTSGjCgkvURFhZP8CgetqGy0SpR7ixmvL6dFMfG1f1ivwzRdaSSwGnW0egP0Xm+iYE57A521EFWVsKh/YrZ1FK/Hdj42sb6WB154jBqrSnOYGVSVUVEpTH3hRVzVVXx4z2342to6Hh/rbCOtwUnLlOmYrrqDt9eWsO5A6MQRZtTx6FkjmJeb0LkeC6D4gtQW/sCBlsfx+ipo9mRwa8Xf0JR4+PkyJphqRU028ZfPX2VWey1HRWwCP/7tEcL3qMTs69yHQRMSGHdSJqZoI5fvOID63SccszP0nKq4FD496TLiw8P5fuzAjv4tvjInDa/v6pya2M4+PxPL6Di04QbY/SV8dgVOv44G3QB2mmZSuL2zjkExjsBimQWAiso6fR3hIwI8ffmFFNa1cfuneeypDtUOzM2N5+EzhiMFdrJ7z23Uex282vpHtpiPgfZiRZsKtzt1DNjtYFGinncz9MzYvJabP3qTcHcbXnMYKU89Tey0zhOVqqosW7aMVatWEeuPIaXJR2HzTx33azUGpl96LaPmzQFHBbw2G1o7TwTMexgmXtfL38pBbH4jVDsCNJsz2TrkL+yvaqGmpnvNSoVsp0yfwmvXzyctunutRaM/yF/2VfBtfQuoASJa3kffGlrAMEwfxh3j7uC07NNwLVxM5S230Gg1sS09Hn+X7M8P009n16DRRLn8XLLZi60uNKwQmWri6fFmSnWhv7fj3PsYW7WZlB2DaAlkIkkqU9KWM+KsaUhxQ8De+0J9qqziWFiCa2Uoq2OdmEjEKVm9dlFW/DLOhSX4y1s7ZsMAaCN0tC58HLm6c7ryzuHDKBg0CFmnQ6PRcNVVV5GQkIB3ex41992HL797UKyx2Yg460yiLr8c/SFW/F1YspB/rfsXTr8TraTl1jG3YvuhhAObQ4v1aXU6hhw7g+EXX8UN+6pY297wLtVk4N0RmQy29qxZUVWV1qDMfc+/zhUvPUWr3syTo89hXVIo05MWpuO988cRvqcZ15qqbs89WEDStmEjZZde2vk5RUWR8vxzHbUjqqoSVKHM62N9Sxvf1bew2dFGq9z70NHPop0yMe3/csv8GAMqYV4F3a8/rZsY2y40A3ZhGbCGRzffQGlrqJ/NCFsBV9uWMaNlE2bZS6UnnK1Nyexv7dok0IDOPAmtcQSS1H2YPGBoYfD0p7H7ozF4o4gpH4a+LQuFCABqAlVsbItCRUuidQ+TbhpBZOJktFqZfy25n3d184n1mLi4xM/ginKKyr6gNDudh/8lApFeHalAZHXhFj5450dWZX3UcVt0i4G/fyCR6GhjT3Ia1dm3IElGciMCZNPZg8O96lHkxkJIG8jFk8+kwXvodQ0GSW7OxE3AkQCKniprFbVJbnxG0MtBFJdMaZudWiWMTG0T4/QVKCrsrtczuTFUmT7APoFxUdP5FB97vD6GBFQ+HH0/Xn0bZzWp3NjSQiQuQIuKEVmNwquMwiNPwa8Ow0uAj4xrCEoyg4PpmIIZFCPjM2jJN4FXgrpAkBpfEE+XL6mkKpx0YC0nFa8lLzabLXGD2JAwNDR+LgUwJX6O3r4dJRCOu/hGZEMESqwJxW5gkNHA7Oo8NGu+RSsrjCmvJrLNS/Bvd7Lqy4+7fUZVCQO4auFiFCQ+GTSDt4d0plnPPSaVO+cNIjqs+xTmrkWpqgo7mqbz7u6zaPaG9j9Nq8WSZWcQTZz05Wuk7N9LUKNlwdTZNMTNIbOh8/V2pBvYPMKKEmkgTKOhMRikKSCjk+DBpiLqP34TCI0rfznvQvyJaawfkI7vu5LuK2RqpNBCaEOjO080B1bAe2eAEoTMaXDO22CORFFV3qlsoOidBSSUJoGkw6u6ec8m0awDjSozq/4nFElipy0XJTKRv544lNPGds5+8vlq2bHjWpytO9jZMITXG6+jPjMBjL1f2d21rJIJPz6LvTXUAt04cQppjz+M32Lh66+/pnxXFZP9uVj8TfxU80HH8/RGE5c/+RK26C5/720NULUN3u+yfHh4Cpz1OqRN7HX7v9RafYBt7/+dn1wDUOm8ko6KimL48OEsWred71pTaVXNWLQq/5qXwZlTc3tkFL4sz+ehDf/C0xa6UjeZs7l38v3MlsNw/riQhueeQ22fUlo7fx4vJ6dxzKalHc9XtDpOvf4GshaeTaFvKj85/oiMEa3kZdnQCFYPNaO0/z6nNm/lkrWVlLtCXVEHmX5iuv0ldJIfko+B+Y9A+UZInwxJozrf65pKHN8dABVMQ6KIOndQR68PVVXx7mmi5dsi5JbOLJ7WbiB8bgaW4bEgKbQuWkTdG28S2NXZ02bbqFHsGzwISVEYt2EjmaWlPT7nlBdfwHb88Yf1O/mZy+/iuiXXsb1+OwDDisIZcyCa4ZOPZ/I5FxIeE9ex7z82OLitoLzjO/Pk4DTO7rL68cYWF6dsa18cT1UJL23FsK8Flxr6Ox1bu5d7NryFUQkScf55xP/lLpxLKzuCN4D4249B30tRruJ2UzD2GFRVZeugXKpj49Geex7LoxPY6Gjr8fifSaqKPqiS3CgT55DRKiomv0p2pZPC6O+oCyulLqwUUyCMJGc2JkVHktbFBP0mdG1mLDoZ7eggiieS6k2X4a4detBtBVCpt+7iY30GQXRkqdX81fs6pc2RNPu6ZFclIxptAjrLDDTaSHRGLVE2kJtlbBoJndlBrqb3eiy3RqXA6yBfDkMF3KkHcCTV8lHiCR2PGdsY5OXNnm7Pq/dW8L5tB4/fJ4pVe3WkApGNxXt45e0P2ZD5FdHuSBotzUgKvP6UTJhPZcOkK2kzjkGVa7jkoTmEhUcSrHOHDhCeQkouuRxU2HlpKmtbJpNSspmgpGNz2vG06sMplyNw0zM9OManYabHiKzx0xyzBVXTc5rcz5oUMyXBSFIa9pLl2Ici6ZiecBYJpjTuVj3URX9JRfwawj1xuA7cjEPTeeIx4+Vs7UpipRZq1ChOlCeQbEjlQLCKFYbdSCqc7Z9MuNrLlxqVyvoCGgoXsi4yicFNZYyrC/WB2BM7kDsm/wFF6vrF8WMZ8AxaQwOKPxJ3yfWocs8ZAjpJZVjdPpLkYtK9ZR2r4e4dNZXvxs/BotdxU6uXhSsK2aMJjUnHq15euGYaYwf0HuwVFj1GaelLBGQd31T8me8LQj0eTHoN980bwrTCNtqWLMK79S2Q/ah6E1tmXENrcBBq+9KV1ZFaFoy1Uh3de/OnKJ2WaVE2jivcRlV7Ua6i0TI25VxytJ0L80l6DbFXj0BjM6CLaA9wFBmW/hPWtBceDpwTWr9Fb2Zdi4t7dxZxysJN0BBaGyfBsp3YmXG4LTk8sKyc8kCoBiHFU8FJtT+gV0PF0lc9+xr2Li24g0EXhUWPUVn5HnnqKL7wnkGhJbfb+xhuMPBqrRbdxjqaPS4ad35OXNVaJFRks5UVx84hXZOLzlNBg7eMWm/3k9nFjzxDXMaAXj8jHBXw7S1Q2FlEyNwHYeIfu3UJ7ioYDPLDDz+wZcuWjtvMeIihiePTdWSc+Q804QlUV1fz75feZJk/mybVioTK1GgPd14ynNy40Iq87+55l+e2PYdXbp9ebRlPa9Q1pNfW8dzj9xLmDp2MDMcdx18mzWBN2kAUjYZwZzNz1i0gs3hvt307PXUXen0ay53X4JRDKXVzWDEfTU1gR3vWwyR7uWHnMiwF41DREqsrZH7kI9i0v6gHGjgH4nPhuDvAYMW9s4Gmj/dCUEWfZCXi1Gz85a14dtR3ZEAkgwbr+ERMAyMwZkcg/WIYUHa5qL7rr7hWrUL1dg6nrpkymVabjclr1uKIsLMvJ4djK6sY9MLzmJJ6b8D4a4KBABt++Jx/FT5BVXTo5JVrHcSrp7yJzdCz5fu+Ni+X7yymqL0A+uKkaG5Ki+OcvCKKfx5C8wQxbW+C9oLzATFWHpkUSexzj+DpsnyFPjmZsBkzsEw6D+ei7i3drcdEE3FyJlJbNTubmnmtwUuEwcpHzQEch2gECWDyBjlzSz0DKjovRBrNJXjaPibGoUdFZfeANrTh6UzS72CgVM2UVg+qBHsH2ohwa3GHRxOQa6mLMaJVVOJrvKQWafEpNgySm93uuWxpOwuF7seVYk09+VI1Y1s2YA/+nPHSIukz0BmGUBmeTZUqMyrCzGy7BVODC7OiRQHWxGrRqlBt0lBh0WDWaqgKU4nweyiI1LDZ+Oszs7JaZT5e2zkVvk1SsbavQfOGcT1//+cdB3vqf0QEIofw6JJl7FrzAdsyNpDRFku9pok2s8w9H8hkVRlYP/kBkMz4Xd8wcFwSJ918J6gqysonKPzpXZY6J+LUheOxWDCXFqBzt+K32mlLHYxOkrHKFurUMHYoRgqUzhOGUYGLXUYiFQ07DUG2hns4NkzG5zlAFC4kejluqyrm8n3o2lpRtDrMGROpsTXyddKPAMwpPB+bO5lSSwuVSniovkXV4VBNxGtcOFUTzYoZBQkFiZnGQhIlJ01EkufL4WzVQAQSlSiMUbWYilcQsfNTdF3adCNpMA4/F13mceyRVD7FT5MGSjUKTUEFjaEWc+abaDQtBMjBXXEZlhYfsqTtWBnzl0yyB1WnwWOzEpEWznC/hjX7Qgdxrapw8Z4fOWf/MnTR0STef1+3qzlF8VNQ8A+qqj9hb9NAPi68jrKW0Bc+0W7imxumEmPR0fjqqx2zD3zh6Wwb+gfcptCYfmKWnePOH0REkpXny+rIb/Pw1S9Wlu3KGlS5LL+B5M2f0OwLzToYYp9EWuyxfJpt4g/zh5CS0OXg7GmGL66B/QtDP8cPgysXo+rNvFdVz+alHzN2czit/lRAYcKAzYy55nKc+kju/GwHi/bUYg268GgtKJKGSH8TMxpWkOQLDVtEJacy/PjZjJxzAnqjCUcgyEsFK3i2Lpxg11RuQOkYrklUNTwaFsHgL0rxKSo7qwrJ3v4c2qCHvPQEqiK6F/+mj81gyOws3PIazKZkwsIGYbMNIzx8JG53Mfv334/BGMvQIY/i9VRh3b8B6ZsbO18gcxoMnA3DzoTw0ImwoaGBn376icLCwo5F3iIiIhgzcjhTpc1oVj4ayhzZEuGcd/AljaTGWcOqZet4Y4ufA0roatCmdaJJfQONpYFge4AWbYqm0duIOaDh2u9jmbSn8wT2w7SZPHv6RXjae1oMdJZzQ8W7nNC4kp21sVR7bJS0dV7Bj8yyMHl4NPnlA9hcMoqgosVo1pF2RgZ3apzU+EPbHKaROGaNg9SyICbJydyIx0kx7jzo3xHJY/FZj6d+17Gg9LJWSG409tnph5wJE6iupu7Jp3B+/z10aXRVEx/PpvHjcP9iqvZNN91EVFTvBda/5Pd62L5wAdsXLqC1MVTk3TwxisVxBbiDbpKsSTw/83myI3sWTQYVldsLyvmoprMOxCj78GkMmGuc6PNb8bdP+ZudHOS5Y+owWiOgtRp55w80bffRsKK6Y1hVb1NR4idhGXZFt+0sTWzhpewgpeY0FKnn55jYUojkddMUk4pXF/rOh7UFmb+lhEF1ViQ5FIQEDU6acr5koGED8v7TaK7VIvtCtUXRYTpyJw/gtbY4Rrp2MOXzPAxtCrZBbrQBFVN0AHuGG00vyUdF1VATGEyeaw55mnGYHfsJBHYjBTqHHX0aA/lhgygdOpF9o9qH+VWVzJYgkapEXoQW+Te0Vvglq9pKJkXsYThz+J4r81LJrM3q9phKyUGyaudjwzZu+9dvX6X914hA5BD+8s4HlBU+z84sJwMbo5G9Hg4kuzl7lcywquOoTjsHSePA2/Qmqqpw5nX3sTfve/Y319JI55dZ43VjLd6DgsS7Kefj1Nu5GgMX2izsc5fj1pcw3DuIBqK4J8zNXrdKil/iAlfoS/C9xc9uQ2ddgZEgGhSS7Ub0vhaigk2YpQDxtKApK8bubcJtt/LthAN4dV6yHFmMahr1m9//zzMTN/hTacZCrWLrqBmRVIUzCldy0d6FmOQALfZ4iuZdgy6YiE9WGIyWSCTMgIREKyp1KFQaqnlkwL9RJB/GQBLnLNGhVSUadRG06cLYF5ZNvu3Q3V1NOolJiXq0JQcYu3U5k6t3YUyII/W9d9BHRqI1aNmedzlrilp4Z/d5NHhDJ6ZYm5H7Th3GvGEJBJubqbr9DtrWhJqUNcSPZuegS1E1eiK1EkNMGhKTw7CfkIlpUCQ7XB5u3VvGbpcXo0bizowEjosMY4fLy1uF1Ry7t40rDoSu6NqCTlbXfkGLPzT1eH/WSBZPnkubNZxnh6RxelwkOkcpfHAe1LeP0adOhDNfo0Afy9Vb8rhpwyt4So7HISehk3zMPUkl/YT5fLW9kn99u4dmdwCtRuLiienMzY3nyrc34/bLSKgc07yF0c48jIq/2+e2ZOpJlKRk0RwRi54gF6hvMoI8VPUYXqk/h31Rpo6AZLTWx1U7VpJRkQuOavaXf0GltfOAF53RQswxTZije5+CfDB6fTQWKYKsvTVEVHY2F/PpI9g45gn2VTVTUVHJz4ccs9nM6aefTk5OTsdrFOx8n8hvbyPO78ElSdwbE8VCqwWQyHJmYa+fxoZAOnLUBoyxi5A0wdBJS4JIp8pVixSyq1Qi2zPyxcnxPHLpTRSkhrI5OjnI9Qc+4i9Vr3ZWPk25GSZcS+2B/Sx55VlqGkNZBnt8AimDc0nMOZa9GxQaykN1EDkTEvhxtJn3mzuH5KbUyIzY2kqcR2XKTCPD5gxG07gPVj8F+37oeJyshuMKnkKrfF63z848KpbwmWnoY399KQZ/SQlN771P83vv/erjXFYr20ePojKl+6wTq9XKrFmzGDFiBNpe1huq2pfPD889QUttKNi2RkYx5dyLyJ02k92Ne7hz5Z1UuCoI04fx0LEPMT11OvjdoQNK1TbQGWmqLeTRPbv5NH4ebToLqCrTNy9nfVPo9xxHMx8a7idL0/uy9GXuWFb6R1PqTSZv4BBWjpkAqsrzWzxMaOxeh3X2FAvFVg2RLeXYW7YS1rKUyvgYXFHnEjCF1rMJ8yjM2lbL0CoJrdx5YWQwlTNU3kJMSiZrq4bwgyThk1QGmwuILlpKapODUeV19EbWaJBUFUXSYDwJokx+SryTWBo9nt2RKdTozIQ1FTFl04Iez/UaTOxLH8r64Eh8mFABOSOMYE74QTOIXelkmcwamTDFR1xrAJdOw65MDaN0m0ijlCQq0BMgkyJMqpfkai8xBZfiCcxHav+rV2xuJJeFMppJVyP5TJ/HLffdcMht/xYiEDmEJ19+gLU1C9ib0cqQ2jjs9UHWD2tieLHK8dUP4pfCUBQHNnsFDRVLcKcORLF0pr3adG0kVJaSeKCe6ggrJeY0Ng44hlp3aGjgbkwEDDvIzRrEgHwbrTqZOcfbCWgkpHovJ69xMtKnIyipvBnmo+WXpdcHYQu2EpbwPq7YEoz+SGZVnYRRCaXagmjQS7+hkqoLr6qjXrHSKhuYXLmTUSX5RDS3sMeezr0Tr+g2ZflndklCUqEFlaFoGYUWU1ghn6W8gioFSa4zMWlXKmHtnToNpmTqI8az2xBFg89Fs0ZLUKfDrWu/cuvSt+GXtIrM5OqdpFhLSJpUxuL649nZkNtRUzA5zMkTV8/BqPjwbd9B68OPEKypQZG0FA04lfKUGUSn2Jhw6gASDBLNn+1HcQXwaeCdgUZeTTegSBCh0/LO8EzGR4QhO3w0fb4f377mbvuyO1zDF6l6Kpo2M2Pt9wD49Qa+mXUuxWk5XNq6gX/ufwqTqxos0XDaS/izZ7GovISlqz/ktF3l7G4+ExUtFqOXU28ajj8mlvsX7OG7HaEDc1aslafPG82w5NAQVUFNK4/8uJdle0MHRZMWRhhrGL/7yx5lxKpOz5i5J2FJ3YZL+RFJUpFlLd8WnM/nUXOJjDByRoWf0VsWUenciV/pPlNqen4pRknFeboPz7HKwfriHZK1LQil0exuOIYq4pC7pKijo1UGDNCSOnQwPmMqjT4Hz259CgWocFUSLss8VdfAOG8oEFpuNnF7XAy+9g6mOtlIUBu6L+jKIaV0Khfs/YCJ+zqnc3qMel458yK+mjobJAmdHOTE0lXcXPkOQ5UDbDEaGWFNpi1nDhHzHul4XsDnJW/xD2z57ktczZ1X9VPPvwyvZzi7VoSyLJEJFlLOGcCfWuqp9IWGGQwKXLTUQXKTTFpuFDMvHYol3IDaXIp39Rac610E5M4ZKhIuJPwo7Rc34dNisc0Z1G2pA7m1Fc+2bdQ/9TTePd3X1emNYrGg6bKGTUN0NCWZGZSmpxPUd/8en3/++QwaFFrqwlFXy7rPPmTPymWoqoJObyBn4hRmXHEtRp0EXgdYomnZ+CK3lH3NFl8oU3KSJ8DfamsI6+U00qIJ4+yYB9lXF4/Uvg7OCfr1PK55GSkqlTZbMi2uBj5MOolVtqE0aU34MFCv7T1zE+5Xua7AxchGNzm+zoDtrdhv+ChmIQHjQNz2swmYBiMpKjlVAQaVlTCyvJehXel5vE0+NChYjDY2xE9Cb2rhJGktowxFrPOMorHYRn1EVHsWTcObp5zV83W6MPi8GP1ecvdtY9KW5ei69LtpDo9iW+4E8geOxP3zucQvo9/RjLYx9Lcsx5kIDI8kPBhgiGETcUo9VncbDaYoIrUtDGhpJa4kmpbCGT22rbM0otH6iRy4FHPyNiI8LnKqWghriaPJfzNqMHQRqKJQNfI5XPFbGTnkDfY808IANYov9Du56b4//ur7+61EIHIIrz91M9+5NlCY2saQyhRy9st8Pb0ao1/i0i3/RtO+Foas8dEcuQ61/UqywlJBXnQeXp2X7HI9U3ckgiQht0UScUUlRaWD+bj2REzAo+gJV1vJluJ4P13Pk4NNTC/cwdbC0BX8H5x6LKoOjc5LadQWVEkid8x4thaWsatBplBNYbS0n13qAALt+6O3b8KU9DmqKuEuvRbFE0rnGbQS/vaah1EmMxuHWbBo/NxSqnJirYqPAI7oOmKCH1Dva6OYVAoYwOGcZdyKGRt69mn07FPjCPdZuQoja1H4Hl/HvqGqzK1fjNW8i5/G1BPUqSi6QczcGM9ofyba8BHESXqMvnpeUFrZZA4NWekVPxOaNzGkdS+V5iRKLOn4NEYaDdG0aS29D+20By22QGhVyoFtReQ685lUeoCMxtBVqtcQzs5h10LmII49N4eMYZ3Fo3JbgG0rSrgt6KTAFtr/OQ0yD+amkZhmp3VZOe6d9bQ5/MhqaNXkiBNDa3joos3U+wNE6XV8v2EDW99+hbCmOlQklJwobtN8jVZSqTDGc/moJxicNgw5/xse3vUo61v+wH7vsQCkZGg49opxfLSnmqeX7McXVNBpJG6ZNZBrpmWh00i0tTRTtHk9+atX4LTaeS8YT4mS0tFxEqPEGHkHU/av7vkZAbZUF5lzK9BoVfBaca89kZYKF56gg9ZA50nWmu4lPX4YzcWZ5Kz9Cqs7lD5WbRasl5wKp8Sj09mx2YbS5j5ATPR0NBozbW0FlFe8g9mcTkTEMVRXfUpN7de4WqMor8iloT6j2/6MZA8jTHnUDvfhM2hQtBItQYltHi3H24IsdOhY6NQTplFxy/DHZidXOFvRqirNESncFBdNvuLGJ/sw68wkNR1Hzk9BLt+zsGMbfoOBT2eewJfHzaYxIgqNonB61RJuKn+PxGAlD0XZ2WkyUNpxUpY4acCJjE8Yz6z0WVj1VjSSBrfTwZqP32XHkh87Xjt9xGgSBs6mYKOE1xVAo5EYMz+d8jF2Hi2rpaw96B5a4eeYfV5yZA0zJycRVtuGb39Lx+toI3TYRzRhLnsEqnfjCF6OSz4VAItmKZETWnCFn0KgvILaB3svIJQMBlR/aHuasDDsp5xM3G23obFaafz6G3a/8jIxRQe6fcN3Dx3K7mG5qF1a0mtVhSydTPWuvI7bhg5OZOr4dGw7XwVvC+jMEOwscAwAj0dF8lF4GIokkRYI8HJNHSntfWncGiPF+kTuD1zEOneogFPVSQQG25GSDNhx0CQdusgfIKy1jPC2ZmavX8K4gmayKssxqRKWOQ+gNXSeExbGB3h0aAQOgyb0O8/zYGuSsbkVAlqIbFNoGbIbLfVEORpZnDWa7TG5BDU6AodRV3IwWjnIwOI9DCraxcDi/G6r5EpmHWFmD+EpKt9OOo90RzXT69cS21qLS2Oj2D+OWJebD1tPYaUpFMzGByXOaDNi0/gw2OqIzP6JoMeOs2w8/taedT6SJoCq9Nx/X2Q5Z9rK0DqPhfZjtJYavAn3cWBEKF0YFjYY91d/YKASzde6XVx//2+Y8XYYRCByCG8/dRGfefdTkuhmRGEK89d5efbsetwmiTN33E6UHEF47AbqZANuBaSgjLm8AMd0KyMnz+ezvNeI3OAnpyKMxOZWRpbX0/jHIPuGpPL59rPY05TOwCgzbzXoUIBrRnl4pPyv5JdeyxbS+cTqI1LRcIVLj0bV4rZUMD11L+Mcz3fupDUWLvkaNW4oZU1ulhfv4N+7r0NFxtdwPP76uYd8n6pBg1ZWUWSVmDADGdFW7h7hZNTic2khjGe5DBk9o/K3oujt1FvMVLcXtZlUPRMDA8lWEjtez08QQ5crWx8BgsjUSa3kB/Npaj2AxtPKgViZ1SNC6ygEDNmo5ReRVXIAFYnCsOyOL36Ct4Y59UuwB1upt+Ywxj6OoZIJDyqb2/JZbB+OT+NEb64irDDI6uTeGzdZAl5u3foRU6pDMwl2xaSxbOBwjp0+h9PPmITZ1r2w7pXyOh48UI1XUTEpcFu+l1PKQ0GHS1GpDqgU+jqzS8PHxjHxosEYzDpUVUUJqmjbg9OAz8uy5+5n18btAITrvQTHJvPksKvQqCqP7XucidXl/NhyB045AVBJnh5HxMg4HvxxL/tqQ1fx4zIiueuEIeTGGNn102LyFi+grr6evCHHsGvQGBqi4lA1WlBVtAdc6AtDU3m1BJkWs4nTB31Bw6Yomgoiur1XkwUsmmjcHg9e2d3tPr/ewLezzqU8Np27JDfTNRIlP9Wg27KK5MqVaNoLig1DZ5H8yN2YBnZf1birQCDAhg0b2LlzC7W13bNI6enbmCDvYGhFU7fbN4yJwBXWe5EwgFZrY2rKYxR8dQ1/iDTT2l60mWlJ4e8HRhH2/vcdJ2OAJcMn8tq5F1AbHWrLntZWxWNVbzMtPRv0ZtQxl/JmQwVPrrn6oNvMCM/g5dkvkxTWedD/6B9/pnLv7o6fo1MHYbDOork2NMQal25j9LkD+auzgZXNLuI9CtcW+ji5qrN2A52EaWAk1rHxmIZEh7IeQR9UboXVT9CWD83BGwANqmMPbWteQ/V3ZngATLm5KC4X/vZZMZLFQuT55xFz9dX/j73/DrPsqM798U/Vjief0zlNT0/OSaOcswQSSCIJTDLBvlxsLo7Yxlxj44CNTbBNMtkkg0CAyBIoIc0oa3Lu6Qmd88nn7FT1++O0pmc0Mwpg7tfP72H9I83pvWtXXLVq1bvehZE5lXQsCALu+uQnWfOpT5/WxvyaJu5bfjnar+KMHkNGjXo6ruaSrkHWO8cIHIlUmv5FCSZbbIxIkymEuF7EVFsKTJeRegsfzU9TUApbwNLcGurxyxic6GTmYAxqCi0gXJ4mWpBspKY+g3RMDJHNHydReozD3SWMYBiha3ASyUA9fgELRyf4rfv62dxv8oPLrmZw1aX835H5OVk14MMrHXZnDA6nXliix+eTZE1RjknsQONbjdosHauy8thxFh9/mljxCCo4NQrFdEKym0p0rx87601LrBYRmgLbV7RPeuwb2MQfh79LDRtXwSvLNl1nwBBpIjxnGqEFjt+KRqOjaaJoCMveeMqzroDzEgZNpkRQo91+F4Yc4xcresknbMqlFtr3vIOVqoUfGnt4x9+/47+lz56R3xgizyNf+dRv8w1vF8dzPpfsbOYtW6f4xLWCbUvhoqO3cvPyp0m07ycIbPoPXkz9wA2IyS+z+NwLue1P34f+z1v41N01apFNIm9xxbH9VFyXt73vQ4w3t2LWPd5zWPOKoYDHc5LPxHbx9tIg44PXYIkq9xq7cXNxVgSSTL5xYrg1+16cgUHK41m8ko2q1omdey6Jiy+i0J7id/zPMeXPcFnXpaz9Xp3CdJ6ClSHsfiUxXAJbcqge0K8VJalRz+HsaDY9psN5xHhOVLl9/8+5LV/m0CWvIu20sPjsUW9nlRI17rf3MCkLTDpTPNT5MEpESNWBGng1paARcdDqTbKqtI9d6TXM2s0IrdBzkThZBBswuBQTbRf4YWKQnbNLSXsVLh/axpv2303ZivFQ9wZ+tOgiukpT/PlTXyPjVwikwafX3cKP+y467ZonaSg2pWscSzdzOOUStbhcEZr8UVMTlYfH2TdQPK09ZxPDlKy9vJu+DS10+Q8ivv1mHpnq5ZGTiIhGNq7kPfpOVLmVn+T/gprK4FmKb5yfZHSygjHRuBKxHIN337Cca9sVU088wsBTj/FkJBlu7+XQotVMtM5viAsrk6xtinN77D5mJ4f47NNr6c83sA8t7jSvW3knG1p3UzyWZOi+hUQBKOYNKkOYRDok1VPBbPb5Qv0tHL5gY4N6GkiPT/PK+7/C2qCPSGygZeghFh1r4BuEkyb31vfR/IZrMZvno61mZ2d58skn2bZtG9WTrgSa+5p51H2U/rCfiBA/8risWucT4/MMtwATLTYjHS7TOeuMV3OPVwy+MWOjEBha83uHy1x4Z+wEn0NkmmzZdC6fv/4VHO9Z0DDUpuu8pf/b/H5PmY7f+gQYpxo7Wmu+MDTJ/923jdzYXyF19bTvvveC97K+dT1tsTaMasTIrl2MHjrA3ofvP0HfL60VOKnr0doCAZdvasFJGLB/lnjQUKtlE+5vMkhok1vfvI70GcJPg/FxJv/ln6g8PYa78S0Iy0V5ZeqPfQJdOkTu/CaKO6YIyvPtyNx6K82//zZoSeM4rdT3fh0ziJClCfTObxKZBkalzIPTPczsi7Nm7zynyGBTikOdOepz2ZuVaeE3tRPkWkEa2HaFdet/jlIGiUQeITQF0vg4jNLNfVwHgI/NWGDiT38DM2hQo/vBRryBW0DF0K6Bv6EJnbVZHe2iKZziuN/LcKyHyGzoH6e8k2T+P5Cq2PAqGlkiqwe0R5S6GWQLdauN0Gg8n/Mr1KVJ7Zn3I81f7qnz0tGTjD7gg6sdvtNjoYVAKoU62QukNNmyYtF4QO9kSDEuaStE1C2BE2hmUpLlwzUSsaNkrGlUUMKK9YN5lNpEjMpYDB2dHDmoaYsVWbSzTLbqIVDM/GGIv7QxB/xiDxaCnZVWCpGDLSMWTm5gdWaQ1PhmtlarDBpjLFaH+JJ/FWGwkFdWzpxtXRg+Leu+gzfTx+zAInRwH2H9GayNxHDOQVoLMMxeum2TcxONw9O26BhJuY3k+rspddWZmOjjwP7LuDBYx9qojZ8Y+/idvz+7gf7LyG8MkeeRr332lXwrtY/DnsGVT7dw0+4qW1Zk+N4Fo/QVl/Lu1TtP0Ykjj76N8YN1RO1pNlz+SlYf/yv+6+gGfGnxuVf/Ef/02X9mzZFD7F68nD/7/T/DNlx++GAFV8H/WggSeNkxCPIBa1LfYFeujWnPIJvPk5haip9aQ7w6zrlP/RNmdCpAUAMfvVXy6CpJS8XgC2v/Ad9K88OPNchnHDvBDe1vJmY2Tv3jSYvHR2oESjG2wOWbcY9wssZzwUcWIHkzNjc+K+RYwQlmB92bJN6XZmDyGE57nPGfb6ODTnLm6THtYyLPT+xtHIiNs6PtUTB8Iq+NYPCNbNYV1qfqlHJLGZgN2JOXlPXpi841atSjeaWdc2aZ9TK8cmQfr959F5nqqafrYqyN+ze9mu9m0mgdghBM2i0nDBwAoSGjBAWpuapmsdk/+2n8GclkbAoF/6x/b7UGWBf7IZas417zCu66837qs42wvEVNSxjTN6ExmUhLvrZEEByrIJRGC4h6Eo1cObZERhGOX0eqiEri1LmekBGvjz7F5dx/iqs9VJLvH34JPz5y3Qm8zMLqMa6eepBkNG9JGsIkZ3cw5c1zMsRaa6QX1IjWvIsPFrvIdzSAciJUbHr0Ya7efT9u4gbaChWWH/wmTtBok9G+ltxvvQtr8xKenNnHo48/SjgXtSGkoNpZZVu4jdH4mYGI17Sdy7/svB+zdqrXJBIG2y99L3b7MSYmfszemuT+ksUhr3EqXBgo3nRvxLpt8z1wuHchf/PW/8Nge8NYSwZlVm3bxa7ZBnFURtS4fbHibS+/gvb20705kdb8cGgvf/LYx6klr8WpPkG8dDK4sNGr7Yku7rr1Ln408CM2x9cyvPV+Dm59mtnRURBJsqlrWZpcypKTuFvCRJW7VyT4QHOCSAqk0mwYLPN64zMsWzSLvaWCc1ghfnEqGFLkeohd+r8wjHbAJ2f9GwnjATRQjhvMZG0GFs0zvr4Qyc92sGf3laQn86SO95OPNQwQoTSLJ/O06joH1y/jWGwR+xYt40BnL3XTwYkCQlcwbT9Pjhwdkhi7k5j/owYmqdZDVtzM1Rs7aZcLGBv+CQ8Nf5+y7aOsFGF8E8Jdi2v2kAvL1KXDwcSi5/7GGURozdrhIobvsNiH/zMYkHyWnjumNAVPsc2AhKcIDYERaU6KEaB5ejdufRa3PoFeWsQ77zj5wQC/ZOOXLLz86frJcEKS7QHppQq3SZIuL6alvx/nviHCWZOaY/HdtZdyZ8dVVK04koY+7Ubwd8RZxunejkMqT7/v4NdP1Ut97sNMN8eIt+/HTg4Qax1kfFszE9ua0erM2ZYXJjdwfssNSCHor0fsmeNWMpwizSt/QmbRVrQMCH/xd2wI27lH7uet//A7L6r/n09+Y4g8j9z5kZfxuY4BhgLJtU+0sf6oJt97AV+44Ic42uSP7Cb6+y9ice9WOnuPEXlxDj/4J1SPfA8pQtrdAqO1NPv71vCDG1/H0sEB/vXD7yfuhYy35Si1rWV11ES+Msh+t87+loU01+O0WnWs6jFSxRKdo6M4vk9gxnjsvPfhO1mapnYQL29jKrWAzTPHqEmTnenH+fjLDYxI84GvRiwbAbO9g8lVl/LIbCPu3hAmL+l+OwkrQ+L8Diqrmvnxp3cReBHZ3iR3XpFmq1/nVff8kJfcdz+zdpL97ctoat/ELckenJM26yNERMAuIj5GnTNlo+nyJ0j6eXpqwyysj5ARNrnWBFfYr8ScCx09SIW3EYA1Q7zvU0izgh05XDp2CTn/dMWWKhTxbZua4TLkZjhabyYmAqoSpFCEoUtJOxS1S29+lH/Y+lky/vxm+1j7Kv7+/DdhGxZXYJEKikSzWzGiWR5YdQ0TqR5+67Ci6/TDLwAjhuIhN6AsNU1K0G81Fm6XFmw0bIwarKxJ3IUJ6sfO7C5a3vs5Lq7eww+H1zPObRhOg8uj3KL4nAwJ5mjqVc7GXZOjmDi7IZTVM3QwyhvFV1moD54RzbNmzceYGTvGgz8t8b2RBAfdRWghsZXHufmnuc4rkOlayyX/62a88jRHtj/J0N7djB2ezwMkpCLZ5jLk57jjiteSb29ca8TH87x0y3dYmo/j2Bez8vA36RhrUMRHls2xG9s4vqiN8YmlgGAiPcCThqCcvwRpTaPtCdL+KrrbW3jp+ia2H07x/e0N7ImLR7uYZbEY5X3mV09ET1S0w3v17exfCiP6AQCkhpc8BW/8WdhQ5kJwdOFC7rj2Ju7efGmjDVrxxtEf8NbSNzEvew0/2Bnw+T0bKIcNIPRSY5JLsmX+z1tfR3PzqYaz1pqx4iHur6T5ytA4qvQIvcUvkdR5bs427u2nQsFUIBjwDS5KhORMjVYCa+BcrP7z6WIj5tx1YynSHPY8it0/oPWcu5k2cnw6+gMOiaVc+dRjvHTrg6w9cgDbP924Lbw6pHKlQiibzp3vIDV5TqMPYg/Qof4dKeYPKQO9MY4ujKOf5UVSczNFIwiwGaaHmUKOvaNrqJTjjLZ1M9baDUIS2A7JSoV8MnUKbuS5xNIeCkkkLNARa6TD1K5pCsNlZOwY8QVfQBgeGkmQeiVR7HISkU9gOBTtBKF8fuP/TJItR7z0yQoCsEPong5PWxO2gHPjBq3W6W0JdZVj/gAp41Gy/iHKO2r4pSTx6hRV22RqkcPYphjFwThB+eyYETMWokKBCuZwF0aMNel1bMptocV5FBUKBn62iKDQ8HgeSXfwnkvfSdmO04Tgz3G5pDeDHqlB2Nh6ldbsqSkG/GesKI2Xq/N9X3LUUixIDvP2dV8mNlJl8IFn4USEJr2gTNdFE5RH4sRa6pj9m1lfbhgVxysH2clW3Oa1VMbmr7alVaH3yg8jt72ddeFC7pUHePM/nJ665FeR3xgizyPf+cRr+UR2FxOh5MZH2umYcbByb+Q/z/8Ivlnj2tEryNRbGA+e4iVrj5Bob9wBDj52C9PbG0pcI/jca99NYLvctuNh7Kn7eN1PhzDVi+hOoelv6+Gx9stpz12MFJIH3YDH3cYJU8aOEe/9DEJG3LxvCdc9IugcnydfKro2W1csPOF+v6zjVXTFlhBb30JwQRc//OQOvEpIpsWhNvYdLn24EeUxte4lLMisxWxZdqKsaVHmJ3KUQ3qUTfIA/xLeDkDKFpT8526T0IpWf5IFUcC/xufZBbcQcHe7xe03Zvmr7X9G1R9EaJtVlcu5iGVU8rMEwdlJ3c4kll3F0TWMmqa7cx8mPsFkCtoDck0jDD2wmH0dvbh9JVa2HgLL4GDlYtT+zXQcbeYZH4/WIeXwAHtiHRxw40y8CP2YiwQmcEHdZFVw+ouhjDCVgdaKmWA7I/o4hxJLGGlZSn2hy5rZvaw/vJNfnHsNI61dOMD6ocNEUuIEPstju1loDDAzvQCtBaXSfCp63xW4Tg3n2AxiZgbDm496mbBbuKf1GmbtRtTBuo4Uf/+q9azvyZ5Sv+ED+9j3yA8ZeHoLpfFnXNoabUDhpnae7ryQEJPX6S+zQMxnI7UPCjLfNrCGGn1YX6MovCokepazwY8sbGN+XPdMrWCw3M1QqYuNbbv47qGbGau20QgAV9wit/JO8y4GkzP8fXOOSbPRp5sOK952t6KtANVYjPH2dn520WXcc+7FTMcbbUqHJX749DtxmiYY6Euc8BRUghh3Hno5Dw412E9NEXBd1xauWribzqYKmcwavPo4xdJOQCOEjZQWUfT8d5KxmZV07XgnZjCvk8pBnv3F7RxXCzCshkdGq0my2S+yxB3A+lmMxOzpxkd9vcK8qEbQpUl4oEugbE0pY5KYfAWZwVtQSHTsGE36XziQjvNw9hxmrTS2EXA8m2abu55BcXq6iV9GmgplZtIJcpUqSyYLDLQ2UbdMmss+AijGDKq2iW9IzP4S5sA8DX3UFSda5pMo34FbbVDBe+4GKrk3EFmn07O35UMWToQYSpNPGGQrEZv7PaxIE0lBptowq4ThgZZoLWhafi9mLI/bdITK2GryA5djJyZJ9T5OZuFjmEYNlCBWXEnP03+AeJa3dUrvYHLHdyi4LYzJIqE0iM7gXfJNm/HWLg4vXMGS2BTvPf5Z/MDgruHV1KMzGyotToVLNp6POXoJxf134x/dSiKoUzNsPrHhFWztXEvNcvnzG1fQkd/Jnt2Pkal30Rx0MFNorPFY6wHaN9yB23Sc7RNr+eSOtxLpxnq4fexbtNXmuJYMxbL1UzjnTePlezj+wJ8SaxpAaoOr/fUAjHgTPDzyn2gUZnwRmb5F1KYXo4IEaAMzPs3S1CEW+ReyVRzhDf/wthc3WZ5HfmOIPI98+aPv4DOtD1GIJJc+sZalkyUM5xzuO283R9KHWDe9jt5qO/e038sbHu1hw+sPnHh3x+dWoyNNPZ5iy8U3c+WeJ7l86xYyxdIp36jHE4w3N1HMZkiUK2SKBSw/4FiqnWWJ4yzKjZPo8PjrFe/gy8VrueBYyFX1xgT/dsJjoKlIsuNfkWaJoLSa+tAbQAvesP8eXn9gnsFyKhnj8SUNK1kIybmtN7IwtorE6ja4spvvf/hxaoGJW5/houmtpNfcdlp/xDa2cp/cxZ69DUDe7/I1OvUEQoDvtPF46hb+66k6BxLLMHWEqUN2pxunfamjUwiFuhH8MTHOPwnUejAu2NWt+ar8GHXZMOSi1LX800V/wfJyke89cYSn9x5CoEkInwVGYa49EclkRHPuKE2tjTFIJPK/3KDPiVaS6YNLiDcNURqOM/pEK2hB1W5mIreCQ/HF7OdZyaVQZKkwS4oW8vhYFEkgNKwKDDZ6Bt3Rqa5WhWa3HbHNLXK59Tg/ii6ghoupQ9qNMr42EWhWmBPUtUVMNDbu5NypNyPqOGLeHyXCAGtmHBn4WMVTr6WUZRPkWgnSzUSmzYGojafCHsI59++GRJHruiM2Lu/jkksu4d5778Xzylx99UXs3vY+ZgoPYjpnz8R8ioSQ+qlB8h6JCAVaavJvjqid+8uH+g7VLe441sHxeCOvUFte87sPRKw5ptGeyZ61a5ha3cy9K8/nkbaNACSiCq8t/Rd/1P9TmisN3EnBdhjqsRnrtk/gTQ7n+/hO/03sn2mEqVrS55reX3DTop8Rt2qnV+YMUq665JRH2+BVxMeuRwbzm6pklpT5TeLmjyhrkyfGF3LMv4qaeQVCJtA6JKw/zpIjP6YzX6aSzvKJW3+LnctWUooniUyTnsIMb/rR19mzcDllJ0M1aaPaMhSzTZS1xaCROA3n8EJFKI2c0/DmXGSd1GAHmrrdCMEPTHHGzfisZRYDrJ0zyEr4TCfgb2xGtbrEPIUZajKzP8aLvgVCI3WcTaOvZ2VpAc3OMDG3MX+dzBBmfAaBRkcW8fZ9hF4cHcUQMqQ8sp507+PYyekX1WatAQ3BbJpwqJum6YtYGF5+2nOVueix7dP3UdaTlO0cxzr72LZmM8MdvWhp8NeHP8E7hu4A4HutV/PulX+OJx0273iYqx/56WllAgy5Xfys4wbaC1P8/Ume28Aw+MZllxO/dJplmSPYswsZe+LNqKARity6/ls0r7wHgNjsckpFj0dHe/li8dUA2MrjpvGfkurQLE938jr/8wjRADQLDePBSqbCvyQrGx7nr4aDHPXvYtl4BQ3UOs+nqX7p3CCG7G7fypa+Ozm/vI4bhq/k1R/8DUbkjPJrIzT7q7/kvqV3UdOCG3ddTMfgMGAxdKHg502H6Kh24IYuR9NH+UD4+9Tyn6d9U2MxVMZdDn2vj9LyTaeB4FbvPECfzpLa9wAAe9asZvCSFh7svIxduSVUnAbmwX5sktdUf8Y/i//g4dwmfmvth9ADdW7cXWeTb1IxPL5y3idBHIWwjdn6exChhTHaUJx9hVFev/8eLh1tMDiWHIuHVvaeUpcr2l9Dk4zx4NRWbPNCLmppxTbnLflZVeJvzm3m8vMX8o7eNiqFAp/61KfwfR9DCl6vvsvguObJmQWcTXYvOYf+1CIG6+0wl3nXNiUZ1+S2suBNnHoaeZA6H2y7E5q2IoQmDBdTLfwvmNQIDRtbt/O/V30V0z07JuPXIeV8hv7d51CfcZC1CofsPmYSqymQJE2d91j/xiXGPP30Q9Fa0pRxRcABvZCjYTdB6Xrc8PSQRFPUub35j7GMaT4T3syrjF/gYbFFrWGFHEKgyVKmQ8wwoXN8P7qIuPC4VO7CJeDv1FuxZqZZNX06W2dg2pQ7lyDjCZ69RxWVwwPBEmZ043rCEiG/tfS7nNfxNJVKjpaWodPKey453H8ubqxMc+YIg/d1kJ7oZuXodmJzIMGoO466cjP1xWUqrTtQhtfQjs8hvoItFZOfFiw8LZBoLpYhN3UGxObaM7FrLY8tWkNH/Cj3y2vYITZz6+Qgry09Qks1Tnb4CmzrflqMjyLnPINFu4+RzGaK2cY8KrQ/xtbRc7lv8HKOFRvrJGFWuWnx3Vzd8wtMo0EWlylGtEx5pKqC0LHITPlIv4NS+Fo8tRLFM9c6Aa7xAAnjW0xYeQZiWQYxKZSW0l3RPNh5MXnVxJKxBTRXGmtuOCf59iUJPEvg2b/c9cT/S8nVq2gkedfFVgEXFvdQ1gmGRmMUBxtGiyEiXtb2BBflDuKajfGWpocZy2M6RXbXbL5QmDdwNzkOt6Qi4kaAQGHZL44w72yiIkFYM6jPOpSGEuQHUgTlU/FuEoOX9vwOCStzxjKGN3yccvNTtHzYwBoUFFdvYsO6+4nphs59JLOBV2z42AnM2TXTj/KJPR/g58f6ODbHyFtxEzwR38ju9FpiVp3fXv512usTrPtKntjkPHhl5uUOhxOvozR6HtDgAGk/5+tsuvwmWluuIWYvZGrvAF/7hz8h0iEjTgd3djUOkALNazMpfq/QqMes8T3WWZ9r/H/wLipRI5oy73yFD3Y9wE7X4bLtzSwZSeI5MX5w829zpLWb9w3/I/8RzUeC/dmhN/OGv/uTX20gniW/MUSeR/7mr/+Q7yxqJFj73f0XEhzz0dE04RKPr64Yw4oMAhHRU13AH6/4I7bd/3OSHeMsXfEw0lSUJrNs3/eys5a/au9e1u9sbByFmyKGb0rx+eD3eNo+Z/6hQHHd/gf41PQ/cizZw1vW/j2jsxle92iVIz3fZH/7o6DizLT+FVGiEW3ihAGrZwPU8CBNoyMsOnqcyDHYPLifVeMDTKbjJ1Di6XpAvG0jqXNPBSApv8LU7F4e4iCziSTjTS0cWraSt/a0cp4Zcs9PfoouFPF0iJ4ePsMhV7MsW+VQ53q+oS5i0m94D1KOyV9u7ubWq5ZhOyZRwWNCRUx8dR+tk/MK57sy4N8Tj+J0fQtkiAxTXB93ubH99ERdzxZ3n82q9f+CuWEBwyPfIJ1aT0fHK5kc3ceTD0sObTtCkil8JZCJSXwvjh3fTtFO0dW9j66ug89Z/sxMF+NjSymVWrDtKi0tx5kcXMKCcAJHe0zSjINPVhS5hi0kqDPuL+Oewh9SjDoRRJyb+BYrYvfzjal/IzzJEFvoPMlLsx9EvgDSuUgLKqHNtBdn6+RCxurzHprQthm0OjnatJR+oxdLKMq4aCRmUtAUlLig6UmWtPTTEptguNbBT45dy9G5DXhp9jCvXfFdFmWOz5cZWpRLzUxPL8DzY1TKOTwvgdaSE7SlczNhLJkhMTtJy9QoRrXE2uPjLBqfz6+iezZjrX01VsrCCJJoEaLsMtJPMtp2D4XSLMaaB9nhKL44Pd8/Habit5p8ep3n7p+onsO0KqTGziM7eA12tR1l1ME+RkvtKVLmXY07fCUJxGq8aC3B1AiqVkBYLgHjlI2IsrBwyx5t5MmrDK70sT2PyJBMGS0I2kj2/m8sYx7PVBU+u8xB7uq0SZWm2LZkJdO2SzkeJ5LG6VE/WnPeIY+rd1WxQyi7ggfXxNi22EH/CtTdzydLamO0hdMcjPcwbWRY4g8xbmVZo3cxLtrpYITFup8VYj8BFnEqtDJBniayzBLnVCCV0oL7By/jGwduQ80lqVvqHuH1K76Ng4WKTAwCvEqGSpAgiBy6Og9Qq6WZKuXYmznA46qxocel5tpUwFWp8DlJREMvSTXIkU42rgZrhSbSeprJw1kyR0DaEcW4xcREmkrZRemze4vstE+6pUJyQUi21aSt/3zi4YU4lVPxFpFZJrKqeKlBUsFddNaeBglBuIJJ/2/pTyZZVq4RZj9FX/3nABzIrOYH9iUsjt+DlQgp1NPUUy5tzhQJd87jpsCYhab/MAmm2tiz+q2U0o2rtGp2iPsWVaksW8OokWbT0EE2eSXMp7Yip+bp4Ed6LuC+zGpmq40UBf8bB3+RyR1jE2CM8q9RM8vneKWSxp1krS+igDviiwmLb+F+McFTay9krK2HrJ7hqtl38vBJWJi3Hr2ZP3z/b5LenVF+bVczf/ce/nlBIyzxD3e9nPJ0J0H1pwgVccc1g1Rigr/6SZ1A9+BbPUjArpZJLDlK/CWNME/rzgypXwQ8sm4zj55/CYtnh4jVavi2jQaWHupn044GSVD14ojCayK+bL+Fn4qbT6nLgr2H+cXEO4gSEY+ubuffRy5hwHkMgOv2voNk/yApY4bFxRHi9Tp9Y6cmgDqTCDuFvfJl2IuvPPGbqhfwdnyNcHT7C+6n0G4wCsqmReBXGGlezhO5BXy7tY8Zq+HdSUQhN3pV3ixTZKMAHXnIWBOY85uMEBKtFWLuNBE4Mzy87At8hn7ykUSguTUbcFky5Nn6+Xixm+8fuhFrShNkN3HhpsVcv7SVA9smGL5vBFefWZs1p+Dc4W8QPP0QABrN1KtiHF7XzeNGF0FlL822zzWtMxjy+ZdAuZxjYmIRI8OrGhu01iQqPcTKixBIpCyxOvtfrLUfoZk8hbCDh0tv4ah3/inlvKHlfzNeDfCViULwpLmaopPlD6zvECjJj0dW0F863bOSND1esWA3rW51rj0N06CYNOnvSvOkXEpVOiSsCotPMjIAgsjkR0eu4+6j1+ArG4Hi8p6trHAmODC0jkKYxhIeS40pJBoT9UKYpufrViyxdvduFgwOIrUmNAy2b9zIkcWLMKSJ8D3cWpV1O3dhV6f4/PWabUsafW5E8IqpHDe2aSodEygrBAWyDOakIOjVaAvMMTBmBERgzAqsUYE5LjBmBX6fQngCZ1wj8wLqJ2K9eDH3RcLJYLQsw+q7DLN1Ph1BVBwhOPIgweDWBvfHWeRA7yKKiSR12yFTLjHR1ELdttFGDldcgCEajJo1o8DerhmGW2KYUcieRcuxwgBTS2ZTCc4fDzhvOkKGCleBKQTtdYVvSwq2oLOmWFuI2JUxWFBV9NTOPn9P7gE/No4yPZRRI4xNM5gYpOpLvPanqBdbsG0PjWbEqDIcNzFnXTjYwsPelYyZjesoqRVvLt3FrfsewqgIJjanKF5oInIByeQsk5MLyWTGse1TGXv31SR35W3GwsbYrHYjfqvJI2mAX2pj5tDV1DtGmfI8Jo9VyNVHSE1kkaFARQJHRpTDM4e0nmirjFM223k62U2nn+dV++9nYXUGlODJzUm4PY74UZENB2qY4xDZHTgXvg47vu6sZVaadjPT91Na+l9BfzhOn/MRug2fYz1xZu0cYVsz2h886/sAlSmXoGDhly9kZv8rQJjIyGfTjn9j0IJ/3vw6CskEt03+gNbifHi7ISRmbAU/uvAqNpg2b+i3+Dtd51EaXshgWZru3AhXH3uI3x9vYPq2JJ/mydTdvCd/kGY9xffaruGdq/7viTKFVryz+nbumD4Vm/eGwRv4s/f9y3O248XKbwyR55HvfPg23t/SSEn950+9nVlvDcr7PEGtxBOrRtizKOBVDyle8/Dpp7P860KqlzV+d7cLcp81EWfZDGFeESgLdExzpLeboUQv3SNjHO7u5WDvIi5++gnOr+xmoDXivTe6hIbgnMFLOH/oNdhegXOf/hCulz+t7Nlkmh3LV2GFIWiNbztcFN9Ma/P6U54bP3o3uj7Lk52duJNDrBgcIl08gjwpsZ0WEvHMv604BPOnopFEMw92b+RrK69vnPyAXL3IlUPbeO2Be0kHZwhFEQagiRKK/JsDvNWaru2/R2ryvBOPHF79GT4b382OubvmZjPH6pkrsQ7Z7E12crSlk5oZQ8cMhBchIo1qctCugZz2ENWQVtvCsg2S+YBWw6TdklyybJqfujvZN7QVx9fcuMVl4SQsyR9HpwTNyTGeXg7DzSaL6xnWGlMkXI9KykALgaE0I+0uWkCqEpIphti+wrMbStTIZ9g6+G6m641cFvHYAcLUHiZlmjQlbKfOYjHIhGzmeKwTa7aTC4v9ZOUkR71zEGi6xbeJVJ2872LFDRY60/Q6MwxV08z6MdqcCoGSpGyfmuqh3e5nJmdxuC+B60XM5CyyhQCpYTZjkaxGxKsRxZSJFSikht7BGnuqS3kyvpCfB+cyONPLGnmMg6qHOjYVXM62URsoIiQtsoRDhELSKsq0yjLNsopNSEVZZEUdt16nZWqKdKHI0v5+3DmejZrjEFoWgW1RcxwGmsb58tWSQrLxzbVHBb9zr0mqIklWKqg560f+N6skJQR7Fy2je2KMdKVEJRanEosz2txKNRZngdVFR2whTU1rkOIZMLMimNhDdGwr08VD+IZBa2H2eb70XHUwGO66jIFFLyMyXYSKWHT0B/QO3ntiHQaGxDckWpoY6R5SiW6IAoglEHYSI9aBMExErBkZb0aYz70xP5fUU8dQhkdklTDCJNXcPmStmaIOMUKHWut2vjO9mB9NXIhGYkuf6/vu42WL78aULxBPdJJU832UR1ZxTzjDk7mGt9gNTTYd7KNnZhFxNYisVOa8cM8tccun2apSj0za3ArnNw+SsetINEJAwYuTcZ6lk9rWwMSe08oqDbm4LRrhpKkFKyioPz/jN/3W7xDFBpjoKuAnjuN6EZEhGjrhJKu9PJJk5mAKOwFLk63sLGUxqiZWcRXF+kYA0nKApSPfJbt/AIB93U0caTk1krDTLfKynn0kTItC+NYTVy622MV/yV18NLqZjRh8nPnkhkVrnB8u2MdAYg01Ori769S8RUIpbj/2nxyK/YzjvkGT1Uf3pMmubD+vGr6K97/3356371+M/I8zRD75yU/yz//8z4yOjrJmzRo+9rGPcdlllz3ve78uQ+SLf/M7fKTvUZxI8LtP/i2BSpHM3sHUkSEO9lbYunaKJQXNp39WwC+beL7JmJdCC8iqGhPvFAy1NLN3egUDTy2jb3SSV/Y/SPZZTIgvRiYy8IHXGUzkBOf0K975kzZ2rft9PCeH6ZdoGvwhBxImx1q7ycXrxFOC0DBYfOAQnTWDRcnVuB2bMK3G5FNememJx9lSewxvLpytze1lYXI9bW4v04kkuRB2ZWDc0TSHJmFUp+JY1CyLkfJhjs76HNRZSqKh8DRgqYiXz+zmkvFdeLZJIBSd40PE/IBCMsX25auY6kvzxDnrSBlFasQokSbCQGrNqlmLVx01OH+q4Rbc2iz5x74H8WvfRugALWxKTW/HS1z0qw3y88gF+d1cUNzOruQyhp02VlSOUrBS3DpxL2vK/Yw5LZxT3EtNxOj2xzFQaA0H6lfxcPEteDqFJWpcnv4My50HkPLFnr//v5d7os0nMCpbo9UsDQa5KfHUib+P1bOUCjHCqoFIaKQXkUnVcK2AbQcX0zYzg0uAEw/wSyamowiqBkHNIN7sU89bhDVJvi3iY9fa7F3YmIeOr3nD/Yrrn9Yvur/6exru55GWNjKVErYfsG/RUgwVMZvKUIonOd7RxXhTM6FhEhomSgqms02gNVYYElgWdqS5ZTjgDUd9uk/yKJQNeKDd5FNLHWbMiOWzJep2msNZEzMMSdRrpP2QTSOTBELSPT3DgslxOidGcYsjxEolWmbGCZ04xaTFRMqjpeaSzdcQSlFPdHGg71bymUYW1ER5mDX7vkSyMoLRvAztldBRA9si7CTaK4IKMTs3Ek4dBK2QiTa0X0Im2ggrkwitEIZNFFQQfgWzfR1aK6reYWrLWrHii4j6Biiv3YcRuQSxMnViSCIcPDQCD4cSGfI6w89q13NkqJvJqA1ZCljcfIx0b53zrccokcGh4e04Th+zNDFMNzdPPsC6qf0cTXew21rJAEtZND5IbnIQqxQSq85SsxyaZyeYSVfZum6afKpxKu+adLlsRwsxfx7wXXXjmCpiJtuClZKM9i3CcTW3zd5PLipRNuIcdzs5GutixGnjXYNfp9Wf4d8XvJ5JO8frx35EyYgzaTdxxewTxCKPopmgLh3WlA9jEJ1x7oW6FV+tIdQtVKMrCXXfac/E5c8x5SBxuQVhjhFKSU3HSEVVIik4XsqgIsny9DSFIM19xT9lJFgLwObEN1mV/D5VYpSHXI4NxSl2Nwj7prw4ldDhwkUzJBxFszaZCd9CnRakFjjm3YRyGzlR4Cn/97hQzXtydqeq/PU6OJpsw1U+S2rHMXWE0JqFtRHeNnwnrcEYv+hR/EuUwtSabx4v8OH0eWzNHeJlo5fwD39+OgvvryL/owyRb37zm7zxjW/kk5/8JJdccgn/8R//wec+9zn27t1Lb2/vc7776zJE/vj978Iy41TMEu8vP8Au8wLKmRJDB2pM1EO+ffUIQsMPjq4lYxzmvnycb9Wu4HB8EZNm8wnyqAVinA1igG1qKWO0kHHLXFraxXRTDjOK6J0YITBsjMhn0cggl+zdR39XN8fbO4j5Pl0ToxhK4xuaf721zGizIlOxuPjAeaS8AGEnSahrsMMUGsVQzxH29znEqj5d9Uk6Sj5LajnODdefyI/jiYgdWZ+fN0ua/SGawmH6My6Hsl140uHSyW0sqQxybn03x51Oppwsj7gbiRkeL535BT/MXcaTtaWM1pvws3G0IxH1iKg3eca+TAYBZevscfdnEjfUfOaJKquL8x6Zd609zn75dcygca1QS16Dn76NrLKZsBvXQEvrUxyzswRzXATZqEzeaNQrG3oUDRuJInxWWnBLhSfe+WWkt1rn/PwwQ3YTj7bkiAeam4eqBPYondUkNTPBwvpxcp7ACnrZnrPoqSoOZWZYVjvES2e/TdxrYtpsoSz7aC+vICG3oEUdT3jEdEjJniUXwIyVYWp6nFimzGJ5GFM37tK1ttBIBPNXA4FejqCKKUYAiRDh2Rvx/4Fo4MFYjL9paWLKbBii75gq8tZKAUNJjssOyiLB48YabmAr385dxyFjIYvDIQLD5NHEejJBmWXjRyjrOP954StBCFaXD5EJyvQneomEwfrSQQSapdXjVA0XW4WkwzJFM8mMlSYVVjB8G6EF101P015dTra24kQ9FQFVdw+Tid1YYpSBeDvt/jCoJLEwRof/MAP2OayvjZKJNJN6ExNGK452EGQR4jh1mUMwS0v1asAhEmV862GEymCHm5C4c30SgjYY8BV7a88E3muWOgbLXYl10ulaGXWEMkGbaBqB5yW7jh04HE0pbGeYjA/jyRr742n6W6fYLVcSmTUSlLHNGRxZIcRkP2uoEsMkQhKRFw2ApaPraAS++OW8K2bgY6iIdfufZtHxg/QNH37ed/LpHLOpFKNNx+nvHkRJBVqCdRWFplfhO3On/BdzP/griq18/njoc2TqdeqGQyYosbx6jBY5S3b6Ikrh64HT+yhrfoKk+ROUjiHFqVFYk8EifjD7V9RUFktUuS7zMRa5TzxvXab8FAWZIJQWkQY78mk1CySERz0yKeo3o6JbTzyfMr5FxvpPQgx8aRJXZ74+nDQkr+ruZMYweF2hxHtnZvlgdjNfz01y/eRmPvwnX3oxXfa88j/KELngggs455xz+NSnPnXit1WrVnHrrbfywQ8+Nzjm12WIfOQv/pqi08incm2xQFfsPrLGBDFZJB/EuX1hG6NuxKvLm3lJIUY6lKS8JBaKulqNr+u4ugnkIMIYoaySTNUyhLpIizVBDRMVzJC1PBSafi/LpsQMR1QPrqpQM6voeCt+lMWXik+338+AWyIRmbxn8mI6lc+IdJEyz47kKtrqFdr8MpPapY0JBo02mlUPLbWlOMIk0gFGMI42thCoMSQGFWVSSGSxKnmkqlOxmolZAqUrCEMyZjQ1kiVJE+l7mLbPoNNOQvtUhCa00yhH4MkUU06GIRUjWy6Qqc4yk+0gb5lYoaSUbkeEAXUnRsWwcYRPS/koZs5gfbSDRD2iX3aRNmboKIcIJ8/BIEfMbeKd+9pYVFhyYlzGmp7iC31f4eF646SUlYo3Zj0WhwpPx6gog2rVoDlVJFOWeAXBkQXtLFYjNHseFR2jkHTIC9DKJWH5HA/6WCEPUqin2G6up6CaKFsWebuFveE52MyyeXIX021NHPJXoqSBb8ZI18eYTbi42sWLLBJeiGUJatrCl5pkIDDCEsVkE4ElMOohZqQxpcAyfSIdoMoCjQlJAye08cMaVdMhY5RJ+UVm3Rw90TRFlWEkngUpiFcCQkMQWZJICJJBhXWVAfxkiApstsfWkvZqXD5zkAV1j32dAceDZbyq+BALgiM8al1A80RELjZMoFKgFUFMs8R7CrO2AKomrlFga8saQlFmaXWYJgNC5VG1A+KlFdhqiEhOIcudyBCmYzHSxgBO4FOXii4xRN1LEQiJlCFVL0WsGhGJGK5Rxo7yTDgGX+uDXXPXMJ2e4l0jAX0FE1MsIuscoCAsTKnIUiIhNKOkaYtmiBma2aCLlBURiCroVrSYpiYcJlQHi9mHry1G7SxNocDVLo4ImDEzzBgWTlRgVnehtENkBzg6jls/h2S4HFPP65GQGkruYcY+jhH5WDpGgkmSIk/ebMYI0ng6CVqQUWWEIVHSICQkH6ZxRQoPSVWEzFgubf4waAvfTuPU08wIl5gok9YKQ6YJtaJmTBIGx7HMJmxjHffEBV3WExSjc5i1sxjONIqjNNUS3NXXxbDVjaHydBbHWOAPsD21iaFsN8koz+rjhxhpXoxVmEalXaYS7WhpUNYOPbMDeJaDVa0SJBJYhkHeTREIsOpV0rUKxViSUArMSGMoSRRpfEuSNUOSlVkmrTbS9RLZ2SkwXFpmJokSmhpxOseP0VT3aJ2Z4PCCPrK1adKT0w1SwlSaOgaGUoz0rsHWLmNxKCXizGY7SUiT5eUaR12XhDfEdPB5lBoHwKaJqaa34MXWsaTs0ep5BM40x2UbVSy0ZeAGAZWYQSQMQsNqxOuGCkNpcrpIs1+iZLiMuC0YRChpNHhIIoVr1El5NWbNLIlqFStUFJNJrChCaEnNAS0FsdDDqRskq5qZpCTlC2JRkZUVaNEpYhHszhi01xUd1YBZ26RmVjGDEUI5RlNYQQmHmtmob2RBzTHI+BWWV44w48c4JziELQNyqkxfZYS8kWC6nsGIhSRLFfaklxAlXa7JP0ohzFIL/pZakMIQNpYAYVh45jfQaiu95hiD1WYwHcbsbnQoUbKCiiyShschvZTv544wmCzSVMtywbFNICEvDjLtzJJu7uHjf/y1/7Y9Fv4HGSK+7xOPx/nWt77FbbfN81e8+93vZvv27Tz44IOnPO95Hp43b80Vi0UWLFjw326I/Osf/in5dBItNIujNgxtILQi0BEFUUE/k0FRawwNIKgbETFlYmsDpRUl0yemLJRohJ4iJBYGpjbwREBAhKkFCo2QEk0j74dCI+acgm7UuF+MUDhYRChCIrQQWBgIBIYGXyg0mqKs0xzF0UAgNQKNUOCLEOZKjVBEQuFLjakFkWh8LxFZaDRKNjguQhShUDjKwNEGVRnOIQEEgYywIomhBZYSBKZAoZA02qHRREIRobG1xJxD0gshKMg6MWViYlATAQYCQ0scZeDLCBsLA0lIhBRyLn+vRKOpioCYtkhoFyEESkdIJEKDJwI8EWIgcbVNTfiYWmBhYWpJRTbc2RERZdmYQ7G5rJShiIgpm5oIGsyMmIQo4jiURI1gjq/D1iaWNpBaUJcBEYqUjp0YT1s3xtdVJpFQJ94TMDe+mkAobAwcbVISdRACR5sIDWounNXWJhXpEaEwdKNPTQRCCyKh8ESEnnvWUSYJ7eCJAIXG1BJPhrjKojrXZkebVKSPrcwT5TjaJBKaugzwGxdjZFQMoTW+aISrBkKTVm4DXyQiQqFJ4FDDw1YGtrTRSp2oa1xZqJPG3p0jWoqEpioDbG0QEhEIhakF9bl6SiQmkrrw0YCtDLRo5EOKUAga9fVEiKUNIqHm+qsxq11lUhcBgYxwIgOJoGh4J/4GnOjfmhHOlQ+xyCSQivrcvGrEdkQ42iQQjT4RWuDJEFub1ESjP0+MqwaJJBIKVzfmkk/YmJNzz1nawNYmYm79VUWD+CuhXSKhkFrgiYBwzvcRoUjO/U0gqOERwyZC44l5AKHUAhuTCDWnjebng0TMvaPw5rxgam4u1UWAhcEzl4QajaUlPiGh1CQjh0BEzKk1TC1P6DBJQ18YWuAog4oMTvRTKCLkHH5DzGmbZ/wVpm6sdTE3XlILlNDY2iQUCktLIjQV6eFqC0NLYsokQYy8rFCQNRLKJqeS+CKgLkKsxmUoJgZV4eET4mgTjSYUeq6cRh0kBlKDLyN8QnwREoiItHKpE8zVxSChHAwt8EWIRFCRjXmh5vRGKBSGFiS0Q6BDlGz0X6MekqrwCYUiHjXaFUhNLDLndCxoIahKv6H/dIPQ8Jn66pPWfqOPIBQNH2dNBIRyjoJdCywlT2CVAtFYTwCJyCIUujFflYGpG+MSCIWlDVxlYGhBKBRlI8DQAkmjPFsJPKmoGxFWJNCCE/tIh8ogSxWO1/fzd5/+Kv9d8mIMkV9rQPvU1BRRFJ2W56G9vZ2xsbHTnv/gBz/I3/zN3/w6qwRAtQ6xmKZqw4Ax8fwvzEmZ4Fn//hVd4af0/gsjVxo2Ss//0JyczMZRl2euqy8jzlRiaL4wQFpDwZ5ads0IT/w2xzJBdY5ps8JzM6mWhUeZ5+YXKHIyIv/s/VaT898KjPl3/Dni+vqz6uKLcM6om5eCmAe91YQCAkrPk9jTJzylDc8uk5P+Fs4pmbMxp3gyxDvDPPON+fEJ5zZQX4Ynyqk8q8SQiGnjdAzTM8bMM1J8pj+faeNJbS0Zp45L4dllnVzvZ+phnIFN9AxzsTY3FrUzzI+KPKkvT5qXGn1iXp0s/hyYMjjp2aoI4Dm+URen/6bnDKVn/12dlPigsVGcvlZOzJsz3C6UxakRJdUzjL4S+rT5CRDO9WfpOdZIwKkg+5NXSN58YXrm1FQoc+07a+j5s+o51+ZnjKTaSX1QFwGIxphOMc9iW5E+FXkqUd9pXzmpn70zjNezpSjn+zkUiqo8/Z0zzYXyWVdjQ0pmcNL/n/5sTc7rv2eL/zxlR0ITGRFw+pyqnDTXG0bX/DO+iE7M+2ckFI1joy/VST0Nnnmq72HMKJBNxagXzpL/4v+B/D9h1hHPuuvTWp/2G8Bf/MVf8Ed/9Ecn/v2MR+S/W1R2BDmmYcEy8CNcv05cKWxtYZnu3OlZgBAY2gBpEs1Zxo2TgIkvA8wIEAZKKKQ2CUUISMwobFjEAgylCJUHOJhaNDJha01oaepmhK8CHC0wlERG4AgDQxpURBkVQWRbxLEIJSgR4UYKEQUYUuHpECEEMW0BilCA1iZxbeGJECcyibTfOGmbBpHQyKiMjUMobAxhovHwlY+QFqaGSPkoYYHh0EBgSmTkI6IIU0doLRDKoOLM+WAMh0D7SKURUYRG40qXqoiIjAg7VEQIbBoemoq0kGENA4sAhRYBgfTQhoUvBW4ocJHY2qaChy9t6qKG0nMn/khhGyaBtDGVJCQkEiZJwAkCqih8y6JiKGKRJOtLQnyUAVYUEckYBhqPAISgKXLRQZmKESCMOCL0G34rYaANgaFNbBmnSg2tfCxlIJ0YtSjE1gKTiKoQCBUQSIWBxFImnhRIw8aUJjKMEJGHtlOUoypKh8RCkIYFMqJmgBkZCNXwQMjIQ9kS3xCYKsJSNlYUUjcCQiuGxsOMGv3vGRaNc0+AHSi0BHPO8xYJqJsgtERoF1vVMDAJsdBWHKs+DWZIKBzsQCGlwrASoE3qukoMiac9AlNiRBCTLlqH+GGD5VPjY8150RwlyYsILSycoOE9w4kR4aOjiIiIXKSR0sGn4VFSOiSSAl8IhIKklgRhba4fGzT6UikMKwb4hDpEGkkiFeLLEIFBTAksLRHKJDQFYViBSGHNRZ/UpCShNL6uEvkQmYLQsrG0IJAmprIQhEglcH0fbYTkDRA6QhkSZYAQcYxaBSuoIGwX37CJsKmoOtlQYJgGngzQ0iEeJVDaR0UVAttG6hp2CB4S0xT4lkkitDDqEdOOj6MjkAkSYYiwXCqqSE5FlAyLkmmTjSxSPlQNhak1kfCRQUjkOETCxPEjdFgmsGJoaeIbEbHQxACisI4QGqRJChOUQdkUFI2ImIqwgwgMF6kUQRiA1FiGhSltKjLCiSRe5GHpxqZnKwtT2A0uHK2oC4UnJVJFCGHi2RLTjzANkyCoYlgucVw8VSVSEXVTkBIuPhG+hEgH6AaBPcnAoGSCg0aEEeNmEROHUIQo08BWglbPQWhBLRYjJmzKon4iQiwyBDqsoXExDQctPAzVgI+HIsIOBZ6hkNIGZWLgo2SExMTEQQmFrUTDTBACrRVK+cSlRSgUIpJIJL5pIoSBFAFCKRqzUGFqh5KsYQhJJlBExJCGi6FqBCIkxMSXCkNo0tohMi3MSOKpeoN914CaoXC0hYlq6B4/pIUYs6qAMBpXSzXHIa0kblSjKkKUsLCkSzwoEBkVAiRKmLjCRkQ2BVMxYQQEQpEJIINB1jDJUcbQgppqZT+aY+Ywf/PvX/5v32tfqPxaDZGWlhYMwzjN+zExMXHGbJiO4+A4v3xI2guVZXqc8ZpJ8+hjzNzQTZirsYYGd4fwEthTS/mPIxNsX1hg2UwzH57+E4woQWBVGU7VGHQtimaG3bmIe1pzBPKZzKcedQPGn6cNVn0PmcmPILRPJX0r1ewrT/l7c63KJVMBbzmi6K41XNEKzUG3yP7UGHb4MMrPUZs8n0hqjMihN/4LLnDvZX+6D8eoYuBiGQGG0rSICSr1DAUd55zKIQIk90bnYDmKRe44D7RdwAWFRxmzW1gT7cdsmSKftvDtRqZKt6YoJh3uEK9jL2sYEPM5appLU0yn5nkvLKUJpOC6HY+wc+FyxrPNGEpjavAkJPwaq8cPsGDqGFbdIdQ2uTBktreDqlmlt7SIW8ZbafPnmRFHrSk+1PVF9sePANClOmiPvRwLybmzdQygKid4KtWKj8uK6jEm7XYumq2Q8Q3s0GE0UaSvnEZSomwphh1Br1ejs16magS0+HWisLHx26IbTzdTsDxCc4J00Ixv1XDUYZQGQ7dQF4rjbpWheAuOyuLLDOP2AjxZp037RHKWMbuTvalm2uqSqiHYnY7RVZdk/AQ7sgZaVKnOpTfvqhXxZZaxOUpRodUpmYPPPpf3sZz93MT3yVB83ufR+nlBgNO7bqEpXkT7aT5TW8X2qS6EAa4laV6YocWsk7UKDCaSRIaHWf0aE/XdjXobaRK5m/DddQzLBayKdhMQZ1pmmZ0DSJ5NLO2RY5YJcXpekrNJW13x9sM+502HLKhpcGDKFmxpNXk6Z3BPp0lwBvKwk/t3c30b66r5hsGlkozqLLlaicFYhkk3SUc4zgp/gGzZ5HgiyxJzLzdNPM4R0UNK12it2JSz48SMIm49TnpiMclwF4WYxXR3SGYsJF9zUNOChI7w8wamrRkfi1HUJstbChydzFIuOjR7Edky9C9+LWbTBZSBajCNPfMtjMog+aSFlgHNpYhiwqYemRiRQSExn6n62bNAaM24hooZZ9puYsZpJ59cjfQOcv3QQ5hEhNIgU60znE1RjSXJlAvULAvfbBxKUuU8AKEhSHghM+kM6UoRK1DUHBPPgqqjCG1N07RFYEnK2TgBRTqjGB3lGsKPk6zkEUSYoabm2LRMF8gVq1jBqR6EYsrmx5tCfnSewLMb43fpHsVbfgEicJAt0B6fZX9yGV7WIJOo0KPG6TXGmGMYYNRuIdKSTj9Aa5sx16Wp1kJMbkNrC1+voBpdjiHGiclHqKnL0NpAiiIaFy/qxediNDBtC0KhSQXwSItBItSkQxh2BVFFocZ8YhpMCYcWO4RxhSGP010x6PLHyXktdFZXnNLGM+6+z0xVDVgwbfgoO+IXbSZrJsbJKYcJWaBkhMykW5lyLdqKMxzN9dGVL+OaTdzdk6KzMEzf7AwP575LxZjCooVW422MZjvoCMooodFGyKyZYcxuZsWD+/mr5JkDEv5fyP8TsOrmzZv55Cc/eeK31atXc8stt/x/Blb93N//Pgk1RWA4vOfCP+CD/BHevov4z4k1THtZbKBF72Z69VdBQ0/+tWzbcBOXjz9GqC2WFgeJKhbrJjxusP6TPXolX3IvJ78gw8vTD9CePoSuJvj43tdzSC4nytnEXQ/bruB4B/HUfyEISXoLWDJzPT2lSahD18Q4lwWH6eh7JxEnKWP7IJWFH8eUY4y0uvjxufvDShMjj7+V2mRjgie7n6LjnK9jxk5VRZPVZr675RaeVOuIhIGrPd759Lc5f2YvE4tyZMUk5ZconL5T3b1+1aSWd5kdzlDaGyfwbPLpJlKVAqFhEvMabt6aE8OIIiLDQCqFE8yXo4RAzE0xO4xI+AFmMmJKNZDxccNHCn2CrMgkYmEyT1ZZLG99KUo2kpYpFD/JPsxn2u/ElwFpz6ZrQpJKNLMtFydXdqnEDLLVMVYkjzNtwaqU4rxExIBvEClYFT/dtaxCm/yRS5nc+Qp05CBkQHLVPYQrd9Cv2+jXCygrhwm/jXF3MYHVMreZGyD+m+14P0LUArANtCWRtQo4Fpnpcc49UmfJpM9Ib4LzJ/aRJEM9GkSbY2CHmK4Bcho7WcTNVqjPSrQ2sJOQ6s4T+TbS1Bh2naCSwXArSOOFXS0emFnKV/a9htFKY06mrBJvW/dVWtL7+easzdG5sMvzEyG3Zf0T9OzPFg3UQ5dps5VOhulnOTY+rUyQpHFtpJRgImxnwu4gywxGqGgzx5jQ7ajAxDY8Kl4X3fke9PSFbBidZ8esmT4D3Y9z74I822MrOV89yrpgOzOylTounfYQVeJ0MYyHi0mA+zzXgM+Wmdkc0lKMF1uJaQ/taw4cWIo9W8UoK6oyTmQYjDttLPeOYkgPt+YR66wjtaI27qKUQFoaFT63oSnNXszYJaAjouAoUXAQVP5F1TdEsiu9li1NFzUML61ZVunn/PxTNAXPwYsiEqBPTQDoJDrRtkM5FSdSHpEdx7TjhEQ06xRT8tmXvI1139Q0RBRZBIFDW9sRFvTuOe0xYwKsEYG2QfhzpHVHBaVKkjuWeTy8WqCFoKWgeeN9iov2n33bqmTaGOtqZSrbRCHbRkLa9PcsYCJVpanyGCmVxzc0T2UhLw02VkdwVECkVnHMViwP6rhMsDXe0FG5Wh1LriJvFXjZZCuXlC4hETUzbcwy4Nnkiw3a+LSEDXGDJvP5DxChPEzVcDBVmng0v7fNLPwRUEeEOYrtWwhqyyiWLZqLNmJsFovjGItXoLIVxBw2zyn3ENpFZBjDrrZxqNzCwXoTP+37N8ZixzGVwYcG/pDWoJW9xhjVwmEMJ8GEKHFP5xr6C830+NNs+cc3PG+9X4z8jwGrwnz47qc//WkuuugiPvOZz/DZz36WPXv2sHDhc2eM/HUZIl/56w+wxjuHoiV445Ut/M2xL3LX4XXsDhcQzV2OLmIIu+XzjLTWWHMkzSs31mlK508r67BayvA9raSPzTLc3ssdN17Fq8c/z0u6jyKMiG8cuI17j18JgHTGiC/8FMLwsNGky00sKk2RiGuuPahYfeASYpvfckr5E8v/i9mFd59y12yEiuikyT6196VM7bkFtMRwSnSc9yVSXTsBeHDoYr6y9zUnQo43tu7kHRu+hHUWzAiAXzQ5dFcfQbUB0OtLzNATKxK3Y4xGF3CgdhmRtwfQCJkFYWCbMTrMxzGNUeom5OsWjqVpmqzSsXecqm2Riju0rL8YN53AED47kkv50IqFjMc0I24bKwsR/+fADBfMKjTxM9Ztd6yfD3V/kUlrFqHhWtflhtYZPOJIoYhRP+N7GgiwGKULlzoeDo8VbqT34c1kKo2+OdYq+dH5FtPJxBnL+FWkpXaUipkikC5thScIQ5ea1UE4FuCEdWrjzYjohS/FZkKafBtDC2ytOd+3iClBWWosDZkzEEMJw8OMFQjKbVjxKZLd2/FLHdjpUdrWfxshz06vHirJw8MX8r3+mygFKaz0NuJd32q4tIXmt5s9FroxyipDWs4SIfGES5kke1nDQb2SUdHORTzKiugAOjI55K9inbGdDbP9tE0EHJnqovvBMfLrDfyliuyPBalNVTItNXavT1N3DXr3bsAdfucpWVW1CJlachczPfeC/cLuuQPfJoxswtChVGo+jf7/6aduIopM6vUkrltBypBaLY3WZwcI1bXBrIpTmqubFJqKtokTIIRmVsVBhsTiRc5p2U0mNk2TkSfmVKmPCupTDkHZwivaqEASVEzOykzT4AtEKxAZl1a9gHhkkbKaaHWzSJ7i29WI72ZuoGI2TrpN/gzXT97LgmiUVqeCbWYJjXXM6HPxlEAId85bZhO4U1QSx4hEHiEMlNEA1sdiBZLJGarVDI5ToVBop7llEK0FYeAQT+QxZERzy3Fct4xpPj+W4xkxi53ES0tJTK3DCOPkhw6SeuBhhFfmUBf8yystZpONNbJwQnD9kyHrj2qUaZGsBKTOvPRPiDIthDAo9iyCdAcpu5NkahmjboGMvYDUSckuIxQj9gQdfgszZoHmMIsSilFripIsM06eUr4XUZ/LM2MfJeFtIeclWN90BVm77QW3+2SJKpMYifls297+H6LDOqo4QjS5D3QDB2K0rCAsDEJQQbXGqWyuIyyX6nlFUuXreE9ZM5HZglY2V4+8nveUzjvlO3ruevq9zhEe9zppZYon/vHNv1Sdzyb/owwRaBCafehDH2J0dJS1a9fy0Y9+lMsvPz0b4rPl12WIfO0f/pYrildyLC74i0sHufqJfi6uPsoVPMoXoxsRWlE5UuJYc5X7zp3E9SS/9fgilt/ajxs/O9hLKxAS9usVLDYL2NEYWsOT45t4YHQ1g9mfIc0yUW0B3cWrWNM0wGU9v6BZO3Tu+l0SM42Mtsork3fuYPLaLTAHQKp7SVyrTMusx5r95ROZNJ8ZvKlwIffm3810uAiAZam7+JLVydY50pue5DBvX/cVFqRGnrd/okAwvSfH+LYWornTrjRjWMl27NRaUj2HqU8vpjq5HD89gNGxDTNWwrLqlEotFAvtoDUbduxk5f79AJTX9pE65zaklEzHq3yu6SJ+1N0wdGwV8s7BAW6ob8ettpCaaCyaQtdD1HNHMN0MdVtTL5VwIoE7ei5fjT3J3dmtAKyOmrm9pYwb89llrCZGjTbGeYILeZSLKUVZJsxTFcP6Ix43Pl3BCaHkCrYtdnhkZQzf+tW4C5r9Wc4v7GJ/so+X5B/kmsqD9IghfFviW4K6a1BKGCghUBqE2fheLXSpBjGqYQwpFMPlTo4UFjJRbUEpg9r0YkphnJWBgaMFrhbkIkFWCaznoAWL0NQF+EJja0FJao6bERNGw2CZMBQThkajcYRPHI+e3BCbO3fTnhlnWerQKeXNeDH+bXAheafB96K9dq50ctzSsw35PEnuflkxvAyth16FXenCLTQo9UO7QKVlB15yhPyCe9FnAK0CiApYBZi1U4QJcITHrntWYY02QIPKtNDSQJsW2rJxkjWqQY56LEklLolhY2ERiABLvzi+HAC0QkQRIvARYYBAY5SLyMDHqBYbCkOdmVzr1E6QGM5aDLkCYbRide3F7H4cO1YiHi9g21Us08MwQwJlcM/eG/je2PUAtBkzXKG20jd0GM+3OJVGzsDJxhGyGSO5hLrp4PY8Tj206enZQy43RrmcI4osEonZF2VYnE1kEENok8hueFB2lG3uLRkcDwV2NUZy19t4y56fcsH4/lPeK8XgMzeleGxZQwc7kcN1sz38r+IRQmuIrrogHDGotKxmML2G1FREuGs/5vAYSojnZewdy3SQijeTdVrQQQVhJ8GwEYaNcFJzqStcZsKIp50+PGlhaEVT6XH86Z9hqQjPNEiHFqsTG1GGScGo4mSXYM6OY1dnsbs2I+ZIJ41096/cl2eSbfH9/N/ejxMJRX38pQQzl/MmbH4XF9+dRCqL0bWfpdqyhw8+/m7680to05M8/k+//d9aj/9xhsgvK78uQ+SnH3gfa6s3sCct+dT646x/4iBvEN9lOUco6jjFmsE3j20kEoJvXztEzQq5eUsHabmAu6+4Edf8D1abw9yUeWGLcjoU/NuEQyGSuFGGmcPvIooap5QLDY+/I4kbxdAioJa/n+j+O9GGYvQtMO6cx087z+Oe3CUIAW7g87KpB/nt0e9yTnk/HjbOHBLb0w5ba69nb7GRkO+IGfG9hM+VCx/gNcu/h/GsE2+yHDZCRyNFOW4SWaeeooOawdDDHRSPptBqXnktvGaI3NIStVqSWOwMbLIKUncZpH7WMGKOX9LCoU2L8QOXkfYcP2q5noKZYTGH6A6neLP4LI4sn4iDDclhitlnFSmZopUiacIgy7IDL2G2VOSfu76IJwMcZfN/xn6XSmI9TzeZ7E1LDqdOP72mqxHXbq+xZrDRZ8NNBndcmqJ8lvuEtto0E7FG1tVNpT1MeUlS0zP0jB0jsGwWVo/xytV3E6U1ni0JTfGiiZhUZCJExFChmfDYpfhj6yEyMKwqqu4S1dsQ2M9fELAjVqYsIipYHDUkBal/RbpXjRQKpQ2kO0S8+78Q9jRoEPmLKY7dBBgszR7m9uXfZbDcw6Ojm7mk63Eu7X7sV/ksTmkhTcduIDGxCSOax0AUuh5mbM3nG9leI02iGtGU9zEizUiHS9NMQHYqYrbcxOqwkZtp1kiSi8rck76A92XfgS3rJItF2mbGSBdn0QiS1SK5/AyetElEVSbsVnJBnqKZZNjtYlXlIJYKqLgJxjLdTKebSKDprE5SdZMElo0oVWiZHSHuV9GWg1GvnLiafO7mCpTjoucyZIfJzIn/astpzCktSJT6iFcbAP5I1imn+/HdRrSJ1nBENfFU2ENlziuz1BrnptZHSMXzpNMTuG6R0mGX0jGXoGzjl041rnLL83SeP4nphiewFr+MBIFNKd9GtlxjWX2EfBtMNzfq5NYjegdrjMzcyHRwGd9vATFZZreOMMYzvHv7HaycbeRvmUrBWA7WnpQ+6cnlLl+5WjCaa+jflloL502eh6Ns9i7bjZtNsHOy4RFujbWSkCmK9jmE+fVsOriP1tlJ2ia3s3RsnLZpgR09fyJKACUkR/pu5tjCBt16rDrOut2fJVkd/aX7SeYWQbqrQbfQthrbSmOlFyAMq0Hvb1gI44WtfYARa5J3LfogVaPOFYVzmRh5NY+jsYBXm/3Y5jSJRJ6u1AHa2o/w9/v+gKPFhbQG0zzx4Tf90u04k/zGEHke+Z0vfZL9uQvQAppKE5xz6DF+ny8SCcmrNn+UFdufYNWuHYx3LaOweIqt6e1sPJhhY3+W8RZ4eskQk7kIJRuo7HWxkAvciIVli3iTz2jUSU+soQDHA8EnJxtGSLupeFdbnbrfxEODF7H06E28au4KYlIH9O/6Fl2lhyEuaDoWoGKalpck0PqPCPQC/jmjuLPDJGp3IWYitObi4qNcV9tBbDRPsu8o3zj+Uvxj53NVzcJCEMbyLLvyn3BSjQyp5VqGnB8jt+2VpOobMWVDEWkUQ6u+yKiucPToOSxZ/XOSLUeBhkFSHokzvLWdcO66JtVTpu/aYYxnZUuVRWj+uIk11NjY868NqV7+whY6QIRknA6G6KVMioOs4DgLOSYWn/bsunzEB7YN8LHOr7E33mB0fPnMlbxt4jZsbTHmCj6/2OZYQvJ0zmD5SMArt5YxVcM1eWhxHb9riNF4M66e4brpLdhGnYwusrmyk4lmB2IBJcslSCqmD2QYfGAek9Bx3gSta2ZP64NT+iOIYXpZIq/CzuEWii01pN9EaXoRmWIfop4lXu4GNPJ5TtxaR4BGhcOocBhNnYhpRH0cUCipCZo7iNLNLBwcJDNTIVZJk08tYCq3HN8wwUpRNF0kMGooJDBul2mTBRSSraZLXieIOUMoo0qoHZBVjPhx7OaHECJCBRnqw7cT1Z4Zk7OT27fFJnnpop/Rmx6i6Cd5aOhilmYH2D65ltXNByn6KSarzbTFJ2mNTVMN47y88wk6Bm4hMzLvNY1EwI7kcb4e2OwILV7S93NmvRwPDl2M4wfUrAZzaUwH1MSp/dhCHg+bGB4TnJrT44WI1BG2CsgEszQFBbrrIyyuHsFRzx2KebLUpUNdOmjRiHg4Futlxm7CFxbLa4cpWBkiyyahfXK6xNrECIEdw5aKhcY4FZlgnBYKpNFeOxQ3oOawBVFshMnUER6LejgYNTx/DgGbzGFWGJNntIulDFEhJItHEJOF06JNDSfESoS0bZimafk85qxCnH/hvdjhMKXpH7PJGmFPzSKMXKp+ilxsgvTYpayttmLrZ7ypHuvX3UsqNU3zWMiagQJWqNFasKN6E1tLb2KnGdE0dDe3H7wPW4WEhuT7N1/Bt697BYUQLhx6ijf87FEW7tyP1FC34PsXSr5/gcS3wFQmq2ZXsbS4lLsW3oUS6rQp6cU2UcneTmQ1PBGmd5DU9Gdx66N0zELnrKalAC1FTXseXB8MlUTINpS0KTbfQD3RAOobYZ3zH/8AUpUJDIlUmlgYogwLmerENGIIJ4Ww4qjaLEZ2IUbrCnS90PCuJDvRfhkZy4EVP2MU6bNFawUIook9BIOPUtv0RmqmT0obGEJSMar8ad9HmLBmWFhs4eVP9FHwZvhqz2soWFlMHXKj2MtkTysPrt6MIKT7x3uZMlvo8Kd49CP/f34188vKr80Q+dxH+cGSqzCU5v2PV2ktH+Bl5h/zqoVf4NFFi3jHN/6ZVL5AYsWNRPFZPt15B82lJC97qHEy3jA1ylNrk8zWbCqxkMGlBYbSPmuOpFi/r5liMsFnf+tPyUUDiIl/R0R5mg3BO9N1mhOK1Nj55I5fT+wkVtFbKTGFpr02wZtmn+KKkV9gDAVETYqF19eou/+Iuep8vh+v8fP930C0W1zesoVFNBInHc73ceehl3FgtrFQ1puzvKSYQvkptFkjtuIupqoJarXGScu0XYzRo9hVj17RQT7t0Ne2iiNDLQTh/KJwFmxlxpxGGgH1aRt3eADhzWutBc40PYlZ9JIIa38rscNFzNEIZWuKr46oXnLqJh1iMjYHxD3GImZoYoZmjtFHP8uJxItzf5tKs36mTsn7L/LR/QAsrvfwF8Nvo8efj8yqioADFchHEJljLN34cdzsEFo0IgG0FNQdecb07LP9Kab25qiMNrAjqZ4ybRunSXVXsaZWMWGUGBIlBqOAyak+VpZWc+XE1VSVYKoO0+qFg1qF0FgWqCiiK7adruROUsYhjlmDHA5SHHck7QMtmMphuvkclBPHKOdxxweRfgN4mfRCNg8Mk/Dnx+mTN0keWiOIDEGz38k5R2+gd3YNljr9tKVPIt3b27qVnV33k483+HaMyKar2s4xt4gO02gyFJO/g3EkQM4lLzRkQLebJ9c0iaWXc2jKpitrcN3qLg5OH8MNDjNdnKDopcg4BfqLGxBGExvzmr8gdkpdplB8A59vncKa8OuReFhlcXUAECyoDREJSWd9jHT03Dmk6tJBI4ipOmUjQdlMYCuf3ak1lMwks1aOWfvFG0AnSwsFmkWBTbKfSZ2lopJsqCVJeosbBG9C8aNEwJCpWB9UOc+DpBXgx8dQqkEOpqwKgQxAc1qWawCjXMAdOYKMTrVKKlaSqVgbTzevZ6y1jcifxjR3Y8SOI608QnoIs4Q4CXfmhA6r8qtYUprXcbNOniftIo49ymXqCNbsVeRrG9gfjfPn995Fc61x5TLQ3sKnL78anUrRXG2jK4xxsbiHVc73KNcl1n4XubtxgBvLwb+/zOBQd6NBdmgjtaRunQ0rJqhkXkUt8/K5HwKS+R+QKP8YS0AUNnhh/PTtFLPXg7DonAm57ZEyzeUGQdmUvI/UdCOzemAoHtw4xWTOw7PndV1TpZV/urOL1kwfzvKGB8WrT1KTdbL2qZQUIRHmHDaxFMySsk6fK6HymfJHeMp5igvvfhC7XmdP71J2X3QOWghSCcEh9xBb0zvIhik+dPQPSRYf5p6xw3jS5sdtNzIU66bZn4H1SUZ7ehFqnLafzjBr5+j2J9jykbec9t1fRX5jiDyP/P5//D3fXn4Trzru8+f7Gsq7YN7J+xa/iv3ZGm//5r8SSYMbe9/BHYmHuGvhD0DDOx/NUp3NIE3F8lcOMLWniak9uQbzEY0gCsOwCL2A4699E3fXv4blD5Bz2vjmTV+hvO8Axfu20J6/AgAtIkpNu9kef4qvDK1mn14NQKvS/OVlOZZ85O1Q14QrIsRNHnRvYnouTPIZ0RoeHrmQ/9zz2hOA1FQq4E/tzzA+vRS7dA1mlEKjKaf7qcdPdyMaYYx4uQ+n3oyYKyMwS1RSRwicPADbwy6OR1nO1RneXi/w+Pi38NQ8XmbV8BQLp4vUHJeRlnZml17E0Pqr+dYim8ApoJRBWSRRSKJfIe/LM9JbH+L88DE61TgLitNcM/k4O42ID2RylIXE0vB7o2/ghsLFZ3zfS4xQ7NpCZFapZ/vxUvOpvEXUMIakl0aNdrH93hCtJcJoJZ1MY2Y3UwosRu1J0rUOpJYkguwv1Y6FPMLG3E8ItEOLdZSUMXXWZ0NhMy472C1W8Vi4EsX8dVKiWKR3705GUjZKNqIjumfLREIw3tzE5IImwmSGhJoH5GkNRC52kEBiEKv0IJWNVCYCyWjqMA8u/ib5+DhmZHP5wO0sm9pMfGGVapfkvxwYaO1ESwlKYQ6UMAfKJ4BLV69s499ft4mEc/p4e944+/e/j6mp+4jPrKH10O24xfncUwNJySd7TR5sNsiV87z9J9/iqie24kubyVQ7Ma/IaLyZby2/ikhIxpq66VzQznl9OfIjEyS2P85AWVF0ElRMl6X1AuvtHENNC9lBwOIwz5Kon6QaxwlKzOQLqOi5TR0NTDhtjNutrOIYL03voOok2CLWUSTJGnGEzUY/Y7qJg7qHJ9Vy+nU3C8QkAk27mOWg6qFMjH2698R6PVmSVCmfBah9JmkLBS+r2jSpRln7rZAn7ZCqhKWBZFlgUJXQFAlsQ3DdjYtYdlknjw2N8tVtOwmPj6EBh4h2M8KtVzBL0xj1Ku748dO+FySz5NsXUzBS5HWcsnaY1THy2qUsowbRQNSYY8IogjZJihBTmfTKWWIiYMaZYSS7m8iosSw/yB98P6Az3+j7J5YJ/vmV8nmvN3snNNdsV5x3SNNUggfWCb5wvTwrxqsrMpCOS92/gOEZRWAuR648n4rduC5aGPnUyyVqtoNnO3iGhRFpLj5Q4bLdPoaGUFdQ5R+jwoauyCcC7jl/nGpsft6YwuT29jeT/OlqLhIm7XZDl3iH78Xf/e0TYNMnz93M0b7FSBVy4fAoPQdGiSoTbF/cxphrkzDT9C3YyJHBbYTKP0XX5so1LhgYRWrN3pUr+ciqV7K07VGebnoQQ0s+dvQ9LK+CdeTPmNiV4u71i6kaLl/teR11I0azP80tUz9k40tewv990qFgZVjgjfHQR9/2vPPtxchvDJHnkQ/+29/yr+texoe21bh6omHFl6ny+a4K+6MRrnz0p+jcIha1bGKXeZyfd/2cglPgrQMhzmQ3tWmXdHeJlecXiC94HXd/aRdOMX/KNx7YOMnRripKxCm2/TW/s+UQr6r0krYbXpVK8y7G1nyRcO5+V2nBdw7dzE+OXneijFuX/pCbF91z1jVZq9t85hdvZicNQKqZ0tTWtHL57ns5d1cDyDmyZj19lTXIQicAdXeccvoweu70YvopcjObTpSphE8h9RSbNvZy9W2v5v2f+hE/ndQUdeOkul6H/OmNRxjrr/OQt4ojTLF9+VoC69fD/3JeYRfXTW8hHVZp0+MMxtrZ6DyCK2sU0hbKEESSE4prNhR8adrm2BzI9uKhG7l+8moucJNEwsfQz33fujMJTzkR5kiZRHkW0UCUIs0Xzm3xjBjWKAKIiQpt9gFWqKfgWJ5goIbvuUg1Rwfe7hFr8ckurmDGFTMiS4oKI7SznyVM0USZOGO00Eh9Nn8VIqOIS3Zsoetgw8AsxGx29bRSjLtnrJN0Y6hkFrl4JctWrCAej2NZFkIIbNvGMAwiLfn09i/whPUAAPEwxXUHfpvO4tLTygslfOXKFEMtJgiBqIYYAyXM4Ub0SlvK4feuWsqbLlp4ivtZ+RGVR0cpPz1INDZ/ktYoghv3w/Y6Xx+a5I6LrmSiqcFTs2TwKG/aUyMstJMpHGbFkW+TzM9vll9ffi3fXn4l543t4+27f0hrvYB7xeVk3/X75EOfHff8GCkNjmx/ijA4e9huPZUg7ZdZmMoTywk2R/2kLA+BxpS/nLr0lcR+FkbrQLSOFnGECMl3oku52XiMo24XH8+9hqBlKdfbFr/YNUyhFlLULmEj0T2j6lRdaGm4pmax1m+khagKzb2xgP1W9Jz4oNc1pzmWNnggK1BNToMEA1hYrtJWnKJjIqT1+C6SpSGc0qkHGGWY1Lv6iJLZE79FWlDDoqBcRlWaOiYFFaOsbWrPwjhZUchv7/0xLx94GFMrxmMZ/vzGG5m028D0kNYMyAAdJRBGCbSNkB5Gcj9CRGgRImQVU8E7f+xxxYEyR9rhi9cZ7F/QaHTKT3HexHmkwhRjYTMPRksIlIGUgj+4YTk3nNPF3+88yM89hTqJs0cozUX9HpfsqOLODdmMGiNevBN0Y94c7Cnz+OoZzuk5jw2tG1jdvJpreq/hi08OYnxtgEtsiSsFvtBsl3s4FBzhyvsfIF2aD3Eea2ujrVpFluc8bkLQ84mPs3NqlEfv/C8A2vqW8Jr3f5ADj/yCp390F9PDgwTpJnpLPpu2N7wy/3rVcrZcOIDQgj8qv5Hb/e0MfvkJonpDB5qbV/LZ5m7smTzf7ryNuuGyuDLA9ZP38rXu2ylZafr8MR74yG8MkTPKr8sQ+deP/Rkf3PA6fvBgmc76fPN/YD9Nf/4AXePHWddyLXubA/KywnDTz3k0U+CyvYp3pKr8fPdqtBb0zBS5+R8+zPDyFbzvk5/igu0PAbC3r8jjqxtgS1u8mXPkFbx/97yrsFI4wtbBL1FbKHBzCdo3FXFzDSt7tp7mq/tuZ/tkw7hYlD7K7Su+y7LcEYwZiE3CE9uWsLNpDb9Ql1CXMdAaV9WJ7Djv6Rum+PO7ALjn8pezY/X5oDVX7K5x+d5GHVoXphhfF+Opewc4rzZPYrPhmhw///GHqcZcZjO9HMhdyBHHRKUsXNfEyEDgKjzhosRzI9mEUo2T8guQZn+Wm6Z+we+OfJPucJRJ0Yxp+pRbIqpJyXTTCwdr5WsZZGTznaNL2Z5pLNREkOGNMzcRD1soF3tYF1k0iRo2Pkl5epidrzRVpdlfV0gB+VBzUqZ4FBGF2CToIXLFMr1+nGzrBbSZBgaaQvRjzkl9+qwGZBQI8ofjTGzPnPa3wDTZd/FFHF+6lEw2S61Wo6urC8dxOHjgAOVKg9uhZ3CQS7ZsJbIlhj+/wdU7V1Jf+xJqyuNg/jEqYf6MdbBjMVSkuODWV3P+ba9GziETtw5v5QOPfoDhcgPjdEHnBbz/ovfT6XZx6Ilxdtw3xPTQ2a8qdi60+fmGOGKiRnAgzzOBNBt6s/zxtcu5fHkrwWSVqc/vJsrPGwNihc9Iz2eoTD1J5psm7v7G3PFNi+9eeT1fvvW1VA0TCVwnXC74+RR60qNpdj+r+r+OU51BA0PJFr614jKGMzk2OgWaR3fMuX5OFyeRQNkutWQTo4k0e9oXsH/pulOM6nNmQm4YLXHNuEk28DHFOGnzyxhiCkNMYopG/waqHSU70FaCCdHKk4f7abarTHtxprwEpdDGljav7VuObZbwlr6dA0uaeW19Gj3lYe0vIOqN03IuZfNXL13FrRu7EULg+z579uxhy5YtTE1NMRkluT9YSpUGG/Jq32CtbzBqKBZHBk1Ro+8OmRE/i/tUXtgyBBrOXZ22CPuSWMWADVMhN5fgOgX7C49xqPgUwUnZXYXpIFvayKebwTi7p7OqLaZUglkVJ+2XueTodjYf3k28WuPhrnX828ZXUbJfXNi8FKDmhjalfEQQkKvncdLbyC95hJoTIbSgdeoCDk/dBFhkZJWNqVG2rNtMOXH695qLES9/vEzPdGMstI4Iq/cR+bsA8E0FG7t4xzv/iVyicaj0fZ+7t+/kg/0+f/i4xwWOgRSCvKhwv7WH6Tl+FdP3ufDRx+geOTVyUdg27X/5XuLnnY+zuBH1ePDRh/nBR/8RgL6Nm7nlj/8S07bZsfUhvnvPvQBsePIJqA3w128wUFKwZiDNeftzLA5myAz7uEGIWtAOQxNMZ5p495//Ax27DzE5liKSJhsLOziYWErVTLDEH+Xej7z9RfX/88lvDJHnkU9+7A/495Vv4mcPVFBoZuQULaqVp0U/BwfubCRSWnwBBacxGXdc0EX/xL+Trmi+vqWG16754fAqNILNocFlX/gyP/I0v7ftAF2jO6npf0dLzYXjfbzl+C30JucZ9bYGe1n300+iI59jzWn29rQiraXYyZeRWfQwifa9PFEcY693I3tmVhPMJRaTOmLFzHGSYYWn2ladMAQ04CxJ4x8usqq0n2unGjiJFTe/hse6zuOzJ+XpWD7sc8tjFdxA47uSHd0mB3scNFDImdgpizH/hZFcNT6ucQIfz35+b8jq6X46o0mGYu1squ7jj8f+gygWYAjFTM7C8RQTLQ6BLZ8L+9joCy+BEhHa8KnUMjw8fCGDfgsPN19Dl+Xy2odK2KFmT/sWHuv9EYFZRSqDi4/exsrxSzBPcomnJVySNImA2VDTZArcZ12gV4Xi7tQYezru5ZYWOC+5gOaRHahqgb39ryYjVjYUT+jR4fwDLdZT811kZxBLr4K2VWilEM2Lwc1CdRq9/na8g4eobNnC9Oe/QDR7aqTQsi0PM1KpcMcdd1CeOzXJKGJZ/0E2btt54jkRi9H1T/9I6rrrCIbLeAMFyo+MEM16jFYPs2v2YWb9OXZjIU7bmKVhsPKyK5m6IMtHdv8boQ5J2Sn+8bJ/5PKeecCo1pq/PTzKlw+OsWzE58LBkJbxswM2S4bm3lY46NURGizgr3M5rpidd2UbWYfcbYupPv5TZr/5Dfz+U9PI125L0vX772M6fQ1/cWiUxwsNQ6zVMnndcIXE/UehPoxZ2YHH1BkxPs+Im0qz5NwLqfYs4g63id1uhqng9Pl+UczlJbtKXD9Q51lpOZAZG1VotFnYmqz+CAnjfo6Uc3xncO0Zv2uKiNWZCS5tK1JTr2XWuA7HFzyZM/hFm0kkoKMjSe54lS+MzDAxl316TUeKv8xmWTTpkbq0GxUqvvH0AB8eKeEJyESCV1dssk6BBaZkfboTo+xzwFMcqjeS5RkCNiYM3mdW6aeRTFA/q4vO9NuZpNmQVELV8FqhiUc1lpcPkgvydNdHWHHeUexOybC3iH1jMaQySQdpYlHsjOUJpZB+SMFO4Ogqi/RR2sQUnrYZ0J38TG2mX3fzy4R9CbNArPtrGPGGxyyq9VCfup1Qd4It/3/svXWYXOX9v3+fcd2ddXfLbtyVBGIkEAiuxbWUQoEW2tIWqVFKBWmRQrHiHjTEjbjrbjbr7jM7PnPO+f0xm90sG4NPafh997mvKxfszPE55zyv560oMUYUqw5UlShnN1mudvK6Eih26Xoa6ClIng3Ige29VhB9UgrWiZO4aMFFyLKMXq/nlbffobW2BkmVmBQqZKiSDkCFppm1+gO9faaio6O5NDkZ50MPH/OYM559Buv06b2Ww9p9u3n/kQcJBwIkZOdyzt2/ZMmq1ezbtw+DwcB1113FVe+fS7MtzLBKGLcvPVJo8SiENVqevupe/GYrhhonmv1u9FIIjawS0BgoDNbz5V9v/sbX+XgIIXICnn76LpbGXcnj23zU64PstTcytyMLp+Lii+qnkY0WvLmReI1dabncc+G53LNoFh4pyC8+tHDuyBp2tsazoS0Ljapw1sjJFN3/az5q6eT+Fb9E8q8lscPIzbtOZ2rSQgC+Mndw17RMZI3E7//5Z2Z0NJP7+WcowJsP3EdLdTfGqCsAUMLNBLtfw621siZ2KuW2vAHnYFc9XK//ggMlJdy98HbqvtrA1uf/iiSprMo+ndDoGZw2LpV9rd1EVbhYGxugzWgjqTPMxevcxHgUfHqJt06zUZtwlABRVYWAglnrR6uTcUsnd/3T3V1oXe2kNlSTV13KAtNWptsO4orS0eHQ44zW0xmtP+6AcZju7jhczgRUJIKudIwdY3k1FE1sqJFf8wU+1c5T4fMJh2NJMuqxoyHBpfR7bXUbOliX8x5VsZHYmsKW8UytOZ9kcwydriAao4ISX80BlpNQEcDmDZBhHcKouFmYtf1nTCEJtsUGyQt9wlDfq+zzPU6cLhLX4JIbyTPdjVHbTZdnHK1La1HCEkooInoS772X2GuvQTqGlUhVVdqfeYbWx5/o9/nKGTNoTkpEqyik1dczbM8e7N19FonYa68l9tpr0Cf3dx2piopvbxuezc34D3bQ4C5ne8cyPOFIqzpJo8Fsj8Lr7EJFZVNxJ/tzIjO3dGsa/5jzT3Kj+zKVDnn93LSnin2eiFVtVmwUzwzNwq7T4mr3sfzl/dSXdaHRSihfK8zm0ig4zSpz9XoKj+imZjszC7lmJS1fq7CsS0lCuXoILTnbCSqRmBmLJY+U5AtosF/Enxevxl62i6S2BpJbB9bF0ckKpmAYuz+AqhrZb8/jw+zT8ZjshBNNyMlmlERTvziEmbF2fl+QTo7liEJpqkqw0knXp5WE6vtbgXTxZixnpLBz1ec07N5BnbdqwHEAJJmymJaUQ7rpeXSaiHtDVmPpCt2AT5nO1wfZACpvEeRVAr3N6s5V9Zwf1vO4GmCHISLi0sMazvMpBO2VBE2RaxSjWBkuZ5IvJ+OWJbZ5wzh7NF+qXiItVk9tIMRf8NGpqEz268g2GFg+3EKZTkYKKmg8YaQWH1JQ+RbDP8QEO5kb5yV10jQWHVxKoL2NcxvHoJd8mLvXYpJdhAxGPDYrXTEDgzL1hCiIM6BNHYpsdGCLS2JLbTdf1fo40OonVeqgQe3fKkBCYZhUSZvqIEHqokzJwBrw0W6KQh+7FmP8MiStH1XREWidS6jjtH7XPS+kYbZXT1RPEcBOtQOz8z1QI8/DIVsurfo4DtgKSTX6sUhBzIRwaPxESz5Q9ZwVLiBHiVhX92hr2agrY86ZcxkzZgwmkwk1GKT5z4/R+eqrvfvVxsVhGjECz4oVfeefkUHMZZfhuPACtA5HPzFiiE+iPS4NNBrmnTeP31b8lpruGqI8Kn9/TqbNGkVZSmykRlHPe0ajRPpCbZw0l9Wjpkfe6yo4VlbgD/W5b4uDNXz+1x9+i1/82AghcgKefeaH7LBcx/37AuzWdfBUiZandkejV2FJwys02iGYkMaWzCJyJk/hyeIs7vzsVpa3ruOiNTKpcdO4yvoJn1VlU+mJxRoKc8Ujj7O3sY6bq34CwHnrs7ja9iPMOhsai0rnGz/ksatu5vPJM3B0u3hzZB6jsiJpZKqigCTx+q9foKst8vIPeZb0mgOrzRm062PRhDUospnxTQeYGthD0qxuPks9g69Sz6a0Q0ZVVWrSB4qWr2Pzylz8VcT8GNbA6nEeNuodhGPNkSmU8cQFBDSKwoiD+zln01L0JdCUHE+m7iCjdFvp9Jmp3J5MZ33kN0sc1Ub8sE4M1oGzT41fh2IKY96swbhfQl8rIfklNF4bfizU5eSzP38MkmpCo+gwIBEdVPCEjl+VFyLxLrLOj6wJsDd1HVuSV6KiEqOPwWowU+eJDGK6sMQPvuwLlJS0YeYX7CRbyWeFYzYB+XTGd/QXEH4Nvf7j0LA4si8rQNJoI40Cga733qfp4YdRA30WKfPIkSTcczfWCROOeryqqrJr0YcoL/wLU1mkr07AYGDLuLFM/Wp973LauDiizz2XuJtvQneUl/nXCdZ149nUhHNHA1VtOzno2oor1B65RjqJsukGNpgilUVHlEcxtjqJhJQMxi+8kMJJU6nwh5i2sa+41M+yk7k7O+moKYeKotJc4cTrCmK06tj2/F4KUbFpI8sGVZWPpCD/IUg7KmP9Gu5d9QhRvkhWTuJP7yH2uuuQtFrC4W5K9z7J3tWf4W6WCHl1eBot/WraAHTZHXhySyhwWwi3JKEnioKaj0lq3oS2pw1BRXQK/xxxAXtjsyNNzUxapo9I4oHpBeTEWdEeJzhSCcq4V9fh2dyE3GMN6Qw081XLR7jD/a1YWklBViNxPBMT/Aw752l2+RWU3XVkKovIUl5H29Px1S8PxxW+kqB2OJIkoYb6XGwdKDyh+mkOqowLaNlkktnbI0JKgloe1phJ1Em0al2UGhspU+p719VIEuN1RRS6ktiq6GjtjuzPZNUz9aJ8YofH8pPtFWzt8uC0aiOxPYrK9L0+xh3wsdkQZosxTNisITgjBU27H02LHyXWiLbajaYryJG16zSqinKC4FJLyI+3J8W6wFXLXyz/xGSFOhKoIpsa6fjNTXU6HXl5eWgkCRmJ2j2rMeJji1zAXfr3GKs5SLdk4jfy9bzPdMKZVv751h/JaGjgk8JhLJ3aQGdCTyC4LxN/wwWY/Cks8OpID0eszh4pjN+/Aat3U+9+P0xeQK35xI1XU5FoQCVGozAk1UJRRhIlqdFkxFpIaKggeNPV30rYJd1/P97cLN7+x2OoskzYYmPUddfyTMczlDsPoVFU7n1XYcyhyA8S0Oh4p+B0VI3K5aXLeW3e+by04CKsOi0eWaHQYqTMGyCzvYz2rUbkHov7sEA1n/zttm9xhMdGCJET8M7zd+DUlTDvwFCqfAe5fnYOj1daGN4Q5IBzE2UOL2UxVj4aOYUvpo2iyGrinbJ3eHj9w5RUqyzcN5yGIRncqn2HN0rzcIVMJPldvDNXT4WthTO7pjC/YhxF5iHIBhnfpw+gelpwxcZyw08fpi0mjlSjnlUThmDX9Q36cjjMpo8PsXVxPX6DzLqMz9GGSkmMu5TdpmSCsSHiNQ14Wh3UJaTgtpygSZGsgF/GEvKTaWlF05pAp9lMa1Rknxesd1PUEEIFlo40s7HQNMBSMaL7AB6thXlta7mwZQk6OYhplQdPpRkkFe8dPrqKBvqGVRXqv0qibU/f7CVrlootNYsEZzd53a3omw8hh1ScvkR2SZcTMqbjd6q4fDpC+pNrwOQ0g16WsARVVK1E4aRkxs3ORK+28ckHr1HaGkRFRUFhfeJ6mq3N/daXZLhsTTJGb2QmnGx2cWX2zgH7cenjeSbtJUoaNYxy9g0Y9SaJvw4zYyiMIcmg5+e5KcQb+q6Hb/ceWv70J7xbtvR+pk9PJ+ayS3FcdjnannLyLpeLt954jfrGyPFlV1YybtNm6tPTyKyt613XdsbppPzpT+i+xfOgqirBahediw5RXraJ5d5PWDaqgY6ewnzn+SaSviuMu70vc8dQUMJfZl/B4VCqQouJVROKTlj3QAnKtL+yj0B5V2TfWolGWWWnM8hqQ5hNxjCBHm1nVySm+XWUBCQmnm0m4DmEq7UFd0c7dfv3HHMfKaNT2Dz+aj6SrHglTSR+RGsiZ2krCS0h9EE3jo61ZNWsJMobmd02xqfxp+EXUxqd3rudSbmxXDslh7klSWhOYKlr3lrG+pdfpaJ5Byp9r069xkRIiViLDFoN85L3UBDVTkjSsttWyE0lD1FvSiIh2M7L3Z8yev9/kOQekTpkAeqMXxLW5oCi0l7TTWVVN9uW19KsVVhsDtKsi8xkh0g6bjwjhwvOyEVj0KHKKmigu7ubd999l5qavuDdjOR0rrr+GhpKnWz4sIL2HquOKdfOkyVamqx94jqlPcz5GyIpqgBKtB79qBjWB30sC/qQY42osX3WojSlhjylkntry4g6eD67VC0bwp3s8VXRYYjBo7Xg15i+UYbcMEsLo+RadFLkGA4HUQeDx3b/WfARQxdt5mi2xAyl22ShIiENtymSeRTf1cGf//Z7MlsaWDpa4uVZOkL6iC9qVP0sxtfNR6vq6JZ2o+9YBT3FIdOmzaUubyQvOMM4JQsadwhHSxdJ7k5aVWtv8P43oaCzluE5CegSE8l+/WmyXU0keTvwLriAottuxNbeTNs//oln7dp+61VlZ7G1pBBTQxVeY5B1o9toiAlg9as89KpMZhu9/rWgRsuNs39Ouzma89x7ef2ieQMPpKfx5XUtT/DG9kjD1XH+ct79+53f+JyOhxAiJ+CFF3/HKGpJKv0B1e79/Gy8nauldBbsA0VVuHOKhfVRem7LSOQ3+ZECVtWuahZ8sAB9WOXZ5y0snjmHmZk+sive5o2qkTTGBlg8qRmLrOPl3JewfREpArS58zOGrPqwd9+dw0dy652/oiUU5qKkGB7IS2Gzy8vGLg87u720BMNU+L5ZI66YrjbiPW0MNbaQmFdISzjACnccTun4g7mkqMzf6mVsRWR/3qhukjM/JCdcSY6vjphwFwbCtMQb6IjR4wvrML5oQl+vQdWodF0l45t4RCZAWE/AnYg+lILqH0qouZjOSh/tvmZARZIsGEzZxGnrccrJBFT70Q/s66gK9u5aovw1tEQ76IixoxjcKJoQNlcB+rANVaty3vj1pMc2RyoS7n4HlDBdGLkiJZta09FL8xdV25i4LxZNj5N82um55IyYSGJWIex8EzY/37tsQ+BiQsrVaCUJvwSmI56cz1J0vJJjoNKuZVqMnSkOG3dm99UxCdbW0vLXv9K9dBmE+iryKldfzcHiIezY2V/85NQeYsK6LRyN6IULSfz5fSdlDTkaiqLw0YZ3eKTsMbySH2NAw+S9sWQ3WYlJTiMxNw8J2Ld+LW+eewP1KRHrU7RGYv2kYmKNxw4eVlUV5+eVuFf3zdCN+Q5iLyvCuXYVdb99lBZDFm6Nyj+GnU1QacKk+HuKhFVjVo7+O1kCIRwBH7Eju9Cc4UWjj1z8bn0+ey1X8qRzeJ+rRVXJawxx4Xo3xjAY/Z0Ma3iH6Jq+a9ww61yeyDidnV19929qtImrJmdz5aRMokx97kpVVWk+dJCP//4nXK19QjbRkkWsPpkq9x78sgcJiRLHFIYWnkFH1GpSW54lIdQn6vZmn0XUuX8lIzYFOqth+W8j9+nh3yVlLLuzn2PtBxExUaeVedcWJCSBWa8lyqyj2RV5VqfkxfH784eTE9/ffdjS0sIHH3xAY2PEDaTRaDAYDFxw/oVs36vQtKwenRzJdlo31MyM+TnMSYpmi9NLebefdWvrOH2Pl6ie6GxvkhHL2emcX5LEzE2ldH2tjH9CfQ2aPTqux8hC9OiQaPPVs6FtCZ5wMyFJFxElWCl1FNJlj6WG42egWSUvUVIIh+QnWedl5mlT8Idktu89QLJFwuBrx999nIZ9QFCrI6DV0a6x0uS0MGfHWuZUbaYyPYvn5xupiou0LrD7EhixfxQFTX29hqJnXMiF11xJjNVAm6ubX1S38nGb6/DNAO4wN+7ycEO3hFuC1XKYpzR+fEdqWFUl2dtBWNLSZnEc91gBNKpCvsPI+CEpxD7/BKnOJjLcLWhMGr6cF6lD4vVWsqRoO2Gdii4MD74WpqhFIX54mO4aFX97RCg2W+O4fta9KBotI+ZmsUnqs0QnG/QkGnXsandz2sbP2eyNZEzO8e7kX0/88oTH+U0QQuQEvPjEvYy0uUksu5wKz36ey2oi2RjLRWVm0q2F7HRoeHi6gxUTi7FoI7MGVVWZ9c4sWn2tPPCaTDB+FGWFhVyGhZrGt/hbnpa6JB+ntar8oupnSLZcyl3b2N66mDl7qpC1Wkozc2n62X00pGbwUkPENK6FkyrUJCkeohQdI6udJOQsx9AeRtpmZe2ICdSknFzPgmhPmNxQORnBBs5qW82C1tXUGROod57GHuf5hFUzJnMThaMfx2xrxOnQoyoSIU88clMcxo+SkENW/GYHyqgOWkMTMRhcKJ4E/O6EiHnhOE3BTkRcmpXs4fEosopW7ibbsBGH2oDr48/o2OxGCfU96csnX4JqnIKEHkUK0RW7k0R9JeewlFRaKNXr+VusgwqDnkZd36zMpGq5LnQGS7oPUh5bDRJYfVqm7UzAHjMW1RAxH48bN46EhATCHTVY/Q34NwVIUyYhSRIuuZsc0320Wk5D47y83zn8vsTIBxkGJFVGRcOiMQV0hWXi9DpG282oXh+d775NzVevsSh12oBrkEMNEys2o246wo11041kTJpE7Q19Ue2SxULB8mVoHY5vdI2bPE3csuQWKpyRQnijHSO5vfR8Kvavpd7b11cmK38kG0+bw6tGB4agn6vf/Scxrg6sMbHMuPI6ik87Y8C2Q61euj4sJ3DI2ftZ/A3DMObYaXvmWeqeeZq6WDshrZbGuGj82oHWh6Ckx6uPx6bNwYSBjMZtpLW1EOWpxzJ+PAfuf4B/dDVS4n2D01iJqafJ4S5G8CI30yKl9G7r3Jgoztrto/6rZlAhtquUYZ1L0FXvB0AbE4N3wYV8njOZ18u66fZHrrlZr2V2cSJXjoqne+0iyrdswOvs6t1ulDGOIfZJuEOd7HNG0uSNBgujomeSbRt6xNmoHIpZwQzfX/s+Mtjh4hchZSTYEqFpD+qnP2P57rEc8M/sXaxGJ/O+LUgIyI6z8OoNE0mMMvLcqgqeWlFOIKxg1Gm4a04hN07LQaft7zqsqKjg3Xffxev1ogI7MvLZmDuMGLfMgq1espsiYtho0THj8iIKxkdE88YuN4+XNWLY2MbwMj+mUMTu01asJWfCYlb7DFjw8o50Rb/9jTWaUPZ18JMamRKPD+/qR2hVOqmKj6Yp2o50hIDJdAT4Z8wVVJJImklLgz8UqakiheC41YVVFJueEm0VLcMz8Uo27H4vejlMirMdbXeQdHcbUcrAYmbasBmzKw9zMGKhrXBsYk3uu/iMEWGXV2fD33QuFeYigprIgD4m00Fegg2tTcfLIQ+qTY8GuONAgB/URK5fp91Ayc/Gssfl46mdtahI+Fat41dv/6V33x6dkdvOuIcWa//YlpMlS9NBkq6Fg5mvEtbLmAIaztyQzLSAnxKdHc/GcnpjXnqC0dfPuowHCk4jNDwGNBLXpsbxYH4qBknDFf/ZwoZ9Lf32ca5nM088+eC3Or5jIYTICXjljz9ieKJEwsFLKfPtZ5n0FQann4QAzMn6IWZVg3RRPmnjUvqtd9/q+/is8jMuWqOwcH8sH806A4NkYJTOyL2ZryApcPeOM5ltXghqgFtz29hSOOSEx+PQaZnksBKl05JhMqCokOtROfhiGcaQiqzz8dLYfyBZCjCb51FnOnFNC70a5jfVn1JdejqJThmtCqdH/YNi61I8Fi1Oq572KAO1wbEEww58rlScFTNQFT2gABokTajn72+HTgfR0WESU7TINbVUtPvxy260qhOrdQqTk98nVldDXLIJbc3KY27HpZo5Pf9fTDy4lwuXfY4/agLVWfMBMIbbIXYDdZaIdUWDgiGhmU/Nu+jS9gUYJluS+d203zE2bjT/+cVPaK+roSbRy5qRbT2mWih0FlLkLMLwtWqjI8KZTAhHKtbu19axR7uZHE0NE9lBAu1Ua8/B6Lmpd/lym4Z/5oVIcm3CFA4Q43ET9B7blJtBPWPYQ75ahXNHCt2lEauAIkk0/ug2Zt9+OwC+HTuouqy/8Im54nKSfvWrYwbBHsn6hvXcsfwO/HLkRf3DkT/k5hE3o5W0BA52Uff+Fmqq97KzcwVKT+Gl1tgkkoZPJKp0M11NfbUkrDGxnHnrneSMGoviD+PZ0ozziyoIRywMkkmLf3qIA889QWdXOx1WMyHdQJGqN1vojorhoDWBBiWJCjWDsEaPVoXCkJYxAR2psgbGRfNGgZFypU+gxajtzOELzuUDpB43Scg2jS/01/NmVyQ12q7V8GhiEsYVzVTubANVIbN7O7lVn6HpiGQSaaKjsV1yKW9mTOGdcjdNrr6BLN1Xx4TOLaQFIuc+Jm42CcZMtnUsodUfSblPLSrBffktlIa1dO9q5af7/BxR4wqjZgcOw3Po6V8gLDjtN1TarmD7khra6z29n7da9/GmIR2/qmdGYQJPXD6aaHPfc1jT7uWXH+xmbXnE2jI0NYoHzx3K+Oz+A104HGbx7r38srqN5uhIqmmOq50H81LJ9sSw9u2D+D2RAXXEzHQmLcxD3xMfpqoqX1S2s+WDQ6S0lJI25WkM9hYUVcMmaT6jh/2K6/cODBSeumMzD7zyPHpfxIJgGn8LVSklyK7H2dnZJzxbDfFscozFpYuizRg/YDuqVkKDik6R0anygDokh5ETTagxQaQWHdpOP8akTyk2lPJwixuvZGUrw3B5h2J3FfQVa1SqkV2f4TV0s35YB7VJkefNpIkiU76JrQcSjrovTbSBn1psnNsYuQf3R+s546fj0em1BGtq6HztNZyffIrc3t67TtBk5pxfP0nQYUHT6EVX54Wwgsb9DbITNV4sGS/1ZgB5q24mtsuOWfYxrL2cS/euI6zRMf7396P4/DT+8pfIej03/OIPVKekY2sP8PFpxdz6ylaq2/t3pzYpQcYZ6yjsrOY3Tz128sd0EgghcgLe+82t5GYaSSi/iP3+A+xqjNTd6LbYYdId3FgZxpBpJ+GWkUhHzNreLXuXh9Y/RHGdhodeDVI1ZAQbRxWzPXs7FVIFuR1x/KP5twA8UaDjldyBg49ZI5FtNqKXJPyKQpk3wNgoCx+PKUBzhN+9yhfgsS8PskwToNN2fCvDvO1rOHfxYuJcnRhiZeInd9PmH8m2tr4ZdGbyF7ikBCRbJ97WAoKu1EgXzpMtP364tXAPklEiQQZrlAuTqZko6ojzrsOha8Atx5Ggr8Kk6e63CU+4kP9U5uMOd5NgTCcxajpjox4lwVB51F36TPH8KPsOPkuKVKLVKCozd3qYXBbx4ya2bKHw4DuYo020zp3NylCI0BG1DMpiy5g5fSYLChaQbE0mHAzy4Z9/S/Wu7ZHtabVc8IdH+HvlcyytWQqAHTtjGsYQH4gnOSmZ7LoohsmRYLUd2iq26A4dNZtQo0pMkgsoCfcFtj2db+DNdIW5ezeRdAxTco6+nYtZir/MT/MmY28eZZcjmu2XXsp1t96K2dx3H4UaG2n75z9xfvgRao+Lx5CVhW3WLOKuuxZdwsCXaKe/k+sXX095VzkAOo2O+yfez0WFF/VbTlVVymq7uGrVci767BW0St9omu4owpaRwIHd/f3XU0+7jPS6vsDhbrrY372BmvZ9yOrAppC2mDiS8wuxx8VTOHkaqYVD0Gi0LG5z8tLbH3LpK6/x7MiF7I/J7l0nOSwx06cnTdZyKFnHumFmEhOtTEuP4e7sZPzeUurqXqGh4W0Ol3UtN53Nk/I1tIUjz85VqXHc0G3gq7fK8HWH0Mghcj1byG5cidIYicHRWK1E/eynPF7aypKuKNqPGCDTlRDnqiYm+ivZ2bGUUDiAVq9n2mVXUzZyCneXH1HwS1XZnpGFvSOAb287gbLIb6+TqrFpP8Km+5KGYDGfdf6in3vSaNXRXFDFv6oiomGGZifPFm7BNPuXkD5uwG/17tY6fvvJPlw9lpwLx6Tz2/OGYjHoqPcHeby6mfeaO/H0NHUb0VjF5LIdSEB8fDwL5i3k0NpuDmxo6vltjEy5MJ/8O3IY3QAAZrFJREFUsYmR4FlVpb7hDQ6U/haJIHLQTMOGm+hoG86GIjPri0xclhbHl7UdNBtU7njrJc5f9WXknrNHseT8O7jIk0G0HLmnP9e2UC7VEle+Aq3ad2+tTZ7HNnsuSoKJcH4UqqX/OymnpZ7CfYcoC8XTptgIcfT3oaTrIMnsZ0Kgg0RNN/Gym6TuXBr8PWnVaoiQfwOyf0vvfRKKjqM0H7Yn7ETu6XQ+KVyE13gjqzxm9OEQUS1OtAEzj6sWciQtMvCb4SYWp+qx7O3gbLeTH77+EFKwv0s9+cEHcVxyMbs8fp6qbuEn2Ulscnp4u7GD7Z1uNJ1BNM0+VIsOc52LcI9XUofMxcad1CoOAlo3NamL8BrdqLIZb80NKP50jomq8pfdr1BSsZutRcP4xTU/RbOp7aiBsiOdu5hEM4EkB3T4efCJR4693W+BECIn4L3f3E5ehp74QxdwQN7HzpqPAVg3YQ6vXX0T7Y9vg7CKNspA4p1j0Fojs5HazhrOWnQ2GlXi78+EiHXr+Nel57Mq4wOQ4MmKX5AfyKA71MGz8pe8d9bVhPRGSsp2ERv0sXbYRLZNKibVHDH9NQVCTN24H4+s8NNEHU1aO7VuN+u7gwSPcuuY/W7i/NsYtr+VpNoGxmoOcUH8Tjw+B7sPTCPg0tGaMIr2uOHf6HqYDW3EmsoJZtei0QborDidoLPnZldCDNv3bxLadvOPi37AezPn86s9fs5pCGOUakgy3IkknXxr8Ep3Ch/VFSKrCnqNkclJV5I9qZ2ElE7wdkDhXKjbwgG3n9Mt5/auZwooXLbGTUZ75KU7dl4mReFdtDzxd5SWVgAOJUu8siCHEvf43vXsdjuXX345Vp2GZf9+hsrtkbiLkukzGTX3bFIKIjVellYv5dHNj9LoaUSv0XNt8bXM/Wo8tobI/jbpDrFLV9W7XZ1ORzg8cFYzPVRModzXGG9Vgo5fjjQR625jdM1B8rrqOENZjxczXxSew8OX3Izv3Xdp/f3ve4VFdWYmu0YMZ94Xi4mbP5+k++5FFz9w1tj13ns0/f4PqN7ILEcTHU3OO29jyOzLAGr2NHP/2vvZ2BTphLsgdwG/mfwbzLqBIrkpEGLOllJag2EMQT+/DHShXfQWru7I9ZXQMCxpOmFTiP3V6xgeM50Sx+Te9fd0rmV/13oUeoINwzLmYIj4oEz6tdejWswMmTqDqPj+YmlT6SHq//Uvlhkjg/LysZPpUqzoypxoXH33Vm5Iw0KPAV3PszF0ehqnXVKAtqciqMdziIaGt6itewlVlfFj4jnd/WyUI6n4WSYDTxZkEFXuZv0Hh/A6g0hKmKHmgyR99Qpqd2QW7zbqqUpwoORfwAp7Nks0Oqzhbqa3ryXHVw1AQnYemT+4iXu6JeoD/e//RwvTuTot8nupIZnO98vxbo+YwrtllVXdIeQjnu806yEm/GAKT1XKvL4pYmW5NnYv93seQS/Jkbozl/4Hck4b8Ju1uQP85csy3tpcg6JCnNXANecU8YLHRXNPTaDJDitPFWcRq8qsWLGCTZsiWSEmk4mrrrqKYLuRtW+X4WqLWILiM2xMvyKFFtfDtLUvByA2djp67mTx+x5MLT0xZQaJoA5m+v5Dyt6V+FoiVovPJ8/g8cuuI2AwYg+pXF8R4MqqEBogKMGiFB9VFR+T0dg3AdlXMJKa1Bx2F/cXXIfRyjLX7fgYTTfsCKfRRDwt8rFjlTJCGi71GHp7JilyO8Hut0GNjPYT5s8jadIsStesY29NNS69zOaEzTRZIqJML+tJ8iRw5QqZYeWtmHQ2QEIz4gfsVgN8mi9zwcrF5NUPLIP/3hlXo0yZztiRuUwriO9nzTqMKyyzxenh1YZ2WoIh9nb78AfCzNi9mQVbV3OoqJAD0QfYG7sXgMRwmPjas9jun0awxzqkUftXhD1MVMDN08v/QpM1lsfGXEajrf/zlqmp59xDi5C1OuSYXIIJUaidAR56/I8DtvV/QQiRE/DJm4+T7qolvmIhDcbtrGxcTU1UBlUXXMcnU0bg2dZM59s9wUtaifhrhqJPs9Hx5gHu8T/MdtsB4sOzaIo/H5+0CXvnKySH0nmxPBLs81nd83SH2tGpMrIaaaR2bfYW4syRh8CZNolFjolsTpjC+2oiYTS9kcxHUqzuYbJ/E42V8yg4ZCHaq+BQPqfZ04Y92kqGQ0enLoWOlvEcD43ei0bnxyCHSNBVoiVMrn4LDm0DUYY6qgo0NKT0DUxDd+vp3HMOm/wjcVsjg2pNrJt3TkvHa4rc+Nm+eu6peokibyUlMfHoRl0OMVkQV0Bo/xc0rnyeTP8+AHxDLsS88C9gjgRXdjU38cFDD9DRHgloHBs3j6Hnnk383GzCwF8qG/l7TZ8PM701xBWruzGGAa3C7KuHYitReHLHk6zY9wk3fKlw2t7IbSzrtTiuuZrKCZPYuGkTbrcbrceFrbESpWegn3PT7YyYPTCavMPfwX2r72ND4wYAcvxp3Nh8AekJExl1y3ACgQCBQACbLRIE7HK5KC8vp6urC6/XiyM6GiWkENuhJU1KILA9Ur7frYO3Mw08l2cg02oiIMu4OzuI6nZz40dvMn3H5t5j2DV8OAeKhzB1337S9vRljCTceQdxt946IFtFdrlofvRRnO++1/uZbeZMEn5yJ5+wi0c2PUKgJzvjyuIr+fmEnx/1HqnyBZi0YX/v37emOLg3LZbWykNs/ug9qvfs6P1OJ+mZnLiQVEskVbzNX8+W1s/RepqJ74jEhyR0e0nMziPtsT9jzBuYUu6TFZxhmT+s2czb2mP0VlFVdG0B7Puc+Hpm/ToVxgd0TPTr0CORnBvFBT8b2++6eL2VVFc/R0Pj2wBsZgL/lm7HRSSw85wEB7/PSGbPokr2rdlH2L8L1beNosZW0jtc6HvKdUpGO5Zp89mV56B047Le7e+zFbE59QxcWdEEUsyoFh1nxUdzc0YCRo2G0VH9z0eWFdrr3JSuaWDv+kbknjorCbp2FsTcg0nj4t7wzbwrRyx/Pzw9j/vmDYGOCnjramiOpPFTdBYs+DvYk/g66w+1c8d7O2lIMiCnW0EjkWnUc39+KgsSHP3Sk2tra/nggw/o6Ojo/ez6a2+gaU+YrZ9VofScf/zQRcSXLCa/4G4yM27stZJs29TIqrcPYvTImL3NjNn3JEZ3J4ok8dqoebw6+iymRJswTU5lcXtE3A3tknloj59sT0Sk7onW8O+kLiYufrrfedSk5rB2/GzaYhN5cvQQRjcGiFn1BOHul3GE3axSFrJCEylx4FN1bA/mcY+ajFsLpaEuXkDLhKCRyX4d2h4RstQcZLtBxqT4kIBojYfL9Ss457wrsBVOJ8FuZP3qr2j68yNsGWplVV41LmOfW3dox1DGVdrIq24jtaGhX5n2w3SZbPxs6m3U2ftXatZqJDJizBSnRJHmMHP2iBRGZw4MMq/2BfhDRSOVOzYz5eAe9jr2cSAmkjKfGwhRVDuXbGM6SkoOGcOGMHd0MWXNbj5+5306dnxFQGNkceIcwprju9KT/E1c0vhB5J4ZPYOxtY0EEqJQOsM8/PjvjrvuN0UIkRPwyVuPk9FVT1zlOTRat/HWhC7+Y1jINalx/KkoA1VV6XizFN/OyEwQjcROh4Zao8SrSatwBV4jaCyiO+6HxDX+ClQ3tzVdyjmdM9BOjieQ4eaTRx4icMSYkTlExhav4Yv4abyVPP+YxzZH/ZwZ6jIKWloYU1OH3mOm2j+Wpa6fnPjEJAW9vxurtxmbp44oVxXWlG6GDVmNWeorUCSjIWyA+jgLjWlG/JbIN1GaFIYFJtK9QU/7Gx8R1hopy7+AppRIUGVAUlk73MKWfFO/5lLFVhN/KkxnXLQVTd1meO9G6IrMHFcxkc22uVxxxRWkpvZZChrK9vPGr3/W+/fwmOmY86dz1xADdYfTChWV7F1tXH5QRqcYUKQQoy5P4N66H+EO9S8wdX14IvNfKUNt7vnNJImOO29jw4ov+i037pwLmPGD6495CUNOP/949TFes36Iv6cqbU5UDk/OepKsqBPXLjkSz9ZmOt8t620C12yUOG+6FVlVePWvD5JaUd67bGVqOpunTUbVaAiMGMev5s/GtXoNzvvuRfVHZqqmkhJS//QIxoKCgcfd0EDFeeejuFzUJMDrMzRsK4hcx3xHPr+c+EvGJ/cXrL5uF3qTme6Odh5Yu4nKmmoS2xoZE/biryofsA+AEscUCqLGYOop9tbqraZ+13NkN7ehPeJVYj/7LNIeeQRJ3/diVFSVUo+fe0vr2OzyDNg2RGbvxVYz16bF86fKRj5tdYKiYq71oB7oC4KN1mgo8WqY6teRXhjDyFkZJGRGYYvpSzH1+xuprnmWhoZ36VY0vMCtbGISqqQhTq/lnjYf3W89QljpSw/VygpjQyNIqF+J6o7sL6jVUJ4Ugzx5IqvzZ/NxhYoU6jvXgoJY3rp8LLGW/jP0cFBm6Yv7OLS9td/nZpueokQzmc5uNLzN42oKbytj0SLzJ/1zLMxNRXfpI0iWWPB1wbKHYNsroIRBZ4Zzn4QRF/fb5naXl6t3VdDaUylW0+gls87Ps5ePYWSGY8B1DgQCvPjiizQ1NfV+duutN1Nx4FH2fDKRkDsidhxJOubeMJqEzD4X0t6VdWx6ewPFHe9h37kbjSrj1pu5f8pNlMVkQlE0/mwbX4wtZKTdzDO1rTx0qAET8FSHnhFbOzjcdudAip6dyfXw/otHvR+Gj8hmVvA/aCUVV8HNrOEcnjjQwDCpEnvP81kcTCHPY2VV03tooi7BoI0ce7lOZrEliPcE4VMau55gghHFrgdJ4gpPBY6a1SxO3EmXre8+jfPHMbFlIvn1TpL8fkyNjezOK6bZYmfluCksyBuCt6Ybi0FHuyfA3gYX5S1Hb4dw1vBkTDotE3NjmZwbj14nIVWs5R+LVrE9bgfV9sj7c0wAmhJ/wU5jEZquYKTVlKKicYWYlx3HhvX1uP1hYoMddBgGBsMWdVRT2FXLx7mRd/jYzq1M6dpEmTWfj8+8lDtWv4M/IQq6FB78+7Grvn4bhBA5ASs/+TcxdWXEVZ1NrW0H7xS383rsefy1KIMrUuN6l/OVdtD6xgE0/j5/5rupTl6Ivh/oS/vL82fw16qfUhYqp8Zcy+zqGtxbtrBkeKRvQJfdwaezLqEhuc9kDpAfrCRJX0MmVXwePpefVL/GpXUrcQYzcMsJVKijqPeOQpGP3sDMFFuBYuhGp+rwNvdF60c5Kxiz90k0Pfn3Gr1C2pROtqcMY71hFPHJVWRm7UY6nK8flig+4MQYupD6f63q3U5tYjIvXnMLPxw5nUMfVuHtMd0GdFCba+HTIj0uS5+/1qKRyHeW8ty+B8jyNyAXnMVzXdNoaW3FaDRyyy23UKUzMsRqxqLVsKW0jC8efQhzzws/0ZTJiORzuH98AlvidIzd2Mj8Wh2SrMWvd9GyYCMr2pbh63GmFsYUMjV1KtcNu44YU0ykOumbb3LgsUdpibJSmejoPbawLRpfag7pWdksXLiQhKPEUsiuAA1PbEdyh2jUdvC3gnfYLUVSPrWSluuHXc+Nw2/Eoj/57qiBKietz/SVY18Xr8W94xWmbOm7zv+55maM3g4UrZaQRsu/py1APWIGm9PcwP3/erzXDBx/x4+JufzyAem73m3b+eDXV/L3hRr8xsj68/ebuCk0Gff06TTWVBEKBNBoNDSUl/arF3IsTFYbKflDGGKeQFRz/3TrXR2rONC1noKmDvJaugA4kBJHZUI0MWkZXPn7v2C0WGkMBDnkDfDrg/Xs9wzMaJh76AB3XXgWo2P6P+OyqnLDnkq+OJw6GVK4QTHxxeZ62j2Re3t0QMt0nx5Dj8yeckE+OaPicST2/UZ+fyNV1U9TX/8aZRTxBPfQKUWe87E71zFj42LiDRlIttF4wplIkg691EZi+dPk1Tej67EQyCYTS0ZN4NUzz6NJjsKw3wk91o0Yi57bZxZw7ZRsXC0RV9nrD27sdz4pedEMnZ5G4YRIMTinN8jFT6yjrCuy/GO6Z7hItxoARTXinfEltpmjIivXb4XPfhb5L0DODLjo34TMcfyrrpU/VzbiU1Ti9DruiIvhzU8PUtnmQauRuO30PH48swCDrv+ILMsyW7Zs4fPPP8dub2VI8VeYTC7koBl//Q9o2DEROaRitOgYeloqo2Znsu6VvURXPEXWocW0H4jcD+1Ryfxi/FXU2pNIljWYhsVyILOnq63JwI+zkpgXH91bXyfU5qN7eQ3eHS2ggMaiwzYrndrwQXYu/YzGsgN8HZ1WItxzrSvNWcSr3dhDLpB73KOSGYNtIRpdZLIT9m/BIu8nzzaSKEsO6/U2NhGmHJlGTnLI03qIj1oCjnICPdVrNaqGGH8sQ7tKSPBH3iHBlHRWO5LpTsvioYJ0FiY6ei10TU4/68rbeHzZQWo6vMfclZ4w51hXsyZ1NX5d5BmxqdFkBv+EPSOaJWtrkORvNlTbEmVee+GXGGSZBydex8aUyBiR6G/Gq7XgTEvgR4c+wZ8QjeSEB/724Dfa/okQQuQELFv0LxLqq4itnkdF1C4WZzbxQtqFbJxUTNYR8Rs/3HqI2g4vb37l6a2iCfCPpDf5JDbywogLRfNo9d3EbvqCUPUadhQUs7OgmFVjJhI2Gjhv0fOYgpEbqyExnUXzLife3Mrt/n9QGDyEbX8mLW0TqPGPwyUfJxtGCmNJ3I+3+fjxHzGFS0gY/j4aKYxpvY6ojzTojhDloRQF9ywF/xgFi5xOtGUM0Us7Ca9fhaepT/C8cM7FNF95FX8uzibZqCcckln2SQXbl9Zg7wk+M0TpMYyK5TGLj9bo/gFmuUYdL4/Mp9bt4aHNu0mrKUdKTGZZXCT2JE6voz0UBlVh6pblTNm6EgCT1sbkhIXs0sTh9kW6iXaZWvh8yHORRnOAXW/nrnF3cVHBRf1M8qqq8vHf/sjBjV/1OxatojJqxERWyn0/4vjx4znrrLN61/eXd9H26j4IyHhklaaCGE67YShvH3ybt0rf6g30BLhzzJ1cO/RadCdZrEl2Beh4t5RAWURwyd2N+Nb9je0ZKbxy1vmMaa9BH464jXzzz+dl79EfyShnF4V1VUzdsYnTt65Hf9F5qMOGEgoG6Qx28W7jx2yPb0CWFJLbdczYacHsP7laIyGtDl1yGmlWC0l5+VgdsRRNPg2LKYr2Z7Yg92Q8qIpM6NBSDrasZE+qo3f9dByMjjqdreZOGpr7RNZnp1/AgfzhyLqjm4yf2ruRC394I5L26AGIiqryfF0rvyk/IkMjrDC3Lszq0sj9oAUKg1rmevsEyelXFpE3OhFNlx9/WSeejU34A3U0DnmJxvg63tRcxRopkoKcrAnzXGEu45NjOLStni+ffQqfM+IW02ttnFEwAu/GtURVRWIaFEmiae58Mm+8iSf3+Fi0M3JsBhXG+3VMCQw815lXD6F4Sp9FsMnp59Ln1lPd7iXOauDBMwqYuK0eQ/MHOPT/6l1OnvYgminXRKwjigzLHoZ1fweg25bBlVNfYZM/IjCmOGw8XZJFklFPlzfIbz7a23tsJSlR/PXSkQxJHvgerah8i4qKXyFJCoqiodt1Puee+wfcHUE+f2Y3HQ0Rq4Be8jHJ/BKOHVvxNETek2FLNLfNuotarY3TNCYmdIAGieoEHctGWKiPjzwjcXodD+SncnFSTO8zF6h20fn+QcLNkQFaG2si5vx8atr3cvCL1ziwv/ao98RA9BjsF6PRJaOqAey2vcxcMBNzkxn/zoFiO4TKa7hwSpWM0K7kX/LZuFQLXRyrrpGMKe0t9FG7+n1q9CcS7SpG7xxBZTiRAHpidD7iU6O4YkQen+5upr7Lx18uGUlBop0X1law/EALTl8IWVZp6xHTDm0r+oTl+KN3gyaMqmoItMwn1DUOlJMrnKZE60kwd3HF+lf6fZ7X4qKosZWwRuLhyVewOWF073cqcJtrKb7EaExOiZ//7YGT2tfJIoTICfjyw6dJaWggpmYupdF76Ixexl9G3MX6aVNRVZUX6tv41cG+gkzzW8L81mdC3x0i3O4j6A/wVvwXlJqrubZ7AcbONl41B2m32lk5bnK/faX4Opi75G0SG/qqY45LjqNTHUNrOIegcpyiY5owCUM/IilTx84Pagh5glx0/x9QpTSWvriPgLd/sOSXhS8y1CCTZ/GTnr4PnS4EQXC8rsWy6eTre9zy898xbcpEHspPQ/+1SpM7qzv58xObmezpPwg3OrRUJ+oI6CV2ZxvxGDX93DfHI1qnpbC+lomLXsQshzA6bkGSIi86j72Kt4ueJaCPvKz+PP3PzM2ei0bqq+9SvmUD699+jdaaqt5t2mLjGKa3Ydy0BUuXCwlQpkxmTUYGTT0vwujoaM455xwyzcm0PLsTggoeWaU63c6s20eiPaKGzGeVn/HzNX3xFcPihnF+wflMS5tGqq1vgPk6qqoSKC2l6tLLkMwpWKbehaQ3o6Dw0hAz9e0bSOnuQAoFSRs/gXOnTmXp3v2saWnD1e3GUlXGkLIdx71+blOYzyc14bFELHdZjRZO2xmHTjm6TTrVE2DXpJl8OHQcCe3NOB3x/GP0EMYrITR2O/rkZLo++ISO/6xBnzMbSdcnUD0rfofijFhmQloNB4pyqO0Zd4OOBF4983KGHNrD1C3Le9fpiI7jpUt+jCkc5nf/eJSSynIM4RBJ999P7FU/OO659Z5jWObGPVWs7Ozzz88M66nd1kxtZ8RCFitLXOE2Yj6ig9skq5YkvQZZldnatphK925MsX5SJrSzNXMib0pX4pHs6NUgP21ZgfbLbQQ8feZ4g/1yNLoUDibraDfXcNXKN8mo7GnMp9Fgnz0bzZyzeWuzBUPLwAqg4xfkMP6sbKQjnqOvDrXxs3d2Ud/lI85q4MXrxjMi3YEqq/jLOvD/5zFi9P/sXV5RzXjlWUjD52G5+EqkQ8t5f8VL/CznNjw6CxY1zO+HZHNpSly/zDuAT3c18qsPd9PpDaHXStwwLZc7ZuVjMejw+xuprHyiN5YGkti4cSrBgBW73c7111+Psambmld/zXbX6XSEI67JpObN5FZ+ROfUidxuPwMfWtIcZj6/Yxr7vqxl6+Jq6Gmkt7nQxLJhZsK6yHENt5m5LCWWKQ4bxTYzqqzi2dSIa0k1ijcMEtiHurGV/5AGj0JD/Gw2NkdR3eYmNdCTbm0wEtQZ0Hq70RqK0ZmmoNFGo0hBumJ3sPDSsxgxYkTvNQi1etng9LBtUx0Ld7uPaGSoEqV7jSjdmwA0y3E8EvollaTjQiVKkWhUlEhVWwApiN6xGWPSZ0hSn5VcVbQooTiCrXOQvTmo8slUhZbRmmvRx65BH7W371NfOr66q1HD/cc7vVbil2cV89clZXT7w+Qn2ai2anCnmFBtfcJXGw4xZs8Gpm/8Eo2qopUVppXVYg2GaRlRTMdN93HXsj5xdptrKd7EaKIDBu76oyhodlS+KyHyxXtPktbUTkztLHbH7OP0wK945vQb+clpf+CRyiYer+6rnnhPRYjbLx+Jucf/q6oqoTo3Lf/ZR6cO/jwtmi/9/c3NkqoQLTs5K/A5V7e+R+vWVPa6To90cgRAi9Y4Aq1hGBpdn4tA0vlJGv0GBzMVDpnO5p6SyaTIZl6861bkcJhJF17O1EuuBKCyoppFby6my+1kb+we9sdv600rzXHlMKZzGGecnkp8fDNu5xa0Wz1YFrcjHVQ4Gm/POotdBcU05iTx1KSxjEk69uC6tbqDH7+8jZSOMONQiPIPdB15DRKfj7VQlmrofQkdjc/GFtBc7eT217aSGQhyka9vBh/2b0H1f0VJ4Vx0I+2MmDiD+PSIe0tRZDZ9+C7r3np1wDaHz5zLnJt/HAmuk2Uqz7+AQFlf5cRQbi6fDR+G32xGI2mYEiykSE7Fp8D+eAtn/WQ0esNA4dbsaWZpzVKe3P4knlBksNJIGmZnzube8feSZO0fRKj4fHS8/DKtf3888jegSR+Cfdpd4I9ck7ASYmXTm7QHBtZkOBEdUVb25LRTkRa5Xw0hDWntJcR156CTFeTcQs5qbyC0fz8F23dhDYYJ6vRc8dvHaXf0XefH//IgI8pLe//W58/BNKwvBkHxtBKqXkuw7POeBfR4PljEn5xB1ri8FB7aw9zVH2EO+HDaHLx9znUYVJVxezYzdM+63u0Mq20hs6MbTXQG5sm341gwEgDrpBQUXxidw4ikP7ZgDisqV+wsZ3VXn1AY0RHiIo+OJ/c30q2qJIUlLvQYsR4hRtL1CnXuJfi9+wAVS7SDc++5n7isaLYefJy7WyYx+suvKKiKBOvqjDryLrmau9QUTt8nM6IqiKbnLZkz3MHYrA6Cn76P+4hmZV3ReTQlTaA9toQtcQ62SRF//rnTs7n/7OJeK8C7W+v42bs7UVVIijLy7q1TyIjt7+pTfCGcL36ItvEL7JpFSFKfwHEOe5BXx1/B7yoi6cKJgXb+XvoIM60q/OB9MA18T7Z2B/jlB7tZsi9ynwxJsnD31B3ovf9CUSJxFinJF1BU9BDbt+2l7KNtOFQr49VO4vS/RQ0Had4Vwy7/ORzKOw8AVVJZZA5SZlCYNSSR3543jFRHZPbe2eRh7Tvl1OyN1NOwxptYM8rCp7FHCci3mvjLkAxGGU10LTqEd2vkGCXcOHI381jyhbz4VRUA10/ORLdnEcGeoPP8uHE490aundmuR8msoa79IFqtlmnzz+ZprZ00s5GVHd009mQ2SaqKI6hyc1Yil2UkEB1WUb94D+P+B3CGrsGnnA5AUyjAJo+GKC1k2SRUSaIBhZcJkIiKN3oHB0wtKLataAxdA645gBKMRQkedvWryN48kGQMsWuQtIGvLRvDKMMC0q1n0uEN0djlY2+j6+uNslF1EuFcO6ZMG56e0hLTY2zcl5OCArQFQ8Qb9ORoFJorytm7fStDm1vRvPgK6HRkPPssnj1Wfl3ZzJeEuM21BG+ig5iwmTt/d99Rz+PbIoTICfj0nb+R1dyNo+4MNiSUc1H3T9ian8Bfhn3M8s7IDTK7KcT9pQFyrx6GMdfRu+5L9W08Vtl01PbhWlTOCi/m5weewdyYzPruq2kJ5aEQUayK7CTk/QI13GNtkSB/tkLCkABhcz57TAtY5Mlkh1vh3KQYni5K5z+/vIu26kp0MfHoR0zA7Xbj8/n4+s+mpqq8b3y/92+LzsLjMx9nYvLEPveFtwP1gx+iHvgCf6cet8fMi3nX8fikhShaLYWBRt7dehuJ438Ac3973Gu4e/8BLn55P34MnK/u4CJDEFfK+dSVOQkeEVMDoI8xkHBJDos3fkFSUy1BrY5GRzwzY+3I+Xk8/EEr6SFd/3S7UB1B97scGYtzIhKz8xg2cw4jZp2J9ghXQLitjcZf/6bfwAFQMXkamzNTQZLIDCeRmjqB2TeOQncUEXIk9e56ntj2BJXOSvZ3RAavOFMcZ2XNI0tJIrVOh7+ri+6lywh3tBPUavEZ9bh63H4aNAyPncGQ6Ejzu6DsZ23L+70FsgAknY60wiHYYuLQaDSEw2HGn3MBGq0Wn9XOC/s/5pPKZwj19GiVtTF0Jd6Poh+YUQGQZtRTvHkDpYkp1Cb3icx3fn4b8c5InQuNIxvzuBvR2CKR/6oi42pYwxfGZpodDuJcXVh9Xv4z73yq0vo3ArN6u7nm7aew+j0gScy77S5Kps5g80O/YU1pX2n1EtNQhqcsOOa11caakDv8mIpikAxadPFmjDnRuJbVEKyOxIqErTp0njDtBom4YOQ5qEDmNjy4AbsCV2pMRHXJqPS33JmsUDQpgyGTk4lLs7F7+Zcsee7J3u93DRlD+6RULjK+yRpO51PpPGK6ZS6tUUjY2w1qpNO6VqvF2FFDStN60hrWolV6Unh1euy/uJ9H5SwW7YsMxLnxVs4ZmUpRsp0fvb4NVYWp+XE8dfkYYqzHTkFVAjL+r77CsOJGdJommgxxXDzibxy0RiwTl9eH+VPqVxhW/zqyQnwRXPlOJHvta6iqyrL9Ldz77mY6vD0DWNo6fjixkuLCe3A4xkWsdwe7aP/3RqJ1L2LTfYGqQtWX8fg7I8fpGjGHLZnngzty3VW7jhln51IyLbU3jfrw/qp2tbHiPwfw9TTdsxZEsWNaDGU6mW2uvngJm1bDJIeNW5o/Zczq5bhCVyITuY8/JcizBJg/Og7dvs+RJNDrDIzNmkvFV5GBesTMdCadl4dXUnn8pZdR6iPP0YacEnZkFvbuJ8mg4/q0BObER1Fi63N5hJ0BOt/YS6DKA8g0hJrY7EnEqAuxMH8HiuYMQg0D226Ee3pY7TZX8HLaB1Rq6whrvkGhMsAWcBDVXcTshDP52dX9A5AbnT6eXnmIV9ZHAldVvYbgpIS+OithBf3+LoplLeOzYylOieL80WlYjf3veVVRaLj3PlyffIJkjcE649c0GSz8QPJwo/NLPIkOYhQrdz78M/6bCCFyAj5+61FyWkI46qfzRUoj6ZqXuH7ob1GknuJHlUHuOBQk4ZqhyLlRdIRl/nCogUPeALvc/Xth5Bg1TFd2cV3F39A2SnS3F7PfN4uuUP/AVJ2ljfjiz7BlbMZTY6NyWZ8lxOyIJWvsRMyZOewKKDxqT0MBbn33H9jbm1AlDd6cYhTjQH/hlClTmDp1KlarldKOUh5a/xC723b3fl8cW8wzc54h1nRERPXeD2hf/QRXpd7ItqihGJUgP9I3c0+CFu1bl0ci8+/YDlEpA/YHQPVX8OJ8lspjuDX0E8LomJJl5YUbTsOk1+DpCrJx0SEOrG8asGpQ70TR+XAaW/AE0rAHYlCBOEXqTbfz65wYQzYCXf8Ejl2jRKvXY4l2MPrMBYxdcB4azfEFhOxy0frUU3S+0mdFCZvtrJ0wluaUJOLi4pk9exZDhgw5alM3Z0sTrdVV+NwuQv4AQa+Hjz//NyvGtNJ9RGdhY1BDSrsJs1/LkBo70Z6jx0ekW4oYFjONaEM8MmGWzU/glZZqSmNTMKgy12ancn1afG/cEsCKmhU8t+s59rRHYhhSzEmMq4rDUJVAU0IGlakZ7CwsOe51OExmYx0XrFyMJz6bOaFMcrV9MUoNoWbumBhDVULcMdcfbjMjqyrOsMyD+WkkNVWz77UXaK+KlI83hxUml9bgNerZnpfWm0Vmd8QzofgcErpTUT3f7MV9LHxaeDZFy4fNTsI9XWxzPNWc3VWF2XqUxl8QKXDlXY6qhlEJsXxSIdtKJqNIWvRqkFt9z5Nbl4S/cjImq5mO+qO/KotyFfI71+L/YhGqL/J+0Njt1E84g5usU5G/dl8uGJHC3y8dNaAs+7HwV3bxxY5F/MKaRac+GoMS5GdVL3Jr9QoC5llYLrwUzaKbwN0E1kS44i1IG9P/+vhqqax8kj2Vy3lp3+Xsa49UfC5MsvG384eS09BI98cbidK9hVm7CVUFZ5WZ1n0Owt2RH847cw4Pl1zC3lonZ/j0jAr2DXgp+dHMuX4o9tj+1tGgP8z2L2vY9mU1SlhFp9cw6bw89OPjeKy6mc/aInFTo1z7+XDHHZjUIK8mXkhj+9Vc6tGgRUJGZYuunAPaepSwkQR5HHJXZPtJY+N5dKiWmh6Lh04OM6NsBwUtEVd4RXwKG3KHkRQXyxsj80g39Rd+oRYvbf/eg9wVAA20WZtZVxuLhhALYn5PhjEiopWZv8MffRnB2m4C5Z2EmgYGnsrIeLQ+/pX4PitjD+I2F6OTJXT+NWhVCVvYiDnkwKPzYA/ZiQnEMMRZxJDEPOJ10aS224ly6tGnWEErobXq8ZdGJglLUvT8ZbSVNjkyydOVu9BWupGUgffkeLuZBy12Eu0mZGcAVVZRvF7cnzyI4m5CmzSCuB89zLIsM9Wv/BVPgoM47Pz4wXtOcCd+M4QQOQEfvfFH8lsgunEab+WH+XNexEytU8P8onI/F3YWE3/dUD6V/dy+r4bQ1y5RqhTifveXTKl6m/i2OhoCI1ji/AkBpX+wkzG6juSxr6K3taJRJFxNKm1l8TSZJ0BQwdRUjc7bPyc9kJDG51PmE99QybTNkdoF/qRMtKmZJCUl4fF4KCoqYvz48TiO0Wfks4rPeG3/a+xq6wuuunPMnZyRcQa50blsd3m5aU8l9cEwMSEnr+75BeNcPX7KuHxoL4eRV8D5/XP88Tvhs3th15u9H32RcTf3VE/EE5QZlxXDP38whkR75GXkbPWx/JX9NBzsOqnfxWtqwRt1kHPPO5fqlTJ1+2swR7kpGm+kIGEY+z9ZRlPXIRRVISEmkxEz5hE/p7C34NyJUGUF97oG2l/5CN/af8AR0fPdNhstSYnsKylh1mWXkZuWyr7Vy5HDIZoOluLu6qS7vZVw4CgzI41KVYqH2kQf1SlHj4y/VDmdyZYx6K2xrPhqA5IikzukmIvOvxjnK2WEjijxvXZUNL+Ik/H1uLQeK0jE3/kZS6uXsre9z598WdFl3DfhPrSSFteiRTTcF4lh6bZYsWZl0vjbP7LP5mBFh4v1zv7pshpVZXJQwxW7PEzs6LNghSR4cLgJ7bA49nv9mDUaonRaYvU6tJLEjzIT2dDlxqbTcmVK7ADBFu7s5M1776DZFXmBxnV7GV/RSMGa1Xz+8rOUb97Qb/n5t95NWiCHUJMXfaoVNSATqOmO1NUJK8juUMQKYdAgd/Zde0NWFPYzMmg0we/dTj5tdRLt6mDK+mV4O3VsdoxFkbQkBFq53NKJsX3kUX+XI9mfrudAuoG0jiATyk6+SJ8txsikhbnkj4yh86UX6Xj1P8g9NTo8xSO5YcjlONW+QXv+sGQeOGcoydFHz4Y7kpCicteBGt5tjlzPGNnLmzvuZKS7z9WoqGbC+mz0Vj+SsxJVa4Tz/oU0fCE+Xy0trYs5VP5nVCKiLyXpQg5+ehYPdHjoAiwEeUD3EhdrV6GRVEIeDTWrEwg6IwJK1mjYNH48/0qfT6NsQ6uRuOm0XK7ISmDr59X9nu8hk5OZfH4+lqj+A35nk4dlL++nuTJi1UorimHWNcUEbTpeWPE6t276OVGyh8WOydwo/wxtq58RaPmtZCCup/9MadjLXq8erRJx/X5VbGJjgQnlaz2LUg06Fh7aiVoR6Z1kMpm46667MBqN/ZZzb2ig6+MKkFV08Wa8E1L4/I1SUGFW+jsMCb/e/8e47HXImQ4GGyoQOOREcQcjg31YRl7+NKpqJlr/PJ0GDf/MuJx/ZvS1ZLi76iWmVW9niXp6JCtOZUCV5kQlijw5mUQlmnjVTodBw3N5Bt7LjFxPR1Dh79t8xDvDWJCoRuZ5AgSAPUfpWnYfJs5GjwYJuasW75pHQA6RcPfdxN10I3+7425ccdFkm+O49r4fD1j//4IQIifggzd/R1GTgaimyfylyMgb2ZEf+e2ddzOlexvbx/+QRx0XssbX38R1oWsjV1X8h3HOveiQ2aMfw9qmu5FDfR0wdZZ2rIn7SR2ygli1BFt0CYkjZmC2F/DSPT/E1dpC8qjxxIwcz/59+/DVVWFsrUcTPvqLr2vmuVw98wzy8vLQnEQ/kSP569a/8uKe/vn5xpj51NsvR0Ui06jlP/7lFFZ9ATX9M02QNHDxy5GZVesB+M+FA3cw/1GYeAtbqzu4+oVNeIIyUSYdL143gbFZEXEXUkIc7DjIK1++j3+fAbe+m9yWKUiKHr+kEqvpYrLlIzZEj8OpdHPdddeRnp6O1xXkrd9vwusMkpBp56L7xkJYoXtVHe61DajByEMnGbVYJ6Zgm5SCLvbYL3bZE6Lxt32DYDgUoG3d45jdNWjCQfw6LdXx0TRHW/EY9f3SZ4+FPSaWxMxsjEtXYO32oEgSbpNEc4yft+caabANDF5M8iZhlI3odDquPe1a5hTMwRDU0fVmGf7yzkiDMV0nslnPlaMUAlI7FueH6IOH+m3nnXPeYUhs/z5G7nXraLz/V7R4fezLKaAqK5dX5y0k2BPYq1VUHu02Mrncg8EVhGB/t5dxdALas3OItfV/YZ8s3m3bqb7iCkIaDdXxUZSlRKwpMckpXPLAIxhtNjZ9+A57Vy2ju62vtkbm8FEMnT6TgglT0JuOPzirstqv7YKqqnS3tbL4tRepWb+m9/NDlhwWJ81GRodq1JAXr+fMrZ+jD7YjaRPRW+YiHaUq5THPLcpHUtJGzNaIlW/0zGnIzvFs/KCT7o5IjFhMipVZ1xSTkKij+U+PUv/+R9w39VYOOSKZYraQjyh/Nw32ROKsBq6flsMl4zJIsB/9entlhXO3HWRPjxX21owEbs9MIj7Qhvr+rUiVK466nqyB1lgDVRlxeOx97xVt0EJK+UTSm+uwatfTrtq5PXgn69WIBW2BZj13tS0muLovzS768svZMXEe961polvWIqHy+jXDmTQks1eEdjR6WPT4DjxdfUJx6kX5jJyZ0S9IV1VV9q5pYN27BwkHFQwmLadN6aJo33VIyFQnTeUOfsHOahdIKrN1B8nVeBgaziDKm8l+X6QBX3usjlem2XCbe+5rCU5z2LHqNMyNi+bSlIj1d9u2bSxatAiA/Px8zjzzTBISEpBdATrfO9hrbTAWxqCdkc67T+wkFJApmpjM7OtKwN0Kb10Jtf3TsPuQoGh+pPz+sqPX4Hg+9QJ+VXAnGkXhrN3rSe+K3PcxipV5wVHUaztokrqo13bgkfpPcvQGO3tiHDjNVtqt0Qz3xfDDQ2GSAgOHbG20gU5ngKtw036U9OTh8VaevXAk5o1f0vTgg6DRkPn8v/jXm+/SFRtFvi2RH/z0tmOc57dDCJET8OE7v6WwzkxU80QeHWLk7SwD7236jMmBR6k0pjFvzLN06yKRz+Oce/hx7WvM6NiCSQ3iM2mojYlhU+tNOOsm9m4zOnsdWflfkem+GXt8MY45+Wi+5qur2L6ZDx55CIDTrriWoTNmYbJHoSgKQY+bbZ8vYvsXHxPqCX5Vgd3DJ/P4T+/BcYIX9LFYV7+OXW27eG3/m9Sbz8RnnweSBoN3K/b257isYAE/Hv1jHCsfhQ3/OLmNjr4KZj0AR5QO3lnbxcJ/9AUmzhnjoVH3KtXdVZFzkQ2EnGMJtM4F2YxeI/OE7nHm6XbQeParJI+ZRygU6jdr6Wrx8u4jWwh4w4yZl8WkhblIkhRpsrapCdfSmj5BYtBinZyCKc+B1mFEazegeEIoARnP5ia821p6l/WGfazsPISsq8Ma7cHdXI/Pf/T281aThfisbBIyskmNicMRE49r6xb0iUm4H/nTUXs45H72GYacbPyyn9KOUv6w8Q8c7DxIWP2/uSHCulSCljGcnncdfyzKwSMr1AeCTHHY0EgSflnh9cZ2fnlExhfA6QdrucYYw4hqLeqRmVZaCUO6Hfv0dEwlA60bJ4vsdNL61D/ofLXP5SUZjQTv/jFLPotUcTTZ7Jx2xbUMnzkXSZJoKNvPx3//U79aJlqdjiHTTmfErHmknqBZZDgYZMVLz7Fr2RcDv4yNZ+nsS6hRzRi+qqfTEAOqyvT2tYzs3kOXPYb9+SPYPGomP/zChd0/8BWYnBtNS4yWx5Nlunp6PTlw8Uf1TqLoqWuChsSEBbgbRrF/eSI+p7F33WEX5PDD97ZT0enHFvRybsVazju0BnvIx4qCqfyjYB4eQ8TVesv0XH5xVnG//Vf5Aty8t4pd3ZH78pe5KdyR9bX4n7otdH+2GXvDzwnqJLqi9RwosBEyDBRYeZUeMut8vUG3hwmpWp7wX8CrwVn8bMsbjGmNWBFUrZbc999jneLghpcjbRF0KEzWV5GnbScjI4Mrr7wSU897qavZy7r3IgGqSk+9C51eQ9bwOE67tBBr9BHPdbOXpS/t67WOJOgOUTJiPze2nUWTK4AOmVn6g6RouzGEHES392XApOklxlq0+JMs1M1Lw5EezSi7+Zj37vbt2/noo0gvMbPZzPm5s7DuCqCGFJAganYWltPSePdPW2iv95BW6ODcO0ehOew2U1X4/F7Y9NxRt39cJv4Q0sdRnbeAP376Jcl7twFQnpDGhHln4ddomBhtY1eHmw5ZJkv2UV96gKaGRqLbm9EpX4u10+nJz84jLiqGEkMWZo8WVVGJnp+N1haZTCvBMB1BmRtf3sKO2q4Bh3TD1Gyu/eo13B98gDY6miVjxtKalEBBdDJX3nXrNz/H4yCEyAl4591XiS6zU+KK44/FRu4oC5AwOokPRoW4vzYyg0gJtPDEgT8yrWsbEuA1adidF8fubfcT6OwLBrOlbaUksYv07JkknX46GuPx4xQWP/MEe1Z82bd+bBzujvbjrBFh6IxZjD37POIzsk6q0+qRhBSV2/dV8FFrxA1k9KzF3v5cb8dSgAvzz2eUZGFSw36S93x49A3N+g1M/Qn0+LzdQTdPbn+S7mA3DZ4Gwv4kNu5JJuTuCxDTmOpQZRNqqK9XSrxJ5d/qg4yQDsLsB2HaXcc89gPrG1n2ciQgdPIFeYyZ23ftVUXFs7mJrg/LOVGNIm/YRY33ADvbjz6LPBKHx09eSycxHj8G+eSDZXUJCeR+vAjtES6zzs5O/v3vf9Pd3U2LqQVfoo9wUpgdbTtOapsZgWTy/OnM65rKSG8Rn6TqeDHHQPURjRCjdBqGWM1sOsL9MqU1zA0VAYqcMiZ14EvaMjqRmAsLkHTf7F76Oq7FX1J/5519H0gSOe+/h6k4MrB2NNTx6RN/pqUn5XXCeRczZv65WHuydtrralnyryepP7Cv33Z1BiMxKam4OzswWizEpKSh0WojQdqqSnt9Lc7m/jFI1phY5tx0O4k5uRzc+BU7l3xORbOLJQkzaerpWD01S+a6i6bjMOgpsZkxaSLh0SG/THeHH5NNj6rQW6HVLyv8aH91pMIrkGWUuN2yjBzPewQC/fev+ApoPTCG5W3DWKpGuv/GWPQ8e24++bvW0vr4Eyg9qcFBi53/ZJ/G6rSRNFvjuGB0Gg8tHIqilZi9pYxaf5817a6sJO7LHRivpaoqLY2fUX/obbpCG3pdL4dJafKT0uzH7FMwfc36pUbnIBXOIhQzgUM//jOqp7/r7j/n/YT2oeP4Ym/kHPMTbfz78mI+fOfNfqXhzznnHEaPHt1rrVUUla/eLWfXyjrUw6XyJTjjqv51VJSDy9n+/FtsdZ1Lq2TkfXuIdklBj8wcQxlpIT1GfwJmX1/cUvHkZEZF6fFu7Lvutqmp2KaloYs59kTt4MGDLF68mLa2iOjNkROZHTWOhCtL0CZZWPbSfg5ubsZs13Ppryb0E029tB2Ejc/CqCvg4JfQsAMOZ5GZe2q8jLkKjFGQPCziwjHaUVWVTz75hK1bt/Zu6vUJs3GZj5/iawwFSe9sZajPSa6/m3Bb64DeVqmpqeTm5jJ27Fhivlbc8DDeYJjHFpexeG8T9V0RUXvx8ARuW/QX/Dt3sfL0GTQnJ1MUm8bld9x01G18W4QQOQGvv/MWuopkpnRq+F2JkRFdMrumJPBhd8QkadOo/EP+OQ73AbCnIGvA7fVQs/JnBHqawWn0PoYW1jBy6FnYJqT0KtIToSoKX/zzb+xbc/QBMTYtg5zR4xi/8CJefu1VfCv7z/isjhimXHIllugY4tIziEk+dpotQEsgxA17qtjs8iABTw1JJUdTx+PbHmdby7bjrpsQDjNR1pHn6SIq/0ya0kawoXEDFc6K3vTVoxFsn0ag5eiZEXMLbPyu8VYSww1QOD/idz2OsFJVlY2LKtj6eSRyfOy8LCb2WEZ6lwkp+Pa349/fQaDSidwVQFVVupQWOn3N1HsO0uAdWLI8bUgJOaPGkTakhKScfLQGPRqNFsXjofbAAbb8+c+kVlUR5XShOcZjEnPFFdjnzkEyGNAlJmFITwMiVSs//vhjduzY0busw+Hgpptuwmq1oqoqiqrgCrpY17COss4ytJKWJk8TBTEFnJu+APNBha5PK1D9A32/EInnaDBLGBSwh1VsJ2Fw8a5/HPsZw7DPmYNt6tQTr3AMOt96m6bf/Q5Cfab/xHvvJebyy9CY+wdVy+Ew6956lc2LIv1wDGYztzz9MgZzX9pqU3kZ7/zuVwR9x64+OQBJInf0OCaefwlJufm4Wls48NVqvnr7tX6LJWTnsTFtFp82RMTbbxaUcP20nJPejaqqrOl0c8veKjrDkd8iyaDjvZwqmir+QCAYSTn1hw08s+s6drf1VTn+VcmnnDn5DtLy8pDQ4vzgQ9r//W+Ch/pcbSvSR/NiyXxipgxhV1JfvFOKUc+jhenMjouKBNSqMocO/ZnOrk0oSgA57O7dN4DRkEQg2IzJlEFx7gPEvPMzpPYeC0febLDGIU24BdLHoqoqbf/8J+2vvobaFXFRhPRWttz6ax6u7W/JLUyy8fYtk3FYDPh8PjZs2MCqVX1F66Kiojj77LMpKirq/Swckln+8n4ObunrGWUwackbm8iQYpm4xRdhCDaxOe5yrq5fgF+CGFniXLkdh2LE4O/f5HHSebmMmZuFpJEINXnoeLOUUFPPO0gjYS6OxTI2CX2qFUmrQQ3K+Pa14/w0UoTOT5AV+r3Ua/tE1E9+8hMObehiw4eR4Or5tw4nd9TAisvHROkRd0d5f4VCIT7++GN27eqL0ysaMgTjabNY3OXho55KxEejyGriqtQ4htrMTIi2oj3cCbm+nvLycvbv309zc/OA9TIzM4mJiSEuLo5JkyZhMPSNScGwwrtb67j/w92oKtw8LJoL/nIHyydNpCUpieK4DC798Q0nf+4ngRAiJ2Dta7+gsf4sJnfAQ8NMfJzW9/BPj7HxwrAcbFoN1dVPc6jiL3TXj6Jpy1XIgcgxpMYYOPOaEsxFMd/anK2qKju+/JTyTetpqaogOjGZebf9hPiMvhl/UFa46fkXGbH8g+NuKy49k8kXXYGzpYm8sROI66m1sb7Lzd37q6j0h9FK8FRxFucn9SlnVVUp6yxjfcN6drXt4mDnQapcVd/4XFKtqWRGZRJjjMEb9rIwfyEJmvF8vLOBzFgL+xpchBSFe89IJ/n9C6FxB2RNhasXgfbE1UlVVWXdu+XsXBZJyxu/IIcJCwYOJL5uF1U7t7H1k49orjw4cEOSCdSI2+vmp1/CHjuwo+2RhMNhNm/ezNLFi4nq6KDL4UCVJGbPmcPYkhJM0dEDKoLKsswHH3zAniMa1kFk5jhixAj0+pMLrD1MsK4b14paAmWdEXPyN8Q2Ix37aWmE27po/fsf6f7iiyO+m0HU2WdhmTgJfVLicbYSqYmieDx0vPYanrXr8O/uy8wyjx5N8q9/hank2Nk6qqry8V//yMFNfbFI039wPePPuaD3b1+3C0WW2bX0CxrLS5EkicaDpVhjYmmrqcIS7aBoymlodXriM7LIHjkGqyMGd0c72xd/wuaP3kNV+65Reskw5tz0Y2JT01AUld9/tp8X1kYGpssnZPDz+cVH7Yx6LBoDQf5Y0cjbTZ29nz1amMYlCUZeWfkBL2+xUO+KiKt4cxu3j3qeDHtffRirZSh2ewGSIhG7K5vO3/a5QmVJYt3Icbwz+2wOpWVyWWYKP0/voKHhnd6CYzqdnXB4YMM1gIKCX5GRfk3/uJeQD9b+DVb9KfL3pa9B8QLCra20Pf0Mna/3BWN2x+SS89RfcWWm8bN3drGtJnKOEvDz+UO4ZUb/xoUrVqxg165ddHb2XYvk5GTOP/98kpL6XEi+7iCbP6ti94o6BhLmkA5qdCoZMuSH+v8WqQUOiiYlUzQhGa2+/2Cv+MO4NzTi39dOsObo12TA3nQq79s34/JFlrdabBgb89D6opl2SQEjZ2acYAsnRzAY5M0336SioqL3s5SUFK699lqMRiOqqrKotYscsxGHTktnWCbJoKfBH6QjLDM77vhjnaqqtLW1UV1dzfbt26mvrx+wjMlkIi0tDZvNRnZ2NkVFRVgsFn76zk7e3Rr5LZ5p+ZJDphCtiYkMTcjk4h8duwfXt0EIkRNQ+vYf2Vs5jQmd8NciLa9nWyi0mLgwKYYfZyWiyG527riFLtdGnFWTadwU+YGizFrOuL6E9OHfQDX/H/myzck1uyvRB/z8wVuPtHUdWp2exoOlKPKxp8Ax+UXUNDVhdztxRcUSj0xKdi7Vu7ZTOHEqHmcnjqRUcseMIy4jC7/bjarIuBO0fHpgEWGdyvLStzEGvRSZk+hOKibOHMfw+OFoJA172/cyLmkc09KmEWM6uTLiLPstrHks0oX3ljXg+GYP/qZPKtn8SWQgGTs/i6IJVlqqDtJRX8eu5YsH9E7RaLVYHLn4uk1oDcVkjRzBaZcUEJNsPdrmj0l9fT0vvfQSoVD/gOLk5GSSk5PZsWMHsbGx/UzWh9HpdNx5553Y7ccqH33yKEGZQKUTxRXEtbwGFJD0GsJtPvQpVkKNkRmiZUwiUbOzBgTvquEwdbf/GPfKlUfdviE/j+gFCzBkZtL29DPIHjcJP/oRzg8+xLtly1HXSfv734mad+bJHb8is+XjD1j7xiu9gmHI1BnMvO4WzPajP99qz6yzevcO0oaUoDeaUBQZORzm0OYNrH79pX6Br7aYWIpPO4OxZ5/X6/7p3Zaq8sSycv62NJJxEmc18JtzSlgwIhWt5uQmFLKqMndLKXvdfUUMM5sDtOyI3Ht2o44/LExifGo1zU2raG1diqQ9uvVQcoH8RhKpu7oGWNyeGb6Q5AXlTMjYPmA9m62E3JwfoyhBoh3jMBmP0xoC4OOfoG55EW+bGV/yJXQu2024p9ldS8JogrMupWPOSB5ffYgGZ+S8JCAj1tLbH+WScen87rzhA/rV7Ny5kzVr1vS6PQ6j0WiYN28en332GbExsUwaMo89S/YTchsIc+JgaK1ew8I7R5GS7zjhsv7SDtzrGwnWd6N0Dwz610QZcJydg3lYApJWYs+ePbz77ru932fbxnLpj2ZjNg8sj/BNUVWVRYsWsX175HfLycnh7LPPJj7++JOe/8v+WlpaaGxspKmpiYaGBpqbmwl8LbtPo9GQl5dHYWERv1zl5GCbH3vQwy2BVbQlJDA0ZygXX3PxMfby7RBC5ATs/uLvHNoxjnFdKjVGhZKLS3AMi4iLcNjN2rXTkJVuXDUTaNgQ8ZtlpFk5695x6E4QA/Jd8EhFI3+vbiZer2PVhCHEGXSE/H7WvPEyFds24WwZaKb7b3DJbdcRt+QWfLIOx7kPoYy9Fr3h22VU0LAdXpgLchAufgmGnj9gEVVVaamqIC49E93XLAeqqtJ4sJSl//6czsYA4cBWUAcGmBrMFjKHjSEYjKWpMh6N1gHAmDMjLh3NSQ44XycYDFJdXc2qVauoqzva7G4gp59+OtOnT//G2U7fFjWsgEbql6nwdRS/n8433kTS6fBu2kT3kiXfeD/WqVOJ/9FtWMaMOfHCR8HrcrL8xWcp/SrSr0lvNFF82umUTJ9FXHoGRot1gKUx6PMiyzK7lnzOzqWf9xMfELEKjl1wHkNnzDphPZll+5u5+dWtyD0xDPmJNj6+fRrmExSyO4ysqjxT08KzS8txHZG6GpVg5snLRjMxOZqAohCt16EoYQ5u38aBPS+iSi3Y03fgxcInLKSeDLZIkYD3YeUH+MMLj2Lv6n9Pb0/OxzVaw4TL4knNWkhM7BSMhpMf1Dpef53mh49enLA0/2J08y7ANjuFa1/qE5qTcmO5/YwCJuXG8qcvDvCvNRHxPyE7lt+fP4yCpP6iWlEUVq9ezcpjCFyAVJq4hvcIqxK3+h4iFMzFpMLokA6Hw0RMspXk3GiiE8zsXVNPY7kTjUZizLwsxs7PQneciruHUVUVxRume2Ut2mgj1vFJAxIGIFLb5MWHv6RNLSVkjMT+aLVazj77bEaNGvWtnldZllm2bBlffdVn8bvssssYMuT4QdffBeFwmMrKSiorK5EkiYMHD9LS0tJvmUNyLOtD2Zyt3UuMPkDx1DO5dM7kY2zx2yGEyAnYvvY56taWMLpLpd6oMPbuSeiijQQCrWzasJCg3IwcNFPzyV8JhHU4kiws/Mnofi3G/5cEFIW5W8oo9fiZEWPnhWHZ2HT9H8z2+lr2egL8ZuU6Civ3UZecRWFHIxmlOzhcJ1hnMBKdmITV4aCx/CAJmdk4W5vxdA6cyZ8Ie1wCmcNHMvashWj1evasXEpqwRDSi4dhstnwupwc2rKRpNx8EnSdVD59HeVteoLWDOKnXoak1aLIYQIeD2lFJZRuWNs7MAEk5uTR1dSIyWbH1XocoSWZ0eoMyCEnyQVzcXePIBzoM8/rDBrOunUEGSUDW2R/GxRFweVyceDAAfbs2XNUUbJgwQLi4+PJysr61q67/xVqOIxn/QacH7yPZ91XSBYL4cbGAcvpU1NJ/fOjmEeNOmaDum+CHA6x4f232L1sMZ6uzgHfp+QXMeasc6kv3ceOxZ8eczs5o8dRNPk0iqZMHyBej0ddp5fHFpfy4Y4+18kFo9OYXpjAzOJEokxH39aBJhdbqzt59ItSnL6+2bccayQ0Lq5fCfOrU+MosJjQSlDm9rO8vhO3J0iH/WsNIrXt/DZ6CTlSHCyrxbWuFOOemn7LBPUGDLGxRE+agHn0aAzZ2YTq6rBOnYouIYFwSwtyVxehlhaChw7h2bgRz+o1fB1zfABLYpB9CRexpfAKvpR8lB3Rqv7HM/O5e05hv/v2w+31/PKD3XiDMlqNxA9n5HHXnMIBVqS6ujr27t3L+vXr+30+jFIWsph9Sha3he6iXo2kdd88LYtfnD10oOj0h1n5WikHN0ee+7RCB+fcOaq399P/BUVR+eSpndTu68Bo1RE1vpV9B/rcjHa7nauuuorExOO7KmVZpra2ttdFsvsIVyVECk3OmTPne/H8q6pKRUUFO3bs6HecXlWPRYrcw8XT5nPp7InH2sS3QgiRE7Br5TvUrk9hpFOlyaAw9qHpAGzZcDEu33Yk2UDHmgdpbkkgKt7E5Q9MPClF/l2yw+XlvO0H8Ssqw21mfpWXyozYvpnJinYXl+/q80kOtZn4ZEwh5iMatx3roehqbqKrqQEkiS0fv4+rtYXOxoF+x5NBo9WiyEcPrvxvYo9Lwho7mc7W7GPWgyiemsJplxSi/46sWIqiEA6H0ev1dHR0UFlZyZgxY/5nFpDvCn9pKWo4jGnIEPz7D6C43Vgn/XdfUodRZJnq3TvY/vkiKndsPfEKPej0Bub/+B4KJ377gFuAP36+n+fXVPZaRw6zcFQqpU3daDUSZ49Ioabdy5ubB3aDzYg1c9vp+cRlRXFnWW1vMOvJcrXXwO/OLMLwtYmFZ+Mmdn25lj07DjLk0Dbi/a5jbOHksJ59LiviziXF9Q90+nr+Fr6I3Wpu7/cOi543b5501O68AHvqndz/4R529qSEnlYQzy/PKqY45djv5VAohLrpeeoW/5035Zm8IJ+FjAa7Sce9ZxZx1eTsY657uObIqtcjPZAs0QYW3D6ShIxv7+IMBWS+fGEvVbva0Bk0nHf3GBKz7LS1tfHqq6/icvVd46ioKK699lq6u7ux2WxYLBZUVcVsNrN//34WL16M0+kcsI8RI0Ywa9YsoqOjv/Vxfpf4/X4qKir45JNP8Hr7AsPnnnshU8Ycv7P7N0UIkRPQtnknW5Z0M8yl0pYgM+qe0zm468/UtD2DFDZh2P43dlbqkDQSF/x0DMm534+bapvLwyU7DuHuSSk9OyGaoKKyz+2jPtA3O7snO4kfZSZh+T/OIGr27MJgNtOw5N907FhMalSYfbb5tDc2nVTK8bdFq9cz/pwLSC0qwdXaQvXu7Wh1ekpOO4OskaMJ+nyYrJH0t7a6bjZ/WkXQF8bmMOLzhIhOMFMyNZW4tJPpgin4PqCqKq3VlXTU11KxbTONB0vpau6zzJScdgaSRoOk0XL61TditFiOs7VvRrPLz+8+3U9Vm4fd9QMHl6Mxc0giF45J5+wRfWm1bcEw/6xp4bXGdpzHESSXx0YzfL0T346IJTJ3dAIzry7GaB7oRlBVlYc/3MWKLzczo34Hl5Ut+0bn5nvgEV6XM6jf08EOJYDvKK+Ev1w8krlDk7Afwwp05LG8t62e+z/YTSAceQeNyXTwl0tGkRP/tbgrv5O693/Fk3uNfChPJUAkg2NGYQJ/vnhEb/XlE1Gxo5XPn90NaiRuZPa1JeSPPb614lgseXEvZRubQYLZ1xRTNKnvtwuFQtTU1PDqEbVwvglpaWksXLjwhJaU7wsej4fX33iD+h6L7g033EBGxn8nWPcwQoicgJbF29i5xUdxt4L3LCOOYie7d0eKuVjKbmbHrgkoisrEhbmMm5/9X9vvf4NKb4Anapp5o3GgO6XIauI/I3LJMJ1cKvFJo8jw3Axo2g1FZ8MlL6OgQdJocHe242xpJq2wmIDPi6ezE1dbCx2VByjY/whdnU4qgxlox/6A8Rddg95kpLOhAUdyMt3t7dhi4ziwdiVRCUlkDhtBOBhEVZQTVtgU/L+NIssc2rYJnd5A9sgx/zMT9/aaTp5fW0lylKk3wwbgnJGpJEcZyYy1cM7IVByW4z9jwZ4gW50ksbbTTYJBR5bZiAYw9UwQ9q1rYMWrBwCwOozMuLyQnJFHD4QvbermrU01hLduZmmnhuEt5Xj0Jvw6A5Kq0mCNR5E0ZKbH0yDrURvqqbMffVC0GbWcraxiIrs4V78V3c1LIPnkZ8MHmlz89pN9rCvvm4wMTY0iP9GGxaAFZx2by2opV9N7vx+SbOfuOYXMKUn6xr9l3YEONnxUQXOlC0mCETMzmLAgB8NRhNvRUFWVso1NLH1pP5IE5/x41DFdtX6/n7Vr17J79+6jWjx6z3foUBRFYcyYMRQUFHyj8/m+oKoqtbW1dHZ2MmLEiP/6MyaEyAno2FvK9g/bKOpW6JzfSLvyB2S1G2PpBRyqWojbGSR3VALzbhn2vfDxHY0lbU4+b3PSGZKZEWvn7IRoEgzfLDX0G1G7GV6YA6iQMwMufwMMx8g+aTkAL84DXyfE5sJlb0Di/z5oSyD4v6AoKiFFQSNJ6P8L8QlHo3pPO2veKsPZGglSzR+byBlXDcFgOvYg2+4OsL6indtfH5hRczwKE23865pxJEWZMJUtgiUPQFd1pJ3wzSshZcQJt3EYWVFZur+ZP3y2n+r2Y9d+0Ugqj1wwkgvHpp90ZtLRUBSVVW+Usm9NJKbHaNUx+bw8iqek9FVBPQqdTR6Wv3KApoqIqBhzZiaTz88/qX263W4aGhrw+XzExMTQ2NiIzWbDaDSSl5f3vR0bvi8IIXICmktLOfBOG3luhbKxf0eN24GxM5f6bQ/Q1h7EGm3g4l+OP3qFvcHMjjfgw54ywDE5cM0icPTvMszud+G9nsI4khZ+8B7knfG/PU6B4P9HhIMymz+tZPuSWlRFxRpt4Jw7Rp3QtagoKjvquihJieKJZQf558q+ImkWBUYGdUzw6zCURNOQauCe+UOItR5hyXG3wOOjIOQBvQV+8D5kfbPMCU8gzMrSVnYdqoE97+HxB2lU4zCaLFw2fTgTps7C9F+Mrzu0vYXlrxwg6IuULkjOjWbWNcU4kiz94uBCQZm1bx+kdEMTclhBo5UYOj2NaRcXfOvMOcE3QwiRE1C3dy/V73WS5VUpH/cYcsxe9OueYHeDCZ1ew6W/noAj8b/ng/5/ip1vwSc/gZAXkCJpuIVnwspHwGCD5p6obJ0JbtsAsSdfwVIgGMzUl3byyVM7CYcUdHoNE87NZcQZ6WhPsgy/xxlgw6patiypwdYTMrbwJ6NIH3KcjLG2cnj9Eug4BBo9LPgrjPrBcasd92PPe7DrbahaB8GewmJzHobJt/e2gvhv43UF2bW8lp3Lawn3lK432/X4ukMgQUpeNI3lfW6V+AwbZ982AttxysAL/vsIIXICDu3aQ9sHXaT5VCom/J5gxXRKyycBMP7sbCack3uCLQxyOirhtYuh/SjVSyHSZ+GSV8Hs+J8elkDw/3ecrV6WvriPpopIBkfm0FimXlSAI9F8TBeEoqjsWFrDpkWVyD1BpJlD45h/67CTy/bzdsArC6Gppxx5XAGMuASm3gm6o1iFW0uhvRy2/BvKl/b/bsHfYNx/t0LnsWivd7Pq9VIaDx07lmPm1UMomph8XPeN4LtBCJETcGDHTjwfdJMUUHFGHWBDXR5+BfLHJTLnuhJx054McijS+rphO1T11CtIGwsjL4+8iL6j2ZBA8P86clhh75p6vnrvUK+wgMjMPjknmqScKJJzozm4pZldy+sIBsIo4chr3B5rYvgZ6YyalXHcwnYD8HbAsodg2ytwRJl8UsdA6mhw1kFXTeS/hy0fh0kbCyMuheJzIOr4va++C1pruulq8dJS5aK7I0BMigWdXkPxlFQsUf/lwH3BSSOEyAnYvXU76kceYoMqZX6Z/X6F6AQzl/56AvqTrK4oOAI5BNrvMFBWIBiEVO9pZ8Wr+/E4gydcVqORGH5GOpMW5qL7v7zDupvg03vgwCcnXnbstRGrSaywIAsG8k3G75PLf/p/jKCiYukpYFTf42OcflmhECHfFiFCBIL/OlnD4rjmkan4ukNs+riC2gOdOBLMuLsCdLf7kcMKJqueGVcUkTU0bkBjuG+FPRkuey3SF+rg4kjciKcNnDVgjIbCuTDhZojOgKiUE29PIDgJBqUQCSky+h7rY0iF6DjTf60EuEAgEPy3kCQJS5SB06/8H6e/z/p15J9A8D9gUAZDBBUVXY9DSgVyRieInHCBQCAQCE4Bg1OIhOVeIaLAMasZCgQCgUAg+G4ZlEIkfEQkuqJCYta3b6QkEAgEAoHg2zMohUhI7hMiZqvu/xZlLhAIBAKB4FszKIXIkV3q7Q6RZy4QCAQCwaliUAqRsBwJEJEBk00IEYFAIBAIThWDUojYwxGTiCyB/jhdLgUCgUAgEHy3DEohkidHOjdKioreMCgvgUAgEAgE3wsG5Sis9gSrKiqimqpAIBAIBKeQQSlEOCxEAJ1RCBGBQCAQCE4Vg1KIHO5UqahgMAkhIhAIBALBqWJQChFtTBwQKe8uaogIBAKBQHDqGJxCxB5pSawAeuGaEQgEAoHglDEohYjak76rqKAXrhmBQCAQCE4Zg1KIyHE6vvK52euXhWtGIBAIBIJTyKAUIllDcvGEDLSFVSSNdKoPRyAQCASCQcugFCIGgwENPQJECBGBQCAQCE4Zg1KIqIqK2vP/wiIiEAgEAsGpY1AKERS193+FEBEIBAKB4NQxKIWIeoQQEa4ZgUAgEAhOHYNSiKAKi4hAIBAIBN8HBqcQkUWMiEAgEAgE3wcGpRDp75o5dcchEAgEAsFgZ3AOw0foEGEREQgEAoHg1DEohYiqqL1hIhJCiAgEAoFAcKr4zoRIVVUVN9xwAzk5OZjNZvLy8njggQcIBoPf1S5PHvlIk8ipOwyBQCAQCAY7uu9qwwcOHEBRFJ599lny8/PZs2cPN910Ex6Ph8cee+y72u3JcWQdESFEBAKBQCA4ZXxnQmTevHnMmzev9+/c3FxKS0t5+umnT7kQUVX1yDARgUAgEAgEp4jvTIgcDafTSWxs7DG/DwQCBAKB3r9dLtd3cyD9LCLCJCIQCAQCwanifxaseujQIZ588kluvfXWYy7zxz/+kejo6N5/GRkZ38mxqLKwhwgEAoFA8H3gGwuRBx98EEmSjvtvy5Yt/dZpaGhg3rx5XHzxxdx4443H3PYvfvELnE5n77/a2tpvfkYng3pEBq8wiAgEAoFAcMr4xq6Z22+/ncsuu+y4y2RnZ/f+f0NDA2eccQaTJ0/mueeeO+56RqMRo9H4TQ/pmyOCVQUCgUAg+F7wjYVIfHw88fHxJ7VsfX09Z5xxBmPHjuXFF19Eo/l+lC3pV1lVmEQEAoFAIDhlfGfBqg0NDZx++ulkZmby2GOP0dra2vtdcnLyd7Xbk0NYRAQCgUAg+F7wnQmRL7/8kvLycsrLy0lPT+/3naqe2mBRVRHpuwKBQCAQfB/4znwl1157baRex1H+nXIUUVlVIBAIBILvA9+PoI3/MUfGiIheMwKBQCAQnDoGpRAx5TuQzD1eKaFDBAKBQCA4ZQxKISJp+05bBKsKBAKBQHDqGJRCRCAQCAQCwfeDQStEDsfMil4zAoFAIBCcOgatEOH7kL0jEAgEAsEgZ9AKEdFrRiAQCASCU8+gFSL0umZO7WEIBAKBQDCYGbRC5MhKIgKBQCAQCE4Ng1aIHI4RERYRgUAgEAhOHYNYiJzqAxAIBAKBQDBohYgIVhUIBAKB4NQzaIUIoo6IQCAQCASnnEErRFThmxEIBAKB4JQzaIWISN8VCAQCgeDUM+iFiAgSEQgEAoHg1DFohchhHSIsIgKBQCAQnDoGrRDp63p3ag9DIBAIBILBzKAVIiJUVSAQCASCU8+gFSIifVcgEAgEglPP4BUiAoFAIBAITjmDUoio6hEt74RBRCAQCASCU8agFCL9AkSEEBEIBAKB4JQxKIVIfx0ilIhAIBAIBKeKQSlEOMI1I3SIQCAQCASnjkEpRETqrkAgEAgE3w8GpRA5UomIYFWBQCAQCE4dg16ICCUiEAgEAsGpY1AKEfUIJSJkiEAgEAgEp45BKURE+q5AIBAIBN8PBqUQEcGqAoFAIBB8PxiUQqR/sKowiQgEAoFAcKoYlEJEFXVEBAKBQCD4XjAohciRCB0iEAgEAsGpY3AKERGsKhAIBALB94JBKURErxmBQCAQCL4fDEohInrNCAQCgUDw/WBQChFVuGYEAoFAIPheMCiFyJEIHSIQCAQCwaljcAoR0WtGIBAIBILvBYNSiIheMwKBQCAQfD8YlEJEpO8KBAKBQPD9YFAKEVWUeBcIBAKB4HvBoBQiAoFAIBAIvh8MSiHS22tGGEMEAoFAIDilDEohchihQwQCgUAgOLUMTiFyOEZExIcIBAKBQHBKGZRCRHhmBAKBQCD4fjAohUj//F2BQCAQCASnikEqRHoQJhGBQCAQCE4pg1KI9NYREUJEIBAIBIJTyqAUIoeRhBIRCAQCgeCUMiiFiKgjIhAIBALB94NBKUQQOkQgEAgEgu8Fg1OIHEYoEYFAIBAITimDUoiooqCZQCAQCATfCwalEDnsmxEyRCAQCASCU8ugFCIifVcgEAgEgu8Hg1KIiGBVgUAgEAi+HwxOIXIYESMiEAgEAsEpZVAKkcN1RIQOEQgEAoHg1DIohYhAIBAIBILvB4NSiIhgVYFAIBAIvh8MSiHSF6wqlIhAIBAIBKeSQSlEVJE2IxAIBALB94JBKUR6dYgQIgKBQCAQnFIGpxARCAQCgUDwveB/IkQCgQCjRo1C+v/au/+Yquo/juOvyw8voHi/KcMrgvxobVZoGZT9YNmvqQtrra2lw19ra6OFQW75I9t0DYM/Wmu2suWaa7OGa5KzVk0so5woxY9CWVmLlFS0H8ilWZjy/v7RPHXDCOVezrXzfGz3D875cO/nvC7Ka+eeD8fnU2tr60i85KC41wwAALFhRIrI8uXLlZGRMRIvNUTcawYAgFgQ9SLy3nvvaceOHXr22Wej/VJDxvJdAABiQ0I0n/z48eN6+OGHtW3bNqWkpPzr+L6+PvX19Tlfh0Kh6EyMRTMAAMSEqJ0RMTMtWbJEpaWlKiwsHNL3VFVVKRAIOI+srKxoTe8PXCMCAICrLriIrF27Vj6fb9DHZ599phdeeEGhUEirVq0a8nOvWrVKPT09zqOzs/NCpzck3GsGAIDYcMEfzZSVlWnevHmDjsnJyVFlZaX27t0rv98ftq+wsFAlJSV67bXXBnyf3+8fMB4AAPx3XXARSUtLU1pa2r+OW79+vSorK52vjx49qtmzZ2vLli2aMWPGhb5sRHGxKgAAsSFqF6tOnjw57OsxY8ZIki6//HJlZmZG62WHhnvNAAAQEzz5l1W51wwAALEhqst3/yonJ8e5SNR13GsGAICY4MkzIgAAIDZ4sohwrxkAAGKDJ4vIuSZCDQEAwF2eLCLOlSo0EQAAXOXJIvLnxao0EQAA3OTNIqIYWb0DAIDHebKIGMt3AQCICZ4sIpwQAQAgNniyiPx5sSqnRAAAcJMni4izfJceAgCAqzxZRPhkBgCA2ODJIsK9ZgAAiA2eLiL8RTMAANzlySJizikRd+cBAIDXebKI8NEMAACxIcHtCbhhbFqyCuZkKyXgd3sqAAB4mieLyP8mpOjG+y53exoAAHieNz+aAQAAMYEiAgAAXEMRAQAArqGIAAAA11BEAACAaygiAADANRQRAADgGooIAABwDUUEAAC4hiICAABcQxEBAACuoYgAAADXUEQAAIBrYvruu2YmSQqFQi7PBAAADNW539vnfo8PJqaLSG9vryQpKyvL5ZkAAIAL1dvbq0AgMOgYnw2lrrikv79fR48eVWpqqnw+X0SfOxQKKSsrS52dnRo7dmxEnxvkG23kG13kG13kG31uZ2xm6u3tVUZGhuLiBr8KJKbPiMTFxSkzMzOqrzF27Fj+IUQR+UYX+UYX+UYX+Uafmxn/25mQc7hYFQAAuIYiAgAAXOPZIuL3+7VmzRr5/X63p/KfRL7RRb7RRb7RRb7RdyllHNMXqwIAgP82z54RAQAA7qOIAAAA11BEAACAaygiAADANZ4sIi+99JJyc3OVlJSkgoICffLJJ25P6ZJQVVWl66+/XqmpqUpPT9d9992nr776KmyMmWnt2rXKyMhQcnKybrvtNh04cCBsTF9fn5YuXaq0tDSNHj1a9957r77//vuRPJSYV1VVJZ/Pp4qKCmcb2Q7fkSNHtGDBAo0fP14pKSm69tpr1dTU5Own44t35swZPfXUU8rNzVVycrLy8vL09NNPq7+/3xlDvkP38ccf65577lFGRoZ8Pp+2bdsWtj9SWXZ3d2vhwoUKBAIKBAJauHChTp48GeWj+xvzmJqaGktMTLSNGzdae3u7lZeX2+jRo+3QoUNuTy3mzZ492zZt2mT79++31tZWKy4utsmTJ9svv/zijKmurrbU1FTbunWrtbW12YMPPmgTJ060UCjkjCktLbVJkyZZXV2dNTc32+23327XXHONnTlzxo3DijmNjY2Wk5Nj06ZNs/Lycmc72Q7Pzz//bNnZ2bZkyRLbt2+fdXR02M6dO+2bb75xxpDxxausrLTx48fbO++8Yx0dHfbmm2/amDFj7Pnnn3fGkO/Qvfvuu7Z69WrbunWrSbK33norbH+kspwzZ47l5+fbnj17bM+ePZafn29z584dqcM0MzPPFZEbbrjBSktLw7ZNmTLFVq5c6dKMLl0nTpwwSVZfX29mZv39/RYMBq26utoZ89tvv1kgELCXX37ZzMxOnjxpiYmJVlNT44w5cuSIxcXF2fvvvz+yBxCDent77YorrrC6ujqbOXOmU0TIdvhWrFhhRUVF/7ifjIenuLjYHnroobBt999/vy1YsMDMyHc4/l5EIpVle3u7SbK9e/c6YxoaGkySffnll1E+qj956qOZ06dPq6mpSbNmzQrbPmvWLO3Zs8elWV26enp6JEnjxo2TJHV0dKirqyssX7/fr5kzZzr5NjU16ffffw8bk5GRofz8fN4DSY8++qiKi4t11113hW0n2+Hbvn27CgsL9cADDyg9PV3Tp0/Xxo0bnf1kPDxFRUX64IMPdPDgQUnS559/rt27d+vuu++WRL6RFKksGxoaFAgENGPGDGfMjTfeqEAgMKJ5x/RN7yLtxx9/1NmzZzVhwoSw7RMmTFBXV5dLs7o0mZmWLVumoqIi5efnS5KT4fnyPXTokDNm1KhRuuyyywaM8fp7UFNTo+bmZn366acD9pHt8H377bfasGGDli1bpieffFKNjY167LHH5Pf7tWjRIjIephUrVqinp0dTpkxRfHy8zp49q3Xr1mn+/PmS+BmOpEhl2dXVpfT09AHPn56ePqJ5e6qInOPz+cK+NrMB2zC4srIyffHFF9q9e/eAfReTr9ffg87OTpWXl2vHjh1KSkr6x3Fke/H6+/tVWFioZ555RpI0ffp0HThwQBs2bNCiRYuccWR8cbZs2aLNmzfrjTfe0NVXX63W1lZVVFQoIyNDixcvdsaRb+REIsvzjR/pvD310UxaWpri4+MHNL0TJ04MaJb4Z0uXLtX27du1a9cuZWZmOtuDwaAkDZpvMBjU6dOn1d3d/Y9jvKipqUknTpxQQUGBEhISlJCQoPr6eq1fv14JCQlONmR78SZOnKirrroqbNuVV16pw4cPS+Lnd7ieeOIJrVy5UvPmzdPUqVO1cOFCPf7446qqqpJEvpEUqSyDwaCOHz8+4Pl/+OGHEc3bU0Vk1KhRKigoUF1dXdj2uro63XzzzS7N6tJhZiorK1Ntba0+/PBD5ebmhu3Pzc1VMBgMy/f06dOqr6938i0oKFBiYmLYmGPHjmn//v2efg/uvPNOtbW1qbW11XkUFhaqpKREra2tysvLI9thuuWWWwYsNz948KCys7Ml8fM7XKdOnVJcXPivlPj4eGf5LvlGTqSyvOmmm9TT06PGxkZnzL59+9TT0zOyeY/YZbEx4tzy3VdffdXa29utoqLCRo8ebd99953bU4t5jzzyiAUCAfvoo4/s2LFjzuPUqVPOmOrqagsEAlZbW2ttbW02f/788y4py8zMtJ07d1pzc7Pdcccdnlye92/+umrGjGyHq7Gx0RISEmzdunX29ddf2+uvv24pKSm2efNmZwwZX7zFixfbpEmTnOW7tbW1lpaWZsuXL3fGkO/Q9fb2WktLi7W0tJgke+6556ylpcX5UxORynLOnDk2bdo0a2hosIaGBps6dSrLd0fCiy++aNnZ2TZq1Ci77rrrnOWnGJyk8z42bdrkjOnv77c1a9ZYMBg0v99vt956q7W1tYU9z6+//mplZWU2btw4S05Otrlz59rhw4dH+Ghi39+LCNkO39tvv235+fnm9/ttypQp9sorr4TtJ+OLFwqFrLy83CZPnmxJSUmWl5dnq1evtr6+PmcM+Q7drl27zvv/7eLFi80scln+9NNPVlJSYqmpqZaammolJSXW3d09Qkf5B5+Z2cidfwEAAPiTp64RAQAAsYUiAgAAXEMRAQAArqGIAAAA11BEAACAaygiAADANRQRAADgGooIAABwDUUEAAC4hiICAABcQxEBAACuoYgAAADX/B9tZ5REXYpuzgAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "def plot_wpe(num_columns = 768):\n",
    "    for i in range(num_columns):\n",
    "        plt.plot(sd_hf[\"transformer.wpe.weight\"][:, i].detach().numpy())\n",
    "    plt.show()\n",
    "\n",
    "\n",
    "plot_wpe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[5], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m pipeline\n\u001b[1;32m      2\u001b[0m generator \u001b[38;5;241m=\u001b[39m pipeline(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtext-generation\u001b[39m\u001b[38;5;124m'\u001b[39m, model\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mgpt2\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m      3\u001b[0m generator(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mHello, I\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mm a language model,\u001b[39m\u001b[38;5;124m\"\u001b[39m, max_length\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m30\u001b[39m, num_return_sequences\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m3\u001b[39m)\n",
      "File \u001b[0;32m<frozen importlib._bootstrap>:1229\u001b[0m, in \u001b[0;36m_handle_fromlist\u001b[0;34m(module, fromlist, import_, recursive)\u001b[0m\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/transformers/utils/import_utils.py:1525\u001b[0m, in \u001b[0;36m_LazyModule.__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m   1523\u001b[0m     value \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_module(name)\n\u001b[1;32m   1524\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m name \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_class_to_module\u001b[38;5;241m.\u001b[39mkeys():\n\u001b[0;32m-> 1525\u001b[0m     module \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_module\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_class_to_module\u001b[49m\u001b[43m[\u001b[49m\u001b[43mname\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1526\u001b[0m     value \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mgetattr\u001b[39m(module, name)\n\u001b[1;32m   1527\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/transformers/utils/import_utils.py:1535\u001b[0m, in \u001b[0;36m_LazyModule._get_module\u001b[0;34m(self, module_name)\u001b[0m\n\u001b[1;32m   1533\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_get_module\u001b[39m(\u001b[38;5;28mself\u001b[39m, module_name: \u001b[38;5;28mstr\u001b[39m):\n\u001b[1;32m   1534\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1535\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mimportlib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mimport_module\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mmodule_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;18;43m__name__\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1536\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m   1537\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\n\u001b[1;32m   1538\u001b[0m             \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFailed to import \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mmodule_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m because of the following error (look up to see its\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1539\u001b[0m             \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m traceback):\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1540\u001b[0m         ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/importlib/__init__.py:126\u001b[0m, in \u001b[0;36mimport_module\u001b[0;34m(name, package)\u001b[0m\n\u001b[1;32m    124\u001b[0m             \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[1;32m    125\u001b[0m         level \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m--> 126\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_bootstrap\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_gcd_import\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[43m[\u001b[49m\u001b[43mlevel\u001b[49m\u001b[43m:\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpackage\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlevel\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/transformers/pipelines/__init__.py:26\u001b[0m\n\u001b[1;32m     24\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdynamic_module_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m get_class_from_dynamic_module\n\u001b[1;32m     25\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfeature_extraction_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m PreTrainedFeatureExtractor\n\u001b[0;32m---> 26\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mimage_processing_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m BaseImageProcessor\n\u001b[1;32m     27\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodels\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mauto\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mconfiguration_auto\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m AutoConfig\n\u001b[1;32m     28\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodels\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mauto\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfeature_extraction_auto\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m FEATURE_EXTRACTOR_MAPPING, AutoFeatureExtractor\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/transformers/image_processing_utils.py:28\u001b[0m\n\u001b[1;32m     26\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdynamic_module_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m custom_object_save\n\u001b[1;32m     27\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfeature_extraction_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m BatchFeature \u001b[38;5;28;01mas\u001b[39;00m BaseBatchFeature\n\u001b[0;32m---> 28\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mimage_transforms\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m center_crop, normalize, rescale\n\u001b[1;32m     29\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mimage_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m ChannelDimension\n\u001b[1;32m     30\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[1;32m     31\u001b[0m     IMAGE_PROCESSOR_NAME,\n\u001b[1;32m     32\u001b[0m     PushToHubMixin,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     40\u001b[0m     logging,\n\u001b[1;32m     41\u001b[0m )\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/transformers/image_transforms.py:47\u001b[0m\n\u001b[1;32m     44\u001b[0m     \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorch\u001b[39;00m\n\u001b[1;32m     46\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_tf_available():\n\u001b[0;32m---> 47\u001b[0m     \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mtf\u001b[39;00m\n\u001b[1;32m     49\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_flax_available():\n\u001b[1;32m     50\u001b[0m     \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mjax\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mnumpy\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mjnp\u001b[39;00m\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/tensorflow/__init__.py:37\u001b[0m\n\u001b[1;32m     34\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01msys\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01m_sys\u001b[39;00m\n\u001b[1;32m     35\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtyping\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01m_typing\u001b[39;00m\n\u001b[0;32m---> 37\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mtools\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m module_util \u001b[38;5;28;01mas\u001b[39;00m _module_util\n\u001b[1;32m     38\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutil\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mlazy_loader\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m LazyLoader \u001b[38;5;28;01mas\u001b[39;00m _LazyLoader\n\u001b[1;32m     40\u001b[0m \u001b[38;5;66;03m# Make sure code inside the TensorFlow codebase can use tf2.enabled() at import.\u001b[39;00m\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/tensorflow/python/__init__.py:45\u001b[0m\n\u001b[1;32m     43\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m distribute\n\u001b[1;32m     44\u001b[0m \u001b[38;5;66;03m# from tensorflow.python import keras\u001b[39;00m\n\u001b[0;32m---> 45\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfeature_column\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m feature_column_lib \u001b[38;5;28;01mas\u001b[39;00m feature_column\n\u001b[1;32m     46\u001b[0m \u001b[38;5;66;03m# from tensorflow.python.layers import layers\u001b[39;00m\n\u001b[1;32m     47\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodule\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m module\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/tensorflow/python/feature_column/feature_column_lib.py:18\u001b[0m\n\u001b[1;32m     15\u001b[0m \u001b[38;5;124;03m\"\"\"FeatureColumns: tools for ingesting and representing features.\"\"\"\u001b[39;00m\n\u001b[1;32m     17\u001b[0m \u001b[38;5;66;03m# pylint: disable=unused-import,line-too-long,wildcard-import,g-bad-import-order\u001b[39;00m\n\u001b[0;32m---> 18\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfeature_column\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfeature_column\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;241m*\u001b[39m\n\u001b[1;32m     19\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfeature_column\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfeature_column_v2\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;241m*\u001b[39m\n\u001b[1;32m     20\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfeature_column\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01msequence_feature_column\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;241m*\u001b[39m\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/tensorflow/python/feature_column/feature_column.py:143\u001b[0m\n\u001b[1;32m    141\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m sparse_tensor \u001b[38;5;28;01mas\u001b[39;00m sparse_tensor_lib\n\u001b[1;32m    142\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m tensor_shape\n\u001b[0;32m--> 143\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mlayers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m base\n\u001b[1;32m    144\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mops\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m array_ops\n\u001b[1;32m    145\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mops\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m check_ops\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/tensorflow/python/layers/base.py:16\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;66;03m# Copyright 2015 The TensorFlow Authors. All Rights Reserved.\u001b[39;00m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;66;03m#\u001b[39;00m\n\u001b[1;32m      3\u001b[0m \u001b[38;5;66;03m# Licensed under the Apache License, Version 2.0 (the \"License\");\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     13\u001b[0m \u001b[38;5;66;03m# limitations under the License.\u001b[39;00m\n\u001b[1;32m     14\u001b[0m \u001b[38;5;66;03m# =============================================================================\u001b[39;00m\n\u001b[1;32m     15\u001b[0m \u001b[38;5;124;03m\"\"\"Contains the base Layer class, from which all layers inherit.\"\"\"\u001b[39;00m\n\u001b[0;32m---> 16\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mlegacy_tf_layers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m base\n\u001b[1;32m     18\u001b[0m InputSpec \u001b[38;5;241m=\u001b[39m base\u001b[38;5;241m.\u001b[39mInputSpec\n\u001b[1;32m     20\u001b[0m keras_style_scope \u001b[38;5;241m=\u001b[39m base\u001b[38;5;241m.\u001b[39mkeras_style_scope\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/tensorflow/python/keras/__init__.py:25\u001b[0m\n\u001b[1;32m     22\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m distribute\n\u001b[1;32m     24\u001b[0m \u001b[38;5;66;03m# See b/110718070#comment18 for more details about this import.\u001b[39;00m\n\u001b[0;32m---> 25\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m models\n\u001b[1;32m     27\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mengine\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01minput_layer\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Input\n\u001b[1;32m     28\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mengine\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01msequential\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Sequential\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/tensorflow/python/keras/models.py:20\u001b[0m\n\u001b[1;32m     18\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m ops\n\u001b[1;32m     19\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m backend\n\u001b[0;32m---> 20\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m metrics \u001b[38;5;28;01mas\u001b[39;00m metrics_module\n\u001b[1;32m     21\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m optimizer_v1\n\u001b[1;32m     22\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mengine\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m functional\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/tensorflow/python/keras/metrics.py:34\u001b[0m\n\u001b[1;32m     32\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m ops\n\u001b[1;32m     33\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m tensor_shape\n\u001b[0;32m---> 34\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m activations\n\u001b[1;32m     35\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m backend\n\u001b[1;32m     36\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mengine\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m base_layer\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/tensorflow/python/keras/activations.py:18\u001b[0m\n\u001b[1;32m     15\u001b[0m \u001b[38;5;124;03m\"\"\"Built-in activation functions.\"\"\"\u001b[39;00m\n\u001b[1;32m     17\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m backend\n\u001b[0;32m---> 18\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mlayers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m advanced_activations\n\u001b[1;32m     19\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mgeneric_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m deserialize_keras_object\n\u001b[1;32m     20\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mgeneric_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m serialize_keras_object\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/tensorflow/python/keras/layers/__init__.py:22\u001b[0m\n\u001b[1;32m     17\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m tf2\n\u001b[1;32m     19\u001b[0m \u001b[38;5;66;03m# Generic layers.\u001b[39;00m\n\u001b[1;32m     20\u001b[0m \u001b[38;5;66;03m# pylint: disable=g-bad-import-order\u001b[39;00m\n\u001b[1;32m     21\u001b[0m \u001b[38;5;66;03m# pylint: disable=g-import-not-at-top\u001b[39;00m\n\u001b[0;32m---> 22\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mengine\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01minput_layer\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Input\n\u001b[1;32m     23\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mengine\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01minput_layer\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m InputLayer\n\u001b[1;32m     24\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mengine\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01minput_spec\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m InputSpec\n",
      "File \u001b[0;32m~/miniconda3/envs/general_ml/lib/python3.11/site-packages/tensorflow/python/keras/engine/input_layer.py:24\u001b[0m\n\u001b[1;32m     22\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m backend\n\u001b[1;32m     23\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdistribute\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m distributed_training_utils\n\u001b[0;32m---> 24\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mengine\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m base_layer\n\u001b[1;32m     25\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mengine\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m keras_tensor\n\u001b[1;32m     26\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mengine\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m node \u001b[38;5;28;01mas\u001b[39;00m node_module\n",
      "File \u001b[0;32m<frozen importlib._bootstrap>:1176\u001b[0m, in \u001b[0;36m_find_and_load\u001b[0;34m(name, import_)\u001b[0m\n",
      "File \u001b[0;32m<frozen importlib._bootstrap>:1147\u001b[0m, in \u001b[0;36m_find_and_load_unlocked\u001b[0;34m(name, import_)\u001b[0m\n",
      "File \u001b[0;32m<frozen importlib._bootstrap>:690\u001b[0m, in \u001b[0;36m_load_unlocked\u001b[0;34m(spec)\u001b[0m\n",
      "File \u001b[0;32m<frozen importlib._bootstrap_external>:936\u001b[0m, in \u001b[0;36mexec_module\u001b[0;34m(self, module)\u001b[0m\n",
      "File \u001b[0;32m<frozen importlib._bootstrap_external>:1069\u001b[0m, in \u001b[0;36mget_code\u001b[0;34m(self, fullname)\u001b[0m\n",
      "File \u001b[0;32m<frozen importlib._bootstrap_external>:729\u001b[0m, in \u001b[0;36m_compile_bytecode\u001b[0;34m(data, name, bytecode_path, source_path)\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "from transformers import pipeline\n",
    "generator = pipeline('text-generation', model=\"gpt2\")\n",
    "generator(\"Hello, I'm a language model,\", max_length=30, num_return_sequences=3)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "First Citizen:\n",
      "Before we proceed any further, hear me speak.\n",
      "\n",
      "All:\n",
      "Speak, speak.\n",
      "\n",
      "First Citizen:\n",
      "You\n"
     ]
    }
   ],
   "source": [
    "with open(\"/Users/mattia/Desktop/zero_to_hero/tinyshakespeare.txt\", \"r\") as f:\n",
    "    text = f.read()\n",
    "\n",
    "print(text[:100])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[5962, 22307, 25, 198, 8421, 356, 5120, 597, 2252, 11, 3285, 502, 2740, 13, 198, 198, 3237, 25, 198, 5248, 461, 11, 2740, 13, 198, 198, 5962, 22307, 25, 198, 1639, 389, 477, 12939, 2138, 284, 4656, 621, 284, 1145, 680, 30, 198, 198, 3237, 25, 198, 4965, 5634, 13, 12939, 13, 198, 198, 5962, 22307, 25, 198, 5962, 11, 345, 760, 327, 1872, 385, 1526, 28599, 318, 4039, 4472, 284, 262, 661, 13, 198, 198, 3237, 25, 198, 1135, 760, 470, 11, 356, 760, 470, 13, 198, 198, 5962, 22307, 25, 198, 5756, 514, 1494, 683, 11, 290, 356]\n",
      "First Citizen:\n",
      "Before we proceed any further, hear me speak.\n",
      "\n",
      "All:\n",
      "Speak, speak.\n",
      "\n",
      "First Citizen:\n",
      "You are all resolved rather to die than to famish?\n",
      "\n",
      "All:\n",
      "Resolved. resolved.\n",
      "\n",
      "First Citizen:\n",
      "First, you know Caius Marcius is chief enemy to the people.\n",
      "\n",
      "All:\n",
      "We know't, we know't.\n",
      "\n",
      "First Citizen:\n",
      "Let us kill him, and we\n"
     ]
    }
   ],
   "source": [
    "import tiktoken\n",
    "tokenizer = tiktoken.get_encoding(\"gpt2\")\n",
    "tokens = tokenizer.encode(text)\n",
    "print(tokens[:100])\n",
    "print(tokenizer.decode(tokens[:100]))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "True\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
    "print(device.type == \"cpu\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "Dataset.cleanup_cache_files() missing 1 required positional argument: 'self'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[5], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mdatasets\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[43mdatasets\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mDataset\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcleanup_cache_files\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m)\n",
      "\u001b[0;31mTypeError\u001b[0m: Dataset.cleanup_cache_files() missing 1 required positional argument: 'self'"
     ]
    }
   ],
   "source": [
    "import datasets\n",
    "print(datasets.Dataset.cleanup_cache_files())"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "general_ml",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.1.-1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}