{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "(api_quickstart)=\n",
    "# General API quickstart\n",
    "\n",
    ":::{post} May 31, 2022\n",
    ":tags: \n",
    ":category: beginner\n",
    ":author: Christian Luhmann\n",
    ":::"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/xian/anaconda3/envs/pymc-dev-py39/lib/python3.9/site-packages/pkg_resources/__init__.py:123: PkgResourcesDeprecationWarning: main is an invalid version and will not be supported in a future release\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "import arviz as az\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pymc as pm\n",
    "import pytensor.tensor as pt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "RANDOM_SEED = 8927\n",
    "rng = np.random.default_rng(RANDOM_SEED)\n",
    "az.style.use(\"arviz-darkgrid\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1. Model creation\n",
    "\n",
    "Models in PyMC are centered around the `Model` class. It has references to all random variables (RVs) and computes the model logp and its gradients. Usually, you would instantiate it as part of a `with` context:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "with pm.Model() as model:\n",
    "    # Model definition\n",
    "    pass"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We discuss RVs further below but let's create a simple model to explore the `Model` class."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "with pm.Model() as model:\n",
    "    mu = pm.Normal(\"mu\", mu=0, sigma=1)\n",
    "    obs = pm.Normal(\"obs\", mu=mu, sigma=1, observed=rng.standard_normal(100))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[mu ~ N(0, 1), obs ~ N(mu, 1)]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.basic_RVs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[mu ~ N(0, 1)]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.free_RVs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[obs ~ N(mu, 1)]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.observed_RVs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(-143.03962875)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.compile_logp()({\"mu\": 0})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It's worth highlighting the design choice we made with `logp`.  As you can see above, `logp` is being called with arguments, so it's a method of the model instance. More precisely, it puts together a function based on the current state of the model -- or on the state given as argument to `logp` (see example below).\n",
    "\n",
    "For diverse reasons, we assume that a `Model` instance isn't static. If you need to use `logp` in an inner loop and it needs to be static, simply use something like `logp = model.logp`. Here is an example below -- note the caching effect and the speed up:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "83 ms ± 7.1 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n",
      "18 µs ± 276 ns per loop (mean ± std. dev. of 7 runs, 100,000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit model.compile_logp()({\"mu\": 0.1})\n",
    "logp = model.compile_logp()\n",
    "%timeit logp({\"mu\": 0.1})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2. Probability Distributions\n",
    "\n",
    "Every probabilistic program consists of observed and unobserved Random Variables (RVs). Observed RVs are defined via likelihood distributions, while unobserved RVs are defined via prior distributions. In the PyMC module, the structure for probability distributions looks like this:\n",
    "\n",
    "{ref}`pymc:api_distributions`\n",
    "- {ref}`pymc:api_distributions_continuous`\n",
    "- {ref}`pymc:api_distributions_discrete`\n",
    "- {ref}`pymc:api_distributions_multivariate`\n",
    "- {ref}`pymc:api_distributions_mixture`\n",
    "- {ref}`pymc:api_distributions_rimeseries`\n",
    "- {ref}`pymc:api_distributions_censored`\n",
    "- {ref}`pymc:api_distributions_simulator`"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Unobserved Random Variables"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Every unobserved RV has the following calling signature: name (str), parameter keyword arguments. Thus, a normal prior can be defined in a model context like this:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "with pm.Model():\n",
    "    x = pm.Normal(\"x\", mu=0, sigma=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As with the model, we can evaluate its logp:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(-0.91893853)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pm.logp(x, 0).eval()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Observed Random Variables"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Observed RVs are defined just like unobserved RVs but require data to be passed into the `observed` keyword argument:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "with pm.Model():\n",
    "    obs = pm.Normal(\"x\", mu=0, sigma=1, observed=rng.standard_normal(100))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "`observed` supports lists, `numpy.ndarray` and `pytensor` data structures."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Deterministic transforms"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "PyMC allows you to freely do algebra with RVs in all kinds of ways:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "with pm.Model():\n",
    "    x = pm.Normal(\"x\", mu=0, sigma=1)\n",
    "    y = pm.Gamma(\"y\", alpha=1, beta=1)\n",
    "    plus_2 = x + 2\n",
    "    summed = x + y\n",
    "    squared = x**2\n",
    "    sined = pm.math.sin(x)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Though these transformations work seamlessly, their results are not stored automatically. Thus, if you want to keep track of a transformed variable, you have to use `pm.Deterministic`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "with pm.Model():\n",
    "    x = pm.Normal(\"x\", mu=0, sigma=1)\n",
    "    plus_2 = pm.Deterministic(\"x plus 2\", x + 2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Note that `plus_2` can be used in the identical way to above, we only tell PyMC to keep track of this RV for us."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Lists of RVs / higher-dimensional RVs\n",
    "\n",
    "Above we have seen how to create scalar RVs. In many models, we want multiple RVs. Users will sometimes try to create lists of RVs, like this:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "with pm.Model():\n",
    "    # bad:\n",
    "    x = [pm.Normal(f\"x_{i}\", mu=0, sigma=1) for i in range(10)]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This works, but it is slow and not recommended. Instead, we can use {ref}`coordinates <pymc:dimensionality>`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "coords = {\"cities\": [\"Santiago\", \"Mumbai\", \"Tokyo\"]}\n",
    "with pm.Model(coords=coords) as model:\n",
    "    # good:\n",
    "    x = pm.Normal(\"x\", mu=0, sigma=1, dims=\"cities\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "`x` is now a array of length 3 and each of the 3 variables within this array is associated with a label.  This will make it very easy to distinguish the 3 different variables when we go to look at results. We can index into this array or do linear algebra operations on it:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "with model:\n",
    "    y = x[0] * x[1]  # indexing is supported\n",
    "    x.dot(x.T)  # linear algebra is supported"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Initialize Random Variables\n",
    "\n",
    "Though PyMC automatically initializes models, it is sometimes helpful to define initial values for RVs. This can be done via the `initval` kwarg:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'x': array([0., 0., 0., 0., 0.])}"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "with pm.Model(coords={\"idx\": np.arange(5)}) as model:\n",
    "    x = pm.Normal(\"x\", mu=0, sigma=1, dims=\"idx\")\n",
    "\n",
    "model.initial_point()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'x': array([-0.36012097, -0.16168135,  1.07485641, -0.08855632, -0.03857412])}"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "with pm.Model(coords={\"idx\": np.arange(5)}) as model:\n",
    "    x = pm.Normal(\"x\", mu=0, sigma=1, dims=\"idx\", initval=rng.standard_normal(5))\n",
    "\n",
    "model.initial_point()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This technique is sometimes useful when trying to identify problems with model specification or initialization."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3. Inference\n",
    "\n",
    "Once we have defined our model, we have to perform inference to approximate the posterior distribution. PyMC supports two broad classes of inference: sampling and variational inference.\n",
    "\n",
    "### 3.1 Sampling\n",
    "\n",
    "The main entry point to MCMC sampling algorithms is via the `pm.sample()` function. By default, this function tries to auto-assign the right sampler(s).  `pm.sample()` returns an `arviz.InferenceData` object. `InferenceData` objects can easily be saved/loaded from a file and can carry additional (meta)data such as date/version and posterior predictive samples. Take a look at the {ref}`ArviZ Quickstart <arviz:quickstart>` to learn more."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Auto-assigning NUTS sampler...\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (2 chains in 2 jobs)\n",
      "NUTS: [mu]\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='6000' class='' max='6000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [6000/6000 00:03<00:00 Sampling 2 chains, 0 divergences]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 2 chains for 1_000 tune and 2_000 draw iterations (2_000 + 4_000 draws total) took 4 seconds.\n"
     ]
    }
   ],
   "source": [
    "with pm.Model() as model:\n",
    "    mu = pm.Normal(\"mu\", mu=0, sigma=1)\n",
    "    obs = pm.Normal(\"obs\", mu=mu, sigma=1, observed=rng.standard_normal(100))\n",
    "\n",
    "    idata = pm.sample(2000)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As you can see, with model that exclusively contains continuous variables, PyMC assigns the NUTS sampler, which is very efficient even for complex models. PyMC also runs initial tuning to find good starting parameters for the sampler. Here we draw 2000 samples from the posterior in each chain and allow the sampler to adjust its parameters in an additional 1500 iterations.\n",
    "\n",
    "If not set via the `chains` kwarg, the number of chains is determined from the number of available CPU cores."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Frozen({'chain': 2, 'draw': 2000})"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idata.posterior.dims"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The tuning samples are discarded by default. With `discard_tuned_samples=False` they can be kept and end up in a separate group within the `InferenceData` object (i.e., `idata.warmup_posterior`).\n",
    "\n",
    "You can control how the chains are run in parallel using the `chains` and `cores` kwargs:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Auto-assigning NUTS sampler...\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (6 chains in 4 jobs)\n",
      "NUTS: [mu]\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='12000' class='' max='12000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [12000/12000 00:07<00:00 Sampling 6 chains, 0 divergences]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 6 chains for 1_000 tune and 1_000 draw iterations (6_000 + 6_000 draws total) took 7 seconds.\n"
     ]
    }
   ],
   "source": [
    "with pm.Model() as model:\n",
    "    mu = pm.Normal(\"mu\", mu=0, sigma=1)\n",
    "    obs = pm.Normal(\"obs\", mu=mu, sigma=1, observed=rng.standard_normal(100))\n",
    "\n",
    "    idata = pm.sample(cores=4, chains=6)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(6, 1000)"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idata.posterior[\"mu\"].shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1000,)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# get values of a single chain\n",
    "idata.posterior[\"mu\"].sel(chain=2).shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3.2 Analyze sampling results\n",
    "\n",
    "The most common used plot to analyze sampling results is the so-called trace-plot:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Auto-assigning NUTS sampler...\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (2 chains in 2 jobs)\n",
      "NUTS: [mu, sd]\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='4000' class='' max='4000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [4000/4000 00:03<00:00 Sampling 2 chains, 0 divergences]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 2 chains for 1_000 tune and 1_000 draw iterations (2_000 + 2_000 draws total) took 4 seconds.\n"
     ]
    }
   ],
   "source": [
    "with pm.Model() as model:\n",
    "    mu = pm.Normal(\"mu\", mu=0, sigma=1)\n",
    "    sd = pm.HalfNormal(\"sd\", sigma=1)\n",
    "    obs = pm.Normal(\"obs\", mu=mu, sigma=sd, observed=rng.standard_normal(100))\n",
    "\n",
    "    idata = pm.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA2gAAAEoCAYAAAAt0dJ4AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOy9d5wlyVUlfOL5V8+U9953V/se751GEvDtwi6SgAV5DwKtEBISCATSCrfYFRIjg9AiBAgWJ4QEjEbje6Znpn157719tp7L+P44GS9f2a6eme6umYnz+/VM1at8mZGREZH3xL33XCGlhIaGhoaGhoaGhoaGhsb1h+16N0BDQ0NDQ0NDQ0NDQ0OD0ARNQ0NDQ0NDQ0NDQ0Njn0ATNA0NDQ0NDQ0NDQ0NjX0CTdA0NDQ0NDQ0NDQ0NDT2CTRB09DQ0NDQ0NDQ0NDQ2CfQBE1DQ0NDQ0NDQ0NDQ2OfQBM0DQ0NDQ0NDQ0NDQ2NfQJN0DQ0NDQ0NDQ0NDQ0NPYJNEHT0NDQ0NDQ0NDQ0NDYJ3Bc7wZoaLyS0N7eLgF8EMCnALgAvM/8/x8AsAN4V19f37/nHFva19e3aP7eCeBDfX19j12HpmtoaGhoaLxo6Pefhsa1gyZoGhpXjtsAtAB4E4AvAfgX8/c3A/g8gNbr1zQNDQ0NDY2rBv3+09C4BtAhjhoaV47f7evrWwfwDwDKAPxRX19fwvy9pb293XtdW6ehoaGhoXF1oN9/GhrXAJqgaWhcOeYBoK+vL27+vrDpd9/1aJSGhoaGhsZVhn7/aWhcA2iCpqFx9RADkJfze9n1aoiGhoaGhsY1hH7/aWi8BOgcNA2Nq4dLAH6ivb39DwH8LIDC69weDQ0NDQ2NawH9/tPQeAnQHjQNjauHj4AqV4sASgH0Xd/maGhoaGhoXBPo95+GxkuAkFJe7zZoaGhoaGhoaGhoaGhoQHvQNDQ0NDQ0NDQ0NDQ09g00QdPQ0NDQ0NDQ0NDQ0Ngn0ARNQ0NDQ0NDQ0NDQ0Njn0ATNA0NDQ0NDQ0NDQ0NjX0CTdA0NDQ0NDQ0NDQ0NDT2CXatg7aysvKiJR7z8vIQi8Ve7NdfsXit3jfw2r331+p9A6/de3+t3jdwde69sLBQvKwnfIlIJBLytfp8X268lufKywndjy8PdD++PND9+PJgt3ffVfOg2e32q3XqfY3X6n0Dr917f63eN/DavffX6n0Dr417fy3c47WC7suXB7ofXx7ofnx5oPvx6kOHOGpoaGhoaGhoaGhoaOwTaIKmoaGhoaGhoaGhoaGxT7BrDpqGxqsRobDE2bNA/4DEyAiwsgoIAQT8QHEx0NAgcPwY0NoC2Gz7KjVGQ0NDQ+NVhukZidAacOCAft9oaGgQmqBpvCZgGBJPPg18+18lzp0DWlqAgweAW28VKC7iMeEwML8AdHdLfOObJG133ynxhtcLHDkMCKFfnhoaGhoaLy9GRoBYHDhw4Hq3RENDY79AEzSNVz2eeVbiS1+RiMaAt7xJ4JMfB0pKdiNbAoYh0T8AfP8RiV/7tEQgALzlzcAbHgTcbk3UNDQ0NDQ0NDQ0rg40QdN4VSAUljAyQEGBwNlzElVVgMMBfPZzEsPDwPvfK/DGNwAOx97Ilc0mcKAdONAu8IH3STzxFPC335L48leAN78JePOPA3l5mqhpaGhoaLw06OAMDQ2NzdAiIRqvWHT3SHzr71mq76++KfGv/8bPn3te4uFHJN7+TomRUeB3fwe4527gLf9DIp2WWFmRuHBx7yX+HA6B++8V+PKf2fBb/0vgwkWJN/+kxDf/RmJ9/UWXCtTQ0NDQ0NAETUNDYws0QdN4RSEUkviFjxhIpSR8eUCRmT/2wfcLvPWnBTIZCacT+OZfAx//mMC3/9GGjgM2eL3A//4dAYdDYGIS+Pf/JLF69DGJp07tnWQdPSLwh/+bRO2ZZyV+6mck/vU7SRiGJmoaGhoaGi8CmqBpvAaxsCARiWjbaSdogqbxisDX/1Li+RdULpiAEEB9vcCDD/DNJoRALCbxy7/CcMSvPCRwz13WW8/hEGhu4u9Hjwj88i9x6Pt8QJ6Xx3zutw0MDu1tsTh2VODzfyzw0Y8IfPnPE3jfB6/MK6ehoaGhoQG8uvjZyqrcdxuWhiHx6GP7r12vdZy/CAwNX+9W7F9ogqaxbxEOSzz+BBfUQx1AVSWJ2J23iy25ZKurEh/+qITNBnzpCwK1NXt75d18k8DJEzz2nrsFqiqB2VmJD33YuOxiLoTAnXcI/OPf+fH6BwU+8asSn/p1A1PT+iWgoaGhobE3vJpCHF84A0xPX+9WbEQmA6QzQDp9vVuioZBI0E5yaCWMHaEJmsa+g5QSmYxENAo89gR3vW66UaC6evu32OysxM/+vERjA/BbnxXweF7c2+7OOwTy8gQKCoD3vEvAZhP41t9LfP0vZbZd28HpFHjLmwS+9U2B0lLgHe+S+MKfGQiHNVHT0NC4+kintXfglYxXE0EDAMO43i3Q2O+YnLreLdj/0ARNY9/h81+Q+Od/ASoqBD79KduuxaJHRiU++CGJu+4EPvnxrZ61FwOPR+D4MZ7n9a8DXnc/P//QhyUuddIISqe3GkPBoMCHf96GP/8K89x++m0UK9mJ2GloaGi8HHj0caCn93q3QuPF4tVG0PbrK2+/tms/IRa7Np20usr/62eyMzRB09g3uHCRZOYtbxL44R+6/PHDwxK/8BGJN79J4IPvt12VQtKFhQI1Zrjkr3xCoK0VmJ6himM6LRGNblVyrKsV+J3P2fDLHxN46MsSH/241GGPGhqvIczOcXPmWiIcvqaX09DQeJUhk5F4+hkgmbz6a5eUQEH+Vb/MFUNKKn3vB2iCprEvkExKPPRlidlZes683t3J1vCwxC/8osRb/4fA//jJa7P9WF0l4HYLVFUKfPnP6K17+BHgs78VBwD0D0isrVkT+47bBf7q6wLNTcA73yPxjW/KbT1vGhoary4UFQLtrde7FdcPUkrMzl75Wjc8IjEweHXXSMNgCP1+wqvOg3a9G7AJ2kuzN6h+uhb9JSVgs+2/Z5NKAS+c3Tml5VpCEzSN64rVVYm/+mtK43/x8wKVlZd/Uw2Z5OxtPyPwljdfnzdbaSmv+2P/VeDTn6IM5Lf/VeJSF//+z9+WiMUkvF6Bn/ugDV/4E4EnnpR413utMEkNDY1XJ+x2oLz8erfi+iEWQ3YtvBIMDQOjYy9/e3IxPAKcPXd1r3GleCUStHR6Z6K7D2zbDbiWxOPVgNcyQbPZLEG66w1N0DSuKySASETCMPY2IQaHJD78EYm3v5XCHPsBLhfb8Uu/aMOdtwskEhIXL0o4HMDYmMRf/pVEa6vAQ18Q+NH/IvCxX5b4/T80rlmst4aGxpUhmXxpYclra8ATT22fq/pawn7Yhd6M+jrg6JHr3YqN2Ae24BXjsceB8xe2/9s+fOwAtHjJfoJhbCVo6bREPH59B4/NBuQHd1+7kkl5Tew3TdA0rgt6+yQe+rKBwgKBD7zPBrv98m+ogUGJ//mLEu98u8Cbf3z/vtHcboFf/5QNLpeAzQ4UF/Pzf/oXoLAI+MbXBebngXe9V6K7Z5++yTQ0XqFob29/Y3t7e197e/tge3v7J7b5+0+3t7dfNP+dam9vP7b5mLU1ifHxF9+GoiKBW26iJ+1aYT+tJIpw7EdDfS0EzM1f71a88iGxS97jPnvuL2YcXsvNBcOQ6OySWFq6vh2nbvlaEFnlQcvF5BTw/AtX/9q7IZ0Gevp2HzMXLgJPP3P126IJmsZ1QVkp0NK8d5I1MGCSs3cI/Ph/37/kbDNqawR+5IfY3gPtQF0tUFICQACvfz3wPz9KGf/9lhOhofFKRHt7ux3AFwD8EIAOAD/V3t7esemwEQD39PX1HQXwWQBf3nweQ740cpFMSmQyL/77rxbsR4I2PQ0MDV3vVmzEZg/awIBEKLQPO+8ViisNcQyFJb7/g6vXns1YXwdmZgGv99pdcztcy/kqJTewcq/ZUC9w913X176z2YC2FuyqHp6+Rmu7LhGncU3x8CMSw8MS73+vDa97YG/f6R+Q+MhHJd79LoH//mOvHHK2GYcPse2GIfGj/0XglpuBpkaJ3/9DiRfOAJ/5NHfeNTQ0XjRuBjDY19c3DADt7e1/C+BHAXSrA/r6+k7lHP8sgJrNJzEyL81YicWYaH7LTUAw+OLP80rHfiRoR4/svzV2M0Gz218Z4Xg7Pd/99tivlKD5fcDJ41etOVuQlyfw4B7toauJa5mrZ0jAJoBYXCKRYOTR7JzE3Bxw7Oj1m6N2OxBfp6LlTpFdjmsUGaE9aBrXFCeOA/ffu/fJ190j8T8/KvHed7+yyVkubDaBO26nCmTHAYFf/DBQVwf8zNslvv+DV8BbWUNj/6IawETO75PmZzvh3QC+t/lDQ740I7OgQOC+e4BA4CWc5BWM/RziODEpcanTwPLy/mncZoJWWQkkk9enLVeCnXpwPz534Mra5XRt/P3hRyQSiatzY+m0xOnnJMbG9kfHXZMQRwOw2YGFBWBlhRvX4TAQiVz9a++GZBKYmNw9L3RzaObVgvagaVwTfO/fJSanJN77bhtKivf2nQsXJX75VyR+/uesMMFXG8rKBO4vE7j/PmB11cDv/B4QDhm47Tagolzvn2hoXCG2Wyi2tXra29vvAwnanVu/IeD1eBEIOF9UI2Ixidk5Aw31NjidV3/t8nqSyPOKF93elxt2u4TXk4Lf74Tdbkdgj0zV6yErCQQ2WscLCwamZwwcO2qZLKefS6Ot1YbCwitbJ222DFZWMlhbA37oja7Lf+EaIC8vDa/HyN730HAa6TRQVWXH1LSBlmb7FfXjXrC2ZiA//8W/Y7yeJGy2rc/K60nC57MjELiGCZjgGCkqEtt6PYS4svEYi0lcvJjC6x5wwukUkJLfz893XpX5TMXnNFpbHXC7r5+t43Ra/RQI7N6Olzoe3e4U/H4bgDS8XidWViRcLok3vuH60pK8PIm77pC7zg2fL4143Ngy9l9uaIKmcU1w041AW9veF57nX5D41KclPvaLAq974NVJzjbjtz5rQ3ePxC9/UuKrXwP++R8MOJ2apGloXAEmAdTm/F4DYHrzQe3t7UcBfBXAD/X19S1t/ns6YyAWiyMcXn9RjQiFJS51Ak4HUFy8/fo1OyvhcAIlO/z9ShBfl7Db8aLb+3IjFpOIrwOh0DpcriDCe6yiHV8nlw6HExs+TyZZiiUctvoqGJBIJjd+thdUVwHSkOjp23qd64V4nP2l2pPnlQgGgZ4eYHQcKC8TCAQCe+7HyyGVknjsCeB19794OfH4uoRNbO3D+LpEJHLlz+Wl4smnJdpagPr6rdeNRlX/riMY3Nt4vPUWifX1BNbNKXXyhEQstr5rbtJLwZHDEvE4kExeP3tnfd2at5cbFy91PMZiEutxwO+TECKRFZ35zr8B99x9/fpASonuHuCoA3A4tm9HIrFxvr4UFBYW7vg3bf1pXFX863ckvvZ1iZISgeamvU26p05J/OqvS3zqk68dcqbQcVDg638uUFEJfPyTwB/+saGVHjU09o7nAbS2t7c3tre3uwD8JIBv5x7Q3t5eB+AfAby1r6+vf7uTvNQctGBA4MEHxI7kDAAyGf5LJiUefuT6K7hdDbxcoW5SUl0tF6trQOJFhAH2D0icPbe/+nqzLRwMAouLDLW9GnA4gLvvfOm1nnZ8vtewe+NxiWiUF8zsEJp3peqE6bTE+ATD7vh9iaefQZasvdxIJCSePgX09F6d8+8Vqp+isd2Pe/iRnWXmDWNvReqlZIhjOMKc3VBIYnnZFFG7jlhfB5aWdw9jvFbqvJqgaVxV3HIzcN+9ez/+3/9T4rOfk/jMpwXuuvO1Rc4UiosFvvh/BAIB4MmnGS4Uj0usre0vo0JDY7+hr68vDeBDAP4DQA+Av+vr6+tqb2//QHt7+wfMw34dQDGAL7a3t59vb2/fIuz8UlUcQ2GJ8xd2r5UTXwfW40Aqxd9fDNl4uXHhokRf/85tjkSurFNerlyWUJiEJRdra9vHs14OeV6r9Ml+wWae1NdPw1VepVygRAJ48qmdpeTV5+m0RCRqYGbmyp77tXxTPXsaOPWsed2dREuU+MUez5lOs2i6ygOUkrWx3O6X1NQdISVQXgYc2qw3e42h+qmre/fjbLadSUosdvnvA5ZISDIB2GwSPb2AzydxqOP62n1uN3DHbburOOocNI1XNP7pX5jw+baf2dtkk1Lir/4a+NtvSfz+7wocOfzaJGcKbrfAb/wa8LWvS3z048B/+68SU9PAr3/qtd0vGhqXQ19f33cBfHfTZw/l/PweAO/Z7Rwv1YNmtwHRKBCPA3l5OxxjB9weZOX494OwwvwCjab2tq1/W12VeP4M9qQ2t5d7CYUkAoG9eXEKC0isctHU+OJ2squq2Of9g1f+3WuFxgaOm+GRq3N+h4NkxTC29uHYmMTyCnD8mMSjT0isxwCPl8Ilm7H5MV+PwuS5kuc7bQjILT/sDo9no6qizSbQ3CS37a9cnH5O4uQJXHGemscj0NAgEYsBPt8VffWaQUqJvn6grRW483bA6dxeyMbvF3jg/j2czyxUnZ9Pz2c0SnL38CMSD17HyCkhgGdOA3fdIeFybd+Oa0XQtAdN46rgtluBe+/e27GZjMQf/YnEv3xb4ouf1+RMwWYTeM+7bHj/ewT+/h+A1z3A3IGv/+XVU5PS0NB46R40n49KrbuFOLqcNAZ2Csu6UrxU21itKTudp6BAbDCckkmJ9fWdPDCXb9Pp54Hpmb21LZXaWlx6ecXyPl4JOrvodXmpeDnX4C0y+w6Ss6ulpme3A/fdg20FNRJJehFGRoGRYcDnZzhkLgaHtn8HXalMeySytQbow4/IK/bYKezYX3to1/KyRDrNA5JJiedfkEilpHleibPn6XncDfkvsqRGLCbx/AtXj5DvFbv1j5QkUFICTzwFhMPbH7y6ypDty14LDHGMmBtZADdOOg68iIa/jIjHOY6cu+gt2U3mdLXr12qCpvGy4rvfk/jGNyUqygXq6i5PtGIxioFc6gQe+qLYNsH3tY7/8v8J/MonBH7zfwH/8X2JWFyaBR41SdPQuBowMi8tTGtpSeLJpyRWVnc+i8qryha03sMF19clVnc4ZzT20gyGi5d2/3soLPH0Kev8z73AEOzdcLklaq/FvNdCW/N/pmckhLjy+62uAg6+SCMwZBqly8sSTzz14s6xHayyBAyL/eZfyy1FfF9OhMPAo49v/w5pbgIa6tlPVVUA5MbcqFRKYm1tdy/C5dodCksYhkRXN7C4SaKntgbw+/d+Lxuue5kctN3adeYcMDZuHbe6Zm0ASAlUVlzeu1VQ8OJItd0ONDTgum9O79Y/mQwQi/O5l5VyE2o75OUBRTvrXgCwcvtsNl7TYeczLygASktfZONfJuTlsUTKrrhGZUQ0QdN4WXHyBHDrLXs7dmpK4gM/x7CBP/0T8bKomb1acfddAr/zOYE//QJQUc4aap/8FPNcNDQ0Xl4YUu755ZtOyy27yX4/DY3tDEZlFEciAOTlSUoiIbMGzZNP777LPjK6tzZvh8u1Qxo00BTW47scq0QZXqblqaJ8a9jl0hLQv63Ey+4IBBhaeqVIpSROP8fnnXwRnrvdkFs3LhZjXcymxqtnAAYCQDCw/TNfWASef4GetHCY+X8Lixy3Xd0Szz0vkZe3fRjfXtt7+jlgdBQ4cnirMX+gXVxW4n0n7DTe9pqDlslwE8Ttprc4L4/tsNsFCgsu70G71HX5Y7aD2y1QUgzMzb+0B/7wIxKh0N7Okesx3AucTgG/T3mzJZJJehiTyY3ncDj4XAHsIiTC/9sE4HYBa2HWQpudAx5/cs9NuipIpyUefXxvdQg1QdN4ReCpUxJf/do6KioEWlsuv7g+/4LEez8ocdedwG//L7HjboyGhRPHBT7/RwJf/78Sf/4XBt75du4Eh8K7ixFoaGhcGTIZ7NmFtrICPPvcxs/cboED7QJFRRvXtVRK4vs/4A5yIMidc+MyOWg9vcC8Gd53+63AsaM7t2V1dW9t3g073XZ+/sYQx926Z3HJFDV6mZalSHSrwl18/fJqc9uhuwc4d/7Kv7fBC/MyL7eqV5XhmkyyjVcrxDGdBjoOUkbcMKwNAABIrDMHbnycYaVlpXzuQghMzwCxuEAmQ/XEzciO4b14gxNA/wAwM7vx84cfufKCzcqbd7kctMuJrszPcxNkfV1uUCpMpyW6ey+/idHe+uJyyMJhiTNntwrhXCluuWnnnNfNOHOOQii52I1wpNMSQrCvO7s4x08/R7GZXM99KESSFYsZW9bFzdex2c05LAGvl2GFt+1xg/9qIZkECvJxXevRKWiCpvGyoLEBG4qI7gQpJb719wxr/PhHBd77bttVqyvyakRrq8Cf/anAfz4M/Ou/cbfqn/4Z+Mu/0gRNQ+PlgryCHLSSkq05OrNzNPA2y03nCoLYBABxeaOvvp6J9ADn+25espdi0F9Oq2N5eW+5JQDzONbXd25POr2RFOyEhx+RmJuXWFkBXNvUhN0tzC6dlhgZ3XqNpibg2LGtx2/2BGw+l8JL2TWXUm4fmr6p76dngPLyF3+dyyES5aZCJiPx5NMbCWttLT2MBw/wXyot8fiTMitnH4sx6sVtPg+Vp5ULucPnuUil6C3crIx4/ChQUbH1+Mef2Flh1GEKd1zu2Vzu73EzjNZmA3w5REcIoLVl57A+BZspDnSl8HiAAwfwkhQMt/Pk74bxia3H7/ZttU7ZbBJlpUAwKBBfp9fyB4+RsAHMVW1r4dxXm0+b8xWzBE3w+btcJJblZRvXw+ERmT3v1UZnl8SlTom8PIH2NuxpfdIeNI19jUudEn/11xLVVQI33bg7QVtbk/iVX5P4h3+S+ML/Ebj3Hk3MXgyqqwW++HmBri7g05+R+Ik3S7zrHQLRqMRTpzRR09B4qchsk4M2MWnVW8pFPE71w1yUFANHj2zdzc4lQfMLQDplkZidZu7YmBkOCYaGrazsbDzspayVYews7rEbPB7uLO/1WKdz53vq6qa3by91pcJh5kRVVW4UJnC7djeG5+aBwaGtnzvsQGpT+FIoJPH4k1b46cOPSMznhJs9+jjQ28efr4S8b8aTTwEXLu78d3Xe1hagtEReNQ9aYYFAVSWvl0xyTCksr/D5hMIMQ4zFAI+bz3NigsSquIgeBpuNHpPN7ZcSeOwJzhkAWFnZKgaSSgE3nNw6poLB7QUakim2bTtczoOWFQnZ4c+b4XIJ3H4bQxxjMYl0mmQjtAsBMszi5y/mmTmdAgE/MDDI8ycSV0a2AK4N//BPwOzs5Y8F+Aydm022XS7pdgvE41yLPB7O3dy9dRXynE5LFBZS5EyC9/LEppIOaoNKCPbr4hI9qUNDzG1VCAa3aeNVwswsQyyTSYnTz19GgGhTTqMSRkkkJJ548uUTcdMETeMlobCASb2Xw7nzEu94t4THA3ztywItzZqcvRQUFwt8/o8F1taAj32Cce8Tk8DTp3bYodXQ0NgzLEPTmkurq9sTgliMxnsuaRKCuTXB4PbrnKp7ZLNbMuE7TVuHgyTl6VMSlZUSN90o9hx1oIpg5yISpcdkc/7I5chdXp7ATTfu7brZPJwd7qmqkqFgY+PYUx7M0jJw7sJGwrWeAPJ2CSfb6X56+yyylXt+YGPeydraxmMUSX4ppCmR3Jlk5GJlBfjyn1ttWFx8edf0WEyivJwhjsDGx5RYZz2uxQWOyZJigVtuZt6z3UHjfGYWWAvJrFy/wmYxDkXAu3q25mal0nwO4+MbP3/iKRLDXKjC4juNPvtlPGhXqi4ZjXLerK1JTE6R9AyNkNyn09vnbgkBnDhuebuvBCurEs89j2xnrq0BU9PbH6vyvzYjFgfa2kxhlz0gFgOmN5G53fonkZDw+ejtGp8AUkm5rQc7FqNCq9oEyq0lp2AYgLABEGy330fC6PFgg0BHOLw1BHavePiRnQWVdkMmA9RWbx/i+PgT9CBvPquqYZlMsn9eTB7idtAETeNFYWSUoYo1NQL33L3zSzudlvjKnxv45K9KvP99Ap/+lA1+vyZnLwf8foE/+D2BwkLgQx+WKC4CfvmXbIjHgT/5vLFtjoCGhsblsV1tsva27Qscl5QwRyeXNM3O0YMwNLzLjrukwXc5g7+hHqiupiEzMgqcv8Dk/ExGYnx89znudAI3ntxINB127g6fv8A8lL1ChW3uBUaGxspOBt/8Aj2Pco9iLLEohVeqTeNTSgm3ywqz2w47vWU6DtJzk4tMNhTr8m2R8spS0PoHJM6dzyHClzk3wCLV9XXW7+cu7I3I7hX/+X2JU6e2JxqVldyIaGkBmptFNh9rbU2ipBjZWl15XlNuPOcUOxIhaYa8GQxTlFIikzYJYMnGQ++5i2G9uVAEeifSfdkcNNWeHbpws0fa7ea8czrpxQnmAyeOMU/q0ceZO7cZQgjEYnv3YCk8/gTn8w0nmcIAcG0IbKNkmUxKXLzEHMLtMDe/tzFsGBJzcwxnzcXl5qLHw2dQW8Oc1O0IWjAocPK45QXdbi2V0poHwQA3oZxOjr2pKeu4aPTyipAKicRWz1U4srfv5sLrFSgo2H6+JVMbPcYK6t7SGYmmRo6TlwOaoGm8KNjtW2PHN2NmRuJDH+bO0Fe/JPDG12ti9nLD5RL4jV8TuOEk8P6fkxge4a5WaanYNmdDQ0Pj8tjO0Hz8ye3zv1ZWJJ573kBfv5H1dFRXCdx1B6W5dzp/aA3ZYsEAII3t87K6uoGVVf48Ps6wSSH4Wd82hmIulDR2Lmw24EA784Zbm63Pd/OgDQ6REDU3bv3b8MjWNvv9bOdOaRwuJz0E26kwbteM2lruaqvzpdMkdkqiPRKRW8LPdrqfZNIy+BXUc95g3Irtj9mLB21+3jIWp6a2SsnvBBU+WVuzNb9ur96fR36wfShuLnw+kc3zSiQkunus42dmSTJWVpjCkEpxrAQCJAA2G1BUxGchxPbtUka5egYN9TTugY1hrW2tWws/Ly+TgDDXbePJt/YJ/67OcTmRkEh0+/Dgzd9zOCyxs8VFIBrhM1xaAm69efsyDakUCzkHAtu3YSckU7xnALhwkd4xt5vzY7P4l5QMf1Xqklb7eVw4tLexZrMJtLQAyU1kbrdR43YLzM8Djz7G57sWktvOsfV1iXQG2Q2rnXJsheAUW1/neJueBkbHNhaQr6vdW9g2QM/r6ef2rmK5E9bXJS517dzu3BDnzcQ/tMZ7UAqnsZjEmbMvvj2aoGlcERYWJP75XyTqagV+7L9uP3MMQ+Kfvy3xzvdKHD0KfPHzAjU1mpxdLdhsAr/wIRve/OMCP/cLrC3zP36S/f3RjxvbJspraGjsDGXw5BqfHQcYhpOLUIjS40+dInmbmOTniQTzVjYbUgpSsgBwNGoZh+cuAM+e3jpXy8osA66hXqCtleFme4lyNAyqFubmGEWjNP7y8i6/yabAUESgsBBbFPY2K8EBNBKTSexo8bk9NPrb2rb/ey6kpMetpw+YNPv3+z/gZ+p59PQCPT17u5f+Aes8udcANoY4zs9vH1qoDLTJKYmlHQQMLlzavl/2isVFhpFdjgym01vD3RYXZTb3aydEowxPdDgEHA6GnCo4HcDBgwzpLC3hM6+t4T17vRw34+MS0ShDdLfDZuN2dJx9m8lYSqNSsmTE9KZQvktdFEl5+hnmJO1+//y/Im6byeLYmGRel/n5yCgwMrq1Uze3d3bOwMOPSDz9DNttGJzbqj5bfJsSEw4HcOfteFERQpEI6xCWlfJeCvIZAr2ZvAL0Tm+OjlH5UjfcIFC7B1srk5H09s3tvY3RKHPLIPh8BMS2zz+V4r2oDZMdPWimImQkSi9qZSUAiQ1KsRljY4hjIrF7CsfMDMMrc69zpRCC0RK7qTjmnreziwqfAAVShEB2XXC5GP2wHXYKlc2FJmgaV4R4nAUcd5ok4xMSv/ARib/7e4nf/S2Bn32/bdt6KRovP37qJwQ+9lGBX/k1iX/7noTdLvDTPyVQW8MFXeemaWjsDVmvVs6UCQS2SmjH4sylOHJYwG631rmVVeCZ08yD2C5fRIX4BIPWNVIpwLuNRHZRIXfNpWTh62eelRgelrh4aet5lTGUSkl0dkm4XAL33k0jW8HnowBEdw/Q2b2HzgBw9DBD2144u7ewIY+H95PJSEQiW9eeSITvkVBoqxG13Y55OkUS0dJstae42Dq2vZ2kYuOJtm/byRP0gPT0SiwsbCTiuW2JxUmaN0Md4/ftLZRpTx6ATX2QyTDEcbOzZ2hYYjSHIPcPbK0bVVQsMDG5+0WFAAYGaPAKsVHMprSUBLa4WKKkhHlATzzFMe1xkzy6XEBxkYDDvtXwVu3PvXdfHv/mdAoEAtb8cti3GrAPPiDQ2MAvrm/y8Gz2oG0mVpvHUv8gPRq5n29X32ozEb54CWhtlqir5Xzx+YA7buNxzz5HT+J2GBsHhnPCmnv7qICZSu0u+hEMMr+zspKbL2Pj7LvNUTC9faxJtxmZDNeH7u6dPUiZjMzm8sVi9CI3N212E+/YRDgcfP5Sch4GAhtFQtRXAwFGDygVzPQ2nigpkZ2fpSVcK9JpoKYWG2q7Dg1tVDN96untn5/q2+bmrYq6APAXf2lgesZ6yKur1tzPRSTCjbV0andV19z7mJm1xmEyKdFQz4LbCl1d29vLQ8PchNkNmqBp7AnhsMS//6dEXZ3AO97Gmii5SKcl/vxr63j3+ySOHgH+4qsCx45qYnatcf+9zEt76MsSX/qKgePHuEv6O78n8Z8PX+/WaWi8MpC766uS3Z9+RmJomLlfK2byeUE+FQHV5+o9XFEu8Lr7GUqYa1RuNhTtNss49PuZj7EZg0P05oyNcRe/sZFeNZWnkxuyZamK0XBIJiX6BzbmrCSTFIFoaeb/94LFJbbvyGESh8shECD5TGeAJ59KbTGqAgGGi13OQFGoqKCxqsK3vF4ah3OmB8DIbC2cvZkYrayQKM7PA5NT9FbEzDpqqj7WbiaZ+pth8JdQePd8n3Ra4vRzV7Yppp5fWdnWc0sJ5Ac35iY5HKpN1nUudcrL5h/n5QkcPMjvR8JAX06o6cgoDeb+fnomDQNob5UoKRZYWeGzkxLIyyO5y72SlYuz8XpeL721mQw9dyo0sqxcIhzZ2NbuHovMbCZOm5/pZu/MdnuQ0ShVS7MEaZtjNl+HZBLw+yTWzXp7vX30RD9wH7IEMhfJJOdnLuFcWeHnXd1bayXmIpWioMW58/x/WSnH+uaQ6mNHKdji9W5vW6VSzBXdDokESZmUEoGAQH0dsLyyNYTS41Y/b/yb2y0QjvA8oRAwO2tQ6GMTIhGJiUmrT3fNQRNWyPHyCjA1CayZOV6GIeF0SaRz1BQDOcXVDcN6pkpMx27fvpZcSbGZLwmrTdvl8a2vc10aGsndbNg4n2T2P1vHWzRmRVEAXF+8XmyxlwFe/3IlVjRB09gTVlaAnp7tvTC9fRLveb/EI4+l8Wd/KvC+99j2RZG/1yoOHxL40hcFnnwK+LXfoOrQRz4scP99LHWwsrL7y1tD47UOZe+qwrUADZOpKeBvviXxwhnuwo6NSyws8GWbq/AYDrN2V22NyCrlAcAjj1JsIZOhhTI3ZxkyU9Pcbd2M+joaLaWlJHwV5eb5zDbmGpfq51x7YHpmo9Gyvs6wMpudin2hMInnbp6e6Wkaf5GIVT9rZsYqKBwKbfQQTE0y2sJuF3jgfucWT0A0CjQ10vP4+JPYWOtom3bMzdETsrrKa/3DP9GTUFbGvw8OMVwuF+o06p2lvH+LS+ynoiIa0909lirbXoIMsrlomcuXCSgq3EoqtuvnzZedm9s+lygW3yj/rep/Tc9YpRMCfou4KTx72gqnkpIkQD2fYAFzwXLbfKCd4WWNDUAqLXD+Ir1t+fn0ji4sbG9cbvagKSwtWaGCqZQlwf7P394amjo1DSwty23PoxCPMz9tO+N/M+bngflFjh8l9d/XLzE6ZmTHRmYTQUskWGf0W/+PRM0mSCJKShgWuPkdKqVEIkHyltv3anNmJ1GP7PXWed8tzSp/U+DYUebu5WJ1lZ7zSGTz9UkCmpsFxsZ3t72kJCFcWzPz66LWHF5PYFvSBSC7KeV2M7zY598+zFoI9rUiTdsSNCiJfYmZWXrRysuo7HnPXSp/ix40dV2Ax6i1ZHTUIr3qiLl5oKtbon9AZguwS0mvWO5ziUa35uaq8/h8VON0uwWkpKhNrjjSbiJB+aZqrwop9/tZd3FziQnVL5dbbzRB09gViYTE40/Qc/aRD9s27ASsr0t88SEDv/ARiTe+QeAbf+HT8vn7BFWVAg99QcDIAO/9gMTqGsNL/v0/aWBqaGjsDFVgNdfzk07TwCwr5e/PnwEGBoGGRobfKW8MQNnlSBQ4c3ajMXWgjQbA8AhDXMorLFJVVEiDeDPSaaC5iYRncgL4wWMUI7hkkrnN8tUAsuzE5aLCZGWltS4XFNAYO3OG7fC4lUdj53Xh5pt4nZFRoKKcxkVxsVVQeHXNkqFX10gkaYBNTG6TSCVp5M3M8Jq5OXLbwe5gXkjHQX6vspKKjkmTrBw+RKNqO6jbevABgWBA4PAhgZpqoLMLGBnhc7sS6XzDML1Z+ciqvW236aUEWgxDYnpmbyHm6hCXiwIJm/8Wi1kehlyEwyQ+4bBETQ02pBVIKRGOWGP5+z8gyRoZNXOZjI1Es6BA4FInS+gIwQLlg0O8RsZgLTSHAygsFJcXCTF/LzXnjNMpkExaRaw9boYx9vYaWSP2wQcEBga3F5hYWqaQxlOnaKBfLsQRoKe5qtIKQ5bg/T7zrJXbaWw6j9cr0NQE1FTzGg6HxL13c4x3dW+c6wCJwTOnJc6dZ+iowm6F1HMRCAgc6hDw+/md7h6JoeGttbhmZkmQcuvExWISGYMk4FLn7iGOgIoKYFFuj0fg1LP8++nneW+KdG3uW7+PEQOGQc+717u9iqPPxzWnsIgn2pacShLBkVFukkQiXN+qKrm+AdwkW162hJZWVgyMT1j3Fl/neM9kZNYD3lAncPddDBEdGuaYXVyUGBllDquC3bH1mQMMbYxGKVoyNmbg+z9ANtx0L4jFJKqrqewLsK8HB7fvA7WO7AZN0DR2xcIC8INHtyYznjkr8fZ3MXzmL74q8JNv2ZiDoXH94fcLfO6zAm98g8AHflbi0cck3vIm4H3vEQiHt89h0dDQsDxoaoY8dUpifIIGd254k8dNg3Vykh4PpdxXUixQVyvQ2mKp1wH02ths9Io1NtBIkJJGkcu1vejCwiIL/s7M0kC+9WYSkptvNNua60HbNKXjcYmnT8kNanBjYzT+/H7g+DF+VleLXWurDQ3zOjecoBHlcolsoj9AoyY3rM3jIeFMZ4D+/swWQ7O4mGGFm2uNbQvJc4VCDLkTggZPKmUJTijhk1yotikj6OFHGJr6/BkDFy+R9Obl0djMVWN74YzE3A5hYrnnC4eB+LrE8Ai9cwCNYFWwVuVrZQxkJeV3QyolcepZEvrCQos8LC0xh0lK1rjaThk0HqPR3tPLf8orEo/LDTlRCh4PpdDdbhJpCpLIbCmFQICeouERHtPSTKMzHCI59nqBRNLyyG3um83GbzjM8Z1O89wOBzA7S7XClRXgqVOWYMVTT1ubGtsRZ1UUPpm0DN/dCPbAAMfvpU6rWHZDPce/lOyjzWqJmQw9TJkMsLAo8cijfMaRiCVioZ5zOk1PnvKItLdb59lO5GM7rK9LzM5SQn96mh5NITaO6URC4uABgfY2sSFC6elngL4+ritlpeyL8xe2FqN/4kmVi05CWF62vQiO8qA9+vjGzx0OeriSSZKWsdHMtgRtZVXihTMSSXMtVM9o80aSACMSVldIeNfXOQaU8I80SN7mzXy/F84KzM5ZG0HpNNfeoWGucera3d38uaKceXC9fQIdBzdufgX8G/NyFYoKeY+5eWXRqBVKDTB3d3BI5dZu/H4qxeen3gMrK5w/20WUZTJWaPVO0ARNY1sYhsTzL7DO2W9+2pYN0wmFJX7n9wz82m9IvP2tAn/0+wLVVZqY7VfYbAJv/WmBz/6mwB/8kcQXH1IhHsD3/kMTNA2N7ZD74pRSoiCfQh12G8PFlFEaCgGQJCQlxTSS02mJf/oXA1PTBoJBhjh2ddOYO/UMv6N24RcWaazYbFQg6+/HluT1pkbmV7W1MvRMCIbqKel9ZUjceIPVbrUi22wSdjsNH2WcZjI0mD0e7vwPD9MYGxndatQBvJ+hIZbvGBllketEQmJ0zMpdyg9K2GzWd+fmaXDZ7QKvf9CZbavCxCTDEw8cYEsvt0M9OQVMTvJelPrf/IJVl25klGF0uWCNNcuIcjlZN62vj8ad3Q54vfTGqGMWF1mMd1vPhyIfBn+02bjrn0tGbDbgYDvHQTJNo1AaPG43AqyUIXv7gJU1En5V/HZm1spHm5nhs9vUJMTivIYQNHCVOmc4TC/vZiwuSkxN8/iCfIEjh1nHr6gQOHqEY93rJXEfNxU8Q2EWtxaCxFga/LmrC/jevxsYGTW2hjiat5xMcjyosc42WN6JoqKceleCx62vSwwO7qx0J7F9+NxmBIP0Brpd1vFDw+bPgpvQuQY4QEN7YpJ973SyP11OegIHBiV6ennBJ54CLlxkY5xOgSOHNyo87uRBe/gRi1So/orFufFSbXrtGuqBpkZrzDz7HBUov/2vBp49vdGyX11jiGN5uUBBgcDC4lYv3223cs6rvNrV1e3n3U6jdH6Bz93jYV3C8nLbtt/3ejheI2bI93beIxXi2N4GhKP0xpaXc31V2gWG5PhVhFFKieJiPk913o4OgeER4NAhfhaJWKHBs7PMCYuvy2yIrcLcHMlTOLxRiXVpmWOx4wCVWAFT7GgTkUqlts8/9QcEvB6LRJ67QNKcW5/tyadY1sIwWKpgN2iCprEt5ueBb/7NRgWyxx6XeOvbJaIx4Bt/IfDDP7RVLERjf+KmGwW++iWBCxeBD35IoqKcRa2jUYl//Get8KihkYvMJleUYXp78nxqd5vrXl4ecwyKiqwirpmMWeNHkMwtLUkUFNBYu/lmhsbZbCQxFeWmB81GtbKKcmQlmxVmzYKyS0sMazxzDhgYkOg2FRiV0el0WIaEWpYdDoFbbxFYWrIMtsIiHjc7B8zNSbS1SZw4xnZsp5A2PkF1SWFjIn9jI9vb2sKQQ4C7+IM5RMDvM8PukhLf+W5ygzIbwGT/ySlgaGhv605BPkPh6moZzqREThRZOXlia/HpwUGSALW03XkHSUdZGa8/MMj8vPo6kmIpJWbnaVAVbSqnkAs1NFwutmvzHXT3meIZBo1up5NlBTYX0X36lMyGePJ8LKEQiwkUFlrS95WmQIrytC4uWeu1urfKSh7T2MDxpTw3BQXbh37m55N8xOM0YKdnVM4Ox9NTT7Ovkkk+68lJiuGEQiQuvHcOMpuN4WMqz9Fh39ondbVsk8slsLhI47almeO9qIjGsvJa3nm7QDAo4HYrNbztx8jSEo303Ottd2RxMcOKm5uV51eiqIhkQ4B/2+zI8HhIWlua2TYhuDmyssLC47lhpssr/H86TQ9YrtdrJ/n/22/dOF59foGmRoF0mn0zOMQQztzafuk0w3ITpqjG3PzGk6ZSDHFUhGPzNScmLS+fWjOKizfab4uLEuPj1hf7+q2fS0v4vJJJKqYK2/YeQo9H4I7bBQoLNoap5uboqgc1vwDUVNHzFQkDHi+y+V5q/igVRymB5SXLW5pK0SsaiVhhmZWVAnfewV+CQa4PUvI6g4MUTfr+IxKBINfARJIkTsHrBeZmuQYrol1YyFDXXAhhhSjm9mA4JJGXZ/VrxwGus8kk7/H5F5jnt7zM6ILRsa39lwtN0DQ2QErW9amoEPjjP7BxQV2S+JVfM/DHn5f4pV8U+Oxv2LZMbI39j4oKgS9+XuDmm4B3v1/ie//OePWpqa2ueg2N1zKyqn6SZGxpiTuzK8s06JSB7HDS6zE+QQNIeTF8PoHSEoEbb+ALvrePL/R4jAZLx0GBA+0Ml4lGZdaQc7qsJPlcDA7RKCstYYhjNAr4TcVHZbDY7TkeNPMU4TBD1pThDZjS1WVATbXE8gpw/gIJS2HhVnEJ1QfjExQyOHGM9+90CkQiltGliJJhsGC000XDyjCY77Y5BK2kmIqE9m2utx18PpKpxx4HDMkd8aUlK3dqdo73kRuq5vVaXhsA+MFj9JZMTdMD195Gb1NpKQ2luTkSkIcfkRtEVVIpifEJa42UpmG2nuDzzlV7G5uQ6OxU6m0Ca2tsg9ORW0xZYnFJIha3vKDKq3GpU+LCBQmXy6oPlkgiq5ZYXc1xNjhkfc8wJEbMUMTeft5bNMd7MTllHavgcAC33EwxCinZlwuLFMTp6qbXdmqKG7VuD9DSQqMzGiOhnV+w+jq+TqLu8fBcdrtFTNbWOP4Gh0lUEwl6QVwuq67Y9DR/7zW9sQ8/QhGTTIbX3mkTOL5OcuRwYFf5zeFhPt/uHoskFxVZJHxtDdicnZFKkbTOL/B+olHgYifJuctFArkZhsF5pApcAxs9aPPzVojl5luKRlk+YcYs2HyoQ8Dnt0J41fk9HoH8fK5Fm4u8Oxwk6Mp7urlLJiY4Xh9/kutTfj4JzuKilUPp91MIRSFXZfWRR4GJKX7W1Q0MD28fnzc/L/GDx6xi6cqDduacdYwKj15bo4CLYbD9oTXOS3W/5WUUkXnK9DY6HGbUAkhwggFuDJy/SKI0Py/xjFlL0m4Hgvn0XB8+xM2PeJz94nGb8v7JjfmvxUVcgwHgJjOEPBSigm4uEgmSLik3iqoIwTkdidC5MTTMdc7l4vNaXpEYHeUGi5Gx6urtBE3QNDZgaRn4wz9mTLaUEt/5rsRb38Ed4L/6usBdd2pi9kqGwyHw3nfb8DufE/jKn0t88UvAW39aIJEA/uhPjC2x+Boar1UogzqTkQzHa+fL+9x5y9idm+NxgQCL+SqDd3WVCoepFA2NvDy+0C9eorH3xJNUeYzGaMDYbPRo9A9gg2IYQIPY42H4U2WFQDhMA3l6hn9XBCQWlxgdt7wrqZSE08nvZzKWsEBFJa81N0ey0j/AUK2Z6a0hWdEoZekzGRoZXd3ApU4gHDawtGRJShcW0vAJhYDTz9HoIUkQuOdu5wYlS4DGeDDIwtvA5UMch0dIdKprACmZi7KySiMLoCHr9dKTNzsrs20KBOilMwyJ8jIa5X4fd8QTCRp8L5xhLp5hkMDFYhvrT9ls/I6C8qB53JaRBtDLNDAgcPAAjeTpaYnKCn6fBihvcn2d4VfAxkLhdjsNxIIChhWqNqwsm0RU0usXDtPQHh6WWFxi33k8fHf78jhO8/Loaevrl9lr5ZLkuTk+y3RawpdHb1FpCT0799xF0lpaCtTV8XqRCL2MtTVsSybDzQmAnp7uHrZHha65nNb9lZYAeV6ew2Zj2C2VBEk0/X6OTVU3q6aav6+uMnwyV/RibGxjvlg6zXbk5hBuRkkJvZDKWy0lcPGSxPIyPSqp9Nb6hobBfg+FaGCzBIZEMABTudUiAQDP6XKx5qgiO2trVBNUSKasZ/D0M5Y6LMDcU5eTkS1NTQIrqxJFhVxTHn5EIhQyzOcm0dPL6504zueXG/3idOYUyt7UF/feIxAI8G/hMDdnnE5uNKgcSikt4R2FS5cMDCpPt+R3HA6gpXn7BLvCQva3Os9Oap8zsxJ1dQxr9PsY4pjns3IsMwY9TWVlVniq18s1Z2GBnvSqKkYw3HQjiZKUVhmKcBhYXOAGxvgESahaZxYWWWhd2LhZpDA4zHFyuAN47jmrrbmbcgDnW8DcIMtdu/LyBFZXJc6c5aZbIsn1IhZj8XjD4KaU8sBtHneboQmaRhZDw6x18tUvcefvFz8m8Y2/kvjcZwQ+/lGbNfE1XvE4cVzg618TcLmAt76T8fCVlWKLHLaGxmsVdjuNrbipxKd2/E+esPKJAgGVx8PvqB1yj4dhZP0DNDIa62lc3HuPQH6+QEMjQxwbGyyPQ001wyfLyza2o6ubxvLQEHD+IhXJlpaBsLmTrMIafXk0WM9fkNmwHhajNYvKmm/7giCPXV+ncVRRLnDHbQx93CzacepZ5pLU19HeS6ZovEgJNDZSeY73TYPD6wVuuYn3Hl9n+NzjT6Q2yEyHwiQuwyPcwd8J3T1mqBMYInegHagoA6QhceQwiZASlug4KHDQzGeLRIHRMQpYhcLMc7rUyX5YWJDZZzY9zb91HADOnCVh9HhooOXubE9MyaxQAWB6KSUJXm6hcQmOk1iMBGhikgTO5aLwwOqq5VFoqOfPueut0ylQWcm+rK21SgjU1VlCM/n5JC6zsxKDw1Zpg9paEomyUivUsLubY+DWW6z2KaiwsWSSxvrQEDcT5heYU/XscxyX6+skWYuLJEKLi7w3r5dCE0Kwnb48koyVZfat2gzIyxM4fkwgEJTweGXW85pM0ivX1EhCGovx3+gYBVJ8PoGSEoG21o3GcVHRxj4zDGwplr0ZeXm8eb+fHqipKQP1tSQZhmQI5MTUxs0Jt1vg0CGBQx2Wl7Os1CrWvZ1hnUxKXOq0VDYdDkuJc21Nwu+z1DVfd78lNgIAXo9AJCrw/R8wRHFujhswCwuA0yGzoXBOJ8dxZQU3Wc6d5zHqWfYPACMjlqiMwqVOA//xsMyqZ9rtJM3NTRvXm8VF63wKo+PM8XzwAYHqaj7f+jpLiGYz7HauY0pyfluCBhKoiQmuTYvmPc/MAF/9Gs87ZXp+S4otQY9YnEQ/ErVyNhcXOW6lIREMimxea0mJlQcHaW5omV3u8dD7ardhQ4xiTTXX285uawMiGFSbJjJbY9AwzPBJbCzWvbxKMalkirnHx4+a+XgRvgdsNjN3zQyFV17ynaAJmgYAxsd++jMSa2sG/t8/Au94j0RTE/B/vyZw8oQmZq9GBAMCv/YrNvzyxwQ+/wXWuVtelvj0Z4wtQgUaGq8lFBSwxk8sZtU4Mwx6hmIxy2AUgiE/NhuNt0TCCkXy+wWOHRUoKqIhYbMxfyWRkKgoI9EZGeUufSIhkUzyOirER6GyAjh/nkZ+Y6NZmyoFHDy40QDyeGw41KGIGnf77TaG9q2sWLkyp56lgd7SDFRVCSwtM5ysIH/nkJuJSUpQH2jn/WUMgfl5y5MQizHEcH6BoXuxGL1BhmQbcpUU//U7NBRra6ySBZvfMKurlhADQGO3t49S4MkUDfmxccuDMTrG3BKApEIR3rU1GvWHOoAnnpI49SxD/iYmmZNUVcVz5OfTWEwm+UyUgiIA9Jo5gYpkKg+asDHUbGbWOjaRIOnz+1maIJ0B1sI0hlXfhsL0HG1WP4xEJDq7OAYyGSunb3GRHrNnnk2jxCxtMD9PgZaREV6zp4dj8bkX6FWLRnlfySTJJ8BzPH2K429+HmhrIYFyONina2ts1+oacOwIhTSUl6WlheMjGuMYjMWA5SV6JGw2EkS3KZlPkQ+qR3b3MMTxu9/jOFfeL7ud/SpNr6DfT2N6fl7iH/6RYXexmEQiSeNb1bibnt4oOpFOs32qJ6NRbCkOPjZO43xwiH28FpJ49jQ3PfK8AgsLZnhvjkNofZ21Abu62YfLK/QSul1AeblAXt7GEas8hzXV9AoPj3Cs5eZdTc9YIZara0BnV26hZWmuDcDZ8+zLgnyOg2jM2ogoKiIpnpjknC7It+aW282wafbjRtI6M6sK1/N3j4f/evs2jvWKCq4LufB4BO6/l3O3r9+sTzYMTM8aG66hfp6d45qztsYPNgtsqA5TeV3z8yTdRUUkYKrQ99PPkGQ+bZZUcDoF8rwUT1HfrazguBoZoXppV7fEt/5O9SlDIG02gbo6gYYGkR0oTifLLyRTGwmp18Pcz4J8RiwAJGJT09aa6fFwjVGes1wPmtfDdToWpS11qYtjy+XiPxVq7rALZAyK1+wGTdA0MDEpUVgg8JlPA5/4VeDb/yrxh/9b4Od/1gaPR5OzVzvuvF3gG18XcDiBd72PalrbSdBqaLxWcNutTghBL9D6Ol/oTY0kbSqfDKCRlB8EgkGBxgaRDXFcXKSBt7ZG4uX18tipKRpJTz1Nw9Nrqqr19dOwmZhkuGEuysoEGhuB1mbA7QSee56qkip8ysiQ4PT20guSTAGxdXrogkHmjbndNC6/8JABIWhg9fTxHKkUPSY9vdvnoAH8XNh47929rF+WzpBsAJay2sgIvVWxGI1TAYG77rRCHOvrJPx+9oPLNHYBk5DkCIaEQhuN284uhgy1tzJUUBpAfsBScZQSOHiAPyeTPH8qw1pp6+v0LDQ1cLe+uIiejbU17n5f6qLBV1FB+624mM8rF0q9ELDEAXx5zG/KrXPn9dKzZ7cDZ88Bz5+RmJig0aw8NCq8UoXbASTUHg//VlJMsqhygeLrJBmhEHNaRkcZOlVRzvtxuZhro8QpjhxmKJvygGXH6jIN4LU1jr3zF2nQss0CZWWsX6U8O02NQHOjqYy3CPz130o0NtCgdzoZ7js1TaLc28cQz3Ezz8lu5tyVljA/LeDn91wui6j6AyTDVZX8zvw8jeG6Wt5XNEpilkpaRN7p2qiep3KXsjmjsMakQlUlQwUbG3hsLCYxMUVvzVpYwuvlPMz1oDEUkz8X5JuFlMv5/YEBianprRuYTqdAIMCi4R4P71MRK69XoKLcOufcLAmh5Wnkcw8G6c22CXqoSku5NihiNTZOb5rXw7Dc8nKrxlwmQ4LXUG+FHCsIIXDDCQGfj892YUFiYVHV8cvpT8l1IxeRCMVPSkvYlx43iU9jg33b8gaVFcCRQ9a97hTiuLBIT1xhIeBxcyOrsMAar8Egx+mxoyZ5i1FgY2zc8hJ7PNwwuPlGgUOHOG6UdxiCocTpNNfiqSkrF3ZtlWHEDz8iEQxaPTUwyHlXWMj5y74zawKaY4JlCkwbSW4kaG6XQMBPr2NeHsflwgJVdxNJbqz58pAV5NlRMtOEJmivcYTCEr/0yxJf/qqB9/8spZq/9hUrdEXjtYFgkN60T3xc4AePAb/xWYmP/JKxwWjS0HgtQQiGA6rdz54eCX+AnhFV87GkhC/rVIqCO0r1tqCAxszSEkPHV1cZunWPmQdy8gSNj8JCGp3HjjLc6MhhhtxJKbOiAqeeYU2tsXGSo8Fh7sCrUC+lGtnSwtyfsTHA5xVwOuhx8HjMXVw3N1+EMBPkU/x/TTWN8pZmyzhbWd0478tKaZgoGfaJSaCqUqC5if2QTJqGlge4924aSdz9Z4ijCq0aHSP5KSy0alMZhsTqGo11heJierUUjhxm2JTNRoPrja8X+JEfFujrA/79Pw0U5Es4nBtzRCYmGG6WyZC8+Pxsp8fDew+F2IbjR0kqbYLGp9f0LoyNSUxPS6yvWzLmAL8rQSNxLURiopBK0YAeGSVJzWToPbPbLCn3+QU+a5tNZInFufMkToEA29jaam2SNTVSZOT++xwoKwUCQZ5bmB7eVAooL0U2P6ynl9L0djs9wTfeYI4T81plZcw5czrp1VlaojBYKCzx7Gl6vPoHLbXAYICkPxBQXjA+w9oagbJShshVVtAbqZDnFaivF/T4lTOHnfXPBFIpkoLqSmTz9aTkOYNBGrZut0BpKds5PmF5f0uKSXxiMW5+ZDIshr68YglwhMNyg2KmECTI6TS9QekU2+v3s18DfnrHcjcnXC5uuBw5LLBoqkW6XRwH5eUWYVRQ9dS6e/h7wM+2HjzAz8+eozdIhTgeOMBQPLUB7nLR476+zmLX8wss/zA2LnGow6qjVVzEsVNWJvDCGT4vJemeMUjeR8dM0pozhTMZifMXuD4ZhkRnN+dySXEOoQEwOWGJcCg4HPQUdxzkOQzJdW95aSvzSiYlEkmJVFpmyeBOBC2TAcZMEZK5eYnRUc6B4REglTJQVcmcvplZIC+P+bRCcHzMztG7OjJqlicZkJia5N+UV6q0xCqHUVLMMWCY7m+P15qbs7PW5+1tLGA+MqoURBnO6nAAFy9yoyce5xydmaFHPxdTM5KlAUzP8vFjHNd2U/FyeNgszWHOxc3hpJuhCdprGHPzTCD2eoDnngce+oLAu99pyy4iGq893Hm7wF99XcDnYw5Df79EZtsYBQ2NVzeSKYlQ2BR5yHCnenWVu+LpNHdkMxmGzKkwyHTaqvVkszHhPxZjeJVhMPwqGpVIG0zyn57h91ZW6WEYN3dewxHW4VleJiE6f4FEruMgDXGvlwbW7CxFDmw2Gup1tUBNDQ29oiIaoc+cpkdp3AwJ7O/njnRtDY3msQmJuXkJYbPyUV44A1y4aJjFWCWmpmhkBAM0oirKmesyOUnDJplkTtz4BAUYxs3cEgGgrMyql9TZRYPL7aZMf2MDjRkVqri+LpExJGbnTCnqNMMho1F6afoGSBxOPy/x+JNUBLTZ2L/f/BueQ0p6ztrb6P0pKiJpvHCBfTQ+QZLU0CCy4Xp1dSTTiQTzkZaXSdLsdj6PSATZelxKGMTvJ0lTYgEAz6/kuW+6UWRzszweSoArDI+aAg/m7yqcqqeXpG9tjX0lpcTwMInLI4+mGQpmku3xCfZjOk3yHo3SS6uk2qk+KLMeWWUURqMMp3O5uIngNMsFpJIcdwBDQsfHeZ5oFKiuEigsoGFeWwtAkrw5nSQLXu9GQhCJMMTx2dPA9x/hM+/sAjq7DDz5tFk/rZvzaXCIZDwQZPs7uyiGsbzMjQ1VKxCwQhzX15GtbWV3UGGUeZASCwv0Qj/3PBs0Ocn5NTlJz29BIUmi388Qz/EJjsNcD1osJtHZxZyjpKn0d6mL/RQMbi8v73QCba0SZaVcI0bHSOicTt7f/Dz7/vwFiTNnDZw5SzIsJT87/RxJnKppx5w5XluRT5I4ej6HRzhflXctzyPQ0WGqGS5ggwvNZmO7Mxmeu6aa9zA4ZNUPDIUkqqoswjYzw00ij4cbOE8+RbKSTpNEhSIb739+ngqRA4PA3/8DhTgAJe2/UcxEgp6+PC/nWkEBNyIyGYZRp1IClzo57598GujsJLkNBjmf1UZSfZ1ZAiVEAjYyys0WlTO8tMR25ecL1FQLSGmSxjTvc2mZ4zsS4QabIYHjx0ngKys4Dnr7SFCPH+M89fmoBpmXt3UMeD30tNXVcAycPc+NFrebnrPSUoYBqw2+zfnGm7FHkVuNVxtWVgy87Z0c3O98u8Bb3oQtSlsar00EAgKf/LjAA/dJ/N7vSzz0ZeBDP2fg9a/T+zka+x/t7e1vBPAnAOwAvtrX1/c7m/4uzL//MIAYgHf09fWd3XyexUUa5moHubAQiEb4wvf5rfyFkmKGMHm9fGlnMsxdKS4CystpZLjdNETiMRqyFy5wh9cmZFawQu32vnAWuMn0eqwnGEZ2/BjQ3UcZ6nSaoTNj41YIn81mhig6KWzi89H4cLmozNfVzWP/8/vcge/rZ4jRepwG//AIwxPLcgwGn4/Gi89HYzGRYOgOwPswDEtiWoUjKcO7sYEeo/Iy5losLgIPf99ATTXPNT/P8/n99EzZbJJy1uOmJ8vFvlSKdUvL7H+VH1OQbxbMjfP7Ho9EUyMNwbl5YHlFoKSIBGR8nG1taACmZwScToaCzcxItDTRI2m3AyWlJBK11aYUt8civvV1JFoZw/SgmQQtGGT/SykhwBDXI4dJNF84w13+ygreq8q/Ki8X8Hr4czxOoz2ZopHq8fCzlRXeqxACDofE0jLQ3iYwPWPVTmptobfDbuf4ml+g0akk4KUkuaiqZJikIjnr62atrUHmfHk9QHW1QHGxwIMP8JjJSYm2Vo77s+cYEpfJAHfcxqLmrS30InV2sVZWOk3PRU0Nv6+8tu2tDEEbG2f44vQMn10sxrbOzNIzOjlpisw00ECXYB+shWjYFhXwvIEAssaxlDC9OQKFRfx7ZyeVAYvNZ3+pi8+9rsbyXESjzNOT4AZHRbnA9OxG0uVycX7OL9Ablp/PeReJ0GD3ek3hnJy9S4dDIBKR+N5/SPzIDwuWKZhjDcH1BDcB3G7Ou0SCocdOJw15kkWSkAfuY7+Gwrz29Az/brezrz1uZOeRBO8fIOFfWWFulaqbp8aBEAy9XVrmxkp9HednTTXJTkEBa7tJg21rbbVyChcXJf7texJ33AY89wLneHkZUFtjw5NP0WNUXi6yoaelJQLNTXKDkMrUlCV0wzbRG3XTjfS8Op1cU8vKuDkxOydRV8vvHWhnm1ZXSWA9bhL74mKS0+pqoLiIoeWzc5I5uGZObSRiijX1S1RUkJgBAvF1bkbE4wwPnp/ns56bA0pLJOx2ga5u1hesqeY6EIlyDHu99Ahv5xlMpYCSImBgCLjnbo6t0VFubCnPWkE+zEgLwZzNXaAtrtcgnj5l4EMf5ov6a18R+B8/KTQ509iCm28S+Mu/YDjWH/wR8E//YuiC1hr7Gu3t7XYAXwDwQwA6APxUe3t7x6bDfghAq/nvfQD+bLtzFRdZ9Xomp02RADfDEZ1OgUzGyltKJqm+Fo8zNwsgSfG4aWR6PPQ03HsPQ5luvpHJ/0oa+o7bBOrrBNrbgBtOWMb03Bxrf8XiwMQ4QwuXV2g4FRXSYA2bXr6TJwTyPKwr5PcLuF00vuJxej5sNpKYZJK714l13ktxscBttzDEcWwcCK1JhCMSeV6S0JQZ3iYlc5BOHmebW1sFqqv43ohGabA7nWxHVRXDLVdWJc6fT8PptERWhKDxPj7BPl1ZkRgc4rXb24CODuDIEUsNrqGeypCFBeyHZBLo6BA4cVygf4BhhUXFlpLk1DQgQJGGxUUzjNRJz0I0SkIcNXPCFpd4P0NDlgplNGbmGg1awiErq5bBGzNJ9tgYv7O8wv/39klEIvT8TE7xXDSklfHI74+OSTOfSWByiqItfX3c7TcMPq/6erP2mZSorSURPH7cjqpK9nNJMQ3ZTIb/SkqAtlaWYKDXR2J6hv2lctnUmCouZuheQaG1KXCpk96Shx/hv6ERkvbxcavwdWMDyaHTyXuzmR7Xhnr+rabGIobpNAmn20MBk4ICejH4d1Od0EmPRDLJTQCfzxIiAUg8GhsEPB4a0/V1MquOGotZIYljYxQjWVqSaGggAW1pse47keA8WFkhcVlf52ZFUSHzR30+ktVcD5rDIVBeTlKzukbvopR81q3NljqjIUlgkgkKfnR283x2G++5vZ33FzHJwKOP83tVlQLV1QI11dYaY7OR2Cuxm2iUIXFHDotsiGNjA4me10tS29e3sQzB2ppF4GX2M3qHzp7j+tTYKDAySm9OOs1+7B9QxMEKre04KFBVyXppo+ZYn5/n/2uqgd7eDD2fm+TmWaKJypTpNENR/X4SqmyJBMnSFTOzAuEIwwW7uizRnYFBjvm2VrPmo7lJpDZFEqbXcGaWYZ3nL9ILabMpwRbB8efm2K2vJ9Gva+D3/D6OheYmkraSEsExUcRosqlpoLLc8kYnEsDzL3AcqRpoqnxFrkU0P8/xW17GDS913y43N8/CEf5Ta0muOux20ATtNYRkUuLzXzDwiV8F3vgG4E//RKC2RhMzjZ2RlyfwG79uw+/9tsAXHwLe9q7tE6Q1NPYJbgYw2NfXN9zX15cE8LcAfnTTMT8K4C/7+vpkX1/fswAK2tvbK3MPSKclbHYacG43vTrtbXy5Dg7RkLLbSV5UiBDAF69NmHWA0kBpqUAyaRX2ffRxhm2trTH3aX6OBkdfP/OdOrv4gldKgZEICUt/P0nekcMCjQ00Lg3JsL+paWkqCpKoVJYLhMOmMRsEzl3gLvzZczzf0hKNlspK/n9gSGJs3EA8ToPldQ8wP6i3j6GdCwsMHfKbwg1T0wxz6+ySGBySZi0mVWyZ8vjnzlvS/vV1NhQUAIcPsdDxwgKPO3iAIZsuF43uw4dIeqamgIsXZVYkZHGJ1x8eoUGzvg6cOiXx2OMSDfU0MMfHYKo6Mkm/r5+em1SKnonWFqu489gYsrv+hQUkTq2tNOCTSbMI8AAN7bUQjbR4nETIbufzWV21PEAlxabxvmyFuHq9HC8qT7CkRCAYoCBXMMjnmZsndcNJ3sfoGMcYcxd53sEhnvfJJ9MU4LCbXsgFK8xqZoZer/i6Gr8ktG6XpeKoCNrqKkP3CgtINMrKGe6qCvQCwNHDQKmZB7i2RqPdbue/igr22dSUqUjnIGGKx2X2Oj29bP/Zc8DTz7Kt6TRLVoTCbPfEJMODZ2ZJZnw+bkiMjnGMTM9QzVEJgQBWGKr6GaAR39zEebS0TG/h6ef4D+A1kgmOm75+enhWV0kQPR6BCxc5PnI9aJEI+6inl/dYVMR2Tk6pDRnr2HCEfZRIcEz7/YJy9YscS3l5nIcLCxZBmZqWePIpiTPneP61NZ5bzcvqKt5PaRlFSS518r07OcWx19dPw7+52RL58HgEmppYKmduziIBU9P0/iiJ/KUliaOHOTdn50wvehHnRWGhJbzTPyAxMSHhcLB/Tj/H4zxuoKsHmF/gmqHGuPKmx2Kcq1PTEqurVkhxOs36b+vrXC+qqkgKw2GOqePHeEzHQbazs4vzfWrKlMQ312Onw8oBbG0xvY8ejpHhYfZNOs0yG4tL7AuHA4CgGi4ALCwBZ89RdCeZ5LwcHCLxa2rkfPD5eS8Li6bgkRBobeEGWyi8UfE2k6HqaGGhgNsNHGjjGtLVLeF2S7icJIhVlRSHUWVaGhuwKzRBe41gcEjine9lEuvXvwq89adt2UGioXE5HDsq8NWHgJtvBN75Holv/b2xobaRhsY+QTWAiZzfJ83PruiY7/8ghcUFemASCXqsVKFUhwPZxPylZe4mu1wMEfN4BIQQmJmlxwug+mNpCQ3jgnwahhOTVNGrrKQhvRYCIEgGn35awjC9cCmTHNxwI1/uk2ZNrtVV/mttMUPxBHfUU0mGbUlJo+L8ReCmGyQgeY35BXoWhoa5wzs2zlCutTUaIsqATia5Ux8K0xtQWkJvyvwCP5uaMusTFdCwm50DKiqoHBgOk6CuhlQooMDsLPCd79KD19ZKz46Sj08krNyj9YSZf9VNA7V/gDvkIyM0Wh0OfrelmcapMqoL8nneTIaCI4bBttbUsK8vdZq76D6B5mYahGPj9HbOz9MQKynm99rN8C6P25LVrqqk19TvY9hZbhFwJbl9+20CBQWs35UfpPBHXx/bl05LDAwxRLaokOIaVpFjquQFAjTYgmb4rMtFz57yGNXWsobYzCz74chhEl4lsJFMsY8OH+LvS8v0/NWY4h2KoClPx/AIzz8wYKrSFTDX6L57aNh6vJZC4MoKn0VFJeXxKyuAujqB5WWS57l5S1zi+FFeoKyURveRwwJ+P4+Zm6eRvRbi31dXec8Dg/RIqE2Iigphqt2ZYg55NGqLitjfgRwFTyFMlVHB/mURZW5sAAyRq6zipkJrC0lSNMbxNzQkcfiw5YVWyMujZzDgNz0tzSQO4TC9bUpFUEoWlDYMPpe1NXoj7XZ6bHO9nM3NljqoKjzf1sK6eYWF9KA7nSQBNhujmlxOzonqKs7BaJTzpaWZ60g4TOl9AFhPSEzPsNh1VRWyrp2SYn63IJ/jOhrjZsLcHMkIb4QbDpEI52EqJbPFmGfN/MFbbjaFaeIk9r48gZ7ejWUmAIbYHmjnNfPzSZ4LCyw5/3SaTevp5e+1NewfFY47OcUxfaCdbVVeyIUFkr1QmOeSUmJpiWO0qkrghpOc24cPcW411PN+6+o4xltauJEBADJjFdJeW+P4VoI3ak3qH+Aa1NTI0MtQyIqSKC+znqU0rPDdeJzlTZZXmFMZDgPf/R7Xs0SCfUUvLh+OqrG3E3QO2qscmYzE33wL+L/f4KLxf/4QKC7WvFzjylFfb8PP/xwwPWPgb/4WePQxif/1m5lsKImGxj7AdrtOm3cSLnvMGx504+w5G554MgWbTSDgA6amJF53vxPpDNA/kITfL1BXa8PAoIGSYhuWliUCfjsgbPC4Ezh8yA3DEJhfSMEwDNTWeVBaJnH6dBrHjtrRP2ggHJYwpMD999kwNJTOijvk5Tnh9XBrfHQ0g+VlB6amM4hGDPh8zEsqKbbB62Uoo99vwx23OxGJGJBIorjYiYKCFFIpoLfPjoMHbXjmmRSOHRFYC0kcPyrQ3ZPBnXe4MDRk4KYbnRAijRfOpNHXb0cyIdHaakdleRpVVTbMzBhwuexobREoLrbhqadTaGkWWFpiPsbsrIHFRYFgQKC9jXLe1ZUSsTjDz+rr3BgbN1BR7oTDAZSVC1y6lMTaGlBTY0M0CpQUSzTU22AzSV48JnHjSYGqSjsqq2x4+PtJJBKUsm5sdMDvF3jiyQSam2yoqHCguzcFX55AUaEqJCsxF5a45WYHWlrsmJo2sB7PwOEQiEYNVJQJOOwOnDxhw9/9vwSqq23IDxgYnwAOtNkwOGRgZUWiqcmO0JoBp9OOvDwBw6ABu7ycQXWVgBASDrsN/QPA7JyB/HyBuTmJtjY7ICVcLoq25AdtOHbUwNCwgRtOujC/QBZuGBJraxm43Ta4XHxnNzTYMDNrwO8n6c0PAGWlDhQU+NHbl0QwINDXb5jXF8jz2nCow46nTyUwPi5RW2vD8rJEY70NobBEYaENbjdz37weirzMLxiApMjG4KCBhZMu9PWRxTkcAotLBtbWJIoKJYJBG244acPCokR9nQF/wAGn046mpgwcjgwyGWQVCYP5dhw+bCASNpBM2bC2lkGeh4RvYsKAq8AGX55EQT5JycKiRFMDPV/FxTaMjhkoKRGoKBfI8wmcOpVCMCjgdnOMVlbYMD5uoKBAwOsR6O4B5uYy8HpZFHtiwkBJsYvlLTwZLC8bmJyyYWnJQGmJwFIUaGlym0WNHQgEbFgLJVFXZ4d3zcg+E7eLpHV8IoNMxgmBDAzDwLGj1uZ2KiUxN5fBbbe40NaSxsKCgMuZQU+vHcXFNjQ3C/T2ZZBMZhAJ21BZSfJVXGxDRYUdi0tpzM6mUFxkz6qxfue7Eg++zolkIo1/+56BG0/amPvkYX06l4vzY2nZQCjEENCyUhscDsDrMTA7a6C11Y48nwOBgB2PP5HE+rqB3j7mhLa3Ciwu0/s8PmEgP58ew5ISG5xOicOHbBgYyODWWx2IhBkS7HJJxGIOJBJp5HmZP7WyCtxwwpMVvHC7BDIeifWEDalUGoGAE3neNObCEm43UF5mQ19/Bo0NDnR1GygokEgkbIjHM0inBeYX7YhE0kgmAI/bhkSSQjsjowYCAYHiIgBCmGM5DY9bIBLJYGCAi3dRoQ2FhQKLixIOOxDwC/h9Bvw+O04cB5obnTh1ah1TU0BjoxMBfxr1tQLhiERJqR1Dw2lEo4w+CAbtZpFyieVlA26XqcAp+X8jA4RCBspK7bDZgLJSieIikmkB4OQJB0JhiaefTqGsjMRbSgNOh0QmI+Dz2SElMLq6TSJbDjRBexVjakrif/02kzgf+oJAVSWT2TU0Xgo+/lEm2n/zb4CfemsEb/sZgZ/6CS0yo7EvMAmgNuf3GgDTV3pMNGpgfCKaVRhUIhMSKfT0MEwtGmV+SjTG0Bi73VSYM0OGLnWmEAoLrK1JMzk/mQ0zDPiB6kqB/+hkXtcPHuUucSzGXdv29nXE1zmfGhqAudkk8vKAygqBjCGxuAhE48ByP3epW90CFy/Fs8WfH30sgXSaYWO9ffTwTUzR62MT3M0tLwfOnE1hcBDID8YxPMIwqNtuYY7Kk09JxExxidk5hsUPDALhMEnQC2d43yXF9Ag4HNzdjq8D852qFpJAx0E3Esl1NDcDKyspZAzuWjc10diJRql8F41Z4XhC0NM3v8Dd7ZUVenyKCtlPj/yABn9jIyAhcPESDS+/n94IKaliOTwMJJIpOB0CAwPcpJyYNIU1PALxeAKDQwJNTVRLtDvYjguX2K/RGBCLpRBfByJhwOkQCIVkVthhZJReukSShbxVKF5+Pj1FyysiG3Y4Nk6BieYm4PTpJMIRZKXI29vpYZ2bZzje+ASfUWkp8/RsAnj+jEB9bQIrqwy/jcbY3mSSanEvnGNIpxI3aW3hjv3EJHDyuEA0ymezsMD219ep3EKOMZcrhUSS3t6WZoaqetzAxU56emfnSBLyfAJTUwnAEHjmtERJCcMNAwF6TyJhie5uzg+Xi14Cj4del9paempdLrZtbJxejsJCs5ZfP71TUtK71t5GkQ2bDYjFkgiFze+7GQrZ2ipw950M4UulJC51csw/8mgS4xPAwQMCs7P0eDidPP+BNg8udiZw8ADDE599TqCyQiKxbj2rUIj13Twenm9+gecrLKR3RHmGASAQkOjpS2F1DbjtFgACWF5OIRqzwoldbnolXW5+7+IlidlZgWSKoiZLy6mscEpFORCPJ+Bw0kv4wib5orJSzovDHeyb+Xkgvi7Msc9xNDGRQsdBwblabGB0nJ6qrm4ec8ft9Iqpch3FxfQA1VRzDNXWAl1dKcTjyOZAdnYn4PVyPegfAPIDLrjdSUBSlCOTpoiO18Nn09uXwNQ0vaaBgCVms7aWhMPOueL1CiwuSRzqEGhrAR57TOLAAY7T7h5TFVFwnDudFNuIxQR8PolEUqClhWUGDIPzsa+PfZznpaBROs37YtRDHIkk/9bbm0QkwnnWcYD5byrUMhhkNMDomMyu8flBbiopzC5K5OWx3wWAtZDE1DQjjTh2KHwUiTJUsruHXlC3mx7I9QRLbDQ27h6FpF0pr0JIKfHP/yLxrvdJHDzIwV5aosmZxsuDwkIBv9+GZAr4bz/mwmOPS7zvgxIDAzrkUeO643kAre3t7Y3t7e0uAD8J4Nubjvk2gLe1t7eL9vb2WwGs9fX1zeQeMDFhIJUk4VA1p5TUem0NjY1MhoYIC+Cyvll8XeBiJ42CMTPEsbSUYgDpNIslB4M0ri910RAuLaUBkZfHsJjllZzCu1JiZUVmw4T6+ilhPzdPktNxkN8XgqFfqRTzKdxuGu7pNGX6qQJI9UW/3zLckybBcjiZ07a6yo29hUXusK+t0ZCvqAD+7XuUvI5EaKzX1dHoXlzi/ebnc1e9oIChQnPzrMm1sCAxbYqslJYyPM7pgimDzTpjoTAJWJ4PgAAKCnmeiUkaSPMLVqhRQQHrdZ48rnLDJCormEeWyfD+02nmopSX0/jq7mFbvV6BxkbKdQ8OkjivrMismEg8ztC4ygo+44MHGBpWUAA4zPIzq6sk4HY7r7m8zH48fozhjV4vvV65uYmpFA3+/HwKFDQ1WSFSmYzE8AhDypoaWR/L6STp6+7htQwJtLfa4XBKrKxaIY6zcyRyXi8Nz6pKhrdJMz9xfp6hXmqTQUoaln4/x+fICEmsw8HvP3CfwNEjAkPDVmihuufpaf5+qVOitITtAhg2RoLE3z0egeJi9v3BA6YgST6J19gYidjKKvtWCG4KjI1T3Ka02AxxLBeoqGA7DdOz5HTQi7KyStKkFCOXV1j3LJMhaRc2bg6o8L2DB9nW8jJ6d8MRCZsg6R8fYwmG+Xkrhwog0Tx4gOdIJTlvjx6xinyzCDtD1Twe9sv8AvO9Ors4Hvx+9nkiAdMYt0id2w0cP8a1hGUGBCorRbbOl2HwuHSaOVdNjewXj4ffbWvlPGEJBh4bWpPZHMf6eoHpGZao8JiKlBnJ+eNwWKUHWlvMEhlhErjlFZKi2TlTHt7DcdTbx/UjmaSX6J67gOISgXSaY8MwOIdnZrnx0XFQoLaW4+DgAQouRaN8DtXVJDJzc/ysoZ5hp0tLEjU1DCEFWOrBbme/eb18XgsmeZ9f4LwZGjLFZQpIgDo6qNjp9eaMvQJLoMdu58aP18M25+WxtuTEJK8DAEuLwLOnGXbs87GPKiooBjM3R9GTkhIrZFiCbUqnmUqUn8/1Nj/I/lY5eokE18lYjNEBDgeL2O8G7UF7lWFlReK3fpcP/pMfB+69x4b3vVtmww80NF4uvOvtAvn5HqytJfF3/wD87C9I/MSbJd72MwIulx5vGtcefX196fb29g8B+A9QZv9rfX19Xe3t7R8w//4QgO+CEvuDoMz+Ozef5+BBO0pKBMYmJDIGd9qTCe62GgbJh9cDuAS9KO1trNfk99EI8Li5keFxA+MTJgEoEAj4JWbM3I/RcYm+XuZG3XiDwNAwZd+npukVAkzDJwQMjVBR0O4goQqHTVW0OL1a1ZUSb/pxG9JpCa+XRrLPR1GG4WHgzjuAM+eYB7O0RGLX3QOcPAkMDrBY9fo6RQsmp5ifEQrROBkaEchkZJaUVFVSztvjMQ0RU/1tfFyipprewVDIlLifYChdTQ2NmISZy1dcRIN+eYX3s7jI45WwSCxGg+zwIYHqKnpAvvM9GsV5eZS8dzqZl1JejqwwQmmpdX23SQLzvEBTI0sfLCxQ6W1pyax9tmwWPjZFFHw+oKuTXoPlZaBnmZ6KggKKbAlBEYZ0msQxnSY5WQsBmbTE+CQ9ZJNTvEcl9iIEd/8LCtjv7e1WLhhARc3lZSAY5K69KlhdZBq2dbWAAeYB1tdZBY/Ly0iYpSTxn5y0apnV1/L7U9PA8AjJQH8/x1tjgzBr3LFNQ6a4wsws5c1tNpKmVIp9ooRWpqd5f4ZBMnTiOI1lr4deAYDiJ0rmvatLAoIelpSZV2e3s91lZQKtrRSTqKk288AclIGvqaFAVVGRpBz6OoueLy+TIPT0MkcJACYmBAyDZRrq6+gpXQtZIhkjoxxf6TTJaSrFPvD76TkNh3nO3By0dJqlGJQAzOwsNyKiMWSLs9vtVgmI0hI+l2iU4y2V5oZJY4PA8Ahz3hYWGQrncDAEuKeXHm27nUTvUAef+dOngDc8yM2CkVGuFeEw21RWyrGxvMw5PDPDvNSaagGfn6RgbBwszbBIotrXT/K0ssL1I89UKi0u4trhy7MItj9A6fvlFd5TPA4Y+RwDMzM8xm5j3wkhEAwKFBZybths9LQODVMEqaWJ/TM8zO9XVZG8lpdx40YIbkLMzTPvcnWNfZxKc+OgxPTkDg1zXvt8AtKQSKUsz1rGsHLZZkxPWTzOtUEptvp8fA6BgMD6uoGBQZ7X5wPKfDx/Qz3nVnk5iWsiwfEeDpv1Bk0vo8vFc0ci7DOVBxkI0POZTPI9cagDWDWFTY4dYRmQrm4eqzaohOBz2Q2aoL2KcPo5ic/9tsTttwG/8CHglz4O3HKz1J4zjasCn4+7xV/5c4FEQuLPvyTw278n8dgTEp/8OHCoQ487jWuPvr6+74IkLPezh3J+lgB+brdzLC0bOHOWO98eNw3UvDzA6RIYG2eB5NCaWQ8tSeOuqJAkqq1NIBg0d1qbWB/N6QReOMOQl7l57qyOjgJLK8Chw9yxjUYZyjY2AdTWMM+jt4/GRHkZiUc0KpBK02MUi9Oosdv4sr/UKXH4EMtjPPU0jZP8fIbmqcLPyqicmjLrRF2iYeJyMUTn0EGBW2+hYtn//YaBYJAepK5uGtTr6xIjozTgolEaehXlNPJ8PtZcGxikZ7GhnsZlQb4d0VgKBQU0bJxOhkg1N9HzGAoxzHNhkcn8hmQ/3HQjMDIqMT4O3HwTSVVpCY2a8+dpjNXVsa2d3fTE2e1AQQHXneJiSoxHwjS41tb495VVq9hwJMJ+UcqERUXcER+fIKFKJE2JbDsQSpo1oMqBp06Z4ioh3qPNxjwxCRqPDfVmgWtTidLhYFj4xCSfyaVL7LtgEAgGBA4eZFidCkudnaVX0+nkfWcMwO/PUO48A+Tl0dC3mQIuU9Nss8cDlHlJmvymIa8I1MycWdPJHCtVlbxfl1Ogvk6isdFSEfT7aIyHw8DzZ2iYrq3SyKaKKdt47jzvZ3AIKC6SKCpimxbmgXgCWAuzL/LzOc5KTEGasjKB5WWGJJaWcEwWFwPDptJmKkVvcWM9icjQEEm3InqtLSQearxf6mT5gkudnJuDQ+yTw4dI6qurGYI6NExxk+4e4EA7Sd3sPL1HNhs9jJkM729k1PI42+0MXa6qZAihYVAq3+tluG9PL8MNW5o5ZuJxjpV+M6okz8vvr6/zfP0DEuWl/Fl51x12AU8QOHmCxdJ9PoGyUhakBuhJS6Xp2QqFgFtvESgrY6276RmJlmZ608rLSDrbWklyG5skzp7l5kx3D9tVW8u5BrBPa2u4weFx87r5+SwboTYJ3G6OBZ/PVE2doCCGyyWxtspzTM+YYiQFphrqolVMPBAgQWxsIIGx2Uh6ysu4aVBVRWGRp05JlBRbHsmFRa57UjJPrrCAbQ4ESMgqyuktE4LtPHfeLFlg53cL8tV4IuF2u5XSrLmRE1YhpZy7qtzD8jLX6RKTgPl8LE+hEI1SHAag9y8S4fUOdQgIm8TUFMmyYQCxuIRhCFRVSazHGaK6skpPXUP9bm8hHeL4qkAyKfH5Lxr4jc9K/PzPA//9vwnU1tjwja8LTc40rjp++qeAd7xNoLwc+J3PAT/2XwU+8ksSf/pFI6tWpKHxSkI4TC9AfJ1GvMtFb006LdHeRiM3ZYb3tDQrA5wv8nRaYt6Uki8rY+H3qioa5CePMxRHSBo0Lc0MXSwtpfFaUQFAWoolhQUkMw4HDaRzF/gXJc1dU0WDLhyxQuZmZ2nAZDIkUfVmqGJrC41Br5efJ5O8r9ZWGiIlxUA6Q6Xfnl6JjoOUlG6oJykBYBqDvLfWFoZdzc2T3CjDraGe3oS+frO+UXcGff3c2Q8EKDlfWsqd75kZmVU3m5un8RkM8PuFhdbO/ugYPSbFxfz7bbfSK0ijnYZbUxOPHRmRZj4SvX6hMD1ppWU0mMrLSGQmJtlHAdOzVVUJuN2sRdfaQqPw4AH2VTAAM9GfuWoHTA9YW6vA0BCNzLo6GrZOp0A8Tm+AQjrNumTFRbyHQ4es2nIV5RI9PSTUBQXs86Ii3lv/gFWX6thROwoLTCEC87U+N0ej0+fj8ysuQjbkbniYx7Y0A8eOAdEwDdfSMo7B6Rm2O75uhScePEChl9PP0aBWEu4rK5ZXqH+AxnAwwFp34QhJkMq/83oFTp6kcXzkMOvVHepgIeOBQZY3AHj/RUUc9ysrDG9taABaWgRKS2iwu9wMi/R6SQKqKpWKJp+NlBLjEzJrJFdVcm7ecIJeDIBkxGE3VTIbmfPo89FLu7TM4tsjowBAz/DMLD1EhzqAG28kyaiuBhqbTBn/OM/rcHIDQJH2SJgexuERkjSPh/0yPsG+q662QhwbGzjvysrp9fT7BerqSG4Ng2Quk2E4q9vF8dbezj4tLuL4DAa47uTlUShoaYlebFW82e5gWF40aobvxjivSkuA6Sne/8ED3LxwOLj2zM+zT2dmGMZ3qIPtHxikgmc8znu7/16grdVGr7iZf1tYyHN5PAL19QIVlawld/gwvWxxcwOlrJyhjyurnPM1NbRhJyYl8oNWvbOmRv6/vJzPPBbjGuhykXwHg/RUA5yrdhvnY0Md+6mhnqqqKqQc4POoreFGkhDsj6lpzoW2Nh4zNc3rhEI8z8EDXJ+nptkv4+OSJNn0fk1O8j4MgxsfHre5cWbnc02mSHzjcZLO6WnOzcIiy8u7EzRBe4VjfFziAz/HpNy/+IpAa7PA7/8ha9PoMDONawGXi/Li//pvwFe+Brzpvwt8/c8FBgaBd7xb4tx5TdI0XlloqKfyV0kx8zAmJpGVNFeS9EVF3Bl3u/md6Rl6lkIhEqvycgFVyUTVTFs3jdT5RYa6KInypkYBn4/nOniA4UMACUapme+Qn0/jXknIFxfTmOzrB244KdDSzO81NdKICQZpYJ89x2T0kVF6R8IR5mq0tQrcdQel4/PzBcrK2NZ0mu1gfpjE+YvMwwFo4BbkM0QnYwqQHeqggTcxQQMvlaKhdqCdxW6VEVJuEqSlJRqe+UFLIj4SodFaUECDzG6nF6S5SaC5mWGFY2O85uKSVTIgHifZXV1jWJSUNDQzGZheAPZDfR29QiUlIkvY6uusfqqupMFmGBJ9/XyOKnzKJmiYq7plxcUkqvF1hg46nCTUT59iHTu/n2Ifbpc1nmw2hhy63eyneIxtTKWskgKrqzT4p6YZLpafTy9IOs3/Ly+TWLQ0I6ucV1UlzALH5ibCPA3qWIybA4c6SOL6zXw8m6AHIxCg4anybhYXKbDw8CMSFy6ykPZaiP0Q9DNP66YbKat/8ACv53ACLa0cxzecFNlcqEiUHoPDh/h7dzc9ZTYbDdWFBfaj18tC55EIwyWlwX7t7pZYXqEny2YzSy+EgLlZzjFhowc4lbLmYzLJuSAl52ZXtyXVOjLCcdA/AMzPS2TS9Jrk59N4/4//lPB4aeDH4/QGJxIka+Ew5//QMPs2kwYqKwWKigQcdvZ5KMR2VlWxbYWF9NbFYkAwX6C5iW1RYygel9k50W2GvUUilMi3mwTNZuM9pVIkMNPTVnkFp5NjubhYIB6T6O2TWFzic6ioIPGZn7dqgo2O0CM0MaVKFLBnCgo4vu+528wjnSYRsdlIqEqLgYYGloRobCARUaUhuHFgg9MpkOfj2HU5KT6ytCQxNiaxFmJu4KVOeo79Pm5yDQwy3E/lcPnyOL6FYF+ur7NdKytAq7mm1dYKlJVxjVxYoJT9/ALX4IFB/uvrp2dyeJR9tbrK4uH0fLLYd3kZw5lbWgQCAYtsv+XHgaOHOJcypgT/wQMk2T29lievoIBr6OoqsrtobW0CHQe56VFdxc+OHuF9RCISFWUCwmaGXbs51g8dYl6yuIyJrkMcX8H43r9L/PHnJX7izQI/8WYW2jt2VOChL1iF8DQ0rhX++48ByaRAMsnCjH/8BwLf+Tfgk5+SeN0DEj/7fu72aWjsd8zOGjj1LA0Xv98SWrDbBebmmQsSCvEdrUQaykpZhyk/nyRocUGaRIsv64lJhqdVlNOQVPWRggGGpy+vMIypt487tLE4wyAbGyga4PPRQwAA1VU8vqKMHrLFRYlnTlOBsaREYGaGHsDCQl7rmWdp7HV1kzj09gJ33cnCsXOz3B0OhYA3PChQU8OcnhfO8N7rapmnBliGpgoXa27mPVRV0mtz911Mup818+wOHQKEsGNlNQXDoOqZwy4xMEgDyOGgLHZ9HTA5TaMWoLF3+23A2fNsV1MjCVE6zXC9afPYigrm+fUPMPfO5aJxK4RAXS29ELOzliqc3U6DrbqKBrCUlnKmKqDscm0U+Mgv4PONr1vG68gYd8pV7TEhzOLC+eyzH3o9sLjM5w6Y3ytiW2prgZExPtvmZj4Pd6VlLJYUm4Ipefx+LEaDOB7PYHqaxLHjoITdzrU2GOT3xsfN2lMF9AK43QwNDEdIjqMx1iXrH7AUMZVntKpK4OABFlEvLhY4c5b9WVsDTE3T4zE0ZBYsfp6G6uoq0NNDI3ZkRMLvZ+iix817WF3juYuK+TxVvTj1jBcXSdxamjnW43ESMFUUe2AAOHGMfx8dNfOQ/NwQVES6vY1eus4uAJCYmeW9rq7xeZaX83koxcpLXUBBvkDfANDaQlVNkk4BuwMoK5OmGBCN/PwgPWzBgMDKKufl4iJDUYuLzBDHIm5+KHEcJUDhcpFsZsyfkwmeN5mk56einOOusJCf2+3IEoSMYQraNLCYMsDxEIvx++q55fkYKjw2Rk+v3c65EgoxNLSpkcSoqwdorOcaVFZm1Vf0eoGZaaC2mn2fTHLueDxAb7+E08V7oUgL2+V2kbgqj30swjEWjTH0OBDkPcSjJM8FBVaeW3k5x0JTI/92+61AOi2Qn0/vtNvNPs7PJ0FTGB+XuNTFMgPjE1xvlpa44XD4MADJ+/3ef9D76A9a9fJSaWB1TZrKtYz0OXeefZlImDUb1wTSaQmbjX2+aIZbv/H1vD7XEq7loRBDXIuKTG/jLNfWUEhtnvC7dXUk1KydJrK5m/n5wMQEw1BVjcKdoD1or0AkEhK/+/sGHvqKxO/9tsC73iEwNi7w//5RQkqpyZnGdYHNRk/ao48Bf/YlGqf/5f8T+MZfCMzPAz/zDolnT2tvmsb+h7BZ+QHpFA2okVEglZToOGjK6Sf4glc7wYbBcK10muFObre141xYQCPx5Em+oJUXrKmRRmBrC69XV0uDNhwBpiZpPAyaRjYNWq7xiYQysAQK8ukVqqnmtU49I03jgcZncTGJ4YF2GnNuNw3d+QWSyltvFWhpprHb2yfxzLMkZy3NrN/jcdPIBXgNFcrW0mL2T5qELBoFLlwEGuroxZucoiF08VIGQ8M06MvLmBdTX8ed6YkJehOGR2kwlZeRFLS10ah1OEg6XC4a4nl57NOTJ4AH7ie5SyYl6uqogre+zt10BZeT7VpZMQUO7DRQ6cljv+bnMxTq6BHWqGpvEzh8iM/k4AEzxM7D0MVEQqJ/gKIWmQxFKfoHuHvv8fAaQlDUZX7OakcmIzEzw34M+AWaG/l8VH5OVzcNSp+P3sK6WnrZJiZo4AJAe7sdtbX8WQlahMM0fP1+elqCQRqKTgdJmjeP93CowyJ7VZX8bHnFUsyLxSi9/+xzbNfzL9Crpgjm1DR3/pdXBIIBlnvw5XG8C8F/gQCP9Xq5SaC8AzVVHOfFxSQIhYUMXywp5rN2Okn8fT4Waa6sFCgpFjh4UMDhFBge5rmFjW2bnGSB4oMHhKlWKRGNMTyurpbP4IaTDK284YSVr6nyxg4dsqOslM8vnWJo6sAgPVGJBOeMx8M+u+tOYGGBBLW6in1mtzOk1GZjiG4mY6khzi+Q6KTTHC8NDewDn48bKVWVAg/cx3mocrgnJlXorYDNzp9VofpQiOSm4yA3asrL+JyPHzPHgbC8xmshektHRvh7QT7zXxeXSaZWQyQNAMOg7eYal84wTFEpJfJ5MxessJCbVMMjXO/W13nszTeJ7Bj0+Xiu8jISRpeLZLq4hF6vmmqOSyktj7XbzQ2PU8+SQI1PkCzbbPTYNjWoEFZeIy+P60AyxZ9DYXosF5eA8BrXlmgUuO8ea02tqKAYSzCIbLkUl4t9ebiDY6KigkR8cZGEOZOR6O01w9lNVdDDh7ghdKmTEQWxGNswPW1Obsn1HuBabUhrM8njEXC5LVGkeJzrwsIi1SYvV6haE7RXGGZmJH725yUmJxnSGAzyhdxxUOCzv2HL7thqaFwvvP5B4Jc/JpBKSUxOSpSWCvzubwl84H0Cn/2cxOd+20AopImaxv5FeZkNjQ0kSOXlNHxcLubwTM9YXonyMn4uwB3hWfPlW10NvPENAiUlwC03UZXR72cuVV8/PUe1NTR8lk0lQYeDRlBlhRX243SSFEUiJFD1dSphnkZIOMKwtyOHBWpruPafPGEaOqZh0tNLg+nCRVMtcAWoq6WH6VAHjXmldlZcTAJTU0MjLZWS6B9E1lKw21W9K8BrKgN7PJSVD4eRLbbr8wm0tZrFZUGDprqa4ZzTM6biW4VJWAI08NrbeJwQPNfIKFBdJVBRIeBw0EBKp5UcuMCFi6xr5nAwab+3j2Svucl6jj29QG0dyYDKCVleplFWXU2CWl0lN9RwXF9nnlkyye8HA8pjR8GtslISnYyZcxIwyeu583yemQz/nuez2mGzATeeRDbtIBa31CqFILGg0h7f7SpksbmZnokD7cDwsAHDUPlvSgiF+W7hMA3YkhI+31icYZuKCPf2sa/jcRryKys0VNtNJcRYjER0ZJT5h1VVbN/8Asd4XS37anUVePB13HAzpKVMefKEVcZnYVGis0tmQwyfe4G1vIwMzzU9Q4ESu4PP3uEgKSOJ5SYEPbqUw8/LoyE+P0/Sb7cpjwWft9vN8Mi1EOdlJELRndVVibPnON+mpkgOp6Ysz7LPJxDMB+bmSO7sNs5tl4vhgVPTJKqBAOvzzc5xPhYWCtxys8gKU6hrlpcx5Lms1BTQiVKCv7GBBvrKCksCGIZAUSHzElXfj4xS5MRuo2EvwfHyhgf5TIeGSabDEY7Lri72bSLB+5ubo1JheTm/OzYOXOykeMncHL3e4RDXGoD3VFjIsXHjScubVG9uSlWUm6UkbCSmrS1WviMAPHPaig4oKRXo6BBYTwBHD/O4wSF6jsJhhv329LIP/D7g/AWSyNpqrj9uF9e7oiKOW28e4PMLGIbYQNB8Ph6XMUVNxifYtplZXnNlBTj9HK89MspQyNVVidAa54kS1Xn6Gc6DkmKzXIJgPqvDwTFfUKBk+oFLnVSeTGfYfkU+Z2c5n4QQ9D4f5PlaWzgGjh4xlR4jEkWFnKOTkxyjQgAH2gUCQY6Z3aAJ2isIz5yWePf7JW68Afij32cc9NKSlSipobEfQClqgedfAL7wkMx+9vrXCfzV/xVIJIG3vkPi1DOapGnsT0xMZPDo43z5RyMkQDXVzIdIJhgetryiZJdpqASDNCAqyrkLPjWNrBQ1QC/JpJn7ZBgyq/CXn0/jvn+AhmhnJ42lQJAGstpzc5tqkjYb8yeiMe7019YIJJPA9x/hfLLZSBJjMRo9995F47KgANlSAJcuMUQSIHE5c5b/ysoEmptIQmzmrvPhDubeAEp4YGNfpVLMCamuFrjtVuZbpNNUsSwuAo4cprjF6qpJknx8ZxUW0thdWqYAgctFQ2ZqmgZQUyNDFy91ctfa5TQl+otpxC4t8fs+n8jK+ns8QG4AydEjDOFKJNkvq6sUUairJamhauHGTU0qr9FIKypi2GK16Tm8eIl1jhIJS4Wuro677MePcZw4HALHjpL4KgghTCVNPqOZWRK8wkKBhUW2u7KCRmi1GW5md9CDksmQYK2sMJent886bzxONTm7nUZpXS0Jgc9HQ/3ceR5XUsLxUllJsY7ZOY5hFW5YUiJwoJ11ow4eoBevoIAhW3PzNGQHBuk17evj+RWJnpvjdaam6c30+6waZABw6CDvrbKS3pT8IEOFl5YYdqqISjrN8e/x0PhdWuYzKynhmKmv5Xmbm2kULy6ScFDchc8jmWC7MxkKPNx2q0BFOZ9Rx0F6lBobbOZYk1hYYBu9Xj7ntlaBqEmaEwmSoeIiKx/J4wZmZyV6ernJ4HaLbPF0lYuWNoVnvF7O+ZFRfu5wcCOnu8cUEknw2gfauQlTWMDjEklrXYjHSbYSCapyJhNmwWszv9Hh5DNzueiNzmQYltfSZNbvKud4LQjSW5Qy57HNRgLR1MjyG2Vl3ECaN/ujtIRrxVqIXp5YjPPVMMwSIgXWuqRUQaNREtqCAq6BADca6uu42TQ3Z9Xpa2nhMystYU5ccbFAeZlAfpDe6vIyhgLbzAiEuXlubkWjHBcFBcwJW10FThxn7cAbbxCoqaGntayU/X34ENs5M0NdhuVl9vXQiJW7WFJMYjdtrtcVFVbuWcdB/txQZ9WbVHmRsZiVbzdgrt1qPvX28fl5PCxQH4tz40ht+I2PMyXJcxkRP03QXgGQUuLrfynxm5+V+MTHBD74fhse/j4lSW+8QeAtb9JeM439h9tvE/jsbzC2e2CQL+HCQoHPfNqGj3xY4HO/LfEHf6yVHjX2H/LzbbjpBr7MyyuB5iYWXE6lZLZeVmkJDeN77uJ3DIOGw8AgE8nr66zzHTlMD9GhQ0rOmzu+DfWU7j9+jEZgSzO/NzPLZPbyMu78A/z/8rIpBW7mhThMsQivBzh2lMdduEgjOJ0m2SkxQwRrqmkYuVxAZRUNtGiURtCJ4/x3/oLEw49IPP4EUFNDL8HKKkPBABo9Xi8NaFWHCiBZWlhgCLOAVSesfxC41JnB1LSZq1ZBIlZeRkN1epr5quNjVHIrLWWR28OHkK1D1dTIa7a00EsjJQ2dB18nMDsrEYlIVFYy9C4et1QPAcuIXFgAiopooFea+V7xOL0yhQUb3595eTR6nU6BqkrmP/ny6D1pbaERlw1dLVTXYdHeuTmq+nX3IEuAAeDgAQo5BAKmelwtCdKlTobg9Q+Q+LpcApkMDVpp0GNSVEhifvKEzVQMtc6bStGI9vtJRmNxhkXGojQ46+tIGisr6MGSUsJhp+Eaj1OBE6A3anpGYmqKAh3j4+yzZTPPJxRmny8sUGwiGORYV4XXi4p43MwMjV2PB1mVjmC+qmNFwuLz8Q/l5Qx1VH3pdvO5NzcBRYUCjQ30eIyOsuTCWogkSBXIVh7ZJ55iP2QyMGtyMRff4xWYn+e7ZXnZ9GYUCfT08p0jBElCebmgEt8syVd9HT2XzU0CD9wvsl610mLO2UCA81YIloFIpVgGAjC9ZMvIzs+Og5zDs3OUwC8qErjtVpJ55bVVhDs/3wobBLgRkzZzVI8cFqiqZNhnbQ09VgA3epg3yHkcizFfrrKS68zKKvuspoZtU7LxK6s83uPh+QGO73UzD5KFuqkmGouRuDmdPKfTpeaBNceKi0iKyiu4/nk8vJ/SUpGtiefxcJPA5bSKNj/2BDA7x7DhF86Q5C0us62RiCW009IssutAYQE3sfLzeb7hEYnZWXrQ6+sYPu12M5z04AEb8vNNL73dUmu95Wa2QZFOrxeoqWV/dnZZOaihEMfj6DifUyIB3HMXi5hHoryHYJDjw+PmeptM0juYSHCzpqyMnr5olPfEIttc15JJ7ApN0PY5EgmJz3xO4j8elvjKQwJ33cnPi4qQrcOgobFf4XAIdHUDD32ZuTMK995DpceJCeA975cYGNAkTWP/QBVMLiigwbO8ItDYwJf89AxftMXFLH7qcpHIJJM0GJlnZIWzAUBFOb0HnZ0MJbPbaXCMjnEnNxbjC3xqigZ4USGNxLw8kjaAnpEf+WH+nEmrUEDOm/p6GkMA1fZU2wN+4MIl3su5CxSSWF6mQdVx0MwfMcMT43EaXseO0KBbXJRZT6DKL1L5N60t1i6+UnILBIDDh9kXHg8N7MYGHlNVSWNoYor5JlLyvoqK2M7mZqu/KLnNHenCQiX6QdKTSDC/bn4e+MGjLFtQVETv0vwCDcEbTlr9LoRAU5NALM7P3G6RDYcqKyPpCIU3rj2xGL12hkElP58P6OmzhBGktHbHe/vMMEXQmFMeiDwvn52CzSZw+20WGQmZOYpFhTx/exs/i0Rktn5UfT0JFgscA2fOZhBaQ7ZPARrS6+s0HOfm6bFIZ+g9Ky9n317qZP6bw8z1SiQZBnbLzcB/+69WX62ukVROTdHLoXJ98vP5/Px+9sGDD3DdjsWA9STHQUW59bzq6rjmKwP+2WeBi5d43ppqeg8Aes6Ux0H93tlFEnfuvMTiogQEn9P8PMmqEnR58AGqP7a1UkhEFRBeXeXzUaIbEvTWRkzBirExiWCAIbMeD3MaJ6ckggUkkVFzHnZ2UW3wkUfpKTtz1poHeXncEEmnrdBUtSnjDzD8Ts2n9XWWOKiuooKkCtNdXuE4B0hCJqfoLVZzSqGxgf3e1SWzOVCrq1b0SSbDjZulJba/oEAgFmNoZ3+/pao6bxJxlWNWWsI1QAjK/XNuIJsz19xEIhWLcT042E7C73QKGBngB49ZeZBCUGRmdc3ctLIxHHN6WmJpSWZVFgsLSQovdnIzorSUAiyFBRxfbW3sU7/PUuP0eKxr+HwiW7S8o4ObAVWV7OtUmrZGOkVRlYlJYHqWGw5ckxn9UJDPkFtVmD6xThXGlmZuQtlsDD1XOYcuN7IFphvq2UdCsBSJyuUsLGSuodPJ8ahEbhrqgeNHgZJiAaeD74dolBsvjY2cHLmbSdtBE7R9jOVliQ//It2yX/oiX/Cf+FWJi5ckbrmZO40aGvsdx44K/O/f4c7wxUuWMVRaKvCH/5tCIj/3YYm//lsaRRoa1xvDIwZOP2/+Ihn6xLAd1hzKz9/6HZuNxltZ6fYqugODNBIbGujJmJikIVRQwDyS8QkaJoNDNPo8HhKMPK8iLiQBQoisDLdSUstFOExiEYvR+L/hBHfMa6ppyPp8JIorKzRq7DYq9PX0Iiv8UFysCvQK3HEbw4YAGpPz85biIEDDWpGyYIAELZXirnYiARw9YkfEFOpQuR3LK2pXnSIJuTvJsRjvs76OpEwVRs56TqpsKCyksXzokA1eL71Xd98F3HmHyObZAIAhadimUlxX1tYkkilTjnyFng67eW9q/0g9RyHYByXFNGLTaebPAOw3j4cGOo0/euiOHBbZwsi53hABFqdeW+PvC4sqD47em0TCzF/JswQfMhke53CQyBcV2RCKbBRBSSQkAj4rXLGulgTB7aLC54WLvAd6DgRsdoG2Vh7zwll6LwASvdpqtr+hXmQ9Hm1tHDvLyxwf1dXAM89Shj8UMsNR56xyBOr6HQctgnbrLcgKRQAkMgAN2qkpS2RHoayUfaFqsDmd7JOmJoZJqvPG1xk2Z3eQOFRXc0zU1YksQausEKg129TSzPp7NTU2OBwiK4wS8LNOWn6+JWbS0mwKgQjOhxtvYB8bBjdoLl6yvHbFRTTup8znGInyu14PQxn7eukxCwTM0OhlejnV/bW08Hp1tRxXZaVWXzgcNqytsQ1NTRwLiQSPBYD77xV419up8KpEaVwunu/gQYYrHz7EcgoFBexLgPN32RTOOXcOgOT4UekyKyv0fieTSgyHpAhg6OHhDquMgXoevjzmxjldfMYqyuAD7+W4GhsDfF6SmJoaAa+H53e7Wfsv4Od9OhxmrcAOjhuVxwrwOcZiDB8uKiLRO3qUXsUD7QJ2Bz3pZaUM6ywt5bMZG+M47xsAmhtV3ioAGwn+xUsWefV4eA9T01yvlBc/kzHrrdm5ATM9w/k8PMyNhXCEmxTJJDA9yw2n0lJ6qccnScqqqtim/gEW+FbrwU7QBG2fYnhY4n0flGhqAv7g9wQg+WJ+59vEhtASDY1XAmw2gdEx4Ot/uZGE2WwCP/FmgS/8H4Hv/bvER35JZsNSNDSuF6qrbLjrDq65UjK/5vRzVPnyB7eGpthsVp2n/oHtz3nv3QJtbdZ3UymGCUYjwC0304hpaaYxtbBAAxiwDKDFRcqaK3g92xc6nZlVRZCZy2UYzMfx+2noulysX9XexuPtdhpzN5wUOHMOeORR5hSpULS8PIEKs7iwy41skd/cEKdwiH3DD3htQypjNkNlQSeNnSOHBQ62UyhgcpIiG8p4B+gFONTBXJPGBobjeb3M9ck3jwsEBG6+SaCnl56W0lKB/KDAxUskMwokuFY/qZIJkSif19qadZ8KHg8NWyG4qRSJMo9tatpSz1PH2e3mfZvezKFh0xDsp5c1FxQp4c8N9VaeVkszPSC9fezL9XVkvbUC9DCUldILe6Dd8qiqvg+FgTtuF/j/flhgZpaEN5HkszrQzp1+JUYgBOXC77uHBrLyYK2sSAyPUNRhYIika8kkEh43PVGtrfRQMfeKxvORwzx3Qz1DGQMBgaefIflQvZrJ0KANBplPpYhrVaUNP/xGka3p5nDwuefnk6gqKXl1zelphtGq8zbUcQ69cIb3FY9bBCSZ4ncWF7lZMTtD8ZK8PIHTz6Wxvi7hdNL4z88nqe8foOcnk2HfV1UK3Hcvc+USCY7LtTV+h+qTEgX55jw+aBn9KyvWRseRwwKNjRyHXq9AdTWJ5K23IDuBurpJglXblZdV4d57BN7yZqC4ENmQuaockjs8IuF2s5YiP2M+WTQqMTNL8qBqNyqRj0iE5MPtZsglgA1lPNbXgbYWekaFTSAcYVgfwA2NwkJkH7Bqr99v5mmBJMfno4pjKMyNkUDAqu0GSJSWAs+foXDLxUsSTz6FrPfY5eJmTzAocPKEyD5zJRbSP8DrJlMsZTA5JfHUKQkjw3BPekj5/9U1fgcw51EFsjm8BUEWki4vo+ojwA2QsLn2Li+SLA6P0CtHJVgbmppIkmdngQfu53lLiukdS6cFTuSsE9VVAg/cx7zUwgKrfIPPv7FW4nbQBG0f4plnqdT45jcJfOwXmQD+jndLrKxKHDggdAFqjVckWpoF/uD3BAyDdZ9y0doi8NUvMSTqne+h1LeGxvWCw0EDFTDJhsF6OzabwNysleCvoPLKYvGdQ89XV1m7aWkJ2YLSXd00CCenqGDX2UUjpqyMBtdNN1jeuro6gTe83ob6Otp26bQlKJCLtlbOsbw87pr3m+pvfX30lMXiLO6sPBc2GzC3QKJzwwngzttpqC0uWXMwK1TiQrY+lsgaaCLr3QJooLlcLEJ85DDlvlX+yMQkCVQkymKtlWboXC7RjMWoHJkyPYQMzzLrfB7jRcfHmSvX2MCd9Lk5iVhM4sEHKBaQhWS4ptPJ59LYQIW+9XUa3PlBGo+5CIWscga33kxxo0SCIU+5/R2Nsv6VktZPpUzCI0gucr2bQtADkSXbC2zP6+43lTprrGcai9EzBPDeZmZhhnVSlS83DE6F16ZSzOdRIWEAPbV2O41ZdT4ly/7MaRL01hYV+mmNhUyG5Ksg3xJXKTDHoJTcTBgeobdgfJzjtaiIx9VUk3jOzVv3evYcx+DCAknL5KTVf4PDVui7AAsYDwzS86eOq6sDZueEGcJnnbe2FnjLmxgmB7DdayEawYDp6fCRwDpdDP0cGpaoqbFlxX1sNuaReTxAeyv7b32dBPtSp8Sjj/N6nV38bmWlWSzazXF/4jhFRfr6gKpq9kNLM8PeXC6B5WXWk6soFxgZlTh7jkIe3T0s2QFwHCwtsXaWega5SKWAJ5/i5kMiQWGTZ5+z/r64aHq0zX5JJhniuGCG/Pp89FQG/Ly38jKGsFZW8HilvmmzCdx+K38uKeE6MTML3H2nEuwROHmcYZxPPp07//n/qSl6WD1eU5VylKS/r4/jr7CAz2NkFCgqYJmE++8lYTp4gHUPAWusbUDOtTIZenZDIZLlxkbg1puZ95VMcX2ZnuGGyswM189iM/dO5aK53Qx3XFtjyGtREQV3AN5rSQnJaWERQ0Vtgp4/t5sN6exi33Z0cJ0uLxdwOoGffAvPOzyy9RbcbuYg5ucz77GkmM9hN2iCto8gpcTf/wPFQD71qwI/8kNUxcnLE/j618SWZGYNjVcahGAOyN//g8yqdym43QL/8xds+MTHBT7zOYkvf9WwduU1NK4hhkcMdJveKgkannYHk8gLCjd6fAAaVakUjTeVg7AZC4s8rrWFa/3wCI2A4mIaN8vLNGImJ2koql37bM2rCNXj2loFbr1FIJXGlpwVgN6QcITG2MkT9Pqsx2k8dRykZ2BgkKGDANu6vMT2JZIkCQX5lqELWMaYy8XdflWEGKAHKRRG1hPCfDyJkRESmJoaG0ZGmCtyy00M65QmOWRdK6veFsDrp1JAWTkNofkFHl9ZYe04l5eTbDmd3NH3eNi2qWmJ8QlrzZCSBCVt5uxFIsyDKSpE1lOfS2oAq+i4EMIsf8Ais+sJGmsKLheNOY+HO/yBAL2gAD1GmyveXLpk5qBIYGmF/S0EyU4oBBw+RGGSoiKGXkppGraF7KPCIoYt5iKTYU6Ty0XDVdWR87iBxDq9afV1QCDfeo7KC/nMaZITgDZGaalAXS3JqHoehw7SUF9a5r0nk8Bjj5MYLy3RM7MW4s/VVbxefj7JrDKq77uX/ZfnZWjcf/tRK2R3ft4i506nKdZQTcGT/HyeQgh6XIN+SzEVYPH2oWGqYwKmcEm+5Xlz2Lk50Naq8g0pIFFZYYMQJIhT0xxX+fn0aFRUsE5dx0G2o6iQGwi33sJ7Wl1lmycmOD+Wl825Usjc0mQS2ZBkl0uRAbanqpJhihFTll9tkJSXM5xPlTzYTNAcDnooW1vYR04nvcoA59w9d2+sO+d0UjCorlagtITz7dAhrjPl5TyOoj7WmFAoK+Mvi0skZ1JShGV6hvmexcUCN9/IjSP13HIFc0IhS5Y/meIzuf025nktLFKF8shhgePHBWIxbtioDbBEgve1G2lRSpjpNM+9ugq0t1IMpL6edQyDQbahuornWluDWcicHi8pLW9/bS2J2fmL1uZLOs2wyOIi3u/b3gr8lx/hOqSif5Ti6tws8MyzJPPxODcWVO3G7dDcJGATQGeXhM8vtnjvN0MTtH2CdFriD/5Y4m++JfH5PxG483bGpj/8fe4wBQOanGm8OlBdLfD7v8uX5KOPbRQPAYC77qQ37dnTwC9+TGalqTU0rhVamm144D7zF8lwvIsXaEhIiQ3iBgBztEpLBQoLTKGPbQjayRP0JMXiNDprqmkgTEzSK9HRQXXFtjYzl2VTiFw8buWIxGIMcdycvwPQuL7nTubNhEICsSgNVL9foKCQ75HDh4BDHWrnnDWUDrQLDA1zd35gcFOeXTacUeCmk4CUlkFos9HwUkaPCvcMBHgPnV0ZSFiCJLE4vYGApYqXl2e934JBgY4DwNwMCeWRwwLNzawpp4xBh4MhRr19wOw8w9R8Pua5bM7raG/LLYVAI10pH25Hcp1O7ojzfvnZmCmucuzIxuPW160cvNxlbGFBhXJZ/VdaannVWpotI7uuzvquAElcaQk9Gkpwpq4OEBCoq7NCAlVfV1SwXx58gMR7YpKfJZMMq737ToH8gNWOujqBBx9gPyhyurQk0dsrsbpGYZjFJZLwS50cyx43wxldLo7ZVIqE4oaTNFaPHRU4cZz3de68md9jYm5OIhSiR3dpWWQJS2GhMAseKy8ea/PZ7ewPr5cbFDec4HPKeiTN21fEan0dJuHiz4rE22xmLtUAyeXUFDv5B4+lsvmbdbUkUF4PSzX09gEQVBPMz6dnJxqll0ptmhSaGzTRGDcrjh0heXE6rfBIAGauKkNvAY7ZgJ/3dPutAlLy857ejZsUFeUbN0cOtDPk1u22CIgKhwSAp0+xpIXImaPJJBCKUCCjt4+EctkMGRaC/ZnrqdocKu1xM8RR1UUzDKuocjRqRQyofgbYP1Qp5abS0hIVIicmqY6pipAn1qmrML/AdWZhgc/oYifXgUxmq62r7s3jEdk10zD47/wFmVWfzWRY8iOR4CZHKsV1p7aG37/9NgGPh2Hrhw8JHDtKO6SlieMRYC5wNMbSE24XVV5fOCuwusrnC/BvTic3yY4cZr9WV3O9i8WQFWzajIFBibU1bpps947YDE3Q9gHCYYmPfYLhL1/5M4G+PuA/v89wxl/9pC4+rfHqxOoq8PAjcku4GMDd2D/7U8brv/O9XIA1NK4V4nFYHjRJg+zkCSASoYLdZmKkhCZ8Piu0bDMWFhimp5LRHQ7g7FkShZ5eidExoLeXu9ClJVtf8lWVNKwBfscwKJ2+GZWVNP5KiqlINjsnsqIT6ozLy5YCpN3OWj2TUxJHj/AaPh/g94ksSc1tSVUVjSQFIThPc19TzJURuO0W4PgxBw600xAOh5lLNGom7ZeWUmwjd5NmbY2hfG4PDaz+AYniIglAZInx5CTw+JMkcNVVAuMTEtGoxO23WV4s9exyUwIMg8/A6aAxaBhbCd3KCkMceW/87OQJgfe9Gyiv2Hiu6Rk+ByGsMSEE1Sz9/o3Pr6yUgg1OJwmu05RZNwwrN039PjfHPvH5aOgqUrbZuyIEa0gpG6G+zgxBrSWpC4WA8xcZ6qXaZhg0ZktLgZpqRVzpYfGahK3jIHNqgkGGrHm9DJN1uegFmJtnmCaNcQEJCs84nSIrYKH6bmqa3sLVNRr8U9P8PBRiyF82xFGwntTkJNDda5WXKCoSGByyNizUeWdn2T4llpbJKNEW/l3l/KlaapUVJFpHDjngdots3lomA9xzN/uuvAyAJCHv6mZRY7ebYXl9A8gW8Pbn8f/lZUAqLXCpU6C9je1Rc18RfzWyJyZU/TOJZ05bESRtrdwwmJnlcQUFm8J0TWTM8TU3D1y8aH2u1EJzx0ZfP3NbS0qYh7gWIuFsaeZ5KysoiQ8w9HMznC56Tfv6GEJaXW3VP5ycAk4/v3G8A/QsqlavrPDvvX0cg+od73YLuD0sat3UyLWmspJz9rZbOL9z54KCukbAFC5qbbbChg910DN54jif5fS0Vdh8ddVS3syFwyGyHnePR8CQQDTC59HawvWX5J3jpL6OZF1t9Nx4A8+j6iN6PPS6v+4BgdbWne31ulq+R9S4vBw0QbvOmJqS+MDPMYHyc5+hS7WuDmisv94t09C4uiguFvitzzIf4Dvf3T7k8eMfteGD7xf45V+R+ObfbPW2aWhcDSwsGlmDCWBuSSQGxNdpNG8OcczdvXY6xbYEzWYX8LiZMwHQaDh2zFIag6QRtbRMhbVIZONYX1piIjxgqrklLXXFzcdFomatr3UagKnkxnZOTSNbA0vV1VpdIzmZmpYoL2O+j/Ju5NbeWljcWKxaSpnNF1LXSCQkLl2SeOY0cPKEAyMjJBoVFfQiKtn+ZJJhZrnT2uEwlQfzaSj7ffzs2BHL0KquptdifZ3nKDFVJ/sHJLp7JI4czun3nD6SkiTE7WbxWrdrq0EYDDIsLLe/8vIExsYFRkdzzytw843AffcgK4yS2we5EALo6qFXS4KGpGrX3ByJqzou16CcmrZUD4HtiX8unE7mUhUX0Tjt6QOOHLLC/oR5jcoKimv09Erzeyx+Xm6GuCVM6f6mRsrZLy2RkC0sAs+/IFFRTkNdrcfKswYA7W0Ud1BdcMvNFP/Iy6P4QnubyDYmV2zH4xE4ehTo6BC46w4zTNLEsSM5kuvZTuU9qs8KCli0WHmXbDae82d+ip7EhgYb3vrTNvh8QF0txUZm56ji53AIJJLcYHG5SBhaW2iYp1JUB21pNos3r/F7hYXc6CgtYQiizUai7DSJmZozqoZgQwMVMjMZ/k0NF7eb11MiHztBbcYEA1w3FE6eEKyhlvP1W29huKIQ9BgdaN8o6jM/T4J79AhJz+bxuh7nZy4XSerkpFXX8eAB5qXJTZtUgQDz/QCulyXFJCRHj7AMiLrGgw9QdXFpSeLceZYOWFujOFhb2+7EJS+PeWvr66qcCNfbYECYcvaC9fkamV9ZVibgy6NHMBeZDEMSlafS4bD6IBLh2hnObggIU3nRihJQ6UbhMIl8Ty/r9T11iuq1O8HtFjh7niGXl5vLgCZo1xUXLkq8/2cl7rsX+NSvAL/wP5n8fPTI7ixcQ+PVhGiUdW+286QBwBtfT2/ad74r8alPc6dcQ+NqoqHenvVWSckdaZXEH4lwV1h5G4CtRsV2L9+qSiqwzUxb3zEkJZ6PHBaor2d4U0szw182e+lsdssomp1lCNV2+xUOB/Nn3G4SqfkFy8hXRggVI4XZVqr6VVVSsa67h7LQmZyd9ePHWDcL2HjfPCfrc7a3WtdwOhn2U1kBnD1HPfGgKcixusraQIApMFG4sSyBz0cvzOgYjfmqKhphkYh1v5kMrzEzSyPZ7xNwuWxIp+kdU6qTEhQ9sfqGoZIrqyTGqsYakBNmKDYaswr5+dhA/PiZQF6eLVsHLfv9Tc9EgEaj38dGGQafJ0BPlzvHgAyHVb0lSq7nhtNuHlc228ZQ1IFBIGMIuF0UI7jnLvax8ubw3gQOHxI4bIbUAvTunrsAzJl5edEYx3nGIIHJz2c7q6s4FlIp4IYbkPXcFRYwDC8XHjMkcXBImjlqNHqXTPGZYICeInUOux0oLqJXJc8rsoIMADct7I6Nz0TlGClQvVBkiZEEsLIqce6CwIVLJO+RiMTp59NoqKfnhsSKx8/OKHEHCvYIQfIlBHD2nMwKqFD9kATWZmdfuFzWeZyqnebvyZxQV0OSZNxys3XfhsF6XaHQ7u+1XM9cLrH9waNWzTiFkRFgLcR6g0IgmwOq+s/hIBktN0ncLTczP1ShrIx5ePV1wI0nuYmhyNfCIsMSjaznk5+73VYpDFXcOi+P68nwiHVvz5yWmJ2TWE+YG1FRbhbNzJII5obHKmyeT0vLYotXDACamyXsdl67qor5Za2tzNPbjIDfCputrRFZsZSFBT4zVe5ASokXzmxcDxUKCjgfDnVw4y1ghk3vhptvpFdTe9D2Mb77PYY1vv2tDElxOW346pdENjZfQ+O1gkBA4Nd+xYa8POChLxuYntn6ompqFPjqQ4wdf88H5IYFX0Pj5cbyioEnn+IYk2AOww0naZDGzBpgJcXIkjj1slUCDbmqhrmIRGiQBAM06Lu6GCb1whmJwUFLcc+Xx3wpwDKASoptuOtO/lJebsqwb/O6yM+nWIMQJEmpFLK76+r48Qm5QaWxf4DiGm2tNJDdro0GidstsnnQbvdWD2JeHj0U6ho2m4A/wHChH3qjCx0HLQW2mVlLnEJJYedidZUhjmVlyBqtdjtrCynSOr/AMKumRqpFDg5R5bjj4NbNzVxDH2DoHHNl+Cyim/IJV1ctAZXc/i0q3Og5zP17Km0ZZn7/9p7NxgYBj9cKa1RhsbFojrEmSOKowCfhcGwUUFE7/i7TS/TAfWJDfnpLM4U4VJmFnl6G5k3PWOeXkiGOdjvV9ACz9lcTx63dTg9MeTm9Nmsm8QyFuEHgdAosr1hhkzuhpFjgRpPEMf+Q0UHKAF9elnjueWsMOp07G62TUxZRVX0+OWUJXeRCCIqS+H3853JR5a+qkoSg46AdbrdAJiMxaYrzAPQANjZwbC8v02uYTLEvl5Y5j5qbOGb9PqtY/OqaJfuu7sPsarQ0w6yfSBgZkoZnnrGiQaRku5THZifcdivzKefnWQ5AQSmk5vbdwgI9d4qgud3WJoDy0ubmoPn9IrveKIRC3JgKBCgso9aDUIie2c0bSKGwVdstleL1LnVxrfPlkKnWFs4lJT9fUizQ1ipw7Cjf79sRr9x5aLeTPG4nkORwsGRC1IwgWE+QSDscG+/NbmcB+9z0IbVB09LCtd0itMyDPNSBDfmf6m9Op0A4bBYlN2uy/f/snXd4HFt5/79ni7ar914sj/u1fatvrwktPwIJSSAJoQUIEEroECCEEkIC4YYWCD0ECAkkIfTL7cX3Xvu629K4SFbvdaXV9vP74zuj2V2tpJUtWbJ9Ps+jR1tmZ86cOXPmfc/bciFzX9lwLLuFYlWJxyW+/BWJXz8AfPrv6IP/059xpSPTZ12huNooLRVZfdABrqx/4m+B7/8H8Ka3SLz7ncA9d6t7RrH6RCOWwGMTFMrMmJiaakM5ShGIzG23aEvXqayu5gr77muA6aDAvhslQiHGikBYrn8jo8B0MD05VP8A05Dfd4+YL96b7SE/MSkRjdIFcnKSgqmpcJh4Pfwzqa2hVWlgUGJklO5DizE1zT5J/f0CF6mwxMGDVKT27E6iTaciWlws4PfTWm7GxU1N0ZplUlBAy5vXy/a/9HcpCKVawmqqTSFKIjgjsamFQuSRoxLhMHDTjaZZbGH7S4opXI6MsL99GQJhcbFVNiBV6KWLU/q2qUKv2Y8V5SJN+c3sHylpmTL3PT5BYdKs1XT3XbwWQgj09cu0jHCmFSlbchiA7nmmtXR6WmJ4hJZPASv1vRACO7ZJHD1uKXrSMMDkBwRG84CCfDFvMero5PhPJKyFB7cRT7icx3lRoZhXKpNJusLuMhKtuN3pSoLDYQn4mdx4fUrmUKMvTetW6mcmlrugxDU7Kcy7XAJ5eRLhCL8zM3tWV/O9x8Nnz6YWjrtY3ChlEeE9NzBgHk9idJxxT2fOcvuyUmt+SE1S0tSY3jAprULMluWQ5Shqqpd+lrndAl6PRGkp45jmz7VZoKsn3fXz5ptZs81U0O69R8xbeAHecxMTVvr5bBQXC7jdkgljJq2C0ZtbmRnTTCVvXgO7zbIiFxRYMYH19YIutvMLTennOTvLrLNzc7RaZbNUpZJMMjvsNbsWfseYTIn8fPZ9Mknr16YWuUBJWwyzeHlqSY2ZWboybtsqsWCwgYlFvF7G1Lc08ZosxrkOK+HKcigL2iUkGJR4z/vpSrBzJ9Dfz9W/N/y5SgSiUAgh8Psv5Yrw5/45icceX/j0F0LgFX8k8ImPCfzTP0v88xeSC2LXFIqLpbLShltuFrjpBgaEnzxl1WUaHKLAkjpl5+KuAnD1u7OL28fjEp2dXI1ubGCcQ3ExPSoKC6wsX+Zx/H6rkGxn50LLk4nXw5V2r4cryb19VlFks52lpSItc2Jzs0BRkUA8jjRBLht+X3qNLyBdZDFX7K+7DrjjNoFTpxLw+2gRHBtjzJl5bJdLoMUovDzvGiaYvKOtncJdtmfj3ByV2NCcUTTbOK+yUipJ2Zi3RJZSuaispDtcprKzfWtq4grr8/p6Js8wuf3WlFg14zNTwVgsQ5uAkVY8JQatpdmKgxMCGJ8Q88JhTXW6Bc1kMQUtlfx8WkO7uy2h13SRLS4G9t3I2n4A+6OtnZbVfTdZi8WJBK1PZaW03g0bFquyMjGfnGM5Dh1mUgzTtc5Mi+/1CvzOiwQ2b+L7qkor214mZ8/RYgVYfV1UJFC4TOmhWIzFkB97gqnNxyeAM2fYGW63QEkxEIsvvNZnztLlsKKciskDD6Za+hjXlEhQwfT52BZTWZ237GRpWsKwQG7Zkmq5kdB1iZGR5Z9jXi8XJlKtvg8+bLlkmtiElXGWsWRMxW82q7KS43kpIhGJmmq6C9tt1tg+3yVx4qRcMAa9Xlq9t2qcH8fHOcZPtUmcO7f4ucXjjHmMxTi+sroIppybELwnhoez7y8ctqyYoRCzUeaqnAFcsGnNsHzqp7mfTBdns89f92rea5s3WYtsi7Frl0DtMsq4iVLQLhHdPRKvewNXtL54P/BXbxf47d9a71YpFBuTFzxfYOdOIBaTC5IlAMC1ewW+8VWBEyeBt75DLlixViguhoGBJB54UCIQYGzC9m20egEUcs1U8iaLFafOpKgIKDdW/ufmuPJaWAA8c0CirY2B5r29EhKWEmMKAfkBMZ8a30x1ng2XS+D4CQpnrZuoUJlC8WLrgI88RiGqpkZY1qdFqKxk/E4aWZTVWIzWvPvudc4nhsjLY7Hs3j7rfjUVMEdK6nCXi5aJ0dHs9/WU4X5VUc7Yua4uuo/W1AjULuFi1NhAV9XffwkF0EhkYT/a7AKDg+a5WPty2Hm9TEHcTHueirmvVDc3nqP1fz5JiKHEFRfb4HZb+/H7LLe7TIuSuZ9kDtNdLCbxmwclBgZZbiF1f489QWHYPt8GAU2jcmuek9bK2MWublqRpoML3cpyydlUWsIFAjPbp6m8Dg9LPPo4kG9Y0bzehW52JmPjVtzVStayXS6BW/YBd9/JRYs8J9DSzAGaSEr09FiKXybhMAV7v5+LHeY1jUYt18ShkYVWbHPhJFszzUQfGcOGSUNy6Euvl+UkBgasHezZbVjCUu9Bu1WqI/NYELzGyykt0SgthNGoREGBFVNos3G/m1vt2KpZhw2FuGBSW0sX07paJrnZ3Gql689GQYFAQwPdHH2+dMv8fJPTFDRaHAsKGA9blDH3zoassSIlrV+5YHZ/cbHAxBQXgEzuvhN40QttqKnOrjL1D3Bhq7p6cff2+fYj9wU9paBdAh56JIk/f6PEffcCd95uBCqXiJx8UBWKq5HNrSzM/qsHgM9+LvuTq7xc4Av3cwX+tX8ucfSYUtIUq4PLbVmrAAo7k5N0o2tooFCQbl2xUuAvRV4e00yzTpjAnXdQgG1tYWbCggLu23RxTKWrS6at5C+WBSwclojFuaJ95iyF8tQkFMBCz7/r9tI17uxZWjtWSqbAEYuxhtax40BbW2J+ASUQELj3HjGf3j0VV4rwX1gIQCzu7mSWHJielhgalti+jcL9iZMSzzxrtT9T6HU4BCrKBWZmmXQkEV9oiaysYDHeTM6cpVK9FPMWtIxEEUhR0CDZP/Ys0pcArZONhkA7OZV+7cxW7dhGhWMpokZWwrvusOrOmdaJ22+lq9Wx40a7YzLN8gDwN3l5wlDweH1KlhE+s1FfL+azQ546ZQmwhYWLn0NJCS1qJnfctrRlYimlzW63hO3iYoG6OuPGkUBBoWUtTN1HY6OYL9rs9wvccjMtUFs1S0FxuXg9zOLFmYWbswnh5nDMVDhaWqzjLccWDbghJaFHIGDE72UskkxN0302U1PMlgAnG4EAM3uGw3zWmpkL6+u4iOPzpS+G2GxWxsq8PMYplpbwnltKGZyelvNWOZvIbjHO5PARnvOttwgEMmoE33s3cK3hAupyLSyjsRg+r6UchsPpc8+hw7SiZnrrmEfu6eWYeOQxLhwteRyflRFzOZSCtobE40l8+98k/vbjwL33AK97jQ2ve41tvpaCQqFYmhc+H3jXXwnE4xL/99OFE2RensA7327DG98g8O73Sfzwv1QqfsXFU1xkm7dWAayD5HAw9bYQwvi78P2bqeiPHKXLY6CAyQlcLipWNdULsyVWVDBlOsAEBjZbdiUtL8+Kz2gwMgSasT6LtbmoiIqB200l9ELOJ/V1Xh4L6ppxZ81NFO6Hhqlkpt6j5WVUIkzrzL13sz7XmTOYLxidyeQkU3QDtBbMznJu2LqFFrKl2hiJMMFFSYlARWVK21OmjWwzyLat6S6O2TCVqXmlL3NHgqUPkjJdGUrFzJIHsB8KChb2QVWVQH3d0gPQ5xO44Xrgqf1W5kRTgZyYoJJ2ndFX0RjHeHfPwv3ceTstaXYHt0kll6n20cdpyQOonJkJS5zO9EWQVPLymGky9b3NvlCRyoW5OS4WZCY1sdtNa57p4mjtOBiUyA8sPDmfn/NAsbFAw/lg4X65w/TPiwphxRNmfHf2LN0Uc2FiEujosN4/8QQtVZalPV1Zy2yfEPx+ubCacJhFnzOtmu3tEk8+ldJW42un04qjdDh4rV0Zc1g27HYrHnFmNvv1zfzIZuccmI2pacudMxxZ3qJlkpdHRVyAC2apY3N2losJiy2K3XcPrYDX7V3cTdfE6cw9GaBKErJGnDqVxNveCVRWSHz9q5ZZXaFQ5I4QTKc7NiZx7LjE835bQEq54OHy/N8W2NQMfPAjEidPAu99N9JibBSKlXC+K4FDh+W8VcwUFqemLMEkVzeVbAghsPsaibZ2xpuFDDccr1egv1/C6cCChby8PEvYCPgZI5GaXMNql8Cx4xK37GPRWzOonsc1/mf85sGHgdOngd97SRb3xUVwuah0jY0vVNCSSTmfja2iwgavl50VCkmUl6X33c4dpludJSj7fEBZmcS5juxB+bEYi9Hu2S3QUA/09TIxSuY9n6oEmW10uwV27WTMTk+vFTtUUWFlLMymeASDKdkQF2GHoUDTO0bOuyLOuzoa/7dq6QW0U9uYH1jcLWslykk0ShdCgNaAkmIrdfjxk3xtWqny8+k21rpp4X6ePUA3tWj0wpT3ndstxbUmJT5waIjtuOsOKztlLqxUQSssFLjvnoWfS0nLYDZPpt27RFblQoD9OjXNpCKpsZjzrq/G7/IyFPDU4tOZ57D7GqtW3XKMjqanor/7LoEHH2aWF3O+ikRT5qlMBQ3ImmU0k2SS7q2VlTJtrJaWZt/e4bDiSO12WqFSS0Rkc10EuJBgKnbxhJyvd5dKZtbYvbuzZ3EEWPMxEuWYS42dyxUhgK4ezh2ma+btt3HOWUypffoZibo63ruLtetCUFrDKvOt70Tww/9M4n0fBK6/DvjXfxFKOVMoLpKSEoEPvp/W5w9/VOLAwYUSVGurwNe+IjA3B7z+TRLd3cqSprgwysts2LHNej86JvHwIzJNscil0OhS1NbYcN89rMvl81FJaWqkq2E2F8fRUcwL3M48JiZIjV1KZdcOK718Xp4VIycEs/rtuyl9+ztuA177ah431Y1yKex2gb17Flo1hOGaODK80CXQ62U67VRBx4x5qii3kmXE4xIBP9IyGKZSVma5OA4PAy98gW2BcnbrzXwGA0z0YmbXTCaZqCQSZT04U/jMzxfzQnQ2Ba23b/lYoVRhf/MmoK7G6hOA57fnmnRFJRW/n4KhmXwEoAJjUlrKos25ICVX8++9my5qe/cIFBezIffdI5CXZ7mTzSuQ2dwuBfcVCORujUiluJjucABw4IDlylpeDtyyjxapVOVlMcw+zLYwspTSNjcnceaMRCyWfuEcDgFNS/9hRTktyc3NImtWRZuNYyAaxQJvDnNcFBVybC52bwLpSw52O7DvJtuCeMbF2L5N4IbrrW1Hx9JLaQDp7rML+kZkd6/NxOtl3cbM8V5cDGxOcU0195WfLxBIsbZFoyxbANBau2uRcTsxIdHWTtfk8XErvX0qZsIbkyf3p9eCS2XnDsv74ILmaMHsk6kK8/g44zaTGcGf8xks7eyHp59lttfVQlnQVoGBAYljx4HbbgUOHIzj0GG6Zf3WvWoFX6FYbV71SoGqSloz2tqRltQgPyDwqU8C3/kulbT3v5eZ5BRXPpqmFQP4DwCNAM4D+ANd1ycytqkD8B0AlQCSAL6q6/r9mfvKy0svADw9RWuD+cBvbKAb4mowMGC5BgFUblpajKLGsISA8nLLEhCJLG3BM118AMbQbNoE9A2YFpqF9wOVFIGGenlBcUaZMTVOJ1BRuTDTW0enxLmO7JkWKysFKg2LTjzOzH2LldwYHZU4egy49RZahnp6mXEvdaXfLDwLYD5+xtz33Bzm46KykU0J230Nzy01xm0pGhoEBgclevqsz4QQi1ogNm8CamsZ69jTa8VnMX6HFhIhKDTngsslUFMt8ZuHgN27JMrKrPM9eUqiuYlWWj1FoMwmuN+8j78bG5M4e27p1OzLUV3NdP/1dRznobnsda+WYqWWa6eT9/MCRUUu3N+undzogQc5nsz3JkJwQaG6Ui7Y30ose2n3S+4/AwB0dDAbpanUdhtJXDIXSUwyxzJLLSx/nFCI929mHcHjJ5hg5qW/y/dNTcxO2dObns20vFzMlxnI3EcqXi/n1soKpu535mCByg/wHs42dg4fZYZSp5Ouu4spcothE0BhQbqCXVoqcMdtMk2J3r3LspaZZUkCAblodt0LQZl2LhApJQ4d5qpMLM7q6K98tYQA8N1vKeVMoVgrWpqZIry7h64FAFdJTWw2gVe9UuCjHxb49D9IfPkrKhX/VcL7ADyo63orgAeN95nEAbxT1/WtAG4C8GZN07ZlbjQ+IfHkfut9czNTY5vCXGMDcl7xXg63O12ImphYPL7CJBxmVr1cyctjNrvlElMVFAjUZEngsRyZSUgSCbppZiaBqKlmgovljuB2M84n1UUqFYeDSq3LxXiTUCi31PMA+6KuFktmfs2moHWeB57av8J5xHQpzaFL7XZeH7/fOpfUmDf7CsdbJCLx9LN0McxUqvoHjPIExi7NtP5LWRzCESN5SworDfctL7PcLCcmmOwhV8yzz2pBW+J3DgfjgzITVWRL2GGyd3f2RQQh6OJ4vmvhvbRtq5WcYlkWUaZy+qktfUHn+uuMRBkp+7GlXMdsGT9zUXIdDqC/f6GlsKUZad4FDoeYX9Qxz2W5WmapuFwsl1BUJFBTvbgrZCpbtywciyZ2u+XW6PVkd9tdCiEWWpJjMZmW1RGgFd+MD33gQYmODom58OLZdS8EpaCtkNlZicFBDtjv/4fE8RMS3/13iWcPAK99jcDn7/fmnI1HoVBcODt3CLz9rTZIKfHmt/FeTOXGG+jyeOA54J3vkZiYUEraFc6LAXzbeP1tAL+buYGu6wO6rh8yXgcBtAFYIIqVl9nSXGq6e5jcwu1mIPhqJnrau4crzWbdnfJygYmJFPezLIfKz2cc2krIJSZz/zMyZxdHk9tvzV5kt69vYSIMuz03N7l4XMLnW5igwKSwkJnkZma4UKptXtqlLJVEQqJ/YGllJJviISXmi0DnyoUkkrHZ6JpYXpberyu1HNlsdOusrFxYDuC+ewRKSqxENzu2ATdchyX7sLBgZbFi2TjVZimftAivvIMuJvYzFZnFgmbi96db0FOPbbo5ZuJyWS6ky5E6LjLjq5ajvo4xgUvtM9USKpMLt8ulD51OWvIzt3U6FypHpkIzX2uwJDdFC+BCyaHDEg8+JNHZlVsR52cOLL54s3O7VafR4ViY5XE5RBYX0JlZjt3FaDQy+/b25p41MheUgpYj5mrb//4f8JOfSsTjrMX0gb/m9//2TYHn/3b2opoKhWLtEELgs59mrap2XeLTn7GeSFVVAl/+PF0iX/t6JhpRXLFU6Lo+AFARA7CkM5imaY0A9gB4ZrkdOx2WNaOoaPXn+IICgZ07uN9wWKK1dWmFKpFYufUiF67dQ/eglZDNfcluF9i1c6GCNjQEPP4EljWhJZPMKJgZN2QyOkpF0uUCNm3ifR+J5NYhUtI1KdXtMds2mdTXpad+zwWx4MUS7TL+m/XxUhWElmZg+7aVBdQ4nQJOx0ILCMDMitNBy02vuBhZs0WmEokAA4MZbV7hGMzPp+UM4Dhv13PfwZLp4S/glrQUtIU/fuwJ4NmD2X9nt1vxjBeKecSWZqu+Yq60tQNPPrXw88w0+yaZFjSB3JKEzM0xm2hm/+ingScyjm/LuDZVVcyImAuFBcD2bXRXduUttMZno7RkcSXz2PGVuzWmkk2BNeMKF6N1Ey2Au6+5MA+ExVAxaEtgPhwmJ4HXvVHiP78P/P5LJX7+S4E/+hOJ4mLgM/8g0tIxKxSKS0+hIWxVlEvcdQdf//h/JFo30dL2vvcI/PTnEu9+n8TvvFDiz18rlvSLV2xMNE37DRg/lskHV7gfP4AfAXi7ruvTmd/bbDYEUgovOZ0UZi92zHi9UcgkEAgsEWghwxgbs8HrdcJuF/D54vC4kxm/icNmtyEQWN011mCQ2RdT47cuhDxnBNNBGwoKnLDb7fN9uWUL/9raEvC4E9i82Y5AILvi0VAfRTAoEQgslNj8fomyMsbXBYMSU74kCgpyL2FTXp5AcEaguip7/3m9C/u8rS2BkdEkPB7KBqnfeTwxJjbJuK5z4SQ87jgCfseS18rjjsLnY184nRL33ZPAzh2WeHbNLsButyORWKIYWAaRiMTZczHU1zsXjFu7LQqf14H8fBte+HyZ07iemk7C7U4iELDa5fFkG5uLs6kliZISAadTIBpNYnQ0jsB1uf02FGJfFhQ4F1xnn4/jKZd2mOMx2zU2ecHzmIHTm3EfOBwSXk8MdXVLX89lz2WO51JYaEdBwcoU7+amJGpqZNp943FH4Q9YbXI6JTxu+tp5ven3mM+fgG82iUBgkToPBna7RCwWW9A/1+6VmJuTafd1NGaM84BzxdmTEwkaPOJxYHOrREGhWNDvmdx+2+Lf7bspaViHL2wOKy+Po6TEnjYHhsMSJ08lcO3eS6syKQUtC4mEhN0u8IEPSbzgeQJ33Snw79+W+PkvgO/8O1BUKPFXbxO4ed/ytSQUCsWlo6hIzGduK8inq0MiIfG5z0u84XUC1+4R+NQ/SLzqdRIfeC/mrRaKywNd1+9d7DtN04Y0TavSdX1A07QqAMOLbOcElbN/13X9x9m2SSaTCKakEzvVxoD51NpMF0IkIpFIAMFgZNFt3B6J2RmJyckw8vIEQiHGNqT+RkqJRBwIBld3/B4/IeF0Alu0i9tvOJJEKAQEg1R0gxmp2WaNcyovE1mztsXjjO+WEAgGF18ODwZZwNvhAMJhkVOR23hcorOT2d4W67+ZmYV9brdLVFQwKUPmd3NzEvEs1zUc5n5mZrBksd65sMTMDNsTjUr4fQvblq0flyKRYF24aDSywKJw6y0AEJnv+1wsDk6HREFBeruyjc2lOHpMYucOFkHOy2M7cv3tdJDHCoXCC6w6K2mH2Y8TE4v/Znqa90Einn6cSMS4nrMXF4Nqtjc0u/J72OvlX+pQmAtL7stwUY3FuH8A8+Mq9diRCBAMLn2zJBISmzcv7J/ZWYloDCgqyp8fj6FZc5yHkUis7HxGx3g/Tk0xVrKuDigtufC+dbl4zhfKFo3KYmr/TgclurqBza2rLy8UFRUt+p1S0AzM2kqPPS7x819KfOoTAh/6gEA4LPH1b0r85KdAWanEu94hsO8mpZgpFBude+62XMYqK1hP7VwHU//edYfAO98jcd89Eq9/XfZisIrLjp8A+DMAnzL+/2/mBhrzan8dQJuu65/Ndcfa5guLJ8pk1w66ii1FKCRRUZm9TpaJ3Za9mPLFsloLFjabWDIdfC4xMJGIwL4bs9dBS6WhQeDwEYnS0twsQUKwftxSK/3ZXPcKCpgAwOUCgjkKgGZdqJWMHSlZf6q+PvffZMNuF5iYlCgokEsqh7kSixmCb471urLh91vK4MyMxJFjwK05usKZsVSrlZxnsRgmgDFObhczc6dijtuLbYH5+9USI/dckx7bmebimCV5Ti73n90uUJolY2dHJzA4RJffzP1dyPmUlgj4fVxkOfjcxfftWpAfyF5Lb6256hU0KSViMeB1b5D43GdYL2X7NuDQYYkf/4/EU/uBW24G/uZDYj7NrkKhuHxwuwX++OV8XVMtcdutAtfuFTh+UuJUG/DyP5V44fMl/vSPgfx8FZZ7GfMpAD/UNO21ALoBvAwANE2rBvA1XddfAOAWAH8K4LimaUeM331A1/WfL7Xj5bIf5kpq+vvFyCysmu2RE0+sLFPaerBYinyAiyRLpfN3OASamuSSSmoqlRW51zyy2+kWOTwsV5TQq7sbmJgCrr829xiXzBi8JTELHbsEbrn54tXvSIQFyhsbLnpXABijli1xxor2kW+Ni2RyYZ28pciWjdCk8ALaVVgIOBcpCH7PXdmV9NUS/+YVmlV63GTOK6kKWGabbeLizmPrloVJSpaMD1yGaFTi8SdZE6+paeVlFy4FoRCz+l5IUpuL4apU0Exr2ee/lER9ncCLf0fgfe+RGBmRePBh4DcPATIp8TsvEnj7X+b2UFUoFBuf0lKrDtE73y7m6y2974N8SLzhdUn86gHgox8WkJICxFokhVCsPrqujwFYsM6p63o/gBcYr3NIUbG+5OeLtALNrZvSi6YCFxcEfylYTpBxOMSS2RzjcYmxMavQ7XJUVeV+SeNxiWAwPYV9JtmE84oKWikcDpFzrSNzu6WUi2yshpUoL4/FulfDerYYK00S0j8AFBXTCsniwys41hJlFEpLV27hWMpdeXCI1s+ysvTPL0YRScVcTFirKyME+2NyUmZdKLmgAs4GwSBdPFPr+V1Mf4RCXGDxegXOnJVw2K0sjBsFj4eGm0vNVaOghUISXq/AgYMSP/wviX/4lMCLf4dVzL/5beA3DwLjE8CddwB//X5hBOVu6Oe4QqG4CEwXp717gJ//BPjFL4EvfIkFYQ8+B7jdEl/7BvDlLwg88aTE9DTwgucLDA1L2B0qG6Ti0pCXt9DVqLmJ9dOuVGw2YHKKVsLVLPxq7rupaWkhNZtb2IUs1FCGkIjnUBtptbNySgkcPQZcf53cMLJMYWH2Yti5sFIl92I4f57jI1NBuxhXvlTmFbQ1dtgozJKpNNdC1YsxMAj09acvcFxMv+TnMzuqlIzz3YhOakIIVK+wxMZqcEUraH19EoEAV5Je8jJmYayrlbjxBuCTn0rimWfpTnLjDRJ/8UaBG69f3fo2CoXi8sDhEPidFwHP+23gZ78APvM5zh0v/V0mACguttL/fu3rEvtuiuHuu4B//KckXv4HAtXVwNmzZt0YNYco1paV1va53BCCtblWq+ZVKjabQHc3s1UuVtdrtY+7FuexHIkEY+XWUuBdqVK5dcuFN2YpC9pqc/O+7O1kiMvFa4rzCto63MbFxYDXt/x2i7Ftq1hgfb4Yy+LsLHD4KK3ue3ZfeLuuRK4YBc10WzxyVGJ2FrjlZoGvfk3i7ru48vWSFwPveb9Eu86A75tuFPi7T/D1RlldUigU64vTKfC7/w944fOBRx4DfvzfEl/+isS9dwP33iOQTEp88P02+P1OzMxEsH2rQCCfq/0f+LDED74r0K5L/PoBibe+xYbBIQmZXJkLlkKxEVeRLyVCiBUXhc6VeFwiGgXyl8hYv2P78slccuX2W3Mrz7Da19zpXJ/EBmvFpbSgnT3HshotzQsvysXGcAGrl2zkQvD7xZLxoRfCxfSHEKsXJ3mlcVkoaOPjEm43XZJOtUm0NHN16Pv/IfHaV9tw5CiFqC99HujpkejoBJ47JNE/CHzkb4GyMondu4CX/Z7AddcuX5BRoVBc3ZjCzX33CJw5I/GrByQ++jE+tG/eJ3H7bXFs3SLx/OdZc8l/fp+vS4olrr+Or/c/DYyNSbzuNQJf+VoSu3YK7LtR4NhxiU0tS2eSUygUq4/dzuLWS+FyiZwK5uZCLsrZnt2LW/M2MmtRLH0x/Bdh9Vkp4fAS57YKU7ZpQbuUSudacjEWNKcT8G6wmLONwmWhoH36MxLP+y2BO+8AvvQvEm99C2+e02eA734vifNdXO267/kSeXnAphb6x/7JKwR2bANKLqKmgkKhuLppbRVobRV40xsljp8Ann5W4uvfjEA/LaFtlti6lXWjNm8CamqAsjIxH7vwkhcLmE/0m28SKDFiib7+TYl3/ZVAPCHxF2+W+M43BYaHGfv2Oy8SGB+XiMWBihVkmVMoFMsjhEDneYnSkotLlrCaXEzdp/Wkvh7wjFyaY5WVXTqL4FIJRGprGDZzMZixiZfSbXOjEomyrERNzXq3ZOOxYRS0eNwo1DjDWhszM8DEJDA6CtRUAw8/IvGfP5IYHAJe+3qma62tBc53AfV1AnfdwfiPinKVCl+hUKw+NhuTB12zSyAQ8KOnZxpHjgLtusQvfyXxhS/S1bG0VKKmmgHmgQBdqQIBAb+PwdWnTkm85MUCXV0sBvqiFwJPPwMMDUmcbGOMwLMHJIaGgd95IfDj/5GorKDb9vd+IHHTjUBzk0hpF+Dz8c/vYxprt1vFwl3OqCu3diSTEnNzG0c5u5ypKBeoKF/vVlxatM2rd3dmS0ZzOXIxMXX5AYGb961ue64ULomC9pOfSvzs51wRjsew4H8kAsyFeXH9fv4F/CwMWVbK6uK7djI9dnk5VzCu9CBphUKxsSkspFX/zjusuWhmRqKvn4rY2BgwPS0RnAEGhxgbG49bf4lEqhuN5evyb/9uvf7OdyUSCWBqinERc3PAw48Ajz9hbROPA7MhIDTL9MfRKOdSn5eJTvLz0/8K8vlQzC/g60CAc21+gHOvislVXMnYbFdWbJbi8uVKcXF0OATuuUuqRcFV5pIoaNdfC5QUCzidTJnrdLLGhMP473JRMPB61aqvQqG4fPH7BbTNTD5ELv18FotJzMwCs4ZHwvQ0MDUNBI3/09MS/f2Sr4PA9BT/B4NU7AIBifxAukIXyAcK8hlc7vdFEItLNDct7QqkUCgUisVZj+yea4WS3VefS6KgVVWtXUYmhUKhUFg4nQJFhUslHcj+IE0kWMB3OkilLl2xkxifkOjuAQQSCEckZmcFdmxfo5O42lGyzmWFiqpQrJR9N9ItXaFYjA0Tg6ZQKBSK9cNuFygsZDHZhVgSaCDgRTAYvEStuvrYuR0oLV3vVigUirXE71davWJplIKmUCgUCsUGobJSCW6XG/V1jP9UKBSK1UIpaAqFQqFQKBQXSHOWgsYKhUJxMVxBIYoKhUKhUCgUCoVCcXmjFDSFQqFQKBQKhUKh2CAoBU2hUCgUCoVCoVAoNghCyiukUp5CoVAoFAqFQqFQXOYoC5pCoVAoFAqFQqFQbBCUgqZQKBQKhUKhUCgUGwSloCkUCoVCoVAoFArFBmHV6qBpmlYM4D8ANAI4D+APdF2fyNjGDeAxAC7j2P+l6/pHVqsN60GO510H4DsAKgEkAXxV1/X7L21LV59czt3Y7hsAXgRgWNf1HZeyjauJpmnPA3A/ADuAr+m6/qmM74Xx/QsAhAC8Stf1Q5e8oatMDue9BcA3AewF8EFd1//x0rdybcjh3P8YwHuNtzMA/kLX9aOXtpWrTw7n/WIAHwPnsziAt+u6/sQlb+gasNy5KywWe7Yt9WzQNO39AF4LIAHgrbqu/2odmr4h0TTNDuAggD5d11+k+nHlaJpWCOBrAHYAkABeA0CH6scVoWnaOwC8DuzD4wBeDcAL1Y+XjNW0oL0PwIO6rrcCeNB4n0kEwN26rl8DYDeA52madtMqtmE9yOW84wDeqev6VgA3AXizpmnbLmEb14pczh0AvgXgeZeqUWuB8eD8IoDnA9gG4OVZruHzAbQaf68H8OVL2sg1IMfzHgfwVgBXjGIG5HzunQDu0HV9F6iwfPXStnL1yfG8HwRwja7ru0EB6GuXtJFrRI7nrrBY7NmW9dlgfPdHALaDz4QvGX2uIG8D0JbyXvXjyrkfwC91Xd8C4BqwP1U/rgBN02rAZ/p1xqK6Hewn1Y+XkNVU0F4M4NvG628D+N3MDXRdl7quzxhvncbf5Z5GMpfzHjAtKbquB8EJo+ZSNXANWfbcAUDX9cdAIf5y5gYAZ3Vd79B1PQrgB+D5p/JiAN8xxvnTAAo1Tau61A1dZZY9b13Xh3VdPwAgth4NXENyOfenUqzGTwOovcRtXAtyOe8ZXdfNuduHy38eN8nlPlcYLPFsW+zZ8GIAP9B1PaLreieAs2CfX/VomlYL4IVIX+xQ/bgCNE3LB3A7gK8DgK7rUV3XJ6H68UJwAPBomuYALWf9UP14SVlNBa1C1/UBgJM2gPJsG2maZtc07QiAYQAP6Lr+zCq2YT3I6bxNNE1rBLAHwOV+3sAKz/0ypwZAT8r7XixUsnPZ5nLjSjynXFnpub8WwC/WtEWXhpzOW9O0l2ia1g7gZ6AV7Urgah7vF0XGs22xZ4Pq38X5HID3gK6iJqofV0YzgBEA39Q07bCmaV/TNM0H1Y8rQtf1PtAjphvAAIApXdd/DdWPl5QVxaBpmvYb0Nc8kw/mug9d1xMAdht+wv+tadoOXddPrKQdl5rVOG9jP34APwLjNaZXo21rzWqd+xWAyPJZptUgl20uN67Ec8qVnM9d07S7QAXt1jVt0aUhp/PWdf2/wTn8dtC98961btgl4Goe7xdM5rNN07TFNlX9mwVN08wY7ec0Tbszh5+ofsyOA4yF/ktd15/RNO1+LB56Aah+zIqmaUWgVawJwCSA/9Q07U+W+InqxzVgRQqaruuLPoA1TRvSNK1K1/UBw61reJl9TWqa9gjor7qhFbTVOG9N05zgA+zfdV3/8Ro1ddVZzWt+mdMLoC7lfS1o8l/pNpcbV+I55UpO565p2i7QLen5uq6PXaK2rSUruua6rj+maVqLpmmluq6Prnnr1parebxfEIs82xZ7Nqj+zc4tAP6fpmkvAOAGkK9p2neh+nGl9ALoTfHM+i9QQVP9uDLuBdCp6/oIAGia9mMAN0P14yVlNV0cfwLgz4zXfwbgfzM30DStzLCcQdM0DzgI2lexDetBLuctQJ/oNl3XP3sJ27bWLHvuVxAHALRqmtakaVoeGBD7k4xtfgLglZqmCSP5zZTpDnAZk8t5X6kse+6aptUD+DGAP9V1/fQ6tHEtyOW8NxnzGjRN2wsgD8CVoJxezeN9xSzxbFvs2fATAH+kaZpL07QmMKHSs5eqvRsVXdffr+t6ra7rjeCYe0jX9T+B6scVoev6IIAezTLh3gPgFFQ/rpRuADdpmuY17vF7wPhS1Y+XECHl6lghNU0rAfBDAPXgxX2ZruvjmqZVg6mKX2CsNH8bzAhjA/BDXdf/dlUasE7keN63AngcTFVq+pd/QNf1n69Lo1eJXM7d2O77AO4EUApgCMBHdF3/+vq0+sIxVjc/B47fb+i6/glN094IALqu/4sxkX0BtAqHALxa1/WD69Xe1SKH864EU0Png+N7BsC2y8WNdylyOPevAfg9AF3GT+K6rl+3Lo1dRXI47/cCeCWYGGYOwLv1KyfN/oJzX98WbVwWe7aBcWgLng3Gbz4Ixiya5RmuhLjNVcNwcXyXzjT7WZ+xxnaqH7Ogadpu0KMhD0AHmB7eBtWPK0LTtI8C+EOwXw6DKff9UP14yVg1BU2hUCgUCoVCoVAoFBfHaro4KhQKhUKhUCgUCoXiIlAKmkKhUCgUCoVCoVBsEJSCplAoFAqFQqFQKBQbBKWgKRQKhUKhUCgUCsUGQSloCoVCoVAoFAqFQrFBUAqaQqFQKBQKhUKhUGwQlIKmUCgUCoVCoVAoFBsEpaApFGuMpmkzmqY1rnc7FAqFQqG4VKhnn0Jx4SgFTaFQKBQKhUKhUCg2CEpBUygUCoVCoVAoFIoNgmO9G6BQXK5ommYD8HkAfwjACaANwG0Ang/gcwDyAXx8vdqnUCgUCsVqo559CsXaoyxoCsWF81sAbgDQBKAYwNuN//8G4M8B1ALYBsCzTu1TKBQKhWK1Uc8+hWKNUQqaQnHhxMCVQg1AUtf1p8EVxCd1XX9Q1/UwgA9D3WcKhUKhuHJQzz6FYo1RN49CcYHouv4ggK8C+BaAAU3TPgqgEkBvyjaD4MNMoVAoFIrLHvXsUyjWHqWgKRQXga7rn9F1fQeAmwG8EsAY6N4BANA0rRL00VcoFAqF4opAPfsUirVFJQlRKC4QTdOuAyABHAEQBJAAMA3gVk3T7gLwFIC/AZBcpyYqFAqFQrGqqGefQrH2KAuaQnHhFAD4NoApAMcB/FDX9f8AVxO/AaAPzG41t24tVCgUCoVidVHPPoVijRFSyvVug0KhUCgUCoVCoVAooCxoCoVCoVAoFAqFQrFhUAqaQqFQKBQKhUKhUGwQlIKmUCgUCoVCoVAoFBsEpaApFAqFQqFQKBQKxQZBKWgKhUKhUCgUCoVCsUFYsg7axMTEuqR49Hq9CIVC63HoqwLVv2uL6t+1RfXv2rIe/VtUVCQu6QGXIRKJSDXGVgd1v64Oqh9XB9WPq4Pqx9VhqWffhrSg2e329W7CFY3q37VF9e/aovp3bVH9q/pgNVF9uTqoflwdVD+uDqof154NqaApFAqFQqFQKBQKxdWIUtAUCoVCoVAoFAqFYoOgFDTFZUlfv8R0kCGSn/9iEpOTEhOTEm95WxIA0K5LfPLv+frESYlHH+e2kci6hFUqFIpLgKZp39A0bVjTtBOLfP/HmqYdM/6e0jTtmkvdRoViMaamJLq61DNKoVAoBU1xGfHUfolHHuXD68tfkTh5ip+XlgoIAfi8wB+/gvGWFRXA836Lr6NRwIxl/fQ/Svz3/3IfTz8jMTurHoYKxRXEtwA8b4nvOwHcoev6LgAfA/DVS9EohSIXZmaA8Yn1boVCodgILJnFUaFYb851SHzvBxIf+oANLhdgM5YUPv5Ra23h5X9oJcHZdyP/FxUKFO3h6717rO/f8y6BRIKv//t/JRrqBQCJB34DvPj/AUJsqGRyCoViBei6/pimaY1LfP9UytunAdSueaMUihyRkn8KhUKhFDTFhiOZlHjjmyU++mGBygrg3rupNF279+KVJ5fL2sfff5JKXv+ARFe3hBA2tLdLuD1AY4NS1BSKK5zXAvhFti9sNhsCgcAlbs6Vid1uV32ZI15fAp4ZiUBgoWim+nF1UP24OlzJ/Tg7K9E/kETrpvXNVKkUNMWG4d+/L+F0AH/wMoG3/SVQWgo4nQL7blrb41ZXCbztL6mQteuAwwk0NgATkxJFhUpRUyiuNDRNuwtU0G7N9n0ymUQwGLy0jbpCCQQCqi9zZCYoMTcHBIMLnzuqH1cH1Y+rw5Xcj/0DDKGprFh7+a+oqGjR71QMmmJdOXtO4r0fYDKPW28G7rqTn2/fJuB0Xnrl6HdfLPCiFwjMzEi86jUSU1PK30ShuJLQNG0XgK8BeLGu62Pr3R6FwkS5OCoU6091lcB996z/4rxS0BSXHCkl3vZXSfT0StTVAn/4MgEpJRoaBMrK1v+mAAC/X+A/vidQUCDws19IPPmUemoqFJc7mqbVA/gxgD/Vdf30erdHoUglqRQ0hWLdmZqSOHBw/W9E5eKoWHOklBBC4N+/L5FMAn/6xwKvfTVQVsqYsL171ruF2XG7qSyWlQKBAM9jZgYIBDaGEqlQKNLRNO37AO4EUKppWi+AjwBwAoCu6/8C4MMASgB8SdM0AIjrun7d+rRWkUosRve+/Pyrd35VyplCsf5Eo8Dk1Hq3QiloijUimZSw2QROn5H47OckvvwF4M7bAbeb3+/amf0hLKXE8Ahw5iwwNARMTQHhiITdDjjsgM8nUF4OVFcCDQ2Ax7P2D/MbrucxTpyU+Oz9El//isr2qFBsRHRdf/ky378OwOsuUXMUK0A/DQwMAvfds94tWUeUBU2xQZmZkQhHgNKSK1/2KSsTG2IeUgqaYlWJx6lMveq1En/zYaCpEXjvuwWEEKipyf6bSETiiSeBp56WOHAAmJkFmpuA6mqgsIBKXTQKzMWB/n5u298PjIwCVVUSTY3AFk1gx3Zg+zbA612bCWTHdoHP/SOVsyefkrjpRsBuv/InK4VCoVhrzPInlyP6aYlgELh2LxUsm+3CngtJpZwpNiinzwBj41fHAsroqMTho1j3ODSloCkumnhcwuEQ+MrXknDYgde+2oZPfAyoqeaDqqkx++8GByV++F8Sv/gVUFUF3H6rwMteCmzaBDgcy98YMzMS57uAcx1Ae7vE/Q8DPT1Ac5PEjh3Azu0CO3YAVZWrZ/HKzxeIRCR+/D8SmiZQWrIqu1UoFArFZcrgIBCNUYgdGADuvOPC9rOe1rNolAfPy7u6Fx3DYYm8vAtXsq9U8vOpoCUS8opfmHY4aBxYb5SCprggEgkJm40PpE9+SuJbXwf+4PcEvF5+X1e7+A08MiLxre9I/PoB4J67gc99RkDbvPIb3u+n1WzHduDFv8PfT08zPerxExL/9zOJT3+GFrhtWyS2bRPYthXYsgXIv4g4MpdL4DOf5u//80cSN94A1Ndd2ROWQqFQKBbBmP61zQLa5gvfjZRAMrk6TVopp88AQtAL5Wrm8SeBxnqgtXW9W7KxsBslwRIJ6/WVSmGhwPUbIDJZKWiKFSOlxBvfIvGudwi0NAP/8Cm6MC5RzgEAg8B/+F/Ad74rcecdwHe+KVBVtbqKTX4+66btu4n7jcclOs8Dp9qAtjaJhx4GzncBRUUS9XVAfR1QUyNQUgwUp/wV5Oe2gpZMXvmTlUKhUCgWx3xSTExKhEJATfWFPdfW04K2RVu/Y280ItH1bsH6IKVc1kV3I7giRyJMOLdWOQgGBiROnFIujorLiGeelTjXAbzijwT++n1AXR1v5PLy5X97+ozExz8p4XYD939WYIt2aQa+wyHQuglo3WRZ2cJhiZ4eoNv46+yUeO4QMD7Ov4lJPih9XgmvD/B5Ab8f8HoBvw/w+Y3/Piql3d3Aj36cxNYtwL0boHaGQqG4eA4dltjUcnVnFVTkhulB39fHRCc11Re2n/Wsg9bdDUgALc3rc/yribExiZINmGyjpxeYnAR27Vx8m/Wy8KYyPAKEw5TrVptHH5fYtkWipWn9r49S0BTLcvyExLatjBOzGZXzGhpyG7zxuMR3vwd87wcSr3mVwB/8/vr7drvdAq2tqS4M6e1JJCSmg0BoFpgNATMzwKzxenaGSUxmZyWGhiXa24HRMaCvH/jPHwGf+2eJ5uYZNNQnsWunwO5rgPLy9b/RFQrFyrDbrflOsfFJJGi9Wo8yKMIYJzu20+3+QpGSStJ6MDUN5OWt08GvImZnJQ4d2ZjJNoqLgIA/+3fmwsFGsKB53EDBGsWIRaNANCbQ3Lz+cptS0BRLkkhIfO0bEm9/q0BTo0B9Xe6/nZiQ+OuPSITDwFe+xN9fDtjtAkWFQFHhUlstPJdYTOLr35SYnbWhoCCBn/xU4lOfBsorJG6/DbjrDoEtmkrRr1BcDhQWMFhccWm42GnxXAfQ1b0+gq/Z9P4BiakpYOuWy8/Fcc9u9Vy6lJj1YTcSM7O0TC0VrpLYABa0iUkAEsgPrM3++wckTrUpF0fFBqXzvMSP/lvinW8XuP+zK19G1k9LvP+vmUDjHW8VV0VmKKdT4IUvALweF0pKEpBSIhoFjh0HHnlU4t3vlSgpBV7yYuD5v81kIwqFYmPSP8gC9WbtxquBSERetvNSPL5+xzbl7Lk5YGLiwvcjJdbNhHbsOOOPrtl1eV7/1WQt9SZz31Ku7XEuhNAsyxc1NmT5cgNZ0EpLgdGRtdt/eRnQ2rJ2+88V5cChSENKiVhMoqJ88WLSy/HAgxJvfYfEn/6xwHveeXUoZyZ1tQKNjXb89GcSX/4qhZ3rrxN49ztt+PF/CvzJKwR++SuJl/2RxA9+KBEOq8I3CsVGxONefeWsp1dCP71x7/nHnsBlMydJKZFMKRy2mPVpYlLigQfX9pxMF8eWZoGb9134826tY9BmZiSmg9kP4HIBJcVrd2xFOhshliuTmhpg546lt0kuo6BFIhJHj63t/TY2hkXr6q4GNrExkr8pBU2Rxo/+G/jilyW8XoHfulesyASfSEh86StJ3P95iU99QuAlL17Z768kbrkFeOHzeO6JhFVf5r57BL78BYG/+bDA409I/PGfSTz6mIRcT98WhUKxgKLC1Y9BO3eOiYk2IuYcdKlWyEOhi5v32tqBhx5efruAH9i6xhkKzadcR4fE/mcu/JzWWkE7chR45tns37U0AxUVa3dsxcZnaJiJQrJhDsvl5oeJSSbxWE0yF1lstrWdRwcGgacXuU8uJcrFUQHAKlL5/N8GotGVK1XTQYmPfkxifBz42r8IVFZenYqZSVEh49geekTiySclPvRBqz+EENi7B9izG3j4UeD+z0v87/8B73zHhadnVigUq8vE5Nq6OE4HJRx2wOvdGPf8pV4jenI/sGMbk09dCBMTuXkD2u1rr3iY65Aut7yoGptrfQ38fmAunP27w0d4Htddu7ZtUJCNaEGDZCbrpViPds/OpL+vqQZ6+9bueNVVG+M+UBY0BQDga9+U+P5/mKnjV/aAOd8l8fq/kPD7gC9/QSlnqdyyD3jVn7E/IpH0p68QAnffKfDdbwtsagFe++cSv/q1sqQpFBuBufDaxp898yzw7IG12/9KMZWDS6moxS4ibsxs56HDEqHQ4o0eHwceeezCj7MSKisEtm+7SBfHVWxPJku5bVVU5J5if2JCYnDwyn1WXQrHn43oNFNdna6YTEzKBXJLqgWto+PSuGxnXo+Tp6hErRXRKNCzATwdlIJ2lROJSMTjEn/2JwJ/9Acr//0TT0m88c0SL3oB3fbcbqWcpeJyCdTVChw4KPGe92efyLxegTe90YZPflzgX74q8dGPJzE7uwFnb4XiKuJCa1mthOWEtP4Bif6BSzMXbESBcSnMlfyxcZZCWaz9xcXA7beubVvMY588dXHxbuuZJKSsFHA6c9s2GgPOd61te1aKlBKPPS7nQwrWm/Z2ib7+xduyEe+3jk7g+Anr/cHn6O4HZF/A6ehc6Gp4KZTb2hq6OK8VE5PA6bNrt/9cUQraVc7XvynxvR/QcraS7F1SSnz73yQ+8XcSH/lrJr+4WuPNcuHavcD738v+mZnJPjPv3SPwra8LhOeAN7xZord3A87gCsVVwswMEImu7TGWi3ETYMD61cBKHx+pguJSM2UiQXfIWGzt5lNzz5UVwJaLiHdLJpmNMh5f3bbOzlJxXKqPjx4DzuQolBYVMtPdRiKZ5P0ai613S0hobml3wKW+W+3rnyvFxelW1p07gNKS9G1SW7ZeZUhKS4GK8rXbf0W5WPcU+4BS0K5aEglazl71ShaPXglzcxIf/ijd8b7yRYF9N63/QN7o2GwClRUC+mmJN781PftYKgUFAp/4GF0fX/8miWcPKCVNocgVTdO+oWnasKZpJxb5foumafs1TYtomvaupfY1NAS4LqJwb6ZrUDYWE5i7eySGhlmm42LcAFdCLi6OoZBcN+Exk1QBd6k2B4PA8ZN0c5yYWJu2S6MtBQX0mLgYYvHVd30NBpffprER2Nya2/7GJy5cOA+FJM51rKGyvDGGJ1o30SqZyXLtC4UknngSi8oIa4nflz4GkklrESnb/LBeCtqTTy1dq+1imZ2VOHR4/QeSUtCuUn7wQ+Br32C2xpW4Jfb0SrzhTRKRMPDVLwvU1yvlbCVomwXu/6yAzSYWdX+w2QRe8yqB975b4MN/I/G//7f+E4VCcZnwLQDPW+L7cQBvBfCPy+1oc+uFZzQcH5d47Inlt1vUgiatOkmXqr5XLoLtU/uZ6W0jkCq/yiWsEUVF1mp4dI2sK2Zbnju0Ci6OAGZDq9CoFeL1Lp5AJBOfF+g8DwwNJdHevrLzbddXL8vfyIjE/qfTj7/UOE4krNI28bhExyKK4mo4A3V1W+6B2dq3WDu9XoHSUmB29uLbsFJ6eoETJ633J08tfa3sSyhoUnKRKZmUGBxaXRnm2r3AoSNYM3fWSISu0+uNUtCuUl7yYuBlv7eyWeiJp5gM5I7bgU99UsDvV8rZhVBYKDA2JvHOdy8d3H7HbQKf+6zAv35d4t/+XaXiVyiWQ9f1x0AlbLHvh3VdPwBgWVF9curCFbSiIuDuO5ffbjFBsKoKKC4CHE7A47mwNqyUecFxiW0aG7nKvhFIVcqWanMkInH8BLdYqyeW2ZYtGnDjDRe+n0uVIS/bs+ToUWAwi0KRjUBAoLWVcWg9K8ymt2M7cP0qZcgbHgFmDEUmFwtwVzfw6GO89RMJ4Fzn6rQjG5EI4Hbx9dSURFdXesMWu9axmETAD+RdhPX+QqkoZ1kKkxuuo9sugPmbLLV/nVkUNPMeC84Ax45TierLMkYikQuPF7Tbge3bFl/gatethRIzQ3kumPdFUfHauDiu1M1aKWhXGYcOS3z0YyF4vQIlJbkNwERC4l+/nsQn/k7iQx8QeO2rbbBdLYERa0RJicC/fUvA6xU4emxx5WuLJvClfxb4n59IfOFLi7tGKhSK1WU6mK4cHT0mMTaW2/03O8vV5+VYTEF7+hng0GHLinZJWeIUiwrXNrPlSkht5lJCeTgMDA7x9WJ9eeDg0otl2ZiZkeju5m/MaVnYsgutS3H02KWPN87WXzt20C1vKWIxCr7dPRKhEC5IDgiF0q00q81SYyE/AGxuZZCVwwFs3pRdWV0NtmhAQQFfnz1nJZ1YbiFkappzT2ZOgJGRS7BIK5jJcf6Yo1ks+Dm6ODqMWDYhBNzuhYrS/qdXUMssY5jtf5rK72J5D2prgF07gaFhiUcfz/EYsK7N1NTaFLd/5DFgeDj3/ao6aFcZrZuAQCAPwFxO209PS3z04xKjY6xvVlOjFLPVwukUiEQk/uWrEn/zYbFo0Gt9vcCXPg+8890SwaDEe98N2O3qOigUa4XNZkNLsw/CJhAIcB0zGIxifMKGxsblH5tCSExPx+DxOOFwWPeqxxODIybh9zvhccfg8wkEAgtT5113XRJul8DQUBLRKBAILJEffZVwOiU87hi8Xsf8OWfyxFNR7NzuQGlp7mu7drsdgUBgwecedxQ+n33+3LzeODzupPF8Wh6P28rg4vPaEYnIrL8PBIDaWuAXv4zCH8h+bpFIFC7X4uedjdBcEolkEoGAA253DHabxNmznNOf/7zczR/a5iTy8oBAwAaXKwaPWxrtTt/HYv2YC8GZJDzuODweGzzuJPx+54JnSDTG7MGlpYuPtWCQY6S5yYFHH4/D5wU87oVtXQr9dBw+HxAILLyPznUkYLcDjQ25jXefzxozsRjb5vM7EVikFp3HIzE8IpCXRzNRUiaQn5/eDo87Cq/XlrV9K6GjMw6fT6Ciwg6vN465ObZTSqOdi9xngQAwNhZHNGZDSbH1/RNPRhEIOFBWlvsYnZhIwu8XcDpzkxeGhhMYGkrilps5Jw0ORREI2FFVZYfHm4DHnYDXuGc5Hr2YmUm/50IhjrVAgHOcsDkQjrCfU9vxOy/K+TTg95n7zJv/7S9+FcXddzqzJrfz+SQSCaB/IAmPO5Hz+EwkJObmIkgm7SgvQ9a5eTliMYl4HPB4FrbL447C7rDnPJ8rBe0qIRqV+PfvA6/4I2DvHkdOQcOHDkt8/O8kdu8CPvG3KoX+WuByUfkSQuDXD0js2sVaOplUlAt84X7gHe+S+NSnJd7/3gtbvVQoFMuTTCYxODgLjxsIBnmfzYVpNTDfL8ettwBzc5G0z+bmJDrOS9TXhTEXZlrzYHBh4I+ARDBINyxXHo85OyvhcKSvrEciMqfsu088KVFSAmzdsvi24bDEXJiuSalKZSpNDRI2W+59AACBQADBLA+cubDE7Ky1r1DIOH4wsmDbbMyFrZXomRlaLbP9PhSSeOZZIBaXmJ0VCGZ5jt16CwBEcnoumng9QFMjE3DMhSRicWDXLiA/IBAMRiClxPAI5+6l6O6R8Ps5n5t9ACw8j8X6MRdmZ7jfmRn20fR0eME1fvxxibo6oKhw8fbOznI/4bDE9q1MejUXFvNtjcclunsl6moWVwq0zeb5Lfzu7FmJ4mKgpDi38ZU6ZmIx83UYYhFn1r5+if/+Hwc0LY6WJolznQJ1tenjfS4sMbeC+3wxgkGJ/HzuZ27OamdwxnxN61RPL7CpxTpWKCTh8zJ7a2ob5sISMzNYkRz28KMSDfXA5tbcfhPwm/ckB+H110rY7WyH2dfmPRsIBBAOhzAXBiYnw/MKvzlGgkHOcePjLN4eDguEU6a6dl2isDC7vJPJzGz63DA+LnH9tUAkEkY0uvD3jz0uEYkCWzVgOijT2rcU8bjE2XO8H+++05Z1bl6OAwclJqeQ1UVyLiwxO5N+XYuWyHaiXByvEsIRKmlLFao0iUYlvvjlJD7wIYnXv07gQx9UytlaYprpz3dJhJYIDC4sFPinfxQ4fQb49D8qd0eFYi2R8sLjvyYmJJ54Si5w60kmJRx2y41osRiK5w7RRVLYLI+ip54GTp+xtpmezi0RCUChfLmg93nvqYxpJRaTGBiwXPlyeYZcapaaCpm6fukYtAcelJiaWtl8euaM5QaVlNz39JSVEGFyijE4yxGNWqUUzBacOCFx9Njy7YnHF46xbOQSn3XLzbkXqu7oYLxapotZVzfwvz+hIrgYg4MSjz6evSE37xPYouUua6QefrHxmwqVag7g4IzAnmt4D+qnl65ZthzJ5MKCzk2NQF42A0zKtRgYZLKVVObmKK8tV4JjLQiFgPx86/3JU1ywAbKPHbvRxmzxdOZnDrtAKERFKZWhIZ7rhXDmLNu62Hi+6Ubgrjs4f/b0AlNTue975w6BoiJcsItjeBmdbiVeqkpBuwo4c0bC7QLe8Oe2RVdGTdp1iT//C4lTbcA3/1Xgeb+l6ptdKl7/OhuamxlvttjkUFjIxCEnTwH/+E9KSVMoUtE07fsA9vOl1qtp2ms1TXujpmlvNL6v1DStF8BfAfhrY5v8bPtyu4HRsQtrh8dDgT1bTaZYfPnkIzt3AHt2A/EYMD3Nz26+ybI+ACtPYLJUpkPAEhza2tOVlWDQEiJPn2ZNseWIRCTm5i7h3LTEofx+gbvv4nNssUeZK29hPM1i9SpNKiuBbVuMw0vAZqcwmFroNxfKy1IKRBuHbGpMjwcLhyWOHV+YzvPsOeDI0eWPYQrL5v9sQuLYOHCuI7c2NzYyOUg0I+mBlIy7crkW/+3kJNBQn/27ri6Jp59Z2LhTbUunPU+NzUosk9EzEuVzc3ZWovM8LZfdPVQ6L5TpaWYVfOBBK0tkV7e1KJKqbKUqy9nmh5ISgclJxn9lciEhaCtR9EJzQHtKAehQaOH9nq0N2eai1HiuaJSusKnccbtAU+OFyZY33iBwqo2LG5kMDEjEYpy3bIIZR5caj5lt7h+QmAkCxUUSR44uL2MlErklO0kmVx5DqFwcrwK+8S2Jl/2+wN49i28zPS3x1a9J/Po3wKteKfCHL1NxTuvF5lZrlToWkwtcRYoKBe7/LPDWd0h89n6Jd7598WBZheJqQtf1ly/z/SCA2uX209uXQCgE1GXZ0nzILnXPud0Ct9y88HObTcDpkPOp6hcTnhwOCkaJpJVVLRymgG1mdzMPL6XM6f7PNUOgy82VZ5NoTBpp3wX27M4tScjTz1J4uu+e3I4JZE/gkUjInJ5DS9dBk3hqv4SwLX7Nbr8t/XMpJfY/A9yyj6VoshEICJghYTLJjJtbNLHiVP6TU4DPyIxpXiOPNz2L3/Aw0NeXRFNj+m+3aCInoc+UMZdS0Nraci+yHY1yweDEyfRodiGY5XOp4ahp2UtHxOMSwZn0JBUmff3Z92UeJpHIzYLW1y8xMJBESwvvsckpq17hxeTfyMsDYoayMDkFVLqpdBcb3mvZLH1Jmb0fJiYlaqqpuD/wIENMysoW79BYjK7P5tg+cJBuoi3NfL8SBa2yIj3Jza23WMfNZoU1X6bOLfPz0vwHQF0dFsgxB5+TKCqy2pnJc4ckdmxPd+k257qeXombblwoo8bjNC6Y433nDvbxUkp7KlICM0GeQ1mZgH6av8/MqPnAgxLXXUtZ7OlnOJZuvIFWwnMdMmuuhgcf5kJXrrUGAWVBu6KJx1lU9JMfF9i7J/tNkExK/PRnEq/4U4npIPDdbwm84o+EUs7WkW1bBbTNAvufkfjAh7I/NYqLWU/t0CHgC19SKfgVitXk2LE4/D6ZdeX12HFkTRudyuAgreCzs+n3JedkoL6O8+tiguyhI1yBT111PnQkva6SzVjEydWStpyCZk4hleV0BTMZHgb003w9MpqbIJttZftCeOgRZq9bjqW2cDiAwkLjzSL9/cCDEqOj1l5My8ZSwu2Jk5angzS2HRqS+NWvV54R0kzHbv6qrY2Z6kwWEzBDIYmDzy1f1DhpjJGlrt299wjULlJkW8r0Z0z/ANDRuXBMCQH09y/t5nW+i9nsMnn4UaCiXFpp3TPIlnbePO3Ue2CpcR4IAK2tdtjttKjeerO131yu2MCAxDPPLtxSCGDbNr6OGOdeVspU+4uRTGS3oAF0/TO/G1/GYv3IY0Bnp/Xe46FF2MSR4ZL8wIMSo4tkox1JqXk2PMzxvVjWwUSCMbnxePb9mRZ7p1NgaAjzbtLz7XLQurUY4xPp1rtoVKZY5Tgvma7L/Ezi4UeBe+5mivz77hHzrsPxHNLbRyLc/+bNAi4X8NRTSyvuQcOzITTHrJsA+zo/Sx6fkRGJliagvk65OCoMfvzfFN4XWzXUT0v8xVskvvcDiY98SOBvP2JD+TIBzYpLxw3XAX/1Nl6Ps+cW3tUlJQKf+4zAY4/TSqpQKFYHIQRCc9lX7uvrgNLSpX9fUsLtFu6XxV1N97nFFIDrrwWuuxY41ynRrnPbu+4ANrVY25jCx2oraE8/Q1c9k9JSQDNWffv6lxcYV5M7bmNfJpNLuxolk+mCz8iIxMOP8Dcej8Ce3RTIe/skJiYW7qemGkhNkLiY4JzK5lZakUzFxWZj7NXk1MqEML+fMUeAJdRu34E0C2w299T2domTpyggLkemIpOtfe06XbqycfA5/pm/a6gXmJ5eaAGy2ThevEsI3jYBtDRJnO9aeKyOTuDxReIqXXlMsjM5af3OHNOTU0Akuvi5meQHBMbHuHBNy+oilrdFxKCBQUsYT2U6aC3amO3o7cuuqJqHOXo8uwWtqFAYiTeM7VPr/S2mLKTE/O3YTkXbdLvLNscslmvG7gDadKv9JcUp90JGP7XrCYxPUJk8czZlJ/OWff6fGOeL8ows1buvEaisXFrenC/cPitx+oz1fsd2geGR9IWgSISuwA88KHGqLYmDzyVhs3HM52JFfOwJuqp2dEhMTwPbtqbu24oxNAujCxtjjQcHrYvi8VilFRIJ6zehEF3bM6/fcin3lYJ2BfO7LwZe+ScLb4DpaYnPfi6Jv3y7xG23Cnz7GwLXX6cUs42G3S5QVSUwMSHxNx9buBoPAOXlVNJ+8lPg+/+hlDSFYjVISq4OV1Uu/K7zPAXCpbDZqEy53enWDbtdwJXHWkfA4ha0SAQ4e5Z/pjtkVzfdZIaG01d2c3VdXC5c1dyftgWorrI+j0YsQfOmG7BoOZALIRpdmFzBJJnkyvzUFAXjJRNuZOwiFALiCQrAE5MSDz5EZS0Wya58bd2SbqHJ1QKY6lpnswN19QJbt4gVKWhmrAxg7YtZBFOOk+UaB/KBTZuAO24Ty2b0TY1Bi0Qkzpxd2MCJSaCxIfvvJ6fSFc/paYmdOxe6rdkEx3Rkif6rrWWsW5pQn/L7xUIxhAAOHwEOPGd9Ziqcx44Dx45Z57gYZ89JBGckhOC9abNdeKIKk+4eie5uzCv+5vjKz7cWctLu85Suz7a4MjgoUZCP+cXyXMLMUxW9Bx+WOHZczu9brEDKLysF9u7m65kZLkJUVaVvYzbHtA7a7RnJUDJcIb1e1iXLvCcefSy3RDjmPja1WPtob5fYvg0L3I/NMXXkKBMtwVgQy6YIZyMS4Tzg9dLVG+B4atctLwKzMLp5y9nt5uIMlcg2I4avqwvzSZzKyljzrbub52Au6swskRQOUAraFcnIiMTffpyrB8Up6WqTSYmf/ULi/700iPEJ4N++JfAnr8i9RoZifSgqEvj21wV8PoGf/izdFQcAamqopP379yT+9/+UkqZQXCwOu0BRYXZhz+sFEos88GMx3p99fXTPe+gRYDwle2I0SoWjqhLGfZz9fj15ilYVn4/KxtycRIfhxuTNyCyZq4K2HGZL8pzp+5ycolsaQEElvITbVs7HMgSUkVEKMdmsYw8/AvzyV0zUUpBP4XG5tmfy6OPA1KTEphYKyU1NIquXyG8eYlbCri6JEyflfBxZNkUrEpGYnpY41wE8cyA1Wx3Q3c0YlNTfPf5EMuvimonbBfj86efR1QUcPWZtk+0a5zmB0CzwmwdlmqtXKuPjtCgkk2zb5CQXHlItpCY3Xk/hdClLpfnN1DSTaixIjiDoepZcwqp79pwl7GZSXbNw0eI3phupXKispCo45utwmOMrW2bF2hpgU4sNdrtAPMG4IZ+PB4xGsy+CLkdxEa28u3byvXmtvF4rydBiCzHZlEOvj9YW0002EllekUlddNjUzNjZ+b5ZwSl1dVkWwtJSYP8zVpH3bEQivA+KCq3PMmPVnHm0dqW6Z585w+uzWLKY+X0Z/0Mhus6a5OXRwpd5fTe1APtuBK7dCzQbsW15ztwt2skkUFsrkJTAoUOmay9wzS6BXTszFiNsXDjJz+f1HRxiCQIzxqywEKit4YHPnOWiV3Mznwe/eYjbLJfxUSloVyB+P7Bvn0jL2HjmjMSb/lLiu9+T+OTHPPj4R23L1mdRbBzsdgaDd/fKrKuTTY0C//hpgS9/ReLXv1FKmkJxMdgdrNljWq9SSV0Zz6TzPHDYyKpXXyexZzeFNxOnk/Pz8LDEwCBTTWeLadl3k8DuawRsdgpMc3OYj6swi/Cav1ppNkeTBTFyxstjx9JjUUqKgc2bgclJ1mGaWCZdfy6YAlNNtcC+G7MLsEnJ+k2tmwTm5mAkKll6f6m/NQmHBaqq6Lb6yGPZswFes5MuWB2dFCTjGQra6TPWwtj4OBXWrVtEWq0jm42r6Q5Hukx84LmlLXI2u9Xfpjvbzh0iLXGJnLeAWXvu6gZOtTOpxmIuXKawLSUQjVHZDgToQpvJocPAk/uB4ZGF380b6IzDV1cxI2aq4vjcIYkjRyRqagCff/FnUEE+0JqRKMFU9Hq66fqXSuqelspEmkhQ6NfP8D4814EFZSjy8oDuniSiUZa0eXK/Fcc0MmplxMw159ZzhyR6+yWiESq9VAz5XW+vlewrW5IQKSVOti2MH8837m/TdTUeBxyO7P1pKnHxlDmgqopzTP9A+vFSyTy/AwepzBYVW8qzTTCbqJk0ZN7DMWV/DgddT3uzxOSaQ3VgkNa8upT4xvPdHI9mcpzFSFX2ZlPS6jc3CyQSCxcuEgkqlUePMRsjJC3DJ08t3HckIvHgQ0lMTlrXIJEETp6SmJoEbriBc8Z0EGhrSy4IMzHjLQeHeNzGBiYloVWdNfDadVrWPB4mz5mZSY9LXG7uVgraFcZDj/BmMB8cwaDE5/45iTe/TeKWm2mJuXnfyqujK9YfIQTe9AYbaqoFvvcDiZ/+PH3C2KIJ/P0nBT7zTxKPP6GUNIXiQhGQGBljJrXe3vR7aWDASn2/GCdOSfT20aqSukpuswm43XQB27mDr1Prik1O8t4dHGIygplpPsSDQQpRDzwo0deX3p5cM5RlQmuJ9d4UfnbuSM+kNzPLcz7wHOOi6pdZ9V4JU1MUaBezAg4OSXR00uqTmewglUwhNPX95LTEI49SgN++lW6BmQQC/I0p6GZaarq6afkB2Fank4JXV5clkJuZ3xrq06Vf1lVaXOIPBq1MnWa7aYVlspHTZ+T8NU7tJ20zcO0eKozt+qK75+8SXMEfMeJ2TpxM/15KJsTZvSt7kgNzjKa2r6423cWxpprui3PhpZX40tKFddJMQdXnt1zsMhEi/bpOT8u0UghDQ5i3Ms/NWdaJVCvLyVNGHKidizB2m5y/P10u5FRTLpXxCeDgQZYcMPdjXqOaaqC0ZOFvUs/B5Vo4djs6Jew2oLTEsADlCTQ2LrRWjoxIPPLYwvY++jjP0+zjXM5ocoqJNwrygdtvpdLa00crUGod5cxRbLcL1NdbFuC08zP+l5cBNTVYkDjn5Cm6rC6J4Q6o64wJM90DDz5H65vHk96izvOAK09ifJxtlZLKajaXdNNtemg43V28sgIoLjYTIkkcPwF0dlmLNrOzEsdPsIxIS7N17545y4Qt5zo4ngeNGnfJJEtynD7Le9Us5xGPyyW9AgCloF1RJJOsITIxyYH1q19LvOKVEsMjwHe+KfCnfyyQl6esZlcC+24Cdm7ndU6d+K7ZJfDxjwp8/O8kDhxUSppCcSE4HBSwxrIIv6Uli8c0mLPr9DTrCR14Lt0aFQrRclZYAHR2ShQWAtdda83J4xN0IRwYYNxCSSlXqAsK6D7TUJ9ikTOFihwtaFJKTE1bEv5NN1B4sb7n/0iULkUmsaiVGOThR6zaTsPDC5XFXDGPFZyhm6CZECGT8XEK1EVF6YLm7KxEV7f1CQW31ANYLwvygRuupzBZWLjQRVRKiSeeSr9OS9V6Kinh9RgeodAlJa+7zQacO0vhLfX4J06mJ7YYHk4vLl1cBOTl8b2pGE5NU4CMxfiXLd5wYpJC5LMH5YIMeQAVmHnLHCiIlpRahZBTLTdCCGibjQLAGW53oZCcj2Myf5JIAGfOprsQVlYKVFUKjI1RgU0kshfRbmtPd1dLPa+S4oVJOMwMkjMz6bFtQ8PAWEqdwpJSK4YutZ9SrWjbtwGNDYaLY1xiahrzFmm3m326UmpraGlqamQ/pqbRN12Ds1nkhBCorcGC+MGqSvbzhDFm5uYknnzSKMxsbGMmiDHnodRd7LmGyns0yjGZq3ufEJzrzpwFHA6BhnoqUIOGa6KU6UqylGzbmbOWlW10zEr+kkwyaUcyQbfXzGLRDfXANbuWbpN5LGEDTrVZ7+vqqIxn1ircuoXfNTcDVVXsFFeetcAwPGwVkpcS2LGDGbPnYzQTTL6WSNKF1zxeU6PAli3cn8fD+Sie4KKAmVyopJjPjB3b2X/5+TxHKfksaGkCGhrEvLU7Gs3uapyKUtCuEKamJCIR4APvtSGRYI2sr39L4gPvE/jkx2yorFCK2ZVEU6NAQ4PA/qeBD344fZK6/jqBD75P4K8/YggLCoViRTgcAhEjoURTU/p34QhXWAFLyB0clMzuZUyzJSUCW7cyC2FDgzX3ejyMperppWWquwdZi9Lv2S3Q3GS4MhqWnTvvEKirXZhuPFcXx9lZZmg0eeyJdEuGJfxxWxN/QGDnDralvNxy0YknLsy9cnTMqgNXW003wZKS7M+nbVtZzHZmdqGQm5pKfIEFLWM/ISMu6cmnWKPN+p3E6Chw2y1c5c7cQep+zXMNBim0NjdZLo6ssQYUFnEFPpm0lHWbLb0I9tHj6UWRe3okfvy/6cdtaRa47lpaWAsLrG1TFY9QiOOnvo6JEDI52WZZDqSkBWBkmEr5zTel14SLxyWeO0Q3spkgY9qGhpOIRJJ4cr/loml2R2mpwJmzjLE6foIWjcefkHjiSVoV3G4qYo8+vrBdtbVAS0v6Z+Z5nTkL9PSkf3fipBHXlnFRWzellwWYnbWUgLS6aLDu03AYaGtPYm6OxYzPd2G+sPTo2NLxVqGQzJo2P57gtejr5yK5OU66uii0AxkujuA8UFkuWUcuo6C7272wsPKWLZYiCQANDcDN+ywLUmoiEI+H5x+JGuUblhEBUrOQtjRz4YFZU4GtWoYbokjfn9vN+SxVUTbHYihM5W1oiOdvKkwmPm92199gMN3t01wAMZVAIQQqygXyA+n3lXkvP/0057Dz5xk/NjJi9f/R4+mF5Lu6JLq7rZjRRJLjeaAfuOlGK/lOWzsTr/D4VKI97vRMv34/lfXxCcYi+/2cK5NJifJy7ntkxLK4R6NLZzsFVKHqK4b/+jEnBqcT+N4PJP7wZcCf/rFIK/KnuPLYdxNjIQDgyFGJ3dfw9e23MYbmPe+X+NxnAG2zGgcKRa4kk6wtpG1emGp/dpaCr9slceAgcOstVDhmZmn1AijM+X2MzSgtkcjPF/P7tdsBt4eubz6vRCDAOLSCAiuW6HwXhZu5ELcfHweOHpVISqa8r6/PPYujKez4fFQYTepqMjfkv+uvS1dWpqYk2nW6UJuZKQEqDvELUNAOH2G9MI+HVhC7Y/EEIB2GldHvt1yJgIVlRxbEoKX0yXQQOHMGyHMxriQ1C+XYOHD4qMSuHVzxBtjfpjIwMSHn42vMc00kqKCPj0sjFo1Cm83GeLeyMiAckZgzintv2yrg92fMv8bbEyclBodoRTPrMAFAb5+EfprWuo5Oq45b6nltaqEr6hNPZu87M+bF7J/aWu4rFgMeexy46045nyADACoqgJ1ljMPq7aM1ZUGxdbN9/RJut+VGWFvD5BYVFWzPwODiNcD8Pgr0qWPM7NuiIsDjlkh1pqusoNKRyYmTEoePSDjzuE1wGhgdN8sypMflDQ7SWpZI0A3V7aagX1Yq8ewBHi8/QGsrkN3i9eT+lG6QVvmigQH2b1kp/5sK2tYtlnKTmcUxzwkE8gWaGuWCBZdTbfxdZaVAPJ5ELEarL62R3JHTSStkJCLhcomULKASTz4lUVnJBabCguUtaPPZHg3r2C37aJkbH2c7AgHg0cclImGZ5tKamqXRjMl1uyxXZFce+6C6WtDNcFKisND6fftp/u66lHjIZFLi6Wdp3Te6CgAV4EojsVJlJfDEU8CtN6cXqk4kaFEuL+P9Yo6ZgoKFiuDpM0mMj1MRnpziuDX3samFCtjp0xI2O8dJQb5VdFxKXqOGeonWTcDpM/y8t4+u0P39VKAHBqnwJ5P87TMH2K+pJS+WK9eiLGhXAFJK3HkHV0ef2i/xr/8i8LrX2JRydhUgBOMbJiYl/uWr6UH/v3WfwBtfL/BX75JZ66gpFIrsuFx0+RodtdyUAD6ca2roUuT1An6/xONPWokVTEEsEuGD+1xHeo2icJhKgcfNlVq3m1m/Egla1bq6re327qaANBemW2VZGRvgD1guOqn/+Zouz+c6GB+V+n04DDz1NJVHKbmqm+riaNLTy/MGaO0aHzfd7CSe3G9913meZQAuBLvdcjvq6kq32KUiwPMuLEi3bnR0ZrhMZU5vKe+LC5lww24XiMXSYwKPHJE41QYcP2kpMwJyPt5ncoqCGmAJskVF7Mu5MIxwAiu9/NFj9FoYH7Ou5fETckGxbXOcDAwCDieViceesJotBBNi5DnpspVNGT/XAZw+TUUqlsUSkRlfODhIwTUSYZ+mrt47HALVVUywMDxC9zq3G/BlpDE3swX6vRwHfj9d+woKJDxuCaeTfVZUaLrXsd5YJCLxyKO0tO1/euH1Nt10p6fTLZwAk/JkU9Cam3gtzGQRNTWWpTcaTb8v3G6e+/ZtAkWF5jZUjiJRYdRFWz6rnkmq5bi+jq5sZWVUGMzvZmeBhx+ReOjhZFrslukqCEg4ZsQS1wAAnp1JREFUjBTw5vjoPC/hcEjYBOMvZ2c5/zx3KP2cjp9Ivx9MZfToMVrOmpvkfKxktid/antSYyi7uhkb5nSyv9p11ne7+SYYiXa4v2SSiwnhMH9jusWOT1jtikaYcGRmVhpWJeuYw8MSxUXA7mvS22WzCdx+qzUvnTXitoqKOC8dOcZzvXYPLbSpNQ0dDl5/h4MKV2GhgAStbEXF6cd5+BEmUamsZHZGs1/jcZ77XJiLCObnDoeYj8UrKxWorwVOnWJ/m/dRVSVdbHdfI+B2CxQWMHuszS5w7AStkVVVYj7RjUR6gfFsKAXtMqetPYmX/4nEG99Mq8mXvyDQ2KAUs6uNokJee59P4Mf/YxVjffHvCLzmVQLveFf2wqAKhWIhQnDF3elML1gqJWseFRVRsDmX4qqWSFgZAouKBPbsBu65i5kKTXw+geIiy8XtfBcF89ra9ONrmymkJJIUAKIxxjZMTlkK0nybUl4Hg8ChIxTmYnGzzWb7KMg/e4DC0nOH02ttmQH4/f2W61AkTPepnTtY6Lk1JcFGSQnTeafS3c1EJuPjVqumppJ44EHWNDOJG0VbK8oFbt7HRaZsVovGRrozjU+kZ8PMy7OslZl9kPk+FuMCVTIpcehweoKM6SCv4333WOn3e3uBQSMDXkM9M2mmxlpNT3NFv6Za4J67RIrATSG2qZGuoDt38LOCAsxb50zSXN6S6aUYAGZJ3LJFwOWiQpUa12QSCFBB1DYvrEcGLHQ/TUoeJxBgG9PdJeniCFDo9vk49uJxieFhlh4AaDngsQVKSti2zvPA174J/PC/gAMH2R5meKQL39PPGmMvzn1v2gQ0Nma0zWhLV3d6GYeODtaW6uzkdUwlL49CcV0N79PhESsmMpiSLS8YpDWyskJgbEyiXU9ibo7HHByki6GUdHE0499MZeLpZ5KYmVlook7t29lZLrr09LC/zO/OnKV1+MgxIJalDEIizm16e4G+fn5/9hz/PB66AJqK5bV7eZxzHdxu9zW0dJuL8Ob4mJhg2558iu/t9uUtaGbfSwm0bjKuVYy/NbPQzszw2glBS9GDD/M3Ho9AUyPvibExWjRrjLppc2Hue3qalqqyMmH0Ha3nXq8Vz9reznkjEkliaNjKVhpPAPppiekgrYjXX8tFaZeLinGq+2U8LtHRIdE/QCWzrZ1x+NPBjDptALZsYTbcs+dYwsBckEkkqPj19gA33WS5OB4+IvHTn3GbWEzC66UibLdbc3k8Tit/by8Xyj0eMe/u2LrJGCO9lpVcJq34tcVQCtplzMSkxL9+nYPqC/cLvOqV6an1FVcXQggkkxL9/TLtAfJ7LxV4xR8JvO2vJHp6l5mtFQoFkkm6y/h8FHpScbvpmjcysjANv6k0TE1JTEwwdfnwMBdM4nE5L2SWlVHpqaulJaA7I+5G16m4me5NkxMUinp6gSEzaN/Ydj65R4TZ/rZvY/szLWx+v8AdtzPlvJTAFi3dDYyKhsC+m6ysg6WlFBKOn6DVze+34u+GRyTa9fT5RD9Dd55UwcNcLEpNZpJIUoDu6qbylJnhzeRUG7NZOp3p2QWlTLdMLuXiGJozU6ADt93C8zO57Ra6YZ1qk3joESqWxcVWVrrBIQr3Zsryhx5hP1RX87sHH6KFaHhEzqfZ93goxD5uuB7WVGNBHauebolHH2cjh0YsF0aTc+cknjvEmnmjoykKWmo69UrgztupjC+oR4b0RDZUhmm5DYWAX/4aOJbSJqeTitWNN/D6ul1c6Y9EOVa3baXrmKn0d3RS0DSP0djAbW68nopK/wD3WVPNrIBeL8sp7NjOhYfMODPzejU2mjW82LbSMrbb4VhYYFw/TUtS+2kqL0KkJzgx9+n3023t6DFag5uabPB6aeWoquI9EI/TPa/GyF7aP8AkK4eOpMcLZu4b4KJJMsFxL4SlvN1wPRWD7duYiTEel9j/jCWge7wC27YyxjW1xtbIiCHsBwRCIVqKwxH2gekKPDtL65Z536SO/45Ozks2kVuSELO9UnLBxsyWGI0CoyNUrg4eoqU71fRGd05aHutr2Sa7nQluACDgp0WrokIgz2nMg5MSDz3CazI4aCUg6THciOfmeF1TkxTZbLz2bg/dyONxiUce4z5Sk97FjQWAhnrLqllYwHE4nWJtl5LzVjQqUV1FV8wnnrL6Ysd2loE4+JycVxTr6vhn9v3ZDo6p7dvpbj41JXHwEC3xsyG2+fx5yeRHkvfd8LCEz5s+L5dkWPYyUQraZcpzh5L4g5czfuE73xQqxkgBgC4Cb3mTDaWlAt/4FrN6AsDL/1Dg914i8LZ3SNYHUSgUi+JyUXkaHUsvsBqO0CLi9dJaskWzvrPZKMSaDAxaWeEOHqLQETUyJDqdVHoSCUsoTA2M93op2DodbENpGV1kdmwHqqoz5nrjZ4ODQFsbXW+kxAKz0uysxEMPyzT3stQVaAnDCniEgfPxOOPgBoa4Miwl48dMC95zzy0sOHzfPQLX7hVpFp1IlP1kKq+JhESek4qMGce0WJ2wQICxfjJpWXEAbh8xEn9MTcmFCkrK28JCgdtupYvj0LDE4KD15eNPcsW8rx9orKfQNx20lD9TEDfjTxIJtqmnhwJwUREF9MFBw0Wsi1YmlwvzRXhPtdFqOTCQnG+nx2ul7a+rtY4TDlOZLyqiFc7joVUjmzvr4SNM633+fPasopmfDQ+z5prp+na+2yoC7XQKeL3AM89SAJ2eNizBhQLRKC0oqcJkeTnHgc/HxBIAFe7JSVp7KyoorAcCVFZHRpL46tclDjzHOnuZSU3M87fbqEyfPGUkKhnksYVgm1PZthXYvVugoY7jqKSENfNMUt1C7XYqtK2twlCimCY9GuW97nTy3h5KcRuMRo2EG1liPFOvQ00NY6xcbha4jydoARoe4bg6ecqyCAX8EhKYb8PUFHDuHPDkUzJtf3NhJrBwOHis4yd4H5kKcud5zjemYk8LoEQ8wX6prOQ5G56UXLxJLKy5BljnJ8G55sRJzB+3x4iruu8eWnRTZ55IRCIe52+Ghmlpn5mxrPLhMN19z51jmQxnHu9ZgMcQwirubeJyMfGOzycwMyMxNiZx7Djvp/Fxzm0Oh8C9dwNPPS3R02NdHLebiZkmp3gfu90cM3nOhdlqZ2c5LjweWtNMS1kyaSWbSS1/EghYc2V+vsCmZrqwP/UU+8rnA3ZfI7F5E+P9PR4q/9pmfv/sAWD3bqC42MoYKbEwvjkTpaBdZkgp8e1/k3j/XwM33Qi8/z1iQS0IhQJgCtvGBo6ZZFLilX8i8ILnA299e7qQolAo0kkmuTJcWJAexD47SyG9qJBJePpSCrSGw7RMSClRUMBC06brXHkZ3WJ8PiYoOHuWil53N5WExvr049fVUdiJx6kczM5QwenqAuZMa1OG0F5ZyeB0s65YpoXNZqN1hMkGmPgjzbVOUtEwM9IdO85jVldxvzabwM7tVoa5oiIruJ7HkXjs8XQXx44O1tcyjzU8LOfTZUsJTE4JbNGQljwgErHS0peWAv2DVERcLrqrRaN0kaqpYf8Mj6RnJJyYkGlFrUNzEs89RwG1s9NMYCHnCxQ7HDAySTJuZ3KSigIAVFXSrTPV0jgwSOGvqEiiqZGC/66dFIabmmgxSS1mXlPN13aHNV4cDoH6OiMWKmLFv0Ui7P/iYoG6Wo6Vru4UN1VDuHvo4STq6vhhayvgzFI+J9OC5nBy/Hq9FEyTSSt+Znxc4vARCrPRKN0HbTZgLiwxasTThUIUuM93SXjcAjU1ptsdXXXPnqMFtbmJ4zU4w+ve0SERi9OKkB+gi2Nq0WLAigvUT7MNZttjcV5Lc1+phbofe5zPMYfR5uMnJM6ctb43BeGZGbatvFygu0eiry+JSIQC+MQkldHUuMTUPrOJdGtO6ncm4xPso+5utk/ATMTCYsU+H90Z43FrQcO0tPX1cyylJkyZnZXz95bTyXF/683MwtlvjJ+dRnr4okKB8jLe60eP8rvJSd5rNhsAI2bssSeoUGSzpplW2YkJib4+jt39T3Ms3rKPFszublq/zNssFpPo7UvC5WLioNAcx7/PZ2W9nTNcIoeMzKFFKff4Fo33b2YMVnCGCzHRKK9JJMJ7JxLmAsEtNwOjo0mcOMn5ua2dLoVS8jcnT1K5OtVGxbinh/Ny6mnbbMKoQSnQ3g48e8DybJialug8T6+J3ddYituJk4w3A6ysm16PEafXzrF2+DCTA53vYlF7YaNnxNQUUF0tceQoLeOpiy2Ziw6ZqCyOlxHhsMQn/56D8DN/D+zcqfRrxeJcu5eTy3/+SGJkVOJNbxB47avpavGWt0nc/1mu1ikUVwqapn0DwIsADOu6viPL9wLA/QBeACAE4FW6rh/K3I41fBi309UB7N1jKAwldNfp6KRL20yKNcrttuowjYxw1XhsnFkXz5wFysrkfByHGTxeWiJRU83YhFQl4/ARrkQnk4ZiMiNx+gmB4AwwmVEk2xQ+Oju5wn7NLq6wj49LPPAgcP21FHYSSSYk+b+fsd17d6cnX5CSAofWarj4SQpI00G2f9tWiWhUzMeC2R3MnGcSDEoMDgI37xM42UaFbWRUoLpaoOOcRFMTUFnO2k9zcxR8R8dYz6mp0drP7Kzl8nniJBXE6mp+Nmqk804kqOxs3izmLUym4HMw42rGouxLfwBoahJ4/EmJ0TEBvw+47Vbgqf3AT3+WxOmzvDYeT2oCE1oRzWx2AAXfkhLgRz8G+gclnncf21ZRgfnSDIODtAT5fEaszRitoUeNjG9nzkkMDVHQHhq24usKCgQKCqhsjI1LI7sjUGGUyTETDBw5RgH3rjuAH/034HBKZJYRjmUoaPkBCuMzMxTga2t5rQAK5Xt201VrLsxkFw6HBCRj7WqqKZQ77BQqT5zimDJjFVuaqXTl50v8/BcUpmdmBbZtlbjrTqYjb2yUaN0kkUwKnGqT2LZV4DcPStTVSXT3sB1bNFpAunuo9J4+wwyRPp+ZKdM6x65uXlchmEESsDKMApaCVlAgsH0b8MRTEqXFrIOWSHI/dbUUmDs6qZSmFmgHLFdckxMnJWprgGQyxbUuyiQ+hQXcj83OMVBayjmkqhJwuQUSCYmubiszps8rsHMH+7WjE3C5OICDQV5nl8u6T3r70q2VIyMSPb2854qLqYWZuuvAABd/JiZorTNjYOfmFiposRhjD01ruc/HhB4VFQKzs5yHTLfR2Vmr8HYsBgwNJVFbK9Hby2zSwnDxPXuOfZkfENjcyvirSJRznKmQJJNs5/ZtfJ+XRyU7HgcGBtjHbjfj1+rreD9NB7kQEIsx1rGpiTFqbToV3GQSyC9gf5tW04py4PhxYGrSOud4XKKtnZbpzZuByko5X+dRCF6TRJxlI6qqeC9om7lf/p7W560aUF4msG2bxMAA5/pIhOfi8dCyLZPATIgLchMT9LqYd4+VgM229EK5kvAvE4aHJd70Vrqn3HIzMDWtBGtFbjzvt4CXvljALPb5hj8XeMHzBd78NivTm0JxhfAtAM9b4vvnA2g1/l4P4MvZNnK5KChPTjIz2W8eojAzOcWV0YpyCis7tlvzcDJJYVEIuovF40w57fVR4GRNHAoYsyFDCB/jb8bHKXTF4xIzM0wlfcvNdAsaGOTxrr+WAn1ZaXpigHadVoBAPoW7A89RgfH5gG1bKFB3dwPDQ1RGYnG2ZWSUsUHHT0g8/kQSwSBjdMzkIYkkV/xnZ6gkCYH5ukYAY+FSCwfrpwUKi5hgRUoqAqfPSPT0JuFyU1Hy+wXsdgpefj/PKxAAznfL+TgvIbj6DlDhvXYv44PM7wG2X9hoDTx+Ij0BSSY+n8DePXRxPH6cisW+G4G9e4DHn6AFqPM8BUGvlyvjZjY/j5fJGlJT8/u8AgefkwiFmd49GuP5CME+Pd9luE5tppJ65izH0HBKvGJVhfHbqERzk2VB6u7m+VRW0nI6F+a+Mi1oO3cIdHQCDz9KwdBU3EzGxqx6Syajo3TjczotgdaswScEBeSjx3jdRsYkQnOMg5qdpVu810eraVUlrWSjo1QiNrea2UmZQIeJKQRiMYnpaVooHn6EQvGBg+wfsz9LS+V8fSuA/ajrvLeiUb4fGmIcGLMYWte5qkpg82aBrVvYl9u3UZkzsepNMU5wzzUUyEMhWltmZhgj5PMxFqy6ihZqKU13QFpuUl3dNrdyvKaOtrIyprSXoGXUtEKOjfHanD1Hi63Hw1gtSPZ3JMJ48Xad99m0sdhRWSlw6hSTo+Tl0aJ4/rzhemq4D45PUJk0FddUxWvHDt5jfQPpRc4za8MBjBdLSiNmqouLPEeO0NoZi1E58/u4ENDSLObXANxuoLnZjmSS47+vn9bGiQlLaTeTszx7ID1Gb3aW52azIc0lFQC8HgEIWq5cLh7/zFmOs1iMiqoQvO6Dg+yTmmqel9vNhQT9NN/HYkY8nKDCmorbbcW2FRZY6fpZS41lU2w2K5lPMmlZdf1+gS2bea+caud8UlnJxYVt23h/uN0CHrdASwtjOTvP093R47EUaSnTPTCyoRS0y4C2dok/f6PErp3Ahz4I/NXbbbj1FqWgKXIjEBCorBR4+hngwx/lSv1rXiXwst8TeMvb5XxmKIXickfX9ccAjC+xyYsBfEfXdanr+tMACjVNq8rcKB6XCM4w1ubmm+jq43BQ0MjLo1D3m4cWxkV1nqebk8/HeJi77hQoKqTgWJAv4PUK5OVR0KitpvvPkWPA1q0U7mOGsOPKkxgYpCJXV8sg9uMnLWUkM6NdMMgaTg0N/C8l21tdTaGxqpKCTEMDLTkOBy08/QNUEqemmWzBjLOYm6PSeO0eWoYCAVov9u7hKjVAobgyxcXRzNr35FO0rDmdRnKKChvGJyhMjYxQCXQbxXRdLro+DQ2JeTelvDwqAICRwTJCJdWM1QPYzppqClClJek10mwZj8ZgUOKRxwzl13BXC4V4fCFoNdyzm7FJNmEkJDAsMaUlApWV6an5j5+gZcmVR+E8P58KIMCV/507BLwezAuzzU20ELrd3H9Lk5X0obuH7num8Gem8h4YpGIQNzL9dXXzmodCVDBOnmIK7+uvpTU2LyXmLxhkcovUbpCSfRaL8bqYbrD5AbqHDQ1TsC0tNeLs/FSKz56jdWdsjGNsZJRWokiEFozJSVq5BgaBsVG6c5WX0xI3Pc1xbpZDqDRc9kpL5fx57tguaAEy6B/geHM46BrpdnNBwe6gkpKa/IoLChITk7w+J0/R4koXXktBm5ujG6zDwRpv4TD34zaUkIEBWjNdLi4a9PbSdU7C6jMTU+FJVYiHR5jx9fx5utM6nVRaQnO8d8vLeB2npuhmSqsV3QWDQfZLdYplZXxcYmKK19VuB2IJ4O67BISNGTEjEQlts0BFOb/PTATS2ysRjXHcjYxY301OWYXLrYHBfzabQNw4t5ISypzT08C9d7Pfjh0H+vvl/JgKh+kO6HIJaK1AyEjSUlQEbDKsfDFDKbPb+bnPZ6WzN8/5+Al+IJM8j3adSmswyOMXF9FqGI5w+9tu5dw8MSFRVyeMRCGMoZybs9ynz5ylYmyefyxmZWJ1ODg35+UJdHXToyC1PJFZL6+62nJxPHOW90ckIhGc4X24ZQv33dvLua3zPK2C7adpLTx+UqKtjdtu20prZHu7NXaSkvPgUigFbYOz/xmJd7xT4rWvEdjULPD5L653ixSXKzfdCHz0wxSEOjol/vjlAn/2pwJvffvCbGwKxRVKDYDUHHK9xmdpCCHgdHAF/blDFPCSScYGhWaZxGBuLn1l1uMR8ynGe3oZD/PAgxJnzlAYG5/gqn0iwaLP5ur3tXtoJTBrR/l8PObICJWAaJQr5gcO8jiDg/w+VSiLxSk4B4MUzMwslL9+gBkGnXkUqgN+ugVNTVHpNBM/uFxUMqQEdm5ntjink9a0kVEKJ9EolUa3EYMmQcHcFIg7z/Pz7dsp3JiJGdwuK0jf46EA7/OyPWfOAP/1Y8uaoZ+m8GdmdzvVBvT2UzjLFJQ7OymYVVamx4iZdHZS+RCC/SgE0NhAoe7ocQr0t95Ci9nJU3Q/i0QpXJsK2emzkrXsUsoRhOaoVA0NU8Ds7ZU4dpwxMSdOAj09Ej09TNgiBGuvdfdwfNhsFCgHh6i8VFUCM0G6GEop4fNZqc5PtdG65/dxLLS1J3GugwWTZRIIz7Ffu7qQdf42ywPE43I+3qWggNd+fILvIxGWT6iuErjheirE+flWfExhAa1dO3ewGHJVJcdQVxeVs/x8XstNLYCm0RLVP8BrWFLCWJ+77uTChFkUeHSUfS8l74/ePqvtzU08p87zwMAQleaGen6+fXt6lupwmK66pvJoxkbqp6kIm5aKggKWHjp8hMpGZaUNHg/3VVPDxYexcfaxz0eFfcd23gt2e7qraEcntwuFgO4eQ+C3cwGmdRPHUl4ex2dNNRc5PB4rEUlfHy2/WzQqLJomjHqKloKWTFqp7kMhKndHj0l43FT0R8dYyP7pZ9mXNpFu0QtHeM/NzjDmNNWSmpoFFLDmEP00E4zU1rAfN7Ww/Q/8RmJyylhESFjJTeJxYHgoiUiEFuKWTTwvm43zVDIpkR9g8ffdu9jmdj0JaZzbxCTvAdNlUkr2Y2kZXw8OYd4LwXQj7x9gnF0iSUuimeSl8zxfCzvbvGM7x+u2rcCObdzP7Kx1D8/NcaFrdpaKbn6+tSAjhEBLs0AgwHvbXAjbuYOL3E/t58LHwCD/bDaBLRrdQSMRKvb5Ad4n09NUTF0uzimxGC2489dKMq5wKVQM2gbmF7+U+NznJT78QYGbbuTgv/suZTlTXBhCcDLq7pH42Cck/vVfgN9/KVf03/EuiU//HeYLfSoUVyjZBvgC6dbttsHn92IuLGCzJdHbC4TDSRw7Dvz+S/OwebNAX1/UcJXhLiMRifAcBZP6WqaArq62oapK4DcPRVBYmAefP4l4PImpaTu6uuPw+wUiUSdmQwkACQT8NsRjErff5kRpqQ0/+b8Y+vriaN1kR0sT5gVUm03A77fD46b06HLZsblV4Oy5BPTTFPjm5pJwOoG6Wid+9vMI/H6B02dtcOclUVIs0NNrx57ddrjdcUSmkzhxUiASSWB80g6vz4byMoHp6QSCDontWylozszY0D8gMDoqMTAYR3GRwLMHbHj+8/IwOzuHpgaBWMwOl0siHk8imRA41wG4XXkIBJw4cjQJIZIYH0+itdWOqkoqPHlOCl4et0Q05kRenoTHncQ1OyVuusmB8+eT6OiMo6Kc/maRcBKFhRLJpA1nziQwVWHDFs0Oj1vyCkvA7U7AlWdDcbEdzc1U1Nra44hGJF76u17E4xI/+nEUo6MJNDTY4XYB5zqSKCkR8HhscMSAlmY7+npjyM8X8zWnPG6gpyeBpgZmmyspsSEQSGBiUiDPmUAoBHT12NDYYGMmwqEEnA6g87wTbrdEYaEDmzfFMTiUxOSkxI7tDhx8Lo5AAJgLAfkFzBJXXW3DzIyEP2DD5EQSUtrgcdsRi0lcf53A5DRgtztRUhJBcEbC4XDD4xEQQsLjjsHpFOjvi8MfEPB4HAjOxBCNSFS32GE3UssfP5HAXXd5DPc0ib7+OGLRpJFCX6KuLg/6mRjOn5e48YY8PLk/is2tNmzd4kB3TxSFBTZUVkjMBIHxcRtGEhIlRRJlZTYEZySmJiW+9R2J6iqBgYEk8vIEiott2L6N7mybNtngcglMTlJzmJ6W6OxMoLHRblh0JAYGqGHU19lQUCDgctkQCDhRX0f/2uJigZGRJObCTMbhdgM+n20+CczMrEQ4Yse999ghhMC/fi2C0TEHGuptmJiUaGywoaxUoKHehp//MoaCAoGRESDP6cTkZAR1tQ4EAnnwuKO4/lp6oPQP0GLjcVMpi0YFHE4BrzeJwkIbHA5gaioGAZ735lYnSkuSqK0VmJm1QSKJpLShry+G2Vkq0PV1TnjcEnW1wMhoEmPjTpQUx+HxAA6nDTMzcbhdAh6PE3l5VAhPnYrD53dgNpSc17Z2bge6u9kfNTU2jIwCMzNJFBcJuFwOeNwJeH12BAJ2zM4m4XHHUVKURGERy2t0dCYAODE7J3HmbAwvfEEetm2149jxBEZGkjh7lnPOjh0OJBM25OUlMTZqQ0OdA2NjUTQ22GnFPSQxOJRELGbDnmscGBxMoLLCAa8nDplMwO+zYfNmtzF/ReFyC1RV2LGpJY65OS4e+bx0ry0uFhgfTyAcscMeA7ZsFhgcSsKVB1x3rRMej0A8lkRJcQLtegL19TYIAL39AqFQEsVFdpzr4L3rdEjU10kU5NN9Nz8gDHdOicICgb4+iVhcQmu1we/jXDs2noTTIeDJp8W8uAQ4fDgOj9uOickkGuoFmhqZeGR2lvdPoI5uvk6nDbMzCVy7lxlR3W7OI16fHYlklvSrKSgFbQMipcR3vwf8xw8lPvNpAVce8Ka/lPjyF7gSpVBcDPV1Al/7ChX+xx6XeNELAFeewLvfK/GxjwLXX6fGmOKKpRdAXcr7WgALkh3PzSXR2xOC18NkBfn5NvzHfyYRjQLRaBTj40yUAFiLGuGwRFcPY87sdlorWpopyNXXAw57HAJAUkqMjdIq0NsPnDgZxaYWZvkqnGbsyMhoBN09Al3drLnV2RWDz0trVmMDUFbKhCFmrNa5DmBwUOLmfbRcTU0BsyGJWAyYng6jvo7Wg/o6rrpHokB3j0B3D1euIxEJv4/uTdVVAsEgY5Gu2QU8c4Cxqza7wPZtLMA6MAAEfCzzMhcWCAYjaN2UxMFDdBGqr+fxenuBu+9y4he/imJ6OorGBoF2nb+bmYlZLneS1pJYXGL/0xFcf51Abx9Xu7u7Ge9RUMBjxWLM3FdYSOtAUxP3MTbG/jh7FtA0I7Zvgivbp9qYBMPjoQvo089Mo7oK8AckSkqAqso49NNMqjAdNBK0GK5s8QTQ3QvUGgmV+vpZD25sgjGCsRivSU8vz9tup5XgfBethS0tfN/ZGYMzD9h3kw2jY0mEQrTU9fVHkZ9PS0FpCeaTVoyN8xq43WYRXBcKiyI4e47n/Vv3AkJE4Pez8PLUVAzxuEAwyEQfiQRQUChhtwOhUBQFBdLI0sl+N11gH3wwjpYWHqumSqL9NN3igzMS+5+JGgo2cOZsFLMhWr/y841U+2Ps9/x8w1Lkpjviswfp2jc8YsSkgQkSolEqNNPTzJTpN1wI58Ls29Ex3is2EYOwsY3RGK/94DBdMGMxgR//zxzGxji+z3XQ8mUmlmmoZxtiMe5zdlZifAwYHzfcWO15iMZiyHNx/23ttJIVFPKc+vrZzqnpCAoLgfGJGILBCObCEkNDEkXF3HfcsEYND0uUl4v59hQWUvCPxWlJyXMB4XAMneetRDNjY4xnA3hMl4vXZS4sMDDAWnw11TEcPpJEXx9w790C7e1M3a+3R7Bvnw2PPpZEaA6Ym2O9tLkwLVvnuzj2d++ilbbIuE+6ezgmEklhpMMX+MWvkvPXLRSi9bG8HDh+Mop4HGhuBs6cjePUKYlIhFldy8u5v54egcrKGFo30cWzrZ3HLShgG1wuuqv6/UAsHkE4AgRnBObCvOeEAB74TRQ33SgQCjG299HHJfr7+bvJSe5ji8YYxKoqwJXHfqQlVCAclujvjyI0S4vXuQ726fnzVu0/t5v39PCIVSy7oID3df+gBAZ4fzGODYjGOTZtdlojhRA41yFRWMhsqTOzTPZUVsZxOzxM63s0SuuZmbCovJz9cM1OxtoNDUuc7wI2t7IN585Joz5bSq2TDJSL4wYjkZD4p/slfvJ/El/6vMCO7QItLcB73yXSMhgpFBeD3S4wNwf89GecXH/7twQ+8D6Bv/6IxK8fUO6OiiuWnwB4paZpQtO0mwBM6bo+kLmR00kl5lQb4z6e2s/Yqb17rHiD4mIrsxfAldGdO+g6de4c3d1+8xBw8CAFo7Z2ZuYLhSjIRwxXpGv3sCBseZlR26gAOHmSbSgqYuC9qZyZgesi48lNAZ2xPz4f5pN0nD1HV7xkkgJ/LEaBt11nFrI7buPvPR7WORoeAYLTjBGyGTEv/X1UGObmJP7n/yhwX7uXQt3Zs1Yb2nX+b2gAKisEEgmu8sOIE0sYGQSrq+l2ZAqNdJdjPbPzXRSWRkbonnj2HBW+bVusdOftOt3MurpoUawoZ1+eOMm2eX2Wi2d3D69XbS3jf0pKBCJR4Oln6Ja4ZTOVuucOMQ7L6aTr4LETVNJOn6HilRr7VFnB/U9P8/ujx1inKh4zUs2f5rHNjJP9A9xu1y6rTl5LM/uiqopuZ/n5VFbcbrpo2ew832TSKk4cCrMuVm0Nt5+bo3tpezuFT/00rV4PP0rXLJuN/TQ5yfGQjPN3U1Pct8tFd7yGBo7jLZpRc68E87GAjY10d2ttFfB4+Lq0lArG0LBRH60EaKgXqK9nhs6hIQrGFRXCcDXjwnIoxLF7+gz7SQjg0cfYvyamK+usse3cHN36KiuoBLvdVhyTzWbFX83NWf3U1Z0eh5ifL1BeIVBZwb6rrrLNL6oUFXHRIhplEp2IEetkJmEZn7DcZ0dHqSCFDHc/E7+fSuH2bXSnNF1Hy0rZlnicLo4lJbwWO7ZzHgn4BWpqWBfLTIjCe5HjbWgoiWCQMaP7n6E7X3U156Wf/jyJ02esGnHJJK9ru04FuKiQfRzwW66ejQ1WCvyDz0l0dCYxOso2ne9iW/0+o1jzNvZ7WzsXnnr7eZ5mPBePxwLzbTrPsaeXCs3AAAyLIPuzrJT9ODRsuViOjVnz1TMHkkhKZgjd1GLGu/LaBIOcg+MJtm/KyOrosFPxjkR4fz3+pMTICBe9tm0Ftm4V2LIF2LOH5zQ2yoL03V0S58/TxfH4CRaObmjg/FBRgXl3X7ud5z4ywljHnTvEfGkIl5vXy0xaVFfL98KIXy0sZLbYSITf+Xy0TufliXnlDKDyvCAmMANlQdtARCJ0PevtA778RVrOPvChJN7/HoHmZqWcKVYXr1fg05/iuPqvH0vceQfwD58SeN8HWdfl5X+YXl9IodjoaJr2fQB3AijVNK0XwEcAOAFA1/V/AfBzMMX+WTDN/quz7SfPqCs1G6LCNGvEghw6DLzkxYBWYRUkNgmFKOQ31FMAd7lYo2r/01yVN2sfmbWtunv4+nwXBY+xMSoQsbjELTfTitHWxgWUza1cMTaxGW58AIzkGlzRZa0xWhAKCwUKCyl8/+JXEoX5VLQSCbbxwYclKiroXjg+ztiRaISWnDyXlYLfmUfhxm6nIHLsOFerpw1LmYnDwRiQnh6gqpIxevE40NnJulNS0r16aoptbGzkynI0SmUikWC/5eVR+fIHmPJ6y2ZmgzTTnW81lLVEki5x3YZguWunQDjC4/b0UhkqLaV3QDQm0dtDJaeiHCgtFQjNSTzxFAXU7Vsp+JpWjrIy/m9soNKSl8dju10SLc3AT7ooDMbjVKArytke87IEg1Ys2dQUFewDB63kJzt32DAwkMSpNiq7B56jYtSu082xpJiZ4cJhrsrH4kBtjR0TkxQaN22i1SEeZ828qWng6HE5XxzXLGQcMlLhR6Kc02NxtstuZxv7+nn80Bz7YWyMv9u2lUqnx0PhevycRFUFFXmPhwpT53leE5+X5QhCIQrkJYYV8OxZCZeb+y0tYT/6vFQ+t2hcJLzhBonRES5M2+0Cg0NsQ3UVfwdYsY2VFUBxkYSZqqKoiP/raplEZWSE18vrTX9uTU5KjAwDmzdT0zp7LoHxCSZ0mZqiIrJzh0BLi8TR40xMMTLK82VyCWBsLImhIY49n1ekZS/1eqiUJg230DwnrSX9/XSpo8LKhCe1NayXZXfwXE6f5jHMEg20DNMK+sCDXAQy08WfOMHFhH03cAGgro7jKx6XiMfF/P2eTBr3hJ/38egor0cwSCUJ4HiZnLTqlNlttJaFQoz/qijn2Pb7eU+7XKwjNzgk5/dx3V47ZkMxOB0cI+VlvIecTirn7TrHXCLBfquuErxHBBeJioupeB06xGMD7LOiIl4/KSVqahi3ZyYvktIsEcE+BoDt2yQefZR9k0xyXi4toUvz6CjPO8/FfrQ7gKkJzqdmLFw8ztfhMBAISISNxa6tW3hvM3GThNvF+dmdx/IBR4+zTS6XkZo/Qc+AYJDPguJiek+Ew1SkvT7GqRYUcGzu3S3w7MGlF8OVgrZBCAYl3v/XdEf44j/Ttz2ZlLjnLpFWBV2hWG2kZDasZEJg106BL/4z8M73SIyOAm95E5TlVnHZoOv6y5f5XgJ483L7ee65OPoH+CBvaqKCEIsDpT4qLOPjFHDCEUDbzLgUu50P4kSCAo/Xy5VsMxX53t3AyTY+wJ12FkI91yExNk4l6vRZYMbIEPbf/wvs2pnE+S4qU52dgM1OgTjPSeHMVG5mZylU5ecDO3dQeWNaf+5rZoYr4sIG5PspCM7OUuk81UYXHDMFuNNJQcwMqL/tFuCRRymAlZTQXW/bVqbPrqxMrztVX0fLk9NBy2BRkUBPj8S2rXb86gEKVw0NdOusNVbX43Fa/Gw2WsPGxoyabQnA56cyd76L52PWCgsGKbA11FPoZ8wOlYSCQiqRyST7ob0dcLutlPOVlTz33l6JujpaEc3V+iPHqMyEw/zr7aPlbnKSx9y8GRifBEafpaLR0UnFo6yMCtXgEFfi8/N5/L4+oKFBYMd2KtAjI1Zh8N5eJl8oLKIA31DPc2huotXjxEkqsRJ0yYxEgGAwgaIiCqLHT0jcegstRx4P5i0Jzz4LFBVT+bHZqLAMDtG619gEKqnGYoPDYQmhExNG2YMKKmutrTacPJXEgQNWm0+fAYSNiWKEoAtX/4AlnOcHAHcZLXnjE7SGTEzQojA5xbZIyWs7Owt4PBzP3C/PQwgK6yyiTQF3aJjK2bwV05Bp+/uZcGdwkON2eISfV1XymWbGazocVup3gDFrySTHp8vFLJUzsxKlJWzz2XNclCkoZN/397PPWlvpOtdQL9MKg/cPAEWFVAiYHIVKm9/P1wUFPLcTJ7m/0lIqnQUFHDsOBxdjPG5e245OKo+BAN15BwaB++6l9aynFzhzzlC6I3QhNlO3m0l8pqc5Prdv430T8LN/poPcvqCA16u6im0JRDge5gwlvXUTE2A4HRzf3T0c68PDrGnW0sxjnDmb5D20hVkOp6aZjMfnA44dl6isMFwcvfxseERCSoF4nIrqzAzvCW0LZYyBQVrMfV6gooLKndfD8+g8z/FTXsZ7OhqVKK8QmJlhBs4bbxQ4cpQWeKeT83I8ZiUkSiS5QOIzymjccB3wzAHGLI6NsW9amqxxHY7wmnu9hvv0OOddgNb9RJJjxMTMRunKMxbtBFCQT4urxwO0tAj09UtMTFiJpc51ZC+QnopycdwAjIxIvPmt9Mv9h08x29E/fyGJyUngnruFsmIo1hQhBF7/OhvKywW+9R1OIl/5osBzh4C/+Zicz9KmUFwtNLfYUFlBwfzYMVo2bDbDHSpiCJyNzOBlzs9cSRVwOgUGBuki88RTdPlJJCjUtOsUgsrKgd4+uqzt3c3jVBixKIUFFGzLyliMuM+IybDbueoci1sZDU1FwmkUjR4eZubBpKQANzQEPPYEV8l7eqhAxWJUbDweIzufTcDj4UJgTy+F1bIyCsmPP0lr3+AQBbhTJ4GDz1lCxtmzjH0bGJA41W7scyctVNPTfKaNjSfR1EghsF2nYJiIsz/HJygAmnXg+gcoEJmp5wcHKYxu304hCTBcgyYpOAvB7+Nxroa73RSCi4vY3x4vheRNLYynCwQonEuwH851sl+OHKXA6PdjXtDODzCWanTMih0qKQLuuJ2/9XpoMevuppLhsLP/Tp6ikB+O0Jpxqo3f79gO1NVxrERjXKX3ethmh4PKPECXMI/HSPPupVDqclFh8XopQNdU0xXz2YPc/9AwrV5NTezLM2ckxicYc2bWaAtO0z1rcorX1qyvVlrCWmzFRRLPHqDL7eQk4+z2XMP97tjO/nO7qQBFDFe2SITvKyoEAgGB/ADHSbMRF1hdTdcwZjalYjYza7m7HT7Mc87L4/guK+O9EI9zgWF0zHRtpOI7OGRlHszP5zi0GS5+dbX8fGY2PcOp38/EDsmkxNiYRHGRDdXVmLfcbm61rMOjhpJcVycgE1Q6nE5eP/00FahMobq4GBgd5zHp4siEEUVFVMqmp2mRb27muC4qYpy3z8ekHMEgXeBGxyTm5uR8HNPoKN2qPS66SU9M8FqUl3HMTU5xXmhsYDvMQs+Fhfw7dIQLRfEElZC6WsuCa7cDDz1sWns4xgcHaWGanOSctHULF0dsNh6zrtaYU4atOKvpaeDEKbNcBvtrfMJYQGngvW3WCZyc5DVvNOJTo1Gmqo+EuVBTWclrUVHB8VBXy3nz+Am28XwX57PaOqC4hEaNcJhz3lP7WTB7i8Y5uqlRoLVVYIvGMT88wkWtuGEp2/8MlcpEgvX0mpv5WyGYrTGZ5LzX18++a90k0uLX/H4r0ywE71O/n8pwYSFdfoWwsmIODHDBoLHRkuUjUc45S6EsaOtMV5fEX71H4vZbgb98Mx+WyaRERQUnY4XiUrK5lQ/c0lLgC/cLfOBDEm9/p8QnPsZ6RQrF1YDPK+atKUWFFL7tDq66RiIS+flc/TVTl999p8DXvykxa9S82X0NXdB2X0NBfGiIn1dVAZBMbDA+zt+3GUpbXx8Flulp/i8qFEjEJWSSD3nTAlFTLVBYwNeBAIUAs85VXz8Vlx3bGXuTn8/ix1PTVIz6B/ib5iYqJkNDrINms/NcZZIFpWllo/BfUox5F/uiIq4Kj4xQwNi6hULGiZPSKPhK98SGejkfF3P6TMKoVcTzriinIFxfzzY5jZXpRILCjd3OvujpAbZsEWhs4P7Hxug6tHMHV87r6pmmf3YGqKoW8PuAaIwJTeIJCmSmwhWcAc52ADabRE01FdNYTM7Hze2+hgre8DCvdXMTlYk8J1fwk0nG4vT0UAGEwHxx4yf387qOGS58syH+rrHRqrVWWkL32J07JACB5iaB8y0Sx4/TxfDZgxT0BwZ4LLth3ZozXBSdDmBTix3DIxQst26x4qC0zRxfdO2ideBnvzQKbkcMC5tRqiEaNd0LDQtwGDhyjMlfRsd4LYaGBUoM97NojMpJPM5x43BQkfd6gMkCifAw9zMyyvpfNkHBfGSEljiZlAhHrPsqHqc1gy7AAnv3SPT1AV09LHB+vot9Zrofej0UzAGOb7eLfQxQ8QLYf/ppWsIaG8xrbj2rhoclBoeAcFigTQc6OhKYDVHJnZujG+K2rQIN9RJP7mf7zndJlJfRdbamhmOhuMhUHijAm+6sLhcVHboo8/pGY3QzrK2h8tPXx0LVfh8XOPLy6PJ46hStXw1G3NXEJK+16fJbVgaMGe6H+mku+ly3l4q4200loaPD6g+/n8pOdw/Q3MjraRZOf+ZZ/q+r4zzhcNDiM25YT6urOPdMTNKa7HZzTI6Ns68CAYGJSd5fMzPAnmtsdPWUtP7a7bQ45RlzYiLB8dbVzQWWigq6OOYZbuHFxey3wSGr8PnkJM/ZZqN3QFkZx3WeUSZDgue8batA/wCzX15/PbB/v+WmOzgE+P3U0M1FhICf19Dv4wLXbbfw/Hp7GVsbi3EBIR6XOHyEbdm+je1LJJjQw+fj9T9zlvXYxsascd3cLBCJ0A0yGqPCTeVbIjRL19VEgl5J5eXCuG+ZiGcplIK2jpw8JfHe90v84R8I/Mkr+JD91nckXvz/gD98mRKGFZeem/dx3H3vB5z8PvsPAv/4TxKv/wum4W9qVONSceXz3KE4evsoOBTk073tVBuVi9mQtZI/MWkmbKBy5jDc+xxO3j8zs3Rbr6ujAhHw0+2wsJCZGPXTcr5uzuAgV8mFjSvkz+ZJ9PUbboG9SIl7oftQQ70wEkXwr7hYoKSYx01KKlgzMxT2N7XQMpefT6G8p4cK0tQU/9tsFPSdTip2w8MUbpoajRiMPlrDTJcscwU9FKJwt2kT23f6DAVoISgMTk8DNdU2nDlD4a26ikJWXS0FRyktC4bNZsTyGJkTCz1UIE+cZD+3NFP57Omh4BaN0E2tvIwr6T29VJy9PiMLY8LK7Gc3MgLW1vG7c+cY37JjO7+32agUVldTwezo5OcV5YB+hkLe9m1sd+d5CrZt7RTai4spQLpdQNxLYc1U/rTN/AuHeW3Nos3tusTgAPuz4zytYue76EJaXm4VS7bbqUBEo0C7bii6DktQTzjoBmjWjOru5nHyA8xaGZyhgG23M5bvzDlaID1unnN1NbMG+rwcH9futSy10SgtXPE4FykGB+hm29EJVJbDyHBIq1KDkb3S42H6/P4Bifo6CvI2G4VfbbNV32tsjCUVunuoYJiFqJ1OujPOzlKQjUYlCkJGsoskFeH2dommJiM2TXJfpove+S4uKLhcEiUlfFbl5wP+QEqyjEYbZmepcEQiEj29wMSkREE+FffjJ+juWFtDa2h3NzNmnu3g++ZmCZ9XzNfm6DGyI4bmgAJDaWbMFmudBQJcvDCTaXg97IPaGipeUho18gTbffIU+9a8BqarX3k5FxCGR3hf5efzvtA0vg+F6DY7NsY5q8SI+ysu5r0gBPcH4/5LJnn/lpXyGs7O8nq1tvAYPi/H+YAxL/l9Env3cHFgdBTo6EiippbtChnxpsK4lzo7eV6tm6yair0zEskkLYabNwGPPm7MO63WosbwCC2D0ShLGOzZzTmoq5v3Yk015+F2nUaMuTmJc+cYkzkX5ngqKOC+zLhcm6Blb2iI81RwhnPV6KiViGZkBPMLTNu3sm+Ghnhfe73sHzMmVwi2IdVt1nRxdDqA/AIzmQqfCXW1XFTr7pFGtki6xB89JjExvvRzSClo68TTz0h85G8l3voWgRc+nxOJlHy4LqzKo1BcWu67hytBDgfwjrcCP/4fgb94i8RHPwzceINS0hRXNvtudACIIBik8GNm5DMzdQlhpWwGAJ9PYovGwskFBcDoCIUF87d2u8R0kAJeSTFQVwMceI6CtbYZOHyUrk8+Hy0VsRgFk4lJKgy1tZYyNDJiJGIwjj08QuUlHGbijtFRID8gjVpWdPmKhOmaZGa7i8XNRB0C4+Nsx9gYhdGAX6KuVqCrB+g/x2MUFPD4ff0Ukpx5tFz19VOIuWYnlbP8fAo4ExN8v6kF6OpKoKSEgtL4OHDXnUycUldrJEcZp3ITjtANr76ewqLXS2GtspKWoV//hlapdp2r36ydxvguswC0z8fV/NIS9l2pEQPk9wm43VSYze0AS6j3eqhE5eVRwBofZz9NT1M5q6/j9h4PcNONAj/4IWOOIlG6eRYWUhgc6aI1SQjMWznb2vnbTS3A9ddzzAQCVMRjMR5nYpKKSTgMQBpxW5NUGE0hsrqa8TtuQ7kKztDqdPYc211fB2zVBB58mCNjZJQpwKeDtCwNj2L+92VlPK+5OYnycsYu9vSyb2tqrD7ZfY2Afprt37ld4tgJjtdQiMpmTTWFWTOOMDzH+LrqKh6ruNgoi2CnBaggn+dss1Nh6jwP+IwYe7+Pr4eHOb7HxyXGJ6zfOJ3sB7eL+64op0Cd5+Q4ajFi18xxHwxKBAIMGXHnCUQNt2C3i/uZnaWVd9tWCtz5+cD+p3kfOxy0pEUivC7jE1xA8XjSM0QC7C+eK1CQb7g757EQ/fETvLfyt7N21/GThtXnOsas3nevxLe/AxQUMJ4uGKRi5HDw3goGqSSdOGUmh+F3Xd2GNawWqCgzMkBK9oWZWfbESV4fKTlWdu2kIgXws9OnqfBOT3Mcx2NULMeMbLV2O/CzX1jJfyor2Z62dl5vv49joMtYaCkpsTJ7VlSwLMUjj0pMGG6YkYhR+qGACwXJJM+nswsIzQLP+23eE1LyPpgOsg1mkpjBIc6lrZu4ADE0LOfdOvc/Q3fQrVvYRjOBjAAtuEPDwJ5rOBb9fi42DA1zfiguFigslNixAzh2XMDvpyI1OsZ7JRKlggXQ7bSigkrpc6art7HIZGY0TSQYAzo7K1FgKH0dHRJ5LoHKSi447djOtP19fUs/h5SCtg788tdMpf+hDwrcerNAIiHx7X8Dfu8lwKv/TAm/ivXHFD4ffFjioYeBT/ytQF0t8OGPSrz+tcDvvVSNU8WVy3SQAdw2G+YfsuPjFBJMAW5wUBqKGhCPC+i6hITEzTcBO7YzAcG2rcADD/Lh7XJRSE8kaJVxG5aRmRkKtt09FHpCIWDbNmYxS8QtN73CQgojDQ0UWpMJxiU1NdKClJ/PfScllTfT5amtnSu5LS3AuXNcDd7UwhXi3j5mFpOSCmF1lZX9b86w9BXk06pGJIIztEhNT9PikExKHDpMYScWpxK6qYX9FgwCoVkJf4Dnn0xS6ZqcYnuD08D27dYCZVWlkSDCZyTp2ApUlAscOsTA/LPnaPWam+P5HDoMQFJgKiujRSQcplDb1EjFJZkEznczO1s0ZqSN38Qsjl1dFB6rq4CpKVpFZmYkNrUYBY+9VBrm5qh0MiOehMtFwbyykkpUXR0tQKUlPLeCfAq/8Tj7weth23fukCgtEaipFigrk2hrp9LZprOvYzG6WM7MMilFnpOC4tQUa+qNjXM/zU1UNCB4Dbq6qKhFo7Qu6aepWDgcHD/hOWBqkvs3U/2bZQvy8jj2hodpAaAFiu6ww8MSx09QObIbGQuk5LXzeilYnzzF8WbWf7vuWh6flov01WbWvKMy6fEItG5i7OH5LrrVHz7Kfvj/7b13eBzXeTV+7mxf7KL3XjkACLBJbBIpSqJky0kc5XMStzhOXBK3xClO4pZ8+RIn+Zx8TmLHvTuJ/YvjFNtKbCeR1WV1iaRYhwUkQXSCABYLLLD1/v44c3cWS1RJBEnpnufBA2B3ZvbOnTuz73nLeUMFdBhUlDtRUOW4KCvn2p2cYlRzYxdw7AQJiVJxPHeeUcJwmAR6fl5mJc4PH0kjkSTpUNG8ujquobQtJnPyJM+xtJTOkclJHreiAgj4xQKZ/UyGY2ZKJlMcR0aoxt3RzuvXd5Zpd0WFnNenn5HweATGx7kOa2s5d/GEc31U372REYkN7UytO3bcicp6vQIXBiQOH7VrL4sEggVcA/39wPYbOabBIaCuhu0g2KeM93xjI+/rkVHed0VFdG6kUyTrXZ1cQ3Pz9nVLO+nIs7NAe6uBjBSoqpR47iAQG+D2Ph+vcSwmUWg7dlSLC/bz4zbV1VxzsVkK2xw+wuOWl3ONCcH5B3gfqH5mo2NOf7PhYbseuJHrTf0/MiLR1SVwrp/rtrqKjhOZYbSuo0Ng9CKjwbOzfD4++ywAIfHk07xG3V3KiQEcP84Ux/JyRgepquusAZ+P0V7VRmBomM3ZJyclxUqq+FwZGODaF4ItKcbHdYrjNQMpJf6/bwPf+ieJT/ylyPbiEII/GhrXGm69BdjcS2OxowP4zCcFPvgRib6zEr/9fhZEa2i83HC+P5OVzHe7aYCNj/PLNZWiR13VNQB27ZLbicycP28rePm5fUWFYB2bi95ZpoQJjI6yFqWjXaDvnMTUlFPIf+AQP6exgTU66rPqawHLold8elpmG7q63QKlpdLulSYQiVDhsaCARl9BkMb87KxEX58j011bCxhC2OmN9MxPTgL+AA0jNlRmamYgoAwMVVtHL/HmXsrvnzxND35HB429VAooLRMYHaVBVVnJeWuop+FdXUVDTvV3GxriOc7MkjQNDDDbxO2msTs4CBw/TpI6PMzrUlsjkEhQ9r24iOc6PMK5y0V5GT37g0PA2bMS5eVMjUqnHTW1uTl65UdHOT8lJaw7FILEvDDMyJbbbTfPrSbBic2SCI2OOimNR45yLG0tTNmMx1V0SMKyGJGprGDPOyXIUFfLSNDAICMVFWUklfEEDcxgkGPoO+sY6RMTNB59Ps6by8V5Vc6FiC0OsrGbxxy/RBKYybB1w+ioRDjEa7tpE50QbS00kpVcf1srj20Y/OxAgI2Qk0mSs06T82cYTHML+J2oohAklV2dyPb8GhgAKioYTSgtBoZHSZTKy7gGz/cDdXVMYautcdoclJZQ/KKjnQTtTB8wE3X6SXk8nPvaGkf1saUFdrNu/t/b40JsLgm3WyCVopDK5BTH3NvDyFZrK1OPn30OOJkC7tjP1McTFtDYILNS6QCvo+rdpXQDamuB6kHek/V1gMfN9MPYnCNb39JsKyJGkVWc9PlI2jd2k2jNz9uiJ/a5z8Y4h6dOA3W1EjNR4JY9vE7T0yQawyOqlx2fGR43I5ZuD/9OJEnOPB4+IwJ+XvNMhmnDrS127VXK7s8WceoBd+2kpPzYmMTZcxlUVzMKWVPN6zw7y3u+r4/Xoq5WoKYaSKUlJic5p4NDJL33389o9caNVG8tKSExnLZFYspKeV0a6rleSkpIdCYn6JhpahIoL+ezw+Phc258nGNRRLKpUUBmWF85P2+LPCUpgnP2LJ+JUvJ519rMZ+rNu3ktVbPtslK7SbaPToXSMu47P4+swnoiQSdDRxtr7NwuRpIl+BlFhXTEFRRwv/4LXHeqlcRS0CqO64RUSuL//Y3E974v8dm/IzmLxST+6q8ziMUYOcu96TU0rgW4XALl5QKnzwAf+ohEWxvw5S+wief7f4fKUxoaLzdsv9ENcwOjRAMDjAhkJL3ULhe/dAsLBWpqKOxUXy/Q0UHDzO2msTM+TpI1HaX3NBqlPP38PI2Z4RHWURQUCDx3kEZyV6djjJobSOROnqYh39hAr25DA6MuALdV0bn5eYnTpxnJyWSYyhcI0LgaGKTBcfgIiZYwOL6SEoHhIRawZzIc+9QU097cLhp74+M2Eaol6RoepiGn1N/GLtKI7DvHtL6uToHJSRpbJSXA0FAG5eWMQA4MOn2jOtpJXOfmOCcTEzRuGhpoYCUS/L1pE8/92HEa/ADnIZ2mp3s6KrNCHEVFTNEqL+Oc1NWyxcCN24RdyE+Dq66Whf5TUxRCUY2T/X5HNbG4iJ8J0JjOZGjc3bFfZNOvvF4ax0O2uEd0hhGlmRlGf/x+rp2hIRpnRYU895pqzk1kmpHA/gs0wOfs+sayMs55XT3PvboK2LrFhTtuN1BczCjiyAjrXC6O220JgjSIVVuAs+do4E5MMPoxMMA1XFXJeaLYA9dgby+FL6yTHPeZsySUN2wVMDdwDnbvZKSgq5PNwefmmDrb2mITNcm1cr6fJCuZ5Pyo944dz+n/57PThRN2lKqO+1RVkcRWVlJGf3jYln+PcL1JOJGvn34No6GdXTxGp8lG1gUFAu1tHLO05RxzRUPiCZLBKVvwYvMm4Bdeh+w+AhxvZJr/dJqci5FRXiO/b+GzoqFBoKKcSpHFxYykXJpwnO7JpEQixWvjdvF+bG1Btj/W8RPApUsSJ0/SqVNYSJGMSIT3lmFw7kZHgcYGAb9foKONa7SxkWsunZbwB3i/92x0iHQ4TNI4PU3SrdKFh4aYyhyyo8NS8jnl9fEeb2xkpGpiksSuvY3prhfH2eD54kWgtITNx/v7+ZwYGnZULpuagHK7BrDvrETSTkN+9jmSkrN9XIu1NRQAGhomuent4frqNEn2fF4+R9xu/j83y2dARwfX7lSEc3XgENdWdTXXhlJdnZggab04zgh00HZkzMacurJQiJ+nnqlKXTGdJkkdv8TedIGAQH+/RDDAZ6EiV1JyfC3Ndi2hIVBZKVBZaQszDfG8hRDwepG9xu1tC9VGF4MmaOuA2VmJP/iwxKnTwBc/J7JCC34/F436QtbQuFbR0S7wxc/x4XO+H/jU39CweOe7JI4c1SRN4+WFkREqexWGSQY2dvPLdGxMwusVdrRH4sIFiVRKYmqKHtRjx2lMNjYCjY1MYS8rtWXNgyRg4TC3Cwacz/N4aIhYFrI1P5OTTpQpnVaf73irx8c5xqYmu7bI5xhkFOmgjLfHTaOprpbHFYKCEYEA1epUBgdrJ/i9FAqR6FSUs07E56OqZUM9iZUEDc2N3QKNDYJpR1U0op99TmJ8XODm3SQKbjeNJpeL4hKRCIkO+51RzKG4mGS3rlYgnebnz8aYUuT3kVwWFZGUdHTQ2O1oJ/mIRmn8hcOCEQMPU5BqazgXGzcCszGJg4dklogVFwOVFQIzM7y+m3qda3HpEtP0PB5h933j+JXIx/0PSoQKGAUoKaaxvW2LU6vW2sLoUnU165AaGzlmZWh2tJPQGwZVM1XEaXoa2TqkiUmOP5ngPI2M0ticnGJt4/g414/bTTW4m3YxFXNwiAIqM7McS8gmhdFZ1vhRlVJka/bSaaqSHjzIeq+uTs7Bti12r7dzjOic7wceexwoCNLR4PMBmzcJ+PwkAn19jGaNXeR4hoZIcI4dd1QYC8Ocr4AfuGM/yVR7O+e27yyN1qPHSGR9Xp5buV2fNx2xo4gXOc/nzgOHD/OeqLXnmS0sJNJpErtIJEd6vgjZXninTqWzPdOk5LjLywT8OSIQZ85wrVVXUdJ9fp7EprKS485FLMbU5liMLWkmJtira9KO4M7NAdYJ9gFzu3ltnn2Ohvv5fl6H4mKmWRYEOUdFhRRJ6WgX8HnZry8UpoMlkZAIFgjs2yswMcGxzsxw/RcUCK7VKbZIuDju1FodP8E5mp0lGWtv43rw2qnXrS0k3C4X51dtE/BzzienZLb3lwQdVCUlAhu7nbmormK0NpOh4wTgNRsYpHNrQwejUYq8XBjgGLo6uRbPnpOYnpbZFhlKMVRKPl88HpsIzvHevm0fP7ejnSR/cIiE6ugxvp5I8JnU3MRjD1zgumyoJykbGibR6++nymUqxWdwZJrz0djAzz98ROLkKdafnT/P9dnY6Jw3VSeB2BzPeWCQPf4mJ3m+mzep7xXleBOIx9mKYTlognaFMTom8d7fJOv+9N8KlJYyP/kPPpxBMgn8/P8S8HrFygfS0LjK8PmYEvHlr0rE4wK/9zsG3vk2gd/9fYn/+E9N0jRePkilaUwZBr3DhiFQXgbb40wjrKzMEUcYt+tlmpvoUU4kgEhE4thxphmqGq7oDA3Snh4WpysPalGhQGWFLbndyChOJmP3f7LT6i4MMD3wmedooCSTNKSGh51+YJUVNGQAeuUHByU8XuCdb+drXZ085ukz9CRXVdKAMAwSI7ebxKS2hsfiedDwHxtzajMa6klQzvczdSmVEvDa6VN1dcDNNwHVVXQ+VpQb2fFu2ECiVV9Hssn+cBIzM/w5dpzpQzMzTpPcR3/CCElNNef8hEWj6+hxGrMV5Tz/U6dpFDXUAXNzAmfP0fg+dlxkU816NvJ8jh4nKaivZ1Tt0gQAwfNtbeVcS8n6kWPHSQSLiykVXlTIubxwgcZnMknRg2CQ+3lso3d4mJEGj5uCKo0NNMhHx3jRU0lkZcS330Cp//37+TuT4euXJhw5/fFLMjsvo6OMggohMDDI12/ZwzU0N0fjN5Hk2kyl2Sy4tZVRu0CA1zg6Y9eRxWiUu1yM0GzZzNpFYTB9sLSEqXhFRRSPqKtldHVwiPsAQFcXI6e9PXRelJfzumzs5ppzu2mUl5bwGp7pY33OyZO8xkIwwtdQz/H1nXXkyFtbOPbSEkYulGBPsMBWrrwgceoUXysoUKqIXDM+n8AN20hIUylus3mTG709dAoU2qlnP3kcOHKE7wsBdHWxN9b4ODA8xDnNZLj21PVz2+ceiTDF9bZb6ayorha4dR97AQK897u6eN3m5viMaG6mg3NTL+dWCFskpYBrpNMEUkmJ0VE6YeYTJAWbNzkR+gsDrCW7eTfJz8UxiYkJpvyVl7EhfHsr10IoxPnvaOe89PYIlJcb2NRLYnH6jFLp5Brx2MVPSpjlwgAJpdfLfWtrgLPnMohGmapXX8cI0tgYyey588iKsnS08zk3Oirt/nZOjWOoANiwgffn9DSvxfglEkuPm06L4mKu4cFB3hvbttBps3uXwIYOA6Ul3C+T4fF27kA26ltdLbJ1oT4f108wwHvzhMV5crv5HOpo532xY7tAdRUJ7dlznLsNHU5vv5oajv3iuPN9kUhQcVehrJTfGyrKr1JwKyv5/XD4iMRzB+WCYywGTdCuIE5YlCffsR340//D0HQ8Tg/X3a8V8Pk0MdO4vlBUJPC5T7Mp6Q9+JHHbrZTi/+o3JD7xNxkkk5qoaVz/aG5yweWiJ7qinK/V1AgEgyQdd+5nL57SUkaV29sE9t3C+2LLZoGGBgNeDw0MKQGfV9oKd/zSjkxRLl5KEr4nn+J9093FKFggACQSAq0trDepqKABces+Ro4KCjieTpO1YkLQAD12nNtnMjxOcTEN8MOHBUZGaXTEYjRkJiZptPSdJRlRBE1J6AtBT7JqA1BVxdcfe4J1IFMRpgAlk4wiDA7RMKmtZf3VbEzaxnYGRUX03J88RWNrYJAS2qECfgcqyf7qKhpNMkPDtzAM7L+dpOCExXNSqYFKjW9unkSkqZHGZ3GxwG23sldcQz1w536BO/ezibJqAL6xm+c0NiZxvp+GeCZDg767SyBgR0ke+QmvfW0t53d2VmLnDpIbrxfZupnYLNMTpbR7v520le5CnN+ZGT47b7wB2ShEQwOJX1cXSXdxscDMjMChQ05j4F07SOzqaoFNvS401DOS2dVFYp5KUZiAEvesCY7HGf04c0apFfLcBgZI7BTYqoGkLBx2+lgBbG4+OUmxmtJSGt1tbYDfb2DnDgN799Cgnpuj8To9zblJp1VKoX1t5hwZfNW8Oz6v0sG4PhvqGampqXaEH5oamRo3Pk4iPDzM83C7OB+VFazF9HjoZGhq4jX1eES2ngtgemF0WmaJKgBMTGRw5ozEyAjrN3s2kuT09tg7CTpXxi/yet6wjSTm0iV+VnExN1N1dzU1gs2ww/w9fkni8SfYRgCg8a7qFsNhXgefl+R7ZIT35NQUhU7m5+0opu0smI/z7xMnOJe33sLnDeBEt+fjjIKWlnK9ud0C83GON1wosG0r58TIiZQfPsLIf1mZrcIZZCpxMABcslOaheA1huA1Nk2BwUHuOzgE1NYYyGT4HBkYJJnJSF5rcwMQtu/tg8/LrLPp1BnVtsO+r2o41wDTnXt72COw0xQYu0iBj6Fhp2byzFkBc4PArfsMFIZ5fKVqOTTM9dvf76zxkRHWn0WmbPEbry1440K2ds3vF2huofMrnZZZR0hJCZ0SAwPcPpNhdE0IOgvicWSfXR4PzzkQ4JiUAE5lJSOEFy6o9cjnVXUVn+e+vHTZfGiCdoXw0MMSv/W7Em97q8D73mPAMAR+8pjEH/6xhMslcPNNmpxpXJ8QgoX1x45JzMxSse6rXxQ40we89/0Sw8OapGlc3zh9Oo1k0u7bZS9nGiZ8fsfmgHPnJM70SSSTEhcGmPZ29hz/TqclGhoEtm0TqLZFDnx+gS2baMSdOw8U2+ktmQw90D4fjdCz52gsRGdIHtrbaaxNTgJPPc2ifq+Xwj1TUzSqUin2XKqoIMFxuZiZEQzyWMkkDeGCAqdZbWkJyUMwwHs6k6EhIiWNuNJSespN0+5NliJRaGoEQoX0cLe2iqxIR2Uljc4DB0hI3G4ed/MmF+bnVVohDUq3m0ZdJiNRWEhiW1lJolBcQkNTNQGfmKTCmxINKSvlubS18lhzMRpNLheJ1nRUYmSU5FAI4EyfxL33sb+U6l/ncnG+hWDkp6uTnvbGBkbwdu5gVLG1haRZyconEsD9D1DsoMQeZ1cnsHMniXJ7G89TpbL6/TTcNvVS8OLCALKOWSF4vkxPI8lRdUuTU3aqqkFP/eAQcOZMGmfPMWoyPML5drmYStvS4tgTRUW8Vl2d/LuoiMfzeZlGKMCUOSFUewGJp56hMexy8Ti37LFVFQ8yLXR8HDhwkMe/MMBI5aZeEv2Tp5jaOHbR7oUlmFYXi3Etq3TC+jpg906Bjg5Vu4lsOuap01yXp07TEZC0RSIaG/h3Isno5dhFkpixiyR8Ssq/vp5pbZcuSUhJpdGRUWSjo4bBiCVApUbV2L2s1IkEZq8LuP4NlyNrn0wyird1qyNAIWzreWpKIjZH4ay+Ps6NMASa7BS4tO2QmJ+3+4Wl6UiZnOR6Ys8z1vopsR8Bqh42NbLmNRhg2uP9DwLVlRIlxVxbQ3YqJ1P+nGwsl8FI07nzJC9FRdxWtaQos9URUymSs61bWGOWydAZcfYs3w8G+TmTk8DIsER9PddQQz2wd68HRUUC27Zy29JSp1F4JOIQr3RK3cskXhs2ULiltobXUEWkZ2ZVfZvE0DDPsaiYRNQwmKpcVAg8f4SOFQWXi1G9lmZG+WIxJ03c62WKZmsr+9id6+e9UFNDAjV2ke0YLAs4dYZp2WNjvEbVVVyzJSV0DqnI5sAg0zhbmhd+Z4yN0UkBcB2e6aNDpKiIjha1zZ377TWedERGloJWcXyJkclIfPXrEt/9PvBnfyKw/UZBKU3Bh35HuyZmGtc/XC6B3/8A1/I/fktiUy/w6U8KfOkrEu94l8RHPgjsuVmvdY3rE0VFjDglkjTwKitJTAIBRpsGB/kFHZ2hgZBI0Oirq6Uxk8nQqJiZkRgbZZ1MOi2ztVTbttLwUgX6JaX8fekSspLXwSD/Hh5hxGh6mil9h48APr+Ex0MjlPUq7IlVGFb1ahKjo0BnJ7BvL9PO/ut/GAFIJpn6FwjwHAzb0EynnbStdJqG6tw81Rnn52moDo8AP/NTwNCwyKZS3rANePJpgRHbMWNuoNrbmT6+39LiwvAIjeWSEqCshPN06RIJ2+Qk98tknLSneJypROfOkWB2dJCoFQTphb9hK3DweRp5Jbaxefas6nlGQ214hMbZwADJ5IYOwLAJSGSKKU4VFVRBnIsBP/taA/E4U+4efpREd3qaJLa0lEYtG2Mz5XN4mERkdMxuvBygEdfawnkbHmENWVUls2k8HmB4hI21VfpecTGvxZ37acSWlpAEnPl3Gpk1NRxHSQnnx2UAd72KczAywvM+dUqiuJA91m7eDXzvHjstNsJ5nJkBGuuZdqn2KSjgmnLZ6V11NSRkCrOztvBIgV3LFnKM+liM5+n3Oc3T29sccicEDVu3m4ZwKsV2Biq1rb4euPc+CuYIYUcx7EhuextJw8gIiWd0WvK62Wt01w7gu/dQUn1TL3D2vMCp0xIXxxiZLClREuZMDfT5SLIvjpPoAUy5DYU41k09EoNDAuOXnPOjvDvT+SPTHF8qzTmJRDiv9XVO24Fkkj91tZxrNU7l2AkEBHo3sldiKsl7TqUbqmhMKqVSqp05nI5Slt0w6IgoLmGkLxjkBx84JG1BDoGL46wnTSRI7GpqBI5bEj0bOafPPkfBmXBY2Mfg50xHKaLx/GFem029An6/xNQ0x65620WjXIeq/9yGduCElbLTqLlGiooEjhxlg/KRUUciv6eHc3nuHJVTy0qZSab6rZWXUg4/naYTIZHg3+EwMHGJ162jna1MmpooeDNqC8kAzjMrHudrGzqcNFhmOHD9VdlCS4kE06Gtk7zmgQDvl009QDhsoLdHov8Cay8LglyvPXYrkESc51cQXCg8k0qR+Kkx7d7JZ4jfzwj7sROOY2xsTGBwSGbHuBx0BO0lxMyMxIc+KvHoT6h0t/1GXsDv/KvEw4/QM6IezBoaLxc0NtAT6nIB73mXwEc+JPAXfynx2c9nkErpaJrG9YfqKoO1ZePOl25BAde4EE5dSzDIlKO2Vqp8uVwkKB6PyNaFqTqrTJoGnmGwcenp05Rhzkjg2DGmcTly3QKvusNAVxfTimqqGRG5/TaB7m5kjbmN3TQg/H728Dp1mkXs6TTH3dZKr/1DjzhkI5VymvrG48gSqZlZGuyZDLKKjtPTJFGv/wWmuvm8wIMPY8F9LQS90JMRGnFeLw1wl8tOdwPrcObjHN90lAY+Pe9sIK1SfTZ0cGx+P0lPWRmwd4+BqkrWlHk8fN7EYjSqhoad1ML2doGKCqahbttKpcGqKmDfLQJ799DIVtHN4mIafQODFCRQ9Uk+H6OGNdVOqmd5GfDqO+zmudMSba0C8QRJi1JNNIST8pRIkFiqeqvhEY7b7Ra49Ra+pubtzBlGHVwG52F0DDh4kMSz0wQqy2lUBwPAxm4XGhsFYnMCe28WWUdAUZGzRrkeSRBPneL76TQN/HPnaLgKwYtSEKTxXVwssqmNCv0XmGaqBM1iMbspLygCsucmplqmU7weY2PsZ5bJ8JrPztr1ROOMGiaSJEmnz3Bcu3bwHJsagZYmRjg6OuzP7qca36lTJEgnT3HdAIwcV1XyXlT2cUszcNNuu3m7VGPkvTo7S2EVI8/SHRmhuNX0NIleXa3IHi/39+CgHQm274+OthyxHfuYFRW8991uGunPHQSeeMpOT4StrtonYRgUhdiyhU2Tz53n+j13jo6aU6edCIwQXFOBAJvCR6P2PTrjKFO2NvM8p6Yo3NLchAWiE+Ewr5vqy1cUBhrrZZacAXRgqG072rlmR0cdYjA3x3uxq5NEcHSM47ROATtudMPvV3WASkCJa65nI5t1K4RCJGxTU0wjPHGC66aliZEzgDWrGzYI1NUJNDZSgKSomHWQ/oATGaypcVpUAYx0AnzOpdOM9E7bBHNwkCSXZJ3PAJeL93RHG59Vbjc/Mxbjteq/wLrhulqgt5drlv0iuZbTaTrPbr2FnyHB531vDyOYrS2sw1XKpMXFDnGPRlk72dnJyLyKHi4FTdBeIpw7L/Fr76G60Rc+yyLDL381g0hE4t2/LvC6n9PETOPliX23MM3pX/4V+OrXJfbcJPC1LwkcfB74zd+W2aJqDY3rBQefTyGZpPdZGd7HjjO95aZdJDqxGHDihMT8vMTzh1nT0XfWMSZpFDL1pqCA0Rt6qFknVGMbejLD+h6VmjY6xtcjEYknn+KXuddLA+LBhyVmZ5xoxYULND4AwO9jdKeykkaHUq2bmXHSxcpKORYV3bg4ziavXo9DyqTk38JgnV1tLZ2P8TijLFs2O2legNPHs7KCBOD4CdUWQFBlzSZwBUGmDQmQHJywaNwEAiRVqpHt+CUqpFXahnjfWYkHHqSReGmCn9nSwrqjcJifrWr5+vokZmYlzp6TiEQASODgIYn7H6TSYHye+6fTnOvCMNDc7KQIptOU/O40Oa81NTQsCwoEhoZpNAMkBWoOursoflJSQrIVDpN8qloXCkEIzM9L/OSxheustpakXRjAlF0TCMFoYTTK6IGK0B58Po2nnmZk6Ogx2HVjdPpWVTn2hXIk7N5FA7GsjGuguorRD65KO63Pz1rBI0dp4Cps2UxlxKeepmrk3BzJJEDiNDws0dEOhMIC/RccVU5FkKamSBIjEX62x800NNXA3OXivPr93FdKpiAGAgL7buH51tdz/gGn9YRhkCgrsR312swMHQ1K+vzSJZIrdZ1deZZuwE5HDQSABx5yiFF2ckCnY1cnHTIeDyO5wQLeKxMTVG0EgJkonwHn+zmmLpOtHVR9pcfD9Q7QOWEINo1OJZm62GmShG/q4XjUPVVYSMGRRJzXNB4HDh125nh+nlFWVfc4OORE4ACgcwNTQsfHeZ9BMLKWi0zGjuzUk9xbJ3l9VHNwt5vzd+ECU7pVPaRyPAXt9EhDcP2raOvZsySOCobB1+vrBfvt9fIYhw6TmN25n+M6c4YE6ew57tvUKPBLbxLw+6hK6XYDP75P4vz5hccGnObmAIkvwDGVl5PwR6ZJPmMxRhn33y4wM8tn0+HDrKtTzinlMAqHeD3jcdaLbt4kMDLCCG9uD1gpKXAUjUrU1ToiRZOTdGLctIvbRWdIDPvPc60qkZ2loFMcXwI89IjE//1Libe8WeCX3mSnIrjolUqmFt40GhovV7zqTmA2xtqYQAD43N8JfP6LEu/4NYmPfoT1BxoaVxqmad4F4FMAXAC+YlnWx/PeLwHwNQBtAOYBvN2yrCO527S1GIhGaXRGIiQL3V1OM9r2Nr7e3s4v2ZISvtfSTMMJ4P+ZDLLCIpmMxIFDjBq0tlG0YnqaETSvl55glyFgbqDxEQ4D3Z2MWFVUyGz/tb5zTJfyegWiURpYKsVRGOpzKbAwPExZ9apKiXv+w1Htu3SJBnBjg+1dLwQu2NECCVskBBQ4OPQ8CUc8TiOwpARIxJ17WQj2Ehob4xi3biZhMQyRNZ7cblucJMRUrYoKEhCmdVKgJJGk2qHfz/Eoue+GepYHTE5RAfnwURqAZ8/TS11WKpgqeIbe6qJCGpXzcScFtaZazQvHrerBCgsFhoepyrl1C9XmDEGjXcl7nzzFlMqmRhISgGmT8ThJwOnTnNeCAqYzNTUyKjU3J3HpEtfD+DijC0xdY6oqYEcKJ1RaHY/T28ParcEhRqKCdi1dUSFrDMMhGt1MuZV47Aluo+ra0ymgMETCMj3Na91QT6Pz4rhDqNNp2JY7I40lxQufz34/5626moT/5t18PRCgATwwiCx5qK9bmOLY3Mz5NgymOEYiVM6bmyfx+8njjKQVFbEOqKyMx/qVXwaeeoaEy+XivdGz0Wk6LQTnMxhwBE3OnWeUsqGe8w4AlZUG3v6rEvc9wBqmyPTCZ4TqOevzsT/Y3DzJOpDlZ6wHPeus33ic172gQKC6Gtlo4ZYttjR+EZ0r4RC3mbMl110uJx04mWTUavMmRnP8PopzhMMSjzzCnmMKUxGm4d1+q8CFAQmfzyEyAB0Zfj9QUS5QU8M+irkk+/EnJTZ0UKr/mWclNnY7arK5YJN3RiGrqjivdXXOeafSnJ9QiJFSn48k48DBNEZGGLGvqOD1ZiNv3ns+v/MZkQhJTV2dhMtlICMz6GijUqcak8/H51g87pDQkRHgiC2Z33+BzqEd27n+FXJTtGtq+Gwev8Rj8tkrcfIU0NpMkZ6nnqHTZioiIDM8r1pb4TUYZATs4CEStsZ6qnEK+5k6PS3R1ORErAHHoWUIpZLLaPiGDq730TGZdfJVVbI3ZmSa456cuuxyLICOoL0IJJMSn/p0Bv/vExJ/8r8F3vJm9oj6tffQm/pLbxLZZn0aGi93FBezj9GzzwEf+SPm1L//Nwz8/u8J/OmfSXz+i1rlUePKwjRNF4DPAngNgG4AbzJNsztvs48AOGhZ1iYAbwXJ3AIUFFDYKTrjqLbFYuxvJQTTbwyDUSop2VeHxihTtwB+YafS/CIWgpEyt4tkTKoatVmSqJOnaPwACx16Pj+/zClqILDnZoGfuov1EgDrO1TavMvFY41fosFQXc2emyOjEg89YnvCB2jU7djOfSIRKi4qT67bBcBO7TNspbP2dp5fURGNy0ceFcha9rDVHiMS83GmSM3GSHCcJsGMjGQyNLImLtGo3raV41RpQOEQP2v7jZRAn5igcd3bw/GpaEFjg4DPx3TLkVEAguf6c3cbWXGRjnZhG+yM3LS1MtXr+AmmOBYWUsTh7FlpRyuQncOSEqB3oz0HBsUbKiposCfiSnGOJLS5Gdh+I/umqYiOEh8JhQTKymwFxFa+dtNuhwgJweteWUFSMBsj0Th8hAZ/bw/th9JSrqkNGwzU1QqcPsPPLyoiMW1pdmTFAWDHDkZda2pIGnw+Xvfz/Y7ctxA0jsvK2I9JCCCTXvhs9ngYwRkdZWqnQn09U3wLC0mqKyt4Xfv7pb1+SegMQ2BggMZxOs2IgYps3bKHUdDSUqbW1VTTQD55Crg4xtcnp4Daaq7P4yeQPbaSjFepeuYG9gRLJOhQAGibTUUkxsclIpHLUxwVpKSSoao/U3MDLBRw8PlYf7h5k8DWLazrVNexvk6guNjICvmodFmRZ/pJyc8JhdiE+vRpux7qlIDMiKyQiDrPQIDENxziMdPphT1Hm5v4MznFdg6qObNCexuJ7uiYRH0do66q3tM5L4GuTl4DgPfBkN1WAOD4wiEqWZaX8xmosgT23OxGaSnHOjrGCFNREf/f3CsWRJi2bGbvu84NPI+TpxjNm5+niA9AYvjqO0mIKiq4b0GBPU6vU7Pn8VCcSEFFR6XkPfrcAUr6KxQVMlW4ttY5b3MDnV+hEPcLheym99MS1kmZvWcbskIvnOPojHONcuFyCdy0G+g0xYLXUimJ1hYgEKTwSyRCx0p3N8ej0p2XgiZoLxDDwxLvfT8Ljb/2ZbLu/n6JpkbgDz+0UOpVQ+OVhBtvEPjLv+D6f/wJiVv2AF/5osDzh4F3vVfi3HlN0jSuGHYAOG1ZVp9lWQkA3wZwd9423QDuAwDLsk4AaDZNsyp3gyNHU9i6WWJjl2NwnTsPTEwsfK6f6WMvrOcOcE0PDTsKYsJgQbuKWGSkgGkyxTGTcTz1E5OA2ZEj0pCTwnTgIFNsDENgelri/gckTliOR/7ECabVAIDXY9dd2SmO8/MSc3MSbhejBC0trPHyetm/DOC5tTQ7dRxKTvrAIVs0xE25+skpiViMhOfWWxyxDYWaGmBjFyM0589TREAV0SsCZxg09rxeCmmo70iPR2RV3iIR4OI4I3GVlTT4rJOMuGy/gUZrPC5RWclUq/I8A+fUaZ7TmT5GxUIhgUcfk3j0MRKDkF27lEhIzM1z3NXVAjXVzvnE4/xckm/Wo8Tm+Fk3bOM2fr/AWTtC1dvD/ZsanfQvtj2Qdj0OiVAyeXn9XlsriYuSpff7mQ44M8uUsnhCoriYbRyeey6NZ56VCIc5J2z+bUu850RGCsMC4ZDjHC4o4FrraKdxCIHs4hOC6avn+x0ZeoVkUuLpZ9jAWm0LAM8fphFbXsbraRg0gvMlw2uqeQ94PDRMu7oEmpsYpZmcdNRCYzESgfFxEtTWVr7WUE/SUVqyUMDDMLCAcM3NkXyOjTmRl7l51rJ5vYxK5ac4KkjJiMpU5HJCZXZQORBwUg+noxIPPAQMDLC2DQCOHmNkZWKC94+KzuUfD0B2LQ0NK8VDtucoLGT/LSXTLgQQ8NNRMRVx+pLN5UTIxsdJXv0+rqFoXpSwppoEKJlwGr4vJusuhKP+ODREwj0ywu1LiklKDh+WrJdstp0NBjAxSSfs5k0CoQKS6mo7AmdZcgEZDBXQydPdbcDlEti3l+vi0GFHTCQSAR57QuD8eZl9PhUUMCIfCDipvo8+xueegnp2KYIG8PorpFLAzp1UalUIBLi25ub5nD1p8b53u21nkV3fqlJmpWQqZ3cX00ZVGjrf5HPiwMGFkT2A67j/guOsguBnJxO2Mm7y8uuRC03QXgAe/QmV6rZuoXJdZaXAj+/nl4gQYgG719B4JSIUYvrVt7/DniJ1tQKf/qTALXsFfv09Ev/2Xek8tDQ0XjrUAbiQ8/+A/VouDgF4HQCYprkDQBOA+twNbtnrQVmZwMVLNIoMg4Z4Z+fCZ3tNNY3M1hb+31DvpL8YYmFqVipFqf7ZWYl0xhEZmJsDggUC+/YsPHYwKLBzB6MKUtIw371LYHLKOa7XZ4t+tAAZRSZiJAEzMzSuSks5ppOnkE2zU7eealysjElVW8JoBFXjTp0WSCVpUAyPkFDmjtQwmL4sbcGPG7YtFCsA+BmZDNDaxrHkGtljY9KOklBCPjarPOUCLpdAQZDjGBmhoT01RWGF/gtKtMX5nI3drGerr2OalhC2x7qTUbGGBjvSaUd0fD4KADzzrIr2MfL26GNOjHBqimIat+wVCIUckyktOb9PPkVhiNicwKVLjqBDKkXiEItRtfGnX2OgopzzqpBMOqIdNTUkI3X1fK2nmwYvQMJWVWWguyun1UEIUKPMnYPz/c7Yp6cZ2aiq4jpTBqTaXAg7za/VqZlS8HoYhdm2halxbpskNNjjs04y4hIMsh+gqoNTayud5nO/tcVu7msr183PA4ePMoUzmWSUJxLh2rpzP9d3KsV6ofk4sG2bE8U2DNZrhUMLU/3Gx0kelFR+YVhgy2YDhYUCBQUia8TnwzAEursuX0dqlty2I0KJaaTTnHu/36lBrK+z00FrGCVRtWn5x/N6uU15GaNWuZidlThzxhFZAUiADh+RWbEhl8sRngN4jSsrGFnv7BSoq8/7QAHsv12gvp4Bg717xAKBkMXgcpGcbNjA55PXy3RSr4/39OAQr/dt+4DBwQyGhoBnn2M+dDrNWrW5OaClzRGVAfja409SSAYgsUylgNv2ORHl4mISt/p6zilAInTgEAn00WO8vrfscdaDfZoAuDbKy9kPr7kpx+Ey7/RdU3jyaf6kUzwf5bwKBgWqqxiNVc3JATqT2tsExi4yItZQv/B4UpLM5kfECgu5JmTGvte8fI5FZ0gI81Nv86Fr0NaAVErii1+W+MGPgI9+SGD3LuBjfyHxa+8A3vj6hbKbGhqvdBQWCnzqb3hPfO0bEntuBn71rYKN2/9c4rHHgY98kAW7GhovERZbTPmegI8D+JRpmgcBHAZwAEAqd4NMxkA4HIZhJFFWKlFWauDkqTQSSS/KSmmkV9dk4HYnEAoBDQ1++8PjqKwwEA57EAqn4ZvMIBSiYRSPS9TVplBebsBlCBQUGAj4ybTSKaC62ouAP4FAQCAc9iCTkRgY4Gf4fQZedacXHo/A636OhC3gT2JjF8e7ebMXx46n4POl4YNEwC8QrhfY0OHByGgGx46lUVTIpr37b6dleeRoGhMTGZw9B7S2ehDwp1FU5IZhpGiQCqCszINb90kUFQqc6UugslLg1CmgZ6MrO/Zw2IPxcYmAP4XK8gymIi4MDkm85i4qO0xMAkWFAcTnMwgFPTBcAv3987jxBh8C/jTq6yTi8Qxqqg0UFAA3bPPgwkAG8/O0jjo6PIhGJcYvpVBbJ9DcJFFT68Z0NIXR0QwKgh6Ew7TAA/4EwmEXystdKC5KoLBQoNN0Y3RU4tJEAiMjGfT2uBAKGWhpduHRR+OoqTFQXCwQDnO8pinR1gY8/EgKLkPiA7/jhZQSTz2dRnOTgaoqAwF/Als2CXR3eeBxpxEICBw+kkIolEZ5mYHCQi9KipMwOyTCYa4HKSU2bpQoLeH6KShIIRJJorrKQCjkxuwMEHcDg4MphAsyeNWrAtn1uHMHEE8YMIQLTz6VQqfpQmQ6g1CBQMCfRjjsyaaUNTVmMBWRCIddqKqMY3Y2g4kJCa/HQDIpEQ754HYLBPxJhMMe3HqLxI/+KwGPx41w2DEJQ+E0ytMZPH84hZ/5KR9K7XUfDlPE5dz5NMIhgYmJFJ4/nILfL7Chw4VAwEDAn4HXy9/j4xnMxYA3vp5jHB5J4+7XuhGLAWMXMzh5kuuotNRAOOyGYSRQWSFRUQ4UFxk4fCSNqakMNvW6UVjoQVlpCuEwyXLAn8LGbi82dgM/+i+H+fr9HoyOSoyMxNG70cvm7/Z6NQwDAT/v14KQG94EhSqkBAL+pJ2OK9Hc7EFlJQlhSWkageE0mho92Wjl8HAGPm8SjY1euFwCs7MSwkijuNgFn08gmeQ9SgsdqKl2YesWAx6PwMhIGskU0NTEdetyScQTcZR6mBpYWOhBVWUSXo9EQ70bkek03C5k1ygAtLZkcPp0ElJ6cOZMHFs3e7PnCADhkBvPHkijtcVAfZ2B//6fJG68wY2KioVxmYA/gWCQc9/SnEZ1tcCZvhS8HmGLuaTR1OhCJJJBIMA07rIyD6qr3RgYSGNmVuL8+QxSKQO1tRQrKi02MD/vPHZbWjyor5fweNjzMBZLoKDAg/P9HO/G7px1V+Bcx7paD/r6kggGBXbvcsPjAebmJdrbRdbeLgilEfCnUVBAUb5Tp1kH39rCua2qNlBSLBAOu5BOZxDwp/DqOz2YmQH+5d/i8HoEEh7gwoAL9fUGTp5MI51OYVOPgeZmD4aGMojFMjjTZ8Dvz2D8YgZS8pkT8CcgDBKwqkqBYNCdvQ+DwSTm5jJ2TaoboVAGlZUZ3LTbi1QKiEQy6O7OYDlogrZKDA1LfOzPJVJp4KtfVJ3IyfiLCjU509BYDjXV9OQnk1T/+vqXBT7zOYlfebvE7/0ucOs+ff9ovCQYANCQ8389gKHcDSzLmgbwNgAwTVMAOGv/ZPHY4wls3jSHkiKJsTGgtlZgYFBiYCABr/0F7PUAo6MZxOaAQ4cSaG0VGBzOwO0GolEDczFGsfx+ek9nZ4HyMvZCmksJzM0tTMWJRuOYm2d6XzQ6j2RS4rgFtLZJxBMCs7PxrBADQEPl8BGJmmruOz8nUVJKT3YyRQ/80PAcfF6Bjg6mZV0cB2ZjCRiCny0hUVMDxGIJzM0z+pY7prm5OMYvspbn4jjTsrZtNTA0LLPbzczMIxBg5Ozrfy8RClNwIxplZXwmHcTwyBymo4AQ/GzTBObmUpibZ7rhdJQRr8g0cOr0PIQQ2eM/9fQ8IhGSFLcbKCmWEBAIhyWKioHYXALRqMjOSXweiEYFdmxnWuX37uFxJiZYbxRPJJGKACMjAvUN0q6RQ3a8CrEYv+9/8tg8WlsYPeho57Hn5hl1a2qiKp3bzRqqTIbXamYmjuiMxFSEUZNodB6plMSDDzFF1OMRiMUkSkslhkaAYIC1XgUFQE+3xI/+G5ieTi6wKx79iQ/B4DzCIYoxTEWAhjper5mZ+WzKaCbDnmvRqMBsLAMJRkA2bGDUcWYmaRu63G9uDjh/QaK7O45o1DHeZ2clZmaBdEoiI5PZOf7xfRIFIaaxTkdhp4pKKmnOC8zOqmPzd0aywbHPl0QiIVFTxTqhqiqn1x7XGsccCmZwcoiOOyklgkFbpXM+hdnZeWzdwu0vTXDfgYF5uyG2RNgWcYlE5jE4RPGNVDqBVMxZTwG/H3N2IdHsDPvpbd3MCNHcPLJtCmKxuH1fUlRGzZcQAufOSxw5wobY9/54Hr09JC6GASQSjMCkUtzHEBQ7mZ0F5ueZdjg1JVFVheycAsC2rRSuSaX5OakU6zrHLgokExJJIRas0VOnM3j+CLBj+zzSGSAaTWBu3jleLAbAVsecmVE94hZ+prpnYjG+3n+B8z03zx53JcWA1yvx+BNs8L1vL8czOxtHbK4As7F5lJfRCePzUbBnKnK5+MXs7Bzm5lhbFo0Ce24Gksl5nDrNnmG5Y5qzid2+vUAiMY+WFoqzDNkCRY89xgjaDdu4z8wM53lqin3hVF2ZmouJCQmPWyAaFdltR0bmMTtLR1dsDhgZBjb3CLgMoKmRPQ7n5oHYbDz7TAyFKMrT1wfMx3mvzM1LCHCNn7CYxqkczrE5ieiMxLlzwObN7DHn8QDJJAloYSFgGBKA44jJh05xXAFSSvz3/0i8/Z1s+ve5vxOYigh86A+ZonXrPobQNTQ0lsZr7mJqx3/+EPjrv5UIBAR+/wMGPvxBgb/9O4k//N8ZXLqkUx41XjSeBtBhmmaLaZpeAG8EcE/uBqZpFtvvAcA7ATxsk7Ys9t/ugc8nMDHFNKzycuB97xZobVn4rG9s4E9TE/9vsvv3AHYNmqRR5DJ4nOMnbOXGzMIUqMW+QTwegV07gOO2itliQgcV5TnS3LYnt79fIpFgoXs6RYLo9bAZbTxOg1EV3weDAjU5Eu2BAEmYQiwmceQYj2EYFCGxTkoYuWO3/376GeDtv8oeWbkQwpaEN2joqu3V+USjnI+jx5gi5POJBXPTUE8RjucOMi0qFqO0+8ioUx+YC3Vcr5epXTt30Ajc0EHRDkV6Uilek4kJEoZ8qGyz0TES3tv2IZvm19JMo8tlAM8e4Fjm5piKqM5ZSu6r0tbcbqZe5p5bPM4UMr+fQia1NUwBbW6+fDx3vdrD/m5V/PySYqAgtPAaADRk5+1apdnZ3FROkkxVE6n2Kyqi1Lvbdfl1y6SBjRvFAoXH7TcC7a08npI1LyhwRDVUiqOqaQsEKNuvrsmFAYqWjI05ab6hEFPTABJPNc8uF9Mjlcw+xy4WENf5ONMNc1s/+HwC3V20zdxusaDGMh9btyzsq7YY1JpS25SX8fqXlDj7l5YufD5kj5f/GxR5UaIyAKXen37GSfsXgqTn5CmnriofhWHVEFzgF1/HdhG5EIIkpqKC89Xd5aSA5qKqkmmFAMekmo+r9D61RqqrSJQUpqZIZFRtZ9Jul1BVyabhuchk2HZnZobnd+99VDa89ZbF6+IArpXpabY3Ub0TDYNtGJSoSS5qagQaG/m8yG07kUrjsqbQx44zzba0lOujuYmpoD6fQEmJgYYGZ96rKnl+JcU8/4oKgVL7GV8QpMopwNTj/NRuv59r22WoXnkL5z8UWmbRQRO0ZRGNSvyfj0l84UsSf/4xNtE7fATo6hT4/KcXPiQ0NDRWxs/+DPDuXxdIpyX+8wcSO3cA3/yGQCgE/PLbJH70X7o2TeOFw7KsFIDfAPDfAI4D+I5lWUdN03y3aZrvtjfrAnDUNM0ToNrjb+UfZ3Q0AynZ1zIQoLrhYsZNPEGRkExOpopavkaOEezx0oBvy6nNkDn7LPZVIqXE84cdA2ax7xtzg8DP/ozIHiMjmdGRSMDuWyYwPAw88xwNiFjM6bG0dbN93BwrwO2mLLdCIEDFvZJiA12dbJLdfwELjE0hOAdSkgwcPUYy6GzAbVTdTpag2b+Li6nyZm6gB7qr05HnLy3hceNxRgHm52koDo+QdKoGsLlQpEWhMMweZufOs9bNEBIV5WwaPDzCyD6bZufNv3197txPgvLAQzxPAGhvE7hpFxUWuztJrE6estUIu5GtG2prXVgP09W50Eibm3OuryKUsTkagPnXe3CQ9YvHT3A+SkuYVnXjNiyIrBYVOVGpwkKnP9R0xFEUzb12QrB2KJ1Z+NxVJPO5AwuFnQIBzllNNX8A1hSdPGXPm71pxiZo09Ns9gtQ4CWZBO64nWtXrYHyMpJUgPVeSkI/HgeOH3f6Wi3m1KiqFNjYLbL7Lwa1nhYTC5macoRdlkL+fqGQQDqllD4Xd57kk7pcjI5RtVPB67XVXXMuQVkpo7JVVfzJVZoEgEDQIaWHDjMyl9v4WAgSIdVT7Mf3Y9GepJt6HUGZigqn3k7B4xFoa2OkOJeAmBtcaGwkuTvfz2eOlDxeS4s9TwWs2SssFNh+A58BAO99IVi/qUSVFkNZmUBdLcVotm3lGIeGnPWRj6kpCgWpcwY4J02NC7fbuWNhywIAePIp9mD7yWMSIyO240sAdXUCu3cJnLCc+VbX9KbdAj0bBfw+Ol9ySTfAbAaVQbEYRkaXt3V0iuMSOHBQ4mN/wd4Rn/8MlZ4eelhmPTCLfVlraGgsD5eL0tCTUxIHDkq8+lV88H/oDwzcsV/iLz8h8eP7gd//Xd5zGhprhWVZPwTww7zXvpDz9+MAOpY7xtlzGXSaJAHx+NINRScnaQxfuuR4UhVEjoHm8ZDMlZYITNsiEunlyw8AUPGtteVyhT0FJQUPOAZrZ6dATTXw4/slJiYlqqooiX7xIhaIk6gdDOFELBY7ft9ZoDAsUVIMHD9Bw2Ysx9ATgpLR1dWMoqXTVFzMxcwMDXW/34mOqahGKsUoEqNoVBQstQ3BTb00/txuZA2qvrOOwltRnqf+jtsXJ7KDgyTZrS3A7bcx1WlwSGTJ02IGtjrD+x+U2LXD7uFW7Lz/8KOMPHm9NE537eTzjU3CJYRgVKy8fPHnWEEBf/K9+6r/Wj4OH0mhpobRyJlZoMWOmKiIrYLfT4cAYDdpdpHU3ngDcOzE5ceNREgWFvvMdIbXtaLcee2hRyh20NYGZOxIXVens7+KohQVAidPc+0rURuXi/0En3gKaGmWWXKaS4BKy2y59xGul56NEmf6uFyXkstfCYoILnYfnz3HaBTbVSxuMIs8snWmT6LvrEBpicRTT7O/Vj5p4DqUCwRZFEJ5a9fnE9i9E7BOOdtmMiQciQQjQlWVC6/zyLDTUHrnDray2LGdKX3PHuAx2loc4YrenstJXj6mpyk8otIys5FWsCecanQOUHo+kWS0rK6WazlHrBAA52RDB9N5p6edPnX7b+c9wn5hy4+ptYUOpv4LEo0NbEdw7jxwy16+X1bKMUxFeI9WVfJZWxDkuo5G+fwoL+e66slvumJjUy/Xak01HTf5UfX2dh7v+PHL971lr8C99wH1DTkONXDdj405EeB8qH6IS0FH0PKQSLBf04c/KvFrbxf48B8A7/kNLvp9t7APhoaGxotDSbHAH32UBdP/968kfvTfEjfeIPAPXxNobADe+naJb/yDRDyuo2ka649dO91wuQRiMRpKSxGY3h6B3h6xqDMhZKcRJpMkekCOlD4Wj7rlQgh6nY8tYhAstp8yIp9+RuLhR2gQ+WyvvJL2jkQuz7gSBg2sHTdefvxEgqlsJSU0thJJHj/X4FD1dfc/yCaym3qpUqbg91FG3OViXZMykgMBpod1dTKSdOo0jauWpoUpeO1tJFL33scIUpEdFZqYuNxjvVRWy223CtTWKrU+yooHA07KlWpbsBjSaf70dC8kCF0mDfsjR0jQz/dfHulZLhmguQmAXBj1ADjGxQzp19zlRVurQE2N02tvMUxFHDn2WIx1fbMxrqOhIQBiYXSntJRrWOQl2gowClZT7UQ+AKalbb+RhqeSds+9Dm43oyhNNvnNNcINg9LqhmBtlCJmuVHcuTn2yModSDrNHnK511el9q4GS6U4CsH019zI0GJLyJVH0BrqWSO1YzuViZdTR8wlOc6LC2s9p6YknnhyodNjbo73XnExLiNnAFBV7agJFoad91WUR/ULU++FQ/lHWHysGXk5oRCCRH1kxHnN5bLTmW0yGY879Db3/gX4vnVqYYsJw6Ca5WJpyrmYmuJcqDW9ayewe5fzfjDoqFsKQafCnfsdpcxc+X0h8tZWDlwuRugTCRLVRGLhWhgdZQ/H3PPKRW/P5feyxwPc/bNUOV0MKwV6NEHLwfETEm//daZB/Mn/4YMlGDTw9a8sPcEaGhovDr/xXoG9NzOl+J/+GfjN9wl87tMCzzwr8ZZfkXjoEZ32qLG+ONNHl7+SoV+KoCUSFOpQjoS2VnpaAWS/M9Jpx2iqrHD2zTWCllrdTz+7fDPT3P2U0VBby9f9fqCw0MDYRaYdbuymsZdvPBmCxpLq35QLv58Rs2BQIBhkb6hUymnsrI4zH2eU5fQZClhcyokKVVcbqK+j+IDfzzTKO/czraq8jJGBujpGVspKBerqxKIG0OZekkQVQQoGVzbuFJ58ipG5U6dhp64yqqgk8aurlv5+v3M/leeeeMpp9Awo0QBGpurqeM6KqKym/EEIGrf5pGFmhh78pXDmDIn2UpDSSf0sKmJkQ0URLo/ykDQfPSpRXJJ3INtYf/4we9spzNptENpaed4Ar/uFC8BNu5iWl4tYjP0CAWSFNHbuYM2PmqbcCFplpVMjqfa/OI7LSFAweHma2mJQNaDAwrneupn31tlzToSvvW3x9Ln8yJ0QXOezs3TeZzJr+35SkTHnXBZG4IVgtEk1K18MhWGRFUXJRTgssms2F489QWGV5bB5EwmdmoPcelG3m0Iz7pw5LClmxHh4ZKHDSeTNVyhEQb38GqzHHnecGkshGiW5NDdwXzXvi2F6mv3v3G5nbZWULl6zlo8DB9kK4LEneP/4fAtJdXGRU1u32O0dnydJzYXLdXndci4Gh5ZfN5qggV+yX/xKBr/1uxI//Rrg7/4WCIdE9iGpwrIaGhovPUqK2Wx1NsYvAcMQ8LiBv/wL4N3vEvjU30n89gckjh3XJE1jfaB6Gc3M0nO7VIqj280vclVY39qyUFABoOESCLDOJtdoKileSNgWQ0/38tGSXIam0rjq64C9N/Pv0TGJ2hr+X1rKvmL5pCbfmMpFOi3x6E8kzp+niqN1ir3YDENg2xZ7f8GUxPY21rB0tDuiELljm40h2xA3F9Go4yV/+hmJe++Ti9bvVFayLuv4Cee9pQQG8uHxkFR2dZIYxWISh553muQuh3vvYyPihjonKgqQPA/bzWxnZzkvbWvsgVpastBQB2isL+UQUO8vh9x1JQRreFpbGNkMBhcanSrisGWzuIykqjS7jnaHiAE872efI2manORrvT0894ICkZUZVwiHkY1mKLXLe++T6O93rnMuARoZcY6r9s/vO7VWGIsQtPJyrqeRUYeoq7TRpfZX6L/AOrILA6y9UwRvMeQ7RABb1TiHEHs8JD/OPgKplMSFAZmN8l5+XNZqLpU+l489N638vFHo7QF27Vj42ugo1/9tty6co5Zm4Od/zl6XeSmO6pynpxn4yEd9PUWWlkNLCyNbqjl1KgUcty7fTvVH6+5a+NmTE0zTXgmqLu3O/XQY5V/T6mqBcOHS9/fJ05cTtJVQvUzkHtA1aDhyVOKvPiERCgFf/ZLApz4t0dzEokB1oTU0NK48qqsE3voW/v2v35Xo7hJ4zasFNvVI/OBHAr/7+xKbeiXe/750VnVKQ+NKoLfHjWgUqKpgE9ylDGbDENjQsTDFKB/pDD26Sh5coayM0v3Lwedj9Kt9CQ/wYimOzzxLj3M8zpQbt1vkjF9m1QnzxToWHXuaRm1dnROtuu9+if23CxQVqSbXApGIxNPPYsmIRijEPnAzMXlZpM4foCT2hQGJ/bfRGB8dW3pMba1Mb5yKcHyroUTbtrIBsvLyB4MCmzZJ/M+9K5O80hIa0PlNyrdsYqTn8SeZrnimT6KoiDU3CisF/js6BMwNC18Twml2vhi6u5Y/43gCC4i7282om2GQVOWjMCxw676lj5c/P3fczt/DI0yhBYDxcYmffs1S5IYKdgDn/4RFozxXOTG/kXRuSqXPKxAOLz2+1WAxgqZw276lHTD5+6vfba2sL1wV8nOKQSXAXMzMsH4z97xTKSAytTAylY/9t63eITAxwRTr1Tg1vF5hEz9HVdLtZqp0PlwugdgcFVpVGmU+oU2nF4/eVVbSMbPc9XW7BZqaJDz2M2xT79LpgqmUzEr8q7VVXEzH0WJobmI9W3ExMB2VOH6cf6fTnPf82zc/1TUXu3cudJ6sRkNwpefDK5agTU1RnfHBh4C3/BJTWRrqBX7nt1ZmtRoaGlcWH/htA1JKTExIvP3XgX/9NvDanwG++z3g1949gy2bgbf+MhXfNDSuFKist3TKWqcp8eP76OFdSkUus4h3XRkwi31B53rEi4sZcZhfwjObu7865oYOwOMmMcwf096bcww05dlfJoLm9QrcsE3JxJMcJeyxuN0Ce26yP9u1vCc8lZYoLgJCi0R/SooFbtvHPloeD0mfMnQWE4Vg42+JIg8jGKvBvfdJjI7KBfLbkcjCOqCloPot5UN52PfcRAM/YQsTrAVu90I1T4DHmZhgZOKFIDcSdvNu4B+/xbVQX+eoeCosZ0Sq946foGHf2sL/LwwwklKbreWhZPpSUaTcj3C7meqmoFKDc50E+WmG5WWLE8vVwuu9nGDl4iePk2znC87kIn+/aJQOid6NXEMN9Us/I1bzDRUOC9xxu8Sjjy18racH2cbYLxbHTvA8lyIry0EIyviXly/OKAYG+Tv7PMqLGpaUCNy5//L9nnmWEa9cgtZlXr4uOb9qH4nKSqCx4fJ5mZlxatXUGPz+pdNEO9oF2lo5aCXnPx1l1kK+qiaQW7t5+fHOnuPzcaUIdy4uTSx/PV5xKY6ZjMT3/0PizW/lQ+UbXwNe82qBQ8+zgLGuViyQrNXQ0Lg6EIK1n//0j+xPcu+P2QTzB/eE0dgIfOAPJN7zGxk88KBcUHysofFSYSWlxXDYQEfH4jVTCot5wJeKWu25Cdi8KWc7Y3kBgtxVr7y7Pj8V9qajwPDwwvuCKoo8njrq8hE0iYceYZ3IVIS1RPmRJIDKg8spkrkMkoOlVPguXmRa29NPAw8+DNTVMtVoKaN3x/al61AWQ1vLwro5gGPJL+pfCw4fBcYu0nPvdtNZVFeXl9q5goWVTDi90xTYqPyFjysXwaBAczNJfqfpNNGVeVHUxaDe2tS7MMXw1GnHIFeoqxOXqUkCTJPLFXRQuPc+iTN9l/fEA0hIcmuVKisF9u1d2SZbLAp26y10ACwXQetoX1jztlwNmhpvxI7eTk4tXw+Yu89KEZVAgB9y4zb+H49LHD/O9NqXAnfuF5dF7lYL5xwW3/+WPZy3PH62Iro7Lw+I1Ndffh89+BBw6Hn+XVa2MAU2F22twF2vWjiGlebdMJiy3bPRSXEMFdiiJ3nP7kDg8h5vCiOjl4sWrYTFxF9y8YqJoEkp8fQzwBe+LJGIA3/2JwJPPiXx4/sE3vJmgY98UJMyDY1rEaqZ4y+8DojOCBQVGTh4CPjoh4CLFwW+8CWJz3we+Km7JO56tUBdrb6XNV4alBSvrH7Ws3H59bYoQcuLoPXawgoqFWyxbRdDrgGhtjtyBBBgf6zlvLNZo2u540t6kxsbmKLY3rb4dtEo1fkW85IDdopjQmI+vng607l+Grq33+ZEapbDAw+xCfdq0dzMOpRcUzccpnrlUpGqhjrAtYyFtGvH8uliN95A4roc6usXv96LNap+oehoY7qaIieqdq+2xmnRsBxCeXVla0mrW0zEAqDgSyi0fK+wtcLjJmnKLU1R416OoNXmqfq1ty1s1p67v0J9vVh1mv1azm37DU4kzzAAr2/5esQrjdWO/eln6DBxah9XeXyDUa/lopcA+ySqa7dUnaB6b3CIKdmLqmcug4sXJQ4+T2XWokIBw5CXpzi6BLYvonYLLN3iYzmsJC7ziiBoR49JfPHLEufPA7/0ZqajbN4ENDaKVUmPamhoXH243SLrpf/rv6LREYkAX/4a8EcfAf7jB8Av/6pEd5fEq+8U2HPz5T2CNDTWgmBQYNfOF3eMxaJw+d/jy/X8W5ag5aY42gZMTw89yUptbykspqCnoOT53W6BxgaJuTmJQEAsSWb8fmDDMkppLhfrvAuWiAbu3inYKy0qEYkslD1fDE2NJIUDg6uTW7/vAfZCyxW7iE7z+i4VVVgsUpiLpciHQr5YzGqRSlERMp8kvFC02sIlySQXi+qdt3GJflBZLEHgDx+RKC3BZVGOtaCoaCHxeCkI2g3bWH+32LwvFqlbCkKIrOqqgtpPOVuUMd/SzOvVaa4cilzNKeYK0gUCwk6Zu/rfYSuRnUSSbQdyyeVqcPQY0y5XQjDoELRHHpUoKVncMRYKOfWba11T0RmS/NkYRVy83ssjaMvh/geB7TfKbD3yaj5/JQfJy5agSSlx4CDwzf9P4thx4E1vAD76Ycr4fubzErEYlsxL1dDQuLahomoVFaxPCwTYfNbvl9jUK/Dd70v89SeBjd0St+wV2Lvnck+phsaVhiEWj6IoUtFQv7KHfFmClvdZAPtL+XyMGAljmZrqZYzW3LS0M32MJDYtQxgMY3mDxOuFXacksZypGomw3mglglZXCxw8JJBOy1XV1NywlZ7x3DqpcBgIFiy9z9VELPbSH3O5usfFsJSITFXl5WmAnjVakg8/SgKajci+BI9m1QpiMSjjXt1ra1WFzK9hE4KR9bPneO6d5tL7vtBTiyckDh9hJPaFkv2XCiuRjT030ZmTTzhW2u/GG3hfroTHn+AzYdtWoKtr6bTS3DWwmgyBXLS2iGz0/uQpidlZYC3dE2TmJVnGC/CyI2hzcxIPPAh89x6JsVHgF39B4E//GPju94Hv/IvEb75P4Ld/UxtqGhovF6i0sDv2C+y30wxGRiTeYkfLv/VPEl/8MlBZIbFtG4v+t26G7m2occVxy97LjZSbdzt90crLxYLm1YuhqRGXefSzWEQk5Px5oKaGa3+5/l7qncXSvnJT2jZvWjl1J51mNKuxcfH3fT4DwUBmRc96fa1AR8fK9+XhI3TO7Nq5OuurtFRgx/aFryWTtrLdMn3mrgaCQTqUXmrkR4FWi3wDtzKvbmbvzWuPVuy9GTniO0tbwaGXKMPJ5aJIRX8/P2ut0UkhBPbtldk2Eeq+jcXkigqQXi/VD9c6R14P1+ZahWeuBLxePi+Weg499Aibzqt7abURtHFb/GW5+lWAjdHVPBcVrrx9Lla6PgqDgxLHTtAhUVvLc11L+9U79q+NnK4GLwuClskwSvbD/6KiVkszcPdrBfbcJPHHfypx92sFXv8LlzfJ09DQeHlBGZLv+jV+QyQSEqfPSLztV/gl8r3vA319En/6Z0BFuUR3N9DVyZYaGzoWrwHS0HihyO8JBaw9ZamwUFwmcKGwWIrj1q0CtTUL+ywthqUkzi/fbuXxBoMCN+1efpuuTrFiz6bV2kNbt6zeCFTIP4+iorUprl3vUGRotVEBNV3epZwDNpZSL10O0ShFW5aLHu+/bXU1cmuByImArRW5Pfz6+yWsU857S9Ve7r2ZSn25Dc7X8nk1NYv3DlxvdHcJdHXKJZ8FlRVAIKdFwGqFUc6dB8pW0YswV8nyscdZm7d7hdTzbAr3Kgmayw1s7Ab8PiqprjXF8UrguiVo09MSzx8GHntC4iePcSLvvBP4wmcFpqZUJ3YDb3y9RCCgyZmGxisRXq/A+3+D9/7O7RJFhcDePQJf+koGsTmmPT5/WOJ732eD1JYWCdNkL6MNHUzB0aRN41rFAoKWYxS5XGKBMt1yWK0B82LR2LAyqVqtx/ql+D73+cSqG12/nOBe5fVWM7zaRshrwQmLypI+HyNEi2kBvNTkDHDO/cVGN0pKqAx65iwN+qXg9wsYwuklthYIwXq/3p7lI+HrheUcNZs3vbDx7du7THbAEth+IxVqV4Ia7mrXe1Ul07D9foGjxySi0dU7jK4UrguCFotJnDvPnPoTlsTzzwPn+1kIvWM78Od/KtDSLHHwkEBri8CDDznTunvX1V/YGhoaVx8VFSJbr/K6/yWQSlKc4Qc/lPjDjwg01Evcex/FFQ4ckPj2d4DRUaCxQaKjwyFtHSs0JtbQWC9kFklxXO3KXKsB82KRnxq3GNaSUqSxdtx6y+JR3cWQjaBdAYK2d48zhpt2r9+ztLoaaGryIKGa+b1ABAJMI25qWtnpIPLq11YLw2BE51ogZ2vFas/16WeourlSzWkuXK6V1VGBtUfQTp9hRO+O29n+we9/cSm2XZ1UqHwxWBeClslIzM8zT1116FZ/x+YY7p6Z4c9UBIhE5jA4lMH4OA2k0TEqs7S2AO3twHvfLdCzkUIBBw9JNDYA8TiFAXbuAG7dd/0taA0NjfVDrkDQFz5L1a5LEwL3/IfEN75Kqd7xcT5vTp8GrJPAqVMSP/gh0H8BqKig5Dh/BNrbKVxwJby+GhpLIofQZA2RVS7BtSjbrRs0QbuiWC05W7jPFRjIVYIQ7KmZSLy444xfYh2kwlIpjvxM/l7rfcY2BNfn94k655UcLrG5tUfwJyYozrJSSrXCao9fWcHvcCEEysok7tgvXpQjNhQSL7qGcl0I2tf/XuLrf+/87zI4aYaL4e1QyPkpLgJqawV6ewTKy0jMmhqBggJnok6fkTjTx+LlH/5I4mdfyyZzn/jL63Mxa2hoXD2oFMaqSuAfv8G/h4clrJPAtq0CwyMSm3qBN72B37Dz8xJ9Z9mw9fQZie/8K59HMgO0tkp0tDukrbXl2pBJ1nh5ItcAWm3dRz7WK8VxNViLaprGlUWwgJEKv3/lbV9pqK4SKC+TeOAhKhEuB3U7rrWfWXmZwB23X583xGqfQftvW/vzqqaGtXmrHcNqiXFBAYNFwSAwPc32CatRmLySWBeC9rZfEXjrWzhRlONd/oqEw35Eo2zJnUpJuN0CQ8MS//EDiXe908DAADu4b94EfORD15L7T0ND4+WAnTsEdu7g3y4Xv1yllHj/70j8748KdLRTZODu1/L5k8lIDI8wTeL0aYknn5b41reZAVBbY0fb2gVaWtgAt66ONTAaLz1M07wLwKcAuAB8xbKsj+e9XwTgmwAawe/AT1iW9fV1H+hLgAUy+2uUUVdqftcSQdO4dlBeJlB+09UexbULt1tg/21yxShXvkT/WrDWxscvNV7ox682gnbfA2zOXVz8wj5nNWNY7fPtyFG2+LhzP9tcXAsCQutC0AxDrLg4R0YlXAbrRP7pn+Po3SjR0AD89N0S3/wGI22lJQJSSp3CqKGhsW6461V83mQyEm9+k0BJCdMc//hPJP7xGwIHDjKC9guvE/B6JLZucVIjZmb43mk72vbkU8CFAWBqirL/9fXgT51AXR2jeJUV/MK6XtNbriZM03QB+CyAOwEMAHjaNM17LMs6lrPZ+wAcsyzrtaZpVgCwTNP8lmVZLzLx6erC7Rbo6ZarrudQBO1aWme6Bk3jekEiIfHQI6pmaZl7aI1E4eWA1RK7G29wmltfKayWGHd1At32uGuqr43I8bqLhDx/WOJr35D45F8b+N49EocPS/zRRw18/z8kyssEfv5/UY0qY3e7//a3mPYohMAv/vx6j1ZDQ0ODMAyRlfZtbQH+wY65hMNOM+B/+XeJ0hKBN74e+IuPZ/DTPyWweRNJ3HveLeDzAs8f5pfBufMS/ReAsTGBM30SDz8CjF0ELo0z/bu8XKKygv2eKiuBygqBinKSt9JS9oIpKLj6XtZrDDsAnLYsqw8ATNP8NoC7AeQSNAkgbJqmABACMAEgtd4DvRKoWUMz9lCILWmuJWiCpnG9wOsV2H7DCuQMjlT7K4ugsaXDSvfzlWzArYjZalNL5+aA+Ti/yyPT1MhYqr3JemHdCVp7G/B7v8OL8qo7gNtvs/sWvdOhuW94vQ/RKJ2ZV7uDuoaGhsZiUF/M7W0C7W187b3vcp5jP/taRsUAKtEaQmB6GviHb0p8+pMGIhHg+/dIfPFzAt/7PlBeJvGedxn453/JIBwCmpoEfvgjiaIiNtW9/0EJmWH0bWKSapNeD1BcIlFS7JC2khKgpERk/y4ML6zzfZm3HKkDcCHn/wEA+R1zPgPgHgBDAMIA3mBZ1oKON4ZhIBy+ygUIK2BDRwoul0A4/MItv61bXrrxLAWXy7WquSwrTaK5yYVwWJctLIbVzqPG8ngp53E1h5mdzSDgT6G42HPdOdOCwRQC/gzC4culPFeax4A/gUDAQDh89cTiX/dzq9/2+cNJxGJAR7sHbncKwQLjqj+L1n3mgkGRze3UxfMaGhovV/RsdJ5v7303H/ShEPDpT/L1m3YDO7bz7717gHiCf2/oECgqBFpbBQ49D9y8m2Tttz+QwR//kUB8Hnjvb0r85/cE7ntA4t/+HXjH2wQeflRibIwpIw88KJFkGS9GRm3F3BgjFH6fpLqUYCqHx0MCWFUFpJKA2zOLkuIMvF7YP1S5dLuZusI6YkYRN/Vec8/wxQaU78d9NYCDAG4H0AbgXtM0H7Esa1ptkMlkEI2uotnOVURTI39f48NEOBxe1Vxu28rf1/r5XC2sdh41lsd6z2M0KjE3D8zMvDhp/6sDjj0avXzsK83j3LzE7CwQjV5z3xGLoreH0dBodB5+n0Qmsz5jL1kmJ/266IOmoaGh8XKDECIrYV2WI/u/dYvz95vf6Pz9yb92vHn//i98/bZ9wI3bgPJygfo6pml0dAg8+RQjb52mwD//i8SuHUBDA/CxP5d40xuA6Czw9W8Ab/hFgZOnJJ47SEJ59JjE1JREXS2QSNBYTiQlEgmnRUomw7SdRFxgU+8VnaIXggEADTn/14ORsly8DcDHLcuSAE6bpnkWQCeAp9ZniBoaGq8UpDMrb3Otoq3VcQS93JEb3RTG6vtJXklogqahoaFxncLnE/D5+Hd9vfOVsnOH8/cbftH5+4//yPn7BjtisXePwDvs137hdQLhcOh69tQ/DaDDNM0WAIMA3gjgzXnb9APYD+AR0zSrAJgA+tZ1lBoaGq8IFIapq3A9IteJuFZUVwEV5S/teNYL10pzcJ3sraGhoaHxsoBlWSkAvwHgvwEcB/Ady7KOmqb5btM0321v9jEAN5mmeRjAfQA+aFnW+NUZsYaGxssZ4bDA/tuvDYN/PdHbI1Bd/co775cSOoKmoaGhofGygWVZPwTww7zXvpDz9xCAV633uDQ0NDQ0NFYLHUHT0NDQ0NDQ0NDQ0NC4RqAJmoaGhoaGhoaGhoaGxjUCIXVnSA0NDQ0NDQ0NDQ0NjWsCOoKmoaGhoaGhoaGhoaFxjUATNA0NDQ0NDQ0NDQ0NjWsEmqBpaGhoaGhoaGhoaGhcI7iqMvumad4F4FMAXAC+YlnWx/PeLwLwTQCN4Fg/YVnW19d9oNcpVjG/JQC+BqANwDyAt1uWdWTdB3odwjTNrwH4GQBjlmX1LPK+AOf+pwDEAPyqZVnPre8or1+sYn47AXwdwDYAH7Us6xPrPMTrGquY318C8EH73xkA77Es69A6DvGqYaXnpoYD0zQbAPwDgGoAGQBfsizrU6ZplgL4ZwDNAM4BeL1lWZP2Ph8G8A4AaQDvtyzrv6/C0K9JmKbpAvAMgEHLsn5Gz+PaYZpmMYCvAOgBIAG8HYAFPY9rgmmavwPgneAcHgbwNgBB6HlcN1y1CJr9IPosgNcA6AbwJtM0u/M2ex+AY5ZlbQZwK4C/Nk3Tu64DvU6xyvn9CICDlmVtAvBW0CjRWB2+AeCuZd5/DYAO++fXAXx+Hcb0csI3sPz8TgB4PwBNzF4YvoHl5/csgH32s+FjAL60HoO62ljlc1PDQQrAByzL6gKwC8D77Pn6EID7LMvqAJuBfwgA7PfeCGAjuP4+Z8+5BvFbYIN1BT2Pa8enAPyXZVmdADaD86nncQ0wTbMO/H690XbgucB50vO4jriaKY47AJy2LKvPsqwEgG8DuDtvGwkgbEcjQqBRllrfYV63WM38doM3GSzLOgGg2TTNqvUd5vUJy7IeBtfjUrgbwD9YliUty3oCQLFpmjXrM7rrHyvNr2VZY5ZlPQ0guX6jevlgFfP7mPKMAngCQP26DOzqYzXPTQ0blmUNq8wAy7KioDFcB87Z39ub/T2An7P/vhvAty3LiluWdRbAaXDOX/EwTbMewE+D0R8FPY9rgGmahQBuAfBVALAsK2FZ1hT0PL4QuAEETNN0g5GzIeh5XFdcTYJWB+BCzv8D9mu5+AyALnBhHAbwW5ZlZdZneNc9VjO/hwC8DgBM09wBoAmvHEPsSmM186+hcT3gHQB+dLUHsU7Q9+0LhGmazQC2AngSQJVlWcMASRyASnszPb9L45MA/gBMFVXQ87g2tAK4CODrpmkeME3zK6ZpFkDP45pgWdYgmJ3SD2AYQMSyrP+Bnsd1xdUkaGKR1/Kbsr0awEEAtQC2APiM7SHRWBmrmd+PAygxTfMggN8EcAA6QvlSYTXzr6FxTcM0zdtAgvbBlbZ9mUDfty8ApmmGAPwbgN+2LGt6mU31/C4C0zRVPeizq9xFz+PicIN1yZ+3LGsrgFnYaXhLQM/jIrD1Ce4G0ALa3wWmab5lmV30PF4BXE2CNgCgIef/ejBSlou3Afh3O03sNFgX0blO47veseL8WpY1bVnW2yzL2gLWoFWAc6zx4rGa9a2hcc3CNM1NYLrV3ZZlXbra41kn6Pt2jTBN0wOSs29ZlvXv9sujKqXb/j1mv67nd3HcDOBnTdM8B6bV3m6a5jeh53GtGAAwYFnWk/b//woSNj2Pa8MdAM5alnXRsqwkgH8HcBP0PK4rriZBexpAh2maLbbwxxsB3JO3TT+A/QBg10aZAPrWdZTXL1acX9M0i3NEV94J4OEVvJ8aq8c9AN5qmqYwTXMXmCIwfLUHpaGxGpim2Qh+Kf+yZVknr/Z41hGr+V7SsGHXh38VwHHLsv4m5617APyK/fevAPh+zutvNE3TZ5pmCyii9NR6jfdahWVZH7Ysq96yrGZwzd1vWdZboOdxTbAsawTABdM0Tful/QCOQc/jWtEPYJdpmkH7Ht8P1pfqeVxHCCmvXhTSNM2fAvOuXQC+ZlnWn5um+W4AsCzrC6Zp1oJqYzVgCPXjlmV98yoN97rDKuZ3NyiRnAYfYu/IEQbQWAamaf4TqCxaDmAUwB8D8ADZuRVgDeVdoMz+2yzLeubqjPb6wyrmtxqUoy4EazZmAHRrB8PqsIr5/QqAnwdw3t4lZVnWjVdhqOuOxZ6bV3dE1y5M09wD4BGwRlzVTn0ErEP7Dtgipx/AL1qWNWHv81FQ+jwFpkS+UuobVwXTNG8F8Hu2zH4Z9DyuCaZpbgEj/17Qof82MBih53ENME3zTwC8AZyXA6ATPwQ9j+uGq0rQNDQ0NDQ0NDQ0NDQ0NBxczRRHDQ0NDQ0NDQ0NDQ0NjRxogqahoaGhoaGhoaGhoXGNQBM0DQ0NDQ0NDQ0NDQ2NawSaoGloaGhoaGhoaGhoaFwj0ARNQ0NDQ0NDQ0NDQ0PjGoEmaBoaGhoaGhoaGhoaGtcINEHT0NDQ0NDQ0NDQ0NC4RqAJmoaGhoaGhoaGhoaGxjWC/x8x+C6cQdZ9TwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 864x288 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "az.plot_trace(idata);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Another common metric to look at is the Gelman-Rubin statistic, or R-hat:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>mean</th>\n",
       "      <th>sd</th>\n",
       "      <th>hdi_3%</th>\n",
       "      <th>hdi_97%</th>\n",
       "      <th>mcse_mean</th>\n",
       "      <th>mcse_sd</th>\n",
       "      <th>ess_bulk</th>\n",
       "      <th>ess_tail</th>\n",
       "      <th>r_hat</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>mu</th>\n",
       "      <td>-0.019</td>\n",
       "      <td>0.096</td>\n",
       "      <td>-0.193</td>\n",
       "      <td>0.163</td>\n",
       "      <td>0.002</td>\n",
       "      <td>0.002</td>\n",
       "      <td>1608.0</td>\n",
       "      <td>1343.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sd</th>\n",
       "      <td>0.967</td>\n",
       "      <td>0.069</td>\n",
       "      <td>0.835</td>\n",
       "      <td>1.089</td>\n",
       "      <td>0.002</td>\n",
       "      <td>0.001</td>\n",
       "      <td>1836.0</td>\n",
       "      <td>1406.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     mean     sd  hdi_3%  hdi_97%  mcse_mean  mcse_sd  ess_bulk  ess_tail  \\\n",
       "mu -0.019  0.096  -0.193    0.163      0.002    0.002    1608.0    1343.0   \n",
       "sd  0.967  0.069   0.835    1.089      0.002    0.001    1836.0    1406.0   \n",
       "\n",
       "    r_hat  \n",
       "mu    1.0  \n",
       "sd    1.0  "
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "az.summary(idata)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "R-hat is also presented as part of the `az.plot_forest`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x388.8 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "az.plot_forest(idata, r_hat=True);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Finally, for a plot of the posterior that is inspired by {cite:p}`kruschke2014doing`, you can use the:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 993.6x331.2 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "az.plot_posterior(idata);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For high-dimensional models it becomes cumbersome to look at the traces for all parameters. When using `NUTS` we can look at the energy plot to assess problems of convergence:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Auto-assigning NUTS sampler...\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (2 chains in 2 jobs)\n",
      "NUTS: [x]\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='4000' class='' max='4000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [4000/4000 00:04<00:00 Sampling 2 chains, 0 divergences]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 2 chains for 1_000 tune and 1_000 draw iterations (2_000 + 2_000 draws total) took 5 seconds.\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "with pm.Model(coords={\"idx\": np.arange(100)}) as model:\n",
    "    x = pm.Normal(\"x\", mu=0, sigma=1, dims=\"idx\")\n",
    "    idata = pm.sample()\n",
    "\n",
    "az.plot_energy(idata);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For more information on sampler stats and the energy plot, see {ref}`sampler_stats`. For more information on identifying sampling problems and what to do about them, see {ref}`diagnosing_with_divergences`."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3.3 Variational inference\n",
    "\n",
    "PyMC supports various Variational Inference techniques. While these methods are much faster, they are often also less accurate and can lead to biased inference. The main entry point is `pymc.fit()`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='10000' class='' max='10000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [10000/10000 00:00<00:00 Average Loss = 142.01]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Finished [100%]: Average Loss = 142\n"
     ]
    }
   ],
   "source": [
    "with pm.Model() as model:\n",
    "    mu = pm.Normal(\"mu\", mu=0, sigma=1)\n",
    "    sd = pm.HalfNormal(\"sd\", sigma=1)\n",
    "    obs = pm.Normal(\"obs\", mu=mu, sigma=sd, observed=rng.standard_normal(100))\n",
    "\n",
    "    approx = pm.fit()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The returned `Approximation` object has various capabilities, like drawing samples from the approximated posterior, which we can analyse like a regular sampling run:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "arviz - WARNING - Shape validation failed: input_shape: (1, 1000), minimum_shape: (chains=2, draws=4)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>mean</th>\n",
       "      <th>sd</th>\n",
       "      <th>hdi_3%</th>\n",
       "      <th>hdi_97%</th>\n",
       "      <th>mcse_mean</th>\n",
       "      <th>mcse_sd</th>\n",
       "      <th>ess_bulk</th>\n",
       "      <th>ess_tail</th>\n",
       "      <th>r_hat</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>mu</th>\n",
       "      <td>-0.023</td>\n",
       "      <td>0.169</td>\n",
       "      <td>-0.338</td>\n",
       "      <td>0.296</td>\n",
       "      <td>0.005</td>\n",
       "      <td>0.004</td>\n",
       "      <td>973.0</td>\n",
       "      <td>880.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sd</th>\n",
       "      <td>0.989</td>\n",
       "      <td>0.158</td>\n",
       "      <td>0.694</td>\n",
       "      <td>1.262</td>\n",
       "      <td>0.005</td>\n",
       "      <td>0.004</td>\n",
       "      <td>972.0</td>\n",
       "      <td>1026.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     mean     sd  hdi_3%  hdi_97%  mcse_mean  mcse_sd  ess_bulk  ess_tail  \\\n",
       "mu -0.023  0.169  -0.338    0.296      0.005    0.004     973.0     880.0   \n",
       "sd  0.989  0.158   0.694    1.262      0.005    0.004     972.0    1026.0   \n",
       "\n",
       "    r_hat  \n",
       "mu    NaN  \n",
       "sd    NaN  "
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idata = approx.sample(1000)\n",
    "az.summary(idata)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The `variational` submodule offers a lot of flexibility in which VI to use and follows an object oriented design. For example, full-rank ADVI estimates a full covariance matrix:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='10000' class='' max='10000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [10000/10000 00:03<00:00 Average Loss = 0.013113]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Finished [100%]: Average Loss = 0.012772\n"
     ]
    }
   ],
   "source": [
    "mu = pm.floatX([0.0, 0.0])\n",
    "cov = pm.floatX([[1, 0.5], [0.5, 1.0]])\n",
    "with pm.Model(coords={\"idx\": np.arange(2)}) as model:\n",
    "    pm.MvNormal(\"x\", mu=mu, cov=cov, dims=\"idx\")\n",
    "    approx = pm.fit(method=\"fullrank_advi\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "An equivalent expression using the object-oriented interface is:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='10000' class='' max='10000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [10000/10000 00:03<00:00 Average Loss = 0.020591]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Finished [100%]: Average Loss = 0.020531\n"
     ]
    }
   ],
   "source": [
    "with pm.Model(coords={\"idx\": np.arange(2)}) as model:\n",
    "    pm.MvNormal(\"x\", mu=mu, cov=cov, dims=\"idx\")\n",
    "    approx = pm.FullRankADVI().fit()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='10000' class='' max='10000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [10000/10000 00:03<00:00 Average Loss = 0.014234]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Finished [100%]: Average Loss = 0.014143\n"
     ]
    }
   ],
   "source": [
    "with pm.Model(coords={\"idx\": np.arange(2)}) as model:\n",
    "    pm.MvNormal(\"x\", mu=mu, cov=cov, dims=\"idx\")\n",
    "    approx = pm.FullRankADVI().fit()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 432x288 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAbgAAAEoCAYAAAAqrOTwAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAABixUlEQVR4nO29e5xU1Zn3+9tV1Y1BuhswCkIM0opb6A6XESM3CbmYprnFGMeoHN9xzPGTxKAgaM7JOznv++a8M3PO8YKgJq+JE4cJQ7zEZCINNJ3bEOQiQuRiN7gBW9FoJCrYzUW6q2qv88fTq/bat6pd3XXZVfV8Px8/0lW7aq/atWv91vOs56IJIcAwDMMw5Uak2ANgGIZhmHzAAscwDMOUJSxwDMMwTFnCAscwDMOUJSxwDMMwTFnCAscwDMOUJbFiDyBsnDx5suB5E4MHD8bZs2cLfdqShq9ZdvD1yh6+ZtlRrOs1bNgwze85tuBCQDQaLfYQSg6+ZtnB1yt7+JplRxivFwscwzAMU5awwDEMwzBlScUJnK7r/1XXdaHr+uPFHgvDMAyTPypK4HRdnwbgTgAHij0WhmEYJr9UjMDpul4HYB2AbwA4WeThMAzDMHmmYgQOwE8APG8Yxh+KPRCGYRgm/1REHpyu63cCuBzAbZmOHTx4cMHDXaPRKGpqagp6zlKHr1l2DOR67T+QwJ49CUydGsOkiRUxZQDgeyxbwni9yv5u1XVdB/DPAK41DKM30/HFSFSsqanBqVOnCn7eUoavWXb093q1dwgsXS4QjwNVVT1YvVJDY4NvXm1ZwfdYdhTreg0bNsz3ubIXOADTAXwSQDtpHQAgCmC2ruvfAnC+YRg9xRocw4SZvfuAeBwwTfr/3n1AY0OxR8UwwagEgfs1gD2Ox/4VwBGQZZfRqmOYSmXKZKCqCn0WHP3NMKVC2QucYRgfAfhIfUzX9TMAThiG0V6MMTFMqdDYoGH1SrLcpkxGxbgnmfKg7AWOYZiB0digsVuSKUkqUuAMw5hT7DEwDMMw+aWS8uAYhmGYCoIFjmEYxof2DoG16wTaOwreJpLJARXpomQYJn+0d4iyCErZfyCh5AACq1f6f55y+czlBgscwzA5w54Ynl4Uws6ePYlAOYDl9JnLDXZRMgyTM/buA3p77aJQqkydGkNVFRCJpM8B9EqGZ8IBW3AMw+SMuloB0bddZZr0N1Ca1sykiTGsXqlldD1yMnx4YYFjGCZndHVr0DQSOU2jv0uZIDmAnAwfXljgGIbJGVMmA9XVlWfNcDJ8OGGBYxgmZ2RrzVR69GGlf/58wwLHMExqoq2rFejq1gY04Qa1Zio9+rDSP38hYIFjmApHTrS9vejbOxOors7/hFvprXgq/fMXAk4TYJgKR060MvpRiMKEu8vow0xh+P2hFCqQ5PPzMwRbcAxT4ahh7qZJ0Y+FmHDzFX1YKq4/jr7MPyxwDFNhOAMb1Ik2F3tw2ZCP6MNScv1x9GV+YYFjmArCz7qxJtrcWVHFskzCmni9vsXElq3AnNnAooW8O1QIWOAYpoIohHVTbBehn+uvmKK7vsXEAw/Tv1/eDQAmi1wBYIFjmAqiENZNPkU0qEg5XX/FFt0tW91/L1pYsNNXLCxwDFNBFCKwIV8iOhCRUkW3txfY3CZy8tmDCu6c2dJys/5m8g8LHMNUGPkObMiXiA7EMpwyGYhG6bVCABtbgblNAxO5bASX3JG8B1doWOAYJmSUQ/mmXItoe4fAe8cFolH6O1vLsLFBw7xmgfUtJHDJ5MBdp9kK7qKFEXZLFhgWOIYJEcXeKwoj6jXRNOBKHVgwL/vgkeYmDZvbRNauU7/3D2u0JmPBAscwISJfARr7DySwfYcInVUYRJzUawIABw8BxmEAMFFfr3kuCLxqawLA3CZKhJjbpAW6DukWHJyoHX5Y4BgmROTDKqBJ+kzBrcJM4uUlHoBbMOQ1kbUyAXIxPrwKWDBfeHTTdtfWjMWs11VVkdAFIdOCgxO1ww0LHMOEiP5YBU4hcSYUOyMIWz0iCL3EaCB7getbTDy8igQlGgVWLBOuwAqneLS2CWxug0uI5TVpbRNo2WBZckKQNeZcEHjV1kwkrH97CVWh3JDlsL9aSrDAMUzIyMYqcFpBN94gsO5pek4mFE+ZrNkiCDe1As1NNPtLN97qx+GypNT3XbokeAmv9g6REjeA/v/gSuDwEdPmGnSKhwZ/a0kKnT6OhFMIaYlpmNtkXxB0dprQNNqvk53FnRacKlS5ckP2x2Llfnn5hQWOYUJKtvtT8TjwR8+EYg3XL4rh+V/FUxGEqrWkaZb4qV0E5Pv29AAPrQQEgrXR2bvPsrIkQgC/Xk/ndVpm8jMC9HxvL42prlYA0GzXYdHCCOrr3ddFCmF7B4m1aVKV/ptvAoYM0VBXK3D4CCBAwSbq+J0W7lNrBO64HZg+DX3vnXnBkU685PjfO+52p6Z7Xw44GjgscAwTQoJObk4r6HOzkbLgACuheOGCaqzfEPe0liIR+k9aRVJs1H0vs8/d19ubeWKeMpneT1pwKuo+mRSp2xZbInbjDcAzz9G4Vj8OAKbLukwnOKp7UggStymTgaXLrfdoVvbf2jsEjvelH8jX7N4D7D8g8OQTCdSP7d9CQ14j9XuMRpFVmkMpFY0OKyxwDBNCgk5uXi600aPcCcWTJsaweqXmspYsFyRs0YZ799FjW7baK3AIYVlWfjQ2aFixTOChR+yWnOx7VlcrcPcy2heLxYB777FcpE5rcstWf+HwEp26WpFyTzr35DKJz5VXAq+9Zp17z54Ezp7t30JDvY5qBOiiBcCIEcFcvZyGMHBY4BgmZGST1Ow10fslFDstH6d7cO8+oLPTvh+3dAnwp1csa0zTSAgzIV2JrW0CGoArxlkCKnPRADrPhk32XnRa39tHoyTS+w/YJ3k/69bpnly6RF4T4SkU0h0qg1GuGAd0dlrHTZ0aw/YdvRkXGvI7UBcJfvuMXukJfmLNaQgDhwWOYUKE06pYtMA/Z2ugezRS8JyJ1NKC6u0lC+rmm8ht6HRh+qFGcd6/3F2SqrXN3mX7ggssEZCuQimo9fXuSX7tOu+9LKd7Ugqxl1C0dwhsarXELRqlvblmJWBl0sQYzp5Nb0XJaFHThGt/Mp3wSTJ9h4VIQyjnQBYWOIbJknxOCHv3WfteQpA7K9t9H6+xzpxB+0mZ3kfux0mRo/0oYMUymqTrakVfgIrwFN4gbWGamzRsahUpF+XiWzRMv0Zgy1bgvEHAth32clpTJgPHjwu0ttHr/Vx32bj09u6zW6Xzm9Xvkq7Z4MGJtFaUM1rUy/3Z20vXc8UygcYGt9gXe5+t3ANZWOAYJgvyPSHU1Qpb/pa63+UU1kwTujrWNT87g9UrvcXS+T5y7233Hms/Slogdy9Dyr24sVXgsVX2zx+kLUxjg4bHVlmi0dkpUlZQLGYFvESj1n6dPOemVoHHVmm2/cR0If3tHSTGG1utFIHVK71dh+mumZfoOKNFNc3u7pULlWQSeOgRwDhiuiI4i73P5iWwagBQqYsdCxzDZEG+V9xd3Ro0jUQuErHcbH7Cmq6xpxqWnkiQa9BZvsorXL+xQUN9vcD+A/a6jXv3WQnTgPeEOO5ye1DKuMu9LV4pGutbTDy40nIVxuP0uSWHj1jiBtD59+6jyEu/oBs1ZUCtaAJYUaC3Lfa+dur3K8+lvp9zgVFdDcVKs++9qZGkpgmsb6H9xzCV+3IKbF2tsEWcplvAlYJrkwWOYbIg3ytuOWmmi8ZThTVdY081LD0SoQTvRELYyldNv0Zg+HCyYG5bnCnAQbjC/1/aJfDUGss6am6yJ1hv3wE8/Syd02uPSiZtq0j3bDwOvPSy/blIJNg1p4ATgZ4e93tLq1jdg1y7jup0qmXBAHsuXtAFhrx+K5bZXZh+VVTytc8WRICcn4HuM5FxAed1PWTeYJhggWOYLBhoZYtMk46fmy1dVKX6nn5h6YePRLHljwmb+zMeB7Zuo7+93I1OAairFbjiCuDQIevc+w9Y/47HKZFaCrRpAm8esz+vTpheCeFybJL33rM/t2B+sOofdy8TNstP4owCde+VkYv24VWA6MvFk4nl6gJDJoOnE6f6eg0L5wucOAHs3OVdRSXT55BRqEGLQzs/VxBLzP4ZvCNOnXgtuFjgGKYMCLLi9oquAxBo0vFys/lFVTonsqVLvPeWnlqTcFlKKs5JW+Ll5vNC5p3JSMSn1gibq1KiTpjZWL+aRtexuSnzJO90paoIAZw+LbB2HZ2/tc2y8qwCzlZyu5y8VcvdNMkNu3efe1EgcX4v997jH0nphVOkvRYgma5Bf1zpQRdwxd47DAoLHMPkGL/oOsAKPAg66TgtshEjaMKRLjXnRNbV7Z6gHlxpItE3UWoaMGsmMHw4sGGj3d348m7gT68I3HyTSFUAcRYullw6BnjnXauY8vxmS3jbOwRGXWxFY/YH9bXRKDBzOo05E9La9aukAsiUB5FypaqoBZxllKe8jqtXAo8+LnCwz4KNx2lPzUsEvL4X6QIOWhlFFWnnfmAmZMK7TK7PRoCCLOCKvXcYFBY4hskxftF1nZ1WhKRp0iTU3pF+ksgUBOC02KzAEZpI/+v3Tby4nVyHAE3g06+hROzmJnKB7d9vuRKTSSr1Jffopl1j7eOpn+mtt4FZM4Bhw+21HdNZfKZpn6R//rTwtAo1jSxVGT96xTikks9b24Rv4WentXvhhW4Xp/yMfkSjVgHn3/8hhl7Fz9nYoGHcOEvgAOu6OlG/t2iUAn7aO+i5oJVRYjErwEYKbRD8E95zSyFy9AYKCxzD5Bh1clKj6/buQypCEgBe2gWsfjzzZCebdF4xjsLuVSvQy2IDyEXqLJUl6eq2aj/q48iScyLf/8Vt9BkWLQDeeNPaczNN2r8bNIgCS+T7HTrkDuxQeWmXSE3U23Z4HxOL2SufqIEPvb19+2NCpLonHDlKSeVd3ZrN2h02zFvg0jHtGqvDgqzdqUY+OnP4/Fym0sKRKQotG+jfzU3ehZ0B+3fY2KDh3nsEWjYBF14A3HpL8D04v4T3SoQFjmHyhKbR6r2+niYY6TaSAicTmtP1KFMtko2t9pB5aQU2NkRcr/MTN9UKlJGC6fbW5HlOnADGXmoPKgHsfdwy7dMB9Pq77haYNcN9rHSfTr8GeORRivikWpWWNaRWOentha010OWXC1upr7+ZDBw9ar9m6aiqokXH9h1935NJ+3BqDz1nDl860ZGLmmTSikoUsBex3r2H9vIAe54eIK8BcDQG3HpLsM8AlM7+WCFwp9YzDDMgZJUMtRqH6jaSyFw3tQjx2nUC7R004claiTInyytwwjjifqy1TbjELRIBrp0F3HQjsOZn1AJHimsQDhlkVVVVuZ87ecJ7nw4Ahg51P2aawIvb7fluAL1++HASGfl+8Tjlwi1dYh3jx9Gj1nU3TeC55+nzOs+jomnAl68DPns1CWsySa81TUCLWOfcuAmp76WxQevLw7O7R9XvTo08raqyvuPmJkpSv3qqlU4Rj9utus1tIlUIWz7vLG+WDrIeNdz5Dc03ub9SKHsLTtf17wG4AYAOoAfASwC+ZxhGe1EHxpQtXito6TaSyKhAWadQNh3t7RV9fczstRKlEDqtkQ0bqXmpOok5p7ORI4FrZ1ahujpua6WTDe+/TxbFTTcCr+yzqu6bJrB9p/c+HQB0d3u/n3ytk5Mn3K7LffvJ8nGK26TPAPscFqVKIkFj9Qt00TTg8nrgd7+3Fhvy8epqoLEhij+9kky9l19AiTuSVX6X9p50qsV3x+3Uksdp9QpBlvr0axxj9f+YnpTC/hiQ/2Txshc4AHMA/AjAbtB98n8D+J2u6xMMwzhRzIEx5YlfkrQadDCv2R6csXYdiZu0+pxCpF9B7/Xr9cCZM9bjyaQ9vL+9Q0CAziEjHD/8EPjlf8QDW2sqcswA/f/pZ92CYZoUWj9yhIa23whb7ls6cXGOp6qKglacj795DDj2lv3xqiqyvA60+58jFgMGeVicEiGAI69bf0vXpwzMeOPNSErgAHtAiZyY62qFbV+0t5e6I6hlup55Dvjho96dAp5aI1Il0dRxDBtuj+ScGyA9otQoRB3Mshc4wzCa1L91Xb8NQBeAmQBaijIopuxxrqCdogdYZa5k2ad0oe0HD8EWvafy8m6yBlTLQY3WVIsKq8j9KtO0og6PH7dPtk6L0U9MhpxPe0kXXWRP7vZizBhgzCVWkjkATBgPLJgHtP3W+zXqmDTNyivzimOcNBG49FIKoHnkUfvrgoi8aZLr92tfrcav18ddASXpIkWFAIzD9nM5o0fle+zdZ28HJNsFqfmEYQ/DHwiFKDRd9gLnQQ1o7/FksQfClB/pXC5q+P7dy6xIPJnA6yztlA09PcCzz7v3wtR/R6PK/pIG3L+cHpetbbq6Nfz4SX8F8MtrGzbMbXH6EY0CX7+RBCQWo88ai5G4Bf3sQtDrNYjUZ1IZNIja9KxdJ5BM0ufRNGDEiOBRlfv3A1/7KvDYKi1VTUTilxuoju8zjcCBV5EqUaYGejiLAKhuamf6Q7oJX7Uis0kiDwuFCIapRIFbDWAfgJ1FHgcTQgayJxDU5eJs+Cn3dqitjD28PxazRCkTx465rTSJpgHDhgIffGj9ffgI0NpG4rh7D3DllfYZW/Zmk+f2G8MJD0e/n7V00YVkVSWTdMz4K4FPfYoCX7IR9g0brY4DkybaozvnzKb/O6uPeInbyJFUEFoD7SXKMbx5DPjfv3kGy+4GNrdZgR5qJwKnBaeKrcx5i0bteWjrW0w8tJKiMwG69oePAPct15DNTpvTitQ04duPLqzCV4hk8YoSOF3XVwKYBWCWYRieP6fBgwcjKnfMC0Q0GkVNTU1Bz1nq5OOa7T+QwNLlZ1IC9eQTgzFpYvCfyMGD5xCP96SiHg8erMb0aee5jquqOgsgrvxdhZqawQCAc+fOgWKhSAC++pUqDBmi4V//rTfQGNRCwfI9pBvygw+tYIqqKjpvTw+NQwh7jUkAGH8lRV20d2RfjqS2BujyCDD5i0Nk0rle0yH71WkaMHx4DIAVYjrovPNQUzMIgwcnsGhBL/70SgKdb3ibWx98QHuUUnBV4r3Ai9ujiMeTKTfav62N4NvfPA9PPgE88NDHqWsTiQCfuzaKrduStmhXIYBz5wah840YWjb04le/NlPiJtnYCtzw1U+k7rX9BxLYsyeBqVNjvvefvNfU2qLqPTfQe7k/9Oc3OX1afmtYVozA6br+CICbAXzeMIxOv+POnj1buEH1UVNTg1OnThX8vKVM0GuWzSp2+w57p+jtO86ifmzwVeWECcIWlHHeeT04dcqdhDX2UjPl7quqAr74hUTqs6jvIZ/7+dPBo0N6HTp46820Qj54yBK3qVcBd9yuAUjgF7/0f69JE00893zgU9vwErdsGT0aeOcd/+cjEbJw3ztuz59o+805jB7VE6iGplrpPxKxW54CQP3YJF7Zi1S6xs6Xknhl7xksXUJ7bepYamuTngE4H57owZ3f6vEdSzJp3Wv23MeeVAk0wG7pTJjgds9GIsCECb04dSo+4Hu5PxRrHhs2bJjvcxUhcLqurwaJ2xzDMF4r9niYwpBtlNZA9wQaGzQsXWI175SV6J35UjIfTtMo7F51KW1uE7jmaqsEVmensAVjqEQi5ALzS2SORoHRo2ATqWiUXHhyX+nyy4Cjr7tfO3Qo8Pbb6ZOkJ02kPaLtOzIHlmTDhPF07X/+jP8xUig+Nxv4+GP7c3NmZ94nk8hoU5mUP2G83d35yj46x2+U4Jd4nPYtVUvNNClP0GtP8I9b3e5MVUz92iKZJvBCCxVaBuyJ4I0NGuY3C7zQYlmyaldyTvYmyl7gdF3/IYDbAFwP4KSu6yP7njptGMbpog2MyTvZRmll2wpncxuF5Kvh/l3dGoQQvtVJZKdngCamZ54Drp1FE5haPV72VmvZ5D53JAJcNhaIVQML59FjXpVLTJNer0ZRNoyHrcGoXxL0Rx/BV1gl+w+4K5sMFBlwsmVrZnESwi48gJWPd/y4VdVECkAsRqLkDMlX3XxODh1yu24BEtE/vWK3ALu6SXR+vd5+7J/7rFC5IPGyygDYEsOlIErXozxHby8VfB43TkAfZ+8dqKYSlEox5HxT9gIH4K6+///e8fgPAPyPwg6FKST9WcUGSZB1tjLZpLQyyXROZzpAMklBJiNGaK7q8ZvbBAzDfX7TtPK3jh6lSL+FCwTWt7gjKA8fpklV7i85E6OdoihFoFgkEsGjKb2QLW/kHh1An6lxAvBRl9vSVK9XIgG8+27mc8ycgVRAkBoNSd+1lqpCAgHbfpuuA0uX2CuLyKhaZ8sj4wg1qJW5jHJ8Qlj7ll5teJwu+VJI9s4nZS9whmFU5tKlQnH+wPOxim1tszfTVFuZeOW7PbTShADlZRlHgM802BOU128Abvm6cFWPF8gcPRmPA//vAwKXXOJvoSycTwElv/yPzEUZiyluAAlxf8VNooobQO+XruKJyvsfZD5m8S10H0mRk2kW8v6S339drcAjj1rf6dGj9veRXoB9+5EqUC0LaN+/XENzk7DdR84ee4mEuw1PvhOnS42yFzimcvD7gedyFdveQSW0VJytTJz5bn6dpSWmSa7KFcsoZFyK4eEj1h6R+jqvSh9vHiPLcPyV7qjEffuB+rFmv3uzFZL+VFvxeo+gSd0A9bYbPBg49Jr1Gk0DLh4JvPsX+7GzZ9n3TGUbn/0HrP1WWblm7z4N068R1K5IqUua6d5QG7JK8QKovNfefcK2CFLvu3RdxysVFjimbOhvZYRsIi1lIWXJ+PFut5N6bLrO0uoknEySoM1tIheXzBWLRilX66OTwNBh6V1oMirTCQngAM2iEOF0o0ajVMrMKewyUtUpdBcMBz5Ucvc+fYl3Xzddj+Hdv1gn0jRqpyPxExQAti4Q0ag13rpaAUDzvTdM0+rH58xrk50MvPZ+AXfe3+49VOGmki05Fjim5FErOmS75zbQSEs/cZPHqpObSlUVRVCqtR1bNlLEnOpmFMIKlT8TIIMlaGuYUuX6RSROLyoBMDOmk9vwO/cIW9CHnwX3UZclfprmHUxTXQ38/d8NwtVXJfDs8xRRKoQ9MtZPUNSeb+o4TJOS3OvrhauhqRO/ICXLQnTjVd8yXyWwSgUWOKak8dqgz6ZsUSarz71pn92+nnRFRiLALV8HTp+hehVz+1bfp8+YqeAQtW6k+tpsGDLE7dZU389Z0zEXLsFCEYnQddvsaB3zmkHd0r/4BXdUpRfJpBU96vX5pVU+aWIM9WMj6OoW+Mm/uCNjVUF5ebcV5ShgFz4VuV9722Kyxn7+tMCxt2kPzllppb+pKrJTQb5SBMJeIUWFBY4paZwCpW66ByFd1KOXdSfPWVdLeyyyWLLf2FShGTJEw7e/aT+2uW/Clit5dcK9dia1mwkaIAFQ4eUxY7wnTCfDhgE1NUAyQcLb1ZVZ8IopiqZJgiBgr4v5/vvAAw9n/16Z2H8gge07BE6fFjYrrK5WoL3DWuTMmY1U8IcQlJdXXw98fNYdtencN9u1GzZXpmnSZ1sw3+2CDEo+UwRKLZCFBY4paXKRnO03GTjF0925mqpJrFgmUF+vud5DuihlzUSneMrjV6+kfbf1jt4W739IeW7pWsJ4ccwn6dopTCdOeNeRTMdll7mjAQtJpty8XHDoEOUkatoZJBJuS9o4Aqx+3Jrkm5vswq9akfL7Byi9YPEtlmip9xcALFxALYdyIUr5ShEIss8dJguPBY4pafK5WnWKpwZ3dYxkkhKnIxGRqkohV7UvbrP204SwujJ3dgpXNfnDR9wCdOiQ1Vg0LBRT3AqJmlztFDjZwVxO8gJWwrVz7++KK6jCieqWltTVWsnoskVOsQUhE5kWlGGz8DQRpl9PCDh58mTBLwjXosyempoa7Hyp2yZs/Vk5un+Q9klGfU/Aio7zs6giEWDRAncgBGBV00gm7a/32zPLB84Iwkrj/PPtDWMBf7drJOJd5WTMGIpmtUpnWRbZ1m3CVvlk/HigsxOu+0vtBhCJUIoI5dWlJwzWkd8Yampq8KMnuvHkT0XK1XrnN7LbMugPw4YN8z0BW3BMSULV0tXgEisnKZuVYyaXi9PVc+MNAn/cCowaBVcnZskLLd6Py7JLzucKmZ924mThzpUPRo4ERlzUvxJh0Si5CZ2BKH5rfPm9OC24Y8foHlu0wGmVCfzkX+zHqmKn3l9qrUxZ5isT/bWOci2K6dyfYauByQLHlCR79iRswrRFKWibTWh0piATtaHk6dMi1dhT1hd0kkms0jlMChHAUeoOm/feC9601IkQwO//0L/XOpu9JpPAiBEkFmvXUdj/3n3pr6+6D9sfIehPnqdfc918EbYamCxwTEkydWoMVVXUgkTTqPq9M9LN2UDSayXr94P0aiiZ6afq1/E6E+mK/ZYaNTVAWL3t/bWUYzGq+fjSLmDbDqsDQF2twNLlak6k/yJF04B5zZnvu3T0RxT9muvmkzDVwGSBY0qSSRNjWLrEKqz7O6WUtqa5XT7p3DteP0hZ9d8mPj7zgtx3e+nl/lsX5UJYxa2/yDY09fUaVj8uUiL5udl0j8XjImVRGUe8cw3VIBKVoIW9B1Jb1am1ZbCGygoWOKZoDHRvQG1No04qzlwjwNu9Q/UCvc9fVytcE5XaBUASiQCzZtBezJtvCk+BK2QQCdM/Ro4E/vpX7+4Kc5soBUQWRAZoH2/xLcIVZevs+XbfvdkVHlDJRW3V5iYNm1otF6VTZMsdFjimKOQinFi6bJzNJBvGWwLml5NWVytw9zL47k10dWvQNEvkxl8JfPICYPtOS6xk08qt24AXtwtcVm8f39ChwMRG4NZbKGVA7t8x4SISoWRxWbpLvZemX0P3RWen27/5m99alXPqagUOH7GiZAEKaKmv73/of2ub6Ne+soqsXxmWPbFCkzkulWHygLdFlR3kstHwlYVWzyyAKn/85F9IQNs7rNlK1gY0TWDnLiuKLR4H1j0tsHaddfyUyZTbFInQf8Zha/9FIivEy38ffd3eQLSriypVAFTLkAknaok05/7ZsOH0/8NH3K97/wNykR86RMWx12+gx2fNoPtx+w647kEv2jvs9558bFOrNR5noYBsaGygUP1KEzeALTimSOQqnNgqPmvawvOdq97WNmFrMuoUnO07gO07hM2aXLpEuJpvapplCUYi7kLKTgGUFVC27ejf52OKRzRKLr32DoGWjd7HJJPu6irneqxcx0yWl58nw1nmTVqSTHawBccUBWl93fkNzZVc3R/mNmkpiwuwNvalcDrffWid/W/TdFuTtMdnP666mpJy7/yGhvnz0o9J5k/t31/YXDcmO+T+qhPpFdi7L7vvr6eHXhuJZF68+XkypEtdsnMXMlqCjBu24JiikWnDPJsgFDXCTOatqa+7YpwVxl9VBYy5FNj/qr3BpbNm5JTJ9iRfTQOu1GlfBQBa26zeZJoGXPclyrOS1eqlO9RZcJcJF17luACr8v+Uye4Ao8svJ0F65x1L/OT3vf8A3UezZlguTj/8PBmNDRrmNYtUpwm1WSoTHBY4JpSorptoFJjfLFy1/JxYgulOEVj9uCVg995Dj6uTlppDp+J0Oe4/AHznHnpQnfBiMeDCT1qPscVWWnh9XzKfsrOTSpz99X16XNOAN96whPHTlwBvvW2/V0yTApJME9iwUWDFMuFZiitd6L/aaULm3clO3+yuDAbXonTAtSjDwdp1IlXTDqCJhDock8hlumaq9bd3H1LvpWnArJnU3qS3l451/gQ+ezVwx+20D/LjJ4PfDhdeSNF4TLjJpmLMpInusmBBEvqdx0SjwA8fzd4VL+/j06cFnnnOKtCdC7d+rinWPMa1KJmSwdmdW4ZJy2aSQSoxeDVBlb22hKCAknQdn1/eDfzpFYGbb8ouh+3DD92PXTqG9vuy6enG5Jds1vTH3rL/fd559nw4P6ZeZfWIA+jec+ZeApnD9+lxge/cY92HPT2ZfwdhKMocBljgmNDgJUzGEWDjJqtIMUWzmbjhqwnUj7W/VrXYnE1Q5zeLVJSljICULiYpfCrJJPDMc8DNNwFPP2svvHv1VPvkJfFa1R97C3iTnSRZ8YlPUNPQMPDRR/a/z50L9rrde+x/RyL20l4ygMTqSOAvRF5BLhtbgSvGmZ5J5GFrWVNMWOCYoiPF6b3jwiVM9y+nFAB1s/2FFqC17Yyr9YgqjO6Ne2oqGo+TSN18E3Wx3rjJf0UvBLVWmTUDeHG7JYzOySsdvAOQPWERt4Eg7xXAut/UguB+6SwA/R42t1Hn8uYmLZWTqVqOySTl4AkhXCLmV5S5Eq06FjimqDiDSeTKVo0ok5vt6uQgI9xk6xH5XG8vCaPXxr2a1/bMc/RaZx6bROa7bWy1t7jhkluVg99eXTZu60ULKIJ39ePWPRqJuC04ea/L6v+yQPKmVoHHVlEqzeY2gY2t9BrV8+AUSK/IzEq16ljgmKKirjYBmhBGjLC7XWSkWWsbVXdIJu31JtW6kULQ340NEVdIdVe3BtO0IiD9eorJ4skCQMsGtsIqEU0DLh4JvHfcKuE16TPApZcCJ064k7u9ME26h2RRZukSn3oVBTEB7kXY3n32RZcsFHD/8ggaGzTMbbL2qNX+h2qunVdk5tp1wtOqK3dY4Jii4lxtpksFGDlCw733UI7bzBmDUT+WfFlq3chIhP72csdQC51gSJHdrLg1vfbqAFqNXzzSv0ccU1rI3MZ3/2I9JgTwagfw5etoXzgoGtz3+B23a8rizX78lMl0fmnBAcCmVqC5SaSq9shUmPp6f5ejM8c0bI1ICwULHFNUgrQAWd9iptrixGLAvGa7ysg9CjVfSO3TtXolHSdz4dIh25tIK1CO7fhxgV+v935NMgkc/2v/+8Ex4cLPbZ1MAg+tBL70pWDvoy7Ygra5kcWRH31c4OAh67xeFlc2nQXC1oi0UHAenAPOg8s/2Wx2t3cIfOce4aoH6cwFUt+ztc2qABGJUFmt944LvLDe/h6AW/Dk4873X99i4oGH/cepacCIEdwPrhJw7s1FIsAFF1g5kDLSds5sq1UO4F9lxwv3nln+8t5yFXzCeXBMxRN0s1uNrPSqLqIGmag/UAC2KuwAJclu2Oh+D+mycT4OuKPPWjal/1xCsLiFjU+NBv7yXu4Dg5yLoi99ETh+HPjgfQB9i685s9G3RyZSASUyWEnTRN8CKn3+WyEsrnIPPmGBYwqKXwizivzR9fZahXDlRr9cPcsgE+cPtLnJPqGZJvDzZ7xdk05xc1JXK7C+xd1RgCkNYjEqjP3SrmBBIUFRrX9No27yqUWYAG68gdrreKUEyP8HCfTItrlpfwjyeyxlWOCYvODn9giy2a2G/ctJ5NqZ1DhUPi+DTB5cadqaQgrQ+6o5Q/3xwpsm8MijVtsTpvR48xjlis2YnvnYMWOAt94Kdq9M/Axw8JAVru9c/GzbAbz7rr2Xm6bZ003CEuhR7sEnLHBMzknn9gjienFWbxeCCtfeeou1qq2piWHnS+6mkM1NGvRxAg+u9J+sgtYizGThMeEnmQReDGC9jbmEBC4IB14l61DmuD30iH0R1NtjD1SZMQ2Ydg1SnoBolIoRhMEVWO7BJ9wPjsk5mbp1p+swLC2/m2+ytzARwv0+alNITQPmN9N7d3Wn/5FGo8C4y7L8UExZIyvVBEHuAb/7F2qddN+91r0aiVDXAfW9du4il6Xqosx0jw4Ury7hfpRzx2+24Jic01+3h9Pyu/VmqjgiA0LUdiHTp9nPE42Se7K9Q9jSBiAA0/EbHz0aeCNDj7bzz6cyXUxl4CVukQjwmUay2JzPC0H1SPfuE7jpRrtXwOnSTiYt13khXIHlHjiSDSxwTM7pr9vDafmdPgMsnE+Tgz7OikqrqgKefCKBxgYNS5dQhOPhw8D6Ftl7i8KqZZuRdU/bz9PV5Z/rJBk1EjjyetYfnSkzxl4KtHfY99mGDrWKMMfj9iAm0+xbbAkrMIqCnzQ0N8EW7bt2nciLW7DcA0eygQWOyQteEWCZ8m2cFpksy1VVRRUh1B/tnj0JnD0r8Mij9r0yWYT2h48Cty3WsHYdUlVOJM4K8V4c7cz6IzMlTm0t0N1t/R2JkCV/yaestjmxGC2QVNR7KxqlyM2ubs0z502mneTTwir3wJFsYIFjCkLQH3VzE1lsGpBqb9Pb63bxTJ0awy//o8czEET23mps8C59FASuf1AZDBkCnD5N//74Y7q3EgmyvC6r17DuaetGmDyRalF6VbSR6SwrltG+3N599H+vezzfFla5B45kAwtckVCtmenTij2a/JPpR+0UwBtvsG/KDzmfOm1/+CGwYB4waWIMv/oP73NFIvZV6+WXA4cO5emDMSWNFDeArP+FC2hxtbEVMA7bVzn7X6ValF4l2a6eahVQzrSQG8gedVDRKkQOXSnAAlcEnJP5k0/Ym3eWGkF+eFMmW3sT0aj7R63mvsXjwJGj1sa9ptmbjh45Cgw6rwcfnnCH/GsaMHM60Nkp0NpGFUw4SZvJhLpXRtG5bhNeRj9ObBS2Du2RiFVAOV3VfvV3IveIg1pYHDjSP1jgioDTmtmzp3QFLlc/PLXljWkCp07bLThVxOJx4J/+n3O+Cdgvbs9t5QqmvInFgIYJdF91dgpMmaylLCz13hs0iO7TVzvsr1fTWfysM6/akrctDv474cCR/sF5cEVA/ggiEWs/qVTJlPOmHpdMWl25ncdRyxvrb6dLUX0uXdV+pxgGZeTI7F/DlAcNE6g34MFDwAMPk8gtXWJ15K6qAr6yiETJOOL2CKg5mrT/pWHRAmBuk3WMbNib7neSLnfNOWdUcuBINpTuzFrCODeBJ02MIWgR7rC1nU+3YlXHWVcrUrUkvY6rqxWp3DUvkZLluoYPp+oRavRkkMokGihQxQ8ulFy5HHNUMNmyFZgyWYOZFKkFmQb6vZ484X69l+C0tpHLfcNGgZtvok7casUd5/GZPCEcONI/KkbgdF2/C8D9AC4G0AFgmWEYLxZrPP3ZBA6jH975wwOAh1aa2KiE+C9dQt2HTZNWoEuX+B1HlpxX7pppAsOGA/ctp2X1oPOq8fyvzuHCC6iixFFHztqXrwPGXkrvtX0H1SVkGC+caSMnTwBvvClSBQJME1i/ATBNkYqWlK2YFs53N+lV95OTSeDpZ6zFlaYB85rdv9sgLkgOHMmeihA4Xde/DmA1gLsAbOv7f6uu6xMMwwhYga74hMkP77TQ1Pwe+eMG6IfesslumR0+Aqx+3H5cPE7iRvsSGkaPMrHmZ1T2SKIp537goXPo7QUMH+tt7KWUf7R0ub3wMlM5VFfT/ZctR153J/lLl7i81xYtpOIDh49Q/0HAEi1XLVVYoigDWZyki6wMm9emlAgscLqun2cYxrk0z48yDOPd3Awr5ywHsMYwjCf7/r5b1/W5AL4N4HvFG1Z2hCWB08+SlAKsCo4QVGVE9sSqqqIfvHqc020JAIsWRgCYqaLJkQitlNs7BJ5aI9DbQ+/jJW7RKHXg3tzGBZMrmbo6qwlpLpH3nOom39Qq8NgqudjTsGIZtVmSUcPTryEPRHOTd26cnwsyjF6bUiIbC26frut/ZxjGLucTuq7/HYBHAAwfyGB0XT8PwEW5tKp0Xa8GcBWAhxxP/QbAjFydpxCExQ/vZ0mqAgzYV73zmoGRI6zuxpvbRKpiybxmWg3TxrtAYwMJ2crV9hJIL24TeO75YKK1fgO9t0xNGGji9nmDgHNsCZYUuRI3Z1BTNEreBLXcm9qAF6AFWn29wOY22n/btsPqV+iHlwsyTF6bUiQbgTsMYJuu6w8C+O+GYcR1Xb8IwE8ALACwMgfjmQ/gOQDRHLyX5JN973fc8fhxAF9yHjx48GBEo7k8fWai0ShqamoCHTt9WvETw2fOSGDNz84gkaAQ65kzBqOmJobp0yinb8+eBOqGanjgoXOpY7721fMxaaJ1u8njZATpnd86g3hcIBYDvrKQHksk7Er2wvpg4qZ2GLjh+irsejmBt94emMKxuJUXn/ykhg8+sN8TfsFKzsduuL4KCxdUY9PmMykXaCwGXHTRIDz3C5G6pw8eTKCqykQyGYdpkrv093+IYfq0wYHH6fdbCyPZzGOFIvCVMgxjka7rfw8Ssvm6rj8F4PsATgK41jCMnXkaY65w3rqegXVnz54tzGgUampqcCpoGGUIqB9rT1StH/txKgq0fixSOX2jR3kfYz8ubkuO7e0FfvHLOKqqaKWshmSfzqK6fyRCE8IXv5BAdbU7aIWpbJziBgCjRwGfmw289Tbw9tvA23+2XIyAFQz1xS8kUD82iUcf0bC5TaSKgT/w0Lk+r0RP6vho1LIAhQB+vT6OL36hO7D3Jd1vLWwUax4bNmyY73NZLQUMw/hXXdf3AtgJErq9AGal25sDAF3X/xDwFBdmM56AfAAgCcCZ6XQR3FZd2TOQDWuvwJJ00PsLm+vRC1nlRHUDxeOUe3TyBHDoNeD9D/zPowGIOMRQCCr31dkp8PSzmT9b0CaoTPny53eoM8C1M4H/87saBg8ejO07zqKuVlA/N9j30OR+G4C+RZpICZl6L+k68Npr9hzQbNyMHD3Zf7ISOF3XFwH4MYB3AWwABWk8q+v6nYZh/DXNS2cDMAAczHCK87IZTxAMw+jVdf1PAK4D8AvlqesA/DKX5wp7tNNANqwzvdbrs2dzvtGj3KH8+jjay2jvELjrbuGf3A2aMNS+XUIgK6ttxAjOhWPovtm6Ddi5S+CnP0EqElfew81N3ve6WopOjaA0TeBvJgOdncUPDqtEsomi/DcAt4H23FYYhnFG1/W1AH4G4KCu698xDMNvrdwOwDAM4+sZznEjgADr7axZCWCtrusvA9gO4FsARgF4Ilcn6K94tHcIHDx4DhMm+Fs4uWIgG9bpXpspqlK+5qk1Anfc7hbG79wjXNUhNM3e9VjLcGn2H0j/fCZY3CoTWXzAuXhKJKiEXk+v/R6WQSNyT+zee0Qqd1NW6nHWRh0yJBzBYZVINhbcFwDMNQzjN/IBwzD26Lo+BcA/Afh3+IvTLgBzA5xDdkrJKYZhPKvr+gWgPcOLQYI7zzCMnKX/9kc8LGHoKUgIcNCqI9m8FggWVWmawO49wP4DwvY5W9vc4gbQKriulm6Hvfu8S3N94hPU4oRhck0sRiX0zp7ttd33b75pBTrF48BDjwBC2PsNyoIGgPVbCeJmDLsHqBTJRuAaDcPocj5oGEYPgPt0Xf9Vmtc+AGBjgHNsApCXssOGYfwIwI/y8d5A/3LUCh0C7JVmENTyTJei4PfZ5WueWiOwe4/VKUDuyfmVPtI0cvGsfhwATLzns1PK4sYMFK8UkkgEuPceWULPuu/ragUeesR+rJ/bPBIB5s/zz3tzwvlu+SGbKEqXuDme35HmudcBvO73vHLcxwBKsqhSf3LUpDBId0chfPPOlWSQPm1eFUvWrhPKYxqWLhHYshWYM9tdQ++O28lykz/eulqR2teIRumzJxL2aDOAKpA8vCr7djccMMJkg6wyot4zqntc3vdr15G1JtE069513m+mSXmfQUWK893yQzgTKkqUbKOdpCgePFiNCRN6i7Jiy1QiyLmqBNwNHQGytnp6yA35zrsmvv1Nq1GFKv51tSSEapmuhQtoMjh4SOBFR5ub/vRyY3Fj/HAufiIR4L57gZd2WS2WTBM4dEhg/wF7G6spk5EqCK5pVvfup9YIvLzbfo5sg0nCUqWo3GCBKzKNDRqmTzsPp04Vp6ZUOsvTrxWO12Oy3qMVvWgXOYDKZz21xlrxRiI0GRw5AujjBE515/OTMgwhU1IiERKpRQsj6OoWeHG7tZf24nZg1+4zWL3SnhaweiXtG2sgcWts0DBntl3grp0J3HpLcOtNfW/eg8stLHCMr+Xpt6r0esy5Mv75M8C1s6yyW84izJoGXHIJcOwY9eE66Oj/5kUQ12N1NZCII1UJvj+k6zfHlC6aRveH7FrhDPOXxZmlu9JZfksia5y2tlHAFPUyFKnu85mq3vgFk3C+W+5hgWN88VtVej123ZcEfvNb67WyCWRjg2UJquIUiwUPl5W94LbvzOyylKWTLr+czjm0Dni1PTvBYnErP2T7pLpa4RI3AKl95JZNVBxcCO99cS+vhtqNXgjg5d3A3n0ilULAxZOLBwsckxavVaXXY2MvtVc+U5s6OtMFJFUB775rZwLjx2vYtiO4WdbdBUyfTlFsL27jUl2VSCRCVUQWzrMKBnznHiCZpL5u9y8XfV0rSHhWP24FPs1rpvqp9WPtobpqQre8x/fusyw4STwOPLgSAKi+quw0wMEkhSWS+RCmkpARku0d2fn4pkwGBg0iaysapb0NgEoYAVRPb+pVVsJ2MgnEqu3vMe4ye0K33Ky/9RYtNbEE5a/vU3Hm79wj0N6R1UdhSpCRI4Hx48lSkzlo0SiwdImWErF1T1s5l0IADzwMrG+hFZcqPLJLgFocPB3SvelEujrjcep/2N4hUou9SCRYMEl/f48MwRYck8IvatKZN6d271afUzfgAeDuZSKVAvHYKg133K7Z0gUWzgOOHrXSJCY0AK+/gdRextVTgTtutzbr5zULrG/JLkoymRx4lRMmHAwfDpzwyJsEqBLNe+8Bh5S93ESCKo/I++ftt92ve+gRoL5e2OqhCgFs3AR87av2KEqA7ndZsUTWlbxtMd37m9sEWjbSeziroxw6RNHHq1dqtuLJ6dyT7M4cOCxwTAqn+2Rzm0BrmxVQsnSJ3Y0DWBXWpRhubuvbBxOWw1JuyN+/POLav6uvtwum7BNXVUXiBiCVc9fcpGFTq/DMO2LKG00D/vZrGvbus0cspkMI6gt4xTgT9fUa3v6z+xjTtERq+jUilSqQSAAPPPQxltxFN5q8R9MVNWhs0DC3SaT25dSGqIDlkrxtcbBgEnZnDhwWOCaF88crO2/LH9iWrdbf6qa6mi6gRkqqyHWnc//O+beaLydXxMkkuXS+9EVr9cxUFrJ0254/Zfc606RiAQvmexfrliLV3iHw/of259o7TNy9jP5tLeTSW2DW/azZGp7K13NuXGFhgWNSOKMmAbtFNWc2ufu8LDh5vFpJXRKNAnObgpUr2twm8OEJSrxVV7+mCVuUporctxvzaeDTl1AOE4tgeTFzOnD4SP8iXIXoa6nkuDfHj6c9OgCpNBYncj9OXcgF2TeTx923PJKy6rLNb+PcuIHDAsfY8LOo/FyKzv25mdPdArNwfuYfZ3uHwN3LRKCO3U5GjwJuvZkSb1vbBKJRq/TX0KH++zaSQdVAj8fkxuSfcZdZ+66A/8Lkxe19qSX9KMMmF1hXjBN4eBW9nlzu5FaUDXfl3u+VV9LesFo0WS7k1DJzfm2jvPbN+uta5Ny4gcECxwAInnzq/tt6vfxhy9p+AP3Ig1hve/dZq+Vs+fM7FBEXidjdUJoGfPRR5tezuBWP198gAZowPn0wkAzqmPQZYF8/g4YWLYykFmh1tVYjXqcrUFp1soQeYC3kaF9M+O6L8b5ZuGCBY3ISraX+sGVi9vjxWsrSU4szq+dVN+9jMcstGYkAV+q0D3goQJUTwO2+8koK50LM4cI06b9Mka4y/eTSS4GLRgC//Z37e9Q0um9uvgk4chSpDhZqF23ZZZ6sMJF2X00toWeJlEi7L8b7ZuGCBY7JyarTGWa9cxdw6y30nJd4ukVVw2OrNNse3KHXci9GXu8XiQAXXcRNT8OMXJis30D3y/3LKejJGVGZTALPPU/tbuR+cZD+hUEjGzPti/G+WbhggWNysupsbNBseWrJJPWBG3WxV3FmgafWWLUp7ZMM7Yls3yFyJm41NcCpU97PyYLPLG7hRtaGBOh+6ep2FzmW90s8TgEpftGO/bnfvdpG+cH7ZuGBBY7JyapTVlqIxUjcZAfvWMyKuFQ36aW4aRr9d/q0wNp1lrtSWoO54MwZ/+dkc1UmvGiO29E06T46fMT/NQJuoVnfYmLLVmDc5UBzEx0TpCGpWiycOhBYJb6YcMMCxwDo/6pThvbLXB9NAy64AHj/fcuSk/3e5CZ9b6/dOksmqcWOpolUtfdcFjxO914sbuFHg707hKaRBffhCbeJL5uQNjsCm9a3mHjgYfq3tPoGDSKhywTds9b9/PAqqn7C7sfww8sQpt/Ile0LLZYbMpkkcQOswAANVtTa6dN2cXP+Ox4H/vVnbuH57NXApWPy/YmYYhONAp8abf2tae7WR5EIWfkXDHc/vmghlYVzis+Wre5zqQUK0jFlspUuAFjVT5jwwxYc029a24Rv5RJZyf3oUeCFFumOFLaJwgvTtARSZdzllGguV+FMeZJMUtqHxOve0q+w3OjrN9hTQ0aO8HY5zpntDkhRO16oyP22mTMSOHuW/n3zTcAzz9H9WV3N0ZGlAgsc0y/aOwQ2tVoTUDQKzJhO0Y8yKVYfBxiGPYm3v67HI0fR1yHcxJqfUbcAJpzEYv3PaQzCgnnWv2fOALbvoH/7BYzIvbfRo4F3FPGcMN6936xG9z61hjZv5f28Ypm7Uapf/igTDljgmLT4/YBlVXWA3EgL51NZIme3gY2t9hW27KNlJtXucZkZd7n17ws+CZw4aeVQZUJ2amYGTs0Q4PRp+3d3/vn2QJ58iNuYMcDgwcCFF1DFGlWINI2sugXz3CKj7r05ebWd7m/nfe1Xb7WrW8NtizNXLWHCAwsc4yti6X7AzlBrWa3EGawyv1ng1+vt5xMCuHYWdeiW5ZCuuAL4m8nArpeBo6+7x3jkKPC/fmzaGpem6w9XVQVMu4YsSha33HHqtP3v4cOB4cO8v7OBUlsDdPeldxw7RkJmaMCu3QJzm+wNdA8eAl7vdAd/eO29SdSu8xL1vvartyrhqiXhhwWuwkknYul+wF6pBV5CecU49znlpKS6fABKCO/p8R7ny7sp7UDFLwJS0yjRt6ubunkz+ePEicy1PiXZVpFxLkzUBqInPc7pJTLOvbcvXwf8/g/+e2nqfT1zxmCcPXvW1wXJVUvCDwtchZNOxDL9gFVrzU8ou7qpNJKTrduAXbut42TB23RkMzkaR4Ah57O4hYlsvj9NI1e0umcmH9c0YNsOt3ta09z3KOWr0R7cnNn09w3Xp983k/d1TU0Mp075p89w1ZLwwwJX4aQTsWx+wH5CKZO2vawt53FVVfC14AB6ny9+wb9tjkQIYMPG3ObSMYUhogHQ6F64+iq7wGkaMPEztHfmJW433+R9jy5aGMGihdbf6XI+VS/E9GmZx8tVS8INC1yFE8TVGOQHrAqlplHeG0Ah2yuWCTz4sNuOU8O0Gxs0LF1C1Uz+opTNkp0JNI1cmosWRvCJT5h4wbGv54QTuEuTW24Ghgyx3NatbZbbWgigvcNuCcq0EyGA538FXDur/wnYTi/Ek08kUD+2/5+FKT6c6M2gsUFL1YGUP/Inf0r/lyW4grzH0iV9ibkmsPpxq3zXooUR3L8Crhy4ZBLo7KRzLLmHot1UcfvydZbARSIUPQcAQ87PycdmCsilY9zfvxdS3GQi9eqVGj57tVWuSwYlRSK0QJrYaN+b27uP7ru164LfuxJZscQ06f979mQfDtrfczP5gS04xsZAIsO6ujUIIWyTTWMD/ei7ujXcd6+wVYA3TeChR5B6jYqmAW//2Qo5TySouzhACbe2Y5FdygFTeG66kQogOyNqVTQNOHhI4Kk1VuTi6pUa7rhdw/4DlmW1dAnda3W1Ao88as/FzNSQNB11tcKWGlA3NDtLkNMGwgcLHGNjIJFhXm7K9g7g7mUCiQQlAN97D/CnVywXYrp9skFV9r9PnCDRdL5GYGB93sZdBhzJQ5g7Q0QiJEhzmygv0i+YSAjgxW3W3729VpcJr73gteuAZJK+dE0D5jXTefwakmZKyu7q1qBpIuUx6PooewuQ0wbCBQscY2MgkWFyH+3hVZab8pqrrQktHqe8tJnTKQpO4iVys2a6Hxs2nMZUXe0ORpGT0mVj7WIVjQIXj7SXf5KMHAn8l8Xk+rzrbsFBKRkYOhTo7rZcgiqy2ajX3qe615rNIkQI+16uUyycizFZYNlrgba+xUzdl7EYMK9ZuDoJyHtLvnbq1BiADKG9acbDaQPFhwWOcTGQyDCnm/L9D+3PS2GLRoHp1wBd3e5uzpEIPffIo9Zjmkalv6SIPrjSPVmaJongd68nd9iHJ4CdL3mLGwB88fO0P9jeIfCZxsxdpSudjz6y/h1xFEEWgiJc/3MLXBbavGYrFSSb4B/ZNcAPv8WYV9DUw6ss8Y3HgfUt5PJW3YjO95s0MebbR1BFtQz9etAxxYEFjskpzlXswnnA4cPeLklZycSJaVo1LSVCkEVYXy9SIurFy7tpgnpsFU0027b7mwzrngZ+/58m3n+foy6zxVnhHyABfGyVhp8/LbBtB31n1dWWZTVlMllPqgBqGjB6lPciRLXg/PBajDkf83RrC283YraLO6/O9Go5L6a4sMAxOcW5Cibcs2GmwsuHDLLk1GN6eoB1T4s00x0Rj1N4uT4u894cd/LOHXNm0/f/z//oTjWRf997D1nXb7xJ+WxCAMf/ajW4lVG4gNuC629hY+l67O21EsWFyI0bkffdwg0LHJNz5Cq4vUPgqTXebikpOrJB5YTxdhfh++97h5WrQQjpOHmCLL6w7KtdeCFNss7KHMXky9cBv/1d/4NzVEaPJjGSxYudVW7UQCNpXb/aTq5sGSmrRkM6BWggEYpei65cuRF53y3csMCVOGFt1yEnpHSFjiMRYOpVwB2304S4vsXEz5+x3FX9EScpmMOHu2sZDiTSMt35grynV4+7YqJpwNhLNdx6s7AVsO4v77wD/ORfqCO7FB/Zpqa3B7ZAo9Y2CvBQixrLzhAy0tbZlmaglpLT9ZgrK4vLdYUbFrgSJmx5N6rYygkp3eQfjZJbi5J6BRYtjKC+nlb7mepSerH4FitRuLPTnVsXjQCJHO+1DRsWvNhwmBCCuqsPGZK7LEJ1X6uz079NjQa7MMh8Nrmgqa93Ny0Ns6XE5brCCwtcCVMI/39QC9EptkuX0P/9On5rGkVKrn4ciMcFolErdHv6NVSM2cnll1OHcCc1Q4Dp06mlzpzZFJSwYZP7uKDilo2lV1tTmgIHAE8/C1x0UbAPGlQGZcHjp9a4Hwf63I+gsH2ZrL1lK7kphaBgH7/7uLmJXquPsxZF/VnQtXcIbG4TEIArVYApL1jgSph8r2rdeyf+IucU265uWqG3tgls3GRvghmJ0HiHDbdeY5pW6PZnr3a/v6ZR3zEvTp+xCjC/vBuIxUTappvymvmRjRszVsK/INMMHmRz9dX2tjN+yILHc2YL2/GRCOU/7txF3zNdY/uFlveF8z5WF0/RKLCplRK8++O1kPe0/P43tYq09zVT2pTwz5PJt/+/tU249k78zuEltjLYQB9nYsMm4IILZO6b5UbcoLyddHFdMJzeQ67qNY0CNMZd7j3JOgUpU0fpdOI2eSLwaod32sCQvm7WKvlo9OmFrMmZjfiOHJm7KNE33nCPR9eBQ4fsjx85SiKyaGEEL+0yU5a4EMC5Hus79ULdj1VJ12U7W6/F3n32+yOR4MjHcoYFrsTJp//fKWXyby+3pRTb1jZ7GH97h+hzQ5JoTb+GHu/sFKkox0jEHro9t4nKOrW2CZw8QZZec5OWckvli2gU+NY3NXR22hODJU5x6y8yZD0ow4dTjllQcbt0DHDRRcDuABZXUN7/wPp3NEqdHerrNdd+6e49wP4DlEB96y0adu22LK/envSfQaYZOMmmy3YmnLl4sVi49vOY3FLWAqfr+nAAPwBwHYAxAD4AsAHA9w3D+DDdaxkSmo2tlotybpOWMbBlcxtN3i0bBVYsE321Aa0K7Q+vouLKMt9JWmgL5gMjR2g4fZpSC4YOpc7LySRNakPOFzh9hsYhV+DRKPCpTwHHjqX/HNEouce6u4F9HtVKYlFgxEiyIACkgl0efVzg4CH38QMlG3HTtOz2+GbPAi65BK7IyFxFkE4YD9yzxLKy7r1H4LnngY+6gK4uu2Ula0i2tglsagX2v2ofz+hRwDvvWmXW/KqWDDTM37kgu/cekfIoLL6F9+DKmbIWOACjAIwG8F0AB/v+/SMATwP4chHHVRI0Nmh4bJV9MpGdt9XAFoAmkOPHRSqoJJkkMVuxTKTymlRRky1PpNXW3ESW04+fdI8jmaQJW6YAzJ4FjBhRhS9+IYHNbcJT4NQJPZlEqrKGyvDhJB6JJIW5v/OOVb4JIHdbLvFycWYiG1GKRoFp1wAPrszuHCoXjyRrzc/Ne8EFlqi0d1D0o2rBOffRGhvI8k4m7VGtQgCfm0093GRx7tOnqR+gl3D1N8zfHfxk9ygsviXY+zClSVkLnGEY7QBuUB46quv6/QA26LpeaxhGd5GGljdynRfnnFice21qe5Jo1C4spklVKySyioRp0rHOfKen1qSfzaVwjh+v4a5vDcapvkKBLRutZPKIBsycCbz9NvCmInxeOXVeYtPbCzy1RmDQIPskX1sDdHvUJfxswOALr/N9+TrAOJzZAg2CpgEzpgPGEW9RDCqU1YPS5x++tAupZG51j1Yy6mLg1pvt9568Z9SIWk2jlA5ZnNtaxNhz6QaKM/hpy1auPFJJlLXA+VALoAfA2WIPJNcUIi/O6S6iCcSqxP/pS4C33rbqEArQ5CVLc2nKcJz5Tn5BJCrOfZfGBg0336QkK2vAdoe15iz5JfFyFQpB+0hOQfASNyC4uHkhXbDZcukYckOqIi4EsG07WbjpokRlcr3fuP/85/QCJ8P4AXI7OnnnXatmqFqia+kSEl+KgLS+x7377HVFgwaPBF3IORdkc2ZTxZww5tMxuaeiBE7X9aEA/ieAJw3D8HTCDB48GFG5k10gotEoampqBvw+Bw+eQzzeA9Mk6+PgwWpMn3ZeDkZoZ/o0+g8ABg9OYM3PzqRWxcfeoonjKwursHBBNQBgc9sZqxyTaYmdOr79BxJ4/ldn0p63sSGC7973CUyaGEtds/0HEnjmOet16uSsacC0a6I47zwN/7kleHfmXFc78cNP3D75SeCDD7yfA8jie9PD6pPX9Ybrq/Dhhyb+sMV+Ak0DpkyK4OXd/grmNSbZCgcgAZ05YzD27EkgmbR6Fo24SMNf37dKbx08WI3Bg2NYuvxMSkyefOJ8fO2r1Cl76tQYJk2Mue4f6eKcOWMwamq8p6f9BxKO9x2MSRO9j50+DXjyiYTtnI2N9r/9yNXvslII4/UqSYHTdf0fAfxDhsM+bxjGFuU15wNoAfAOaE/Ok7NnC2/Y1dTUpNxtA2HCBJFarcZiwIQJvTh1qh8lQbKgfixVUH9qjUhZPokEMHx4AvVjabaULUTqaq39DwA477ye1Pi277DcXdLKGHc5JSObJk1kS+4SqB/7MU6dsq7Z9h3+LVgiEaB+bBJPP2s9pmlAXZ299UvYaLoOePYXdB01DbjsMnuCezr9FQIYe2kcw4dr+M8/2l2C1dXAhyfc4ib3Nv1C+J3ls+rHfoyzZ4XNMvq726zvVt5723f02tyB23ecxW2LNdSPBYA4Tp2y7h95f6jnUH8SXlVy1PetH+tvxdWPheuc6t9+5Op3WSkU63oNG+aTIIsSFTgAqwD8e4Zj3pL/0HV9CABZ22KBYRjn8jSuopKvvLhM7qDGBg133E7h4XIv7vhx6uZtL7yrATBtDVGlK8sZCj7qYoqyW7iAXjW3r+JEe4dAa5tAd/cZJBImun12UaNRSjp+5jm7VScEcOoUnStdV3HpSi2UNady+gywfCnQsgk4cgR4PYtcO3ldly4Rqead0Shw/SIKynlopfsD3XozcO0sDZvbBF5osX/mcZcBX73eXRvS616rr3feJ8KVG+mF/f5w41clh92MTCY0v75a5YKu6zUAWtE3TxqGkXaJcfLkyYJfkDCvFL36XfkJpxQfdZ/FefzadQJP/lSk9uOunUlBI3KSkq9XrYmqKqpADyBjncpIBFi0gARx7z4qAOzVfXrRQkpLOHhIBO5QkGukVfW52VYlFsDKC1QTm52v0+Ddk02+fupVtN8khWn6tFrsfKnb1bl88kTg8Uettg3tHQJP/Fjgnb8AX/4SCV/Q798Lv7Y5QUq/qRabvGciEeDOb2ipx/NZ4DjMv8swUkQLzvcGKFULLhB94vYbUGDJ9QDO73NVAsAJwzCyyEiqPGS7Gxn9lmnzXw0J94tSmzLZqh4vBNWcfHG7jJzTMHKE5gopj8cpfH/ECC1tlZJIBLjvXspjI4SrwaY8Tusby/HjWV6UHCFz8wSoC7aK06KULsRp11CVl7lNFMH4wnrrmKFDKQ9Nvp4Sru2BRnv3uYNvvvVNdzj+44/aFyS5quIfNAgqiMXGBY6ZIJS1wAG4CkBfOAQOO577PIAthRpIWNva+KG2u5F5a0HcQV5pBGpuU2ODhnnNQqlHaBdP+fqeHvv7fngCmNvk7gjtxdp1AnW1IhUyr2kkKI0TgPf+SqL2QgtZizfeMLAk6P6+trGB6jKm+yxS2OY3Wy5alc1tlvjIPUXVteoUpLpa+8Lhlq/bc9q8LK262mBuxiAELQ6uHtfbS6H9S5e43aQMk4myFri+IJOi/xrC1NYmk9DK5987LlLtbjTNv06gE2cbFNktQP3czU203+MlnvL1zioiFwy3Es9pDy6GN95IuHLdqEWLW3FMEzjQbreOentpjy5bgYpEgImNwJhLqbL96setHK+ggvdRV3pxi0aBhfOBK8b5V/hobqLQe7UepDqGaNQuSF3dGjRNpI6hVjneydCPPIpUBRs1wASgBUR/qogELQ7uzJvzskYZJghlLXBhISxt7TMJrbNqu8yWqKoKJm4S6T5au87KkVM/t1MEvSbPe5Zotk4Gc5s05b011NSc77mnlA6v47wek5/baw9Mischg9x7anCFbP3ilUcHWPl4kQhQleGXt3A+fWb6PuwLBOf35MzzUy1jFVmHUV5Tec3VxUY8DmzYZG9QevgIcN9y7zJtgP9emNf+rYyYTCeQ8v5QI3M5KZvpDyxwBSAszRozCa36PEDBGiNGZO8WCuLekiLY3iEbZNpLKC1dQq45r55d7R0CBw+ew4QJtOfm11hTRbopUxVPIuSik6WiolEqBD1sOFllK1enrwjiLFNG1yjSJ3buQBhNAz7TCLz6Kl1ftQtBLAZ8/W/tKREySMbr+3J+T+o51DEHqZTf3iGwsdV6XTRK5bhsn7nv/87xbG4TaG2D74LJa/y3LQ62d+aMzOVoSaY/sMAVgLC0tc8ktM7nvfZ9VLzcnc5V+403yEak6Vf4atSgLMosrR19nNWmZ30LpRkIswdVfYEps2cJzwapKkKQYANW08yubioVpe7ttHdQkeV0wSya5i5Tpk7w85vt4fZyL+3Vdnfko6YB8+dRSoQTv+9LfRzCP5oSoDFKLz0FAFm5ijJwR4q+pgHzmmlB8dIuy3pu7rOeneMRSL9gGujCLiy/G6Z0YYErEGGI+so0YWQzofi5O52rdrnHtf+AlfMmUY9Viy9rmmVpyaLN9fUCnZ0CD660hEPWjZwzG9jxkrtAsFcbnsYGLSWSpmmveygfT1c+S4bg33G7/Kx2F6y0d2IxqxOCtETXt7jfr7oaGHI+bJ8rkQB+/rTA+PGaK7hCLipuvIGubdLhmlTdlZpm379zRrBubKVuAKoISWvZWWQbcN8fsp+fFHyngOVCoJy/m1IL1mKKCwtchZFJaIMKcWubd/qAumpXrbIgK3w5mdfV2vuxCUHWRstGuwtODUCYPg2ufDZNo2Rv1YL8Xz82ba1kenosYUonbrGYVUvTskbt4qBadLIh6MJ5lLbQ3iGwuU3YokMjEeBKnVyTzs9lT5+w77319qbPg5PdG7zcwmoEazJpdV73EjOv+8ByLdv7+S1d4l8EQLpxAf+GuUEIU7AWUxqwwDFZ095Bydjqvo3aHsUdRemebNUivO7wb6viiZyoBdx1JmWH63icoizVPTaA/q1akO+8a7r6pAE0zr37tLTBKo0TqNO3swKLX+Fp0wReew3o7LQfqwZOmCaNyw/nwmDvPiuy0EvbpCWVLqReRrBmm1PmtJyk9S2/A79Iz1yKUliCtZjSgQWOyRq5lwP07SE12ycttfSSu3xTsElPNh2VQmkcsSIAIxFg7pdj2NhKPknTpHD6FcuAhx6xhFC666RQ/HGr9+eRVmMk4m/BfdTlbY3axUHYwtu9LNeLL05f99GJc+/NOcaIBkCzXKGZ9k374zb0+r6C7q/lUpTCEqzFlA4scEzWeAWj+OG1hxK0Oop0b0m3n6YB468EFswDzp2LQtMSqT27rm6NCvnWkytQAPj4Y+C3v7Msm8/Ndne6lq7F1Y/7i1s0Sl0S1KARtdbm+hYTW7aS63L1SrKQNjrawjhD+6+dSYneyaR9z1GiacDVU+3pGY0NGlYsE6kAnOpqt7XW3iEy5qmpbsYgOW1+0ZBBhDKXosRBJ0y2sMAxWRNkokkXYakmRXtNen6V4wHg0GvA653Ad+/TUsWEnRVT7lsewfoW05Y+cKVOkYqzZ1G/uqoYUFVNYtnVrSEed5tTslbmi9vde2TrN8hKKFYvupd3A99dIXDf8gjmNtk/v1ryCqD6m7feQp9v6zZhS9YGSLy8cg9Vy9Z57bNxB2ZzrJ9IBXFt5lqUwhCsxZQOLHBlRqGizNJFtwFIG2Epo/28qqP41SF0uv26PhIebXishOgtDnfk/gPWfpcaXfl6J3DjDcLWiFUy5tO01+V0JarjcLo9t2ylQs7O6+MlEvKYulq7wE2aCHz7m/6uRr9JPog7UH5Px48HrzE5UJFiUWKKBQtcGVGsKDPneec2eU+0zkney0JxTtIyyk/tUqBpQN1Qqw2PV8WUObP9u1arwSQylUFGA6ruwmNvkbWncvnlwBtvWMEvTrfnnNnuayOFwa+Kx6KFEbzzromfP0Pv+5oR9MrbyeQOTFepJpPrkEWKKUVY4MqIQkaZqdVKtmyFbU9Ng79LK5Ml4G/paNDHWb3kHnjoHEaPose9XxMBYGLDJsA47F92S01l0DRgwXzgL3+xl9tSS2y98YYlsjfeAHz7mxGMHmXtwVmdDLxLVd222HufbMgQq05k0O/Oaa1nur5Od+/CBdQyaKDWPuemMWGFBa6MKFSUmXMvTSKLJs9t0jC3yXuiDZKH5zdJd3VrEEKkKnF41bZUX7NoYQSLFloT8BtvClvftWtnUgsaNZVBVu1QS0TdeINVRksiBFl+184SqfM48VpwUNCM28rO9rtr7xC2Wp2PrbJEzu/6Os/hLIHWHzg3jQkzLHBlRKGizNQkb4lXx4H+Wo9+k7Q6QavFgtXXSOtILeKsujLVavrjx2tYtJBy7qQFJse+eiVS0Zhvve1dlFmI9JaWl2j5WdnZfnetbVa9y3ic/s70mnzcH5ybxoQZFrgyI997Jc4kb8Cy3LLpONAf1Al65ozBqB/7sWdwixWlaa8EMmUyUpGX0Si1BFrfYiWjO8uJyULCTqRrM5Ol5S0omQtQB8F5lYNe9VzfH5ybxoQZFjgmK5xJ3tfOJEuoEPsvqphNmhjDzpfs7rHmJitKE/BOypaW2cZWoGUDsMGnnJhfnUxnf7QgVpMqKLmyouY2adjY6m4nVGg4N40JMyxwTFY4V+y33pJ7q80raMEqkExW2JNPJFzuMQFrbLJupJeVRCItbJGTAFl1Mp/O2eonlx2lc2FFNTZ4F0RWUa/j9Gmup3MGR1gyYYUFjkkRJBou3yt2v6aaagmueBzYsyfhElt9HD2vweqE7TVG9XWyMLFsI/PIoyR+QUXN75oVIrIwXSFj53V88okE6sfmZRgME1pY4BgA2UXD5XPF7hW0cPy4u2v31Kkx1I+Np3LkTp6Q4pS5l50q0sePC6zfYPVIk8gcvNsWZ98yqFCRhenO47yOe/awwDGVRyTzIUwl4B3SXnikdSUDV6ZMdlfOnzmD9uAkm9uonFY2429sIPGa26SlEp4lQQJIAP9rlutrKSND2zvsVyLdeZzXcepUXssylQff9QyA8ETD+blANykBFYtvsawhtfwXEFyc1POpPdIiEeCSS4DzB1NDz3SWV5CO2wO9lumstHTncV7HSRNjOHWq/+MoJTjxnJFoIkjPjgri5MmTBb8gNTU1OBWC2SfME4NzbPKaOctPzWvOPoFZfQ9nZf/vrrBXJ3GOBfDej8zVtVy7TuDJn1oBMXd+w+42DTIWIDz3WL7xqh7T3+tfKdcsVxTreg0bNsz3C2YLjkkR5mg4Z0CFjArMRdCL+h4vbhM4qBQ+lsWTJX7lt7zeMxfXMpM1qCa4yxzASARYsUy4hLkS4MRzRoUFjikJ0kUFDkRMVAvotsXU+FQVOGfx5EJNoEGKNDvHJRPck0ng4VX2pPVKISyudiYcsMAxJUE+ogL9rR7v4slAYSbQoFaic1xqt+9MZcTKFU48Z1RY4JiSwCksFBXoUUcrC/ysHr/iyUBhJtD+WImNDVa3b9nKp1KtlzC72pnCwgLHlAT5iArsr9WT7wm0v1Zium7fDFOJcBSlg0qOoiwlcnXNZAkwafUMJOoul+Q6opXvsezha5YdHEXJMCGjv1ZPvlMq2M3GMAOHBa5MCXNOW9jIVkxyWYqLvyeGyR8scGUId1km8iUeuUoVqKTviYWcKQYscGVIuSa7ZtP+JZ/ikatUgXL9npxUkpAz4YIFrgwpx2TXbNu/5FM8cpUqUI7fkxeVIuRM+GCBK0PKMdk120TvfItHrpqWltv35EWlCDkTPljgypRyi8LLNtG7VMSj3L4nL0rlu2DKD86Dc1ApeXCluOlv34Orxc6XunP2GUrxemQD53RlD1+z7OA8OCYUlOqmv2rt7D+QyGmovvO9ALY4GKbUYYGrQMph03/PnkTOPoPzerS2CWxuQ8ktABiGsVN5DaOY1H5WJFIam/7tHQJr1wm0d1je46lTY67P4HVcEJzXQ4N7AcAwTOnBFlwF4rfpH8Z9KD936qSJMVufNAD9dlk6rwdAVhxH/TFMacMCV6E4o/fCui+Xzp2qfoa168SAXJbO68FRfwxT+lSMwOm6rgFoBdAE4G8Nw3i+yEMKFWHdlwuaQ5XrXKtKCN9nmHKnYgQOwAoAyWIPIqyENRk3aA4V51oxDOOkIgRO1/WpAJYCuArA8SIPJ5SEWSCCWlP96QoQxs/LMExuKHuB03W9BsDTAL5pGMZfdV0v9pBCSyW55bLdc2QxZJjSo+wFDsATADYbhrEpyMGDBw9GNBrN85DsRKNR1NTUFPScpc5Ar9nBg+cQj/fANIFEAjh4sBrTp53neSwllZ9RCj0PxqSJpfXT4Xsse/iaZUcYr1dp/Ur70HX9HwH8Q4bDPg/gEgCTAEwN+t5nz54dwMj6B5cEyp6BXrMJE0RqzzEWAyZM6MWpU961LbfvsEdobt9xFvVjS8uK43sse/iaZUcRS3X5PleSAgdgFYB/z3DMWwBuBzABwGmHa/JZXdd3GoYxKy+jY0JPNnuOYQ3AYRgmPWVdbFnX9dEAnPL+KoDlAF4wDKPT+ZpKKbZc6hT6mpX6HhzfY9nD1yw7uNhygTEM4x0A76iP9Vlyb3uJG8P4UUkBOAxTLnAtSoZhGKYsKWsLzgvDMErPv8QwDMNkDVtwDMMwTFnCAscwDMOUJSxwDMMwTFnCAscwDMOUJWWdB8cwDMNULmzBMQzDMGUJCxzDMAxTlrDAMQzDMGUJCxzDMAxTllRcJZNSQdd1DUArgCYAf2sYxvNFHlLo0HV9OIAfALgOwBgAHwDYAOD7hmF8WMyxhQld1+8CcD+AiwF0AFhmGMaLxR1V+NB1/XsAbgCgA+gB8BKA7xmG0V7UgZUIuq7/VwD/BOCHhmEsKfZ4ALbgwswKAMliDyLkjAIwGsB3AXwGwP8GYDaogzsDQNf1rwNYDeCfAUwBsANAq67rny7qwMLJHAA/AjADwBcAJAD8rm8hxaRB1/VpAO4EcKDYY1HhNIEQouv6VAD/AeAqAMfBFlxgdF2fB7LihhqG0V3s8RQbXdd3AThgGMadymNHADxvGMb3ijey8KPr+hAAXQCuNwyjpdjjCSu6rtcBeAUkcP8NQDtbcIwnuq7XgCyQbxqG8ddij6cEqQW5lwrfmj1k6LpeDVok/cbx1G9AVgqTnhrQHHmy2AMJOT8BLZj+UOyBOGGBCx9PANhsGMamYg+k1NB1fSiA/wngScMwEkUeThj4JIAoyAugchzAyMIPp+RYDWAfgJ1FHkdo0XX9TgCXA/i/ij0WLzjIpADouv6PAP4hw2GfB3AJgEkApuZ9UCEm6PUyDGOL8przAbSAGtx+N3+jK0mc+xCax2OMgq7rKwHMAjDLMAzeC/dAp+7R/wzgWsMweos9Hi9Y4ArDKgD/nuGYtwDcDmACgNN9ncclz+q6vtMwjFl5GV34WIVg1wtAaq9EWrwLDMM4l6dxlRofgAKVnNbaRXBbdUwfuq4/AuBm0CKqs9jjCTHTQV6CdmW+igKYrev6twCcbxhGT7EGB7DAFQTDMD4ATTZp0XX9HwA85Hj4VQD3AXghD0MLJUGvF5Das2wFWSVzDcM4nc+xlRKGYfTquv4nUBrFL5SnrgPwy+KMKtzour4aJG5zDMN4rdjjCTm/BrDH8di/AjgCsuyKbtVxFGXI0XVdgKMoPekTt9+AAkuuB3BKefpEWN0mhaQvTWAtgLsAbAfwLQDfANBgGMaxYo4tbOi6/kMAt4HupYPKU6d54RQMXde3IERRlGzBMaXMVQCm9f37sOO5zwPYUtDRhBDDMJ7Vdf0CAN8HJXq3A5jH4ubJXX3//73j8R8A+B+FHQqTC9iCYxiGYcoSThNgGIZhyhIWOIZhGKYsYYFjGIZhyhIWOIZhGKYsYYFjGIZhyhIWOIZhGKYsYYFjGIZhyhIWOIZhGKYsYYFjGIZhyhIu1cUwZUhfb7x2AH8wDOO/KI+vB3AlgMmGYVR8U1imvGELjmHKEMMwPgIVVb5N1/XrAUDX9b8HMB/A7SxuTCXAtSgZpozRdf3HoOr4cwH8J4AfG4bxfxR1UAxTINiCY5jyZgWAMwB2AvgzgP9W3OEwTOFggWOYMqavj9kGAIMA/LTYHZYZppCwi5Jhyhhd16eCrLdXAYwBNTp9r7ijYpjCwBYcw5Qpuq6fB+BnANoAzAJwAsBPijoohikgLHAMU778I4CRAO7si5r8OwDzdV2/vaijYpgCwS5KhilDdF2fCWArgNsMw/i58viDAO4E0GgYxp+LNT6GKQQscAzDMExZwi5KhmEYpixhgWMYhmHKEhY4hmEYpixhgWMYhmHKEu4mwDBljK7rEwA8BmA6gI8A/AuAHxiGkSzmuBimELDAMUyZouv6MAC/A3AQwFcAXAbgYZDn5vtFHBrDFAR2UTJM+fItAJ8AcINhGL81DOMJAD8AsFzX9driDo1h8g8LHMOUL80A2gzD6FYeewYkep8rzpAYpnCwwDFM+XIlgNfUBwzDeAvA2b7nGKasYYFjmPJlGCiwxMnJvucYpqxhgWOY8sarFp/m8zjDlBUscAxTvpwEMNTj8Tp4W3YMU1awwDFM+fIaHHttuq5fAuB8OPbmGKYcYYFjmPKlFUCTrus1ymNfB/AxgD8WZ0gMUzi4XQ7DlCl9id4HAbQD+P8A1ANYCWCVYRic6M2UPWzBMUyZYhjGSQBfBBAF0AJK8n4EwH8v5rgYplCwBccwDMOUJWzBMQzDMGUJCxzDMAxTlrDAMQzDMGUJCxzDMAxTlrDAMQzDMGUJCxzDMAxTlrDAMQzDMGUJCxzDMAxTlrDAMQzDMGXJ/w/z7MM8YGjcjQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure()\n",
    "idata = approx.sample(10000)\n",
    "az.plot_pair(idata, var_names=\"x\", coords={\"idx\": [0, 1]});"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Stein Variational Gradient Descent (SVGD) uses particles to estimate the posterior:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='10000' class='' max='10000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [10000/10000 01:20<00:00]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "w = pm.floatX([0.2, 0.8])\n",
    "mu = pm.floatX([-0.3, 0.5])\n",
    "sd = pm.floatX([0.1, 0.1])\n",
    "with pm.Model() as model:\n",
    "    pm.NormalMixture(\"x\", w=w, mu=mu, sigma=sd)\n",
    "    approx = pm.fit(method=pm.SVGD(n_particles=200, jitter=1.0))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "with pm.Model() as model:\n",
    "    pm.NormalMixture(\"x\", w=[0.2, 0.8], mu=[-0.3, 0.5], sigma=[0.1, 0.1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure()\n",
    "idata = approx.sample(10000)\n",
    "az.plot_dist(idata.posterior[\"x\"]);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For more information on variational inference, see {ref}`variational_inference`."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4. Posterior Predictive Sampling\n",
    "\n",
    "The `sample_posterior_predictive()` function performs prediction on hold-out data and posterior predictive checks."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Auto-assigning NUTS sampler...\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (2 chains in 2 jobs)\n",
      "NUTS: [mu, sd]\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='4000' class='' max='4000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [4000/4000 00:03<00:00 Sampling 2 chains, 0 divergences]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 2 chains for 1_000 tune and 1_000 draw iterations (2_000 + 2_000 draws total) took 4 seconds.\n"
     ]
    }
   ],
   "source": [
    "data = rng.standard_normal(100)\n",
    "with pm.Model() as model:\n",
    "    mu = pm.Normal(\"mu\", mu=0, sigma=1)\n",
    "    sd = pm.HalfNormal(\"sd\", sigma=1)\n",
    "    obs = pm.Normal(\"obs\", mu=mu, sigma=sd, observed=data)\n",
    "\n",
    "    idata = pm.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='2000' class='' max='2000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [2000/2000 00:00<00:00]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "with model:\n",
    "    idata.extend(pm.sample_posterior_predictive(idata))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/xian/anaconda3/envs/pymc-dev-py39/lib/python3.9/site-packages/IPython/core/pylabtools.py:151: UserWarning: Creating legend with loc=\"best\" can be slow with large amounts of data.\n",
      "  fig.canvas.print_figure(bytes_io, **kw)\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAbgAAAEoCAYAAAAqrOTwAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAACoC0lEQVR4nOy9d3wldb3//5zTe3rPJtneYAsL7LJ0LgsIVuSigiDFclGvqKhfBPFKUbxcQL0geEUQf1iwIYoNRBFFlrbL9l7Se3J6P2c+vz/eJ8kumy1Jdtn2eT4eeSQ5Z2bOzGQyr3l3QymFRqPRaDTHGpbDvQMajUaj0RwKtMBpNBqN5phEC5xGo9Fojkm0wGk0Go3mmEQLnEaj0WiOSbTAaTQajeaYxLavN4PB4BFVQ+DxeEgkEod7N45a9PmbGMPnb+gcejyHd4eOIvS1NzH0+ds7JSUlxt7e26fAHWlYrdbDvQtHNfr8TYyh8+f7wAcAiD3zzOHcnaMKfe1NDH3+xod2UWo0Go3mmEQLnEaj0WiOSbTAaTQajeaYRAucRqPRaI5JjqokE43mSCDzoQ8d7l3QaDQHgBY4jWaMZK644nDvgkajOQC0i1KjGSPGwADGwMDh3g2NRrMftMBpNGPEe801eK+55nDvxnHD0qVLueqqq7jiiiu45ZZbSKVSY1q/s7OTZ599dlyf/bGPfWxc6x0KOjs7uaLgPdi4cSP33XffPpd//PHHd/v9SDqWtwstcBrNLsRiilTqiGrgc9zjdDp54okn+OlPf4rNZuOpp54a0/pdXV0899xzY1onn88D8Mgjj4x5nbGSy+XGvM7s2bO56aab9rnMj370o91+H8uxHCvoGJxGU6B/QJHLQjYHRUWKgH+vHYA0h4kFCxawbds2wuEwX//61+no6MDlcnHzzTczffp0Vq5cybe+9S0ADMPg4Ycf5qGHHqK5uZmrrrqKiy++mMsvv5yHHnqIlStXkslkuOyyy3jf+97HihUrePTRRykvL2fLli08+eSTnHvuubzwwgsopXjwwQdZvnw5hmFwzTXXsGzZslHX2ZVzzz2X9773vaxYsYJAIMCdd95JSUkJN9xwA/PmzWPNmjWcccYZLFq0iO985zskEgmKi4u57bbbKC8vZ9OmTdx11114vV5OOOGE4e2uWLGCn/70p9x3330kEgnuu+8+Nm3aBMD111/Pxo0bSafTXHXVVUyePJk77rhj+FhuvfVWLrnkEpYuXQrAHXfcwRlnnMHZZ5896nk5mtECp9EAmYwimYRJ9QamqWhrA69HYbVqkRviT88q/vDH8Vm3NluMXM7c4/VLLjZ4x4UHdo5zuRzLly9nyZIlPPLII8yYMYN77rmHN954gzvuuIMnnniCn/zkJ3zhC19g/vz5JBIJHA4Hn/zkJ4fFAODpp5/G6/Xywx/+kEwmw8c//nEWL14MwIYNG/jpT39KbW3tbp/9wgsvsGXLFp544glCoRDXXXcdCxcu3Oc6AMlkkpkzZ3LjjTfy6KOP8uijj/KFL3wBgGg0ysMPP0wul+OGG27gnnvuoaSkhL/85S9873vf4ytf+Qp33nknN910E2effTbf+MY3Rj0vjz32GD6fj5/85CcARCIRzjvvPH71q1/xxBNP7LH8smXLeP7551m6dCnZbJY33niDL33pSzzzzDOjnpfRjutoQQucRgMEQ1BWKj9bLAYlJYpQCMrKDudeaYBhSwRg/vz5vPvd7+b666/n7rvvBuDkk08mHA4Ti8WYP38+3/nOd7jwwgs599xzqays3GN7r776Ktu2beOFF14AIBaL0dbWhs1mY86cOaPe0NesWcMFF1yA1WqlrKyMhQsXsmHDBrxe717XAbBYLJx//vkAXHTRRdx8883D7w293tLSwvbt2/nMZz4DgGmalJWVEYvFiMVinHTSScPrL1++fI/PeP3117nzzjuHfw8EAvs8n6eddhr3338/mUyGV155hQULFuByufZ6XrTAaTRHMUopUkmoqhyxJPx+aG0dXeDS1177Nu7dkcM7Ljxwa+ut+P0+otHouNYdisHtilJ7WpKGYXD11VezdOlSXn75Za6//noeeOCBPZZTSnHTTTexZMmS3V5fsWIFbrd71H0Y7fOG2Ns6o2EYI+dvaD2lFFOmTOEHP/jBbstGo9Hdlt8bSqkDWm4Ip9PJSSedxCuvvMLzzz/PsmXLhrcz2nk5mtFJJprjnkRiz8k3hmHgdEEyueeNLXvppWQvvfRt2jvNaCxYsGA4M3LFihUUFxfj9Xppb29n2rRpXH311cyePZuWlha8Xu9uo2aWLFnCU089NZzc0draSjKZ3O/nPf/88+TzeYLBIKtWrWLu3Ln73U/TNIctomeffZZ58+btsUxjYyOhUIi1a9cC4ordsWMHfr8fr9fLqlWrhtcfjcWLF/OrX/1q+PdIJAKAzWbbawLLsmXL+MMf/sCqVauGBW085+VIR1twmuOeWBwC/j1f9/sgFoO3PqAb7e0AqPr6t2HvNKPx0Y9+lLvuuosrr7wSl8vFbbfdBsCTTz7JypUrsVgsTJ48mdNOOw2LxYLVauXDH/4wl1xyCR/4wAfo6uriIx/5CEopiouLueeee/b5eeeccw7r1q3jqquuwjAMPvWpT1FWVkZzc/M+13O73ezYsYOPfOQj+Hw+7rrrrj2WsdvtfOMb3+D+++8nFouRz+f5wAc+wJQpU7jtttu46667ePjhhzn55JNH/Yxrr72We++9lyuuuAKLxcL111/Pueeey3ve8x6uvPJKZs6cyR133LHbOosXL+b222/nzDPPxG63A/Dud797zOflSMfYl+l9pA089fv943ZzaPT52xutrYqGhj1dPEpJssnQe0Pnz/eudwF6HtxYOF6vvaHMxYlyvJ6/A2FfA0+1i1JzXJPLKfY2S9IwDKxWWUaj0Rx9aIHTHNckk3u6IHfF7YbE0R2G0BxGDob1phk/WuA0xzX7EziPR5bRaDRHH1rgNMc1qTS4XHt/3+mE9NhaH2o0miMEnUWpOW4ZSrDaVw2RYRhYLIp8fiQOl/7Upw75vmk0momjBU5z3JLJgMOx/+VcLkinR37PXnTRodspjUZz0NAuSs1xSzotLsj94XTuHoezbN2KZevWQ7djmt3o7e3li1/8Ipdddhnvf//7uf/++8lms/z+97/n3nvvPdy7twfnnnvu4d4FTQEtcJrjllQKXAcgcG63xOqG8Hz+83g+//lDt2OaYZRS3HzzzZx99tn86le/4he/+AXJZJLvfe97h+TzxjO6RnPkol2UmuOWdAbKD0DgbDaDvK6FOyy88cYbOBwO3vnOdwJgtVr57Gc/y/ve9z4+/vGP09PTw2c/+1k6Ozu54IIL+OhHP0oymeTWW2+lt7cX0zS59tprWbZsGZs2bRp1JM2uo2sWLVrE73//e5566iksFgupVIrLL7+cp556iu7ubu69916CwSAul4svf/nLNDU10dnZyVe/+lXy+fwx1cfxWEALnOa4RZkyOeBAsFjYLdHkeOTJJ58cHskyVqxW66gDQa+88ko++MEP7nW9HTt2MGvWrN1e83q9VFdXk8/nh0fVOJ1OrrvuOk4//XS6urooLy/n/vvvB6Qrfi6X47777ht1JA2MjK4B2Lx5M2+++SaLFi3in//8J4sXL8Zms/HNb36TL33pSzQ0NLBu3Tr+53/+h+9+97vcf//9XHrppVx88cW79YTUHH60wGmOS/bVwWQ0XC5xaWqODIY66J966qkUFRUB0i9y9erVLF26lAceeIAHH3yQM844gwULFrB9+/ZRR9IMMTS6Zujn559/nkWLFvH8889z6aWXkkgkWLt2LbfeeuvwcplMBpBROt/85jcBeMc73sF3v/vdQ378mgNDC5zmuORAMyiHcDghlVY47Idun450PvjBD+7T2toX4+2lOHny5D26gcTjcXp6erBYLHuUeBiGQUNDA48//jgvv/wyDz30EIsXL+bss88edSTNELuOvDnzzDN5+OGHCYfDbNq0iZNPPplUKoXP5xt1gKjmyEUnmWiOS8YqcE7HSKlA6qabSN1006HZMc1unHLKKaRSKf74xz8CkM/n+c53vsMll1yCy+XitddeIxwOk0qlePHFF5k3bx59fX24XC7e8Y53cOWVV7J58+a9jqQZDY/Hw5w5c/jWt77F6aefjtVqxev1Ultby1//+ldALMithUzaefPm8Ze//AWAP//5z4f6lGjGgLbgNMclmYwMNT1QHA6IxSUGlzvnnEOzU5o9MAyD//7v/+aee+7hscceQynFaaedxg033MBzzz3H/Pnzuf3222lvb+eCCy5g9uzZvPLKKzzwwANYLBZsNhtf+tKX9jmSZjTOP/98brnlFh566KHh126//XbuuecefvjDH5LL5Vi2bBnTp0/n85//PF/96lf5xS9+oUsEjjD0uJzjCH3+RmhvV9TUgNV64JOQBwY8lJUlsBasgPyJJx6q3Tvm0NfexNDnb+/sa1yOtuA0xyWmOTZxA7DZDbJZhe+WWwA9D06jOdLRMTjNcYdpKoxxXPku5+4tuzQazZGNFjjNcUc2C/ZxZEM6nYYWOI3mKEILnOa4I52RrMixopQimTqiwtIajWYfaIHTHHdkM2Oz4DIZRWurIhpTtLeDbleo0Rwd6CQTzXFHNgs+34Etm88rurqguhrKy62Eggbd//kV3G44gDaWGo3mMKItOM1xRzZ34BZc/wCUlkr8DcBqA8/5p9A95VRyugHz28LSpUu56qqruOKKK7jllltIjbFnWmdnJ88+++y4PvtjH/vYuNY7FHR2dnLFFVcAsHHjRu677759Lv/444/v9vuRdCxvF1rgNMcdB9pkOZ1WZDPg948s63SA5ZXXqWt5jf7+Q7mXmiGcTidPPPEEP/3pT7HZbDz11FNjWr+rq4vnnntuTOsMNYZ+5JFHxrzOWBnPiJ7Zs2dz03666fzoRz/a7fexHMuxgnZRao4rlFJwgOVvg4NQXr77aw4H+O6+C5sNuh7+HbmcwmYbWz3d0YwR7tjn+8pTAnaP/GLmMaLd8nreixGL77l8Ud2YPn/BggVs27aNcDjM17/+dTo6OnC5XNx8881Mnz6dlStX8q1vfUv21TB4+OGHeeihh2hubuaqq67i4osv5vLLL+ehhx5i5cqVZDIZLrvsMt73vvexYsUKHn30UcrLy9myZQtPPvkk5557Li+88AJKKR588EGWL1+OYRhcc801LFu2bNR1duXcc8/lve99LytWrCAQCHDnnXdSUlKy24ieM844g0WLFo06ymfTpk3cddddeL1eTjjhhOHtrlixgp/+9Kfcd999JBIJ7rvvPjZt2gTA9ddfz8aNG0mn01x11VVMnjyZO+64Y/hYbr31Vi655BKWLl0KwB133MEZZ5zB2WefPep52ZXOzk4+97nPMW/ePNavX8+0adN45zvfySOPPEIwGOT2229n7ty5JJNJ7rvvPrZv304+n+ejH/0oZ511Fp2dndx+++0kCxOEv/CFLzBv3jxWrFjBD37wA4qLi9mxYwczZ87k9ttv36PX6FjRAqc5rshmwX4AV30up8jmwOXa/R/M4RALEKC0RESwsvIQ7OgRivfR8/f5fvKd3yE/4wL5JR3ZbXnvKMvHPr/xgD87l8uxfPlylixZwiOPPMKMGTO45557eOONN7jjjjt44okn+MlPfsIXvvAF5s+fTyKRwOFw8MlPfnJYDACefvppvF4vP/zhD8lkMnz84x9n8eLFAMPjd2pra3f77BdeeIEtW7bwxBNPEAqFuO6661i4cOE+1wFIJpPMnDmTG2+8kUcffZRHH32UL3zhC8DIiJ5cLscNN9ww6iifO++8k5tuuomzzz6bb3zjG6Oel8ceewyfzzc8yigSiXDeeefxq1/9atTm0MuWLeP5559n6dKlZLNZ3njjDb70pS/xzDPPjHpe3npc7e3tfP3rX2fKlClce+21PPfcc3z/+9/nn//8Jz/60Y+45557ePzxx1m0aBFf+cpXiEajXHfddZxyyimUlpbyv//7vzidTlpbW/nqV7867ErdsmULP/vZzygvL+fjH/84q1evZsGCBQd4dYyOFjjNcUUuB/a3lAiEQmq4N6XbLYIWjUJRYM/17XYwC6E3r9egv18Nj27RHBqGLBGA+fPn8+53v5vrr7+eu+++G4CTTz6ZcDhMLBZj/vz5fOc73+HCCy/k3HPPpXKUp49XX32Vbdu2DU8piMVitLW1YbPZmDNnzqhCtWbNGi644AKsVitlZWUsXLiQDRs24PV697oOgMViGR7Fc9FFF3HzzTcPvzf0ektLy6ijfGKxGLFYjJNOOml4/eXLl+/xGa+//jp33nnn8O+BwCgX7i6cdtpp3H///WQyGV555RUWLFiAy+Xa63l567HV1NQwbdo0AKZMmcLJJ5+MYRhMnTqVrq6u4XP8z3/+k5/+9KeAjBbq7u6moqKCe++9l61bt2KxWGhtbR3e7pw5c4b/XtOnT6erq0sLnEYzFjKZEQtOKUVXNzjsklU5OAgej6KkxCAahfr6Pde3Wg3YJbfE54NoDAJjaNx8NBO//vl9vq88JSO/OAPDy3t9XuKjuCgPhKEY3G6fM0oPXcMwuPrqq1m6dCkvv/wy119/PQ888MCe+6gUN9100x7Tt1esWLHb2Jz9fd4Qe1tnNHZ9EBpaTyk16iifaDR6QA9OY33AcjqdnHTSSbzyyis8//zzLFu2bHg7o52Xt+LYZQyHYRjDvxuGMRyHVEpx991309jYuNu6jzzyCKWlpTzxxBOYpsnZZ5896nb3NiB3rOgkE81xxa5dTAYGpP1WebmBx2NQWwuJBASDJnb7PhJRDIZFrqgIIuG3ZdePCFRR3T6/huNvABbr8OtG8aTRlx8nCxYsGM6MXLFiBcXFxXi9Xtrb25k2bRpXX301s2fPpqWlBa/XSyKRGF53yZIlPPXUU8PJHa2trcMxoX193vPPP08+nycYDLJq1Srmzp273/00TXPYInr22WeZN2/eHsvsbZSP3+/H6/WyatWq4fVHY/HixbtNEo9EIgDYbLa9JrAsW7aMP/zhD6xatWpY0MZzXvbGkiVL+OUvfzn8YLB582ZAZvmVlZVhsVj485//fFBEbF9oC05zXJHJQolDireTKZhUPyJihmFQVaVYvwGmTFbsLRul95avE/CDFbDZDBSKfF6NuXmzZvx89KMf5a677uLKK6/E5XJx2223AfDkk0+ycuVKLBYLkydP5rTTTsNisWC1Wvnwhz/MJZdcwgc+8AG6urr4yEc+glKK4uJi7rnnnn1+3jnnnMO6deu46qqrMAyDT33qU5SVldHc3LzP9dxuNzt27OAjH/kIPp+Pu+66a49l9jXK57bbbuOuu+7i4Ycf5uSTTx71M6699lruvfderrjiCiwWC9dffz3nnnsu73nPe7jyyiuZOXMmd9xxx27rLF68mNtvv50zzzwTe+GJ793vfveYz8veuPbaa/n2t7/Nhz/8YZRS1NTUcN9993HppZfy5S9/mb/97W8sWrRoTNbveNDjco4jjofzl8spenoAA6qr9pwY0NqqaGgw6OxSlBSPxNx2ZfUak/p6KCvd3cExdP6CQYXVBoFC+UAwqLBaIRCQ33VMbk+Oh2tvNIYyFyfK8Xr+DgQ9Lkdz3NDTC8XFoJT8XFuz5zLZrMLMjy5u2ayitARiUYPSktGFyv/q30lngHfLcEufD3p7pevJ0D3IsCgqK0YKxDUazduPFjjNMUM6rTAMyW4EiEQVqZQaTvVXSsbkhMMigqMRi4slls1CLDb61O+iB+4nm4NMQeDsdoPuHpOGBpg0ycAwDDIZRXc3lJcrPB4tcscrB8N604wfnWSiOWYIhqC4aOT3kmII7ZIAks2C1aqIx8E7WlEWkCi8V/yWdXfFsIiFOPy5QYXPC16PMWzxORwGdXXQ1ydWoUajefvRAqc5Zkin2M1acrsNMumRFO9cDvI58HgY1fWolCKfl8QRm83AYuxDnAovZ7NquKQgPkoWfEmJortHC5xGczjQAqc5JkinFc5R2vt7PJL6DyJwidTeJwmk0+DYZRv+ABQyrgGZBD6MITG3vn7pZOJ2GyR36QEcDCo6OiCRMOjvl9IDjUbz9qJjcJpjgngcPKO4Hb1eiETley4HZm705BIQIXQ6Fd09kEkDhiIWFXdldze43CaJhGKWAosB8bhCmcZwjM8wpFwgnoBUChoa5PVAQLF6DSw+VR1Qk2eNRnNw0AKnOSZIJGRm21txuSQOBhCNKbz7mAMXiUp2ZVUVeKsM8nlYv16xdp1i2lSDmhorPT3QfPN9uN3Q0wf1u3Qx8nogElFEIgaTJslryaQikTAIBBStbYqmRi1wYyEcDvPpT38agIGBAaxWK8WFDKHHHntsuIZLoxkNLXCaYwLTZNSu/oZhYLEocjlFJAoNo7TfkvVNenpg3okGQx2DrFaDyirF9m0yQw4kxhedMZ2YqQi2QVWFWG4ul4HHA9t2QFODdEGJRhWhsDRl9vlg6zaorzu+pg9MlKKiouE2XY888ggej4crr7xy+P1cLofNpm9jmtHRV4bmqCedVjgce3/f44FEUtyYu85225XubhGh/gHpX5LPK0pLJXGlukZKBhJJicFVvfon1q6H2OKLSKbEpWmaiqIA9PbBnFlScD44CJMmidh5PNDepmhrV0xu0gI3Ee644w4CgQBbtmxh5syZeDye3YTviiuu4N5776W2tpY//elP/PKXvySbzTJ37ly++MUvYrVad9vee9/7Xi688EJWrFhBLpfj5ptv5uGHH6a9vZ0rr7ySSy+9FIAf//jH/PWvfyWTyXDOOecMDxD90pe+RE9PD5lMhg984AO8973vBaTI+/LLL+df//oXTqeTe+65h7KysrfvRGm0wGmOflIpcLr2/r7bDaGwiNNoMbBcTtHbJ02Yh4qzTVPR0qLIZsVqKytT9PaYlJYqrN9+iOkJ6D31IpqboahY3JNd3eDzQHOzQgHVVcbw5xmGwcyZijfXQGPD0RuL873rXXu8ln3ve0lffz0kEvg+8IE93s986EPwiU9gDAzgveaa3d6LPfPMuPajra2NBx54AKvVutdBnjt37uT555/n+9//PjabjXvuuYdnn32Wiy++eI9lKysr+cEPfsC3v/1t7rzzTr7//e+TyWS44ooruPTSS3n11Vdpa2vjscceQynFF7/4Rd58800WLlzIrbfeSlFREalUiuuuu45zzz2XoqIikskkJ5xwAjfccAMPPPAAv/3tb7nuuuvGdbya8aEFTnPUk0qPPtpmCJcLQs0idKMxMCjW3YknjHQesVgM3B5FNgx2hyKTMfD7DdatV8zJgmFAVxcsWQxWq4hsIgFVlZKUsrNZ9mnXervycgsqbxIKKUpLj06BO1I477zz9rDE3sobb7zB5s2bufbaawEZu1NSUjLqsmeeeSYAU6dOJZFI4PV68Xq9OBwOotEor776Kq+++ipXX301IHPe2traWLhwIb/4xS948cUXAejp6aGtrY2ioiLsdjtnnHEGALNmzeK11147KMeuOXC0wGmOetJpRi0RGMIwDGIJ6T35VnI5xeCAwuOBQGD3qpl0yqCpCdo7FNmMwjDyvPE6zFZgs0FZBeTz0NwiReFl5dIerL0D5syWpJV0RlFTPWLJNTbCzp1QWnrwjv/tZJ8Wl8ez1/edgCorG7fF9lZ2bdJrtVoxzZEyjEwmA0hd48UXX8wnP/nJ/W5v15Evbx0Hk8/nUUrxkY98ZI8J1ytWrOD111/nBz/4AS6XixtuuIF0Og1IN/+hesuDNf5FMzZ0HZzmqEYpBWr0wu1dyecYNU4XDkM2D2VvEZxUSuFwKJQS9+OOHbB5a57qGhG1gF/ckQBnnwVNjaDyUF4Bra3Q3ApWCzQ3w8qVilhMbsCTJkn25W41dZoJUVNTMzyOZdOmTXR2dgJwyimn8Le//Y3BwUFAMjKHBnKOlSVLlvDMM88Mj93p7e1lcHCQeDyO3+/H5XLR3NzM+vXrD8IRaQ4W2oLTHNXsOt9tb5imdP8331JrncmYbNgkPxsKOjoU5eUihC2tCmVKW67ubmhtB7vVZN48GZCazUFJiUwHNwyDykqFzwevvQolpVBdCd09MHsWtLTCm6vhxLkmxcUWHHbtpjyYnHvuufzpT3/iqquuYvbs2Uwq1GhMnjyZT3ziE9x4442YponNZuOLX/wiNTWjdODeD4sXL6a5uXk4scTtdvO1r31teIbalVdeSWNj4wHNiNO8fehxOccRx+L5i0YlEWRfYpFIKHY2K1xOmDpVnBbptGLHDkUiKXGzsjIDq1VErqtbsi5nzhAxy+XgXy9DKm3jrDNzJDZ14PVB2fw6tu+Qgu5UUpHJwPoNEI3CtGkwc4ZBLAZlZbB9h6KvD045WVyU2SzMm3f8OFCOxWvv7USfv72zr3E5x89/mOaYJJMZ3fW4K8mkJJgMWXC5nHT6dzjEAusbgFhMEQqJCNltUsBdXibuxtY2sRKnTrHR0w2Zqjqor8duF9dnf78imYS6OnFBJhIiig4H5E1xaTZMMigtgQ0bobYWunoO/bnRaI53tMBpjmrSmX0nmIAInN0GNrvE7NrbJflj2zYRPq9Hkka2bQOLBWpqIa+goxOKS8TaypuyzEAQprz+G0qee4pkEsIRWLUKTCWF3P39sHABtLfD4CBUlMtrHo9BeYVBJlPYXk6sSI1Gc+jQAqc5qsllZR7bvjBNUBi4XdDdLYXZ4bCk+gf8ImobN4mIlVdAZ6f0mty2TYrE29uhqQmyGUUsBpW//iGlP/8hGzZBcBCmT4NpUy3YHeKOtNikdKGnTyZ9W6yStFJRLnG7bdtkrE9PrxY4jeZQogVOc9SilJK2I/sgnVaShKLA6TLYuAmKiqRWbeo02LxZ6uBKS2HBfIP6OgOlRNT8fnj1NXC7wGpAc6tsK5sVi61/QBo5JxLQ32+yfp0IXEmJvNa8Q94vK4XBoNTW1VQbZAsjewrJfhqN5hChBU5z1JLNiutxX6RS4CqUTMViilgc6mpH3IQeN5h5hoWrs0uRSEiSSTQK27dDoEgE7cR5Fpn0HRcLcKAPMllZdsUqqKmBuloLNVUGpy2R7Mkd2xVOpzRuzuUUgYBBRYVsOxgamVWn0WgOPlrgNEctB5RgkgKnQ8oEWlqhrETS+uNxae9ls8vMt2gUwmFFby9s3ynuy5dfEfHr6AK/D6orrVRViivTaoHGJvmeyYwUm/f0mHR2gtsDgWJ4402IxUwC/pHZco0NBokEZNPiutRoNIcGLXCao5ZsVrIg90UmLWKlUISC0jg5EpWsx+oqSSTJ52WZaBzWrBPRWr8OKstFBPv7Yd16eOXVLP194hX1eCGbgcoqSTwxEKHr6paygSlNBtOngMMqQun3S8NmkHl0FRVi+fX3H+qzpNEcv2iB0xy1ZLJSp7Y3hmJ0uZxBVyfUVIPDYdDWJu7EHTvFQisuhrZWcTuaOXFXVtdA/SSxEKc2SWF3UQB6++En7/sh67/2QxJJ6WCSz0EwKFabywWhkEk6DUUlMGeOlAbE4wqbfSRzcvZsCIZFOFtbpbFzX5/SHU40moOIFjjNUUs2s+8uJum0CFQuL/0hp02TTMhIWCyqlmZIpiEQALdXxM3pkgzH6dPE5ThrVkEA22Hr9jweD2SKy3ituQyHXVp4uZzSrNnllF6Ur74GGzcq2tokEaWpCV78p4zjGbLiUmkDrweiMbH4GhtlDl17h8TqNBrNxNECpzlqMU0ZSro3UikRnVBQYRhQVGShf0Dciz090D8Ik+qkFVcyCdubRahiccl8bG+Hbdth6w7IZ6G/T1FUBOc1/4za536G3SbTv3fskBje2rXgsElSypw5BotPkRKBfK5QY2co4glJdkkk4IzT5bOzWalALyoyKC8TN6dOPtFoJo4WOM1RyYGUCKTS4jJsaYXGSTLENJEQy66lBUqKJAZWVyftumIRQIkodhY6nSycL5mWFivkciar10DjCz9j4eqfsfw1sczaOqRzyeo1sHYD9PbAqtWKYEgaMpt5EcC/vwihkGLLNkV5mWLSJHF9dneP7LPHY+D36dicRnMw0AKnOSo5kBKBTAbsdkVvv7TQ6u9XuN2SWOLxQiQmsbhUCvr7YPsOme1mtUpPyYpycU/msxBLSOPlyU0iZm6nWHr5nCxXVgozZshXLA69vZLgYir57EWL4K9/lXo4vw+6uw3SKYOaKti8Zff9Li42SOsMS41mwmiB0xyV7K9EYGiMTjgsRdper4hOOCJZknabJKkMDMLy5fDs81BXL+LU1gGJuLTeevKX0NULKKgoN+joEAswk4XSYpkYYLfJBAGfF7wumDEN1q6XEoTGBujrLzR0LhdXpdMB9fVSBzepQSzMbHZ3Mauqgt6+Q3kGNZpjHy1wmqOS/ZUIDAlgV7ckd+RykuARj4NhleSORFyWM5V0+S8plmzI6ippsNzRJWN0ohFxM1ZVWUmkpKTANGW5eEy6oKRSIlzJJORMmDYFXntd9rOsVGrgZs8S0eoodDCprZE+mMkkDA7uLnB2u4HLKdMSNBrN+NACpzkq2V+JQCoFVqsiHpOsyGBQkkocdnEvrl0Lp54ssbiKChG6llY44UTYskXELuCTGFlrm3ze5s05Ghukd6VS8NoKybrM5aCzC/r6xAXZ3QX1dbBxMzz7F7ES2zuko4qBDEMNhRRWq0FTo3x2X7/ECHeltFSsPI1GMz70wFPNUUluP4NOU2kp4FZKJga0d4hF19srIuR2yRBSp1NKAGqqxHXZ0QE7mqWfZDwhyR4Oh2Rb7mwR6+3rZz2JxRCrbOlp0Noirs+hGF5psZQhhMMQCop70lRSR+f1QXcnbNoMpy+FkhKDQEAxMAihkPSyHMJmM3A4FImEwuPRw1E1mrGiLTjNUUk+v+8SgXRa3IdOp1hYQ8KWTEFtNZSWiJhl8zJRYPVascx27BTrr2ESTJ0isTCfD4qKoa7WYNNmsHg8BNMeshno7ACfX8S2qEhq8waD0s6rpkqaKi9/VT6rvV3cmJEo/OMl6O01MQyDqVOk0DwWY49C79ISsT41Gs3Y0QKnOSbJ5xTptPw8MCBp+vmcWHNFRdDSLuUB2bRYYoNBiasVB8SFGQxKvE4pOGGuTPRev0GRTMA56x9j2ZbHcDrFfdneJkkjfYUhptEo7Nwhbs2aahHZSARWrRE3Zle3LPPjn8Kq1SbV1eKKtDsU4cjux+FwGGDo2XEazXjQAqc56sjnZc7a3shkFJmMpPUnU5LU4XBK55J0GjZsguZmcRumUpI1GQ6JVRiJjUwfaGmV5dasEaErL4NZs2Hh1qc5u/tpykplGwrYuBHiSamZO/VkKUMo8kvWZCgspQF2O8w7UbIta6uhshI2bZL4WzYrll00sufxlBTLNjQazdjQAqc56shmJQV/b6TTkrjhdksnkmxeEjvq6uDURSIiRUWw8k2Jm/X0QGOjdCAxkNq4cAh2Nov1NXUaVJRJQkkwJO5H0wS7E+pqxNLrKiSWWG1QXSsiuXlrYZxOQvYjmYS2Npg2VSYWuJxQUTk08Vtm02GRmNuueDwGqeSe7kuNRrNvtMBpjjqy+8mgTKYUeROUKRZYX6+MyQmFRWi6Cp1DVB4GB+XnGdPEbRgJy/IdXRIvc9hh+SvQ0yduy+5OEUFDPIe4C9ae2y2iGA7ByhXyj5XJSClDKimJKkqJlRaOitt0xQrpg5nLiSUZDErBeSi8p5DtOo1Ao9EcGFrgNEcd2SzY9pH/Gw6LML25WqyrQEAEaNpUeHONuCtzOWnjVVMrLbu2bpdEj0RKshnDIdlWXhXEyZQi8ExWXJmZrEzk7umVz7DapKTA4ZJyhOnToaFeRHDadMmgLC6SdWurobgE2jpF5GqqRTD7+qVt17bte5YMBALsEZ/TaDT7Rguc5qgjm9t3iUAsJgXVzc2SBWm3g81asJayYqVZENdhKCQuzN4eib9VVkAqI4KVz8uyVqu4Kg0lRdsWiwiXQsoP3G5JYInFZJ1UUuJ+JiKkAwNizbW2SjZnIgWN9ZKdGQpBLCoim8lISUEuBxs2qt0aLttsBhZjz44nGo1m7+g6OM1Rx75q4ExTEYtLzZrDDsGIjMlpb5cOJv39kM5Ac5vE0fw+MEyZzZbPiTAlE2LlORxQXSmCF4mIeCVTcONJvyOXA0tMRNLMi8jFCrE4Mw/bt8v3inKw2MT9aLFIa6/aGpkV57RDSxucthT8aRhcL11QKsoKHU86oK5OYRhSDuEPyH7sWiun0Wj2jrbgNEcd+6qBSyQUHR1yYUdihTE3/VBeLkkcXd3ifizyF2bFZaGjW6woGWUjSSQ2qwhWa4d0KUmmJIYXjUrdnNcrYmO1SsLL5CkiYKYpluLAoPzePygWXCwm9XIgHU46OiTLM5uGTRslPufzwZq1smxZqWSD9vSOHJvPK+5QjUZzYGiB0xxTdHVJTVtvn4hWWbnEvzIZeOUVybCsKJfJ3P39EIrIe1abCF4+L8skEhLry2dFVAYGRNCyGTj/zQe5ZP2DZLMSO7PbYMtmidNlsyKEBjKBIJ0Rl6XFKu7O2jrJxAyFwe8VN2Z3r5QVNNRLWYHNLuIXiYIy1XA/SotFhqLqmjiN5sDQAqc5qthfDdybq6SY2uGAqmrpJ1laCi/9S8TG54V0ViyvigrJpLTbJWPSbpdsRrdLfjaQeJnNJsIFEnc7rf85Tut/DgNZfmBAWoPF4vK7aYrwJZNSCuD2yPbDYRFBl0syNYMFIRwcEGEN+GXdnh4RZ9OULMzBwZGkk0BAtqPRaPaPFjjNUcW+auA6OkzWrBX3XnmZiE1RMTz1W7HqbDaorYXgoAhcojBZAMRiSiSkB6VhkWkD4Yi4CyOF7EWvR76rXb+UFHsnEiJWFouIVSwmIpnLy5RvU4mlmEhI4bbPL1mYConPbd0u23K5xIU5MCDJNMFBKC5Ww+263G4RTj3xW6PZP1rgNEcVow06NU3Flq0mL/5DBMtiSHZiMgmrV0n2YyIursqOQtNlp10ExWaVwaRDgjQ0Cmc0/Ygn5L1dUWrkNVth/UxGxCmfl5+7eiEZBwyJAWayYtmVlkE4KOLb0S5iWFMt+59IwbatInRgkEhALicJJ0Mip9Fo9o0WOM1RRe4tJQJKKbZtU6RSYrHVVkNxKWAUxtcUsiMTSUkUSaVk/URKBCmdke82W+HLOvI5Y8VasN6GCIfFOhvKvqyqkO0nEpJNaSDdUKxWEb6eHklwyefFben1STeUFSsVgYAiFJLt+nxiYWo0mn2jBU5zVJF5S4lAV7f0nVSmJIf4/GC3ijBEY5K40d4lomEgyR7pjFhe6bQIWSYzYolFIiKC+/IApi1u0hb3Hq+n0rv/bjHkC8RF2dUt+xSLSjZme4e853SIxTnUvqu8QuJ2ubz87nBIdmUwqMjn1XDrLo1Gs290HZzmqGLXGrh43KSzC5oaJLkknQYi0B0XV+SJc0XYEgkRiXRG1jeVfKfgjhwqF8hmd7fA9sZ/TP75Pt8fKgI3lVhuZmEmXT4v428GgxJrS6fEarNaxfpraZaC71RKEmCyWZg+FfoHxHXZ3gFer6K21sDpglRK4XLpOXEazd7QFpzmqCKdUfT1Q3OzycvLxULavFmaKVttgEWmALjdIiJr1km8ymaT72bBUvP6RmJnmYxYSwcibgfCkPHndBb2OS2iNVRCYLPKZ7s9kpSSzcrnm0rG7yhD3JDh0C5TBAyp5VuzDrI5E79PrECNRrN3tMBpjhpiMUVPz0ihdVWVDCZVhSQSgK5OabvV1CAC09khiR+5rCw3VGIwEXH4j557+Y+ee/e7XHoXl+VQjDBTiPmlUtJFpbqykG2ZE7Hr7ZN9dbvFsty+XQQxlxUrz+2CDRvA7VY60USj2Q9a4DRHBYmEYmBQUVcnN//tO2HKZKkRGwxK+6psViZyuz1SzL123chom3RGRDGXExfiRFgc+weLY/8Y17r5vFiSDod0O0llpKXYsCvVBm3tsHOn7Hd/v+xzW7vE+Kqrxa05OCjCqIu+NZq9owVOc8STTitpt1UGTqdBZ6eitBhSaYNkSgQgHoPmFkk2qa2VIaY7du5utcXj0h8yO44MyYNJJiP7MfTdYhXBy2bFPWmxjIh2U+PIXLnubimRsNtlrpzDofQIHY1mH2iB0xzRKCVuyepqME0Dm1XR3g6TJkFfn5LMx5jE4GIxGVqqkCLqoVT/fCG+ZppM3Hw7SKTSI+UD+XxhQoEhWZyqYHH2dEtT5kRcphz09ErCSXHxSG/MWExbcBrN3tACpzmiGRyULvoOh0EuJwIQKIJ4QpSqowtadspE7GxObv65rMSyhrDscpUfrESSiTJUljBkgbldI/s2GJQC73AUtm4R12pPD1TXiOvS6ZSi82yhM0oup0VOoxkNXSagOWLJ5RTxuFhrIGnxff0yTLS/T2GxwPoNMmR0YFBEIpmE7TtGekeCWEYHk7C19KBuLxoVF6XNJkXpFLqrpFMSn8vmJJ640CbCZ98sI30MJW3FAkWKutojxDTVaI4gtMBpjliCwUJvyIJC9Q9I6r8yJaV+w0YgL8LW3SVF3gODYsHtaqkdbKvts02PH9wNIvG4IRQySSAckZ8bGqTziWlKb814HOpqZcGiYti6FQxDUVW59zFCGs3xiHZRao5IcjlFMgV+vzH8ezAo2ZGRiCRZmHnII0NKnXYZRxOPievuaGTIlWoWMj93FNyR69ZJm69YDKqrRNCzWejrF/elzQpul8QmMxntrtRohtACpzkiGRiUrMkhQiFx4RkWGAhKZmTzTqkNSyYgkRZXZDYD+UN8j/9s1518tuvOg77docLzoTZhqZSItqkk03LzFnFZdvVAZaUkovT2gMstcbvqapmHl81qkdNoQAuc5ggkn1ekU+DxGMO/x2IKm02SKjo6ZS5aMCyCFo+LOOTykM3vHn87FMxPvM78xOuH9kMKtLVLvV9bu1h4ubxYc2vXQkWluC4tBsPjdIZEzjS1yGk0WuA0RxyRqGRODhEKSe2XxQLt7VBcBJs2STyuoxOwSH1YLCpWz8FEKYWZj6HUIVbNvdA/INasMsX9umULTJ0qyTTFAXk/k5WC8f4BqRMsKZGsS43meEcnmWiOOKIRqK+Xn01TipkNK0TjkMtI4smWrdIKK54Qiy0SkZ/HM+bmrSiVIxL+HeHgr0gkXsXMS0NIq7UUj+90/pYb4KyDnEm5L9aulankPi+8/ga87z1g2ETMXS4plSgtgmRCxgb5/QbxhFi9Pp9OOtEcv2iB0xxRJBIKpwsshTkz4ULdW3MzhAZlWndvn8xL8/ikn2NvryRgHIxsyWjkL/R03kImsxO7vZ5A0btxOCajVJpspo1Y9G98OddNneHEEv4jvsA7hrM8DxWJhPSsHAxKfO63vxfB27oNZs2AF/8BZ54hxeMDA1BXJ8k47e3Ss1JnVmqOV7TAad42cjmZ3ZYtjKbJZAsWl2J4xkxfn6K4RDIk3W6pd5s8GVpbweOVeWpbtkFJmYhaLC7ZhOYExU2pLD1ddzDY/zBO5yzqG/8//IGLMAzLW5bL897t7+WnqfW0tFyNP3AxtZMewGotmtgO7IdMThJq0hn450vwmU/Caz0yO666TjIuk2koKVEFy86gpEQRDO2erKPRHE/oGJzmbSGVUvT0SkKIUtJ5pKIcGiYZNDQYNEwyqK+HigqDyU0GpaVizaXTsHGT3MDjcRG9nh6oKIPOLhjsL3zABIwUpbK0t3yMwf6HKSn7KJOnP0+g6OI9xA3AMKz8dtozeOZuprLma0Qjz7Fz6zLSqc3j34EDoK8P7A45d9kMvPCijNTZtAlOOQlCERjok4STgQFZJxAwSMR1pxPN8YsWOM3bgstlUFdrUFFhUFxs4PEY2O27q1IsLjdti8XA6TQwTYOZM43hTh9+P7z2htzEN20pxN2SYgXuawL3vlAqS3vrx4lGfk9V7depqfsmFotrv+sZhp3yik/TNPVp8maMndsuIBr58/h24gBIpyVT1G4TyzeRkF6UrW2AEsHP5uW8GBZIJuWElJRIuzON5nhEC5zmiCEaEREDKVg2ChO3t26DIj8EByRNHiVp84axeweQsaKUorPtP4mGn6Gq5i7Kyj9xQOvd3HkrN3feCoDHu4Qp0/+KwzmdtuZriISfGf8O7YdYTDqXpAqNlp0Oictt2SZz8ex22LIZ/D41LGp+v0Eqra04zfGJFjjNEUEupzAVw1ZdMCTWx84WcW16fJDKSf/FgUHp2TjRkoDBgUcIh35FRdWXKav4j70uZ7dkmFW0gfdM+g1XTX2cc3mW080XRt6319A45Te4PSfR3vJRwqGnJ7ZjeyEUEsG3GFL/1t8v56irWyYqDI3d2bpVSiqGrLjyMjlnGs3xhk4y0RwRxGKSEQkjhd5FAcUrr0BludzUwyG5UcfjkmyRn0BJQCL+Oj2dX8UXuIjyys/t8b7TkuKiuj9yYd2fOLnsdRzWkTo464pBItndk0re1fh3nI3v54F/5Olo/QSoPEUl7x//Du6F5mYoKZY4Wy4nPTiLS2TKQFWVTFNYtwFmzVIMDEhc0+Mx6O9X5PM6o1JzfKEFTnNEEItJFw6QQm+fX7F6jbjiTpgL7W0y8DOVht5CYolhQZpRjpF8PkpH68ewO+qoq39w1GSS/1rwVS6u/8Nur/WnyuhLVdKUW0M069vtveum/YBpgW3852wr5zxRzaa2GwCTopJ/H/sO7nPfC4NSTWndNWe2dC6ZMUOmKFRXiRXX3gEBvyTqeDwGgYDELEtKDuruaDRHNFrgNIcd0xT3pM0m1kU0Ahgy8LO0WMQtHBXLLRKSEgOLMf6WXL3dd5LNdtA09Y9YbcWFV4dqFYSnWt7Pstpneb5zGX/tWsaqwZPoT1cA8MPwu3fbnsOSZm1wHpWuXkrdEZZfo3jvz+38o/WTuGzg9B9ckctkxQXZ3y+ZpFYLlBRJAkp7B0yeLGJ37tmK3j6DBo+0Nmtr0wKnOb7QMTjNYSceB69Hfk6lFLmcordXOpMkU9JkubtLRK2/EEsab6vFeOxlggOPUVr+cTzeUwAod/bxvdM+xgnFa4aXe2PgVC547m98eeW9PN914bC4AbQ4p9LinDr8e8Z0cvvqO1n23At8c+0txPNVPP2BIpbU2Wht+SQ1PDy+nd0L2YwkmChTRM5uhVdfh+nTwGanMFVAyilcTohGFRaLgcejJ4Brji+0wGkOO7GYlAcADAwqEslCJ/2YpMd7vOKqjCfkd9T4rDfTTNPV/jnsjkYqq28BYEnFy/zinEtZUrGcL594l2wcAINgZvQK6a/Vf4uv1X9rj9fTposnd17JO//6Z364/UaevKyaORVWXt7wVfLJF0bZ0vjImwUr1ir9KeMpSUBpboW5s8QVGQqL0Pn9MmZIKUVxsSyn0RwvaIHT7EFPryIafXue9JWS7iZS96bo7RHrpK0d+vuksfCKlaDy0kwYZML1eBjs/z8yme3U1N2DxeLl/Y2/4LtLPkGpc5BIJsCj2z7GhCrGC2RMJz/Y+gk+8epvuP+dS3A7q9m6/VqSiTcnvO0hUmmJxykk4SSfh82bpBi8vh42bpDOJqFwoQNMVDJUDUOP09EcP2iB0+xBSbFYS909h/5GmExKdxKA/n6F1Squta4ecbNNqoeWFjALI2HGG3fLZXvo770Pn/9CfP7z+PSs73Db/NuxGiYbQnP44Iu/4m9dyw5oW19r/xxfa98z8/KttMab+Owbv6Js0rNYraW07rwclXmTanfn+A7iLeRy4q5Mp6XQffsOsYZLSyUJpbtb+nT6fSNWXCAg/T01muMBLXCaPXA4DKqrDCwGhEKHVuR2dU/ubAavD3a2QF8PLPs3+Mc/xRWXiE+sqLu3+xuYKkNV7e18ce43+eiM7wPwz56zuP5fj9OZrDvgbTWmt9OY3n5Ay+aVDbujlsYpv8YwHHS3vIv/mnM5Dd6WcR3HWxmyZsMRKZ1YuQpcdqitk9E64TBEo5JFGQrLuY7HDspHazRHPFrgNHulokLiOYfSpTVkwQ0MmDidYq11dombLWtKK6pEQiYIjJd0ajOh4M8oLbuey6at48qpPwbg6db38dnXHiCZ9x6ko9k7DudkFs99AIMMVz+1hTvnfYip/m0HZdvRqCScAGzcCG4PlJWJZbd1G4TCCp9PEQmLped2S/mARnOsowVOs1cMw6C8fKR578Emk1HYHfI5LW0yEWBgUAaXzj8R1rwJnR1yU04kxv85vd13Y7F4KK/8HH9qv4TnO8/nt63v5fZVd5BXb1+lTFCdx0mzHmIwCVf9ejt3L7iaSQfJkstkxV2ZScv4nPoawCJJJTJOyKCoSNy8RUVizWk0xzpa4DT7xOMxyOchnT74T/zxhJQHRKImiUJ3kp07oKlRpgf0B6WZcjI5/s9IJlYSjfyesopPYrOVkVN2bl5xL7evugN1GC7/zvxlLJj5bXYGTa79zQ7uX3Qtla6Jj99Op8VdabPBps1i+c6aDrEEbNggVlxRkbiEbTbIZaX+UKM5ltECp9kvJSXSG/Jgk4iD1wstrVLXFg5LEklllXTp6O8T91tkAkkRvd134bQHOGvaGcOv5ZQdE+u4t7nZfSKb3SeOe/0B4wpOmXUHK7ty3PiHTXzn5Ovx2aLj3h6IlWsxZCJDNiOZp42NYg2nUtDVKVZwSalYcT6fiJ1GcyyjBU6zXzweg8xB7kivlCKfF0HrLnQs2bgJvH7YtlVcbp3dkg04XuLx5cRj/+C2Mx08ftanOKPyHwdl379Z+3W+Wfv1CW1j0HoDp836HM/vzHDHC29y27xbJrxfyZRkViZS0s5szRrpU5nNw/Zm6O1VBPwGiQR4PGpCDw4azdGAFjjNAVFUNDFL6q0kk+Bywc6dCqcTBkOSJZlMSreS3l6xOCaSORnuf5Bil41Pn2Ihkg2wLTrtoO3/wWDQfivnzLqcX29M859/TqDGO9RuF2xWqYmLRmWMDqZYauGwWMrZrKKsDMIRqffTY3Q0xzJa4DQHhN9/cF1aiQQYhqKrR+ruNm6EYFjaTnV1SRJEbgLTAtLpbYTDz/Ifi5zYrXY+99oDdCdrD8q+f7P1P/hm697H64yFXsdDVFV9kubu39LXc/eEt5fNicClUlI6kDclPjcwAL090Nmp8HoNMhlwuRTRiXlGNZojGi1wmgPCYjGw2w9eskkiKeUAgYJw7myWZsHhqFhxapztuIYoS38RuxU+eYqbe9f9P9aF5h2U/QaoynZSlT04xdoApZW3U1z6Yfp77yfU/yCN3p0T3mY6LU2re3sls7LIBx3d8OYacQ+Xlsj5jeo4nOYYRguc5oApKhJX10TJ5RTJhCKRAKsNXl4umX0Oh1hvuRzDE6nHw3TvS6zreIkPznXxZuhd/Lz5QxPf6UOIYRjU1N1HZel5dHZ+jQuLL6XYEZzA9uR7NAoY0pDZYpcHiVgMNmwQKy6bMwqt0rSbUnNsogVOc8B4PMaEUvaHiCcUAwMywqW5GQYL9/LeHnGlDY7/3o7bGmeq5VMksor3nziDO1Z/jYPRX/JQYxhWFky/k7MbXdz05zYuLr0ag/Fl2AyF8rI5GZHjdENHmyTseF2wfiP09ZuUlozE6zSaYxEtcJox4XJDMjmxJ/6uTnA4oa8P1q4Fr1uELRKVWriJuCbTOcUPVoQ5t8nFo83fe1u6lBws2pMzOXHGt1lQbeOuvy3nnJJbJ7zNWAzIS1ZlSTGs3wRFASmgz+aktCAS0Rac5thEC5xmTPgnWD+Vyym6usHphDdXSR1cKCxlAbGYiNtESgMGg78nkorRY/8u26Izxr+hfbDacwqrPacckm3/recyrj/9GhqKrPz4lR/QYH9qQtvL5SCdlaL6WFzq4jCgp1dmw7ndQ2OItMhpjj20wGnGhPQxHP/6Xd0yMWDNOnGP2exS75bPF7rjj9N6MzBRSjHQ/zBO5yyU6937X2mcfLvmNr5dc9sh2/73t93Og+86CY/dYO3WT2Mzx9/OK18YM+TxyGR0rw/WrZMxO8qUhB4zL51ONJpjDS1wmjFhGAYOx/ie+NNpmdQ9MCBdTCwGbNsCLoeIZiw+0jR4bCjuOfkmziv5POnUekorbsAwjvy4297ImE4e3Podfn5ZOYOJDMnuSzDN1Li3FwqJ5R2JQTIhXWkyGclcraySaQ1dBy8pVKM5YtACpxkz423z1NOr6O6RoZw9feIaU0injXhcUtvz4xC482ueY1ntc2zv+DluRxFFxZeNfSNj4NvN1/Dt5msO6Wdsi87gpdCXeOw9RWzt76an49PjLgQ3TREzt0tELhqV8oF8Dvp6ZeZeXz+kUhPwDWs0RyBa4DRjxusVcRoLqZRJTy9Ew9DWKjPL4nHI5SEcHH9cL2AP8eV5X2dDX44/b8/gK7kBi8U5vo0dAA4HFJuDFOUnUMdwgPxkx9VsyNxNdfX/Ixh8msGB7497W7GYJPHkctLSKxqF3gHo6ASv16C4GHbsOHj7rtEcCWiB04wZi8XAMCCfP3CLYus2sSSypmRKDobA7YXuHrEq8vmR+q2xcNPc/6HMOcD9r6SxGE5Kyq4d+0YOEANJwd91Ny0WaY+1K3b7wfk8hYVft1xOScUX8AfeQU/nf5GIvz6ubeVy4qq0WmWSwMo35fe+fnj1dUVZqQxL7ekxdfsuzTGDFjjNuPB6DtyKGxw0GQxCVwe4nHJj9Xpgx3axLIayJsfqgVtS8TLvaXianlien6xNUVTyQWy2srFtZB8YRuGr8LuikOW5y37a7ZIR6rCLeECh3uwgVicYhkHtpAfxOCvoa/8wudz4BvSl0zJJwB+Qn828dJSxWqCmBhonyQNHPn/w9l2jOZxogdOMC68X4gfgVsznFStWQkWZxN5aWsU1GYtLqy6l5EY7VuvNbY1z27yvAfC1l4rJmzlKyw9Of8ghlCqIriFtxEYjnRahz5tizTkdIhDxuGQuWg5Srss7G/7JX67MkssN0tdxw7jicbmcdKKxWyXpZM0aaaBtMaCzE2bNkvZeE+kBqtEcSWiB04wLp9M4oE7/6zcoAn6xfqIx6OoGwyJCl8+LtaMYu/X2qVkPUOftIJSy8f+t6sfnvwCna/p4DmW/DImcwy6JGqsrzmJlyVl4vdJizNhluUxWljOMQjmFAT7v+Nyvu7Ji4BRmVRTx9fO8BMN/IzT443EfS28fFBVLLZzFAlu3S/cYvx+UAX19Sg9D1RwTaIHTjBunC1Kpvd8I+/tNOjth5kwYHJCJAdFIIVV9UG62uZzcZMfKH9rfxebwTD71t1PJ5kKUVXxyAkeyb7xeuflXV0N5Bfxi1hd46sQv4HCINWSzg9spbleXS9Lunc6R/prJlFhzE6E3VcW3N9zEp0/1cG6Tg77uL5NJj70pcyQi+5fPi0W9dYu0S8vkoKMDykrkgWMi7dI0miMFLXCacePziqtxNNJpxYaNMGkSrFsPre2Ssef3S1JJKiXWm8UYX8xnY3guV7z4M363fi0u14l4vKdP7GDegsMhk8wbGqTJdEMDzJopPw81Lc5mJB5nsUBeSRuzkmJJOhkS7Wx2xGU5USvuqZbLWDFwKo+8K4DHlqG7/ZOocRQODvTL98oK+bv4A/Daq1IQXlwix5ZIyOw4jeZoRgucZsxks4rBQUVvn+LNNxXrN5hs32HS2qZobVXs2Gnyr+WKdFaSMPImrF0vlkE6JfGeXL7gopzAPTQU+Qfp9DbKKj454cLuodXtNigrg8YGOPVkmDUdamvEDTkwKKL84JYPcN+6D+ByS3JGeam4LpNJ+bJYRbiLArI9m00suonOM1VYuGP17VT6PNy3zEcs/jrBgcfHvJ1gSASsqEi++7zy99i+szBoNg6lJYq+/ontr0ZzuNECpxkzhiEWTk21QVMjVFWB222gTHC6FPk8lJbAtMnSVDmRKHS1d4jFkE7LdsbqmixxDPDQko8xu2g9AAP9D2Gz1xAofu+EjsflEhGy2aCiUjI9Gxul20coLK68RFKssIEBsGWTeIwkbhdUVEBpmYh1NisiXlwkgmYq2Z7bLe87nRMvIWiLN/LQpv/k6vkulk1x0N/zX2QybWPeTmcnpJIi5q++BqXFcmzBICQKdXIGkEhoK05z9KIFTjNmbDYDn8/A7TYoLzdw2A1qawwaGmS4ZiQsGZKd3bBxA/zjRVB5ib0lk4XEDGPsTZU/O+d+lla+zENLPo6ZfoNE7J+Uln0Mwxi/algMER3ThKpKGcBaXS11e11dUF0DUxpF8Ox2mD0L3B7JQpw1S47D4xWhKystJJpkKAyHlebGRX4R0WxWvibqqvzJjqvYEDqB71xUgoU8Xe03jTmrMhSWekS/T5JNlJLkmP5BeRDZsBHKyxX9/Yy7g4pGc7jRAqeZEN5d4nCplFgtxSUiBE0NYvW0dYgl19s/Em8bq7gtKF3JexqeBuDBTTfS1fMYhsVLSdlHJrT/Hhdk05IEUl0D1VXibqyvleSYXB56+mWkz6RJIlC+QtLJrFli7cVjUFwsySblZbKMyyXnZmgEkMs1Uic3Ub3IKxtfXfV1/t/qpymtuoN47G9Ewk+PeTtbt8mx2qywY6c8eLS1ymuptFh5Ho8idBCG3Go0hwMtcJoJ4XAYZDNS79bbK0//VqtYM+EIbNpU6GCSEwG0WDig8oJdsRo5vnzinQCsC57AL7YtJRx6ipKSK7Fai8a8z1ZrwfLygMcHLg+ce7a4VIuKYfp0uPzfxZLLFwTNYkBNjY2lS8R1Z7WKGM6dC5MbobYW5p0oQ1ztDjn2qkrwuCV2l0qJ+Pm8e6+pGwvbo9PZHp1OSdm1uNzz6Om8jXx+bJNL43FxU/p80Nwija79fomXej1S8pBKQTikdHcTzVGJFjjNhHG5obVNUVysSKXAKFSGbdgk1puZF3efxTI+6+WDk3/KzKItmMrgG2tuo7//h4BJafnHx7wtj0fEyWGHqVPFlThpkmQQRiIiUHNmSUG01wvz54nQVVXDWWc4eNc7DXLvuIC+Uy/A54Ozz4LP3ginnQqT6mD+ifBv54mwtbZKEorLJa7bgUJphMUqonIwMAwr9XXfIJfrpr/n3jGvv26jlAak0pLlWlsNLS3yUNLbCz6fQd6U86PRHG1ogdNMHKVIJiGXM4hEwDSlROC1VyS+0z8ogmKaklo/Fiqcvdww80EAftV8OesGmwgOPo6/6BIczqYxbcvhEJE1DImphcMyLqYoIG7V8go4cY6IUCQm2ZONjTC1SQQpn4eWFkX2M59m+RmfJhGXBBu73WDhQrHiBgbF3bfwJKitk6Lq4mJoahShdDrFunW5JN7nnGBf6BLHIM9c/A2uXeAiOPA9UqlNY1o/nYZYQtyTLa3Q0QUL5sHqdTI/zuNRBPwGgwNKD0XVHHVogdNMiHxekUhK3CYYUiRT0sD3T8/CjhaJR9nt0r0Exl4W8Pm5/4PPHmcwXcoDm24kFHwSMx+mrHzshd3WQmNkv09cbzOmgc8DAZ8kwdTViluupxeaJkkavdcD5eVwwflQVmphzVr41VMwY4a4Y3/7O3j2L4q//FUaSJ8wFxadBFXl0FAvn+FwQDwpwllWJnE5q6UQryyemMgFMyX0pSu461w/fgf0dn5xzEkhGzdI5mc8IUXflVXiko0l4JXXoKhIDVvpGs3RhBa444BcTp6+s1k1pgkAB0L/AJSWQnunWCs11ZJB2dEh6fHplIhfLjv2xBJQtCfqyeTtfHvD54lkfAz0fw+352Q83lPGtCW7HSorZV+sNpg9m2FhtjnEXdnbJwkzCxbKvrucso7XZ2CxGAwGTewOuO7xd9N0zbuJRMUSGxyE+jqYd4IknhQXyWe86xI46ywROqtFYl6JxEh80mYTt6jPJ583vuxKcdsWuZx8/TwPsdhyIqGnxrQFE2mhZrWISL/+OkybKolBHe3yns0qjZj7+vTMOM3Rw0EId2uOZNJpxcCgPJGnM4pImOE+g3a7xJm8XrBax353TSYVibi4Jx02SdjYsVPGrrhchZumTawi0xRrbmwYfHfTjfym9f10JWqJRv5ENtNMVfVXx7YVQzqRZNPScaS6Uo7dbgenW5IrrFaYOV1+TyUlGaS4WI7HYVds2gRl5YpFC6VFmdUq7r0pTRLX6+2VWGM2K0KXSsn7VVVw8sliwZaXw+tvSJmB1yOJNyBZmKYqjLIZR6Pj1ngTP9z2UT668CEefTPFhu5b8QUuwGr1H/A2gkFAiai1d0jyTFcX5G1y7VRXG1itis1boKxMYTlYXaQ1mkOItuCOcZxOqVGrrjaoq7VQX2/Q0GAwaZJYXrmcJBd0du0ZY0kkFImEIpXas/muUoqWVoVSknlXUQnr18OW7ZIlGYuPZA7G45IqP146E/UoLAz0PYTd3oC/6OIxrd/UKEkehiGW0oyZEhOMxcUqWbQQTlog52OgXwRHKYPBoFie/QPSgqu22jI8mNXtMbjwAqkHLC83OOFE6RDiKbg0rVaxEGfOEJGbMUMeJM5YKlmYJy0UkRtyVZrm+HpyDvHo1o/RkWzggXf4SWf76ev5nzFvIxiS4bP9g7B5qyTcKCXJQgB1dRZqa6C5WbsqNUcHWuCOUwzDwOk0KC01aJhkUFYqN/LuHhEzpSS2lkiKO629A9raFcGgpIy3tStyOWhsNIhFYfsOWV/lob8f+vsk1hWPj90qKXP2cf307+OwpIdfSyRWkEy8SmnFJzCMA3c8uJzy+YFAwZKrF+vs9RUiWuedLYXaO3ZAKCJZkyWl4PMrNm6UeGJtjSSMGIZBRaWBy2VgtUrBe22toqVFsXOHlAkoBStWigU7qd4glYSpUwyWnAIV5VA/SbbX1ibCV1cnFuVQhul4syszppO713yFU+vsXLfATXDge6RTW8a8ncGQNMJevXokMSgSgZ0FUZs82aC3HxIJ7arUHPlogdMAYunV1Rp4PHLzTSahvMygvMygqlJEsLZGbsQbN0uW5LSpYqV1dkrMraJCGivnsmKxud0F0RvjA/9n59zPf87+Dj9Yeg3S/AoG+x7CYglQXHLFAW/H4RABcbkl9mUYkjjy6qsiLvV1BcvJCiedBEtONfB4xYp79i8ijicvEiGz2wyamiwE/COuuVRK0dllUF0t8bRNm6G01GDxqQZWq0E0pti8FUqKFVOnykPE7Blw9VXiAsxk5eHBKNQNDk1WGK/zb3nfGfylcxl3nOvDY7fQ3XXbmLeRz4u12z8AL/5D4pLd3SL0sZiJYRjMnA4bx5asqdEcFnQMTrMbAb+Bx63o6YFYTFFRwXAjY6vVwG5XZDPi0uvtM9i6TdHRISnv3T3ytB+JiqtuPLVTC0pX8K5JvwPg6dZLAYNMppVI+BnKKj55wHEli0X2wW6TJIq8KYLc0QXROCxdKvHBRSdJIkkoBCvfVGTS4kqsrJCib9M0qKsTkRs6D6l3vYd4QixVn1cRixmUlUM+J/HIQADKyw1icUVdLaxaBTNnKmproacb5syBd1woFm5fP7z6utSfxeMMrx+OjP3cAdy77v9xYd18AuUxujpvJxr5C/7AsjFtIxSBWp8IcDAksTi7HdrbYcmpJqWlYt11dZnU1OhnZM2RixY4zR7YbHJTDwYVnV1QUy1JBdmsuCbLy6Cy0kJHhykTumPSXHnzFkCJVed0yM16LEjHkq8D0rHkN63vB2Cw//uAhdKyAy/sttnkJowhPTAbJom1Fg7B3DmSml9TLSLc2SlWlN8nYheNijvR7xOXoc1moJQiFlN0diny77hO+ldmRABra2UZMAiGFJ2d4HCa+LwG5Y0GA4MmPb2SUYoh7t5J9QbTpiu8fjlPXT1Sh9fRIe3BLMb4Ji30pGr4/7ZfS3FphoH+H9PTdRs+39kYFscBb0MpqRHMZuVBxkBc0AtOlAQiS6HZ9qo1cNJJJmWlUBQwcDrRySeaIwotcJq9UlIimXMdnVBTbdLVJbEnqw1WrDB5bYU82ZeXw/qNYnUEQyIk0djYP++yxp8zs2gzpjK4e+1XUFjI5yOEBn9MoPg92B21B7Qdu13ci3PmwM5mmFQrlmWm0BPyjNNl1puBzD5Tptywh5bJpKXA2zRh82ZFUZHCZjMoKzex2xS5cBK7DyrqPHtkn5YUG6SSJs0tsHC+vFZWaiGbUdhKFYNBsYRMU1FfBx1tUpYQe0l6X2bSYgkPuVXHi2FxUFV7J23NVzA48AhlFZ864HUthZIGnxda22DxqdKRBkMGu55yipynYEjOmdMB8ZjC4TRQpsLlKrRB82jB0xxetH9Bs08CAYOSYnhzlZQF5HIQCsqU6saGQsq9Q9xYmZRkJubzIyNxDpQSxwCfmiUdS55uvZT1oRMBCA48jmnGxlTY7XSKe3HDRslm7BuUDEmACy+AijJobRFX5Izp0NQEdfUGJ8yV0oDqGhn/4/MZTJ0qsTGrTZFMyA17zhc+SOMNHxy1tCKRUGSzBnNmiTU2lJlaVQXptPTtnD1bbv5OBxSXyvSFqgr5nNMWS/KLQcECHScGJl9dsoYLpzoJ9t1NLttz4OsahW4uUXlQ2bhZJiIkElIMLi3ILMyeZUiPzmqYOtXCpHrJzvX5pPVXewf09uqMS83hQwucZr9kMvJU39oqDYZdLrkBe9wQjUisJh6X9lY2m7gox8pnZn+bgCNCOBPgfzd+DgDTTDHQ/z28vnNwe+Yf0HbcLrHGXE4pX5jSBNOnSgxu6hSYP1/q0BbMl8SaXM6gokISbOx2A5RBfZ1leIZbJGJgd8hxlpcblJUZe80CiUQV/QPSssvrtVBTAz09EI0qDENcmRarWD0uF2AYLD4V6utlqnY4JLVxFy6TujmHc/wJJwoLla4e7rvAhzJTBHsPvHYwn5cEoVRhLlxoEAaDErusr4M162DLVkk4mTpNrPd0WspJ0ml5wCgvk8SkiopxHoBGcxDQAqfZJ+m0Il6IYc2ZA9u2ieClM9DWDuWVsHJFwdWnxiduDkua2cUbAPjups8QypQAEAr+jHyul/LKGw9oOzabCIXXI7+fOEeyJsNRcDskI9LvkxIGh0PEuqZGyiUAuroUTqeio0PcsrmcWF6TmyxMn24QDksZxVuzQjMZic0lCgIg8TiZtFBfL1ZQf7+I3PRphjReHgCPWxGPGdRUwcknifWYz4sL+IQ5cp79gbGfzyHuW/8lagNF3LjEQ9/Ar0nE3zjgdZOF1mJDLtPBASmAX/4azJ4jmajP/80kFhWrffsORTgibupdXasTnbSu0UwELXCavaKUZFOWlSqSSQOny8Bik3hMNCYutPZ2yQwcqncbezsuqeG68h8/59aVd/Or5ssLn51joO9B3J5FeLxn7HP9oVuox1PoSmJIYXV5hYyBcTpFiCc3SYJEbS1UV1uw2w1yOUUwpNiw0WQwKKJUVQUNk6RG0G4fySCtr7fg90nD6HQKOjoVrW0yJqi4SLp9vDXmZLFIob3FAh0dCsOAsnKDSfWwdTtYrVJvWFwikwhMJcNIL7xQMiuTSdl/2zii5f3pCh7e/Gm+fLqXGp+FcM+NKHXgfyCrVVzRpoLmVimDGOiHF/4u7c08bnnImTdXslDLy6Cq0sDv16KmOTLQAqcZpn9ArJfeXpPubpNtOxSmUrS1QzanaG9TOOzQ3SU3YZ9fWk9F43ITjMfH/9l5ZeMP7e/GRKaCRkK/JZtpoazixn1aAS6XVMo5HGJxOJ3SlquyEl56SQR3zixYuACmTTMwLAZuNwwMSEZod7ek97tdMO9Eg5ISY9gCGw2v18DhlHZdVZUwqR7q6w08nn3f1EtLDUpK5IHAYVfk8wZTmgxsdjmGHTsAJSN3EnHYuQPe+S45HqVEmMfDkzuvoDM1i7v/zUcwtplw8McHvG4uJ5+dy44MQbXZxQpOp2DrFklEee11sTb/9bKitVXRP6DjbpojAy1wmmHKSmWki9cr7Zra2yThIJuVUoBsoa2XxwM7d8Lvfi+JFPGYPMGP+fOcfcwuWr/H60op+vv+F6dzJv7ARfvcRrrgEh0aYupwyOy2N96QerLLLhVLrrwUenoUW7cosllZrrZGxCmVMqip2dP62huZD32IzIc+tFtt3IHg8Uj5RSpl0NmlCAQUmbTBCXMNqmuk3ZnPD3WTZKJBOAzz5sm+5s2RieBjIa9s3L32Nj50goul9XZCvV8lnx/biO5kSmKH2TRs3y4WrMdTqB8MywNFtOCqLCpSlJdpC05zZKAFTjOMYUgHDrfbwO+VDMKtW6WbhWJkEvVAUJJOBgfkppbLj+/zvjD3Hn581ge5YeYDu70ei/yJdGo9ZZWfwTD2folarbJfUn8lXUvmz5OsRKcTlp4Gnd3g98j7VitMn25QU2PB75djDYYkrd3lOvCbcuaKK8hcceAdVXbFZjOor5fM1C1bAUMRDkN9rUF5mVhzUxqlDq84ALNmFMb2eMc3LBZg1eBJ/K7tfXzrIj/JTIzBnm+MaX2lJHO2rFxihM0tImhurySf+P1w5hli6a18Ez03TnPEoAXuOCSXU/T2KkIh6Sv5Vvr6C3VihtzQurvgpZclI3DLFnGftbZJQoka15QAWFLxMu+o/yNWw6QzUT/8ulKKvp7/weGYTFHx+/e5jXxe9tFqEbdZVaWIWHunNFT2eqGpAZomG9TVGaTTBsXFI+unUopoVGa0jQVjYABjYGIjrhsaDLxecT1u3aZwOBQ2u8HkJsnYrK4Rl6DfDyfMHonDDcnwWGNy397weSKcT2P1e+nrf3zMg1ETSSmKt9tlnzs7ZYKCxyV9K0NhOP98We7llxXxuO5VqTn86ELv4xCbzSAQUKRSMtLGblOUl8vriYTUujmdUisWK8TX5syEf7wks95sNkl+SKWHOkWODYclzZdPvAuAlQMn8bu29wy/F4v8mVRqLbX1D+63qfJQJ367Q9xlDrsI79SpcMZp0NIisbfeXrAUSRbjUHwtl5MEmrq6sWf6ea+5Rvb1mWfGtN6uGIak0CcS0NSo2L4DTKWYMa3QzSQHfX1QVwO+IqmTo1Cblk6PvYF1MFPGja89hKN0EEvf3+nu/DKNk58a07H394tL2LCAywPbtouFGYvBS/+URJmSEjnff34OGieZVFSAy22QTJmkUgqbVa6foS+dZak5lGiBO8YwTUlxVwpQcjNyOsT15XaPyJHLZeBySWp6IqFo71D4vIqeXmm7tXYtbNshsat5J0pHkL4+EZVUWtyT2cz43JPXTHuURl8LWdPG19d8FVVwJIj1dg92x2SKSi7b5zZsNrnJO4aOzQVeH+RMeNfF0jZs7lyw2w0MC4TDI9abaUoLsspK9plQcqgJ+A1iMYXfZ1BZKa691nYp9B4MSS3alm1QVgLTpkm9YSYrVnNmHFYzgM1WSmXVLXR3fol45Gl8Re8b0/rRGJidklQydbK08DrjdBFdl1vEzuuVB4+ePsjmIZdVFBfnyeUUNhvkc/J3yuXAUAqrTRp1O+wGDgdSa6jRHAS0wB1jWCySgj6EaUrxbSoFHZ0m8bgi4BfXVzwuLqV0GlCwarUUHdts0oViQSHBoasLlr8iVt3AoNRFpdOF+WVjFLhJ3haun/4IAD/efjXbo9OH34uGnylYbw/s13obKkeoLxzrWWfC6rVw0ny5+VqtUtidSIDDoUilDCorpadkZ6eIuNt9+G+kVZVisRWXyN/J64HJjfDPl0S0t2yRKeE11XLuQyE5tlBwfL0qAc6bNpcVGQ/dvV/C478Qi8UzpvXTaUjEYPtOqft75g8yc6+4WPY5EpH2bWZe4raLFoLTaSMcNggEdj/nSinyebmWxltmotHsDR2DO8axWCRppKTEoLHBSk21xK7a2mBgUGG1KIqL5cm6KAAbN0p2ZDotsayXX4UX/ylup3RWCn/thVjQ2K0IxZdPvAunNUNnoob/23LDyDtmhp7uO3C6ZlNUcvl+jkluhDXVkmm45FSxKj0uWLRIhO70pWCxWEgkZJ+LSwrWbQcEisDnO/ziBlJfV1sL0YhBPifdYnp6pbXY5MkydWDLVvlbNE6SwvN8TqzV8XJxw7M89A4n4WSQxOA3x7y+acqEhnhMRNdiKexTofXZlKlyDPX18ndZvwEUag9xA4bdxhaLgcNhjCnZR6PZH1rgjjNsNnFNWqwiYm3t0LxTXJBuN0yfhkwESEtJQEmR9GosKhLLyGaXlPX8OJ60J/t2cHLZ6wDcs+4WUvkRy2Fw4DGymWaqar6GYewnH16JZWmxQnWFzHLbthVOWyLTp6dNg9JSubQTCUXelKLkjk45jsARVogs0xtk0np1tSSZnHKyhVwO5p4g2aCJOGCIaHi8Yh25CgMCxno0D278DHOrq7h8jpOunu+RybSMaX3ThGBQRiQN9MsDRFu7WKLNzfKgUVICb66WfevphS1b8vT27jkZXqM5lGgX5XFAKKSIRMDrzROPKwyLwumEslLp5LFuvfQ9DIVh9RpxRdbXQmOTWHsPfU+ehLIZaaicSsnrY2VnbCofePHXvKPuD/y9+7zh1/O5EH299+L1nYPXd94+tjBivQUKLazOXwZr18i+en3Q2g7/do68l8sp4nGpLxsayLq/guwDIX3ttRPexmg4nQYzphu8/oZJOGwyfboUgJ+ySJJ6XnpJXIKzZ8lg2UQcrPmx/y0i2WLuW/8lvnn+l/j91n7ygzdA9R/HtA3TlBjb5EYZiFpeKUkn2QzU1cO/nScNug2k3jCXM+jvVwwMQCAg199QIbnNZpA3JbZYXs5w9xiNZqIYah/FNcFg8Ih63PL7/USj0cO9G0ctQ+cvkTDp6JRU72BIEkecLrlR2azS7T4alX6Ta9aIOzOekN9bWsYnbvuip/O/GOh/iCnTX8DlPmG/y7uc4k6dOQtmFcoBvF5xV562GBoaxHoLBk02bZbWXHW1++5QciC8XddfMGjS2gbTphp0dyusVhGDV16Blnb5OwWD8jeJx8c7Vkfx8JKP8+KWv/DVv8eYMe0JbJ53jHkr1dVy/dis8iBRUiItu2ZMlwelbCGuVuR3kUylKC1MT8hkxQL0+aGutpAMZEirNM2e6Hvf3ikpKdnrRaMtuGMU01TEYtJ+KxqToZ95M83ggAmGtFjyeiDhkDR7g0KSgFMKu30eGZPy2utS92SzyRP7eMRtemAzrbFG0qZrj/fS6W0MDjxCccmH9ituQ5mTTpeIlj8A9ZMkfT0Wkxtlfb1c65mMYvUahvtKHsx0dKO9HQBVX7+fJcdHcbFBKKQYGJQidIcT8jmDklKFMiQ+t26tiJvdKlmy6cxYP8XgrjVf5cdnrOBHq5PEem+kqPF8DGNsM3r6emFSg5RotLXJ7wMV8reZN1caXbtckn2ZSUvN4dKl8reIx0WkgyF5YBktRqfRTAQtcMcoSsmTc3m5gc+rSKWhtsaOYaSJJyARV6x8U248dpuIRDgiZQU2m8TbNm6S930+GOwfn6UQsId4aMnHSeS8fOmN+9gcmb3LPiq6O27GMJxUVn9lv9syEOvN55F5b3NmiiAP9Elz5blz5Jj7+hWJhDQ2nj3r4IeZvTdIcsxE6uD2hWEY+ANSnxiLS8u0E09ULFkMv3oKvG4oKZW/UTwJ2X6w5sYeF+1ITOKH2/+T/1n2dS79xSDl8TvI+e4c0zbypvTXLCmBhnqJt7W2QnBQYrtz50it4ZTJFuJxiEVlUnxpqQVfYWK6RnOo0EkmxyhWq0FxsUHAb1BZaaFhkoWSEgtWq1GovxLrZubMQnq2gmlTZXZaRZkkMXR2SueKcGj806W/MPceKlz9lLv6CGeLdnsvGv4d8djfqay+BZu9cp/bsdvF3WWzi9VWUyPfN26GmlpJvsgX9tnrkf1vahrfPh8JlBRL7V5drYXyCslEDAQMzjoDMKQGze+HyjJJuPF7x/c5P9lxFbWli5lVPYt1zT8ik2kd8zasFomfdfVIZuuUKfKANRgElMRLZ8+yUVFhUFsHm7dCf7+UrIRC0py5t1e+enpluoNGczDQFtxxQDaryGTAblds3mKybbsUaheVSNNkr0fEY9s2GYNitcDrKyTzMG+K+2s8fRBPr/wn7274LQDfWv8FupO1w+/l81G6u76Cy3UiJWX7Ttrw+yWxRRJjJAGmrkbqreJRmDVdbrA2m0yUjsbEuqmuPnpdXlargcejiEYVk+otpFImbe0Km10yXXfsEFetxZDZcWvWipBEImP7nLyycf3LT5Av7kT1nk5XxxdpaHpyTC7ddAacaUnyGRgU9/eM6dIl52//gB3NYLNmCRQVmgVY4dXXxCotChi4XZI8NPSR4xkNpNGMhrbgjgNMUzrCDwYVgwMSJ7HZYPNmiYts2CSWj8sjTX63bJMSAqOQsTjWtlAAXluM2+Z/DYDX+0/h1y3/vtv7fT33kMt2UV13zz6Luj1uyczLZuUGXlUlfRoNYM1qseKqqmDWLAvFxYaksA9KyYNnbPXLRxzFxZJMopSirlYGs1YWJmQ7XCL2obB0ZKmpllic0zH2z1FYsDvqqay+lXj0ryQiPx/zNiIxmfxts0EiJS3TDEP+ds074bfPpNm4SVFXC5PqDE48QZJl7HYZQeR2G4XuOhNPBtJohtDPSscwuZyiv19+HhxUJJI5drZK0kJ3r7SAqqiQDvxNk2H7Vvjt76GlVQTEoFB/NQ4+O+c+qt3dJHMubl91x3A7LoB47B8M9n+PktKP4PGestdtWCySoDAYlMw8rxdKiyXD01qYHjBnNjQ2jtwQe3olDT2ZOriJJYcDm83A45VpA8XFBpGowmIxaGyEygrpfLJuvfwta2tHOoHkQuOrU6yu+DCe9IOEej9LUeBMckbdmNYPR8HulC4x2VxhblxarMpo3CSehM4OKCmRxgJeH6xcqaivV7g9BhZDHqo87oNTzqHRaIE7hrHZDEpKxLdoKrHiaqtlWsC8E8TtuG4dlJZJ78a16yTRJJeVpIFkcnw9D08pf4V/b/oFAN/d9BnaEw3D7+VyA3S0fhKHcypVtXfsczsejzQXtlgknRygoVHqqmJRqKqB6qqRJ/5gSGG3gVLGIU1eSH/qU4du42+htESyE/1+RUW5JHSUlkoCzcL50NUJm7aIwLnd0vsxGoP8mLMqodHXzlfel2PpYzm80Q8RDvxjzNvo75f9qKqS7jfV1ZIhGQpLiUk6JX8/p0uuM79fMinrJykqysSlZJrydaDz+TSavaFdlMcgpiljcIbmckUiivY2udkoJTGQgUFYvU5uNDt2yByvbFZqyYqKpa4pGBrf57+/8VcArB6cz093fHj4daUUnW2fIZ8fpL7hESyW0TMjnE6Ga79yObHUYlGYO1vacuVyso9lJVBUJDfBVErKIsrLpWTAN86kiwMhe9FFZC/a9yDWg4XFIpPAg0GJy5WWQiJpkEkbVFfB2WdKHE6Z8qBSUgLFReMbjrotOoN/hf6TLy71srx5A9V8b1z73NYmbsmmRrHA582DZedbKQqIS7KmBqY2SceZvCnF+atXw6o14tpsaYEdO3TXE83E0RbcMUT/gGJwQEavKMSNl8lAW4eIxsrVWcwcZHIynTkUgb4sBMNgKMmCs1jkqae1ffz7ccuK/2Z96ARe6jkTk5E7bXDgMWLRZ6mquQuX+8RR1zWMkUbOmcLk6FRK4k2f+Jh0r8/mJB43ZYqsk82OjL4Zaid2KJ/+LVu3AmBOn76fJQ8OgYBBa5s8sPj94qq02RUWC1RVGcydq9i2DaqrxKVcXS1WXC439ll9P9z6Ub6/5Hl+vfEltjTfQXnT+8lQMeZ97h+AlaskpptKwxlLpZdm/wCsWiWdTs49Sx64tmyTOs2AXyw9T7GIdDYrbnalZLkhufP79JgdzYGhO5kcI0Sjkinp80nauFKQTCpeXi7unnQG3C473d1Z+gfFajMMqSuLJ6S4OxKRJIFIeHxz3vZFPPYyrTsvw+s7i0lNP9vvDcrlFLEKBKQ4+KPXwYknwm9/J7VVNdVQV2chnVZ0d8tN3emUdlAu16Fppjx0/fne9S7g0NXBjUYmI8c5adJQs2yFAiorDLbvVHzv+2IZpRMQK/w9Ozvl75lOj+2zpvi28ekp7+aiH/dy8az5NDv+Oub9ddjFWjNNcHvghLnwgcukcbfVAr398vc86wwRrKEWcW63TEyoqgS3x8BmEwvVKASFLQb4fIp02iCVKlj5ebnea6qPXbemvvftnX11MtEuymMEt1uEbXBQ+i4ODCqWLy9kHlZK7G32bDvTpkqNWE01zJkjyRtDmZJOp7w3HnGr87SxpOLlUd9Lp7bS1nI1dkcjdZO+d2DilpVkmIZGOPlkubG/8orEdnx+sVwSCbHcamtF3EC6Y3gPoXvycOFwGAQCkmZvsxlUVRlEIwAKjxvOOUsaHztc4LRJU2ln4SHBOsb/8h2xaayKf5GPn+TmT5tWc4L7f8e8v5msuB+tNrHA12+A7z8KjQ2SiFJdBSteh5/8BF78h8Tl4jGx3BYuMLBaDbweKC8zKC2VaRgOuzyMdXQYJBIioH4/VFbI9o5VcdOMHy1wxwg2m4HbDTaborNb8dxfRm5yhiE3lTfeyPLLp6T2DUM6TqzfJFO6Y1EpGYjGxv7ZDkuae0/+HA8t+TgfnvKj3d7L5fpobf4QBjYamn6G1Va83+3lTUl3nz5NEhRmTJdMyv4BmDNLXhsclBhhbe1Ic95kUuF0Hbvuq+EyiJDC4zGoqYWt22BSvXyVlkrMSyEWTVNToTn1OJ5Yntj+Ed4z73waiyy8tvmbWFVwzNtIpQpTD5zy89Zt8JOfwcqVYllOmyF/661b4V/LwbDKBIKeHhnh1NWt2LbNpLXNZP16k95eRUmxoqHBoLzcwO+X8gKbTQRRo3krOgZ3DBCPy7SArm6FmZcn9upK6fLhdovLKpsEi93E4ZTgfzQqX36vFH3b7ZKxOB6+dMLdzC7eSF5Z2BQeacWVzXbRsuNSctkeGqf8Boezab/bcrkkQaK6SuJvc2YDJrQ0Sxf9RBLsWUkmqazc/aYWjoj4HctUVYnr0WpVVFZY6O836emRYv2TFsDK1RKbXL8RYnGx0Pv6x16or7DwjXX3cuOZIT73+39Sar2H6rq7x7y/yVTBTVnwMJimWJUv/UtibqaCIj8MBGH7NnkQW7VGuuk0NonL1TRgUh3YsuOrydQcv2iBOwZwOuWG7/XC1u2w4g1x3RQFpEGy3wcOK7R15HHYpM5tMDhiscUTUpA7Hi6p/x2XNf0SgO9u/AxvDJwKQCbTSsuOS8nn+miY/HM83pP3uy2PWxo/e9wST3I4RfCCIYmx5U1ASd3bW4uB83lFJn1kTOk+lBiGQU2NoqMTUIrp0ww2bBTLtbJSHlh8fnlA2LZdMisjERGasRLMlPFI628oLbuFwYHv4y96B17fWWPahlIjpSY2mzxIxRPiinQUpkKEI1LekMkW4sVpaNkpk+OXLpFsy3RaHniczrEfh+b4RSeZHMXkcopUCsKFMoCOTsmErK6UQH0mK3VHkaj0k1RIwD+RlKy1gQEpjDbHURQMMNW/lR+f+SHctiT/6D6bG197EIWFRPwV2luux1QpGib/Ao9n0X635fPJzdDplH6Y+bxkRTqcMO9EycbzemUywGjuqGBQsgqHygYOBUPXn+3vfwcgd845h+yz9odSiq5ucf/l82LFt7aKG7e5BU45GX79G7km/D7JPh3vmCPTTLBjyzlAhosWfZ9t8VPHtL7VIrE4ZcqDl9crQtfQIOKbzcjDS2MjTG6Sh5zBfvnbh8OSWFJSJlZcSbGM5amsAJvt+Imw6Hvf3tlXkokWuCOUREI6VQwNghz6bpri1kmnFL29Ila5rPSQTKdlAGVRMfz8ySf5xS8fJ5uxobBit5czfdokMrkG4vGZZPMLSCa94+oxCeCxxvnJWR9gsn8nnYlaPvjiLwmnPfT13k9/77dxOCZR3/T/4XLN3u+2HHZ5uvf75EZWFJAi8/nzYOZ0OGmRFDjX1RqjCphScnOfNOnQJhociddfX58inZEM2lxWJrNv3iIp+Rjw3F8gZ8qU8PY2GOezDCXqNyxf9zE+dGIRHa6X6U1VjXkbhjE04FSuY7tdBM3lglRSJiOUlckDjc0GqQQsOkkeygYHpcuJu5D1mym0bisrgalTwTrWTJqjjCPx2jtS0PPgjkIshbE14QFFJiuF1za7xKecDrF0SkvFHeWwW+jqMgmH5UawbQf09bux23zksnni8SyJ+Dq2bf0TSg35Iq24XHNwe0/G7TkFj3cJdvukA0zQUNw2/7+Y7N9J1rTx+de+SWvPH+nve4BMeitFxf9Odd1/Y7XuPyBmscgTeyAgY2Dq66C5WYqDT1sMZeWSOeh27906i0al7dPblUVnXbsWgPyJo9fyvZ1UVMhkiB07FBabiENLK2zaLNPOp02HN1bI9IFQaPxxVod7CZ86tYQHXg1y/8Uf4fGOZ8ipsc2OG3qYyuVE7PJ52depU6C6FkoC0oAgEYOFCyR2uGmL1MO53VILOblxqORFrotwVEoiSkvUcCatRjOEtuCOcIb+PkPz3XI5RSIpKdWDIYmlDRQGfnrcIoDZnDyxN7cW0srtkM9BJGISi/XQ072WcHgFifjrJBMrME1pOGmz1+LxnobXexoe71IczmkYxmhPxor3TfoF55Tezq0vzWJF20byuT6crrlUVt+KP3DBAR+f0yk3q+ISca0ODMpcsUsvFdfWpElys1500uhNeIest/p6Dnkm3eGsg9sf2azJylVSsO/1wYsvSlZiWRmsWFFIJHJIxuJ44nEAZ1Q8y0trriaYVNx20Ud5cMs3JrTPToe4zW02KRMoLZXXsnlJPFl0krgpp0+T6zdWmF6ezclyAb88AHncxnCLOUfhenI6xUI8VrIrj8d734GiLbijmGhUujsMkUpBWytE4uAoFMFiSgwrEpZ//lyukB6el5uZtRCLy2Qt5PM1ON01VLhEhJTKk05tJBF/hUR8OYnYP4mEfg2AYbhxOKficE7BYjgBhcIkl+3i7vUb+Ho+jGFE8AWWUVJ6DV7fWWNK0bfZ5Em+uFhuSibiXp09W2IsmYzEjmbMYK8d5kNhiescKzey8WK3W1gwT/H6G4oqr7h6+3rE3VtRIeIQj0NVtTQ8Hk+P0Zf6LuSd86/n2y98n9+9+TiXzp7HU60fHNf+DhVuF/nFIuvtkzhdbbW8PhCEp38n13VTY8H9bIiAVVeJOzuTlQc9ZcrvLpfCNA0SyULiSgbsDkVV5fF9bRzPaIE7wvH7pVXTELkcFBXJhO5UUiy0E06QOEZ3twjijp2wfadYQ0pBKCg3uKHejrtiGFZc7hNwuU+gtPyjKKXIZHaQjL9KKrWRTHor6dQGlMphwcTEgs1WTaDo3Xi9S/EFLsJq9Y/7+AIB6Z9YXi7p7/PmSezNVDKCJeCHkuLR4yu5nCISlmQFjRS7V1cpMGDeXHg5Cps3SeeXSAhcDklAKS+XDMXxJBf9ofcuPr74TR58+XUW19/CSaXTWDm4/wzZXTGQ6zKdhr60POhYLdKcORyU5CITKK+AqjKx2vr64ORFYpHmc4VC8kIrslBYCv7TWXFV2u0GdpsIu3ZbHt9ogTvCyeWkkXA6XSicNaWwucivyKREHBJJyYgcGBRRCIZELECees1CL78DqSEyDAOncypO59TdXvdY4/zg9GvYFpnOHatvH3P85a047OByw5yZ8ntnhwjVUMFyc7P87vXu/QbV0ys3sWO1sHs8NDTIVIgpk6UV1utvQE+PWHT+IhGL/gFJuY+No6hfYWF54pdcMvMU7vxHH7/494/Rnfw9nckDH62jEA8DiCWXy0HegFxYromubrHa/D5IZiRGF43Cm6sk03LaVPDawV8NVouB1SrjdZRSGIaBaSqyWT04VaMF7ogkElGEQvKz1Sap4B6PuPJsNoOOTmmoHIlAMg1rVslMsExG+vJFoyNPyImEuKYmgs3IcP+pNzKneAMzApv5dcu/szq4cPzbK9RD1VZDTsFAHwSKoKYWaqrkGCZPgWTCoLp69G30DyicTj037K04HBbKy0yCQUnKWLQQ/vWytGVbsUKKwGNxwJA6yPG4KpOmj0TgaaaVnsvHnulhyvQIMLbZcaYJdps8fDkdsj8gYpfOSPJJb1+hn2UezjsHUoVM0e3bpdTAHwWPV+F2yTXlcMhGLBZD18tpAJ1kctQRi5msXQc7tku8LRSRxIJMVkaqtLVL/CGVGrH4JoKByTdO+n+8o/6PAPzXm3fx27b3TWibTrv0TDxhLnR1iZty3omwYAEsWmjQ1QVeryqMitlTwAYG5Am9uvrtFbeh68/66qsA5Bcvfls//0AJhWTyQDAomYpbtkJnN5QUQUe3PFB0dcvstnBk/J9TbvkLL635KA7nVJqmPrPX8UcHisspQqUUWKzye1mplMBUVoirtaJClhkaiWS1ShcXlxt8XoPycnC5jr2HHn3v2zs6yeQIJ5dTdHbt5U01UjJgtSqiMYmvRWLyZJtOSTp1JCJp4NGYxCUymYmLGyhumnvPsLg9sPHGCYub1ystm+bPkxhiWam41SorJQ4zMKiwOyAWM5g0afd1MxlFX59kyL3d4rYrR6qwDeH3QyRq0NQEb65WzJol2ZMlReICNgsxLKtVkpAy4+xi028uo67hB7Q1X0l76yeYOeUhkub4e6Wl0mDLy/Vu5KU0IJGQ1mw745Jw5PXClCbphJLLSaeWyU0Ss5vcpIatOI0GtMAdEdhsBg2TRn8vkVD09iqSSalhWr0aMArilpaC6HBIZrplMiOxDYdj4iJ3zbTH+PDUJwD46Y4reXTrx8a/scI++f3yxO10SJPn+SfASQvlyby8XDpvGAbYbYpQyMAwFPlCNqjFkPjc4W7HdaRbcFargc0mU79nTBdr/5RT4IV/SOurQb+4sa02eRhqbhl7r8oh/IFlVNd+g+7Om1lkPRl75UO80H3+uPd9KE5stw8NeRVLze+XjEqrRa6RSAx8bvmf6O6W1m7KLFxHZUq7rjWAFrgjBgmMK8IRSQrI50Sg+gbkZjQ4KLVtVrtYPVarCEQ8Jk+6fr/UxEVjI+UBExG3C2v/yGfn3A/Asx0X8T/rbmY4UDJOKiogl5Hvzc0wfz4smC/uSrfbwGpV1NXJKJTSErnjmkqEcSj+eCTgvusu4Miqg3srRQFpc1VZaSE4aOL2QFMDvLIc3vs++MUvpLA6lxHrPxgc39QBgNLy6zmj9P/4/oqd3Hz6Jzix5CnWBudPaP+zBQsTU67/bFaszro6QEmSUl7J+/k8dLTLMosWKsCAfoU/ACXFR8Y1ozk8aIE7hOTzhaa4u2DmFT298nP/gDx1Goa0IRpKl7YWkjAcNrlRZdJSrO10Sh3Q1u2g8lBaIv/cXd1ygxqa/zXRpBKASDbAYLqUbZFpfOXNu1ETnKxUXSUxwdISOZ6myRJTcTqkyNduU0QiBsXFCpfTwOc7tlsvHWq8Xhn+apqKqiqDWFxxwlxobZFxNYtOgldfkwL7JiXuwURivJacQafzj1w29wy++a8BPn/a5YQ8z9KWaBr3/tvtYrG7PUOfIPvW0SEuyWQKJjdATR3EwpBIyTLP/00GotbWgscFNrvC64W6wlgln+/IeVDSHHq0wB1CrNbRXI8GjY1qOLVdKYVpDqXxSwNdkPjU2g0jFlomLZmGHg/4A9DWBlu3SEFsJiNuv3B4fFlxo7G87wz+/e9PkVc2sqZjQtsK+EWgXW45lopKacPldUsqOEj3ipISRTBoUF9/EA5AQyAg1llxsUEwCCfMleScp34DZ5wuVpDFAj6PjOHp75eHo/E0ZQ5lK/D7/8yHTjyf+5cPcM3Ci4naXyCUHXvPShBrDABDXJQerzwM2mziknQ64cVWiSk6nfL/YxRKYtrbRAgDRVBaDBVVMuA3m1UopcXteEIL3GFg17otw5A6HpCbjcup2LBB3I1DHsEtWwpP16ZkTUaiki6dycrrpjm+mqa3UursJ5Vzk8hLNtxAumLC23Q55UaTzYjQNUyCGTPl6dznl84a/f1yE87n5aZ8vHclOVgEAnKjLy4WSy2RMGhsgPOXKVaugKoaWLtWRhH5fDL0ViYTjO/z2hKTKSr5FZ9YdCn/t6KX0yadgavkBVKM/4klnRZ3fd6UbjcWq/xbWK3i3k6n4IQTobFe3PcWZJl0WrwixcVyPIOD4sYfGo4LInjptByzzKvT192xhha4w4BSari3ZCYD4bAiGpUC7WBQLLGePinWbm+Xf8B8fqQTidUqLqVUoafgwRgCWeIY4JGl1xLNBvjUK/9HPOeb0PYc9sJNySM3qMoKueE2NUF5qdxQAn5pL2a1QlmporPT0F1JDiJWq4HTpUgkFAG/QWtQUVSkqK8V1/e69WLZdHZKMkqmELdVSh6cxsO60ELOrnqU7178MT775yCV4dPwVj2BzX3OuI8jl5cMYXu5XDfKkGuquUWmC/zrX9A7TZKUJjfBonni3o7FFAMDMGMaw5PQN24ysVrEBep0GTgdcv3pXgHHJlrg3ia6uhTZnMwta2mVfyq7XeIE23fKU6bHCzZLoclwnaRC19XKzaarR97LK3HRpJIiehMvBQC/Pcz3TvsYU/07yOTtzAxsGnP7pV2xWOSmVFwkomZYxLV66ikyYTqVKqR2m2K9LVpk0N199HQlSX5jYk2G305KS6Qtl8cjAhCJGPh9ilAYzj4TXnhROousWSeTHNweaG2VayudHt9nvthzHt667/DcVZ/n8l/n6Nh6GT7/hVRU3YTbc9K4j6WvX4rUp02Vfc5lIWMRz8bmLSKC8QTY7eZws2WnU47faoF83qC0RKGAbFY8BoYhoqm7nhyb6ELvt4F0Wm4olkIyCUrJTKu0dCCJxUTE8lmp57EYkoAyOCgW3lBMpLdXYm6RyOh9JceDxxrn4dM+xvzS1WRNG194/Vu82HPeuLdnMSQeaLOD0yXupKbJcOIcyYALRWD+iXJsZaVy0wWDdBoqj/CmuEfr9dfdowj4petLR4fC4VS0tEjcLRSEPz8n7u7Nm8WNZ+ahtV2us/GWDwCcWLKa1f1TGOh/hIH+hzDzIVzu+fgDF+P1nY7TNXdMfUydDvEKuFyF5spOuc78frnO7A4R9KIi6VlZUbD4kkn5X/H5JLHJbjcK43qk/CaZkpif02ngcsp1OzSj8EhJSDlar723Az3w9DCRzUrSiFKKRFy6Rpim3DjWrRcrzOWSzEiLRcbeJBLyFDoQlH/oTLrQCT4h/4QHw2IbwmlJ8cDiGzi14jVMZfDlFffwbOfFE9pmcVEhxdsmx9TUBAvmyQ0pFJa4idslEwJ6egxqahTd3ZJY8nbNcxsvR9JE77EwdB02TDJIp6VYPp1WdPfAqacY/O0FxZatMuV9w0ZxHYeiEr8brxX3VvL5KN7UPWzsepVkYuXw61ZrKVZrERZrERaLG4miGWAYGBRGDmDg9Z9DecWnh9dzuUS8KFQFuF2SfOX3STF4cZG8N2c2TJk6Uhje0yPfnS5xz1qtxnCCSlnBu5BOyzWczcrDpdUKdXWH99o82u59bye6k8khIJcT7bdY5MacTitisULKvyH/FDab/BPZbAamCYmkdCKJReRGX1wiy6aS4l7p7BR3yvJXZLuDQenLl8kePHfkEB5rnP9d/ClOLn8dgDtW3z5hcfP7C/cbi+zvlMlw7tmAkjTuxYuhoV6enjMZmVvW02tQWXnki9uuuO67D4DYUSJwdruB26WIRBSBgIHNLn08O7tgcFCx+FRxe7vcIgadXRIzRUkM+GBk5r6z4UXuXPhbnuu8iJtf/RHx5FpSqfXksp3k82HMfKQwlzAvVqNSiDNRvsz87pkvqZS4KH1eSSox87JoMCgPkl2dUvy9aSusWiv/O9kszJlVKBgvhAhqa0QshwrDPR750hwbaIEbJ6GwPOkpU4q0E0lFJFKoX7OLuySfLzwJ5iCVkOQRh1OekFe8Ce0dEhuIJ+TpOZOVYu68OdKPL1doXWS1wEHwSA7z5Xl3DYvb3Wtu5enW909oex63NM9NpeXGM/9EeMfFEjfcvlOSGGbNEDfrpElS5uDxKNxu45jsHXikUVYm59znU5SXQUeHQV2dYvNmOPNMgwULFaveFBdeOi3dcfw+cSt3dIjVM95CcIAm305sljwX1/+BdN7JHatvH9Ng3NHI5cXlbbXK/1w6AyWlYDXA5pT3GhtlMkE2DcWlch4MQ6ZwlBYXRi5FpZmAJJvoa/FYQgvcOCkv2/0fIRhS5E1Jh4/HITUo42uyWRFBqw1Q0D8oN/yhtP904f1USmIFdjvk0yJ6oaAIBhyceNuu/O+GzzGvZDWPbf3YhPtL2u1itUWi8vOcOfDBD4lor9sA06dKgklvn0FVlcQcLVZFImkwSde8vS1I42pFf7/EOktKlZQFmNDerjhhjsGWLWIznXUGvLFC4sBExdKORMBmjP86fHjzp3Hbklw99Ue8r/Ep/PYIX3nzm6Ty7gkfWz4P6ULD8WisUCvqg9o6aeu1sxmWniZNviNhcf1HDKkxtRZKCbq6pUawvFxhtRjDsUe3e8+yFaWkfZwqjKGy27UwHqlogRsnQxe5acqXw25QXCTxjXhKXCTZnCRd5BUEu8R687qlsLa0WN4PhuTmkUjKzSZvyj9pMCip0Aay3MGmL13JZX9/esJF3FZroUg9K7GP+lr43I2wZm2hVVQ5LD5Vmv/6/RLI7+wyUSbU1+sbw9tJIGAQjY2UDUSjMHOG4s1V4s47+yz47W+hogxOOw1WrxGxyO8QN7oqeAxz4ygEB4P7138RCyYfnvoE59c+j9f2GW56/dvDdZcTwTTFCrNY5AEzkZCv6mpJZPrXyxKHq6wQ70pRkbjJs1nwewGLJKjEYlBVpbDbjOFynlxOElFyBVetYSmEJgqXbnFxIR6oOeLQSSYHQDSqCIb2fN1qhXRKXJOZvGRBOh1QVCx1RlI8Kv9wPb0ylTiRkIC4MmRUTCYj860yWUmD7i3MdUsmxnsjGR2XNclX5t3OAxtvpCdVc/A2jAib1yvunxs+Di0tItSxGCxbBh63ZElWVxmEQiY7d8KsWcZhb5o8VoauP9+73gUc2b0o90Yup+joKPR0RNyP4Yj0QD3zdAvLXzVZvRpOPVmiX+s3QGsbrFoN/X0iDtnsRDwKiiunPMEXT/hvALZGpnPjq98d08DU/WGzyf+hQqwrZUpSic0iD5nl5eK6LCuVxgOlJYAhAp5KSTzPXxiK4HTK/2txMfj9h699nE4y2Ts6yWSC+P0GXq9iMKjIFWJq2axkOJqqkLXlkH9+ZQ4VlUpG2pCVFgoWuisUSgBiMUjEJZEklZaODLm8PCXm8uNrl7Q37JYM951yI6dX/os5xev5wIu/nrDlBnIsRQFJlikvE9dkby9YbBAPw0mLoDggbaLq6uTmummzxHmONnHblcT99x/uXRg3NptBZaWMZ5pULzEru12s7bXrTU6YC73dkphx8kKZ9FBZAZVl8OfnpbxjYu5yg5/suJpkzs2X593F9MBWTqv8F79uufxgHeJwCY0B4IGqSrlW/QGx1jIZSMQkbrezRQarOh2SZOP1yJfVIpZaLi+xPYfDIJdTw00XhgrinU7dAeVIRgvcAZLJSFcEWyE70uUEi1UyAg0KY2oKPxuGZBTarBLAzufkn6m7W2JuLpfE2xIpic3l4yP+/Ex2YrVHb8VmZPnvRV/g9Mp/AfDznR86KOJmsYjFVloq7p7yUjjlJGhpE5FuaoKpTTAwIOKWTsP27Yq6usP7JHwwMKdPP9y7MCHcbnGnd3ZJFmEibjB1iqK1DVqaYfJUCK+CjZtg3jxJ0rA74Mwk/OV5uekbSJx4vDzV+u+0xJuY7NtxUMVtVxTiMdnZLAJWmoBsqcQUEylwxOV/M5UsCJoh7xlKwgpl5ZIQZjEgOKhwucUS9PskJGEY8nCgOXLRLspDSCKhhrsl5POKwUGxcFatkeSLZEJGgSTiEN+lM4nVenCSShyWNHcuvIUL6/4MwLc3fI7Ht310wtv1eqWIdqigu7YWzj1HupLkc5KhNu9EGVpaWamIxQ3icVUQPuOo7TU5dP3Z/yznM3vRRYd5jyZGOKyGY06dXQb5nCKTk4e3rVth9VooDsDMmRKLczqlfvPHP4ZMIb4cPQg9UEdQLChdyarBRQdti0NlO6YpYmSzyUOq2yPiZS1YaV6PPGxaLXJNu12FXqkVcq1jiMiXlUlcWcY7yTo260jZwaEqdzna7n1vJ9pFeYhIp0dG37DLo0B3jxrunye9JsUl2dMNvQNSbDrk61dK3Ji71rkdDHErc/bxrVM+w7zSNQB8f/MnJixuNptM33Y6xW2VSEiz5NkzJe6WSoo7qKxURvj4/YrePoOiAAT8kpl2tIrbrji/+13g6Be4oiIDwyLiVlEuxeBWQzwMU6fK9bh9h2QDV1bK33/RQrlWf/akXNvFxXKdHwyun/4I/zn7O/zf5v/g4c2fZqLzB2HEMwIjxdsgzRP6+kSYLIXelF6vCHppmYjfpAYRe4cb6gr1cpZCjafHMxJKyKTlZ+kWIw+zuyagOZ3HxnV/NKIFDqljG4qP7ZrUZxiFGrRCfUwup9i8WZHJ7rJswS2pTLmpDwxKV/befhG2ZFK+UkmZQmww8oQYi4t/38zvpo8Tps7Txg+WXkONpxtTGfzvxs/x+Lbrxr09t1uOddYMeWIvLoLeHpg2Hc45SwqD/T6J6djt8nRcUXjKHYpddHZK/ZvmyCLgN3DYFT09BkUB8TIkEtID1WGXa3TTJkkwmdwERSUwf57UPT75C3lQm1QPbe0T2w8LeRaVSV3mJ2Z+j3pvO19bdedBcaePhs0qMbfiIrHMiv1SJ1dZIWJl5iXe6CokivX1yf9tPi9WXTAIFosUzqfyI31VQQ3fM4aaOA/9rHn7Oe4FLpNR0oUkLu6FTFqRyYjwgLgsLBap2xqqebEULlxb4ftgSJJIsnkRs/5BiU/E43KDyGWlDMAwpE4uGjv4dW270pOsoiMxiYAjwpdX3MM/es4d97Z8BddNba3st9MhQfkT5sCFF8jNr6hI3FUuF8yeBV7v7jG2nt6jp5Hy8YjLZVBfr+jrN8BQhEJirdXXGZx7DtTVKNZvlGzKqqwMr21ogHe+A575k1zL1dUwOFCo+xzHPphY+cyrD3HLvDu5tPHXXFL/e6pc3Xz+9e8QyRYf1OMFSQ7LZKTridMuoh6OSWazdDYRay6bleZhxSVi4al8ISO6X2G3S91cZYVBILD7KB7NkcFxEYMbShCxWuVpzO2WeiyAUEgVRs+oYRehzSoXfyoFfQMiUPE4hKNAoW/dUINkU0kczUBiaanCHKpcTpaJxXfvazf0/VBTZA9R4eplW3TGuNb3ecDrl2OdOlmEOxYVd83pS+HfzoE//0WegC0WmD8fmhqMPUQsElVSj1R19P/zHwtlAvsjk1F0diq27hBLZdZMCIcNenoU27aNNAMvLpHONTub4aWXgEI8rrdXrJnx97BUXDvtB9w459sANMea+PQrD9OeOHhzlCyFeJrNJp4Xo+CidDnA5YHqCikfwMLwvDhvYRpDcTGUFEt8bijBTCHL2GxyfyktGXGNOpzg9Uw87qxjcHtHN1tG/nFjcUU6JcKVyYCz4KJwOQ16+hRmXl6PRqVVkdsjPnhFYdpxUsSuozCnLZWUejZlirgl0zJTK1NI9TcMsAKq4LdPJg9uhuQQJY5Bbpv/NX7ZfDnL+84Y93bs9pHUZ4tFRt2UFMtxpDOSKdnYJP/A/f3Sjb6+DhYuALd7z8zIdFrR08NR0Uj5QDgeBG6IZNJkzVqJD9fWFLwOWejsgFRGPBulpfLam2/CzlZ52AsV5hkmElILOV4uqP0Tdy68Bac1QzTr56tvfp0Xuv/t4B3gLlgshdo5p1hvQ89oDrv8/7s94rWxWMTas9qkPAZDRN5mk4dnv18enodE0FGYqFFbA8XFE8sc1gK3d3SSCVKrYk3Kk5vdgTQATihaW0GZipxZGGeDuCn+//bOPU6yqj7w33vrXdXd1Y/pefQ8gZHDRHkKCIqsxAUiEHRRo6J+wsIiwbgxiRt3ERMXDWpcg5rVdZEgifohIUYD+IAhqLgKIwEEDQMchqfDTA8z3dPTXV3Pe+ve/eN3blVNT7+GmZ7urj7fz2c+1XXr1q1TNfec3/m9h/bK5C2XpFNw1nQTTsahr0ec8S/vaWpo2RwkUlBNmZ5ucSldVS7J41xpbWf2/5xPnnwt/ekhju/5FW/78Q8OullpLCaNI0NHFq6+XvE9xOOyaI3sNV0PkjKxj9oAR2+QAJO1aybfnfp+yK5dUiGjHYRbK8WvfnW+hzDnZDIurz0l5PkXQgpjsGatBFO4rmwQdw7CM8+IWX75Cgm7371HXncc0xbqEATcPTvfwu7KCm447cN0xAvsqRx6d/mpiBoPe558t0RCNDbXlWjR8ogIq1xWzJU9PRKIksvKvHZdWQ9SKfnKqZRsFHt7m4WdIwtR1Og42ujmcjYAZS5ZMhrcdHheyOCgRET29JiGnZ7sQp95FrbvkHyuUlG0s6ibdrUiN2okvHxfXq/VJFz+UIrTzkTSrfJHm77A+475JgDjXo5P//ov+OGOiw7qOvm87DxrVZnY/csk+Tyfl917rQYbN8Ib3gDHb5JJ+6tfwcpVMLDqQJMkSNDOSzsk+Tuq0t4OLMVddBiGDA1J9ZNch9wXlbIpBO7JRvDlXVK8YHCXmPf37JHoy7LpEF4oiNB7JdaLnuQwr+7eys93n334v9wUROkE6ZQI6njcCCLjeojHZcMXNVTt7JAAlNUDYsbs7ZHjDrLRDQOiDkANIjPumtXRb+MQhLLJXr36QH/1Urz3ZsuSN1GOjUkhZNeRCTtelIkoFcQdntoW8tJ2iZwqVcFtqeRfGDUJ2DWZzJWqqS9Zl4ARzzfmGF+SuH1fjgdmp1atHH5Btym/letO/jjHdj0NwKPDJ3Pto59lZ2n2lYvjcQn8SMRlnMuWSWTn7iEJd/Y8Cfk/8QRJ9u3udkglQ554Etavg5UrJze5BEHI4KBUjejqbB/hBi15cN/9LgDeJZfM84iOHLVayK5dIaWyzBvfE5N9aMLgw0CCUPYMiTDwfXjkETFXBqGkkVRrIhQOpcdc0q3y+VP/hG88+/s8PPy6w/cFpyHy3Sfi4lOLx40fPynfPZWETE58ltmsicrsknkVmS87OuR5NguY9SWdljmXycCKFdP76ayAm5q2EHDVakg+30m5XJhVNF6tJg0dAcpl6dwbmQbKpv/auKnoH9SbJbO8KviBnBOF+8Zjct646cLteXLjeqaB4vi40dqCufGxtXLFq77GHx73N7hOiB/EuPHpq/n6tiuph7OzNqdS4kvr7aXhQyiVZQceBCL0NqyFY46WneQxx2AaQjqMFUKWLYPl/ZMLN9+XXKp8vv2EGywtH9xUlEqSShCGIR2dsvA3alOGYt73PFnkh4bgZ/fLhm/VADz0kPivo1y06PFg+OhrPsOlR3+LIHS4d+d5/O22D/D02HGH9TtOJCrblUyIK6KrQwQUmLnhShH1dNq4QBKmKkpGnqdMXmG+03QLN615+pc5EDYDUkwbPHNh2Sh0mnlkBdzULHofXBBIseNKRYrCEoYkjWkgm508/DxqmliuGJOjLzdizBRcjWrwvbxL7Oyj+8S8ODomwipK0qwHNCInXVP1wPNEqHne/jfnYU1mm4LB8ipcJ+TpsWP55GPX8fi+E2b93nRa/vmBiQ6tidaZzUiY9zFHiXM81wnr10qpot1DkhsU1CUcetmyye+lYlFasfT3t5dZ0rI/2axDNitzZGwMhk0/tmxOtBGlJOcxlYZ8l8OK5ZJisO1pl02bAtatkxJglYpYPqJ6rrPlW8+9n1P6Hua4/FOct3oz563ezE8Gz+HmbR84qLlwMNQDIJA1pFSO8t1E80qnRZB5VfFhO4jJP+oHmUlLik1vjxGAcbEALes3JtDGVDHpSVWzUQ7sPDocLGgNLgzD/YRXZ2cn+/aNUSiEDA1LB+yo8nf/MplUqaQxoZiCyEEgEyjyifmemEte+I2YT3a93Kwo4tdFcJUrpjqB8UFVazT6P/n+kQnzB+hK7OOKV93EPz7/XgbLAwDEHJ/fXXsH399+MX44cyG8VEomYtaUJqqZDuG+L8ePO1bKD7mOVKuIuZLwWq3K5NywQXyP/f2TR4KVSiEjI7LILVsmxXzbFavBTY7vh9IDsWrmS1U2O329EoTy0nYI3SRbH69RKUH/CmOyrMiGcmhI7jffBxwJzJpO6MUcn/MH7uaKY2/kmM7nGscf2P16vvzkh3li9DVz/6UnkEw0/XXd3cb/nDFzz3QD6ugQ4dedl3/L+owVqW7MvUiAWn+/CMRVq5rzbS40uDAMG2uklBpbnHN3wZkofV92K5FWNLw3lGx/VwqYVipSLaRQkJtmfEx2e4VSglrFkwgtpHhxsSQCqVIWQZRJSxv7zg7JaXEcYzNPy2RKxEVAbd8Bw0OyIyuXZTdaMT2f5jI4ZDb0JPdy8drbufxVN5FPjvG97Rfz549+5qCukUqZfB0TGOBgygalxcSyakA0s917ZEKuWS1CcOVKqJQdunvAdSRYJJM2WrKJsgT5jcJAdqX5fDOvsJ2xAm72eF7ISy+F9PbK/Bsby1GvF9n+kuTOeWbjOLhL5uO+faakXVHut3hCtKK9I3JssmXKIeC3V93LlcfeyHH5pwD4s4du4F8Hzz9i39N1m2kGcaOdpZKAKxvsKE8uFhONLZuTA/VAUg7icdmg53Iyn+IJqfjTkQUcEZxBAOlMimqlSiYLq1Y2y/rlu+Tzs1l5Xqk0NwueSVdKpURoxmOOdC6pmkEZF4UbE0Hc2WG6pNTM+/1Qygh6EmDU27Mwi6QvCBOl54kfDAe8muz4QprVPUQtl47CpbJoVVGPphDJRan5DsN7ZFdYqUhbj1LFNAqty4QYHpKJU6uZhoTmJol8ZvV6s1GhG4PAl/OjKiWRAIzqzM21Ty0i5VZ4/fL7uWjtnZy94j4SrpQ6KXgdPDP2Khp35ARai8k6joQu5/Py3SLfSLUmu8UV/VIlvbenGe592msjM69ZVDypITk26hCPO2w8pqmVRU1eIZrY7S/ULK+MRMJh3TrxyeVysH59jG3bHDZuDFm+XDabO3eI9WBoSO7TqGlpuSIuA1nYxaVQq8rx1jnpuC4/GjyPHw2eyxtX/JS3rP4h9w6e2xiD6nqSM/q38P2Xfpfh6qGlGURRoJHAiohcGa2ViRpCL0ZjDYvFZJM+PCzzzHUkwjKRkAISTijftbNTrtHdLY91I6iSSZ9q1QS2ebJRjZLVs2nJWU0m5dqOI+un70tCeiwm2mRXlwjEVEo2rIXxQDYWpvJS3XSJSMSbaUFRkMzh6poQhqHRGI/M2nHENDjPk+jFyKkaaQBRf6XI19UYj7Fn7zWRi2EImXSGsUJZlnlXclKiGyjqARUJtcIYFIqi2Y0XpXZcudKsLhCPyedFwsyJdjMmj8eNyedHdveKSRCv++LDKhbFlFI1hVajYcfjLdcy3a69WlOYQ1PA+qaG3TnLN3PdideSiZcbv1fB6+SunRdzy/NXMVzuo9bikE8kRJMKzU7QcURrzeZk95iIi41/7Rq5mT1PzJLpdAyHeqM3VtZEcXX3ilaXSoswy5qJZvtc7U+kwTnDwwCEfX3zPKKFTxiGDO8F182RTo1TNJ0lqjXRzgoFk19n5kphzLSV8mWRjtJxovqQo2OmA0epGdjVWjavHjRdE5866X9wwWrRsl8oHsWjI6fxyPBpPDx8GsPV/oYWtP+mTf5upDUY/3u0EEa1JSNXSCwu8w3ksyNBHT1GgiyXaxZjjnJOXXNdx0RV1gPTzSAmgioShK4LqVQcz/f3++woXy9jIjfjrqyV9bqMKSpUEXUf9zxJ2C+WzOYhJfO8q0uuk0gYwWM2yp2zCBTzfTFzer7pZek31/To95Ufrvn7uY4UiThc7owFZ6KcCd8Pmyq2yS3zPUinc4yPjzd2cVGJnIYTOBCNrFhqFjmOtLmUyVsZNzb/0YJcOxEX9TtjboTQgbgDTsyE+ZuSXdWyXGc8am3jN00TgWmKWDSTzqs1fX8xV26+rlSJjR2adckn2Zj5d77+3NXsqq3DdWBDx/PccspF1MMYj42+js2738r/2/MfKVbT1E2occZUVMjlTAqD6THX2yPjT6ehJy8JqB0dZsdbFgEcVVToymdIp8r09TVvbNdxTJRke/vPDgc2ku2Vk0h08PzzBdwY9HSLbz0MQ4olMU1Gd17FBFmMjkltyz1DRpDV5V4ul8RqUyjIPKuZ5GyvJkIwEW8Knvf1f57z+/6JbKx4wHh2VDdw995Lubfw3oYFpFaVoKuwjtk9i/DBbJpdp6VyiRFqYWCqnMSagi+XgXy3uAB6emQtqVWa38ONyZyMRWZNl4bZMtIICeX1dFrmc29PBig38u/iZn2KktODQNaZTMZYZ8qyCaia3yWZlE1slPeaSMzO3Fivh41Sg5Egi9Y3aAr4RLLZKzMqLn2ktLRFJ+CmIlpgWncNUS6a50HdHA/C5oTxfZMWMCYTCWR3kkrLe0dGJTF1fExMn4BxWMljR05C6rt7RIB0mCIh1apocYVxucHCekjgOsRd2XFu2vd3ZKovka7topftrE49R8xpbmm+tvtT/GTfJY0d5+s67uFXY6cz5neLuTTeLB+USsl7Imdwd5dUEelfDquWi6BKmNykaq1pLkmlZPyRc7u/v4tK5bA28FpSRPdf8tZbAahdeuk8j2jxEP12lYoUc65WZbOWTkMqFVKpOCZnLmw0H40qjBQKsK8gQiJuNqRR1+3IBB8EMLIP9uyWYsjFkgiCgeU1TujbykDtIbpGHqJ77FHioVhKHsj9KVvcKxp++Kvc91AM8uzy1jHsr2Wvu5ax+FrKbh/lsBMHMesEZkMYcyRGIDCaVzIDmaRoaa4rne3jpsdcpEk55v2RxyFmIrsTqWb8QEeHCKqGawDIZXMMD49TKsl382ry2elUszJTZI1yXXl/vks6eqQjH/okBEF4gPBqrZfrmg16wphTm2bLhbMZXpgCrjXhI/o7Si4BUcWC+n7ndXR0MF4Yk6eOA4ls83yvDL54T8MgNCbLkKBunjsJ6vE81apMsMrQburjo7h4pBM1Um6NWOjhV2tUyzXGnRXsSZ/UKLr8mtFb6PafJREWSTtFUhRJhCX5FxTZ2vFetiSultY4Vfgj/83knV0HfO29wWq2+5t4wHsnz4ZniQnD2Lejgq/JpNjjI7tIIiFpDT09JpnUhGR7vqmSYH66hLnx4vHJmy9aDeTQsEEmr5yJ914Yhs1WUlWxiODIglspS13X0AiOqLp/Iuk0TPNRzli9bt6LLPhR8jXIPH/uOQlkKZm81kyyxgBbWeM9zGD+HMqdG8Wc54zx5ofPnHL8IQ5PnfJV9nS/kVoNYtV9bHrheoJkHrJ5nFQWnzS+k8YnRS3MsKfjdPxYJ44DKYp0+S+QSMZIpOKkMnGS6RjJdAI3ESfAhUwPnu9QrUKlWMMrl6lVoV53SGeylCsVkglxHTgx8J0sjuOK5pjwSSb8RkBYEDqS5lSHeuDg+w5+EG8IwWjdcNym8Gr9t5isOQsiyCTxy78ndd9np3w96FhJ6QM/aTxPbvkyyQdvPOC8qMpivX8T5fd/t3E89dO/IvHr26a8vr/uDCrvuAVwGBiA9J3XE3/m3inP373iArZuOImyMTseO/pT+msPTXl+qjJIEDO29i4YHD2TkXCUYnwlpfgAw8njGElvouZ2A5AOQLXk5sUTJqk8YRzCJpy4pxeyGYdk0rabsbQPjiP5dNnsAa8ccG4QhM3Fut4MrIr8YZMvxg75PKxfL8/q9ZDCeMi+fUlGR09mZ+FkSkXZF5eBSuDy6Mpr6PS301nbTq62nWx1O27omauFhKlOujqMy2B8iJUP/XDa7/jihXfgdXfie5AcfIKjf3HZtOffedz9eLFunDis2Xcfp7/4J9Oev/XtW8H4HZNPfIeBX1435blBKs/w5VsaJsTUQ18jdf8Xpz6/ZwOl/3xX43nyp58j8cjfTX3+wEmU331r43lq88eIP3HHpOfW3vgRvFMvn/qLHUaOXKL3YQ9HPMjrTTg9jB3YSDF0E6JOuQnyvUlOeI3T7MqbOJPiyErCRI4gniNMZAniOYJEjnoiS0/nUVzc5+BgbOrO9bgO9DjQ68Bap1kZpdkM0Qosi2UmXNdp+LtfKbGYQ3feoTs/+eth2InnvU986D4M+RAEAU5hN055BKc6CvmNuKa0XS1MM7zu7cS8UeK1Udx6Cadexa1XGv+KtQx+SXx3GWZOnn3D6x3IOCKAngVenP789eubfrT4yPRrieOIufKVE+JMt+ZOXN/DECcMZnfuHHLETJROYRB35EVaw2kaF3cciCUJVp3YPH9sJ874y7RWKc3mcpRKkmsQJtKEfRtbrr8Lp7KPhke48X/pEDoOJDKEXaubA6qMGg9xAmLGK+00b5h2xJooDw1ronzlLPl7L6iDX4G6hxOakNDAM48+TuAT9B4tjjuAyhhuYWcjlDObzVIqmmAZcyxYeXzj8k5xCGc0aqvesmw3QkFjBAMnNc8f24E7umNKYRPGU/ufP/ICbuFAl0vj/GQHwcpmgr0z/Axucc/kP0X3uv3X4kNkQZgow85V1DtXzf78rgHCroH9jjmdnQRTTJKwcyVh58rZDyg9xVbOYrFYDjduDJJS0mQykXLAsXQXQbqr8XS6tQ8gzC0jzC2b9XDCrtXUD0LIhD0bqPdsmP35fRuptygg88WiqEVpsSwkxm+b2tdrsVgWDlbAWSwHy4GRERaLZQHS3k4ni2UOSN18M6mbb57vYVgslhmwAs5iOUgSt99O4vbb53sYFotlBqyAs1gsFktbYgWcxWKxWNoSK+AsFovF0pZYAWexWCyWtmTaSiYWi8VisSxWrAZnsVgslrbECjiLxWKxtCVWwFksFoulLbECzmKxWCxtyaKvRamUcoC7gPOBd2qt/3meh7SgUUr1AtcB5wLrgSHg+8DHtdbD8zm2hYpS6oPAnwGrgK3AH2utfza/o1r4KKWuAS4BFFAFfgFco7V+fF4HtghRSn0MuB74itb6Q/M9nsVCO2hwH4FZdBO0RAwAq4GPAscD7wPOBv5hPge1UFFKvQv4EvBp4GTgAeAupdS6eR3Y4uBNwP8BXg/8NuAD95pNlmWWKKXOAK4Efj3fY1lsLOo0AaXUqcC/AK8FXsZqcK8IpdQFiBbXrbUem+/xLCSUUg8Cv9ZaX9lybBvwz1rra+ZvZIsPpVQHMAq8TWttu8XOAqVUHvglIuD+AnjcanCzZ9FqcEqpTkTruEprvXu+x7PI6UJMSKX5HshCQimVRDZP90x46R5EK7EcHJ3ImjMy3wNZRHwN2Uz9eL4HshhZtAIO+L/A3VrrH873QBYzSqlu4FPATVprf56Hs9BYBsQQ60ArLwMH0T7eYvgS8BiwZZ7HsShQSl0JbAT+fL7HslhZUEEmSqm/BK6d4bRzgLXAicCpcz6oRcJsfzut9X0t78kB3wN2ID45y+RMtOM7kxyzTINS6gbgLOAsrbX1mc+AUkohft83aq1r8z2excqCEnDAF4FvzXDOb4DLgN8CxuU+aHCbUmqL1vqsORndwuaLzO63Axr+kEj7vUhrXZmjcS1mhpAApona2nIO1OosU6CU+gLwbmSD9dx8j2eRcCZiQXi8ZY2LAWcrpf4AyGmtq/M1uMXCghJwWushZFGZFqXUtcDnJxz+d+C/AXfMwdAWPLP97aDhv7wL0UR+R2s9PpdjW6xorWtKqUeQlIpvt7x0LvCd+RnV4kIp9SVEuL1Ja/3UfI9nEXE78PCEY7cA2xDNzmp1s2BRR1G2opQKsVGUM2KE2z1IYMnbgELLy3utOWR/TJrAN4EPAvcDfwBcAbxaa/3ifI5toaOU+grwfuQ+e6LlpXG7qTp4lFL3YaMoD4oFpcFZjgivBc4wfz894bVzgPuO6GgWOFrr25RSfcDHkUTvx4ELrHCbFR80jz+acPw64H8e2aFYliJto8FZLBaLxdLKYk4TsFgsFotlSqyAs1gsFktbYgWcxWKxWNoSK+AsFovF0pZYAWexWCyWtsQKOIvFYrG0JVbAWSwtKKUuU0qFppTZXH3GE0qpqw/h/RvMGC86nOOyWNoNK+AsliOIUuooYBPNOqAWi2WOsALOYjmyXIiUW7KVUCyWOcaW6rIsKZRSv4f01zoW2A18A/jEJL3wNpkWL6cC24H/rrX+l5brnAV8BmnbBPAccL3W+ttMz4XAD2YY40nAXyMV5auItvenWuuJHQy6lFLfRGo9loGvaK2va7nOGuAG4E1Is9GdwK1aa9tfzLIksBqcZcmglDoPuA34JfBW4H8jHSi+PMnptyGdKS5BOlV8Wyl1orlOF/B9RKi9HXgHUpC5e4bPzyLCZkoBp5TqR+qBZoFLgf8K/AfgX02H8Vb+F9KF/R3ATcAnlFJ/2PL6N5DeiR8A3gJcD6SmG6PF0k5YDc6ylPgkcJ/W+vfN87tNr63PKKX+Umv9Usu5f6u1/jyAUmozUg3/GqT1y7FAHviQ1jrqxnDPLD7/zYim9cA053zEPJ6vtR4zn/808CAiTP+h5dytWuurzN+blVLLgY8ppb6qtQ6A04H3aK2/Z865bxZjtFjaBqvBWZYESqkYcAr793UD0dRcxBzYSsMcaYTFHYjAAHgWGAduVUq9VSnVPcthXAhsnqGj9enAPZFwM5//b8ALSEfsScdo+C4wAKwxzx9DhPdlSql1sxyjxdI2WAFnWSosAxIc2Ik7et474fjuSZ6vAtBajwDnmev9E7BHKfUDpdTRM4zhAmbwv5nPmKxb+MuzHGN0DYB3IU0zvwC8qJR6TCn15hk+32JpG6yAsywVhgAPWD7h+ArzuHfC8YnnLQcGoyda6y1a699B/G6XIGbLW6f6cKXUCcBq4O4Zxjk4yWdH45zNGKNroLXeobW+DOhDNNRdwJ2mv53F0vZYAWdZEhiz4CPAOye89HtAAGyZcPw/RX8opVwkKOXfJrlu2fi4vg781jRDuBB4UGs9NMNQHwTON53Xo88/DdgA/HyqMRouQYRbqy8RrXWgtf4F0mg0C6yfYQwWS1tgg0wsS4lPIMEYtwD/CBwPfAq4aUKACcB/UUrVkA7eVwIbgfcAKKUuBC4Hbgd+g2hmVwE/nuazZ0wPMNwAXG3G+VdAB/BZJJLzOxPOfbVS6kZz/GzgCuDDWutAKZUHNiORlE8j0ZMfQbS4J2cxDotl0WM1OMuSQWt9DxIFeSrwPeCPkXyzD01y+rsRDel2JNftXVrrR81rzwAh8GkkevJziOnx8sk+VynVC5zBLASc1noPcA5QQSImvwL8DDhXa12bcPpHgS5EwF2FCOso5aGCCMUPA3cCf4+kFJyntS7PNA6LpR1wwjCc7zFYLG2NUupS4HNa6zUznmyxWA4bVsBZLBaLpS2xJkqLxWKxtCVWwFksFoulLbECzmKxWCxtiRVwFovFYmlLrICzWCwWS1tiBZzFYrFY2hIr4CwWi8XSllgBZ7FYLJa25P8DoGeSFHTGFSUAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots()\n",
    "az.plot_ppc(idata, ax=ax)\n",
    "ax.axvline(data.mean(), ls=\"--\", color=\"r\", label=\"True mean\")\n",
    "ax.legend(fontsize=10);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4.1 Predicting on hold-out data\n",
    "\n",
    "In many cases you want to predict on unseen / hold-out data. This is especially relevant in Probabilistic Machine Learning and Bayesian Deep Learning. PyMC includes a `pm.MutableData` container to help with such uses. It is a wrapper around a `pytensor.shared` variable and allows the values of the data to be changed later. Otherwise, `pm.MutableData` objects can be used just like any other numpy array or tensor.\n",
    "\n",
    "This distinction is significant since internally all models in PyMC are giant symbolic expressions. When you pass raw data directly into a model, you are giving PyTensor permission to treat this data as a constant and optimize it away if doing so makes sense. If you need to change this data later you may not have any way to point at it within the larger symbolic expression. Using `pm.MutableData` offers a way to point to a specific place in the symbolic expression and change what is there."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Auto-assigning NUTS sampler...\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (2 chains in 2 jobs)\n",
      "NUTS: [x]\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='4000' class='' max='4000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [4000/4000 00:03<00:00 Sampling 2 chains, 0 divergences]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 2 chains for 1_000 tune and 1_000 draw iterations (2_000 + 2_000 draws total) took 3 seconds.\n"
     ]
    }
   ],
   "source": [
    "x = rng.standard_normal(100)\n",
    "y = x > 0\n",
    "\n",
    "coords = {\"idx\": np.arange(100)}\n",
    "with pm.Model() as model:\n",
    "    # create shared variables that can be changed later on\n",
    "    x_obs = pm.MutableData(\"x_obs\", x, dims=\"idx\")\n",
    "    y_obs = pm.MutableData(\"y_obs\", y, dims=\"idx\")\n",
    "\n",
    "    coeff = pm.Normal(\"x\", mu=0, sigma=1)\n",
    "    logistic = pm.math.sigmoid(coeff * x_obs)\n",
    "    pm.Bernoulli(\"obs\", p=logistic, observed=y_obs, dims=\"idx\")\n",
    "    idata = pm.sample()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now assume we want to predict on unseen data. For this we have to change the values of `x_obs` and `y_obs`. Theoretically we don't need to set `y_obs` as we want to predict it but it has to match the shape of `x_obs`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='2000' class='' max='2000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [2000/2000 00:00<00:00]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "with model:\n",
    "    # change the value and shape of the data\n",
    "    pm.set_data(\n",
    "        {\n",
    "            \"x_obs\": [-1, 0, 1.0],\n",
    "            # use dummy values with the same shape:\n",
    "            \"y_obs\": [0, 0, 0],\n",
    "        },\n",
    "        coords={\"idx\": [1001, 1002, 1003]},\n",
    "    )\n",
    "\n",
    "    idata.extend(pm.sample_posterior_predictive(idata))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div><svg style=\"position: absolute; width: 0; height: 0; overflow: hidden\">\n",
       "<defs>\n",
       "<symbol id=\"icon-database\" viewBox=\"0 0 32 32\">\n",
       "<path d=\"M16 0c-8.837 0-16 2.239-16 5v4c0 2.761 7.163 5 16 5s16-2.239 16-5v-4c0-2.761-7.163-5-16-5z\"></path>\n",
       "<path d=\"M16 17c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
       "<path d=\"M16 26c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
       "</symbol>\n",
       "<symbol id=\"icon-file-text2\" viewBox=\"0 0 32 32\">\n",
       "<path d=\"M28.681 7.159c-0.694-0.947-1.662-2.053-2.724-3.116s-2.169-2.030-3.116-2.724c-1.612-1.182-2.393-1.319-2.841-1.319h-15.5c-1.378 0-2.5 1.121-2.5 2.5v27c0 1.378 1.122 2.5 2.5 2.5h23c1.378 0 2.5-1.122 2.5-2.5v-19.5c0-0.448-0.137-1.23-1.319-2.841zM24.543 5.457c0.959 0.959 1.712 1.825 2.268 2.543h-4.811v-4.811c0.718 0.556 1.584 1.309 2.543 2.268zM28 29.5c0 0.271-0.229 0.5-0.5 0.5h-23c-0.271 0-0.5-0.229-0.5-0.5v-27c0-0.271 0.229-0.5 0.5-0.5 0 0 15.499-0 15.5 0v7c0 0.552 0.448 1 1 1h7v19.5z\"></path>\n",
       "<path d=\"M23 26h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
       "<path d=\"M23 22h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
       "<path d=\"M23 18h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
       "</symbol>\n",
       "</defs>\n",
       "</svg>\n",
       "<style>/* CSS stylesheet for displaying xarray objects in jupyterlab.\n",
       " *\n",
       " */\n",
       "\n",
       ":root {\n",
       "  --xr-font-color0: var(--jp-content-font-color0, rgba(0, 0, 0, 1));\n",
       "  --xr-font-color2: var(--jp-content-font-color2, rgba(0, 0, 0, 0.54));\n",
       "  --xr-font-color3: var(--jp-content-font-color3, rgba(0, 0, 0, 0.38));\n",
       "  --xr-border-color: var(--jp-border-color2, #e0e0e0);\n",
       "  --xr-disabled-color: var(--jp-layout-color3, #bdbdbd);\n",
       "  --xr-background-color: var(--jp-layout-color0, white);\n",
       "  --xr-background-color-row-even: var(--jp-layout-color1, white);\n",
       "  --xr-background-color-row-odd: var(--jp-layout-color2, #eeeeee);\n",
       "}\n",
       "\n",
       "html[theme=dark],\n",
       "body.vscode-dark {\n",
       "  --xr-font-color0: rgba(255, 255, 255, 1);\n",
       "  --xr-font-color2: rgba(255, 255, 255, 0.54);\n",
       "  --xr-font-color3: rgba(255, 255, 255, 0.38);\n",
       "  --xr-border-color: #1F1F1F;\n",
       "  --xr-disabled-color: #515151;\n",
       "  --xr-background-color: #111111;\n",
       "  --xr-background-color-row-even: #111111;\n",
       "  --xr-background-color-row-odd: #313131;\n",
       "}\n",
       "\n",
       ".xr-wrap {\n",
       "  display: block !important;\n",
       "  min-width: 300px;\n",
       "  max-width: 700px;\n",
       "}\n",
       "\n",
       ".xr-text-repr-fallback {\n",
       "  /* fallback to plain text repr when CSS is not injected (untrusted notebook) */\n",
       "  display: none;\n",
       "}\n",
       "\n",
       ".xr-header {\n",
       "  padding-top: 6px;\n",
       "  padding-bottom: 6px;\n",
       "  margin-bottom: 4px;\n",
       "  border-bottom: solid 1px var(--xr-border-color);\n",
       "}\n",
       "\n",
       ".xr-header > div,\n",
       ".xr-header > ul {\n",
       "  display: inline;\n",
       "  margin-top: 0;\n",
       "  margin-bottom: 0;\n",
       "}\n",
       "\n",
       ".xr-obj-type,\n",
       ".xr-array-name {\n",
       "  margin-left: 2px;\n",
       "  margin-right: 10px;\n",
       "}\n",
       "\n",
       ".xr-obj-type {\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-sections {\n",
       "  padding-left: 0 !important;\n",
       "  display: grid;\n",
       "  grid-template-columns: 150px auto auto 1fr 20px 20px;\n",
       "}\n",
       "\n",
       ".xr-section-item {\n",
       "  display: contents;\n",
       "}\n",
       "\n",
       ".xr-section-item input {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       ".xr-section-item input + label {\n",
       "  color: var(--xr-disabled-color);\n",
       "}\n",
       "\n",
       ".xr-section-item input:enabled + label {\n",
       "  cursor: pointer;\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-section-item input:enabled + label:hover {\n",
       "  color: var(--xr-font-color0);\n",
       "}\n",
       "\n",
       ".xr-section-summary {\n",
       "  grid-column: 1;\n",
       "  color: var(--xr-font-color2);\n",
       "  font-weight: 500;\n",
       "}\n",
       "\n",
       ".xr-section-summary > span {\n",
       "  display: inline-block;\n",
       "  padding-left: 0.5em;\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:disabled + label {\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-section-summary-in + label:before {\n",
       "  display: inline-block;\n",
       "  content: '►';\n",
       "  font-size: 11px;\n",
       "  width: 15px;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:disabled + label:before {\n",
       "  color: var(--xr-disabled-color);\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:checked + label:before {\n",
       "  content: '▼';\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:checked + label > span {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       ".xr-section-summary,\n",
       ".xr-section-inline-details {\n",
       "  padding-top: 4px;\n",
       "  padding-bottom: 4px;\n",
       "}\n",
       "\n",
       ".xr-section-inline-details {\n",
       "  grid-column: 2 / -1;\n",
       "}\n",
       "\n",
       ".xr-section-details {\n",
       "  display: none;\n",
       "  grid-column: 1 / -1;\n",
       "  margin-bottom: 5px;\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:checked ~ .xr-section-details {\n",
       "  display: contents;\n",
       "}\n",
       "\n",
       ".xr-array-wrap {\n",
       "  grid-column: 1 / -1;\n",
       "  display: grid;\n",
       "  grid-template-columns: 20px auto;\n",
       "}\n",
       "\n",
       ".xr-array-wrap > label {\n",
       "  grid-column: 1;\n",
       "  vertical-align: top;\n",
       "}\n",
       "\n",
       ".xr-preview {\n",
       "  color: var(--xr-font-color3);\n",
       "}\n",
       "\n",
       ".xr-array-preview,\n",
       ".xr-array-data {\n",
       "  padding: 0 5px !important;\n",
       "  grid-column: 2;\n",
       "}\n",
       "\n",
       ".xr-array-data,\n",
       ".xr-array-in:checked ~ .xr-array-preview {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       ".xr-array-in:checked ~ .xr-array-data,\n",
       ".xr-array-preview {\n",
       "  display: inline-block;\n",
       "}\n",
       "\n",
       ".xr-dim-list {\n",
       "  display: inline-block !important;\n",
       "  list-style: none;\n",
       "  padding: 0 !important;\n",
       "  margin: 0;\n",
       "}\n",
       "\n",
       ".xr-dim-list li {\n",
       "  display: inline-block;\n",
       "  padding: 0;\n",
       "  margin: 0;\n",
       "}\n",
       "\n",
       ".xr-dim-list:before {\n",
       "  content: '(';\n",
       "}\n",
       "\n",
       ".xr-dim-list:after {\n",
       "  content: ')';\n",
       "}\n",
       "\n",
       ".xr-dim-list li:not(:last-child):after {\n",
       "  content: ',';\n",
       "  padding-right: 5px;\n",
       "}\n",
       "\n",
       ".xr-has-index {\n",
       "  font-weight: bold;\n",
       "}\n",
       "\n",
       ".xr-var-list,\n",
       ".xr-var-item {\n",
       "  display: contents;\n",
       "}\n",
       "\n",
       ".xr-var-item > div,\n",
       ".xr-var-item label,\n",
       ".xr-var-item > .xr-var-name span {\n",
       "  background-color: var(--xr-background-color-row-even);\n",
       "  margin-bottom: 0;\n",
       "}\n",
       "\n",
       ".xr-var-item > .xr-var-name:hover span {\n",
       "  padding-right: 5px;\n",
       "}\n",
       "\n",
       ".xr-var-list > li:nth-child(odd) > div,\n",
       ".xr-var-list > li:nth-child(odd) > label,\n",
       ".xr-var-list > li:nth-child(odd) > .xr-var-name span {\n",
       "  background-color: var(--xr-background-color-row-odd);\n",
       "}\n",
       "\n",
       ".xr-var-name {\n",
       "  grid-column: 1;\n",
       "}\n",
       "\n",
       ".xr-var-dims {\n",
       "  grid-column: 2;\n",
       "}\n",
       "\n",
       ".xr-var-dtype {\n",
       "  grid-column: 3;\n",
       "  text-align: right;\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-var-preview {\n",
       "  grid-column: 4;\n",
       "}\n",
       "\n",
       ".xr-var-name,\n",
       ".xr-var-dims,\n",
       ".xr-var-dtype,\n",
       ".xr-preview,\n",
       ".xr-attrs dt {\n",
       "  white-space: nowrap;\n",
       "  overflow: hidden;\n",
       "  text-overflow: ellipsis;\n",
       "  padding-right: 10px;\n",
       "}\n",
       "\n",
       ".xr-var-name:hover,\n",
       ".xr-var-dims:hover,\n",
       ".xr-var-dtype:hover,\n",
       ".xr-attrs dt:hover {\n",
       "  overflow: visible;\n",
       "  width: auto;\n",
       "  z-index: 1;\n",
       "}\n",
       "\n",
       ".xr-var-attrs,\n",
       ".xr-var-data {\n",
       "  display: none;\n",
       "  background-color: var(--xr-background-color) !important;\n",
       "  padding-bottom: 5px !important;\n",
       "}\n",
       "\n",
       ".xr-var-attrs-in:checked ~ .xr-var-attrs,\n",
       ".xr-var-data-in:checked ~ .xr-var-data {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       ".xr-var-data > table {\n",
       "  float: right;\n",
       "}\n",
       "\n",
       ".xr-var-name span,\n",
       ".xr-var-data,\n",
       ".xr-attrs {\n",
       "  padding-left: 25px !important;\n",
       "}\n",
       "\n",
       ".xr-attrs,\n",
       ".xr-var-attrs,\n",
       ".xr-var-data {\n",
       "  grid-column: 1 / -1;\n",
       "}\n",
       "\n",
       "dl.xr-attrs {\n",
       "  padding: 0;\n",
       "  margin: 0;\n",
       "  display: grid;\n",
       "  grid-template-columns: 125px auto;\n",
       "}\n",
       "\n",
       ".xr-attrs dt,\n",
       ".xr-attrs dd {\n",
       "  padding: 0;\n",
       "  margin: 0;\n",
       "  float: left;\n",
       "  padding-right: 10px;\n",
       "  width: auto;\n",
       "}\n",
       "\n",
       ".xr-attrs dt {\n",
       "  font-weight: normal;\n",
       "  grid-column: 1;\n",
       "}\n",
       "\n",
       ".xr-attrs dt:hover span {\n",
       "  display: inline-block;\n",
       "  background: var(--xr-background-color);\n",
       "  padding-right: 10px;\n",
       "}\n",
       "\n",
       ".xr-attrs dd {\n",
       "  grid-column: 2;\n",
       "  white-space: pre-wrap;\n",
       "  word-break: break-all;\n",
       "}\n",
       "\n",
       ".xr-icon-database,\n",
       ".xr-icon-file-text2 {\n",
       "  display: inline-block;\n",
       "  vertical-align: middle;\n",
       "  width: 1em;\n",
       "  height: 1.5em !important;\n",
       "  stroke-width: 0;\n",
       "  stroke: currentColor;\n",
       "  fill: currentColor;\n",
       "}\n",
       "</style><pre class='xr-text-repr-fallback'>&lt;xarray.DataArray &#x27;obs&#x27; (idx: 3)&gt;\n",
       "array([0.0215, 0.488 , 0.982 ])\n",
       "Coordinates:\n",
       "  * idx      (idx) int64 1001 1002 1003</pre><div class='xr-wrap' style='display:none'><div class='xr-header'><div class='xr-obj-type'>xarray.DataArray</div><div class='xr-array-name'>'obs'</div><ul class='xr-dim-list'><li><span class='xr-has-index'>idx</span>: 3</li></ul></div><ul class='xr-sections'><li class='xr-section-item'><div class='xr-array-wrap'><input id='section-a224efb2-191d-4913-882a-73a4b16b6a81' class='xr-array-in' type='checkbox' checked><label for='section-a224efb2-191d-4913-882a-73a4b16b6a81' title='Show/hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-array-preview xr-preview'><span>0.0215 0.488 0.982</span></div><div class='xr-array-data'><pre>array([0.0215, 0.488 , 0.982 ])</pre></div></div></li><li class='xr-section-item'><input id='section-5292152c-4e8e-4ea7-937d-5a6669f26c6d' class='xr-section-summary-in' type='checkbox'  checked><label for='section-5292152c-4e8e-4ea7-937d-5a6669f26c6d' class='xr-section-summary' >Coordinates: <span>(1)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>idx</span></div><div class='xr-var-dims'>(idx)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>1001 1002 1003</div><input id='attrs-e6d02078-729f-4be2-81d5-3f9046535938' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-e6d02078-729f-4be2-81d5-3f9046535938' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-22b47c07-1831-4dc0-bc3f-575cb4e2216c' class='xr-var-data-in' type='checkbox'><label for='data-22b47c07-1831-4dc0-bc3f-575cb4e2216c' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([1001, 1002, 1003])</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-9fdcb243-f6ab-4a28-80ca-4fed5c87812f' class='xr-section-summary-in' type='checkbox' disabled ><label for='section-9fdcb243-f6ab-4a28-80ca-4fed5c87812f' class='xr-section-summary'  title='Expand/collapse section'>Attributes: <span>(0)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'></dl></div></li></ul></div></div>"
      ],
      "text/plain": [
       "<xarray.DataArray 'obs' (idx: 3)>\n",
       "array([0.0215, 0.488 , 0.982 ])\n",
       "Coordinates:\n",
       "  * idx      (idx) int64 1001 1002 1003"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idata.posterior_predictive[\"obs\"].mean(dim=[\"draw\", \"chain\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## References\n",
    "\n",
    ":::{bibliography}\n",
    ":filter: docname in docnames\n",
    ":::"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Last updated: Fri Jun 03 2022\n",
      "\n",
      "Python implementation: CPython\n",
      "Python version       : 3.9.13\n",
      "IPython version      : 8.4.0\n",
      "\n",
      "pytensor: 2.6.2\n",
      "aeppl : 0.0.31\n",
      "xarray: 2022.3.0\n",
      "\n",
      "arviz     : 0.12.1\n",
      "numpy     : 1.22.4\n",
      "pymc      : 4.0.0b6\n",
      "pytensor    : 2.6.2\n",
      "matplotlib: 3.5.2\n",
      "\n",
      "Watermark: 2.3.1\n",
      "\n"
     ]
    }
   ],
   "source": [
    "%load_ext watermark\n",
    "%watermark -n -u -v -iv -w -p pytensor,aeppl,xarray"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    ":::{include} ../page_footer.md\n",
    ":::"
   ]
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "jupytext": {
   "notebook_metadata_filter": "substitutions"
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}