{

"cells": [
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "view-in-github"
},
"source": [
"<a href=\"https://colab.research.google.com/github/mrdbourke/pytorch-deep-
learning/blob/main/02_pytorch_classification.ipynb\" target=\"_parent\"><img
src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In
Colab\"/></a>\n",
"\n",
"[View Source
Code](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/
02_pytorch_classification.ipynb) | [View
Slides](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/
02_pytorch_classification.pdf) | [Watch Video
Walkthrough](https://youtu.be/Z_ikDlimN6A?t=30691) "
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "r8C1WSzsHC7x"
},
"source": [
"# 02. PyTorch Neural Network Classification\n",
"\n",
"## What is a classification problem?\n",
"\n",
"A [classification
problem](https://en.wikipedia.org/wiki/Statistical_classification) involves
predicting whether something is one thing or another.\n",
"\n",
"For example, you might want to:\n",
"\n",
"| Problem type | What is it? | Example |\n",
"| ----- | ----- | ----- |\n",
"| **Binary classification** | Target can be one of two options, e.g. yes or no
| Predict whether or not someone has heart disease based on their health
parameters. |\n",
"| **Multi-class classification** | Target can be one of more than two options
| Decide whether a photo is of food, a person or a dog. |\n",
"| **Multi-label classification** | Target can be assigned more than one option
| Predict what categories should be assigned to a Wikipedia article (e.g.
mathematics, science & philosophy). |\n",
"\n",
"<div align=\"center\">\n",
"<img src=\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/
main/images/02-different-classification-problems.png\" alt=\"various different
classification in machine learning such as binary classification, multiclass
classification and multilabel classification\" width=900/>\n",
"</div>\n",
" \n",
"Classification, along with regression (predicting a number, covered in
[notebook 01](https://www.learnpytorch.io/01_pytorch_workflow/)) is one of the most
common types of machine learning problems.\n",
 "\n",
"In this notebook, we're going to work through a couple of different
classification problems with PyTorch. \n",
"\n",
"In other words, taking a set of inputs and predicting what class those set of
inputs belong to.\n",
"\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "9wTlTaDKH7Oj"
},
"source": [
"## What we're going to cover\n",
"\n",
"In this notebook we're going to reiterate over the PyTorch workflow we covered
in [01. PyTorch Workflow](https://www.learnpytorch.io/02_pytorch_classification/).\
n",
"\n",
"<img src=\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/
main/images/01_a_pytorch_workflow.png\" alt=\"a pytorch workflow flowchart\"
width=900/>\n",
"\n",
"Except instead of trying to predict a straight line (predicting a number, also
called a regression problem), we'll be working on a **classification problem**.\n",
"\n",
"Specifically, we're going to cover:\n",
"\n",
"| **Topic** | **Contents** |\n",
"| ----- | ----- |\n",
"| **0. Architecture of a classification neural network** | Neural networks can
come in almost any shape or size, but they typically follow a similar floor plan.
|\n",
"| **1. Getting binary classification data ready** | Data can be almost
anything but to get started we're going to create a simple binary classification
dataset. |\n",
"| **2. Building a PyTorch classification model** | Here we'll create a model
to learn patterns in the data, we'll also choose a **loss function**, **optimizer**
and build a **training loop** specific to classification. | \n",
"| **3. Fitting the model to data (training)** | We've got data and a model,
now let's let the model (try to) find patterns in the (**training**) data. |\n",
"| **4. Making predictions and evaluating a model (inference)** | Our model's
found patterns in the data, let's compare its findings to the actual (**testing**)
data. |\n",
"| **5. Improving a model (from a model perspective)** | We've trained and
evaluated a model but it's not working, let's try a few things to improve it. |\n",
"| **6. Non-linearity** | So far our model has only had the ability to model
straight lines, what about non-linear (non-straight) lines? |\n",
"| **7. Replicating non-linear functions** | We used **non-linear functions**
to help model non-linear data, but what do these look like? |\n",
"| **8. Putting it all together with multi-class classification** | Let's put
everything we've done so far for binary classification together with a multi-class
classification problem. |\n"
]
},
{
 "cell_type": "markdown",
"metadata": {
"id": "uxdUc9OfHtgU"
},
"source": [
"## Where can you get help?\n",
"\n",
"All of the materials for this course [live on
GitHub](https://github.com/mrdbourke/pytorch-deep-learning).\n",
"\n",
"And if you run into trouble, you can ask a question on the [Discussions page]
(https://github.com/mrdbourke/pytorch-deep-learning/discussions) there too.\n",
"\n",
"There's also the [PyTorch developer forums](https://discuss.pytorch.org/), a
very helpful place for all things PyTorch. \n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "MSLHJiQxH4jU"
},
"source": [
"## 0. Architecture of a classification neural network\n",
"\n",
"Before we get into writing code, let's look at the general architecture of a
classification neural network.\n",
"\n",
"| **Hyperparameter** | **Binary Classification** | **Multiclass
classification** |\n",
"| --- | --- | --- |\n",
"| **Input layer shape** (`in_features`) | Same as number of features (e.g. 5
for age, sex, height, weight, smoking status in heart disease prediction) | Same as
binary classification |\n",
"| **Hidden layer(s)** | Problem specific, minimum = 1, maximum = unlimited |
Same as binary classification |\n",
"| **Neurons per hidden layer** | Problem specific, generally 10 to 512 | Same
as binary classification |\n",
"| **Output layer shape** (`out_features`) | 1 (one class or the other) | 1 per
class (e.g. 3 for food, person or dog photo) |\n",
"| **Hidden layer activation** | Usually
[ReLU](https://pytorch.org/docs/stable/generated/torch.nn.ReLU.html#torch.nn.ReLU)
(rectified linear unit) but [can be many
others](https://en.wikipedia.org/wiki/Activation_function#Table_of_activation_funct
ions) | Same as binary classification |\n",
"| **Output activation** |
[Sigmoid](https://en.wikipedia.org/wiki/Sigmoid_function) ([`torch.sigmoid`]
(https://pytorch.org/docs/stable/generated/torch.sigmoid.html) in PyTorch)|
[Softmax](https://en.wikipedia.org/wiki/Softmax_function) ([`torch.softmax`]
(https://pytorch.org/docs/stable/generated/torch.nn.Softmax.html) in PyTorch) |\n",
"| **Loss function** | [Binary
crossentropy](https://en.wikipedia.org/wiki/Cross_entropy#Cross-
entropy_loss_function_and_logistic_regression)
([`torch.nn.BCELoss`](https://pytorch.org/docs/stable/generated/torch.nn.BCELoss.ht
ml) in PyTorch) | Cross entropy
([`torch.nn.CrossEntropyLoss`](https://pytorch.org/docs/stable/generated/
torch.nn.CrossEntropyLoss.html) in PyTorch) |\n",
 "| **Optimizer** |
[SGD](https://pytorch.org/docs/stable/generated/torch.optim.SGD.html) (stochastic
gradient descent),
[Adam](https://pytorch.org/docs/stable/generated/torch.optim.Adam.html) (see
[`torch.optim`](https://pytorch.org/docs/stable/optim.html) for more options) |
Same as binary classification |\n",
"\n",
"Of course, this ingredient list of classification neural network components
will vary depending on the problem you're working on.\n",
"\n",
"But it's more than enough to get started.\n",
"\n",
"We're going to get hands-on with this setup throughout this notebook."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "VwvxFEjKHC71"
},
"source": [
"## 1. Make classification data and get it ready\n",
"\n",
"Let's begin by making some data.\n",
"\n",
"We'll use the
[`make_circles()`](https://scikit-learn.org/stable/modules/generated/
sklearn.datasets.make_circles.html) method from Scikit-Learn to generate two
circles with different coloured dots. "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "RGeZvHsyHC72"
},
"outputs": [],
"source": [
"from sklearn.datasets import make_circles\n",
"\n",
"\n",
"# Make 1000 samples \n",
"n_samples = 1000\n",
"\n",
"# Create circles\n",
"X, y = make_circles(n_samples,\n",
" noise=0.03, # a little bit of noise to the dots\n",
" random_state=42) # keep random state so we get the same
values"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "1FwwzJnQV2jv"
},
"source": [
"Alright, now let's view the first 5 `X` and `y` values."
 ]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "oAb8vcIhWEO8",
"outputId": "b7316d88-7733-4981-9b4a-0a98c7cdd829"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"First 5 X features:\n",
"[[ 0.75424625 0.23148074]\n",
" [-0.75615888 0.15325888]\n",
" [-0.81539193 0.17328203]\n",
" [-0.39373073 0.69288277]\n",
" [ 0.44220765 -0.89672343]]\n",
"\n",
"First 5 y labels:\n",
"[1 1 1 1 0]\n"
]
}
],
"source": [
"print(f\"First 5 X features:\\n{X[:5]}\")\n",
"print(f\"\\nFirst 5 y labels:\\n{y[:5]}\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ATakj2bVWBou"
},
"source": [
"Looks like there's two `X` values per one `y` value. \n",
"\n",
"Let's keep following the data explorer's motto of *visualize, visualize,
visualize* and put them into a pandas DataFrame."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 363
},
"id": "XAAqx_8sHC73",
"outputId": "cd6ef4fe-cda3-48db-f2a5-9820660eab14"
},
"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>X1</th>\n",
" <th>X2</th>\n",
" <th>label</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.754246</td>\n",
" <td>0.231481</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>-0.756159</td>\n",
" <td>0.153259</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>-0.815392</td>\n",
" <td>0.173282</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>-0.393731</td>\n",
" <td>0.692883</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.442208</td>\n",
" <td>-0.896723</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>-0.479646</td>\n",
 " <td>0.676435</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>-0.013648</td>\n",
" <td>0.803349</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>0.771513</td>\n",
" <td>0.147760</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>-0.169322</td>\n",
" <td>-0.793456</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>-0.121486</td>\n",
" <td>1.021509</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" X1 X2 label\n",
"0 0.754246 0.231481 1\n",
"1 -0.756159 0.153259 1\n",
"2 -0.815392 0.173282 1\n",
"3 -0.393731 0.692883 1\n",
"4 0.442208 -0.896723 0\n",
"5 -0.479646 0.676435 1\n",
"6 -0.013648 0.803349 1\n",
"7 0.771513 0.147760 1\n",
"8 -0.169322 -0.793456 1\n",
"9 -0.121486 1.021509 0"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Make DataFrame of circle data\n",
"import pandas as pd\n",
"circles = pd.DataFrame({\"X1\": X[:, 0],\n",
" \"X2\": X[:, 1],\n",
" \"label\": y\n",
"})\n",
"circles.head(10)"
]
 },
{
"cell_type": "markdown",
"metadata": {
"id": "FK2T7GpYW2BE"
},
"source": [
"It looks like each pair of `X` features (`X1` and `X2`) has a label (`y`)
value of either 0 or 1.\n",
"\n",
"This tells us that our problem is **binary classification** since there's only
two options (0 or 1).\n",
"\n",
"How many values of each class are there?"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "cV8sVR9tHC74",
"outputId": "dee5739f-1695-4e71-bb0b-de270f08b621"
},
"outputs": [
{
"data": {
"text/plain": [
"label\n",
"1 500\n",
"0 500\n",
"Name: count, dtype: int64"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Check different labels\n",
"circles.label.value_counts()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ytQ5rm9eXa65"
},
"source": [
"500 each, nice and balanced.\n",
"\n",
"Let's plot them."
]
},
{
"cell_type": "code",
 "execution_count": 5,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 265
},
"id": "ANkSmESCHC75",
"outputId": "89b2f9ac-728c-481d-f4ba-6192a8334758"
},
"outputs": [
{
"data": {
"image/png":
"iVBORw0KGgoAAAANSUhEUgAAAi8AAAGdCAYAAADaPpOnAAAAP3RFWHRTb2Z0d2FyZQBNYXRwbG90bGliIH
ZlcnNpb24zLjkuMS5wb3N0MSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8kixA/
AAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOyddXgUVxeH35nZjQsRSAgaPFhwdy+uhQpQqrQfLZQ
qdaeutLTUoC0UaXF3d3cLEiBEievuznx/
LAmEZC3ZBOl9n6eFzNy592xIZn5z7hFJ0zQNgUAgEAgEgrsE+XYbIBAIBAKBQOAIQrwIBAKBQCC4qxDiRSA
QCAQCwV2FEC8CgUAgEAjuKoR4EQgEAoFAcFchxItAIBAIBIK7CiFeBAKBQCAQ3FUI8SIQCAQCgeCuQne7DX
A2qqoSFRWFt7c3kiTdbnMEAoFAIBDYgaZppKamEhISgixb963cc+IlKiqKSpUq3W4zBAKBQCAQFIFLly5Rs
WJFq2PuOfHi7e0NmD+8j4/
PbbZGIBAIBAKBPaSkpFCpUqW857g17jnxkrtV5OPjI8SLQCAQCAR3GfaEfIiAXYFAIBAIBHcVQrwIBAKBQC
C4qxDiRSAQCAQCwV2FEC8CgUAgEAjuKoR4EQgEAoFAcFchxItAIBAIBIK7CiFeBAKBQCAQ3FUI8SIQCAQCg
eCu4p4rUicQCAS5mLKySTx8ClQV3/
o10Xt52nVdZnQcMRt2oZlMBLRoiE+t0BK2VCAQOIIQLwKB4J5DNRg48t73nP7uTwzJaQAoHm7UeHI44R9NR
OfuVuh1xvQM9vzvXS78tRjNpOYdD+7WhlbTP8ajQpDdNmRfS+LM1L8599u/
ZMUm4F4hiBpP3E+NJ+9H7+1VvA8oEPzHkTRN0263Ec4kJSUFX19fkpOTRXsAgaAUyUlKIf1iFJIi41mtEno
Pd6fNbUzP4NyMBUT8+g+ZV+PwqBhMjceHUXXkgAJCRFNVtg4bz6UFa+CW25sky5Rt34zOq39FcXHJd041mV
jfbQxxW/bkEy4Akk7Bo2Iw9+1fgIufr017My5Hs6bdA6Rfigb1prlkCZ/a1ei2+S/cAv0d/C4IBPc2jjy/
hXgRCATFIvNqLAde+ZyLs5bke+h7Va9M3VeeQHbRc3nRWq7tO46s11Ghbydq/
u8hfGpWtWv+rLhrrO34MCknz5kPaBpIEqDh1yiMruv/wKXMjd/
1K8s3sanPk1bnbPX7ZKo9MjjfsStLN7Cp31jLF8ky4R8+T71Xrc8NsK7LKGK37EUzmgqckxSFSkN60G7O1z
bnEQj+SwjxIsSLQGAT1WgkLSISTdPwrl4ZWa93eI7MmHhWNR9KxuXoAl4OS0iKgiRLtJ8/
hQp9O9scv2nA00Qt24RmKlwIVB7Wi7Z/f5l3bPPAZ7iydGOh4wGQZQJaNKTnjjmYsnNIj4xCcXNl3/
MfcWXhOsvXAS4BfoR/
OIGQ+zrgWTmk0DHJJyNYFtbb+oeSZQZe2ohHiO1tKGNmFprRiM7L066GdQLB3Yojz28R8yIQ/
MdQjUZOfPYrJ7+eQXZsAgCu5QKoM2E0YS89hqyz/
7Zw5J3vyLgSY7dwAdBMJjRVYsvQ5xhwfh3u5ctZHJt24TJXlmywOL9mMhE5bwVNvnw1b57UiEirAgRVJS0i
kgMvfcKZaXMwpqQDILu5Wr8OyElIZM/
T7wBQZURvWv78ATpPj3xjEnYdtjpHrg3X9h2zKl4uL1nP8U9+Jn7bfsDsyao9YTTVnxiGotcjySJZVPDfRf
z0CwT/ITRVZftDL3Lo9a/yhAtAdmwCh17/iq0jnseUk2NznqzYBM5MnUXEL//
kj+mw2xAN1WDk7M9zrQ6L2bDLpjDSTCrx1wVD0pFTZMcn2VzekJrOya+m5wkXADUr27bdYLZH04icu4LNg8
Zxq/NaUuy7rco6xeK5E5//yub+TxO/82DesbSISPY9+z5z3Rryt74eG/
s8SczGXfbZLBDcY5SoeNm8eTP9+vUjJCQESZJYuHChzWs2btxIkyZNcHV1pUaNGkyfPr0kTRQI7glUg4GoV
Vs4/+dCYjbsRLXgQbiydAORc1cULgg0jcv/rmaOawMWVevKiS9+w3T9ga6aTESt2sKpb/9kfa/
HWBDSnj3PvItmNBbDaJXYTXssnjakpXP0/R/
smkqS4OLc5axoPJCsm0RZ4YNBzc4pEJTrKJpJJXrNNqJWbM53PKhzK7DhFVHcXAls06TQcymnznHg5c/
MX1iyUVW5umor67qM5uwv8xy2XSC42ylR8ZKenk54eDjff/+9XePPnz9Pnz596Ny5MwcPHmTChAk8/
vjjrFq1qiTNFAjuas79sZAFFTqwsdfj7Bj1Cuu6jGZhpY5EzltRYOzxT3+xa87085c58PKnrO8+hstLN7C4
ahc29nqcfeM/
IHrVVpvbK3ZjJYbj8FvfknExyvYUssy5vxazbcREsyCx4gmSdApIskPbXLbY1G8sO8a8SkZUDAAeFYKo+kB
fqwImsE1jXHy9Cz135qc5dnlvNJMJNI3dT71FeqTt75NAcC9RagG7kiSxYMECBg4caHHMK6+8wrJlyzh69G
jesREjRpCUlMTKlSvtWkcE7Ar+S5ybPp+dYyZZPB/cox2tfv8Ij5Ag0i5cZnG1bo49uGUJcoc7+1Yhy4R/
MIF6k54qcMqYmcX8cq0xpmU4dUm/JnVJ3H/cqXOCWRS5lQug0/
KfST52huxryeyfOBnNYNkz1WXN7wR3a1Pg+Louo8zbZfaurcjUnfQU4e9PKIrpAsEdw10bsLtjxw66deuW7
1jPnj2ZMGGCxWuys7PJzr6xV52SklJS5gkEt42cpBQi560k40oM7kEBVBrWC723F/
tf+NjqddGrt7KsXh9qTxhtjp9wVICoJfduI8kSLoF+qAZDgUyn9AtXnC5cZBc91Z+4n33PfWBVVBQFzWgi8
2ocKxoPtOt7LCkKxz/9pVDxoni4m0Wjnd97zaSSuO+YoyYLBHc1d5R4iY6OJigof/
R9UFAQKSkpZGZm4u5esOjV5MmTeffdd0vLRIGg1Dn59XQOTvoCNduApFPQjCb2jv+QykN7kXMt2eb1hqRUj
r4zpRQsdQzNaGLPk2+yf8KHtP7zMyoP7pF3TnF1sXJl0VBzDOx95l3gep0YZ3uSHMy4il6zDZPBgHKLcKs0
qBtRyzY6tHROknhpE/y3uOuzjSZNmkRycnLef5cuXbrdJgkETuPsz3PZ//xk1Kwc0DSzx+D6nxf/
Xnq7zSuIJFGmURg+9WogKYpZJFjJqgEwZWSxdcizXF23Pe+YZ2hFvGpUthoTUyQ0zbwNdoeUt9o77v0C2Up
VHuiLR8Vg8/fPTuJ3HiJu2z5nmycQ3LHcUeIlODiYmJiYfMdiYmLw8fEp1OsC4Orqio+PT77/
BIK7jaQjp4hasYmEvUfyHmaq0cjhN7+
+vYY5gKRTCB01gN4HFtL36DIGRW+l2XdvUu+VJ6g6aqDN681eketzSRL1X3+6dESGToGbNVKuYJIkkMC9Qj
kq9O9i3spxMhHT5rCuy2iSjp25YY6HO13Wz8Cjcnn7J9I0jtyB3jWBoKS4o8RL69atWbduXb5ja9asoXXr1
rfJIoGgZIndupcVjQeyvGF/NvZ+klXNh7K0dk8uL1lP3Lb9ZMXYSPu9Q5AUBZcyPjR897m8Y26B/
tT630OEf/A8ifttx2Sknr5grtR7ndDRg2jw7rN58yNJ5mwhZyHLVBjQFbeAMmZvTK44uS6YXPx9afbdW/
Q7tYqOi6bSY4f1mjRFJXbjLlY2HUz02hueJ5+aVel3aiVVHuhr9zzRa7eTfS2pBCwUCO48SjTmJS0tjbNnz
+Z9ff78eQ4ePIi/vz+VK1dm0qRJXLlyhT/++AOAsWPHMmXKFF5+
+WUeffRR1q9fz9y5c1m2bFlJmikQlBim7BzO/
7mIs9PmkH7hCq6BflR7ZBA1nrifpKNnWNd1dIF6I6lnI9k84GnKdWh+m6x2EEmi/
H3tafbtG3hWqVDokMyrcXZNlZ2QhEfF4OvTSjR4axxVHuhLxC/zSD1zEb2PFzoPN85M/
bv4ZisySUdO3yhqd0uAbE5iMqkRkXkVdANbNKTqyAFcmLmkaIX5rKDm5LCxz5MEd2+LSxlvKg/
rRXCPtvkEjT0YUtJw9S9TLFuu7TvKya9ncHXlFjRVpWy7ptSZMNpcv0YguEMo0VTpjRs30rlzwd4lo0ePZv
r06TzyyCNcuHCBjRs35rvm+eef5/jx41SsWJE333yTRx55xO41Raq04E7BkJbO+u5jSNh5KH/
2iCzhUTEYnYc7KacvOP1BWBq4VzJ3dS7XoTneNaviUeFGoH3K6fNkRsXiFhyIb53qACyu2YO0sxdtzjskfi
euAX6FnjNlZXP+r8Wcmfo3iQeO3UjhLirm3o5WUdzdGBy9Db2Pl9mG7Bx2P/
km5/9YaK7FIstOz1ySFAXNZMK7diipp87bfZ3i5sqQa7sLdNnORTUaubJ0I9Grt6KZVAJaNqTKiD7obur+f
W76fHY++hqSIuc1lcwNEm/4wQTzVp5AUEKIxoxCvAhuM8bMLPaOe4/
zMxYUWslVUuRiV3gtNrKMzsPNrpRkSVGo/thQKg3pgb6MDwHN6hforRO3fT/7np/
Mtd03evv4NQqjyZevknjghM20bt/6NelzpPAgZENKGuu6PcK1PUccSiNGli2KQ3v/DbqsnU5w1/
xb16lnLxL5zyoMyal4Va/
M1TXbuDRvpXNjdBTZcoXdQvBrUpf79i0o9Fzq2Yts6PU4aRGRSDqdOa7KZEJy0VP1wb40ePN/
qCYTS+vcZ1VMd93wB0GdWuY7ZkhJ4/
xfi4hatglTdg4BzRtQ48n78QqtZLftAgEI8SLEi+C2cXnxOnMzve0HbrcpNpF0OjST0S4PhuLhTt8Tyy12U
o7dvId13R4pWOFWlpEkaPfPt+x+4k2y4xMtGCPRc9c8Apo3KPT0jjGTuPDnQocFn97XG2NaRqEVgSsPu6/
QKsS30nn1b5Tv3tbqGNVo5PBb33Lq2z8wpWc6ZKMzqf/
2OBq+82y+Y4a0dJaF9SbzapzlysgS+DWpR+LBExYFk6RTqNCvCx3m3wgMTjx0kvXdHiE7Icl8QNPMolCDlt
Peo/pjw5zxsQT/ERx5ft9RAbsCwe0kJymFox/8wMLKnfjbpR7zy7fl0OtfkRkTb9f1xz/
7hc0DniF+56ESttQ2kt52OJtmMqG4Fb7FkG8unY5Oy6dZFC6appn7HBVWml9V0VSN/RM+oufef/
GqXvBtXOflQedVv1oULlnx17jw12KHhYtn1Qr02vsvIb075Eu59qxagVYzPqHyiN4255D0Ovyb1LU5Ttbpa
PTRRAZHb6PTip+pO+kpm/
2N7MLBDKej707h6IdT8x27OGspGVeirbd00DAXurPyPdaMJuK23kjHNqZnsL7Ho+QkpuQ1qwTyfg52PfEms
Vv3OmS/QGAvd1SROoHgdpEVm8DqtiNIO3c57wGcFR3P8U+mEfHbP/
TYNhuvajcevJqmkXLyHIbkVDxDK5KTmMzB3GZ6tyGGJXcLRNLp8KpeidQztuNLFDcXqj7cn3O//
5sX31AYbf76jKCOLSyeT9x/jOSbUn0LoGmkX4wi/cIV+p1ZQ/
zOg1ycvQxTRhble7Wn0uAeSFbquVzbe7RIDSAbffwi3jWq0HHxj2RExZB2NhKdtyd+4XWQZJn13cfYnKPKi
D4WY3AKQ+/lSUivDoT06kBWdDzn/
1xo9XtrE1nGu3olUs9csLuw3uE3viawZXhe9d7If1dhV4CPHdzcc+nCrKVkxyVYnFZSZE5+/
hvl2jUr9roCwa0I8SIQAHuefof0C1cKCA/NpJIdn8j2kS/
RY9tswPwwOPzG16ScPGceJMt4hVa4bXEsjb94FUmS0Pt4EtS1NUtq9rAtoCSJ1jM+wb9ZfS7OWY4pPaOA7Z
Ki4Ne0HpWG9rQ6VdqFK3bZmX4xCkmSKNu6MWVbN7brmlxb7eJ6LIzex4smX79GleE3PCseIUF4hNwIKk6/
dNWuTJ7gYmTY1Jn4COf/WlS8ar5GE/
XfGYfOw529494j80qM7WsUmZNfz8gTL8b0TKfF4nhWq5j396srt1j9bJrRRNTKLU5ZVyC4FSFeBP95Mq7Ec
GnhWosPfM1oIn77ARL2HeXM1L859+s/+QeoKmkRjlV2lhQFt6AAMqPji+6pkWV8alWlzvOP5Hku0iOjbL/
pSxKVBnWj8rD7AOi2fgZbhj5H+oUr5joqmoZmUgnq2oq2f3+JbKPSq2tAGbvMtXfcrQS2DEd2dUHNzrE6Lu
ylx/ELr0PFgd0sZtzkkmFHF2ZJUciKtW/
LsDDK1K9Fx8VT2Tp0PMaMTHOAs2T+edL5eOEXXoes2ARST18oXADIMq4BvlQe2hPFxYWchER2Pf6G7YVNKr
Gb9+R96Rdeh4Rdh4rnAbpO4r7jJB46iV94HVSj0WbgtGY0oWmaVc+aQFAUhHgR/
OdJPHjCLgGxttNITE5qFuhbtzretUO5vGBt0Zz5sowkyzT/8d18DwYXf9+81FZLSLKEX5N6eV/7N61P/
4i1XF29lWt7jyK76Anp3ZEy9WvZZUrZdk1xK1+WLCu1XFz8fAttQmgPLmV8qP7oUM78NLvQfydJUQjp24nG
H79o95yugba3gjRVxcWBLaPCCOnVgUFRWzj/
1yKu7TmKpNcR0qs9Ffp1RtbrMWZksr7bI8TvOpRPCEg6BVmno/
0/36G4mPs8VXmgLwde+tQcY2KDm38majw1nDM/
zCrW58hFzclhfdfR9D21Ev+m9biyZINlr44s49e0nhAughJBBOwK/
vPILnrbg8BpwiXs1Sfouedfgjq1RCui1yWgeX26bphRIBZF7+VJpaG9rFai1VSN0JED8h2TZJmQXh2o/
8Yz1H35CbuFC5iDVRt/Yl04hH84oVjNFht/8QpBnc2fNS/
u4npAbJnw2rT67SOH5vOuFUqZ8DpWA2JlvY5Kg7sXzeCb0Pt4UeuZh2j1+2RaTnufSoN75HXR1nm402XdDB
p/9gqe1SqBJKHzdCd01CB6HViQr1ChzsOdDoum2gzGlnQKwd1vCEW/
hnWoOe6hYn8OADTITkzm8JvfcPr7mda3o1SVOuNHAWDMyOTSgjWc/
XkuV9dsQ7UWPCwQ2IFIlRb85zGkpTM/qA2mjKxSWa/
G2BGU69iCcm2bsLRub7tjEmQXPe3/+RbvWlXxqV3N4riUU+dY2XwopozMQmNwwl58lMafvVKsz1AYZ3+Zx/
4XPsaYkpYX/6PzdCf8o4nUfm5UsedXjUauLF7P2V/mkX7xCu7BZak2ZjCVh91XJGEUtXIzG3s/
af6ikO9//TefoeF744trtkPYs8WSsPcoq1sPtxrE3H3rLMq2bZr39ZqODxG32YmZP5Jk/s+K+K7+xP00//
FdTn/7B4ff/hZjSnreOY+KwTT/
8V0q9OnkPJsEdz2izosQLwI7yIiK4cz3s0g+EUHKiYgbAbilhOLmSqWhPbk4d4U5pdhGTEL4h89T77Wxds2
dePgkux59nWv7juYd03l7UveVJ6j32tgSc+UbM7O4sng9GVdicA8OpOKArnnl9e9ELs1fze4n3yQ7IelGxp
aLntTO97E3tA1u7i507hhKrx41cXe3z0NXGkSv28GmfmNRc3LyBKqkU9BMKs2mvEmtZ254WlLOXGBpLetB1
86m4UcTqffqk5z8ajoHCitOeF38dFn1a5G3EwX3HkK8CPEisMG+5z/
i1NczrI7JLdNuT7AoYI5D0evQcgwOZXdUe2woiqsLl/5ZhSEtA9VgyFdyXvFwo8Fb/
yPs5SccFh2Jh06SfCICvZcHQV1a5SsFLzBjyskhatkm0s5fZt/
pFH7Yq2JwccNk0vKSacqV9eSnHwZQpXKZ221uHhlXYjg7bQ5Ryzai5hgo274ZNZ9+oMCW35Xlm9jU50mb8y
nenphS022Os4WkU6g17mEavvcc84PaYsq04NGUJfwa1uG+AwuLvabg3kCIFyFe/
nOoJhNoGrLOcjyAMTOLC38t5si735F5JdbmnN41q9Ds+7c59e0f5iZ1NjwjkiLT5KvXOPDSp2hGo91p05Ii
MyByY14qr2o0cnX1NtIvXMY1wI+QPh3Re3naNZeg6GzddpHnJhbeBFZRJMqV9WLhvw+id2Zn61Igbts+1rR
70Oa4Oi88ysmvphe7TpGkKFR9uD/B3VqzY+TLNsf3Ob4c37DqxVpTcG/gyPNbZBsJ7mqiVm3hxOe/
ErN+J6gaZcLrUHPscHzCaiBJEn6Nw9B7e5GdkMi6zqNIOnLa7rlTz1zEo2IwtZ55kKilG62O1ft40frPT6n
Yvytl2zTm0OtfcXXVVrvW0TS4OHs5YRPNRdNknY4KvTvabafAOUz/
cz+yLKEWkv5rMmlcjU5l46bzdO9a4zZYV3QCWobbzAZT3Fyp/+YzlO/
Rlv0vfkKyA78nBdHwqlaRrNhrdtU+yrgcTeKhk1xduQXVYCCgRUOqjRqIi59vMWwQ3OsI8SIodQwpaZz7Yy
EXZy/DkJyKb72a1HxqOOU6tXRoW+TUt3+wb/
yHSIqSl2aadOgke55+N2+M4u5GjSfvJ+3cJZKPRzhkp6RTOP/HQsI/
mkilYb3MjfcKwb9lQ7pt+gudqysA3rWq4la+nM2U5bx1FJns2ASHbBM4l5wcE/
sPXLU6RlEktu+IvOvEi6zT0fC98ex+wnKNmLCXHsPF15vyPdrR+1Bbkk9EcH76fC4tWGtXN/
Cb0TSN0EcGc+63f+zyPu585FUyo2LN27RoXPx7GYde+5J2c76mQt/
ODq0t+O8gxIugVEmNiGRtx4fJjLq+bXO9zH7knOXUeHI4zae+U6BbcWEkn4xg3wRzeqy1ni2mzCxOfftnkS
qMakYT6ReukJOYzFVL1VglSDp4ksxL0XjXqIIpO4f13cZwbd9Ru7eNNKMJj0rlHbZP4DxMdm6VGI23uRN4E
anx+DAMKWkcmvQFqsGYF9wLEDbxERrc1MxRkiTK1K1B409fpvGnL2NITeP8HwvZO+59u9Zq+N54jn/
0E2d/mm19oCwh63RkxZiF+82/x6bMbDYPGkfLXz4w1x/
adwydhxuVhvSkxhP341YuwC5bYrfu5fSUmcRvP4Cs11GhX2dqjXsY7xpV7LpecOciYl4EpYamqiyr14fUsx
cteiSaTXmLWv+zXZNi3/MfcXrKX06pGmoN9wpBGNMzMCSlWhwj6RRqPvMgzb55g4jf/
mHXY687tIbsomfQ1a24+pcpprWCoqJpGoPun8WlyGSLRQMlCV56oT0jhhXeQPJuIPtaEhf/
XkbGpau4lgugyoje+domWCJ2y17WdrD9exn+0UR03p7se9aG0JEkc40dawL/
eruHfB5MSULv60XXtdPxb1rf6hJHP/iBw29+k+96SacgyTLtF3wvtmbvQETArhAvdyRXV29lQ8/
HrI7xrBJC/3PrbHpf1nR4kLgt+6yOKU3cQ8ox6MoWVrUeTsLuww4FPTb+/
BXCXnjUqfZkZRlJTc3G29sVN7fSc7BGRaWwYPEJIiKu4eamo3OnUDp1DL0rglzn/
XuUyZ9uLvScJIGrq45Vy0bj7eVaypbdfjRNY2ntnqRGXLJQ5VgmsE1jum38i0WhXciItL4FlytMiors5kqL
n9+nTN0a+DWuW2C7OWrVFjb2erzwiyUJ2dWFARfW4x4UWGQbBM5HBOwK7khiNuxC0umsFtdKvxjFhdnLuLx
wLUmHT6H38aLK8N5Uf3RIvgA+xc2teA3vnIwpMxuAjEtRdgsXt/
JlafjeeGo8PsxpdkRGJvHTr3tZs+YsRpOKTifTs3sNnny8OZUqlmwA5Oy5h/
nsy61IkjnoVZYlVq4+Q5XKZfhxSn+CgryKPLemaZw4GcfJU/G4uMi0almZwADn1o8ZPLAue/
dfYc3aiHyBu4oiIcsSn03uiYe7ns1bL3DseCw
6RaZN60rUq2vbc3G3I0kSraZ/zLquo9EMpnxbPJKioPN0p/nUd0m/
eMW2cIFiCRcANSubndczmXzqVKPpt29QvnvbvPOnvpqeV+qgAJqGmmMg4pd51H/
96WLZIbh9CM+LoNQ48MpnnPxqer4aJpbI5yqWJVwD/
em28c+8lMrT389k77Pv3xHiRVIUyrZvSrcNf7Ki6SASD5ywbJck4VuvBs2nvkNgq0ZWU7sd5fSZeB57agFZ
WUZMphvrK4qEu7ue6T8Pplo1/2KvYzCaiIxMRlU1qlQug4uLwuatF5jwwvJCxyuKRNUqfsyZORzZSjl+S5y
/kMjrb63h5KkbTRJlWaJfn9qMH9eabTsiiYlJw8/Pna6dq+HjY70pozVUVWP5ytPM/
ecIZ84m4Oqio0vnajz0QDjZ2UZefGUl0TFp6BQZDQ2TSaNReDCfTe5FgJPF1J3ItQPHOfzWN0Qt2wSahqTI
VBrai4bvPUfG5WgOv/kN8dsPlK5R1wvedVr6IyH3mbeC5niG26yYHdyjLV1W/
VYaFgrsRGwbCfFyR3J58To2D3imSNdKioJH5fL0O7MaWVEwpKSxqFpXchKS7J7DvWIQmZdjiu2yLox2/3xL
5SE9OTXlL/Y994FVUdVq+sdUGz3IqesDPDR6LqdOJxSa6qvIEvXqlmP6r0OKPL/
JpPLnzIP8NesQ1xIzAfD2duH+oQ3Yvfsyx07EFrp2Lt993Ze2rSs7tGZ0TCoPPDyXtPScfIIM8leoVxSzp0
Snk3nisWY89khTp1YRjrqayvCHZpOZaSzwGRVFIjTUj5kzht0V22POIPtaEtkJSbiVC8DF15tzMxawc8wkJ
FmyO1DdqUgSXqEV6Xd2DZIkMcerEab0TKuXlO/
Zjs4rfy0lAwX24MjzWzRmFJQaIX064VG5vDm12UE0k4n085eJWrYx75jiZmfsgSzhXasqvQ8uouVvH1G2TR
M8q1WkXMfm+DWpVyR7bib0kUFUGtwDgGqPDMK7VtVC55QUhTLhdagyvHex1iuMk6fiOHEy3qJ4MKkah4/
GMHTE37z4ykq2bL1gVWjciqZpvPP+er79fmeecAFITc3ht+n7OHIsxup8OkVm6zbHUm5VVePTz7eQnJJdQL
iYbbqxQ2cyaWgaGAwqP/y4mxl/Ovftf9bsQ2RlFRQuuWufPXuNjZvOO3XNOxlX/
zL41KyKi683WbEJ7HriDdC02yNcADSNtHOXiN+
+39wN3FaNGFkiqEur0rFNUCII8SIoNWRFoeOSH9H7et3oDAz5/m4NSa8jZsMuACJ+/
5fMKzF2Xae4utBlze/EbNxN1PJNyC56yvdoR5MvJ9F1/QwCWoVft8MsOKx1ZL4ZnY8XLX7+gFa/fpT3lq/
38qT75pn5uvqaJ5UI6duJrutn2C+6HODc+US7x23afJ7xLyxn/AvLyMmxna2laRp/
zznMshWFFy6z13drz1q5GIwmXn5tFRs3X7D7mpv5+de9ZGQYLJ6Pjknl9bfW0HvAH/
ToPZ1nnlvM1m0XLQqwFStPFyqgcpFlidVrzpKZaWDBouO88/563v9oA6tWn8FguLc7KJ/7/d/
bJ1pu4fLi9Zz/YyGZl6OtjlPcXKn2aNG9kILbjwjYFZQqfg3r0OfYMs78OJuLs5ZiSE3DN6w6lYf3Zs/
Yt21PcP1JGfHrP3avKel1bOr/NEmHTuZV/
IzdvIezP86m1nOj6LrxT6JXbeXCzCVkx13Dq1olQh8dwtF3pxC9emvBG7Mio7jo6blzbqFlzd3KBdB5xS+k
nLlA3NZ9SJJEuY7N8QqtZLfNjuLubv+vsun6A3r7jki+/
X4HLz7fzuLY5OQsXnh5BfsP2hGEaQWjSSWsTuGZHfEJGcyafYjFS06SlJyFj48rvj6uXIxMLvJ6mVlGtm6/
SI9uBQvK/ThtN9N+zd9hOT4hg527LtO+XRU+/
7gXen1+AZuWblkIgdlLdCUqhV59Z5CaloOimMXsgkUnKFfWkynf9KVGdftqk9xtJB05bY6dv92GYC5c6V2j
is2t4dCRA3ALLH78l+D2IWJeBHcEmqqyuFpX0i9GWR2XG1syz6+Z1doreUgSioc7ala2xWJ2Tb97k9rjHi5
w3JiewbYHX+DK4vV5c6FpeFQqT9s5X1G2dWPb65cS6ek5dO89naws28HQN+PqorBmxRi8vFwKnNM0jceeWs
CRozFWvQ62kCRwc9OxetkjeHrmX+fylWTGPLGAxMRMh7ax7GHo4Lo89XiLfIG08xce54PJG61eN+rhRkx49
obnLC0th4dGz+PSZctiSpalvOS3wj6HXi/
z8Qc96NypmuMf5A5n15Nvmr0vJVxzyS7syUCUJCoP7Um7ud+Ujk0CuxExL4K7DkmWqTNxjPnmU9h5RcGjYj
AVB3TN+9ouNA1TeobVKrwnPv3Z3NjxFi4tXEvUis0FbZLArWzpvrUZDCaOn4jl6LGYQrdDPD1dGPlQI4fnz
c4xceRo4S72AwevcvBQdLGEiznN2Pzgvlm4ZGQY+HfBMUaN+Zdr1zKcLlwA/pl/
nF79ZvDmu2tJS8vBZFL54cddNq+bO+8IGRkGzp2/
xsuTVtGp+69WhQuYBYvJpFn8HAaDyguvrGTqT7sBszDcuOk8Y8ctolP3X+neezqTP93E+Qv2bf/
dSVQc0NWqcJF05mD73L+XJPZU55ZkCcmJWX6C24P4FxTcMdQa9zAJe45w4a/
F+Ws0yDJ6Hy86Lv0pL7VY7+1pV6aRR8VgMq/GWRUvGZeiST19Id8WUNz2/eaOuDe/xV3/
e2ZULOu7PULfU6tQXAt6LJyJyaTy+4z9zPz7EMkp5loybm46WreqjK+PKzk5JqpWLUO7NlU4eMi618oSlh6
46zacQ1GkIosXFxeF9m2rULmSL0eOxnA1Oo0e3Wtw6VIyzz6/lJTrn6ckMZk0Vqw8w4ULSTz/
XJt8wcaWyMo2MX/hMaZO201Ojsmpwurn3/bSsEEQm7Zc4J/5x/LVk5m/8DgLF5/
gy89625WVFXkpmchLSZw/n8jBw1eJiUmjbFlP+vWpQ4d2VdHpSufdtHyv9vg2qEXKiYiCIkaS0FSNNjO/
QM3J4cyPs0k+dga9rzdVR/TBtVwgZ6bOIm7zHqfZo/
fxwpCabtEDo5lUyvdq77T1BLcHsW0kKFUMKWmYsnNwDShT6FtSakQkB176lJj1OzFmZKH39aLa6EGEvfRYX
jVMeyr1grkIXLUxgznx6S82Xdr3HVqEX8M6eV9vHvQ/
rizdYPW6NrO+oOoDfW3aUVQ0TeONt9eycvUZa2Vjro8tWs0+RZFYtXQ0/v4Fa5S8/9EGFi89WSTx4u/
vzohhDZj2615MJhVFkTGZVGRZQlFkjEa1RLwt1hg9shEz/
jxYqmsWRvlgL65GpxV6TpLA1UXHiiWj8PUtvF7NmbMJfPL55kIbSeaKocaNyvPdV33x8NA71XZLZF6NZUOv
x0k6fOq6V8OceSS76Gk94xObGXa7n36HiF/mlvjWk6QouJXzp/+5dSUSOC8oHqLCruCO48rSDRyb/
FNeASu34EBqjXuYsBcfy/NeXJi9jB0jXwLtRpM2Q2Iyp7+fSXDXVrhfL0B15N0pdq3ZYuo7SHo9x40/
WR2n8/
LI16hN0zSuLNto3RWuyFxZsqFY4uXosRgWLDrOxcgkfH3d6Nm9Jp073Silv2ffFVasOmN1jkIcQ3YjyxI9u
9fMJ1wyswzIkoSrq47QUP8iCwzVpPHD9S0SuNHQ0GTSMFnxgpUUsiSxd9+VUl+3MCwJFzD/G2ZlG1my/
BQPPxCed1xVNaJj0rgYmciLr6wkO7vw72Huv9fBQ1d5edJKvvu6r1Pr3VjCvXw57juwkKtrtnFl0TpMmdmU
Ca9N6KiBdvXsCnvxUS78tQhTZlaBAHlJUUCWzJW5i6N3JXAN9KPzmt+FcLkHEOJFUOKcmvKXuVHbTZ6WrOh
4Dr/
1DTHrdtBpxS+knj7PjodfLHDj0kwqmprD5kHj6Hd6FbKri10VPMu2b0bFAd1QTSY8q4SQcTm60HROSZGp/
sT96Dzcb6ypqjarAGuqhpqdY9OOwlBVjU8+38y8f4/lbcvIssSGjeepWSOAH6f0x8/
PnQULjxdr28YSuc+y6tX8eeXF9qiqxsLFJ/
jjrwNEXjLHdoQ3CGbo4HrodDIGg2NpsLIskZ5RtO9NSaFqGomJWbRuWYkduy7dbnNssvy6eNE0jbn/
HOXPmQeJumpHgPp1NA2277zE2HGL+fqL3ri7lbwHRpJlQnq2J6Sn41sy3tUr02XdDLYMHkfmlRiz90bT0Ew
myrZvSr3Xx7JlyHOY0jOtbgFbwiWgDOEfTKDqQ/3Qexe9TYXgzkGIF0GJkh4Zxb7xH5q/
uLXnj6oRs3E3Z6bOIvl4hMVgXTQNzWjk7E9zkPS2f2QlRSagRUPAXFum/fwprOsyCmN6Zr7utAD+zRsQ/
v74fNfLioJvvRpmm6zs1/
g1DrNpS2H8Pecw8/49BpAnTHLfmM+dv8ZLk1bxy48Dibyc7DThUq6cJ+5ueq4lZhIc5MXggXXp368Obq46x
o5bxJ69+eNlDh+N5tCRaLp3rc6adREOreXmqiMj03pqcWkjSVC2rCevvNSBkWPmkZp6Z4mrWzl5Op5ly09x
8PBV/
l1wvMjz7Nl7hWfHLyU01A+DQSUkxJsK5X3w9HShSePyxWql4GwCWzRkwIX1RC3fxLW9R5Fd9IT07oh/
k3oA9Dm8mFPf/
cXFWUvISU5F5+WJa0AZNJOJ1LMXraZG5yQkEbNhJ64BZfCuFUqZhrXt9khpmkbctn2c+30+GZejcQ8uS9WH
+xPctbVdAcKCkkHEvAhKlMNvf8uxD6daLmIlSXhVq4iaYyDjkvXCUmXCa5N66gKmLBuBnhK0+Ol9ajxxf96
h9ItXOPn1DC7MXIwhJR2v0ArUGPsANZ8aUagL+ey0Oex+6i3LS+gUBkZuxL18Oeu23ILRqNK7/x/
EJ2RYHTfrj2FM+WEXO3dfKnZsiKJIdO4YyqeTexU49/5HG1iw6ITV6z09XUhPt+9hHxjozvChDfnejqweR9
DrzXEyxblbvfV6Zwb2D+NKVArffb+DtevPlXrcjSP4+7tz7ZrtAGN7uDkwOBe9XmbwwHo8/1wbXFzu3rYGe
5/7gDM//
m1Xz7RcvGuH0uTzV6jQt7PVcarBwPZRLxM5e3lev7XcP8v3bEf7Bd+jc79zBODdjkiVFtwxJB89g2btAaFp
pEVcQrUjUC87PgmTHVs1spsbVUbkDxD0rFKBpl+9xpDYnYzIOkLfEyupM360xb3vao8NpdKQnuYvbnpDk3Q
KSBKtfvvIYeEC5uaJtoSLLEvs2HmJ+3rVdMrD1WTSGNCvoJcoNjbNpnAB7BYuAM8/25aWLSo6ZJ81fH1ceW
liO3ZueYoVi0cVeR53dx3lg71QVY0KIT58/GFPNq97HG/
vks0WKw7XrmXirBf7wn6ODAaVuf8c4ZXXVnE3v8N6Va/k8FZS6ukLbOr/NJH/
rrI67tAbXxM5ZwVAntc298+ra7azd9x7RbBY4AyEeBGUGKrJhOzmarP8v6zXU7ZDc6s1ICSdgnuFcnbViWj
w5jPF3teWFYW2c76ixU/
v4Vu3ep4NIb070m3zX4SOHOjwnHPmHeGJpxfaHCdJ5hTp7l1rUL2af1611qIgAW1bV6Z1q4Kpt79O31fkeS
2xftM56tUtR7VQP4sdpHO14M3nc/8+8sFwZv0xjE8+6sH33/
Rl9fJHeGB4QyRJokwZd1xdi7bTnZlp5Olnl9Bv0F95PYg8PPQMHVSvSJ2uS4tbd1qdjabBpi0X2LuvaGn2d
wJVH+rneH8yTQNNY88z76IaCt/
iNKSmcXrKX5a3jlXV3IogOs5BiwXOQIgXgdOJ23GATQOeZo5rAy7OWmI9/
VGSKNuxObWffdjqOE1VCe7e1q43rNCRA4pidgFkRaHGk8Ppc3QZI4zHGZFzjI6LplKuXTOH5/p7zmE+
+XwLmZm2Xdsmk0a9uuVwcVH46fv+NG4UUhTzAXNyxgvPt833gD52PIYHRs7Ni7txJunpOUiSxJuvd0ankws
IA1mWcHFRmPBsa8IbBucJmbphZfn4wx5MeK4NdWqXpXvXGrRuVTlfmX4XF4WO7atQHKKjU3nhlRV5AubhBx
sRGOhRqECUJChX1rNY690NKIrE4qW2PXB3IqrBwNF3vy9SEC9AdmwCV1dtLfRc3PYDmDKyrF6vGU1Er9tRp
LUFxUOIF4FTMKSlc2bqLJbU6cWaNiO4sni9fTcUTSNm7XaOT55G+EcTgfxVOHO3aVr+8iG1nx1pNUBOkmXK
dmiGR8XgYn+eW5EVxa4AP1XVOHoshm07IvOqpWZmGpgydad968gSFSr40LKFuQ+Sv78HP33fn8CAgnVY7J3
v5oaKp07H8/jYhZw+HV+k+ayhKBKhVc2Vh8MbBPPbtEG0aH5jC0mSoFWLikz/
ZQijHm7Mrz8NYve2sezZPpY/fhtKj241rH6P4+LS2bHrcrFs1K7/77Mvt6KqGn5+7kz/
ZTAtmuXf6nJ11THq4cY8OKJhkdcqToayIktUqVymWHPYi8mkERObXvILlQC7nnyT09/
PtBqsaxVJstiSRM2xL+jc3nEC5yKyjQTFJj0yirWdRpJ+vugPlqgVm9H7etFty0xOffsnsRt3gyRRvmc76o
wfhX/T+gCEvfQ4xycXUrdFlkCWaXRdAN0Oli4/xRdfbc2rhAtQvrw3/
XrXtsvjksv7b3fN57H44afdNuNkLKGqGmfO3BAq332/
g5wcU4k00TOZNAb2vxFbUzesHD9824/4hAyuJWTgH+BRQIQpdnYUB5jzzxGH4m8soQFXo1M5eOgqTRqHEBz
kzfff9uPylWROnY7HRa/QpHEInp4unI1I4Ovv7H+zvjm1PbdwoISEqmkFCgrm/
r2wOdzd9Xz4XjcmvrScuPiMYgUq22OzNQ+Tqmqs2xDBL7/
vIzo6FRcXHRVDvElOySYhIYMyfu4M6FuHoYPr4ePjRmJiJouWnGDP9bo6TRqHMLBfWL4eU84g+WQE56cvKN
4kmoZroF/el+kXr5ARFYt7UCD+jevaVfkxoFn94tkgKBJCvAiKjCkrm6yERDYNeIaMS8XrOoyqcvHvZYR/
+DztrTRMC/9gAoqrC8c/nmbOOpIADTxCgmj520eUbdu0eHYUkbn/HOHjz7YUOH71airTft1rd/
VbTdNYvPQkjcLNvWAuX0nmt2LEpsiylBcnkpCQwfadJVvj5Icfd/
Hpxz3zCu0BBBYiWorC8pWnrQYwS4CikzAa7XvSx8Xn9zZUrOBLxQq++Y7d2l3aGgEB7sydNZyHR/
9DTGwaqno9tOK6VJQkCQ8PPaMeasS584lIMgQHeXHwUDQHrnftlmWJjh1CefaZVkjXP5UjwiVXPDlSH8hk0
ujXt06h5wwGE4+PXciRozE3Hc0h4SYxnZqWww8/7ubfBcd59pmWvPfRRrKzjXl279x1mV9+28vnn9xnV9sD
e7k4a2le5k9R0Xm6U6FvJxL2HuHAC58Qe1ObgoCWDSnbrinx2w8U6kWWdAoBLcMp06B2kdcXFB0hXgQOkx4
ZxZF3v+fCzMVFLtRmiahlm6j1v4csnpdkmQZvj6P2hNFELduIITkVr+qVCeraGtnRoD0nkZVl5LMvC983z8
XeB5CmwbIVp5jwbGt8fNxYsvQUslz0QnWqqtGxQyhAvgdOcQjwdyfBQgrv5q0X+OnnPYx7upVT1rqZ9DTrP
2saUKtmIKMfbswrr6+2OV9goO14luAgL9zd9WTaUbfmo/e7s2nzBYsVdFVVIyPDQGaWkY/
e757vXFxcOknJWZQt60kZXzdyckwMGjaLhGv2/5tJEvzwbX/
C6pTFzU3HvH+P8tmXWwtNk775mho1Ajh+IpbY2DQ6dQzF2+tGBt7kTzffIlwKR9U0YmJTef3ttcCtlZ81cn
JMTHxpBf/OGVFAIBaV7PjE4u3NAQ3eG0/SkdOs7TTSXMH3JhL2HAUJ3IMCyYqOR7spelpSZFwD/
Wjz56fFWl9QdETMi8AhUiMiWdl0MOf/WOB04SLJMqZM6wFyubj4elP1wX7UfPpByvdod9uEC8CSZUXr/
2MJg0Hl9JkEAKKuphR5HkWRCCnvTbcu5mwpP393G1fYZviw+haFC5gfWnPnHSUry/
5tMnupXLmM1dRhc8yNH106V6NsoHVPT1CQF42ve7es4eqqY9CAMJvPyCGD69K8aUVWrTlrdayqaqxYdbrA8
bJlPalZI4Ay1/sZrdsQwdXoVKs/V5Jk/sySZK7Z8t7bXWnerAJeXi7odDIPDG/
IN1/0Jryh5RgwSYIzZxL4fupO3n5vPT16T2fGnwfQNLPQWrLspPUPnu+z5SXxFEDTQDWpzPvnqN3z2cKzSg
hYqh9liev/OIqHO40/f4U6zz/
CnqffQTUYC9aiUlVzLI0sUf+dcXhUCkbSKbgFB1L3lSe57+AivEIrOenTCBxFeF4EeagmE1HLN3F5/
hpyEpMxpGeSEXkVQ3IKnlUrUuOp4VyYtYScxJQiR/
dbQzOZKNPwznHBZmcbWb7yNOvWR5BwLZPywV506Vyd7l2r50vZtefN1FFyY0EsNeezfq3ZU1M+2JsfvuuXV
4CsbKAntWsFcqoIwbqtWlZk5IONiDifaPVNHiAtPYczZxNoUD/I4XWsMXRwPd79INbieZNJY/
DAeiiKzIsT2/HKa5a9Ly9OaGt3ivRTTzRn997LRERcK/TBPLB/HV572dx3KyU126aXLT3dthdny9aLNr/
PAPf1rEXNGgH061snT/jcTPt2VdHpFZ5/cRk5OQUf9LnOhNw/s7NNfDNlB3q9TM0agU4V5SZVY9PWCzw/
vq1T5qs6cgCHXv/
K8gBZxqdWVfwahZlrwSARu3EXhuRUfGqH4lW9Mtf2HyPxoJVMK00j83IMZRrUZmDkJqfYLXAOQrwIAMiMjm
NDz8dIOnwKFLnAG01W3DUSdh0qOQNkGc9KwQR3a1NyazjA1m0XeeX1VfkCbU+djmfj5gt89e02vv+mH3Vql
wXgmgOufXvw9NQTVsc89309azJr9mG7r5VliT731aZ92yp07BCKTpffVfHaKx0Y/dh8u+dSFJlpP/
QnvKHZSxFx7ppd15ZE0bPe99VixarT7Nl7pVCBMHhgXRqFm70M3bvWQPsQvvhqK3HxN/
59ypX15MXn29H1ujfKHry9XPl92mD+
+Osg8+YfJSkpC0mCRuHlGT+uNQ0b3PBsVKvqx+nT8RYf+rIkUbVyGZtr5uSYbH4PNQ3efqOz1aDnY8djGDd
+icMBvz9O28MDwxs4dpEdGB3sk2UNj5AgGrz7HIff+LrAOUlRcAkoQ+fVv+FRMZh9z33A6Sl/
5cXIpJyI4NK/q/
Gqbl8Mzv7nP6LSwG5Os11QfER7AAGaprGq+VASD50o8Zb0lpBc9HRaNo3yd4B4OXwkmjFPzLd6w/
fxcWXBvAeJjU3ngZFznba2JMGohxtTsYIP6zeeIyPDQFx8Olevptp8AMmSRJ06gfw1fZjVcXPmHeaTz63H6
AA0a1qBCc+2pm7YjUrCx47HMHLMv1avc3fXsXbFGNzdnd8MMCfHxLRf9zDv36N5/
YnKlfVk5EONeGB4wwLeFJNJZe/
+KOLj0ylb1pOmjUMcynC6FU3TSE834Oqm5AtKzuXgoas8+qT1DJh33+pCvz6FB8jm8stve/
nx5z1WY1Wqhfox7+8HrM7zv+eW3DGNKBVFoke3Gnz43o14n0uXk1m46DgXIpPw9HCha5fqtGtT2e5/
I03TiPh5LkfenUJm1HWvnCQR0qcjzb57E6+qFTn59XT2Pz+58Alk2e5KgIHtmlL90SG4lQvAr3EYHiHO9Sw
KHHt+C/EiIHr9DtZ3fcS5k8oSqBqKpzumdPv7s5RtZ+4gG9Krg3PtsRNV1biv/x/
ExVmveyFJ8OwzrThyLIZNm887rRJq29aVOXM2nti4jLwMJQfur7z3dhf69rb+YASzCP
n8y20cOmLuJ6XTSfTuVZvBA+uiKBKBAZ4EBRVepXjkmH84eSquUO+CLEk8+EBDJjppa8ASOTkmLl1ORlEkK
lX0LZYgcSaapvHJ51uYW0hshyRB61aV+frz3gU8YrcSF59On/5/YrQS0/H6qx0ZMqiexfNpaTl06PqL/
cYXE3sy6n7/ZTDh1z1Vv8/Yz5SpO/MC0nO3O2vXCuT7b/ri729/hppqMnFt3zGMaen41ArNq/
WkGo0srNSRrGgn1zWSZSoN6UHz79/Grax/3mFjZhapp84jKTI+daoh60u+m/
e9hBAvQrw4xL7nP+L0lJkFou2LiltQAN61Q6k59gHKdWrBwood7X/
6Xt+yajEtf2PF0mLOvCN88nnBlOfCcNHL5DjRDe7l6YKPjwsxsekWtx0a1A/iyNGYfILmerY43btVZ/
L7PRwqd5+amk1Kajb+fu52e0qirqby+FMLiIlNy3tY5cZnNG9WgW+/
7FPkMv73ApqmMfefo8z48wDRMebMI19fN0bc34BHRzexO/
162YpTvPXuunzZZrkCoWuXanz8QQ+roi06JpXe/f8s/geyE39/d4YMqsfPv+7Nl6qd+/
dxT7fk0UfMpQxWrT7DpDfXFDqPokjUq1uO338ebHfnZ0skHj7JinAbFbdzf4EcRZZwKeNDvTeepuqIPpz65
g9OT52FMcX84uNaLoCwF8YQ9uJjovu0nQjxIsSLQ+x55h3O/
jLPoa6shSJJ1J4wmqZfTsp3eO9zH3D6O8duopJOYeClTbgHly2eTQ4ycOhMIi8ll+qa9iJLErVrB/
DMUy2Z/ucB9u03VwatXNmXh0aEX/ealM5NMjU1m4WLT7B0+SmSkjKpWNGXwQPr0qN7jUK3U/
6LqKrGlagUVFUjJMS7SN+Xg4eu8sdfB9iy7SImk0b1an6MuL8hA/
uH2fy3zs420qHrLxicKLCtIUnQskUlRj3ciL/
nHM6LTWrWJIQHRzTM66+laRr3PziHc+cLD4DO5WYvTVFJ2HuEVc2HWrdbUYqfgGCp6qAEoaMG0er3ycUWYv
8FHHl+/3dfjwR5+DUKc4rXJXTUABp/
+lKB402+eAVDWjrnf59vDpgDsBFbo6ka536fT71JTxXbLnvJyjLeduFiLcNE1TROnIynYcNgfp46kJwcEyZ
Vxc1VV+o3Rm9vV0Y+1IiRDzUq1XXvJmTZvKVVHBqFl6dReHk0TUNVNYfEqaurjv596/
DvguPFssFeNA127rrE8KH1+eaLPhbHxcWl2wz8VhSJLVsvFFu8+NQORXF3s1qCQTOZKNe5JbEbdhV9IUsqT
IPzMxZQbfRAgjo7v/
bRfxnhyxJQ+f5eKO7FrAEiy7T8+QNkXUE9LOv1tP5tMn1OLKfepKeoNnqgzekkCZKPny2eTQ5yO7sLS5I5y
8geDZLrjndxUXB304s3uv8AkiQVyav25OPN8SvjeLp9UZFliQWLC6YeHz8Ry6/T9/
Hzr3vZtcd2GxFJkjDkFD95QO/tRfXHhlrsbC8pCl7VK9Nx0Q/o/UrGUy/
pFM7+7LygfoEZ4Xn5D2PMzOLEZ79w+vtZmDLsD6q9FUmnUHFQd5vBab51qtPwvfGoBgPnfl9gPQ5GktF5FL
+omiO4uChUC/Xj3PnEUl0XzC9unTpUY9mKUxbHSBKUD/
bG18fV4hiB4GbKBnoy64/7+fDjjWzdHlni66mqxtWrqXlfJyRk8NKklRw8FI0smwvqmUyazeBeo1GlTh3nb
BmHf/Q8cTsOkLj/ugfq+sKSoqDz9qD9v9+h9/
ai46KprO000v74PDvRjCZSTl1w6pwCIV7+s5iystnQ41Hith/I/8t6U/
Ca5KJHs9UxVZJAkqj36pNWh6WcOsepb//
k0vzVmLJzcPHzIScxxeKNQjMaqTi4e6HnSpI0GyXonU1uMOPDD4Yz9snmbN5ynvQMQ6FbR5oGD45oKDwtAo
cICvLi26/6kpiYybkLiUhA/XrlWLHqDO9+sMGpa8mylNfHKifHxFP/
W8TFyCQAmwX38uaQJLy9Xeja2f5aPNbQe3vRffNMzvw4mzNT/
ybj4hV0Pl6EjhxAnQmj8axSAYBy7ZvRcfFUto98GUOiE7ePZRnXAOe0RBDcQIiX/
yinvplB3Pb9BVvJ39yTxEoAr6TXoRmMuPj50vbvL/BvYjll8+rqrWzq/zSayXSjjsz1VOpC59YplGlQm/
LdSzbd9lZOn44n1kaKtD24uCgYDCaLb5aSBH5l3KlUyZfQqn4MGVSXenXNNSO+/
Ow+xk1YhtFoytseyo2D6dqlGsOHOb9wmOC/gZ+fO039bngzB/QL4+df9xJ1k6ekuKiqRv/
rTR7Xro+w6MW09LuhKBKyLPPp5F55laGdgc7DnbCJYwibOMbquAp9OjH46lZOfjODI29+g2owFC0T6WZUFZ
2XB0lHT+Nbr6Z4+XASQrzc42RcjubSwrUYU9PxrlWVCv06I+v1nJoy06J4yMOKXze4WxtCRw6g0uAeKK4uF
sflJKeyZfCz5pvAzevdsrak14Fm9rj4NQqj07JppZ5e+O/CY06ZZ2D/
MOb9a7mHi6bBm691ymuYeDNNm1Rgzl/38/fcI6xZe5asbCPVq/
kzfFgDenavccfUMxHcGzhTIMiyRJ3agQCMf2EZ+w/
Y12ne19eV5ORsXFwUenavwciHGlGjeoDT7HIUxdWFei8/
QaVB3Tn20Y9cmLmk2JmYlxes5fKCtXiGViT8o4lUHWE5oFlgHyJV+h5FNRjY+9wHnJ02F9CQZBnNaMI1oAz
Np73H1iHPFWt+t+BABl/dZnPcqe/+ZN/4Dy0LIQncypejYr/
OKO5uVBzQlXIdW1h9O0lJyWL5qjOcP5+Ih4ee7l2r56sCW1TGPDGfQ4ejizXHgyMa8r+nW/LIY/
M5d+4apltEmixLNG9WgSlf9xVCRHDb+fKbbfw9+3CBn1NHkSTo2L4qV6NTOXU6weFr/
5o+lIuRSSxeeorY2DTKlfNiQN86dOlS7ban3ptycjCmphO9fifb7p/
glDmbfDmJOs8/4pS57iVEnRchXtj52Guc+31+4aLBypaNI/Q/
vw6vqhWtjtn20AtcnLPcZvfX4VlHrHpwclm6/CQfTN6EwWBCUWQ0TcNk0mjVshKfftQTLy/
bc1jif+OXsGNn0Uqpu7vpePGFtgzqb94+S0nJ4uPPtrB67dm8vX69XmbQgLpMeLYNbm7C6Sm4/
Vy6nMyQ4X9jMqoO7454eupp0jiEju2r0qplZV58ZQUnTxWvkm3uFmnun+ENgpnyTV88PYv+e+0sUk6fZ2nt
Xk6ZS1JkBkRuFC0GbkHUefmPkxoRybnfrPSfUTVzvRVVK1ZkfXZ8ok3xIikKEpLNG6NkR5ryjp2RvPXu+ry
vjcYbtu/ec5lXXl/
F99/0szlPLiaTej0Dwrx2ty7V7RYvkgSdO1WjWdMKBJXzpG3rKvlc8D4+bnz0fncmTmjL8ROxyJJEwwZB+P
iUXtqqQGCLShV9+ezjXrw8aSUmk2Z3UO1z41rx0APhZGUZWbDwOKMf/YeEa0XPWMwld/
3cP48ci+Hjzzbz/ju3vymiT61QPCqXJyPSvu0wa2ganJ+
+gHqvjXWCZf9NhHi5B4mcsxxJkdGseDuc0YAxt3+INcp3b8OFPxdZPC8pMmXbNrWrB8i0X/
daLOKmqho7dl7ixMm4vI7MhZGTY+KnX/aweMkJEq5lotfLdO1cndEjG9OrR02m/
bqX+HjL5flvZuJzbQgJsf52EBjgQYd2VW3OJRDcLjq2r8rifx9m/sLj7NpziWPHY63+/
MuyRJ9etUm8lsljTy0gyo6moUVFVTVWrj7D+Gfb5GUx3U7KtmnMRSeIF0mWSD170aFrTDk5SJIk+iVdR2y6
34PkJCbbHewq27FVUxjle3e0q3R/5WH34RZcFkkpfN9aM6mEvfSYzXkSkzI5dDja6puhLMM/84/
m88jczMmTcXTr9Tu/
z9if95ZoMKisWnOGkWP+Yf+BKKb9MIAKVgRJbiG758e3tSlcBIK7haAgL55+qgXTfxnCc/
9rbXGcLEn061ObsmU9efPddUTHpJWYcMnFZNI4eLD4gsEZlAkPM2+7OwG9r7fNMZqmcX7mYlY0GcQc1wbMd
qnP6rYjuLSg8L5Q/yWE5+UexKtaJVQ7ouMlnULVh/pZ32IqBMXLgyafvWzfWDdXuqz+lXVdHyE7/
nrapHZ928pootEnL1Khb2eb82Rm2v48qgoLFp1g3YZzVKlchgoVvAkJ9iEtPYcVq06Tmlp4DRdNM29BvfL6
atYsf4R/
5zzAth2RbNt+kWPHY7lwMYmMDHO9mzq1A3lsTFM6d6xm1+cXCO42Hn4wnPj4dP6cdQhFkdA08orLdWhfhVd
f6sC589fYs/dKqdmkFTtf2TlUHtaLQ5O+KPY8mtFEleG9rY/RNPaN/
9DcF+6ml9H4nYfYMngcDd55lgZvjyu2LXcrImD3HiQnKYV/
g9ugZVsvMCfpdQR3b8vV5Zvsntunbg3azv4Svwa1HbMpOZXzMxZwaeFaTBlZ+DetR82nH6BM/
Vr2XZ9jokvP3/JEREnx1uudGNi/
br5jJpPKtWuZ6F0UyviKmBXBf4OLkUksWnKCq1dT8fNzp3evWtSvZw4wXbj4OO99uLFU7JAkWLZoJMFBtj0
VpcGORydxfsaCIic9SIpMcLe2dFrxs9WsyqiVm9l43xNW5+q5ex4BzRsWyY47ERGw+x/
HpYwPTb54lX3j3rc6TjMa8apawf6JZZmU42e58MdC/D57xTGbfL2p/dwoaj83yqHr8q53URjYP4zZc4/
YHVToKLIsceJkPAP75z+elJTFnH+OsGjJSZKTsggM9GDwoLoMH9oAb29Rql9wb1KlchmLW0hyKdVgUhSJjh
1CCwiX3BcKnV7Gr0zpthFp8eO7yDqFiF/+sd7j4GauVyJHVanQrwut//zUZrG609/PzPNQFzqlTuH0D3/
T+vd7R7w4ghAv9yi1//cw0au3cWXx+sIHSBKKmwsZV2Ptn/R6ZtKJz3+jfM/
2BHdr4wRL7eepx5uzY+clLkYmlYiA0TStQNGuK1EpjHliPteuZeatGR2Txo/
T9rBk6Sl+mzaIgDsgkFAgKE2aNa1wcycRp5P7XA+t6scbkzrlHTcYTPw58yB/
zz1CQkIGALVrBTJmdBN6dKtRQtbkR3FxoeW0D6j/
xjNsuO9xUk6csypi9P6+1P7fQyge7lQc0BXfMPvaHiTuP241sUIzmri294jD9t8riIDde5g2f31GmfA6+fZ
LwZy+jASmzGyiljje20TSKZye8pezzLQbb29Xpv8ymIdGNMTT0/
kR95pGgcyg199aS2JiZgGxpKoaUVdTmPzZZqfbIRDc6YSU96ZL52oodgav3tyx/
WaHgyybvSsAiixRPtibgAAPatcK5NWXOjDjtyF5W7UGo4nnnl/G9z/uyhMuAKdOx/Pq66v5dfo+J3wy+/
GsHEL915+2KlwkRabW0w/Q8L3x1Hv1SVzL+nHii9/YPvIldj3+OpcXrUU1Fh7Pp7jZ9uoq7v/
dbWzhebmH0Xt70X3LTI5/+gtnpv5NTkISSBKBbRoTt2UvULSUac1oImGv5fL3JU2lSr507VyNlavPkpNT/
JTvXKqF+tGsaUje12fOJnD4iOWKuyaTxsZN5/MqggoE/
yXeer0z0TFpHDsem1fCILfRaMUKPvToXoNmTSpgMJr486+D7N0fBUDVKn48OKIh1ar5s2HjOTIyDIRW9aNv
79r4FhJTlp1tZPbcI/w+Yz8pqdkW7fl+6i46dwylWqh/iX3mW6k0pCe+k38i5eS5AvdSSVHQl/
Gm1v8eAuDinOXsGPUyqtGYt2UU8es/uJUvS8clPxLQtD5g9gDHbNiJ7GYjE1SWqTS4h/M/1F2CEC/
3IFnx14j4eR4XZi8jO+4abkEB1HhyONWfHIZ7UFn2T5xM/
I4Dxar1Yk81XGcz79+jfP7VVgwG57asB3NMzdQp/fPtQx87bntLTVU1Tp6OF+JF8J/
D29uV334exIaN51my9CTxCRmUD/Zi4IC6tG1dOV/7i/
Ztq2IwmFBVDVfXG4+dxuHlra6RnW3kf+OXcODgVbvCS56buIxqVf0ICvIirHZZKlbypUmjEHS6ktlkUFxd6
LpuBlvvH0/spj1IigxIaCYTXjUq02H+FNzLlyNu+362PfhC3tb7zdlTWVfjWNVsCNWfGEbjLyaxc/
QrXF6wxmJ5CTB7dHQ+XlR/fGi+47n5N/
+F5o9CvNxjJB09zbrOo8hOSMpzZ2ZdjSPp4ElOfPoL9d98mpiNu4slXCRFodLg7k6y2D5WrjrD5E9Lbotm6
nf9KBvome+YXm/fDU9fQjdGgeBOR69T6NGthl3xJnq94z2K/
px50G7hAhAVlUpUVP4u2d7eLgwf1oCnHm9eIv3E3MoF0G3jX1w7cJzoNdvQjCYCWoUT1LlVnog4/
ok5s8jax4j45R9iN+3JK16nmSzfo138fem84hfcAv1RTSbO/
fYvp777k+SjZ5Bd9VTs35WwFx+9pzKRbkWkSt9DqEYji6t3J+NytNWy/
y6BfuTk1lyxhiwXnEeWUFxd6HNsGV6hlYppsX1omkb/ITO5ciWlxNb46L3u9OpZM9+xuLh07uv/
h9XgYDc3HWtXjMHDQ1S9FAiKS3JyFgnXMvAr446vrxs9+kznmhPaDgB4ebkw4dk2DB5Y1/
ZgJ6KpKrNd6lsVI3YjSTT+4hVqPjUCnYc7qtHI1mHjubxo3fXFrntedApoGm1nf0Xloc7px1QaiFTp/
yhXlm4kIzLK5ricBDuEC6DzcMOYngHS9bcVTUPn4U6HRT+UmnABOHMmoUSFCxReBKtsWU9696rF8pWnCxUw
kgQj7m8ghItAUEzOX0hkytSdbNp8AVXVkCRo2iTEacIFIC0thw8mbyQ1NZvRIxs7bV5bqEajc4QLgKbhHhS
IzsOcHn522hwuL1pbIO1LM5pAktj+8EsEdW6Ja4Cfc9a/
gxDi5R4idvMe0Clga0tIkmzWJ5B0ClUf7o9fozBi1u8ETaNs+2aEjhqIix1lrZ1JanrhlXHtxdbHlYDwhoX
vvU96pQPx8Rns3H0pLxgx98/uXWvw9FMtimWbQPBf52xEAo88Pp/
sbGPeS4Kmwf4DJdMS4Pupu+jftw5+fqVTH0ZxccGrRmXSIi7ZXxfGCqen/k1gm8Z4Va3IqW/
+AEtJ65qGajBwbvoCwl54tNjr3mkI8fIfRJIVNNVWuX0JzaRS86kR1HxqRKnYZYlKFXzs0VsWqVe3HMdPxB
XqPVEUiXZtqxBSvnBB5u6mZ8o3fdm95zJLl58i4VoGwUFeDOgXRnjD4P9EYJxAUJJ89MkmsrKMhZYjKAlMq
sqKVad5cER4icxfGLWfHcm+CR85Za74HQdY2XQIXTf9SerpCzZGS1zbd8wp695pCPFyDxHUsTmnvppuc5ym
qiheHpjSMiyPMZko09CxFgAlRblyXrRrU4Ut2xzrwprLgyPC+XPmQU6cjMsTQbl/
Vq3ix9tvdLF6vSxLtGpZiVYtS2+rTCD4L3AxMomDhyyXIygJZFkiOiatVNes+fQDRK3YzNWVW4o/
mUnFkJzKvmc/sOlWlmQJ2eXe3NYWaRJ3CarJxJXlm9g3cTJ7x3/
AxTnLMeXk304J6dMJzyohFma4gSRL1Bw7okDxuhsDzNV3Q0cOcIbpTuHFie2KdJ2bm44unarx27RBvPV6J+
rXC6JcOU/qhpXjtVc68sfvQ0S/
IoHgNnExMqnU11RVrdRbCsh6PR0XT6XBO89eT6cuHprJROzGXZRt19RqSrVmNFGhb6dir3cnUiri5fvvv6d
q1aq4ubnRsmVLdu/ebXHs9OnTkSQp339ubv/
th0vq2Yssq9ubTX2e5PSUvzgz9W+2jXieRZU7E7/7cN44Waej47Jp6MtYj9Ku/8YzNHxvPIGtwi1U35Vo/
cenpR7bYo1KFX1p0dyBPkzXefaZVri4KLi66hjYvy4zfh3CyiWj+fP3oQwdXA93t3vzrUQguBvw8rSvXpSl
bd2ioGnQpLH1+jIlgazX0+DtcfQ7t47yvTs6ZU41O8diMLCkKHiGVqTigK5OWetOo8TFy5w5c5g4cSJvv/
02+/fvJzw8nJ49exIba7kAmI+PD1evXs377+LFom0X3AsY0tJZ12W0OdgL0AxGNIM5XiU7/
hrruo4mZvNu4ncdJHbLXlzK+NDvzCpqjR+F4pFf9CnubvjWq0Hi4VNc/
HspHRZPJfzD53GvYO4UiywR0rsD3bfMvCPT6x57pJlD44cOrscDw+/
dOgcCwd1OwwbB+NsInHV1Vfhz+lDee7sLjRuVx83N8XoxtzJ23GJ2771c7HmKglflEDovm8bAS5to8fMHxZ
rr2v5j5nhduNF34foLqUfFILqs+R1Zf2+
+oJV4nZeWLVvSvHlzpkyZAoCqqlSqVIlnn32WV199tcD46dOnM2HCBJKSkoq03r1W5+XMj3+z55l37O+AJk
HIfR1p9OlLpF+4QvzOg1w7cJyrK7YAmrmN+/
X6LW5BgXRZ+zu+9WpiTM9AdtGjuJR85dyk5CwWLDzO6rVnycg0ULNGAMOG1KdFswpIksTRYzEsXHyCK1Ep+
Pu5c1/PWuh0MlN+2Mnxk3EFP/It2751agcycUJbmjVx3FMjEAhKl3/mH+OjTzZZPP/k480Y+8SNrL6HRs/
jRCH3AUeQJPOW8rJFo27rtrEhJY1/
AloUq2jozfg3q49XtUpUHNCVSkN63pZK6MXhjqnzkpOTw759+5g0aVLeMVmW6datGzt27LB4XVpaGlWqVEF
VVZo0acJHH31EvXr1Ch2bnZ1NdvaNfhcpKSVbD6S0iZy7AoupcIWhQdTKzUSt2Gw5kOt64bns+ETWdxtD/
4g16L08Cx/rZM5GJPDkM4tITs7KMy8qKoX1G84xZFBdjEaVRUtO5qUjy7LEilVngPwN3W6ma+dqPPZoU/
z9PPBw1+NppytaIBDcfoYOrkdaeg4//
LgLk0lFUeS8TKOHHwznycea5xvv4V78x5amQVaWkcVLTjDq4dKr+XIreh8vyjSsQ+J+J2QESRLGtAzazv7q
P5EFWaLiJT4+HpPJRFBQUL7jQUFBnDx5stBrateuzW+//UbDhg1JTk7m888/
p02bNhw7doyKFSsWGD958mTefffdErH/TsCQku54jrCdKYaayURWTDwX/
l5GjceHFcE662RnG1m24jQLFh0nOiYNfz93omNSSUvLyfeRTCbzF/
8uOF7g2M3pkoV9G2RZIjY2ndo1yzrdfoFAUDo8MrIxA/
uHsXL1GWJi0gjwd6dn95qULVvwpapmzUD2O9AywBKaBnv3Xbmt4gWgfM92zhEvmkbKyXOknrmAT63Q4s93h
3PHpUq3bt2a1q1b533dpk0bwsLC+Omnn3j//
fcLjJ80aRITJ07M+zolJYVKle6dlFbfBrVIPHTCaW7FAkgSUcs2Ol28pKZl8/T/
FnP8pvTkm9vYOwtV1Th8NIYLFxOpWuXeqyIpEPxXKOPrxohhDWyOGzSgLrPnHnHKmpoGKSlZbN9xicwsA9V
C/
WjYoHTrN1Xo15njk39y2nxGKyUw7iVKVLwEBgaiKAoxMTH5jsfExBAcHGzXHHq9nsaNG3P27NlCz7u6uuLq
6lpsW+9Uaj41nPPT55fcApqGKctym/
mi8vmXWzl5Oj53iRJn774oIV4Egv8ANWsE8MRjzfj5173Fniszy0D33tPzdaoPrerH+
+90pW5YuWLPbw+BrRrh17guiQeO2x5sA0mvwyu04A7FvUiJZhu5uLjQtGlT1q1bl3dMVVXWrVuXz7tiDZPJ
xJEjRyhfvvRT2+4EJJ1S4kWGvKpXdup8165lWOwHVFIsX3mq1NYSCAS3l6efbMH773Qtcl8xSTJvOR84eDW
fcAFz7ZnHxy7k3LlrzjDVDlsk2s//znJQn73z6BSqDO+Ni5+vkyy7synxVOmJEyfy888/
M2PGDE6cOMHTTz9Neno6Y
8aMAWDUqFH5Anrfe+89Vq9ezblz59i/fz8PP/
wwFy9e5PHHHy9pU+84VKORzQOeQTUYSnQdZ4uj4yfi8mJWSouDh6K5du2/4S4VCATQ577aPDjC8VIIEqDTm
YOCC/MKq6qGwWBimhM8O/biVbUiZds2KbKAkXQK7uXL0fjTl5xs2Z1LiYuX4cOH8/nnn/PWW2/
RqFEjDh48yMqVK/OCeCMjI7l69UYDrsTERJ544gnCwsLo3bs3KSkpbN+
+nbp1S7eN+Z3AlSUbyIyKtT9NuigoMqbMLKdOebsC3ePjhXgRCP5LdO1czeFrNOC+nrVQFMs3KpNJY+36CD
IzS/
bF8WZqTxhdpD12xcONGk8Op+eef3AvX3CrKyvuGknHzpAVVzqepNKiVAJ2x40bx7hx4wo9t3Hjxnxff/
XVV3z11VelYNWdT/
zOg0h6XV5ROoeQJbuyjiTAo0KQzXGO0KB+EHq9XMAdW9KUVpdYgUBwZ1CUvkiyLHH+fOL1oFzL90hV1UhJy
cbdvXSKvFUa3IPQ0QM5P2Oh3dfoPN0JHTOEui89hntQYL5ziYdPcui1r4havimvoVvIfR0I/
2gifuF1nGx96SN6G93BSIrikNdF0utoP38K3bfOwr+Z7ah9AE3VnN7DyMfHjQH9wpDl0nHByLJEs6YhhaZV
CgSCe5f4hAx0OsceY7IsgQQmk/WXK0kC31IsYCdJEq1+m0xw9zZ2X2NMz+Tsj3+zvNEAEg/
fKD+SsPcIq1sNNzeCzPXmaBpXV21ldev787WVuVsR4uUOpnzPdmhG+70uiqsLlQZ1p2zbpvTaNY8+x5fT6r
ePULw9LTZhDHvpMTyrOL8S7cTxbWnSqOSDrGVJQpYlxj3dqsTXEggEdxYBAR42RcitGI0q1av52dyh0TRIT
nbulrotJFkm5eR5h67RjCaMKWlsHTYeTdPQNI1dj72OmlOw75FmMqFmG9j1+OuUcHH9EkeIlzuYch2a49co
DElnu5eHpFMI6twy3zHfsOpUGzOEXrvmUbZN/kJMel9vGn3yIo0+ftGpNoO5ON2KVae5EpXs9LlvJTjYi+
+/
6UfDBval3gsEgnuHnt1qIFt4MbPG0uWn7Rq3dXvp99Uzpjseu6eZVFJPXyB67XYSDxwn6fApNAuiTlNVko+
c5tq+o8U19bZyxxWp+69hSE3j3O/
zOTdjAdlxiXhVq0iNJ4dTeVgvZL2eDounsq7LKNLORlqdRzOaqPP8I4We8w2rTvcts0g+EUHKiQh0Xh6U69
Acxc359XHS0nIYO24Rx08Ur/fIrUgSBAd5UaN6ADVrBlA+2JvKlcrQtElIqW1PCQSCOws/P3eeerwZP/
y026HrjEbb3hpZksjOLkK8YTHxrV+T+G37LYoPa2we+AwV+nWxa2zqmYsE2BlecCcixMttJONKDGs7PkzaO
XPHaDSNzCsxxG7aQ8Qv8+i4bBqelcrT58hSLs5Zzunv/
+La3mP5I9IVGUwqjT97maDO1rdOfMOq4xtWvVg2a5rGseOxHD0ei06RaNmiEpUq+uade2nSymI3TSt8Xbga
nYavrxuDBtSlU8d7v/
y1QCCwzWNjmuLmpmPqT7vJzHKe2FA1jZo1Am0PdDK1nnmIuM1FS9M2ZWQROWe5XWP1Pl5FWuNOocS7Spc2d
1NX6TUdHiR+x0GLpf9d/HypPWEUNcc+gFu5AFLPXmTDfU+Qdja/
K9OjSghdVv9W4v0sIiOTePWN1Zw8FZ+vk3PnjqG88HxbXn51VaFdn52JLEmomsaklzswbEj9El1LIBDcPWR
nG1my7CTr1p/j1Ok4kpKLVzlcliV2bnkSnR3b9s5EU1W2PTCRyHkrSqxMht7Xi8HR20vE+14cHHl+C/
Fym0g8dJIVjezI8pFlXMr40HHxD2y9fwJZMQkFgrAknYJroB99ji3D1b9MidibkJDB8IfmkJySVaAAnSxL6
HQyOTkl1H+pEHSKzMqlo/D39yi1NQUCwd1Dy3Y/
YTAU7540f+4Dt6XtiGoycfq7Pzn19QzSL0YB4BYUSFZMvFPmb/z5K4S98KhT5nImjjy/RcBuKZJ8/
Cxnps7izNRZXJyz3L5qbqqKITmFTf3Gknk1roBwAXO8S1ZsAhG//
lMCVpv5e+5hkpILCheziVqpChcAk6qxZJloCSAQCAqnWZMQlGLGw6mlXCk8F1lRqDPhEfqfW8eg6G0MjtvB
wCubqfnMg0WbUJFBkpB0Ohq88yx1Jo5xrsG3ARHzUgpkRsex/aEXiVm/
01wVDsmhSoqaSSUnMcX6IFXjwswl1H2pZNooLFl2qlR7FdlCls09SAQCgaAwHnownB27LhX5ep1OZvOWCwQ
He+froWQwmNDp5FLpPC3Jcr7ic82/
f5vqjw1lTfsHMWU4kMZtUinXsQVt53xVoJjd3YoQLyWMMT3jlqDcvP85nZwkGwKnGKSklG69A3vw9HS53SY
IBII7DE3TOHU6npxsE0MG1eXfBcdRFMnhfmtGo8q3P+zku6k76dqlGoYcld17L5OZaUSvl+nVoyajRzamWq
h/CX2SwvFvUo/az47kxOe/OpSRFLtpN9f2HKFC384AJB48QdSKzag5Bvyb1ad8r/bISunG9xQHIV5KmPN/
LCT1zIWS7U+EuRqvb53iZRJZI6icF5GXnFO3xcVFsWubSbLioDKZNLp1LbnPKxAI7j72HYjik882czbiRh+
fAH93Klcuw9mIBFJTcxyeU9Ng7bpz+Y4ZDCpLl59i1ZqzTP2uP41LoSBnLsbMLHPbGAfDVSVF4dS3fxLYuh
Fb759AzPqdSNe3kzSjCY/K5Wn/
73d3Tfq0iHkpYc7NWMj1vaISRTOZqDF2RInNP2RQvWI1XGzZvAJzZw5n/
epHWb1stNWmaLlIUuFhQbIs0bxZBRrWd25PJoFAcPey/0AUT/
9vMRHn8jcgTLiWyYGDV5k4vi1t21QGsOv+YwtNg5wcE6+8vsquujHOwJiZxfruYzj20Y929a67Gc1kImbDT
pbU6knMxt3Xj6l52a4Zl6NZ23nUjV2COxwhXkqYrNiEInUKdQhJotKQnlTsb19xoqIwZFA9qlcPcDgATpYl
atcK5PNP7qNGjQDK+Lrh4+NGn/
tqW7yByLJEhQo+fPbxfXl7zTqdnDe+ZYuKfP5Jr1LZcxYIBHcHn3+1FZOqWrzdfv3tdj79qCdffnofrVpWI
qicc3qhxcdnsHVb6VTiPT75J+J3HHRYuOSiGU3kXEsGtRCxpWqY0jI49MbXxbKxtBDbRiWMV2hFc6pbYT8s
TsC1XAB1xo8i7OXHkYpQJtseLkYmsXzFaerWKYtOkTh79hpGO/
ZaPTz0jH64MQ89EJ4v4A3g+efacPhoNJGRyfkCgRVFwtVVxycf9qBuWDlWL3+EtesiOBtxDTc3HV06VaN2r
Xsj4EwgEDiHiHPXOHnKehpxcko2O3dfonPHanTqGMpzE5cRn5DhcCzMrciSxIlTcSVeOFM1Gjn9w6wSe5bk
cnH2Mpp//
xYufr4luk5xEeKlhKk0pKc5y6gEUDzdGXRlM7KuZP4ZjUaVyZ9uZsEic8CbJEmoqrnxV7cu1di157LFPeQK
Id58/
kkvatUMLNRD4uvrxoxfhzBr9mH+mX+MhIQM3Nx09LmvFiMfakzlSuZfHHc3Pf363P3t2wUCQckRG5tm17i5
/xxlwcITuLnp2LvvSrGFC4CGhqtLyQe6ZsUkkJOQVOLroGlE/D6fsDs8nVqIlxIiauVmDr/
1Ldf2HCmR+SWdQoW+nUtMuAB8+/0OFi4+DnD9l/zGL/ra9ecsXGXmSlQqD4ycR40a/
vxvbCs6tq9aYIy3lytPPd6cpx5vjtGo5gkkgUAgcIQAO4tV7t5zGU0zb007q/
SDpkGHQu5vzkZ21dse5CQi/1l5x4sXEfNSApz/axEbez/
JtX3HSmwNzaRabMToDJKSs5gz70ixw3UiIq7x/
IvLWbbCekG50qqbIBAI7j1q1gwgtKqfzaSC3PuZM2tWVazgTY3qAU6bzxJugf74N29gX3FTQCrGi60xzfHO
1qWNEC9OxpCaxu6n3jL/lpTU3qQs0Wr6xwS2DC+Z+YFt2y9iMBTf/
tybxeRPNpOZaSj2fAKBQHArkiQxcULb638v3bUvX0nlSlTJ1di6mXqvjbU7AaTh++NRPNwcXkPSKfiF3/
lb9UK8OJmLs5djyixeQzCryDLVxwyh2qiBJbcGkJnp3FbwGZkG1m2wvtUkEAgERaVt68p8+VlvygY6J4vIE
V5/
ay3RMaklvk6lgd1o+s3rNhWaW3BZwl56jOqPDTPXcnEAzWii5tMPFMfMUkGIFyeTevo8cgl2IZUUGcXDvcT
mz6VaqHObkekUudTeTgQCwX+Tju2rsmzRSKZ+14+3Xu/E5Pe7lcq6h49EM3TEbI4eiynxtWo/
N4oBF9bjHWa5SGdWdBwnPvmZ8A8mUCa8jrmfys0Upn2ul8EIe+kxyrZp4kSLSwYhXpyM3tcbrQR7AGkGI4G
tG5XY/
Lk0blSeypV9kYvZ2CwXk6ri431ntV8XCAT3Hooi07JFJQb2r0uP7jUJCfEula2krCwjE15YXuxO1vYgyTKp
J617sg+98TWLa3bHM7QiNZ68H4/
K5irAOk93qj9+Pw3eeRbvmlXyxvvWq0nrPz+l0ScvlajtzkLSHK0xfIfjSEvtkiD5ZATLwnpbHiDL+NarQf
KR00WaX/F0Z2jCbhTXkuvrYzKpXIxM4tSpeN79cAMmk1r8WgiyxIrFoyhbtvRdugKB4L/
LrNmH+OLrbSVeKzSX7l2r079fGK1bVnLay9+tnP1lHrufeMOusZJOQTOaaPLVJGo/
NypfPTBN08hJTEaSZVzKlP7z8lYceX6LVGkn41unOpWH9yZy3sqCAbvXm/U0/
vQldox8mez4RIfnV3MMmDKzSkS8qKrGzL8P8efMg8QnmKPNPT30VAjx5vyFpGLN3bZNZSZ/
tpno6FQCAzzo26cOnTuFoi/BLTaBQCC4f2gD9uy9wqYtF6z2S3MWa9dHsGZdBCEh3nz+cS/
q1C7r9DXU7Bzrzd9uIrf8//7nJxPYunG+RA9JknD1L4OmqlxauJaz0+aQdvYiLoF+hD7cn9BRA9F73ZkvnM
LzUgIYM7PY9ehrXJy9DElRkGQZ1WBA5+VBy18+pNLg7ux68k3OT1/g+OQStPz5A6o/
NsypNmuaxnsfbmDRkpPFmsfLU09auiGvjoIkQXCQF1ej01BkCZOq5Z1rUD+I77/
ph5eX6A4tEAhKDqNRZfHSk8yee5hz5xNxcVGoUMGHiIhrJSZoZFnC3V3HnL+GExLi3GdR3I4DrGnjWC87Sa
dQZXhv2vz1eb7jppwctg59jitLNiApCprJlBcQ7BVakW6bZ+JRoXT6yDny/BbipSRtOXWOS/
+uxpCShnetqlQZ3pusuGus7z6GtLORBZWzHb9Fkk6h4XvjqTfpKafaum//
FZ54elGx5vD00FOtmj9HjtoXtCbLEl27VOOTD3sWa12BQCBwFE3TWLbiNNP/
2M+582YvuKLkVhF3zhqKInH/
0Aa8NLGdcya8TnZSCssb9CXzSqxDysutfFkGR20FwJiewekfZnHsox8xJBWeKSXpFAKaN6TH9tlOsdsWQrz
cIeLlVlSDgaV1e5N+4UqeK68otP7jE0JHDnSeYcBrb65hzbqzxYptkWWzG9KROSQJli4cSflg7yKvKxAIBE
VF0zQSrmViMqqkpefwxNMLSUnJdlohO18fVzaseSzfMZNJ5fCRGJKTs6hQwYeaNewvcnfyq+kceu1LTFlFK
8kR3K0NYa8+ycEXPyHx8Em7mjz22vsv/
k3rF2k9RxAxL3colxevN3tcioHsoqfS4B5OsugGFy4mFjso1xzi42Cbds3s9enb+84viiQQCO49JEkiMMDc
XiAImDNzOLPnHGbJ8lMkJWVhNBavWGd6ev7inEuXn2LKDzuJjUvPO1andiCvvtSBhg2Crc51Zuos9k+cXCx
7YjbsJHrdDvOboz0CTZaJ2bi7VMSLI4hU6VLAmJFJ5tVYLi9ci1TMAFWdtyc6T/
v6eDiC921MY3ZGczSBQCBwBmUDPXn2f61ZvewRtm18ggb1g4qcai1JUD7khld5/
sLjvPXuunzCBeD0mQSeeHoRx45b3nI35eRw6I2vi2bITWgm1aEK8BKUfJRzERDipQRJOnqarcMnMM+nCQtC
2nNx1lJzMFQxyElMdpJ1ZiIvJTPt1z1ERFxz6ryOYOttQyAQCG4Her3C99/0K/
I9StNg2OB6AGRmGvjy622FjlNVDZNJ5atvt1ucK2bDLnKu2XH/
d3IGp6aqlO3Q3KlzOgOxbVRCxO86xLrOo1ANBrPSxfxDUFz0Ps6JDTEYTHz48SYWLz1pd7S9p6e+gAu0OCi
KRNMmIYRWdW41X4FAIHAWXl4ujH2yBU+PW+zwtTpFYkD/MAA2bDpPhpX+bqqqsf/
AVa5EpVChkOwku4QL4N+4Ltf2HHHY1sKQdAp+jcIIaN7AKfM5E+F5KQE0TWP7wy9iys4pVmDurUg6hdCRA5
wy1yefb2HJMnNatL0eQWcKF0mC4GBv3n+7dMp3CwQCgT1omobhlvt2syYh6PWOPy6NJo2zZ81e7di4dBTF9
v5TbGx6oce9qlWya01nCRcA95BytP/
nW6TS7nZpB8LzUgLEbt5T7MDcW5EUBZ2nO3UmPlLsuaJjUlmw6HipbmOGVimDopOJjUvH38+dAf3CGDyoLt
5eomWAQCC4/Zw6Hc/0P/ezfsM5DAaV8uW9GT60PsOHNcDVVUeTRiHs2nPZ4XnT03MACPB3tyu+L8C/
8N51AS0a4lOnGimnL9gdr1JUdN6eNHz3Oao9OgQX3zszE1SIFztIOnqaM1P/
Jm7bfmS9jpA+ncy9IkIKL9yTfOyM3dUPbXJ9Hs+qFWj/
z7d4Va1Y7Ck3bDxffLssUK6sJ6mp2WRmmbtSu7vrGTq4Hv8b2xIXF1FNVyAQ3Hls2xHJ8y8uR9O0PIFx9Wo
q30zZwYZN55n6XX/
GPtWiSOKlUiVfAGpU90dRLJeSkGWoU7sslSuXKfS8JEm0mPY+67uORoViCxjf8NokHzqV1z4gt0BdQKtwOi
//GRc/32LNX9II8WKDU1P+Yt9zHyApct4WUOL+45z47Fc6LfuJoE4tC1yj8/
RwWnR2jbEjqDSoO8FdW+frSVEc0jNykGXH6rHYgyxL1K1bjg/e6caZs/
EA1KoZiLu73qnrCAQCgbPIzDIw6Y3VmExqgdu2psGRozH8/
sd+xj7RnNatKrFj5yW75pVliYYNggkO8uL1t9awYtUZi1lL5uMSE55tY3XOcu2b0W3zTA68/BlxW/
baZUdhVBzUnXZzvybp8CkifplHakQkrgF+VH2wL+Xv64Cs3PkvmqJInRVit+xlbYeHCj8pS+jc3eh/
YT1ugf75TmXFJrCgQgc0o9G+hQrz0khQ7ZHBtPz1I6fvN65Zd5ZXXlvt1Dlz+fjDHvToVqNE5hYIBAJns2j
JCd79YIPVMb6+bqxZ/ggAY8ctYv+BqzbndXPT8cdvQ/h9xn5WrTlrtehdcJAXr0/
qRNvWle22O+3CZZbV64spI9O+CyRAkmj8xavUGT+a+O37STpyGsXDnZBe7XErZ3+hvJJCFKlzEie//
D3PpVYAVcOYmcW53+dT96XH8w5rqoprWX9qjh3B6e9n2vbAKDLe1auQfuEyao45INbFz5c6L4yh7qtPlkig
VKcOofj6upGcnOW0ORVFIjTUn84dQ502p0AgEJQ0p07Ho9PJVovRJSdnkZCQQVCQF+OebsWjT9ruS/
fA8Abo9QorVp2xOEaSoGpVP+bNGuFwB2qvqhVxCwog/
byVrSxJwi04EP+m9Qho3oDqjw8jKzqeZXV7k3Ly3I1hOh01nhpOky9fRXHJ32vOlJNDws5DGNMz8Amr7pTQ
BWcgso2sEL1uh/VsIVUjeu12VJOJiF/nsaxhP/7W1WWOa33SI6Mo36u97UVMKkgw6OpWOq/5nbqvj8W/
eX2ilm1iz9PvcG3f0WJ/jtTUbDZsOsfqtWe5dDkZvV7hnTe7FHteyOvfRXiDYH78rh96/
Z3vbhQIBIJc9HrFrl3+3Jg9e94nJQkCAzxZuz7CqijRNDh/
PpGEhAx7zc1HtTGDrYcTaBo5Sal4Va1ItdGDMKams7bjw6SeuZB/
mNHImR9msXPMazddqnHyq+ksCGnP2o4Ps7H3kyyu1o0N9z1O2nn7ts5KEuF5sYI9dVk0o4ntD0wkct7KvO0
f1WAkavkmNJOKS0AZchKSrM4hyTLG1HR2P/mmWUXL5rLNCXsOE/HzXMJefpxGH7/
osBfGYDDxzZQdzPv3KAbDjc/SqkUl3nqjE88/15qvvt3h0JwFbJck3n2zC3371C7WPAKBQHA76NC+Kn/
OPGjxvCxJ1K4diJ+fOQuoVq1APDz0ZGRYLh2hadC8WQWWrTiNLEs2+ySlpedQtqynw7bXeuZBIqbNJTM6zu
KLtpqZxZkf/
+b8zMWUa9cUU1Z2Xu2xW42+OGsJdV95HJ861dj16GtcmLmkwJjoNdtZ1Wo49+2bj0fF21dgVHherFCufTMk
a4FLsozO28MsXCDfFpFmNJlVb2Ky1TkkRaF8z3Zs7PMUGZeu76Ne/0HP/
WE88ekvnJs+3yHbNU1j0ptr+HvO4XzCBWDPvsuMeXw+fe6rTedOxd/
mWbP+bLHnEAgEgttBk0blqVe3nMUaLKqm8diYpnlfR0Ym06xJiNU5fX3diIvP4MqVZJu9kfR6mXJFEC4Arg
F+dNsyk4DmDa2O04wmDMlpXFmywepugqRT2DfhI+YHtSkoXHLnMpnIuZbE0Q9+KJLNzkKIFyvUnjDacjl/
SULWKaScumDdj6iBpqmFj5EkkCX8GoWRfOyM5R8qSeL4Jz/jSGz1wUPRrN9wrlB3qMmkERefwd9zj/
Dxhz14ZFTjfBlBOp1MqxYVcXW1vQWkqhpbt13Mq2UgEAgEdxOSJPH1572pXs2ceKEokvnWLJv/
nDihLV06VeP0mXgeGj2XB0bOZfPWi1bnTE7O4n/PLWHt+nNWxymKRO9etfD0dLE6zhpeVSvSY/
tsuqyfYfbaW8KenQRVJXbDLgxJqdbHGU2c/
2Mhppzbd98X20ZWCOnZngbvPMuRd77LF7hrbq4o0Xb2V2wZPM7mPH5N65O4/3i+ZliSoiDJEm3nfE38jgNI
Op3l7CRNI/XUeTKvxlqsLXMrS5eftFpTQFU1Zs0+TFxcOnHx6dSs4U92tonQUD/
uH9qA9RsiOHQk2q61NA0yMgzF+gUUCASC20VAgAczZwxj245I1q2PICPDQGhVPwb2DyMkxIeLkUk89tQCMj
PtzCC1A0Uxd7N+ZmzBchtFQQL7ukRbw4HrTZnZ5CSm4B4UWLw1i4gQLzZo8PY4ynVqwekpf+UVqavQrwu1x
j2ET+1qSHodmsHaD7RG8qGTYDKBLKH388U9pCwV+3amxtgReFWtSOyWvdd/
8qzjSKuB2Lh0m3VcMjMNLF56Mt+xM2cTWHm9HoG9jh53dx1lyrjZbZtAIBDcaSiKTId2VenQrmqBc9N+2UN
WltFm7Iq9SECd2oF06lCNnBzntJCRXUq3npak193W6rtCvNhBUMcWBHVsUei5Cn06cWWplX1EjbwUaFQNY2
oa6RFZhPTplJdyFtgqnFNfTbdqg1twIO4V7PO6gLmtuzXPiyVyfzntFS6KIjGgX5jIMhIIBPckmVkG1qyNc
GpRTw04fiKO4yfi+OHHXXTrWp233+iCh4djAkTTNGI27OTc7/
NJO3fJjpdp5yApMpWH9kJxu33tXUTMSzEJe+mxwiO3LaAZTZhyDGwdPgH1+jaRd+1QZFcrWy6yRO1nRzpU9
bBv79pOr6B7K4oiUa6sF4/fFMwmEAgE9xKpKdkYHbjH24umXf8PWLfhHC++stKhuEbVYGDrsPGs7/
oIF2cvI377gSI3AlbcHRMhkk5H/TefKdJazkKIl2JStk0TWv/x
CZJeZ25OcT0I1yqqStbVOCJ++Ycj705hdcv7Ua2o5ZD7OhD20mMO2dW4UXk6dQy1qyZBUfHw0PP2G53x9/
couUUEAoHgNpGRYeDU6Ti7ukEXB1XV2Ln7EvsP2q7cm8vhN7/
h0nxzpfQ80XKz+HHAZH0ZH4fGV32wH75h1e2/oAQQ7QGcRObVWM7+Mo/E/
ccxpmcSvWab9QvsDCrxrBJCh0VTidmwE82kEtgqnMA2Teyq+ZKTY+Krb7czf+GxAunSzkCWJdzcdMycMYwq
FpqJCQQCwd2GwWjihx93M2feEbKySn4bBm5swb8xqZPNsYa0dOYHt8WUbr01gF/
TeiTuO+YkC29QrnNLuq3/w+nzivYAtwH38uVo8Ob/AEg+EcGyur2tX2CnZky/
GMWKRgNAlpEwp7L5NqhF+3++xaeW9RotLi4Kr7zYnrFPNGfn7ku8+8EGp/4iqqpGdraRX37by/
vvdHPavAKBQHC70DSN199cwzoLpSZKClXV7G7ZkrD7sE3hAlBz7AiOTZ5G+oUrhaZKS4pC2U7NiV230yFbS
yOuxhZi26gE8Kkdit7Z7cRVNa/
ib8qJCNa0f4jMmHi7LvX1dUOnk0vkDcJk0li15qzTIuYFAoHgdrJvfxRr19snXJy5LS/
LEiHl7cvesTu2RdVo89dnKK76AsVSJUVGdtWj8/RA52X/
1r+kKAS2bmT3+JJCiJcSQDUa0UqweI9mNJGTkMiZH2bZfU1kZHKJ7dsajSppadklMrdAIBCUJouWnrB5rwz
wd+e5/7VyqmfGZNIY0D/
MrrF+jcKu1xuzTkCrcMq2bkzPXfOoOLg7kmJ+5EuKjGZSMWXncHXZJoz2dqbG7Jmq8dQIu8eXFEK8lADX9h
zBaIdLrzhoJpVz0213Ns3Fy8vFaTUKbsXFRcHb+/
alzAkEAoGzuHo11WamZlp6DpqGw52gc6v3FsbIB8OpFupv1zxu5QKoPLy3xdYzkk4hsHVj/
BrWAaBMg9q0n/sNw5L3Uf2xYTcyZE2quYr8zc8GCwZKOgUkiVa/
foh39cp22VmSCPHiRJJPRBC9fgcppy+Uyno515LsHtupQ6jDjR3tQVEk+vauLeq8CASCe4IAfw8UG6KkjK+
7Q8JFkmDe7OF8/UXvvAaPuSiKRP165cjKNjJ77mFSUuyLe2n27Rv41KlWQGxIioxbuQDazPq8wDWmrGzO/
7nQuq2yhEtAGVzLBeBZtQKyuxt6Hy8qDe5Bjx1zqPbIYLvsK2lEwK4TiNm0m/
0TPyZxv5OiunMzkaxlJEkSXtUq2T1l2bKeDB1cj3n/
HrU4Zd06ZYk4d40cg8kud6iiSHh7ueZrWiYQCAR3M31612bNugiL52VZon+/
OrRqWYlvpuywa05Ng+EPzEWj4I3VZNI4eiyWEyfjUFWNr7/
dwRuvdaJv79pW53T1L0OPnXM4O20uZ3+aTcblaFwD/
an+6BBqPvMgbmULenGurt52o2iqJVtNKu1mf0VwtzZ2fbbbhRAvxSR63Q429HoMzRlbMpKEe/
my1Hr2YbxqVGHbsPFWh9d4arhD07/
wfFuMRpUFC48jyRKyLGEyqej1ChOebcOI+xuwZesFXrheLCnXdSpJEpqmFajY27hRCG9M6kT54NtXIlogEA
icSdvWlWnSuDwHD0UX2GpXFAl/
P3dGDGuAn587TRqV59CRaLsKgqo23ghz58gxmHjr3XUE+LvTupX17Rm9lydhE8cQNnGMzfUBTJn2eXWMdo6
7nYg6L8VA0zSW1u5JakRksRtiSXod1R4ZTNOvJqHz9EDTNHaMetnclvyWfyJJkfFvVp9uG/
+yWp75wsVE5v5zlK3bLmJSNRqHl2fE/
Q3w93Nn9dqzJKdkUyHEh549auDtdWOeM2cTmPn3IdZtOEdOjpEa1QMYPqwB3bpU48jRGLKyjISG+lO5kpMz
qgQCgeAOICPDwPsfbWD12rP5br8NGwTx0XvdCQkxP1sSEjIYO24xEeeuOXV9WZZo2CCY36YNcuq81/
YdZWWzITbH9T+3Fs8qFYhavomzP88lLSIS17L+hI4cQJUH+qJzL5ledo48v4V4KQZx2/
ezpu0DxZrDJ6w6jT9/
hcCWDXEN8Mt3TjWZOD75J05+OZ2cxGQAFHc3qj06hEYfv4Dey9PivBs2neOVSavRuOFByfWcTBzfhocfbIS
qaqxZd5a/
Zh0i4tw1XFwUenavwYMjwq0WncvMMhAfn4GXlwt+ZdwtjhMIBIK7meiYVHbvuYLJpFKvbjlq1SzYQTknx8T
zLy5nx65LTl9/3aoxTr/
HrmgyiKTDp8yBurcgKQpBXVrRcemPbB02niuL1yMpinmsLIGq4Vu3Bl3WzyiRbtJCvJSSeLnw91K2P/
hC0SeQZRq8/T8avDXO6jBTdg5Jh0+iGk2UqVcTvY+X1fHRMan0HzwTk0m1GLsy7YcB/
DnzIFu2XSxwTqeT+e7rvrRsXjHf8bj4dH6ctodlK07l1XVp1rQCY59oTpPGIVZtEggEgnuRzEwDXXv9XiJ1
tJYuHGl37RdrmLJzuLxwLalnLmBMz+T0DzMxZWTlqxcj6RRcA/zMcTQ/
zeH4pz8XuqMgKQrlOjan67oZxbbrVkSF3VLCNdDP9iBLSBKKqws1nrjf5lDF1YWA5g3tnnr+guOoqmZRuCi
KxORPN3H+QlKh541GlQkTl7Fu1aN5XU7j4tMZNeYf4hMy8u3v7j8QxZPPLOLzj3vRqaP1ir8CgUBwr3H+Qm
KJCBcPDz2BAcXvG3dpwRp2Pfa62Xsvy3mVdnU+XpiystByjOi8PKj26BDqvvIELmV8OP39TIuhEJrJRMz6n
SQdPU2Z+rWKbV9REanSxSCoUwtcC4notoWkyChuLnRc8iPu5cs53a49+65YreliMmkWhUsu2TkmFi05kff1
N9/
tKCBcgOsiSePt99eTnX37S0YLBAJBaaJTnP8YlWWJwQPr4uJSvBIU0et3sGXoc3lhBze3CDCmpKHlGKn+
+DCGJu2l2Tdv4BESROLBExhT061PLEnErHespYCzEeKlGMh6PY0+dmDbSJbxb1aPem88Q7+zawju2triUNV
kIjshEVO245V6nVXOZd16c7pgamo2q9eetRhRr2nmMRs2nnfOwgKBQHCXEFrND38/
x+JSJMl6gbsyvm4MHlC3uKZx+I2vbfbRi/hlHmd/
mn3jgF19EcwJK7cTIV6KSfVHh9J86jvovC0Hz+ahqriVC6ThO8/iERJU6JDshEQOvPQJ/wa04N/
AVsz1DGfLsOdIPHii0PGF0aJ5Rau/
GPaKm8zrrtCrV1MxGq13pdbpZM5fTLTbRoFAILgX0OsUHn6okd3jJcDb2xV/
f3eqVvGlevX84QeSBEnJWQx9YDa/z9hfZLsyLkcTv+OgXWLkxGe/
5vXOK9OwNoqtbCJVo1y721vfS4gXJ1Bz7AMMjt6GewXbW0BXV22x2EciK+4aq1rez8mvZmBITgPMBYMuL1z
Lqlb3E7PBPjfdkIH10OlkiyLFXsFcu1YAAB6eeptjVVXD08P2OIFAILjXGPVQIwYNMPclsvVyqAEpKdnEx2
dw6XIKERH5X/o0zXw/VVWN737YycLFx4tkU95WkR2kX7hCemQUAHpvL6o/McwcH1MIkk4hoGU4/
k3rF8kuZyHEi5PQebhjsLVPiFmMpFpoH3Dg5c9Iv3ClQAqbZjShGoxse+AFVIP16ohgrqb7+ce90OmUfB6Y
3L4ar7zY3q5AsLFPtACgQogPNar7W/2l1FSNLp2r2ZxTIBAI7jVkWeKNSZ34/edBBAbaH2RrT3G7qT/
tLlJfOo+KwRZ7HxXGikYDmevdmHVdRhHYpgll2zYxn7hFxGiqStr5y+x+
+m2ST1iuRFzSCPHiRHQe9u17yi4FPRQ5SSlcnLWk0Nx7AFSVrJh4rizbZNca7dpWYcHcBxj5UCNqVPenapU
yDOwfxt9/3o/
BqBKfkGFzjq3bIwFzhd2nn2ph0WMjyxK976tFxQqiaJ1AIPhvIkkS4Q3L07F9qM2u1I4QF5/BqdPxDl/
n4udLmYb2ZwMZklMxpmUQu3kP20c8j2/d6rT8fTKBLcNRPK5vI0nmWi/ZsQlE/
DKP5eH9ubJ0g8O2OQMhXpyEISXNZs8IABc/H7xrF0wpTouItHm9pNORfPS03TaFhPgwflxr5s4awfy5D/
L6q51ITMzky6+32XX9h5M3cujwVQA6d6zGm691wkWvIEnmGJfc5mU9utXgjUmd7LZLIBAI7lUG9g+zy6PiC
JGXkop0naRzvBpKbsfpsz/
NQefuRthLj2HKuN4u4KY3WM1oQjOa2DJsPFmxCUWyrziIOi9O4sxPs8m5ZnuPsd5rY5ELceUpdnhtNFW1a5
w1/vjrIIosYbLDDSkrEn/OOkR4w/
IADBpQl66dq7F85WmOHovFZFJp17YKvXrURCmBdEGBQCC4U0hLy2Hj5vMkJWdRPsiL9u2qFprKXDesHEMG1
eXfBUWLVSmM9HTHs04By558O5AUmVPfzDALIEUGUyFJG5qGmmMg4rd/
qffqk0VeqygI8eIkIn6ZZ9c4jyqFV6L1qVMNr+qVSYuItHyxqlKxf5eimAeYU9v27Ltil3AB837szltKXp+
/kMjCxSc4fcastFetOct33+/kuXGt6d3r9hUsEggEgpJA0zSm/3GAab/
uITvbhCxLqKqGj7crr7zUnvt6FrzvTXq5IxVCfJjx10GSk4vf5NDPwVTsvOsa1TW3AjA6LmI0k0rCniPmra
LChEsuqkrctn1Fsq84iNdlJ5EZFWvXuP0TPiKpkK0fSZKo/9b/
rF5bvld7vGtUKZJ9uTiam2+66Yf2yNEYnnxmEWcj8jchi41L54231xY5Kl4gEAjuRC5fSebt99bz3Q87yc4
2C4Dc4NmU1Gxef2st6zeeK3CdLEs8MqoJq5eN5o/
fhvDLjwMJrVqmSLEwOp1E0yK2X6n1zANFEi65mLeGbBQflSSHAoOdhRAvTsLeSruZUbEsb9CPk19NL3DOxc
96L4fkY2fsyjayhCRJNKgfbLUGzM3kdjbN5Yuvt2EyaRYj37/4ehuZWUW3TyAQCO4ErkSl8PSzi+k/
eCZLl5+yOE4Cvp2yw+JLoV6vUL9eEE0ah/DlZ73x9XGz+/6by5CB9fDxKVoXZ/
+m9W+8FFtIfbaJHe+7wd3aFG3uYiDEi5Oo/qjtNuM3s3/
iZK6u3prv2PFPfjbvLVog41I0lxets2v+zCwDS5ad5POvtvLd9zs4dCQaTdN46IGGdqfdqaoGmsa+A1FEXk
ri8JFoq9empxvYvPmCXXMLBALBnUhcXDqPPPYve/
ddsTlWAyIvJXPylO1soCqVyzB31nAef7Qp7u72RWz4lXFj7YYIOnb9hZFj/mHRkhMYHPSkNHz3OdrN/
RqfOoWUspBlc7fooiLL6H29qDZqYNHnKOrSpbHI999/
T9WqVXFzc6Nly5bs3r3b6vh58+ZRp04d3NzcaNCgAcuXLy8NM4tFzWcetOk5yYcsc+LzX/
O+NGZmEb9tv9W9RUmncHXlFptTb9sRSc8+M3j7vfXM/ecof8w8yJjH5/PokwtoHF6eWjUD7DZz/
8GrPDF2IR9+bDtFW5YlYmLT7J5bIBAI7jR+/2M/SclZDmUM2RvX4u/
vwdgnWjCwX5hdjpDEpCwSEjJJTcvh2PFY3v1gA889v4ycHMcEjFe1SqSfv4R068uxpllswGgTWULv5UHnFb
+g9/Eq2hzFoMTFy5w5c5g4cSJvv/02+/
fvJzw8nJ49exIbW3iMyPbt23nggQd47LHHOHDgAAMHDmTgwIEcPXq0pE0tFq7+Zei+cy6yq4t9F6gqMet35
bkb7YoK10C1obpPnorj+ReX50WnG41q3i/
h0WMxPD52YV6wrT3kXrtnr+23EFXV8PcvfhdUgUAguB2YTCqLlpxwONW5fHlvh8bf16vWzT0SHWL3niv88t
teh67Z+9wHqDmGvDToPDQNJNB5eeBnT8VcCdwrBBHYpjHhH06k39k1BLZq5JAtzqLExcuXX37JE088wZgxY
6hbty4//vgjHh4e/Pbbb4WO/+abb+jVqxcvvfQSYWFhvP/++zRp0oQpU6aUtKnFxrdWaOGuOQtompqXN6/
z9MC7ZhWrtaU1VSWgRQOrc07/4wCaphVaUM5k0rhwMclu+xzFzU1H544Fa9gIBALB3UBmppHMTBsBqjchyx
IN6wdRpXIZh9apV7ccHdtXdTj+BcxJF3P/OWq39yXlzAXitx8oKFzyJgRjWgahD/a1YzaJOs8/
Qo9ts6n36pO42RnrWRKUqHjJyclh3759dOvW7caCsky3bt3YsWNHodfs2LEj33iAnj17WhyfnZ1NSkpKvv9
uF6kRkSQdOmn3eL9GYUjXfYeSJFF7wmjLg2UJnYc7oQ8PsDhEVTXWbzzn9AJJ9vLMUy3w9LTT8yQQCAR3GO
7uukJrtxSGLEvodDIvv9je4XUkSWLyBz24r2dNJMn+Zrm5pKRmc+myfb2LMi5G2R4kS2iYq/
JaRdOIXrMNQ8rtDw8oUfESHx+PyWQiKCh/
B+WgoCCio6MLvSY6Otqh8ZMnT8bX1zfvv0qVKjnH+CKQevaiQ+Nv9dLUeGoElYffZ/7ipg1RSacg63S0+/
dbq3uLBoPJZvdnZ3DrL5qXpwsvTWzHQw+El/
jaAoFAUFIoikyf+2rZldIc3jCY36YNom6Y9Ya8mqaxfWckE19ewYChM3lo9Dz+nHmQnBwj77/TjaULR/
LqSx3wd7CWi71p1y4BZWwPUjXcgwOpPWGUTSUVvXY7G+57HNVWCnUJc9cXqZs0aRITJ07M+zolJeW2CRgXX
8f2PXVe+eNDZEWh7cwvqNC3M6e/
+4uko6dR3FypPKQntcePwrduDevruyiUK+tJbJztBpHFQdPg7Tc6o2kavr5utG5ZGTe3u/
5HSSAQCHj0kaasWRdBRoah0OzKls0r8tqrHalU0XYvN1XVePeD9SxZdgpFkfK84idPxfHHzINMfr8b0THpu
LrqqFzZl6TkLLuyQcuV9bRrfTB7+L1rViH1bCSWGtRJeh3B3VpT+f77SD4RQeRsy0kymkklfvsBrixeT6XB
PeyyoSQo0SdOYGAgiqIQExOT73hMTAzBwcGFXhMcHOzQeFdXV1xdXZ1jcDHxb94At6BAsmLsaKIlSbgW4qK
TZJnQh/oT+lB/h9eXJIn7h9bnhx93ozpYjM5RmjYJEY0YBQLBPUeFEB9+/3kwb76zNl8KtF4vM2xIfcY/
2xq9zr6tpdlzD7NkmblOzM3b+ZoGCQkZPPnM4iLZOPKhRna3ZJEkiUafvsyWQZaLoGoGI5v6P03XdTNoO+t
L4rbuI/
NyjMXxSBJH3v2egJbheFQIsjyuBCnRbSMXFxeaNm3KunU3apOoqsq6deto3bp1ode0bt0633iANWvWWBx/
JyErCjX/96B9gzWNKiP6ON2GB0Y0JCysrMN7qI5QsYIPFUIcSAsXCASCu4jq1fyZ9cf9/
DV9KO+82YXJH3Rn9bJHePH5dnYLF1XV+HPWIafbNmhAXR4Y3tChayoN7Ebrvz6zWtPl2t6jHHr9KyRJwpiW
YX1CTSPp8EkWVu7Ezsdew5SV7ZA9zqDEff0TJ05k9OjRNGvWjBYtWvD111+Tnp7OmDFjABg1ahQVKlRg8uT
JAIwfP56OHTvyxRdf0KdPH2bPns3evXuZNm1aSZvqFOo8/whH3/8BzWB9PzCgZTh+jcKcvr67m55pPwzg/
Y82snL1GafPD9CubRWkklRHAoFAcAdQN6yczZgWS0THpBETU7TA1tz+Sbn4+LjSsnlFhg9rQONG5Yt0/3UP
CrRa00UzqZyZ+je+DWrjVs4fQ1Kq7UlVlXPTF5BzLZn286eU6nOhxMXL8OHDiYuL46233iI6OppGjRqxcuX
KvKDcyMhI5JuCU9u0acOsWbN44403eO2116hZsyYLFy6kfn07ctDvAPRentR4cjhnf/
zbYmqa4u5G5zWFp4o7A3d3PePHtS4x8fLP/KOMGNaAyg6mBwoEAsF/hbNn7QgfsEDFCj48P74t/
L+98w6L4urC+Dszu+zSe28KCPbee8feuzFq7IkmJsbEFDWa4hdTNVFjTIyJvffeu1gRQURAqvTeYXf2fn8s
rCJsZZei9/c8JDJ7596zbJl3zj2FEDRp4gg726rXz0q/HQRGwKnsdSQrkeD2zC+0m1gmQ/yhc0i/
8wh27bXzCFUFhmjbqa+Wk5OTA0tLS2RnZ8PComa2Nkqyc3Gux1vIevQU5SoRsQw4kRF6n/
8X9p1aGdyODz46jhu3YvWeOs1xDMaNaYbFH3XV67wUCoVSl8nJKUJwSAp+33BLo5YByrCwEOHS2Rl6tAx4v
HoTHn7+s/J6L1WAEXBoMG8S2q79skrzaHP9pr2NDICRpTn6XduB5ivfh7GbPNCYMxbDe/oYDAw8XC3CBQA+
+bgbLCzEOvfjUgbPE1y9Fq3fSSkUCqWOkp5egKVfnUPfgVswf+GxKgkXBoCjg37L7RNCUJiUZhDhUroAitM
yDTO3Emh+q4EQmpmi6Rfz0PSLeZDxPFiOQ054NCL+2IW0m4FgRUZwHdwDXtNHQWRrbRAbXF0ssG3LGMyccx
CJSfotKiQ11IeAQqFQ6hCZmYWYOmM/klPy9OPlZoCRIxpXfZ6XCP5mPcJ+2aLXOcvBMDD1dDHc/
JVAxUs1wHIcIjbtwe25y8AwjEL9ply+jeBvNqDXqb8M1h/
C2ckcObklep2T4xi0aF556jqFQqG8Sfy95Z5WwkXAMXBxtkBsJRVyOZaBl5cNhg9tqDf7itIyELxyvd7mqw
wi5eE1fZRB13gVum1UDaRev4fbc5YCMlLebUcIJNm5uDhgJkqyDNPWQCLlIdWyhbo6eJ5gwrjqC8yiUCiU2
ohEyuPQEe0aOfIygrW/
DMb4MU3LtSLgOAb9+vpg04bhMBYL9WZj7O6TmjX+rQKNPn4HFr7V29eOel6qgeBvNgAq3tuS7Fw8+/
cgGn6goreRDjxPyMG7C46iuFg/
b9yyCpHvv9cRLZpRzwuFQnmzyc0pRkGBRKtzCAFGjd+J4UMbYfuWMUhKzgMvI2jSyAG2esgqepXCpFR5lpG
a8h26ILKzRuPP5qDhh9P0Prc6qHipAjKeR/qtQJRk58Hcx0Op8kw6d0PtXEFL1yD46/UQmJrAc/xA+M5/
C6Yeuu8hSiQ85s4/gqQkDXL1VWBkxEImkwd8OTmaYcb0NhgxTL/
7sRQKhVIXMTExqlCTRRNkMoIjx0Jx6UoU/
v17lEGrlZu4OKhMj9YKhkHjT2bCqX8XcGIRbNs1AyvUn5dIG+i2kY5Ebt6Hwx49cbbrJFwePBvH/
AbgbLdJyAp+WmGsJm8caW4+StKzUBCbgCc/b8HxJoORditQZ/
suXHqG589zqhxAVlIiAyEEMp4gKTkPK7+9hF/
W3sBrlmFPoVAoankanoZde4Kwc3cQwp6mQSwWoHu3eho3SXwZnifIySnCd/+7YgBLX+AxfhBYoQo/
BcuCM9awxQ4hyAoOh1PvTrDv3LrGhAtAPS868eTXLbj/
4aoKx9NuBuJM5wnof3M3RHbW4IyEKNYhloXwPKSFRbg8bC5GxF0BJzLSeo4rV6N1uiOojDIBVPb/
rdsD4exkpoh7yc4uQmZWIaytjGFpKa7yehQKhVKbSE3Lx2dfnsX9BwmK1iuEyDtLz5zeBteuR+s0L88T3Lo
dh+cJOQZruSKysULzrz9A4Kc/
VniM4ViwRkLUmzICkZv3ARrcaKdcuYNdoqbgjMXwGDcQDT+aBsuG3oYwXSVUvGhJSWZ2pW8CoFR05BXgVJt
RkBVXMcOHl6E4NROx+07p1KSxqFiqs3dEE9Gzect9tGrpjD/
+vIMr16JBiLyTevdu9fDe3A7w8bbVaW0KhUKpTRQWSjBr7iE8T5DfiL78tRockoz//
XgVnTp64Oq1GJ3XiIrKNGi/uEaLZ0JgaoKg5WtRkp6lOG7Z1BcdNn2NtJuBKls
HvIw0Nx+AvBrvs3/2I2rrIfQ6sQmOvToawHLlUPGiJTG7T0CmKvCJkKoLl1IYoQBp1+9rLF4IIbgfmIiDhx
4jJCRFWfdz5esxQD1PKzT0s8epM+Eqz09LL8DUGQfAS2WKcYQA167HIOB2PP76Y4TOPUEoFAqltnDsRBhi4
yqmNQNyz8nz5zlISKhatqhYbNhLMcMw8H1vMrxnjUXyhQBIsnNg4eel6K9n4uaE+x+tUpVXUilEyoPICK6O
XoARz69CYFx9nnca86IlBXFJYDTsKqoPGE6ztXhehuUrL2DW3EM4fTYcKan5Wq9FCBAdk4WTp1ULlzIkEhn
4V9Q6zxOUlPD4+rtLWq9PoVAotY1jJ8Kgrt9gVUIATU0EyMwsRODDRL1s8yvj+fFLuOg/
A5cGz8L1CR8hYOaXiN5xFIQQGDs7yDOGdOmrKJOhJDMHsXtO6ttklVDxoiUie2uD58yXQSRSOPXtpNHY/
7YF4tiJMACoUpCuNh9CZdtSMhlB2NM0hD5J1dkOCoVCqQ1kZhVWSZyoI79Aik+/OIN3Zh/
E0JHbcP5ipN7XePz9n7g8ZA5Sr95VbA9lPHiMG5M/
xt0FX4MQgpbfL0bjT2eDNSoNwi0VMoxAvVeIEQqQfjtI73argooXLfEcP6h62n4zDARmJsgJj0FRWobKoRI
pj207Ag1vUymaPv3Y2CyD2kGhUCiGxt3VEixbDd/
5ABKTcrF4yWmcPhuutzkzHz5B4JKfAKB8kdTSpsHh67Yj4cRlMCyLlqsWYWTCVXTY/B1a//
QZuh9ejxFxlzRaRyF6qgkqXrTE2NkBjRbPNPxChIAvLEbgpz/
gkGt3PNtyQOnQyMgMZGYVqZyOZRkIBGyVP4QMA9jaGms01tRU+ywpCoVCqU2MHN7YoNs5lfHDT9cg0bE2Cy
EECaev4tLQOTjg1Blnu05UecfJcByCv16PK6PnY69NOxz19UfC8UuwadcUbsP6wMjKAiZuqouSEokULoN66
GSvrtCAXR1o8e2H4MQiPP7fn+CLig22Ttn2lKxEglvvfA5jFwc49+9aYZwmHyxCCHieVNn9SQiQllaodpyZ
qRHatXWt2mIUCoVSw/
TqWR+dO7rjZkCcQbePXiYjsxC3b8ejS2dPrc4jhOD+ov8h7Jct8qq6GgggwvNID3hYbnz84fOI238GLVcvR
vzBsyiIT1J6PiPgYOHnBac+moU46AvqedEBhmXRbPl8jEq+gc47f0a7P1ag/
aav5W4zA7kXGZaRtxmohPr1rGGsJlqdkKoFlWnLzHfaQCSi2phCodRtOI7Fzz8MwpTJLWFs/
GJrRCwW6LWB4qvoknQRt++Uonu0tlV1Xx5f9u/
AT35AWoDqWBYTTxf0PPEnGLZ65QS9ulQBoYUZ6k0YrPjdxN0Z18Z+IM+DF3AAL9ObYiC8DKlX76IkMxtG1u
VLSRsbCzFyRGPs2vOoUi8MxzIVsoIMBcsymDG9DaZMblkt61EoFIqhMTLisHBBZ8yZ2Q5hT9NACODna4ez5
yNw+OgTg6ypS5+jJ79sAcOyIDKZ+sGaomau9htWVKmVja5Qz4secfHvhlGJ1+Azd4K8Ku5LwsWmXVN4TR+t
ebSrEqSFlce2vDevA5o1dQRQfgmWZWBuIYKLi3lVl9aIb1b0wbzZ7asnqJlCoVCqgYyMAmzZ+gDffX8Zx0+
GoaBQArFYgJSUfAg4w1xGO3Vw12o8kcmQFvBQv8JFDQzHIfN+SLWt9zLU86JnHnz6AyL+2FXheMbdEGQ/
joTA3Ax8fkHFdGuGUeulEVpZQGxvU+ljxmIhNq4bjiPHnmD/wRDEP8+GubkIQwc1xNgxTXHufAR+
+Pmazs9LU2jLIwqF8jpx7MQTrPz2EmQ8ARj5F9z+g4/
RwMcGgwb4gTeAWLC2EkMo1LKeGMNAnt+swZcwywJEptFQVRBCNEqlNgRUvOiR2P2nEL5uR+UPEgK+oAi2HZ
qjKDEV+TEJYIQCgABEKoW5jycK4hLBF5dUqgAYjkWDuRNUNsIyMuIwZlQTjBnVpMJjI4c3xumzEXgUnFxua
6lMMzVuZI/
HoVWvy2LIEtcUCoVSndy+G49lKy68OPDSV3N4RAa273oIlgW0Kf2libyY8lYrbcyUz8swcOzVHimX7qisRW
bTpgkKk9JQ+DxZ6zUqIJPBqV/nqs+jA3TbSE8QQnB/
YcVmja8MQvqth+h9aSt6HP0DDT+chkYfv4NeZzZjyJOT6PTf9wDDVKiqy3AsrJr5ocnnc3S2TyQSYP1vQ/
H2Wy1h9lIKs4uzOb78rCesrTRLf1YGwwCenlaKrSsKhUKp6/z9zz2V2+1paQVab5Ev+7IX/
Pv5VDovy8gTMMaMrHgDqgmNFr2jXLiwLITWFpDxvF6EC8NxcOzdEdbNDRe0rHJ9omv3vlpKTk4OLC0tkZ2d
DQuL6vMC5IQ9w7GGAzUa2/
fKdjh0a1vu3Ogdx1CclgnC88gJi0LK5TsAITCytUKDeRPR+NNZEJqZ6sXW4mIpnifkQCjk4OpiAZZlsHjJK
Vy8/ExdbFalsCwDlmGw/
rehsLQUIzgkGSzLoH07Nzg7mevFZgqFQqlOCosk6NJjk97mY1kGrVu5YN3aIWDAYONfd7BzdxAKCiQAAI5j
0K+PDz75uBusLHXvEfR49SYEfvpj+VRploXQ3ASmXu7IehCqj6cDc7/66Hd1h9JQBl3Q5vpNt430RElWrsZ
jRbZWAACZRILbc5fj2eb9cm8Ly8gzlBig2bL30OC9yTCysQSrYX8jjdcXCeBVv/wbrkf3+jh/
8ZlO8zVt7IC3JrfE+o0BCHz4oh4AwwB9+3hj6We9YGZGC9ZRKJS6Q5mo0AcmJkKMGdUE82a3h7C0N957czv
gnWmtERKSAqlUBt8GtrCx0T7D6FUafzILzv274un6HUi/HQROLILbiL4w83bH9XELqzw/
AIBlYN+ptV6Fi7ZQz4ueKExOw0HnrmojVk3cnTA85hIYhsHd97/
B09+3KT2n3R8r0GDOBEOYW4HiYilGj9+J5JQ8lb2ROI6Bs7M51v48GJmZRbCzM4G5uQgT39qNtPSCCueyLI
PmTR3x54YREAjoLiWFQqn95OYWY96CI1WKA2QYoH07N7z/XifUq2cFY3H1ls9/
lZvTliBq22H5DbIeEJgaY1xeoF7mKkOb6ze9mugJY0c7uA3rrTYVus2aL5F2KxBXRs3H09+2qhQ7wSvXQVZ
NTSDTMwrRtq2rUnPKnpaDvRnWrx2Kep7WaNXSGe5ulti7LxipaRWFCyCv/
hsYlIRr12MMaD2FQqHoj2UrzuNJWFqV5iAEuHP3eWkR0ZoVLgBQnJ6pN+ECANL8QqXNeasDum2kR1r9tATJ
V+5CkpVTqSjx+3AacsOjcXXUfHmqmhoKE1KQcTcYdh1aGMJcBY9DUzDnvcMoKpJWKHJnZmYEP187WJiL0Kt
nffTt7QPxK9V8Dx8NVdmigGUZHD3xBD171DeI/
RQKhaIvYuOycflqtF7mkskI8vNLKnxn1gRm9dw0bhmgCaZe7jVaz4t6XvSIubcHBtzZB/fR/
cu1CRA52qLBu5Ng7GiLwE9/lB/
UMDK2IC7REKYq4HkZFn16CoWF0ko9J3l5JXCwN8VPqwdiyKCGlX4Is7JVN4WUyQjS0gr0ZjOFQqEYitt34v
Q2l1gsgIWlSOUYQgjuPUjAvgPBOHYiTO33qa54zxijN+EChoHvvIn6mUtHal4OvmaYe3ug2961KExNx+Nv/
0DEpj0oTk5H+Hol9V/UcG/
hd7Dv0R4JR84j69FTcCbGcBvRF7btmulF9V67EYvk5DyVY06eDsflK9Fwc7PAqBFNMGxIeRHjYG+KmNgspV
tOHMfAxZlmHVEolNqPlCea1AxVC8syGDakoSJAtzKCQ5Lx5VfnEBubrTgmELAYP6YpPljQWW2coEwiQdyBs
4jcvA8FcYkwdnWE17RR8Bg7AJyRPEkiPy4Rz7YcQH5UPKxaNETWw6q3MzD38USD9yZXeZ6qQMWLgYjavB9h
a/
6r8jyFz5Nx0EHerZMVCkAIweNVG+HQsz267f8NIhurKs0fEpIMjmNUBukCQEGhBOER6fjfD1dw5FgoNq4bD
tPSejGjRjTGL2tvKD2X5wlGDGtUJTspFAqlOmjWxKHKwoVhADtbE8x8p63SMZHPMjBr3mFIJOW9IVKpDDt2
ByG/QIJlX/
RSer4kLx+XBs5C6rV7AMcCvAy5YdFIPncTT9duRa8zmxG+bjseLv1VfqPLMIoYFdZICFmJ7tlUTZfOg8BY9
3RufUC3jQxASXYugr76Te/
zyiRShdsv9eo9XB42r8oBU5yA1fiDWjbuSVgafl5zXXF81IgmSuu5MAzQs0d9tG/
nViU7KRQKpTpo3MgBDf3swHG6e7Z7dK+H/zaPhp2K5oob/7oDqZSvNF6QEODQkVBERWcqPf/
e+98g7eYD+S+lgbhlfY0y7gXjQv/pePjFL4CMgPAy+bWjdJxMIoXYya5ceIPGMAwce3XU/jw9Q8WLAYg/
dA6yohKDrkF4HmnX7yPlyp0qzdOpg7vKYNvKkMkIjp0IQ06OfG/
29p14JCRWXueG4xjMnN6aNmqkUCh1AoZh8L9v/
WFlKQary8UdgI+XLRwczJQ+XlgowYWLz9SWpTh56mmljxWlZiBq6xEQJdlDhJch4/
Yj5QYSgqKkNEDL736G4+A+qj9M3Jy0Os8QUPFiABLPGL4BIgAwAgFi956q0hzNmjrC3U37ejgSiQxhT9Mhk
fL4etUlKPuIy2TAL2tvVslGCoVCqU483C2xe/
t4zJjeBo6OZjAWC+DubgkTY81SnvfuD4ZERXBsXl6J2ptGhmGQmVVY6WNpN+6DSKUa2aJ8AYAzFmuU+QqGA
RjAsrE32v+5smrr6gkqXvRMcUYWYvecrKbVCKR5VcviYRgGq/83QKdz//
7nLi5djkJmZqHSRmMyGcG9+wmIf56tZASFQqHUPmxsTDBvdnucPPI2rl+ejcP7JmPHf2NhY62+D1x2TjFSU
5V/N1tYiNR2jZbJCBwdK/fe6KO8CsNx8Jo+EgJT43IChikNMHYZ3AM2bZpA7GwPm9aN0W79V+h/
a0+V4yz1BQ3Y1TNR/x5S2dFTnxAZgWUjryrP8/
x5jk7n3b77HI+fpGgUmf88IRdurpY6rUOhUCi1AQ8PKwwb2hBbtwWCV+M5CQpOUpplKRIJMHigL44ef6Jy6
2jooMqbHtp1aC4XHLo0oyuFSHm4DOqJpkvfQ8SfuxF/6Bz4wmLYtGsG33cnwa5jS53nrg6o50XPZAU/
rdAV2nAQCK0twRdXLb6mKj088vIkGt0FWFqornVAoVAodYFuXeqpFS4A8PmXZ7HvQIjSx2fPbAsLC7HSwOC
yLavKMHZ2gMe4Abpfa1gWxq6OcB7QDcZO9mi2bD4G3j+EIaEn0fm/1bVeuABUvOgdgYkxoDQCRDmdt/
0I9/GD5L9oHNzK4M6cZTjo0g3xh89pvWYZXvWtdT5XHQzk+8d+vnYGW4NCoVCqi5YtnNC4kb1GoSL/+
+GK0jpaTo7m+PfvUWjf1q3cFcPaSoxPFnXF3FntVM7dfv1XsGzaQP4lq0VCBCPgwBoJ0GXHT3pv+lud0MaM
eibp/E1c6DtN6/MGh56AhW99RG7ej7Bf/
0V2SDjAMnDs1QEiW2sknr4KSbaSYnKlOfx9zm+BY88OWq9NCMHEKXsQEZmhdeaRJvywyh99envrfV4KhUKp
TgLuxOOff+/
j9p14jcazLIOZ77TB3FntVY5LSMhBVEwWjMUCNGvmqLKw3ctIC4sQvfUwwjftQVZgqPoKuiwLjzH+8PtwGv
Kjn6MoOQ0mro5wHdILnLjmvePaXL+peNEzhBCc7jAWmQ8ea1yKmeFYjE4LgJHVC3tlEgnAsgplnPPkGY41G
qh8EpaFfZfW6Hdlu052hz1Nw4zZB1FcUnmbAF0wNRXik0Xd0KuHF2QyGczNRTRlmkKh1EkOHQnFym8vgmUZ
jW/yGAbo3dMLP+iYFKEp+THPcbheb9W2cCyafPkuRHbWePjZT/JkDwYAAViREZqvWIDGn84GIL/
+FKdnQWhuCoGp8lo1+kab6zcN2NUzDMOg5/E/cWnwbGTceaSofKh0PMfBbVS/
csIFAFhh+ZS8+MPnwHCs0rx+yGRIvXoXhYkpMHZ20NpuP187bN0yBn/+fQfnzkdWWcCIxRzat3XDT79ex/
KVFwAAbq4WeGtSS4wZ1UTn+gkUCoVS3aSm5ePb/10CAK280yzDQCQy/
GVWWqBBPySWRdqth0g6ffXFsdKnIisuQeCSn5B64wFM67ni2eb9cnHDMnAd0gvNlr0HmzZNDWO8jtCYFwMg
treBf8Be9D63Bb7zJsGmXeUvOsNxEJgZo8U3C9XOWZKZA0aDTdaSrMqLxWlC/
XrWWPV1f1w5PxMnj7yNRg0129etjKIiHhcvRyEnp1hxLP55Dv73wxUsW3HeINtTFAqFYggOHw3VKT2ZlxH0
6lFf/wa9gqmni7xmiwqIRIrUa3dVjnl+5AKe/
rbtRQkOGUHC8cs43Wk8ks4pbwFTE1DxYiAYhoFTn05o+9tSDLi9H+3//Fpejvkl7Lu2Qf+be2Dhq/
7NbeblDpmabShGIICxi/
Zel1cxNhbC0dEMq1f5w87WtMrzvcqJU09x4eIzvc9LoVAohiAiIkPrcziOgYeHJfLySzDnvcMYM2En3v/
oOC5efgZehTdeFwQmxvB6Z7Ty7COWgcDMBHx+5UXvyvGKSiM8D8LzuD75Y3k4Qy2BbhsZGL64BHEHziAnLA
r1p46EqYczTOu5wcK3Hsx9PDWaI+PBY0gLi8AIOBBJ5VUVGQEHz/
EDYWSpv+7Nri4W2LV9PPYdCMaff92FVKqfDxzDALv3PULfPjSIl0Kh1H4IIVr3kXN1sYCAY7Him4tgGQYyQ
hAdk4Vr12PQqYM7fv5hoF63lFp8/
QGSL9xC7tOocuEFDMeBAHAe0A1x+07rNrmMoDglHc+PXYL7yH76MbiKUPFiQJIv38a1Me+jOC0TjFAAEAIi
5WHbvjm6H9lQ6TmZgaF4suZfJJ66BplUCshkKMlQXZ2W4TgY2VihxXcf6f05WFmKMXN6W9jamODr7y7pZU5
CgIhI7e9kKBQKpbo5fDQU5y5EarVt1LaNK8QiDjcD4gAAstKTy7bLA27HY+3vN7F4UTe92WlkbYn+N3bh8f
ebEL5xFySZOQDLwmVIT3AioypXfmcEAmSHhNca8UK3jQxEdmgkLg2YieJS4UFe6gidcT8EF/
pNl4uTl3i08necbDUCUVsOoigpFSVpmRoIFxZuI/
tiwO29MPVwMcyTATB8aCMMHewHAHoJthWLqW6mUCi1C0IInkVlIPBhIpKT83Dv/nOs/
OaiVsJFwLGYN7s9rt2IVZr4ICMEBw4/Rl6efhv4GllZoOWqRfC/sx9d9q5B77P/
wHVoL720rCEyWbVmHqmDXkEMROiPmxWek1chUh7Zj57i+dGLChUbvmkPHi3/Tas1Wv/
6OepNGgqxvY1ebFYFyzL4amlvdO9aD1t3PETY01SAyAPSdNlO6tDezQBWUigUim5cuRaN39ffUniFGQCWVm
JFOrEmiMUCbFw3TCPPcnExj5DHyejQ3l13o18hNyIGd95dgaSz1xXHGI7T6jkohRC4De9TxUn0B/
W8GIjYPSdU1nlhOE7REVpaUIh787Xv1Bmz81i1CJcyZDKCoEdJCA5JRkkJr7NwAYB+tGgdhUKpJZw+E44PF
51A5LMXooMAyMoq0tjr0rWzB65dnIlmTZ00PkefVdbyouNxpuM4JF+8VX4Nnq+6cGFZeE4cDDMv/
QmtqkI9LwaAEAJpgeqobsLzkOTKK+bG7j0FWYn2UdzpAUHIjYyFubeHTnZqy7o/
ArB1x0PF77oKF5YF7t5PgLW1MRo3qnp2FIVCobxKXHw2duwKwolTYSgokEAkEsDbywazZ7RFp44eiu3v4mI
pvv3+MqBBg1lV3LgVh7S0Ajg4mKFlcye14xkGsHfQXzbnoxW/
oyQ7V+PiqNrgNrwPOvz1rd7nrQrU82IAGIaRCwoV1WQZAQcLP3lH6KygMF0XQsTGXbqdqyWZWYXY9pJwqQq
EANt2BOKtafswd/
5h5OYWqz+JQqFQNORBYCLGT96N3XsfITe3BDxPUFAgwaPgZCz48DgWLDyKyGfpuHQ5Cn/
+fRd5eSVV9oLIZARfLJP3mPPyskHbNq5Kmy4C8u/B+e8fRWpavuKYtLAIUduP4NGK3/Fkzb8oeJ6s0drS/
ALE7DhmEOEicrBF9wO/
Q6Cmjkx1Q8WLgWjw7iSVjxMpj+L0LKTdCgQrNtKqsdaLSQjSbgbqZqCWXL4SpbdUaUKgCGS7ey8BCz8+oXU
aIoVCoVRGcbEUHy0+geKiystKAMDNgHiMnbgbH31yEv/
8e19va997kICEhBwAwLcr+sLJUXXpirT0AqzbEAAAiNl9Agedu+DmW4sR/
O0G3P9oFQ559MSd91ZUSO54leK0TJ2895rACmvnBg0VLwaiwbxJsO/
aRnlVXJZF9LbDONNpPJLO3tDZX8kaCSscy7gXjLDftyF8ww7kPI3Sad6X4XkZjh3X0TukBpmM4EFgIq7fiD
XI/BQK5c3i7PlIZOcUVznMQ1ceh6YCAOztTfH2lJYqx/I8wcnTT/Hs4AVcn/gRJDlyLwyRSAEZAWQyhG/
YiXsfqN6yMbK2hNbl0FkGjIBTu0Pg2Ev7Zr/VQe2UVK8BnMgIvU7/jZDv/
kD4uh0oyXwl5VkmAyl1ZGTefwwjG0t5af9KspNU4TK4p+LfeVFxuD7hI6TfDnrxhiQEzgO7o/
PW1RDZWuv0XNb9EYD7gYk6naspCz8+galvtcS7czuA46implAouhEckqxV80R1MAxgZ2uC9IxCjebkBC/
EQHJyHgQCVqXXWiKRIWjZr/KMoMrmJwThf+xCk8/
mwMRNHksjzS9A1LYjiN52BMXpWTBv4Anb9s2QcSdYHqCrDpYBZAREpnoskfLwXTBF/
Xw1AL1KGBCBsRgtvl6IkUnXYNnMV6nCJTyPkoxsWDVrID+gxRaSxxh/
AEBxeibOdpuMjPshpZMShTcn6cx1XOg3HXyJ9jUFsrKL9BbrogqZjGDL1gf49n+XDb4WhUJ5fdHnzQ9TmmL
85Wc98fuvg9WOFwhYtGr5ot6WqYmRWsFjUZyDguCwyoXLS8Tuk2enFsQn4USL4bgzbzlSr99HTmgkEo5fRv
qth/Ltd008MGrWYgTyNgNtflsKu/bN1c9XA1DxUg2UpGch+9FTlVtDjICD27A+6HPhX/jMGa/
x3HyhvJto+B+7UJiYWmnAFuF5ZD4IRdyBs1rbvmPnQ41iXcoi93UJ3SmDEHnb+ZfTFSkUCkUbOnVwr7LXpe
z7zMRYiO++6YduXeuhYwcP9O+rvMQDwzAYMawRrCxfBLb26eWl0haGARq7G6u1h+FYlGTlghCCq6MXID/
muTz9ufSaovC2yGQwsjTT4BkqR+xsj3qThsL/
zj74zX+rSnMZEipeqgGpJs2wGAZ8YREce3VE+w0rIHa212huoYX8jfpsy0HVW04si6j/
Dmk0ZxnbdgTir3/uaTT2i897YPV3/ujY3h2eHlbwqq/
bFhXLAkePP9HpXAqFQunUUf4dpCsM82LLKb9Agu07HypuqJYv7a0osFnm4CjLKOrUwQ2LFnYpN5eHhxUGDv
BVWpWcEGDCu73BqPEWEYkU5t7uSL/
zCOm3g1RmFckIgdDKQv0TrQSGY9Fg3kR0+vd72LZtptMc1QUVL9WAsasjBKaq1TWRSGHR2Efxu9/76vcZbd
o0gbGzvE5KcXqm6sEyGYpTNPdo3HuQgJ/XaN4CvWM7d/
Tt4411a4fi4N5JaN7MSWWaoAozcflKFB6Hpmh9LoVCoXAci99+HQwHe91qqLya+fg4NBXTZx1AXHw2jMVCr
FszFGt/How+vbzRvJkjevfyxm+/DsHaX4ZU2mhx2ec94d9P/t3OsgwEAhYMA4
hFAqxc3gfdBzaD28h+iq2ayhCYm8J9tD9SLt5SK3SkWbmKGmJawzAoSk7X7dxqhgbsVgMCYzG8Z47F09+3V
x5MxcjblXuOH6Q41PiTWYj4Y7fcPaiE5t9+qPi3qacrsrJylW9NMQxMvTQvyb9zVxA4jlHam6MMjmPQrq0b
nJ3KpwRKJLzOdRNiYrPx1rR96N/
XB19/1QdCofxDTYi8wm9qagFsbU3QormTXvosUSiU1ws3V0sc3DcJy1dcwLkLkVWaSyYjKCyU4K/
Nd7FiWR+wLIOuXTzRtYunRueLRAJ8u7IfZs1oi3PnI5GXXwIPdyv49/
OBqakRAKDV6sVIuRgg3xp6+RrBMgAB2v+xAtL8QmTcfwyiyZYYr1tZCyLlFUHBtR3qeakmmn21ABZ+9SuoZ
objwLAMOm9dDYGJ3DtDCEHWo6do/etnsGzuV2EuViRC5+0/wsX/
RUdSn1ljVadbEwJjJzuN7b17/7la4QLI94QXf9S1wvFGDe2rXLvl7PkI/
PSrvEfHtesxGDZ6O6bPOohPPj+NGXMOYujIbbhw6VmV1qBQKK8nxmIhXF0tIBBU/
TLH8wSnzoSjuFh1vRVV1PO0xsx32mLhgs4YNaKxQrgAgFl9d/jf2Qe3EX3KXSOsWzRCt4O/
I+1mIA66dJM3WDRwTaz6bw0z6Pz6gnpeqgkjKwv0u74TIas2IuLP3ZBk5QIMA6f+XdD0y3mw79waAJB49jr
uf7gK2SHhinPNfevBrktriO1tYOFbDx7jB0FoVt4lauykPkbm+bFLaLPmSzAaRNVq4s+wtBTh379Gw6OS/
eUhg/zw+/oAFJdIdf6sEQLsP/gYLVs4KSpXvkxSUi4Wf3oKq1f5ow/
tlUShUF7BylKst5RpiUSG3LySSreG9IFZfXd02/
cbitIyUBCbCCMrC5h5ueP6pEWI2XXc4KIFAMAy1PNCqYiRlQVafb8Yo1NvYVTyDYzLvY9eJzYphMvTddtx0
X9GOeECyDuFRv93CE59O8N7xtgKwgUAUq/
fB1TsmQJAflQ8ChM0iyVp385NZcwKyzIYP7ZZpcIFACwsxFj1TT+wLFulrR2el+GHn+Xel1c/u6T0Z/
VPV8Hr6CalUCivL/
37+eiterdQyMLczEj9wCoitrOBTesmMPNyR8aDx4jZeUwvwkVgZqJ6AMPAtpamRVcGFS81ACsQQOxgC4Gp/
M1UlJaBs72m4O78lZW/SWUEREZw592vlH4QCSEaeVQ0/RBMmtBc6bYRw8jrGYwe0UTlHD2618e2LWPQr0/
VvCKZmYUqzU5NK8Dd+wlVWoNCobweSKUynL8YiSVfnME3qy7ByEj1TZ0mcByDAf0bGMzroozobUdUBvJqgz
SvQPUAQtBw4TS9rFUdUPFSw8gkElzs/
w5Sr9xVPZAQ5EXEIu1WYKUPO3RtIy8prQITd2cYu2jWxblFc2csWdwdDINyHhh5tDyHH/
83APYaRPP7+dphxbI+6Nhe82BhXUhN1TG6nkKhvDZkZBRg4pQ9WLzkNM6ci8DNW3EoLq5as0KWZWAsFmLmO
231ZKXmFKWko7r6HJj71YfHuIHVs5geoDEvNUz8kQvIfBCq8fiC2ESgU6sKx12H9YaJm5O8UF2lGU1Aww+n
Ke+1VAnjxjRFyxZO2Ls/
GPfuJ0AgYNGlsyfGjmoCFxfN6gg8Dk3B+x8eR0amBrVuXjWZAdxcLRAXn6N2rK2NGpcohUJ5rSGEYMGHx3Q
ucskwlTumnZzMsOanwXB3s6yihZpDCEHs3pNIunBLfbl/
jtU5u6jcmlJeM+99LYGKlxomZvcJMBwLouGbT2RfvvhbQUIynvy8BXEHz6AwNQNEJiv3KWQ4DoTn4TlhCHw
1qB3zKr4N7PDFkp5qxxUWSnDqTDgeBSeD4xh06uiBxo3sMfe9Iygo1K3bKcex+PH7gVi46ASSknKV3oDY2B
ijXVvDenYoFErtJuhREkKfpOl8vrKt6YSEXEQ+y4C3l43Oc2tnB8H9D1chbM2/
akuWMxwH71lj8fzIBY3jGZVRW7tHK6NuWfsaUpKepbFwETvbw6F7OwBAUWoG7i38DjE7j1Z0KzLySolGtta
wbtEQDd6dBLdhvbXyumjD7bvxWPTJKeTnl4DjGDBgsP/gY5ibGyG/
oESnWDOGAcaMaoIGPrZY9GEXLP70lNKxixZ20Us6JIVCqbvs3P1Ip/PKvhZVFSj/
ff0t9OvjXS2eicTTV+XCBVDbUkZkb4Nmy95D29+X4VjjQch7Gl3JQAYiWyuUZOYo9eIwHAfXIT2rbnw1Qr/
xaxjzBp4aB2S1Wr0YrECA4owsnOk0vnLhAsiPMQxM3Z3R+8xmuI/oazDhEh2Tifc/
PI6CAnnTR54nkJaKsdxc3YQLUFo2e6y8PHXvnl5Yvcof9nblt4ZsbIzx7cq+GOjvq/
sToFAorwWxcVk6nScSCVQKFwCIf56DsKe6e3W04elvW8Fw6q8JTv26wP/
WHhg7O4DlOAwNPYmmy+eXyypiRUbwmT0Ovc9tkdePqUx8MQwYAYcG8ybp82kYHOp5qWF8Zo1DxMbdasdxps
aI+u8wjKwsEPH3XuRFxqocT6Q8Mu4FI/3uI4P2qNi5Owg8L9N7CYL69a2x+d/78G1giyGD/
NCntzd69qiPu/cTkJqaB1sbE7Rr60Y9LhQKBQBgaSFWP6gSCgs1KzyXm1ui0/zakn4nWG2ci0UTH/
Q6sancMYZl0fyrBWj65TxkBYVBViKBRSNvGFnKq593O7gOV0cvgKxE8sLNxLJgjYTotv83mHm5G+T5GAoqX
moYmzZN4btgCp7+tlXlOD6/
EMkXbiHp7HXNJ2cYpAcEGVS8nDsfqVElXk0pC9eJiclEbGwWjh4nWLvuFr75qi/
69vFGh3Y0toVCoQAJCTl48DARhACtWjqjT29vBNyJN9h6ri7m6gfpAdZIqHZMmSCp9HyBADatK5axcB3UA8
OjziNi0x4kXwwAADj2bA+fWeMUPfLqElS81ALarPkC5j4eeLz6LxQ+T1Y6Tm3UeSXoq0aAMoqqUC4bAH7/
dTDMzESIiMzAn3/
dQVp6PggpuzGQi6KSEh5LvjyDfxxHoVlTx6obTaFQ6izZ2UX46psLuHIlWrFrzgDo0tkDYrEARUVV+06qDH
c3C40zLKu81sh+CP9jp/
LO0SwDt+F9dJrb2MkezZa+h2ZL36uChbUD6nOvBTAMA7/338bwmIsYFHwMfh+8LW/
IpQec+nbWyzzK8PG21bqCbtm268TxzdCpoweaN3OCjbUxUlLzle49y2QEn35+Gnl51eO6pVAotY/
iYinmvHcY167FlAv3IwCu34ytUu8hVQwZ1NAg81aG7/
tT5DEvSuJTOGMxPCcOrjZ7aisGFS8ZGRmYPHkyLCwsYGVlhRkzZiAvT3UxsZ49e4JhmHI/
c+fONaSZtQaW42DVpAHyYxKqXpiIZeE2rDfMvT30Ypsyxo1pqnXvkPr1rPHV0t74+MOuiuj9i5ejoC6mOCk
5D3PeO4Sr16Jx6Egorl6LhkRStQJUFAql7nDydDiehqeDr+Q7hxDDtP/hOAZjxzTV/
8RKsGhQD90PrwdnLKooYAgBn1+I402HIvSnzXprfVAXMei20eTJk5GYmIizZ89CIpFg+vTpmD17Nnbs2KHy
vFmzZmHlypWK301M3qwCZJpEmquDExvBoWd7yCQSsEL1e6i6MqB/
A1y+Go1z5zVrO79uzRB07OBeLuUwOCQZNwNi1Ub8A0DokzR8sOiE4ndLSzEWLuiE4UMbaW07hUKpWxw5Fqq
0mJy2sCwDmYxg+NCGOHz0idJxb09uCStL3YKBdcXFvxtGxF3Go5Xr5PGQr4g1aU4eHnz8PfiiYjT9Yl612l
ZbMJh4CQ0NxalTp3Dnzh20bSsvq/
zbb79h0KBB+PHHH+Hi4qL0XBMTEzg51Y3OlobAqW8nxB04XaU5+IIi3P9wFRKOX0aPYxvBiYzAFxUjZvcJJ
J65BiLlYdu+Obymj4LIxkrndTiOxaqv+4HnZbh4KUrteGNjYTnhcuNWLD746ARkmiiXSsjOLsKKby4CABUw
FMprTlpagd68Ky1bOGHalNbo2sUTLVs4Y/
VPV1FYKIVAwILnZWBZBm9Naon35nXUz4IqKEpJR15UPISWZrDw8wIAZAWFIW7faZVKLWjpGjj16QS7ji0Nb
mNtgyEG8jtt3rwZixYtQmZmpuKYVCqFWCzG3r17MXLkyErP69mzJ0JCQkAIgZOTE4YOHYqlS5cq9b4UFxej
uLhY8XtOTg7c3d2RnZ0NC4vqCbDSN5LcPByu3weSrByNC9gphWHQdNl78Bjjjwv930FRYqq86i6R92TmREb
oumcNXIf0qtIyj4KTMXXGfpVjRCIO505Oh6mpvDNrSQmPAUP+RXZOUZW/
kCwtxThzfCqEQsMGKFMolJpj1rxDeBCYqPVW9au0bOGEzX+OKnesoECC8xcjkZCYC0tLMfr29oadrWG9/
nlRcbi/
6HvEHz6vSF8296sPMAxynzzTaA5OLMKABwdh2bBqDXBrAzk5ObC0tNTo+m2wmJekpCQ4OJRPvxIIBLCxsUF
SUpLS8yZNmoRt27bh4sWL+Oyzz7B161a89dZbSsevWrUKlpaWih9397qVq14ZQnMz9Dr1FwQWZuUCdxmBPI
jLY+wACC3NNJuMEDz+35840WwoihJT5Yd4Xv5BkRHwRSW4Mmo+soKfVsnmpk0c0NDPrlwTx5dhWQYjhjVWC
BcAuHQlClnZVRcugNwDczMgruoTUSiUWsuIYY2qLFwAwMJcVOGYiYkQQwc3xJyZ7TBhbDPDC5foeJxuLy/
t//KeeW5YlMbCBQD44hLcX/idIUys1WgtXpYsWVIhoPbVnydPlO8fqmP27Nnw9/
dHs2bNMHnyZPz33384ePAgIiMrj6n47LPPkJ2drfiJi3s9LmC2bZthWPgZtFr9CRy6t4Nt+
+ZoMHciBgcfQ9c9azAy8TrabfhKo7lkxSoydEqj3MJ+/a9K9jIMg9Wr/
GFjbVwu+6hsh6hZE0e8/1559+uzqAy9FpnLyFDT8p1CodRp+vf1QeNG9lWex7wS8VLdBC75CSVZykv2awwh
SDxzHflxifoxrI6gdczLokWLMG3aNJVjvLy84OTkhJSU8o2ipFIpMjIytIpn6dChAwAgIiIC3t4V3WIikQg
iUc2/
EQ2ByNYajRa9g0aL3qnwmMBYrLfQeiLlEbXtMBrMmwCbNrpH1bu5WmL3jgnYfzAER489QXZ2EVxcLDBmVBM
MHugHI6PyWzrGYqFe7qLKcHDQ0BtFoVDqJEIhh/Vrh6Fnv791noNhUG1NFpVRkpmNuP2nlddy0RZCkB/
9HKbuzvqZrw6gtXixt7eHvb165dupUydkZWXh3r17aNOmDQDgwoULkMlkCkGiCYGBgQAAZ+c350XRFGlRsf
pBGiIrLsGptqPhu2AK2qz5QucGZFaWYsyY1gYzprVRO7Znj/pY8/
tNndZ5FVtbE7SnnaUplDeAqt3wcCyLYUOqr25LZRTEJ+lPuJRiZFU9FYBrCwaLeWnUqBEGDBiAWbNm4fbt2
7h+/Trmz5+PCRMmKDKNnj9/
joYNG+L27dsAgMjISHz99de4d+8eoqOjceTIEbz99tvo3r07mjdvbihT6ywFccpjh3Tl6W9b8fT3bXqftzI
8PaxKO7WqHysy4sCqGNilkwftc0ShvOZkZBRg/gfHdDq3bDt7ySfdYWNT/eU3+OISZAU/
RXZoJATmpnqd29y3HiybvlkNag1a52X79u2YP38+
+vTpA5ZlMXr0aKxdu1bxuEQiQVhYGAoK5LEKRkZGOHfuHH799Vfk5+fD3d0do0ePxpdffmlIM+skhBAkHL9
kkLlDV/+FBu9OAquHejPq+PLzHrh4OQpSqeqsqulTW+P8hUiER2ZU+viRY/
I4q0fByUhKkmcLDB3SEG1aOePs+Ug8CUuDibEQvXt5YfBAP5iZGVU6D4VCqZ3IZARz5x/
Bs6hM9YMB9O3tjdt34pGTK/
dQN2vqiJnT26BLZ09DmlkBvrgEwV+vw9N1OyDJygEAiJ3sYOLpIr8B1bFMxMu0XLVIZ295XcVgqdI1hTapV
nUZaWER9pi0MNj8gx+fgGUjw6feJSblYvBw1U0pteHlAlZl/
y4rRsUAAAPY2Jhg47ph8Kqvet+b52UIepSMrOxCODuZw8/
X7o37gqBQqpuSEh7nLkTg4KFQpKXnw97eFN261sPRY08QoeTmpTJ8G9jCydEc9vYmGDa4IZo1q/
7aYTKpFJcGzUbS+Zt6ESmV4TK4B3oe+9Mgc1c32ly/
aWPGOgpbmjZtkHrYAGQSSbnf+eISJF8KgCQ7Fxa+9WHdUj8F4fRdl+XlP0fZv8uCgknpf7IyCzH/
g2M4fGAyhEoaV546HY5ff7uBlNR8xTEfbxssWdwdrVspL7BIoVB0IzwiHVu3B+L02XBIJC8u9DGx2bh7L0H
r+Z6Gp+NpeDo4jsH+g48x6522mDu7XbXegDz9fTuSzl5XOYY1FkNWWKTzGu3Wf6XzuXUZKl7qKKxQCMc+HZ
Fy8bbKVDuBuQmkudqlEAvMTGDuI3etEkIQtuZfPFqxTuHyBACRgw3a/
PoF6k0cgoz7IYjefhTFaZkw8XCG9/
TRMPPSrN6OrY0xfBvYIjwi3VA6rAK8jCApOQ+XLkehXx+fCo8fOfYEX319ocLxZ1EZmDv/
CDZtGI4WzWkAOYWiL/7ecg/
rNgQYZG6el3+xbNp8F87O5hgxrHoqcccfvYD7H61SOYYRcLBs7I3MeyE6rWHXuRVMPd7Mmyka4ViHafzJLK
XCheE4mNZ3Q7s/
Vlb6uFJYBt6zxkFgYozMoCe40G867n+4qpxwAYDilAzcmLQIB1y64lSbUQhb+x+idxzF41V/4ohPPwR+/
rNGTcMYhsGM6W2qTbiUwXEMAm7HVzheXCzFj79cq/
QcmUzuxfnpV9V3UhQKRXP+2/7AYMLlVTZvuWfwZoYp1+7i0tA5uDJsnlrPOJHyKEnP1mkdTixCh7+/
1enc1wEqXuowzv26oN0fKwCWfdHMsbQ1s7GrI7rtXYOA6Z9pN6mMQGhphosDZuBki+FIPq86lVlRtVfKy39
4Xl7Vd9VGhK3VrPBdvz4++GB+JzAMyhW4MzR8Ja0XrlyLRl6e8qJ+MhlBcEgKomM0CxqkUCjK+XfrA/
y6Vj/lEjQh/nkO4uJz1A9UQl5UHAI/
+wkXB87E1dEL8Ozfg5CWbvkQQhD42U84120yEo5f1nhOU08XzSuml34/
mnl7oO+Vba9FSwBdodtGdZwGcybA2b8rIjftRebDJ+CMRXAb1hseYwfiwac/QFYiUT/JKwR/
9TsYruq6NuS7jfB9d5JGXa2nTmmF3r28cOjwYwSHJOOODnvc2sDzBM0rCeBLSclXBPiqIv55Nup5WhvKPAr
ltefmrVi91XnSBolEt/oq4Rt24M78lWAYVn6TxrKIO3AGDz//Gd0PrUNe1HM8/
l9p4KwW3p3Mh6Gw69IaiSeuqB3r2Ksjmnw+B469Or7xyQM02+g15oBzFxQlpdWoDf1u7IJ9p1ZanSOTEQwd
uQ2JSbkGsYlh5IHC5uZGyM4uAsOwsLYSY/iwhrC1McH/friqdo5WrZzx14YRb/
wXCIXyMmnpBdi7PxgnTz1Fbl4J6nlaYezopujf16dCHaZ33z+K23fi9VplWx3GxkKcPzUdYrF29+2JZ6/
jYv+Klc5fhhWLINOxcCjDsTCysUJJZrbq4nUMg6HhZ2Du7aHTOrWdWtGYkVLzaBuoawh4HaLoWZbB7JltDW
DNiwStkhIe6emFkEoJJBIeKan52PT3Pfy85jpERuozoB48SERwSIracRTKm0J4RDrGTtiJv/+5h/
jnOcjOLkLQoyR8ufwcOnbbiIlTduPQkceQlF6c7957Xq3ChWUZjBrRWGvhAgCPv//
zxda8EnQVLgBAeBmK07PUFg9mWBZR/x7UeZ3XCSpeXmNM67vWrAEsC4uGXjqdOnxoI7w/
vxNYlgHLMuA4RtGxul9fb9jb6VYh09hY9RZWSYlMoy9UjmNw8nTVOnFTKK8LPC/
DR4tPIDevpNzn5+VyBWFP07Hy20tYsPAYSkr4qlb5V8mrsXMMAzT0tcO82e21nksmkSD5QkDVGyiqXUimfg
0GyI99sxowKoPGvLzG+L47CXfeXVEjazMCDq5DesHExVHnOaZNaYXBA3xx7EQYnifkwNJChAH+vmjgY4vxk
3chNU07z1L/fj44czZC7TiJmmq/gPxLOTunoldJJiO4/
yCh1F4xOnV0h0hEP2aU15tbAXF4nqDZNu+duwn4+597aNHCCQ8CEzW6WRAZcRg5ojEcHUyx4c/bKClR/
hkVCBgM6N8A5y8+Q2GhFM7O5hg3uinGjW0KY7H6+LtXkUl5g9XT0gWxPY21A6h4ea2pP20UIv7ai8wHjw1z
l8MygIyA4ViQlzJ3GI6DsZM92v62tMpL2NubYvrU1hWOZ2Zpvh1lLBZg+rTWKCnmwbKaFbrkOEZRH6IyGAZ
wdS6/J3srIA7f/O8SEl76EjczNcLc2e0wcXxzGh9DeW0JDEqCQMCqbfMByLNy/
vrnLjp38lApXBgG+PD9zmjcyAGNGzkotnsIGKxVEujLMMDE8c3x4ftdsHK5/
GaiqhmMnFgEc996yA2PqRYR8+r36csQKY96bw03uA11Abpt9BojMBaj78Wt8Jo+GoySSrIqefViy5T+QB6c
5j1jLHqd2QzPSUPBCuVfLAIzE/gueAv+d/
fDxM1w5bg18WaIRBxWf+ePsyenY+b0tuAErMbfPSYmQpVfejIZwfCXil3de5CABR8eQ2Ji+bvPvPwS/
PjLdWzdHqjZwhRKHSE8Ih2nz4bj6rVo8LxMq/ophMizjVR9xggBNv19F/XrW5eLU5n6Vku8/
VZLRWmFl7eUhw9thAXvdlKMrYpwKUrNkHd/
5nn4ffC2zvNog9DSDJyxuPJsT5aB54TBsG5Rsx2xaws02+gNoTg9E5kPQlGYlIabUxYrH8gwsGzkjYaLZyD
k2w3Ii4gFAHAmYnjPGIumX80Hy3EQmJmUa9wok0ggzSuAwMKsWho6frb0DM6ei1R559a9az38+tMgxe8Pgx
IxfZZmwW4MA9jamiAzs7BSD8ysGW3L7Z9PeGs3noanK51PJOJw9sR02hCSUueJiEzHim8uIuTxi4B1oZAtV
9Jfn3jVt8a+XRMrHH+ekIOjx58gJSUfNjbGGDzQD/XrVX1LJe7gWQR/
swGZ9+VVb41srdBg7kRkhYTj+aFzuk/MMLBs2gA5jyOUelZafPcRnPt3wfXJHyM3LEp+s0jk2/
A+s8ah9a+fgzN6fb9DtLl+U/
HyBnLjrY8RvfO40v2TrnvXwH1Uf2TcD0FOaCTEzvaw79QKAtPqbyOvjAeBiZgxR7UQ2fDbUHRo/
6JNASEEk6fuxZMwzdLHOY5Bh/
buCLgdryhoZ2UlhquzBUokPExNhejf1wdNmzji7Xf2q51vxbLeGDqY3jVR6i6xsVmYPG0vCgul1ZopdOTAZ
Li5Whp8nSe/bsH9D1fh1f1lhmVh27EF6r09HHfnrdBq+4jhOBCeh8f4gWj3xwpcG/M+ks/
fAiPgQKS84v8+s8ej3YavwLAsCCFIvXYP2cFPwRmL4TKoB8QOtoZ4yrUK2piRopL2m74BX1yCuH2n5dtJDA
PC82A5Dq1//Rx8YRGOePVBfkxpoTiGgbN/V7RZ+yUsGtSrUdvLaNXSGdPfboV//
ntQrqgcwzBykTKhOdq3cyt3DsMw+OWHQRg8YqtGX7w8TwBCcPbkNETHZGL3nkc4fTYCubnF4Hl5l+qHQUka
BQEyDJCeXvOp6xRKVdj4910UFVWvcAGAkyfDMctA5RPKyI95jvuL/if/
5ZUbOyKTIe1WINxG9IXYwQZFycq9rC/
DioRwHtAdPrPHw2VgdzAMg95ntyD5wi1EbzuCorQMmHq6wnvGGNi0aqw4j2EYOHRrC4duhn3OdRkqX
t5ABMZidNu7FlmPwhCz5yQkWbkw83ZHvbeGIWbHMdx8+9PyJxCCpLM3cKbjOPjf3ldrCiTNf7cj/
Pzs8d+2B3gcKm9T4Odri7cmtcRA/
waVBsg6OprBxtoYaRoKiZsBcQCAyMgMnC7NVCrbRirrUl1QqL6KMSHAjVuxGD6sEaytjDVam0KpTRQWSXD2
bITKQHZDISOG2ZJ6mci/98lvfpRlN8gInq7bDkag+WVTVixBl50/
Q2AsVhxjGAZOfTrBqU8nFWdS1EHFyxuMVTM/WDXzU/
xekpmNB4tXVzqW8Dwk2Xm4PWcZRLZWSL1xH6xAANchveA7fzIs/
LSv50JkMuSERYEvKISZjyeMLM21Op9hGPTv64P+fX1QXCwFoFkgr42N5uKFECArqxD/
bQss237WmfsPEjB1xn78t3kMrCzF6k+gUGoROdnFkCqJ1TA0vXrqVi9KG7JDI0HUeJQKYhLg0LM9CpNSAQ3
/
FvpotUKpCBUvFAXRO49BJpEqfZzwvLxRI8cqPrjhf+xE+MZd6LZvLdyG9UFRagYSjl+CJK8Alo284dirAxi
24of32b8HEbxyHfKeyT0brJEQ9SYPQ8vVH0NsZ6O17drUUunRvb7K4NqX4Tj5NlRcvG6dX19GJgMSEnKx6e
+7WPxR1yrPR6HoE0IIgh4l4cKlKBQVSeHjbYOB/
r6KIHMLCxEEHFvtAsbZ2Ry+DewMvo7QzFSepqyqPD8A5wHdkXLptvoJORb2nVq91gG2NQkN2KUAAAqeJ+Pi
wJnIfqRD1ViGASsUoN5bwxH13yEQqVRRh9+0nis6b/sB9l3aKIaH/
O9PPPzsp4rTCDiY1nODf8AeiGysqvBsVJOSkofBI7aqdX8zDODfrwHem9cBQ0du09v6JsZCXDz7DoRCw2dl
Ud5sHoem4PDRJ0hJyYONjTEGDfRD65bOFbZUs7OLsOiTk7gfmAiOY8AwDHheBpGRACuW90a/
Pj4AgC+WncWZc5pvHTGMPI25rP6LpnWWyhAKWOzfM7FagnWfH7uIy0Pnqh0nsDKHbesmSL4UAKjx1HQ/
sgFuQ3vry8TXHpptRMWLVuTHJeJ0+zEoSklX+2FUirI9FZYFaySA/
629sG7REPlxiThcr5fSdRiOQ8OPpqHV6k90s0NDTpx6ii+Xq057NDMzwvZ/x2LLf/dx8HCoXtc/
fWwq7O1N9TonhVIGz8vw9XeXcOTYE0XBxbL/
d+3iidXf+b8o+kYIZsw5iEfByRVECcPIBcif64ejdSsXxMRmYfLUvVoF7VpYiDBhXHN06uCOw0dDEfI4BSI
jDj2610NsXDaOHg9T9Bx7GXc3C2z+cyRsbavncyLjeZxqMwpZj56qVFgMx6LhxzPACjiErd0KaW5+
+QGlnumW/1uExp/
ONrDVrxdUvFDxohVXx76P+EPn1LpLdYXhOLgO7YXuB9fh0crfEbxyndI6BwAgtDLHmPTblW436ZOr16Kx5I
szKCyquFXWvJkjVizrA0IIRo3bqdd1GQa4fG5mhZov4RHpCHmcAqGQRYf27rCzlaemE0IQFZWJwiIJXF0ta
bzMG0JOThFOnHqKmNhsmJgI0a+PNxr62Wt07oaNt/
HXP3crzehlWQZDBvli6ee9wHEs7j1IwKy5h5TOxbEMOrR3w+9rhgIAnoanYcU3FxH6JFUjW1iWgUjEYduWs
RXqsBBCcOhIKLZuD0R0TBYAoJ6nFaZMbokRwxpVe1XqwuQ0HPX1hzQnT+U4U09XDI+
+AL6oGGm3g5Bw4jLSAx6CLyqBTevGaDB3Qrl4QopmUPFCxYvGFKWk46BLV5ViQi+wLMZm3cHd+V8jesdRtU
JpTOYdGFkZ/vUrKeFx4eIzPHiYgKysInjVt8GgAQ3g7m4FQH4R2PzvPb1lWLAsg47t3fH7miGKY/HPs/
Hl8nMIepRcbtyQQX5o2cIZ//x7D3HxOQAAjmPRv683Fi7oXMFzU1LCI+hREgoLJahf37paXO0U/
UIIwd17Cdi7/xEuXooCLyMQCOR1P3ieoHtXT6z6pr/
KBqOFRRL0G7gFBQXqs+Aa+tnBylKM23fj1W7nXL88q1xZgLCnabh2PQbHT4YphIcyOI5Bvz4+
+O7rfpU+TghBTo68K7OFhahGW2mcaDMSWfcfqxxjZGOJMekaxL1QtILWeaFoTN6zOMMLFwCQyVCSlQsja/
WChBFw4Eyqx7tgZMRhgH8DDPBvUOnj6RkFpV+k+hEvMhnB5InNX8yfXoDpsw4iK6uwwrgjx57gyLEn5Y7zv
AxnzkXgfmAitv0zBra2JiCEYNuOh9i85R6ySy8AANC+nRu+WNID7m7VK2JKSnicOPUUBw8/
RnJKHuxsTTBsSCMMHeyntqv3m0zkswx8vOQUYl4RAi/
3C7p2IxZfLD+Hn1cPVDpPUFCSRsIFgMYFGwFgyPCtGDTQDxPGNYOriwX8fO3g52uHGdPbYNXqK9h/
METpVhLPE5w7H4llX/QqV+q/DIZhYGlgj2JO2DM8Xb9DHmxbWruqwdwJMKvvXm6cVWMfZAeFKb/
BYlmY+9U3qK0U9dAcrjccgZkequZqcJPEiowgsrOG54TBKr0ujICD+2j/
WhOh72BvCpmexd2zqEzFv3fseqi0BYEyeJ4gLS0ff/59FwDw+4YA/LL2RjnhAgD37j/
H1Bn7kZikWbdffZCXV4IZcw5i5bcXEfI4GSkp+Qh9korvf7yCt6btQ0YGLdSXm1uMQ0ce4+8t93D0+BPk55
cgJSUPM+YcRFyc6qw2mYzg0uUoRD7LUDrGUGX6M7OKsH3nQwwduQ179gWXe4znZWr7CEl5GXLzilWOMRTP/
juEY40HI3z9DmQFhSHr4RM8+ekfHPMbgPjD5WPffOaMV+0ZlsngPqIvHnz6A66OeR8Bs75EzO4TSL/
7CAXPk5WfR9ErVLy84Vg2aQBTL3f1A1/
i5SaPDMeCE4nkHaZVjPecOBSZgaEoTs+CTYcWlQsehgHDcWjy2Ryt7DEkQwb56RzDrIxrN2IU/
z587IlO1Up5Xu6ZiY7Jwpb/7isdk5tbjL//
uaezrdryw89XFbEQZdsQRF6oGLFxWfjq6wvVZkttgxCCLVsfoO/
ALVj57SX88edtLF95AX0HbsGylReQl1ei0XuB4xicvxCp9PEGPrYVeqrqm//
9cAU3b8Uqfnd0MFNru1DIwsJcZFjDKiHz4RPcmrYEkMnKiRLC85BJeVwb+wHyouMVx+27tIHP3Iq9lMowsr
dG4Kc/IvSHvxG3/zQi/9qL6xM+xOl2Y3DIrTvO934b6XcfGfQ5Uah4eeNhGAYeo/trNphl4dS/
C7xnjIFl0wawbtUIjT+bg6HhZ9B85QeVz89x4IzFSDx9BWc7T8DlIXOQEfCw8l0YQtDww2m1qmuqk5M5TEz
0u9VRUvLiCzQrq0jneYqLpTh4KERlfADPExw7EVZuTUORmVmIE6fCVW4dXLsRq5eaOXWRHbuCsPb3m5BI5K
9FmbetuFiK23fiNRaxDMOorOpsZSU2uEhgWQb//
PdA8fvgQX5qu0oLOBbhEZrVV9InYWu3Ki8URwiIjCDij12KQwzDoM1vX8L3g7dhZGelOC60NAcjFKAkNVNx
bmWkXLmDs10nIfVG5TcVFP1AY14oyA6JkHtO1H15ymTwGO0Pn9njKzzU5PO5ENlZ49GK31GUWJqFwDCwaOi
F7JDwiumESnjy679ovGS21tV2DUX88xyN4wc0gWWBZk0dFb+LRQKN2gtUBsMAWdlFYBkGMhUxOSUlPHJyix
XZS4YiOCRZ0cBSFYEPE6s9DqemKSqSYuOmO3qZSyqVKe2eHP88Gyu+uVhhC1HfyGQEd+89h0TCQyjk4OJsj
mlTWpUTNK9SVCzFnPcOY+d/4+DhYWVQ+9LvPkLcgbOQ5hcg7sAZldtAhOcRveMYLBp6wdm/
K5Iv3caDxatR+NIWkGl9VxSnZoKoKOL5Yj4ZCJHi9uxlGPToaI0GH7/
OUPFCQca9YI3qu4jsrFFv8tByxyS5eUg8cx3S3HxYt2iI4TEXkXkvBNK8AohdHXG67WitbJEVlyB6+xH4vj
tZ6Zicp1GI/
GsvcsKiIDQ3hfuYAXAd0hOsFj1HNLZHm4paGsFgzKgmit+EQhYoVDFcCSzLoEsnD9jbm6rt+yLgWJiZGiEr
uwiXr0QhN68EHu6W6NzRAwKB/pyvmn5Jv4nf5QG345CXX1LleRgAxibybuavcuDQY3z3/
eVqbZoolcoUxRbnv9sR2TnFOHCo8kwdQuRC+r/
tgfjys546rUdkMiScuIxnWw6gID4ZJm6O8Jo2Cs4Du4PlOJRk5+La2A+QdPb6i6azGgiOgrhE3Jr+GSotOA
MgPzpBq07SkMmQHRKOjLuPYNuuufrxFK2h4oUCVqQ+OJYRcOh1+m8ITEtrj8hkuPfRKoSv217ursbY1RFd9
62FU9/OeLblAPhC7a/
MgUt+wtPftsF9VH80mDcRJm5OiseCv1mPoKVrXrST5zhEbz8Kq+Z+6HVmM4wd9VtG3NXVApaWYmRn67698z
ID/Rvg4OFQGBsL0Kt7fZ1zmBhGvj2wZ1+wyhRXlgX69vHCpr/
vYNvOh5BIZIou3La2Jlj+RS907eKpoxXladrUEQIBWy47pjK7W7d00ct61UFuXjHOnotEckoebKyN0b+vD6
ytVTfWfPgoCXv2BSMoKAlCIYse3evrrRknATBlUgtF1tbTp2l4/
CQF8c9zsHlL9W5TuLtZlsscKqvKq6qKLs8TnDj1FF8s6aG1R0JaUIjLw+ch+dxNMBwHwvPIuMshbv8ZOPbt
hO6HN+Dq6AVIuRQAALrVrVImUHSsKJIbGUfFi4GgdV4ouPfhd3j62zYQXsmHnQGaLn0PzVe8rzh0fdIixOw
8Vvl4lsXAe/sRf/Qigleul7cL0AWWAWtkhJbffQSv6aPw/Pgl3HxrceUmchxs2jVD/
xu79O6m3fjXHfz5151Kv78YBjA3E6F1axdcuRqlUelzgYCFTEZ0vkNmGMDO1gTpGYUazdG1szuu3YirdB6G
YbBx/XC0aeUCiZRHcnIehAIODg6mOv0dv1l1CYeOhFZqF8sCTRo7okM7N3ACFh07uKN5U8da61bftScIv/
4mj1HhOLb0wszinamtMXd2u0rt/
mvzXazfeFtRzRaQe8k4jtFLFlCZY2DyxOYICkrGo5Cay275ZFFXTBhX/
sK86NOTuHQpSq0ov319rtZev4DZSxH5977KlRHLwnVoLzw/
fF6rOQ1Nz5Ob4DKge02bUWegReqoeNGK3MhYHG86GLISSYXtI4ZjITA3xdDwM4qGiTlPo3HMz1/
lnJbNfOH77iTceXeFznct5ewwEkJoaoKSrByV8/
W7vhP2nVtXeb2XkUh4fLj4JG7cjJXHl5AXFyUzMyP8uW448gskmDHnoF7XrQyGATw9rBAXn62Xwnksy6BpE
we0a+uGvfuCkZMrj5Wo52mFd6a1wZBB2lUJLSyUYP7CY3gQmKjw8JT9zcq8Mhwnv+jzPEHTJg74afVA2NvV
rlYJh4+GYsU3F5U+/
u7c9pg5vW25Y9dvxmLBQiWCHi+2y5SJYIbRru+Ptn2C9M3Zk9Nga1M+juqXNdexY3eQyvemvZ0JTh+fptVa
RakZOOjSTfWNkC5/RANiZGOJkQnXwGng2abI0eb6TbONKDD39kDPY39CYGIs//CzrPwHgJGVJXqf/
adcp+egpb+qnTP70VM49O1ULq26KpASCUoys1UKF0bAIeH4Zb2s9zJCIYdffxyElcv7oEkTB1hYiODsZI7p
U1tj744J8PW1Q8sWTmjfzlVtrYuqQgj0JlwAeeBl0KNkbN5yTyFcACAmNgvLVpzHxr9eBJmmpuYj8lkGcnO
VB4MaGwvxx7phWPVNP7Rr6woPd0s0aeIAkYhTeGN4nijsD32SijnvHq6WbChNkUpl+G3dLZVjNm+5j/
xXYli27QgEp+L1J0Tu6arsPUKI9tfcGr9GV/
IWHD6skcr3JssyGDOqqdqpZVIp4o+cx8MvfkHQ8rWI+HO3eg+uhn9EsZPhO1QDQLMV71PhYkBozAsFAODUp
xNGxF9B1H+HkHr9PhiWhWPvjqg3cbAizqWMnCfPNJpTkpGNpl/
Mw6OvflM+iOMAZdtVWsIwDPjiqgdFVoZAwGLIID+lngiGYfDT9wPxxbKzuHItBiwrv0ipiv/
QhrJtiLffaon/tgXqZc6XeVUTlv2+cdMdODuZ4eDhUDwMSlLY0rePNxa82wkuzhWzwoQCDv79GsC/
n7xq8S9rb+Dx45RKt5J4niA6JgvnLkRi0ABf/
T4pHXnwMBEZmapjtYqKpLh6LRqtWrmgpEQKWxtT3H+QAF7NNp61tRhmZqIKVXTrGo6OZpXG/
njVt8G0t1thSyVZRxzHoJ6nNSaOVx0DknEvGFdGvIeC+CQwQoE8nVlPfdeEluZo/
+fXuDLyPUDb4pNlhbZLGy9WgGUBQsAaCdF85fvwfU950gGl6lDxQlFgZGkOvwVT4LdgispxAnPNXPxiB1s0
XfYeWKEAwd9uAF/wIujV2NURHuMGgmEYPPn5nyrZXYZMIoVNmybqBxoIU1Mj/
PrTYEQ+y8DlK1EoLubh4GCCb/93Raf5hEIWhMi/
9Du0d8eUSS1gbiYyiHhRBssCX319sZy3oKzUe8DteGz9ZwxcXVS7d0+eeqryos4wwOkz4bVGvLxcfE0Vny9
7UZm1bItMHenphSgurj1eJl1gGGDiuGZKvYwL3u0IJ0dzbP73HlJS5CUSjIw4DBnkhw/
md6rQkPRl8mOe43zvqZDmyysxa5IppLHdHAunfp1xZcR72rutSrekmi57F8kXbiH1qry6tXXrxvCZMwEgBE
VJaTB2tofH2AEwsn6zSgHUBFS8ULTGe8ZopF1XndkgtDSDqacrGIZBk8/nwnfBW0g4cQUlWTkw83KHY+
+OYDn5llLKtXvIuBtcdT+4gINVcz8UJqfpPetIG7y9bODtJd9mk0h5/
LL2pta1YjiOwcTxzbFwQedyx3leBgcHU8VFwdCUvSSvXph5Xt5Ib+Gi42jfzh329qYY5N8ADg5mFeZQlyJM
iDyrJzu7EA8eJiEvtxj29qZo3cpFkYb7KoEPE7F910ME3I4HkRG0aO6Ejh3cIRIJIBIJ0KWTB2x1rGsT9Ch
J63O0Cb7OyzOMd1AXOI6Bk5M5fLxscPV6jMrnUeZ46NGtHiZNaKF8HMNg3JimGD2yMZ5FZUIi4eHhbqVStJ
QRtnYrpPmF+u+3xrIw862PjPuPNYrBY42E8hjAUkzcHNFuwwq4Du4JfLUAMqlU7mUR0l5dNQUN2KVojUwqx
X6HTpBk5igd03L1YjRePFOj+WL3nsS1cQv1ZJ0cqxYN0fTLefAYM0Cv8+rCT79ex67dQWq3FMpgWQZisQB7
d06As1PFbZl9B4Lx3fe6eXMMAccxiuvBO1NbY96c9opMnJjYLIyduEvl9hnLMrC0ECHzlWrD5uZGmD+vI8a
OLh8jse9AMFZ9fwXsSxk9ldk0cnhjfPxhVxgZaRd3NentPVo1LKyNvOwJKstQEgpYSKSycoHDzZs54vtv/
ZGeUYCpMw5AJpMpDShu1NAeE8Y1w0B/X3DKKtZWkQPOXVCUZJi/vbGrAwqfp6gdV++t4aj/9nA8+/
cg+PxC2HdtA7+FUxU3WxTDQbONqHgxONlhz3Cm/
VhIcvIqPOY1Yww6bPpG4xTY2ANncG30Av0aWFoxuNUPn6DRxzP0O7eWZGcX4e139iMhMUfpxbYsbVQqlcHW
xhi//DgITZs4VjqWEIING2/j7y33wLLKL+Cv4upijucJhm/S+OH7nTFlckvk5RVj2OjtVWqBAABTJrfEB/
M7gWUZPHuWgbGTdmmUwMYwQJ/
e3lj9nerMuDIIIdi99xF+WXvDYM0Nq0rZVo2VpRjZOUUVXnuGAfr388F3K/shNTUfV67FoLBQAq/
61ujYwR0RkRm4d/
85CAFat3JBo4b2inOvXovGZ0vPoqBAAoGABSHywOpmTR3x64+D1Na3UQaRyZD16CkkuXkw9/
aAsbNDhTHZjyMQ8ddePF37n+G63GtSRRyAibszCuISFckGRMrDopE3uh9aBwtf2k3akFDxQsVLtSDJzcOzL
QcR+fc+SPMKYNXCD02WzNa6KNPJViOQGfREoy8WrWEYDIs8W6HtfXWTmVWIDRtv4+jxJ4qYhwY+tpg1oy2M
xQLcuh0PGS9D8+ZO6N3TS+l2ycvExWfj8NFQ3L+fgMAg1VsdXbt44Ksve6PvwC36eDoqMTc3wqF9kzFj9kF
E6ykw1cHeFDPfaYuIyHTsPxiiVbbV9n/
HlrtIK2PN7zfx71bl5e1rGhtrYwwe6IvRo5rC1ESIVT9cwaXLUQoPi7GxEBPGNcO82e11rpxcWCjB6bMReB
qeBpFIgB7d6qFFcyeda/
FEbT+CoKVrkB9V2viQYeA6pCfarPkCZvXdQQjBwy9+weNVGxWFJ2ucSnLQGY6DyN4ag4OPQWRbeWsGStWh4
oWKlzpDwfNkHHIzXBEnhmPR+NPZaPHthwZbQxsKCiRISsqF2FgIZyczvRRok0h5jJ2wC88TKvfsMAywacMI
ODmZY8iIrVVeTxN8vK0REZmp93ltbIyRkaF51WaOYzB+bDN8/GFXxTGel+HqtRgcOPwYz5/
nwNpajE4dPLDujwC926tPvv+uP/
r1Kd8WICUlD2FP0yAUcmjR3ElRebc2EPb7Ntxb8HWF4wzHwcjaAgPu7kfimeu4PXtpDVinAyyLFt9+iCZLZ
te0Ja8t2ly/
acAupUaRFujQ2EcLiIwgOzTSoGtog4mJEF5eNuoHaoFQwGH92qGYt+Ao4uKz5TEoMgCMfJth2Re90LqVCyQ
SHmamRnrpsaMOQwgXAFoJF0Ae15GZ9eIciYTHok9P4dr1GEVcSHQMcP9Bor5N1Rssy8Da2hg9e1TcsnBwMK
s0SLqmKU7PxINF/
6v0McLzKMnKwcMvfpV3XlbST8iglEUfa4NMhuith6l4qSVQ8UKpUUzdnSEwM4E0r8Ag8zMsC4GZYbsp1wZc
XCywb/
cEXLkSjctXo1FcIoVfAzsMH9pIkXUjELAYNbIxtm4PrPZrhb5QVaVW2XgnxxdBz+v+CMD1GzEAXmQI1ba/
xcvBthzLQGwswK8/
DoRQTwUfq4PoncchU5HmTKQ8Ynaf0L11SBVgBAKIHWxQmPAieFfkYAuGY1GUmKry3JIs5UkKlOqFihdKjcK
JRfCeORZha7capGQo4Xl4jFEfsCmTSsGwLBi27hadFgo49OntjT69vRXHMjML8fuGWzh0OBQZmYWwtBTDyk
qMzEz9NJqsbggpC1olGokOnicYPMAXl69GIyYmEzt3B+ksVqrDQdC4kT04jkV0dCZMTITw798A48c2qzTrr
DaT9ywODMsq75cG1Ixw4Th4TR2JdhtXIOXSbRQ8T4bY0RZOvTvi6tgPkHD8kvK4G46FhR8N2K0tUPFCqXGa
fbUASeduIPtxhF6DdhmOg2UTH7gM7lnp40QmQ+Tm/
Qhb8y+yg8MBloWzf1c0XjwDjr066s2OmiIpORfTZx5AalqB4k4+O7sILMuo7f5cW5EX7HPD/
QeJKC6WqhUTRkYcps48gPz8kiqLD44z7N+MYYCB/
r6YPFF5DZW6QPbjCDz7Z79K4VIGZ2oMPr+KW8cabgGVxdo0XfYuWI6DU59O5R5vMGe86saOvExekI5SK6i7
t5mU1wYjS3P0v74LTT6bA85Ut3TMMhihAIxArslt2jRBrzObK63PQGQy3Jj8MW7P+hLZIRHygzIZks5cx/
k+0xCxaU+V7KgNfP3tJaSlF1QoPCbvaC2DUKj6429qUnuCP8vgeYK3JrbE8UNTMHN6W6iLdy4p4RU9iKrqN
TG02BOJBBg2pKFB1zA0xRlZONdzCiQ5qosoMhwHp76d4TN7PBhda8aUeklZI83ep/bd26L/
rT0w9XCp9HHnAd3hOWEwKn1TMQxchvSEuwZeXEr1QD0vlFqB0MIM
Lb75EM1XfoDCxFREbT+Ch5/+qPkELAuPMf1h7OwAVmQE1yG9YN+1DRiGASEEabcCEbv7BEoyc2Dm7Q6BuRl
idh2Xn/
vSVa3sbvH23OVw7t8Fpp6uAOSBxYlnrqMwMRXFaZkwdraDuY8nHLq3q5VbTXHx2bgZEKf0cZkMkMlkaOhnV
2lBNhtrMdavHYabAXFY8/
tNQ5oKkYjDgP4NcOpMuMrS+SzLoHlTR7Rv5waWZdC+vRs2bb5rUNt0gWUZMAy0SudmWQa//
DgI5uYiA1pmeCL/3ofi9Ez1HlSGQbOV78OqmS9Sr91Dxt1HmgfQsixEdlbwnDAYLgO74/
EPfyPlgupGmgDgNqw3zL09VJjEoNO2H2DVoiGe/
LIFxSnpAOTdoX0XTEHTL+bSQnW1CCpeKLUKhmVh4uqIJp/
MQub9EMTtO61h0SoCu86t0fCDqeWOSvLycXXkAiSdu/7Cvaz4v/
J9BIYBIjbtQfOvFyLs138R9NVaSCu5mzSt54oOm76BU9/
OlcxSc4RpWCF2yuSWaOhrj517ghATkwUbG2N07uSB/n19IBIJ4OtrB08PS3z6xRlF4TZ1tb7kbWA06/
VjZMRhw2/D0LKFMz7/tAeiY7LwNDwdv627gZTUAkX1XpmMoFFDO8x/t6PixlgoMGwHb11gWQY9u9fH/
Hc7YO26W7h6LVqtiDEy4vDbL4PRrq1bNVlpOJ5t3q9WuDAch57HN8K+UysAQN9LW3HUt7/66relbzy7ji3Q
/fB6Raf7/
NgE9eKFZZEVFKbWfpbj0GTJbDRaNB05T6MBQmDuWw+cEe0OXdugdV4otRZJXj6ujlqApLPXNRo/
JOxUhQqYF/zfQdIZzc5/FecB3eDYsz0Cl/ykfBAj/zLuc+E/OHRrq9M6huDylSh8uPik2nE/
rPIvF+CrjOzsIhw9EYagoCSwLAM/
Pzts2xGI7OziciKlrALsN1/1wakz4bhyLUblvFv+GoXmzZwqHOd5GW7cjMXFy1G4cTMWKakvhKOnpxU+fL8
zrlyNwoFDoWptV0eZGBII2CpV1nV2Nsf2f8fCylIMAEhNy8e0GQeQnJKnVMh16+qJRQu7wsO9Zhr5EUKQeu
0e8iJjIbSygHP/LhCY6LZ1G7R8LYJXrlM7TuzqgFHxVxW/
8yUl2C1qpvokhoFFQy90+Osb2HVqVa4+UnF2DvZbtVN9uoCDz+zxaLduuVr7KDUHLVJHxctrAyEEqVfv4sG
nPyL9VmClYxiOg8ugHuhxZAMAoCglHZF/
70PCqatIvXJH98U1zctlWdh1aI7+N3brvpaeyc0rRr+BW1BSonwbRihkceb4NFiWXmy1JTEpF+s2BODMuQh
FPEib1i6YO6sd2rR2BSEE3/94FXv2BYNlGMhK/
45lqcDvzmmPme8oF3wPAhMx573DpTE6L14DbdOlVWFmZgRnJ3MMHeyHtLQCbNv5UKsmiy/
btGhhlwoNCzOzCrFteyAOHHqM7JxiGBsL0L1rPfTt443mzZxgb6dZh3Z9kfXoKR4u/
RU5T56ByGQoychGSXqW4nGBuSmaLXsPDRe9o1UBxdCfN+PBou/
VD2QYmNZzRc8Tf8KyoVw0ayJeGI6DfdfWEFqao/B5Ckw8nOA1fTRcBvUAy3E41/
MtpFy5o3LrqdeZzXDu10Xj50Spfqh4oeLltYMQgnsffIunv21VlBEv+79dl9boefxPGFmaI/
7oBVwb+4G8xoQBUq9VMSzyHMy8arYNwcv8vOY6tu98qLTR3rjRTfHp4qpXN87LK0FqWj7MzUWwe6WTMyEEZ
89HYtuOQASHpIBhgFYtnTFlciv06FZP5bwTp+xBeES6TmJCE0xNhTh7YjrEYvnueXJyHoaN3gaptPLmhMpg
WQaNGtpj04YRirlehRACiUQeJK2PqsraIuN5XBv3AeIPnNVofPOvP0DTL9/VaGzeszgc8emnuZosLb/
vt3AqWv+0BAzL4kzn8Ui/
HaR2i5jhWBBeBobjQHgeTv26oPvh9Ui7+QAX+k6v1AZGwMGqqS8G3DtQK+PTKC+g4oWKl9eWzIdPEPnXXuQ
9i4ORrRXqTRoC5/5dwbAsskMjcaLFMHmdhhp4W7f83yLYdWoFu86twApqPpxMIuWxdPl5nDkXAa60A3PZ/
3v1rI9VX/
fXuuNyVeB5GRiGUWwtqeJpeBomvGXYjK+vlvaukN1z5Vo0Fi85BZ5/4e3hOLmn6PNPe6CkhMeW/
+4jNU1eVNFYLMCI4Y3x3twOMKmF2VllBMxeikgtMugYoQCjEq9p1Mfnwac/IPSHv3X6zLX8/mM0/
mQW4g6cwVVlzVlVpUKzLHxmj0f7DV/h2b8HcXvWl5CVvs/AMCBSKaxaNESvU3/
B2El9fytKzULFCxUvbyS35y1H5F97tW/
upmG3WU0RO9ujxbcfwnv6aL3NqSuEEAQFJ+PosSdITc2HnZ0phgzyQ8sWujfbqw6uXIvGwkUnDDa/
hYUIl85W3m08ISEHew+E4PrNWMh4Gdq0dsHY0U3h420LQC7ComOyIJXK4OFuWav6CVVGUVoGDjh21u49zjB
ot345fOZMQGFCCgjPw9jVsdJsm3O9piDl0m2dbDOytsTIxGvgREaKmJlyDRo1+GyyRkKMTLwGkY0VilIz8G
zLAWQ9egqBiRhuI/vBuV8X6nGpI1DxQsXLG8kBl65qy3u/
isDMFPXfGYXwtfpvWOgzZzw4sRgFcYkQOdnCuV9XuAzsDk5EMxfU8Sg4GVNn7DfY/
I4Opjh5dKr6ga8Bkf/sR8A7n2t3koCDy8AeyH0SidxwedC12Nkefu+/
jUaLpoPwMhCeB2dijEsDZyLx9DWd7etzaSsce7QHAKTdDkL4uu3IuBcCzlgEM28PxO5WL2K7H9kAt6G9dba
BUjugjRkpbySyEonW5zT5ci7Sbz00gDVAxMbyAbwR63dCYGGG1j98Ap/
Z4w2y5utCk8YOcHExR0JCrtIxpTsDWoc2cRyDjh1qT2ySoZFkK/8bKkXKI+HohXIF24oSU/
Hw858R8u0fkObJs7+E1hawbd+8Sr0T+KJixb/
t2jeHXfvmit+jth3WSLxoVk6B8jpBfWmU1wbb9s3BaFFEymVwT/gumIJEHVOpdUGak4fbc5Yh/
I+dWp2XGxmLx6s34eHSXxG19RCkhXWzN5GmsCyDDxeorp0ze2Y7eNWX1/rgOHnLAwCwszMBxzFKq+/
KZAQTxjWv/
MHXEPNXygdoxauChBCFcAEASWYOkk5fk4sXXbZmGAZWTRoofdiuY0v1c7AsbNupSbWmvHbQbSPKa0PCycu4
NEhNu3qWgVVTX/gumAKv6aOQcS8EZzqM1W6h0nTP/
Kh4nW0VWpphZOJ1CIxVpynzxSUImPUlorcdAcPKLxBEIoXQ0gwd/v4OHqNf73Llp06H4/
ufriI7u0hxc29iIsT8eR0wYVxzEEJw914CAu7EQSYjaNHMCV27eOLSlSh89sVZEBBFkbiywNtlX/
TC8KGNaviZVR8ynscBx87lUqINASsygqy4ROPxjKC0xMHhDSrHXRwwE0nnb1Qay8ZwHNxG9kW3vWu1tpdS+
6AxL1S8vJEQQvDg4+/x5Od/
AI4FSl3JZQGAbdZ+Cb8FU8qdk3rjPs52maj1WsbuziiMS6ySvWZebhBaWsCucyv4vjsJlo19Koy5PvljxOw
8VvEOuHTPpPfZzXDq3anCea8TEgmP6zdikZSSBxtrY3Tr6gljsfog2di4bOzdH4ybt2JBCNC2jSvGjWkKby
+barDa8BBCIM0vACcWqc1uSzx7HRf7v2NYgwTy6rQh36gWIwAAhoGJqyP639wNE7eKRQpfpjApFWe7TkJeV
NyL4N1St5pFQy/
0vbJNUW2XUreh4oWKlzcWQgjiD53Dk1+2IO1WIBiWhVPfzmi0aHqlnaJLsnNxwKkzZEUa3jGyLGzaNEHGnU
d6s5kRcCC8DG1/
XwrfdycrnkfIdxsQ9OUalbbYd26Ffld3AACkhUUoSkqF0MJMoxRXSt1EkpOH0J82I3zDThSnZoARcHAfMwB
NPpsN6+aVN3YM/
2Mn7sz7qtLH9NLZuZRuh9bh6oj31I6z69wK3Q78DmNHO43mLcnOReSmPYj8ay8Kk9Ng4uII71lj4T1zLIRm
1Vvoj2I4qHih4oWiBbfnLUfkpj3qC2QJBXDs0wk5IREoqKLXRRl9r2yHQ7e2eLTydzxa/
ptG5wwMOoLwddsR9e8hRfCjY5+OaPbVAjh0bQsZzyPx1FUknrkGWYkExs4OcOjZHjatG9Mv/
jpGSVYOznabhJzQyHLvV0bAyXsGnfizgieuMDkNh9y6Ky8hoKqOipb0vb4Tt97+FHnP4lQG8A64dwA2rZvo
Z1HKawPNNqJQtKDV6sXIuBuMjHsh8gOlX7oMx0JoaYFmK+bD1MMFBc+Tcfe9lQazgxFwePLTZph6OOPRV79
rfN5F/xkoTslQdMQGgJRLt3G+5xS0Xf8Vnvz4tzzdtbSyaRmsyAgN5k1Ei28/
VPSzKc7IgjSvAGJHO5rSrQJCCJLO3UDExl3IDn0GI2sL1Js0BPWnDIfQ3Mxg6wYtXYOc0GcVhDaR8iAyguv
jP8SI51fKNRKM2nIARFWtFH3dvrIsrBp5o8nncxAw44tKh5SV+afChVJVqHihvPEIzc3Q98p2RP61F+F/
7ER+9HMY2VjCa+pI+M5/
C8ZO9pDk5eOgUxeDVu4lUh6J524g8p8DYFgGRE03YgAAy1QQLkBp6ijD4M7c5S/SXV/JKZYVlyBszX/
IuBuMJl/Ow+NVfyLlsrzYmMDcFN4zxqDp0nchsrHSx9N7bZDxPG5N/wzRWw+/KKjGMEi78QChq/
9Cn0tbYVZPvx2iJbl5eLpuB56u2678PSiToTgtE/
GHzsFz3CDF4ZywKPn7ycDZxG7D+8DI2hJe00cjLyoeId9seNHKo7Scv1WLhui6jwbXUqoO3TaiUDQgcvM+B
Mz8QuO7VLcRfZF+JwiFz1O0WocTi+A+dgBidhyrIEgqUFZmX0/VgRmWBXlJ4DAcBzNvd/S/
ufuNEzBEJkPi2et4fvg8pAVFsGrmi/pTR0BsZ4PQH//Gg09WV/
peYAQcLBv7YGDgYb1VMC5Ky8C57m8hJzRS7VhGKEDjT2aixTcfKo7d/eAbhK/
fob7y9EtB7tpi4u6MQQ8Pw8j6RXfs7NBIRP61F7nh0RBamMFj/
CBFI0UKpTLothGFomdyI2LBCAQgEqnqgQwjv3isWgQAuDhgBpLO3dSskhrLwKKRN4ysLeRxCGowsrVCSWqm
BtZrBnnFRsLzyIuMw6MVv6Ptmi/1tk5tpzApFZcGzkJmYCgYAQcQgBAZHn7+M9pv+hqhP/
+jVMQSKY+soDAkX7wFaV4B8mMTIbKzhuuQnhCamSLtdhCe/LIFiSevgPA87Dq1gt/
CqXAd1EOpPbfnLEPu02jNjJcRcGJRuUOmHi4qhQvDcXDs1QGFCSnIfhwh95bIiMbV/9xG90enzasgtCi/
XWbZyButf1qimd0UipZQzwuFogGPV2/Cw89/
VhvU2z9gb7kKoUnnbuBCv+larSV2skNRUprKMSb1XNFl+486pXlri8DUGKPTAipcFHVBJpEg/
sgFpN8OAisQwKl/
Fzh0b1dr+iwRmQyn2oxCVvBT7XtklcKwLFiREfjCIkVvHoGpMVyG9ELs7hPleveUbac0/
mwOWn73UYW58uMScdizl1bblQMfHlZkHT1Z8y/uL/
xOhbEMGI5Fv2s7YdO2KRJPXkH84fNIPHMNBfFJar16PnPGo92GFbXm9aPUbajnhULRMx5jBiBwyU/
KB7AsbNs3KydcAPnFR1uKktLknhemkqZ0LAvWSIjuB9ch5fJtMEINvEFVRJpfiMKEFJh5Va2kftrtIFwd8S
4KE1PBCAUAAUK++wPWrRqjx5ENaut9qIIvKUHc/
jOI2XUcJRnZsPCrD+9Z42DXoYVW8ySevY7MwFDlAzQog09kMrlwARSvnzS/UFHm/
mVRVLY1+HjVRjh0bwuXAd3LzZVx55HGwoXhODj166wQLjlhz3D/
w1Uqz+HERuiy6xfF38l1SC+4DumFEy2HoyBW9XtXYGZChQulxqDihULRADMvd3hNH4VnWw5UFBSlF7TmKz8
od1jG8wj68led1xQ72KIoOR1gSuNRpDxMXBzQadsPCPzkBySdu6H6wqbHbtkCM5MqnZ8XHY8LfaeBL5DXE3
lZcGU9CsP5PlMxKOioThlOhclpuNBnGrJDwhUZVWm3AhH59z40eHcS2v6+rMIFlhCChOOX8HTddmQGhoIzF
sNjjD8KElLk24NSJYLQQI5qhuMQtnZrBfHCcJqX3Lfr0gpddv2i+D38j11gOFZFijQD61aN4DasT4WHRHZW
at8/xi4OVLhQagwqXigUDWm34SuAZfHs730KdzuRSCE0N0X7TV/
DuV+XcuPTAx6iMEG7gF0FRO6B8b+7H2nX74MvLIJlMz+AENyc+ikKYhLUTuExZgBM67si9Pu/
dLMBAFgWdh1bQOxgq/scAMLW/Ae+oKjSbTci5ZH7NBqxe0+i/
lvDtZ772pj3kfPkmfyX0jiNsgt2+PodMPeth4YfvOggTQjBnbnLEfHnbsW2DQA8+XkLwMgfr24IzyPt5oMK
x+26tFbvXWMYdN23Bu4j+5cTExn3QlRvfRGCrKCnlT5Ub/IwJJ+/pfxclkX9Kdq/
VhSKvqDihULREM7ICB03fYOmX8xF3P4zkOTkwbyBJ9xH+1fao0inbr6vIDQzgd/7bwMAoncdx41Ji9Tf/
TMMvGeORYc/v0ZReiZCf9isPvjylRowCghB02UVK6am332EtJuBYDh5BWOL0uZ/
+bEJiNl1HMVpmTDxcEG9iYMhsrVWnz3FsojdIxcvhBCk3biP58cvQ1YigU2bJjBr4ImUiwEgUh627ZvDsXd
HMAyD9DtBSL12T+VTC139Fxy6t0VeZByElubIexaPiD/
lHb9ftonwfJW6I1eVyrJwRLbW8Jw4BNFbDyu1S+xgC1lRCYhUCkb4om0CJxapfT7K4pg8JwxG6Oq/
kBsRU0EAMQIOIjtr+MydoMnTolAMAhUvFIqWmNVzQ6NF6vvEmPl4Vm0hloHYyR4AIC0oxO3ZSzU7jxAUJqQ
g48Fj3H1vhUZZIxZ+9ZETGinPrmEYECkPVmSE9htXwsW/m2Jc3rM4XBu/EBl3g1/UjyEEzoN6wMTdCZF/
7gFT6pWS8TwefLQKLb9fDEl+gWoDZDKUZOWiMDkNV4a/i/SAhy9sKfM6MIx8+4znYd7AE90O/
I6kszfKeU8qozAhBadaj3pxQFX34xoSLoyAg1P/
Lni25QAKE1IgsreGJDsP4Rt3IS8i9qWBFcVIUWoGbkz+GIGf/
YwG705EvUlDYeruDLfhfeRbiyrWdBvRt9LHBMZi9Ln4H66N/QCp1+6Vbl8xIDwPi0be6Lb/
N9pPiFKj0GwjCsWAnO0+GWk3Hqiv2VIJVs39MOjhEQDAs/
8O4dbUTzU7kWXh0L0t0m4GQiaRaBT30m79cth2bIm4fachycmDRSMv1Js8DEaW5ooxRWkZONF8GIpTM7TOx
DF2d0bhcxXZKwwDE08X8AWFKEnPVvv3zgsAIAAAFkhJREFUYjgOQkszeE0fjbA1/+qcGVQpZV4oHbwwnLkJ
+PwijdOMFTAMWCMhZCUl8vUry2rT1B6GQYN3J6H5yvdxrNEglKRnVtyuYxgwAg4DHxyCVZMGKqfLuB+C5Au
3QGQy2HVuBfsubWisC8Ug1Ipso2+//
RbHjx9HYGAgjIyMkJWVpfYcQgiWL1+OTZs2ISsrC126dMGGDRvQoIHqDxeFUltpt345znSeUBrvod0FtuX/
Plb8Oy8iRvPMIpkM2cHhkEmkGgfsOvXvCnNvD9i0aqx0TPj6HfIAYm0vzACkefmqbSEEBdHPNZ6P8Dwk2bn
Ij3muX+ECgGEZOPl3R370c40Kw5WzS8qDFcoDfssJhlLhwRmLwBeXKP4WDMfKY2xkBLLi0uagytLxNRVShC
B8/Q6wAgH6nN+CC/
3eQVFSqtxDRYjcDrERuu5Zo1a4AIBN6ya0nD+l1qF5KLuWlJSUYOzYsZg3b57G56xevRpr167FH3/8gYCAA
JiamsLf3x9FRUWGMpNCMShWTX3hH7AXrkN7lduuMPerr/
I8hx7t4DLwReaJ0MpCbY0ZQO6REDvaojgtU2ORYWRrBXNvD8Xv0vwCRPy1F5dHvosTLYfjbPfJePDpD4j4c
49OwgUAJJk5sGnX7EVVYD1AeBlSrt6DmZc7GD1WbSVSHvUmD0W/
q9vlKd1aICssRreD6+TP9SWMbCzRYfN3GBF3Ga2+Xwynvp3h0KM9Gn08o1xVWr1BCJ6u2waRnTWGR51Hp/+
+h8f4gfAY44/WPy3BiPgrcB3SS//rUijVhMG3jbZs2YKFCxeq9bwQQuDi4oJFixbh44/
ld5zZ2dlwdHTEli1bMGGCZsFhdNuIUlspSstAUWIqRHbWEDvZI2jZmhf9X3hZaT8jGey7tkGPYxvLbdnkxz
zH4fp91N59m3l7wLZDc8TsOKaxXTZtm2LAnf0AgPQ7QbgwYCYkGdm6PUkV9Di2Ec/
+PYi4vaf0NidnLEKjxTMR/
PV6vcSrMBwHkb0NhkdfACcyQsiqjXj4+c9azSGytwYjFKAoIVWR6kyI3PnS+tcv4Df/
LQAAX1SMuMPncWPCh6qm0x2GQbt1y9Bg3iTDzE+h6JlasW2kLVFRUUhKSkLfvi8CyCwtLdGhQwfcvHlTY/
FCodRWxHY25YIcW3y9EPXfHoHIv/YiLzIORlbm8Jw4RJFJ8zKmnq7wnjUWkZv2Kr1IN/
lyHuy7tMalQbM1tokRcLDr1AoAUJSSjgv93oEkJ0+HZ6cey8beKIhLrNBDqSqwQiGCV67Ty1xgAKGVOXqd+
ktRb6bxktngjEUIWrpWvvWlAcUvtWx42VtGANxb8DUEJmKk33mEqH8Pgi8s1o/
tlcBwLEqyDfNaUig1Ta0RL0lJSQAAR0fHcscdHR0Vj1VGcXExiotffAHk5OQYxkAKxQBYNKiHVt8v1mhsu9
+XAQSI/GtvuTozAnNTtN+4Ep4TBuNky+Hy6ryahkfwMjQoTXmN2LRHLlwM4Iy1adcUxi6OSL/1UK/
zSjQUFBpBAJ85E2DdoqHiEMMwaLhwGupNHoaDLl2rHl/
DMrg9dzlAiN5jdV6FSHmY+3ioH0ih1EG0inlZsmSJPA1Sxc+TJ08MZWulrFq1CpaWloofd/
eqlTCnUGorrFCIDn9+jeFR59Fq9WI0WTIbHf/
9HqOSrqPexCHICY1EVlCYZkG6pZ6dNr9+DsvGPgCA+INnDZMqzDDouHmVYebWUwXhMh5//
yeK0jIqHBfb28BtZL+qLyAjIBJplYSLRvE9DAMjWyu4Duut8zoUSm1GK8/
LokWLMG3aNJVjvLy8dDLEyUne1yQ5ORnOzs6K48nJyWjZsqXS8z777DN89NGLhmY5OTlUwFBea0w9XSutM1
OUkq7ZBAzg3L8LGn08A059OysOSws1D4wv11ywNLtGmben8ZLZsGrqCwCwbOYrL+NfVdHBMDCysURJelbV5
nkVXobYPSfh++7kcocfr96EuH36i9XRFaGFGfpc/A8Zd4MR/
scuZD58UjGIujQwvOPf34Iz0r7dAoVSF9BKvNjb28Pe3t4ghtSvXx9OTk44f/
68Qqzk5OQgICBAZcaSSCSCSFT1brcUSl3H2NVR/SAAXXb+As/
xgyoct23bDDlhUcpTdV+i2/7fILQ0ByvgYNGkAe7MW47YXaUdkwmRCxmZDI0/
nYUW374ISG300XTcmv6Z2vlN67mCSHl5Z+NXYeSPF6dnVnxMD+SERZX7PXrHUQR+
+qNB1tIGRijAgHsHYO7jCZvWTeAzezzynsXhwZIfEX/
gjCK+xq5jC7T4ZiEce3WsYYspFMNhsJiX2NhYZGRkIDY2FjzPIzAwEADg4+MDMzMzAEDDhg2xatUqjBw5Eg
zDYOHChfjmm2/QoEE
D1K9fH0uXLoWLiwtGjBhhKDMplNcGiwb1YNepJdJvBylNqxZamsFteMVGfADQ4L3JiPrvkOpFGMDEzRnOA7
uDKy1FL5NI4DFmACRZuch5GgWBsRgO3duh0cczKnSirj91JNJuBSJi4+5KK+OKHGzBGYuQr6R3k4mnC/
zmvwXzhl64MnSualt1xMjqRZYDIUSeyVSNbQPk9VhkL7xTLAtOJET3Q+th/
krVZjMvd3TbswbFGVkoiE+CyMaqSt25KZS6gsHEy7Jly/Dvv/8qfm/
VSp7RcPHiRfTs2RMAEBYWhuzsFymZn3zyCfLz8zF79mxkZWWha9euOHXqFMTiin1jKBRKRVr/
8jnOdZ8sv85WktHT5tcvlPazsWvfHE2Xz0fwit+VL0CAgrhEHPbshYYfvA3PSUNwaeBsZIeEK8QIw3HIDom
AiZsTmnxeXmAwDIN2G1bAdWhveUfn+yHgjMVwH90fPnMn4tlfexH6w9+VCwWWhayoBH4fvI34Q+e0+bNohf
eMMYp/50fHv2j6WEUYjgXDcZCVSFQMYtD/
5m4knr6K5IsBAMPAqXdHeM8cq7I5psjGCiIbK73YSaHUBWh7AArlNSP15gPcfXcFMgNDFcdM3J3R8vuPUW/
iELXnxx06h+BvNyDzbrDqgQwDoYWZPONHiaen886fUW/
CYABAVkg4Mu+HgDUyglPfThDZWpcbyxeX4IBjZ7UNLbvuXQMTNyec6TRe7XPRFtv2zeEfsFfxe/
bjCBxvMrjK8xrZWsH33Ukw8XDB7VlfVj6IZVB/ygh02vK/Kq9HodRF6mSdFwqFoh/
sO7XCwAeHkBn0BPnRzyGys4Zdx5ZgVDUkfAn3EX3hPqIvZFIpUi7dxoV+0ysfSIhqocEyeLxqI2zaNkXA9M
/KdX9mhAL4zBqH1j9/pqipkh8dr1a4MEIBMu4Gw320P8wbeCI3Ilbj7RyG48CJjSAtKKw0uFhkZ4XuR/
8od8y0nis4EzH4AtXBzJbN/JAd/FRhi7GzA5p9NR/
1pgyHrLgEQgszxd9fml+AB4tXywsTcqwibdpz3CC037hSo+dCobzpUPFCobymWDdvCOvmDdUPVAIrECBq6+
FymUVaISPICgrD2U4TUJJZvmIvkUgR/
scuFCamotv+38CUNiZUCyFgRUZgGAZt1y3HpYEzQWQoL2BK08C9Z41D6tU7yI96DqGlGepPGQ6/
D6Yi71kcHq1ch+TzN+XPUyyC9zuj0WzFggqdkgUmxvCeMRbh63dU3puKZSGyscSAu/
vACgSQSaVghcLyRQaNy297N/
xgKupNHIKorYeR9ywORjaW8JwwWKM+QxQKRQ7dNqJQKEo52XYUMu+FVG2Ssi7NSuh3YxfsO7UCIQTH/
PzVelP6B+yFXfvmAICkczdwb+F38vTrUiwaeqH1z0vgMrCHSrNKsnIgyc2H2MFW4f2pdFx2Ls52m4ScxxHl
AqEZAQeG49DzxJ9w6t1J5VoUCkU9dNuIQqHoBSNL86pl2jCMSuHCCDhE/
XsQ9p1agWEYNPl8rtJUakbAwbZDC9i+1PTQqW9nDHp0FFkPn6DgeTKMne1h3apxhfYKlWFkZVEus0jpOEtz
9L+2E6E//4Pw9TtQnJoBRsDBfcwANFkyu1xFXgqFUj1Q8UKhUJTiMW4gki/e0u1kNR4XQF7CvjAxVfF7/
akjkfcsDsFfr1dsV5VlMVk2aYDuB36vIEwYhoF1y0awbtlINzs1QGhhhuZfLUCz5fPBFxSCFRmBFdCvTwql
pqCfPgqFopR6k4ci5Ns/
UJiQUiHmg+FYsGIRZBIpIJO9iIspFRf2XVsjOyRCZRVcRsDB5KXiegzDoPnKD+A5cQgiNu1B7tMoCC3M4TF
uIFyH9KxxwcAwDASmJjVqA4VCoTEvFApFDXnP4nBpyBzkhEaCEQgARh5wa+xsjx5H/
wBnLEboj5sRu+cEpAVFMG/gCd/
3JsNnzgQ8+uo3hP7wl9KieQDgf3svbNs1r8ZnRKFQaiPaXL+peKFQKGohMhmSzt1A0rkbILwMdp1bwW1Yb7
DC8hlChJBy2zpFqRk41XokCpNSK2YsMQw8Jw1Bl201X3qfQqHUPFS8UPFCodQaCuKTEDDrSySevqYI/
OVMxPBbMAXNv1lY41tBFAqldkCzjSgUSq3BxM0JvU7+hbyoOGQGPgErMoJDtzYQmpvVtGkUCqWOQsULhUKp
Fszqu8Osvrv6gRQKhaIGzeqFUygUCoVCodQSqHihUCgUCoVSp6DihUKhUCgUSp2CihcKhUKhUCh1CipeKBQ
KhUKh1CmoeKFQKBQKhVKnoOKFQqFQKBRKnYKKFwqFQqFQKHUKKl4oFAqFQqHUKV67CrtlrZpycnJq2BIKhU
KhUCiaUnbd1qTl4msnXnJzcwEA7u60DDmFQqFQKHWN3NxcWFpaqhzz2nWVlslkSEhIgLm5ORiGqWlzkJOTA
3d3d8TFxdEu17Uc+lrVLejrVbegr1fdoiZeL0IIcnNz4eLiApZVHdXy2nleWJaFm5tbTZtRAQsLC/
qBrSPQ16puQV+vugV9veoW1f16qfO4lEEDdikUCoVCodQpqHihUCgUCoVSp6DixcCIRCIsX74cIpGopk2hq
IG+VnUL+nrVLejrVbeo7a/
XaxewS6FQKBQK5fWGel4oFAqFQqHUKah4oVAoFAqFUqeg4oVCoVAoFEqdgooXCoVCoVAodQoqXvTMt99+i8
6dO8PExARWVlYanUMIwbJly+Ds7AxjY2P07dsX4eHhhjWUAgDIyMjA5MmTYWFhASsrK8yYMQN5eXkqz+nZs
ycYhin3M3fu3Gqy+M1i3bp1qFevHsRiMTp06IDbt2+rHL937140bNgQYrEYzZo1w4kTJ6rJUgqg3eu1ZcuW
Cp8jsVhcjda+uVy5cgVDhw6Fi4sLGIbBoUOH1J5z6dIltG7dGiKRCD4+PtiyZYvB7VQFFS96pqSkBGPHjsW
8efM0Pmf16tVYu3Yt/vjjDwQEBMDU1BT+/
v4oKioyoKUUAJg8eTJCQkJw9uxZHDt2DFeuXMHs2bPVnjdr1iwkJiYqflavXl0N1r5Z7N69Gx999BGWL1+O
+/fvo0WLFvD390dKSkql42/cuIGJEydixowZePDgAUaMGIERI0YgODi4mi1/M9H29QLk1Vtf/
hzFxMRUo8VvLvn5+WjRogXWrVun0fioqCgMHjwYvXr1QmBgIBYuXIiZM2fi9OnTBrZUBYRiEP755x9iaWmp
dpxMJiNOTk7khx9+UBzLysoiIpGI7Ny504AWUh4/fkwAkDt37iiOnTx5kjAMQ54/
f670vB49epAPPvigGix8s2nfvj157733FL/zPE9cXFzIqlWrKh0/
btw4Mnjw4HLHOnToQObMmWNQOylytH29NP2OpBgWAOTgwYMqx3zyySekSZMm5Y6NHz+e+Pv7G9Ay1VDPSw0
TFRWFpKQk9O3bV3HM0tISHTp0wM2bN2vQstefmzdvwsrKCm3btlUc69u3L1iWRUBAgMpzt2/
fDjs7OzRt2hSfffYZCgoKDG3uG0VJSQnu3btX7nPBsiz69u2r9HNx8+bNcuMBwN/
fn36OqgFdXi8AyMvLg6enJ9zd3TF8+HCEhIRUh7kULamNn63XrjFjXSMpKQkA4OjoWO64o6Oj4jGKYUhKSo
KDg0O5YwKBADY2Nir/9pMmTYKnpydcXFwQFBSETz/9FGFhYThw4IChTX5jSEtLA8/
zlX4unjx5Uuk5SUlJ9HNUQ+jyevn5+WHz5s1o3rw5srOz8eOPP6Jz584ICQmplc1132SUfbZycnJQWFgIY2
PjareJel40YMmSJRUCy179UfYBpVQ/hn69Zs+eDX9/fzRr1gyTJ0/Gf//
9h4MHDyIyMlKPz4JCeb3p1KkT3n77bbRs2RI9evTAgQMHYG9vj40bN9a0aZQ6APW8aMCiRYswbdo0lWO8vL
x0mtvJyQkAkJycDGdnZ8Xx5ORktGzZUqc533Q0fb2cnJwqBBNKpVJkZGQoXhdN6NChAwAgIiIC3t7eWttLq
YidnR04jkNycnK548nJyUpfGycnJ63GU/SHLq/
XqwiFQrRq1QoRERGGMJFSBZR9tiwsLGrE6wJQ8aIR9vb2sLe3N8jc9evXh5OTE86fP68QKzk5OQgICNAqY4
nyAk1fr06dOiErKwv37t1DmzZtAAAXLlyATCZTCBJNCAwMBIBy4pNSNYyMjNCmTRucP38eI0aMAADIZDKcP
38e8+fPr/
ScTp064fz581i4cKHi2NmzZ9GpU6dqsPjNRpfX61V4nsejR48waNAgA1pK0YVOnTpVKDtQ45+tGgsVfk2Ji
YkhDx48ICtWrCBmZmbkwYMH5MGDByQ3N1cxxs/Pjxw4cEDx+//+9z9iZWVFDh8+TIKCgsjw4cNJ/
fr1SWFhYU08hTeKAQMGkFatWpGAgABy7do10qBBAzJx4kTF4/
Hx8cTPz48EBAQQQgiJiIggK1euJHfv3iVRUVHk8OHDxMvLi3Tv3r2mnsJry65du4hIJCJbtmwhjx8/
JrNnzyZWVlYkKSmJEELIlClTyJIlSxTjr1+/
TgQCAfnxxx9JaGgoWb58OREKheTRo0c19RTeKLR9vVasWEFOnz5NIiMjyb1798iECROIWCwmISEhNfUU3hh
yc3MV1yYA5OeffyYPHjwgMTExhBBClixZQqZMmaIY/
+zZM2JiYkIWL15MQkNDybp16wjHceTUqVM19RQIFS96ZurUqQRAhZ+LFy8qxgAg//
zzj+J3mUxGli5dShwdHYlIJCJ9+vQhYWFh1W/
8G0h6ejqZOHEiMTMzIxYWFmT69OnlhGZUVFS51y82NpZ0796d2NjYEJFIRHx8fMjixYtJdnZ2DT2D15vffv
uNeHh4ECMjI9K+fXty69YtxWM9evQgU6dOLTd+z549xNfXlxgZGZEmTZqQ48ePV7PFbzbavF4LFy5UjHV0d
CSDBg0i9+/
frwGr3zwuXrxY6XWq7PWZOnUq6dGjR4VzWrZsSYyMjIiXl1e5a1hNwBBCSI24fCgUCoVCoVB0gGYbUSgUCo
VCqVNQ8UKhUCgUCqVOQcULhUKhUCiUOgUVLxQKhUKhUOoUVLxQKBQKhUKpU1DxQqFQKBQKpU5BxQuFQqFQK
JQ6BRUvFAqFQqFQ6hRUvFAoFAqFQqlTUPFCoVAoFAqlTkHFC4VCoVAolDoFFS8UCoVCoVDqFP8HGHy3EG5f
1LYAAAAASUVORK5CYII=",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
 "# Visualize with a plot\n",
"import matplotlib.pyplot as plt\n",
"plt.scatter(x=X[:, 0], \n",
" y=X[:, 1], \n",
" c=y, \n",
" cmap=plt.cm.RdYlBu);"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "h0e1oR27HC76"
},
"source": [
"Alrighty, looks like we've got a problem to solve.\n",
"\n",
"Let's find out how we could build a PyTorch neural network to classify dots
into red (0) or blue (1).\n",
"\n",
"> **Note:** This dataset is often what's considered a **toy problem** (a
problem that's used to try and test things out on) in machine learning. \n",
"> \n",
"> But it represents the major key of classification, you have some kind of
data represented as numerical values and you'd like to build a model that's able to
classify it, in our case, separate it into red or blue dots."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Ny6_J7F4HC76"
},
"source": [
"### 1.1 Input and output shapes\n",
"\n",
"One of the most common errors in deep learning is shape errors.\n",
"\n",
"Mismatching the shapes of tensors and tensor operations will result in errors
in your models.\n",
"\n",
"We're going to see plenty of these throughout the course.\n",
"\n",
"And there's no surefire way to make sure they won't happen, they will.\n",
"\n",
"What you can do instead is continually familiarize yourself with the shape of
the data you're working with.\n",
"\n",
"I like referring to it as input and output shapes.\n",
"\n",
"Ask yourself:\n",
"\n",
"\"What shapes are my inputs and what shapes are my outputs?\"\n",
"\n",
"Let's find out."
]
},
{
"cell_type": "code",
"execution_count": 6,
 "metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "r0h--vKdHC77",
"outputId": "16e65bb5-83e1-49c7-af5e-90ecede4eeae"
},
"outputs": [
{
"data": {
"text/plain": [
"((1000, 2), (1000,))"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Check the shapes of our features and labels\n",
"X.shape, y.shape"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "PW7zolShbfDg"
},
"source": [
"Looks like we've got a match on the first dimension of each.\n",
"\n",
"There's 1000 `X` and 1000 `y`. \n",
"\n",
"But what's the second dimension on `X`?\n",
"\n",
"It often helps to view the values and shapes of a single sample (features and
labels).\n",
"\n",
"Doing so will help you understand what input and output shapes you'd be
expecting from your model."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "k-L5zobVHC78",
"outputId": "b3a96ca8-45f1-47d1-a98b-c2a7be79c0d5"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Values for one sample of X: [0.75424625 0.23148074] and the same for y: 1\
n",
"Shapes for one sample of X: (2,) and the same for y: ()\n"
]
}
],
"source": [
"# View the first example of features and labels\n",
"X_sample = X[0]\n",
"y_sample = y[0]\n",
"print(f\"Values for one sample of X: {X_sample} and the same for y:
{y_sample}\")\n",
"print(f\"Shapes for one sample of X: {X_sample.shape} and the same for y:
{y_sample.shape}\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Vn692XaRaifl"
},
"source": [
"This tells us the second dimension for `X` means it has two features (vector)
where as `y` has a single feature (scalar).\n",
"\n",
"We have two inputs for one output."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "eLyDPN6ZR_ho"
},
"source": [
"### 1.2 Turn data into tensors and create train and test splits\n",
"\n",
"We've investigated the input and output shapes of our data, now let's prepare
it for being used with PyTorch and for modelling.\n",
"\n",
"Specifically, we'll need to:\n",
"1. Turn our data into tensors (right now our data is in NumPy arrays and
PyTorch prefers to work with PyTorch tensors).\n",
"2. Split our data into training and test sets (we'll train a model on the
training set to learn the patterns between `X` and `y` and then evaluate those
learned patterns on the test dataset)."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Z2gcR31aHC78",
"outputId": "cd4e10c1-c358-4b74-81e0-bab7610197cc"
},
"outputs": [
{
"data": {
 "text/plain": [
"(tensor([[ 0.7542, 0.2315],\n",
" [-0.7562, 0.1533],\n",
" [-0.8154, 0.1733],\n",
" [-0.3937, 0.6929],\n",
" [ 0.4422, -0.8967]]),\n",
" tensor([1., 1., 1., 1., 0.]))"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Turn data into tensors\n",
"# Otherwise this causes issues with computations later on\n",
"import torch\n",
"X = torch.from_numpy(X).type(torch.float)\n",
"y = torch.from_numpy(y).type(torch.float)\n",
"\n",
"# View the first five samples\n",
"X[:5], y[:5]"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "r9XNJv8lfmRG"
},
"source": [
"Now our data is in tensor format, let's split it into training and test sets.\
n",
"\n",
"To do so, let's use the helpful function
[`train_test_split()`](https://scikit-learn.org/stable/modules/generated/
sklearn.model_selection.train_test_split.html) from Scikit-Learn.\n",
"\n",
"We'll use `test_size=0.2` (80% training, 20% testing) and because the split
happens randomly across the data, let's use `random_state=42` so the split is
reproducible."
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "DW6PU82BHC79",
"outputId": "a2d3f3df-701e-44ef-a506-fd31d5443e90"
},
"outputs": [
{
"data": {
"text/plain": [
"(800, 200, 800, 200)"
]
 },
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Split data into train and test sets\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(X, \n",
" y, \n",
" test_size=0.2, # 20% test,
80% train\n",
" random_state=42) # make
the random split reproducible\n",
"\n",
"len(X_train), len(X_test), len(y_train), len(y_test)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "t-wYDWy9gSRc"
},
"source": [
"Nice! Looks like we've now got 800 training samples and 200 testing samples."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "iCyQ93VTHC79"
},
"source": [
"## 2. Building a model\n",
"\n",
"We've got some data ready, now it's time to build a model.\n",
"\n",
"We'll break it down into a few parts.\n",
"\n",
"1. Setting up device agnostic code (so our model can run on CPU or GPU if it's
available).\n",
"2. Constructing a model by subclassing `nn.Module`.\n",
"3. Defining a loss function and optimizer.\n",
"4. Creating a training loop (this'll be in the next section).\n",
"\n",
"The good news is we've been through all of the above steps before in notebook
01.\n",
"\n",
"Except now we'll be adjusting them so they work with a classification
dataset.\n",
"\n",
"Let's start by importing PyTorch and `torch.nn` as well as setting up device
agnostic code."
]
},
{
"cell_type": "code",
 "execution_count": 10,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 36
},
"id": "2itMTezPRnVR",
"outputId": "507bf4a3-b5ae-4943-aa21-4eb181b0d741"
},
"outputs": [
{
"data": {
"text/plain": [
"'cuda'"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Standard PyTorch imports\n",
"import torch\n",
"from torch import nn\n",
"\n",
"# Make device agnostic code\n",
"device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
"device"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "p1Fil1v04nXr"
},
"source": [
"Excellent, now `device` is setup, we can use it for any data or models we
create and PyTorch will handle it on the CPU (default) or GPU if it's available.\
n",
"\n",
"How about we create a model?\n",
"\n",
"We'll want a model capable of handling our `X` data as inputs and producing
something in the shape of our `y` data as outputs.\n",
"\n",
"In other words, given `X` (features) we want our model to predict `y`
(label).\n",
"\n",
"This setup where you have features and labels is referred to as **supervised
learning**. Because your data is telling your model what the outputs should be
given a certain input.\n",
"\n",
"To create such a model it'll need to handle the input and output shapes of `X`
and `y`.\n",
"\n",
"Remember how I said input and output shapes are important? Here we'll see
why.\n",
"\n",
 "Let's create a model class that:\n",
"1. Subclasses `nn.Module` (almost all PyTorch models are subclasses of
`nn.Module`).\n",
"2. Creates 2 `nn.Linear` layers in the constructor capable of handling the
input and output shapes of `X` and `y`.\n",
"3. Defines a `forward()` method containing the forward pass computation of the
model.\n",
"4. Instantiates the model class and sends it to the target `device`. "
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "C_EsAE3VHC7-",
"outputId": "d9c976ea-e23f-4993-c847-a15b0bf7b0b5"
},
"outputs": [
{
"data": {
"text/plain": [
"CircleModelV0(\n",
" (layer_1): Linear(in_features=2, out_features=5, bias=True)\n",
" (layer_2): Linear(in_features=5, out_features=1, bias=True)\n",
")"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 1. Construct a model class that subclasses nn.Module\n",
"class CircleModelV0(nn.Module):\n",
" def __init__(self):\n",
" super().__init__()\n",
" # 2. Create 2 nn.Linear layers capable of handling X and y input and
output shapes\n",
" self.layer_1 = nn.Linear(in_features=2, out_features=5) # takes in 2
features (X), produces 5 features\n",
" self.layer_2 = nn.Linear(in_features=5, out_features=1) # takes in 5
features, produces 1 feature (y)\n",
" \n",
" # 3. Define a forward method containing the forward pass computation\n",
" def forward(self, x):\n",
" # Return the output of layer_2, a single feature, the same shape as y\
n",
" return self.layer_2(self.layer_1(x)) # computation goes through
layer_1 first then the output of layer_1 goes through layer_2\n",
"\n",
"# 4. Create an instance of the model and send it to target device\n",
"model_0 = CircleModelV0().to(device)\n",
"model_0"
]
},
 {
"cell_type": "markdown",
"metadata": {
"id": "TtdkMniZ7KyK"
},
"source": [
"What's going on here?\n",
"\n",
"We've seen a few of these steps before.\n",
"\n",
"The only major change is what's happening between `self.layer_1` and
`self.layer_2`.\n",
"\n",
"`self.layer_1` takes 2 input features `in_features=2` and produces 5 output
features `out_features=5`.\n",
"\n",
"This is known as having 5 **hidden units** or **neurons**.\n",
"\n",
"This layer turns the input data from having 2 features to 5 features.\n",
"\n",
"Why do this?\n",
"\n",
"This allows the model to learn patterns from 5 numbers rather than just 2
numbers, *potentially* leading to better outputs.\n",
"\n",
"I say potentially because sometimes it doesn't work.\n",
"\n",
"The number of hidden units you can use in neural network layers is a
**hyperparameter** (a value you can set yourself) and there's no set in stone value
you have to use.\n",
"\n",
"Generally more is better but there's also such a thing as too much. The amount
you choose will depend on your model type and dataset you're working with. \n",
"\n",
"Since our dataset is small and simple, we'll keep it small.\n",
"\n",
"The only rule with hidden units is that the next layer, in our case,
`self.layer_2` has to take the same `in_features` as the previous layer
`out_features`.\n",
"\n",
"That's why `self.layer_2` has `in_features=5`, it takes the `out_features=5`
from `self.layer_1` and performs a linear computation on them, turning them into
`out_features=1` (the same shape as `y`).\n",
"\n",
"![A visual example of what a classification neural network with linear
activation looks like on the tensorflow
playground](https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/
main/images/02-tensorflow-playground-linear-activation.png)\n",
"*A visual example of what a similar classification neural network to the one
we've just built looks like. Try creating one of your own on the [TensorFlow
Playground website](https://playground.tensorflow.org/).*\n",
"\n",
"You can also do the same as above using
[`nn.Sequential`](https://pytorch.org/docs/stable/generated/torch.nn.Sequential.htm
l).\n",
"\n",
"`nn.Sequential` performs a forward pass computation of the input data through
the layers in the order they appear."
]
 },
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "H7I8GyLjHC7_",
"outputId": "def65504-863a-4361-816e-909dbfa4d624"
},
"outputs": [
{
"data": {
"text/plain": [
"Sequential(\n",
" (0): Linear(in_features=2, out_features=5, bias=True)\n",
" (1): Linear(in_features=5, out_features=1, bias=True)\n",
")"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Replicate CircleModelV0 with nn.Sequential\n",
"model_0 = nn.Sequential(\n",
" nn.Linear(in_features=2, out_features=5),\n",
" nn.Linear(in_features=5, out_features=1)\n",
").to(device)\n",
"\n",
"model_0"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "MiRHq9mxFIf-"
},
"source": [
"Woah, that looks much simpler than subclassing `nn.Module`, why not just
always use `nn.Sequential`?\n",
"\n",
"`nn.Sequential` is fantastic for straight-forward computations, however, as
the namespace says, it *always* runs in sequential order.\n",
"\n",
"So if you'd like something else to happen (rather than just straight-forward
sequential computation) you'll want to define your own custom `nn.Module`
subclass.\n",
"\n",
"Now we've got a model, let's see what happens when we pass some data through
it."
]
},
{
"cell_type": "code",
"execution_count": 13,
 "metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Tt339-_CC8sz",
"outputId": "a4014167-4181-434e-ab75-905094229b3a"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Length of predictions: 200, Shape: torch.Size([200, 1])\n",
"Length of test samples: 200, Shape: torch.Size([200])\n",
"\n",
"First 10 predictions:\n",
"tensor([[0.0555],\n",
" [0.0169],\n",
" [0.2254],\n",
" [0.0071],\n",
" [0.3345],\n",
" [0.3101],\n",
" [0.1151],\n",
" [0.1840],\n",
" [0.2205],\n",
" [0.0156]], device='cuda:0', grad_fn=<SliceBackward0>)\n",
"\n",
"First 10 test labels:\n",
"tensor([1., 0., 1., 0., 1., 1., 0., 0., 1., 0.])\n"
]
}
],
"source": [
"# Make predictions with the model\n",
"untrained_preds = model_0(X_test.to(device))\n",
"print(f\"Length of predictions: {len(untrained_preds)}, Shape:
{untrained_preds.shape}\")\n",
"print(f\"Length of test samples: {len(y_test)}, Shape: {y_test.shape}\")\n",
"print(f\"\\nFirst 10 predictions:\\n{untrained_preds[:10]}\")\n",
"print(f\"\\nFirst 10 test labels:\\n{y_test[:10]}\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "q7v8TVnqGMZh"
},
"source": [
"Hmm, it seems there are the same amount of predictions as there are test
labels but the predictions don't look like they're in the same form or shape as the
test labels.\n",
"\n",
"We've got a couple steps we can do to fix this, we'll see these later on."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "8aoQn39pHC7_"
 },
"source": [
"### 2.1 Setup loss function and optimizer\n",
"\n",
"We've setup a loss (also called a criterion or cost function) and optimizer
before in [notebook 01](https://www.learnpytorch.io/01_pytorch_workflow/#creating-
a-loss-function-and-optimizer-in-pytorch).\n",
"\n",
"But different problem types require different loss functions. \n",
"\n",
"For example, for a regression problem (predicting a number) you might use mean
absolute error (MAE) loss.\n",
"\n",
"And for a binary classification problem (like ours), you'll often use [binary
cross entropy](https://towardsdatascience.com/understanding-binary-cross-entropy-
log-loss-a-visual-explanation-a3ac6025181a) as the loss function.\n",
"\n",
"However, the same optimizer function can often be used across different
problem spaces.\n",
"\n",
"For example, the stochastic gradient descent optimizer (SGD,
`torch.optim.SGD()`) can be used for a range of problems, and the same applies to
the Adam optimizer (`torch.optim.Adam()`). \n",
"\n",
"| Loss function/Optimizer | Problem type | PyTorch Code |\n",
"| ----- | ----- | ----- |\n",
"| Stochastic Gradient Descent (SGD) optimizer | Classification, regression,
many others. |
[`torch.optim.SGD()`](https://pytorch.org/docs/stable/generated/torch.optim.SGD.htm
l) |\n",
"| Adam Optimizer | Classification, regression, many others. |
[`torch.optim.Adam()`](https://pytorch.org/docs/stable/generated/torch.optim.Adam.h
tml) |\n",
"| Binary cross entropy loss | Binary classification |
[`torch.nn.BCELossWithLogits`](https://pytorch.org/docs/stable/generated/
torch.nn.BCEWithLogitsLoss.html) or
[`torch.nn.BCELoss`](https://pytorch.org/docs/stable/generated/torch.nn.BCELoss.htm
l) |\n",
"| Cross entropy loss | Multi-class classification |
[`torch.nn.CrossEntropyLoss`](https://pytorch.org/docs/stable/generated/
torch.nn.CrossEntropyLoss.html) |\n",
"| Mean absolute error (MAE) or L1 Loss | Regression | [`torch.nn.L1Loss`]
(https://pytorch.org/docs/stable/generated/torch.nn.L1Loss.html) | \n",
"| Mean squared error (MSE) or L2 Loss | Regression | [`torch.nn.MSELoss`]
(https://pytorch.org/docs/stable/generated/torch.nn.MSELoss.html#torch.nn.MSELoss)
| \n",
"\n",
"*Table of various loss functions and optimizers, there are more but these are
some common ones you'll see.*\n",
"\n",
"Since we're working with a binary classification problem, let's use a binary
cross entropy loss function.\n",
"\n",
"> **Note:** Recall a **loss function** is what measures how *wrong* your model
predictions are, the higher the loss, the worse your model.\n",
">\n",
"> Also, PyTorch documentation often refers to loss functions as \"loss
criterion\" or \"criterion\", these are all different ways of describing the same
thing.\n",
 "\n",
"PyTorch has two binary cross entropy implementations:\n",
"1.
[`torch.nn.BCELoss()`](https://pytorch.org/docs/stable/generated/torch.nn.BCELoss.h
tml) - Creates a loss function that measures the binary cross entropy between the
target (label) and input (features).\n",
"2.
[`torch.nn.BCEWithLogitsLoss()`](https://pytorch.org/docs/stable/generated/
torch.nn.BCEWithLogitsLoss.html) - This is the same as above except it has a
sigmoid layer
([`nn.Sigmoid`](https://pytorch.org/docs/stable/generated/torch.nn.Sigmoid.html))
built-in (we'll see what this means soon).\n",
"\n",
"Which one should you use? \n",
"\n",
"The [documentation for
`torch.nn.BCEWithLogitsLoss()`](https://pytorch.org/docs/stable/generated/
torch.nn.BCEWithLogitsLoss.html) states that it's more numerically stable than
using `torch.nn.BCELoss()` after a `nn.Sigmoid` layer. \n",
"\n",
"So generally, implementation 2 is a better option. However for advanced usage,
you may want to separate the combination of `nn.Sigmoid` and `torch.nn.BCELoss()`
but that is beyond the scope of this notebook.\n",
"\n",
"Knowing this, let's create a loss function and an optimizer. \n",
"\n",
"For the optimizer we'll use `torch.optim.SGD()` to optimize the model
parameters with learning rate 0.1.\n",
"\n",
"> **Note:** There's a [discussion on the PyTorch forums about the use of
`nn.BCELoss` vs. `nn.BCEWithLogitsLoss`](https://discuss.pytorch.org/t/bceloss-vs-
bcewithlogitsloss/33586/4). It can be confusing at first but as with many things,
it becomes easier with practice."
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"id": "DjpQsdOZHC7_"
},
"outputs": [],
"source": [
"# Create a loss function\n",
"# loss_fn = nn.BCELoss() # BCELoss = no sigmoid built-in\n",
"loss_fn = nn.BCEWithLogitsLoss() # BCEWithLogitsLoss = sigmoid built-in\n",
"\n",
"# Create an optimizer\n",
"optimizer = torch.optim.SGD(params=model_0.parameters(), \n",
" lr=0.1)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "RKmi3fp9wYnV"
},
"source": [
"Now let's also create an **evaluation metric**.\n",
 "\n",
"An evaluation metric can be used to offer another perspective on how your
model is going.\n",
"\n",
"If a loss function measures how *wrong* your model is, I like to think of
evaluation metrics as measuring how *right* it is.\n",
"\n",
"Of course, you could argue both of these are doing the same thing but
evaluation metrics offer a different perspective.\n",
"\n",
"After all, when evaluating your models it's good to look at things from
multiple points of view.\n",
"\n",
"There are several evaluation metrics that can be used for classification
problems but let's start out with **accuracy**.\n",
"\n",
"Accuracy can be measured by dividing the total number of correct predictions
over the total number of predictions.\n",
"\n",
"For example, a model that makes 99 correct predictions out of 100 will have an
accuracy of 99%.\n",
"\n",
"Let's write a function to do so.\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"id": "RcaZQR0mHC7_"
},
"outputs": [],
"source": [
"# Calculate accuracy (a classification metric)\n",
"def accuracy_fn(y_true, y_pred):\n",
" correct = torch.eq(y_true, y_pred).sum().item() # torch.eq() calculates
where two tensors are equal\n",
" acc = (correct / len(y_pred)) * 100 \n",
" return acc"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "OuplloDPxviL"
},
"source": [
"Excellent! We can now use this function whilst training our model to measure
it's performance alongside the loss."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "4UpJKZ8PHC8A"
},
"source": [
"## 3. Train model\n",
 "\n",
"Okay, now we've got a loss function and optimizer ready to go, let's train a
model.\n",
"\n",
"Do you remember the steps in a PyTorch training loop?\n",
"\n",
"If not, here's a reminder.\n",
"\n",
"Steps in training:\n",
"\n",
"<details>\n",
" <summary>PyTorch training loop steps</summary>\n",
" <ol>\n",
" <li><b>Forward pass</b> - The model goes through all of the training
data once, performing its\n",
" <code>forward()</code> function\n",
" calculations (<code>model(x_train)</code>).\n",
" </li>\n",
" <li><b>Calculate the loss</b> - The model's outputs (predictions) are
compared to the ground truth and evaluated\n",
" to see how\n",
" wrong they are (<code>loss = loss_fn(y_pred,
y_train</code>).</li>\n",
" <li><b>Zero gradients</b> - The optimizers gradients are set to zero
(they are accumulated by default) so they\n",
" can be\n",
" recalculated for the specific training step
(<code>optimizer.zero_grad()</code>).</li>\n",
" <li><b>Perform backpropagation on the loss</b> - Computes the gradient
of the loss with respect for every model\n",
" parameter to\n",
" be updated (each parameter\n",
" with <code>requires_grad=True</code>). This is known as
<b>backpropagation</b>, hence \"backwards\"\n",
" (<code>loss.backward()</code>).</li>\n",
" <li><b>Step the optimizer (gradient descent)</b> - Update the
parameters with <code>requires_grad=True</code>\n",
" with respect to the loss\n",
" gradients in order to improve them
(<code>optimizer.step()</code>).</li>\n",
" </ol>\n",
"</details>\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "NMeDqPpsnst6"
},
"source": [
"### 3.1 Going from raw model outputs to predicted labels (logits -> prediction
probabilities -> prediction labels)\n",
"\n",
"Before the training loop steps, let's see what comes out of our model during
the forward pass (the forward pass is defined by the `forward()` method).\n",
"\n",
"To do so, let's pass the model some data."
]
 },
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "e5stsbDl0zKl",
"outputId": "829a0842-0a37-455a-b058-3e547200f836"
},
"outputs": [
{
"data": {
"text/plain": [
"tensor([[0.0555],\n",
" [0.0169],\n",
" [0.2254],\n",
" [0.0071],\n",
" [0.3345]], device='cuda:0', grad_fn=<SliceBackward0>)"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# View the frist 5 outputs of the forward pass on the test data\n",
"y_logits = model_0(X_test.to(device))[:5]\n",
"y_logits"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "b1sNl8D8fWXm"
},
"source": [
"Since our model hasn't been trained, these outputs are basically random.\n",
"\n",
"But *what* are they?\n",
"\n",
"They're the output of our `forward()` method.\n",
"\n",
"Which implements two layers of `nn.Linear()` which internally calls the
following equation:\n",
"\n",
"$$\n",
"\\mathbf{y} = x \\cdot \\mathbf{Weights}^T + \\mathbf{bias}\n",
"$$\n",
"\n",
"The *raw outputs* (unmodified) of this equation ($y$) and in turn, the raw
outputs of our model are often referred to as
[**logits**](https://datascience.stackexchange.com/a/31045).\n",
"\n",
"That's what our model is outputing above when it takes in the input data ($x$
in the equation or `X_test` in the code), logits.\n",
"\n",
 "However, these numbers are hard to interpret.\n",
"\n",
"We'd like some numbers that are comparable to our truth labels.\n",
"\n",
"To get our model's raw outputs (logits) into such a form, we can use the
[sigmoid activation
function](https://pytorch.org/docs/stable/generated/torch.sigmoid.html).\n",
"\n",
"Let's try it out.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "QGC7UmBi0s6E",
"outputId": "3564ee3b-e34f-40a3-a40a-b9c9b948da04"
},
"outputs": [
{
"data": {
"text/plain": [
"tensor([[0.5139],\n",
" [0.5042],\n",
" [0.5561],\n",
" [0.5018],\n",
" [0.5829]], device='cuda:0', grad_fn=<SigmoidBackward0>)"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Use sigmoid on model logits\n",
"y_pred_probs = torch.sigmoid(y_logits)\n",
"y_pred_probs"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HxmWz_GVjZoB"
},
"source": [
"Okay, it seems like the outputs now have some kind of consistency (even though
they're still random).\n",
"\n",
"They're now in the form of **prediction probabilities** (I usually refer to
these as `y_pred_probs`), in other words, the values are now how much the model
thinks the data point belongs to one class or another.\n",
"\n",
"In our case, since we're dealing with binary classification, our ideal outputs
are 0 or 1.\n",
"\n",
 "So these values can be viewed as a decision boundary.\n",
"\n",
"The closer to 0, the more the model thinks the sample belongs to class 0, the
closer to 1, the more the model thinks the sample belongs to class 1.\n",
"\n",
"More specificially:\n",
"* If `y_pred_probs` >= 0.5, `y=1` (class 1)\n",
"* If `y_pred_probs` < 0.5, `y=0` (class 0)\n",
"\n",
"To turn our prediction probabilities into prediction labels, we can round the
outputs of the sigmoid activation function."
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "naZxlTTwlMwX",
"outputId": "6134e47d-bbb2-46c3-e2ec-b4f42d517e39"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"tensor([True, True, True, True, True], device='cuda:0')\n"
]
},
{
"data": {
"text/plain": [
"tensor([1., 1., 1., 1., 1.], device='cuda:0', grad_fn=<SqueezeBackward0>)"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Find the predicted labels (round the prediction probabilities)\n",
"y_preds = torch.round(y_pred_probs)\n",
"\n",
"# In full\n",
"y_pred_labels = torch.round(torch.sigmoid(model_0(X_test.to(device))[:5]))\n",
"\n",
"# Check for equality\n",
"print(torch.eq(y_preds.squeeze(), y_pred_labels.squeeze()))\n",
"\n",
"# Get rid of extra dimension\n",
"y_preds.squeeze()"
]
},
{
"cell_type": "markdown",
"metadata": {
 "id": "5cMsgFWWmPLU"
},
"source": [
"Excellent! Now it looks like our model's predictions are in the same form as
our truth labels (`y_test`)."
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "MaQ0CN4ZmU1W",
"outputId": "6b1cd7b4-f1d0-49b5-a8c3-338cf75c6cb0"
},
"outputs": [
{
"data": {
"text/plain": [
"tensor([1., 0., 1., 0., 1.])"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"y_test[:5]"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "NXqUulG3maPH"
},
"source": [
"This means we'll be able to compare our model's predictions to the test labels
to see how well it's performing. \n",
"\n",
"To recap, we converted our model's raw outputs (logits) to prediction
probabilities using a sigmoid activation function.\n",
"\n",
"And then converted the prediction probabilities to prediction labels by
rounding them.\n",
"\n",
"> **Note:** The use of the sigmoid activation function is often only for
binary classification logits. For multi-class classification, we'll be looking at
using the [softmax activation
function](https://pytorch.org/docs/stable/generated/torch.nn.Softmax.html) (this
will come later on).\n",
">\n",
"> And the use of the sigmoid activation function is not required when passing
our model's raw outputs to the `nn.BCEWithLogitsLoss` (the \"logits\" in logits
loss is because it works on the model's raw logits output), this is because it has
a sigmoid function built-in."
]
 },
{
"cell_type": "markdown",
"metadata": {
"id": "Va7gg8yxn6Sg"
},
"source": [
"### 3.2 Building a training and testing loop\n",
"\n",
"Alright, we've discussed how to take our raw model outputs and convert them to
prediction labels, now let's build a training loop.\n",
"\n",
"Let's start by training for 100 epochs and outputing the model's progress
every 10 epochs. "
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "DFABVGo2HC8A",
"outputId": "e0341074-b603-41d5-a389-c401b4934d73"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch: 0 | Loss: 0.70034, Accuracy: 50.00% | Test loss: 0.69484, Test acc:
52.50%\n",
"Epoch: 10 | Loss: 0.69718, Accuracy: 53.75% | Test loss: 0.69242, Test acc:
54.50%\n",
"Epoch: 20 | Loss: 0.69590, Accuracy: 51.12% | Test loss: 0.69161, Test acc:
53.50%\n",
"Epoch: 30 | Loss: 0.69530, Accuracy: 50.62% | Test loss: 0.69136, Test acc:
53.00%\n",
"Epoch: 40 | Loss: 0.69497, Accuracy: 49.75% | Test loss: 0.69131, Test acc:
53.50%\n",
"Epoch: 50 | Loss: 0.69474, Accuracy: 50.12% | Test loss: 0.69134, Test acc:
53.50%\n",
"Epoch: 60 | Loss: 0.69457, Accuracy: 49.88% | Test loss: 0.69139, Test acc:
53.50%\n",
"Epoch: 70 | Loss: 0.69442, Accuracy: 49.62% | Test loss: 0.69146, Test acc:
54.00%\n",
"Epoch: 80 | Loss: 0.69430, Accuracy: 49.62% | Test loss: 0.69153, Test acc:
54.50%\n",
"Epoch: 90 | Loss: 0.69418, Accuracy: 49.62% | Test loss: 0.69161, Test acc:
54.50%\n"
]
}
],
"source": [
"torch.manual_seed(42)\n",
"\n",
"# Set the number of epochs\n",
"epochs = 100\n",
 "\n",
"# Put data to target device\n",
"X_train, y_train = X_train.to(device), y_train.to(device)\n",
"X_test, y_test = X_test.to(device), y_test.to(device)\n",
"\n",
"# Build training and evaluation loop\n",
"for epoch in range(epochs):\n",
" ### Training\n",
" model_0.train()\n",
"\n",
" # 1. Forward pass (model outputs raw logits)\n",
" y_logits = model_0(X_train).squeeze() # squeeze to remove extra `1`
dimensions, this won't work unless model and data are on same device \n",
" y_pred = torch.round(torch.sigmoid(y_logits)) # turn logits -> pred probs
-> pred labls\n",
" \n",
" # 2. Calculate loss/accuracy\n",
" # loss = loss_fn(torch.sigmoid(y_logits), # Using nn.BCELoss you need
torch.sigmoid()\n",
" # y_train) \n",
" loss = loss_fn(y_logits, # Using nn.BCEWithLogitsLoss works with raw
logits\n",
" y_train) \n",
" acc = accuracy_fn(y_true=y_train, \n",
" y_pred=y_pred) \n",
"\n",
" # 3. Optimizer zero grad\n",
" optimizer.zero_grad()\n",
"\n",
" # 4. Loss backwards\n",
" loss.backward()\n",
"\n",
" # 5. Optimizer step\n",
" optimizer.step()\n",
"\n",
" ### Testing\n",
" model_0.eval()\n",
" with torch.inference_mode():\n",
" # 1. Forward pass\n",
" test_logits = model_0(X_test).squeeze() \n",
" test_pred = torch.round(torch.sigmoid(test_logits))\n",
" # 2. Caculate loss/accuracy\n",
" test_loss = loss_fn(test_logits,\n",
" y_test)\n",
" test_acc = accuracy_fn(y_true=y_test,\n",
" y_pred=test_pred)\n",
"\n",
" # Print out what's happening every 10 epochs\n",
" if epoch % 10 == 0:\n",
" print(f\"Epoch: {epoch} | Loss: {loss:.5f}, Accuracy: {acc:.2f}% |
Test loss: {test_loss:.5f}, Test acc: {test_acc:.2f}%\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "It1Xy_f5perA"
},
"source": [
 "Hmm, what do you notice about the performance of our model?\n",
"\n",
"It looks like it went through the training and testing steps fine but the
results don't seem to have moved too much.\n",
"\n",
"The accuracy barely moves above 50% on each data split.\n",
"\n",
"And because we're working with a balanced binary classification problem, it
means our model is performing as good as random guessing (with 500 samples of class
0 and class 1 a model predicting class 1 every single time would achieve 50%
accuracy)."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "WCeyddo-HC8A"
},
"source": [
"## 4. Make predictions and evaluate the model\n",
"\n",
"From the metrics it looks like our model is random guessing.\n",
"\n",
"How could we investigate this further?\n",
"\n",
"I've got an idea.\n",
"\n",
"The data explorer's motto!\n",
"\n",
"\"Visualize, visualize, visualize!\"\n",
"\n",
"Let's make a plot of our model's predictions, the data it's trying to predict
on and the decision boundary it's creating for whether something is class 0 or
class 1.\n",
"\n",
"To do so, we'll write some code to download and import the
[`helper_functions.py`
script](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/
helper_functions.py) from the [Learn PyTorch for Deep Learning
repo](https://github.com/mrdbourke/pytorch-deep-learning).\n",
"\n",
"It contains a helpful function called `plot_decision_boundary()` which creates
a NumPy meshgrid to visually plot the different points where our model is
predicting certain classes.\n",
"\n",
"We'll also import `plot_predictions()` which we wrote in notebook 01 to use
later."
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "QakJVGI8t2gB",
"outputId": "4f63a8a3-5eae-49fb-e17e-df6c5721ab5a"
},
 "outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"helper_functions.py already exists, skipping download\n"
]
}
],
"source": [
"import requests\n",
"from pathlib import Path \n",
"\n",
"# Download helper functions from Learn PyTorch repo (if not already
downloaded)\n",
"if Path(\"helper_functions.py\").is_file():\n",
" print(\"helper_functions.py already exists, skipping download\")\n",
"else:\n",
" print(\"Downloading helper_functions.py\")\n",
" request =
requests.get(\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/
main/helper_functions.py\")\n",
" with open(\"helper_functions.py\", \"wb\") as f:\n",
" f.write(request.content)\n",
"\n",
"from helper_functions import plot_predictions, plot_decision_boundary"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 390
},
"id": "bEbDUTKjHC8B",
"outputId": "aa344fe8-0207-43df-f0e9-61b9302459a5"
},
"outputs": [
{
"data": {
"image/png":
"iVBORw0KGgoAAAANSUhEUgAAA+EAAAIQCAYAAADuAG/uAAAAP3RFWHRTb2Z0d2FyZQBNYXRwbG90bGliIH
ZlcnNpb24zLjkuMS5wb3N0MSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8kixA/
AAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdd5xkV3kn/
N+5lXPuqs55cpJmlHMcCRkDIhpjgm0M9mKvkdcsYr2AiGtjMOwSZJOE/
YIJNiYoS6OAhCRGGk2e6Z6ezrlyzvee94/
bqaYrdXd1mnm+nw9ouvrWrVMz3XXvc85znodxzjkIIYQQQgghhBCy6oT1HgAhhBBCCCGEEHKpoCCcEEIIIY
QQQghZIxSEE0IIIYQQQggha4SCcEIIIYQQQgghZI1QEE4IIYQQQgghhKwRCsIJIYQQQgghhJA1QkE4IYQQQ
gghhBCyRigIJ4QQQgghhBBC1ggF4YQQQgghhBBCyBqhIJwQsizvf//
70dbWtt7DIIQQQgghZFOhIJyQiwxjrKr/Pffcc+s9VEIIIYTUwFpe+5PJJD796U/
TfQQhK6Bc7wEQQmrr3/7t3wq+/td//Vc89dRTix7fvn37il7n29/+NiRJWtE5CCGEELJya3XtB+Qg/
IEHHgAA3HzzzSs+HyGXIgrCCbnIvOc97yn4+pVXXsFTTz216PELJZNJ6PX6ql9HpVIta3yEEEIIqa3lXvsJ
IeuD0tEJuQTdfPPN2LVrF44cOYIbb7wRer0en/jEJwAAv/
zlL3HPPfegoaEBGo0GnZ2d+OxnPwtRFAvOceGe8KGhITDG8I//+I/4l3/5F3R2dkKj0eCKK67Aq6+
+upZvjxBCCCEXkCQJX/3qV7Fz505otVq43W586EMfQigUKjjutddew8GDB+F0OqHT6dDe3o4//uM/
BiBf610uFwDggQcemEtz//
SnP73Wb4eQTY1Wwgm5RAUCAdx9991417vehfe85z1wu90AgIceeghGoxH33XcfjEYjnnnmGXzyk59ENBrFl
770pYrn/dGPfoRYLIYPfehDYIzhH/7hH3DvvfdiYGCAVs8JIYSQdfKhD30IDz30ED7wgQ/gr/
7qrzA4OIivf/3rOHr0KH77299CpVLB6/XizjvvhMvlwsc//nFYrVYMDQ3h5z//OQDA5XLhW9/6Fv78z/
8cb3nLW3DvvfcCAPbs2bOeb42QTYeCcEIuUVNTU3jwwQfxoQ99qODxH/3oR9DpdHNff/jDH8aHP/
xhfPOb38TnPvc5aDSasucdGRlBX18fbDYbAGDr1q1405vehCeeeAK/93u/V/s3QgghhJCyXnzxRXznO9/
BD3/4Q7z73e+ee/yWW27BXXfdhZ/
97Gd497vfjZdeegmhUAhPPvkkDhw4MHfc5z73OQCAwWDA2972Nvz5n/
859uzZQ+nuhCwTpaMTconSaDT4wAc+sOjxhQF4LBaD3+/
HDTfcgGQyiZ6enornfec73zkXgAPADTfcAAAYGBiowagJIYQQslQ/+9nPYLFYcMcdd8Dv98/9b//+/
TAajXj22WcBAFarFQDw8MMPI5fLreOICbm4URBOyCWqsbERarV60eOnT5/
GW97yFlgsFpjNZrhcrrmZ7kgkUvG8LS0tBV/PBuQX7jkjhBBCyNro6+tDJBJBXV0dXC5Xwf/
i8Ti8Xi8A4KabbsJb3/
pWPPDAA3A6nXjTm96E73//+8hkMuv8Dgi5uFA6OiGXqIUr3rPC4TBuuukmmM1mfOYzn0FnZye0Wi1ef/
11/M//+T+rakmmUCiKPs45X/GYCSGEELJ0kiShrq4OP/zhD4t+f7bYGmMM//Ef/4FXXnkFv/71r/HEE0/
gj//4j/HlL38Zr7zyCoxG41oOm5CLFgXhhJA5zz33HAKBAH7+85/
jxhtvnHt8cHBwHUdFCCGEkJXo7OzE008/jeuuu67oJPyFrr76alx99dX4/Oc/jx/96Ef4wz/8Q/z4xz/
Gn/7pn4IxtgYjJuTiRunohJA5s6vYC1ets9ksvvnNb67XkAghhBCyQu94xzsgiiI+
+9nPLvpePp9HOBwGIG8duzBzbd++fQAwl5Ku1+sBYO45hJClo5VwQsica6+9FjabDe973/
vwV3/1V2CM4d/+7d8olZwQQgjZxG666SZ86EMfwhe/+EUcO3YMd955J1QqFfr6+vCzn/0MX/va1/
C2t70NP/jBD/DNb34Tb3nLW9DZ2YlYLIZvf/vbMJvNeMMb3gBA3s62Y8cO/
OQnP8GWLVtgt9uxa9cu7Nq1a53fJSGbBwXhhJA5DocDDz/8MP7mb/4Gf/
d3fwebzYb3vOc9uO2223Dw4MH1Hh4hhBBClunBBx/E/v378c///M/4xCc+AaVSiba2NrznPe/
BddddB0AO1g8fPowf//jHmJ6ehsViwZVXXokf/vCHaG9vnzvXd77zHfzlX/4lPvrRjyKbzeJTn/
oUBeGELAHjtMRFCCGEEEIIIYSsCdoTTgghhBBCCCGErBEKwgkhhBBCCCGEkDVCQTghhBBCCCGEELJGKAgnh
BBCCCGEEELWCAXhhBBCCCGEEELIGqEgnBBCCCGEEEIIWSMXXZ9wSZIwMTEBk8kExth6D4cQQggB5xyxWAwN
DQ0QBJr/rgW63hNCCNlIlnKtv+iC8ImJCTQ3N6/3MAghhJBFRkdH0dTUtN7DuCjQ9Z4QQshGVM21/
qILwk0mEwDguXf9IYxq9TqPhhBCCAHi2Sxu/vEP565RZOXoek8IIWQjWcq1/
qILwmdT0oxqNV2UCSGEbCiUNl07dL0nhBCyEVVzraeNaYQQQgghhBBCyBqhIJwQQgghhBBCCFkjFIQTQggh
hBBCCCFrhIJwQgghhBBCCCFkjVAQTgghhBBCCCGErBEKwgkhhBBCCCGEkDVCQTghhBBCCCGEELJGKAgnhBB
CCCGEEELWCAXhhBBCCCGEEELIGqEgnBBCCCGEEEIIWSMUhBNCCCGEEEIIIWuEgnBCCCGEEEIIIWSNKNd7AI
SQSwfnHPHJMPx9U8jGUlBqVbB3umFtdYIJ1c0Jcs6RiaYg5USojRootepVHjUhhBByaeKSBDErQqFWVH2dJ
oRURkE4IWRNSHkRA4dOIzIaABgADoAB4SE/tDYDtty9Fyq9puw5gv3TmDw6hHQ4KT/
AAGurC40HOqC16lf9PRBCCCGXgnQ4gcnjIwj1T4NLHExgsHW6Ub+3BVqrYb2HR8imR1NahFwkOOfrPYSyhn
/bi8hYQP5idqgz/02HE+h7/
HjZ9zB1fBiDz56ZD8Bnnh8e9uHsL19DKhhfnYETQgghFwkuSYhNhhAe8iHhjxW97sanIzj7i9cQPC8H4PLz
OILnp3H2F68hPh1Z62ETctGhlXBCNrF8OgfvmTF4T41BzOYBAAqNEo5uD1zbGxEZDSAdTkJQCLC0OGBqsIE
xtubjzCbSCPZNlz6AA6lgAtHxICxNjkXfTkeSGH91oORzpbyIod/0YPubD9RoxIQQQsjFg3MO/
9kJTBwdRD6Vm3tca9Wj+epumJvs8nGShP6nT0ESpfkJ8/mTQBI5+p8+hT1/
cA2lpxOyAhSEE7JJZRMZ9P76dWTj6YLHxUwe3lNyYA4AmAm6vafHoLUZ0H1wD9RG7ZqONTzkr3wQYwgN+Io
G4b6zE/
Mp7MVwIOmPIemPQe80rWishBBCyEYkiRLy6SwEhQJKrWpJz508OoTJ14cWPZ4OJ9H3xHF03r4b1lYnwsN+5
FPZ0ifiQD6VRXjYD1t73RLfASFkFgXhhKwjLkkLVqsVsLQ4oDHrqnru4HNnFgXgxV9kPnJNh5PofeQodtx7
BRSq1f/1z8bTiIwG5H3glXCOyLAf3jPjcHS5oVDPjy/pj5YOwBdIBuIlg/
BkIIZMNAVBqYCp3gpBqaj2bRBCCCHrJpfKYurYMPy9k5DyIgDAUGeGZ28rrK3Ois/PxFJFA/
A5HBh+sQeW5msRn46ACWwuDb0YJjDEpyMUhBOyAhSEE7JOwsN+DL/
YI6eFzazyjr7SB2urE203bS8IQi+UCiUQnwwv/
UU5RzaWRvD8NFzbG8scxgEuX2iXQ8zmMfxiL0ID3iU9L5/JYfSlc5g8OoQtb9gHnU0u/
lJtylux8canIxj57bmCPeOCSoG6XU2o39cGQUHpdIQQQjambCKDnl8dQS6ZKZiMTvii6H/
qJJqu6oJ7d3PZc/h7J8tnkwHIp3KIjAZrM2hCSEUUhBOyDqJjQfQ/fXJRgTIACI/40ffYcWx942Ulg8/
wkG9Fr+8/N1U0CE/
4opg+OYrwkA9c4lAZNKjb0QjX9sYLVqZj8J4ZQ2wiBM4Bo9uCup1NMLot4JKEvidOIOFdfuGWfDqLvseOYd
c7roagVMDcZEdsIlTxeaZ6a8HX8akwzj16bFHhGSknYuroMKaODsPoscC9uxnWVteyx0sIIYSshpHf9i4Kw
AHMfT32u/MwN9nnJq2LSYeTlbPJGEM6nIDRbZnfzlYClziMbkvlwRNCSlrVJaDf/
OY3eOMb34iGhgYwxvCLX/yi4nOee+45XH755dBoNOjq6sJDDz20mkMkZM1xzjH6Sl/Z/
c0JXxS9Dx9FdCxYEECmw0mce/
wYJo4MrmgMxfZ7Bfun0fOrIwgN+ubS0HKJDMZfHUDPr44gn5YLuXhPj+HsL15DoG8a2XgGuUQGoUEfen/
9OiaODCA05EdiOlJV+nhJHMglswgNypMNzi31EJRlPq4YYGt3Fex155xj+Lfn5PdSZizxqQj6nzqFscP9Kx
gwIYQQUlvZeBqRkUD56ykDfGfHy55HUArySng5nENQKmBtdUKpU5c+ngFKnbqqNHhCSGmrGoQnEgns3bsX3
/jGN6o6fnBwEPfccw9uueUWHDt2DH/913+NP/3TP8UTTzyxmsMkpKai40Gcf/IEjv7gNzj6g9+g7/
HjiIwG5oLpVCBe2GarhIQ3ir7Hj+Pco8cw8fogTvzotzj9H79DbKzyinAlKoO64OtsPI2h587KF/
oi7UrSkSRGftuL6EQIoy/
3yQ8uPG7mz5NHhzF5dKjyxb5K3jNj4BKHUqtC5x27S6bHC0oF6vd3FDyW9MeQDiWqfq3pEyMIj1RRQI6QS8
xqTah/
4xvfQFtbG7RaLa666iocPny49oMnZBNL+KKVD+Jy1lc51lZnVRPjlhYHmCCg845d8latC7upMAZBIX+fKqM
TsjKr+ht0991343Of+xze8pa3VHX8gw8+iPb2dnz5y1/G9u3b8ZGPfARve9vb8E//
9E+rOUxCamb8tQH0PSYH3VJOhJQTER0L4vwTJzDy23PgnCMVWlo/6/
hkGJOvDyGXLFOtdImcWxoKvvb1TICXu0JzIDTow/ALPRXPnYlUkfZWpaQvhjP/9SqyiQy0Vn3JYmpSTkT/
Uyfm2rQBqGqiowADvKdGVzJcQi5KqzGh/pOf/AT33XcfPvWpT+H111/
H3r17cfDgQXi9S6sjQchFrdqWohWOs7Y65UyxMqvb5mY5AOcSh7HOgu1vvgKObvfc5DcTGBzdbmx/
8xUw1lEqOiErtaH2hL/88su4/fbbCx47ePAg/vqv/3p9BkTIEoSHfJg6Nix/
USQI9fdMIJvIQBLFtR3YQoxBa9HB3llY0TQ6HqoqcM7GKldjL1dRdTnS4QR6fnUESp26IMi+UCaagvfMGOr
3tQHA0qufcyA+GQHnfF16qROyUd199924++67qz5+4YQ6AGzfvh0vvvgi/umf/gkHDx4EAHzlK1/BBz/
4QXzgAx+Ye84jjzyC733ve/
j4xz9e+zdByCZkrDNXLKgGBpgbbGXPwwQB3XfvxblHjhZO6M+cmwkCoqMBnPz3l6DUquDa0QjPnha03bgdr
ddvhZgVoVAraPWbkBraUL9NU1NTcLvdBY+53W5Eo1GkUqmiz8lkMohGowX/
I2QtiNk8wsM+BPunkfTHMHVytGIadnQ0gPhEeNXHxgRWMHs9O0uutejQsL998ax5kRT0DYPLe9NT/
ljF43xnJua+NDfawJZY+bxsNgAhpCqlJtRffvllAEA2m8WRI0cKjhEEAbfffvvcMcXQ9Z5calR6jdwGrMK9
RbluJ7O0Fj12vu0qNF/
bDUOdGRqzDiqdvDWNi9Lccfl0DpNHh3DukWOQ8iKYIECpVVEATkiNbaiV8OX44he/
iAceeGC9h0EuIVySMP7qALxnxgsuXBuBoFag8/
bdM1XKOUKDXkRGAoiOByDlONLhJAYOnQZTMLh3t6BhfzsYYzC6LUgG4jUJxgWVAkxg8qr1Gse0uWQGXJLAB
AEKtRKu7Q0Vq7wupHeYaBWckBWqNKEeCoUgimLRY3p6Sm95oes9uRS1XLsFqWAc6Qu3ejEGcI62G7ZBY9ZV
dS6FWom6HU2o29GE0KAPA4dOFT+QAwl/
FJNHh9B4RSfSkSQSXnnSy+ixQGOq7vXWk5QXER72I5fMQKmVC8mVa/1KyFrbUD+NHo8H09PTBY9NT0/
DbDZDpyv+C3///ffjvvvum/
s6Go2iubl8v0RClotzjoFnTiM8tAELeDHA0eWZT0tTyKvgxdqZcZFj6tgwMtEUOm7dKQerp6sPVsuNwbW9E
Y5uD/oeOyanvVVKpauxfCY/N7vfeEUnsvF01f9eapO28kGEkHVB13tyKVJqVdj2+/
vhPTMG35nxueuqtdUB9+6WZbcK854eK3995oD3zDji3ijik+GCb5mbHWi7YStUes2yXns1cc7hOz2O8SMDk
HLifMq9QoBnTwvqL2+jyXayIWyoIPyaa67Bo48+WvDYU089hWuuuabkczQaDTSajfchQC5O0fHgxgzAAQAM
dTua5r7ikoSh58sXUgsNeBHb0QiTx4qmq7ow9rvzKwqaNSYdPHtboNSosOud18gr8cMBSKIIpU4NLkoID/
sh5eSvXdvqoTJqMfJC7/JesIj+p05i6xsvB5up4tpx2y6Eh/ylZ/
wXqFRhlhBSWaUJdYVCAYVCUfQYj8dT8rx0vSdrTcyJCPZPI9A3hXw6C7VRC+eWetjaXWuanq1QK1G/
rw31+9ogiZK85WyFgWTCF614rZdy4qIAHACiY0H0/Pp1bH/
TASi1qhWNo9a8J0cLW47OvEcuSpg8OgQxJ6L56q71GRwhC6zqJ0g8HsexY8dw7NgxAHLF1GPHjmFkZASAPK
v93ve+d+74D3/4wxgYGMDHPvYx9PT04Jvf/CZ++tOf4qMf/ehqDpOQojjnSPiiCA/5EJ8Kg0sc/rMTNWu/
VUtMYOi8bSe0Vv3cY9OnxqpKL588KheTc+9uRucdu2FwmZc3CIFh6xsvh1IjX5AFhQBHlwfN13RBZzciOhp
EaNAHpUaF+svbsPOtV6BhfwccXR4oNLW7iCe8UYy+1DfXEo4xBqWuuvPnU7mCvuyEkKW75pprcOjQoYLHFk
6oq9Vq7N+/v+AYSZJw6NChspPuhKylTCyFM/95GCMv9iIxHUEmkkJsIoTBZ8+g59evI5/Jrcu4BIWw/
iu5nCMbT8N7emN1FMlnchg/Mlj2GO+pUWRixetMEbKWVnUl/LXXXsMtt9wy9/
VsGtn73vc+PPTQQ5icnJwLyAGgvb0djzzyCD760Y/ia1/7GpqamvCd73xnrpoqIWslPOLH2O/OIxOZ/
6BW6dVyTLuBYjSlVgXHlnq4tjcs2qMVHQtWdY5UcL7gmbXVCWurE7lUFvl0Fmd/
eQQ8X92+d8+elrk08LlzhxLoffgoxGxu7u8tG09j8ugQ/D0T2Pp7l0Nj1qH56i4MPX+2qtephu/
sOCRRROsN28AYg79novKTMLOffb1vbgjZYOLxOM6fPz/39eyEut1uR0tLC+6//36Mj4/jX//
1XwHIE+pf//rX8bGPfQx//Md/jGeeeQY//elP8cgjj8yd47777sP73vc+HDhwAFdeeSW+
+tWvIpFIzFVLJ2Q9cYmj7/HjyCYu6Agycx1L+mMYeu4sOu/
YjchYAMH+aeRTWagMWji6PTDVWzf8tcRUb0V0PLj8exoO+M5OoP7y9g3zXkODvsq1ehgQODclF6klZB2tah
B+8803l11Veuihh4o+5+jRo6s4KkLKCw54MfjM6UWP17JP90rpXSZ49rbC1uZa8bmKXTxVOjVUOjXcu5rn2
66VoTHr4N5duDeTSxznnzheEIDPfxPIpXI4/9RJ7Lj3Cji65RTU0Zf75IJuNdhHHjg3BVubC8Z6K0KDi/
fFF+Poclc+qATOOZK+KEKDPog5ERqTfDO2EffMEbIUqzGh/s53vhM+nw+f/
OQnMTU1hX379uHxxx9fVKyNkPUQHQsUTMIvwoHIaABn/
utVpEOJ+WsWA4J9UzA12tB5+24oVEtslbmG6nY1VT1ZX0o+nYOUl2r6PjPRFLynxxDom4KYy0Ol08C5rR51
O5oqpr5nYykwgVVslZqNV263Sshq21B7wglZb1JexMiLK9ufLKgUMDXYEBmubu84UwhVV1lXGdTY/
uYrFq04F2NptiM2Eap4nKlMf1F7pxvxqTDiU5GSgbGt3YXma7fMpaHPiowGkI1nSr8w50iHEohPhWGqt8HR
7YGtow6RET8ysTSiowHEiuxFqxpj8J4Zh9qkq/
rvt27X8oo85dM59B86Je+dY2ymaC3H+GsD8j4+KgRDNrHVmlD/
yEc+go985CMrHR4hc2a3kcWnIgDkPtsGt2XJn7/
hYf9c9fFy0qHEzAuj4L+xiRCGfnMWnbftWtLrriVTvQ1MwcDFFcx4M0BQ1O7aFp+OoO+xY5BEPvd3n0tm5O
y53klse+PlUBu14BJHOpyAJErQmHRzwblCraxiSxmDQkPhD1l/
9FNIyALhYb+8ErsC7l3NqL+8DQlfFNMnRxGusAorqBQQqw0SdzZXFYADgHNrA8YOD1S8iWi6snPRY8lAHKM
v9y0qVKbQKKHSqaGzG2FutMHc5IDaUHylNzoeBAQGlJuRZgzR8RBM9fJEgKAQ5J6oANy7mjD0Qi+CfVNlx1
/SzM3YbL/
0aoQGvfDsaVlUcIdLEoLnp+E9M450OAEmCLC0OuDe2Qyd3YjzT5xAwh+de92Ff+WTR4cgqBTw7GlZ3vsghB
BSUToit+BMBePztVs4oLUZ0HHrTuhshrLPj02F4Ts9hvh0BPlMfmUtOzkQHvQhHUlCa9FXPn4dRMeCKw7Ar
a3OmhWok/
Iizj95ApIoFc+eS2bRf+gU7J1uTJ8Ymc9OZAz2zjo0XtEBW3sdxl8dKP9CnMPWUVeTMROyEhSEk0vSwqJdC
6XDycqBYzEzq8T2bg/qL5NXPY11FhhvsyAy4kf/
06fk1+SFx1vbnEtqn+Xa1lD1kBRqJdpv3o7BZ8+UPKbpmu5F6dLJQAy9v35dvhAuxAExk4e11Tm317ocLvG
KKeWMoWTaGBMEtN+0XU6JPz6MyEgAUl4sf8JF52DQmHXQmLTIxCqnn028NojEdBSdd+yau7GQRAnnnzyB2P
jCrAIJwb5pBPumYWq0y1Vmy5g8OoS6HY0QlApwSa4Q7zs7gUw0CYVaCVtHHZxbG6qeYCGEEDIvm8igd2Gxt
AWXlXQ4gd5fv47tbzlQsr/1+KsDmDo+XNXqd9UYEB7ywbO3dUWnyaeziE9FwCUOvdNUdU/
wSnKJMplqVXLXcHI5OOCFmCmzCMI5kr4Ykr7YoseD/V5Ex0PY/qb9sHfWITjgLX7/
wQCj27L8ArSE1BAF4eSSwSWOQN8UvKdHkQrKe7hM9Va4dzXD0uIEAAhKYVkXYKVWhY7bdsFYJO0tn8lDoVI
uqqTq3FqPpmu7ceyhF6p6zc7bd0GhXtqvrL3TDaVOjdGX+
+bT5iDv4W6+phuWZsei54y8eK74TPSMwLkpOLrrYaq3ln1tvdMEVCiIxiUOvcNY/
jwOIzpu3SmnGU5HkPDHEJ8KV568YAzmJgcYY3DvacHIb8+VP35GZDQAf88kXDsaAQATRwYvCMALxcYr76mT
ciIiowFYmh1yQD8RXpDen0EqOIjpE6Povnsv3Rw
QQsgSTZ8cka+xxa5bHBBzeUwdH0Hr9VsXfTvYPy0H4EDtAnDIk/
wryawTs3mMvtKH4PnpgslqU4MNrddvXXEwrlhKa7GF29EYwMDQdvN2GOuW16O8mNh4aPn1YDhHPp3D6Cvn0
X7zdog5EZGRwPykysx5DS4zOu/
YTdvDyIZAQTjZlLKJDALnJpGOJCEoFbC2OmFuspf8YOWShP5Dpwv3aXMgNhlGbCIMz75WNB7ogKXFWTmVqd
j5RQ6Tx7rocV/
PRPE95hzw905CbdLC3GirWKFUY9FBZy8frJZibrBh51uvRC6ZQT6dg3Km6FoxqVCi4qouGIPv7Hh1QXgFCo
0S1iqLyzHGYPRYYfTIEyfjr/
Zj6vhI6SdwDvdOuW+6c1sDUqEEfGfGq3qt0Vf6YG1zQqFWVv2cSvKpHEZe6pvf537Bv7eYy6Pv8ePY/
c5rljzZQgghlyrOOfy9k+WDNw4E+qbQfE03BEVh+nTZ68hKxiVxqEusvFci5UWce+wYkv7YovcVmwyh51dH
sO1NB6AxaZc9PkuzHYJSgFShA0rL9VuQjaURmwoDYDA3WOHc2gC1cfmvXcyK24NyjvCwD2K2G5137EbCG0W
gbwrZRBoqrRr2LjdMDTYKwMmGQXd6ZFPhnGPq+DAmCvpAyi2otFY9uu/aW/TCMH1qrHihtJnP/
KljwzC6LbA0O2D0WOaKulSr2L5jMZvH6Mt9ZZ83cWQQ7bfsqFih1L27ZcUXDpVeU7FSdzqcKPt9AADnSIUq
Hzf+an/
FYzx7WhbdEFWrYX87UsEEIqOBC2bp5Znvluu2zE0EMMbQfE03DHVmDD1XuRUalzjOP3kCjVd2LTkFvhSmFB
Domyp9oziT7h/
sn4Zre2NNXpMQQi52Uk6ElKv8Oc1FCWImD0GvBuccsYkQvKfH5T3kS6Ax6+TsqgpFXJlCgH2Ze4/956YWp1
3P4nI/7IkjA2i/
eceyzg8ACpUSnr2tF9xPLcAYdDYDnFvqa7bvuxyD04TQgHdlJ+HyYoJZr4HRbYHRvfSVejGXR7Dfi8hoADw
vQmc3wrmtYcPu7SebFwXhZFPx90xg4rULLxhyVJOOpND7yFHsfOuVEJQKpMMJRCfCkESx8kw3Y/
CeGoWl2QG9w7S0IJwxmBoXVxgPDXirqsqdjaXReEWHvAK/cD/aTGDp3NYA59b66sezAtUGxIKy/
HGZWKpsCvespL/ETUYVmCCg845dCPZ74T0zhlQwASYwWJodcO9qguGCNDnGWMXV+8KxxVc0vsIXn/
lvFTP94WE/BeGEEFIlQSmAMVZ5JZUBCrUCkihh4NCpmXTl6l+n/
ZYd0Ji00LvMYIwhG0uVvbdovKJj2VlNFTOwuHyP0XxN96LOJEvh2dcKMSdi+sTIgr8L+T5E7zSi6849axKA
A4BjSz3GXxuo2F6skpWMN+GLou/
xExAXbB+MToQwfXIUDfvbUX9Z24rGRshCFISTTYNLUukZWwDgHNlYGr6z44iMBqtqz7XwubNpwqHBJc7ELk
h7XigdraZfJUM6kkLbjdtgdFswfXoMsfEQOOcw1JlRt7MJlmbHmqVPGT3WqlqmVepPXs1KOSBXYV8JJghwd
Hvm+oxXotJroDHpkImV6f86d3ImF+qrQc9y8OqL4NRq5Z0QQi4FTBBgbrLLWVElDwKsLU4ISgWGX+yVA3Cg
6s92tUkLe2dhD/
uGAx0QVEpMHRsu+NxWqJVovKJjRZOpmWiy4jFc4sjGMysKwhljaLqyE67tDQicm0QmloZCpYSt3QVjvXVNU
7eVWhVab9wmZ6tdeN1lCx4o828mqBQwuCpvhSsml8yg77HjEHMX7OOfeb2JI4NQ6TVrtihCLn4UhJNNIzYV
QT6dq3jc+KvLnEmdeUq+XHXOIpqv7l606goACpWiqj1OCpUCAOb2O68nhVqJuh2NmD45WvwABggKBRxbyl+
EhCpnotkyU9GXizEG9+5mjLxUXZE2QJ5wCFVoM1cNZTWVzxlb9t5/
Qgi51IjZPAafPVM+AAcAMHj2tiKXysr7x5eobsfiiXbGGOr3taJuZxMiowHk01mo9BpYmh3L3mY1S1Aqqir
qNnv/
sFIakw4N+ztqcq6VcHR5oNKpMXl0aD4jkQHWVgcc3R70P32q7PNnu5Ash69nQg7Ay9y2TR4dgmOLB4wx5NM
5xKfC4BKHzmGkdHWyZBSEk01DrCIAB0q3vCqLAfqZ2VOVTo1svHI7K3OTHZ59rUULsgGAtc1VfuUeADiHtb
26wmRrpeFAB9KRFCIj/kXp8YJCQNddeyq20jK4zZULvsysTKw15/
YGBM5PIeGtUIAOHFqLDvYuD+Le6IrbuZib7NBa9EhHyqxwcA7n1urb0BFCyKWKSxL6HjuOhL/
8ZzlTCOi4dQcMdWb4z00urQI6AwxOM1zbS38uK1SKZe/
9LsXa5pqpIVJ6rFqrHuoVFGbbqMyNdpgb7XIx2UweKr16brW//
eYdGHzuDGZT5gHMrZqbm+2ov7x92a8b7J+umBmRjacRn44g2DeFQN9Uwf2msd6K1uu3UjBOqra2y1CErIBK
v4o9lDlQN1dJu0KqEZMDqu679pYMwAFAZzPA3GQvveeMMehdpmUVDllNgkLea915526Ym+xQG7XQ2gyov6w
Nu95xddn3PEuhUlZMxWOMlb2xWS2MMXTdtadoMb0LObo9UBs0aLxiZSsETCFAoVLAUOHf2r27uWLLNkIIIX
L9jIQvWjZwUmiU2P0H18DaKk92V1PAbZagFFC3owndb9i37NXV5XLvWrzyfiHP3taLutK3Sq+BzmYoSLe3d
7qx4y1XwLnFA6VWNZN+bkb7zTvQdcfuFWUgVNtObuTFXvjPTS5a8IlPhdHzqyPIRKvY7kYIaCWcbCIGtwVq
kxbZWOVV6qWyd7phm5nJdm1rhO/sBHLJ7OJZaCYHcQ37q5ttbb9lB84/
cUJedZ3d0jTzX61Vj64N2q+SMQZri3NFK9UNBzqQCicQHQ0u7jHKGDpu31XzFifVUqpVaLl2C4bLVLdt2N8
BlV6DTCyN4d/0rOj1mILh7C9eK5lhIagUaNjfjrqdTUtuv0cIIZci/
7nJijU7xEwemXASKo88iV9Vb20GWFudaLtx+7q1i9TZjei4bScGnzktb2u7oPtH/
WVtVddCudjo7Ea03rANrTfU9rwakw75VOWMy3S4RDYblwP58Vf70XHbrtoOjlyUKAgnmwZjDM1XdVXcE7QU
apMW7t3NcGypR2Q0gFwyC5VWhS1378Xgc2fl6tgMmE19UunUaL95Bwwuc1XnV2pU2Pp7lyMyGoD/
3CRyiTSUOjUcXR5Y21wr3je2kQkKAV137EFoyAff2XGkQwkICgHWdhdc2xvXPWXLua0BglKBscPn5QmXGUq
tCvWXt8+t0vvOjq+8fymYHICXOA2XOBxdHkyfGMH4awMFz5ttv9d1cO+KesISQsjFJBsr/
ZlacNyCrUTmRjtUenXBZ/
4iHGi4vH3dAvBZtjYXDO+4Gr6eCUTHguCSBIPLDNeORugdyys+RkpzbWsov01tZkte2W12HAgN+ZFP56DUL
r9gHrk0UBBONgVJlBAdCyCbzMh7evumwPOS3JYEvKoL8Syd04jO23aBCQwqvQaB3kmc/
PeXC1pSKFQKeC5rRfM13YhNhMAlDr3TBEuzfcntL5jAYG11wtq69vuf1xsTGOwddQX75UbTGjwctiKZEFCn
zuI6axgm5fpUBLd3yRkQsakwcokMlDoVzA22gn/j8LBvxdXRpQppblyUMPxiL8JDFxaAm2+/
d+7R+fZ7hBByqVPq1ECpVcmFxy0IhpjA0HLdVvQ/dbLk8c7tDRumQKbaqEXjgQ40Hlj/omkXO1unG96z4/
Liy4XX/JkMvqrm4zlHJpaiIJxUREE42fC8Z8Ywfri/
6OyjzmGEudEG75nxqvd6NVzeDo1JN3fu0Zf6Fh0j5kSMHx5A/
eVtaFhBoQ8yLykK+PpIC47GzBDAwcAhgeH/m6zHO9zTeKPLh/XIuGYCg7lhcZ/
3WWVnvSueHFBq1cinyqy6zAiP+Et/c6b9XrDfS+1RCCEEciXt+Exr0VKUWhVM9daCx6ytTnTduRsjL/
cVbG8TVAp49rTAs691FUZLNjpBIWDL3fsw9EIPwhd0RNGYdGi7cRv6nz6FfIUWrgBospxUhYJwsqGNHe7H9
ImRkt9P+mPIJtKwtjoR7PdWrHract2WuX3OYjaPsd/1lz1+8ugQnFsboDZolj54MkfiwD8OtaE3YZC/
BsNsxTqRM/
z7VD3UgoS7nJXazKw9nd2IXDJTcTVcbdIgG1tQQZ3Jbecq3STOqaKqf6BvioJwQggBYO+sw+SxIWTjmZLX/
obL24tmr1lanNjV7EB8OoJsLA2FWglzo42Cp0ucQq1E5227kI2nER0LQpIk6GxGGD0WMMZga6+Dr2ei7L2m
xqSD1koV0kllFISTdcE5n9sjqzJoFu2NzqWyGPtdH4LnvRXPlU/lkArGwQQGLpb+YGy5YStcC9o/
BQe84FXMaAb6plBPM+MrcipuxNlE+fS+n055cKs9CLWw0v3XtVW3vQHRcj1ombzPsOvgHsSnI0gHE2BKAaY
GG/oeOVrTseTTlVfUCSHkUiAoFdh6z2Xoe/
y4XCyLFVZpa7i8Hc4yHTgYY3K3j0uzvhkpQ23Uwrlt8c9O3c5G+Hsnyq73ePa1UCFVUhUKwsma4pzDd3oc0
6dG5NlryDOP9k43bJ110Jp1ABh6fnWkql7ds1LBBJqv24Lx3/VDyi9OS2+
+prsgAAeATDQlB+5lVyAZtZuogRdCNggz6eelpCQFjsVMuNJSqX/
32jI3O2BrdyE0eOF+bQBMbsfWfHX33A3dbAu32GQImWor+Veo8Dt3mELA0PNnIWbzUJu0cG5tgM5mqPq9EE
LIxURt1GLHW69EdCyI8LAfUk6E1qqHY4sHagMVsiS1pbUa0HH7Lgw8fapo1XrP3hY4tlC2GqkOBeFkyaS8i
NCAF/HpCAC5dZi9o65iGhfnHIPPnUGov3B1W8zm4Ts7Dt/
ZcQBysZVq9tBeKBdPQ1AJRYPwYhQqRVVVrxVqSk9bqVBOWTYAl3GEcxuvkAljDO237IDWOgzv6bGCXqLmRj
uar+4umnpWso1JES3XbcHk60PlK/YCSAXiSAUTciocY/
CeGoNzWwNart1SVd9zQgi52DDGYGl2wNLsWO+hkEuAtcWJXe+8Bv6eCURGA+CSBL3TjLodjdA7qWo9qR4F4
WRJYhMh9B86BTGTx2wVLX/
vJMZeOY+O23bC3Ggv+dzQgHdRAF7McgJwAPCeHoNUIr189OU+KLUq2Dvdc49Z21yYODJY/
qScw9bmWtZ4yDyrKl9xJRxgsCjLVxFfL0wQ0LC/
HZ69LUj4opBECVqLoWzLsGr3FuqdRkRGAhUD8DmzE0cz//
X3TIAxwFBnAeccBpe5qtVxzjliEyGkQgkIggBzk726HrqEEFJDUl5EPpODQq2CQrW8SW8xm0dowIt0NAWFS
gFrq3PDVDgnFx+1QYOG/
e1o2E+Fe8nyURBOqpYKJdD3xIn5fdQLVpHFbB7nnziBbW86AL2j+IXPe3qs6rTb5ahUxXri9UHYOurm9uro
bAZYWhyIjAaKj4kBBpcZBrdlFUZ7abneFsJvw6UrkAOAThCxz7yxUtEvJCgVMNWXfx+zzE32uRS1ciSRyz+
DK+A7OwHf2Ym5rw1uC9pu3FayF3t8KozB588WVAYGAEuLA203bqfWKoSQVZcKJTB5dEje6sM5wOTK5fX72p
a0oujrmcDoy33goiRvMeMcE0cGYW6yo/2WHVBq6POMELLxLK3hMbmkTR0fLrt/
mnOOqePDJb9ftPfiGspEUnIq7wLtN+
+AcTbInl2knfmvzm5E5x27qcBGDewxxrFFn4BQ5gfgXvc0NBusKNtKqHRqOLd4UHLxnwEKjRLpUKLmvxcJb
wS9v369aF2FhC+Kc48eWxSAA0BkNIBzjx6reksHIYQsR3w6grO/eG0+AAcADoSH/
ej51RFEx4NVnSfQN4WRF3vnFge4NL9PNzoeRN/
jx8GlFbSZJISQVUJBOKkKlySEBiq0AONAaNBXMiV8XZpAX0DM5Aq+VqiV2HLPZeg6uAe29joY3GZYW53ovH
0Xtr9pP1Q69TqNdGkkDrwWMePrI834PwNt+O5YI/
qTGye1WGDA37YNYbsxLn8NDgUkMHAI4Hirewr3OMv0yd6kmq/phmm2B/kFP/
5KjQqW2dXyWuNAPpPHxNGhRd8aO9xfuhYCB1LBOALnp2s/JkIIgXw/MXDolBwcX/
hZxOVAeuDQ6YqTgVziGD9cps0oB5K+GMIjG6/1JSGEUDo6qYqYEytUEZ/
BOUZfPgcucqiNWji2eKAxycGgqd4qz27XatWPyXt1q2kzNktVpN/3Zi/
qEsop8cXBdoymdXP7rgVwPB104BpLCH/RPAblMlaY06KADGcwKkQoahAnGpUi/
q5jEANJHX4XsSApCahT5XCDLQSrKg/OgfG0BnFRAbsqB5c6V/
mkG5ygVKD74F5ERgPw90wgHU3OdQNwdHsw+lIfVi09hHMEz0+j5Zruuf3pmViqqr7l/
p4JuIq0ZyGEkJWqpgaGmM0jNOiDo7t0/7DYZAi5SjVkGBA4N0m1XchFJRVKIJfMQKlVQWc3UsbmJkVBOKmK
QqUAU1QX8Pp7Juf6dU4eHYJ7dzMar+yEe1czomPVpZiV497djLrdzUj54zj/5InqnjSzv7vUHtnNSuLA/
xlsx3haLhA2W/
hs9r+vRKwwKUV8oHGi5DkudCJmxK+8LpxOyHvydIKI2xwBvNHlg1m58jTlDn0KHfrCtm+HI2b8bMqNscz86
v12Qxx/
4JlCt6H6KuMbERMYrK1OWFudBY9zzsG5tKpbNLgoIZfMzhVcm20LWEkmRm35CCGrI+6NyulR5Sb2GUPCGyk
bhFdVzJID2UR1n3tLkedAPK+EViFCexFtoyIbW3Q8iLHD/UgF4nOPqfRq2DrqYO/
yQO+ggHwzoSCcVIUJAhzdHvh7JysWmgJQcMz0yVEISgUa9rej/
vI2TL4+VMULMqiNGii1KqSCCQgKBkuzE3W7mmBwmQEA8Vx4Ke8ATVd2LuH4jSkpCngpbMV4Wgu1IMGoyGMk
XTrtnIPhUMCBe93TsFQRQD/
pd+D7E40Fe7dTkgKP+Fx4OuCAkkmQuIAWXQp3OgK4yhLBSjtjPRWw43vjTWAXRKO9CQMeGOjAx9uGsMsUL/
HszSmfyaH/qZOIT0VW/bWEBdWGFerqPvKVaipkRAhZHYwBjFcz/1j+4qLUVfE5xVDTbWXhnBK/
8rnwbNCOtKQAwLHHGMeb6rzYYUxUfD4hyxUe8qH/
0KlFvzi5ZBbeU2PwnhqDzmZA87VbYKq3rssYydJQEE6q5tnbglD/
NMS8uOTVu6kTI3Dvbq56hk6pVWLrPZdBbSzdAkqlX5xaXgxTMHTdsQdGj7Wq4zeq54M2fG+8EVnOoGAc4Az
iXLn50n+vIoDXIhbc5iifhTCZUeP7E3IK8oWtxDgY0pIAQA7oziUM6EkYcYU5jP/
eOrLsdPVwTomHxhvnXmMhCQyMA98cbcbXt59dcbC/
UXDOMfD0KcSnVzkAZ4DeZSoIvHV2A9RGbdGCbQufZ+9yl/
4+IYSsgNFjxdTxkfIHcQ5jhUDC3GCDUqtCPl1m6xJH2dX0pfBlVfjU+S5E8soF10iGU3EjTsSN+HDTGG6yh
2ryWoQsJIkShl7oqXjvnQolcO7RY9jyhr1Vd3Ih64cKs5GqaUw6bPm9y6Exzqy8MlZ1USkuSpg4Mli5L/
cMo9taNgAHAKPHUnSP94Xabt4ht4vaAAaTOvzLaCM+fq4bf9fXhf+YciOYqzwXdjhixoNjzchyBoBB5MJMA
F6ZACAlVf5VfyrgqPCBMP96szcgr0Ut+IW3rqpxFPN8yFb2msLBEMqrcCxWfbuajS7hiyI2GV79TgEcSHpj
OPr953Hyxy9j+sQIcol0xWJHglIB13baD04IWR3mJjvUJm3ZzhFKnWrRFp5FhwkCGi4v06eZMWhtBlhrtB/
8wdGmCwJw2ezX/
zLWhECWsohI7YWHfBAz+eoO5hwjL54rXYCVbBi0Ek6WRO8wYuc7rkJsPIT4dBiA3NYo6a+QLszk1iPVSvii
iIwGkArGwRiDqdG+qP84YwzNV3Vh4JnTJV/
T4DLDVuFCvhY4B3467cYvvO654mkAMJDS4Zc+Fz7aOozLzbGSz/
33yXqUXvEuH4xLYHCpKhc5Oxs3LLq5qISD4XG/
E29y+RYVf0vkBTzqd2E8rYFFmccVlih2GuMF8zbDqcoV3AVw9Cf14ADSogJuTQadutRGKLa/
LKF+b1X9w2spG09j7HA/pk6MlF81AuDa1lB1lgkhhCwVYwydt+/
GuUeOQsyJhZ+FjEFQCOi8YzcEReXJY+f2Boi5PMZfG0TBNZJz6J1GdFV5nkom0hqcSZSbDJaz0p4J2vF2D3
WXILWVCiXABFZdgWQA6UgSCW90vgUv2ZAoCCdLxhiDuck+t7qcS2aRDCQqti8rmwJ7gVwyg/NPnJiPLw/
3w+ixoOPWnQUBgq2jDm2ihJGXzkHKifKHFJc3m1maHGi7eTuYsP4JH8+FbPiFV07xXRjocjDkOfBPw634+
+4+NGgLC8hwDvx4yo2p7HKDIg6DQsTl5uii855NGHAyboTIGdp1KWSl5UW1cVGJobQWXTPF1vIc+NZoM14K
WzH/D8jxZNCJOnUaH28fQr1GLqijFKS5hPpSJAC/8rmQ5/P/
jo2aND7QOI6dm3APXj6Tw+ovg5d47QoBOCBPqjVd1bUGoyGEbHb5dBb+3kmEBn0QcyJ0Vj2c2xtgbrSX3X6
mdxix/
S1XwHtqFP7eSUh5EUwh155x726uuogqYwyeva1wdNcj0DeJTDQFQaWAtc0Fo9tSsyJVfcnK45HAcDZhqMnr
1dpgUoeng3YMJHVQChyXmWK4xR6ETVXl6ipZV4JCWPLKdjqSpCB8g6MgnKyYY0u9XLCtDKYUwPPVtxKbi1E
WfObEpyPoffgotr/5QME+V0e3B7Z2F0KDPqQjSShUClhbndBaN8bFkHPMpGyXXsmWOPBEwLGoivl/
TrvxK99y9+fKr/
ee+kmoFqxST2XU+PJQK8Yyckszjtn92MsPDPN8pio7B77Q34GzSQMK36v8Z29Wg0+d78SXtp6DRSlirzGOF
0KVtgqwufPPmsho8IWBDtzfMYBdmywQVxvKb7NYb+lwEpxzqrBKCCkr4Y2i7/
HjELPzgVwmmkR42A9rmxMdt+4sOwmuMWnRfE03mq7uAhclMIWw7M8dlV4Nz97WZT23ljbapybnwE+mPPilr
25BFp6cXfYLbx3uaxvCvous8OnFyNLsqHo75yyFUlH5ILKu1n+JkGx6hjqz3GO7zNWn8UAHlCutUMqBTDQF
f+/idluCUgFHtweNBzrg2du6YQJwQA4YvVkNyv0FSWB4JWwteGw6o8Z/Lmu/
tRxMGxUiPtw0ipsXFIqJ5hV4oL8TE5n5lmbzBdGWd/
vAwOdW0V+NmnE2aSxzLoaYqMRTfnmLwFWWCKzKXEE19mrwmVrq3xtrXMus7ppwbPFUnu9gwMJKdIJy7T6qm
cAoACeElJVP5+QAPHfBSurMZ1t4yI/xVweqOhdjDIJSsaE/d7YaKk/
2MnBsN26sgPbZoB2/9Mn3EQuLyfGZye0vD7VhKlO76vFkdeidpqWtagsMpkYqzLbR0Uo4WTHGGDpu24nhF3
oQ7PfKAQSTe4AyhYDG/e2o29kEKSdi4vXBFWfi+nom4N7dUpOxr4TEgaSogJJxaBWLV/
nzHBhI6jGYqm7lM3PBau8zQTsEyOnYSyEA+HDTCK6xRgr2aec58L3xBoTzStRuvl5eSf/
iYCc6dMkqA2KGQ0Eb3uaZhlLg+Hj7IP73+S5I/
MIx8bnji78yw2RWi3NJPVq0aTwTtONQ0I5AVg2dQsT11jAOOv1wqSunYK8lrUVO1/SfLd
27vfFAB1zbG5GJpsAEBq1Vj8D5aQz/pmd1B8cYLC3rX0OBELKxBfomC1bAi/
GeGUf9ZW1Vt0bcyDyaLHYbYzgdN5aoncIhALjVXr4LyVqSOPALrwulsvD4giy89zWUz2ZcK5wDGUkAYxwa6
r9eoOO2nTjx7y9VdQ9ta3NBqaEigRvd5v9kJBuCoFSg/
ZadaNjfgdCgF2JWhNqkhb2jbu4CbKgzgzFWcl8LUwjgYuWQM5fIVDxmNWUkhsf8TjzhdyKclz/
kOnUJ7DHF0aRNw6rMYyCpw699LkTF6j4EGTjq1YXvazyjWXIADsy09mJAQhIQzqhgVIhISQL+frAd/
lytZ7znL+xDKV3V443l5z96InklcrzYSm91EwUDSR3+ebQJU1nNzLWJIZsX8JjfiUNBO+5vH8QWQ7LKka2N
lmu2QFAq4Ds9JhdamSnUJigF1F/ePtfOT++cLwRkbXFiZAmFWZaFc7h3Na3e+QkhF4XQkK/
iMVyUEJsMV6xyfiExm0fg/
BTCw35IeRE6mxGu7Q3QO9a3S8aHm0fxqfNdCOZUBYH47Lauv2gZgX0D7bEez2jgy5WvJzObhbdaQXhekrPW
VBUCapEDhwIOPO53YDIrL1y0aZN4g8uP663hTVuItZZUeg1UejVyiWzFY+2dy+9aQ9YOBeGk5vQOEwSVAga
XaW4/WDIQx/knT5YMIASlgM4796Dv0WMVz69Qr9/sXlpi+Fx/
JwZSuoLJyP6UHv2pSinwpft5cwB3XNDHW82Wu1Ob45deF74x2jz3egpIS658vlSVS6wV6knosc2QxGN+Z0H
F+KV6OuDAdFZTtM94RhLwD0Nt+Pr2s9BuoFl1JsiV/
ev3tiA05Ec+nYVar4G1zVVy1UipVcG5tR6+UivoTJ4Mk3LlW5AVf648CdBy/
VYYPdalP58Qckmp9nOmUkvECyV8M/vMF7RjSnhj8PdMoG5XE5qu6lq3tHW7Ko/Pd/
fhUZ8LTwftSIhKMHDsN0fxey7fhpvszVTRmnQpx1WLc+ClsBWP+p0YSMkF7Zq1KRx0BHCLPbhwpxUAOQD/
ylArXo+ZCx4fTuvwzdEW9CQM+NPGcQrEIS9WVYMvZwWHrDkKwklNJANxjL3SJ/c/
nqHUqeDZ04q6XU2YeH0QXCr9qSCJEhLTEejsRqSCZfZUMcDRvdxCZSv3sykPBlO6RQFfdau2s0Fq4bECOLr
0SdxgCxU8frk5ipcj1mWMkmE8oy14Hbmn+FpcwYq/
xwuJYHigvwsfaBjH2cTSW6MtNJEtne7PwZAQFfhtyIbbHBsnTXCWUquGa1v1PbmbrupCJpZGdCyIC+c8FCo
luu/ai/
CIH1PHhqs+J1MKsHe64d7ZBJ3dWPkJhJBLns5mRCqUrNhqsdoq5wCQS2XR91ixfebya3hPjUFt0MK9u3nJ4
60Vs1LEu+qn8A7PFNKSALUgQblBg0OXOgsGXuR+ZR4DR72mdtmFnAPfGW/EM0HHTOUW2Vhai+
+MN+Jk3Ii/
ahkpCMQf8ztxNGbGhfcNs+N+JujALmMc11gjKxpbngPnk3qkJQFudXauS8tmorMakI1W7jSkMW/
sArBERkE4WbGkP4aeX7++KMjOp3IY+915pMIJRCr1COfyXu+Wa7eg/
6mTxY9hcqDh2tFYo5EXGQYHDkfNeMLvRH9SD8Y4dhriuNsZQLchgWeC9hWuKBc+VwEJN9pCeG+DXMGccyAh
KiACuMIcgV2VRfiC1LcK72Dm/
5czSVAr1QTi8ve+P9EAFVv9FeqTcSNucwTBOTCVVSMpKuBQ5WBdkDqYkxh+F7Hg2aANwZwaJmUeN9pCuN4a
Lrrnfz0ISgW67tyDyKgfvrMTM90AlLB11MG5tR4qnRqGOjN0NgOmT4wgGahcJIjnJVia7BSAE0Kq5tzegGB
/
mX7YTA7UF26pqcTfOyEH4GUuCVPHh1G3s3HdW48KDNBvkOtCKRaliAPmCI5ELSXvITiA2x2Bmr3mS2Erngk
6Zs5d2I4VAH4XseDJgAN3OeXXlDjwuN9ZNoeOgeNRv3NZQXgop8RzQRsORywYz2gLtr5t1Sfw3oYJdMy0V9
0MnNsaEBkp/++lsxvXfesGqQ4F4WTFhl/
okQPwEp+igQrty2blkllYW51ouX4rRn97bn7v+ExMp9So0HXX3lVr8SRx4F/
GmvB8yD6fHs2BYzEzXo9ZcJs9gLRUm5YPBx1+7DTGsdWQgFkpgnPghZAVD/
tcGEnrAABWZQ5XW8J4KWxFVKy2mFrtCq4t93wCpJnq5ZVXxAUAOkFEXmRlZ+tXKphV4ZWwBf85XYexjPz3y
8Cx1xTDuzxTsKty+PxAB4bTurmVg+msGn1JPX7lrcP/7uzfMAXemMBgbXXB2uoqeYy90w17pxvZeAqn/
+MwpHLtARngPT0GWzvtISPkUsEljnw6CyYIUGqXvsXL6LbA3u1BsG9q8TeZXLC19fotSzpnqN9bcUdTPp1D
3BuFibbNVOUP6qdwOm5CWhIWBeIMHE2aNEZTWnx3rBEeTQY32EIwK5expWnGY35nxdX3x/
xOHHQEwBgQyqkQqFCrhoPhfFIPiWNRKns5D/
uc+PfJ+plaNYuf2JfU49P9nfhkZz+6Nkkgbml2wNxkl7PhimEMzdd2r+2gyLJREE5WJBmIVbXaVg2FWg5wX
dsaYG11InBuEslAHExgMDfaYWt3QVjFvoeHgnY8H5JbOiy8WM3+
+dDM7G4t7DDGcYUlCqAwfWvhHUg4r8QTASfadSkgiyoC8eUHzgsxcKgYR4cugZ7k0mZTBXBcZw3jLW4v/
n3Sg1ej1rLHS2BLmGBYvr6UHl8baS1Ij+NgOBEz4UzciGZtCqNp7dzjC/
8byKnw94Pt+Ict55Z0A7ARiFmxfAAOAFzu95vP5JZUTTXpjyHhjcqtUDxWaK3Vp50SQtaHmMtj+uQofGfGk
U/LE4s6uxHuPc2wd7qr3m/
NGEPbDdugMWkxfXK0YI+43mFCy7VbYKgzlzlD8bFVY1l1LzawoZQWh4J2jKe10AoSDpijuM4Wqkl18HpNFp
/pOo/vjDWiJzmf7SRAglEhYjSjm2lZKi88/PuUB+/
2TOENrgrZi0XkuVwfpzwGb1aDSF5ZkIlWa88HbfjhZPmtXhIYOAe+PdaE/
9Pdtyn2nDPG0Hn7Loy+ch6Bc5MFdZY0Fh1ar99KE1SbCAXhZEVSocq9M6vl6PbM/
VmlU8Ozt7Vm566Ec+ARX+mVRWC+AupKV2yVTMKOBT1Hnw3a5tK3CoNROWQcTOmwVZ9ANFn+19WqzCGaVy2r
ovpCu41x/FnTGBzqHD7b34Geqvdsy38/97j8qNdkcZczUDEIXxvzm6eLFW/LcZQtqifN7LE/
GTdir2lj9YCtqMq7Ci5xHP//
XoTRbYF7dwssLY6SN+OpUAJDz59F0h8reNzUYEPbTduhNpSvxksIWR9iNo/
eR47KdVcWxHepYBxDz51F0h9H01Wd1QfiAkPD5e3w7GlBbCoMKSdBa9Ete2uLxqJHNpGpuBquMemWdf6NRu
LAv0404InAfHFSBo6jMRN+Ou3GJ9oH0aKrvP+3kkZtBp/qGsB4WoPhtBYMHP8x7cFURv6sXlgzRuQM/
zbZAK0g4dal1lFZ1Ga0zKEz/
7WpcrApcwiVaZ3KwNGhS1U9CS5x4GfTblRTn4aDYSStw0BKh85NshouKBVovX4rGg90IDoehJQTobXqYXBb
1q1oIVme9d1UQzY9ocpKjdWo27l+rZGCORWmsxqU+8CeDURZpTuEMhg4brEFYZxJ9+IzF+Fydx0crGAGu5R
wfil7x+fHI4DjTa5p/HnzCL6ytQf3dwzCMZN6/RfNo7CrchCqes/
yazdr5ZuGFm0aiopTApUvkrVR+jWqmVRRgOO16NJWdTYCrUUHpa7K1W0OxKci6H/
qJPqfPAmpSLvATCyF3odfL5r9EpsMoffh1+dW1wghG8vE64OLAvCFvKdGERsPFf9mGYJSAUuTA7Z214pqS7
i2NZQPwJnc6vRiybr5tc+FJwJy+7bZazefCYhjeSU+P9CBhFi7e6xGbQbXWiOQuICJjLbM/
QLHT6fdEJd4q6MUOFq0qQr3SBwOVRYWpbwKLjDgLqe/
Qo4fw13O6lfmzyf1Mynu1d9bjGc23+SxUquCvdMN57YGGD1WCsA3IQrCyYqY6m1gNcjRVZu06zq7na9yBpc
D6NAmZy4yS7lCycfuMsbxngX9OE/
HjchwBWoRiDIADlW2TMAsPy6AQzHzZ5Mij79tH8S76qdxoy28qFqoQ53DF7r7cLDKCyAHQ27m79KoFHGdLV
whgN8oF43y/5YcQK7GbVzWAhOEZU1uRUYDGH+1f9HjE68PQczmi1dE5kA2nob3zNhyhkoIWUViToS/
Z6JikOs9vX6/v9ZWJ0wNtuKXhZl95s1XXxz7XXMSw6/
KZN9JYIiJCrwws0Wull4IWSsEygyRvAqn40ufULnb6a94xT/oCBSsar/
B6cduY3zRfdXsGG+yBXGdNVz1GGLi0rctPhOw48NntuPPTu/Ax3q78f+Gm/
G434FIfvW2QK4VLknIxFLIxNIl2wST9bH57irJhqLUquDYUr/
iWEqlK1+YYzWFc0o8OFo5UGHgaNGm8b+7BvAGpw9LfdMMHHc5/
VAv2Od1LGZC9cF8hSJnjGOXMQa7KrfoYiaAQydI+G/Nw3iHZwpvdk/
jvtYhfGPHWeyrkGIdzKnQoM5AySonupsVeagXVDv/w/
pJuNTFJgY22oWgUsoa0FDDNi5rybOnBeZm+5Kf5zs7IQfcM8SciFD/dPl/
Og75Rp9cdL7xjW+gra0NWq0WV111FQ4fPlzy2JtvvhmMsUX/u+eee+aOef/737/
o+3fddddavJVLUjqcqKo+RHx6ZW2gVoIJArru3A3nlvpFW2m0Fj223HPZkveZb1RnEwYkxfJbzDjkauO1Fs
qrqsoAi+WXvmP1RlsI11jCwKKFCrlc625jHHe7fAXPUQocf9s+iPfUT8Klms+katBk8GdNo/
izprEl7dfWVnGvcqFzSQMieRViohKjGS1eitjwg4kG/
MWZHfjJlBubMXaVRAmTR4dw4t9fwqmfvIJTP3kZJ3/
yMqZOjJRtGUzWDu0JJ0VlE2n4eyYQGQsCnMNQZ4FrWwN0diO4xJHwRpDP5KE2aNB0VScy0RRiE6HC3sVMvq
gyhooXf1vH+lRmTosCPjPQgekqUpE45LQpjcChZJivoF4V+S/
mu+ON2GfqgcCA3oQeL4ctqNVqMOcMLnUOX+zuw9NBO54J2BHKq2BQiLjRFsJBR2Auzbwa42kNHhxrwvnkwv
3SpdPHBXDcPlPxdJZZKeKzXefxX946PBu0z1WXb1BnMJ3VzOxFW9K7XPDnpTy3mrT30scwyDcXm40kSpg4M
ojYRHjJz+WihNhkGNZWOV0yn8pWNYueS8rH1SJDhmwMP/
nJT3DffffhwQcfxFVXXYWvfvWrOHjwIHp7e1FXt/iz++c//zmy2fmsmkAggL179+Ltb397wXF33XUXvv/
97899rdFsvpTQzaLqVNV1/
rUVlAq03rANjVd0IDoegpSXoLXpYXCZL6p021RVq7UMyWWs6lZiV+Uwli6Xji6zqJa+tUhgwEdaRrEtkMSj
fufMNj+5Zs0eUxxXmCPISAKUF7R3UzLgDS4/7nb6kRAVYIxDL0jLKpY2kpYLzS3lh7lwUoLN/
VcC8AtvHThneFd9kU4AG5QkSuh7/Djik+GCx3OJDMYP9yM+FUbn7bvWvdXfpY6CcLKI9/QYRl/
pK4h3koEEfGfGYW1zIuGNIpecv8HSWvVovLITru0N8J0ZRzqShKBSwN4h71UJnJvExJHB4i/
G5NZjC4uyraXnQzZMZsrvBQfkVezLTNG5QGw6q17yWi4HQzCnxom4ESJn+MpQW03XgyUwXGsNw6gU8eY6H9
5c56v8pBK8WRU+1d9Z5EaheA9wARxOdRZ3F0lbNylFvLdhEu/yTCGUU0HJOOyqHL491ohnQ/
ZF5yrHqszjWmsYIgdei5gRyM9mUMyeY/HY5pulFW+bIkDexzaU1hV5vvz1u+snV7WS62rgEkf/
0ycRHV1icZ0FpPx8FeLZ7gWVMIVAAfhF5itf+Qo++MEP4gMf+AAA4MEHH8QjjzyC733ve/j4xz+
+6Hi7vTDz4sc//jH0ev2iIFyj0cDjWZ/P/
kuN1qqHoFKUryzOAFO9dc3GVI5Sq4a9073ew1g1depsxWMEcHjUtc/
AuskWwrFYuYwCDpsyj+36BF6LmPFEwIH+pB4C49hrjOEuZwDdhmTpcTPgTmcAdzgC6E9p8aPJBpxNGPGbkB
2/CdmhZBJusQXxhw2TiyrAM4a5mjnLNZKupo3t7LW+mmCd4WGfC3e7fLCscGxrxXtqdFEAvlBkJAB/
7yRc2xvXblBkEQrCyZy4N4KRF8/JhVsuNLMHNDy0OMhKh5Pof/IkOm7fhS33XLbo+559rcjG0/
D3TsqfsAv2kyo1KnTfvW9JrZGWi3O5L+TLYQsSogKN2jReCFWXptusSeG/tYxAMfNZrRWkgkX/
ajFwjKS0+C+vu2TvyuVg4LjKElm0p3u5/
mPKjZSoKDFTfuFjHHtMMXyoaazsxVMtcLgXjO8tbi+eD9mrquberEniDxsm8XLYht+GrRA5Q4cuhbdbpzGd
0eBozISkqEBCVCAhKef2knEwtGlTeGOdD/
881oRcQa9U+ZgGTRr3dwziXMKAH016MJmdv4DbVTm8wz2Nm+y1WQVPiQKieSX0ChGmVb6Yhwa9KwrAAUBrn
c+CUGrVMHoscrpqqR98xmBfp6wWsjqy2SyOHDmC+++/f+4xQRBw++234+WXX67qHN/
97nfxrne9CwZDYReC5557DnV1dbDZbLj11lvxuc99Dg5H6VaQmUwGmcx8UBKNRpf4bi5dglIB1/
ZGTJ8cKf37y9e3QOqlpE2XQrM2hbG0tmRquAS29ArlVThgiaBdm8RwWlfyGv9OzyT+ZbwJvwnZC7L+XolY8
VLEhvc1jOMuZ6Ds6/
hzKvzDYAcSF0zm57mAp4MOjKa1+F8dg1DWoBXbQlNVFVmrNgCXSQBeDlsrvueNgHNeVW0H7+kxCsLXGQXhB
AAQmwyj77FjKyraMPxCLyzNjkUV0xljaL1hG5xbG+DrGUc6LK+U29pcsHe6oVCv/o9hNK/A5/
o7MJpZuNpZfV/t0YwO/2+kFX/
bNgSBAVdaIniuygB+IQ5gLK1FWhKqet3yZ8LcOczKPG611+bikBIFvBSxVkhV4zApRPxRwwS2GhKoW0Ka+y
yXOocD5ggORyun5Ldq0/j7wQ4wzFeRPRU34kTchBttQXy++zwENj/Rci6pBwOwzZCYazvSpU/
iqYADL4ZsSEkCnKosbncEcZM9CK3AccASxX5zFAMpHYI5FUzKPLbokzXpDT6ZUeM/
p914JWydS8HfaYjhXrcXAuN43O9ET0IOUHYY4rjLGcCWMisN1fCdHceyZooAgMm9fvUOI/
LpnDwxxxjqdjUjPlV6zyhjgHt387LHTDYev98PURThdheuSrrdbvT09FR8/
uHDh3Hq1Cl897vfLXj8rrvuwr333ov29nb09/fjE5/4BO6++268/
PLLUCiKZ1188YtfxAMPPLD8N3OJa7i8DQlvZPHv8MznRP3lbTDV174Q2GYTyKoQyKlgVIio12SWlRLdn9Th
xbAVsbwSNlUON9pCaNbOTyAxBry/YQKfH+gAimRpMXDsMcawzxRDrSkZcH/
HIL423IrTCSOEmf3aIhhUjOOPGiaQkhT4zUxRuIX3ArN//
sFEI9p0KWwrc5368aQHiRKT+XLXFwNeCFtxS40muWfJ/17V/KNV/w8rgCOUW/
3FolrIp3IF2aqlpMNJSHkRgnLzF5/brCgIJ+CcY+g3Z1dcNVHM5BAZ9pfc322oM69LUZU8B/
6urwu+3IWpy0vbL3QsZp7rFb3XFEOTJlWhzcdiszGRYuaCt3S8aFwVyyvxhcEO/
GnjOG5b4cx5KKeCyCvtE2KIiwpcbw0v6wZl1hvrfDhctpc4h0Eh4rcR28xtwrzZv/
ffhGxo1abxBpcfjAFbDMmiAaxLncO766fw7jL7uhgDOvUpdKJ2/
UKHUlo80N+JbMEqPHA2YcRnB4wAWMFKw+8iVrwcseHt7inc6/
Yu+3VTocSyA3AmCGi8ogODz59BqN8799kgKAWYGmyITc7cNC04P1MI6Lx914paFJGLz3e/
+13s3r0bV155ZcHj73rXu+b+vHv3buzZswednZ147rnncNtttxU91/3334/77rtv7utoNIrmZpr0qZagVKD
77n3wnR2H9/QYsjG5naTRY4V7dzOsLc51HuH6Op/
U4ceTHpxOmOYea9am8Db3NK60VJd1kRYFfG2kBcdiZihmtkIBwMO+OtxgDeLPmsbnVn53GBO4v2MA3x5rgj
erwewCgQIcN9uDeG/DRE0mgYsxKUX8XecABlNavBaxIC0JqNdkcK01DK0g4a96tpV9vgCOx/
xObDOMFP1+PK/AKxUm8xmAJ/
2OmgfhZmUelVe55XsLeZW+8l+yBAaTcnNsSWNL2eZ9EdVZ2IwoCL+ESXkRwf5pTJ8cnbsYrwhjSIUT2Gjz6
C+FrPDlVl7wRwDHoYAde01xCAz4aOsw/
vbc1iU9/1prGHqFhOWtgss9vWf7iC40e6H77ngjthgSBTPuS6VTVJcmrVlm0ZSFOnUp3GgLzsy4L05zZwDa
tCmcTRjLxpMP+1y4y+lftRuWUiQOZCQBakGa26qwEOfA/x1pWRSAA8VXFxb+
+WfTHrTqUthvXt5KiKAQUM2/pKAUCgonGuosaNjfjpEXe5GJpQoCbSkvITYZgs5uhKXJjqQ/
BggMpnobnFvqodRujpUCUj2n0wmFQoHp6emCx6enpyvu504kEvjxj3+Mz3zmMxVfp6OjA06nE+fPny8ZhGs
0GiretkKCQoC9ow5c4sjG0lBolXB0ei6a3tvLdTZuwBcG2yFd0K50LK3FPw234QMN47izilTkr4204ERMDu
IvnGh/MWyDWuD406bxucd2GRP46tZenE0YMJHRQCNI2GuKwbxGe4/bdWm06wrv/
yYz6pk+26VJYDgeM5X8vjerrrhAwcEwma3t73NGYqivqpMJw822IB71u6qeq77GUjwLTOTAiZgJExk1HKoc
rjRHsZ71zhQaFbQWPdKRMtl0DDA4zYsyV8naoiD8EpVLZnHu0aNIh1eW8lqIb8i0ll/
7XVhqpcxiJDBMLbhgnE0Yq9rPPLvKudWQwJ80jeFkzIQnA0tfcdhjjOJMwlS2pzkD8GTAgT9pXH6bKJsqjy
5dAv0pfcm9agL4TBuSlWEM+FDTGOyqHB71uZBdsALvVmfxgcZx/N/
hlgoXc4ZQXoWJjAZNK5h8qBbnQCivxCM+F54N2pGSFFCA42prGL/
n8qFtwQ3N2YQBk5lqisQsJoDjYZ9r2UG4tc0lp6SXucNQ6dXY+farkfRFIeVFaCx6aC16jL5yflEAPocDqU
Acjm4Puu/et6yxkc1DrVZj//79OHToEN785jcDACRJwqFDh/CRj3yk7HN/9rOfIZPJ4D3veU/
F1xkbG0MgEEB9fX0thk2K4Jxj/
NUBeV845K1inHNMHR2GraMObTdu25DX8NUmceAbo80QOVt0zZv9+gcTDbjCEoGtTIHOgaSubMEzDoZngna8
pc5b0KmEMXlVfIcxscJ3Uhvl7jEWEsscpxGqa4G1sKXpSiRFAT+b8uDZkA0ZafZnuPh9HwPHDkMc7/
BM41zSgP6kvsKKPcdt9uLdZX7ldeI/
pz0F9y4KSLjNEcT7GybWZaGZMYa63c0YebG39EEcqKOtY+uOgvBLiCRKkHIiFGoFBp45VX6WbDk4NmQ6Wzi
nQm0KoHEYhPnZ6cMRS1Vbbpu1KbzV7cV+cxQCAy43R+FQZRHKqapKZRfA4VZncI8rgBNxS9ljJTCcLDM7Xa
03u734x6H2Et/lYIzjbtfiIn3LITDgnZ5p/L7Lh1NxI
1KSgDp1Flv1STC2eDWhlFyVNw7LMZTS4lGfE7+LWJEteB35zyIYXgpb8UrYgv/RNox9M4Fzf1K/
xFZ28yQw9CSMyEqsoLd8tep2NsHfMwHOSz/XvbsFCpUCpob5/
BVJlODvnaj4g+09PQb3LrqIXwruu+8+vO9978OBAwdw5ZVX4qtf/SoSicRctfT3vve9aGxsxBe/
+MWC5333u9/Fm9/85kXF1uLxOB544AG89a1vhcfjQX9/
Pz72sY+hq6sLBw8eXLP3damZODKI6RPz6cMLPxtCg15wUULnHbvXY2jr6kTcWHHllwN4Nmgvu0Xot2FrVVv
NXolYcE+Nrp+roU6dhUYQFwSzizFwtGpLZ1DWazKoU2fgzapRrq3pVSVWl5ciKQr4dH8nxhe1Xbuw+Jo8pV
KnzuK/tYxCLXB8omMAP53y4JmAHRm+MHiffTbDTbYQ3ldkYePHkx780leHCy+WIhieDDgRyKrwP9qHV/
z+lsO5tR7x6QiCfVOLSyBxwLWjEbZ217qMjcyjIPwixTlHfDIM39kJJAMx5DM5iJmZGVyByVO/
tcQAc6N9XVLahpJa/
KfXjcGUDiJnaNCkcaczgP3mKJQMUDMJtVgJB4BrrPMXjJQklFwpXuigM4ArFuwnUzDgb9uG8NmBjhIVyOWx
zrbUcqqzuL9jEBNVVfyszT/tfnMM728Yxw8mGhYUQ5PfrZJx/
HXr8IpS3ovRKaSCv6dZLdo0zidLr8oDgIpJcFfR8mU5Xo2Y8dXhVgAoG0xzMIgAvjrcgm/
uOAu9QoLAeMVJmkrynGHpDfEArUWPjlt3YuCZ0/LN9txFWK5g59xaj7pdTchEU/
CdHUd42A9JlKC16Mq3MZqRjaUhiRKls10C3vnOd8Ln8+GTn/wkpqamsG/fPjz++ONzxdpGRkYgXJB/
2dvbixdffBFPPvnkovMpFAqcOHECP/jBDxAOh9HQ0IA777wTn/3sZyndfJXk07mCAHwRDoSH/
Uj4YzA4Vz6Ru5mMpHRVTZZWan0VFxUVP6kFcMRXofd3LWkEjpttITwVcJT8O+FgOFikJeksgQG/7/
LhO+Olqu3LV/Ry56jWz6fdRQLwWWzm//
lcMdbbHAEYZvqUawWO9zZM4h2eKYykdJjMqDGU0iElKeYK6hXrOhPMKfFLn6vgNS58zSMxC07HDNhpWvsMB
8YY2m7cBkuTHd5TY0j45Xsro9uCul3NsLY6wWg/
+LqjIPwixCUJg8+dRWjAW7w6cq0DcAAKtQrtt+yo+XnLyUoM/3e4BUdis6vDcvAazqtwJmFCiyaF/
9U5ALsqh2C+/Cx3JQI4zMo8rrfNFxBp1GQqpjEBKLo/
qVWXxt939+HxgAPPB+2IiwqYlXnsMCSQEhkiogomhYhrrWFcYw1DLXCoBanijYIAjq0rrKo966AzgMvMURw
KONCX1EPBOHYZ47jFHlyz/
WoAcKcjgL6koeT3BXBcbw3N7LWvrWBOif870rKEdnIMGS7gNyEb7nIGsMOQqGqipji5V6uuyrS+YqxtLux8
+1XwnZ1AZNgPSZKgd5hQt6MRxnorIiMBDBw6VRCk55LVT65ExwKwttJs+qXgIx/
5SMn08+eee27RY1u3bi2ZhaHT6fDEE0/
UcnikgtCgt3LxVcYQ7Ju65IJwZRWTpbMT0OXYVZW7hEhgsG2CAl9vc0/
jRMyI6axm0T0HA8flpiius4bLnuNWexBTWTUe9tUV3LsIM9l0/71lZMVbyLKSnOJfKZ28TZvCF7acL3mMVu
DYYkiiW5/EtdYIlIyXTSV/
3F9d1udPp914wDRQ1bG1xhiDvdMNe6d77rOYAu+NhYLwi9DEkUE5AAeWVx15GSwt9jXp9b3Qg6NNOFKw/
6rww2Uko8Vn+zswltGt4FXkwN6szON/
dQwUBHq3OQJl25QxcLhn0qqLcahz+MP6KfxhmWrdC1mUIq6yhPG7MhVHJTDc6ahdH8s6dQ5/
UOX4Vsu11jBeCVvwesy8KKAVwOVe3p7pEs9emWeC9pl9b0u7cPUkDLjLGUC7PoUufQIDJSdrSmdozK4SrPS
aqTHp0HRlJ5qu7Cx4PB1JygH4hTfmS/
jM8J4epyCckE0gl8rOZcGUxuXjLjG7TTHwyYayx0hg2FuhXdgN1jB+4XWXPUZgHNdUCF43AqNSxGe6+vGTK
Q+eD9mQm9nzbFLkcZfTj9+v81YshMoY8If1U7jKEsFTAQf6k3ooGcc+Uwy3OwJwLqO16YX8WTVSZdLmAXnN
fThd/
j5wMqPGIz4XXgjZkOUC9IKIW+xBvMHlg71IHYD+pA7V3BeMV8ieWCsUfG9MFIRfZMRsHt7TYzU5l0Krgslj
RXjIV/HYTDQN/
7lJ2Dvq1qSwy1hKg5cjleqwM4xldHNp3ct1rSWEDzWPLdqX26lL4WZbEM8Vqew9W97lTxrHa1qY470Nkzif
1COQK6w8Ovse762bRneNVsI3CoEBf902jF946/CE34m4KH9sKZmEa61h/
IFnCtYyxXJW4mTMtKKfHQD4q5YRfLq/E+ELagCwmfY1xX4+BXC06VK4qwapeqX4zo6X3S9ejdhECEd/
8BvoHUa4tjfC2uai9HRCNiCVTl0hAAcAJh93kZG4vK1HVWJ1s1mbwU5jDGfjxqKTpQI4jMp8xf3LDdoMbrH
Jk/
OlrhtvrvPCtIaZZCthVIr4k6ZxvLt+EhMZDRSMo0mbhnKJl8QufQpd+trcl15IUWVht3LH9Sb0+MJAB/
Kczf37JyUFHvM78ZuQDZ/
s6IdBKULJOIwKEYyh6jotQo0Kz60lzjkS3igykSQElQLmRjsUagoXVwP9rV5kYpPhgnZDy8UEhl1vuwqCUs
CJH4UgZssHOQlvFInpCEZf7kPbjdtXveDDQxPlZ63nrSwABxjucfmLfuAyBnxwtrK334n0gtnYBk0G728cx
64aVzu1qvL4XPd5/
MJbh2eD9rnXbNGm8ft1XlxrLX+TsFkpGfA2txdvcvkwktbO7P3PwLjKNzPLvXxuWZD94FLn8MXuPjzhd+JQ
0I5IXgWtIOI6axi32oJ4PmzDc0H7XHVVjSDiFlsI7/RMQbOMgmzVCg/
5a5IpI+VExKciiE9FoHea0H333jXPiiGElGdrr8Poy33lU9I5h727fNu5zeR8UoeHfS68GrFAAoNZkcMdji
DucvoXXTs+0jyKzw50LKi9Mp86rVOI+HjbUFWB1580jUMtcDwVcIADEABIkIPAN9d5cW9d6cJuG5VOIaFTn
1rvYRTlUmfhVGXhL1OAVwDHbmO86PeyEsOXh9qQK1IZXwJDXFTgf/
ZtmQvOW7UpvMHpg1lR3Sr+vgrZExtNdCKEkd/2IhOZ//dmCgF1OxrReEUH2Hr2XrsIURB+kZHytQlKmq/
unuv523rDVgwcOl3+CTMz7FJOxMAzp9B9116YG0unaq9EWmLoSZTeI1xo+QE4A0e7LoWOMhcfgQFv90zjjX
VenI4bkRYVcGsy6NSlVq01hVkp4r0Nk/gDzxTCeSVUjK/
aSvBGoxL4mt4MdOuTVe37nyf3cr9xQe0AQP43e7tnGm/3TEPiKEjj6zCk8C7PFEZn0tZatGloV2F/
+4UksfavkfTH0Pur17H1jZdBqb34VtQI2ayUWhXcu1swdbxEtWYGWJodF81+8JfCFnx9pGVBYVEgKqrwX94
6vBi24tOd/
bCq8hhOaXE0ZkJOEvBmlxcxUYHngnYEcmoYFCJusIVwuyNQtjXZQgoGvL9xAm+u8+KViAWxvBI2VQ5XWyKr
Pml8KRIYcI/Lhx+UWZiRwHC3q3hG5+8iFsTE0qEQByuYqx5Ja/GtsZYqRiY/
6y1lqumXMprW4NzMPe4WQ6LmRXBLiU2E0PfY8UUZM1yUMH1yFNl4Gu237qTU9hqiIPwio7GsvDq5qdEG147
Gua9t7XXoOqjA2OF+pENVrOxyeV/
6agXhx2MmiFjt2TgOkyKPv2opU012Aa3Al93PeblUAoerBnuqSGm32YN4tMoCLLP+uHG87M1WsX10OoWELW
u8jUBnNyA2ka153Yh0JInjP/
wtmq7ohHtPNTcrhJC10HCgHVySMH1qFMBsn3AAnMPa6kL7zdvXd4A1Esiq8M2RFnCg6OqmL6vGN0eaIEHA6
YRRLhQGDhECjIo8PtQ0hgNFOnUshVWVx13O2tVnIaXd6QhgIKnDC2H7ogJwEhje7ZksmZV4Jm5cUhvRpWRW
/
knjWNHK6qX4sip8c7QZPQkjFvYU26aP4y9aRlf1fo9zjpHfniu7ZSU06INrMlzQ0pSsDAXhFxm9wwidzYBU
OLHsm2uNaXEBC0uzA+YmO1LBBM4/
cRy5ZPkPloQ3ikw0BY15JUXRiovllahVy7Hi5Mqff9o0XvXsN7k4NWgz+KP6SfzbZEMVtQU4rjZHcJsjVOa
YjaNuRyNi42XGygC1QYNsfBmz8BwYO9wPQaWAa3tj5eMJIauOMYamq7pQt6sJwfPTyMYzUGqVsHW4obNVm1
228T0TtC/
o9LyYBIaTCdPcVL4cgMnHxkUFvjLcivvbB7HbVDyFmWwsAgP+vHkM+y1RPOl3oj+pg8CA3cYY7nb5sa3MBP
fqbPjiaNcmcT5pQCyvwk32YNHibguFc0p88nwXovnZsGz+Z/dc0oBPnu/
CF7v7Vi3rMeGLIh2psBDAGHy9E0WD8Ew0hfCIH1JOhMaih7XVSfVhqkBB+EWGMYaW67bg3KPH5LJPy/
iE0dmNJc+tdxir6iEMyNVYVyMIl9uArF4AblSI+Ju24YqVP8ml4Q0uP1zqLH7prUN/
ajbTRP7FWrjf7x6nH+/
0rG8l+aWwtDhhbXMVL7zIAIVaiS1vuAz5TA69Dx8FX0b6+sSRQTi31tM+MkI2ELVBC8/
e1vUexqo5XaLAWiGG4p9ocl/
XH0168EVT6ZZWZGNhDLjKEsVVS8xg6NIn8Xyo1iu7DINpPYbTenAAP5t24173NN5a5y25TfFhnwvRvLLoz6
0EhmheiV/
7XPijhskaj1WWiVaxzY9zpMOFgbqYzWPohR6EB2fuI2Y6MCjUSrRctwX2zvLdAi51FIRfhFQGDRqv6ID3zD
iysfSSnssUAhxd5X9plDo1xFzlX9jVqrK6xxiHmknILqN1VGUMcVGJE3Ej9tEsOJlxhSWKKyxRhHJKpCUBG
kHEiZgZoZwKZmUeV1oiNal4m5MYfhex4DchG8J5JeyqHG6yhXCFJbLkirSVMMbQcesOTB4dhvf0WEHxRUuT
A83XdENj1kEDHeyddQj0TVdRXblQPp1DdDwES7OjtoMnhJASVrq6ycEwlNZjNK1Zs/
24ZH1cZw3jh5P1SEsCans/WTjJ85/THugFCW9wLe54InFU7HUugeHZoB1/
WD+5KgtEClV1XY0WVknnEsf5J08gPr2gIPDMPYKYzWPw2TNgCgG2NmpjWgoF4ReRVCiB0Zf7EJuYTzEVVAq
Ym+ywd7qhsxsQPD+NydeHSp6j9fqtFVsROLbUY+K1gbLHGFzmVVkFnzdbd3R1zu3LUlEpstjC7Qk322ubdh
7OKfH5gQ6MZbRzqe/
jaS2Ox8xo0ybxiY7Bmre2YYKAhv3t8OxtQcIXAxclaG16qA2FvU3rdjYj0Le8Vf78Jdh3mBCyfrYaEji/
pIKaxQVzKgrCL3I6hYS/
bBnBl4fagCXsDV+On3vrcLsjsKjKflJUVOx1DgApSYGkqFiVAn+mBhsEpVCxu5KtvW7uz5HRAOJT5TvyjP3
uPKytTirmVgIF4ReJVCiBnl8dWVQdXcqJCA/
6kPTFkI0vWBWXM67m6BxGNB7oqGrFyrWtAb4zY8ilcsVXxphcAGa1jKY1yPLV7EXOoBdWvzo1ufgkRQFPBx
w4FLQjkFVDq5Bbkd3t9MNTpkAL58A/
DrXNtceZ3Xs+e0Mwktbha8Ot+LvO8pNfyyUoFTDVW0t+X+8wou2GbRh6oWfJy0xKPU1oEULWzm32IB72lVt
9my96VY5JQdXMLwWXm2N4oOs8/
mu6DkdjZnCwmYlwoJar4wlRiZNx46IivhpBqqLmjNyxR71K96YKlRJ1O5vLdk9QalQFmbL+3olFscSFsrE0
4tMRmDzWmo73YkFB+EVi9KVzcgBe4pehIAAH5o4zNVjRfO0W6KzVF2VRalXYcs9l6H/qpLw/
hDF5G4jEIagUaLtx26pVRgeAlyPWVTs3AKiYhH3mlVVGJZeecE6JB/
o7MZ1Vz128E6ISTwcceDZox8fbB7GjRIXW3qR+wX7zxSQwnE4YMZjSol23tC0mteLYUg+dwwTvmTGEBrxV1
YYQVAro7EakgnHkUlkotWro7AaaFSeErBq3Jos/
bhzHd8ebFlW+FmYCmYwklIkdONzqLNp1G7M3Nqm9Ln0Kf9s+jKQoICEqoBVEfGWoDT1JA2oZiMfyi8MulcB
xuTmKo1FzyZV4ARyXmaNV9apfrob9bcgm0gien57b2z1LqVVhy937oFArIeVFREYDSPpjVU3K55ZT3PUSQU
H4RSATTSE2GV7Wc2MTYSR90SUF4QCgteix461XIjYRQnQsCC5x6OxG2Drqqt5bsly/C1uw/
OroHBomIceFEh92HHc6AjCsQZ9mcnH51mgzvFl10ZY4nANfGmrDN7afhb7Iz9ZLIWsVbVI4Hva68JetozUe
efVmV8TbbtgGKS/
izH+9ikyk9I2qlBNx8kcvFTwmqBSwddSh6cpOKDWq1R4yIeQSdLsjiLqZgppnEnKxWY0g4mZbCHc4/
PjcQGfJQlgAw9vd0yWLaJGLl14hzV2jP94+iI/0bEdcVKBWgbhVVbzN2O+7fHg9akbxe1t5Vf73S/
Q6rxUmCGi7aTtc2xvh65lAOpyEYuZ6be+sg0KlhO/sOMZfHSioIVOJQkuhZin0N3MRSFXTu7uMsd/
1w9Fdv+TnMcZgbrSv6qr3hSQOeHOaZTxT/mC7zBTBexsm8feDHZjKauZSgGYDoBusIfxB/
epUnyQXr8mMGifippLf52BISwJeCNlwcEHv2OGUFj+frsPhqAXVXORfjljxhqQfnfr1X6ERlApse+N+nHvs
GFKB6osYSjkRgd5JBPum0HbTdqqeSsgay6dzCPRNIRmIgQkCzI02WNtcF11LoT2mOPaY4kiKAtKSALNChHJ
mJfGTnf34P4Pt8GY1UECa6RQufwr/UcMErrOF13PoZAMYTusQFyuFSdUuCHFYlHnsNha/
Vm4xJPGXLSP4xmgzJF64YUJgHH/
RPIotZVqt1QpjDEa3BUa3ZdH3vGfGMPpS35LOp9AoYaqnvuKlUBB+ERCUK7tw5tM5ZGJpaEzaygcvk8SBYz
ETjkbNyHKGJk0GN9mDMC+xwAQDoGASRF7te+bQCyK2GJK4wxHAPlMMAgO+tOUcXo2a8buIBUlRgTp1FrfYg
xsiuCGbz6m4EZUuxgzAybhxLgjvSejx+YEOiFVX+Zc3Xz042gQOhnBeCZNCxE32IG6zB2tetK0auWQG6WVO
AnKJY/
DZM1BqVWs6kUfIpSzQN4XhF3rAJT7zscMQODcJlV6NroN7oHeUnkzcrBaubs6q12Txla29OBo142jMhJwko
Embxk32ICzr8FlKNp5QkdTxxWY3RZfPYgMY/sAzBUWZw66xRrDdkMAzQTt6E/
L2tK2GJG61B1etP3i1xFwe44f7l/
y8+svaLrrJvVqiIHyT4pwjNhGSU0EFBkGpWFSUbSlSofiqBeFTGTX+frAdU1kNFDNpNRzAT6Y8eG/
DBO5csDJYCWPA5aYojkQtVVexfG/DJG66oJK1UuC4xhrBNdbylR0JqYbIWaX6JOAzxwFAngP/MNiO/
BLb7HEwjGVmf08ZEqICP53y4Am/E5/s7Ed9meJvq2HqxMhSu5YtMnFkkIJwQtZAZDSAoefPzj/
A5/4PuVQW5x45hh1vvRJqw3KyzTYfBQMOWKI4sMTe0uTSYK6qMN/sBrRihdXk3y014/
ijhvFF96HFWFV53Ov2LnGkqy806KtYOX3OzM2QZ18r6nY2req4NjsKwjehyGgAwy/
2IpeoXbEDthqNByFXi/
5sfwfCeXnvp7jgQ0oE8P2JRhgU4pJSv+5x+fFqdHGqTDFqxnGlhQJtsro6dKmKlU0FAJ26FDgHvjXSVFVLk
uJYwZ85gGheib8fbMdXtvauSg/
RYrjEERrwLrl3+IUS3iiy8TTUxtXLxCFkI0r4oohPhsEBGOrMMLotq1q0cOL1wdLf5PJql+/
MOBqv6Fi1MRCyWWw1JGBT5mZWxEv/
Xr7R5cXLYRt8OfXM1kYAYHCqcrjb6cet9iC0m7zOUDaWBmMMvML1Xm3QwN7tgXNrPTSm1WxTfHGgIHyTiYw
FcP7JE+WX3CotyV14uMBgrKsuqF2q50M2hPKqMgEKx8+m3bjWGi5ZBGU4pcVASgcBwA5jHFsNSXywcRzfGW
+s2ELi7Z4p6Db5hx/
Z+Lr1STRrUxhPa8tmaOwyxvCxc90Yy9T24iSBYTqrwfGYCZdd0P5ktUh5UU5prYF8OkdBOLlkZKIpDDx7Gk
lfbP7yxQGtVY+OW3dCZzfW/jVjKfn1yuFyujoF4YQAAgPe4ZnCP481F/8+OFzqLO51e/
FOzzROxY0YSumgZBy7TbGLqse8QqOsGICDMVhanGg8QJ8f1aIgfBPhnMtFESr8HuidJuRTWQgKBYz1Vvh7J
soe79reCIV6dX4UfhO0VRiuHDwMpHSL9mOPpTT46nALxrMLAxaO/aYo/
qx5DFsMCTzhd+ClsBXJmVVFAYAEeQX87Z4p3OP01/YNEVIEY8BfNI/igf5OZKXCyvuzxf/
eVT+Jr420IlLVPrOlU0DCsTUMwgWVAoJKUVWrskpUFXqJizkR2XgagkKA2qSlFmdk08ols+j59evIp2eqJC
+4QKYjSfT++nVsf8sV0JhrO1GXz1S3pzSfKV69mZBL0c32EJKiAj+crJ/
Z2S13ERfB0KRN42NtQ9DMFPubLQS4XNMZNZ4L2TCZ0UAjSDhgjuJyc7TsPvK1YmtzYeyV8+UP4hy2DtfaDO
giQUH4JpLwRpGJVigcxhg0Ri22v+nA3EOmBisGnz1TNHg31VtXddY7KpZP45kVEwtTc0/EjPg/
g+1FVtAZXo+Z8en+Tnyu6zz+pGkCf9I0gVBOicMRC2KiAg5VDldZIkVbQRGyWtp0aXyu6zx+Nu3Gq5H5mgU
duhTudU/
jfFKPaF5ZMW29tErFX9jcnvO1wBiDc0s9vGfGlpR5U3gSwNxoh0pffA9qPp3FxJEh+M9Ngovy77PapIVndw
uc2xsoGCebzvSpUeTT2eK/MxwQ8xImjw2h7cbtcw9LeRHpSAqMARqLflmFjlS68hNdsy6V/
eCEVOsNLj+us4Xwm6AdkxkN1DMB8k5jvCZt7DgHfjrtxi+8dRAwf6X/
TcgOjzqD+zsGUKde38kxtVELe7cbwb7p4gcwwOA0w+ixrum4NjsKwjeRigE4AHCO9AXH2Tvc0NmM8J4eQ3j
IB0mUoLXo4drRCEeXG0xYvcqFDlUOoVy5dHTZt0ebsMcUxw5jHO3aFL401Fbyvp6DYTKjwaGAA2+sk/
sm2lT5gtZPhKyHRm0Gf906gnhegVBeCb0gwTFz8fyXsaaqiwkWV/
65IoAWbXoF5186955mBM5Pyz1Dl7E3nDGGhv3tRb+XS2XR86sjyMbTBQFLNpbGyEvnkAzG0XLdFgrEyabBO
Zcz08pWcOQInp9Gy7VbwCWOidcH4e+dnMs4UWiUqNvRBM+
+1iUF42qDBqZGG2ITobKv79y69HalhFzsLEpx7n6z1h7zO/
ELr9yqc3bpaPZX1JtV43P9nfjS1t65Fff10nrdVoiZPCIjATn9j/
O57a9aqwGey1qRiaagtejXdZybCQXhm0i1KePKIsepDRroHUZ5NYkBJo8Vto66VQ3AAeBmWwh9ycq/
kMG8Gs+F7HguZEdhh8TSngrYV+1DkZCVMCpFGC9ocxNdcRp6ud8LDjXjuN5WufpqLakNWmx742XoP3RablW
2oB4FExg0Zh2UOjXi0xG5TyEwd4xS
p0bHLTtgcJmLnnvscD+y8UzJgMHfMwFrmxOWJkfN3xchq4FLXJ6wquK4TCyNwWfPIBWKF/
wOiJk8Jo8OIe6NoPvgniVdwxsPdKD3168X39vJ5PsE57aGqs9HCFmZvMTwX966kt+XwODLqfBS2Ipbqqiuv
poEpQKdd+xGwhtF4NwksvEMOOfIJeRWpf1PngQgb4ltONBO1+YqUBC+iZgbbVXtwbR1ugu+Dg/
7Mfjsabm9wMyqUeDcFEZ/
dx5dd+xe1fSR620hPOZ3YiKjWcIqYHU9k325xel1E2kNxjIaqBjHNkOCirKRDcOgEBEXV/
KRK0evs3vM5x+V2/59sGlsXbZgaK0G7Lj3CiSmI4hNRQBwGOssMNZb51apOedI+KKIjYfAJQ690whLs6NkA
JFP5xDqny6/us4A3+lxutCTTYMJDExgVRU0DJybXBSALxQbD8HfMwnXjsaqX9/
gMqP7rr0YfO4McsnszP0AB7h849x52y4oNaqqz0cIWZkzCUPF+wIG4Leh9Q/CATl7zei2wOi2IDzsR//
TJxcdk/THcP7xE2i/
ZQfsF8QjpBAF4ZuIoFTAvbsZk68PFT+Ayfu+Fv7QJ7wR9D99av5mdsFNrZjN49xjx7Hj3itWLX1ELXD8XWc
/
vjbcirMJIyrva13Cudl8wDGa1uB7Y43oSRoLvn+nI4B3eqagXOc0HkJutIXwuN+5rJR0Bo4D5igOOv34yZQ
HfUnD3PdatSm80zONfQsKsnEOjGU0iOeVsKtycK9y/
3DGGIwea8kJPcbkDgzVdmFIhxOVAxUut3giZLNgjMHW6UbwfJkJJgaYGmzwn5usWGvBe2ZsSUE4IJ9797uu
QWQ0iGQgBiYwmBvtJTNSVopzoDephy+rhk6QsMsUg5aux4QAAOJi5ValHGymvtLGIeVFDD1/
tuxn1PALPbA0O1at8PPFgP5mNpn6y9qQS2blfWWzezJmKDQqaMx6HP+3F8A5oHcawUWOkr8lXE57mz45itb
rt67amC1KEZ/sHMDTARu+O1681cPScVxplvt/
j6Y1+OT5LmSlwlW1LBfwiN+JiYwaf9M2vGb9kwkp5i6nH88G7chcUD1dJk9OKSEhD2Gu16hc7Z9hjymGv2g
ZgVbg+ExXP6YzaoTySliUedRfEGC/ErbgZ9NuTGTmW35t1Sfw7vpJbDEkV/tt1kaVv6yMfqnJJuPZ04JQ/
3TZJA/
XtgYMHDpd8VzpcBJckpa8rYwJAqytTlhbnUt63lIdixnx0HgjprPzxd60goh7nH7c656mazK55DlUlQuuCe
BwqVZ3In2pQoO+iltrpLyEYP80XNuXNlF4KaEgfJNhjKH1+q1wbW+Av2cS6UgSgkoBxhjCQz7Ep8NzMXfFn
qAAwDkCfVNrUuDowmBh+eQ3+PtueT/
4v000LGoLNX8kw+sxC45EzbjCQqtmZP241Dn8r44BfGmoDZG8CsLMz7EEQA0Jf94yiqssUfQm9XghZEMkr4
RVmceNthC69cmCKqxuTbbo6vaTfge+P9GICyfeziX1+Ex/
Jz7ePohdK2ihUitckhAZCyKXyECpUcHcbIdCNX850tuNlbfeMAZzk30NRktI7ehsBnQd3IP+p05Byhf+fDO
Bof3mHTC6q8sYkZ+0MSPZo1ETvjTUtujxtKTAf3rrEM4r8adN42s/
MEI2kC36JNzqDKazapTKEpXAcKsjuLYDqyAVjFfeWsMYkoH1v9/
YyCgI36T0DhNarjMBAKLjQfQ9dlz+xjKyvLgogUscbJWbEbZpU1AxCTm+0mJwDDfagmjWZuDLqnAybip7tA
COpwMOCsLJuuvUp/D1bT34XcSCMwkDRM7QqU/iemt4rn7BNkMS25axYj2U1OKhidmiSoW/
yxwMEji+OdqMr28/u64rUIFzkxg73D/fJxmAoBTg2dsKz75WMMYgKBWo29GIqeMjpU/
EOep2NK3BiAmpLXOjHXvefS0C56cRnwwD4DDUmeHorodSqwLnHFqLHulImc8BBpjqbRuyO4DEge+Oy6tfxT
ujMBwKOnCbI4B23dp2dCBkI2EMeE/
9JL483Ipi2zUFcGw1JHCZqYpFtTXEBKGqhijLaad4KaEgfJOR8iKyiQwEpQIqvRqMMXhPjRVUJV4qhVq5qm
md55M6/MrrwpGoGVJBF8Tl4FAzER9sGgMATGYq9zSVwDBWxXGErAWlwHGdLYzrbOGanfOXXhd+MuUp3/
kIDKG8CsdiJlxuXp8Lur93AsMv9C56XMpLmDgyiIQ/
is7bd4MxhvrL25H0xxAdv6AYzcw2nJbrtkDvLD8BR8hGpVArUbejEXVF9nQzxuDe01z0d2UOB9y7a7W9q7Z
Ox40IFCmcupAAjmeCdvxJ48QajYqQjemAJYq/
bhnBd8cbEROVEGaKrXIAV1ki+LOmsQ23dcPcbMfU8eHyB3FO2WoVUBC+SeSSGUweHYKvd3Ku1Y9Sq4Kj24P
IeHDZATiY3Bd0tWbTXwhZ8c3R2RsFtuC/yw/EO/
UpKGeeqhGqqwZd7XGEbDZPB+z48VS1vX05vjzUinpNBt36JK6zhbHTkFiTjFYpL2L0lfNlj4kMB3Du0WPov
msvBIWAroN7EOibhvfMGNKhBJggwNLsQN2upoKUXSkvQsqLMxOKNPNONj/
HlnokfLGZ+i9Y0KFQnoRq2N8OS/
PG7AwwlVWj0jVeAsNkmibHCQGAq6wR7DdH8XrMhMmMBhpBwn5zFC515T3j68HotkBnNyIVShQvMskAjUlHQ
XgFFIRvAtlEBj2/
fE1uKbJAPp3D9MnR5Z+YMSg1StTtWp3Z9OmMGt9aFICjxNfVYuhNGJGVGNQCR6cuBaMiX7bFgwCOqyyRZb4
eIRuXyIH/
mF5KCxAGCQzjGS3GMzo8F3LApcrgb1qH0apf3bTQ0KCvYntFAIhPhjH+6gCar+4CEwQ4t9bDubX4JEPCF8X
U8WGEh/
0Al9PaHd0eePa2Qm3UFn0OIZsBYwwt122BpcUB7+kxJLxRsJkU9LqdTTA12NZ7iCVpBQmVrvEMnFqIErKAU
uC4cpNsm2SMofOOXeh9+Chyicyi7yu1anQd3LMht8tsJBSEbwKjL51bFIAv2+wvBOfQWnTovH031IbVmY1+
OjA7S1/bX0IJDElRAbWQh1LgeKPLh3+f8hR9HQYOJeO43b6xiloQUgtnEwZE8svp6zv/u+LLaXD/
+W681T2Fe+t8q7YqnomlFnV0KMV3dhwNl7eVbW0i9yg9hdk+x4Cc1u7rmURwwIutv3c5dDZDyecTstExxmB
tccLasrpVzGttrykGBSSIKJ2VwsFwJU2OE7JpaUw67Lj3Cvh7J+HvnUQ+lYFSq4ZjSz1c2+qh1JbfkrKQmM
0jNOhFOpKCQqWAtdUJnd1Y+YmbHAXhG1w2kZZXeWrA3uWGxqxb0NPXsqqzVCfixhJFWVZGySQYFfMrar/
n8mEqo8azIcdMayc5d48BUDOO/
9E2BMcGTekhZCkkDhyPmfB8yAZfVo1KrbSrxQH8x3Q9IjkVPtA4sSqBuEKtrCoAB+RikbHJcMkWSvlMDoPP
nC5+Ps4hZkUMPHMaO+69gmbiCVljZqWIW+1BPB10FL0HEMBhVeUoQ42QTU6pUcGzpwWePS3LPoevZwJjr/
RByktyxXXOMXFkEOYmO9pv2QGlZjkLDZsDBeEbXNJfu/
L+6UgS7TfvqNn5KqlVgLCQAI4brCEohfmTCwz4YNM4brCF8VTAjuG0Dmom4QpLFLfYg7CpyvcyJGQzSIsC/
mGoDWcTxoLJptqQb5SfCjpxwBLFnlVoY2ZtdWGswp7whbhYOlU12DcNqcz3wTnSoQQS3ujS2j0RQmrijxom
Ecqr8FrUMvd5xWYKTlmVOfyv9kGohVW4SSCEbBqBvimMvDhfgHJhy7PoeBDnHz+BrW+87KKt9UJB+AZXy6r
l5W5qV8NWQxJjGS2Wk44uX6wXt2rQCBJ+v863+HgGbDcmsN2YWO5wCdnQvjXahN6EnF4tFRQ5BFbWcWAeA8
eTAceqBOEakxb2TjeC/
dNVHa8tk0oen65iBY3Jx1EQTsjqGkjq8EzQjrG0FlqFiCvMUVxnDeO+1mGcThjwTMCOqawGBoWIaywRXGsL
QUsBOCGXNC5xjB/
uL3OAXPclPBKArc21dgNbQxSEb3AGl3lF7cfmMAadY233V9zuCOBQcHnVWy3KPMJ5FYSZNy6BwanO4q9bh+
HR1Gh/
PCGbxHRGjcNRa5kjajNZx8HQn9TX5FzFtN6wFeloEklfmRZpDDA4zeX3c1OGOSHrTuLA98YbcSjoKFjtPh4
z4afTbnyifRC7jAnsoslxQsgFYpMh5FIV7ucZEDg3SUE4WR9yG7J6BM5NruxEnMO1bXE/
0tXUpkujXp3GZHZpVYpVTMI/
bunFYFqHnoQB4AxbDAnsMsY3XK9EQtbCq1Fz0eyQQrVZDRfY6q1QCUoFtr7xcvQ/
dRLR0SLFEhkgKAS0XL+l7HmMbgtCA97yL8YBo4dWwQlZLb/w1uFQUG5BNJudM/
sZFc8r8YWBDnxlWw8MVAWdEHKBqgpOc7lD1MXq4kyyv8g0X90FrbX86hRTMAhKoeQ9uGtH47qkZW4zJsCWt
IzPcbfTD4NSwi5jAm9ze/E2zzT2mCgAJ5eutCTMZYWUt9IAmmO3scwqdQ0IgoCuO/
eg8YoOKDSF88BGtxWdd+xBNpZGaMiHbLx42zRHt0f+vCuFATq7Qc4kIoTUXFZieNjnQqmbDgkMMVGBF0Ibt
5UaIWT9KHXVFVy7mAuzrUkQ/o1vfANtbW3QarW46qqrcPjw4ZLHPvTQQ2CMFfxPq720+70q1Epsf/
MBuHY0Fr3eKbUqbHnDZdj2pgMwN9oLvqfSqdF0dRear+leo9EWutEWqqpC+mygfqMthHd4plZ7WIRsKh51F
mLFvrtAuzYFJVvJqhNDlz61gudX+SqMwbO3FXvefR223HMZug7uwbY37YfKoEbf48fR//QpDDx9Cid//
DJe//
7zOP2fhzF1YgT5tNzlQKFWouO2XXIxiAurnzP5ot1x6y6qjE7IKjmTMCAlKcoewwG8HLauyXgIIZuL3mkuP
5k+Iz4Vhr93Yg1GtPZWPR39Jz/5Ce677z48+OCDuOqqq/
DVr34VBw8eRG9vL+rq6oo+x2w2o7d3vloe3UjJaZwt125B01VdCA16kfBGAQBGjxXWVicEhfyD3H3XXmTja
WSiKQhKBfRO47pWFdyqT2KPMYZTceOCYlKF3Ko0dpkSuMUeROcaBACEbDZXWiL43ngjUpKAcinn97UN47+8
LjwTXH5f4Uhu7XYpCQoBpnorxGwePb9+HelwYtFiPhclpEMJjB/
ux9TxYTTsb0d8MoxMPANjnRmccyR8MYBzCEoFnFvr4d7TDLXh0p68JWQ1pcTyAbiMISlSwiUhpFDCF0Xf4y
cg5SsvGnCJY/iFXjCFAEeXZw1Gt3ZW/W7rK1/5Cj74wQ/iAx/
4AADgwQcfxCOPPILvfe97+PjHP170OYwxeDwX11/0cnFJgpjNQ1ApISgECDM/
hI4uDzLRFPy9EwgP+iCoFLC1u2ButENt1EJt3Bg3oIwBH20bwjdGWuZalbCZAi4COO51e/
GWOu+q9CUm5GKhFjje1zCBB8eaUWrv95vrvHCqc5jIaEseU43/8Lrh0mRxoy28ghEvjffMWNEA/EJiJo/
Rl/
rmH5gpWqk269B1x25oLfqadpQghBTnVlfezymAo15z8e7nJGQjSooCXg5bMZXRQCNIuMISQauu+Nau9ZBLZ
tH32HGIuaW1Dx4/3A97h/uiusavahCezWZx5MgR3H///XOPCYKA22+/HS+//HLJ58XjcbS2tkKSJFx+
+eX4whe+gJ07d67mUDcMzjnCQz5MHR9BMhAH+Pxdqa2zDvV7W6G1GTD+6gCmT4zMV05nDIFzk9DaDOi+a8+
qrgLlJYZXo2b0JfVgALYZErjcHIWCAaGcEsdiJmQkAQ2aDBg4HvG5cDxuAiAXXWvRpnHAEsHN9hDMSnHVxk
nIxeQmewhKxvHDyXqE8vN7pPSKPO6t8+INTj8AIM8ZVlqg7Z9Hm7HTkIBDnVvRearlOzO+vO3sM8/
JxtIYfOY0tt97RU3HRQgprl2XQrM2hbG0tuSWMwkMtzmKFGAkhKyKQwE7/
nWiAVnOoJgp5vqfXjd2GWP47y0jMG6Ae25/74QcgC/
xmp9LZhGbDC3adruZrWoQ7vf7IYoi3G53weNutxs9PT1Fn7N161Z873vfw549exCJRPCP//
iPuPbaa3H69Gk0NTUtOj6TySCTmZ9pjUajtX0Ta4hzjqHnzpbsoxvq9yI85Iejyw1/70y1dD73ZABAOpzEu
UePYce9V86lqNdST0KPfxpuRTSvggJyGsmjfhesihza9Ukcj5khYXZuQL4wswWrchmuQH9Kj7ikwM32UM3H
R8jF7DpbGNdYwzgTNyKQU8GkzGO3MQ7Vgp67ekHEyiqly7+9zwTteLunup7eKyGJUnVVUsvhHKlQAtHxICx
Ny2uLSMr7xje+gS996UuYmprC3r178f/+3//
DlVdeWfTYhx56aC77bZZGo0E6Pb8awznHpz71KXz7299GOBzGddddh29961vo7l6f+iUrlYmm4D0zhmD/
NMSsCI1JC9e2Rji21kOhqiZ1e3NhDHh/
wwQ+P9ABFOncwMBxmSmK3cb4+gyQkEvMCyErvjM+HyctrCNzJm7EFwfb8UDXeSjXeSE52D+97BqyK75X2GA
23Gada665Bu9973uxb98+3HTTTfj5z38Ol8uFf/7nfy56/Be/+EVYLJa5/zU3N6/
xiGvHe3qsZAA+i4vSfABe9ACOTCSF8JCvZuPiHAjmlDgZM+ILAx2I5eW5GxECxJkfobCoxNGYeWbfNyu4IF
94cZbAMJ3R4AfjDTUbI/n/2bvv+Lau+/
D7n3OxAQIEwb239rIlW5JHPOIVZ9hZddO0SdM2edIkTVM3TZM8Gc3oz9m7vzqjWU+TJs1OnMRL3rEsD9mSr
U2Key8QxB73PH+ApEiJxCABihLP+/VSZAIHF4cRcO/
9nvH9KmuFJmCL0881ngkudU3NC8ABLnUtP7u5jkiWB1wBQhO5qfstBN6O3J33lDNmcrt8/
OMf5+DBg2zfvp2bb76Z4eHFy8S5XC4GBgZm/3R1dc17/
nOf+xxf+9rXuPvuuzlw4AAOh4Obb755XqB+oZjqn+DIL55m+Egv8VAsmcfAG6TnqVMc/
+1zswkFLzabCgJ8uOn0OUvTjULnpuIx3lffraqaKMoK0CX8eKCSxaJbHcHpkJ3nfOe/
Ykgimt0y9LmM1osrU3peg/CSkhIMBgNDQ/MDy6GhoYz3fJtMJi655BLa2toWfP5DH/
oQk5OTs396enqW3e/zQUrJ4KHu3BxMkDaYz4Qu4YExD/90Yj3vPraJ/
9PRREyKRZaeZbcEVkfw1KQb7womgVKUteDqogkchpnZ8IXkrw74UgghcNctPZHcGZJE7PwvtbsYzc3tsmnT
Ju6++27sdjvf/e53F33NTG6XmT9zV8RJKfnKV77CRz7yEW677Ta2bdvGD3/4Q/r7+/
n1r3+9Ar9R7sQjMdoeeBGZ0Bf8aoW9ATofW3jl38Vgc0GAL60/wceb23hHTQ/
vqe3mPzce46+r+88ZIFQUJT+OBhx44yZS3YdrSB4dP/
9LuS0u25IG3g0WI86qi6vkYV6DcLPZzM6dO9m3b9/sY7qus2/fPvbu3ZvRMRKJBC++
+CKVlZULPm+xWHC5XPP+XGiklHQ8fJR4KEfLLCTEQssbeZcS7u6p4bt91QxFzXOeyd2wto6gLZi6/
rmiKNmxG3T+taETm6YzPypI/
rc1gxJmAkmLPcDxgJ3jAXveMxyXb83NCiaLy5aT4yhnzOR2ueGGG2Yfyya3S21tLbfddhtHjhyZfa6jo4PB
wcF5xywsLGT37t0pj7kajZ8aQk81+CNhsnuUyNTFW/
lDCNjgCHKdZ4Iri7yrYt+poqwl3lj6GWIdwXgG7fKtdEP1kuYCqi5tzMs22/
Mp79OQd955J29961vZtWsXl19+OV/5ylcIBAKz+8Xe8pa3UF1dzV133QXAJz/5Sfbs2UNLSwter5fPf/
7zdHV18Xd/93f57up5IaWk6/HjTJxefFlf1oTA4lxeYrb9k4U87s3/iJk/
fvHtlVOU863VEeSL60+wb6yYP3ndhHSNclOUG4rH2Oue5LOdDRxdtGxg8ur4h5FSfjuSnL00CZ1rPeP8ecU
gdsNy6pAvrKDCja24gNDYMvaPSihZv/
BgrbJ0+cjtMjg4OHuMs48589xCVmMOmMm+sYzaTfVPYFlvQ48nGD89zNiJAaLBCCabmeJ1lXiayy/
KveOKouSfy5h+ibdA4jae/60xRU2lDB9zJUstLxaMi5n/
STaourSR0k3VK9TDlZP3IPyOO+5gZGSEj33sYwwODrJjxw7uvffe2Ytvd3c32pw61hMTE7z97W9ncHCQoqI
idu7cyZNPPsmmTZvy3dUVp8cTtD/
4Er7eHGcPlZKSdcu7Gb13tASxQLKV3JKcDNq5tlglaFOUXCsyxXlDxRBvqBjiZMDOvaMl/GCgiv/
qq8ZpjCNnr35nvuMakpkQOz5noVRMauwbK+ZUwM7HW9qx5mGZqbXQTmjcv+TV8uXb6rA41Uz4arB37955q9
2uuOIKNm7cyDe/
+U0+9alPLfm4d911F5/4xCdy0cWckYnMPrBSl8SCUU7+4XnC3uDs49GpMIFhH0OHuln3yh2rpryooigXjk0
FfqxagrC++ECeRPCyVZAQWWgarbdsp/
uJk4yfnp+kzeyyUr6phrAvhB5PYHHZKG6txOywnL8O59GKbMh9z3vew3ve854Fn3vkkUfm/
fzlL3+ZL3/5yyvQq/Ov49FjSwrANaMBPb7Ici8BzsoinNXL2zdxOmjPcwAOINg/
6eZvavrOe7ZGRblY3TNSwo8GquYNqkViC12oJS5jDG/
ctOB3X0fQFbbxx5FSXluew5U709z1JUtaEaSZDFTuqKd8W13O+6TkJ7fLzOuGhobmbTUbGhpix44dix7nQx
/
6EHfeeefszz6f77wnY7WXOJkamEg7eGQvLqB934uEJxdelh7xhzj5hxfYcNtOjJbzv2RUUZQLx1jUTFhPtV
RbYhY6l7vO/
+ohAIPJSON1m6i+vBlf3zgyoWMtclBQXogQaycguLgW119Awt7A0jL5aoKWm7fScM1GDObpMZQ5H9iipjKa
b9y67A+xECuTUCWsG/DHVXI2RcmHI34HPxpIViHIZFAtXWIXCdw/VjxTETGn3A2lmByWeeezdGwlTra/
+UoqttevqQv3SspHbpfGxkYqKirmHdPn83HgwIGUx1yNOWBKN1alDsAF2IocSCAw5GPRL49Mljk79N9P0Pn
YMWLByMLtFEVRzrJv3JMmoBNEpYHBeTmezj+zw0LJukpKN1bjrHCvueu4in7Ok4mOkbnbHTJS1FxG5Y4GbE
XJ0kFFjaV4u0aJ+EIYTEYK60uWvRd8xkZHgCOL7hmdce5y1qWwaLnfY6ooSnJfd+bbSjJr442bCOoajhzvD
dcMGutesYOTf3g+41qg1Tsb0YxqH22+5Tq3ixCC973vfXz605+mtbWVxsZGPvrRj1JVVcXtt99+vn7NJbE4
bdTsbqb3QPu5TwqBZhA0XLsxWTZUiMWD8BkSxk4N4esdZ8Ntuy7aZZiKouTOqYA9zf16UnvQTo1VDfCtFio
IP0/ikRhCCGSGU0pGu5mm6zbPe0wzGvA0ly/yiuW5pWSUF/
3OFC0kzbYg7SE7yWA8+0BcQ7K5wI8tD4meFGWtkxIO+wvysq3EmKeVMla3neYbt3L8t8+lHaA0OcyEJgI4S
l3zaoeGvQGGj/Qy0TEyvafMTummaopbKy66zKorJR+5XT7wgQ8QCAR4xzvegdfr5aqrruLee+/
Far3w9kSXb63D7LDS/3wn4YlA8kEB7rpiqnY1YStyMN42lFEMDoCUxEJRep9qo+nlm9O
3VxRlTdMEZHIvrq3QKlclMyoIP0/MDitSz/zLEM9wZihXLnVN8ZrSYX47Usb8L/
aZPtdaw1zvGefbfTVLSOKWTAD1mrLc7y1VFCUpIZcSgKe+kFeaw1jyWP939MQAmSwTigWi9D3dTv9zHTS/
fDOFdSV4u0Y5ve+lZKAzHe2Exv10P3GCsZMDtL5iOwaTuuwtRa5zuwgh+OQnP8knP/
nJXHXxvCpqKsPdWEp0KkwiGsfksGCynVn6aXU7srrmI2Gic5hYsBWTfXUtIVUUZXXZXODnWMCR5qop2eAIr
FCPlEyoaYHzxNNcntXeR8248v9Ub6oc5FLn5FmPitk/
j054OBW0c5Xbm1UALpBowDtqetlSoE4IipIPQiQHyrJLN55+JH0qYSSbWCJbE6eHMpwuTJIJnfYHX2Kydzw
ZgOtywdcHRnz07G/
LZVcVZR4hBBaXDXuJc14ADskgPevruISQV10jFUVJ7TrPOAYhEYtc7zUkO50+Ss3nv0SZcoYKws8Tk91M5Y
76zBoLgbu+NL8dWsB4zMjzUy4WuymXCB6ZKOYJb2aZ2M0iQY0lxG1lw3xlw3GuWwWlEhTlYnZzcWY1jM9IP
wPtTxg5GnAsuU/pJGKLVH5IQUrofbot9fYeCeNtg8TDK7uqSFEADCYDdVeuz/
p1QltbiYoURclekSnOP9R1I0gG3GckA/Myc5S31/aer+4pi1Dr8s6jyksbEJqg/
2BnmpkfSdnWlS3DEkpofL+vOsM5tFSzZ5JiU4x/
quuiyR7KZvJfUZRleplnnKcnXRzyO8ksb0Nm+R28sfyVUDIXWIlOhbN7kZSEx9PPGEpd4h+cxN2w8oOailL
cWoFmMtD3dDsR38KlyubSTAYcJalysyiKoiRdXujj062n+MNIKU9NFhKXGkXGODcWj3FTyWjOk6kqy6eC8B
UgdR1v1yjB0SkQAldVEQWVyVT8lZc0ULa5ho5HjjLZfdas1fS9cOM1m1b0QtwftvDp001MZFw6LNVNu2AsZ
qbUElUBuKKsMKOA9zd08dPBcv4wWppB9tSZmfDU7VzGeK66eI7SjdX0Pb1ApukcyWpfrqLkWFFDKe76EiZO
D9Px8NGUbUs3Vuc9+39cwotTTsZjJgqMcXY4p/Ka80FRlPxptIV5d10P75I96IBB3XevaioIzzNf/
wQdDx0hHo4l0xdKGHyhazYLsLXQjsFspOWmbQRGpxg52ktg2IcQAleNh9KN1VhcthXrb0wX/
J+ORibjRpZbemyuxybc3Fg8ri7uirLCjJrkzVWDvLZsmN+NlvLkhJvhWKqyR6m/
93YtzqYCf247OUfphirGTgwQ9oWy2hueKVtxQc6PqSjZEELgaS5H6pLOx44B56ZNd1YXUbWzMa/
9eGzCzY/6K/ElzqxssWoJbisb5rbSETVwrigXKCFAFe9c/VQQnkeBER9t9x46M/
MyZwYmPBnkxD0H2fS6yzHZzEgpSYRjxCNx9HgCoeV3u/5U3MCjE0UcnnISl4JmW4iXF4/
RHrQzFst1JlbJjwaq+PVwOXfWd7FJJWNTlBVnN+rcUTFEmTnKt3qXvr2lyBTHmMebc4PZyLpXXULXY8eZ7M
l2T3sKApwVbqyF9twdU1GWobi1AluRg6EjvUx2jSJ1HavbQdmmajwt5Xm9D3horIhv99Vydg6IsG7gp4OVB
BMG/qJyMG/vryiKstapIDyP+p/rWDxRkIR4OMbI0T4qL22g6/
HjjJ0cZG4h0aGXehg+0kvj9ZspyuEexhenCvhiZz1ROZO+QXAi4OCe0RLqreEllBtLJ3msYMLAZzoauav1F
NXWSA6PryjKSumLWPHHDRQYs0+glimTzUzLzduI+EJMDXiJhaIMHupCjyeyS/
Y+QySD+7qrsk+MpSj5ZC9x0njNxhV9z4mYgf/qq5n+aeFr/
e9GSrmheIwylU1ZURQlL1R29DyJhaL4esdT3zBKGD3Rz9CLPckAHOYvSZPJ/
Yun9x0hPBnMSb8GImY+39kwHYDPlBtjeq+ooCtsW9I9biYkgoQU3DOikiIpyvnSYl/
+uSSor8ylw+KyUbK+ksod9Wy8bScWZ4Zbc+bGFUJQ1FjGxtt2qVlwRQE+09FEuhRNGvDIuGcluqMoirImqS
A8T+KhzMrgxEIxhg53p203crRvuV0C4N7REhJSpJnpzt9aUx3BE153XusMK4qyuFprhA12/1llTDJnFHpeE
7Mtxup2ULO7JbPGEkwOC803bmX7m6+k6frNK5pbQ1FWq/
agje6wjXTXeQkMR3O9NU1RFEWZoYLwHIpMhel5qo1D//
0ER3/1bEavMZgNyaRtqUjJROdIDnoI+73uDDIk51dcakSlyviiKOfLO2t7cRrjWQfiGpIr3F6s5ynBor3Em
fEYYSwQof2BFxk7pfa1KmvXSNTEoakCjvkdRHXBk143IsPvvVVTJY0URVHyRe0Jz5HAsI+Tf3whuz2LAlw1
Hibah9M2lYncXAzDy1pGOvOLLS+AtmoJLEJNhSvK+VJuifJ/Wk/xm+EyHhgrzjAHhEQHTgbs/
G64hFtLRolJjf6IBYOQVFvDeU3YBmB2WHDXleDtGs34Nb0H2jBaTRS3VuSxZ8paE5kKEZkMoRk1HGWuvCdT
zVZ/
2MIP+qs47C9g5pptN8QpMcVmCxGmIhHsKZzMdzcVRVHWLBWE54AeT9B2/+GskwZpBgOxYAbL1gVYixxL7+A
cpeYoAxHLkhKvOQ1xthZM8eTk0veJaUiu94yr0ieKcp54Y0ZOh5JLs19bNswlTh+f7ZwphXT2F3PuwFvyuc
GohR8PVvHTwQo0IDa9oMppiHNLySivKRvOazBee8U6/MO+jLf8APQf7Ehmm1YnHmWZgmN+ep86xdSAd/
Yxo9VE+bY6yrfWrorPWH/YwkfaWojoGnO/
08GEke5EJoWLJB5jjM15LEWoKIqy1qkgPAcmOkbSLylfgJ5I4B/
0pm8ooWxTdfYdW8CNxWP8sL8qq9dUmMO8u66HZlsICRw66iKQSPfRkZx9Q68hsRsS3FqS+SyWoii54Ysb+H
5fFQcmz2xJ0ZDsKfTyjupefjBQRUTXMExXR1h820ry8QSCxJw2UwkjPx8qpyNk45/
qu9DyFIuYHRZab9nOsV89k/FrolNhgmN+HCXO/HRKWROCY1Oc+N1B9LNWpsXDMfqebicyFaL+yvOfgf/7/
cnv8sLf4cy+mB9uOq0GyxVFUfJoda2fukD5+idY0tVKktHMeWFdMe763GQUv9YzTo01nMVeUInHFKfFHkII
0AS83DOe8vUCiV1Lli/SkLNtKy0R/q25nWJV8kRRVlQgofFvbc3zAnBIJkp8atLN70ZL+dK6E/
xddR9XF03gNMwkXjszA36ucx+XCJ71FfInrzvXv8I8ejyOMGR3zo1MV5iIh2MEx/
xEpsL56JpyEet+4mQyAF/k8jd6rB//0Pldwj0SNfGi35km90vqm4/
Xlw1Rbc18pYmiKIqSPTUTngt6htF0loRBUL6llqqdjYgcTStZNcnHmk7zrd4anvW50i5LF8AlLt+8x15VOs
J+byFjMfM5F3oNSak5yieb2+gK2zgVTJYE2ugIsMERUCPrinIe/
H6klKGoZcEbcx3BUMTCvvFi3lgxxDO+BqbSrnRZnEBy32gJVxd5l9HjxfkHvZz8wwvILEssdDx8lN4DbfO2
ANmKC6i6pAF3gyqbqKQWGvcTGPGlbiQEI8f7KCgvXJlOLaAvbM2glcAqEtOlSpPXbR2BQUheWzbMa8vS56l
RFEVRlkcF4TlgL3Ey3j6U24MKKFlXRfVlzbk9LlBgTHBnQxcjURP/
t7uWE0HHgsG4QGLRdK4pmpj3uNOY4JMt7fxXXzXPzQnkBZJLXT7+troPlynBVpOfrU61p0xRziddwgNjxSl
nxnQED4wVc3mhl0NTrmW9n0TQlVEgsIRjS0nn48ezDsBnnJ2DIzTmp/
3Bl6jd20rZ5ppcdFG5SIUmAukbSUlo7Pxe88wZZjT3mGN8tOk0T00WMhU34jHF2F04SYExkeceKoqiKKCC8
Jwobq2g75n2Jd8YLkgIhCG3uwXiEp6bLOTQlJO4FNTZQryrrpuvd9dzKuhg7j5ugcQsdD7Q0IlzgYuy2xTn
nxu6GIuaOBW0I4AWe1AtNVeUVSaYMODPYGZ7KmHkwGTh7KzYchjyVP0gMDRJZDKU8+P27D9FYV0JFmd+Bg+
UC5+W4fVYM2aS+Cx/
WuxBbFqCkL54PzQkl7l8uE1xbikZW8HeKYpyoYnpggOThZwI2kEK1jkC7C6cxHyeSpVmIzTuZ7x9iHg4hsl
uwdNSjrXQfr67NUsF4TlgtJqo2tlI3zOnc3dQXeKsdOfscD1hC5/taGQsZp7do/
2E182PByqmPwRzv0zJxEzVlggNttQ3vMXmGMVmVcZEUVYrUxa1fl+cWn7iMg3J9oKpZR9nISFvMC/
HRcDoiX6qdzXl5/
jKBa+g0o0waGnLhbrrS1aoRwsza5JXlIzyq+GyRVe4GYTkhmIVfCuKktrxgJ0vdSa3qBlInvseHC/mh/
1x/qm+i00FGawQWgYpJROnhxk+2ktgKLkdSDNqGMxGHGWFlG2qTp6bz9rrqscTdDxyDG/
nyJycXZKB5zspWV9J3ZXrVkVZyfPfgwtcLBih/
2AHoycHc3dQkcwAXFhbnJPD+eIGPtXezETMBCSXnuoI5PSfZImhuQmYkn+fDtv4f45u5Ad9VQxEzDnpi6Io
K8uiSTY7pjJIxihpD9mWPQuuI3hFaX4qIGQ6G5k1CcF0+32VNc1oMVGyvjJlG81ooHhd6jYr4XXlQ+yervE
993uvITEKyZ0NnZSoVWuKoqTQG7bwf0434Z8ua5hAIzEdNgYSBj7T0UhP2JK395dS0vXYcToePjobgAPocZ
1YMIq3c4STf3iBrsdPIOX8+5uOR47i7RqZOdD0n+SPoycG6HmqLW/9zoYKwpdhasDLS//
7FAPPd85m3s0Fg8lI801bc5aM7cGxYvwJwxLKlQhi0sB9Y8V84OQ6DvpUeR9FuRC9umwkg+BaIDO+JMiz/
j7z31sLfGxw5GfG2lXjWVolikysglFxZXWr2d2S/AzC/EunSM7OtNy8DZPt/
A9YGwS8t66bDzR0sN05RYkpSqUlzKtLR/
jS+hPsULlaFEVJ47fDpSSkWHBFjUSQkILfDJfl7f1HTwwwdir9BOfYyQGGXuyZ/Tk45sfbOZoyX/
bIsT6igUguurks6q5jiWKhKG33HUaPL16uZKlabtmGvTh3Ae/
jE0XL6qJEEJeCL3fVMxY15axfiqKsjO1OP2+t6oM5JQOXqtAQ4+xVM3P/+0W/iwPe/
GSHNtnMFLdWpK6apolMSyHP46ouWk7XlDVAM2i03LSNppdvxllZhMluwVJop3JHPZvfuCenW8iWSwi4xDXF
Bxo7+frG43xp/Un+vHJQzYAripJWXML+s0qank1H8JTXTUzP/
cC4lJKhF7szbj90uBupJ5fLj7cNph+slzBx+vxXgVB7wpdo9EQ/
ejwPWUQF+AcnKSjL3U3sVMLAku5K5xHoEvaNe/
izihxnglcUJe9uKRljc4GfB8aKOeovYCxmIqzPbEXJXEA3MDeJ49kEkntGStjtzk+uiLorWon6Q0z1e5Ndm
DOmYDAZqb1iHZ2PHs3qmJrRkAzuFSUNoQmKGssoaszfDJCiKMr5FE4YiMv087QJBCFdw6TlNh6Kh2JZJWGN
h2MER6dwlBUSD6cfaBSaIB6Opm2XbyoIXyJvZ372PAohMvoAZcNjjBHIQSCuI3jO51JBuKJcoGqtEf6muh+
Aj7U1T1dFyIZMe2GWCNpCDqbiGk5j5knhMqUZDbTesh1v1ygjx/
qJ+EIYzAY8zeUUr6ucXg4s6Xz0GCCSe8EWI0BoGs03bcVoUat8FEVRFMVmSGASOrE013uj0LFnkfw1U2fv8
c6EHk/2w2RPvyVI6hKTPX/
72TOlgvAlysssODMfjNzuKbu+eJwf9lflZNV8XOZpP6aiKCuq0BhfQjmyzNt+6nQzH2k6jSsPdYeFpqWcjS
xuqcBR4mLkWB+TPWNIXcde7MRkNzPZO04sEEEzJQP3ss01q6pkiaIoiqKcTwYBLyua4OFxz6L3CBqSq9xej
HkoVWaymTHazMRDmc9WW6av48WtFQweSrOUXQiKms7/
aiYVhC+RzVNAeDKUepZlKYTA01ye00NeUzTBfaMlDEfNy8p8rCFpTFOyTFGUC8NVRRM868vP3m2AvrCVL3Q
28Inm9rzlUkvF6rZTu7eV2r2tK//miqIoinIBe3XpCH/yuonq2jmxg4bErOm8piw/+6qFJijbVE3/
cx0ZNIbCmmLMjuTMttXtwNNawXiKpG4V22pXRRJNlZhtiUo3VuU+ACc/
HwybQedjze202pdXz09HcJOqLaooF4VdLh/
11tCyE7UtRkdwKujgVFDNMiuKoijKhaTcEuVjTafxmJJbZA3os7XCi0wxPtJ0mkpL/
vZVl2+txVHuSt1IJHPB1Oxpmfdw/
VXrKdlQOdtGzCRsFYKK7XVU7WrKT6ezpGbCl6igwk1xa8XC6fNFcm+31DO4uZ1JLCQE5Vtr8/
LBiOoCTUg+0tTBl7vqeH7KtWDJgcUlkzDdXDzKujyVHlIUZWUZBHy46TRf6GzgVNCBAYnOTJ6z3ExdG5Acm
CxU5w1FURRFucA02kN8dcNxDk05ORFwIIH1jgA7nFPkqIryojSjgXWv2MHgoS6GjvSiR8/
d2lZQ4ab+qvXnbCnTDBr1V22gckcD4+1DxMMxTA4LnqbynG/5XQ4VhC+REIL6qzdgcdkYerGHRDQ+
+1xBuZvKSxvpePilZJK1RWLxouZyzA4LJrs5Lx+M00Ebvxku5RlfIRKBSeg4DfEMAvCZDifbFRnjvKJkBLO
QfLevCpOQXOrysckROC/LTBVFyQ2XMcEnmts5GbTz9GQhgYSBo34HIzHz9Pjgcr/gcjoD+
+oTC0YYPTlIeCKAZtQorCumsLYYoeqFK4qiKAqQrPp5iWuKS1xTK//
eRgNVO5so31pH5+PH8XaMJJ+YnsAMjfkJDE0umtfFXGClYnv9ynU4SyoIXwahCSovaaB8Wx2BoUn0eAJLoX
32w9D6ih203fsCseB0tvM5s961e1so21STt74d9Dn5UmcDkjM30jGpMR43kaq80ExH/
6aql3pbGJOm0xm08b3+auJSTC9dFfxhtJQ6a4j3N3RSquqOKsoFSwhY7wiyfnq2OqYL9o17uG+0hMGohfTn
i8XpCMrN578MyNmGXuyh9+m2OY8IRk8MYHZaab1lu0rUpiiKoiirgJSSjkePMdk1pyrV9FxhIhqn87HjoAm
KWy68MqMqCM8BzaDhrCqa/
VlKyfCRXoZe7JkXgFucNoqayyhZV8lU3wRdjx8HwFlZhLuxFM2QmxmYYELja911JGbeeJ5MbqYlR/
wOfj5cTkzXCM2pC5yY8/
resJVPtTfz2XUnsRlyX6JAUZSVZ9Ikt5SMcUvJGDFd8IuhMn4zsrRkkYJkhtXVZOR4P70H2s56NHlFj/
rDnPz982x+w24MZnV5VFKLBSNMdI6SiCSXOhY1lKrPjaIoSg4FhibnB+AL6H2qDU9T2QW3kk1dLXJMSknnY
8fPzconITIVYvRYP8Mv9aLHEsys5R49MYDxKRPNN26loHz52YqfmCgiomssfV+n4Bmfe042xIVnwnQEIzET
j08UcVOJStimKBcbkya5o2IIlzHBr4bL8Ceyu2S8vnwItymevmEWwt4goyeS9cE1kwF3fSnu+nOXkesJncC
IDxnXsbrtmOxm+p49zdDhnsUPLiEWjDJ2cpCyLflbqaRc2KSu0/
NUGyPH+pMJWkWyHn33n05StbOR8q21iBXcq9UetNEZsmEQks0FfrU6TVGUi8boyYHZc+xi4uEYR3/5DBXb6
ylqKsvZpGa+qSA8xya7RxdPiy+TH5QzP5/5QMUjMU798QU2vvayZS+FPBm0owHLmZueX44g9c3EIyoIV5SL
lhBwa+koNxWP8ch4Ef/Vnz44tWtx3lAxxC1pqimEEhr9EQsaUGMNY0pRb1RKSd/
T7Qy92DNnaw+Mtw1hcdlofcV2LE4bUtcZeKGL4Zd65+XqMNpMxEOZBSdjbSoIVxbX9fiJ+UlZp6/
lMqHT93Q7ABXb6vLfj5CV/
+yppStsY+YLIZDscvl4R00vBcZzExkpiqLkmpQQlwKjkDnPFRWZCmdUjSrsDdL56DGGXuph3a07MFpMue1I
HqggPMeGj/SduUHMhgQ9IRl6sYf6q9bno2t5IvDG1MdIUS52Rk1yQ8k4/
VELfxwtTdFSUmMJUWqK0hW2UmcNn5NF1R838NOhch4d9xCTyRFrhyHOzcVjvLZsGOMCwfjQ4e5kAJ58i3l/
R6ZCnPzDC2x63WWcfvAIvr7xc16faQCebLv69rErq0NoIrBwVZQ5+p/
roHRDVV6XpveFLfxbezPR2cSHyS+ZRPCcz8UnTzfxyZY2rCkGthRFUZZjPGbkDyOlPDzuIagbMAudq4smeG
XpSM7KlxmtpqziqtC4n85HjtFy87acvH8+XRjz9ReQ4OhU9gH4DCkZbxtELrP+
+HpHYFmz4NkQSIpyvNxUUZTV668qB/iLigHs2mLfe8HJkJMvdjXyoVPreO/
xDTw45pkdyA4kND7e3sxDY8WzAXjycSO/
Gi7j850NxM86BerxBAMvdC3eKQnRqTCn7j20YACeLVOBddnHUC5OYzNLI1OQCZ2JzpG89uOng+VEde2sVWt
JOoLesJVHxj157YOiKGtXf9jCB0+u44+jJQR1AwBRqfHwuIcPnlzH8UBuEpx6msqyi6skTPaMEZ5c/
aVRVRCeI5GpMCPH+pD68sJfPa5nVl88havcXswimRd9cbkZHZfAtZ7l3/
QqinJhEAJeXTbCTcVjZHIeGYuZ+K++Gn46mMxc+suhcgYjlgWDB4ngsL+Ax84KHnz9E8k8GmkEhnyZ/
RJplK6vzMlxlItPNBAh7edeCKL+cN764IsbeNZXuOB3aK4Hx4rz1gdFUdamvrCFw74CPtvZQCBhOOc8pCOI
ScEXOxuI6stfm+6uL8Hqtqcd/JxHJLcHr3ZqHfEyJaJxuh4/
zkRHbka9DSYD4uy1mxmK64KnfS6enHCTPo4XmIVOdHYmSmIWkqgUZJrQTUNSao5y9SrLfqwoSn5JCfvGPGR
2rki2+c1IGbtckzw87kkZPAjgvrFiri8+M7iXiKzQahsBtiIHRU1lK/
N+ygUnuc8wzdpIKZNLKPNkLGqeLT26aBcQjETNeeuDoihryxG/gx8NVNIRSj/
DLRH4E0aemizkZUXeZb2v0LTpks+HCE0EMn0VemL1V21SQfgySF3n1L2HCIzkZvYFAcXrq5aUVXUsauLfOx
oZiFgRyLQXaA3JlUXj7Cn0EZeCGmuYgz4XP+yvSnFrkTyqBiQQNNhC/
HNDp9pzpihrTEjXmNKzCzI0JH8cLZkuebg4iaAnbJ1NOg1gXqHl4c7KIpqu34RmTN1HZe3yNJcxcqwvdSMh
KGpIlTdheeyGzBKuWTWVmE1RlOU76HPyxc6GrNbQakiO+QuWHYQDmB0WNr72Mnx94/Q9c5rQuD/
1C6TE5nYs+33zTQXhyzDRMUJgOHcBuMFspHxr9hl5dQl3dTQyFLEApA3AIblcZCBsZVtN/+xjL/
eMc8BbyImg45xjaEgKjTF2uXw4jAkucU7Rag/
mPAuioiirn2l2u0vmJ4CZfaqZMJyVYbWgohBzgTWvS3xLN1VTd8W6vB1fuTg4ygspqCjEPzS56GR46cYqTH
ZL3vpQZo5Saw3RG7Yuer3XkFyRg5tfRVHWtriEb/bUkrzqZ3fTn8spOqEJCmuLsXkcvPiT/
SkPbrSaKKxb/dtx1J7wZRg53r/0UtxnsbhsrH/VpZgd2c/4PD/lpC9iTbs/bD6JUcz/
BJs0yYeaOnhl6ci8EXST0LneM87n15/kb2r6uaNiiHUOFYArylowFjXx6+FSvttXxc
8Gy+kLWzBpkmZbtklPJDZDgnJzBJHi6qkh2e6cmveYEILavS1L6H0a0ycxT0s5tXtac3985aIjhKD5xq0Ul
BfOPJC8D5j5LLVWULsnD5/
VeX2A15YNL3pDLJAYhExbIlBRFCWdgz4XvoQx6wBcB5rtuU+OZnZYqb6sefEGAupftgGhrf4QV82EL0JKiR
5LIAzaokXfo1OhnAzzNFy3CU9T2ZKWoQM8PVmIhswyCBd0hW30hy1UWSOzj5o1yZsrB3lD+RA9YSv69FJ1u
2H1761QFCV3dAk/Gqjkj6MlyRhjepvLL4fL2V3o5bVlQ3yhqynj4wlgp2sKqyHBd/sWX/
GjI7i15NyEKu76UppevpnuP50kHs683NhclkI7nuYyvF2j6PEENk8BpRurcVa6l3z+VdYeo8XEuldeQmBok
vH2IeLhOOYCC8WtFdg8BTl9L2/MyCMTRTzvcxGTgmZbiJcXj7HXPclYrJ8fDVSiwfT1P3mbbNF0/rmhk/
IclQhSFGXt6glbMSBJZDnRZ9F0rnJ789Knim11GK0m+p/
rIBY4E8PYPA5qdrfgqr4wKkOoIPwsiWic4SO9DB/
tm60V66wqomJbHa6a+f+oBrMJiCxwlAwJKKwtobi5fBk9hlDCsKSSZIGEgU+ebuJz607iMs7fO2bRJC320L
L6pSjKheungxX8YbQEZuetz1yAn54sJCEFV7nHecKb/
mInkJg1nSuLJjjmd1BmijAcs8zLXzEzkPhXlf1sKlg4+UpRYxnu+hJ6DrQzcqQ3q9/
HVGBhw22XYjSbqLq0MavXKsrZhBAUVLgpqHDn7T0OTxXwxc4GYvLMd7ArZOPB8WJuLxviz8qHuMzl4zfDpR
yecuJPGDBqko2OABrMy6ugKIqyFCYhs94LDvDeum5seZzAK1lXSXFrBYERH4lwDJPDis3juKAG1Ff/
XP0KikdinPjdQfoPdswG4ABTAxOcuvcQQy/1zGvvackieD77MyGSS9Drr16/jB4nlZujS/
qH1BH44kYeUrVEFUWZwxc38PuRUhbbbyMRPOsr5NaSMTY7pkhXDlEAf1vdy7+1tfCNnnqGY+bpZ5JMQmd3o
ZdPNrdxa2nqsiJC00DKzKtICIGnpZxNr70Mozl/Gasvdv/xH/9BQ0MDVquV3bt38/TTTy/a9tvf/
jZXX301RUVFFBUVccMNN5zT/q//
+q8RQsz7c8stt+T717hgDEXMfGE2AD9TtWRmxduvh8t5eNzD6ZCNRyc8TMRNRKSBQMLIQZ+LT51u5gf9VUi
VN1VRlGXY4ZzKeKWtQLLD6eMTLW1c6ppK/4JlEkJQUFZIYV0J9uKCCyoABzUTPk/vgTZC3sC595PTP/
c+1Yazsgh7cXK5Wcm6SoYOdxOPxNKXDTVoIEEmdEwOC6UbqynbVI3BvPx/
gms949wzurRMrBJ4dNzD7WW5KbGmKMqF78BkYdrVNRqSx71uJuPpAluBjuR/BirntBXz/o5JQY01Qqsjs/
1jQhPpgwuRrC9ad+V6TLbpoH96m5Fm1C6I/
WKrxU9/+lPuvPNO7r77bnbv3s1XvvIVbr75Zk6cOEFZ2bnl3B555BHe9KY3ccUVV2C1WvnsZz/
LTTfdxJEjR6iurp5td8stt/C9731v9meLJX/JzC40940Vk5gNwBci+flQGZNx0/
R39Uy7mRvm+8ZKqLaGuXFOuT9FUZRs1NnCbHb4ORZwLBiMa0g8xhgfaW7HaUyo7atZUHch0+LhGONtQ6mDa
SHmlSYxWk2su3VHRuVsZFyn6YbNXPo317LtTVdQuaM+JwE4QLU1wi3FIyxtg7rAF1fleBRFOWMyZsro4jAZ
NzIcNZM+Q6VgIm5KMZouuGeklIie2Si2s6qItFG4hJINVZhsZmLBKL0H2jj0/
z3BCz98nIPfe4zT+44QHM3/SP3F4Etf+hJvf/vbedvb3samTZu4++67sdvtfPe7312w/
Y9+9CPe9a53sWPHDjZs2MB3vvMddF1n375989pZLBYqKipm/xQVFa3Er3NBeMrrTjP7JJiIm2f/
e2GS3w2XoavZcEVRluEf6ruoskRIrmybOaEk/
9tljPPBpg7KLTEVgGdJBeHTgqNTyHRXKimZ6p9ASklgxMdkzxhSTt8QpiMEobFA5ksos/
RXVQO8oXwIS9Z1QSWagJGoWqapKEpSoSmWUZ4JtzGOVcvsopvuzBfSDbzkzyypVWFNcbJ2+KIxvcDisuGq9
hCZCnHs188w9FIPiWg8+byUTHSOcOw3z+HtOrP8PewN0vdMOx0PH6X7yZP4hyaRa3w9bzQa5bnnnuOGG26Y
fUzTNG644Qb279+f0TGCwSCxWAyPZ/7Wp0ceeYSysjLWr1/
P3//93zM2prJ5zwjpmd2epQvUR2Jm+iNqhYGiKEtXaEzw6dZT/F11H022EIXGGDWWMH9ROcDn152k2rqM/
FhrmFqOPi3TtAOJaJyX/
vcpolNn6tVmNqMt85ogRRPw+vJhXlk6wqEpJ4G4kWJzlJ8PltMesqdY0iYIJAz884n1fKCxgy2LJERSFGXt
2F04yQ/6qlJmQ9URXF00gS4F948VLxoMiOlyiDGZPqgIJjJblSM0QctNWznx+
+eTgfXc07cAo8VI841bEULQ8chRYqHoAtuMkg+cfugIW+/YQ//
BTkaP909nskrWQB852kdBpZvmG7ZgtKzNgcrR0VESiQTl5fNzoJSXl3P8+PGMjvGv//
qvVFVVzQvkb7nlFl73utfR2NhIe3s7H/7wh3nFK17B/v37MRgW/hxEIhEikTM3ez6fbwm/
0erXFrQR1jVmPoeLS/d8UizDgF5RFGUxFk3y8uJxXq62t+SMOjNPc5Q4M0ojGg/
H5gXgwJnZlVQkOFcgZb5Vk+wu9HF98TjbnX7eVDk4fYlefJBBIohLwRc6GphUS9MVZc1zGRO8umzxLS4Cye
WFXhpsYW4uGcUg5i5Rm08iaLCGZjOmplJqzrykks1TwKbXXZ4sVWIzJYNvm5mKbfVset1l2IocBMf8BIZ8K
XfqyITO6YeOJANwSAbnktkg3T/opf2BF9f8jPhSfeYzn+EnP/kJv/rVr7BarbOP//mf/
zmvec1r2Lp1K7fffjv33HMPzzzzDI888siix7rrrrsoLCyc/VNbW7sCv8HKkhK+1TtTwm/
xexINiV1LLPq9m2FAz+p7pSiKoqwMFYRPM1rNeJrLMhlUzp4QOEpdyUB/
hW0qCHBnQyf2NMvUJYKo1HhEZUpXFAV4Y/
kQry4dQZve92UQ+mwgvdft5d21yWoRFZYoH2jswKzp0wHBmf1iIFlnD3CtZzzNsllJmTnCOntmidlmmB0Wq
i9rZvubr2Ln317H9jdfSfVlTZjsyeW3/
iFvRsfxD06m6hr+wUn8QynaXMRKSkowGAwMDQ3Ne3xoaIiKioqUr/
3CF77AZz7zGe6//362bduWsm1TUxMlJSW0tbUt2uZDH/oQk5OTs396enoWbXuhag/
Z6AnbSDcDLoTk1aUjKVa5JQP1ve5JCozZblNTFEVR8k0tR5+jdk8rgZEpIr7gOcsbl5TzbPq1ZruZppdvzk
EPl2ana4q/
re7j6z31KdtJ4KDPxW0qU7qirHmagL+oHOSWklH+NFHEeMxEgTHOFW4vlZYoCQmPTbi5f7SEnrAVTUocWhy
/bmLuMtlTQTsng3bqrCF6wtYFgobkI2+t6ifnKTNyNXktBONtQzjzWBN6tTKbzezcuZN9+/Zx+
+23A8wmWXvPe96z6Os+97nP8e///u/
cd9997Nq1K+379Pb2MjY2RmVl5aJtLBbLRZ9BvSdsTd8IQZ01xKvKRjgSKOCIv+Cc75WGxGmM8+cVg/
npqKIoirIsKgifw2g1seE1lzJ0uIeR430kIsll5gXlhSAE/
kFv2uzp9pICor4w8Wgck91M6YYqSjdWY7Sev/
2EUkJfRolZBDF5YdXYUxQlvzym+PTS9DPiuuALnfUc8rsQyDMBgD6zneXMeUROj2J2h63sdPl43udCZ2ZsU
1BkjPM31X05rymqxxNEpkK5OZiUyVKUa9Sdd97JW9/6Vnbt2sXll1/
OV77yFQKBAG9729sAeMtb3kJ1dTV33XUXAJ/97Gf52Mc+xo9//GMaGhoYHEwGggUFBRQUFOD3+/
nEJz7B61//eioqKmhvb+cDH/
gALS0t3Hzzzeft91wNjCKTkSOJ0xDHKOBfGjr56WAFD44VE53OuyCQXOry8ZaqforNa/
dzqyiKspqpIPwsRouJ6suaqNrZSDwSQzNoGMxGup44Mb1kMdUFUlJYU0zlJQ15y4K+mN6whX3jHo77HYzHT
IR1AwYhqbeGGImZGYuZ0x5DQ9JgzdFNq6IoF62fD5Vz2J/cXpNqOewZyZDbLCT/
sfEYz085iegaFeYo25xTOZ8BT0TjnPzDC7krQSYEZvvFPQObyh133MHIyAgf+9jHGBwcZMeOHdx7772zydq
6u7vR5tRd/8///E+i0ShveMMb5h3n4x//OP/2b/+GwWDg8OHD/
OAHP8Dr9VJVVcVNN93Epz71qYt+pjudrQV+NGTK7RsCZgetzJqcrY7SHrQTB+qsYTymDHLVKIqiXODikRhh
bxChCWyeAjTDhbPTWgXhixCawGQ7E7gW1hafSdyzGAkDz3cy9GI3xesqqdheh9mRydKypZMSfjJYwW9Hyji
zBHT6bwnHgw4y3eiuI7hRZT1UFCWFqJ7Mhp5Z8D2X4JlJF+
+t7+Y6zwS6hJNBO8/5XHhMMZpsoZxVkOg50EZwLE0Ans02IykpXpd6//PF7j3vec+iy8/
PTqbW2dmZ8lg2m4377rsvRz1bWdFAhJGjfYy3D5GIxrG4bJRsqKK4pRzNmF1iUynhdMhGf8SCSUi2FPhxm+
Jc6Z7gT96iBQNxgcSm6VxdNDHvcZtBZ4vTv6zfTVEU5UIRD0fpffo0422DsyWmDWYjZZurqdjRcEEE4yoIz
1BhbTEWly25vDHNjZse1xk51sd4+zAbXn0pVrc9b/
26b6x4OgCHM8H23At3Jne1yaD9VaXDNNrVTLiiKIvrDNkI6UurohBHICU8OlHE/w5WMBE/
s02n0hzmLyoH2VWYedmpWCjKZM9YMhhy2iis9ZCIJRg/
NZj2PC0MGjKeWY3zwrpi7MUrn1hTWV38Q5OcuvcQejwx+/kKjk7R/cQJRo/
10XrrjoxL2bUFbXynt4ausG32MaPQua5onL+qHGAoauFk0DFvu4eGxKzp/
GtjB3ZDZp9dRVGUi008HOP4bw4S8c+PyRLROAPPdxEYmaLlpq0ILXUgLnUdhEDks4Z0CioIz5DQBC03b+Pk
H14gFsigKL1MfhhOP/QSG197WV7+gRMSfj1clr5hGsWmGLeVDXODR82CK4qSWmIZeSPcxhh/
GC3hvweqODtKHoha+GJXPe+t62avO3Umcj2h03ugjZFj/
bOlxCCZ16NkfeXsqHgqmQbgAHVXrs+4rXJxSkTjtN13eF4APldw3E/
X4ydovmFL2mOdDtr4ZHsz8bO+S3Gp8eB4MUNRC/9v42kO+Ap5cKyYoagZm6ZzhdvLy4vH1FJzRVFWNV/
cQF/
YilFI6m0hzFpuS3z2H+w4JwCf9/6944y3DVG87txEn4lYgpFjfYwc7SPqDyM0QWFdMeVb65I5wFaQCsKzYC
20s/n1lzN2cpCxUwNEpsKpa4RLSWg8QGDYl5d/
2FNBO5Px5SZ8k7ypYoDdhb6cLQVVFOXiVWMNY0CSyHo5uuQKt5cfD8xcFM9+fXJ9+Hd6a9jp8i160ZZS0vn
IUSY6zq3iEA/HGDzUnWW/0pO6mnVc68bahtJc78HbOULUH8ZckHob2g/7q0hIseCWDongsN/
JIb+Tq4u8XF3kXWbPFUVRVsZ4zMiP+it5atI9u53GYYhzc/
EYry0fwpiDOEOPJxg7OZB2tdvw0b5zgvBENM6Je54nNH5m647UJd6uMbydo9S/
bAMlCwTu+bL6F8yvMgazkbItNWx87WW4aj0ZrfYeeL6T4Zd6CXuzq4GbTjCxtCWhZ/
tGTz13nljHUCR98jZFUda2qbiRFntguiZ4piRWTcdu0NO8ShDUDTwzufigZWBocsEAPJ8mTg+v6Pspq4+vd
yyzdn2pV5QNRMycCDpSJl7TkDwwVpxV/
xRFUc6n8ZiRj55qmReAAwQSRn41XMZXu+rJYJFaWpGpMHoGK9nmBtozep46RWhigdwZ0yvquh4/
Tngyt7FaKmomfAX4esfx9SYvzK4aD43XbsRoTQa8UkqCIz5ioRgmuxl7iTPjpetRPRdT18ljjMXMfPp0E19
cfyLny0YURbnw9YUtfKevmuOBgjmPnqkHvrjk+SSsazwzWZg2H5oBnf4UJRVHTw6AEPOWoS8om8RrqQ6jid
QzoMqaIBOZrYbQE6k/
dEMZlAvVEQxkVFZUURRldfjJQAXeuGnBAUaJ4FlfIQcmC9NuN0sn0+pTZ7eLh6OMtw2lvS8YOdZH7Z7WpXY
vKyoIX4aCskIm2rObIfH1jXPi9y+w8badeLtG6XvmNFF/
ePZ5i8tGzeXNuBtK0x5r33gxmd0Ep6cjGI2Z2e91c41nIv0LFEVZMwYiZj7W1kJYP3vx1JxqDIBAR56zwOr
M+akrbEs7gy4RmLTFA56IL5Q+AAcMJiOJWHzZgbjUJaY8V7lQVj+bpwBf/
0Taz5Pd40j5vNWQyODdJDYtk3aKoijnnz9u4EmvO+UKH5D8arhs2UG4xWXDXGCdFzudQwgKa+evJgoM+9Ln
i5Hg61u5GEgtR1+G4tYKNGOW/xdKCE8E6Hz8OB0PHz3nQxTxhWh/
8CXG2gZTHmYsauIlv5NcBOAzBJInve6cHU9RlIvDTwYqCOvaIhfY5GM1lhCZnI/
SlTbTEex0LZ4h3WAxZXTaq76sidKN1fPO0TaPg4ZrN2J2ZR5UC03gaVp+AkzlwlayoSp1AC6SeWMcafK/
tNiDOA2pV1YIYM8yb1QVRVFWymDUTCJtSCnoCVvpDi1vUFsIQfm22tSNpKRsS+3ZD2Um44bLp4LwZTCYjTR
evzm5NDLLWDjdDHr3EydJxBYfCR+JLTch27kkgkCO9pkrinJxmIwbeMZXmHKEWyDpjVgzrh2+2Gy4hmRbwR
S11sUrUHiayjIqP+ZpLqfuinVs/
8ur2PJne2i+YQtmp5WuR48T9aUYQT9L5aUNGK25P98qFxZroZ2qXU0LPylAaBoN12xIu53MKOA1ZYtf/
wUSg5A8Ml7E37y0mX86vp7fDJfij6trs6Ioq5NJZB64/nYk/UrfdEo3VlO8fjqB2txz7vR/
116x7pyE2PYSZ/pYTYi0A6m5pILwZXLXlbDhNZfiri/
N5aQ0ejzBRMfiF2pHRkvasqMhKTdnUH5NUZQ1YyRqThtcZxp8zygwJKZflbxwz/
xdZwvxnrrU2c3dDaVYXDZSlXMo31KDwZzcbaUZDUz1T9D+4EtMdo8jMxzl1owa1Zc1UbG9PqP2ysUtOOZns
md0weeclUVsePWlOMoyu3l7ZckoNxcnj6XNjiid+T7EpWAkZiakGxiMmvnpYAX/
erJVJU9VFGVVqrGGcRtjpN//JXjK6ya+zJxWQgjqr1pPy83bcFUXYbAYMdpMeFrK2HD7Lso2VZ/
zGrPDgruuJHWsJuWCr80XtSc8BxylLhqv3cjYqSJGjvYRmggs+5hCE4RTHKfGEqHCHGEwambxT1R2+8V1BN
cVq1rhiqKcYUmxP3up/
q6mh6m4iccmivDFjRSbolznmWB34STGNIkhNYNG6yt2cOqPLyT3h89uS08mayteV0HVzjMzlqGJAF1PnEj+
sEgA7ih34WmuQOo6MqFjsltw15fMBvLK2hYc83Pid8+hL5KczWA2YisuWPC5hQgBf13dz9VFE+wb89AdtmH
WdPrCFqYSRuZft5OhuTdu4vOdDXx+3UlVTlRRlFXFIOAGzxg/H65I2zaBIKRrOJeZ90JM7/
s+e+93KrVXrCMwOkUsGF3wfqBqVyP2Yuey+pUNdYeRA7FghJO/fyGnae2lTM7gLEYIeH35EP/
RU7fw88is8hEJJJc6fWx2LH8AQVGUi0e1JUKpKTq9BWbhu//
k+SaTyEDi1OK4jXGemXQzELGQkIJiU5SIrtEbtuAxx3AZU1+cLU4rm99wOd6uUSY6RkhE41hcNkrWV55zAR
051pc2m3pwZIqWm7ZhtKhl52uZlJJ4KAqA0WaeXVres/
9kMgBf5CPk7RzB1zue1c0gQLM9RLO9D4DDUwXc1bHIcneSg+R9EStHAw42F6jrtKIoq8ury4b5xXB52nsBk
9Cx5WE1bybMDgsbb9vFwAudjJ0cmC11Zi9xUrG9jqLGlc3/
ooLwLMXDUUZPDjLZM4ZM6NiKCwgMThL2hTI7gEgG13qK/
d4ASElhXeoL+lVFXiZiJv5nsAIB6JyZFHIYElzlnuDesVLOnRFP/
jwTqBuAaz3jvLWqX42wK4oyjybgtrJhvtNXs0iL5B5WpyGGN25KcwEWhKXGx9tb0GB2n/
mRQAFHAjPBs2SXy8cby4eosy2+d1toGkWNZWkvmr6+8bSJVqQuCYz4KKxRtZnXIqnrDB/tY/
ilHqL+5JYsk8NC+ZYaXDUe/
INpkqSJ5GBPtkH4XIemnBiQJFJ8fwxIDk05VRCuKMqqY9bg2qJxHpnwLHofoCF5WdEExvMYa5jsZuquWEfN
5c3EQlE0gwGT/fxs9VFBeBZ8/RO03394XpH4wPDiWXwXYrSaaLlpG12PH08uW1/
o3lCAo6wQR6kr7fFeXTbCHreXh8Y9dIZsmIRku3OKK4smsGqSZnuInw+VMxQ9U3O01RZkd+EkBk1i1XQucf
koTDPzpCjK2nW9Z5yhqJnfjZShIWeDZ4HEKCR31ndh1nT+T0cjujx7j/j8QcCY1EgWM5tr/
vLbgz4Xh6ecfLS5nRZ7hgOci8k4I+ry3ka5MEldn84XMDbv8VggQu+BdmyZlCGVLHsbWlzOL/
e32Bsl2ymKoqw+t5WN8NSkm8gC1VQ0JBZN59WlI+epd/
NpRgMWp+289kEF4RmK+EK03XcYuciesHQsbjuV2+spaixFMxpouWkbJ37/PNGpc2d6rIV2ml+
+JeNjl5pj3FExtOBzVxV5udLtpStsxZ8wUGKKUWGJLul3UBRlbRIC/qJykN2Fkzw4Vszp6QG/
S1w+rvOM4zElSy59rOk0/z1Qyang3FrJZwcN6YMIHUFMwje66/
jy+hPLWqHjKC8kMhVOPRsuwJ7Fnl7l4jFyfOCcAHyu0OhURscxpNg+lokGWyjlLDhAAo16a+aZ/
RVFUVZSuSXKx5rb+XJXPcNRC4bp0e0EyW1ndzZ0Ua5ikFkqCM/
Q8NE+pL60AFxoAldVEcWtZxIWmAusbHrd5Yy3DzF2coBYKIrZbqF4fSWeprKU+8Gzfn8BDSmWdSqKomQiuY
e1d9Hn1zmCvK2qn0+0NxGZnvFeKolgKGrhiL+ALU7/ko9Ttqma8VODizcQUNRQijBoDL/
Uy9SgF6TEUeaieF0lJpvKSH2xklIy/
FLP8g8koGiZteT3ur38sL+KiK4tspRTYtN09rq9y3ofRVGUfGqwhfny+hO86C/gZCA5IL/
OEWBrgR9NLeSZRwXhGZo4PbTk5YpSl1jdjnMeN5gMlG6oonRD1TJ7d4Y/
buBxr5v+sBWzprPT5WOjI6D2eiuKkne6hK92180uOV8uDUlHyLasINxR6qLy0gYGDnae+6QAs8OKu76EF//
nyXlbjbxdo/Q/10HDNRvxNJcv+f2V1UuPJZIZ9pdJM2iUzNSsXSKrJnlnTS9f7a47J9HhTOmyv6/
twZymeoCiKMr5pgnY7vSzfRnX7rVABeEZSptILQVh0Chuyf9N3P2jxfywv4qZngrgD6OlNFiD/
Etj5+ySUYCILtjvdXM6ZEMDthT4ucTlw6CCdUVRluiov2Be/onlkoBBLD/
oqLq0EWuhncHD3YTGkjcFmtFAyfpK3A0lnPrjIaR+7vtIXdLxyFFMdgvOSvey+6GsMllc7
4oaS5noGJmfaV8kA/CWm7dhsi//c7/bPcmHDB3872A5baEzA/ct9iB/
VjHIFpWQTVEU5aKhgvAMWVw2gmNLG9Gp3dua93qzj467+V7//
ALzM7eUnWEbn2hv5vPrTmLWJAd9Tr7RXUdI12b3a9w3VkKxKcq/
NHRSr5auK4qyBKeC9nmJ25ZLIthSkJuRdE9zOZ7mcmLBKHoigcluQTNodDx6DJkme/rgC504K3fkpB/
K6mEwGbF5HITGUwe3Vredhus2UbLBy8jxfkLjAQxGDXdDKSXrq3KaWXer089Wp5+hiJnJuBG3KUaZOZaz4y
uKoiirgwrCM1S6sZquJ06kbCMM2rzEbWanlepdTXlfyqhL+H5/
NYtnVhUMR808MeGmxhrhi50N06G3mJcIZiJm4lOnm/hs6ymK1UVfUZQsiRzMWs/
QkKx3BFKWKUsnEY0zemKA0ZMDxIIRTDYzxesqKVlfiWbQkFIy0Z5mq5EEX98E8UhM1RG/
CJVtqaXrseMp25RvqUXTNFzVHlzVnhXpV7klqhIYKYqiXMRUEJ4hT0s5Iyf6CY5OLXrDJhM6BZVuilsqsBb
ZcZS6ECuwGfv5qQLCerpEboI/
jpbMLklfKPGLjiCUMHDvWDFvrkyRyEhRFGUBGx2BDGbBk4OF82fM5w4gJs9OJeYo76nrXnJfov4wJ+45OFv
3GSARidP3dDvDL/Ww/lWXYnJYFlyGvpBENKGC8ItQcWsF/gEvY4sk7/
O0lFO8zP3eiqIoinI27Xx34EKhGQ2se8UOPE2pZ7X9g176nzuN2WFdkQAc4AVf+nriAKNRM4f9BSlvknUEj
46vzEi/
oigXl3X2ILXWEFrKqeXk+UcHLnN5+ef6Dm70jOE0xDEKnWJTjFeWjPBvzW3z8lhkQ0pJ2/0vEg0sPJMYC8V
ou+8wCDBY0o9FC01gsqkA/
GIkhKD+ZRtouGYj9hLn7OO24gIartlIwzUb83otT7MTQlEURblIqZnwLBjMRhqv24S91EnvU20LN5LJG7z+
Z0/TcM3GBZvEIzEmOkaSyyOtZtyNpcsqg6NltARUJtvJ9DcT/
kTuyqMpirJ2CAHvq+vmE+3N+BOGNLPigmd8bl5RMspbq/
pZ5wjy25FSesI27hkt48HxYq4tmuC15UO4jNklxvQPTRIaT7GXXErCk0H8/
V5KN1QxeLh78SXpIjkbmsuykcrqIoSguLWC4taK2VKkQsvfHEVcwqPjHu4fK6YnbMUgJDucU7yiZJRNKvma
oijKmqCC8CUYbx9K3UBKxtuHzknIJqVk4PlOBl/
oSi6B1AToku79pyjfWkv1ribEEorobbQHuX8sXStBnS3EiUDBIjVIz3AZlzb7pCiKUmWNcNe6k3yzp5bD/
gLSpaD+5OkWrFpiekvNmUg4rBu4f6yY53xOPtnSjjuLWXFfz/
j8LNYLEYLJ3jEqttczdmqQWCh2bnuRTN5VuaMh4/
dWLmz5DL4BYrrg850NvOgvQJDcfBGXgoM+F8/6CnlrVR+3lKS9oCuKoigXOBWEL0F4Iv1ItdQlEV9o3vK2g
YOdDDzfeabRzF5EKRk63I2eSFC3d13W/dlZ6MPSlyCSZl/
4mysG+eVwOYemnIvOUGlIri2ayLoPiqKsLSWOxQcjS4BtUxZe8jsyypR+JqfF/
LY6gtGYif8dKeLDrS9l3LcxwxRCyDQxuMQiAlSWTOC+o45D9/YxORA60w0JBR4L219RTUGxD/Bl/
P4LsRhVsksFfjlcxkvTg1NzP54z35Mf9FfTYg/SYl9+/
XJFURRl9VJB+BIkR8r19O0MZ0bUY6EoAy90pWw/
cqSP8i21WJy2rPpj0iRvqezn2321LJwhXbLH5aXFEeL15UMc9hcg5LnJ2TQkDkOCm0tGs3p/
RVHWlhLHEO5/vQNhXPwSUv6bIPI7/tSZxzMg0Xh0rJIPf3UrRYWZzVKW/+Qgne/9Rerj6jAyFOP5g2Ea/
+xSbvrEX+I7NcLIU50E+334O8cIDvo41SGpaq6j8U07sXjsS/
49DFNBuPv3S369cuGL6oL7R0tSrkbTkNw7WsJ76npWsGeKoigXtlTVUFZrUlUVhC9BYX0J44tkUp1hLrBgd
Z+5YRtvH0qfgUXAeNsQlZc0ZNWf00EbPxuqOOvRue8lOBVy0B2y0mwP8cGGTr7WXcdUwogBnZlSZWXmKO9v
6KRoicmQFEW5+JU4hii4po427TIwFizarvFlQfjOH3PynrqEh7o2sO3SzMo96q+7DO3//
SO6P5hyECA87Cc8GmT48dMc+voztP76y4yM/4rB//g9GAyQSO5FH36yk8NfeJSW//
kMzqsuWdLv4DdMLel1ysWjJ2wlmGbFmo7gRf/i3ytFURRlvshUmJP3HCQaWKAaypFe1r/
yEiyu7CY4V4IKwpfAZE+fRK18a928jKqxQAShiTTlcARRf3Y1cceiJj59uomIPjNDJM76O2m2Bvi6k2xx+v
m/G4/xjM/F6aAdTUg2F/jZUuBnCVvSFUVZI2YC8M4r3stDpxI8/
uChlO1d1S4me5e3jHvG939yksLHMy+dWPGKN7HzZ98FAWLOAOg5a4WmE3EFT/VwYO/
fYZ8cTz6emJMMTkoSwTDHXvd+Hnn3Rwi5s68gEYuohFur0VT/BMNHepka8IKUOMoLKdtcg6vGk/
Os6HoGiVGzaacoirLWSSlpf+Aw0eAi1VCCUdruP8ym11++YlWrMqWC8CwFx/
wMHUpdu9bqtlO6qXreY0arCZlBLRKjNbslE/
eOFRPRtbT7LnUEwYSBB8aKuaNiCKMm2eueZK97Mqv3UxRlbTo3AO+k3uNI+Zraq+p5cX8Pg13etHnS0vHYz
NSkeb95rrySzmI35ff8AntP5+zDi50pNaljnxxfcEMPJAN5TU+w7aWnGHzNG7PoeVIku/
FVZQX0H+xg4GDnvCR+vr5xfL3jlG2uoWZPS05v2qqtYUxCJyYX31ahIWmxB3P2noqiKBcz/
+AkofEUg9xSEvYGmeqfwFW9ukowqyA8SyPH+tJm3Y1MhdFjiXmZ0Ysay+h75nTqg0tJUZo65Gd7fKIoo8RH
cKYG+B0VZxIqjUVNDEXNWDSdRltIzYQrF6SGWy3nuwtrwEwAHuPxB7upc9sZ6fcRmopiMGmUVrkwW+dfUjS
Dxvar6mncXEb/6XH6T08Qi2ZXbmyGwZh91mr/hs34N2zGPDxI6f33UPTs/
nmz4gtJWVRN1yk8+PSSgnBldfF2jyYDcJh/PZ/
+z+EjvdhLnBS3nr3Va+nsBp2riyZ4ZNyz6HVbR3BzscqOriiKkglf71hm1VB6xtn29sr89ycI/
DCztioIz5KvbzztdI5M6ARGp3BVFc0+ZnHZ8LSUT+8NX+BFAgpri7EXZ7cXLNua3lPT7XvDFv67v5JDficz
t51FxhivKRvm5uIxVtmKDUVZVMOtFox79qI53ee7Kxe9h15IBuCB4QCPPtJJJHQmf4QQgpoWDxt2VqEZ5gf
MriIbrp3VuEsdHHo8dYLKxbhLspgFP0u0rIKEowCpaYjE0gYBZmhqSvuiMPRiz2wW/MXbdONpKc/
pbPibKgY5FnAwFLGcFYgn12Dc4Bllu1PlD1AURcmEntAzicEpqBUrcq9o9gWAb2bUVgXh2cpwOWU8cm45mr
or1xEc8y9Y4sxoMVF35fqsu+M2xhmLpd+jPsNljNMdsvLx9maiusbceZ+JuJEf9FczHDXzlqqBrPuiKCutx
DGEcc8dfKt9B5Df+r4KPP5gJ8HhAD3PnXt+kFLSc2qMSDjOjqvrFwxcymsLqVtXTPfJ7Gb6Sqtd2AoyP88t
JFJekTYAX2wp+uzzQhApzW61krL6SF3HP+BN2y40HiARiWe9TSyVAmOCTza386vhMh4a98yW5ys3R3lV6Qg
v94yrQXBFUZQM2TwFafJtJctGe67bviL3iqGAP+O2KgjPUkFFIePtkbSz4R37juBbN0bdFevQjMmL7NjJwU
VrjMcjMTofPUrrK3ZkNep+vWecnw+Vpyx5MkMguc4zznf6qokuuI88+fMfR0u50u2lWdUpVVaxmTJZbaa9P
P7gcQxCBeH5JKUkNBak94XUydGGeyaZGA7gKT93VY8Qgg27qikqL6DjyDC+8fTnGFuBmc27a5bc7xmTl+6m
6pc/
gVg0daDN4oG4kJLxq65bdl+U8yvdDdv8tunLkWarwJjgr6oGuKNikLGYCaOQlJhiKvhWFEXJkqepjO4nTqQ
9r09tvp7HH+zK+71iNJx5ElYVhGepdFM1421D6RuSDLojU2HWvWI7Upf0P5tiT7iEqX4vUwPeecvY07mxeI
x9Yx68cVPKveEaEpcxzmaHn1+cU87s3LYPjhXTbO/
NuB9KaiWOzD4zSuZmAvBPfCMZgNcULb2Gs5JaIq7zwuOdjPanXyYrBPS2jS0YhCefF1TUuamoc9N9cpRjz/
QteqyKukI2XV6DybKMS5WUONpOYBkawHvp5XgOPLF48rVUhxEawYYmJi/
dvfS+KKuCZjRgcVqJTKXeWmC0mjBal7cCIxWzJqm0LJzRV1GUi5u6L8wNXZcYjIJ4NEUQrmk88JGfYrjtL/
N+rxgJZz7Iq4LwLBWUFVJ5SQMDz3dm1N4/4GW8fRjNqJGIpdmLKGDs1OCiQbiU0B6ycdDnIqprVFvD7HV7+
WhzO//
W1sJk4uwlc3J6y5vAICQlpgiPTqTPDKgj6Aitvnp6F6qGWy0YXFvOdzcuKtq27ZzSL1EB+Ao5cqCX0YHM9q
lKCcGpzAKLunUlmK1GTh0aJOg7U9+zoNBCdZMHm9NCYCpKodmwpH25jlPHqP7J97GMjswG3lIIdJMJQzTz4
EdqGhO79jLwhjcjjeqyeTEo3VxD71NtizcQyUF3obKVKoqSYzPVRgwu1/
nuygXP2+4lHj2WupGuU37iJSZX2b3iitxN/Md//Aef//znGRwcZPv27Xz961/n8ssvX7T9z372Mz760Y/
S2dlJa2srn/3sZ7n11ltXoqsZqdrZSMgbwNsxklH74aN9FLdksI9QJuuJL8QbM/
KlrnpOBR1oSASSBIIf9lfRYA0ymVj4n3ImDI9JjbaQg7ZQJsmNJGYt90vw1qKGWy2YrrqaU+Ky892Vi84n/
vM4IFQAnmchf5SBzomsXmOyZJ4wsqLOTXltIVPeMLFInMmxID0nxzjx/Jl95/
YCM+suraK8tjDj49rbTtD4f78EMnkumwmlhJRo0ShxewGGoD/
tRp6Ra29i5IZbSTjVzdLFpGR9JYMvdBEPn5u/
BcDqdlC+tW6Fe6UoysVubrlPDGtzUDcaSdDX6wcJ1bUFmLO4ZzhbIHEcuD9tO6NcfXFN3v/1f/
rTn3LnnXdy9913s3v3br7yla9w8803c+LECcrKys5p/+STT/KmN72Ju+66i1e96lX8+Mc/
5vbbb+fgwYNs2bJ6ZhMNpsw/
MJHJIEZbBkvaBJgWaBfVBZ863cRgJFmGKbnsPHnrGNY1jgedix9wwb9Tpx8SwKUuX/
r+KinNZO3+5oktwPIyMisLEWnrVCvLN9w7mfVrKurcWbUXQuAqstF1fIRTC+w5D/
qjvPBYJ1uvqKOqMbPtOlW/+h+Q+oIlyQRgDKZPniKFIOYpVgH4Raj/
uY5FA3CARCyuZsEVRcm5mQD8oVMxUm+CuvjEowmeu6+NY/
u7iUWS98Umi4GNe2u59KaWpW09S1TgMhoR8fiiTaTQCFUtP7dMruU9CP/Sl77E29/+dt72trcBcPfdd/
P73/+e7373u3zwgx88p/1Xv/pVbrnlFv7lX/4FgE996lM88MADfOMb3+Duu+/
Od3czNtWX+cyQZtQorC1GMxrQ4ymCMQmeBWbM/+R10x+xsPguxnQ5fTN/
jUBiFjrXecazOJ5ytrlZu1ciEcRapALwlRGPpS//
MUMIsNhNVNS7s36faDjOiYP9KdscfbqX8trCtDXDrX092Hq7U7aZ+XVS1gWXkoQju7KRyuoXj8QYObp4LgK
AmD+Ct3MET7PKhq8oSm7MrI586ESy3KdhDWVj1BM6nQf6CHnn5+KIRRIcfqSTU88P0LCn5pwSp5nYuulSql
56Fm2RRJpC6oxfff2S+p1PeQ3Co9Eozz33HB/60IdmH9M0jRtuuIH9+/cv+Jr9+/
dz5513znvs5ptv5te//vWC7SORCJHImSXcPl/
+Z3CDo1NEF1k2vhB3QykGk4HKS+rpe2aR5GwCHCUuXDXn7tl+ZNyTppzpUr7EYvp/
deR0un4NiUnT+dSG52kuzG75qTLf2Vm71ZJp5UJlKzBnFIBDMgDf9fLmtEHyQvo7xtO+TyKuM9jtpbopdW4
L81j6rUKZnDV1oxHf5u0ZtFQuJJM9Y+kzpAuY6BhWQbiyJqgkYflXcE0dpquu5psntswG4Gvp3rDjyPA5Af
hcockI8cEATVuyP+dOveEOEl2nEFOTiLMCcYnAt+0SJrfvyvq4+ZbXIHx0dJREIkF5+fz/Q8vLyzl+/
PiCrxkcHFyw/eDgwmVx7rrrLj7xiU/
kpsMZ8g9ltzyzoCK5j7F8Wx16PMHAC11AcgmmlICUFFS4ab5hy4LJh8ZjpoxKkC2F0DQKC8Bu07jxaitvuN
VGZdnq2X9/oTolLlNJw5SLQnltIUdNGolY6v1U6y+tpG5dyZJGsQH8k5G0M+5CQGAy/
QBowpY+saQEdJMZLRE/
56I987xIJPDsf4zR629JezzlwpGIZrA9SEIiuvjyRkW5WMyU+xQq6WTerdUAXEpJ98nRtO26T47SuLks60S
s8cIi2v75I1T85me4n3969poetzsYu+ZGhm98JWirb0XqBf+N+9CHPjRv5tzn81FbW3see3QWAaExPzSVI4
SgamcTJRuqGW9Lli8zmAwUNZXhKF18z6HbFGM0ZiIfe0d0Hf76vXvYfVU1AH7gVM7fZe35xFdfUAG4clEwG
DU27qzmpad6Fm1Tv6GUho3n5vg4WzQcp79jAv9kGINBUFpTSHFFAUKIjGfPNWP682CwsZW4owBjIMW+byEY
ueFWXC8+j72365wNOgJASip/87/oZouqD34RsTit6RsJgcWlzt/KxW0mAG/
TLgOj2nqTTw8dmeTxBzvW5L1hPKYTDi6eg2NGJBQnFk1gXsLe8HhhEb1veQcDr/
8LLIP9SKORcHXdqq5okteelZSUYDAYGBqav8xlaGiIioqFa1VXVFRk1d5isWCxWHLT4QwVlGeeoRdAj8+fZ
TE7LFRsr8/49S8rmqAtmL8v7P/8so17n0s/
QqVkY22NcioXt+pmD0LAiYMDRCNnZgcNRo3GTWU0bUkfgHefGOX4wX6kLpkZ5O4+OYaj0MLOa5soq3bRfSL
1eUhKKKtOf/6VRiMjN9xK5W/+d+HnESRsdsZe9nJCtQ00fusrKYc4y3//
Syb2XIU0nl0GUrkQuao9mOxmYsEUZeqkpGR95cp1SlFW2NwA/BP/
2cZaSxJ2PqzFABxAyyLJZfvhQXRdYndaqGoswmLL7rqbcBQQbF6XbRfPi7wG4WazmZ07d7Jv3z5uv/
12AHRdZ9+
+fbznPe9Z8DV79+5l3759vO9975t97IEHHmDv3r1ZvXexfRinJU83TA447TASCWSwVE1CSVl8WfttbreO8s
dRD0MRKzq5X05RUeygQiW5UhQlhaomDxUNRYwNTBEOxjBZDJRUOTEa01eK6O+Y4NizZxJhzV1yHpiM8MTvj
mMrMGFIsexdCCgqc+DypF9qDjB63c0YJ72UPnL/mRrhM8dCIuJxXEcO4TxyGKlpCy5Jn2EMBig49hJTWy/
J6L0vRrkuNSql5OMf/zjf/va38Xq9XHnllfznf/4nra2tef9dhCao3buO0/teWrSNp6U85Qo1Jb/
UHuX8K7imbl4ArpKdKvliMGoUltiZHAumSnAFQM+pMSB5n3DqhQFatlfQuCn7JeoXgrzP0d9555289a1vZd
euXVx++eV85StfIRAIzGZLf8tb3kJ1dTV33XUXAP/4j//INddcwxe/+EVe+cpX8pOf/
IRnn32Wb33rW1m9r+sVm3A58jdDXtsZpe03bWnbCU2w/n17MTmWPiBQCHzz2inu/
KGJtkENg5bcIZ6Yc8+41D3jBqNGaZW60VAUJT1NE5RWZ3e+kFJy6tBAyja6Lgn4UsxKAo5CK9uvasj8jYVg
8LY/w9F2fDZT+tyzpBaNUPvf3yFcVpEyAJ9h6zq9ZoPwfJQa/dznPsfXvvY1fvCDH9DY2MhHP/
pRbr75Zo4ePYrVmsFy8WUqaiyl6eVb6Nl/
ct6MuDBolG6qpuayprz3QVlYw60WDK7VU5L2YtW+5a956FQCFYArK6FhYymHHu9K227uIH0yEB/
EaDRQt74kj707P4SUmea9XbpvfOMbsyPoO3bs4Gtf+xq7d+8G4Nprr6WhoYHvf//
7s+1/9rOf8ZGPfGR2BP1zn/vcvBH0VHw+H4WFhXj7fo7Llb+TSs9vDvHEX343bbu611/Cld//
65y8p5SSZ18I8/j+IOGoTmOdmXXNZv7xw4NEopIM7iPPsf7SKho2luakf4qiKGfzjgY4cF/
6Acuzma1GDEYNq8NETZOHinp31knfnC8+T8N3vr7o8xKQJjMiFkOkG54HptZvovuv34Vuz345YSQc4Mv/
ejOTk5O4XBfWwOfu3bu57LLL+MY3vgEkV7TV1tbyD//wDwuWGr3jjjsIBALcc889s4/
t2bOHHTt2cPfddyOlpKqqin/+53/m/e9/PwCTk5OUl5fz/e9/nz//8z/PqF8z1/tn3/
I2CszmJf1uUpf4+seJToUxmIy4aj0Y87WKTklrpoSTsKn9yfl0MryRh45HePzBThWAKyvm1AsDnD4ynHHZ0
xkms4FrX7dpyYlfV1I21/oV2a3+nve8Z9Hl54888sg5j73xjW/kjW9847Le879ebMSWz/
qu1XU4i36B8PoQC3ySJIDBwIt/+wFefCGH/
RBgvwLswCTwjIRb31PPoz85wmjvVHaHEsnyQ4qiKPkSDS8tw3QsEueKWzdlvR9srqKnHk+51FwAIpZ6Bn6u
glPHafj2Vzn93g/CRbg0biH5KDXa0dHB4OAgN9xww+zzhYWF7N69m/
379y8ahOejJKnQBIU1xcs+jrJ8DbdaMO7ZyzdPbIE8bL1T5lIBuLLyWndU4qkooPvEKOPDAZASzaClvU+IR
ROMDfqzXom32q3elHHLdOCRbszW/J5cil/1l+z60X8CzAvEZ/7r8GveTP/
TY8BY3vogpSQ0GSEcyaDkyjmvhUOPd7LnFetwFWW2z1JRFCUbSw2ipYTR/imqm1PXBE/
FPDGe0VJz3WBAS6Q/hwpdx3H6FI6TRwms37zkfl1I8lFqdObvbMqRwvkpSaqsjBLHEMY9d/Ct9h08/
mAXBqGC8HwzrJGBRGV1Ka5wUlzhnP15/x9PZjRYv9QB/dXsog3Cq4vsWKx5zkC4aycdxR+k/
J5fUNB2YvbhUG0Dw6+4HW3zNmry+PbDvT5OHOwnOJW+bm4qncdG2HZFXY56pSiKkqQndKa8ITSDQE9kv/
MpHl/CHpu5ry9wIoVYcLXSXCKDAHyG1DSKntm/
ZoLw1WQ1lCTNZcKw41MufjlQxwFvKTFd0GD3c1tFDzeUDmIQed8puKq4//
UO2kx7efzB42s2g7SirEVWuwnfRChtwjaL7eILWS+
+32iFBRtb6PiHf8U0MY5xcoJEgZNoSfpyPcs12O3NKMFBOlLCUJcXubf2osw8qCjK+RGLJnj2oXZ8Y6ElH8
PhXN52Ge9le3GeOJK2XTZnPqHrGKeWvwz6QpGPUqMzfw8NDVFZWTmvzY4dOxbty/
koSXq2gmvqMF119bKP8+v7Qvz716fQDDAzBtQeLOQL7YU8UXgpX/
poIQPDCfYfjBKLQWujkcu3m7Iq9XMhOSUu4xPfUAG4oqw11U0ehntTX1PNFiOeObPnFwsVhOdIrMhDrGjpy
yazoSd0jhzozd3xdImUa2aLo6IoK+DIgR5840sPwC1207wla0sxueMyyu77Heax
kYyWpWdCahqxQndOjnUhyEep0cbGRioqKti3b99s0O3z+Thw4AB///d/
n89fZ1kabrXQecV7QRjBsPQM7l2nJ/n3bzyI5EwADqBPzwQ9dTDK7X8fZHgwgBAghEDXJaXldv7+/
bvYuPXiS6b6ia+
+oAJwRVmDSqpdacuXrbuk8qIcgFRBeB5YBvtwHn0REY8TrqphatM20HK3v2moZ5J4NPs94IsxW40X5YdbUZ
TzIxSIMtQ9uaxjbL68BrHM85I0mTj9nn+h4e6vYBvoRc6ch6UEubTCjkLX8V52xbL6daHJdalRIQTve9/7+
PSnP01ra+tsibKqqqrZQH+1mcna/dCJGMm1E4ElH+ux/z1OuvTAw4PJ4yc/
qsl2I8NBPv3Bx3n1u3dTVu9e8vuvNo8/mKxTrQJwRVl7NE2w87omDj/
RxejAVHJCUAikLtEMgvWXVC0rN8xqpoLwHDL4fdT+4Fs4Tx5FJoevEbpOrNBNz5v/Nmd7CAO+SNbp/
RcloLZVZYZVFCV3xgYyq9TgcFmIhGLEY2dmqe1OCxt2VVFalZssqHG3h7YP/BsFJ4/
iOnwQLRIhWlpOwfGXsHe0ZRWIS6Hhb91AoGV9Tvp2objjjjsYGRnhYx/
72Gyp0XvvvXc2sVp3dzfanIHmK664gh//+Md85CMf4cMf/jCtra38+te/
nq0RDvCBD3yAQCDAO97xDrxeL1dddRX33nvvitQIz9bcrN2PP9i97IRW7YcGkPoSLuAS9ITkgf8+ROOefGa
cWVkGoQJwRVnLTGYDO69vYmoixFDvJImYjt1pobLBjdFkON/dy5sVqRO+kmbqhv7TZ+/
Dkufs6HOJaISWL34Ky9DAOUmAJIBm4PQ/
fIBgU+uy36vj6DAnXxhIm8QgHSHAajez5xWtmC1qPEZRlNzoPjHKsWf70rZzemzsvrGF8SE/
8VgCm8NMYYl9RfJTlOz7IxW//VnKIFwCUjMgkAhdZ3LrJfT+1dvRLdkHihdynfDVauZ6P/zf/w8ue/
72ihv37J3O2t2dk4Dx4V8cWXam35fdtlGVGFUURVllVl2d8LWg6OknsQz2L3hDJwCpJ6j47c84/b4PL/
u9Ckvsyw7AATzlBWy9ok4F4Iqi5FSBO7Mg1T8RAsF5qf3p27yNit/
+bNHnJcns6t5de9FtdiZ37CJSUbVyHVQyZr7uRsyu/
A263/1Cw2zZrFzM2BYW2xnt9y1rNVsoEFVBuKIoSqYSCRwdbRgCfmLuIkJ1jec9GZaKvnKk+PF9KZ8XgKOj
DfPo8LKyp48P+Tn4SMeSX280aqzfWUVRWQEO1/nNMqsoysWpqMyB2WpMO9snJTy7r50te+pW9Hwk4jHqv/
t/U7cBjP4pxq6+ntgKVLxQlu6/XmzE5ijI2/Eff7Ajp0nD6taXMNK3vAz7JvPFu0RTURQll4qefJTyP/
4ak+9MrppIaTkDt9/B1JYd561fKgjPEfPoSEZ7C6t+9t/4121kYveVJAqym/
2JhGIcfKSDxFJr5woornJiMGok4rlL7KYoijKXEAJPeQGDXd60bb0jQfbfe5LLb2jB5bHlv3NA4fPPYh0aS
N9QCIqe/hPDt742/51SluzAI92Y87j9LNdZu4srCqhp8dDbNr6k19udloxXmyiKoqxlpQ/
8nop7fnHOAmLzyBD13/4a3X/99/
guuey89E0F4RnQQkGKDvyJomeexOCfIlbkYXzvy5i8dDfSZAJA6JkFtQUnjlBw4ggV9/yS/
te9ifGrr8+4Hz1tY0sPwAEkDHVPzmYtdhZZ2XR5De6Slds7ryjK2mB1mDJOIJmI6xx6oourXr1+RfaDu59+
Aklm9cHN42P57o6yTNVFdizWCyexlxCCTZfX4Cyy0XF0mHAgBoBmEJTXuhnpmyQe1xfddtayrXxFvieKoii
ZCPmjjA1NIXVweWy4PLbzdo4SsRiFzz+NvaMdLRrB/
ez+5ONntyN5iq3+3x8ytXUH0mha6a6qIDwd88gQTV//LMZJL5D8RzNNTmDvaKPkkfvpePe/
kChwIjUtozq0s0nbZILqn/83CUcBk5denlFfllvy52xTE2GeeaCdy25sVoG4oihZiYRj9LWNM9zrQ0/
oOIts1LYW4y5NnkuKSh10Hh3J7GASglMRJoYDeMrzt6x4hmnSm1lWdCkR8Tim0WG1JF3JKSEEdetKqG0tJj
gVRdd1bA4zRpMB33iQ5x7umL+dY/qOcf3OKiobis5bvxVFUWZEI3GOPNXDcO/
87TXOIitb9tbhKlqZ1W0zHCePUffd/8AYCiZLkqYpRSoAYzCA6/
DzGcdiuaSC8FR0nYa7v4RxyjfvH3EmkLYO9lP33f+g56/
eTsxViHl8LLtyN0D5H37F5CWXZZQcYFmz4IvQpeTYM33suaU1eSOQ0LEVmC/qkgCKoizPTG6Kueck/2SY/
o4JaluL2XhZNeFgLLuDCvCOBlckCI8VFmEZHjynksUCXcL9/
NO4n3+aYE09w7feztTm7Xnvn7J2CCHOyYfg8th52W0bGez2Mto/ha5LnG4rNS0erHaVjE1RlPMvHk/
wzAPtBHzhc56b8oZ5+v429tzSSkHhymydsfb10PDNLyMSyZXJmUyMAuiaAcvwYD67tigVhKfgPHIIy+jiMz
lC1yloP8nGf/
sXIPuE5QKwjAxh7esmXFOfvj9uK+FANPuMqjNrLhYiwTce4tFfHSMSml4Spwmqmopo2VaBxbbyyzMURVm9w
sEozz18Gj1xVinG6R97To1hKzDTcyr7ZdwrtXrNu/tKnCePpmxz9nJ1W183Dd/6Kr1vehsTe67Oa/
8UxWDUqG7yUN3kOd9dURRFOUdf2zj+yXMDcAAk6AmdU4cGueRlDSvSn9IHfo/
Q9bSD62cTUkc3nZ9YRzsv73qBcB05lFzOkKGl3j8a/
f6M2tW2Fi+tpEkGr5kJwAF0XdLXPs5T956a97iiKErPyTF0PfVJpePIMCF/NLsDSygqy/
8sOMDkjl2EKqtTnt/P2T8mZXL/2E9/iMG/vMzWiqIoinIhSzfQLiUM90ymrZKSCyIWo/
DQsxnPfs97rZT4zlOGdBWEpyBiKxOAxtzujNoVVzopryvM/MAiOZq+FFImA/Pjz/
Yt6fWKolycBrsn0w7sxaLZVV8QApxFNtwluU+uZRodpuTh+yj7429wP7MfEY0gjSY63v0vBOubAJBCQwqRd
rxSAEidogN/ynk/FUVRFOVCEQpkNtAeDmY5IL8EhlBwSQG41DR8m7YRLa/MQ6/
SU8vRU4hUVGWW2neJpBCEq+uIVFRn1F4IwbYr62l3DtJ1YjTtHnEBVDUWLWlZKCR/
9aGeSSKhmFqWrigKQMblDYUGMotroslq4NgzvZTWFFJcUbDszKpaJEz1j79H4QvPJKN8oYGeoOpnVgZe9yY
m9lzN6X/8ELbuDlyHn0eLRTCNjeI6cijtcjZbb9ey+qYoiqIoFzKjUSOaSH8/
sBI5phJ2O7rBiJZIPes+s81MCoGQklBNHT1/9Y68928xKghPYWL3VZT/
4Vd5CcRnjjjwmjdk9TpNE7TuqKRpSzkTIwFCUxHajwwTOSsJkslsYOsVdRSW2OnvGCcRX9rvICX4vWEVhCu
KAoCj0Eok7E87G15R52awy5vR6VNKGB/wMz7op/vkGI5CCzuvbcJWsMQkVLpO/be/
jqPt+PTstQSZvFnQImFq/ud7SIMR72V7CdU3EZqeES/
Z90dcRw6lPrYQSINKXKkoiqKsXRUNRfScHE15jTdbjURCMWwF5ryWLJNGE96duyl6dv+iM+JSCOJOFwmrjV
hRMRN7r2Zy26VgOH+hsFqOnkLcVcjAbXcA2SddW4iccxzdbMa7cw9aLAYZjCSdzWDUcJfYkzPVC2QhLq8tn
K1ButBu9Wy+C0JT9UgVRUmqbS1OfUIUUFxRQOuOSizWLAfvpo8b9EV45sF24hnOup+t4MRRCk4dW3BGeyZP
ZcVv/vecc69/w+b0GdN1Hf/
6LUvql6IoiqJcDOrWl6SND6LhOE8/0M6Tfzi5eBK3HBm58ZXoRhNygQBHCg3dYqX9fR/m1P/
7f+h81z8zecnl5zUABxWEpzV27Y30/OXbiXlKln2suR8LLRbDffAADd/
+Ghv+7f0UHHsxq2NJKXn+sU7GhhZO6tbbPs4TvztO57GRBZetF5bYKatxpX0fg1HDVbyydf4URVm9ymsKKa
50LvykSK7WQQge/80xwktM7Chlcr/ZQId3Sa8vOvBE2qRrpqlJ6r/7Dap//F1K9v0Ro2+ScHUdgfqmBS/
ikBxJjxW4mNyxa0n9UhRFUZSLgcNp4ZKXNWbUNjCZLFmW6T7ypYiWVdDxDx8g5i4CkqXHpJZctRb1FHP6vf
9KrLg0b++/FGo5ega8l+3Fu3M3tp4uHO0nqPzN/y75WDO3dkLK2WXuxikfDd/
8Kh3vfj+B1g2Z9WkkyPhg6qzqqfaMe0eDVNa7075PbWsxRqNaeqkoSpLQBJdc08DJ5wfoPTU/
U7rDZSHoizA+OJWTXTx9p8eTM+9ZMk2MZZSkxXnkcHJZkJRU3PMLfJt3YO/
uhOlM6HDmnC2FQLda6Xzn+5DnqZyJoiiKoqwWma5WkxLisQQdR4fZdFlN3voTqmvkxMc+h/
PYS9g7ToEQBJrW4V+/
CbKodrVSVBCeKU0jVN9IqL4RkUhQcc8vkJo270bv7LqymRJSIkVyeWT7+z+W0WsGOidm7h2XRsJApzdlE09
5AS3bK5b4BoqiXKwMBo2Nu6pp2VbBxLAfPSGxO808+9DpnKbQWGqJxHiBczbxSipzB0ORksIXDy7YTgK6xU
LbP33kvGVRVRRFUZTVpK99POO2Uibbb9hZnVwxly+axtTmbUxt3pa/98iR1TcscAEYufGVdLzzn/
C3bJidLYkVuAjWNy/5mEJK7D2dWAb7M2ofjcTzmbid9Tur2HldIwaD+ogoirIwk9lAWU0hFfVu/
JMRYpGl7eFejHGJJRYnd+1JG4AvZLFXCEALhyk4eXRJ/
VGUGYm4jn8yTMgfRebzIq4oipJnUxOhrNrrCUk8yxKmFzM1E75E/o1b8W/
cCokEQtdnlyc2fv2zONpPLukGEMDkHU+WRkvDYjMtbyY8HQmaCsAVRcnQ5Fgw5+ekgkLrkl7n23op4YoqLM
ODWdUOTTc2X/T0nxi/
+uVL6pOytkXCMdoPD9F3ehw9kfyS2F0WmjaVUdVUdE7mYCkl3pEAPafGmJoIYzAKymoKqW7xZJ/
wUFEUJce6T44SCaUuCXYOAUaTii1mqCB8GYzecUoefZCiA09gCAaIO134WzfM7ic8+4Yuk+XqCbsjo/
eubvLQfWJ0Cb3OzPiQn4aNqyuBgaIoa4ur2L6k10mjkY53vZ+Gb34FW193MjmLlCD1JW0ZguS52zg1tcRXK
2tZJBTjqftOEQnG5g1SBX0RXnqqB/
9kmPWXnhl8l1Jy9OleetvG5w1sTY6FaH9piEuvbaS4YpHkiIqiKHmWiOucfH4gq9cIAWW1hWqCbw4VhC+Rr
bOdxq9/Di0em72pM/kmcT/3NAmLBUM0ikQgpJ5ReTMJxDwlhGrqM3p/
l8dGRX2yDm9+qGVyiqJkrqjUkfOBwdLq9BUcFhMvdNP2/o/
hOHWMwkPPoYXD2DvaME+MLW2puhDEijxL7o+ydh1/
rv+cAHyuzmMjlFa78JQXJH8+OkJvW3Kv5dmv0ROSZ/edZtPlNUtKWqgoirJcQz2TKZM/
L6ZxU1keenPhUkH4EmiBAE1f+wwikThnVkUgMUSjRDyl+HZejr2jHQQE6psofvJRDKHggssjBTD0ituyyt6
3dW8tBoOg7/
QEiOn6tzPT7cuMod0lmc3IK4qydsWiCbwjAfSEjqPQitlqJBrOcnnaAoSAovKCJS9Hn6VpBNZvJrB+M4XPP
YXz+EspA/BUq5WElIzvuXp5/
VHWnEg4xlC3N+U2DSGSSzs95QXoCZ2OY8Npj3v06V6EBjXNKhBXFGVlhYPRrLafaQaNHVfXU7jE1W0XKxWE
L0Htf38bLbF4YgEhJdaxYfpbNzL0ytfNPj65aw8N//klzN6JZA3bOZ/ewde8Ee/
lV2bVD82gsWVvHc3bKhjq9hKNJLDaTfgmQvS3jy95b6bQBNXNasZHUZSF6Qmdky8M0HNqbHZ/
K4CzyEo8lpj32KJEMvFaPK6fM2hod1rYdmVdzvpb9OQj1Pz0h2nHJmfGL8/
ZSqRphMsrmbx0d876pKwNfm847bVYSpgcDQLJ3AqZJjg89nQf5bVuTGZVRlRRlJVjMhszijFsBWbqN5RS1V
iUv/OUlBgnvYhEgpjbDYYLJ7S9cHq6SmjhEM7jL6VtJ4GCk0cJrNs4+1ikopqTH/
0srhcP4jxyCBGLEamoZnzv1cTdSw96bQ4zDRvPLPE4+nTv0g40fQe6ZU8tFptK/
KIoyrmkLjn4aCdjA+fuj56aCKd9/
czo+bYr6vCUF9Bzaoz+0+PEogmsDjM1LcVUNxVhNOXmgm0e6KP6pz9MvncWr9MNBoSUCF0n0LyO7r9+p6oP
rmTt7IRr6dpls8RT1yVP3HOchg2l1DR7MFnULZ2iKPlXVuPi2DPpZ8I3X15DcWWe8ldISdH+Ryl96D4sI0M
AxO12xq+4jpEbb0W32vLzvjmkzthZsg70ZZxtd167RByT1wuaxuT2XUxecnl+OggUltjpOTWW9euKKwpo2l
w+uy9NURTlbEM9kwsG4KkIDeT06bCkykXjpjKKypJbXlq2VdCyrSLX3QRACwZo/
tpnsnqNIDnzPXr9LegmM1NbthOuzt2svLK2uDw2NINIuTpECCipSt6o2p2WrI4fDcU5+fwAXcdHuOyGFhyu
7F6vKIqSLYvNRE1rMT0nF441hACnx4anIk/xhJRU/fQHFO9/bN4KN2MwSOm+P+A8dpjT7/3gqg/
EVRCerQzXeAsgWNuAiEQo3fcHip94GGPAD0CkuJSxa29i7KrrstoDnqmKOjfHn+0jHstssGDHyxrwlBdgMh
vwjYd4aX83I/1TSClxeezUrSuhtNqZ8Yi+oigXr+6T2SdfkzpsvKya6iYPhiXW/
l6K4icewhAMZJ0RXeg6wze+CmlRAY2yPEaTgdrWYrqOL/
69kRJq1yX3dtudFjzlBYwP+bN6n0g4znMPn+aqV29A09S1WlGU/
Nqws5p4NMFAp3d2hdvM384iGzuvbcpb3OB86QWK9z8GnLvCTUiJtb+P8j/+hoHX/
nle3j9XVJ74LIWratCNqZckSkA3GPGv20TTNz5H2f33zAbgAOaxESp/8SNqfvQdyKKGbaYMRo3tVzckP/
xpPv9164opry3EZDbQ2zbG/j+epL9jgmg4TiySYHxwiucf7eClp3qQeStKrijKaielpP/
0ON6RwJJef+K5/hU/h3iefGxJr0tYrUizOce9Udaq1u2Vsys/
5pq5P928uwan+8yMzYadVWiGLG9eJYT8UUb7fMvpqqIoSkY0TbDtynr2vqKV2nUllNW4qGosYuf1Tey5pRW
zNX/zvMWPPYgUi4ewQuoUPfkoIhrJWx9yQQXhWdKtNib2XIVMMbojgIHXvIHSh+/
F1tN5TjZeMf2n6NmnKHzhmbz0s6TSKXLjaQAAzG5JREFUye6bWyitWrjEj8VmZMOuKjbsqgaSyWCOHEjuJZ
/b3Zn/7j89QVce65IrirJ6SSk5/
mwfL+7vWXLCR12X9HdM5LZjaZgmvVnPgktNY3zPy85ESIqyTAajxq7rm9h0eQ0FhVaEAM0gKK9zs/
vmFmpa5mc4dxbZuPymlqxXjQgBI/0qCFcUZeW4PHY27qrmkmsa2bK3jpLK/
K+ctXeeRsjUk5iGaATL8FBe+7Fcajn6Egy+
+g3YO9qx9vfMC7BnsuqO7X0ZU5u3se4zH09dDkcIih97MC8ZdyfHgvScHCXgi2B3mXGXOKisd2MwahiMGk6
3DTFnyVrX8ZG05QY6j41Qv65k3usURbn4jfRN0b3I3q9sZJK4LZcSNtu8VUjpSE0jYbMzet3NeeyVshZpBo
3a1uKMa3sXeuxc9eoNHLjvFOFgLKPXSMisMoGiKEqGpC4ZHZhipN+HnpA43dZktvPzmQgyw628Mg9bfnNJB
eFLoFttnP7HD1Ly8P14nngI01Ry5DlU28DIja/E6POy/tMfTjsDI6TE3tWZ8/61HR6k/cWheUF1aCpK/
+kJtuytpbrp3EzsI31TaWe4IsEYganI8mv3KopyQek+kX6QLq3p2b+V5N21l+LH96VMpjm3JFmktJyuv30P
cXfRivRPUVKx2k1c+er1DJyeoOPYCCF/
NPULJOr6rChKzgR8EQ4+fJqgPzq7OExKOPn8ABsvr6amObNBxVzzt27AdeRQymt73FFAtCw/
SV9zRQXhS6RbrAzf8hqGb3oVhlAQaTCgW204X3qB6p//KOPjyBzPKg90TtD+YnL5xULLyl/
a34PDZcFdMn9/
mp7h3nQ1yq4oa493NLi8ABxAJrfJrKTRa26k6KnH0KLRRVclzZyBpRAk7I5Vf9FW1haj0UDtuhKqmz088qu
jKWuICwFVzWoASVGU5YtF4jzzYBvRcByYH1PouuTIU72YzEbKawtXvG9j19xI4YvPL/
q8FIKxq1+ONK7uMHd1z9NfCDSNhKNgNg1+2X2/
TblffC6paQRaNuSsK1JKTh8ZTtvuxMH+cx5zFqVP469pArtTJStSFCV79gLzbBmms0VCMU4fGeLwn7p46ak
ehnom0fXlD/jFikvo/Pt/JmGzk+5oQkocHW3YO9uX/
b6KkmuaQWPLntqUbTbsrMZiVbXsFUVZvt72cSKheMoB+FOHBs5L0uZA6wYGX/
k6YP6Sc4lAAv71mxm58ZVpj2P0TlD++1+y7lMfZMNH3kfTV+/C/
ex+SMTz1fX5778i77JGGL0T2Ls7M24vdJ1IaRlaOJSTWnaRUBy/N/2eS+9IkId/cYT69SXUrS/
BaDJQt66EF0e7F++rgKqmIowmw7L7qSjKhaWozMHYQPotK4sxWQxcet3C5Uq6jo9w4mB/
8tjTBR362sexFZjZeV3TonWPTeNjeP70MIXPP40hEiFSVsH4ldfiveQyEBrOI4dwHTmEFo0yevXLsfd04Dz
6YsptQlLTKHz+GYKNLUv7RRUlj8pqCtn18iZOHBxgaiI0+7jdaaZlWwWVDWoWXFGU3Og7PZ62TWAygn8yPK
+6w0oZuelVhGobKHnkfgpOHgVdJ1xZxdjLXs7E7qvAkDrEtbefpOGbX0aLxmaTvBn9UzhOn6LoT4/S+c5/
ynuZUhWE55AhHMyo3cweRAkUP/4QRc/sp/Md/
0iwed2y3j+RyLzcWTQc59ThQfo7Jrj8xhYq690MdnkZWaC8iRBgsZto2a6WaSrKWlS/oZTR/
qklvdZiN3HFreswL5DEpb9jguPPzVmZI5mdsQ4HojzzYBtXvmoDJvP8wT/
HqeM0fOsriFh89uJpCPhxnD6F57EHMfr9WMZGkiPkUlIIICVSiJTJMgG0cCjl84pyPhVXOLniVif+yTDhYA
yzxYCzyJb3bMSKoqwtM8vQ07dbfItMvvk3bsG/cUtyrbyUGSds04IBGr71lXO2qs38t6PjFFW/+BF9f/
E3een3bD/yevQ1JlZYlLJu3Qwx528BaJEwDXd/
GdPY8kqAWW0mMnj7MyQEpyIcfaYXoQm2XVVPWY3rnNriZbWF7Lm5VS1zU5Q1qqTSSePmsiW9trqpaMEAXEp
J26HBRV8nZXJ1T1/7/NF4g3+K+m9/
FRGLzStRMnPxtHd1YB4bST6m6wgpk38ALd1UvkwuYVeU1a6g0EpJpROXx64CcEVRcs5qz+ye32pfBfO5QmQ
cgAMUHfgTWiSyeK4YKSl65kkMU/kt+aiC8Bwwjw7jeXwfnv2PEaqqzvr1Qkq0eIzix/
ctqx8Go7ZoXfDFSAlD3ZP4fWGee+g0w70+5m2eFDDaP0VwanUXvFcUJb/
W7ahkx8sacJfas3rd6SPD85bOzvCNhwgF0mR7Bvo75gfhRQeeSJt
obbGQJP1qesnE5VelbaUoiqIoF7PqDDKfuzw2HK4LryKD68ihtOVehK4nl7nn0SoYvrhwacEANT/
6LwpfegE5vZkx3VLHxQhdx/
3cUwzefsey+tS8rSIZSGfp6IFevKOBc5+QkIjrPPdwBy+7feOCM1qKoqwN5bWFlNcWoid0EgnJi092MdKXe
pm6ALpPjrJ59/ykUrHI0pa6uV56Ycm10tLNF468/
FZiReeWcFQURVGUtaS6qYjuE8nSiItdctddUrmyncoREY2kvR8AEPH8JmhTM+FLJOIxGv/
jC7iOHk7+jJwNwCWZzLicyxBa/l5EV5ENW0H2GcwnhgMpO52I6/
SfnlhGzxRFuVhoBg2T2UDz1vR5IqRkwYFBqz2z85TVMX9JnIjHMrp4ppIwJ99bTh8pYbYw+KrXM/
Sq1y3zyIqiKIpy4TOaDFx2QwsuT3L1mxDMbn0xmg3seFkDxRUrW3Y0F0Qkgnl8NKM4LVxVk9e+qGnNJSp87
gD23q4Fn1vKDaIEop7lF73XdZnxDFO2RvomadhYmpdjK4py4cm0NIm+QNLIArcVZ5GVqYnUFR1qWubPTIeq
67H1diP0zBNRnq3j3f+CadKL0eclUeDEt2l73rOgKheJRBzL6AhInWhJGdKocqUoinJxstpN7LmllcmxICN
9PnRd4nRbKa8tRDNcmPO45X/4FcYpX+pKKUIQrqohXNuQ176oIHyJPE8+mlGmXTgzwZwuOB+/
4trldotQIEo8tvSb01QSiZWvBagoyupld1oQIv3qcPsie8bWX1LFsw+dXvA5IcDhslJZP7/
s0vhV11K8/9El9VcKQaS8klB9EyGVzErJgojHKdn3R0oeexCjP7kFI2GzMX7FtQzd/
Bo1iKMoykWrsNhOYXF2+WBWIxGN4Nn/aOoAfPrv3je9Le/9uTCHMVYB8/hoxvu/
ZxIF6QbDgssfpKYRKa9kYu/Vy+5Xvm4rhUgudVcURZlhthipqHeTLp6dGg8y2O095/
HiSieXXNOAyZIsQSbmZFUrKi/
gshuaMRjnX6bCNfWMXH8LcO4OmlRn5JnnBm77M9J2WFlzDP4pSh66l5r//jbV//
M9XC88C4npVWWJOHXf+Trlf/z1bAAOyS1kJQ/
dR9PXP4uIqOSliqIoq5l1oB9DmnO1ABIWa95nwUHNhC9Zwu7A6JvMOOiVmsbUxq1YRoawDg0gp6ePBDC1YQ
u9b/5bkBLPEw9TcOoY6Dqh2gYm9lxN3FWYcb+sDjNmqzHj+n6ZkhJqW5e/XF5RlIvLuksqGR/
yEwktfs6REg490YXlRhNFpY55z5XVFHLta50M9/nwe8NoBo3SaidO9+KDfoOveSNRTwmlD/
4eszeZq0Ky8CDkzOMJu4O+P/9r/Ju2Zf9LKhe1ov2PUfWz/y+5xWF6gMbz1ONE3R46/5/34ehow3nsxQU/
X0Lq2Hq7qPrFj4gXuhGxGJGKKryXXo40q9lxRVGU1SPDFb1ZlDtbDhWEL5F3117Kf//
LjLP0Cl3HGPBz6kOfxt7Rhq23G2kw4F+3kWhpOfa2EzR8+2to4RAz6ztdLz5P+R9/
Q98db2FiT2az5JomqF9fwqkU9XeXonFTGU41E64oylmsdjN7bmnlwH1thIOxRdsJ4PRLQ+y8rumc5zSDRkW
dG+oyfFMhGL/6esavvJaa/+9buJ9/
JmXJsqEbX8nILbchjeqSp8znOnyQmp98/8wgzpzPkcnnpekbnyNudyz2ciBZFcVz4AmkEEhNQyQSVP7yf+i
74y1M7tyT1/4riqIomQlXVJMwWzBEF58Nl5pGoHndivRHLUdfovG9LyNhdyBFZv8XSiFIWK0gBMGmVsZe9n
LGr7yWaGk55pEhGu/
+MloknFy6Pj1DLqQEPUH1/3yPgmMvZty3hk1llFTlJmOh1W5i02XVtO5InwVZUZS1xT8Z5tgzvTz5h5MpA3
BIxjaj/VPEY4mU7bIhYjFcLx1KuTVIahq2vh6k0YgWDGIaH0OkuAAr842Pj/PmN78Zl8uF2+3mb//2b/
H7/Snb/8M//APr16/HZrNRV1fHe9/7XiYnJ+e1E0Kc8+cnP/lJvn+d+aSk7A+/
SuZ3WeBpoesYAn6sI0OZlbOREi2RQABaJEztD7+F86UXcttnRVEUZUmkxcLE3qtTxm5C1xm75oYV6Y+aFli
iRIGTjnf/Cw13fwmTb3LRpZCzpMS3fdeCTxU/+iAiEV/wRlKQDODL7vst/
o1bM+qbpgkuuaaR3lNjdJ0YJTi1tBtOzSC45JqG2fIEiqIoMwa7vRx+oivrkt3xmI7RZMhJHyzDAylHtCF5
QXW0n6Dh/34R54kjQDI/h/fS3Qzf8hpiJWU56cvF6s1vfjMDAwM88MADxGIx3va2t/GOd7yDH//
4xwu27+/vp7+/ny984Qts2rSJrq4u3vnOd9Lf38/Pf/7zeW2/973vccstt8z+7Ha78/
mrnMMyNIBtoC9tu7TX9wUIkiXwKn73c6Y2b1d5CBRFUVaBoVe+DvvpNmy9XbPbgoHZZNvDN7ySQOvGFemLC
sKXIVxdy4mPfY7CF56l9L7fYllktFxqGvECJ95Ldy94HPez+1OW2xFS4uhoxzg5QbywaNF2c2maoG59CXXr
S2g7PEj7i0MZvW4uXZcce7aP5i3lBP1RjCYDJVVOzBb1sVGUtSwwFVlSAK5pYjYJW25kFthokQgFJ46e+Tm
RoOiZJ3E//zSn3/nPmKcmMfomiTudTG3ZgW5ZOJv7WnPs2DHuvfdennnmGXbtSg4if/3rX+fWW2/
lC1/4AlVVVee8ZsuWLfziF7+Y/bm5uZl///d/5y//8i+Jx+MY52wJcLvdVFScv1VWhsDiM/ozBKBP7w/
MtiyeQGId7Mfa30O4OtO9FoqiKEq+6BYrp//hXyl55H6KH38I01RylVaotoGR62/
Bd8llK9YXFU0tkzSZ8F62l8lLLqPmh9/Efei55J4wXZ/d/
h93FNDxrvcvWsLEEEldJ3e2XTCYcRA+V926EnpOjWWfrE2CdyTIcw93zD4kNEFtazHrL61C09TIvqKsRT0n
R7N+jRBQ2ejGkMPaopGKKhI2G4ZQaNE2Z0pEzh8xEADxOM3f+OzsiiMhJQmzhZGbXsXIDbeu+dnL/
fv343a7ZwNwgBtuuAFN0zhw4ACvfe1rMzrO5OQkLpdrXgAO8O53v5u/+7u/o6mpiXe+85287W1vQ6T4/
zwSiRCZk9nW5/Nl+RvNF3Onv55KBPFCN+aJ8SW/
j9E3CdVLfrmiKIqSQ9JiYeTmVzNy4ysxBANIoxHduvJ5r1QQniPSaKTnbe9ivO04nicfxTI8SMJqY/KSy/
Hu2pPyHzdWWIRpYixN4XiNWKF7SX0zW41cfmMLBx/
tIOhb3l5IqUu6T4wSCcXYflV9yhsmRVEuTsO9vqxnwQ1GjabN5TnthzSZGLvyekr3/
SFlYrbFzH1u5vWGaISKe36BiMUYvvX2nPX1QjQ4OEhZ2fzl+kajEY/Hw+BgZsk/
R0dH+dSnPsU73vGOeY9/8pOf5Prrr8dut3P//ffzrne9C7/
fz3vf+95Fj3XXXXfxiU984v9n773j2zqv+//
3c7FBAiTBvYeoPaw9PGTZ8pDtzDrDjb9JnSbOdPJt4jSj3+b7a5tv02Y0bVaTpknaJrGbJk2c2oljR17ykK
xp7cW9NwiAxAbu/f0BEiJFEgBJkCKp5/166UUR97nPPZCAe5/znHM+Z/pvZArCufl4a5ZjbapPoCug0X/
7PnTDQxQ+
+1R8kz12JLVcjEimPV0mSyQSiSRdKArRzPRoaM0E6YSnEyHwLl897VoC5423Uvj0E1MqrWuKgnvDZtQkCq2
JyLCbuPlNKxnoHqan1UV3i3tWAkk9rW5c/b4J7YYkEsnSR1On54ELAZv2VNPX6cE3FEJvUCgsz8bumP3Oc+
++t2BtaSCj7mLsWqM2jslImslWYcEffovz5tum1SJysfD5z3+er3zlKwnHXLhwYdbX8Xg83HfffaxZs4a/
+qu/Gnfsi1/8YvzvmzZtwuv18rWvfS2hE/6FL3yBT3/60+PmLy8vn5WN3W9+BzXf/
krsc3LVM1hTFEKOPAa334RqtuCrWUHugf1k1F9CaCrhrByM/
b1Tfr40IJRfSKBMpqJLJBKJZDzSCV8ADNx8Gzmvv4xx0Dmh5kwTCqreQO89b531dYQQ5BXbyCu2sXprKacP
ttLT6k5+4qRzQUf9gHTCJZLrEFuOhYA/
nHLLzcxsM8eeb0RTNYQSa8HYeLYXR1EmG2+uxDALnQnNYKD5I5/GcfAAuS8/
h6mvB00IhmtXoYSDWJsaZjoz2UcP0r/
3nhnbtlB59NFHeeihhxKOqampoaioiN7e3nGvRyIRnE5n0lruoaEh9u3bh81m44knnsBgMCQcv2PHDr70pS
8RDAYxTVG6ZTKZpjw2U3w1y2n+8J9R9tMfYhj2oCm6mFiPpuKrWkbrQx+JZ7INr1rL8Kq18XOVgJ/lf/9/
MbgHJz67iW3+dL/p/
uu+rEEikUgkE5FO+LUgGsU40Ifi95HZcBn76eNoio6oxYreOxxb147UJwbzC2h734cJFqW3oEzRKazeWkpf
hwc1Os28UmJBe+9QKK02SSSShY+maVgyjCk74ABDg1d0L8ZG0Qd7hjn+YhM77qqNOecztUmvZ2D3XgZ274V
oBISCzu+j6rtfm/mcioLROf3a98VAfn4+
+fn5Scft2rULl8vF8ePH2bJlCwAvvPACqqqyY8fkQqMQi1DffffdmEwmnnzySczm5EJ3J0+eJCcnJ+1Odio
Mr1rHxb/
5OvazpzB3tqHp9AytXk+gvDLhearZQuMnP0flD76JpasDVdHFouJqFE1voOMdD+LZOHlXFIlEIpFc30gnfB
4RkQh5z/
+evAP70Y+osl4RDYot+gACxWW4tu3EV7kM37IVc7aLbrIY2HJbDcdfbJyRI24wplPlWCKRLHQ0LdYxoe3yQ
MrnKDox5f1F08A94KOv00NBWZrSvnV6lGCA6m9/BXN354xS0SGWmhw1X9/
tGVevXs2+fft4+OGH+f73v084HOaRRx7hgQceiCujd3R0sHfvXn7yk5+wfft2PB4Pd911Fz6fj5/97Gd4PJ
64gFp+fj46nY6nnnqKnp4edu7cidlsZv/+/Xz5y1/mM5/5zLV7szo9nhu24Llhy7ROCzvyqP/
c35Bx+QL2c6cQkTDBolIGt+5Ctc7P58c3FGSgawhV1bDlWMgpyJB6LRKJRLLAkU74fBGNUPNPX8bS1jxeDG
js30fS2czdHRjcbny1K+fcLEdhJjfdt5KDT18mGple+5WC8qVXKymRSCaiqRrhcBR3vy9lB9xg0lFS7aDlY
l/igQI6GwfT44RHIxhcLnIOvYy5q2PGDjjE7sfueWxVslB57LHHeOSRR9i7dy+KonD//
ffzrW99K348HA5z6dIlfD4fACdOnODw4cMA1NbWjpurqamJqqoqDAYD3/3ud/
nUpz6FpmnU1tbyjW98g4cffnj+3lg6EQLvyjV4V66Z18uGghHOHmqjr2O8SrzVZmT9rgqyZbmYRCKRLFikE
z5PlP783yc44FMhNA3Hay/Ss++tc76THgpG6G51T9sBB8jJv76jRBLJUifoD9N8oY/
2+gEi4endIzbcVEnAm0LJikasvnwWiGCQgud+h+PVF9H7vKPTzhhNURhesUYKagEOh4PHH398yuNVVVVoYw
TN9uzZM+73ydi3bx/
79u1Lm43XI9GIytHnGvC6J7Y49Q2FOPpcAzvursXukM9piUQiWYhIJ3we0Hnc5Bw5OK1zlEiEzMvn56yezO
P0U3+mm772mfdZnY2YkkQiWdj4vSEOP1tHKBCZdjsyBHgGfGRmJ1c/
FyJWGjNTlGCA6m99BUtH6zh165lEwUfFtLzVtbQ+9JEZ2ySRzDWdjU6GXRMd8FFUTePyyS623r5sHq2SSCQ
SSaoo19qA6wHHwQMIpr8otJ0/
PRfm4OwZ5vCzdRNS2KZDdp4Vo3TCJZJFi6ZpeD1BPE4foWBkwvEzB1tn5oADaDDkCpBXnJlUO0LToLQmZwY
XiVHwzJMTHPCZIgBVr6fl4U+iWmQEUbJwaatPUhaiwUDXMAFfLBvF6wnQ2eiks2kQfyoZKhKJRCKZU6QXNQ
9YW5tmdJ7twmlQVVDSt1eiqhqnX2tBnWaf36upXluQJoskEsl809k0SP3pbvzDVxbjOr1C5ao8qtcUEPCFG
ez1zuoa3S0uCiuyqL2hiAtHOyYdI0Ss3VleiX1G1xDhcGyTMw0O+ChKJEJm3UU8GzanbU6JJN2M/
e4mwtXnpbWulcGe8d/
ngjI7a3eUYzTLZaBEIpFcC2QkfB7QFGVG9YkGjwdzZ1tabenv8BD0T4x6TYcVm4rTp2QskUjmlYYzPZw52D
phER+NqDSe7eW1316is9GZlmtdPNZB2TIHKzYWx5s8CHGl4UNOQQZbbq9BmWF7MmN/
L7qAPy22jkUJBdM+p0SSTvQpdic5d6QD1yQban0dHg7vrycSjqbbNIlEIpGkgNwCnSN0Qx7MXR1oOh2+ymX
Yz7wxs3n86V1gup0+hGBmKaaA1W6keo2Mgkski5Ehl5/6090JxwR8YZrOJ1E0T5GgP4Kz10v12gJKlznobB
7EPxREZ9BRWJ5FVu4sU76nmSU0WvOdjGBB0YzMkUjmi5KqHBrP9yZUINQbFCKhyZ1sTQOfJ0jrpX5q1hXOk
ZUSiUQimQrphKcZvXuQ4if+i6xTx+Itx6ImMygKmqpOuy485MhLq32qqs3YAQeoWSMf1hLJYqWtLvX+3uli
tP7UaNZTtSo/
rXMH8woI2+wYhqbWt9AA1WAkWFBIKK+A7FPHpx4rBIGiUvzlVWm1U7I4UHw+Mi+fRwkFCRYW46+ovpK2scA
oX5FHy+V+ogm6FqTS9aStbkA64RKJRHINkE54GtG7XSz7xv/
D4HHHHXAAXTCANuJ+pxqJ0Ygp9IZz80BVsZ0/
Tc7rr2Ac6COakYlry05cW3agGU0p2xcKRuhudk3rPY3F7rBQMgsBJYlEcm1x9/vm/
ZrJhNlmhU7HwO47KPzdE4gpQoICUMIhDG4XIUceYZsd/ZBnwn1YEwJNUeh813sXrOMlmRtEJELR//
wCx8GXUCJXyrUCRSV0vPtP8NUsv4bWTY7ZamDr7TWceLGJ8NhotwA0qF6Tn1JGS8AXRlM1xAxLQiQSiUQyM
6QTnkYKf/frCQ74KKMLRG9VLdbm+qSOuAAitixEMEjVv36LzLoLaIqCUFU0Iciou0jBs0/
R+MifE85LLT287mQXwRn24xUiFtF69alLFFdlU748d1ZthSQSyfyj6Ga/
0B4tZylfkUvb5cSRdUUnyCu2zfqaiejbuw9rcwO2c6di9k0yRgCG4SGyzrwx6qNMIFBaTuc7/
he+6to5tFay4FBVKv7tn7GdOzVB4M/U00X1d75G0yc+uyA/
F9l5Gex+22q6Wlz0dw6hRlXsORbKanNR9CIlJ1xRxMz6+UkkEolkVkgnPE0oAT/
Zx1+f1AEfRRMCoUYJZ+VgdA8mndPY30vpL/6DjPqLAPG5RxcKBvcg1d/7By7/xd+CLvF/
ZTgUpbNxMOVU9KvrxjUNwsEo4WCUhrM9tFzsY+veZbOv6ZRIJPNGXrEdV9/
souF5JXaq1xSQlWthoHMIvzc05X2lek0BesMcRsIBdHpaPvAIua88T/
ETP084VFz1UxOCUHYOrR94hIBMQb8uybx4FvvZk5MeE5oGapTiXz1Ow2f+7/
waliJ6g47y2lzKa3MnHMvKsybMfhECCiuyEDLzQyKRJCHgC9N2uZ+ORifhYBSjWU9prYOK5Xmyy8IMkeroa
cLY3zcujW0yhKZh7uogas1ISS1daCrZxw9P2X5HqCqm/
j7sZ08lncvrCaTUlkxvUNhwUwXVawrIyJoi1V2DSETl+AuNUllVIllElNU6ZqxErugEd7x7PZv3VJNTkIGi
U9h6xzIsmSP3iTHq5wDly3NZtn6eak11OqIZmdMO6AlNwzToRD88NCdmSRY+joMH0BII/
AlNw9rWjLkjvZ1K5oOatcm/f1Wr06vTIJFIlh5Dg34O/u4Sjed7CfojqKpGwBem4XQPB5+
+hG9IdhSZCdIJTxOaPrVdIFWvx7VtV9LFokYsHT1Z6FpTFOwJhIZGSXWnWyiC4qocypbn4nUn+FJpseh61y
xqzCUSyfxishjYuLtq2iXPQkBuUSY6/
fhHhiXDyE1vWsnG3VUUV2aTX2qnfEUeN963gjXby+Y1wqYEgzNqBakpCllvHE27PZLFgamnK2EG2yjG/
t55sCa9FJTZWbW1BLhK5kDEnvUbbq7E7pDZbBKJZGpUVePES02Ew9FJa7lCgQgnDjShzUb1+TpF5g+kiWBB
EaEcB4ZB55QOtqYoeNZvon/PXRQ88z8ooVBCZ9xfXklm/
UVItEBQ1ZR62tqyzeiNuinblUDsIT1avznQlVpk6PIbnVgyjXNe9ymRSNJDfqmdG+9byYmXmib0Cp8KTYPK
KZTNFUVQWJ5FYXlWOs2cForPh4iEZ1baqqpz0mtcsjhQzZaUBFNVU+oiqAuJypX55JXYaa8bYLDPi1AEuYW
ZlNXmYrZKXReJRJKYvg4PAd/
UelKaBl53kMFeL47CzHHHAr4wHQ1Oht0BFJ0gv8ROQXnWjDPylhrSCU8XikL/
7fdQ8qvHJj2sAWgaA7vvAJ2O5o8+Ss23vgKaOmGcALrf9m5CufnJd+gVhVAKPW0VnULFilwaz069m69pULE
yttBOJXUdIBKOpaVn5VpQVQ2DSU9xZTZFVdno9XNcCyqRSGaE1WaaVilJzboCcosW3kabbshD0VP/
TfaxQyjR2PtJtQPFWEK5MiX3esW9aRuWtuaEWWdRiwXvspXzZ1SaybCZWLm5JP57KBihvd5JV9MgoWAES4a
RsuUOiqty0OlkgqREIrnCQPfQBJ2oqxEiFrwb64Q3X+zj0onOePRcCOhsHMRsNbDl9hoys8xzbPnCR95t08
jALbczcOMegHE1ZpqigBC0v+dPCZRXAuCrWU7dF76EZ9XaePsygEBRKS3v/
xj9t92NZ+0GIpm2hCmWQlVx7tydkn3L1hWSO0nEejRNbdWWErLzYqlp0/1yuAf8DA0GcHYPc+5wO68+dQmv
50qEPhSM4B8OpdS3VCKRzC3+4RDhYOpOeH/n0IL77uqGPSz7x/
9HztGDcQccmFL9fCoE4Nq4Ld3mSRYJgztuJmqxok1ROqEBfbftQzMsjajxsCvAq09dpO5kF8PuAKFABPeAj
3Ovt3P42TpCwcTaNhKJ5PpCSzEoNzYdvbNpkEvHO8c9jEcPB/1hjj7XELvXaBrWhsvkP/
sUBc88SeaFM4mzf5cYMhKeToSg813vxb1xC7mvvIC1tQlNp2No9QYGdt9OsKh03PBgYTEtH30U3fAQBtcgU
bOZcG7+Fa9Yp2do1Tqyjx1KeFmjs59QQXIBFkWnsHlPNZ1NTlov9TPsCiAUQV6JnapVeeQUXNnByinIwGoz
4htKLV31akL+MMdeaGD11lKazvfh6vPGbFAEJTU51KwrxJJhnNHcEolktkyvdsvj9NNePzBlSvq1oPB3T2A
cdE7REnJ6aIs01Vgye6IZmTR97FGq//
kf0PlizykB8Zagzl276bvzvmtrZJpQoyrHXmgY31d8DMOuAGcOtrLltpp5tkwikSxU7A4r7fXOhGM0jbi+h
KZp1J/uTjg2FIjgOn6JG1/+OZaujnjgUqgqIUcerQ99BH/
l0r8PSSc83QiBd+VavCvXTn44GCT7+CGyj72O3jtMyJHH4M5b8KzbCLqr0rdVlcy6CwkvpwlB7oE/
MLxq8utdjaIIypblUrZsYjuT8W9DsG5nBceeb0g5NX2cXRoEvGHeONA8bkWsqhodDU562tzsuHs5GTa5+JV
I5htLpgmDSTetaHjr5YXjhCsBPzlHDqYkqJUKUbMlLfNIFieB8iou/d+vkHP0EPbTx1GCAQJFpThv2o
O/atm1Ni9t9LS5CfqnjnRrWizrxesJkGGXqaISiQSKq7K5dKIzYTacwaSjoMwOxJTUk+nNZISGufHX/
4k5GgAY9yw3DA5Q/Z2v0fDoFwkWlUw1xZJAOuHziLG/l+rvfBXDoBMQCDRMPd3Yz59muGYFLR/
+36hjFoPG/
j4MblfCOYWmkXn54pzYm1OQwfa7ajn5SjMB79SiDEm5yofXNIiEopw91MqOu5bPzkiJRDJtFEVQsSKPhjM9
KZ/jGwqiadqC6Cls7O9FiSS/J43eeqYUyxQCf0U1keyctNkmWZyoFisDu/
cysHvvtTZlzujrSF7bCdDZ7GL5huRaMxKJZOmjN+hYv6uck6+0TKz3EjFvZsNNlSgjehKpbO5v6T6JKexHT
JKVJzQNJRKm4NmnaPuTD185oGmISCTWjWoBrEPSgawJny+iUaq//VUMrkEExD94YkSYLaOpjtL//
LdxpwgtxShPquNmQFaulY23VKV9Xk0DV5+PIZdUJZZIrgU1awvIKcxIebyiEwvCAQfQdKntHwsSp6YLTaP3
rjelxSaJZKGjqmpSBxyg8UwP7Q0Dc2+QRCJZFBRWZLPtjmXk5I9fM+QWZbL9rmXjOiSZUui6sL7vLEqCsji
hqmSdPIYSDGBw9lP8q8dY87mPse4zH2bNZz9GyS9/imERto28GhkJnweUgJ/
q73wVo2vqmgqhaWSdPEb3QD/h3DwAQrl5RC0WdP6pHVVNCPzlVek2eRxZuVbsDgseZ/
odZveAD1u2TAWVSOaLgC9MZ9MgAW+ILIeVzCwz7XUDSZVPr2ULsqsJFhYTybShH06tleJkaIC/
tIKhdRvTZpdEspDJzDLTI9wpSUKce70ds1W2H5VIJDEchZlsv7OWgC9MKBjBZNZjskx0uDOzzAl9BkWNYok
mb60s1CjW+ktU/
PQHKMFgPGVdFwriOHiA7KOHaPr4n+OvrJ7dG7uGyEj4XKNpVP7wO1jaWpKPFQL7uZNXTtUbcN64B01M/
d8kNI2BW+9Ig6GJKarKnpN5xcw6+0okkmmiaRp1p7o48MR56k520VY3QPOFPtouDyTtF6xpUFabixpdIKql
ikLf7fumKS83HgFYOtvReYfTZZVEMi9EoypdzYPUn+6m6XzvuE4kiSirdaSuySig8Vzq5SoSieT6wGw1YM+
xTOqAj7Jyc8mUaWiaohBWkkfLNaD0v36CEghO0H8RqooSClL5w29BdPF2dJCR8Dkmo/5iUnG1OEKgBMc/
THvvfjMZl85j6Wgbl54++hx1bd6Be47b63Q2DdI4jdrR6ZBTkHo6rEQimTlN53ppPDt5+pZ/
jObDuJrRkfovRSc4+lwDAPlldqpXF8zLd9fU3Unm5QugRvGXV+GrWR6vBeu/
7W5yX3ke42Bi1dZECE3FMOgkmpGZfLBEsgDobBrkwtF2ImE19l0FLr/
RRX6ZnfW7KjAYdVOea7YaWbm5mEsnupJfSIPBHi+hYASjSS4VJZLrgVAwQkeDk+4WF5GwSobdRPnyXPJKbN
MqR3MUZrL51mrOvt5GKBCJ36vQwFFsw7VtF3lHX51SXFVTFPxlFVhbm6e8htA0DB439jMn8WzcOr03ukCQd
9Y5JvvooXirk2QIVSVYMF4MRdXrafuTD+N49SVyjr6K3ucDIJyTS/
+eu2IiMsrcJTQ0nuuh7uTUrQYSkUgARgjILbZhleroEsmcEwlHE7YMGUt2fgahQGxnOeAPEw2rqNErX+T+D
g997R7W31hBSfXcCJrpPW7KfvoDbJcvxPs3C00jUFhM23s/RKC8EhSFus99idV/
8UmEGp1xTo1qlirQksVBT6uLMwdb47+Pfb72dXg4/mIj2++sRVGm/
jZUrS7AYNBx9nB7SteMhlWQj2mJZMnjHvBx7IVGImNaGPqGg/R1eMgvtbPxlivia6mQX2rn1revob/
Dw5A7gE4Xa4mcmWXG2ZtJ7huvQziMuMpRGP0tmF+Epb0NoU4t9KYpOjIaLkknXDI5eo87JQdcA6KZNjzrbg
BAN+Sh6Kn/JuuNo+hCsei4t7qW7u03MrxyHeEcR9qdbzWq0tPmprfNTSSiYjLr6WgcnPF8a3aUc/
5wG3CVMy7AnGFk3c7yWVoskUhSobvFlZIgE4Cr38e2vTU0nuvFNzQxzXV0nrOHWskpyMCSYUyjpaD4fdR88
8sYnTFhqLEPaFNvDzXf+nsaHv1LgkWlqBYL9X/+/
7Hsm3+HEojVn42Kt479ORkagkBxCaHchdF2TSJJhKZpXDzRmWAAuPt99HV4kuo3FFZlp+yEG81ymSiRLHXC
oWjMAQ9f5fCOPH77OjxceqOL1VtLpzWvoggKyrMouOqeFCoopOmjj1L5r99C7/OiKkrsWa2qqEYTbe/
7EBmNdWgisbiqdrVa+yJD3l3nmIg9K+VIeMe73geKjtznf0/
Rb3+FctU51uYGMprq6XzbAwzcdlda7fR6Ahx7vpGAbxatyEYRMcXEsmUO7DkWmi/
00tPqRlU1TGY95SvyqFiRi0GmuEkk88JAd+p1z5qqcWR/Q/JxQHu9k+U3pLeVkeO1lzAO9E/
YHYdY+rgSCVPw9G9o+9OPAxAsKePiX32NnCOvkX3sEDqvl1BuPkNrN1D05C9BVSefC42+u968ZFqdSJY2rj
5v8lahAtrrB5I64Z6B1ERWdXoFnV5KB0kkS53ORue4CPhktNcNULuhKGHJy3Tw1Szn4l//
A1knj5JRfwmhafgqa3Bt3YlqtiCiUfKjiW1SolH8VTVpsedaIL2gOca1bReOw68mHKMBrQ99FM+GzRT/
6nHyXnl+0o2d0YVkyW9+zvDKNQRLytJiYyQc5ehzDQQD6RE3EEDtSI9Ru8PChpsq0W7U0DQSpslJJJK5YU4
E1TRw9qRf1Cz3tZcSNjIWqkrW6Tfo9A7Ha7lVi5WBW+9k4NY7x40NFpVQ+cPvQCQc6zFKrNYMVaX7ze/
AvXl72u2XSOaClDbItdTGaSmmxUgHXCJZemiaRiQURSgCvSHmUPe2u5Oep6oaA91DFFVkp88WoxHX9ptwbb
8p/pqIRHC8+iK5Y3yhyTwHTQiiFivuRZqKDtIJn3O8tasYXr6KjPrLU/
b9Hty6i2hmJhkXz5H3yvNAkvQLRSH3tRfpfOd702JjZ9MgQX96HHCDUceGmyrIzhsv2iSEkAEnieQaYXNY6
G33zMHM6c8DM7gGk9Z3C01F73YlFVQbXrUuFiU//
Cq2C2cR0Qj+imoGbtpDqCC9EXyJZC5JNXMsFRE1W7YloWYLACKmDyGRSJYGalSl5VI/
rZf645t19hwLlavzCSeJgsfniMxthxQRCVP5L/
8UE2Tlii90dWmZpihoikLr+z+Gpk+utL5QkU74XCMELR/8BOX/8S/
Yz5+OfXCEQIykWAjAcewQjmOHUBUlYQ1jfEpVJaPhctpM7Gqeed03QPmK3HiE2+P0c/
KVFoSAvGIbFSvzpQK6RHKNKa7MoeF0+jsc5BSkX1U8ajaj93mTj7NaU5sv00b/
3nvo33vPbE2TSK4ZjsJMDCYd4WDixXIqYolGs57Cimx6WhNoRWhQsSJvBpZKJJKFRjSqcvyFRgZ7xz9bPYN
+zhxsxWpPTdslI2tuhUwLnnmSzLqLE/ygcQ44Avf6TfTd9WYCZRVzas9cI3ON5gHVbKHlw3/G5c/
9DX133Itn7Q2xOsSrQsOKqqas8KulMayc7KE+JQIKK7JYvbWUcDBKy8V+Bvu8RCMqkXBM5O3I/nqaL/
SlzVaJRJIakUiUnjY3HQ1OAr4Q+WX2tF+jqDI77XO6tu6MpYxPgSYEvsoaItmOtF9bIlmoKIqgdv3U2RtCg
CXTmPJ3ctWWEkwWw5QZahUrcnEUyg10iWQp0Hi2d4IDPhafJ5R0jswsM3aHJZ1mjUOEw+S+
+sKkGi6jaIqCe+MW2v7044veAQcZCZ9XgiVl9BSXsuJv/
wIg4QctEZoQeJevTptdVpsJ71Bw2pmltmwza3eU03qpn86mkWj6mDlG396lE53YHRYchbIXr0Qy12iaRuPZ
XprO9xIdkzpmsujJyDLhdU9UPJ8p1sz0KqMDDNx6J45Dr4A2eesSoWn03v3mtF9XIlnolK/
IJRwaaTc44jwLYs9aq93ElttqUq7jNlkM7Ny3nPrTPXQ2OeNtCC2ZRqrXFFBW65hWX2CJRLIwUaMqbZf7Ew
8SYDLrJy9NFbGS0jU7yub0nmDuakfnTywaKVSVzPpLc2bDfCOd8HnG2liHqW/
maaGjS9KBm29Lj0FAWa2Dvo7U60Uzs82UL8+ltMaBohMpRbobz/VIJ1wimQcuHuug9fLAhNeD/
kjsAZumlh72HEtc1CWdhPIKaPrIp6j612/F2o6NFq+OZA+1v/
O9DK29Ie3XlUgWOkIIlq0vpHRZDh0Ng3g9AXR6hYLyLPKKbdNeIJssBtbuKGPl5mIC3jCKTmDJNErnWyJZQ
viGQ8lrvrVYm7LaG4poPt83rlWZPcfC6m2lE7Se0k4KXaSmNW4RMKdOuNPp5BOf+ARPPfUUiqJw//
33881vfpPMzKmdsT179nDgwIFxr334wx/m+9///lyaOm+YerpmPUfHu/
8kraJC+SV2HIWZKSsdb7yligy7CQCvJ5iSGutA1zBDg35sOXOXyiKRXO8MuwOTOuDjSJOWWuXqueuv7atdy
cW//jrZx14n88IZjAN96H1eNCHIPnYIzWDAvWnbohZkkUhmitlqZNn6wrTNpzfoyMxO/
4aaRCJZXCxbV0jV6nxcvV4iERWrzYgte37W7cGiElS9ASUytU+hKQq+RdyS7GrmtCb8wQcf5Ny5c+zfv5/
f/va3vPzyy3zoQx9Ket7DDz9MV1dX/M9Xv/rVuTRzXtGMM0/
f1IDmD36CwV2702cQIBTBpj1VmDNSW9D2d16Jmqfa6gTg8P56zr7eSvPFPkLB9KixSySSK7TXD6SlC4HOIM
gtGtksHTvfyN8rVuZRXJU9+wslQDVbGF6xBmtbM+auDvRuF0bXIBmNdZT/7IfU/
OPfovOmv0WaRCKRSCRLBWumMWlvbzGmG4JOp5BbbKOwPGveHHCIPfMHd9yUUBNGqCoDu+
+YN5vmmjlzwi9cuMAzzzzDD3/4Q3bs2MHNN9/Mt7/9bX7+85/
T2dmZ8Fyr1UpRUVH8j92efkGha8XQyrUJP2CJEED5z/+dgt//
JpammUb0eh12RwpqwyLWK3CU4cHU7YiGVToaB7l0vJOXfn2etvokETuJRDItfMOhxG2HUuTmN61iy+01bLq
1CkdhJopOoOgEjsJMNt1axaotJXOfshqNUvX9b6Af8iC4shcwWidu6Wyn7Kf/
Orc2SCQSiUSyiFF0ChUrE3c60DSoXDl32W2p0v2m+wnmF6KJ8X7S6LKm/5bbGV61bv4NmyPmzAk/
dOgQ2dnZbN16pYn6HXfcgaIoHD58OOG5jz32GHl5eaxbt44vfOEL+Hy+KccGg0E8Hs+4PwuZqM2Oc8fNU6q
bT7Z+HvuafniIgmefYtk//
i2KzwvRCPbTJ8h77mlyX34Ow0AS8YUE2LLNyfujabGacICOBienXmud3kVG3oymapw/
3E53q2vadkokksnR65W0RMINRj1CCArKsti2dxl3PrCBOx/YwLa9yygoy5qXmlH7uVOYBvoQU9R/
CVXFfuEMpq6OObdFIpFIJJLFSvXagoTtgitW5pFfaptHiyZHtWbQ8Gf/h/7b7iJqvhKFDxYU0f7AQ3Td/
+CEzlKLmTmrCe/u7qagoGD8xfR6HA4H3d3dU573nve8h8rKSkpKSjh9+jSf+9znuHTpEr/+9a8nHf93f/
d3/PVf/3VabZ9ruv7oPRidA9gunUNTFISqxh1tTacDVR2nCjyhX56mYerpouLH/4ylqx398FAsuq5pFP/
qcdwbt9Lxx+9HNU8vjaSs1kHDmcSicWargbxiG+FQlPNH2qc1/2TUneqmsHx+FvUSyVKnsDyLrmbXrOYwWf
QpKyynhWiUrFPHcLz6IqaeLlSjCc+mbRgG+uP3x6nQgLKf/ZCGz/
zfJfVglkgkEokkXeh0Cltvr6H1cj8tl/oJeGN113aHharV+RRVZi+YdbhqtdL91nfRc9/
b0bsG0fR6Ilk5S/IZP20n/POf/
zxf+cpXEo65cOHCjA0aWzO+fv16iouL2bt3Lw0NDSxbtmzC+C984Qt8+tOfjv/
u8XgoLy+f8fXnA81opPkjn8J27hSO117C1NdD1GLBvXkHgztuRoRD1P7Dl9B73FMGpoWmkVl35d957EI169
Rx9B4PTY/
8OehSF1sxW42s3FzCpROTlAuMtChYt6scIQSdTYPj0tJnis8TZGgwMKe9ByWS64X8sizMVkNKYolTEQnPn/
KoCIep/
ME3sV0+jybEyObjEHkvPksqefUCsLa3kPXGUdybt8+5vRKJRCKRLEYUnULV6gIqV+UTCasIwZx0OEkXmt5A
OK8g+cBFzLSd8EcffZSHHnoo4ZiamhqKioro7e0d93okEsHpdFJUlLqy944dOwCor6+f1Ak3mUyYTKaU51s
wKApD6zcxtH7ThEPGvh4MHnfSKRI66I2XsZ87hWfD5mmZVbU6H6NZT8PpbnzDofjr2XlWVm4qiQs3DLsC8c
5Bs0WKtEkk6UFRBKu3lfLGgeYZzzEdscXZUvQ//xXfTByX/
TMmOygZGpD78nPSCZdIJBKJJAlCiKRCbZL5YdpOeH5+Pvn5yYv3d+3ahcvl4vjx42zZsgWAF154AVVV4451
Kpw8eRKA4uLi6Zq6aMk58hoaycuzE6EJhZxDB6bthAOUVOdQXJXNkCtAJBTFbDVgtY3f6FB06UsLMVtkmyG
JJF3EVc1nSIbdnCZLEqP4fDgOvTzO+R5Lqu3MBWBpbUqnaRKJRCKRSCRzypwV/q1evZp9+/
bx8MMPc+TIEV577TUeeeQRHnjgAUpKSgDo6Ohg1apVHDlyBICGhga+9KUvcfz4cZqbm3nyySd53/
vex+7du9mwYcNcmbrg0LsGZz2H0FSMvYnruxOeLwT2HAuOwswJDjhAfoktLVFwW445LvQmkUhmT9A/
u8ySyiQqqukio+ESSiRNWTBiHmvYJRKJRCKRSGbJnK5cHnvsMVatWsXevXu59957ufnmm/
nBD34QPx4Oh7l06VJc/dxoNPLcc89x1113sWrVKh599FHuv/9+nnrqqbk0c8ERzciEGbYxG0UDTP29FP/
qcYhG02PYGHKLbWTYTQl1EjLsRqw2Y8IxKzZePxkOEsl8EI3OvKbbUZRJcXVOGq2ZGpGCA55Kvo0mBN7lK2
dvkEQikUgkEsk8MWfq6AAOh4PHH398yuNVVVXj6g/Ly8s5cODAXJq0KHBt2UH+i8/
Oao7RxWvuy88h1Cid73zv7A0bO78QbN5TzZHnGghOIgJlzTSydW8tQsCJA014Bib2Ey9f7iC3+Nq3RJBIlh
I63fQ38HR6hfLludTeUISizI8CabC4NOmYVMpyhKbRf+udabFJIpFIJBKJZD6QOXwLkEB5FZ7V6yc0q58JA
nC8+iKGgb7ZG3YVVpuJm+5bycrNJWRmmzGa9dhyLKzeWsque1dgthpQFEF0CrXltjonF451oKpqWpTWJZLr
Hb83xJH99SmNXbaugK17a9h2xzL23L+GlZtLZuTATxe9exDbmTcw9vXgraiOtVecglS2AwJFJQyvXp8+AyX
jcDqdPPjgg9jtdrKzs/nABz7A8PBwwnP27NmDEGLcn4985CPjxrS2tnLfffdhtVopKCjgz//
8z4mkqzxBkhZCwQjdLS46Gp14nL5rbY5EIpEsKeY0Ei6ZOW0PfYSKf/
tnbBfPxXuAA1OKGCVEUcg5eojefW9Js5VgMOqoWp1P1erJxfoun+zGOxSc8vy2ywO01Q2ABpYMI46iTEKBC
P7hEHqjQlFlDqU1OQu6jYJEslA4e6g15ZrwSEQlt2j+MlH0HjfF//0zsk6fiN/HNKGgjXjaM42/u2/
Ymh4DJZPy4IMP0tXVxf79+wmHw7z//e/nQx/6UMIsN4CHH36Yv/mbv4n/
brVa43+PRqPcd999FBUVcfDgQbq6unjf+96HwWDgy1/+8py9F0lqRCMqF4930NEwOC5b0ZZjZu2OcrJyrQn
OlkgkEkkqSCd8gaKaLTR/5NNYWhrJPv46+uEhIpl2so4dQh/
wj+sLnhyB3j17sbfpEglH6Wx0Jpc4Hjnu94boaHCOO+Tq89F4todte5dJATeJZAyaptHfNcRgrxdN1VB0Am
ePN+XzOxqcrNhUMi/p5zrvMDX/
9LcYB53jW5FpKiDQFB2o0Rk54i7ZmmzOuHDhAs888wxHjx5l69bYZse3v/1t7r33Xr7+9a/
HRVYnw2q1TtmO9A9/+APnz5/nueeeo7CwkI0bN/KlL32Jz33uc/zVX/
0VRqNxTt6PJDmqqnHiQBPO7onZDkOuAEf217PjrlrsDumISyQSyWyQTvhCRgj8VcvwV13pj+7ctZua734N3
fBQbAip1E1qRDPnv/
Z62B1IS5p5KBjh6PMN7H7ranT68amrrn4fLRf76OvwoKoamVkmKlbkUVLjmLfaVolkvuludXHucBuR0MxF2
CJhlUgoitE894+B/Oeejjngk2weCk0DbfoOuAaE7VmECqW441xx6NAhsrOz4w44wB133IGiKBw+fJi3v/
3tU5772GOP8bOf/YyioiLe/OY388UvfjEeDT906BDr16+nsLAwPv7uu+/mox/
9KOfOnWPTpk2TzhkMBgkGr2RWeTye2b5FyVX0trkndcAB0GJO+qUTXWy7Y9nkYyQSiWQGGHu7yXrjKDq/
j7AjF9eWnTGh6iWMdMIXGcGSMi79n78j5+hrZJ04gn7Yg7E/
cb23UFVcW1LvzZ4uRCJZ9OmgQSgQq00rXeaIv9xeP8C5w+0IEc/WZ2gwwLnD7XQ1u9h8W/
W81LhKJPPFsDvA2UOtuCcROpwJim4eNqqiURyHDiTM3pmJFQLovfftJGy/
IJkV3d3dFBQUjHtNr9fjcDjo7u6e8rz3vOc9VFZWUlJSwunTp/nc5z7HpUuX+PWvfx2fd6wDDsR/
TzTv3/3d3/HXf/3XM307khRoq+tPPEADZ88wvqHgpO1LJRKJZDqIYJCyx39E9sljaIqCJgRCVSn6zX/Ru+
+t9N1535J9zksnfBGiWq04d+5GNZqwtLWQobuIqadr0oWsJgTuG7YQLLqiRGxtqsfxyvNkNNaDgOEVaxi4Z
S+Bsoq02pmZbUZvUIhMIcw2XXrarjjhQ4N+zh1uB5i0X7mzZ5j6U92s3Dx1uqREspgYdgd4/
dm6KYUOp4UAR2HmvGgt6L3D6Pzp2TSA2D1NaBoDu3YzuPOWtM17PfH5z3+er3zlKwnHXLhwYcbzf+hDH4r/
ff369RQXF7N3714aGhpYtmzmEdQvfOELfPrTn47/7vF4KC8vn/
F8kol4PaGUxvmGQ9IJl0gks0PTRvSvzgKxoOGoLyOiUYp+92s0vZ7+2/ddOxvnEOmEL0JsZ96g/Kf/
ihIMxGopNS3+odWEEg8rCVXFs2Ez7Q9+EMNAH/
Zzp7GdeQPb5fPxhSxAzpHXyHn9Fbruf5CB3XvTZqdOp1C+Io+mc71pmW+sM996eWBcBHwy2uoGWLahEL1ei
rpJFj9nX29LjwMOoEH1moLk42aBCIfJOnEYx8GXUjVpyoi4BiAEmt6Ar7Kagd134Nmwecnujs81jz76KA89
9FDCMTU1NRQVFdHbO/
7+HYlEcDqdU9Z7T8aOHbFMrPr6epYtW0ZRURFHjhwZN6anpwcg4bwmkwmTSTp+c4neoBBMYc9Mr5dZZhKJZ
HZYG+uwXziTcEzB7/+HgZtuQ1uC937phC8yrA2XqfzRd0GL7RYJNRo/
pgmBptPhWXcDYUcerq27COXmUf6zf8V+6jhwZZE7ThxpJE205FePESguwbt8ddrsrV1fiHvAN3WNWYoIAZl
ZV4TZ+js9CR1wiCm8Djn95BQs7ZoSydKn5VIf7v70tQhatbWEvOK504nQe
Yep/
u7XsHS0oY04ygmdbEVB1elRopEp09YHt+6i6x0Popotc2P0dUR+fj75+ZN3tBjLrl27cLlcHD9+nC1btgDw
wgsvoKpq3LFOhZMnTwJQXFwcn/dv//Zv6e3tjae779+/
H7vdzpo1a6b5biTppKgym4azPQkFVY1mPXapkC6RSGZJztGDaIqSsFxNFwpiP/
MG7q0759Gy+UE64YuMwqefACZfzApNg2iUUH4hPW+6H6IRar7191hbmlOqudQUhbwXnk2rE67oFLbcVkNHg
5PWS/0MuwMzmkfToKzWMeb31ATfpiUiL5EsQIYG/
Vw81pnWOa2Zc7ujXP6TH2Du6gCubPglvAepKv177ySj4TKZjXXx9b8Y8zPn2OtYOlpp/
N9fkI74PLF69Wr27dvHww8/zPe//33C4TCPPPIIDzzwQFwZvaOjg7179/KTn/
yE7du309DQwOOPP869995Lbm4up0+f5lOf+hS7d+9mw4YNANx1112sWbOG9773vXz1q1+lu7ubv/
zLv+TjH//
4kot067zD5Bx+layTx1ACfoIFRThv2sPwyrWgxKLJpq4Oso8exOBxE7HZcW3ZmfbysFQprsqm8Vxvwmdszd
oCKXwqkUhmjd7jTrpQ14TA4HHNj0HzjHTCFxF6t4vM+ksJxwhNJffl5wkWFkMkQkZzY8rzC1XFduFM7Auhp
C/VTFEE5ctzKat18MbLzfS1T1/RtrgqG00DrzuAOdNIVl4Gfe3upNFwkbQ/
mkRy7Qn4QoSDUUxWA0bT+Ntyy6UkQknTRUDr5X7yS+3pnTYUxHbuNJb21nh9VyqMppoX7v8d4ZEuDpNvMqq
YuzopeOZJut/27rTYLEnOY489xiOPPMLevXtRFIX777+fb33rW/Hj4XCYS5cu4fPFMjWMRiPPPfcc//RP/
4TX66W8vJz777+fv/zLv4yfo9Pp+O1vf8tHP/pRdu3aRUZGBn/yJ38yrq/
4UsDc1kL1P38dnd8XLxsz9fWQdeYNPOs20vbeD1Hyy5+Sc+wQ2phnbv4Lz+DesJm29z6MZpy/
TQmvJ8jR5xrQEnQ1qVyVR8XKvHmzSSKRLF0imbaYv5FIuFXTiNjSu15ZKEgnfBGhH2lLlgwlGKDsZz+M1VA
yPeVhoWkIVR23IEgXfR2eGTngRrOermYXXc2u+GsZdmNSBxzgwvFObrx3RfqU2iWSNNLX4aHhTA/
ugSup5gVldmo3FGHLiUV7e9vc6b2oxrjrzX4+jdwD+yl8+jfogoGUtr3GRrrFyBwQu8clumcJTcVx8AA99/
0RmsEwW8slKeBwOHj88cenPF5VVTUualpeXs6BAweSzltZWcnTTz+dFhsXIorfN+KA+yct/7KdO8Wyb/w/
TL1d414fxX7mDcp/9kNa//
Tj82Kvqmocf7GRUCAy5ZjsfCurtpROeVwikUimg2vbLhyHX004RjUY8KyfvG3lYkcqaywiUt0JGl3YijGCb
amgASFHHpp+bvZmWi8PzOi8yRYFqSq4DrsCaa2llUjSRUeDkxMvNU1wiHvbPRx8+jKvP1tHf9cQajT92Rwi
jamkeS88Q8kTP0cXjJWapDrzpNHuFM7XBQMYB9Ij9iiRzBU5Rw+h83kR2uQRHqFpmHo6xznoVx/
POnUc00hZx1zT1+HBPxxKuLnt6vPh9cyspEwikUiuxlu7iuHalQkDf3133LdkS9CkE76IiNizGFq5dk6i1A
AIwcAtt8/N3IAnndG3aZDWqJ9EkgaC/
jDnDrclHOPu93H8hUZ0htS+70IRVKzIRadP7MYKAflpEmXTeYcp/
O2vp33ebLcANEV2PJAsbOynjycdk+x7oCkK2cdeT49BSehrdydvNiBizrpEIlk4aJqGx+mjv2uIYdci2yQT
gpYPfoLhFTFBTk1RUBUdmoj1C+
+94156737zNTZy7pDp6IuMnnvfRuY3L45rMZYONKHgL6tg4Obb0jbn1USjqaukma0GAr5wei4sU9ElC4yOB
mdK5RQweSbI1eSX2ti8pwYAvVFH49mpI8WaRtpqOrNOHB7XoWGu0YCIPZtQ3ty2V5NIZosSDM5+swmB3pta
GdpsiUa15KUkGrReGkBRFEpqctAb5GaYRHIt6WoepO5UN/
7hK9mhthwzKzbFOqBEIypDg35UVSMz2zxBc2YhoFqsNH/005jbWsh64wg6v4+wI4/
BbTcSyc651ubNKQvvf0OSEH/VMpo//L8p/8kP0HuHY+1/
kqSdJ6sLVw0GBnfcTPdb3jlnIjCqqqWcVrvl9mo6GwfH1YDPhtxC2aJMsrDwOFNoxDuKiPXkjUzRI9xo1rN
6W1n892XrCvE4/
fR3jl+8j9wqWLO9DLsjPe2FzO2taZlnOvTvuTOtwpESyVwQKC7F0t6SsPVOMgQa4az5WYSObQGaCL83xIVj
HdSf6Wbr7TUgBF1Ng4SCEUwWAyXVOSnPJZFIZk7rpX4uHJtYrjI0GOD4C40UlGfh7B6Krx2EEBRVZrFycwk
myzxoqmgaIhxC0+lBl3zDLlBeSaC8cu7tWkBIJ3wRMrxqHRf/
5hvYT58g9+XnsDY1kLCp5wiaUEBTYeTn4PabcG3dhb+iCtUytz0/1WksRGzZFoTimvU1hYDs/
Awys+WCQLKwmFZNtgaRsEr5ilza6gYmfNUVReD1BLFkGGO/6xQ23VpNV/
NgrC2gK4BQBPmldipX5ZGdl5G292Hqn1ltdsKe4SNZPmN7h46+5r5hC/
177pqZsRLJPOK88daEgkNXt+GbFFVlcNuuKSbQyKi/iHWkA4q3diW+qmUzzvwqXZZD/
enulMeHQ1Fef7YutqQYc8mmc72UVOewdkcZik5ulkkkc0EwEObi8cR6EVeLumqaRneLi8E+Lzv3LcdknhtH
XAn4yTuwH8crL2IYcqMJwdCaDfTtvQffshVzcs3FinTCFymaXo9783b8peWs/PL/
SThWAF1v+iMsXZ2IcIhgYTHOXbsJ5+bPj7GATqdgsugJ+hOn1uqNOgwmPblFNjobB1OefzTKd+UFMFkNbLj
pSq9VTdNwdg8z0D2EpoHdYaGwPEsuFCTzRjgYwe8NkZk1/YwTa6Zx0r22gC/
M8RcaWbuzjLJluUDMMS+tcVBa45ityQmJWqzTTrnVxvy8+lxNKKgmIx3v+F9knzhC5uULCFWNlcrsvgPXlh
0yCi5ZFPgra3Du3E3O6y9P8jkXaIqC+4YtZJ84Mul3SAOcN+0hPEnphbm9lYp//
x6mvp64RoxQVfwl5bQ+9BH0Pi+2sydRQrHnvWvLjqQb7WarkRUbi7l8siu1N6hdeeZeXVrT2TSIohOs3VGe
2lwSiWRadDYMplzSNhZNg6AvTP2pHtbuKEt+wjTReYep+ebfYertjpfMCk3DduEMtnOn6HjgIQZ37U77dRc
r0glf5IQKi3HfsBX76eOT1ohrQmF45Rr673zTNbDuCkIIKlbkUXcqwU67gPLaXBRFUFSRxaUT+pTqYc1WA3
klNrqaXUQjKiaLnrLluVSsyIvXv3g9AU4caMbnCcZ37TUNDCYdG26qJC9NQlUSyWT4vSHqTnbR3eIe184pV
aw2I5dOJF4cnzvcTnFlDjp9+p1UU3cnuS8/j/3MCUQ4TKCkDOfNtxPOdiQtdxkb8dNEzLb+W+8g5/
Cr6P0+VEUXU0VXo0Tsdpof/iSB8irc225M+/uQSOYNIeh49/sIOXLJf/
EZdP4rJSj+skq63vZu8p+LtWgb+x2Kb1LpdOS8/gpZJ4/j2rKdgd13EMovxNjXQ823/
x4lGKsBHZvubu5qZ8XffzHeZlQTAhGNUvybn9N5/4NJF7/
VawswmHXUn+4hOEtNlvZ6JzXrCuMZOhKJJH0MuwMjD9Xpn6tp0NnkZOXm4rTrOhT/6jFMfT0T/
BGhqmhA6X/9B95lKwkVFKb1uosV6YQvAdoe/
AAVoSD2C2diu+KqCiOpnN5ly2l9/0evtYkAVKzKo7vVxZArMOHGIQRYbCaq18Z2/
WMptVUcfrY+6bwBX5jaDUWs3VGOpmkIIfB7QwwN+tHpFUwWA0f2NxAOxhz6sfeGcDDKiReb2H5XLdl5c5uS
L7k+8Q+HeP3ZOsLByIx2riG20eQbStKWT4OGsz2s2Fg8s4tMgf3kMSr+4/vAlQV/
RmMdmQ2X8VZUJ42Ej64TokYjA7feifOm2wjnOOh50/1knTyKtaURTQi8tavwrNuYUu2YRLIoUBT67n4z/
bfvI6PhEkowSCivgEBpOXkvPovt4tkJ35/
R30U0JnioeIfIffVFHIdepvnDf0b2kYMoodCkrc+EpsU3+YSqXpk7HKbs5/+OajLj3rw9oclly3IprXbQeK
53WunpE42B7hYX1WukiKJEkm4UnZipDw6AGtXwD4ew5Uyz9ZemofN50YSIZdeMqUXRe9xkv3F0Sh2M2Ea8I
Pe1F+l6+wMztHxpIZ3wJYBmMtHy4T/
D2lhHztGD6D1uIpk2XNtuxFu7csGog+v1OrbdUculE510Ng2iqSOLBQFFVTms2lKCwXhlAT6dm8OoKIzXE+
Ti8Q4GuobjxxSdSCgKp6FRf3pEZEYiSTPnj7bPygEHCKaQEQIw0DUEaXTCjb09VPzHv8DYBT3Ed7mtrU1JI
+GMHNeFQgyvXEM4J5YirxkMuLbdiEtGvCVLHM1gYHjVuisvqCq5B/ZPzOOeAqGqoGlU/uCbiGg0odjbZN/
F0cV60VP/jXvj1qQlHaMaErNxwgWx57JEIkk/
+aV22uuds5pjWqWY0Si5r71I7kv7MQ30ARAoKGJgz104d+0GRcHS0phUiFKoKhmXz8/
G7CWFdMKXCkLgW7ZiwYseGIw61u0sZ+WmYjxOPxpgz7FgNE/
8KAa8qafDOXtiTvfhZ+sntEJLqsquxZyXYCA8Z0IVkusTvzc0QaV8uggBSoobaelrWhgj99UXiDVKmpzp7M
RrikLmhbN4l69Oj3ESySJFP+TBODi9BbTQtFgEfIbXFIDR2Y+1pRFfdW3S8XaHBVuOmaHBmfUd1jTmR4FZI
rkOyS+xY8k0EvCGZrTBb84wYLWlWCoSjVL5o+9gO3dq3Mum3m5KfvETMuov0vbeD6XeNjndC5VFjFS4kVwT
DCY9ucU28optkzrgMD1F9f7OIc4faY854DP8grde7J9Rva5EMhVDg9NoRTYJQkBRZTY5KbbZcxSkT/
kcwHbuZPKd7RTn0oRAic5fT3GJZMEyi+y02T6h9EOelMeu3lo2vU4OYxACiiuzZ3SuRCJJjFAEW26rmXL9n
IzqNQWIFO9Dua+8gO3cqZh2y1gbRv5knThCzuFX8VVUx9omJ0BTFHy1CztYOJ/
ISPj1iqpiO3+azEvnEdEo/vJKXJt3oJnmpk/4TLBkGieqnk9BOBjFPeCb1fUaz/
USjWqs2lIyq3kkklFmuoAdS9WaAqyZRlov9ScdW7MuvWInIpK+dFIlGsVfKtWSJZJIpo1QTi6GwYFpRbYFE
M7IRO/3zbj/eMRmT3lsTkEG2/
bWcO5IO153MP66ogisNiPDY167mqo1BVNGwoddAVov9+PsHUYAOYWZVKzIk/
3FJZJpkGE3cdObVtHR6KSz0UkoEMFsNVJW60BVNS4c7Ri3hh79e1mtg/LlualdRNPIO7A/
8RghyD3wHIO7duNZvwn72ak374WqMnDTbdN4l0sb6YRfh5i6O6j8wTcxDfSjKTo0wPFalOIn/
pP2Bz+I54Yt19pEIFZDnl9qp7c9+c69wZQeMaeWi30UVWSRnZ/
eiKLk+iQ7LyOpJsFUKIrghlsqsY9oI6zaUsLF451Tjl+5uSTeDSBd+MurMHjcCRf8qdSEa4BqtuDeuC2d5k
kkixNFoX/PnRQ/
8fNpnaYJhaE168k5fnjyFn+TvDb2WNiRh69yetonOQWZ3HTfStwDPryeIDq9Qm6RDZ1e4eLxDtouDwCxDig
xYdSYA778hqJJ52u51MfFY53jnAOvJ0jb5QFWby2lYmXetOyTSK5nDEYdVavyqVo1seVwdn4GbZf76escQl
M1snKtVKzIJbfYlnIUXOcdwuhMHAAQmoalqx0RDtP5zvdiaW/
F4HKOWzdoQkFoKp1ve4Bgcen03uQSRjrhSxi920Xm5fOISIRAcSn+yhr0Qx5qvvUVdP5Y1Fio0fhDWwkGqf
jxd+m9601YOlrRDw0RcuQyuOPmmKjMNejPu2Z7GX0d55NGw/
NL7bOuvYXYTmFr3YB0wiUpo0ZVOhoHab3cj9cTRFEEBeVZVK3Kw+6wUrbMQWvdQMp5pI7CDHKL7ZQtc4xLN
atclY/JauDisQ6C/isRaqNFz6rNJRRX5aT7reG8+Tayzrwx5fHRRb+3unacKIu4agxC0Pa/
PohmlO2KJBKAgVv2kll3EdvZk8D4FmVTL481eu95G54btsYEE8PhK6ntmgpCxM6/6oE5Omf3m98xo+e4EIL
svAyy88Y/
F9dsK6NmbSHdLS5CgQgmq56iyuwptVX6Oz1cPBbbSBxr4ujfLxzrwGo3yZahEkkasOdYWLtjttln08vmi9i
zqH/0i+Tv/
x2O119GF4hpSviql9F3x70Mrb1hlvYsLaQTvgRRggFKfvFTso8fHtfGJFBUgq+yBp3PO6mAwqjIUuEffhvr
L6ppWNpbyD55jOHlq2h5+JOopvlNFzNZDGzaU82JF5umHLNsfSHFVTlcOtE5o4jjWDQNPLNMa5csDTRNY6B
riLa6AYYGA+j0CgXlWZQvz8VsjS0yoxGVYy804urzxs+LqhrdzYN0NQ2y/
sYKVmwqYcgVYLDXO9Wl4mTlWdlyW82UqqVFFdkUVWTjGwoS9EcwmvVk2OeuhGR45VqcO24m5/
CrwMTH8ejvGU31NH/
gETLqL5F18ihGtys+xlddS899f4R3+ao5s1MiWXTodLT86cdxHDxA3oH9mPp6Yq9P4kiPPo+73vZuwrn5hH
PzufClb5Bz9BCW5gYQAm/tSoZrV1Hx0x/E2v7F+4SraAY9HX/
0nqTtyWaC2WqgavXEKNxkNJ3vS6jmKAQ0n+
+dthMeDkUJ+sPoDbr4vVkikcyeaEYmwbx8jP39iCm+uJoQBErK0Qwj66JMG91vf4Dut7wD/
fAQqsGEapUtgCdDOuFLDBGJUPW9f8Da3DjB0Tb1dGHq7ky4rxXvUTqm1yhARv0lSh//MW3v/9gcWJ2Y/
BI7u+5ZzoXjnbjGODLmDAPL1hVSVhurbSmrzU2pbjYZim5htHSTXDtUVePMwVa6W1zj0iaHPQGaL/
Sy+dZqcottXH6jE1f/ROd6dPyZQ61k5a5i6+01dDYPUn+qe1wU+2rc/T5e/
NV5Vm0tobTGMeU4q82E1TYP+g1C0P3md5Bz5LWEyqeaopBz5DVaP/gJuv/
ojzEM9KEf8hCxZRHOlemlEsmk6HQ4b7kd5823oQQDIAQG1yCFv/s19tMn4t+5QHEpvXe/Bc/
GrfFTVYuVgd17YffecVM2fOr/
YG1uwHbmDZRwiGBhCa4tO2I9fa8h0Yga72IyFZoGA93DRKMquhTaJw27AzSc7qa7zR137LPyrCxbV0h+aeq
17xLJtSISjtLd4sI3FEJnUCgsz1pY2ghCMHDrXRT/6rGph2ga/
XvunHhApyeSlf4MvaWEdMKXGFlvHCGjqWHSY0LTZqysKjSNrJPH6O7vJZxXMHMDZ4jdYWXHnbX4h0P4vSH0
BgVbjmVcXcvKTcV4PcFYr+Tp9E4ai4g5/
ZKlhaZp+L0hIqEoZqsxqaJo49keultcI+eOnSjW8u7EgSZ23bOc9gZnws+ZANrq+lm1pZSyZbmULculp81N
47kePAOTK6dHwlHOHmpDCEFJ9bV/
gJl6upK2HhGqirX5yn1nNFonkUhSQAhUc0z7IVhYTOuffhzd8BAG1yBRszn2XUpVUV0IfNW1KbUhm0+ubh2
aCDWS3An3OP0c2V+PelVHFHe/
jxMvNbF2R1l8g14iWYi01Q1w8XgHalRDKLG1Rv2pbvJKbGy4qRKDMT1aR7Nl4ObbsNZfJOvUcWBM6cxIho5
z+424tt147QxcxEgnfInhOHgg/
sWYjFnFeIUg68wb9N9292xmmRWWTCOWzMnrShWdwpY91fS0u2m73M+wO0gkHJ1WiroQgrIR1choRKW9YYC2
ugH8wyF0eoWiimxKl+Xg7vfT1+lBUzVsORbKlueSMR+RScm06Wl10XC2Z1y/
24IyO8s3Fk+64xyNqLRc7Es4pxrVOH2wLelnS9Ogr3OIVWO0DgvLszCadBzZP/
lm2SiXjndSVJmNkgaF9VmRYg2pplsYCwaJZCkQzbQRzVw6tdEGgw6DUUc4lLhNod6goE/
ifGiaxumDLQlbkp4/0k5+qV32KpcsSDoanJw/0h7/
fUzlKP1dQ7z224soOoGmgn1EUM1RmJmyoFpaURTaHvoow6+/
TN5Lz2Huiek6BIpL6d9zF67tN82q7eL1jHTClxjGvp6kUasZIxSUQCD5uGuIUES8bhbg9WfrcPenXuNduiw
HS4aRcDDC0ecbxjluajRKW13MKR+Ls2eY5gt9LL+hKN4iKhSI0Nk0iG8oGE8xysq1Xpsb6HXKsCvA+SNtDP
ZN/P/v6/
Aw0D3M9juXYXeMT9N09XuJhJNHbYacqfUA19SJ38f2BmfS9nuhYISBrqFrnlbpL6sgajKjC0793dcUJSbeK
JFIJJMgFEH58lwaz/
cmzB6KhFXOHW5nzfayKTcgXX2+cS3TJkPToL3eybL16W3bKJHMFlXVuPxG19QDNMaVrQX9bnrb3JTVOlizv
eyaOeKDN+5h8MY9iGAQBGhGGXiaLdIJX2KoZgsMJW/pNd32JhBTUg/lz38qeqpomkZPq5uWS/
0MDfpRFJF0R/
1qOhsGWbmphHNH2hl2pbbhMOpI1Z3qxmQ1EA5GuPxGF5p2ZXOw+Xwf2fkZbNpdlTQVWjJ7mi/
0cenE1O28NC2WHnnmYBs33rdi3ENttuJ+VxMKhDn7eisVK/LiDr9/
OJRU8R8g4A2l1ZbJ0Luc5B14jpwjr6HzeYlk2nHuuoWBW/
YStdnRjCacN+0h78Vnp97gU1UGbtk7+TGJRCIBqlbn093qSnr/
62hwougEa7aVTXrc40xtY90tRVYlCxBn9xCh4NTaMFcz+l1pr3eSmWWmcpJ2ZPOJZpLOd7qQ3sASw7V5OwV
/+G3yGs6Rn5qigBCIaOIUsVifXzPuDQujh/
jVqKrG6Vdb6Glzx1+LQtLUt8nmaa8boKfVnXzwJFw60Uk4eOWa2rhaNS/
HXmhk577l1z7FeAmhaRpDrgABbwiDUU8oGE7ogF85MSbs4+73jWtJl2618WhEo7NxkI6GQZZvLKJmbSEGkz
4l3YLpbiJNF3N7K9Xf+Sq6YCAuwmjwuCj4w29xHDxA4ye/
QKigkJ57346lrYWMuguAiKukaooCqkrPfX+E7cIZso8dIpKVjWvLTiL2rDm1XSK5nhDBINnHXyf72CH0w0O
Ec3Jx7tqNZ/1G0C2OpZzBpGfHXcs5/
VoLA92JRdra6gZYtq5w8nTyFCOBQj5nJQuQROKsyWg630vFijz52V4iLI47tyRlnDftIe+FZ1HCoZTqv507
b0E1W/CXVmDuaqPgud9PGDMaIe+8/0E0oxG9x43j4AGyjh9C5/
MRzs3DuetWXFt3xVsUzDdN53vHOeCzwZlCK6mpGOuAX42mwdCgn952dzxdXjI7BrqHuHi8c1zWgphmG1zPo
H+cE261mXAUZiZV8p0O8WyJk91k2s0UV2XTm+TzqujE3KaiR6NU/eCb4xzwUYSmofcOU/
mjb1P3+S+hGQw0f+RTZB95jdxXnsfc3Ymm0+NZvQ4lFKLwd78eWRgL0FSKfvNfsePrbmBgz134apbP3fuQS
JY4hoE+ar7zNQzOfkY3wUy9PdgunsVbVUPzRz59zdXPU8Vo1pOZbcbZM5w4G0iD7hbXpFG/
3KLMlK6VW5jaOIlkPjGYZu56Bf0Rht0BbDmWNFokuVZIJ3yJEcm0xVJFwsnTWLWR9kOqNeaAuLUdRDNsFDz
7FLrAlXrX
iM3O4LZdZJ06TsEzT2IYHECoatzJ13uHKW1pwvHqizR9/
DPx+eYLVdWSCmlNh+k6cdObHDobB6UTngb6OjyceGli/
3gtdRFeYPJoSUGZPa1O+Fiazvey7c5aMuwmfEPBKReiuUU2dPq5+zDaz7yBwT045XGhqpi7O8mov4R3+So0
vZ7BG29l8MZbY8dDQWq/9teYertj9wJNY2xoX0QjZJ06Tvap43S+/
QEG9tw1Z+9FIlmyqCpV3/9HDC7nyDN3pH3oyI3O2tJM2c9+SOvDn7xmJk6XcDCatHmJEEyZspuZZcZRmMFg
r3fK+6dOr1BSc+27S0gkV5NXnIneoCMSnl6m5ijqJDozksWJdMKXGPYzJ9EPDyUdpwmBZ93G8Q6zEPTfvo+
BW/aSeekcOu8wUWsmuS8/
R8ELz6IpCkJVJ9SOj6a+WzrbKHv8x7R+8BPpfVNJGHb5E0agp0tJdQ69bcnr6meEBkF/
eG7mvo5QVY2zr7elZa6royVeT4BLiURTZomr30c0orJ17zKOv9DIsHty7YG+Dg/
nXm9j7c7yORFiybx8AU3RIdQE2RuKQubl83iXr8LU2U72icPofF7CtiyyTh7F3Nud8BqjVpc88XP85VX4lq
1I4zuQSJY+tvOnE37PhKaSdfYkxt5uQgVF82jZzDFZ9EmrcTQNzAmUzdffWMmR/
fX4h8cHHISIbaxu3lON3iA7NkgWHopOoXZDIRePp1A2dxVCMGWHIMniQzrhS4zMuhQW1gAIeu956+THDQaG
1m0EoPSxH5FZdyF2xkjK6lTugFDVWHRtoG9eewSnc1cwv8xOYXk29txehpz+lMSzpoUAk1W2TJkt/
Z0eQoGZ11VB7GGWW2LDOqa1nBpVuXC0Y1JF83SiRlXMVgNltY6ED+KOxkFyCjMprXGk7dqmrg5yjrxG5qWz
ydMGNA1zazOV3/9H7BfOxGrAEaCqJC1oHzuNopB3YD+t0gmXSKaF/cwb8Q3wqdCEwH72JP2375v2/
ErAT86R18g+cnCk1tyBc+ctuDfvmLPyspIaB03nE2evCUVQWJk95XGz1cCue1bQdrmftvoBAr4wer2O4ups
Klfmp13bQyJJJxUr84iEVerPxDbY4ptSCR6rQkBRZTbGWaSzSxYW8n9yqZHgQT0W1+btBEorxp1ncPYjgFB
OLuh06N0uco4emnbLM9uFszhvvm38i5qGtbkB27lTiEiEYFEJrs3b09LiIMNuRigiLY7Tmm2lAKzfVcHhZ+
uIRtSUHXFFESg6JXGKkQalNQ783hABbxiDUUdGlkm2Lpsmw+5g0hZfybDaTKzfeeU7EA5FOfZ8A54UW4/
NFL1Bh8GkR9M0Wi/1Jx3fcrFvWk64iITJOnmMjMsXEJqGv7yKwW27UI1GSn/
+HziOvBYXVEs6l6Zhu3j2yu8p3l8mzKOqZF48N6NzJZLrGSUUSn6jE0ps3DQx9vdS/
e2vYHDFylIEYHA5yWisI+
+lP9D08T+fk17lmVlmSqpz6GyauhymZm0BiiJou9xPV4uLcCiK1WairNZBXrENIQQGo46adYXx1qASyWJBC
MGy9YWU1TroaHTiGwqh0yu4+724ByauQYSI1ZIv31h8DayVzBXSCV9i+Cuq4eCBhGME4NmwOfZLNEL+c78n
78Vn0ftj7TyiZjP9t95FJCtr+gW2QOb5MwyvWB1PjdO7nFT+8DtY25rRFAVtRI29+Nf/
SccDD+HevH3a1xiLwaijuCqbrqbBWUeudbpYDa5Or1BUmUN3y2BKPaMBKlbm4ur34ZqkL/
UoVpuR1kv94+qNrXYTtesLKa66/
urXNE0jGlFRdEpSxXj3gI+B7iE0FQK+1Fp8TUVuUSYrN5eMaxd39lArnsG5dcABypc7UBRBKBDBN5x84Tw0
GCAaVeOfzURYWhqp+sE30Q8PjUStIfvIaxQ9+QuGl63ENuIIT8eZTtf2ULIODBKJZCLBgiKStVIQapRg4TR
T0VWVqu99A4PHPWl5mbm7k/L/+D7NH//
zaducCmt3lqPoFdrrBmLXHdlUFYqgZm0BRRVZvPrUxXFK0l53gN42N3klNjburkrpniiRLGRMFgM1a69sIq
lRlbrT3bRdHiAaufKczi+1s2pLKZYMmYq+lJBO+BLDtXkHxU/
8J0owOOniWROCSKYt1tYkGqHmm3+PtaVx3FhdIEDBs08SzsphuuFGAdjPnyLr3Enc6zbS+c73UvPtr2B0jj
xoxwi6KcEA5f/xfaJmM8NrNszwHcdYsakYZ88wQV94UnMVnUja/
9lk0aM36uhtd3PylRY0TZtOxi3NF5JHNX3DoQmOl88T5PRrrQT9EapWX9v+j/NFKBih5UIfbfUD8Xr+/
DI71asLyCkYL+znHw5x6tWWWM9XMbIcneVmy0D3MAefvkxpTQ5rtpcR8IXpbZ8jHYCrqFg5g//
jFN6vYaCf6u9+PR4RG+doh8PYLp5Nm0M9XTQh8JdVJB8okUjGMbjzFgqefXLK4xoQtWbgWb9pWvPazp/
G1N875XGhqtguX8DU2U6wZPJ+3bNBUQRrt5exbF0h3S0uwsEIJquBospsdHqFV568OKHkaPS+3985xIWjHa
zbWZ52uySSa4miU1i5qYTa9UW4B3yoqkZmlhmzLGNckkgnfImhmUy0vfdDVP7ouzEBtTGR7FgUWqHtTz4MO
j0Fv/
v1BAd8FAEY3IMzWrSP7qTbz54ko7EOnc875TU0ISh68r+pX70+5d6fk2EyG9i5bzl1J7vobHLFU9ONZj1Vq
/
PRVI26U4lFpCpW5OEbCsYc8LmqCU4w7aUTneQUZOD3hkADe64Fa+bSq2sL+sMcfrYevy807t+jv8NDX7uH9
TdWUFIdywoIBSMc2V9/
RcxuevsiSelojGVP2HPnr72PbyiI2WrAYNJhzjAQ8CYW6svMMqekkp53YH+sNeEk2SsptCSfU4SmMXDL3mt
ogUSyOAnnOOi5920U/e6JCcdGv9Md73ofmn56i3TbuVPJa80VBfu5U/TNgRM+itlqmLD53NnoJOhLfF/
saHAS8IaoWVeIQ7YikywxdHpFfq6vA6QTvgQZWr+Jxk98loJnnsR2+TwQc3aHVq+n5563EiivAk0j78BzSe
caFXETM1jCC0Dv8yY8U2galq52TF0ds95tN5kNrNtZwcrNpfiGgiiKICPLjKIIohGV3nYPbqdvojciwO6wU
Lkqn8tvdM4+zDoLXn+mbtzvucU21u4oW1IpSOcOtxG4ygGHK//
sZw+1klOQgSXDSNvlAQL+cHIPchZeZmfTYCwtfZ481Wh0ROBQCCpX5XMpiUJq5aq8lObNPnow4YI62RbX6F
tPZ7R8dE73DVtmXXYikVyv9N35JqLWTAqe+R8MQ1cydkL5hXS99V0MTTMKDqCk0MYUIRDh+e/
m0dPmTmncQPcwA93DrN5WSsWK1O6TEolEslCQTvgSxbdsBc0f/
wy6IQ967zCRTNs4gRXF70UXnLw10iiji3ENLVbHPUPnNJVFvcHjTlvKm8GoI+uqyKZOr7D1jhoaTvfQVnel
1kanVyirzaX2hkJ0eoXuVnfKPvhshcFSwdk9xOFn69i5b8WSSEfyD4fo60jcQk8D2usGWL6xmPb6gZQcY6N
JRygws5pjISDgS8HRTxOZdnP87xUr8hjoGqK/c/J/k8KKLEqXpSbKpvNPrUWQEjP8QI9tWXh1+8KILYuBW+
+g7/
Z9oMj6TYlkRgiB8+bbcO7aTUbjZXReL+HsHPyVNTPOIAsWliT9votolGBRyYzmnw1ja2FT4cLRDrLzM7DnW
ObIIonkCtGISneLi/6uIdSoii3HQlmtA7N16QRLJPODdMKXOFGbnajNPuF1JZi6kmrbe/6Ugud+j7n3Su/
kiMWKr6oG+4WzCc5MnYgt/QqsV6PX61i5uYTaDUXx3sxXp/qq0dQe/
pZMI46CjLiwzFw545oGQX+EU6+2oEZVgv4IJoue0mUOSmpy0OsXVx/
Uwb7h5IM0cPbGxqXaU32mDvgoOr2CyaIfJwKUboSA3CLbuB6fiiLYdGs1rZf7ab3YHytFIKbcXrkqj/
La3JSV8yO2LAwe18zt0zQ0nQ6mKaDmL6+KlZyoKr7qZTh33ELUZkNTdDFRKd3i+oxKJAsWnQ7v8tVpmWpwx
80UPv3ElI54vNZ8w/
Sj7LPFajfh7Bme1oZ42+V+1u5YmjXimqbR2+am9fIA7gEfiiLILbZRuSqP7LyM5BNI0oZ7wMeJF5sIBa+sF
Xo7PDSc6WHllhKqVl0fuj6S9CCd8OuUqM02IWo1GRrg3rIT9/
absLQ2YXT2EzVb8S5fSUb9pVk74RoQLCwmUDJ/
D0+dXpkQKR8lw26OCYAlQsDOu5djNOvpbnHRdnlgDqwcj6vPG/970B/G4+yg+UIf2+
+sXVQR8mFX4uyLseOOPt8Qaz2XRFAvHZjMetbtLOfES03T3lBRdIIVm0qIhqP0trunbC+iM+hYtbV04vmKo
GpVPpUr8+IidQaTbtpt65y7dlPwh99OWhOeDE0IBrfdSDQjg7wX909ZfqIRqxMVmgZC0HfHvfTc+/
ZZ6TlIJJL5J2LPouut76bkif+csBbQRr7PHQ88NO1a83RQXps7reeqpsFAVwobvCME/
WF629xEwioWm5GCUjvKAlVa1zSNMwfb6GoejJdMRYGeVhfdLS5WbS2lcqVMxZ8Pgv4wx55vIHJ1psbI4/
LS8U5MZv112elGMjOkE36doukN+GqWk9FYl3Cct2Y56GMfE39lTSz9bfRY7SoiGZnovak//
MbZQOyZ0vOm+xfMIr58RS7uQ1M74UJAQVlWvLVVfpkdvUGXuDf4HBHwhnjjQBM79y1fNH3Gh1JsARYJqzi7
Z/
a5mi6aBiU1OWTYzWzdu4yLxzsYGky+WSBErK570+4q8kpi2SbVawpoOt9L84U+wqErn4m8EhsrN5eSYZ9aa
E8IMa5l2nQZ2H07jtdfRj/kSbkF2airPXDTbXT90QOAQOcdxnHkYFy0afRnML8Q9/
pNKKpKODsH15adROxZM7ZXIpFcWwb23Ek0I5PCp5/A6LzS3SNQVEL3W9/
N8Op118QuW46F8hXTdcST755GoyoXjnbQ0egE7UoFjsEY2yAdFQRdSLRc7I854DCuZGr07V481oHdYSEnX0
bE55q2uoGYA57go1Z/poeiyuxFsyaTXFukE34d0/Gu97H8q//flAt2TVHoeOChKc/
X9Hp6972Vkl89NmMbNGK9jeN9y68xxVU5dDYOjuvjPYoQoDfoWLGpOP6aTqewamsJZw+1zaeZQOwh7HH6cf
X5JrT1AgiHonQ2OnEP+BBC4CjMjLd/GSXoC+Pq94IQ2B2WlATgfENBnL2xVMEshxW7I/
U6vGBg7tK9Z0pxVTYZI3XajsJMbrx3JR6nj45GJ/1dw4T8YfQGBVuOlaA/
jH84hE6vUFiRTcWKXKy2K461UAQ16wqpWp2P2+lHjapk2OenvUg0007DJz9P5Y//
GUtHa0qZLgKIWDNiDrgu9jjoePCDDNx6JzmvvzqS+WLBvXk7Q2s2yLpuiWSJ4dq2C9eWHVjamtEPDxPOzo5
lpl1jJ2L11lLMFgON53qT1ogLwaTPwLFomsbpV1vGtaIcdWTDoShnDrYiBAsqiqmpGs0X+xKOEQJaL/
ZJJ3we6GwaTKod4/
ME8bqDZGabEw+USJBO+HVNsLiUxkc+S9UPvoku4B+njhy1WGn68J8RKixONAUDN+0h+/
CrWNtbpn39UTHq/
Oeexlddy9C6jdOeI90oimDznmoun+yivX5gXG9xR2Emq7eVjXO6AEprHAjg4onOeDpxIvQGBTWqoaahDZoQ
0NfhmbAA6W51ceZga8z+kd7anU2DXDrRycbdVfiHg1x6o2uCvXklNtZsKxtXtzxKMBDm7KG2CSJi9lwL63d
VkJmV/KFjMC6sW05xdQ7rdkwUBLQ7rNgdM29bpuiUa7Io0gxGhleuwTjQiy6QPJqvEetgsPqLn6brre/
CteNmAAJllXS9o3LcWCXgx9LWAqpKoLSMaOZErQmJRLIIUZRxWW4LASFiG5qVq/I5/
mIjg73eKcdqGpQnUUcf7PWOc8An4+LxTgorslGUhRHF9A0Hk7Zq0zTom0LYU5Jexma3JR638IINkoXJwloR
S+Yd37IVnP/
yN7GffiOWmi4E3prleNZvjEfGElH0219hmYEDPsqoI1745C8ZWnvDNd99h1jN+OqtpdRuKMLV50VVNWzZ5g
nO91hKahwUVeXQ3zlEwBfC3e+jqznWg3rUCdY0sGYaWbahiDMHW9Nmb/QqMbnB3mFOvTLm/
2RMb+1wKMrR5xqmnKu/c4jXn7nMzntWjIuKh0NRjvyhAf9wcMI5Q04/h/
9Qz659yxP+G2mqFnPue1J7X3OJTq+w654VCdPDFwXRCKa+HlA1UFVqvvcPcZG0VBj9tum8w5Q//
mNENMLgjXvGjwkFKfrtr3AcfDne1khTFFybttH19j+eVPhRIpFI0oFOr7DxlioOP1uHzzuxtSVAzbqCpJue
HY3OpA0gQoEIA91D5JcsjHuamqIeSiqp+JLZY8kwMhRKXlInVdIlqSKdcAno9Hg2bcOzadu0TlN8XnIP7J9
1X2EBWHq6MHV3EiyeKFx1rTAYdeSXpv4wVhRBQdnI+BWwYlMxHY2DeN0BFJ0gvzSL/
BIb9ae709beTNOg9VI/
AV+Y6tX5ZOdn0HCmZ1Y9r0PBKHUnu9hw05VIaFtdP76hiQ74qA3RcJT6Mz1suLFi0jGqqnHy5Wb6OhJHIuY
Lk8WwuB3waIT8539P3oHn0A/HoiCz6fM9ek7xb/
4L15ZdaKbYv42IhKn+3jewNtWPa1EoVJXsN45ibW6g4dNfHNf+UCKRSNKJ0axnx77lNJ3rpa1+gGg4tsloy
zFTvaYgpRRy/3AopWduwDv/fdGnwmIzouhEYmdcgC1btmabD8prHZw/
2jH1AAGOgsxJMwklksmQTrhkxtjPnkRMs51RIvRDngXlhM8Wk8VAzdqCCa+nIw39avra3fS2uVm1tYSBNAi
adbe4WL21FIMpdotoq0sskKNp0N3sYs22UvSGiS2pGs70LBgHHBGrA1+0RKNU/
ui72M6fHu8Yp2FqJRgk69QxXNtvAiDn0MtYG+smnVuoKsZBJwXPPkXX/
e9Jw9UlEolkcowmPSs3l7D8hiKC/
giKTmCypK61YTCl1irRYFw4LRX1eh2lyxyJ26BqUCHV0eeFkhoHLZf68XomD0gIIcZpBkkkyZBOuGTG6Lxe
0hbShetGadmWY0l7X/
ErSqmdaZvP7w1hMOnRNC2l6ICmaQT94QlOeDSq0nqpf4qz5h+dTqGsNvdamzFjco68hu3cqWk73SlFynU6j
P1XhIByX3kh4ZxCVcl5/RW63/wONKPc/ZdIJHOLolNSijQG/
WHa6524+r0IRWCYZHN44tyCvJKFldVTu6GIga6hKSP5BWV2iiuz592uxUQ0qtLT6mbY5UcoCnklNrLzrNNS
MI9GVS4c65jSATdnGFi/
q2LK9rcSyWRIqVvJjAnnOMZF4maKBvhLKwgWlczeqEVAYUUW+gW02z4Vo31ThRDjFNUTMVkUfGjQf01auE2
GTq+w5bbqRdVb/
WpyX35uxtoJSc9SVVTziMCepmHq7U56ji4UxOAenJE9koWP0+nkwQcfxG63k52dzQc+8AGGh6fOtmlubkYI
MemfX/7yl/Fxkx3/+c9/Ph9vSbLE6WhwcuCJ89Sf7qa/
c4i+dk9M2ToJ1WsKJn2GXUuMJj077l5OWW0uiu7K3dhg0rFsQ2EsUl4/
QFfzYMrCYdcTve1uXvr1ec4cbKX5Qh9N53o48od6Xn+mDr83lNIco8r6HQ3OKccsW1eIozAzXWZLrhNkJFw
yY4bW3kDEYkXn9804FVYDEILuN9+fRssWNjqdwvpd5bxxoPlamzIlOr0yrma6qDKbzkZnwgh+Vq510vTAVM
VlhCLQ5iBV3+Ywo9frKCjLoqQmB6NpEd/
2VBVzZ3taUs8nRdNwj7YLFAJNp0NEkiu9qobFu6khScyDDz5IV1cX+/
fvJxwO8/73v58PfehDPP7445OOLy8vp6ura9xrP/jBD/ja177GPffcM+71f/
u3f2Pfvn3x37Ozs9Nuv+T6or9riLOvJ28ZOprEN/
qzfHkuy9YXzoOF08do0rNmexkrNhXj9QQRisDrCnDpROe4tp+KTlC5Kp/lG4oQC0Th/
Voy0D08bp01dv0yNOjn6P56dt27MmkJgqsvubL+5ZNdlFTnxIMXEkkqLOLVqORaoxkMdL/1XZT9/
N+nf+7IT9VkpuOPH2J49fq02rZQCfrDDPZ5QYs5tt0trmtt0qQUV2WPS9WqWp1PZ+PUu8AANesmX8BkZpmT
Vy0IsGQY8A1Prn47U3R6hRvvWZm+Ca81QsR6daeofj5KKj3DNSFwb9xGOO+KjsHQ2huwn3ljSrV1DUGwqJh
I1sLprStJHxcuXOCZZ57h6NGjbN26FYBvf/
vb3HvvvXz961+npGRi9pJOp6OoqGjca0888QTvete7yMwcHynKzs6eMFYimQ3JhEmFiLUbNVkNRMIq1kwjp
cscKbXYBIiEo/S0uQn6wxjNegrLsuLaKXON3qAjK9dKV/
MgpyfpsKJGNZrO9RIKRFi3s3xebFrI1J3smvJYrOQuTEeDk6rV+Qnn6WgcTLqGCQej9HcOUVB+fZRVStKDd
MIls2Jw127QVEp+/
Z8o4XBKi33GjOl+yztxb9qe8vVEMIh+eIioxYpqXTy1N+FghPNHO+hudaXVyZwLdHrBqq3jBfKiETXhA0hR
BEMuPz1tLoQQOAozKazIQqdTYguVimx6Wl0JxWV8Q6mlhk2HokVSK2dtuEzuqy9iaW1C0+vxrL0B5023Ec6
9SnBHCIZXrCHz8vmU25BB4u/k6Hd2ePlq2v/4/eOO9e+5C/
up4wnm1ejbe8+CaC0oST+HDh0iOzs77oAD3HHHHSiKwuHDh3n729+edI7jx49z8uRJvvvd70449vGPf5wPf
vCD1NTU8JGPfIT3v//906rTlEjGEgyEcfVN3U8cYo6Uq9/HHe+e3sa/
pmk0ne+l4UwPalSLO2XnlQ6q1+RTu6FoXj67qqpx4VgChW5i6fgVK/Ow51y/qum+oSDuAV/
Sce0NA0md8JSV9ZP0dJ8pIhQi+8Rhso8eRO9xE8nKYXDHzbg3bUXTzzwLzdTVQdbJY+j8PkKOPFxbd8pOJ/
OMdMIls2bwxj24tt5I7kt/IO/
AfvTDQyk54hpQ8OyTOG+8NRbdS4Cxt5uCZ58i640jKNEoGjC8ah29d70J37IV6Xgbc0YkHOXI/
ga8nsDCd8ANCjvvWo7uqpSqZG3VVFWj/lR3vCd6R4OTi8d1bN5TTXZeBis3lzDQNTTvNWtVqxI/
XK85mkbxrx4n75Xn0RQl7liberrJe+kPtD30UTyj6eEjDNy8B9vFs6lNT/
JNMQGEchw0f+zRCc60r2Y5He9+H6W/+CkIEbdv1Na+vffg2nZjSrZIFh/
d3d0UFIzv8KDX63E4HHR3d6c0x49+9CNWr17NjTeO/5z8zd/8DbfffjtWq5U//
OEPfOxjH2N4eJhPfvKTU84VDAYJBq8II3k8C6TjgmRBEAmltjEZ21TWpuU0N57tpf70lc/86LNQUzUaz/
aiRjVWbp57XZv+Tg/hYOLnqBCxZ7B969LpNjNdgv7UHOKgP3m5ldGsT6nt61xo/
ejdg9R8+6sY+3piz2BNQ+vrIbPuAnnPP03TI39ONHN6fe2VgJ+yn/
4rWWdPoikK2sizvejJX9B7z9vou+NeubE+T8jiBUla0IxG+u96Ex3v+UDK9aoCMHjcZDRcSjjO3N5C7df/
huwTh1FGWqIJIPPyeWq+/RXsJ4/
Nyva5pu3yAMPuQMKdVJ1+4r+a3qhQOVetR0RMzTMz24TBpMNqN7J8YzG737qazOzxaXmhYIT+zqHUFN21K4
uTcDDKsecb8Q0FMZn1816jtmpLyYT3stD
IfeUF8l55HmBcZFtoKiIapeLfvoep+4rivW54iKLf/jrpXo5GLL28b+89SUbGxuqHPFPusAzeuIe6z/
41zp23EHLkEsrOwX3DFho++Xm63/JO+bBehHz+85+fUjxt9M/FixdnfR2/38/jjz/
OBz7wgQnHvvjFL3LTTTexadMmPve5z/HZz36Wr33tawnn+7u/
+zuysrLif8rLZcqt5AomS2rPGZNFPy0HPBSIxNLcE9B8oS9loa/
Z4BtOfg1Ni0WCr2eM5tRijKloxBRVZid1wBWdoKBses5wUjSNqh98C+NAHwLiQsijP809XVT8+J+nPWfFj7
6D/dzp2FyqihKNIjQNJRql6Le/Ivel/el8F5IEyEi4JK0MrV5HMDcf4+BAyumy+qGhiS+qKnqPGzSVin//
Pko4NGE+oapoQPlP/5ULK1ajWjPS8A7ST2td8vZcmgY33beS/
u4h1KhGht1EfqkdRRHYciwpCc1Mh5z8DDburkrpARQKJN8pngo1qtJyqZ/cItus5kFAXrGN/
s5JPiuTUFCeReVCj4KrKnnP/37KaHVs410j95Xn6XznewEoe/zHUyqWj10jqCYTbe/7MP6KavKf/
33CjTEBiEiEjPpLeFesnnRMsKSMznf/SUpvS7LwefTRR3nooYcSjqmpqaGoqIje3t5xr0ciEZxOZ0q13P/
93/+Nz+fjfe97X9KxO3bs4Etf+hLBYBCTyTTpmC984Qt8+tOfjv/
u8XikIy6JozfoKKrIorslQemTgPLl09vc7moZREu2Cy2gs3FwzsXd9IYUYmdi8k4lkzGuxt2kp6A8a3GLl4
6QYTdjyzEzNBhIOK50WXI9k/xSO5nZZrwJgilVq/
PTrqxvbbiMpb1lyuNCVclsuIy5rZlAeVVKc2bUX8R2+ULCMYW//w3Om25FM05+H5akj8X/
TZMsLBSFlg9+gppvfwWdz5tSVDw8tj94NErey8+R+9J+jK7EQmAw4rxEI+QcfpVASTm5r76AtbkRJRhANRg
JFJfgvOk2PBs2gW7+P+6amlqPbTWqoejEpOnTpcscOIoyYz1P+4YJBaMMu6Z+sEyWNm7JNJKdF1MvL6zIJi
vXknIkYDYPZE2DzkYnBpNuVi3lC0rtbLylimMvNOLsHZ56V1pA5Yo8VsxDWuBsMXV3Jv2MC1XFfuoEne98L
4b+3oT9wUez5Vybt9P5wEOoplgWQCQjE4N36pZSoxid/
SSuppQsFfLz88nPT75JtWvXLlwuF8ePH2fLli0AvPDCC6iqyo4dO5Ke/6Mf/
Yi3vOUtKV3r5MmT5OTkTOmAA5hMpoTHJdcQTcPaWIeppxPNYGR45VoiY5/
t80TthiL6OjyT6pgIAWargfIVudOaM+ANJ+3eIYCAb3aR8Eg4SlvdAG11AwR8YfR6haKqbCpX5se7lRSUZn
FetCd+lmrJ9VA0TaP5Qh/1p7vH17gf7aBqVT7Lb5h/hfVhd4CgL4zBpMOWk/
oaZSqW31DMiZeaJj8oYmubstrknwVFEWy9vYbjLzYyNBiYqKy/
IpfaDekXmLSfeQNN0SHUqcsPNEXBfuZkyk549pGD40rfJkMXDGA/
d2paek2SmSGdcEnaCZaUUfe5v6b0Fz/
Ffu7UlOM0IJztwFezPPZCNErlD7+N7fzpCeMS3oo1jbwRp310rEbsRqKv82Cru4ivopqmjz46/2JuInYDV1
NovZWoF7clw8jyG67c5LuaBzn7elv84Qmxh4El08jmPdUIQVyFPTs/I2XlVwC/
N8RA1xCqqmHLNpOVZ8VqM85YOC0SVlMpp0pIVq4VoQg276nm3JF2uq7q+ao3KJTWOKhZX7hodvGVgD+1ceH
Yv3tmkt3rUXTBYNwBB/CXV6C/eD7phljUfP2K+EgmZ/
Xq1ezbt4+HH36Y73//+4TDYR555BEeeOCBuDJ6R0cHe/fu5Sc/+Qnbt19ZtNXX1/Pyyy/
z9NNPT5j3qaeeoqenh507d2I2m9m/fz9f/
vKX+cxnPjNv702SPqz1lyj7+b9j6uu58gxWFAa33UjnOx6c14ia1WZi+121nDnYOiEKmlOQwfobK6f9jDAY
dckj4SPjZkowEObI/
gZ8nitp5OFQlPa6ATrqnWy+rZrcIhtGs56y5bm0XR6YdB4hwGKLZdIloul8L3UnJ69xbzrfSzQSZfW2shm/
n+kw0D3M5Tc68TivPBOtmUZqbyiiuGrmnTfyS+2sv7GCc4cnrpWsGUY231ad8mfBZDGw654VDHQP093iIhK
OYsk0UrbMQYZ9bsreRp/9idCESGncKAaPO2mWqiYEerc75TklM2dxrFYli45ItoPWP/04y77x/
zB3tsVrWEYZfVB3v/WdcVE2x6svYjt/eoKzkMpeqGEkojg69uqflrZmyn/6A1o+/
GfTfi+zQQhBQXlWYmVwwO6wTNpjeyqKq3LIL7XT2TTI0KAfRRHkldjJK7bFd6+n+2AIh6KcO9xGT+v4m6/
BpEsqBJMIo0lPXomd+tOJa+qmQggorXUAsY2KDTdWsGJjMX2dsWhHhs007n3PJ8bebkx9vURNJvxVy9D0Kd
5SNY3C3z2RdINJE4JAUczZEdHk/
wdiknHuLbuwXzyf8DzVYGR49bqk80uuPx577DEeeeQR9u7di6Io3H///
XzrW9+KHw+Hw1y6dAmfb7wS8Y9//GPKysq46667JsxpMBj47ne/
y6c+9Sk0TaO2tpZvfOMbPPzww3P+fiTpxdpUT/U/fz2+sI8/
e1WVnCOvYXQO0PSxR5OKr6YTW7aFXfeswD3gwz3gj7clm85m9FgKK7OpO5VYiFDToKhy5g7j2UNt+Cep49a
0WNT6jQPN3Pr2NQgB9hwLmdnmSTPiLJlGtt5eg5LgeRgORmhI8jxuvTxA5ep8rJnp20AJ+sO0NzgZ7BlGGw
kQWG3GWLndVesj33CI06+1EgpGZ6WNU1IdWyt1NQ0y5PIjFEH+VWulVBFCkFdsI6947hXEFb8PnXcYEkTBI
fa8DxakHoWP2OxJI+FC04jY01zfLpkU6YRL5gxNr6fp45+h4t/
+mcy6i1dUGKNRNKORjj96D+7NsZRGw0AfRb/
91YyvlVQBWtOwnz+NqbuTYNH8pipXrc5P2g98qh7bidAbdFSsSI9wmxpVOfZ8A57BidHZ2TjgCCirdZCVay
Ur14rH6Zt2SvraHeWYzOM3KMxWA+UppJGlG8Xvw/HaS5g627C2NGLu74sfi2Rk0rf3HvpvuzvpgjP/
2Sex1ScXvhKahmvbLgACZRUp9foW4RBF//OLWMuRLTtwb9pO4e//
B4PLOemDVwP6b7trXPRcIhnF4XDw+OOPT3m8qqpq0ijhl7/8Zb785S9Pes6+ffvYt29f2myUXDuKf/
U4QlUnbLRD7P6VWXcB+5k38NywZV7tEkKQnZdBdt7stWIybCaKKrOnfo6PaJbYHTPLJvIOBZPqnUQjKqdfb
cHZO4wa1eKLntEU+8xsM8VVORSWZ6GM6W7iHw7Rermf7lYX0YiK1WYiw2ZKmp0nRmrc05Vm3dPq4tRrreNS
+p09ycukLh3voKgia1pBiqsxGHVUzJXI7QzQuwfJfeUFco68hs7rJWK349y5G+fNtxHNyCTn4AFKfv04Ipy
4lFEjJors3px62vjgtl3kHD2YcEzUaMKzdmPKc0pmjnTCJXNKNCOTpkc+i7m9FfuZEyihEMGCItybtqGaLS
gBP6X/
+e9knTyasqr6WFLtSw4xB8V29uS8O+FZuVY23FTBmYOtsc3ekWfQaD3Rik3FFJbPf+3cWLqaXeNSwdKF0aS
PP/xuuKWSI/vrJ9bIC9DpFOy5VgbH1Htn51mpWV9Ifsm135EVkTAVP/w2tgtnp/y86b3DFD/5S4zO/
riQ2mTohj0UPvNkyp/d4l//J+bOdrre9gD+4lLM3V0IbfJdbKFpZDTWYW1uQKgqxb/
5OT33vp3Gjz1K9fe+gWmgL+aoa1p8N3xw12567nlbCpZIJBLJFUxdHVjbmhOO0RQFx8GX5t0JTzfrdpajRl
V62z0TaoIdhZnccHPljOdOxRkF6O8a46iPpo9r4PeGKV2WOyF1e6B7iBMvNcUc7pHx7qAPd3/y/
tlAUrX3cDBCNKpiNOnHOf5X4x7wcerVlhlpwmgadDQ6qVk7t4J384W5o43q73wVnd8ff44bnAMU/
v435L72En23303JEz9PniU3crzj/
gentYHuXb4ab83y+BphMvruehOa1N6YF6QTLpkXAmUVBMoqxr8YjVD1/X/
E2tw4IwccUnfAY4MVlNC1adtRXJVDdl4G7fUD9HcNoWkaOQWZlC/
PnXGKXDppS0HBfSbUrCuI72BbMozceM8K2uoHaK9zEvSH0Rt1lNY4qFiZi9lqJBSMEPJH0Bt1mK0z3/
lOK9EItV/5/zD3ptYXOffVFxncfhP+yppJj+e8/ipoWsqfXSUaxXHwAMaBftr/+E+p+c5XUSLhcQ/
QsQ9soWnxlHQRiVD85C/R9Hrq/uJvsZ8+QdapYyh+P6H8Apy7dhMom/niUSKRXL8YB/
qSjhGqirGvN+m4hY5Or7BxdxXuAT+djU6CgQhGk56S6myy8zNmJSKWSPAtVRrO9lC+PDfemisUiHDipeZY1
HyGTFXj3tfhofFcL66+mJSnTq9QusxBzdqCSSPWzReSf06mRJBQiHZREY1S+YN/
GueAw8izW9PQe1wUPfnLlDbow448ut7yTjybtk3PBkWh+UP/m4p//
x62i+fG9QkHQe9d98X6hEvmBemES64Z9tNvkNFUP61zphP5vhqhRjEMDmDqbCdYMj+CI2OxZMZ6cS/
fWDzv105GKr1HZ8LVwjgGk56atYVT7mobTfoFJ6yW+
+qLmFJ0wGEk8vPaS3RM4YRnNFyetg1C07BdPMvAzbfR8Om/pPB3v8Z+9uSVvqFJzi98+jc4d92Ke/
P2aaWuSSQSyVSoKYg5aimOWwzEUtytZOelV+B1pmnsY9FUja7mwXhrzvYGJ2o0tTaxk86nMakoWuulfi4c6
xj30IlGVNou99PT6mLH3cuxZBjHzKMl1cRJhICEUfbFhP3sSYyuwSmPj91AnwoNgb+ymoY/
+4sZ6yyoFivNH30Uc1sLWSePovP7CeXm4dq6i0hW9ozmlMyMhbXalVxXOA69jCaUKVNrr2a2e8UakHPkII4
jBxletoL2936IcI5jlrMuDfSG2YmvTYpgVrvwC4W855+Z1nihqpg729NuhyZizn3LRz5F6wc/
gW7Ig8E1SP7+35J1+sSkNZmj6AJ+bOdP49m4Ne12SSSS6xNv9TIiGZnoE7VAFALXluTt7K5nsnKtMaE1d2B
WCx1Xv4/RvKa+Ds/MJxoRssvKHb/
Z4PUEYw44TLBT02LR93OH29h6+7L462pUm7EDPjpvMqX3xULmpXOoig4lidhaIgQaSjCQFqHDQHklgXKZCX
ctWRrbS5JFiXGgL2UHHEaUn2dwndH7/9jzM5rqqfmHL2E/
eQxzWzMkadmw1Cmuypl5isFUaGDLufap9rNC0zC4B6f1T6MBqtE45XFfde2MTBGaOi4iH7XZCZRXogsGEzr
gENNDMLin3oGXSCSSaaPT03vnm6Y8rAmFqMXK4M5b5tGoxYcQgg03VqDTKcymNXZPmxv/SFbbdKLgo9cc/
ZlTkMHGW6omjGurG0hon6bBQNcwvjEq74pOYDDNrHWbEGDOMCwZJzwW5Z5dYEITgrA9Oy32SK49MhIuuWZE
MzLR+nuTKz6P/PSXVWJpb5m2rzjZeKGqGIfcVP7bP8evESguo/ut72R49fppXmHxU748l5ZLfUTDiR/
cYx/
AyXa3hSIorVkCmQaKMr1NGiHwrN985XdNw9LSSPbRQ+iH3ETsWWgjc07buTdP3NSI2GyptRyxLY2FjEQiWT
gM7LkTg3uQ/Befjd+HYooXGlGrlaaPPUo0I/
Nam7ngseVY2HXPcupPddPd5o4vfOwOC8VV2Vw60ZV0Dk3VaLnUx6otpdgdVoYG/
Umf0xtuqmCwz0vQH8Fo0lFclUNOweQ17q6+4ZSi2u4BH1ZbTNhLCEH58lwaz/
VO2/80mPRsuS1xu7XFhL+skpzXX0k6LlHZpdA0XDtuSqtdkmuHdMIl1wzXlh1YWhqTjovYs+i/
7W5C2Q4q/+P7c2KLACxd7VR//x/
pvvft9N395jm5zkLFbDWw9fYaTrzYRDh0JVVqVP21dkMRxVXZdDQOEvCFMBh1mDOMXD7ROeVDefXW0rhIzK
JFCIaXryLz0vmUHGYNgaY34Lkh5oQrPi/V3/
sG1tamcQ9WbczPlJcXQuDeNLGe27V1FzlHDyU8NWo0MbT2hlSvJJFIJKkhBN1vezeD22/
CcfAA5q52VKMJz/
qNuLbskirL0yDDbuaGW6pYE4wQ8IfRG3Tx+uq+jqGUVNQ7GgdZtaWU8uW5tNcPTD1QQJbDSnFVzqS131OeN
AMqV+XT2TRI0BeesF4QAvQGheo1BXS3ugn4wjHBu5ocSpc5FpxGzGxwbdtF8f/
8AsKhSf8lNSGIGk3og5ML0WmKEusuJMvKlgxL59MtWXQMbr+J/
OeeRj88NGUUr+euN9N7z1tBURChIFGTGd0UN6h0UfT0E/
hqluNdvmpOr7PQyM7LYPfbVtPV7KKvw4MaVbHlWChbnkvGyK728hvG9wzNcli4fLILV9+VlicZWSaW33Dt2
66li9673ozt0vmEY0adaYGGCIdY8eW/ZOCW28m8cAZzV6yGbuxDd/
TvEYsVvT95uxhNCFSzGeeuiWmdwyvW4K1ehrWlaeqWI3feJ/
uASySSOSNYUkbXOx681mYsCQwmPYarnM8Vm4p4/ZnkQraRUBRN07A7LFSvyafp/
ERlciFiYmdrd0xPoDa3KBO305c0op2dP743u9GkZ8ddyzl7qJWB7vEbCVl5VtbvqsBqM1G9RNqQTYVqttD+
4J9S/h//ElszjNmRGFUpb/
3AI5h7Oin6zS8QajSmm4SGUFX85VW0fPATaPoF0jlGMmukEy65ZqgWK02PfJaq7/0DxkEnmlBAU+Ppv713v
yXmgI+kRWlGE713v5niJ385p3ZpQpB7YP9154RDTKCtfHku5ctzUxqfU5DJjruW4xsKxnawzXoy7KZZtWtZ
aPhqV9L51ndR8j+/
GPf6qOM92XpECYfIe+GZpHEDnd+XUj9QTW+g6aOfIZo5SUq5otD8oT+j8sffJbPuYuxhjhh5wGv03XEvfXf
el8QSiUQikSxUrJmpZRQYzfr483f5xmIsmSYaz/YQ8IXjY/
JKbKzYVDLt9qhltbk0ne+d0gcXAvLLssapo49ithrYuncZXk+Qwd6YI56VZ8WWvTSU81PFvWk7EWsmhb//
zbjuQMPLV9Nz39vxV9bgXbkG15adZB89hKm3G9VkwrN+U0xPZgmtrSTSCZdcY4KFxVz+y7/
HfvoE9jNvIMIhgoXFDO7aTSivYML4/
tv3oYSCFDz725jDPsLVtyVtitdTQWgatvNnyHvhGdwbtxJ25M1glusLq80UrwFbigzcdjciGiX/
+d+jG4lca3oDEaMRvc87ue5ACvNO5cSPHyTo23MX/
srqKYeo1gyaHvkslpamkZYjPkKOPAa330gkewnU5UskEsl1jMGkp6A8i75299R12SLmKMd/
HanHLqt1MDQYIBqJYsk0YbbOLJJqyTSyblcFZw62xkvVxl7bkmli7fbE0fUMu4kM+9JdK6SCd+UaGleuwTD
oROcdImLLmtAaLJqRycCeO6+NgZJ5QzrhkmuOpten3r9YCHrveRvOG28l58hBrPWXyGhuQBfwx4dEjSaUcH
hayusTLhONUPQ/
v6Dof36Ba9suOt79EJrBgOLz4jj8KvZTx1GCAYJFJThv3IO3dqXcoVyExPpkHkMX9BPMLcC1befEaLOqUvr
zf8dx+NWY8NDo69EIhjHRhZmQik6N0DSCpamlDforqxM66xKJRCJZnNSuL6S/
04M2SetPIWKOesXKiVlsQoi09CIHKKnOwWoz0ny+j96RDQGjWU/
FijwqVuZhMM5MCf16JJzjkG1yr3OkEy5ZlESycmIptnfeB6pKRmMdBmc/qtmCv6iEVX/
7F7Oaf6w7nX3sdZRAgL4776Pqe9+IOfxaTP/
V3N1J9okjDG7dRfuDH4j3btS7nNgunEUJhwkUl0onfYGh+LxU/Ns/Y7t8IV6LJVSV4id/Sc+9b6Pvjnvj/
1+O114i5/CrAONqrpO1BUuFZJFwDYhaM/
Cs3zTra0kkEolk8WLLsbD19mWceq2FoC8cX1JoGmRkmdm4uwqTee7rhbPzMti4OwNN01BVDZ1OdjuWSGaCd
MIlix9FiTm5rETx+ShPs4K60DSyzrxBxuXz6EKhcc7XqFOWfewQYUcufXvvofS//
oOsN46O5GoJBBrBvHza//hP8dWujJ0XDmNtbkAJhQgWFk2aei+ZI1SVqn/5R6ytzUDs/
zC+PaJFKfrtr1BNJgZ23wGqSt6Lz86ZKRowtGot9ovnJj0mgM53/
i8pxCKRSCQScgoyuPWtq+nrHMLj9CGEwFGYQXb+5G3F5hIhBDqdDC5IJDNFOuGSpUM0QvX3/
gFLe0vSodOtGdeEQBcMTt27Ech9aT+Zl85haW0Z46jHfhoH+qn+56/T9Mhnyai7SN6Lz45TxR6uXUnn/
Q8SLJmeWqlk+tgunCGjOXFrvIKnf4PzxlvRu92YBiaqy6YLzWCg9f0fx/
H6yxQ8+xR6nzd+LOzIo+tt78Zzw5Y5u75EIpFIFhdCERSU2Skom0SoUyKRLBqkEy5ZMmSdPoG1tSnpuBmJt
qWQeqwLBbG2TH59oWmgqlT86DuxlmxXHc9orGPZN/
4fgztvIfPSWfReL+HsHJy7duPafpNsL5VGso8ejNV2T9HOC0Dv95F54SzBwpI5sUEDEIKmD38KzWxmYM9dO
G++nYy6C+i8XsI5jpgSqiLT/CQSiUQikUiWGnKFJ1ky5Lz+CloK6ViaXk/
7gx+c9vypOO2Jri80DcMkDjjEUqKVcIjcV57H1NuD3juMuaONkv9+jNqv/
TV6j3va9i54NA0RDqe0wZFODG5XQgccYk6yfshN2OEgak4saBPPeRhxmDWSC64JoO19H8Y3pg2eptczvHo9
7q078S1bIR1wiUQikUgkkiWKjIRLlgwG50BKYlkd73ofru03kvvqC1ham1I6RxBzsJONnY1Y19XO+ejvxoE
+yv/
9ezR98vMznnshoXcNkvfiszhefwVdwI9qMODauou+2+4mVFg859cPZ2UnjYQLIGLLQtMbcN54K3kvPItI4F
r37r0Hg8tJZt1F9B530r7fQ2tvwL1p24zfg0QikSwVRCiE/
ewbGAadMSHKDZuJZmRea7MkEolkTpFOuGTJEM20ofX2JHSWgHjf796730zVD76ZdF5NUQgUFGHp7px6jBBo
Oj0iEp5Rb/JECFUls+Ey5vZWAmUVaZ59fjF1d1Lzrb9H5/
fFnWAlHCbn8KtkH3udpo9+OhYFngQRDJJ18iim/
l5UownPhs0EZ+C0u7bdRPYbRxOOiVitDK9ehwiFEOHQlDLmmhAMrdlAz31/BMDq//
vppA542J5F60MflWr5Eonkusfx6osUPflLdMFALJtIVSn95U/
pv2Uv3W95J+hkyyvJAkRVsZ07hf3syVgXnMJiBnfeTCQr51pbJllESCdcsmQY3HYj1sa6KY9rxKKb3prlAA
ytWoe3upaMpvpx/lXc3xqJfHtrltPypx+n9Jc/
JeuNYxOcfE0INEXH4I6bcBw8MGV69Yxq0ePXULBdOLO4nXBNo+LH3x3ngI8iVBW0MJU//DYX/
+YbaIbxauA5r79C8a8fRwkG0XQ6hKpR9Ntf4Vm3kbb/
9UFUizVlM4ZWr8NbvQxrS9OU0fCee98OCKr+5RtkNFyeNMNBE4L+2++m+74/
Ap0OU08X+uGhhNcWgN7vRzMaU7ZXIpFIliKOV16g9L9/Fv89fj+ORsl76Q/oAn46/
vj918g6iWRyjP29VH3vG5j6e2MbR5pGFl
D4+/+h+83307/3nmttomSRIIsOJUsG15adhB158drcqxFA7z1vje+sF//
mv7A2NcSPjf4ZRTUY8ReXoikKOcdfp+MdD9K3dx+qYbwDFSgpp+kTn8W9biOaopsyDj+ruKcQiEhkNjNccz
LqL2Hu6ZrS8RWaht7nJeuNI+Nezzr2OmX/+W8oI+r0SjSK0GJz2M6dpupf/gmS1HiPQ1Fo/
tCnGF6xGohlOqg6HZoQqDodXW95J86bbyf7yKtk1F+ausRACJRAAHQje5mpliLMcw28RCKRLDREMEjRU7+c
+jjgeP0VTF0d82eURJIEJeCn+ttfwejsB0ZanGrayB+V4id/
Sc7rr1xjKyWLBRkJlywZNJOJxkc+S9X3v4G5t3tkhxJGY9A99/0Rzpv2AKD3uMl99YUpU9cFMbVzS1cHWlc
HmZcvUPD0b2j+6Kfpu/vNZNRdRAkFCRYU/f/t3Xl4U2XaP/
DvOdmatE3SPS2ULoBlpyy2lh0ptMAgKKNWHQXHF0bHZRwcEGYUBtCfjDrq6OvKDwFnUNwBR6gim4ClLFIsp
SCFQindm6bpmiY5z/tH2tDQZitNunB/rqsX5OQ559x5mubJfc6zoLFPP4R/uQXBB/
daxo3D9q53y1jy8ikzEHh4P3iT0e2x45xgRmMPXL6Mb2ywJLImE3zPn3U6FpvxPHzzzkGXMN6yQRAQvv1T6
5rZ1+OYAN/
8PPif+QU1w+JdjktQKHDpsWfgc7UAqqzj4A2NaAoKgW5sknUsYtDBvbDbDx2Wxjfg6GEUz70XTCZDU3AIzH
I5RA0N9l8fx6M+KsblOAkhpDdSZf8M3mBwWIbxPAKOHETJnWleigoQV+sgKysGE0vQEBkNJqavyeSagKM/
QaKrsntThQEI3bUNVQnjaXJV4hR9upBexRgUjPMrXoB/
bjaU2SfBNzXBEKaBNnEiTOprY3WUp467fEey5cNW1NiAmHf+iV//
9v9sEr7gPTsRfHCvpWzzMVv2aenWfuGJZagfEIeaYfGI/
uANwHgtEW9J0u0lmozjYPL1g37YSFeroctxJiM033yJwMP7wBuN1u2u1LhP0RWE7fgcxsBgGP1VkDiZGd7y
Re2QW0l4i8Y+/dDYp/0u/rLSYqfzC/
BGI6RVFTBo+oCJJagcPxUhe3bZvcjCMQGVk5LdjpMQQnoTibbSkqQ46sXEGKRVlV6JR1pRBs22T6E8nWX9/
Db5+qFiygyUJ8+ihIoAANTHf3L4PAdAqquC4tIF1DcPfSTEHkrCSe/
D86gZOhI1Q+0nreK6OoDjAWZ2+bAcY+ANjQg48iPKZ8wBAKgzD0Gz4wv7+8CS6/
ufy0H9gDjUDRyEc8+9hMCfDkCVdQJ8kwGNmgg0BQYj+NBeMHA2iR/jOIDjUPi7/7nW7bm7EwT02/A2/
HOz2ySjzrrkc4IA+ZUC+BQVWu6YuzB5GScIkOg6/4saE4kBs/P3hyC+Nn69bMYc+P2aC/mVSzavveUCi/
a2idCPHNPpsRJCSE9iVvg6H0bEcZZyHiatKEP/f66FqLHB5nNbXFeLsG+/
gqy02NIG02SaNz1Rba1LQwtFdbUej4X0fD3kWz0hncuoUgOC6wm4FWNQnziK8hlzoD6WgciPP3S6C8cEqE4
es8ygzRgkVVpwRiNqBw5CU2gYdGNug9nXD3W3DEbYzq/h02oW9vro/
iiZ89s2M4bLSoog1lfD5OcPQ3gfgOMgqdLCN+8sIAhoiIyGwY3u66JaPfxzcyxd7EPCYJbLIdVWwqxQoD5m
oGtd8gQBYn21pRfCmV/sFrN7xx8t4/IZuJbk14XeCozjYPJTOo/
PTTXD4qHKOma3+zwD0BQSBmNQyLVtMhkuPrkMIXvSEXRor3WiNkOoBhVTZ6AqaTJ9kSOE3PT0I0Yj4ostAH
OwVKQgQDcqweOxhH/
1iSUBb+ezngMQcDwDujGJqB0ywuOxkO7NGBAIqbbC6ZBCozrQSxGRnoyScHJTqo4fi4gvtoAzGZ0XboWDZZ
wzZzIh/OtP7CaU1+Pr6xHxyUYEHM8AbzKBAdbx0Zptn6Fk3j2onJQM/
YjRkJUUQVRXC5M6AE3BoTbH8TubA803n0NeWGDd1hiqgVmugOK6Nc/rovvj6v2/
d7iMF2c0IvyrjxF45CA4QWj39Zh8/VA2/TeonDK9/QTSbELw/
t0I+vEHSHVVAOwn2ujAdmc4xqBLGNf2CcbANxnAAPjnnkbAkYOQ6rQw+SlRlTAO1aMSbGdhFwSIa2vARCKY
ff1QMWU6VCeP2h+PDqB82sw2dcKkMpTNnIuyGb+BuKYa4EUw+Ssp+SaEkGYmpQracZMR+NP+9lef4Hk0REa
jrnkCTU8R67TwP/OLw6SK8TyCDu2jJJyg6rZJ8Ms7Z/
d5xnEwhIX37JVsiNdQEk5uSoJcgbLUO6D575du7cc4HobQMPjlZkPsYncjBg7iuhpLotu8jcO15Vg4swkRX
34Ms8wHusQJljvb7VCeOoF+G99ps11WVtJukqgoyEfs6y8i7y8rYbwumQcArqkJURv+F37nctqMZW9NXFeL
iG1bIdHrUDL3HtsnzSZEf/Am/M7l2Ny1diXdbLkIcUNLt/
E8DCFh0I+41sWbNzQi6MBuBB3cB4leZ02irWPvuSL4nc9F6Pf/xcUnlkKQKxC8Nx1Bh/
ZZ71w39OmH8ttTcTVtIfps3WTZt/n31RJ3xeTpqLptov3gRCKY6Go4IYS0q/iu+8A3NiDgxBHrGuFo/
nxt6BuFS4v/
5PGLlz4lxU7vanKCAJ+rBQ7L8I0NkOi0ECQyGAOD6KJrL1U96lYE7f8e8qIrbXpOtLyLiufdS79/4hJKwsl
Nqzx5FgAgNH07OJMZTMRbu0HbvVvLBGjHT4W0qtKa1DnDwf6kay0YAM1/
v4Tu1nHtTgDDNTWh78cfAoy1OY7dWAUBIkMjwnZtR+GDi5pPxKDMOo7g/d/
D99IFp7G3FrI3HVWJE2DQRFi3Bf241yaJd0f+o0vQFKpBxCcboTyX47Cs9ejNY+QBy+trjOiLS4uftnaX5+
vrEfvWOvgUX7VeFLBe+Gh53PyvtLIc0e+9DnA8fIoLbV6DT9EV9Pv3Byi/
PRXnn12DoIN74Z+bDQgC6qNioJ04DXUD4qihJYSQDmJiMQofWoyK21MQkHkIkiotzApfVI9OtCwh6YXJ0AQ
XZz9nreb+aE2s0yJs5zaoj2eAb/7+0KiJQNn036B67G2dFmdvI9ZXQ9RQD6O/CoJC0dXhuIyJxch//C+I/
OgDKHOzm+ft4cEJZph9/
XD13gWoHTy8q8MkPYTHkvAXX3wR3377LbKysiCVSqHT6ZzuwxjDqlWrsH79euh0OowfPx7vvvsuBg6kGQaJ
B3AcyqfPRuX4qVBlHYNEpwVvMFiWphLMbRJLxnGoGxAH/fBRUP+c6VLi6epdXg6ARF8N37xz7Xa/
U506DlGj/aWv7B5XEKD++SiK5t8P34vnEfHFFssFBLePZLkDHJjxI4pblothDMEHdndo3WuTrx/
qBtwCiMTWNb8d4QBUJk6AMTgEsvIyCDIZqkeMQd3AQTaJcPj2T+FTUuTaxRFBsCxBd91keMC1RD1kbzpqBg
1D0T0PuvcCCSGEuKSxbxSK+0Z1ybkbomJh9pE7bF8Zz0M/YnSb7ZLKCvR/
7QWI62tt7orKSorR798foLS8FGUz53ok7p7K72wOQr/
bAd+L5wFY6rZ65FiUzZzrcOhch7R8D+jki+WCwheXH/
0zZKXF8M85Bd7YhMawCNQMi6cl7YhbPPZuaWpqwt13342kpCRs2LDBpX1efvllvPnmm9i8eTNiYmLw/
PPPIyUlBWfOnIGPj4+nQiU3OUGhQNW4ydbH1aNuRd9PNtpMkMZ4HlUJE1A0/
z5AJIJ+6EgIYjF4k8nhsRkvAu/GBHDiGstyXJzRCOWpE/C9eB5ifRXEer3TNbbt4QQzIr7YgoATR65tc/
solqRVVlIECAL4xgbwTU0dWj6GoXksdfNs76KaGpf28SkrQfnMeZal5xobIK6tAWcyWcd1i+pqoT72k1t1Z
Omh4GQs4ME9qIsb4vIxCSGE9AxMIkHF5GSEfvffdtsCBssF+MrxU9o81+ezj9ok4MC1NiUsfTv0w0fR+OBm
6qOH0XfLBpukmBMEqE4dh/+ZU7j41HI03ujFGMagPHUCwQd2Q3HpAgAOdTH9UTl5uuVCSicm5Iaw8M6/
cEBuKh5LwlevXg0A2LRpk0vlGWN444038Nxzz2HuXMuVw48++ghhYWHYtm0b0tLSPBUqITYaovvj/PK1kF+
+CJ+SIghiCWrjhsDsf20GbkHhi8pJyQjem253bW9DSJglSXUjCTcpVVCePIa+WzdZr8y7OvmbI60T8I5iAK
TlpRjy1ychamhw+256y0UE7bjJqJiaYt3uU1bidF8OgOLSBcStXtq8wTJG2yyXo+iu+6FLGA/
5lcvW7oCucmXJNN8Lv7p1TEIIIT1HWcodkJUUQX3qhM3FbsbzYByHgof/
2GZeFUllOfzOnnY8zIznEXh4H4ruXeDB6HsGsb4afT/
ZBABtly4VBPBGIyI3f4Dzf32h44kyY4j49CMEZRywGS7oezEPfhd+RcXEaSiefz8NIyPdRrfpN5Gfn4+Skh
IkJydbt6lUKiQmJiIjI4OScOJdHIeG6P5oiO5vt0jJnN9CVF+HwCMH20wq06iJQOmseYja8LZLSTQDYFKqw
Tca0G/Tu7ah3MDLYLCMZePMpg6N274+Dmlluc3kcs6627c8L0hlaIiMQunsu1AfO9C2EXTxBdrE3/x/
vqEBkVs2gG9shNzJxDkdRg02IYT0XiIRrix8DLqcUwg6tBc+RYVgYgmqR4yGduLtbVYpAQB5YYFLF3EV+e7
NvdJbBWQeApjgcA4bn7JiKC6eb7Mkq2UG+2zwTU0waMJRe8uQducLUB/
7CUEZByzHaz1RbPOQt+CDe1Af0x/
VY2isPukeuk0SXlJiuRsWFhZmsz0sLMz6XHsMBgMMBoP1sV6v90yAhFyP53H1vodROSnZsvyVtgJmuRzV8b
eiZtAwxK19FoBrOSYHoOQ3d0Hzzecu79Oao2W03F2GzZH2JoVzlNq3lOebDPC78CuEvekoiIq1GTdVFzMQf
udzO9ZFvvn8EV9uATjO7V4DTifM43nUDhzUgcgIIYR0J7KSqwg8fADywstgYjFqhoxAVcJ4mH39AJ5HzfBR
qBk+yqVjMVcnjfPC5HI9gbzgktP5YxjHQVGQb03CeUMjIj7dDPXPRy37Nt/dblIH4up9C1E7aJjN/
sH7vnM4YS7jOATv+56ScNJtuPXpsHz5cnAc5/
Dn7Nmznoq1XS+99BJUKpX1JzIy0qvnJ6SxTySK59+Py4ueQuHvFqFmWDz8z+VAqqtyOiM6AyCIRLj62wfQG
BEJn9Ji15b3uu4Ybf7P82AASlPv6MhLcourFxkAwP90FsJ2fm3zXOWU6Td0t59r+Wln5nhn6mJvscxuau/
YgoDKScl2nyeEENLNMYbQXdtxy0vPI+jQXvhePA/fX3Oh2f4Z4lYvg6+DdZ/
tqY8ZACYSOT4tx6PGwzNly4qvImzH5+i7ZQM02z+DrKjQo+frKMZzLvUqY1xzWmI2I+q9N6D+
+Zi1bW9JriXVVYh+7w34ns+17sc31ENeVOiwxx/HGBRXLoFrMtgtQ4g3uXUn/
JlnnsHChQsdlomNje1QIBqNBgBQWlqK8PBrEx2UlpYiPj7e7n4rVqzAkiVLrI/
1ej0l4qTLya9cdmkitcaISFx88lkICgX8T2e5fHwOgEnhC5NKjarECageOhLqUyfgdzYHnGBGfVQstOOmoC
k4BIGH90NS47yHSGeMPXcl7qADP6A05Q4wmQwAUDN0JCpvm4SgIz96+OzXMACN4X1w6bEliHnnVcsELq2S+
JbfXcmsO9t0jSOEENJzBGQeQlj6dgCwtskcADAGvsmA6Pdfx68rXoAxMNjlY5r9/
FE1NgkBR39qd4UP1nwS7fjJbZ7rDJzJiD5bPkTAz5k2d+VD9qZDFz8WhQ/
8D5hU6vZxfa5cgurkMYgaG9AUFALdreNgUqpuLFhBQH10f6iyjjssxjFmWZoOgDL7JPwutj8fC8cYGAeEf/
0p8pb93bLNjQlZOUHo0AoxhHQ2t5LwkJAQhISEeCSQmJgYaDQa7Nmzx5p06/
V6ZGZm4rHHHrO7n0wmg6z5yzwh3YVLXdV4Hg2RUdY1Mk1+/m6dI2/
ZahgDAq2Py6fPRvn02W3KaSfejtBd2+130Wr+tyk4FNKKMuu4dgAur4XuDt5khO/
F86gdPAycyYTwrz62jKtvft4bI7A5AMV33gcmlSL/8aUIOrQXQT/
+AKnWMtt7XexAVExNQc2weC9EQwghxCMEAaHffWN/yBZjgMmEoEP7UHLH3W4duviu++BTVAj5lUuWY11/
bEFAQOYhlM2c14HAHYvYuhnqk0et52lNdeoEwPO4suBRl4/H19ej38Z34P/rmebvLxzABGi+
+RJlKXNQlnqH2/OjiGr1CN77HQJ/
OgBxQ721t167k9nyPOpiBsAQ0RcAEPjTATCOt7uEKccY5FcL4HO1AI19+sGs8EVTQCAkVVoHc9RwaAoOhiC
j1ZZI9+CxwSoFBQXIyspCQUEBzGYzsrKykJWVhdraWmuZQYMG4euvLV1TOY7D008/
jRdeeAE7duxAdnY2HnroIURERGDevHmeCpMQj6iNG+L0yiwnCDZrgjf0i0FTQJDTK7QMQH1ktE0C7kj51BQ
0REZf6+Z1/fFEYpTOuhNX734Q5dNnoy4qBmaZDwSJBA2R0aiLGeDSedzRMk6973/+PwJ/
OgAOzNqtvDO17qIPXLs4Upo617rsGJNIUDE1BedWvozTr7yL7Nc+QP6Tz1ICTgghPZyspAhSbYXDtoUTBKh
+znT72IKPHMXz7mn/mM3/
hqXv6NCxHZFWlCHg2E92L5BzjEH981HISotdO6AgIPqD1+GXZxlOygkCOMFs6QbOBISlb0fw3nS3YhTrtBj
wyhqE7PsO4oZ6y3Gbn7Npk2G52G9UBeDKQ4uvvcbKcrsJeGuS5gvn4DjL0DGHFwqYC2UI8R6PTcy2cuVKbN
682fp41CjLZBf79u3DlClTAADnzp1DdXW1tcyyZctQV1eHxYsXQ6fTYcKECUhPT6c1wkmP09AvBvWR0ZBfL
Wg3GWccB5OvP6rjx17byPMonX0XIv+z3uGxOQBlKXNcjoVJZbj4xDKEpW9H4E8HrEufmeQKVCWMR03cYPT5
6hNoWo3VFkQiaMdNQcmc32Lwc0+7fC5XGUI1kBfkW6/kewzHwSxXQFRfB/
A8agcMQsXUGagdMqLdskxKvWoIIaS3EBkaXSrHGzo2Tjjo4F6b3mPXYxyHkN3fonpUQqclf6qfMy0Tvjm40
M94HqoTmSibNc/p8fzO5cDXySzuod99g8qJt7vcRvbdsgESva6dNdRbXRznOBhVamjHT4F2/
FTLBHnNzHKFS0PkBLnC+v/KScnwP/MLfPPO2VygaDlXbdwQVE6Y6lL8hHiDx5LwTZs2OV0jnF2/
ViDHYc2aNVizZo2nwiLEOzgOBb//I2L/tQ6S6qo2440FqQyX//
AnMLHEZjfdrUkQ1dcifNunNg1s61nIi+feY71LyzfUI+BYBpSnToBvakSjpg+qxk1GfXR/
mwafyWQomXsPSmfdCVlZCRjHoSlUA8XF84h555/
AdfffebMZQYf2QlpRClEnTmLCAAgSKZrCwhHx+b9dGjdv7zhwoas8xxgu/
eFpNPSLsdQHXQEnhJCbRlNgkPNVMDgOTUEdGGrJGJSnsxy2YRxjkBcVQqzXwaQKcP8c7RDX1lqGijkKjeMg
rq1x6XjqYxlO22KRoRHKnFOWiwlOSMtK4P9rrt3nueb4ylLnWrq5t0M35jbICy87nFHd5Odv01OPicW49Oi
fEbwnHcE//mB9/
UwkgiDzgaihAYEZB6G7NYm6pJNuodssUUZIb2MMDEbesr8j8PA+BP70I8R6HcwKX+huHYfKidNgDAxqd7/
KydOhG5OIwEP7ocw5BXGNHozjwBubIKnRI2L7Zwg6tA/
6EaMRkHnIcpcXloZNXliAwKOHoU2cgKtpC9ssj8IkEjT2aZ64kDFEfPEfAKzdZJZjDMrc050+YVvllBkAAE
mV1uGVfHsYx6EudiAaovuDazIg+OBeu+VqBg9HQ1QsJd+EEHITMqkCUDNkOPzP5thPMhmDtiN3SBkDbzK5V
JQ3dt5SoUaV2oXhbgxGtdql40lqqp0ej4GDuMa1pN734nmnZTjGHM5KX5U4ASE/
7IS4vtZubGUpc4DrZqhnYgnKU+ZAmzQJsf/7smXFGUGAuL4Oosv5kF++iJAfduLik8/
CGOT6RHyEeAIl4YR4kNnXD+Uz5qB8huvdxwHA7KdEeeodKE+Zg/
AvP0bwwT02S2lJK8sRvO87ALYJcktjFZB5CMbAYLtXmQFAXpAPHydjxhjPw+TnD3Ftjf3udq1iaJ3KX5/2W
sayR6Es1VIXLWuzOuxSB8tVbI4xmGU+0I8cg9JZ867dURAECDI5QvbsAsAsV/MZAycI0A8fhSu/
W0QJOCGE3MRK5twN37xfwRuNbcYZM45HQ79o6MZ2YO1onoeheUJTR62MIJHCqFS7f3zGIC/
It6x6YjahsU8/6IeNhG7sbdB884WznaEbm+TSaYwqtdM74RwYjDc6S3ob9u9yCwoF8p9Yiph3/wlJtc7y/
Ycxa9f/sumzUTlxmt39I/+9HrLyUkvszTcZOLRa4uz913F+
+Vpax510KUrCCenGlNknEXxwDwDY3K12llZyAIL3pqNJFYCA4z9Bqq2EydcXurHjUJU4HoJcYZkJ3dlxBAG
CVAYwfbt3xFuvUc4BMKnU0CZMgKS6CuoTR8CbzQAAs1QG7YSpKJ05z9oFXzc6AQFHDzs8PxOJcHbt6zZjxW
zwPErnzEflpGlQH8+ApEoLs8IX1aMTYNBEOH19hBBCejdDRF9c/NNy9P14I+RXC6zbGcdDNyYBRXc/
2GZomKsqJ96O8K8/
hb2EkvE8qm6b4PZyYZIqLfp9+DYUBfnW2co5wQyjvxKFv1uEiqkpCN6b3v5M4wAqJ9zu8pJrVbeOQ8CxDId
lzD5y1LQ3l0o76qP7Oy1j6dHmePlPQ3gfnHv+H1BlHYf/6ZPgm5pg0ERAmzQZTaFhdvfzuXoF/
r+esfs8JwjwKS2G37kc1Hp4HXdCHKEknJBuLOjA7g6PmxYZGhG5daN1mTGJtgLyK5cRsncXLj6xDIKP3Okx
GCxXyUt/cxf6/
nu95a51y8UAjgMTiXDlwcXQDx8FzmwGk0isd56L77wPPsWFlqXY+kS2mdClNm6o48nrYJloxW4C3opJpUbF
tJlOyxFC3PPiiy/i22+/RVZWFqRSKXQ6ndN9GGNYtWoV1q9fD51Oh/Hjx+Pdd9/
FwIEDrWW0Wi2efPJJfPPNN+B5HvPnz8e//
vUv+Pk5/3snxF2NfaOQt+zv8LlyCfKrV8BEYtTeMhgmlfqGjqsdNwXqE0cgv1LQ9i47z8OoVKPMzZ5wfH09
Yt9cB4lOC8B2CTJxbQ2i338DF59YCnCcpUccY62+J3ConDQNxfPudfl8dbcMQe2AOPheOG93RvLSWfNcvpB
g0ERYjnfxvN22HRwH7bhJTo/FJBLobk2C7lbX7uoDgH/
OKaffmxjPQ5mdRUk46VKUhBPSjSny8zqUgLd2rSuWhbhGj+j3XsP5pX+HWebjdPbY6lEJqB6VgNoBgxB45C
AUzeO96vrfgqrbJsD