Deep Q-Learning Agent Implementation
Deep Q-Learning Agent Implementation
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "[Link]
},
"id": "mYu0OlZ6sK7d",
"outputId": "517a3634-ac29-4c49-ee12-733eeff0e75f"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Requirement already satisfied: gymnasium in
/usr/local/lib/python3.12/dist-packages (1.2.1)\n",
"Requirement already satisfied: numpy>=1.21.0 in
/usr/local/lib/python3.12/dist-packages (from gymnasium) (2.0.2)\n",
"Requirement already satisfied: cloudpickle>=1.2.0 in
/usr/local/lib/python3.12/dist-packages (from gymnasium) (3.1.1)\n",
"Requirement already satisfied: typing-extensions>=4.3.0 in
/usr/local/lib/python3.12/dist-packages (from gymnasium) (4.15.0)\n",
"Requirement already satisfied: farama-notifications>=0.0.1 in
/usr/local/lib/python3.12/dist-packages (from gymnasium) (0.0.4)\n"
]
}
],
"source": [
"!pip install gymnasium"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"id": "VpsHzyWmseVk"
},
"outputs": [],
"source": [
"import gymnasium as gym\n",
"import numpy as np\n",
"import pandas as pd\n",
"import [Link] as plt\n",
"from collections import deque\n",
"import random\n",
"from tqdm import tqdm\n",
"\n",
"import torch\n",
"from torch import nn\n",
"import [Link] as F\n",
"import [Link] as optim\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"id": "cQJgkAMMsEoK"
},
"outputs": [],
"source": [
"device = [Link](\"cuda:0\" if [Link].is_available()
else \"cpu\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"id": "jQk7LBu5s3yo"
},
"outputs": [],
"source": [
"# Define model\n",
"class QNetwork([Link]):\n",
"\n",
" def __init__(self, state_shape, h1_nodes, action_space_size, seed):\
n",
" \"\"\" state_shape (int): Dimension of each state\n",
" h1_nodes (int): Number of nodes in first hidden layer\n",
" action_space_size (int): Dimension of each action\n",
" seed (int): Random seed\n",
" \"\"\"\n",
" super(QNetwork, self).__init__()\n",
" [Link] = torch.manual_seed(seed)\n",
" self.fc1 = [Link](state_shape, h1_nodes)\n",
" self.fc2 = [Link](h1_nodes,h1_nodes)\n",
" [Link] = [Link](h1_nodes, action_space_size)\n",
"\n",
" def forward(self, state):\n",
" \"\"\"Build a network that maps state -> action values.\"\"\"\n",
" x = self.fc1(state)\n",
" x = [Link](x)\n",
" x = self.fc2(x)\n",
" x = [Link](x)\n",
" x=[Link](x)\n",
" return x"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"id": "W2a1w61qtpWV"
},
"outputs": [],
"source": [
"# Define memory for Experience Replay\n",
"class ReplayMemory():\n",
" def __init__(self, maxlen, batch_size):\n",
" [Link] = deque([], maxlen=maxlen)\n",
" self.batch_size = batch_size\n",
"\n",
" def append(self, experience):\n",
" [Link](experience)\n",
"\n",
" def sample(self):\n",
" return [Link]([Link], self.batch_size)\n",
"\n",
" def __len__(self):\n",
" return len([Link])"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"id": "YbRg16A-uGjZ"
},
"outputs": [],
"source": [
"#Define the Deep QLearning Agent\n",
"class DQAgent():\n",
" \"\"\"Interacts with and learns from the environment.\"\"\"\n",
"\n",
" def __init__(self, state_shape, action_space_size, seed,
h1_nodes=64, learning_rate=5e-4, replay_memory_size=int(1e5),batch_size=64,
UPDATE_EVERY=1000, LEARN_EVERY=4,GAMMA=0.99):\n",
" \"\"\"Initialize an Agent object. \"\"\"\n",
"\n",
" self.state_shape = state_shape\n",
" self.action_space_size = action_space_size\n",
" [Link] = [Link](seed)\n",
" [Link] = GAMMA\n",
" self.UPDATE_EVERY = UPDATE_EVERY\n",
" self.LERN_EVERY = LEARN_EVERY\n",
" self.h1_nodes = h1_nodes\n",
" self.learning_rate = learning_rate\n",
" self.batch_size = batch_size\n",
" self.replay_memory_size = replay_memory_size\n",
"\n",
"\n",
" # Q-Network\n",
" self.local_dqn = QNetwork(self.state_shape, self.h1_nodes,
self.action_space_size, seed).to(device)\n",
" self.target_dqn = QNetwork(self.state_shape, self.h1_nodes,
self.action_space_size, seed).to(device)\n",
"\n",
" [Link] = [Link](self.local_dqn.parameters(),
lr=self.learning_rate)\n",
"\n",
" # Replay memory\n",
" [Link] =
ReplayMemory( self.replay_memory_size,self.batch_size)\n",
"\n",
" # Initialize time step (for learn every LEARN_EVERY steps)\n",
" self.l_step = 0\n",
"\n",
" # Initialize time step (for updating every UPDATE_EVERY steps)\
n",
" self.t_step = 0\n",
"\n",
" def state_to_dqn_input(self, state)->[Link]:\n",
" return torch.from_numpy(state).float().unsqueeze(0).to(device)\
n",
"\n",
" #Returns actions for given state\n",
" #Epsilon-greedy action selection\n",
" def act(self, state, eps=0.):\n",
" if [Link]() > eps:\n",
" action_values =
self.local_dqn(self.state_to_dqn_input(state))\n",
" return [Link](action_values.cpu().[Link]())\n",
"\n",
" else:\n",
" return [Link]([Link](self.action_space_size))\n",
"\n",
" def step(self, state, action, reward, next_state, done):\n",
" # Save experience in replay memory\n",
" [Link]((state, action, reward, next_state, done))\
n",
"\n",
" # If enough samples are available in memory, get random subset
and learn\n",
" self.l_step = (self.l_step + 1) % self.LERN_EVERY\n",
" if self.l_step == 0 and len([Link]) > self.batch_size:\n",
" experiences = [Link]()\n",
" [Link](experiences)\n",
"\n",
" # Copy local network to target network every UPDATE_EVERY time
steps\n",
" self.t_step = (self.t_step + 1) % self.UPDATE_EVERY\n",
" if self.t_step == 0:\n",
"
self.target_dqn.load_state_dict(self.local_dqn.state_dict())\n",
"\n",
" def learn(self, experiences):\n",
" q_target_list = []\n",
" q_expected_list = []\n",
" # Obtain random minibatch of tuples from ReplayMemory\n",
" for state, action, reward, next_state, done in experiences:\n",
" # Convert state and next_state to tensors only if they are
not already tensors\n",
"\n",
" state = self.state_to_dqn_input(state)\n",
" next_state = self.state_to_dqn_input(next_state)\n",
" action=
torch.from_numpy([Link]([action])).long().unsqueeze(0).to(device)\n",
" reward =
torch.from_numpy([Link]([reward])).float().unsqueeze(0).to(device)\n",
" ## Compute and minimize the loss\n",
"\n",
" ### Extract next maximum estimated value from target network
using the local network to select the action\n",
" if(done):\n",
" q_target = reward\n",
" else:\n",
" next_state_action = self.local_dqn(next_state).argmax(1)\
n",
" q_target= reward + [Link]
*self.target_dqn(next_state).gather(1,next_state_action.unsqueeze(-1))\n",
"\n",
" ### Calculate expected value from local network\n",
" q_local = self.local_dqn(state).gather(1, action)\n",
"\n",
" q_target_list.append(q_target)\n",
" q_expected_list.append(q_local)\n",
"\n",
" ### Loss calculation (we used Mean squared error)\n",
" loss = F.mse_loss([Link](q_expected_list),
[Link](q_target_list))\n",
" [Link].zero_grad()\n",
" [Link]()\n",
" [Link]()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"id": "VuWb1rptzDoP"
},
"outputs": [],
"source": [
"def dqn_train(agent, n_episodes=500, max_t=500, eps_start=1.0,
eps_end=0.01, eps_decay=0.995):\n",
"\n",
" scores = [] # list containing scores from each
episode\n",
" scores_window = deque(maxlen=100) # last 100 scores\n",
" eps = eps_start # initialize epsilon\n",
"\n",
" for i_episode in tqdm(range(1, n_episodes+1)):\n",
" state = [Link]()[0]\n",
"\n",
" score = 0\n",
" for t in range(max_t):\n",
" # select an action\n",
" action = [Link](state, eps)\n",
"\n",
" #apply the selected action\n",
" next_state, reward, done, _,_=[Link](action)\n",
"\n",
" # store the current experience\n",
" [Link](state, action, reward, next_state, done)\n",
"\n",
" state = next_state\n",
" score += reward\n",
" if done:\n",
" break\n",
"\n",
" scores_window.append(score) # save most recent score\n",
" [Link](score) # save most recent score\n",
" eps = max(eps_end, eps_decay*eps) # decrease epsilon\n",
"\n",
" if i_episode % 50 == 0:\n",
" print('\\rEpisode {}\\tAverage Score:
{:.2f}'.format(i_episode, [Link](scores_window)))\n",
"\n",
" [Link](agent.local_dqn.state_dict(), '[Link]')\n",
" return scores"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"colab": {
"base_uri": "[Link]
},
"id": "dgqM0KQY8474",
"outputId": "0addd24c-0e38-47cb-9d28-e3a75c46982c"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"(array([-0.0295206 , -0.03779708, 0.04963383, 0.01742936],
dtype=float32), {})\n",
"State shape: 4\n",
"Number of actions: 2\n"
]
}
],
"source": [
"env = [Link]('CartPole-v1')\n",
"print([Link]())\n",
"\n",
"print('State shape: ', env.observation_space.shape[0])\n",
"print('Number of actions: ', env.action_space.n)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"colab": {
"base_uri": "[Link]
},
"id": "GQ53wv7a-fEU",
"outputId": "d628246c-6594-4c71-8d61-cd0f817d3d45"
},
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
" 10%|█ | 51/500 [00:25<02:14, 3.33it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\rEpisode 50\tAverage Score: 19.32\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 20%|██ | 100/500 [00:49<02:49, 2.36it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\rEpisode 100\tAverage Score: 19.78\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 30%|███ | 150/500 [01:18<03:01, 1.93it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\rEpisode 150\tAverage Score: 22.58\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 40%|████ | 200/500 [04:02<24:14, 4.85s/it]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\rEpisode 200\tAverage Score: 82.63\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 50%|█████ | 250/500 [08:25<23:12, 5.57s/it]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\rEpisode 250\tAverage Score: 181.14\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 60%|██████ | 300/500 [13:24<17:13, 5.17s/it]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\rEpisode 300\tAverage Score: 233.25\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 70%|███████ | 350/500 [18:23<13:39, 5.46s/it]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\rEpisode 350\tAverage Score: 245.50\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 80%|████████ | 400/500 [23:06<08:52, 5.32s/it]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\rEpisode 400\tAverage Score: 237.00\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 90%|█████████ | 450/500 [28:01<04:45, 5.70s/it]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\rEpisode 450\tAverage Score: 234.61\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"100%|██████████| 500/500 [32:32<00:00, 3.90s/it]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\rEpisode 500\tAverage Score: 231.86\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
}
],
"source": [
"agent = DQAgent(state_shape=env.observation_space.shape[0],
action_space_size=env.action_space.n, seed=0)\n",
"scores = dqn_train(agent)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"colab": {
"base_uri": "[Link]
"height": 412
},
"id": "u3kPJmXM4Ss4",
"outputId": "c4fc7cf0-bacd-45df-ed5b-f0e67a02574f"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
],
"image/png":
"iVBORw0KGgoAAAANSUhEUgAAAjsAAAGwCAYAAABPSaTdAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIH
ZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+na
QAAxvtJREFUeJzsnXd8FGX+xz+zNT2hJaH33kFpKiigwGHnbIftRCyHeopiO8V64nH2ev4UwYYdOxZEQaX3
3ovUJLT0ZNvM74/NzD4z88zsbEl2Cd/
368WL3SnPPDu72eez3ypIkiSBIAiCIAiinmJL9AQIgiAIgiBqExI7BEEQBEHUa0jsEARBEARRryGxQxAEQR
BEvYbEDkEQBEEQ9RoSOwRBEARB1GtI7BAEQRAEUa9xJHoCyYAoijh06BAyMzMhCEKip0MQBEEQhAUkSUJZW
RmaNWsGm83YfkNiB8ChQ4fQsmXLRE+DIAiCIIgo2L9/
P1q0aGG4n8QOgMzMTADBm5WVlZXg2RAEQRAEYYXS0lK0bNlSWceNILEDKK6rrKwsEjsEQRAEcZIRLgSFApQ
JgiAIgqjXkNghCIIgCKJeQ2KHIAiCIIh6DcXsWEQURXi93kRPgzgFcDqdsNvtiZ4GQRBEvYHEjgW8Xi/
27NkDURQTPRXiFCEnJwf5+flU94kgCCIOkNgJgyRJOHz4MOx2O1q2bGlatIggYkWSJFRWVqKoqAgA0LRp0w
TPiCAI4uSHxE4Y/H4/
Kisr0axZM6SlpSV6OsQpQGpqKgCgqKgIubm55NIiCIKIETJThCEQCAAAXC5XgmdCnErIwtrn8yV4JgRBECc
/
JHYsQrETRF1CnzeCIIj4QWKHIAiCIIh6DYkdgiAIgiDqNSR2CIIgCIKo15DYqcccOXIEt956K1q1agW3243
8/HyMGjUKixYtSvTUCIIgkg5JklDlDSR6GkQtQKnn9Zhx48bB6/
XinXfeQbt27VBYWIj58+fj2LFjtXI9r9dLWWsEQZy03P3pOsxZfRA/
Tx6KDrmZiZ4OEUfIshMhkiSh0utPyD9JkizPs7i4GL///
jv+85//4JxzzkHr1q0xYMAAPPDAA7jwwguVY26+
+Wbk5eUhJSUFPXr0wLfffquM8fnnn6N79+5wu91o06YNnn32WdU12rRpgyeeeALXXnstsrKycNNNNwEA/
vjjD5x11llITU1Fy5Ytcccdd6CiokI577XXXkPHjh2RkpKCvLw8/
PWvf43lLSEIgogLc1YfBAC89fueBM+EiDdk2YmQKl8A3ab+mJBrb358FNJc1t6yjIwMZGRk4Msvv8SgQYPg
drtV+0VRxJgxY1BWVob3338f7du3x+bNm5UCdqtWrcLll1+ORx99FFdccQUWL16Mf/zjH2jUqBGuv/
56ZZxnnnkGU6dOxSOPPAIA2LVrF0aPHo0nn3wSb7/9No4cOYLbbrsNt912G2bOnImVK1fijjvuwHvvvYchQ
4bg+PHj+P333+NzgwiCIAiCA4mdeorD4cCsWbMwceJE/O9//0O/fv0wbNgwXHnllejVqxd+/vlnLF+
+HFu2bEGnTp0AAO3atVPOf+655zBixAg8/PDDAIBOnTph8+bN+O9//6sSO8OHD8fdd9+tPL/
xxhsxfvx43HnnnQCAjh074qWXXsKwYcPw+uuvY9++fUhPT8f555+PzMxMtG7dGn379q39G0IQBGERKnNV/
yCxEyGpTjs2Pz4qYdeOhHHjxmHs2LH4/fffsXTpUnz//
feYPn063nrrLRQVFaFFixaK0NGyZcsWXHTRRaptZ5xxBl544QUEAgHFAnTaaaepjlm3bh3Wr1+PDz74QNkm
SRJEUcSePXtw7rnnonXr1mjXrh1Gjx6N0aNH45JLLqFWHARBEEStQWInQgRBsOxKSgZSUlJw7rnn4txzz8X
DDz+MG2+8EY888gjuueeeuIyfnp6uel5eXo6bb74Zd9xxh+7YVq1aweVyYfXq1ViwYAF++uknTJ06FY8+
+ihWrFiBnJycuMyJIAgiNsi0U9+gAOVTjG7duqGiogK9evXCgQMHsH37du5xXbt21aWoL1q0CJ06dTJtTNm
vXz9s3rwZHTp00P2TM7UcDgdGjhyJ6dOnY/369di7dy9+
+eWX+L1IgiAIgmA4eUwUREQcO3YMl112GW644Qb06tULmZmZWLlyJaZPn46LLroIw4YNw9ChQzFu3Dg899x
z6NChA7Zu3QpBEDB69GjcfffdOP300/HEE0/giiuuwJIlS/DKK6/
gtddeM73ufffdh0GDBuG2227DjTfeiPT0dGzevBnz5s3DK6+8gm+//Ra7d+/
G0KFD0aBBA8ydOxeiKKJz5851dGcIgiCIUw0SO/WUjIwMDBw4EM8//
zx27doFn8+Hli1bYuLEiXjwwQcBBFPL77nnHlx11VWoqKhAhw4d8PTTTwMIWmg+
+eQTTJ06FU888QSaNm2Kxx9/XBWczKNXr15YuHAh/
vWvf+Gss86CJElo3749rrjiCgBATk4O5syZg0cffRTV1dXo2LEjPvzwQ3Tv3r1W7wdBEIRVKEC5/
iFIkRRvqaeUlpYiOzsbJSUlyMrKUu2rrq7Gnj170LZtW6SkpCRohsSpBn3uCKLuaXP/
dwCA8QNb4d+X9EzwbAgrmK3fLBSzQxAEQRBEvYbEDkEQBEEQ9RoSOwRBEARB1GtI7BAEQRAEAwUo1z9I7BA
EQRAEg0BFBesdJHYIgiAIgqjXkNghCIIgCAZyY9U/
SOwQBEEQBFGvIbFDGLJgwQIIgoDi4mIAwKxZs1TNOh999FH06dMnIXMjCIIgCKuQ2KmnXH/
99RAEAYIgwOl0om3btrj33ntRXV0dt2vcc889mD9/
ftzGC8eBAwfgcrnQo0ePOrsmQRCnHuTFqn+Q2KnHjB49GocPH8bu3bvx/PPP44033sAjjzwSt/
EzMjLQqFGjuI0XjlmzZuHyyy9HaWkpli1bVuvX8/l8tX4NgiAIovYhsVOPcbvdyM/
PR8uWLXHxxRdj5MiRmDdvnrLf4/HgjjvuQG5uLlJSUnDmmWdixYoVlsfXurGuv/
56XHzxxXjmmWfQtGlTNGrUCJMmTVKJhsOHD2Ps2LFITU1F27ZtMXv2bLRp0wYvvPCC6bUkScLMmTNxzTXX4
G9/+xtmzJih7HvwwQcxcOBA3Tm9e/fG448/rjx/
66230LVrV6SkpKBLly6qDu579+6FIAj4+OOPMWzYMKSkpOCDDz7AsWPHcNVVV6F58+ZIS0tDz5498eGHH6q
uU1ZWhvHjxyM9PR1NmzbF888/
j7PPPht33nmncozH48E999yD5s2bIz09HQMHDsSCBQvC3GGCIBKBQBHK9Q7qeh4pkgT4KhNzbWda1GkCGzd
uxOLFi9G6dWtl27333ovPP/8c77zzDlq3bo3p06dj1KhR2LlzJxo2bBjVdX799Vc0bdoUv/
76K3bu3IkrrrgCffr0wcSJEwEA1157LY4ePYoFCxbA6XRi8uTJKCoqsjRuZWUlRo4ciebNm2PIkCF4/
vnnkZ6ejvHjx2PatGnYtWsX2rdvDwDYtGkT1q9fj88//
xwA8MEHH2Dq1Kl45ZVX0LdvX6xZswYTJ05Eeno6rrvuOuU6999/P5599ln07dsXKSkpqK6uRv/+/
XHfffchKysL3333Ha655hq0b98eAwYMAABMnjwZixYtwtdff428vDxMnToVq1evVgnB2267DZs3b8ZHH32E
Zs2a4YsvvsDo0aOxYcMGdOzYMap7TRAEQViDxE6k+CqBp5ol5toPHgJc6ZYP//bbb5GRkQG/
3w+PxwObzYZXXnkFAFBRUYHXX38ds2bNwpgxYwAAb775JubNm4cZM2ZgypQpUU2xQYMGeOWVV2C329GlSxe
MHTsW8+fPx8SJE7F161b8/PPPWLFiBU477TQAQWuLlcV+xowZuPLKK2G329GjRw+0a9cOn376Ka6//
np0794dvXv3xuzZs/Hwww8DCIqbgQMHokOHDgCARx55BM8+
+ywuvfRSAEDbtm2xefNmvPHGGyqxc+eddyrHyNxzzz3K49tvvx0//
vgjPvnkEwwYMABlZWV45513MHv2bIwYMQIAMHPmTDRrFvqM7Nu3DzNnzsS+ffuU7ffccw9+
+OEHzJw5E0899VTE95kgCIKwDomdesw555yD119/HRUVFXj++efhcDgwbtw4AMCuXbvg8/
lwxhlnKMc7nU4MGDAAW7Zsifqa3bt3h91uV543bdoUGzZsAABs27YNDocD/fr1U/
Z36NABDRo0MB2zuLgYc+bMwR9//KFsu/rqqzFjxgxcf/
31AIDx48fj7bffxsMPPwxJkvDhhx9i8uTJAILCbteuXZgwYYJiYQIAv9+P7Oxs1bVkESYTCATw1FNP4ZNPP
sHBgwfh9Xrh8XiQlpYGANi9ezd8Pp9i5QGA7OxsdO7cWXm+YcMGBAIBdOrUSTW2x+Op05gngiCIUxUSO5Hi
TAtaWBJ17QhIT09XLBtvv/
02evfujRkzZmDChAm1MTsAQcHEIggCRFGMaczZs2ejurpaFZcjSRJEUcT27dvRqVMnXHXVVbjvvvuwevVqV
FVVYf/+/bjiiisAAOXl5QCClittbA8rzIDgPWP573//
ixdffBEvvPACevbsifT0dNx5553wer2W519eXg673Y5Vq1bprpeRkWF5HKL+4vWLcDkohDJZoJCd+geJnUg
RhIhcScmCzWbDgw8+iMmTJ+Nvf/sb2rdvD5fLhUWLFilxPD6fDytWrFAF1saTzp07w+/
3Y82aNejfvz8AYOfOnThx4oTpeTNmzMDdd9+tWHFk/vGPf+Dtt9/G008/
jRYtWmDYsGH44IMPUFVVhXPPPRe5ubkAgLy8PDRr1gy7d+/
G+PHjI5rzokWLcNFFF+Hqq68GAEVgdevWDQDQrl07OJ1OrFixAq1atQIAlJSUYPv27Rg6dCgAoG/
fvggEAigqKsJZZ50V0fWJ+s+BE5UYOv1XXNqvBZ65rLfpsaIoYc3+E+jeLBspTrvpsQRBhKCfEqcQl112Ge
x2O1599VWkp6fj1ltvxZQpU/
DDDz9g8+bNmDhxIiorK2vN8tOlSxeMHDkSN910E5YvX441a9bgpptuQmpqqmH2w9q1a7F69WrceOON6NGjh
+rfVVddhXfeeQd+vx9A0JX10Ucf4dNPP9WJmsceewzTpk3DSy+9hO3bt2PDhg2YOXMmnnvuOdM5d+zYEfPm
zcPixYuxZcsW3HzzzSgsLFT2Z2Zm4rrrrsOUKVPw66+/
YtOmTZgwYQJsNpvymjp16oTx48fj2muvxZw5c7Bnzx4sX74c06ZNw3fffRfLLSXqAe8s3gtRAj5bdSDssW/
9sRvjXl+CCe9Yz5okCILEzimFw+HAbbfdhunTp6OiogJPP/
00xo0bh2uuuQb9+vXDzp078eOPP4aNoYmFd999F3l5eRg6dCguueQSTJw4EZmZmUhJSeEeP2PGDHTr1g1du
nTR7bvkkktQVFSEuXPnAgD++te/4tixY6isrMTFF1+sOvbGG2/
EW2+9hZkzZ6Jnz54YNmwYZs2ahbZt25rO96GHHkK/fv0watQonH322cjPz9eN/dxzz2Hw4ME4//
zzMXLkSJxxxhlKirvMzJkzce211+Luu+9G586dcfHFF6usQcSpi81m3Wfy3tI/
AQCLdh6rrekQRL1EkCRJSvQkEk1paSmys7NRUlKCrKws1b7q6mrs2bMHbdu2NVyQieg5cOAAWrZsiZ9//
lnJZjrZqaioQPPmzfHss89GbSWjz92pw39+2IrXF+wCAOx9eqzpsWdN/
wX7j1dZOpaInDb3By2tN5zRFlMv6Jbg2RBWMFu/
WShmh6hTfvnlF5SXl6Nnz544fPgw7r33XrRp00aJbzkZWbNmDbZu3YoBAwagpKREKWR40UUXJXhmxMlABIY
doo6gAOX6B4kdok7x+Xx48MEHsXv3bmRmZmLIkCH44IMPdFlcJxvPPPMMtm3bBpfLhf79+
+P3339H48aNEz0t4iTATisrQdQ6JHaIOmXUqFEYNWpUoqcRV/
r27YtVq1YlehrESUokMTsCtaisE+gu1z8oQJkgCCKB2MiyQxC1TtKInaeffhqCIKhqvFRXV2PSpElo1KgRM
jIyMG7cOFXaLxAsxT927FikpaUhNzcXU6ZMUVKR4wnFcRN1CX3eTh0oZocgap+kEDsrVqzAG2+8gV69eqm2
33XXXfjmm2/
w6aefYuHChTh06JCqb1EgEMDYsWPh9XqxePFivPPOO5g1axamTp0at7nJFW8jqZhLELFSWRlsNnuyxzIR4Y
nEjUXUHuwPDDK21T8SHrNTXl6O8ePH480338STTz6pbC8pKcGMGTMwe/
ZsDB8+HECwVknXrl2xdOlSDBo0CD/99BM2b96Mn3/+GXl5eejTpw+eeOIJ3HfffXj00Ufhcrlinp/
D4UBaWhqOHDkCp9MJmy0p9CFRT5EkCZWVlSgqKkJOTo6uvQRR/
yA3VnJAxtT6TcLFzqRJkzB27FiMHDlSJXZWrVoFn8+HkSNHKtu6dOmCVq1aYcmSJRg0aBCWLFmCnj17Ii8v
Tzlm1KhRuPXWW7Fp0yb07duXe02PxwOPx6M8Ly0tNZyfIAho2rQp9uzZgz///
DOWl0oQlsnJyUF+fn6ip0HUAZSNlRywWseoojtx8pJQsfPRRx9h9erVWLFCX/
q8oKAALpcLOTk5qu15eXkoKChQjmGFjrxf3mfEtGnT8Nhjj1mep8vlQseOHcmVRdQJTqeTLDqnEKwbS5IkW
mgThEimnXpNwsTO/v378c9//
hPz5s2r8wqxDzzwACZPnqw8Ly0tRcuWLU3PsdlsVMmWIIi4w4bsBEQJDrux2JFAC3JtQWKnfpOwAJRVq1ah
qKgI/fr1g8PhgMPhwMKFC/HSSy/
B4XAgLy8PXq8XxcXFqvMKCwsV835+fr4uO0t+buYCcLvdyMrKUv0jCIL4Zt0hLNhWVKfXZGN2/
CItuImC1TpkW6t/JEzsjBgxAhs2bMDatWuVf6eddhrGjx+vPHY6nZg/
f75yzrZt27Bv3z4MHjwYADB48GBs2LABRUWhL6d58+YhKysL3bpRXxOCIKxzuKQKt3+4BtfPrNuO4qwbK0B
iJ2GoDDukduodCXNjZWZmokePHqpt6enpaNSokbJ9woQJmDx5Mho2bIisrCzcfvvtGDx4MAYNGgQAOO+889
CtWzdcc801mD59OgoKCvDQQw9h0qRJcLvddf6aCII4eTlWnpiYPDtZdpICchHWbxKejWXG888/
D5vNhnHjxsHj8WDUqFF47bXXlP12ux3ffvstbr31VgwePBjp6em47rrrlEaMBEEQVklUyIagidkhEoOocmO
Raae+kVRiZ8GCBarnKSkpePXVV/
Hqq68antO6dWvMnTu3lmdGEMSpRKKyovwBsc6vSQShAOX6DVXIIwiCgNqNUZcGFnaNJTdW4iCtY41fthZi6
PRfserP44meSkSQ2CEIgtBQl73JWIsCubESB7WLsMYNs1Zi3/FKXP3W8kRPJSJI7BAEcdIyZ/UB/
N9vu+IyFqtv6tayE7oYWXYSB936yKjyBRI9hYhIqpgdgiCISJj8yToAwIiueWjfJCOmsSTV47q07IQeB0SK
2UkUKstOAudB1A5k2SEI4qSntMoX8xjsYleX8RvsdX0BMi8kClZ00rtQ/
yCxQxDESUltxtXUpdhRW3ZomU0U6gB1eh/
qGyR2CIJISiRJwuRP1mL6D1sN9sf5eszjulzsRIrZSQoktR+TqGeQ2CEIIinZdaQCc1YfxGsLdqGaEwwZiL
MgkZLAjUExO4mDFZ2kdeofJHYIgkhK/MzCf+BElW5//
F0+iXFjqCw7FLOTMFRil9xY9Q4SOwRBJCWV3pA1Z/
+JSt1+UVUXJb75M4mK2SE3VuIQExSgTtQNJHYIgkhKKj2M2DnOEzuhx/H4JZ6oX/
YUs5McJKrOElE3kNghCCIpqfD6lcc8sVObmUuJahdBMTuJQx2zRWqnvkFihyCIpKSSETv7eJYdMb5uLFUyT
h1adiSK2UkKyI1VvyGxQxBEUlLBuLH2HecEKKsWp9hXJ1Y81aVlh2J2kgOqrVO/
IbFDEERSwlp2TlR4dfvZxcmqRhBFCT9vLkRhaTVnvNDjum0XQTE7yUCiLHtE3UBihyCIpIS17HgD+lgWNrz
F6q/yL9YcxI3vrsTQ6b/
q9iWuXUToMcXsJA6J6uzUa0jsEASRlLCWHZ9fLwJYN5Zo0SKyYPsRAICHM546u8vqLGMnkpgdMjjUHupsLL
rR9Q0SOwRBJCUVTJ0dD9eyE1qQ4lFNWe0WS1TXc1pkE0WixC5RN5DYIQgiKanwhCw7Xr+oi6NQiROL3h+zW
IxEtQtg44N8YcROnGsnEgzULqJ+Q2KHIIikhI3ZAfTBuwExvpYYMQq3WDxQWXY4FiyibpDIslOvIbFDEERS
wsbsAEHrDgsrTuLixkqQzqBsrORALZjpfahvkNghCCIpYWN2AL3YYY0gcamzk6CYHYlidpICVYAyGdjqHSR
2CIJISio9GstOwMSyE4fFKSmysUjsJAw2doraRdQ/SOwQBJGUVIa17Ejcx9EiJUE2FrWLSByUjVW/
IbFDEERSUqGN2TGx7MTHjRV6XJdrndpCRf6TREFFBes3JHYIgkhKKj0RWHbiIHbi3WvLKuylyI2VOGK17Bw
r9+CBORuwbn9x3OZExA8SOwRxijJz0R6MfuE3FJXp+0QlGq9fVCw5GW6Hso0lmmJ8Zkclrl1EfN1xRHSoLT
uRvw8PfbkRHy7fh4teXRTPaRFxgsQOQZyiPPbNZmwtKMNrv+5K9FR0sAUFG6Q7AQA+UzdW7NeMprFoPIik6
znFktQe6kagkZ+/
vbAsbnMh4g+JHYI4xUnGPkDlNWInxWlDqtMOoPYDlNlwmYR1PaeiggmDLSQZjRtToPLWSQ2JHYI4xXHZk+9
roKw6KHYy3E64HMH5aftjibVaQTnm4SzDzpxidhJHrAHqJHWSm+T7liMIok5xO5Pva0C27GSmOBQxZhazEw
+xo2oXUIeWHYrZSQ5UdXbobah3JN+3HEEQdYrbYU/
0FHTIMTsZbodi2dHG7ARUIiH2awYSFKDMWpHIspM4pBgtOzZyYyU1JHYI4hTH7Ui+r4EyRuw4jSw7tejGqt
NsLFDMTjIgxWgp1GqdumwmS4Qn+b7lCIKodVgrSTKKnfKamJ10t0OZn1mAsuXFyeSweLvFrBJJNhZRe4ixm
nYY3li4C70f+wlbC0pjG4iIG8n3LUcQRK1T7QsV7HPXZDtJkoSPV+zD5kOJ/4Iu9/
gA1MTsGLixxDjHuiSqgm68X0dts2bfCXy19mCipxFXjpR58M7ivcrzWGO2pn2/
FWUeP6Z8uj7GmRHxgsQOQZyCVDFix2EL2t9/33EU932+AX956fdETUuhvKZ6MuvG8ugClNV1cYorvbjzozX
4fceRqK4Zb7eYVRJdQXnl3uOY9MFqFJRYKy55yWuL8c+P1mLVn8dreWZ1x3VvL8f8rUXK82jefl7q+fEKby
zTIuIIiR2COAXx+ELCQf5eLywNLXaJtjDIbqwMNhtLG6DMPBVFCU9/
vxVfrj2Ea2Ysj+qaydD1PBH3fcI7K/
HdhsP4+6wVEZ23taD+FNHbfFhtzYzX+3+03BOfgYiYIbFDEKcgrGVHXmzzs1OUbQdPVNX5nFhkNxabjaWL2
dF0Kd9/
ojKma8a7saj164Yea111dUFJVfBebzkcmfuy2mc8151F5Zi3uTCmeSWSaNxYvFwsrTWSSBwkdgjiFKTKGxI
78mIrMF/Xu4+W1/
WUVJRbSD1XWUQkKWariJgEMTuJqGbdKS9DeezxB0yOVMPGfWkZ+dxCTHx3JZbtPhbT3BLFSRA6RUQIiR2CO
AVhLTvyAsv+mt1ztKLO58QSqqBsXFRQlY0lSjEvUKpsrDpc7dgrJcKN1aZRuvL4l
y1FJkeq8ZiIHZmNSRDsHg3RxeyEHidjVfJTHXpHCOIUpNqnt+ywX/CJFjtKUcEUEzeWKqDYmkAxc0/
Ey7Kz92gFVu61Hryb6Jgd9pL//HgtikqtBSpXWRA7J2+Zvdjq7DTKcIVGonLMSQGJHYI4BVG5IBTLTog/
j8UW/xIrSrsIt3GAsjZlOxDjohJrUTmZs59ZgL/
+bwl2H7HmCmQrKCdC7LCLsdcvYrdFoWsWs6OMHfWsEkus+qRhekjslNZYKYnEQmKHIE5BqriWndA3PBvTkw
hU2ViKZUe9AmmLAMaqE1RCIw6rtNVspWjr7MTLYqAViVaFnlnMzslOdI1AQ6YdB+PGooys5IDEDkGcglR5Q
7/
KRY5lR2tFqWuqa1xWKU57qF2ELvVcHdgb6+KvrdsTK1aFiypmJ4LXEC8jkHYcq1OotpBpdLK6cGJtF8G+7i
NlJHaSARI7BHEKwovZYVddbXxMXSMLBZsgMJYdtSVBbREJLy4+Xbkfv20/arg/
3u0irI7BLoz+QN1bdrSxTmTZid2Nxd5DK7FNRO3jSPQECIKoe3h1dtjg3UTUe2GRFwu7TTAMUGYXaSmMG2t
nURmmfGZeuj/e7SKsioZoRVb8LDvG7kEz6rXYieIcNhibjcM6Wa1b9Q2y7BDEKUg1L/
WctewkWOzIc7EJoTRen8bqwT4NiJJpNtZhC60Q4l3vRrR4C1WWnUhiduIU/
qsTOyZzYOdar8VOjLnnqs8S1RVMCkjsEMQpSLjU8+R0YxlbdgKSZCpQeLu0C5pqjY9HzE40lp2IApQjnZHB
9TVvtdl9ZF2FVrKx4s036w5h3f7iOr+uFVSWHU3BSyLxkBuLIE5B1G6smv+Z/cnixrLZBOMAZVV7B/
NFhbeAS5I6qDTejUCtChcxSstOvKotR+LGYvfVtWVn/
YFi3P7hGgDA3qfH1uq1Yi0qqO6zRmInGSDLDkGcgnCzsZgv5UT39GHdWDVN2TmWGHXKtrn7Rb9Nv8irxVM0
qAWTtXNU9X1qybLz5LebMfqF31Dp1dd8iST1nN1XHUFriXiwy2LdongQVTaWwfnUeiI5ILFDEKcg1dwA5RC
JtuzIC7BNEJRfzNo1Q+/GMh6PF9+iPT4e2VjRuC/YudWWZWfuhsPYWlCGbZzaP/
rUc2tihxXMRsTTqFG3nehjOz/eVkIidkjsEMQpiF9kLTvB/
5MpZkdeIAQhVKxNu2YENBkvphYJzssxtexEOF9lTlF0To+2gnIkc5SH5Ykp09glg3EAa72xTlai6nquClAG
9zGROEjsEMQpCN+KoTa9J6J1ARBcfOUp2VWWHW02VgRuLEvXVc8hGtjTrN6/
aINZpQj0qDyujyNitfO0HKBcx26suiSqmB3msTobi9ROMkBihyBOQdjFnGfZARJn3WHXhqAbK7iMaK0z2td
g6sbirF61EbPDioGoKihHUlQwAuuD/
Pp9nDlpN5nNm72PvoC5wIw3derGivX8OLhEifhCYocgTkF42SLar+TEiZ3QTGxCqOOQdn6qdhFhGoHy1mSz
RT7aNTyaWj1SlJadSOaouLE4sVhawWI2Be01edYddXHGk3Ohj8ayp87GogDlZIPEDkGcgvCsGDrLToKClFV
ixxZaRLQLUEAjEswWKGuWHeb4KBdp1vpkdZFjjwsXoBytq00WctrCjMHrB7c57YLqudk4MpWchrG1ZcioS8
1g5TW88PN2/
OODVYpYZBuBavu2EYmHxA5BnILwYna0C3yixA67NgQtOwL3OG2at6n7hbctjFssGqLpYB5tfEdklp3gwX5O
pLYsGh02W9hxzdL/edvim40lcR/XBlZGf+HnHZi7oQBLdh/
T7Yu2UCRRe5DYIYhTECsxO7xg1rqAFQmq1HPN/
LQLipm44O0zj9mJboHSBk1bgb1UeMtOdC4iecHlNRqVh3RYsexo7xk3y83ytKKmtoPnI3n/
q2TrlkHXc9I6yQGJHYI4BeG5Q3QxO8nixqp5rMvG0gQDm8eaROjGioNlx2rNHJ21xOS8aOcon8ernyQqlh0
5xd967JOV+1obRFKPKBoiGV0+lrU/BlRih9ROMkBihyBOQXiBtNpFLlmysWBo2VG/
BrNFhWfRMFu44xGzwwsG5p6juZTZQs7OKzKxI7ux9CfJotFhD+/
G0goxKxazeMGOWtsCIhoXIQubVUftIpIDEjsEUQ/
ZWVSGz1cdMPyitZItkjDLjsaNZRP47hVtEKhZJhMvVsXMohJtp+qoLDsaYWXersHacUbz4ll2FDeWLbwbS7
uPd2h9cGOFU5Lq+KHg/
2w2lo9TtJNILNQIlCDqISOf+w0A4HTYcGHvZrr93ABlzZdycqSewzD1XFul1mxR4QkPs3YR0a5P7CJsteWG
VliZWnZU1ifrhNxYxpYduyx2LLrRAH6qfDwqUXNRxWjFc2DTS3FR34fgEzaQnrUkJqo4J6GGLDsEUY9Zv7+
Yu533y1RrYUhUfyx5bRCEYAl+waA5lqo3VpgKyrwF53BJlSaQNPY4C/
Y0y2LHxGJlNn4kWT7ymNw6O0rqeXg3lpVqy5FUdo4E9vMZST2iqK4VZnj2PvAsO6xgpZid5IDEDkGcgnCLC
iaZZUd2Xxk1AtUGgZotKjyLxiWvLcYLP+9QnqtOj3J9YufEixPioZ22mdiJZuFkBZ2ZhcuKG8tKMHVtpZ6r
6xHV7mczXMwWrwClwK+QUKeVnwljSOwQRD3G6HuWF7OTfGIn+FxxY5nF2EjmXc8DBovji/
NDYicelh32PJ7A4mGWZaY/ln8t8zmFHptmY1kJUDZx/
fHmFc8KyuqK2XEblktYyw7nNRrWgyK1kxSQ2CGIUxB+UUE1dRWgXO7xc+uShLPsRFLAz0qwcDxiTVgBZtX6
EElvKpHjPgkHOx4/
K61G7FhIPdfOjTfXQC1ZdlSlBhKcjaXOtgpzLImdpCChYuf1119Hr169kJWVhaysLAwePBjff/
+9sr+6uhqTJk1Co0aNkJGRgXHjxqGwsFA1xr59+zB27FikpaUhNzcXU6ZMgd/
vr+uXQhAnFfyiguov5bqw7Kw/UIwej/
yIez5dH5qPqHZjybYdnbsngoBVKy4lVtvxfo0XllZjzb4TpmOoXC0WLTu6mB0zN5LJeVbG9/
EqKCup55FnY3FjdqKMKwqHKg4mzkG/
WhdUuHTxAEcYkxsruUmo2GnRogWefvpprFq1CitXrsTw4cNx0UUXYdOmTQCAu+66C9988w0+/
fRTLFy4EIcOHcKll16qnB8IBDB27Fh4vV4sXrwY77zzDmbNmoWpU6cm6iURRFJh9EXLqxasPdSqGyYWXvt1
FwDg89UHdHOT3Vg2xbJj7sYyw4plhxe0LVPh8WPgU/
NxyWuL8eexCsMxWOuDZcuYVsSZ3Hd2XlbfHVU6vFkFZSVmx9pYvOfabfHUJKwrMt4ZTgY6xRDWaid/
Dg3/1igbKylIaOr5BRdcoHr+73//G6+//
jqWLl2KFi1aYMaMGZg9ezaGDx8OAJg5cya6du2KpUuXYtCgQfjpp5+wefNm/
Pzzz8jLy0OfPn3wxBNP4L777sOjjz4Kl8vFva7H44HH41Gel5aW1t6LJIgkRORZMXQxO/omj/
GG92tYcWPZZDeWnBKtPi4St4ZRzI76unoBCAC/
bi3CDe+sUJ7vPlqB1o3Sw45hvahgBJYdgzmajx96zIvZ0aaemwdImz/
XbounC4ederxdQzZBiCiwmv04yffUSHCT1kkOkiZmJxAI4KOPPkJFRQUGDx6MVatWwefzYeTIkcoxXbp0Qa
tWrbBkyRIAwJIlS9CzZ0/
k5eUpx4waNQqlpaWKdYjHtGnTkJ2drfxr2bJl7b0wgkhCuF3PdannifmW1mVjhTku+Nh8TCsuJaM6Ox+v2K
9a/
EoqfdzzK71+rD9QErqmxVVOH7NjLJKiaRcRLmham3pu3i4ifMyOOq4onmKnFi07WjdWGLsZa9mR32djsUNq
JxlIuNjZsGEDMjIy4Ha7ccstt+CLL75At27dUFBQAJfLhZycHNXxeXl5KCgoAAAUFBSohI68X95nxAMPPIC
SkhLl3/79++P7oggiyVHFVUj6bUDdBChzLTtKzI76GLOO2+FcBZEGKLPjeTQWrhOVXu75415fgge/
2KA8j77OTvD/tfuL8cGyP01qAVkaXh00bVJB2W7FjaXZyRMz7KZ4ihL2PYy/2FF/
EMMNz2sLYnQOiZ3kIOEVlDt37oy1a9eipKQEn332Ga677josXLiwVq/pdrvhdrtr9RoEkcxYidnxRBCg/
N36w/h+42FM/
2svpLli+1oRNYuvnNKrnZ+2EagZVhZHo3gY2RqS6XagzOPHCQPLzpbDand4tHV2ZKvBxa8uAgDkZ6VgRNc8
3byspnWr69Poz5FdQg6bnHpu3Y0VLhsrnppEW0QyntgiDFDmWXastGYhEkfCLTsulwsdOnRA//
79MW3aNPTu3Rsvvvgi8vPz4fV6UVxcrDq+sLAQ+fn5AID8/Hxddpb8XD6GIAg9/
Eag6mMiqaA8afZqfLv+MN7+Y0/c5iZoU8+1C62kP8cIK6+FVygOCGWlNckK/kAqNrDsRHNNgFc/SL1/
R1E591irtWbCtbAIubHCW3b0FZT1x8SjXhEPXlXigChhz1HjgHGraGvkhJs1L+jb2LITy8yIeJFwsaNFFEV
4PB70798fTqcT8+fPV/Zt27YN+/btw+DBgwEAgwcPxoYNG1BUVKQcM2/
ePGRlZaFbt251PneCSDaMfv1z3ViaY6NJPT9ewbd6GMErxCYvqLpf25BwvMKLj1fs49Tmid2yYxSgLLvz8j
JTAMDQsqPFasyTdmpm9XnU1ierliP9wszuU7KxLMTsmLkSecfEMxOJZ8m746M1OOeZBfhkRWyhCNrPWrhby
wovOZ3/VIjZOZk7uCfUjfXAAw9gzJgxaNWqFcrKyjB79mwsWLAAP/
74I7KzszFhwgRMnjwZDRs2RFZWFm6//
XYMHjwYgwYNAgCcd9556NatG6655hpMnz4dBQUFeOihhzBp0iRyUxGECfG27MjI1oFYkOchByjL/
0sSMOGdFVizrxgr956IyI1lLfWc/
1i+D7mMZccXEPH4N5txRofGGN2Db0W2WlQwXNdztTCVuNvNULWw0MyJvS3Wup5rn+uPrb1srNBYUz5bj39f
3APfrT8MAHhtwU5cfnr0iSbamJ1ws+YVajS07NQj04727ZQkSXfvkpWEWnaKiopw7bXXonPnzhgxYgRWrFi
BH3/8Eeeeey4A4Pnnn8f555+PcePGYejQocjPz8ecOXOU8+12O7799lvY7XYMHjwYV199Na699lo8/
vjjiXpJBHFSwMvq0X4lR2PZsel+IoeBm3ouW3bUbixRAtbsKwYAzN1wmNuMUebrdYdwzjMLlDgaK2ngRu4X
RexkymLHh4+W78N7S//ELe+vMhzPelFB8/
NYMaSK2bG4hqpTz42FlZUAZa144WZjRSHItBwp8+isCKxg3VlUjiv+b2noOtFdRkFn2InAUhg+ZiemqSUV2
pdyMhl6EmrZmTFjhun+lJQUvPrqq3j11VcNj2ndujXmzp0b76kRRL3A6MtIvYBK3IOjETuOCMUO72hF7NT8
FAv9cAzNL9XlULeL0Mz9jg/
XAACmfLYO395+VkztIuT7kKu4sbzYdSR8nAivWjEP7SJpXmcn9NhyBWWTmB120VZidkzr7BhbnULXi3yOLB
8s+xP/+mIj/
jmiI+46txN3ruHmFTGaD2LYdhGcDLdTwY3FKyppi7gkY2JIupgdgiBqH9WCVPNY+5UcjQvCHqllh4O+zo6+
XUS6287t76VFFipWYnaMAp5la0jIjeVDhSd8SxqfPzLLTriiflpR9Pi3m3G03MM9Vj2+WcxO6LHdihvLQm+
sSHqW8fjXFxsBqJu0AtZFYFRo3TMRdD1X6uwYaNt6pHV0r+VkslqR2CGIUxBecG88vsgituxw/P3K4m/
SCDTN5bDUBdvlCH7FWQkWNmoXIQcoN6lxY5V7/
CiuCh+kbDlmR0n95osdeS7a92PVnydwz6frwo6vcmNp5sQKiFDqubWxgs/
NxU48P0NW22hEgxWLlWounJgdo1OS0bIzbe4WTJi1IuJ4It19imNX+9qGxA5BnIKorSLB/
61k2oTDbov9K0X+ApZFjrz0sfNJc9lVz41qArlqMoxiaRchW4caZ7iVOR08URV2vEizsUJztWbZAYB1+4t1
2wKihMW7jqK02qcbT2vZEVViJ7xlR596zhM7zOMo1I6RddDMFRlrlpB26IjETs1ny2gO8a4JFA/
e+G035m8twrI9x2MaJwl1nCEkdgjiFMRKUcFoFqp4xOzI1gZtgHIpY01Jc9nD1o8BQpYdSzE7zBC8bKwUhx
0pDjsA4HhFqNaO0WIWaW8sueu40XhW3473luzF395chqtqAnjZRVh7nyTmaSj13HhsvSDmzVNvNYwEo8+Q2
VixrrmRumxVqedKNlZs71siiDTj0koj2GSFxA5BnILw4l30bqzaj9nhZa3Klw2Npc8SkiRtlhH/
S1vu92StNxbf/SKP7XLYlHosstUEAKp9/
IapPqurXM1hDgPLjiwwuDVtOMN9VtNBftOh0przQvu0oo9d5ENFBU1idjS7eMKMFURWRURAlJTzjDL6zC07
li5jcn5ki7gqnT9Mu4h41aapDQtRpCNSzA5BECcVEmdh11l2LH6RsV/
CjjjU2dFWUOatfdW+gMryxGaOsQLK7TB3DbGo6uxAFoCS8svdaReUhbjSGxI4hmInQsuOU47ZidUlY9IdXm
ttYhd12ZJm6sayIAp4ZQ3M8PpFnPvcQlw3M9hZ3jBmx7RBKl90bTxYouttxj9fe6758Wz8kHx/
azMb66EvN+C0J+ehqKw65rHUsWmRzU3/
HXHyqB0SOwRxCsJLs9Z+8Vn9ImQX9YgtO5rne45WYOaivQDYRqD6MT1+UVMsT79oA6wby0K7CI4AZJuhOh0
27uurNogXkiSrlZuD/
xtZdkLH8RZ0znVNztPV2WGqVYeywYznasUCEmkPq9X7TmD30Qr8tv0IAOO4L7OxeHt+3FSA81/+A8/+tD3s
HCINvGU/K7IFz+jPJR7Wj/eX7sOJSh8+Xh5702r2byXSqUUayJ1MJLwRKEEQdY/
613dssQbsl2es2VjnPLNAeRxqBKqn2hew9KtSDvo1c4EERAl2m6Aer+YxKw5cdpuSIaadi9E99AVE2G120z
nyYnZ4mWFWFxYzQaK1Nsm3xSYIirg0E7m6AGWOMFKLRgtiT1UcUjKx7Ji5sfT7DtQEke87Vml6fbZlRmib6
SmR1dmJo68nxWn+WbJCLO4w/
X06edQOWXYIoh5jpROzUcyO1S9Fv8qyE7+vFG0jUBaPXzRcRNh5K5Ydk5gdWQCwr18ewsdYbZx2GzeepNoX
MA5StuI+k+fKCDO1S02ek34s3r3RB5Eaz0cJBrcJyv2OKGYnjLXJylqonV902Vj6bfJ7Uh3GjWXFOmY0NmA
lQDk2QcD+Dae6Yhc7Vj6TVuYCUMwOQRBJjmphV4oKhndR8GCtH3HoFqEbi9cstNoXsBTb4gzjGgKYonAq11
7wsezGstsE2G0C9/XNXrYPBaX8WAorGVnyAiLPVRQl1WtTLDvcc/
XbzGrh6Cw7jBsrFLNjPFe9G4PjxmIDlC0Vc2StJJJh3FekFZTlcT0+8/
fAqnvQaC5yLJGRpzRWQVDBxIelxsOywwr/
COcWjySGREFuLII4BTGz7NiE4Be01e8xdgGN53efNvWcpdoXUMSBFcxaN/
j8IuDmZ2PJgc9yphLPjfXBsn34fcdR7tjW2lQE/
5cXeb8o8bOcLGYJ6359m9TZCb3nAuTbKUoSnvtpG5o3SMUVp7cyHAvgx/
dYqWytPp4RY6LIvcfBa5lYdnjHB6xZdvjWKfN5R9YbK7Y/
CrbkQjwSANj4tUiLAlLMDkEQSYlRR2Jes0Z5i90mQAxIlr+k2QU04i92k+9uo0UPCLqxMixcS16UzBZKH+e
XuTy0knZeowSM0qL3HefHhVjLAqux7CgVjPn3nrcw8RZYs/
RgbaC2vNDbBUERlxsOlGDO6oMAoBc7Fn7ZR1pnR9W7yy9G5cbiuTStWnZid2OZp54HRAnXvb0cjTPcePby3
mFG1sOWObBaqNIMngvOKtqjKWaHIIikwErwsdayE65Hkxaf6pdi9GgXLFnr8ASGNhvLCPk1mMfscNxYktqN
Jcf+RJptFpVlJ6C27MgihzdUabUfC7YVqbZpD9MubrxWIYIQEsYnKo1bYWjvOV9s6S1kZrBlA8xidiK27NQ
cHy713Cht3Qz2PoRLPd9WUIaF24/g89UHohIHpVWhPmyRFgHk4Tex9IXDLB4s2SGxQxCnIKpsH+X/0K/
84DHWxlK7saL/
9tMupKFGoHyMWkSoxpTFjokbi5dNIz+Sm3nKLjMza5PZ2Eaw90uJ2ZEkrpXJ6N5eP3MFFtakbcvnG10DUIs
GWWCy8UhmdVjMxgptM9+vhX0fvX4xqpgd3q2RF/XqsDE7nPFMzzCqoMw/
lv0x4I1CrJQxlp1wn6f5Wwrx0vwdpn+HrMCx2r9NwYJlL1khsUMQ9QwrgsPMsiNbUqJxY0XuxQotbNrFTEk
9N9AXVd7wxeLkRcnUjcVxQ8giQF6cZCESodYJa9lhdzuZmJ1wxfq0LNl1jDnO/
Nc3Oyd16rn+fTeqy2M2p0jdWKzlJWjZCS1L7OIeaeq5qFh24h+grIqDCtMbi90cjRsqEjfWhHdW4rl521Xi
VwsrcCK37Kifm539y9ZCXPzqIuw6Uh7RNWoLEjsEUc9Q1dAxPMbY1WCPUOyoLDuWzgg/
J4BtBMpXGPIi9sTFPRShoEW2FpmJDnkB4Vm7fDG6scJZNthryl3HA7psLP38zNBVUNacx1oX5HtuYy07zLF
at4l2bQznArImdkLX8AVEVZ0ddq6mMTsmlh2PQYVrZb7cIGvzefNcQUbnsJu9FqyRWlg3llVLTKFBdiDAb2
JqFV3Gpsl7csOslVi7vxiTP1kX0TVqCxI7BFHPsLIosodoF1O7hRRkFrWlIDK5w1pKtMLALBuLZUCbhjirY
xPuPjkjx0qdHZ61K5SNZVPNySrhfjmz12SLCqqqEMvvj8k4ZtPSvid+TqsDGxOzowoY1jYO1VmNzC1QVtZS
r0bssK5CNrjYbGHlBW8HLFp2uLFfEVl2zN8fVrBFE3PDZmPFI0CZ54Kzis6yY+H04kpv+IPqAMrGIoh6Rji
RYrRgaQOULVt2mMUklmQs7cJoVkFZNYYAZKc6uftClh2T1HNugLK8T87GElRzskq4X87sNdmaQNpWGJM/
WYt0l7Wva50bS/
OB8HNKBbBuLFZ0amNMtIKUn3oevWVHKw7l64uiZHoveZ95ea7eQLAApVEmndUGqyxqy05ojjxYy1JUlh2VG
8va+Wa33axXWvhxjcVutS+A2z9cg3O75uHy01sq2yONc6stSOwQRD2Dt2ir92ueK0UFg0QsdlSZQ9GjD1Cu
eRDmu1IA0CDNxR8zgpgdVQZUzVxidWNFUq3WwWTBsXNZsusY1h8osTyOWeo5oH6/
lArKTJ0dletIG7NjwY1lVmcnIErYcrgUXZtmKfeSFQO+gKgSNR6fiMmfrMWSXcfMrRA8scNc2+MXDasPR5O
NxYtrMjpFFYAdlWWHcWPF2bITaTVl7Wtkn7635E/M21yIeZsLVWLHSGTWNeTGIohTDH0Aq/
rLWglUtfi9rLYURP9lrBUkSruIMGpHEAT845z2yErR/3aT+0yZLZR+zmIlP/
Ro3FhGdYtSnJE3rwQ0lh25Q7ukbhdxwoIbQDIRGHo3Fi9mJ/Ta2Hul76UVPmbDLPV82twtOP/lP/
DU3C3KNnXMjqSKC/IGApiz+iAOl1TjaLlHdy3lmjw3FjOQWfp5NHV2eBlNRj8OtDFJ4fAFRLy39E/
srgnsjcayY2ZMYbvHxyp22NdcXMX/nCaLZYfEDkHUM9gvICu9k5TUZjn1PJYA
5Qi1jpkVQP5BGO6HoSAAjTPcWP6vkbp9AVEK69YLxezo3S/
ywh9KPeePYVTNOZKYHaeBZSdcUTyzMQG9IGHFjJJ6zrix1Mfy20sYXQvQtlJQH/DWH3sAADNq/
gf0YoBdjMOljcvwPnesZcdsnKjaRUj61xhpTSEj3lm8Fw9/uRHDn10IACirZuvsGF/
E6g8NdoyI3VgaGche0+hHCVl2CIKoFVTZWLxfrTpTtNqyIYsdq8LFp0o9j/SXovHCGEo9N/
+yNAtk9oti2LgZntg5VFyNal9A2aeIHaPqvgaLUCQxOw6DmB0r9YRYwjVrZOekTj3Xj+X1By1j+45VQpL0w
pEX3Kv+/IX/PKhTz0XVvbTq9uH2xmIFo4llJ1z6PACs3V+MgU/9jK/WHqwZW22NMpqDFiuWmeV7jquea+
+PEayVxmrMTqwBylYEXgRdXWqVJJkGQRDxIpJ4g+DzmvNqnisVlK3W2eEsnlbh/
UKWCbmxzAmF9uiPFMXw1hVeUbhfthbhyv9bqixObod5NpbRohzOTcDeYqNsrHAVgAG10NNeUfs+8tp7BFPP
+Zadt37fg6H//RXPz9tuqYKyqhGoFbHjUwsH9nyrVi3eVdRix8Sywxz32vh+3PFum70ahaUe/POjtTVjh/
bJ1hErfy5WhKvWSuj164UVD6vxPOqYndiEtJXXTG4sgiBqhXCCwzDIVJd6btEs7md+UVqbIncu0aaeK/
V4DCw74X5NGxWFW7u/WFlsnWGysYxicwJhFiD2mi4Dy45VV45MuArKqjo7qtRz/Vh+UcS/
a+JrXvplp26sal8Aj369SdWyQhWzY2HqWjcWuxhbtexw3Vgiew/NLDvB49JddvRpmVMzoPoYrfuJF/
dizbIT/hjtZ8xqzA9bqbm2YnbMAtSNrkluLIIgagV1cTzzX97B4+Vjg9gidWOxvbEicGOVe/
y6TBwWOT4mXICyLIp4lomAFH6BkRcynmDZXlgGIPo6OwWl1Rjz4u94Z/Fe7n5VnZ2aooJGXc/
NUAVXmyxIgNayE/zfZhCz4/
Wrz9WONWvxXsxavBfXz1yhG5N3PA+VmyagjVcKb9UywrJlR74HNkFZsCVIqPIGFJHk0CzYvIwmK6/
VSsyOVuyos+PM2p5Yc2Opgqsjzu4y/zzwiPRvprYgsUMQ9Qyz7x+PP4B5mwpV2/
R1dtTbwxFNu4iSKh96PPIjftocmot2QVK+JC1+V/
IOC1iy7OjdWDJr9hcDCKWes79Sh7RvhIv7NDMd+9mftmHL4VI88vUm7n5VBWXFjSVGHOhtVrVY+/
JVLRiY1HMrAcrasXhCMpY6O96AOmanKgax44/QssPeA19AQo9Hf8RpT/7MrdGjKvpYk/
FnRZ9aidlhxU5AlNRuLJOLsC4pM/
dhLHV2rBYVZD+PkZZrqC1I7BBEPcOszs60uVtx96fruMeHsrFsqu3hULeLsHbO6n0ndNu0Ykew6May2YyPC
1iK2RENLVI7i4Lpv7xsLLtNwNBO/MrNMsVVxh3EgdDiIQhMyr9kveO8jM9EcGrfR3nBLKny4b8/
bgUQTD3nBZKGq6DMgxUCVl4GG5fj18TslHv8vFMsYTX2R1LEjlowB0QJ5R4/
fKKoE4Ja949Vd5sVscO2Pqnw+tVix8QyxKuMzT2ODVCOtc4O85y9Q+zfMsXsEARRK6iyYTT7Plj2p/
54uaigbNkR1NvDYbbQRoI2EFdefMOZwZUAZZ4bSxTDLkTBoFjzufGKCtoZt4cR4e6HxFgVFBeKZD04XIZdR
K1WUP7bm0ux8WApgOCCxLt/esuOBbHDurEsHM+
+79qYnUpPfCw7ltxYgsA1D4qi3jqhE5AW3UFWApTZe1xe7bfcH4wVO0bzqfYFNI1AQ4/X7S/Gpa8twqo/
j/NOBRC+hpMMKy5tSaIykmQaBEHEC9a6ov0uMu0cXfN/
pHV21EXqrM2RZwDSxjMoAcphhmLXaO16HQjTZgAILrDhXqv8a5sVXnZBCBtPFA7FsoNQPSEJkiWRwOJXxU2
Ftpd7/LpUZl9AQrUvgE2HSpVtglHMTpgKyjxicWMF6+zEybIToRtLMHg/
A5KkS8vXWgv3H6+0NKcVe47jRIV5kcgqRiiUe/y63mFAUCSv3ncCJZVMwUEDESPz6q870eXhH/
D7jqOh45h7NP6tZVi9rxjjXl9iOLdwVkOZSl/071ttQWKHIOoZ6mDV8IuVYQXlmg1r9p3AjD/
2GC7A6nYR0Zt2onZjMQdoF+yAKKmyxXiUVfvCWmDSavpSqa5lwbITDvl+2ZiFVorCjcUGErML0LUzlmHOmo
OqY/2iqFrwgKDA5YVWaBdNK+JFlWEXodjRBmdXeq0vmtrPuqrthIlFRd0MlbM/
IOksO9rXpRWURny66gDOe+E302OqvCFhVlbNFzu/bivCpa8txihmLHU3c/19/+
+P2wAAc1aHPg+saLMiLHVdzw3e3gqPtUKIdUlMvbG8Xi/
27NmD9u3bw+GgNlsEkQxE+staH7MTih0BgEteWwwAaJzhwkV9muvOj6WCMovWsiO7scK2izB4DAS/
9H1hLDvHyr1h71N6TV8llRvLwPUTCWzMTsiNZS3YlUUdNxViy74C9BEO4O+OH3C6bSv2SXlosygXpWktcbM
9gLbCYXwSOBs2YaC1CsoW3uCIU8/ZjDy/1rJj3Y3lFyVVvAt7bTPLTigwn/
9J83NiduQ5pjrtqPIFuGLHbhO4ovVImb7txau/
7sT+45WYdmlPlVuvrNqnaToafPxTTZJBQWm1so99r6zX3Im0zo5uS+ghc4/
Y9y2aTu+1QVQKpbKyErfffjveeecdAMD27dvRrl073H777WjevDnuv//+uE6SIAjrsF9I1twO8onB/
0IVlNUny2nYWqLqjcVZVYyyscLX2RGYx+p9oiiZBnUCwLEKb1iRlpES7Kpu08bsmJ8WFtlaFhQ7Nfcd1l2I
MuyCki8dwbWOuUiDB0Pt69FCCFlxmgnHgcItyAfwQE2j+MvsC7H6xCBk7r4AOWiEDKEabYXD2Cq2QurxLfj
O9QBKpXQ87b8SvkCwwSNvIQ+IQQtITG4sjduxKgLLTkCU4GR6fVq17PCysbTj6iw7Na99ULuG+HXbESzjiB
2HgdjhIVtdrhzQSmXZ+UNjgZOtqA5O3xJev65wRGp10buxgv8XlFTjGNO7TG3ZOYnFzgMPPIB169ZhwYIFG
D16tLJ95MiRePTRR0nsEEQCiXSxkRTLThClgrIusNXAjRWnAGWjmJ1wqGN2BLC/
Nv2iFLZw2rFyT9j7lOEOflWya4xR1eFoCLqxgkSXjVVz77Z9j68cD6CBUK475kP/
OVgidsPVfRsio3wPTuxegzPsm2AXJJzuWQIsX4K1KaHjvZIdriUBJdhhhu0ZzDzeCM3hx2n23TjNtgnVcOG
jwDmolFLg27cCdrESdl8DZYxoYnbYdbrCa92y4wuISGHUDvtxtdIugrWusQQkY7HTp2UD/
LrtCLdJqcMmwLh1KZ9Kj1+Vbv8W00MMCP2wcHCiflVZVlYtOxGnnmvcWGKwHtGgafNV21X9vMK4keuKqMTO
l19+iY8//hiDBg1S/
arq3r07du3aFbfJEQQROWYF5ngo7SJ0FZTVxxmJBl8EAcpfrT2IpbuPYXiXPN0+7YJkVhmZhRUc2kNFSQqb
jXW8IrwbKzNFH7NjN1gcI4G1KrBurEizsQJ+H6QP/wZh23doUDPOUSkLcwJn4U3/
WKQIHuyXgvf8tBbd4QtIeGLbZth9AQyxbcKFjQ9jLBYhrXSnMqZLCL0fx6RMNBZKMeXAJExJUV0aEx1zgw9
mBf+7XnDiXFcO9ku5eDxwV9i5q4sKihrLjnWxo7c0hcax0giUjZti8QckQzdWowwXMt0OlHHiXazWl2Fj4S
SYu9xCvdp482Tq7Fi07ETc9VzzXJTUrjQZlWUnQldZbRGV2Dly5Ahyc3N12ysqKmL2YRMEERtqN1YEMTtyg
LJBNpaRtUFVVDBMgPKL83dg95EKNMlw6/
bpYnaUbKwIYna0WTOiFDZ+IRizY3oI0mssO6wbyxYPNxZjVZAX1G/
XH8a36w9bOt8GEWfaNuChgi8g+LZDlAS8FfgLnvFfDi+coQOZ1+cLSMrCGIAdv4u9gOzhaHnmFJS+fx2aCs
dwg3cKutj246qmh/HaoY4olBpiiuNjXOr4Aw4EUIEU/CnmwQs7ugnBcgb2rHzYRR/
sFUVoZTuCVjiCNwJTge3ZQKfzdHM/
XFKFvMwUlRVCWwYgkgBlrTWD1bhmlh22zg7vDQ2I6mwsSQoFUTtsAlo0TMOWw6W68xwWO2CyYkCUJFNhJn+
WeWNHZ9kxP+6md1eirNqPD24cCJvGRQkE/
9553wsVzPu2+0gFhj+zAHP+MQQ5aS5L86oNohI7p512Gr777jvcfvvtAEK+5rfeeguDBw+O3+wIgogYtRsr
/
PHadhGyyCir9itdngHjOACfQdozD7n+Bi+GQhezY5PTvc3HZAUONxsrjGWnTNO2gkfIjaUNUDafWziUtGdE
ZiWyI4ALbEtws+MbdLXtB2oykKf4bsbn4lDTc/2aWjZAzX1zpuEm393KtiNiA0ipw7FRCsaN3Ou/
GZ9nXQPxxD7sSeuJo9XBizrgRwA2/Pb3EWiZ7cK2//0NnY/8CABog0PA7MuAC18G+l6DMbZlmOp8D/MC/
TFiWjWeHT9ENQ+tVaOyDiw78sfDZvB++jUxO96AqFje7DYBrRqm8sWORcuOtgK5WdVo+W/
NqamybLcJ6gBly5Yd4+M8/oBS4XzvsQq0a5LBLSrIi9PTZnbtPlqBdxb/
iX+O7GhpXrVBVGLnqaeewpgxY7B582b4/
X68+OKL2Lx5MxYvXoyFCxfGe44EQURAtNlYMnbGRC53eQYsWnbCXE92KfHEjtayE3JjhbHsmLixwokdp12A
LyDhCCfmgkVxY+mKCsamdlhrWiRjTXW8i+sc8wAAJVIatrl74mhmV3x+8Kyw5/
o598RuEH90TFMTZpe3AY5Kaci32yErLH/NMuLxi4Ddge87P4kx+69BK6EQD7o/
xXlYCnx9O7DgP3jWeQRpggfXOubhTNsGfPzdlegi5KObsBcuwQ9n1RjV9SIRO2YFEM1jdmosOwb3QJTUbiw
vkzFmtwlo2SCNO662e7kR2i70Zq47Of6FtexU+QLIcDs0bSCsWXbMLEDs36M8tr6UhcQdo7xab5ErrjKvL1
TbRCV2zjzzTKxbtw7Tpk1Dz5498dNPP6Ffv35YsmQJevbsGe85EgQRAZLhE4PjJfX/RuXdjQOU+WnP/
DGCx/LiaHQVlKMqKsiz7BjPqmG6C4WlHm46MIti2WHWLzM3lk2walVj40Ws0QQncKX9VwDAB/4R+K//
cjRr2BwZLgeA8PVefJr+U/
J8eYYIbQG8Mtmaw4kZkRdHUQJE2LBXaop7pDuxfuhKYNGLQOkBpNWc5pdsaGcrwAPVL+ABxqNZsfsjFNhuw
jzxNAB6N9altt/Q2lYIv2RHGdLwZeAMFCMTAM+yI6GVUIhzbavQ4WgTYPM+
+Jp0hyertfJ+BucbcmM5tn+H55z/
hw1iWywRu2Or1EoXs+PRiJ1Wjfhip7e0FZMcP8ELJ45LWcgVTmC52AVfi2prltYyWm0izGRLDGtpqvT6keF
2qD7nVmNxzC07bOC4OolBRpT4QrKCE8MUSzXseBCx2PH5fLj55pvx8MMP480336yNOREEEQNmTSF5GNXZ0W
Jk2YkkG0s+lteryLCCciQByppjA6JkmnHSKN2NwlIPjpab/
+pMq6mzo6ugbDA5l8Nm6jqRYSsoWzPsSHjI+QHcgh8rxE74l38CAKBJQEQhJ1CUh7YlA1BTPZgzgeMasSMv
gDyrhbzosZ8/vyQAIx4GBk8Cirbgjv/
7DgvE3jjTthFX2n9FllCB9sJhHJOyIEJAOxTgTddz2Cc2wTapFUSfA+/YRmCJ2A2DbFvwnOt/
qmteZf8Fv4s9kYZqpGwvAQJ9gJIDQMUR3OX5EmNdP8MhiEARgE8AG2y4V7oXj0+ZjMY1cWPydAf4V8H95dO
41O7BpfY/
EJAEXOu7HwHxTFXAuNcfun92m4CWDYNipzFKcKvjaywQe8MrOfGC52m4HOreaFdjPvr5dwDSWOUNZ4Vnmce
vzOeSvs3xhaYgpPz3w/7AqPYGHxu1gTDDzALEih3ZtaYtLCpJEtdKy6uPVBFB/FVtELHYcTqd+Pzzz/
Hwww/XxnwIgogRVW+iaAKUjSw7BmKH/
RUX7no+E8uOdpusucK6sQweA3JRQeM5NcoIBkyGs+zIc1CJHYOqw4CcGmy9D1K4NPYBwhb0t+3AmbYNOMO+
CT7Jjum+K5X91f4ACkusJTr7A/
p0fFHUt0QAjBtc8uJRZLHKimLl85DWEGhzBr4WiwEAc8VBmCsOUp3vhB/
PNfoKF1R8rgQ4A8Ao1zIckbLRRCgBAKwRO2CL2BLn2lejs+0AOtsOBAf46VfVeBcBgACsEDtBSG+M/
hknYD+yBY/gf/hlQR9cXvUJUF2C7mVl2JuyHKgInbtPbIJWtiP4wDUNxT+vQ5/
K03FMyIAPDvhP7IcYEDHcthpdNy9Ek/Kt+MW1De1sBQCACfheGWet2A6rxU7IQBU8cGK8fT6ud/wEafn/
QRh4M1bvO4H3l/6pHF/KNI69rH8LRey4HTZ4/
KIiYliRIrdmYO+71QaffgP3FKAu9ijHUmmPkiS+S5pr2YnAJVkbROXGuvjii/Hll1/
irrvCpxUSBFG3RF1UsAajwEojyw7b2Tvc5RSxwzF9a609NosBnqoAZc45ZsHHDWqyQ05UWosnYK1eRgGtwX
2WhsOxiqBAaZTuMnRjjbKtwBuu51XbHvLfgBVSF+X54eJqy64LX0DSpSZ7A/
oqwWbwsoE8jBtLJpKsYx8ceCttAp44NhxdbfvQXdiDrrZ9GGFbowgdALjPNxHbpZZ4P7AXtzi+QZGUAxE2X
Nt4G1KqjwLZLYGMXKzaXYAvvAPwfmAkTm/
WEDOv7olD0weik+0gLl8ZEoo5zBwC7YbjzM2X4AQy8KbzWZxl34icvXPxIObiQdnd9g7wPtxIcXmAYNN4ZH
HCczY6uuGK8nvhQSgDab/
UBA86PwR+eADY8BmkfSfQTuyGC20tUIY0VFS0AQBk2z1oVL0XAkRIsCHd7YDH71UEj4+Tnq9yY1nsVu83ia
Fjt8lCRftjxuMPcD83vNYTsfQ5iwdRiZ2OHTvi8ccfx6JFi9C/
f3+kp6er9t9xxx1xmRxBEJHDfiFZqWisFBVkAjV5GPn3SxihYHa5gBhKK9a6rADAo7PsqN1TRmOb1dkBzKv
n5qQF07OPhXFjyai7nhunxVutsVJQEnQ9Nc20o9PeD3CXYxs+8Z+Ng2iC4bbVuNr+M862rQMA7BCb46DUGN
8EBusyriKpl+IX9W4sXxix0yE3AzuLQoUKeYJYvs+RulGBUNsFjy+AIjRAkdgAC9EbCASzvcbYlmO4fQ22i
S2xXQpWcd4stcEdvtuVMQaMOwN9WuYoz29+ch6OBrzK3I55bBjvfRAzXf9FD9ve4EF9xuNgeQD+7b/
g68wrcdPfHsXhh34AAFzjexCd/
fvwfrcVKN27Grn+AtggIs3mR4oUFKmVGa3hb3Um7lmbi362nfg50BclyMBA2xbsaPgXeMrVbqz/
C5yPLrb9uNT+B3BgOfrbgP62Hcr+6sWv43RXPnra9sD5WQCfuTriXt9NuFlYiNaunTgi5WDTU0/
ikoyGGOAsR3vhEAIbJwGt/gl/
QMQZtg043bYN3Y4IwK8dgsIvtxs8ub24910WSNosuIAoacROjVDRvJ23vL8aU0Z11o3LEzZal2hdE5XYmTF
jBnJycrBq1SqsWrVKtU8QBBI7BJFAYk49N0gisWTZMVnc2DgD7i9JrWVHk1LOpvsazYXn8jIr0ibX/
TheYc0FZKURaD6O4R7pG2Q6g8HCe6SmeM1/YdBVZBOAI9uAg6uBnpehqMZ9dlX1J+i3fxb6OYB/
Or7AJrE1uttC7o0Fgd6Y6LsbvtjaGQIwsOz4RXCK8ir0aZmjFjumAcqh98ZqccQmmW7sO17Jfa/
8cOAbcQi+0QT26o4zy8byiTha7sURNMDF3sdxkX0x/
n3NCKR0OQ9btxRiwsYL0Ts1GzdrxOs2qRV2DL4Mjx7dhO2Fwdc/Z0JvfPD1XKw7KuGhqy5Bx7xM/LT6F/
wknq6ctyPQAn0d6QCKNbMUcK/vJowaNxHpbjsmv/cHzrGvRQvhKJoKx5AfOIF+tlBhx/
62HZjvngL4EWrbHQBQAnSRi0UvnwqUrcSwoiJc6Voa3FYKgEmMdjtSMN/
VAFVw45PAMLQSijDEthlHPU2AQw1RmaYWLB5/
QGURla1HvHfzhZ+367bxxA6vynRdEtVfzp49e+I9D4Ig4oTVooIOmwC/
KOlidgyzsTgCw+sXVb54s6WNPZ9n2dHGhxillNsFAQHmSuqu5/rrmomdBjWWHau/
OtnxeQHKqajGZ+7H0EI6CjB9mgbYtsDvvxiug0uBj8YDnlKgcCMKq69CC+EIzjn2oWocWejMCZyJN/
1jsUVqbWl+VuDV2fFxqgTLOGwCujfLwmfM71onRxnJAcrs0HIdFkEQTIVwriJ2oq+2q31N7PNqf0B5j/
1w4PPAUNzXfChSmPkaideApC5MWSWkYKOtC3ZKZXDYbHA7+CqRd4/
k61e2H4n0TDfmiDbMqbHSCRBxe8fj2LtrO0qyO+Hl8QNw5P8uQXvbYey3t8Rn1QNQCTeKpBwMalyN7cd86G
/bjvPty4AtX6Npzfh/BLqjOqsNRrYUgKpi4OAqCP4qtLcFC1UqVi0AkP4E/m8YGjXsgkXuI/
BKDjiFAGzfX4RA+38ohxm5sVJRjbZiATyCE7ukZsp2OWuvhXAEo23L0cu2Gzm+cvjK+sGZ2Zh7X2qbmH8my
B9gqpxMEMmB1ZgduyJ2as6DuRuLZ00pqVKb6U0tO/5wlh1N6jkzD3VcDoK/
bjn7eI4sswVUjtnR1pMxQu3GUjuxmuAEXnG9jBbCUZQiA9/6T4cdEi60Lw7+Wn+qiXqwJa+gf4NyjHUuhVP
04Eij03Hn4ZGY7PgMCwO9sVTsiuVSF+5rigbZIsars2PmxmrVMA0N09WVb61adoDg51EQzGu6NMkMBsSYpV
0DQHaqU/eZk9FmFokay84xjWVBno+6XQRnXE1/Na8/
VFTQZgtm3vEwc2X6RVEfVwMbVktd8IfYGF3cmXDnd8IF3n+jr20HqpsNwqoDoQjq7fYsbAmU4t3AeWh4+uU
Y0qAEi/Z78ciGhtgptcCArIYYeWVNgd+AHwX7t2Py/
32DgbYtOM+2EpVIwaeBYTjLuRVj8Qfcx7eiuYDQR23NDPTdNhf3OAbg90AvNCoqAapyIElAS6EQdzk+R29h
F9oKBbAJwXtxXMqAGz4IAIo8DeFx2UPB4zUcOXIQTU42sfPuu+/iv//
9L3bsCPobO3XqhClTpuCaa66J2+QIgogcqzE7bKNCSZIUkWQUoMxLUy3RFAozE1dsUKUVyw47jeAyVOPG0i
zKqmysCC07ORFbdowClCW86XoWfWy7AQBPuyZhdnVvAMBqqSP+46wp0+HKBLpdCLgygOVv4KITswAb4LenY
XWfx7Ho4Aks8tZOrTKX3YYqMcCtsxMUO/zz2jZOR3aqU7XNNEBZW+9GkmCDeQdwReyEqWQ9qF1DTBnVBS/
8vF3XUkMbU6a17GgFrU8TY2QT+D/
aAwF1+QKPP6BYsdwOY8sOTxAqcwtIpq6ezBQHXHYbKpGCRWJP9BHU91+OkwvAjp1NRmLI4DZYv2AXdq4PRk
wv33Mci3cdxZD2jQG7A5XprbBY7IHFYg88j8uUcb6xn4uxd76M7ZtW4/65+
+FAAA2Ecrza4COkVhzGbY6vcJvjK2A9gJ2N0KzzzfjC9QoaC6GK0celDKSjGg2Z5rNtcBgQgIAkYLnYFQvF
XiiUGuBm5EAj+euMqMTOc889h4cffhi33XY
bzjjjDADAH3/8gVtuuQVHjx6lLC2CSCBqsQPmsXqxYX95ilLIBRVJgHJxpdayYzwvdoHlFSLTx+yo1E5ou2
Z+Yd1YNYsaL8hZtuzw0mInndMeGw+W4vbhHZRt7D1rVL0PPeffgeedNiwVuylC5xbvndiSPhhAJQDg48A5W
Cu2x+c39EJGm36AMzU4kZyWqPjpSVRKbpSe9xoqXa0AnNC/
AAQXvzJOVdpIcDttqPIFxY5WePgCkqF1vm3jdGRpxI6Tc6PXHSjG7R+uQXGlVgDX1IYxSc2Se6WFc2O5HHZ
0yM3QzQfgWHYkrWVHI3YC6uwxwaJlx+MXlRiWVGdQlPAwaxfhDYgordK/n7Igy0xxqt4P7Z/
VCebvTv7sauOw/
vbmMmx7cjTcDrthkL5PlICG7XA4LxOrpeXKxXZffgNK1nyNklWfoYNwCG1shUDlMXRY8xQgAIVSDu7zTcQm
sS2OIAfpqMK5tlUoRRp2S02Rh2JkC+VYJXbCMWTD7bBhw2OjDK1gdUFUYufll1/G66+/
jmuvvVbZduGFF6J79+549NFHSewQRAJhvxjZL3xtTAP761xkLDuRxOxoxY5ZjBDrOrFm2TGI2dEsImpNZBy
g7LTbdNeVLTs8OuVlYsqoLqpt8rUbowSXbHwMmZ4CXGIHLrEvAgB86h+KH8QBaKe5h9ukVvA1Ox1wupRJi4
Nuw4BvW8AvAgu7jISw+5jhXJrnpGJrQZnhfivIizKvzo6pZacJz7KjP3jO6oO6bUAo/
dysgF3jTH1jWB6yFYUntsxidjz+gJLmL+MNqN1uQcuO/
pqipBc7ssBId9sNRaLdJOLbH5BQ5dW742QLY1aKemnWCpkqTvAwz024+0gFujbN4v69BechqsaQKUMGFmeM
wvO+tgCAv/fPwSPpX+HEnjXYXFCB5/3jsJIpfVCBVHwpnqk834umqi+i/OyUhAodIEqxc/
jwYQwZoo+MHzJkCA4fttatlyCI2sEo9ZfXD0l9nKTbzqJ1TwDqTKxwsF/
GVtpFqNxYmsBgFiGcZadmYXBxxY5xF2YHZ7EShGAg6XPO15DpKUDAkY693iy0tx3GbjEfLwbGBedhYTE+Wu
FBheiCTQAaZ7hMKyi3apgWu9ipWWx8oj4byyxmp20ja24sI+TPoFlVX21MkBHya+AJCfbzLYqSLnZNTvOX0
RZBtBlUkf5hY4HKzenxBRSxkeqy644PYS78eZY6eS6ZKer7bSYU5bnwLK/
bC8vQtWmWoWVHlIL3qsqnnsu415eonh8PpAF/mY7VWwox4Z2VhnMxwmqfsNokqhl06NABn3zyiW77xx9/
jI4dE9fVlCAIbQXl0GPtQs+KhmDWTPCx0aLH++WodVnEknqubwSqjo/
hbddOlbdYye4xJ8cakZXiMBR3POuFHcAk+1cYat8Avy0FG//
yOUZ7/4MrvQ9hjPdpHJCCEQk865jW6lVUGrQ0NM5ww2G3mSZ5yJWeY0G2ivgDou699PpNxA7HssOzrBgRUN
xYxp8NbTNNo+Fl6xTvvWE/X7yU9wMnqjTHa7IQay6qvQ1frzukel5aHWrpkOYythdo7/
GPdw5F85xUZa5yxhKPTI1lx6yOkmyV4Qmi7YVBgWxk2ZHHrvKauw+rvPpMu0hIBrETlWXnsccewxVXXIHff
vtNidlZtGgR5s+fzxVBBEHUHUZxOlprCrvIs2InkgrKpVVaN5bxvNQxO+YVW4NzCh3Pzoidn5Wqv3KGz+D2
jTB3Q4FqnyAIyEl1crOxdOJIFHHepnvR1jkfALCk0z1w5XSCD8exVOymOpQnoLQLltzLKi8rJTgXk9fgdph
ZEKzhqhkj6MbSWnYkbp2dVKcdeZkpsNkEpLnsivsmEsuOpLixjFtPtGmsFjtpLgc3gNftlC07YcQO54N4sL
hKuZ6ckVZW7VOOlcVmKBSeD9scNdVp/L5o73FGiiMkOEXJNAZLa9kJiBL+d3V/
3PL+Kt2x8nvCE0RybSCzru+l1T6VW4yHvN9KkVIevB8adU1UcmvcuHFYtmwZGjdujC+//
BJffvklGjdujOXLl+OSSy6J9xwJgogAo6KC2l937K9jUZLCpp5zA5S1qecmy4Q3TMyOPv4n9Ji1eqhS0jVj
8BZs2Y01qF0jfHDjQJ2VwihuR+cqWf5/aHtkPkRJwCv+i7CzxTiTeA2OZUcndoKWnbysYLyKmXCTF/
lYcCtuLOsVlAe3b6R8Htj7ZhZ8qyUgSRBFCQu3H+Huz0xxIM3lUFkzUgxEhFu27Jj05gKMC2ACQLsmwYr/
2wrK0P/Jn3H3p+sAWO/
FJgcHpzhtpunlWsuO0yYof3M+f6SWHRGje+Tj5mHtdMfKLiiemNxhwbKzs6g8bBZc5alq2QGA/
v374/3334/
nXAiCiAOiQcyOzo2lidmRDxUEfuYSbwGRXUQuuw3egBgmGyuygnGigWWH1SA6N5ZJnR2n3YYzOjRGs5xUVa
0Wo7gLlaum4ijwy5MAgKn+6/F+4Fw8brdF1BtLKzAKtJYdkzU2xWGH0y6Y1qoJh8thHKDsF/
VFBX+6ayjaNQ61AspKceJwTdyLWVq1FlGS8PW6Q5j61Sbu/
oyahb1pdgrKqoOWiFQXf3F014ggnsj4bsNhSACuHdxG5caSW1EAQWGZ4Q5e76u1B1V/E/
LrtwmqMk46ZNetmQsL0MfIpbjsShyYL6xlRxOgXPO+Z3CuKf8N8tyEsqA2a5myo7DMtH8cwGYrRvf5i0Qc1
xZRya25c+fixx9/1G3/8ccf8f3333POIAiizjCI2dEulA6V2AmdJoDfgZtnJmdbOGivpyWWhZrVMHaD+J3g
c/2p8q9W+fVqTfGGlYPZX6O/
PAl4y3Asqys+CIxQzjP6DuctxlqxWKQRO2brgcthU9Kzo0Wx7AT0Be1412+U7lLdA7VlJ7IA5Z82Fxjuz3A
Hx5XvA2DsHnKZWHaW7j6OqV9twuZDpYo4AIIZUzKtGqYpVgZtcLpi2QlTxPFITS0cdo68j5A2hibNaYdTfg
/8IspMGmNm1bixOudlAgBG9wjWR85I4YgdOdCa8/
dV5Qug2hfgWnba11i4theWm4ohAKiq6Y0VpRcr4ZlYQJRi5/7770cgoFeCkiTh/
vvvj3lSBEFEj7pcv5llx6Y6jrXs8BZenmVHtr6EFh+TAOVIWmDDxLJj0viTJ1yUbCyDL9ywrqi1HwKrZgIA
1nS+CxLYuBHrbizt/QvF7MgixsSN5bAphfdYXriiD1o0SDU8Tz1GcHH2cdpFAPr7oI3L6dYsK7Qvgl/
qohi0TBmRyVh2tHPVIr+HZotnYVm12rLDWO5aNkhTzi3VuJGU1x/
mpclZXWnMuDw3jday47DbFGuhX7Tmxvpg4kA8e1lv3Ds62Lsq3c0TOzWp50aNeqt83Jidbs2yAQDbCsvCur
Fky1i0bqyT1rKzY8cOdOvWTbe9S5cu2LlzJ+cMgiDqCqOigvoAZfacULyNAL4A0H55A6E4FLtdtpoYz8ssf
ZaHUcwOG1OkFTe8r1S5qKC8IGnnaOSRcdoFwFMO/
PRQcMOw+3C0yWDmPH4vJd68AL3YKahxMeRacGM5bAK6N8/Wbb+4b3NVzNGVp7dUMn60sMGx8nt5x/
AOyM10470JA3QCV2tdmTKqMy7o3QwtGqSiF9NdPByiJCnuJx6yWymfsew47AK3WJ/
8GsxcSKIoKffabhNUQqslY9kp0cSI2axpHaV5Kyt2eHNlBaVSH8guW9ckblFBGTlAuXGGG+P6t1BimDK4Yi
f4Xhr9fZ2o9HItN12bBq1Gu4rCW3YqlUag1v+GWcHfqmGayZF1Q1RiJzs7G7t379Zt37lzJ9LT0zlnEARRV
7BfR2YxO+yCLEkhP5Yg8FOneV+I8ve5Q3FjWUs9t4LKsmPoxlKfwxMM8us2mqNxA0wbsOx1oPIo0LAdMHSK
WmjZ+O4+AOjBESaGbqxM2Y1lvMw67DY8MKYLLujdTLcv0x0SOy0bpmHR/
cPRJT+TM0aNVSEQamx5brd8LP/
XSJzVsYnq+naboLOepLsdePmqvvjjvuHItVgEEAi+bqOWCkAw0BcA8rNDIs1hE7gZPPKceIs+ez1W7LDB3U
E3VnBcbXC9Ueq5EazgCpcKLwsjJUA5ICrZYTy0MTsyXMtOTcwOL4EAAE5U+Lh/u/LnrqTKxxTe5L/
4Co8fAaaPniAAY3s15R4rk+a0Y+b1p+PC3s0w+bzOpsfWBVGJnYsuugh33nkndu3apWzbuXMn7r77blx44Y
VxmxxBEJFjlI2lFRvaomvqmB39uDyxoo3ZMbPsRCp22LFsBpYd7TTNMmnkeAntFI2yz1y+YmDRy8EnZz8I2
J0qoWW36a9/87B2mHZpT+5CwLpWRFHC8ZpA18aZLu5rUc3dLiAzxYmXr+qr28fGcbgdrItNjXwPg26sGgHI
LG7sPU4zscQYjW+Exx8wzK4CQvE/
zXJClh2boBdbQMi9lWZSzE+UGLEjCCqXWIfcDCUFX9tQNJR6bu21hXNjsZYW+fWzVaz3H680HJvXDgMAMtz
61y2XVjCy7BQbWHbkGCy/KKG0JljaKC5MlIDDJVWKW3xI+0Z49W/
90NgkjizFZcc5XXLx0lV9dRmQiSAqsTN9+nSkp6ejS5cuaNu2Ldq2bYsuXbqgUaNGeOaZZ+I9R4IgIkBSub
GMLTuiJCmiJhizI9cb4VsZeEGO8jmyCDAzcscSoMzOhl1XrLixZJw1i2ooRkYeg398k1UvAJ4SILc70EOuj
Ky+tvY2dW+WjasGtFKuxcJWLa70BRQxJ1tmzN1YofHeuvY0pDrtePVv/
YLnWxQ78vhBN1bw4uwveXbK5pWBzYOptVR5RdPXJguFjnkha5Qk8QWEFcuONxASOw6boOp71iE3Q3nNWksb
m41lhdQwbixW3MsuQYdiVfJyazvJ1083uP/
mlh0jN5aP+7fblBGXcoXoJowrUcuuIxX4eMV+ACFB2DzH+HgzQZoIoko9z87OxuLFizFv3jysW7cOqamp6N
27N84666x4z48giAhRW2yMiwpKUvALXpQklWUHMOoRFEwfZwNXA5qYHTM3lpXU87wst5Iuy9alMWwXoZmnm
StIXuT+M64XHvxiI248s63hOT2F3cjaEAxKxnlPKEpA6+rRnisvlPwA5WA36k9X7scNNde22wTFjWM6d8bK
MbJbHjY+Nkq5RqabFTt2w7FYy46oiAGbbj9gRexYVzvV/
oCuySuLLGCaMQHK+09Uci078rY0E7FT7Q0oC7/
NJqgsKOlu48adcvp1uDo7MmrLjrkbK0URO8Fr7zlaYTiutgkoCz9mR+6Npb7Hcsp9MGZHH4DcvkkG3A4bPH
5RETtm7skH52xQXG/y9Pq3boh1B0q4x5sVXEwEEVl2lixZgm+//
RZA8ANx3nnnITc3F8888wzGjRuHm266CR6PJ8woBEHUJkbtIrRfhkHLTkikhLKxBEM3hVYwhWJ2ar5KYnRj
ffGPM5TH6qEsBiibWUdqFpoWDdLw7g0DMLRTTWsHzWu1I4CnnG9BkESgx1+BDiNC+5hjeXFN8nx4MRx+UcT
lbyzBp6sO4N/fbQEQ/AVvJQtI256BnYfKjaUIJ/
0Y8qayaj8qaqwdrIhSubHC1JCJSOz4AqYVfGWhwC7wh0uquaJE3sZz58gUllbjvOcXAghadrSVmI0K3MkLv
tVXpo7ZCY15Tufg5+rqQa2VbbJ4lOe/64ix2GlmEGAO8N1bSuq5xrIjZ7cVV3pR6dHf/
xSnXbEUKZYdjtiRA97ZGCP5vRrQtoHhXMMJ5romIrHz+OOPY9OmUGGoDRs2YOLEiTj33HNx//
3345tvvsG0adPiPkmCIKxjVFSQ57eX15dgBeWabTDpj+VXf6GKTCAooBYoAVHCDxsP40hN9ooVNxa7cEcTo
MyiXSyNftGrqjMjgNecL6KnbS9EdzYw6inVsey1bTa9G0t+yq+gHHq860iweB77S91skTVrz8C2FpDdWGaW
HRZWRLG7w7kg2NcXroZKtU80zfYxEh+87bIw4rlzZGYu3quIcFYYy4u/odiR+7xZDlDmx+y8Nr4/
Zk8ciH+OCPWJVNxYNfPZXSN2GnEaoLY0KSWQ4XLohKxRNpbspiqu9KHcqxZ88hjya5AFIc+y07axPulInsJ
pbRoazvWktuysXbsWI0aEfuV89NFHGDBgAN58801MnjwZL730EvXGIogEo+6NFXqs/
eXHWnaCvbFCMTtGZnSPpr6Wts4OK1BmLtqDW95fjQtf+QOANctOuosVO6Ht7GzMApTZBV1rXTGq+stuvsX+
DUbZV8IjOVEx9jUgM089vsayow1m5d23xjVNPNlsGdmtwS7aVlxwPDI4biyeO5E3PCui1JYd84WKHStcU9C
gZcea2BnbMxjYnel2cEWUfH/
NLE9sh3KHTcDMv5+OXi2yMfPvpwev5+DP14plh30fVKnnzFxTXXYMad9YdW9lV6VsSTtaU5hQbl3BYpambb
MJOutOQJSCzV012Vj5WUHRdKLShwqNdat5jaBK19xHnmUnjxPHI7/
ljTPcuH5IG+5cky1mJyKxc+LECeTlhf74Fy5ciDFjxijPTz/
9dOzfvz9+syMIImIkA8uONoBRkkKLFpN5XlNnhz+2NtBR/
jHJy8aau+EwACgtBsw6N8uoLCIWLDtmbiztL3ijX/
TyGE1wAv90fA4AuN93I6ROowyPleeqjUOWd7PZJ01rUqqPlqsXYUAtdsysVO2bZBjuYwOU5UWXd6t5bgV1N
hZzbATZWM6wlp2AaTuCMzo0Uh5PG9cTE85si49uHsQVePJ1jQJ4tXj9Is7pnIuvbzsTXfKDRRGNLHxyb7Zq
k/gi1oqWyggFV5j2GbK41QrDptl6K07LMDVpeHE71X5R97fZu2Ww/AHPjSW7ptI07sDcTL2w4QkgVtQ/
emF3/GdcT90xZhl4iSAisZOXl4c9e/
YAALxeL1avXo1BgwYp+8vKyuB0Jj7FjCBOZUQjy06YmJ1QnR3j5FvtF6qSjcWx7GjdVmbNCHmwr0MrMmS0A
oE9rlGG2kXQwKDhp/
zFfbF9EVxCAGvEDvhCPJObUaXKBLPpLTvy9RtnuPHJzYPx451DFUGxjwmUldOeWaHCu+vndsvDJzcPNl0Ae
dlYPMuOy27Dd3ecqdrmNAhQDverXGVBC9M6otpv7Maa+ffTcVbHJsrzrBQnHj6/
G7o3y+ZaduS33mrXdW2VZMBY7Mho49JYsph7zd6jcPcgVROgLMMTEuEK8PHeG48voPTaeuqSnvj81sHoXlP
x+mBxleKmkoPAp4yqqcissezw3FgjuubqtmmNebzPrllaeiKISOz85S9/wf3334/ff/
8dDzzwANLS0lQZWOvXr0f79u0tjzdt2jScfvrpyMzMRG5uLi6+
+GJs27ZNdUx1dTUmTZqERo0aISMjA+PGjUNhYaHqmH379mHs2LFIS0tDbm4upkyZAr/
fuDolQdRn2CqnppYdaGN2Qm4sIxuMdtEKmMTsaMWNUdEzI4wbgbJix9iyc3rrUDxB28bpaGTw5ZsCD3oKuz
HePh8A8GlgGAB+kLZKdHFSz9mnA9o2ROf8TMUSxWYFyWnH7GLD8wa1a5KOAW2N4yKAUG8pwNyNFRAldG+Wr
bhUALVlh30tqREEKDdMN/+B6zEIUE512nFOZ/
1CKsOmjMuwlhUr8OLEtJYo+X22sjiz12etcuGsW7JVTWtd5ImdcO0/
eC48j19UhN2Atg3Qv3VDdMgNpvIfLqlWWpO8cGVfrHpoJPrX/
G2kayw7rItsVPc8rJt6nkFFbpMPfg2ntTEOXk4EEYmdJ554Ag6HA8OGDcObb76JN998Ey5X6NfT22+/
jfPOO8/yeAsXLsSkSZOwdOlSzJs3Dz6fD+eddx4qKkKR6nfddRe+
+eYbfPrpp1i4cCEOHTqESy+9VNkfCAQwduxYeL1eLF68GO+88w5mzZqFqVOnRvLSCKLeYGjZ4bixQpad0LG
C5jyWKp95zA5q0tP/
8cEqbCssUx0babuIXi1ylMeqIGLmi1X7Hcs+H9guJBL6tzb44q08jvsP3oZv3A+hja0QpVIavg0MBMCPk2E
FkM2mFyi8H/
jyOazYkd8LVaAtZ8EQLbj+VDE7NUKGZ5yQxa4qi8hAOIa37IQet2qYZlqbpsrLj9kJV5hQ7rjeOMOFqed3w
10jO3GDZSNFKzhm3zgQl/
VvgQ9uHBj2XDnYHgBOZxZzy24szXE8gdU8rNix6x5X+wIorbEWyk1Es1OdSk0pWVxnpjhUol9r2WGFsAAB2
WlO7mdB97nn+GBPa20u0uuaiOrsNG7cGL/
99htKSkqQkZEBu119Ez799FNkZBj7lrX88MMPquezZs1Cbm4uVq1ahaFDh6KkpAQzZszA7NmzMXz4cADAzJ
kz0bVrVyxduhSDBg3CTz/
9hM2bN+Pnn39GXl4e+vTpgyeeeAL33XcfHn30UZUYI4hTAesxO9qigjU7BEHXGVxG2zBQNtawbqx5mwsxd4
O+y7WZe4Bl/
t3DsPFgCUZ1z+PuVzUC1f7AZDb0ahFq2cBdJCUJ+OwGtPAGW98ckbIw0XsPSpGhG0vGrrHsaBUK9xyb3o0l
w6ZQ8/tp6aethefG4r1/ssBSd+vmL9KRZGO1bJiGh8/
vhse+2YwbzmiLtxftUR3L1tm5oHczfLPuUPDaplcA7hvTBUM6NMYFvZrFNY1ZK0w65mXiv5f1tnTusYqQ2G
HjbYziwWRCYsfYsjOmRz6uH9ImbNo/uz/NZUelN1hLR/7zZq1PnfIylbpVgD7eRxuzw/
YRky2xvNgbXRVyzpuZn21ccDARRN0bSyt0AKBhw4YxiYuSkhJlHABYtWoVfD4fRo4cqRzTpUsXtGrVCkuWL
AEQrP3Ts2dPVeD0qFGjUFpaqkqTZ/
F4PCgtLVX9I4j6glFRQX02lsaywzQCNbIn6MSOYtkJNdlUUng1WLXstG+SgYv6NFctxOyabLXOjtthx41nt
kWH3AxceXpL/YXWzgZ2/
wqv4MIoz9MY4HkNa6UOpnNTWZhMUs9ZZGFQVKavQZYeJvXcrEijDCt2VDFYGuR2FVayZCIpKtiqYRquH9IG
v9w9DA+N7ao7Nph6HvzcXD2wlbI9XKmeptmpuPy0lnGv16IVHJFkDU3/ay80zU7BF/
8Yotpu1HxVRltBWYaNkRnaqQkGtmuEcLDzld2W0+ZuBRC0HLHWmU55mYbnAnrLDttHTHYBuh02nZgx67OXm
+nGfaO7hH0ddU1UFZRrA1EUceedd+KMM85Ajx49AAAFBQVwuVzIyclRHZuXl4eCggLlGFboyPvlfTymTZuG
xx57LM6vgCCSA6PeWPqYHUkds6MEKPMtA0Cw9D+LrjcWJMNAZLPU8zE98vH3M9oa7jess6M9TnPOQ+d3w0O
8AcuLgB8fBAB83/jv2La/
Fe8oHWo3lj4sk2edMXPXqLOx9MdZETvsr3V5PJ73q0ezoKXLyuIerjcWKzhbNkiDIAhoV5Mx9sY1/
fHNukPIz0rBW3/sUaWes93PjXqS1Tas2LHbBNMmpVou6dsCl/
Rtodv+z5EdUVBajYv6NOeel1ojIrTB0awby8JbDUAdZyOLk5V/
ngAQdGGxn6OOuRmaczWWHa3YYSw7cqyYIAhIczlUxRm1P3rYj+6yB0dYrkJdlySN2Jk0aRI2btyIP/
74o9av9cADD2Dy5MnK89LSUrRsyfnlRxAnIeqYHdayo8nGEkMLrDr1XDC07OhjdoL/
h+rsGGddmRUVfP3q/
ob75DnJ2E0ClFUNQ82+cBdOB6qLgaa98Xv25cD+QuNjGdi1yi7o20Vwa9mYLOpqq4x+v9Yax8Nht2Hm30+H
xxdAw5oidWyszw93noXle47jihrrlhVLSfgKyqHHrRqps4dGdc/
HqO75eH1BsFE0W1TQbVCxuS5hs7zSnPa4LMyZKU68UtOrjId8z9nPgtthU73/
VoQtAKQ69XWVZLQ1eNj4H56wY4WT0x4Myv/l7mFYuP0I/s
ZY4VJddpXYMaublIxCB0gSsXPbbbfh22+/xW+//YYWLUKqOT8/
H16vF8XFxSrrTmFhIfLz85Vjli9frhpPztaSj9HidrvhdidXWhxBxAvJwLKjNaywMTt6yw5/
bH3MjsayIxl/
EUba9ZzFyI2lj9lhjjP60q06Aaz9IPj43MchrbSe4aNNgTdLfQ87D6jdCLzDrC6A2qwmtsN6l/
wspcYMEF7IAOEFEfu5Msoekq0ZwZid4OeGXWwTtSSylp3abmlwfq+mWLbnOMbUFEtkU89z0pwqS4/
V8H21G0stXtjUeADIZwoCqlqTKGOFjpfjddo1yVCsdLxrAvrvgUQJ10iIKmYnXkiShNtuuw1ffPEFfvnlF7
RtqzZj9+/fH06nE/
Pnz1e2bdu2Dfv27cPgwYMBAIMHD8aGDRtQVFSkHDNv3jxkZWWhW7dudfNCCCKJkKxadpiYneBhoZgdo0VW/
pI7XuHFvZ+tw4aDwTi7kLVFUrJCtESaes6iTvnmbwfUFiBu6ZOAD/
jyH4CvMtjNvO0wWCzZEry2Jl5IV0GZc45R5WZA61bgBShHlsEmYyaSrCzwrRuZ13pplp2Cy/
q3wC3D2huKJzmw1cO4sVirSqwWALn6cL5Jp24eLqaCslE5AkBfl+n18caWGyNevqovltw/
XMmQYoN9c1JdaleeRWHLBhXrxI7GssMGCfPut9olZvy50BaZ1Fpvw2WQJQMJtexMmjQJs2fPxldffYXMzEw
lxiY7OxupqanIzs7GhAkTMHnyZDRs2BBZWVm4/
fbbMXjwYKWY4XnnnYdu3brhmmuuwfTp01FQUICHHnoIkyZNIusNcUoSScyOXQgVoWMtO0Y8+d0WbCsoQ2m1
Dz9uCrl+7Iwbq9hA7Hj90S3cgFmdHc1x4Sw7Gz4Dts0FHCnAmP8AGlfUkPaNMKJrHjprAjt5YzrsnADlCC0
7GW5zN1aUWgdmutIsHuft60/DwRNVqrR/HoIghM1gkhf2Sib1nHW7xBqy88GNA/
Hh8v04p3MTXPLaYtW+f47oCLtNwPAu+jo+rGWnqUnGUOMMN07UVFWefeNADOnQOOI5CoKgErt9W+Uoj7Ui2
Op7fVaHJpiOYD06rUDJ0tQhYjOztA1RAbVlxyx2SSuQtZadfq0a4NELuqF1HEoD1BYJFTuvv/
46AODss89WbZ85cyauv/
56AMDzzz8Pm82GcePGwePxYNSoUXjttdeUY+12O7799lvceuutGDx4MNLT03Hdddfh8ccfr6uXQRBJhbrru
Xk2lrwOB1SNQAVTm/
qnqw6oYg2AUCyCJElK2X0tsVh2WLVjFqDMwhUZG4PtIHDmXUDbYEFUbYbVhDONA6W1MUF6N5b+HLOYHfaXN
TdAOUq1YxRgDpgHKA/vwk/
3jwY5K0iu7AsEA2rvPrcTnp23HU9dom8xEAlNs1Mx+dxOKCqr1u3r2yoHZxsULGTFDq/v0/
AuufhlaxHG9W+Bp7+vyXKKIIjZjHaMGNh0KLos4J4tsvH5rUPQPCcV989Zr9pnJlh4VkL288dmcWnRubE4r
urrTRIMkoGEih2zP0iZlJQUvPrqq3j11VcNj2ndujXmzp0bz6kRxEkLW0FZMrPsSKEvfn9ACv09CuFjRdgF
DADscuo5YOzGirCoIAsrA7SuJBb2CjqNUXEM2P1r8HGPccx4zHXCuFbYawdjdrQByhzLDnNO4wy30gQSABq
khUp18K4csJqiE8F5HQ2sVvFGtjqUMJ8Ht8OG20d0xA1ntjXtXB4JvPYP3ZpmcY4MEs6y89a1p8HjF/
HT5gLuObEgCAJ6Ns/
GhoMl6NMyR7XPynooIxfJ1Db41CYQhIO1YO49pq8DJcMGRQMw7XWWrCRFgDJBEPHD0LIT0IodSfkl6PEHVI
1AI11iHSo3Fr/OjtWigjxYEaGKc9AqBGbiOuExbyog+oGmfYDGHUPjqaw15vPQZ2Op9/
POZy1RrRulqcROQ6Z/
F88SdWYUrhPAvBjhlae3xIETVaoGnLVBKkfsyMIkXkIHUMcBNUp34c5zOyHXJI6HFUe8eB+bTUCqy67qd2X
WdT5S3pswAK/
+uhPjB7ZWbY9G1pZrGnxWcFpsmNEoww27TUBAlEzjw7RWH55lJ9lJaIAyQRDxh1dBef2BYhwsrlIfh5DZ2+
MTmZgdwXIWkIzdbsGNFYvYYa9lkl7OWrVUwqNoC7D2/eBIY/
6jOsdyujq0okvfAJGbes4slGzxOaddQKZJ1/
M7R3bEuH76mi5WMLMSOOw23D+mi6oBZ20gx+zIPZvcDlutpCWzVpfrhrTBNYNamxytFkdmVX5ZK1645qGRk
JPmwr/GdkObGpdWl/
ygdWVk18hdiOUe9d8ab5685p4s790wAHabgGsHG983ba2oaAPnEwlZdgiinqGuoAzsKCzDha8s4hwnKQGjH
r+osuxEiixAJJMAZbM6O+FQFRVkA5TN5sR+Qa+aFfy/y1ig1SDVcRFZdsJVUA4ToCz3KgKC1g2zxX9U9/
yoC+9FKlZrA9kaIE8lkuJ9keCw+HmQYa00lsVOLc0dAL65/
UyUVfuVGkmRUM64k9s0SsMDf9FXLn7z2tNw+4dr8MAYflXjIR0aY+W/
RuoyuVhOhtTycJDYIYh6BrvQSZKEtfuLDY4LVWD1+AOKNcCszo4R8sJQ5Qvo0lIdNWbyWOrsGFlftN/
B7LyV4zzlwLqPgo/
7/50zduhxRDE7nGO5qefMOWwvJG2pfisFCq2SDL+8UzQF78xSm2PBqK2IEey94QUoy7DvW7xidng47baohA
4AVDBurAVTzuEe07tlDn67l79PpkGY65/8UofcWARR7xA1lh2jdgXqmJ2QEIlG7MgLQ3m1Pr3VL0ro+eiP2
FpQptsXDey6oxUIrNBTdq14K1gtuWE7oL3+S9+qpUg1JmraRZhUcGaPk2EDktM1TRj1fbaiX2KSwLCjayBZ
W5YdFitusqaMK1FbhI/FVkdiJxbuHd0ZAPD3M9rU7oXqgdohyw5B1DMkjWXHWOyE6p54/
UzMDgRV7IsV5Jgdo/
TyyggDJ7UYBiibYBMEoOIosOjF4IahUwCb3rogGFiNwmEXBAQ094l3PmshYF0F2mJ8VtLYrRJtFlc80Raiq
wuxY4UMtwPLHhwRNoaI3RPPmJ14MuHMtji7cy7a1nJ9m/rgxkrOd5AgiKjRxuw4uKWENQHK/
kCo67mgL3AW7suezcaqDdivWrOAYkl73I8PAlXHg9WSe17GHVtlKYrgG5HXCJS3JrDijC36luGuPTdWMsTs
ZKU6VK+xWZjO4PHA6j3Ly0pBTpq564YVjE5Hci72giCgQ26GabPZeKAdvlNeBv/
AJIbEDkHUM7QLnZFOESUpFLPDZGPxYF0up7dpoNsv19mprVgRw67nJt/
xtl3zgfUfA4INuPBlwM4PwFTHAFlfNGyCNYGituyEFn9toTa9cIp+AUuCkB0IgoCOzKLYqQ7q+8TTAsFaSJ
PVjVVXsLL+wb90wbs3DEzgbKLj1H4HCaIeol/
nwruxPH516rk2dZl1uUw4sy3+9Zeuqv2yAKkLsWPWLkKeth0BCD/
cF3wy8BaghXFX9WjdWAKngjIvzoYVZ6xlR1trRleg0PJM9ERbeTnedMoNCZzatAZc2rc5slIcuKx/
dKn6PFiPrFkV7FMBth7UTUPbm2axJSsUs0MQ9QytZcfoe1pkApRf+XWnsl2A3jLAWnayUpzo3lxtJZFrydS
a2GGWfvM6O0Eutf8OHNsJpDYEzn7AdGz1eObzYDOoHDYBgYAmQJnz85GtXM3G7PRqka06zkoHdasMatcIf+
w8qkp1TwSsZac2Kzc/e3lv+EUprhaYgCrY/
dQWO7ee3R4bD5bgwt7NEj2VqCGxQxD1DK07ymjRDFp29IsD7/
BUZpHPSnXqytTLMQO1FRjLihBVewftgZIEJ/
z4p2NO8PmZdwEpxq0DtGOHExgN0l347197wWm3IcVp11WF5ll22ODsTLcDn986GH/sOKYrfmcl/
scqL1zZB+8s3ovLT2sZ/
SBxgI3T6Zhbe5YdQRDiWuUYiKx9Q30nK8WJ9yacfK4rFhI7BFHP0H5JGy2awZgdTnYSZ8FmO2Wnuuy6rsey
mT8Sy07DdBf+d3V/tGqYFv5gg2ws7S9uCcAV9l/RQjgKZOQDp98YdmgztxiPyxgBoT2cZxlihaHNJqB/
64bo37qhfh4W0tit0jjDjbvP6xz1+fHijA6NkZPmRIcmGaoO3CcDRoH9xMkJiR2CqGdo9YaR/
mCzsVj4lh21G6tEUyXZrmRjWRc7WSkODGirX/
R5sFMyC1B2idW43fFF8MnQewBXeCEVSbsI3bwsNAKt8OprD/
HHiujSJwXZqU4svn940qZumzGscxOc2aExejTPDn8wkfSQ2CGIeoZWcAQMat+wMTssvDXXZbfhyYt7wBcQ0
STTjcMl6j5b0Vh2zMrT6+akcmMZiBO/
F5PLn0WeUIwDUmO06HedpbHN+oqGnZfJPGUqPNZqDFnps3Uyoq0ndLLgtNvw/
o0nt+uGCHHyyW2CIEzRGleMujSw2VgsRovs1YNa4+9ntAXAcbloxE5OmhNTRpm7UTJNqtfq5sRei7XssAet
eRdDvIvhkRx42Pd3wGGtBL+heLKAFddTZZSWnfpQyI0gkgUSOwRRz9DG7BhVNQZCvbHU6BdZbUVlbREzrWX
HLggY1T3fdJ7a3lBmsO4hu1GMzfpPAADP+C/
Hr2LfqMaONExDn3qup7nFYnr6pqKRzYUgCGNOTvsiQRCG6GN2jF1LVmN2tGjFjlxUUL6WIAhh07i1FYTNUF
l2eAHKx/
cA+5dBhICvAmdYHheIrBFo+LH05/9rbDfYbAL+NqCV6blW+mwRBBEdJHYIop6htcL4A+rnvVpkY/
2BEtw1shPfjWXhGkaWHbmmjE0ILxzS3Na7YBtWUJYfLH0dALDG0QdFaGB5XEDrxoroVEsVlJtkuvHc5X0sj
KV+TlKHIOIHiR2CqGdoLTvaoOEnLuqBVJcdHXMzsGTXMd35PJGiNQ7ZBa1lR1AdZzOw7DjtAnw14it6N1Zo
e7DZ5zFg9bsAgM9SxgHllofVjR15Npb584jG0gUok9whiHhBMTsEUc/
Quq38GrHjtNvQKS8TgiBwY3ZisezI8PpGAUAKY0mKJEuHHYkVAYIAYPkbgL8KaNoHa+y9LI8pY1aROZJ5RX
O+aiyK2SGIWoPEDkHUN8LE7DiYSrNWs7F0mUK6mB29VYI3Diuu0uPgxkqRqoHl/
xd8cuadUSkEdcxOZOfq6+xEfHnDc0nrEET8ILFDEPUMnWUnYJxJZTVAWevG0lpyHJpS/
TYb38rB9i7SNsI0Q9Ubi7n2OZU/
AFUngIbtgK4XmnZuNyKWooJaV11Mlh2NvKEAZYKIHyR2COIk5sWfd+CzVQdU28LF7DhsYSw7FmwK4erLBGN
24ih2mKFkq5IAEWPKPg9uHHIHYLPrgrOtoMruivDceHYqJzcWQdQeFKBMECcpGw+W4PmftwMA/tq/
hbJda93499wtqucqyw6vzk4UqefaPkIC+JlNrAUo3RWbG+s0YTsaB4oAdzbQ+yrLY2mxcYRUtMQSVKzP7CK
1QxDxgiw7BHGSou1PJROuPxUrTHhuLB7aEY2ysWRsgsBdrF12GzrlBbtfn26xLxagdWMF/
x9rXxp80GUs4EwJzjMKN5ZhkUKrc4sh5kc1jsm4BEHEBll2CKKeoa2grMUe1o0VHrvdXOwIAt+yY7cJ+GbS
mfAFxMiysVjriyAgDdW40L44uKH7xcq+KLROTKnnWmI5P55dzwmCUEOWHYKoB7ACJ9yCz8bsuLgByuEXWa1
lhxeoa7RYO+22iJtDsnPKLN+Dz1yPoaFQjkJHM6D9CGVfOKHHQ+XGilFfxHQ+ZWMRRK1BYocg6gFsEHI4Nx
ZrldFaZABri6y2hxSviSVP7ETjZgqeV9OGAiJ6LrkT3Wx/
AgC+y7kasIeEUzTDx1JnR4uV4G7Dc+OY2UUQhBoSOwRRD/
CrxI75sdq08Uv6Nlc9FwQgN9NtOobWsqOVSIKg2xQXzrctRUbxVgDAg74JWJJ5nvqAKNSOukhhjGInhm9UK
60nCIKIDhI7BHGSsGTXMUyYtQIHTlTq9rGWnXDWE+2i+vwVfVTiRoCA2RMH4sLezQzH1Ack66/
Bc+lEadgJXhMB3OX4DADwrO+vmB0YEZeMpVh6YwHqexNHLxZBEHGExA5BnCRc9eZSzN9ahLs/
Wafb51eJnXDZWPpl1aaybgAdcjPx0lV9DcfQVw62VlQwmpgamXH239DOVgCfuyHeDoxR5qoaP4px1TE7iQt
QJjcWQdQeJHYI4iTjYHGVbltEMTscsWOPobAe7xyzAOVoyAiU4h7HpwCAQz3/
gQqkKtdhiS5AObbXzhLLSyY3FkHUHiR2CCKJKan0YfLHa7Fo51Flm7yes6ImwInZuXd0Z2Sm6LOeeK4f1Sb
uImsuIngF8eK2WB/
fg+kFNyBXKMYhqSGOdb2auU4ks+TDFhKMtahgPAUeWXYIIn6Q2CGIJObpH7ZgzpqDGP/
WMt0+1nXFi9mxCwLXZcVDbd2IfJHVu2DiuFgvfR2ZYikqJTcm+/
4BoaaAYPC6WstO5MPH0ghUCzUCJYjkhMQOQSQxu4oqdNtkV02AafDpF0Xd/khcSeEX/
MiWXsMA5UjFiLcSWPcRAOAW351YKnaLq9sJSJ7Uc3JjEUTtQWKHIJIYb0DUbZP1gpFlR3ZvCYL1VOrwAiIy
N1bcLDvbfwA8JThiz8PvYk8A2uwpjWUnCkeWuoJylPOMw/
n6dhGkdggiXpDYIYgkxuvXix1ZzLACRxY+v2wtxJdrDwEILpZWF19V5+8oFlm9C4YfsxOxGNn8JQBgadrZk
Gq+rrSZY6rxY3RjxWzZiSkbi8QNQdQWJHYIIonhWnZqFnTWdSULnxtmrVS2RWJdiTVuRSd2hDgEKXvKge0/
AQCWpp6lbDbLHIu9EWisAcqJOZcgCHNI7BBEEuMzcWOx2Vj+gH6VF2B9AQ3nxoq0UKH8XJ8abm0+AIBtcwF
/
FdCgLfY6Oyib7cy3VjxcZfF0Y5FlhyCSExI7BJHE+DhuLDkAmRU4AU6PCJtNsLyACiauIUvn667N3x4R6z8
J/t/
zMtWkVAJH58aK3LQTa40hgiCSHxI7BJHEmLmx1DE7+uMEQeAWEOShPiyamB2Llh2rA5YfAXb9Enzc63LVLr
MA5WhQxeyQL4kg6iUkdggiifHwLDs1//
OysTLdoSKCkbix1HEr+v3NclJNz9fH7AiGY1li85eAFACa9gEad1TtMnO5RdcuIn4xOwRBJCckdggiieFlY
0km2VhZqU7VcVYtH4KBgHjnhgG4qE8z3HNeZ/PzNc9l7RR1OwfZhaWx6gTnyn8cHN/
a8Cy2OMbsEASRnOhryRMEkTSYBSjzLDsZjGXneIXPsmVFnY0VejKsUxMM69TEwvlGbiz1cX8/
o234yRzfAxxYDgg2oMc4AGoRYzOK30F0dXZscQ54Jggi+SCxQxBJDCfumInZ0aee+5htR8qrI0g9jy1Il9c
uQjvuC1f0wUV9moUfbMNnwf/bDgUy802vFQ/
Ljp0sOwRR7yE3FkGcZMgp5zzLjsfHiJ0yj07sPHd5b+6YMdfZ0UgkXsxOj+ZZ4WNiyouAFW8GH/
e8TNlsZNmJR4yNQDE7BFHvIbFDECcbsmUnoI/ZYQOaR/fIV2UXXTOoNS7t14I7pDpmJ/
YKyoplJ9KCfXPvAcoLgSZdFBeW7loGj4FoA5TZxyR2CKI+QmKHIE4y5AU9ILGWnaDI8fgDAID/
jOuJi3o3t2yxsausG5HPSS929KnnYYXEkW3A5q+Cj8e9BTj5GWBmNYFiraBMbiyCqJ+Q2CGIJEXkBezAvDe
WbNk5q2MT2GyCZbFhi/GbwLjODrstzCAL/
xP8v8v5QH5Pk2sxj+Ng2zHrtUUQRP2AxA5BJClVvgB3e6g3ljpmR5IkJVXd5ZCbZobOM1vIY13wdUJGkMey
aNn5czGw8fPgicPuDXOt+Fp2bHEuUkgQRPJBYocgkpRKr4HYAceyE5BU8TruGrFjVWzEHLMDvmWH3WpYnVg
MAHNrBE7/64Cm+iBqNqU83q4mo7R7giDqDyR2CCJJqTISO7JlR9MbSy127ACsu5Hi3fWcl3pueP3lbwKFG4
CUbGD4w+GvZSLGOudnhj1fCxUVJIj6D9XZIYgkxdCNVfM/
W2fHL0qo9PoBBIWH064PEDazWtRegLJ+m4rje4CfHw0+HjEVSG8c/
lomP9Gev6IPnp+3HdcMbh12HN68yI1FEPUTEjsEkaTI4kUHJ2Zn+Z5jePCLDQCCLixZ2NjC9LwK7YuvG0se
LqwbbenrgL8KaHMWcNoEw/
HZWByz2eVlpeDpcb2sTJmZl7WxCYI4eSE3FkEkKUZuLF421pdrDymPZRcWYL2GTPzdWPqigjoXUVUxsHZ28
PFZky1fmH0d0QQka2FTz+MwHEEQSQiJHYJIUso8fMsOrzcWixycDFiPR4m1XYS+N1aYY0QR+OJmwFsGNO4E
tD3b8rXi7WmioGSCqP+Q2CGIJKW82kDs1JgzjOrwuJ18sWPmnmLr7ETXLkIzHmcQ1bZt3wHbfwAcKcAlb0R
U6CfecTWsMIuHpYggiOSDxA5BJCnlBpYdkROzw8K6sUzdSGD3mTVhCI9Wf/
CsJYqeCfiBBTUFBAdPApr3i/h68UTtxiK1QxD1ERI7BJGklFX7TPcHDMSOw6BInpm7JtaigvoKysH/
uQ08F0wLppq7MoHBt1kan32l8bfskBuLIOo7JHYIIkkxitmR8TOp5yxept5OVAHK1qanwihAWbft9+eA358
JbrjgBSCtYczXipV4BzwTBJF8kNghiCSlzCBmR8bIssNWXrba5NKqBcgIfcwO5xondgO//jv45JyHgJ5/
jfg6wbFrL2aHIIj6CYkdgkhSjAKUZYxidthihGYdwlnUdXYiRytA9IJJgnP+VED0Ax1GAsOmRHYBlTuM3Ry
7KUZl2Yl5NIIgkhESOwSRpEQbs8PW57Ha9ynedXbk53Lm2N/
tP8C2fS5gcwAjH4v8Aqqx42zZIdMOQdR7SOwQRJJilI0lw/bGYvEG2Jgda60QWHdXNBWU9XV2Qs/
H2X7DI873gk9GPALk94h4fIIgiFigdhEEkaREG7PDYrWooFV3l1VsAoCAD9f45+BG54fBjYNvA4bcHvvgtY
hEEcoEUS8hyw5BJClhxY6FhVldZ8eaGysauNlY86bi1sD7cAoB/BboCZz7RPxTqQiCICyQULHz22+/
4YILLkCzZs0gCAK+/PJL1X5JkjB16lQ0bdoUqampGDlyJHbs2KE65vjx4xg/
fjyysrKQk5ODCRMmoLy8vA5fBUHUDrIbS+5grsUoQHnSOe2Vx3aLjUBjrbOjFVKtS1cBS18DALzkvxgTfXd
HVCVZCxX7IwgiFhIqdioqKtC7d2+8+uqr3P3Tp0/HSy+9hP/9739YtmwZ0tPTMWrUKFRXVyvHjB8/
Hps2bcK8efPw7bff4rfffsNNN91UVy+BIGoFSZIUsZOT5uIeE9DU2bllWHv8PHkY7j63s7LNelFBWDrOCPa
MTFRi7O4nAABf2M7Dc/7L4QH/
NSQb5MUiiPpJQmN2xowZgzFjxnD3SZKEF154AQ899BAuuugiAMC7776LvLw8fPnll7jyyiuxZcsW/
PDDD1ixYgVOO+00AMDLL7+Mv/
zlL3jmmWfQrFkz7tgejwcej0d5XlpaGudXRhCxUeULKDE5OalOHCnz6I7RBiinu+zokJuh2ma5XYQqQNkaZ
3duggXbjqBLfqZKID3seA/
Z3gKgQRu8XHGdxdHMqSsRQhYkgqifJG3Mzp49e1BQUICRI0cq27KzszFw4EAsWbIEALBkyRLk5OQoQgcARo
4cCZvNhmXLlhmOPW3aNGRnZyv/WrZsWXsvhCCiQI7XsQlAZgr/N4k2QDnNrT/
OajZWNG6sF67og3/9pSvenTAANgFIR
TVusX+Nyx0LIUEALnkDlUi1NliUkCWGIAgrJK3YKSgoAADk5eWptufl5Sn7CgoKkJubq9rvcDjQsGFD5Rge
DzzwAEpKSpR/+/fvj/PsCSJy/jxWga/WHoQoSorYyXA74LDz/
0y1YifdZdcdY7V+jrpdhDW1k5PmwsSh7ZCbmQJh63dY7L4D9zs/
AgCsbH4N0GqQpXEIgiBqm1My9dztdsPtdid6GgShYth/
FwAIiphOeZkAgDSXQ9XYU0YUJV2AcipX7NRBI1BfNfD17WgglKNMSsVP4mk43PoWnB7hMMkAWYoIon6StJa
d/Px8AEBhYaFqe2FhobIvPz8fRUVFqv1+vx/
Hjx9XjiGIk43le47DU9PM0+20cS07AUniWHb0v12EaOrsRDrhTXOAquMolHLQ3/M/
3O27FZL95AhI1tKzeXaip0AQRC2QtGKnbdu2yM/Px/
z585VtpaWlWLZsGQYPHgwAGDx4MIqLi7Fq1SrlmF9+
+QWiKGLgwIF1PmeCiAeSBHj8wZYPboeNa9kJiJKu63maW2/ZYXWSeQVl5kkkaifgA/
54HgDwbmAUvHAGr1Uz53gF/Na2weWP+87BF/
8Ygo41FjWCIOoXCXVjlZeXY+fOncrzPXv2YO3atWjYsCFatWqFO++8E08+
+SQ6duyItm3b4uGHH0azZs1w8cUXAwC6du2K0aNHY+LEifjf//
4Hn8+H2267DVdeeaVhJhZBJDsSJMWy43LYVLVyZAKihIBa6yCNY9mxWkFZ5caKRO2sfBs4uh1Ia4wPis8Lj
aH0xrI+VCJp0SANLRqkJXoaBEHUEgkVOytXrsQ555yjPJ88eTIA4LrrrsOsWbNw7733oqKiAjfddBOKi4tx
5pln4ocffkBKSopyzgcffIDbbrsNI0aMgM1mw7hx4/DSSy/V+WshiHghSYDHV+PGcti5lh2/
KOnq7PADlK2JGHaP5ZidqhPAgmnBx+c8iMov0wGIYa9FEARR1yRU7Jx99tmmvWgEQcDjjz+Oxx9/3PCYhg0
bYvbs2bUxPYJICBLUbiyeZYcXoMxLPRcsZmMh0pidkgPAB5cFBU+TrkC/
64Cv5im7491I3Oh74iQxHBEEkWCSNmaHIE5VgjE7smXHBicnQDlo2dGIHae5ZccsZkdt2QmjVMQA8PlEoGg
zkJ4LXPQqYHeoxpCvRWKEIIhk4JRMPSeIZIaN2XE77HzLjsSz7JjX2TFrTWWLxLKz+CVg32LAlQFM+BFo2E
4/BnmxCIJIIsiyQxDJhgR4fDVuLCc/G4tn2XFxLECWLTtW3V2H1wG//Dv4eMx/FKGjPc/
sWgRBEHUNiR2CSDKCMTshNxY3GyugFzs895PNYvCMyo1lZNvxVQFzbgJEH9D1AqDPeMMx4h2zQxAEEQvkxi
KIJEOS1G4snnDwavPODbBZtLYIarXD5+fHgCNbgYw84PwXdSYglRVJrrMTp6Adiv0hCCIWSOwQRJKhzcbiL
fRev1rs8FxdQCRurDDxNrt+AZa9Hnx80WtAeiPOIPzxCIIgEg2JHYJIMlR1dpw2+AN6uSOLIQD4/
NYhaNs4nTuW9XYRzGPdxcqAr24LPj79RqDjSP4YzGNyYxEEkUyQ2CGIJEMds2OHJAV0x1T7QpadXi2yuenp
gPWu52ycjs4qs+BpoPQg0KANcK5xzSs2PihkRYpTuwjyYxEEEQMUoEwQSQBbNC8Ys2PeG6uasewYubAA613
PDS07JQeA5f8XfPyXZwEX34KkPU+eEokUgiCSARI7BJEEsJlV2qKCdk6BHNnN5bAJpiLGzrW26OG2ixBF4K
eHgYAXaHOWofsqdJ41YRVPSEwRBGEFEjsJoKCkGtO+34L9xysTPRUiSWALBEqQlABkt9MOh10vHGTLDy8tn
UVd+8bacYpLa+HTwKY5gGADhj8U5hVYz/
wiCIKoa0jsJICb31+FNxbuxtUzliV6KkSSYGbZ4bmp5P1GsToyVrOxdNWPT+wF/
ng+uOHCl4FWg8K9BLD2ofhG7BAEQcQGiZ0EsG5/
MQDgz2Nk2SGC+LViR66g7LBzBY28n2f1YVHpJKvGFl8l8NkNQfdV22G64oFWrmXWmiIaSDQRBBELJHYIIgk
IaNxY6kagxpYdRxhVEU2dHcfiF4CDq4DUBsD5z1tudEXtIgiCSFZI7BBEEuAXQ6nkAZERO05+1/
OQGytczI7FOjs1/2eiEvYVNdlX5z8PNGpvYfZBWOEV9wBlikQmCCIGSOwQRBLAWnZ8ATb13NyNFS5AOdJ2E
ZfYf4fgKQUadwa6XmR1+jVzDc0zlHpOIoUgiMRDYocgkgC2SrJfFJXUcpfDxo3LqbYYoMyKIfOigkEutf8e
fHDa3yMOvHGpxE6cLTuG45GYIggiPCR2CCIJ0Ft2QjE7Lo6gqZYDlMOmnrMZUibZWDYB7YWD6GPbDUmwAz3
+GtH8Aa3Yifh0c8hCRBBEDJDYIYgkgM3GKq704mi5B4AcoKz/
M630ytlY4QKU+Y+1CAAusf8RfNJhJJDRxNrEGVhRJosskigEQSQD1BuLIJIA1rKzvbBceex22uF06AVNWbU
PQHjLjioby+TYxsXrcY3jq+CTXldYmrMWnhsrXgYZEk0EQcQCWXYIIg58vuoAXpq/
I+rz2WwsFrfDBidHpJRW+QFEVmfHUOvs+Bmjl10bHFdKg9DlL+EnzKFW3VgEQRAxQGInySmt+QVPJDd3f7o
Oz83bjg0HSqI6n7XssLgdNq5lp6Qq+LlwhgkiVqeAcxTI8T3AZzdAgIRlYhfc4L0HcKZanjcL68aq7To78r
WGdozc3UYQxKkHiZ0k5s3fdqPXoz/
h81UHEj0VwgS5jxUAHCmvjmoMI7HjMojZkcVOeMuOSZ0dXzXw6XWApwRHcnrjGu8DWCl1iWzimrnKxFvr3H
1eZwDA3wa2AgD8cf85ePeGARjdIz++FyIIol5CMTtJzL/
nbgEQtBqM698iwbMhjChjrG9ef3TRJTyxc2HvZnA77Ny4HNniFy5Amd2ts7b88gRweB2Q2hBL+j4D7/
dHIp84A8+yE686O8M6NcG6qechKzX4lZWbmYLczJS4jE0QRP2HLDsJINJfvYmuvF/
tC+C6t5dj1qI9hsf4AiJEA+tEfaes2q88Lq2Kzu3o19y7xhluvHRVXwBqi4n2mhEFKLMfJF81sPrd4OOLXk
FVWuwWktq07ABAdpoz/pWZCYI4JSCxkwAi/bpOdJ+h95f+iYXbj+DRbzZz93v8AQyb/
isuf2NJHc8sOWDFzvFKb1RjaC07aS678tiscGBEdXbYQ3f8BHhKgawWQKcxpjV4rFKrRQUJgiBigNxYCUAQ
hIhychOd2XK03HwB33SoFIdKqnGopBqSJJ1yv75ZN9aJiujEjtayoxY7xvczXAVl9rOjelvWfxz8v8elwUr
JcXjL1HV2gv+fmrY+giCSDbLsJIBIxUuifyXLfZqMYN1X2kX7VIDNmDsepdgJaFLPLVt2IgpQrnlcVgBs/
yH4uPdVuuOihSw7BEEkKyR2EkCkLoNELxweP78GjAyrb7xhjk1mdh8pV9owREIp68aK1rIT0Fp2QkZXczdW
JBWUa54segkQ/
UDLgUBeNwBxMeyQ2CEIImkhsXMSEK6zdW0jN6U0go03OVnFzuJdRzH82YW4Ioq4o9qI2Um16MaKLEAZwJZv
gKWvBjcMuUPZFw9twi0qeOoZ+giCSEJI7CSCky0bK4wbyxcICRxv4OQUO5+s2A8AWBdFUcDaiNlJcfLdWFr
hE4kbS5BEYP7jwSeDbwO6nh/aF/
eYneCAQzo0AgA0yXTHfgGCIIgoIbGTANh1xUq6duItOyGxw6sHw7p+TlbLjhUDxPEKL9fNxVp29h6rxJRP1
0V8fe19ZUUNK3ZSHHbNcWHcWMzuzB1zgKPbgZQcYNi9quPikY3l5lh2/
jOuF6aM6ow5tw6JeXyCIIhoIbGTANhf2z6DnkhGxycCNmbHx7HcVDP7w8X3xML+45X4aVNB3ArVsYTTnEWl
1ej3xDz85aXfdfvKNC09Pl11gHufzNBadljhwIpdt1P9J2s19bwRStB48ZPBjWfeCaRka46LaLpcnJyigjl
pLkw6pwNaNkyL/QIEQRBRQmInAbALizYwlUeiU89ZawZPzNSVZees6b/
ipvdWYd7mwriPHU5ALdgWrC68+0iFbh9r2ZE5XBxZ2whtNpaRxcatseyEq6BsEwRkoQIfu56Aveoo0LgTMG
iS7rh4lAugAGWCIJIVEjsJgF0GjCwArFsj0QtHFSNmuJYdVuzUQczO0t3H4z5mOGORWfq9LHaev6I3OuRmA
AD2Ha+M6Ppay46h2InQstOgcAm+cE1FB9sh+DOaAVd9BDhcuuPinY1FWocgiGSCxE4CYJc1n4FlhxUQiRY7
5Yzlgme5qeuYHakWUnzEMGqHtWhp46xkN1ZWihOtatw1kYodfcyO8Z8mKypMA5S3foee869Fe9thBCQBx8a
8ATRqzz003gHKif7MEgRBsJDYSQCs68rIslOlEju1PiVTysKKHdF0f7yphZAdldjhvSes2PnPD1ux5XCp8l
y+PxluB1o2SAUA7D9hXezsP16J/3y/VbWN1w8LCIqidCsFBw+tBT6/
EQIkrBXb4RbfXfA3P91wDnFvF3EKfbN8dNMgtG+Sjg8nDkr0VAiCMOAU+kpKHvxMfIZRzI7aNZS4YiWSJKn
FTlg3VuRF+aKZU/zHDD3mZVyxYueN33ZjzIuhQOUKb/
D+pLsdSiBuJJadK95Yggqv+pouA4tNQJRUBQe5bixJAr6aBPgqUdz0LIzzPoZ54mmmojnedXbiIZ5OFga1a
4T5d5+Nwe0bJXoqBEEYQGKnjhFFSV1x2MCyo3YN1b6AMMLjF1VzTArLTi2MybqRqjhip5wThCxT6QkerxI7
x6yLnUMl+mBmI4uNKEpId4csO9yyBAdWAIUbAUcqdg97EQEEjzdzLcWjvAEv9ZwgCCIZoEagdYw2ENXIjaU
SEAks1FeqSavmWnb85tla8cDPXLc23FiVjGWFVzFaex9Cc5FQWSOO0l12dGuaBQDYfLgUJZU+ZKc5o5qPkd
jxixIy3CatJAI+4Nengo97XAoptYGyy8x6c3bnJuiSn4kezbONDwqDyx4SYadaM1iCIJIbsuzUMX5NirElN
1aEAkKSJDz85Ua8sXBX5BPUoLVocC073toJUD5cUoWb3l2JJbuOqWr51EaAciVzv3lurJIqvtjx+EXFKpTq
sqNlwzR0zM1AQJTw244jYa9rJKK65Gdyt4uShMyUkIBSBSiLAWDOTcDuXwFHCjDoHyrRYeZacjvs+P6fZ+G
Zy3qHnbMRToemNQVBEESSQGKnjtFadoysNqwrRZSClo2SSh8KS8PXb9l8uBTvLf0T077faqlCsxmVmlgSfl
HB2kk9/9cXG/
HT5kJc9eZSlQA5UeFDUVlkdWzCUeUNiboKbwA7i8pVsUFGYoe9P3IszfCuuQCAX7cWhb3u3qPquj29W+Zg+
l97YUiHxtzjA6KEjBTGsiNHApcXAe9dDGyaA9icwBXvA/k9VPImnACJ1RpD2VgEQSQrJHbqGK0lx2/
BjQUERcQlry3C8GcWoNxjHD8CqF1JxQaLtFUqPBYsO7UUs8MG+bJi57sNhzHg3/N1c4uFCk9o/
Ee+2oiRzy3ErMV7lW2lhmInOAe3w6bEvfRvFXQd7TpSrjt+6e5jWLg9ZPHZoxE7p7VugMtPa2k4T78oIZNx
YznsAlC4GXh7FLDnN8CZBlw2C+h4LgC1gKltAUJFBQmCSFZI7NQxWnFjVGdHGyRbXOnD7qMVqPAGUMAJaFW
dy1gbjpZ7opxpkErNPOqyzg67XGrFHwAcLK6K27XY+y03A33i283KNp5lZ+Xe45j0wWoAweBkmUYZwaJ92g
7o1b4Arvy/pbju7eXKeHuPqgOZwxUJFEUJmTWWHQEiemx9Afi/
YcDx3UBOK+Dm39QNPplz61LskNaJjo41RSlPa90gzJEEQUQCBSjXMboAZYPeWNq4kf2MlSOcRYO1Qhwp86B
TXij+wx8QUVzlQ+MMa12oKz0asRMu9TwGsVPtC8DjE5WgXnZx5lUwjvZaoijhWIVX6cRdUunDcU63cvat4o
mdv/5vifI4jal90zA9OO6JCvU5rKXneIUX2alOFJSqBVu4rKiAJCHTZUNTHMMtjq/
Rafu84I5Oo4ELXwYycg3PFWr5p42bCVAOV6SR4PPuhAH4ZMUBXDXQ2LpHEETkkNipY7RuLJ/Bgq0VO/
siETtM0KvWsjNp9mr8tLkQ8+4aig65/CBYlkpvhG6sGGJ2Ln9jCbYVlOG5y/
tgbK+mKusAz7JjFNwbjvs+X49PVx3A57cOQZf8TJw1/
RfT430BURe7pEUldtKClp1yjx8ef0DpZ7W9sEw55kSlF22RjsMaK52ZZedc20rcIXyBzkuLcEcK4/664EWg
33VhzSm1bWxhLTtGFkvCnKbZqfjnyI6JngZB1DvIjVXHaLOxrLSLAID9J0IWgLKwlp3Q/
iNlIbEjSRJ+3FQISQI+Wr7f0ny1i3xtWXZ8ARHrD5TA4xcxafZqVPsCqngTDydDin2dkfDpqgMAgFd+2YGt
BaUoNamhAxgHJ7Owhf4yUxyKhaa4MnTu9sKQZae4xsWldUlqLX+QJGDDZ/
jY9TjedD2HnrY9cAUqIEoCdov52DzoGaD/
9YZCh91cl24s7eecIAgikZDYqWO0i5nRolChcR8diNKyc4Sx7LAxLmlua0a9Co5l5+fNhRj70u9Ky4RwXdG
toLVAHSnzqCwRvEJ/ZVFadmQkAMcrzMcY/9ZS/
GmhQCBr2bHZBDSoccWx7rEdrGWn5roFmuw6lbiUJODnR4DPJ2CgLdhOYl6gH34f+RU6eN7DcO9zONb+4rBz
U+ZVy2KHdcE1segmJQiCqAvIjVUH7DlaAUmS0K5Jhs6NZWQJ0caQsL2WIonZOVoWHOfD5fvwwJwNyvbiSn2
MCo8qTur5je+uBADc9fFa/
HDnUFUNHNbyU1Llw8aDJRjUrlHYWJSiUrXYOV7hVfVXOsaJqeFZZI6Ve7CtsAyD2zXiplJrLWYFJeZBzot2
HoPbsdP0GEBt2QGABmkuHC334kTNvCVJwpbDajdWtS+gsvwAzP2uKga+
+Sew+UsAwOv+CzAv0B+rpY54P68HRCwDEFnl47oIGv7+n2eh0utHIxI7BEEkESR2apnSah/
OeWYBAGDrE6P1RQUN6uAcq1Av/
mzMTrnHPH6EFQGyxYTNLAL07hMti3cdxfoDJbo0d1ac7SgKumVYAVFW7cdL83fggt7NcM+n67DqzxOY/
tdepunUAHT1g56auwUbD4aabfKyynjp4OPfWoatBWV445r+GNU9X7efFVXVvoDOsmJlbjzYFg4A0CA9GLcj
i7RVf55QWdaKK33Ke5DqtKPKF0Bb4TC6Hd0I/
PINsGoWUFEE2BzA6KfxnznNlHNVdXZMuqMD6kKCdSF2utZUkCYIgkgmSOzUMn/sOKo8Lir16GJ03l/
6JxZsK8LzV/RRWQeOlastGYXMIh1pNhYAtG6UrurUHW6R/
9ubQctBflaKajsrdgKiBEmSVGLnm3WHAADztxZh3f5iAMAXqw+GFTtFZWoxs2zPcdVz2ULFwgtQ3loQtJ7M
XrYPC7cfQWaKAw+M6arsP8xYcpbuPo6lu4/rxtAiizozFDeWtxIo3ofB2AibrRj2QwEgpzHW/
LIRo2wHkQovUgUPeu79Da5iH/
7j2IWWrgq0FPaipe0IUIDgPwBo0BYYNwNo0R+Y851yLbZdRLhUdRaqfUMQxKkKiZ1a5hemim5RWTW0hpxNh
0qx6VApvl57CFcOaKVs57ltZMIVFWRFwP7jldwqyrJV4c9jFchMcaJhjSUCUAc1y6JIEIIhJIUad1NhqUf3
mgAoQgcAbLZgJpKcAi9JEjYeLEW7JulKfRqt2NGitXQB5gHKbOG+v/
RoimtmLMMNZ7ZF28bp3ONHds0FIODnLYW6fTxXYyqqkQ4PUgQv3PBiQNl2YPa/gV2/
AAEv7gIAF4BlwX8TAUx0MQMcDv67wgEgACV67oCjFVq0agf0uRrodhHgcEFLVgordsJYduowQJkgCCJZIbF
Ty/zO9EcqLPUogatatAXyjtW4bTLdDl32VbnHD69fxPtL/8TQTk2QleLAN+sPY/
zAVkhx2lUioMzjx77jlUrsyGMXdscjX2/
CkXIPthaUYvQLv6NXi2x8fduZyjmbDpXo5tcgzYXjFV5dVeBfLLREWLTzGM57/
jfMv3sY2jfJwPwtRbjx3ZU4s0NjPHt5b/
y4qQCHwhQI5Lqxqn3AsV3AvqWAYIMXdpxt244GKEcjoRSNhVLsk3Ixd0k6PNWVeGfRbkwc2h5pqEY2KpAtV
NT8X47bOw7EnsNH4LLtgAMiUgQPMlGJRkIZUuGBG140E46jqXAMTYVjyBI0893DPE7JxlGhIU5UeNE4JYAG
mZnYfNSPCsmJJg0aYPtxP0qRjmNSJkqkdHRq3QKz96Rjr5SPwX2648Ur+
+pe64zrTsO9n63Hc1f0UbmxIkn1p35VBEGcqpDYqUWqfQGVJaSorFqpfgsEFx/ZKsLWYJEL/
wFA05wUlBWqBUaFx4/3l/6Jx7/dDLtNQNPsFBw4UYUKjx93jOioWHbk8TccLFGq+Q7vkosnv9sMX0DCy/
ODgbfrD5TAHxDhqIn/
2HhQL3ZyUp04XuHFTo3YmbP6gOX78ceOo2jfJAOzl+8LPt95FNfOWI5tzGtv0ygNeznZT4t2HtNtK63yAX8
uAr6+HUDQkDJLbwgBNs/AAykAJCCw0IZ/pHAEwk9ATwAX8s43oVpyohoueFNzkTvgMqDHpUCTLpi79E9M/
WoTujTMxOc3DcFfHvkRAPDS8L6448M1qjGe7NUD/xyejg+W/Yl/
je3KuwxGdM3DyodGQhAEVc8uXtNSI6gTOUEQpyokdmoRbWBrUZkHrRulAQB6tcjGf8b1wlNzt+D3HUexgxE
0Jyp9kKSgCyIvK0VVnwUIWnaW18S0BEQJB2pq8Dw3bzs+X31AKVQ3pH1j/
LHzKJbvOa64YhpluNCyQRp2H63AdxsOK2N2+Nf3uGpASzx6YXdVYLCMXNVYmz208s8TAIJNIFkrQ5rLrqvR
Iwdjs24YVugAwQBXntjhUVrtB7KaAR3PA8QAyioqsO/
QYRyXMnEMWaiU3Bhq34AWQihuyo7gHL2SHSVIR6mUjkpbGnqkHEWVLQPry7MQkGxISc9E11ZN8dHmKlTBBR
8cqE5rik3lmTgkNUKh1AAVSIFU43/6W59WeGp4T+U6Y3s2xTM/
bsPWgjJ0rxE6LocNrRqm6V5Hz+bZ6N0yB2cYNP+UkcUKK1rk9gIEQRCEMSR2ahFtdVw2QNlhE9C1aRaeuaw
3Bj41H3uPVaDaF0CK067Ep+SkOpHitOvGrfD4Dds9sDVhBrdvhD92HlVcaW6HDalOO87q2Bi7NQ0oAeDD5f
uRl5XCbWCZk6p2v914Zlu8v+xPpbJxuybpSnAwADwwpgse/mqT5vUH74eZ6+W0Ng3x/cYCw/
0spVU+oMNIoMNIlFX7MPmTdZjnDcbc5GeloF/
rHDy4oQB2BJAKD1zww4EAypGKtycOQ5OsFKS57EiVACEnFc6AiCv/
9T0AYFhuE7x5+Wl44uHvIRtSemVlY32p3uoF6ON6GmW48dDYbrj38/
XKtiYZbmSn6t2YnfPDV7LWsuJfwdecqwkg543dulGa5fYgBEEQ9REqKliL6C071QiIstgJ3vrczOACKErAl
sOlqPIGcMt7qwAEF8yWDUKWALlCbYUnwO3lxHJetzwMad8IABRLSaN0FwRBwDldjPsnrdx7QlXTR6ZBmtq/
07NFNsb2DKVDd2AsDLmZblwzuA3+uO8c1TnbCsvw2DebMHcDX8w0yXSjezPrqcsHi6vw+Deb8cCcDRj23wW
YtzkodEZ0ycWSB4ajX0338QDsKEca/r+9e4+Kqlz/AP6dYZhhuMwMMDDc
LwaCiKCCDoOSGhSaP8sOp595SElNj3dIu5kpZrXwnMysczp0OamnY0tMf+GpFMuDSmEqhoAgilqYVlxMk5t
ynef3B7FjCygWw2V8Pmvttdj7fWfPux9g7We9+33ffQUqVMIe12CFUb6OuMvJFq5qJdw0SgCt07g/
XTIWY/20SIrxh1wmhWu7ZELTLgZj/ByxdY5e2A/QdUxY/neUJ56eGCDsa23l8HG0xkMj3EWPMztLaG/
FyU6BQU637tWxtJBi//Lx2DnfcNvfwRhj5oJ7dkyorWfH0UaOy3WNv/
TstPYAyCx+fSQReZcjMorKcbDkEs5U1AjJiUwqQbD7rzd/
H0drnKmoxY9V13GtqeuZSGumBCE+wrvDasZta79EDHKEvbUlquubEaCzQ3G7Kek551sfeUkkgI1cJsz8Ut8
wsHqQ1hbuGiX+75cxO3e1u/
G2JT439iYcLLmEgyWX0BVfR5suZ0u1Ge3jgLH+Wvzj4DnUNxmx6VBphzpOdgpIJBK4/5LEdKarxfiC3dXY+
vivScyK+4dgybY8KGRS/
Gm0J744cwnWcgt88HgEAOCTxWNxoKQSMyO9Oz+fm1r4WWvb2q7Xpg2H0Uh4L7sUEYMcb3q9PeF2Fh5kjDFz
xMmOCbVN7w7xUONAySWcv1yHfxz4BoD4BjQh0BkZReV4PfMsPOx/
vUHHDNFhmPuvN0sfRxucqahFTX0zam5YPXje3YOw5avz+GhBJIJ/
+YylhRTuGqUw06ttermVpQU+WjgGDc0t+KTgR1Gy0/
Y4xk2txEhve2HdHI1S3LPjo7WGrUKGiEEOOFtRi5He9kLZ4gl+wvd0h4ONHHUNzUh+IAg6lRU+XjwGC7Ye7
zBDDWh9XLY02h/
RQ5zxcf6PePuLbzvUaUvy3G5IdlZMCkRKxmlsnDa8W+0CgCmhbhjiqkJ9UwuC3dXYPi9C1KMyzEONYR7qLj
/
fPnmzbze9XyqVYO7dg7rdDsYYY78dJzsm1JbsRPk74VJtA4p+qBYG5LZf+XZCgLOwjk3bYOO0eRHQ+zqI1r
DpbJ2UAJ0dnpkUgAkBzlh27+AOCcZgna2QNLR/
FNV2E07P+0E4ZiO3QN0vg4o97JUYN9hJSHa0dr9+1t7aEnZWrT09/56jhwSts76i/
LUI8VAj8hYDbdvkPBcNSFrHsjQ0G4W2h3hoEOhiJ7S7cM19GLbmcwAQxqgMdVNjqJsaS6L9UVJejed3nRQW
TWzr0Rl8w6Olx6MGYabBB0r57T02av+ITn+bPTHtE66m3/
FGeMYYY78dj9kxobYF+dztldg2NwKPjPp1FeFz7VbldbJT4KWpwQj6Zal9d40Sel8HSCQSWEglwviOScNcR
G+WBoDPnrgb9wTqIJFIOu1JaX/Db5sJ1p7hl5u3XCYV3dS9HKwxbrCTsN/+1QvtX0dhaSGFzEIKuUyKf8/
R46nYQNH528+8AoDAdoNxnVVWcLaz6rTtE4Nbv8/
BRg47K0ukL4zE7DG+eDzKV1TPViFDmLcDMhKj8FnS3Zgb5YsF4+8CACjlFgj11Ah1LaSS2050fq/
2PXi1t3i7OmOMMdPgnh0TauvZcVFZwc7KEuviQpB27CKA1sHK7cXrvfGn0V7Yf7oS3o7WounFe5PuRuH3Vx
E71AU+jjY4V1mL53cVYUKgE24l0k+Lt7/4FqN87DFnrG+H8nGDnfDOjDAMcVXh1c9LUPB962wjLwdrONkp8
NHCSBC1jjdZ/3AontxRIDym6o6MpLtR+H0VfLTWuNbYApWVJSa/
8aWQzHTlj2EesLOSCcnKCC97jPCyv+lnAlzssHJykOjYuj8Mwx/
+8VW3YmUqfwzzwM7c74UkjDHGWO+SUPsVyu5Q1dXVUKvVqKqqgkrVcy8yvHjlGsqq6hHsrhLee3WqrBpLt+
UhMcYf/
xPidoszdO3nukbYKGQdeno6U15VD2c7BaS3GKi6/3QFln1YAIVMis2PjUZQJzOjKmvqobW59blupupaE5Ry
i261vSdcvdYaq1u9NNNUWoyEy7UNt5wmzhhj7PZ09/7NyQ5Ml+wwxhhjzHS6e//
mMTuMMcYYM2tmk+y8+eab8PHxgZWVFfR6PXJycvq6SYwxxhjrB8wi2dm+fTuWLVuG5ORkHD9+HKGhoYiNjU
Vl5a3fyM0YY4wx82YWyc6GDRswd+5czJo1C0FBQXjrrbdgbW2NTZs29XXTGGOMMdbHBnyy09jYiNzcXMTEx
AjHpFIpYmJicPjw4U4/09DQgOrqatHGGGOMMfM04JOdn376CS0tLdDpdKLjOp0O5eWdv3AyJSUFarVa2Dw9
PTutxxhjjLGBb8AnO7/FihUrUFVVJWwXL17s6yYxxhhjzEQG/ArKWq0WFhYWqKioEB2vqKiAi0vnq/
QqFAooFIpOyxhjjDFmXgZ8z45cLkdYWBgyMzOFY0ajEZmZmTAYDH3YMsYYY4z1BwO+ZwcAli1bhoSEBISHh
2P06NHYuHEj6urqMGvWrL5uGmOMMcb6mFkkO9OmTcOlS5ewevVqlJeXY/jw4di7d2+HQcuMMcYYu/
Pwu7HA78ZijDHGBiJ+NxZjjDHGGDjZYYwxxpiZM4sxO79X25M8XkmZMcYYGzja7tu3GpHDyQ6AmpoaAOCVl
BljjLEBqKamBmq1ustyHqCM1nV5fvzxR9jZ2UEikfTYeaurq+Hp6YmLFy/
ywGcT41j3Do5z7+A49x6Ode8wVZyJCDU1NXBzc4NU2vXIHO7ZQeuLQz08PEx2fpVKxf9EvYRj3Ts4zr2D49
x7ONa9wxRxvlmPThseoMwYY4wxs8bJDmOMMcbMGic7JqRQKJCcnMwvHe0FHOvewXHuHRzn3sOx7h19HWceo
MwYY4wxs8Y9O4wxxhgza5zsMMYYY8yscbLDGGOMMbPGyQ5jjDHGzBonOyb05ptvwsfHB1ZWVtDr9cjJyenr
Jg0oX3zxBaZMmQI3NzdIJBLs2rVLVE5EWL16NVxdXaFUKhETE4OzZ8+K6ly5cgXx8fFQqVTQaDSYM2cOamt
re/
Eq+r+UlBSMGjUKdnZ2cHZ2xtSpU1FSUiKqU19fj0WLFsHR0RG2traIi4tDRUWFqM6FCxcwefJkWFtbw9nZG
U899RSam5t781L6tdTUVISEhAiLqhkMBmRkZAjlHGPTWLduHSQSCZKSkoRjHOuesWbNGkgkEtEWGBgolPer
OBMzibS0NJLL5bRp0yY6efIkzZ07lzQaDVVUVPR10waMPXv20MqVK+mjjz4iAJSeni4qX7duHanVatq1axc
VFBTQAw88QL6+vnT9+nWhzsSJEyk0NJSOHDlCX375Jfn5+dH06dN7+Ur6t9jYWNq8eTMVFRVRfn4+3X///
eTl5UW1tbVCnfnz55OnpydlZmbS119/TRERERQZGSmUNzc3U3BwMMXExFBeXh7t2bOHtFotrVixoi8uqV/
6+OOPaffu3XTmzBkqKSmh5557jiwtLamoqIiIOMamkJOTQz4+PhQSEkKJiYnCcY51z0hOTqahQ4dSWVmZsF
26dEko709x5mTHREaPHk2LFi0S9ltaWsjNzY1SUlL6sFUD143JjtFoJBcXF3rllVeEY1evXiWFQkHbtm0jI
qLi4mICQMeOHRPqZGRkkEQioR9+
+KHX2j7QVFZWEgDKysoiota4Wlpa0o4dO4Q6p06dIgB0+PBhImpNTKVSKZWXlwt1UlNTSaVSUUNDQ+9ewAB
ib29P//znPznGJlBTU0P+/v60b98+GjdunJDscKx7TnJyMoWGhnZa1t/
izI+xTKCxsRG5ubmIiYkRjkmlUsTExODw4cN92DLzUVpaivLyclGM1Wo19Hq9EOPDhw9Do9EgPDxcqBMTEw
OpVIqjR4/2epsHiqqqKgCAg4MDACA3NxdNTU2iWAcGBsLLy0sU62HDhkGn0wl1YmNjUV1djZMnT/
Zi6weGlpYWpKWloa6uDgaDgWNsAosWLcLkyZNFMQX477mnnT17Fm5ubhg0aBDi4+Nx4cIFAP0vzvwiUBP46
aef0NLSIvoFAoBOp8Pp06f7qFXmpby8HAA6jXFbWXl5OZydnUXlMpkMDg4OQh0mZjQakZSUhDFjxiA4OBhA
axzlcjk0Go2o7o2x7ux30VbGWhUWFsJgMKC+vh62trZIT09HUFAQ8vPzOcY9KC0tDcePH8exY8c6lPHfc8/
R6/
XYsmULAgICUFZWhhdeeAFRUVEoKirqd3HmZIcxJli0aBGKioqQnZ3d100xSwEBAcjPz0dVVRV27tyJhIQEZ
GVl9XWzzMrFixeRmJiIffv2wcrKqq+bY9YmTZok/
BwSEgK9Xg9vb298+OGHUCqVfdiyjvgxlglotVpYWFh0GHVeUVEBFxeXPmqVeWmL481i7OLigsrKSlF5c3Mz
rly5wr+HTixevBiffvopDhw4AA8PD+G4i4sLGhsbcfXqVVH9G2Pd2e+irYy1ksvl8PPzQ1hYGFJSUhAaGor
XX3+dY9yDcnNzUVlZiZEjR0Imk0EmkyErKwtvvPEGZDIZdDodx9pENBoNBg8ejHPnzvW7v2lOdkxALpcjLC
wMmZmZwjGj0YjMzEwYDIY+bJn58PX1hYuLiyjG1dXVOHr0qBBjg8GAq1evIjc3V6izf/
9+GI1G6PX6Xm9zf0VEWLx4MdLT07F//
374+vqKysPCwmBpaSmKdUlJCS5cuCCKdWFhoSi53LdvH1QqFYKCgnrnQgYgo9GIhoYGjnEPio6ORmFhIfLz
84UtPDwc8fHxws8ca9Oora3FN998A1dX1/73N92jw52ZIC0tjRQKBW3ZsoWKi4tp3rx5pNFoRKPO2c3V1NR
QXl4e5eXlEQDasGED5eXl0XfffUdErVPPNRoN/ec//6ETJ07Qgw8+2OnU8xEjRtDRo0cpOzub/
P39eer5DRYsWEBqtZoOHjwomkJ67do1oc78+fPJy8uL9u/fT19//TUZDAYyGAxCedsU0vvuu4/y8/
Np79695OTkxFN123n22WcpKyuLSktL6cSJE/Tss8+SRCKhzz//
nIg4xqbUfjYWEce6pyxfvpwOHjxIpaWldOjQIYqJiSGtVkuVlZVE1L/
izMmOCf3tb38jLy8vksvlNHr0aDpy5EhfN2lAOXDgAAHosCUkJBBR6/
TzVatWkU6nI4VCQdHR0VRSUiI6x+XLl2n69Olka2tLKpWKZs2aRTU1NX1wNf1XZzEGQJs3bxbqXL9+nRYuX
Ej29vZkbW1NDz30EJWVlYnOc/
78eZo0aRIplUrSarW0fPlyampq6uWr6b9mz55N3t7eJJfLycnJiaKjo4VEh4hjbEo3Jjsc654xbdo0cnV1J
blcTu7u7jRt2jQ6d+6cUN6f4iwhIurZviLGGGOMsf6Dx+wwxhhjzKxxssMYY4wxs8bJDmOMMcbMGic7jDHG
GDNrnOwwxhhjzKxxssMYY4wxs8bJDmOMMcbMGic7jDHGGDNrnOwwxn638+fPQyKRID8/32Tf8dhjj2Hq1Kk
mO39vOHjwICQSSYeXIzLGTIuTHcbucI899hgkEkmHbeLEid0+h6enJ8rKyhAcHGzClv5+48ePh0QiQVpamu
j4xo0b4ePj0zeNYoyZHCc7jDFMnDgRZWVlom3btm3d/
ryFhQVcXFwgk8lM2MqeYWVlheeffx5NTU193ZQe09jY2NdNYKxf42SHMQaFQgEXFxfRZm9vL5RLJBKkpqZi
0qRJUCqVGDRoEHbu3CmU3/gY6+eff0Z8fDycnJygVCrh7++PzZs3C/
ULCwtxzz33QKlUwtHREfPmzUNtba1Q3tLSgmXLlkGj0cDR0RFPP/
00bnyNn9FoREpKCnx9faFUKhEaGipqU1emT5+Oq1ev4t133+2yTmePzJKSkjB+/Hhhf/
z48ViyZAmSkpJgb28PnU6Hd999F3V1dZg1axbs7Ozg5+eHjIyMDuc/
dOgQQkJCYGVlhYiICBQVFYnKs7OzERUVBaVSCU9PTyxduhR1dXVCuY+PD1588UXMnDkTKpUK8+bNu+V1M3Y
n42SHMdYtq1atQlxcHAoKChAfH49HHnkEp06d6rJucXExMjIycOrUKaSmpkKr1QIA6urqEBsbC3t7exw7dg
w7duzAf//7XyxevFj4/KuvvootW7Zg06ZNyM7OxpUrV5Ceni76jpSUFLz//
vt46623cPLkSTzxxBN49NFHkZWVddPrUKlUWLlyJdauXStKIH6Lf/
3rX9BqtcjJycGSJUuwYMECPPzww4iMjMTx48dx3333YcaMGbh27Zroc0899RReffVVHDt2DE5OTpgyZYrQ0
/
TNN99g4sSJiIuLw4kTJ7B9+3ZkZ2eL4gMA69evR2hoKPLy8rBq1arfdR2Mmb0ef486Y2xASUhIIAsLC7Kxs
RFtL7/8slAHAM2fP1/0Ob1eTwsWLCAiotLSUgJAeXl5REQ0ZcoUmjVrVqff984775C9vT3V1tYKx3bv3k1S
qZTKy8uJiMjV1ZX++te/CuVNTU3k4eFBDz74IBER1dfXk7W1NX311Veic8+ZM4emT5/
e5bWOGzeOEhMTqb6+nry9vWnt2rVERPTaa6+Rt7e3KCZt39UmMTGRxo0bJzrX2LFjhf3m5maysbGhGTNmCM
fKysoIAB0+fJiIiA4cOEAAKC0tTahz+fJlUiqVtH37duEa5s2bJ/ruL7/8kqRSKV2/
fp2IiLy9vWnq1KldXidjTKz/
P2BnjJnchAkTkJqaKjrm4OAg2jcYDB32u5p9tWDBAsTFxQm9G1OnTkVkZCQA4NSpUwgNDYWNjY1Qf8yYMTA
ajSgpKYGVlRXKysqg1+uFcplMhvDwcOFR1rlz53Dt2jXce+
+9ou9tbGzEiBEjbnm9CoUCa9euFXpjfquQkBDhZwsLCzg6OmLYsGHCMZ1OBwCorKwUfa59LB0cHBAQECD0k
hUUFODEiRP44IMPhDpEBKPRiNLSUgwZMgQAEB4e/
pvbzdidhpMdxhhsbGzg5+fXY+ebNGkSvvvuO+zZswf79u1DdHQ0Fi1ahPXr1/
fI+dvG9+zevRvu7u6iMoVC0a1zPProo1i/
fj1eeumlDjOxpFJphzFCnQ1otrS0FO1LJBLRMYlEAqB1fFF31dbW4s9//
jOWLl3aoczLy0v4uX2yyBi7OR6zwxjrliNHjnTYb+tl6IyTkxMSEhKwdetWbNy4Ee+88w4AYMiQISgoKBCN
lzl06BCkUikCAgKgVqvh6uqKo0ePCuXNzc3Izc0V9oOCgqBQKHDhwgX4+fmJNk9Pz25dj1QqRUpKClJTU3H
+/
PkObS8rKxMd68k1hNrH8ueff8aZM2eEWI4cORLFxcUdrsvPzw9yubzH2sDYnYR7dhhjaGhoQHl5ueiYTCYT
BhUDwI4dOxAeHo6xY8figw8+QE5ODt57771Oz7d69WqEhYVh6NChaGhowKeffirczOPj45GcnIyEhASsWbM
Gly5dwpIlSzBjxgzhsU9iYiLWrVsHf39/BAYGYsOGDaKF+Ozs7PDkk0/
iiSeegNFoxNixY1FVVYVDhw5BpVIhISGhW9c9efJk6PV6vP3228J3A8A999yDV155Be+//
z4MBgO2bt2KoqKibj0i6461a9fC0dEROp0OK1euhFarFWZ/PfPMM4iIiMDixYvx+OOPw8bGBsXFxdi3bx/
+/ve/98j3M3an4WSHMYa9e/
fC1dVVdCwgIACnT58W9l944QWkpaVh4cKFcHV1xbZt2xAUFNTp+eRyOVasWIHz589DqVQiKipKWMjP2toan
332GRITEzFq1ChYW1sjLi4OGzZsED6/
fPlylJWVISEhAVKpFLNnz8ZDDz2Eqqoqoc6LL74IJycnpKSk4Ntvv4VGo8HIkSPx3HPP3da1/+UvfxHGE7W
JjY3FqlWr8PTTT6O+vh6zZ8/
GzJkzUVhYeFvn7sq6deuQmJiIs2fPYvjw4fjkk0+EXpuQkBBkZWVh5cqViIqKAhHhrrvuwrRp03rkuxm7E0
noxgfTjDF2A4lEgvT09AH/
ugbG2J2Jx+wwxhhjzKxxssMYY4wxs8Zjdhhjt8RPuxljAxn37DDGGGPMrHGywxhjjDGzxskOY4wxxswaJzu
MMcYYM2uc7DDGGGPMrHGywxhjjDGzxskOY4wxxswaJzuMMcYYM2v/D9hM6iPm+E9KAAAAAElFTkSuQmCC\
n"
},
"metadata": {}
}
],
"source": [
"scores = [Link](scores, name=\"scores\")\n",
"[Link]()\n",
"fig, ax = [Link](1, 1)\n",
"_ = [Link](ax=ax, label=\"Scores\")\n",
"_ = ([Link](window=100)\n",
" .mean()\n",
" .rename(\"Rolling Average\")\n",
" .plot(ax=ax))\n",
"[Link]()\n",
"_ = ax.set_xlabel(\"Episode Number\")\n",
"_ = ax.set_ylabel(\"Score\")"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.5"
}
},
"nbformat": 4,
"nbformat_minor": 0
}