From 2a7fa9abe35e139825ab80a3c42e19bbd3d2ebb2 Mon Sep 17 00:00:00 2001 From: bushuhui Date: Tue, 28 Sep 2021 17:48:42 +0800 Subject: [PATCH] Improve descriptions & index --- 6_pytorch/0_basic/1-Tensor-and-Variable.ipynb | 113 +++++---- 6_pytorch/0_basic/2-autograd.ipynb | 204 ++++------------ 6_pytorch/0_basic/3-dynamic-graph.ipynb | 220 ----------------- 6_pytorch/0_basic/ref_dynamic-graph.ipynb | 100 ++++++++ ...1-linear-regression-gradient-descend.ipynb | 227 ++++++++---------- 6_pytorch/1_NN/2-logistic-regression.ipynb | 2 +- 6_pytorch/README.md | 11 + 6_pytorch/imgs/PyTorch_demo.gif | Bin 0 -> 264025 bytes README.md | 47 ++-- 9 files changed, 349 insertions(+), 575 deletions(-) delete mode 100644 6_pytorch/0_basic/3-dynamic-graph.ipynb create mode 100644 6_pytorch/0_basic/ref_dynamic-graph.ipynb create mode 100644 6_pytorch/imgs/PyTorch_demo.gif diff --git a/6_pytorch/0_basic/1-Tensor-and-Variable.ipynb b/6_pytorch/0_basic/1-Tensor-and-Variable.ipynb index 3b7d7e7..fe0929a 100644 --- a/6_pytorch/0_basic/1-Tensor-and-Variable.ipynb +++ b/6_pytorch/0_basic/1-Tensor-and-Variable.ipynb @@ -6,22 +6,28 @@ "source": [ "# Tensor and Variable\n", "\n", - "PyTorch的简洁设计使得它入门很简单,在深入介绍PyTorch之前,本节将先介绍一些PyTorch的基础知识,使得读者能够对PyTorch有一个大致的了解,并能够用PyTorch搭建一个简单的神经网络。部分内容读者可能暂时不太理解,可先不予以深究,后续的课程将会对此进行深入讲解。\n", "\n", - "本节内容参考了PyTorch官方教程[^1]并做了相应的增删修改,使得内容更贴合新版本的PyTorch接口,同时也更适合新手快速入门。另外本书需要读者先掌握基础的Numpy使用,其他相关知识推荐读者参考CS231n的教程[^2]。\n", + "张量(Tensor)是一种专门的数据结构,非常类似于数组和矩阵。在PyTorch中,我们使用张量来编码模型的输入和输出,以及模型的参数。\n", "\n", - "[^1]: http://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html\n", - "[^2]: http://cs231n.github.io/python-numpy-tutorial/\n", - "\n" + "张量类似于`numpy`的`ndarray`,不同之处在于张量可以在GPU或其他硬件加速器上运行。事实上,张量和NumPy数组通常可以共享相同的底层内存,从而消除了复制数据的需要(请参阅使用NumPy的桥接)。张量还针对自动微分进行了优化,在Autograd部分中看到更多关于这一点的内介绍。\n", + "\n", + "`variable`是一种可以不断变化的变量,符合反向传播,参数更新的属性。PyTorch的`variable`是一个存放会变化值的内存位置,里面的值会不停变化,像装糖果(糖果就是数据,即tensor)的盒子,糖果的数量不断变化。pytorch都是由tensor计算的,而tensor里面的参数是variable形式。\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "## 把 PyTorch 当做 NumPy 用\n", + "## 1. Tensor基本用法\n", "\n", - "PyTorch 的官方介绍是一个拥有强力GPU加速的张量和动态构建网络的库,其主要构件是张量,所以我们可以把 PyTorch 当做 NumPy 来用,PyTorch 的很多操作好 NumPy 都是类似的,但是因为其能够在 GPU 上运行,所以有着比 NumPy 快很多倍的速度。通过本次课程,你能够学会如何像使用 NumPy 一样使用 PyTorch,了解到 PyTorch 中的基本元素 Tensor 和 Variable 及其操作方式。" + "PyTorch基础的数据是张量,PyTorch 的很多操作好 NumPy 都是类似的,但是因为其能够在 GPU 上运行,所以有着比 NumPy 快很多倍的速度。通过本次课程,能够学会如何像使用 NumPy 一样使用 PyTorch,了解到 PyTorch 中的基本元素 Tensor 和 Variable 及其操作方式。" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 1.1 Tensor定义与生成" ] }, { @@ -113,7 +119,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "PyTorch Tensor 使用 GPU 加速\n", + "### 1.2 PyTorch Tensor 使用 GPU 加速\n", "\n", "我们可以使用以下两种方式将 Tensor 放到 GPU 上" ] @@ -245,7 +251,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "**小练习**\n", + "### 1.3 小练习\n", "\n", "查阅以下[文档](http://pytorch.org/docs/0.3.0/tensors.html)了解 tensor 的数据类型,创建一个 float64、大小是 3 x 2、随机初始化的 tensor,将其转化为 numpy 的 ndarray,输出其数据类型\n", "\n", @@ -284,8 +290,15 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Tensor的操作\n", - "Tensor 操作中的 api 和 NumPy 非常相似,如果你熟悉 NumPy 中的操作,那么 tensor 基本是一致的,下面我们来列举其中的一些操作" + "## 2. Tensor的操作\n", + "Tensor 操作中的 API 和 NumPy 非常相似,如果你熟悉 NumPy 中的操作,那么 tensor 基本是一致的,下面我们来列举其中的一些操作" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 2.1 基本操作" ] }, { @@ -629,7 +642,8 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "另外,pytorch中大多数的操作都支持 inplace 操作,也就是可以直接对 tensor 进行操作而不需要另外开辟内存空间,方式非常简单,一般都是在操作的符号后面加`_`,比如" + "### 2.2 `inplace`操作\n", + "另外,pytorch中大多数的操作都支持 `inplace` 操作,也就是可以直接对 tensor 进行操作而不需要另外开辟内存空间,方式非常简单,一般都是在操作的符号后面加`_`,比如" ] }, { @@ -692,9 +706,9 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "**小练习**\n", + "### 2.3 **小练习**\n", "\n", - "访问[文档](http://pytorch.org/docs/0.3.0/tensors.html)了解 tensor 更多的 api,实现下面的要求\n", + "访问[文档](http://pytorch.org/docs/tensors.html)了解 tensor 更多的 api,实现下面的要求\n", "\n", "创建一个 float32、4 x 4 的全为1的矩阵,将矩阵正中间 2 x 2 的矩阵,全部修改成2\n", "\n", @@ -742,28 +756,38 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Variable\n", - "tensor 是 PyTorch 中的完美组件,但是构建神经网络还远远不够,我们需要能够构建计算图的 tensor,这就是 Variable。Variable 是对 tensor 的封装,操作和 tensor 是一样的,但是每个 Variabel都有三个属性,Variable 中的 tensor本身`.data`,对应 tensor 的梯度`.grad`以及这个 Variable 是通过什么方式得到的`.grad_fn`" + "## 3. Variable\n", + "tensor 是 PyTorch 中的基础数据类型,但是构建神经网络还远远不够,需要能够构建计算图的 tensor,这就是 Variable。Variable 是对 tensor 的封装,操作和 tensor 是一样的,但是每个 Variabel都有三个属性:\n", + "* Variable 中的 tensor本身`.data`,\n", + "* 对应 tensor 的梯度`.grad`\n", + "* Variable 是通过什么方式得到的`.grad_fn`" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 3.1 Variable的基本操作" ] }, { "cell_type": "code", - "execution_count": 35, + "execution_count": 4, "metadata": {}, "outputs": [], "source": [ - "# 通过下面这种方式导入 Variable\n", + "import torch\n", "from torch.autograd import Variable" ] }, { "cell_type": "code", - "execution_count": 36, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ - "x_tensor = torch.randn(10, 5)\n", - "y_tensor = torch.randn(10, 5)\n", + "x_tensor = torch.randn(3, 4)\n", + "y_tensor = torch.randn(3, 4)\n", "\n", "# 将 tensor 变成 Variable\n", "x = Variable(x_tensor, requires_grad=True) # 默认 Variable 是不需要求梯度的,所以我们用这个方式申明需要对其进行求梯度\n", @@ -772,7 +796,7 @@ }, { "cell_type": "code", - "execution_count": 37, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ @@ -781,15 +805,15 @@ }, { "cell_type": "code", - "execution_count": 44, + "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "tensor(-22.1040)\n", - "\n" + "tensor(-7.7018)\n", + "\n" ] } ], @@ -807,33 +831,19 @@ }, { "cell_type": "code", - "execution_count": 45, + "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "tensor([[2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.]])\n", - "tensor([[2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.],\n", - " [2., 2., 2., 2., 2.]])\n" + "tensor([[1., 1., 1., 1.],\n", + " [1., 1., 1., 1.],\n", + " [1., 1., 1., 1.]])\n", + "tensor([[1., 1., 1., 1.],\n", + " [1., 1., 1., 1.],\n", + " [1., 1., 1., 1.]])\n" ] } ], @@ -856,7 +866,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "**小练习**\n", + "### 3.2 **小练习**\n", "\n", "尝试构建一个函数 $y = x^2 $,然后求 x=2 的导数。\n", "\n", @@ -931,6 +941,15 @@ "source": [ "下一次课程我们将会从导数展开,了解 PyTorch 的自动求导机制" ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## References\n", + "* http://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html\n", + "* http://cs231n.github.io/python-numpy-tutorial/" + ] } ], "metadata": { diff --git a/6_pytorch/0_basic/2-autograd.ipynb b/6_pytorch/0_basic/2-autograd.ipynb index 164cb23..21f272f 100644 --- a/6_pytorch/0_basic/2-autograd.ipynb +++ b/6_pytorch/0_basic/2-autograd.ipynb @@ -10,7 +10,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -22,7 +22,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## 简单情况的自动求导\n", + "## 1. 简单情况的自动求导\n", "下面我们显示一些简单情况的自动求导,\"简单\"体现在计算的结果都是标量,也就是一个数,我们对这个标量进行自动求导。" ] }, @@ -61,7 +61,8 @@ "$$\n", "\\frac{\\partial z}{\\partial x} = 2 (x + 2) = 2 (2 + 2) = 8\n", "$$\n", - "如果你对求导不熟悉,可以查看以下[网址进行复习](https://baike.baidu.com/item/%E5%AF%BC%E6%95%B0#1)" + "\n", + "如果你对求导不熟悉,可以查看以下[《导数介绍资料》](https://baike.baidu.com/item/%E5%AF%BC%E6%95%B0#1)网址进行复习" ] }, { @@ -92,210 +93,106 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 25, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "tensor([[ 5.7436e-01, -8.5241e-01, 2.2845e+00, 3.6574e-01, 1.4336e+00,\n", - " 6.2769e-01, -2.4378e-01, 2.3407e+00, 3.8966e-01, 1.1835e+00,\n", - " -6.4391e-01, 9.1353e-01, -5.8734e-01, -1.9392e+00, 9.3507e-01,\n", - " 8.8518e-02, 7.2412e-01, -1.0687e+00, -6.7646e-01, 1.2672e+00],\n", - " [ 7.2998e-01, 2.0229e+00, -5.0831e-01, -6.3940e-01, -8.7033e-01,\n", - " 2.7687e-01, 6.3498e-01, -1.8736e-03, -8.4395e-01, 1.4696e+00,\n", - " -1.7850e+00, -4.5297e-01, 9.2144e-01, 8.5070e-02, -5.8926e-01,\n", - " 1.2085e+00, -9.7894e-01, -3.4309e-01, -2.4711e-02, -6.4475e-01],\n", - " [-2.8774e-01, 1.2039e+00, -5.2320e-01, 1.3787e-01, 3.9971e-02,\n", - " -5.6454e-01, -1.5835e+00, -2.0742e-01, -1.4274e+00, -3.7860e-01,\n", - " 6.2642e-01, 1.6408e+00, -1.1916e-01, 1.4388e-01, -9.5261e-01,\n", - " 4.0784e-01, 8.1715e-01, 3.9228e-01, 4.1611e-01, -3.3709e-01],\n", - " [ 3.3040e-01, 1.7915e-01, -5.7069e-02, 1.1144e+00, -1.0322e+00,\n", - " 9.9129e-01, 1.1692e+00, 7.9638e-01, -1.0943e-01, 8.2714e-01,\n", - " -1.5700e-01, -5.6686e-01, -1.9550e-01, -1.2263e+00, 1.7836e+00,\n", - " 9.1989e-01, -6.4577e-01, 9.5402e-01, -8.6525e-01, 3.9199e-01],\n", - " [-8.8085e-01, -6.3551e-03, 1.6959e+00, -7.5292e-02, -8.8929e-02,\n", - " 1.0209e+00, 8.9355e-01, -1.2029e+00, 1.9429e+00, -2.7024e-01,\n", - " -9.1289e-01, -1.3788e+00, -6.2695e-01, -6.5776e-01, 3.3640e-01,\n", - " -1.0473e-01, 9.9417e-01, 1.0128e+00, 2.4199e+00, 2.8859e-01],\n", - " [ 8.0469e-02, -1.6585e-01, -4.9862e-01, -5.5413e-01, -4.9307e-01,\n", - " -7.3808e-01, 1.3946e-02, 5.6282e-01, 9.1096e-01, -1.9281e-01,\n", - " -3.8546e-01, -1.4070e+00, 7.3520e-01, 1.7412e+00, 1.0770e+00,\n", - " 1.4837e+00, -7.4241e-01, -4.0977e-01, 1.1057e+00, -7.0222e-01],\n", - " [-2.3147e-01, -3.7781e-01, 1.0774e+00, -7.9918e-01, 1.8275e+00,\n", - " 7.6937e-01, -2.7600e-01, 1.0389e+00, 1.4457e+00, -1.2898e+00,\n", - " 1.2761e-03, 5.5406e-01, 1.8231e+00, -2.3874e-01, 1.2145e+00,\n", - " -2.1051e+00, -6.6464e-01, -8.5335e-01, -2.6258e-01, 8.0080e-01],\n", - " [ 4.2173e-01, 1.7040e-01, -3.0126e-01, -5.2095e-01, 5.5845e-01,\n", - " 5.9780e-01, -6.8320e-01, -5.2203e-01, 4.9485e-01, -8.2392e-01,\n", - " -1.7584e-01, -1.3862e+00, 1.3604e+00, -7.5567e-01, 3.1400e-01,\n", - " 1.8617e+00, -1.1887e+00, -3.1732e-01, -1.5062e-01, -1.7251e-01],\n", - " [ 1.0924e+00, 1.0899e+00, 5.7135e-01, -2.7047e-01, 1.1123e+00,\n", - " 9.3634e-01, -1.4739e+00, 5.3640e-01, -8.2090e-02, 3.3112e-02,\n", - " 6.6032e-01, 1.1448e+00, -4.2457e-01, 1.2898e+00, 3.9002e-01,\n", - " 2.7646e-01, 9.6717e-03, -1.7425e-01, -1.9732e-01, 9.7876e-01],\n", - " [ 4.4554e-01, 5.3807e-01, -2.2031e-02, 1.3198e+00, -1.1642e+00,\n", - " -6.6617e-01, -2.6982e-01, -1.0219e+00, 5.8154e-01, 1.7617e+00,\n", - " 3.3077e-01, 1.5238e+00, -5.8909e-01, 1.1373e+00, 1.0998e+00,\n", - " -1.8168e+00, -5.0699e-01, 4.0043e-01, -2.3226e+00, 7.2522e-02]],\n", - " requires_grad=True)\n" + "tensor([[1., 2.],\n", + " [3., 4.]], requires_grad=True)\n" ] } ], "source": [ - "# FIXME: the demo need improve\n", - "x = Variable(torch.randn(10, 20), requires_grad=True)\n", - "y = Variable(torch.randn(10, 5), requires_grad=True)\n", - "w = Variable(torch.randn(20, 5), requires_grad=True)\n", - "print(x)\n", - "out = torch.mean(y - torch.matmul(x, w)) # torch.matmul 是做矩阵乘法\n", - "out.backward()" + "# 定义Variable\n", + "x = Variable(torch.FloatTensor([1,2]), requires_grad=False)\n", + "b = Variable(torch.FloatTensor([5,6]), requires_grad=False)\n", + "w = Variable(torch.FloatTensor([[1,2],[3,4]]), requires_grad=True)\n", + "print(w)" ] }, { - "cell_type": "markdown", + "cell_type": "code", + "execution_count": 26, "metadata": {}, + "outputs": [], "source": [ - "如果你对矩阵乘法不熟悉,可以查看下面的[网址进行复习](https://baike.baidu.com/item/%E7%9F%A9%E9%98%B5%E4%B9%98%E6%B3%95/5446029?fr=aladdin)" + "z = torch.mean(torch.matmul(w, x) + b) # torch.matmul 是做矩阵乘法\n", + "z.backward()" ] }, { - "cell_type": "code", - "execution_count": 6, + "cell_type": "markdown", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "tensor([[ 0.0034, -0.0301, -0.0040, -0.0488, 0.0187, -0.0139, -0.0374, 0.0102,\n", - " 0.0337, -0.0249, -0.0777, -0.0868, 0.0132, 0.0042, -0.0627, -0.0448,\n", - " 0.0221, -0.0324, -0.0601, 0.0048],\n", - " [ 0.0034, -0.0301, -0.0040, -0.0488, 0.0187, -0.0139, -0.0374, 0.0102,\n", - " 0.0337, -0.0249, -0.0777, -0.0868, 0.0132, 0.0042, -0.0627, -0.0448,\n", - " 0.0221, -0.0324, -0.0601, 0.0048],\n", - " [ 0.0034, -0.0301, -0.0040, -0.0488, 0.0187, -0.0139, -0.0374, 0.0102,\n", - " 0.0337, -0.0249, -0.0777, -0.0868, 0.0132, 0.0042, -0.0627, -0.0448,\n", - " 0.0221, -0.0324, -0.0601, 0.0048],\n", - " [ 0.0034, -0.0301, -0.0040, -0.0488, 0.0187, -0.0139, -0.0374, 0.0102,\n", - " 0.0337, -0.0249, -0.0777, -0.0868, 0.0132, 0.0042, -0.0627, -0.0448,\n", - " 0.0221, -0.0324, -0.0601, 0.0048],\n", - " [ 0.0034, -0.0301, -0.0040, -0.0488, 0.0187, -0.0139, -0.0374, 0.0102,\n", - " 0.0337, -0.0249, -0.0777, -0.0868, 0.0132, 0.0042, -0.0627, -0.0448,\n", - " 0.0221, -0.0324, -0.0601, 0.0048],\n", - " [ 0.0034, -0.0301, -0.0040, -0.0488, 0.0187, -0.0139, -0.0374, 0.0102,\n", - " 0.0337, -0.0249, -0.0777, -0.0868, 0.0132, 0.0042, -0.0627, -0.0448,\n", - " 0.0221, -0.0324, -0.0601, 0.0048],\n", - " [ 0.0034, -0.0301, -0.0040, -0.0488, 0.0187, -0.0139, -0.0374, 0.0102,\n", - " 0.0337, -0.0249, -0.0777, -0.0868, 0.0132, 0.0042, -0.0627, -0.0448,\n", - " 0.0221, -0.0324, -0.0601, 0.0048],\n", - " [ 0.0034, -0.0301, -0.0040, -0.0488, 0.0187, -0.0139, -0.0374, 0.0102,\n", - " 0.0337, -0.0249, -0.0777, -0.0868, 0.0132, 0.0042, -0.0627, -0.0448,\n", - " 0.0221, -0.0324, -0.0601, 0.0048],\n", - " [ 0.0034, -0.0301, -0.0040, -0.0488, 0.0187, -0.0139, -0.0374, 0.0102,\n", - " 0.0337, -0.0249, -0.0777, -0.0868, 0.0132, 0.0042, -0.0627, -0.0448,\n", - " 0.0221, -0.0324, -0.0601, 0.0048],\n", - " [ 0.0034, -0.0301, -0.0040, -0.0488, 0.0187, -0.0139, -0.0374, 0.0102,\n", - " 0.0337, -0.0249, -0.0777, -0.0868, 0.0132, 0.0042, -0.0627, -0.0448,\n", - " 0.0221, -0.0324, -0.0601, 0.0048]])\n" - ] - } - ], "source": [ - "# 得到 x 的梯度\n", - "print(x.grad)" + "如果你对矩阵乘法不熟悉,可以查看下面的[网址进行复习](https://baike.baidu.com/item/%E7%9F%A9%E9%98%B5%E4%B9%98%E6%B3%95/5446029?fr=aladdin)" ] }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 27, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "tensor([[0.0200, 0.0200, 0.0200, 0.0200, 0.0200],\n", - " [0.0200, 0.0200, 0.0200, 0.0200, 0.0200],\n", - " [0.0200, 0.0200, 0.0200, 0.0200, 0.0200],\n", - " [0.0200, 0.0200, 0.0200, 0.0200, 0.0200],\n", - " [0.0200, 0.0200, 0.0200, 0.0200, 0.0200],\n", - " [0.0200, 0.0200, 0.0200, 0.0200, 0.0200],\n", - " [0.0200, 0.0200, 0.0200, 0.0200, 0.0200],\n", - " [0.0200, 0.0200, 0.0200, 0.0200, 0.0200],\n", - " [0.0200, 0.0200, 0.0200, 0.0200, 0.0200],\n", - " [0.0200, 0.0200, 0.0200, 0.0200, 0.0200]])\n" + "tensor([[0.5000, 1.0000],\n", + " [0.5000, 1.0000]])\n" ] } ], "source": [ - "# 得到 y 的的梯度\n", - "print(y.grad)" + "# 得到 w 的梯度\n", + "print(w.grad)" ] }, { - "cell_type": "code", - "execution_count": 8, + "cell_type": "markdown", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "tensor([[ 0.0172, 0.0172, 0.0172, 0.0172, 0.0172],\n", - " [ 0.0389, 0.0389, 0.0389, 0.0389, 0.0389],\n", - " [-0.0748, -0.0748, -0.0748, -0.0748, -0.0748],\n", - " [-0.0186, -0.0186, -0.0186, -0.0186, -0.0186],\n", - " [ 0.0278, 0.0278, 0.0278, 0.0278, 0.0278],\n", - " [-0.0228, -0.0228, -0.0228, -0.0228, -0.0228],\n", - " [-0.0496, -0.0496, -0.0496, -0.0496, -0.0496],\n", - " [-0.0084, -0.0084, -0.0084, -0.0084, -0.0084],\n", - " [ 0.0693, 0.0693, 0.0693, 0.0693, 0.0693],\n", - " [-0.0821, -0.0821, -0.0821, -0.0821, -0.0821],\n", - " [ 0.0419, 0.0419, 0.0419, 0.0419, 0.0419],\n", - " [-0.0126, -0.0126, -0.0126, -0.0126, -0.0126],\n", - " [ 0.0322, 0.0322, 0.0322, 0.0322, 0.0322],\n", - " [ 0.0863, 0.0863, 0.0863, 0.0863, 0.0863],\n", - " [-0.0791, -0.0791, -0.0791, -0.0791, -0.0791],\n", - " [ 0.0179, 0.0179, 0.0179, 0.0179, 0.0179],\n", - " [-0.1109, -0.1109, -0.1109, -0.1109, -0.1109],\n", - " [-0.0188, -0.0188, -0.0188, -0.0188, -0.0188],\n", - " [-0.0636, -0.0636, -0.0636, -0.0636, -0.0636],\n", - " [ 0.0223, 0.0223, 0.0223, 0.0223, 0.0223]])\n" - ] - } - ], "source": [ - "# 得到 w 的梯度\n", - "print(w.grad)" + "具体计算的公式为:\n", + "$$\n", + "z_1 = w_{11}*x_1 + w_{12}*x_2 + b_1 \\\\\n", + "z_2 = w_{21}*x_1 + w_{22}*x_2 + b_2 \\\\\n", + "z = \\frac{1}{2} (z_1 + z_2)\n", + "$$" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "上面数学公式就更加复杂,矩阵乘法之后对两个矩阵对应元素相乘,然后所有元素求平均,有兴趣的同学可以手动去计算一下梯度,使用 PyTorch 的自动求导,我们能够非常容易得到 x, y 和 w 的导数,因为深度学习中充满大量的矩阵运算,所以我们没有办法手动去求这些导数,有了自动求导能够非常方便地解决网络更新的问题。" + "则微分计算结果是:\n", + "$$\n", + "\\frac{\\partial z}{w_{11}} = \\frac{1}{2} x_1 \\\\\n", + "\\frac{\\partial z}{w_{12}} = \\frac{1}{2} x_2 \\\\\n", + "\\frac{\\partial z}{w_{21}} = \\frac{1}{2} x_1 \\\\\n", + "\\frac{\\partial z}{w_{22}} = \\frac{1}{2} x_2\n", + "$$" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "\n" + "上面数学公式就更加复杂,矩阵乘法之后对两个矩阵对应元素相乘,然后所有元素求平均,有兴趣的同学可以手动去计算一下梯度,使用 PyTorch 的自动求导,我们能够非常容易得到 x, y 和 w 的导数,因为深度学习中充满大量的矩阵运算,所以我们没有办法手动去求这些导数,有了自动求导能够非常方便地解决网络更新的问题。" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "## 复杂情况的自动求导\n", - "上面我们展示了简单情况下的自动求导,都是对标量进行自动求导,可能你会有一个疑问,如何对一个向量或者矩阵自动求导了呢?感兴趣的同学可以自己先去尝试一下,下面我们会介绍对多维数组的自动求导机制。" + "## 2. 复杂情况的自动求导\n", + "\n", + "上面我们展示了简单情况下的自动求导,都是对标量进行自动求导,那么如何对一个向量或者矩阵自动求导?" ] }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 28, "metadata": {}, "outputs": [ { @@ -316,7 +213,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 29, "metadata": {}, "outputs": [ { @@ -423,7 +320,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## 多次自动求导\n", + "## 3. 多次自动求导\n", "通过调用 backward 我们可以进行一次自动求导,如果我们再调用一次 backward,会发现程序报错,没有办法再做一次。这是因为 PyTorch 默认做完一次自动求导之后,计算图就被丢弃了,所以两次自动求导需要手动设置一个东西,我们通过下面的小例子来说明。" ] }, @@ -516,7 +413,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "**小练习**\n", + "## 4 练习题\n", "\n", "定义\n", "\n", @@ -650,13 +547,6 @@ "source": [ "print(j)" ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "下一次课我们会介绍两种神经网络的编程方式,动态图编程和静态图编程" - ] } ], "metadata": { @@ -675,7 +565,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.9" + "version": "3.7.9" } }, "nbformat": 4, diff --git a/6_pytorch/0_basic/3-dynamic-graph.ipynb b/6_pytorch/0_basic/3-dynamic-graph.ipynb deleted file mode 100644 index 6c2079d..0000000 --- a/6_pytorch/0_basic/3-dynamic-graph.ipynb +++ /dev/null @@ -1,220 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "# 动态图和静态图\n", - "目前神经网络框架分为[静态图框架和动态图框架](https://blog.csdn.net/qq_36653505/article/details/87875279),PyTorch 和 TensorFlow、Caffe 等框架最大的区别就是他们拥有不同的计算图表现形式。 TensorFlow 使用静态图,这意味着我们先定义计算图,然后不断使用它,而在 PyTorch 中,每次都会重新构建一个新的计算图。通过这次课程,我们会了解静态图和动态图之间的优缺点。\n", - "\n", - "对于使用者来说,两种形式的计算图有着非常大的区别,同时静态图和动态图都有他们各自的优点,比如动态图比较方便debug,使用者能够用任何他们喜欢的方式进行debug,同时非常直观,而静态图是通过先定义后运行的方式,之后再次运行的时候就不再需要重新构建计算图,所以速度会比动态图更快。" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "![](https://ws3.sinaimg.cn/large/006tNc79ly1fmai482qumg30rs0fmq6e.gif)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "下面我们比较 while 循环语句在 TensorFlow 和 PyTorch 中的定义" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## TensorFlow" - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": {}, - "outputs": [ - { - "ename": "ModuleNotFoundError", - "evalue": "No module named 'tensorflow'", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# tensorflow\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mtensorflow\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mfirst_counter\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconstant\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0msecond_counter\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconstant\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'tensorflow'" - ] - } - ], - "source": [ - "# tensorflow\n", - "import tensorflow as tf\n", - "\n", - "first_counter = tf.constant(0)\n", - "second_counter = tf.constant(10)" - ] - }, - { - "cell_type": "code", - "execution_count": 16, - "metadata": {}, - "outputs": [], - "source": [ - "def cond(first_counter, second_counter, *args):\n", - " return first_counter < second_counter\n", - "\n", - "def body(first_counter, second_counter):\n", - " first_counter = tf.add(first_counter, 2)\n", - " second_counter = tf.add(second_counter, 1)\n", - " return first_counter, second_counter" - ] - }, - { - "cell_type": "code", - "execution_count": 17, - "metadata": {}, - "outputs": [], - "source": [ - "c1, c2 = tf.while_loop(cond, body, [first_counter, second_counter])" - ] - }, - { - "cell_type": "code", - "execution_count": 21, - "metadata": {}, - "outputs": [ - { - "ename": "RuntimeError", - "evalue": "The Session graph is empty. Add operations to the graph before calling run().", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mRuntimeError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompat\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mv1\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSession\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0msess\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mcounter_1_res\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcounter_2_res\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msess\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mc1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mc2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", - "\u001b[0;32m~/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36mrun\u001b[0;34m(self, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[1;32m 956\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 957\u001b[0m result = self._run(None, fetches, feed_dict, options_ptr,\n\u001b[0;32m--> 958\u001b[0;31m run_metadata_ptr)\n\u001b[0m\u001b[1;32m 959\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 960\u001b[0m \u001b[0mproto_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTF_GetBuffer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrun_metadata_ptr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36m_run\u001b[0;34m(self, handle, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[1;32m 1104\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mRuntimeError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Attempted to use a closed Session.'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1105\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgraph\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mversion\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1106\u001b[0;31m raise RuntimeError('The Session graph is empty. Add operations to the '\n\u001b[0m\u001b[1;32m 1107\u001b[0m 'graph before calling run().')\n\u001b[1;32m 1108\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mRuntimeError\u001b[0m: The Session graph is empty. Add operations to the graph before calling run()." - ] - } - ], - "source": [ - "with tf.compat.v1.Session() as sess:\n", - " counter_1_res, counter_2_res = sess.run([c1, c2])" - ] - }, - { - "cell_type": "code", - "execution_count": 19, - "metadata": {}, - "outputs": [ - { - "ename": "NameError", - "evalue": "name 'counter_1_res' is not defined", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcounter_1_res\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcounter_2_res\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mNameError\u001b[0m: name 'counter_1_res' is not defined" - ] - } - ], - "source": [ - "print(counter_1_res)\n", - "print(counter_2_res)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "可以看到 TensorFlow 需要将整个图构建成静态的,换句话说,每次运行的时候图都是一样的,是不能够改变的,所以不能直接使用 Python 的 while 循环语句,需要使用辅助函数 `tf.while_loop` 写成 TensorFlow 内部的形式\n", - "\n", - "这是非常反直觉的,学习成本也是比较高的\n", - "\n", - "下面我们来看看 PyTorch 的动态图机制,这使得我们能够使用 Python 的 while 写循环,非常方便" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## PyTorch" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": {}, - "outputs": [], - "source": [ - "# pytorch\n", - "import torch\n", - "first_counter = torch.Tensor([0])\n", - "second_counter = torch.Tensor([10])" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": {}, - "outputs": [], - "source": [ - "while (first_counter < second_counter)[0]:\n", - " first_counter += 2\n", - " second_counter += 1" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "tensor([20.])\n", - "tensor([20.])\n" - ] - } - ], - "source": [ - "print(first_counter)\n", - "print(second_counter)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "可以看到 PyTorch 的写法跟 Python 的写法是完全一致的,没有任何额外的学习成本\n", - "\n", - "上面的例子展示如何使用静态图和动态图构建 while 循环,看起来动态图的方式更加简单且直观,你觉得呢?" - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "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": "3.6.9" - } - }, - "nbformat": 4, - "nbformat_minor": 2 -} diff --git a/6_pytorch/0_basic/ref_dynamic-graph.ipynb b/6_pytorch/0_basic/ref_dynamic-graph.ipynb new file mode 100644 index 0000000..a1c35e0 --- /dev/null +++ b/6_pytorch/0_basic/ref_dynamic-graph.ipynb @@ -0,0 +1,100 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 动态图和静态图\n", + "目前神经网络框架分为[静态图框架和动态图框架](https://blog.csdn.net/qq_36653505/article/details/87875279),PyTorch 和 TensorFlow、Caffe 等框架最大的区别就是他们拥有不同的计算图表现形式。 TensorFlow 使用静态图,这意味着我们先定义计算图,然后不断使用它,而在 PyTorch 中,每次都会重新构建一个新的计算图。通过这次课程,我们会了解静态图和动态图之间的优缺点。\n", + "\n", + "对于使用者来说,两种形式的计算图有着非常大的区别,同时静态图和动态图都有他们各自的优点,比如动态图比较方便debug,使用者能够用任何他们喜欢的方式进行debug,同时非常直观,而静态图是通过先定义后运行的方式,之后再次运行的时候就不再需要重新构建计算图,所以速度会比动态图更快。" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "![](https://ws3.sinaimg.cn/large/006tNc79ly1fmai482qumg30rs0fmq6e.gif)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## PyTorch" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "# pytorch\n", + "import torch\n", + "first_counter = torch.Tensor([0])\n", + "second_counter = torch.Tensor([10])" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "while (first_counter < second_counter):\n", + " first_counter += 2\n", + " second_counter += 1" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tensor([20.])\n", + "tensor([20.])\n" + ] + } + ], + "source": [ + "print(first_counter)\n", + "print(second_counter)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "可以看到 PyTorch 的写法跟 Python 的写法是完全一致的,没有任何额外的学习成本\n", + "\n", + "上面的例子展示如何使用静态图和动态图构建 while 循环,看起来动态图的方式更加简单且直观,你觉得呢?" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.7.9" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/6_pytorch/1_NN/1-linear-regression-gradient-descend.ipynb b/6_pytorch/1_NN/1-linear-regression-gradient-descend.ipynb index 0529fae..ef09890 100644 --- a/6_pytorch/1_NN/1-linear-regression-gradient-descend.ipynb +++ b/6_pytorch/1_NN/1-linear-regression-gradient-descend.ipynb @@ -5,7 +5,8 @@ "metadata": {}, "source": [ "# 线性模型和梯度下降\n", - "这是神经网络的第一课,我们会学习一个非常简单的模型,线性回归,同时也会学习一个优化算法-梯度下降法,对这个模型进行优化。线性回归是监督学习里面一个非常简单的模型,同时梯度下降也是深度学习中应用最广的优化算法,我们将从这里开始我们的深度学习之旅" + "\n", + "本节我们简单回顾一下线性回归模型,并演示一下如何使用PyTorch来对线性回归模型进行建模和模型参数计算。" ] }, { @@ -19,7 +20,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## 一元线性回归\n", + "## 1. 一元线性回归\n", "一元线性模型非常简单,假设我们有变量 $x_i$ 和目标 $y_i$,每个 i 对应于一个数据点,希望建立一个模型\n", "\n", "$$\n", @@ -46,7 +47,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## 梯度下降法\n", + "## 2. 梯度下降法\n", "在梯度下降法中,我们首先要明确梯度的概念,随后我们再了解如何使用梯度进行下降。" ] }, @@ -54,7 +55,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "### 梯度\n", + "### 2.1 梯度\n", "梯度在数学上就是导数,如果是一个多元函数,那么梯度就是偏导数。比如一个函数f(x, y),那么 f 的梯度就是 \n", "\n", "$$\n", @@ -79,7 +80,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "### 梯度下降法\n", + "### 2.2 梯度下降法\n", "有了对梯度的理解,我们就能了解梯度下降发的原理了。上面我们需要最小化这个误差,也就是需要找到这个误差的最小值点,那么沿着梯度的反方向我们就能够找到这个最小值点。\n", "\n", "我们可以来看一个直观的解释。比如我们在一座大山上的某处位置,由于我们不知道怎么下山,于是决定走一步算一步,也就是在每走到一个位置的时候,求解当前位置的梯度,沿着梯度的负方向,也就是当前最陡峭的位置向下走一步,然后继续求解当前位置梯度,向这一步所在位置沿着最陡峭最易下山的位置走一步。这样一步步的走下去,一直走到觉得我们已经到了山脚。当然这样走下去,有可能我们不能走到山脚,而是到了某一个局部的山峰低处。\n", @@ -117,6 +118,8 @@ "cell_type": "markdown", "metadata": {}, "source": [ + "### 2.3 PyTorch实现\n", + "\n", "上面是原理部分,下面通过一个例子来进一步学习线性模型" ] }, @@ -128,7 +131,7 @@ { "data": { "text/plain": [ - "" + "" ] }, "execution_count": 1, @@ -141,43 +144,27 @@ "import numpy as np\n", "from torch.autograd import Variable\n", "\n", - "torch.manual_seed(2017)" + "torch.manual_seed(2021)" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, - "outputs": [], - "source": [ - "# 读入数据 x 和 y\n", - "x_train = np.array([[3.3], [4.4], [5.5], [6.71], [6.93], [4.168],\n", - " [9.779], [6.182], [7.59], [2.167], [7.042],\n", - " [10.791], [5.313], [7.997], [3.1]], dtype=np.float32)\n", - "\n", - "y_train = np.array([[1.7], [2.76], [2.09], [3.19], [1.694], [1.573],\n", - " [3.366], [2.596], [2.53], [1.221], [2.827],\n", - " [3.465], [1.65], [2.904], [1.3]], dtype=np.float32)" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "[]" + "[]" ] }, - "execution_count": 3, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -189,6 +176,10 @@ } ], "source": [ + "# 生层测试数据\n", + "x_train = np.random.rand(20, 1)\n", + "y_train = x_train * 3 + 4 + 3*np.random.rand(20,1)\n", + "\n", "# 画出图像\n", "import matplotlib.pyplot as plt\n", "%matplotlib inline\n", @@ -198,17 +189,9 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 3, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "tensor([2.2691], requires_grad=True)\n" - ] - } - ], + "outputs": [], "source": [ "# 转换成 Tensor\n", "x_train = torch.from_numpy(x_train)\n", @@ -216,13 +199,12 @@ "\n", "# 定义参数 w 和 b\n", "w = Variable(torch.randn(1), requires_grad=True) # 随机初始化\n", - "b = Variable(torch.zeros(1), requires_grad=True) # 使用 0 进行初始化\n", - "print(w)" + "b = Variable(torch.zeros(1), requires_grad=True) # 使用 0 进行初始化" ] }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 4, "metadata": {}, "outputs": [], "source": [ @@ -239,7 +221,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -255,22 +237,22 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 7, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -301,33 +283,33 @@ "这个时候需要计算我们的误差函数,也就是\n", "\n", "$$\n", - "\\frac{1}{n} \\sum_{i=1}^n(\\hat{y}_i - y_i)^2\n", + "E = \\sum_{i=1}^n(\\hat{y}_i - y_i)^2\n", "$$" ] }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "# 计算误差\n", "def get_loss(y_, y):\n", - " return torch.mean((y_ - y) ** 2)\n", + " return torch.sum((y_ - y) ** 2)\n", "\n", "loss = get_loss(y_, y_train)" ] }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "tensor(153.3520, grad_fn=)\n" + "tensor(719.2896, dtype=torch.float64, grad_fn=)\n" ] } ], @@ -350,7 +332,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -360,15 +342,15 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "tensor([161.0043])\n", - "tensor([22.8730])\n" + "tensor([-153.8987])\n", + "tensor([-237.1102])\n" ] } ], @@ -380,7 +362,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 11, "metadata": {}, "outputs": [], "source": [ @@ -398,22 +380,22 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 13, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -440,68 +422,54 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "tensor(3.1358)\n", - "epoch: 0, loss: 3.135772228240967\n", - "tensor(0.3551)\n", - "epoch: 1, loss: 0.355089008808136\n", - "tensor(0.3030)\n", - "epoch: 2, loss: 0.30295446515083313\n", - "tensor(0.3013)\n", - "epoch: 3, loss: 0.30131959915161133\n", - "tensor(0.3006)\n", - "epoch: 4, loss: 0.3006228804588318\n", - "tensor(0.2999)\n", - "epoch: 5, loss: 0.2999469041824341\n", - "tensor(0.2993)\n", - "epoch: 6, loss: 0.299274742603302\n", - "tensor(0.2986)\n", - "epoch: 7, loss: 0.2986060082912445\n", - "tensor(0.2979)\n", - "epoch: 8, loss: 0.2979407012462616\n", - "tensor(0.2973)\n", - "epoch: 9, loss: 0.29727888107299805\n" + "epoch: 19, loss: 15.28364363077673\n", + "epoch: 39, loss: 14.795312869325372\n", + "epoch: 59, loss: 14.536351699107472\n", + "epoch: 79, loss: 14.39902521175574\n", + "epoch: 99, loss: 14.326200708394845\n" ] } ], "source": [ - "for e in range(10): # 进行 10 次更新\n", + "for e in range(100): # 进行 100 次更新\n", " y_ = linear_model(x_train)\n", " loss = get_loss(y_, y_train)\n", " \n", " w.grad.zero_() # 记得归零梯度\n", " b.grad.zero_() # 记得归零梯度\n", " loss.backward()\n", - " print(loss.data)\n", + " \n", " w.data = w.data - 1e-2 * w.grad.data # 更新 w\n", " b.data = b.data - 1e-2 * b.grad.data # 更新 b \n", - " print('epoch: {}, loss: {}'.format(e, loss.item()))" + " if (e + 1) % 20 == 0:\n", + " print('epoch: {}, loss: {}'.format(e, loss.item()))" ] }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 15, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAD4CAYAAAD8Zh1EAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy86wFpkAAAACXBIWXMAAAsTAAALEwEAmpwYAAAZoElEQVR4nO3df2xc5Z3v8fcnwSUEuLQ3WCwlxKbaiiUkJCSGDbdqmwsBsoD4IbhaqFvIqmwov0p3K1awSMACud2VrsgWWAER5FLalIsautxclG7TQhCg8stmnRSSQCLqgNO0MYGm/EjID3/vHzMOxh17xvaZOWfOfF7SyDPnnJzz9ZH9zePnPM/3UURgZmb1b1zaAZiZWTKc0M3McsIJ3cwsJ5zQzcxywgndzCwnDkjrwocffni0tramdXkzs7rU2dn5TkQ0l9qXWkJvbW2lo6MjrcubmdUlSZuH2ucuFzOznHBCNzPLCSd0M7OcSK0PvZQ9e/bQ09PDrl270g4lNyZMmMDkyZNpampKOxQzq7JMJfSenh4OPfRQWltbkZR2OHUvIti+fTs9PT0cc8wxaYdjZlWWqS6XXbt2MWnSJCfzhEhi0qRJ/ovHLCuWLYPWVhg3rvB12bJET5+pFjrgZJ4w30+zjFi2DBYuhI8+KnzevLnwGaC9PZFLZKqFbmaWWzfd9Eky7/fRR4XtCXFCT1hrayvvvPNO2mGYWda89dbIto9CXSf0KndHERH09fUle1Iza0xTpoxs+yjUbULv747avBkiPumOGmtS7+7u5thjj+XSSy9l2rRp3H777Zx00kmccMIJ3HLLLfuPO//885k9ezbHH388S5YsGeN3Y2a5t2gRTJz46W0TJxa2J6TihC5pvKT/lPREiX0HSnpU0iZJL0pqTSzCIVSzO2rjxo1cddVVLF68mC1btvDSSy/R1dVFZ2cnzzzzDABLly6ls7OTjo4O7rrrLrZv3z72C5tZfrW3w5Il0NICUuHrkiWJPRCFkbXQrwPWD7Hvm8B7EfHnwGLgX8YaWDnV7I5qaWlhzpw5rFq1ilWrVnHiiScya9YsNmzYwMaNGwG46667mDFjBnPmzOHtt9/ev93MbEjt7dDdDX19ha8JJnOocNiipMnA2cAi4O9LHHIecGvx/XLgHkmKKq5APWVKoZul1PaxOvjgg4FCH/qNN97IFVdc8an9Tz/9NL/85S95/vnnmThxInPnzvVYbzNLXaUt9H8F/gEY6gnhUcDbABGxF9gBTBp8kKSFkjokdfT29o482gFq0B3FmWeeydKlS/nggw8A2LJlC9u2bWPHjh187nOfY+LEiWzYsIEXXnghuYuamY1S2YQu6RxgW0R0jvViEbEkItoioq25uWR99orVoDuKM844g6997WuccsopTJ8+nYsuuoj333+f+fPns3fvXo477jhuuOEG5syZk9xFzcxGSeV6RSR9D/gGsBeYAPwX4KcR8fUBx/wcuDUinpd0APA7oHm4Lpe2trYYvMDF+vXrOe6440b7vdgQfF/N8kNSZ0S0ldpXtoUeETdGxOSIaAUuBp4amMyLVgCXFd9fVDymav3nZmb2p0Zdy0XSbUBHRKwAHgR+KGkT8C6FxG9mZjU0ooQeEU8DTxff3zxg+y7gfyQZmJmZjUzdzhQ1M7NPc0I3M8sJJ3Qzs5xwQh+Dhx56iN/+9rf7P19++eWsW7duzOft7u7mxz/+8Yj/3YIFC1i+fPmYr29m9am+E3q16+eWMTihP/DAA0ydOnXM5x1tQjezxla/Cb1a9XOBH/3oR5x88snMnDmTK664gn379rFgwQKmTZvG9OnTWbx4McuXL6ejo4P29nZmzpzJzp07mTt3Lv2TpQ455BCuv/56jj/+eObNm8dLL73E3Llz+cIXvsCKFSuAQuL+8pe/zKxZs5g1axa/+tWvALjhhht49tlnmTlzJosXL2bfvn1cf/31+8v43n///UCh1sw111zDsccey7x589i2bduYv3czq2MRkcpr9uzZMdi6dev+ZNuQWloiCqn806+WlsrPUcK6devinHPOid27d0dExJVXXhm33nprzJs3b/8x7733XkREfPWrX42XX355//aBn4FYuXJlREScf/75cfrpp8fu3bujq6srZsyYERERH374YezcuTMiIt54443ovyerV6+Os88+e/9577///rj99tsjImLXrl0xe/bsePPNN+Oxxx6LefPmxd69e2PLli1x2GGHxU9+8pOS35OZ5QOF+T8l82rmFomuWJXq5z755JN0dnZy0kknAbBz507mz5/Pm2++ybXXXsvZZ5/NGWecUfY8n/nMZ5g/fz4A06dP58ADD6SpqYnp06fT3d0NwJ49e7jmmmvo6upi/PjxvPHGGyXPtWrVKtauXbu/f3zHjh1s3LiRZ555hksuuYTx48fz+c9/nlNPPXVM37uZ1bf67XKp0nJOEcFll11GV1cXXV1dvP7663z/+99nzZo1zJ07l/vuu4/LL7+87HmampqQBMC4ceM48MAD97/fu3cvAIsXL+aII45gzZo1dHR0sHv37iFjuvvuu/fH9Jvf/Kai/1TMGl7Kz9lqrX4TepXq55522mksX758f3/0u+++y+bNm+nr6+PCCy/kjjvu4JVXXgHg0EMP5f333x/1tXbs2MGRRx7JuHHj+OEPf8i+fftKnvfMM8/k3nvvZc+ePQC88cYbfPjhh3zlK1/h0UcfZd++fWzdupXVq1ePOhaz3Knic7asqt8ul/46uTfdVOhmmTKlkMzHWD936tSp3HHHHZxxxhn09fXR1NTEnXfeyQUXXLB/wejvfe97QGGY4Le+9S0OOuggnn/++RFf66qrruLCCy/k4YcfZv78+fsX1jjhhBMYP348M2bMYMGCBVx33XV0d3cza9YsIoLm5mYef/xxLrjgAp566immTp3KlClTOOWUU8b0vZvlynDrVCa8UlBWlC2fWy0un1s7vq/WkMaNK7TMB5MKS8DVqTGVzzUzq0tVes6WZU7oZpZPtVinMmMyl9DT6gLKK99Pa1i1WKcyYzL1UHTChAls376dSZMm7R/yZ6MXEWzfvp0JEyakHYpZOtrbc53AB8tUQp88eTI9PT309vamHUpuTJgwgcmTJ6cdhpnVQKYSelNTE8ccc0zaYZiZ1aXM9aGbmdnolE3okiZIeknSGkmvSfqnEscskNQrqav4Kj833szMElVJl8vHwKkR8YGkJuA5ST+LiBcGHfdoRFyTfIhmZlaJsi30YsXGD4ofm4ovj4UzMxuhatcKq6gPXdJ4SV3ANuAXEfFiicMulLRW0nJJRw9xnoWSOiR1eCSLmTWSWtQKG1EtF0mfBf4duDYiXh2wfRLwQUR8LOkK4K8jYtji3KVquZiZ5VVrayGJD9bSAsUlEiqSWC2XiPgDsBqYP2j79oj4uPjxAWD2SM5rZpZ3VVqT51MqGeXSXGyZI+kg4HRgw6Bjjhzw8VxgfXIhmpnVv1rUCqukhX4ksFrSWuBlCn3oT0i6TdK5xWO+XRzSuAb4NrAguRDNzOpfLWqFVTLKZW1EnBgRJ0TEtIi4rbj95ohYUXx/Y0QcHxEzIuK/R8SG4c9qZlZ9WVqBrha1wjI19d/MLCn9o0r6Fy3qH1UC6dXrqnatME/9N7NcGm4FurxyQjezXKrFqJKscUI3s1xqwBXonNDNLJ8acAU6J3Qzy6cGXIHOo1zMLL8abAU6t9DNzPLCCd3MLCec0M1GIEszD80Gcx+6WYWyOPPQbCC30M0q1IgzD62+OKGbVagRZx5afXFCN6tQI848tPrihG5WoUaceWj1xQndrEKNOPPQ6otHuZiNQKPNPLT64ha6mVlOOKGbmeWEE7qZWU6UTeiSJkh6SdIaSa9J+qcSxxwo6VFJmyS9KKm1KtGamdmQKmmhfwycGhEzgJnAfElzBh3zTeC9iPhzYDHwL4lGaWaj5wI0DaNsQo+CD4ofm4qvGHTYecAPiu+XA6dJUmJRmtno9Beg2bwZIj4pQOOknksV9aFLGi+pC9gG/CIiXhx0yFHA2wARsRfYAUwqcZ6FkjokdfT29o4pcDOrgAvQNJSKEnpE7IuImcBk4GRJ00ZzsYhYEhFtEdHW3Nw8mlOY2Ui4AE1DGdEol4j4A7AamD9o1xbgaABJBwCHAdsTiM/MxsIFaBpKJaNcmiV9tvj+IOB0YMOgw1YAlxXfXwQ8FRGD+9nNrMaeO2sRH/LpAjQfMpHnznIBmjyqpIV+JLBa0lrgZQp96E9Iuk3SucVjHgQmSdoE/D1wQ3XCNbOR+PrKdv6WJXTTQh+imxb+liV8faXrF+SR0mpIt7W1RUdHRyrXNmsU48YVBrcMJkFfX+3jsbGT1BkRbaX2eaaoWY65C72xOKGbVUkW5vO4hntjcUI3q4KqzOcZxf8QruHeWNyHblYFra2FJD5YSwt0d4/ihP3/QwycJDRxorNzA3IfulmNJT6fxzM+rQJO6A0iC/25jSTxh5Ge8WkVcEJvAK7PVHuJP4z0cBWrgBN6A/Bf67WX+MNID1exCvihaAPw5JKcWLas8L/wW28VWuaLFvmBaAMa7qHoAbUOxmpvypTSIy7813qdaW93ArdhuculAfivdbPG4ITeADy5xKwxuMulQfivdbP8cwvdzCwnnNAt91KbVOXZXFZj7nKxXBtcAqV/UhVUuQsqtQtbI/M4dMu1xItkZf7ClncuzmUNq+YlUPq7WUol86pe2MwJ3XKupiVQBhbNGWlAFZ7eXfI2nLIJXdLRklZLWifpNUnXlThmrqQdkrqKr5urE67ZyNR0UlWpojkJXdgF1qwSlbTQ9wLfjYipwBzgaklTSxz3bETMLL5uSzRKs1Gq6aSq4bpTxnhhF1izSpQd5RIRW4GtxffvS1oPHAWsq3JsZomo2aSqoYrmJPAg1OXQrRIj6kOX1AqcCLxYYvcpktZI+pmk44f49wsldUjq6O3tHXm0ZmkbriO7iv07Lodulag4oUs6BHgM+E5E/HHQ7leAloiYAdwNPF7qHBGxJCLaIqKtubl5lCGbpaRcR3YV+3dcYM0qUdE4dElNwBPAzyPizgqO7wbaIuKdoY7xOHSrOymPLXc5dIMx1kOXJOBBYP1QyVzSnwG/j4iQdDKFlv/2McRslj0pd2S7wJqVU8nU/y8B3wB+LamruO0fgSkAEXEfcBFwpaS9wE7g4khrCqpZtXilEMu4Ska5PAeozDH3APckFZRZJi1a9On6LOCObMsUzxQ1q5RXCrGMc7VFs5FwR7ZlmFvoZmY54YRuZpYTTuhmZjnhhG5mlhNO6JZ/LiRuDcKjXCzfvLanNRC30C3fXEjcGogTuuWbC4lbA3FCt3xzIXFrIE7olm8uJG4NxAnd8s31V6yBeJSL5Z/rr1iDcAvdzCwnnNAtdZ73Y5YMd7lYqjzvxyw5bqFbqjzvxyw5TuiWKs/7MUuOE7qlyvN+zJJTNqFLOlrSaknrJL0m6boSx0jSXZI2SVoraVZ1wrW88bwfs+RU0kLfC3w3IqYCc4CrJU0ddMxfAV8svhYC9yYapeWW5/2YJadsQo+IrRHxSvH9+8B64KhBh50HPBwFLwCflXRk4tFaLrWzjG5a6WMc3bTSjsctmo3GiPrQJbUCJwIvDtp1FPD2gM89/GnSR9JCSR2SOnp7e0cYquVS/7jFzZsh4pNxix6MbjZiFSd0SYcAjwHfiYg/juZiEbEkItoioq25uXk0p7C88bhFs8RUlNAlNVFI5ssi4qclDtkCHD3g8+TiNrPhedyiWWIqGeUi4EFgfUTcOcRhK4BLi6Nd5gA7ImJrgnFavRtqfr/HLZolppKp/18CvgH8WlJXcds/AlMAIuI+YCVwFrAJ+Aj4m8Qjtfo13Pz+RYs+vQ88btFslMom9Ih4DlCZYwK4OqmgLGeG6yfv7v7kmLfeKrTMFy3yuEWzUVAhF9deW1tbdHR0pHJtq7Fx4wojWAaToK+v9vGY1TFJnRHRVmqfp/5b9bmf3KwmnNCt+jy/36wmnNCt+jy/36wmvMCF1YbX9TSrOrfQzcxywgndzCwnnNDNzHLCCT1BXr3e/DNgafJD0YR49Xrzz4ClzTNFE9LaWvgFHqyl5ZPZ7ZZv/hmwWvBM0RpwFdjhNUJXhH8GLG1O6Anx7PahNcqiRP4ZsLQ5oSfEs9uH1iiLEvlnwNLmhJ4Qz24fWqN0RfhnwNLmhJ6g9vbCw6++vsLXWv4iZ7mPupG6ItL8GTBzQs+BrPdRuyvCrDac0HMg633U7oowqw0n9ByoqI865T4Zd0WYVV/ZhC5pqaRtkl4dYv9cSTskdRVfNycfpg2nbB911vtkzCwRlbTQHwLmlznm2YiYWXzdNvawbCTK9lFnvU/GzBJRNqFHxDPAuzWIxUapbB91o4wbNGtwSfWhnyJpjaSfSTp+qIMkLZTUIamjt7c3oUsblOmjbqRxg2YNLImE/grQEhEzgLuBx4c6MCKWRERbRLQ1NzcncGnbb7iHnh43aNYQxpzQI+KPEfFB8f1KoEnS4WOOzCpX7qGnxw2aNYSKyudKagWeiIhpJfb9GfD7iAhJJwPLKbTYhz1x3srnpsp1W80axnDlc8sucCHpEWAucLikHuAWoAkgIu4DLgKulLQX2AlcXC6ZW8L80NPMqCChR8QlZfbfA9yTWEQ2clOmlG6h+6GnWUPxTNE88ENPM8MJPR/80NPM8CLR+dHe7gRu1uDcQh+hLNcdN7PG5hb6CPQP9+4vi9I/3BvcODaz9LmFPgKucWVmWeaEPgIe7m1mWVZXCT3t/mvXuDKzLKubhJ6FNRo83NvMsqxuEnoW+q893NvMsqyi4lzVMNLiXOPGFVrmg0mFGuBmZo1guOJcddNCd/+1mdnw6iahu//azGx4dZPQ3X9tZja8upop6nIlZmZDq5sWel1Ie6C8mTW0umqhZ5oLvZhZytxCT0oWBsqbWUNzQk+KC72YWcqc0JPigfJmlrKyCV3SUknbJL06xH5JukvSJklrJc1KPswMGerBpwfKm1nKKnko+hBwD/DwEPv/Cvhi8fWXwL3Fr/lTyYPPm24qdLNMmVJI5n4gamY1UlEtF0mtwBMRMa3EvvuBpyPikeLn14G5EbF1uHOOtJZLJrS2FpL4YC0t0N1d62jMrAFVu5bLUcDbAz73FLeVCmShpA5JHb29vQlcusb84NPMMqymD0UjYklEtEVEW3Nzcy0vnQw/+DSzDEsioW8Bjh7weXJxW/74waeZZVgSCX0FcGlxtMscYEe5/vO65QphZpZhZUe5SHoEmAscLqkHuAVoAoiI+4CVwFnAJuAj4G+qFWwmuEKYmWVU2YQeEZeU2R/A1YlFZGZmo+KZomZmOeGEbmaWE07oZmY54YRuZpYTTuhmZjnhhG5mlhNO6GZmOeGEbmaWE07oZmY54YRuZpYTTuhmZjnhhG5mlhP1ldCHWqDZzMwqWiQ6GypZoNnMrIHVTwv9pps+Seb9PvqosN3MzOoooXuBZjOzYdVPQvcCzWZmw6qfhO4Fms3MhlU/Cd0LNJuZDauihC5pvqTXJW2SdEOJ/Qsk9UrqKr4uTz5UCsm7uxv6+gpfnczNzPYrO2xR0njg34DTgR7gZUkrImLdoEMfjYhrqhCjmZlVoJIW+snApoh4MyJ2A/8HOK+6YZmZ2UhVktCPAt4e8LmnuG2wCyWtlbRc0tGlTiRpoaQOSR29vb2jCNfMzIaS1EPR/we0RsQJwC+AH5Q6KCKWRERbRLQ1NzcndGkzM4PKEvoWYGCLe3Jx234RsT0iPi5+fACYnUx4ZmZWqUpqubwMfFHSMRQS+cXA1wYeIOnIiNha/HgusL7cSTs7O9+RtLmC6x8OvFPBcY3G92Vovjel+b4MrZ7uTctQO8om9IjYK+ka4OfAeGBpRLwm6TagIyJWAN+WdC6wF3gXWFDBeSvqc5HUERFtlRzbSHxfhuZ7U5rvy9Dycm8qqrYYESuBlYO23Tzg/Y3AjcmGZmZmI1E/M0XNzGxY9ZDQl6QdQEb5vgzN96Y035eh5eLeKCLSjsHMzBJQDy10MzOrgBO6mVlOZDKhSzpa0mpJ6yS9Jum6tGPKEknjJf2npCfSjiVLJH22WHpig6T1kk5JO6askPR3xd+lVyU9ImlC2jGlRdJSSdskvTpg23+V9AtJG4tfP5dmjKOVyYROYTz7dyNiKjAHuFrS1JRjypLrqGDyVgP6PvAfEfEXwAx8jwCQdBTwbaAtIqZRmE9ycbpRpeohYP6gbTcAT0bEF4Eni5/rTiYTekRsjYhXiu/fp/CLWaogWMORNBk4m0KJBSuSdBjwFeBBgIjYHRF/SDWobDkAOEjSAcBE4Lcpx5OaiHiGwgTIgc7jkxpUPwDOr2VMSclkQh9IUitwIvBiyqFkxb8C/wD0pRxH1hwD9AL/u9gd9YCkg9MOKgsiYgvwv4C3gK3AjohYlW5UmXPEgPIlvwOOSDOY0cp0Qpd0CPAY8J2I+GPa8aRN0jnAtojoTDuWDDoAmAXcGxEnAh9Sp382J63YH3wehf/0Pg8cLOnr6UaVXVEYy12X47kzm9AlNVFI5ssi4qdpx5MRXwLOldRNYaGRUyX9KN2QMqMH6ImI/r/kllNI8AbzgN9ERG9E7AF+Cvy3lGPKmt9LOhIKxQaBbSnHMyqZTOiSRKEvdH1E3Jl2PFkRETdGxOSIaKXwUOupiHBLC4iI3wFvSzq2uOk0YPAyiY3qLWCOpInF363T8APjwVYAlxXfXwb83xRjGbVMJnQKLdFvUGiB9i88fVbaQVnmXQssk7QWmAn8z3TDyYbiXy3LgVeAX1P4vc/FVPfRkPQI8DxwrKQeSd8E/hk4XdJGCn/R/HOaMY6Wp/6bmeVEVlvoZmY2Qk7oZmY54YRuZpYTTuhmZjnhhG5mlhNO6GZmOeGEbmaWE/8fWWtPLpmPxEQAAAAASUVORK5CYII=\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -523,7 +491,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "经过 10 次更新,我们发现红色的预测结果已经比较好的拟合了蓝色的真实值。\n", + "经过 100 次更新,我们发现红色的预测结果已经比较好的拟合了蓝色的真实值。\n", "\n", "现在你已经学会了你的第一个机器学习模型了,再接再厉,完成下面的小练习。" ] @@ -532,7 +500,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "**小练习:**\n", + "### 2.4 练习题\n", "\n", "重启 notebook 运行上面的线性回归模型,但是改变训练次数以及不同的学习率进行尝试得到不同的结果" ] @@ -541,7 +509,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## 多项式回归模型" + "## 3. 多项式回归模型" ] }, { @@ -579,7 +547,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 15, "metadata": {}, "outputs": [ { @@ -611,22 +579,22 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 16, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 17, + "execution_count": 16, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -655,7 +623,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 17, "metadata": {}, "outputs": [], "source": [ @@ -671,7 +639,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 18, "metadata": {}, "outputs": [ { @@ -695,7 +663,7 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 19, "metadata": {}, "outputs": [], "source": [ @@ -708,7 +676,10 @@ "y_train = Variable(y_train)\n", "\n", "def multi_linear(x):\n", - " return torch.mm(x, w) + b" + " return torch.mm(x, w) + b\n", + "\n", + "def get_loss(y_, y):\n", + " return torch.mean((y_ - y) ** 2)" ] }, { @@ -720,22 +691,22 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 22, + "execution_count": 20, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -764,14 +735,14 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 21, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "tensor(447.3372, grad_fn=)\n" + "tensor(1144.2655, grad_fn=)\n" ] } ], @@ -783,7 +754,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 22, "metadata": {}, "outputs": [], "source": [ @@ -793,17 +764,17 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 23, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "tensor([[ -60.7756],\n", - " [ -81.7448],\n", - " [-401.0452]])\n", - "tensor([-15.4545])\n" + "tensor([[ -94.7455],\n", + " [-139.1247],\n", + " [-629.8584]])\n", + "tensor([-25.7413])\n" ] } ], @@ -815,7 +786,7 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 24, "metadata": {}, "outputs": [], "source": [ @@ -826,22 +797,22 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 25, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 27, + "execution_count": 25, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -870,18 +841,18 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 26, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "epoch 20, Loss: 22.71861\n", - "epoch 40, Loss: 5.37627\n", - "epoch 60, Loss: 1.32816\n", - "epoch 80, Loss: 0.38091\n", - "epoch 100, Loss: 0.15742\n" + "epoch 20, Loss: 65.56586\n", + "epoch 40, Loss: 15.41177\n", + "epoch 60, Loss: 3.70702\n", + "epoch 80, Loss: 0.97122\n", + "epoch 100, Loss: 0.32874\n" ] } ], @@ -911,22 +882,22 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 29, + "execution_count": 27, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -959,7 +930,9 @@ "collapsed": true }, "source": [ - "**小练习:上面的例子是一个三次的多项式,尝试使用二次的多项式去拟合它,看看最后能做到多好**\n", + "## 4. 练习题\n", + "\n", + "上面的例子是一个三次的多项式,尝试使用二次的多项式去拟合它,看看最后能做到多好\n", "\n", "**提示:参数 `w = torch.randn(2, 1)`,同时重新构建 x 数据集**" ] @@ -981,7 +954,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.9" + "version": "3.7.9" } }, "nbformat": 4, diff --git a/6_pytorch/1_NN/2-logistic-regression.ipynb b/6_pytorch/1_NN/2-logistic-regression.ipynb index cef4c03..1ced160 100644 --- a/6_pytorch/1_NN/2-logistic-regression.ipynb +++ b/6_pytorch/1_NN/2-logistic-regression.ipynb @@ -782,7 +782,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.9" + "version": "3.7.9" } }, "nbformat": 4, diff --git a/6_pytorch/README.md b/6_pytorch/README.md index cbe9c54..3645aa6 100644 --- a/6_pytorch/README.md +++ b/6_pytorch/README.md @@ -1,4 +1,15 @@ +# PyTorch + +PyTorch是基于Python的科学计算包,其旨在服务两类场合: +* 替代numpy发挥GPU潜能 +* 提供了高度灵活性和效率的深度学习平台 + +PyTorch的简洁设计使得它入门很简单,本部分内容在深入介绍PyTorch之前,先介绍一些PyTorch的基础知识,让大家能够对PyTorch有一个大致的了解,并能够用PyTorch搭建一个简单的神经网络,然后在深入学习如何使用PyTorch实现各类网络结构。在学习过程,可能部分内容暂时不太理解,可先不予以深究,后续的课程将会对此进行深入讲解。 + + + +![PyTorch Demo](imgs/PyTorch_demo.gif) ## References diff --git a/6_pytorch/imgs/PyTorch_demo.gif b/6_pytorch/imgs/PyTorch_demo.gif new file mode 100644 index 0000000000000000000000000000000000000000..b4f17374e034911dfaf7d639a695f036f9166244 GIT binary patch literal 264025 zcmY(p2T+qw^r-!&(n&y?NC`baK$>(Rq4y?TL=aG_hN1)oNuh+^5u`{bGz~?hsdNw! zX(A{pO$0>+K?Q{TKJWj2bLZZjXUpuIot@co_Uzd;H8;`J^4^4~fd2ph2mtYLuxd#O zo<|EAVnm&_&_QOZWLLf7_{fJ14NVPAO^pv9Ha%)>Ztd^w9~~VV8lN1QoPIeuJux-+ za(4dJ>&4lHck^%GFD!k0`(b5idF{i>`tsVw%KGQ^jjd0cU*CV;oBe$9?(50Qx08+S z{V!j?Z-3kQ{^RHF?%vP6UqAK^w)Ysjzfbmm9sK_N=g*(RgM-6^!@s`|PY#bxj{YA1 zJ^Ficbae9fgz=ZbIR3vlVI2PtCk)2_f${%`|6TDv(kI7^e;of0|3~isEu8$?Ki>a& zyz~9<=KA6C+k?fKKQrUMMtgrfZQFa&u+v&I(^NE6SMY+C`-+yaRGYL>mHwkN|3^;7 zx8(S*q^K`hgsn2dcGayPRpGmpVY`*#d$g#%%Fw-v(4Q6f|IKa%ez)>}u~Tv5NBNB} zMIoQEgFa+jeVuk?oa)(6be+F_VI{#3Q5`bNjXL2+~T;r;`sd1gnOll1!dI2GV1;Exs=s>}y9S>?4k z6?J)4_4(C}_iCC7X%Fw$Ju0rJmo_v%XlyNi*jDlAaaD7BP4ko5)(%=*SKZ^ThW4I^ z9Z%_<&zifQH+T27Jne6LHqhQX)X_KG*+0@fIQndO{Q2la@5J2D(*DrL%>OYKsen@(Hc&F>|R>whj`{9kYgP@iJzefjN zO@A&m{<+xj$F=T{bKP%e+JQ^m;XlOwW3w@KykLm4GgeVlf`9-35IckdzW;K}zX<%V zZ2~YefD~pSGkRGch53}6$0)sgAQ35HQEb*+F_a>p8n`stTse|~GE5dSZ>f5bgT7Gj z@uH=A{GO7}Sh0C)&C4Rq@Gna*T5DfDz*1O+E!t?)m1a3|m&V%aW^3&#ElMmN*S~IX zZ4G=s_PF8ABd>vEVaxW$#a92>`b*>OP4AxI*TzaLpFDiuP1yVLe*DR!kI#t^HW8~1 z`pN+Hl)UFeNAuc9ri5jwRcFhm@dDML4-=iOpI?<3rifT~wQbGPE;M+)?0Wq54c%wF z)VjO<+q;hNuOD7^Kl$;om%=7$)6=oLHku=Ud9tT-@AFipC zeY)qBAiGiEn;)=I=wDN}aX+|yYoiE1Ec>}QVm{z=31Oq|b7^$Cm z04L&JSOHfK%&&yucZSIY&*=n=jlpA0j;pPcxQ-I0U@yv1W zr|WOqK?iFVoh5DcH`RE)<48xqEB(LQdkFoB^eJ1t!CNCV1ZKTqx>Nc^E24E+yN#^R zU?0C>Fn{~kq~80ZB>R?iPo9U`$M`c~?O$2`x>lUcZ^9zAlv^X(E+{+N=XbJE*7Gcu=lX`1msb)w9W z>tagCFVi>^i%sS~ncGu+-|=U-9&0?xBpCQ29&)`~;ETKU?t0`s&hdiTx49qqPF~O| zNEbzB9teH(`EHyR8#BxNwf}CSqH`sIVXe+J^&9Pq9 zI;kZ#fehf1M<-7DV$;KOeVm!Z-ankfrPrSef^O_wZv0uB9wrbR3ic*x&6RWhQBEd) z0*Vo1&72Vv^?0ybpVoXI_CK*W*r%xnf05!Ux63T;76kiPPZJ;s)G{H)XMZoQEBskp zUl78AhNJ8T_;eDD9`hq;bZ;tBCw9|{wcCBZUWEj*3gp0^bzk>=%pSqZc5K;jXurs2` zJ*L`UXz8&FX+nQCN5+0<4eF<%L32QLRiQq*#_7t1s9xY%!hX5iH#$t!#ZDuj;!x&qw8Zn>i`FqT?hqr0 zf%MC)%v<{ukr19#PF*aB#SXALl}WUbvZIjvy=qVO_F@CeW{YhAJDu0EtZ)Z%m9rO0 zeSydp_KC!5wp<79#5qKLnXS5ty{njswF%KiqO6?o;-MsX*cge_i>fo_rE<0(kx2w> zqxMs5S+JdBGq-P}wgOH&g$PE_zDb(kaqz&m&ZHhx9gjdGCm>I1_&99`w%g%5n}73 zruzF_h>!h{(s$n!#~qzt+#EC%b&?pF``*VHL8pj>2UlS6N(k>S5RtE5rn)Uj8E%KY zBJ=N=%)3tyg>651zD;AAiPOn6WaNl^v%~wdNb4xF`a*x(`RdM*(r=l~32UN9^}c#@ z#%vpke8V#l|0rh^i1>;;%2P7`wQKE{^hWfsKoM_Uq;#LDv7+IT<_C_uz96fMAz|MA{I+Uoe^6qlX~NbLJd^O4s0aUCie;+lv2qKvBBO zlf=8dSO?-4^P=xCHawQaCL3gO7W*0;imN?;KJ!f3(WHz3Gwf~}#}mQ(lh7p9`gl1c zE1?T~e!meH7~;>u4uugm9%Jv95q+30qE2PD77N>Tu&I@`u!N^-9ho7+y$*ZW50}nY zpdq(+427F4L`L@QGh)>CY*hqkT07;Od}VmpLR(@5mF=mGwz3Fs5DlA|S3_ec+EhPYD< z`5@NO@*a3>8(Gj(swv9MvB32ygP#N&KB>V@+P~%2un1$6C7Qaqy}DocMQD8~QKvq^ z^zO0GIuf)JuHOu~ic-AcFVTM@hLA0tj*K12XV3hsV?2CG$)Upp zJcvqAp1^TN5e?T)pM`7adUE=e^$3jO6LluaIdVk@1lCcBS`*$sE3OR)|0E`=q>^?k z9t@oMX_o*U?F6+dCUJ7p4~Acner3NoKBFC*IB}try=nxqX_%3yHQ2}Aewpa`-#sql zbLF7ivxXwtj2{UvG#DIJ2*%f;DY(`YXz#wvfROHwgg4!nISHtfgVUGcT1z-iU$frg zN7J*_-lRYK8qs0&XgX6=cp1}u)4O=DyTc=dFEUJ_D0pK2olIrK8)Kvj(b7F1iM4Z= zV!|HnAUFq=p%S4sgO_4ek+0SeBE}xSkda&B7XRT1Y*!H$;pjFAcea&Kh_~LiGBgg4 zsgOkMBp|=qDZ4o%am-M@15PrPS0y9~393h^t4UB})oaJ^mNf4i_C36Hh>0{=>xd_*#fm7A(~6?utg*$Uz#7n*2L5cHTAh@e^PkNJ-|>_)7^gx8PfoW1cOE96T2RZw4<)hE`obRt!26^;5vp|Ar_2LbtaBZ8dG`QI`_S!P~Q6#Z|& zZr&eIly-Hdu4fqIIZv?0@D)ytdF0>qI455VrgD3TmQi$K#?K4TU%*-RU0pvTc}V`I!rtivak%kjJmUPFTc_(xx3?DwOMiuOKkYgy{tocC^m_*0W58%rgWxO z)h6$L&L=J=z30D|iSsaHLCdL9oDDgT%QUa}kigRMj9!FLB$CeT_1F!%ZKn}-I#2eh z2I;3-sanEfo(067b6paA!_|4t6!}Xj%h4aX@$aPDRp4eUsw`BX*NNxZn!zVK2n;df zgK-87Aa=$)DT(CtAL< z3MxWT+)`x#i{0JjHwD+sE26n_kSl=$XcW|$`lqd zCwol!iim+!Snp=I6c#O{Mai*@H$U1Sh+-KSo!@d28)8U z8*mQJ7Qq70LQ$S<=15aYq7JPX;!V0T0%oWwA-w{T<&SerIuH#n(6d{dpX@j{lV*HOfOP=yO4wrF4N zK>jjo)v{b4V`k;NuJH3m$hvBay8Rsl+ULP3!D6?7oFENZY$lB&24Y9SY1At9+m*LZ zC(j)e%xy+Z9Tb)_Gr6PuMa4iVwM+%fOdGU&U+-6x`{!%kPQlaf;(K8zdr0IkJj><2 zp?g(%QvO1H%5EalpUAtJ*V3;OL45dg#&}4$b8IKADlj1b<5&tI>3-U-?gmk$!z&XmrXs9^+@)ir+go3}4JEQ_suHc& z+Bmrfk@8=W5}o&@F1SC5vb8I+wkk51hF$#8a_L|}^Tlnn=Ca}+Nh|xmh@VJwPa*PG zA(GEE2byL5W9>m&b_0jEUJgNrD;zl+W&AzK(v$76lxv=uw0^ygVTv*g*M-t=g$ zYrmePK5?zoNUrp-xF56lFlvVog1UzC=3t|Dl$bSRz7&2Wq;C+SGF;%CQy>u#B=Xk1 zES7>udNrFSJ^e*WlzFmWFYpF+zP=l{j!h>3o$6iHprFbPW~Li-;`JTa#+U%P%WksU z+T7>dI~By0R>j{8;6^zGsfR*bm__W`ablF(gv~R1laOx=OCim*+T*RUf|qB+!F&g8 zKXw$@>}{{!Mt(T=80;-~VNYIu=ec|@7{rf{m(zcI&gMH3{Ax81+N{W=ja0Q$76W?! zlkbH@d&)|Cq=vOyOITQU<}!AyuLmLV2vL4s|%2i#g)>a(Ax8KA3Q8#xf64rS{7r_l0B=hQbL zg{n&5<&k4EMHWx4ew5TD>L3Alz2PFF*<#EYstPNI{Ien?Jdjd7$U)xtk;49B zBQe`%D}n~cO}GXOjCWdrLv>Gf^6rLS3t4_xB@kP6ri-Xm=p9{Iu6514k&Cr=&`NID z4MUn3=IR;--Um;9kIwfv=8A_8|7aZY?E#XrwEjjQ4rg95CctNF@kQA-uBJ8;^NH}R zr||N4lv`lp&k^Y9QD)_*8WYdpp`)yzENcifke}+{j;@a9TshXy4n}I1LHHIJ3d$1b z3Lb>)=nLFMXuz3bhcd_oiV8(a*0i;hsjtsNGE4p9z#%cC(+b($h&0+7o0OV>g+3Af zt$M}`JyJ0t{QJp_fxDRQ#N@<)*Y36J%N->_lNmB;8^QU1bY}!`FJTv78DXN>Gbg^aJ*%O%B;HLU@i+o$8iIb;k4a1(uvVDRQ#vQ_#^uO}xiY~%YGRsO z!!F=?GFZ9QRoHQx=kK83GDx(Ei*p$mB&5f3(8Ex0R^W}G{m_2ThkfC@9?Sl9Ux6!A zll#`g?3u5yz2NUHB=Qxxh5gnpbHtxAzwC-Bs4`^H_l2<+)Hi5x(68lvRDFGJJ@d0? z!letiI}P?p)6yK|{HC{cX-NOI#e}X2MrIMfGrLyN&b){a-9$4d6%)D9&z@2W*W+js zFbO+bA?LYqxA)A`od1>0@p4Q!yqI%#jqKaH%BKAOByRo0$b_6S9}{|Q>t#ym*M}Lk zm8mc0&&q{d>@7HcIq#PVD!i(`$KLbnWYTSii^R=x80R&=V(HOgWmZweLYXqhY`7h#mLRafef#UVv zdSkm8^K@UF4^`=9YoZFoh~=#v-+StZMWcCim@bk#3DNzK>~t+xSi(FpJJhWfZK8-A zNkcxErCEMkw>gh|{L4Wp9U_kX#O(d)rTg?A9bq`~`f@18o1IVB4hhSVJ%xmx=lpkl zI388FKJts%K$XK@`oE0*mLFMGQ=JpEdi_TfW6~YP9lHGEKSd_bK!N0+OKu9b#zcrq z4NXoU=QAD59U;rfi57UlIYow~4c@?nqn~#oetF?QG7NC8W2-TB>;7G&;I~WPl=@WZ z;B|cC{<6V6Zpcm>;_QFV#k@EHXVZFyzKRlpw{=e*3I0U1a$4i$4d<*k!k*`MudS93 zUtiEJGYn0H$X->}y}{W5xncK4`6~*1$PKp3w{F&Tf7g#-nE-3j!KYvMhZSxc)3-5; zil3JM9Y}vvGV7-%=Un$~tJT2mE%Lv;Hl5Nxz0*T}ZC9z_%s1}+xK4=u$jU@;>-fJrX=jDML=bcoE4-th{JF|DnMq%O)~dY7vjpGeJn5ZHNVV*6bogV3$ovw) zukT;I;jpN7?msUZAKwA?YqmkRY`1|FxmT+ghG-ji-S8hH1pUDRL)_|Hw%M^R68Gw7 z{mr5iJLS%OyKN(Ajn?TCu-)^e_&SqIy(b-u`zZwjZC9H+aVO5+|=@-4>HirjKNm>68Di zro{0XPn18-QJBuKIWXzrGDLu>IWkDO-jX0NT2iyv=AnMfRqbG&Q8HPJ}q zeNsHH3G<3@G_%2`PNgS|Rs7a*RNX>Pa^6iz_0a5o>eV92cBk@+p&->_GBBpIKenXc8OrIW?C* zLDWC20VF2$GN3EZh*6!jUXyd3vw8J1LQ#XqmAG{KLBiYSz&HJUr7_n%zOL}@D6{lc z>arzYj8Bg-zZCgKiq9jZ-s$&BQE|Ijh~MI~d{x(+0a>lk6y%vp74zBMuGbf%oiDBD zmpC&$d1_;EHej6BIr-X~PZ;Ksw>OJhpKG|Nm&7h}sRvG*#?EqdYUi(Um^aQjaN4fe zy&r@8{3eIc{65N!sB!!*@2IJGDf)%w8dS?dOHylj75K2zfr&4=Z|IwSF7YDTniqZd zq1Fb`=bGMVSQHUk*5#94nvz)Q|9px0t+_S7f2pJG>&WxAS{NsDzOgFffoA@+A zj}bJnE}&rm<=lzoHY$ghxhB3=l|qg_wEU|parS}=9>>?OWofCoJz*vM;!m4cdVk6N;h2XKeFL{7UBLWo>Y%=-3*8Gq)DYqe<@Bl z#23lD3!wY}SEHq-qw!n1LjxoV0i!;ix5$xPY{ zoSbZHvW^?QmdUqx6U7cj^zHUhVaI`nCq4O0ptsNcWSwHUqOTd85gcs~oM}+CO6Qzf zVJJi%LqvbpFJFRvt%sqpd2hQ1L>hgG@6HV&LVCC_Z2uh4E7+xlY1Y-ZWhUOt9=cG< z4GeeHjXdw|v;86OdF_GtaE50VuyS#&|LplvxKyI_M08S44U=}D)l ziHXq@1FQ^@YpDdurKZr#cwOJhM%2g@jQe5|`zu6|U+S6<>%@m0-&!H8WdvqRW37T| z^W{oaweQST!|G2;-$6d^td6e^?DV?4vYcYe2P*500Nn)`LM(4!a>ue&>3#s`W2teW z>wn*i=W1Fktx7&l12aTa@9PC!L8e^(X}99T;0|ny>4b=g zH+`|s`Fd_#VKHj!>5aP?593et{9<0Y-m5v-zms%j?5B?T# zAr2Rcr}pP+;^qtP2(W&vWs)S+9S5Ktg0zV&oo{2pxTx*7KDr;gd@ zN>XX(267zlJW-1T_k6JU{?PYsNJNcBiRZQO+fOA?B=0-(b^fd$5B$~hbuMn%sj3=&(g7X$bbv>P=liflKZ9k7SXXlaU|x9>mt(!r4BubYh(N82hkx2gNvP z`5yr9A<#cnMkXPOo;Ei7QpKZpjZ=BCelRa}Y7t9eS>~w^XGGVYUwxOG`kM_I^Vw1- z9XguKa)3sr&h;W-Zw|%7=$}}fu!(Y!X9NgbFv|Zk6 zk720tq1z{DLiR=nC4~#9EM(IacqXN+_ngR)l<`3(5HUs0M)ga6jwzd00hd^ayOH=pKnJx=FkN_h5J1 ze`+=V=%ncP=Bx&^=uUxot*Fv8KxLHjLLx<00!ZA`o|nLV7VF~o#i_3k=r=0sd-PGW z+G~l`Sg+*hLI|8kwD#>;$O2{WtHFds%0Fvn;%AP6t3j=jDu4pI?#Ke0HP*Tk`q84N zCGS`K?hg6WY(`*sG8Z`v)7s(d8Q)xt%&g!n@$j`Rd9|1_Eh^gL{C#SiLD7>)?oUZ+X}Rf z5`96&`c#51XQOAxh?ZY~( zX>v7pG^uJdIf5pRGTsU3J-Wk6(jtmq(XuFnfL$w_{TsCfWi@w(rIo=@iGIf4dsRsW zz`>}-4o*kz{>^@fbJB>s#eF?M{BZG+3QlGtr4GW}6Yz!NF*Ecml>71=e>Yv~Y`L)% zcl{f830-&gl=ZQP`(ux`<-|R7?;fkG1sbX0ENTVBjU;;~EQxUB(~)IB5fAAA)UqH% znMU>0Ly@rK)AKs!=Wq86Z@zdN&PqzEJD*LtPwK8&pb!RxKL(B4gi_%C#C;3unPsAi zYd>0^2j^C)3-r7iG!;p1qe90SbB-@xLoJ)*k{=-rJRB=@n4tky!kAFGdt!!K)6&b{ zhABamxg)v_51>kdWSs&so4H9vqMArZ@D$)AJCWhtIXzZMNiynCI#rh1RI1h|9YunA z5yOre$>vXhpmEaytzfU0zaw7#iLccC<2<^2Aw;U zux&G2T@m1*u;oBJs}qo!CLLPIJYOi0k?hc*Pd!|K=$E~0ZM5z{cKi^kE%z3m>FOek zkLn_)4}7QjZrUfavp)ViM9R?=j8A@jcu$J}*ompE9@h=zHf4!)TvA1$M#uenWMoQf0jbSgI%7t#4y9?Ht-f2&97aX}W zt$uS><9y#^G{!MEWffHDCeEwFTG{4UkriARSJ)%(bgC^VmAa+lbE>ZO0AijA)h9r1 zHqJs)Q=tyTreq zl+gccFZwMwS#Q(!pLfzt(C(52U5QTYh+q%)2h!H89dJ2ShuGXk9l0f~gXYe+-4~h! zdA*ad1-le1@pQYIZ7+eyI?BUj257|zw|L1GuCje!eCF!+=GM(O*oYj*uEr=>YOPYg z75fu(GuuN(AIge{B$d=wgrtbvQrWz7311nppkTQ@m{>!wEbdsljDRtufjrU`uS5e z2N=zrXAb==Z>kobV_jDVSmK4<%~BSt{odC6YAdvUdzyz=RTHG&2(sQUk)CynNouE+ zxahnEp8})=h!&6H)#f7JwmH3X$>VD+d6OJ2km>^@ncr7??CKGitd1uMVjqp5M4z0` zQMUtNUIU{SiGJta=>QOZ*LTA=mqtQ30}AbXO9s?BHDykVvM-rtO0dhK_K3Y(mM{NSTKU?7$HM)(rMgV=|3t?1})F7Q~$qu|9~mskRW zzur2BykB?vaO*J~hK4M|nzI5a#g&(O=m{`_=cA#D8ssZSoOb(^Y*hS*K{N$MPYAn^ zldQ0);{}0tOni#}c;GkvIFkrNQbhA0I&`eo3yBPSg|H!jY3CG+KT&15?y$4Mzh&H0 zip|D5S-m4y&-{@f;nX0_sL07i#qADw7xe%|6#to) zc-c3#C<@HW_VDq_nd`3*c0_2Vzy6_Z-4~Y!9lGf?NxM90e%WV~z-I}JlB&a2 zK`E?)rD()CUd3e#Iqj(T;>u2V}|QE9c280YjI?5Ex0&j zt%pn+tJOKVUx6s&fi?v)w;A#C`x2+8+N$R_{(IMV-UD)Ev(6QKr* zePVi(lKn71g-(%s7?86u!89MBqPd|=uY+b1PubMLnFCbpKL6zkxG$ae$a71xPBoA5 zWt+pZSsD^wNU7orP@lS>GTN!QanX5~1V>|((U6Be6xs)=oQDCbF9K?BC94ZSc6|W^ zk}vw}=J2iUyBAXgd%s#neH1TS)`-f{xX!6Kyv=lw&eOZiP=qIIc;AQFZO3&GH4dxy ztf|~~rPJmY<<4nCMW)6MJ zyL&QRaCd6LuEC@A1LDPkcsB-phpCU~-T`wji{Iz`efRP^Jv`LZA4-aZs+v8F4j1$g zNEmId8twpG3GvSUAk)>~;&hldt^ZjQzo%=wlRq4n3^jG7I0vB3sL*On(4~W0?!EDR zQzV3I)J0c<^dan@CLz5iI=jZZA}mdT1{ztt}D zy1K^SnhO`!BsuxV2VSPBU-yw9!rW*dQfmnvp(MOl{8fJ;g(+~_MsfT@swp0N2D_Kl zapZ)BIa1@3&VuTG5H1s|m}E%^YKV3%f~Pm$iH_$2kxyxY{QO}R8v8mLM=ug>rSWm5 zL~Yqo^5p?CL!QVYPq-~l_kGBpW4UrJEx}tq zr6vkguFW(C>`6}+Yukq<@zmK%Jjj9ui1{05PGMqDTFLv>R4!TPW9*edH1`>K+SJ~#}JQo9b;*__)Jv=oN_NfH#Y|(zX z!LCm(AM2j95K-^uu*;oG7Gi2@i&uYvS z_OX;Z-fL{oK#pr2&UIkvG?%kpXOfLHUp5%Td$)Kg+`-uuD_?AOeyY9Ex5{+ovGYp< zbq*)h9L^9FZ*nEdr7^wtD0Gn4$XD(Kjfpo>tKhl3^LbQ)90B6RT|R&&@n72cLlt$u zM9OtCFkWSHmncM9$}96Yf-$XC^be}fmtQ9dTS zWg2qvsCrx+iJ-f2bvJ_hlv^6Z*i=M)UE@@F&PN%jbhKsjt1E4{N!`12`%tRDJ6TJ* z(C>c0RsOxYMP`x*G7d&cQ|ix^urfBV7M3B zcF=z&EA~$P96Ni~3`aSe#@#j{M_6<>Vx_e`9(zatRZXVk(i+P>fD=q6S34>i~9aDvsAmuU7 z_rc@x%RKvJj7z)2qI@UR+K!{(OE)VApSjq@sb>{4mTWMwxa8J@{xCMUsI{Yy(V6Ac zv9lleDi;g=iel8?1~fcXe;0C30mkQ!EP%bg+IMg0IXT#SfZuj;O4;5)ZQ6Jw!5x%) z+Io)PoX;aOeuhn^&99#&Z|@xD*-$QOh(n-2!1}VxV7G;`$P^YgZtTAo4(F@}UdlD` zkp`}G`lI5x=i64929{Ik+D9}B8O4#bB`R4` zF}-)@liY%7=7k!E^BVYs4zJhwZZ*pmx(;wT{An)N!7KL+AB!oe7^OM|1OFxxhEx)d zXThk7pK7i#j@U_cF-y>KX{k}G;^D$K_7_R@jk?@N*_f&sczwo@`9#Vm(|7kUSAlWO z5TtBs1PLP&iW11}9jBsFGYrq0pK}d8lO5K?EGkgaE&#JnnE>+^37YpPeu117RJC_m zy|3uite;Bo;eD+XaO1`6d{?uC=2Y^Kaj4vf-Rvhl8|QymM!fAN@9#@+P>j4Zd?4rj z$}`O`)!W(6rPhRiCeW?TX2jo zh+{K)fL}_Axx!g&;i9{*@+}23i;xv0V}{7zgvPO55leydmv@aESPNWKCYiZaoq1Gd ztcJED-9TRjbM_6(^^kn1j&EANoKCsQ<}ivcFiS zE*3f(9o)bzG$qc*OIr_3StdJ=UJ+RC0HCzpDQbH^%-V@tfCZe+u5UQ{kt!A8O&agj zjyvPNR3{+8O>!Dt6&O)Us6HE#x?KKbwv?epGdyp4hN_g2x>IMkJV#aBc>@pbu;60d zLKS_qObuam_8<6z^aDx$9pk1Qc=>&35iv}3OSQkQjrRB zkHA+?d#pnxs{s?oOw7w%RDRfbHc#~JEWZ6NnB40Ly8TK@reNLaOV)k(F~MOc)Nipz z)S<|(r!E6#V%05FJe$Y1Z_dGmvAyyZiAG)bzx!fru1ek|6Jc*n7n+!(k_m-*tf;o= z_yqhr15I0TSh}Lg8LmUXM~H=D&a@^`klY&2lI;O_2WmNZje2%UtGOGcp=1QociHdE zkPCVXq)~xY5mRLAb53*4&$Z`UAO6aX_QnK-K@)^#U~zRX^vKM$hBohbROu^To^%EY zLJ5Q=8>dn-%4957U$ZlNQ9gC7o5)`QrC#@y=%Skm!%ap6VmQ{aZ`^uwP8>+Tq9g}a z*c{69-R;5iJmDSiR}WXrO8R6ZncucBd~WA8pQ{<=LcQydO1oH*b5B1%NM=;QxjYr` zwdNu9Z8(qEmlnKER-VuGm}=imt<1}V=b8>xxGSd!o+eebPMN4Xz7n1~#40yXO*AV= zt?dBhom9E&qBR^YJ^0?X)-RLK!sJ!@OC~gbP64mYJd+Z2=y7v`42i}v96i`iB%Nk9 zc;U-#5dp~2`{nRO(=c;QB}#VLxM~PcqnpyoPGRSXJEv<|-3C*@0yu`+D~vBio#1+r z)~{OJs|fY1u!3loy_Qold@S&ywXsxbicPH-j1d^nAP%Tb7+{tRUWW*COP6yiiba`& zfO_*6_$A}Hkr%nbEL?-9Crn>RvNx=}eBs~Mpk*M6w<{?gyb%ZarjX#vGY}XvAYav= zr!>#Y+o$SkB46BpMQQBYX^>`*fxLf8`(VGyLB1%%djd_7J@%GI%_`#!qJq|1Nt*s_a=Bz>E=X)V#rL>e)-}tNfW>I0NUa*XJ?51^ zUim7;2D-^w8N4b_Sbc?zWkd1y>P=)x6r%I!l#TJ`fT$$8$qTvD7_s~k}8Q4i# z%q*eGEPb8k*2h~cY4MZmRDq<${VLnj#{6{B>FqQ_D9F;2{Q=4O*>%lrlMnJ6wTi9B0nV5t$+& z&|)I2jr?q=*U{vY>&ya&EAd=}A$;%?o5#DWXdJ5*_8b;qUFda{F3=ekw5ZwOT>!Y3 zs<;<=&EH~A?N@O{SlKI)IFxV~w4q2f5FZhA=HJ&tW@no(zJc|N#;$$*qw9PJl8eQI zSHDwD%}8uw(UjZfX6N#}aHleopl43j zZ<7YY$x!mfQWL56f**4RqbdKwdqK54TGIF2L<@f$3U@Q+u+(1@SuX zXe`y`ZPeY4!1WiiOByZeU-B3J6p*hHSfVFaWl~?I7mzj|SLpC1Zwy)t=7D)Z)O`&# zmpm)PxAJ|doL-=J&7^t}v$%Q=EQ?%@O?~5}T+_T|qiy-^NlLr#ku&PBR>g+)>+(=@Ta6=kF{25Mqv@Cz`He41F=I82 zV-GRo?TzElFcZU#6O)*i^NlY*U?w*jC% z)thGZ6y{8t=4=#RJ2$=dRG7coG=E*;&8?<4cNG>AnikR(7F*)za)CAVgMm&ZnKcdO zqno$Wf?_W*HYq9%g`**l-RmDsh7{=qEix2nTJjm^>Wfwb2+lSx?fZ0pFNFOmOU=aSZ}PxIc{^PE%x$7fUGNE z?7=o^79e}@!|&oj?9oIfLN8O573;C$&Tsz}Ff-i0Uz$h2VhNDL8^{p)&8D!@!DMMy zu#CWsMn(>gDcoC>|sz zU?8qLWNk*`izW#QfyH~O41IB8XajLnKPo~9HwTtsf6>%~mDx5}{jLa4^lg}-DKk94 zGSNz#JfyRDGE)#3Jqd*q$udem%r~)$sbCqi8%e`NOeR=1S}E0?X1EDJFW>Vz-G|xi zKT`irt1tfN#7e0?+hOzF;=llnH&70)<6QpN3KHuE62~b0>zF^afj@YcPp02;SP;Yy z783xA)B2VT%%!OYgiA&o5n!2#a-1(+`0N)uker&Zn0lsxR0LUej;fkT{+Zw3X}$Tu z9ZEJCG7FxSxI~r_s*Bf(6S_w8^83!2IH(b9fTo?rZO$|)hy5jAd+!|R_&8q1Cy=X^ zOWY;sefzg16M#n)Zf}e}6AzIg_EQ^~#CQw@kzoF{LB4`re&h~AARH$yK<@Pb30kH$ z5Wq5yz!_sh#pk=im-o(`?&DY>27__P;8qTzXO=YSuERLx%V#bVR#tzq^zsta(LiBm zl%uzo2~T8mRpFQeF0k5sI;Qa~U^$>|SuZP{j3JKCi*kl4QXpXElEV^b&9; zo-8dX!R4ds{pcmUF&Wc=Wf}!XzUXH|2VAf=M8}cQR_%Ti19T=To^MbQ->+sAr-TQq zdl@Mc$24P7JaJG{n8NzP!9+?qF*|b?CJzjyVEZ-F>|$w$XeMhEi{*Syer?) z{!0$xcFIU9HjWz@kiqv$hGIPwFoI1M8;8C_+WOamEz@@;+))Z+)!Ui);`j?6Y$L9+tE z-)9is|7)xt{r|D|o?lI^(Z6pxshAK-5_ z1q4kXAXVw2qB{viKvYodr~$EU(G6BaWMB6AjeG8SasPok#?6>(<;hqt)_RdK*PQd2 z^ZTi_(q;8JXt{Lf%M=;}Ch4**Cx$Xy!Fmfa!naq`Xs}Zi5BC#fVtvba${VxPa$$*O z08dVjoVbe~GMd_T*qz^F1WW04boAJl^LpFYQMz8R40BRuC6Xu{71Z9ms$!ZQVtPe? zSf=oyXx%=0sQiOKqhbl`$~U3gkipkKKFC{MzoV>LC+$g|IC@^9(ELS+&G>(L30&cuLdgH>^qDY8h=F&c8;MQ1K zxN`Qp40zZZnFih!4F_*;JA@zP!D3J0rX(n%YiAFKIb$6l;j*MBHeWx<@(4@>;8$A6 za7tFcZYikgPq1E|VAa;aG?umDV=;p~Gn^lK5^(YXqj5X zhB}xgu|~I|%-#u%WvLo<%fIpey!KHM84h?MK0JgCEtNPC&XWHP`EC?;k z0Wr19=R6cS2{JbpeDHiOop6wM7!KPyZ<5`xT zoaMmy^2Pzlh?Wnxx!~ZZGhFrS*>2`uBS=-?$oniAm1y-5q_l1}Z{qdLI@dqzox4kg zo==lS_L!TCQ6Bb5aPYz&O2w4XN4F4dWj(a&VVH_-WvowwbD3_y)yg=(3*I89Q?{q# z1KNVRVmu9?xgCLRrO&6#{J9okeF@LIPX+EbNn&JK0Z+Xj>i4=qP|Z&+#9#2NvG`Vp z^_io4;jCo=V}*EV1#b1w-?v&SF6Qa1%F?89Gn09BCdI|+GNspEr;VU5hFd~#+EA7G z`I*~dR&blc!CrPeVU{}LwnuJl_yDCv@#`%Q03SG@-xk=Hm&bizCKg&;habsg=}GoHViSA2*g@gwJ%t3sIWtA+9#F}=gY zhJv|lA^}$zOZ0Tg7iK9MaT4ey=nvD|3Nzx2w3SygU|E~YSDLzS`8H6f+B=&aR4cS^ zb->lk=Z0$%rY4=vCiL5sH|#PJy|I)buX;`jY=d)77puUWa5R;vvAe>A3oVDDh_-a*V56Shl%FCu2Qua z+jEKw&@6y$$~8JXwrMA)v{~71dZFAW*hrA;Ml*0ZfpD9P2Bj5Zon8v<>UrL)*1(** zN;Pv1YK8O<+3Fg|c#3nBouNy&y3((l3a&V-1A^kv-&ZU6Ts6+^${YjKlEPyfPbDaO zimDS0&+R!?YJX4qEG}tRryvG!Oz~7nq417vg&j>KRnBA<@+ZzK#2J`$^jXtU&z9~ zmx+U|f9mRBtj8C8_EAoTe;!}gzcl;#Rz)jpI&n9RsTRDerE!OA9ZPoF(|lZ4dx&Ay zROMr#f4_n|>M&@UVYBRTHqZ9m_@%$1D_>9JS0{3a5!&wiD-qe#VhgWmpEqfDChs!| z8Bzag)4eb1)1Yi^!=~y;7eqU$0%DLjO+E1Q5Gf`le~${Ppjmz@AmxY?F+5b{m?fZ+ z3op(7bNsLLaGdQ_f$t29_<%QR8p=l^Yvl*qN^|CWDU9Hid7k4+u8s-wj}nFiFL?!t zkCgUNg&fPv9GIz{8PUfB0DXPmLGR89pg%h|(vdzIcf1SD`Km*27-RgTZ7r@B$+ox8 zyC|$G^=@oMVDs7Q5ULWe!d?udspdl!%etZV(YV48qhVF5ESsfWkBtw`CoKeKv122_ z`ewPhy%Q(&Y`9a)fVcJEu8N zCNQ`40WQ+;RkN;9ws;B^=W4bk=_`aTT5{22EEk8S@5T2GIOv#^A$F%TC>B+YMcNhD z_69FN*5@4-ttm)ODsMNmWkfeNN(sF*ud+LC#I#q6MZsSgUZ#w8Bj+)}W1DOr%;Y>R zutEn*1Z9_2a^}5wg#i+lYHLrf5qr5HJavh5EE(Q~OL-19{mubVaRl|xWKw-~FU`rXqEJ;js#^0H#!g^ZS8;H< z!`<3OjscY>8j(#QcG(oPg1Qk_(6q4!@4BjAK+O43>LCIUe{UEge+NR+A&-Y!`diG5CiJPi>K7N=2-r~ z)d%2>n9a*i(0+2Ruidb2Jg~6eXw3Ey#dm-Sl}H~7(H<7)7XE}0*7UAFJjCf8OwR>p zs_$`H>p4$%pU=G~!Xzmw)*@d~vh8X`!YieEUT7d+J$z2_%)p4{#h&#d4${l|^T1>| zX#VPn%1~Z?7O`AlS*{;?cZy-YBmUE2srs(vk~4#Wr$7+fx#7<#G|+jWrmxfV=Es4K z$cCltr04*wa;8Apz2k8PP=f>9R3(9ak4Lt~$We`CgzFVaoz+*+m>Up!xaN|;td@&O ztQxB98QUkOUr^k==hD$Aq#jGWea0 z2$veRZd8J^V;j_JIORsoB5bzHkdF;3E0RH;f+9|st!KQoF+Ka__4D{$v!qk-%ATvW z=iE?5U8vn_RHFM1rdh@`ibGo-b>L#>4`{zDb@Z?u8dl-1;9T%Ohc2{>epEk~?S zAE*{c4MLZZp-J%D4*(QBJ7J{~%>t}CF54L7$ulCs4OE$I>R1)rGE)Vmq^Cvc#FmkJ zh4^YV$t|V}5nc59?(IWAZ~gV`bKVRY)Xa12>-e}HBTfR)Z%#rU(UK7E?YYYTKFPNf zio!&LFc=m-c`Zw`Bynthx2IVVy~-Bt&%XM?Z<(>}tN$`;8UU*GNcSz`=I>5gK;iV_ zUp7T%8MSgzAuBSsL2UCzvn4k4G00~cpiCa4;)iL;I5%w7sH}Fm_(H2PNwae7pf;?a zb)eC=tH60$_*mfo!_|#kzZ_EYAP6dFAFneGT#&E^e$+9SxC$j5s0=>1QoZ#_7 zTc>pLUpciXfKAh}&6CdA&x3Us+o@ZFcQ|`t4~<>cP&mEm5V|T+Y4JiftnID4>{!q5 z%36jwfv{gKy4$czZ9ylu)b+lkG;iI)VL>MkegxOMG;5v#qiSE#2DvPDSmc}T1D5QDFt;e=eRhqMBft(dBV+?Gu6kJ)T3 zj!-?CiMQestT}C!z(5uYTrQ2tl@fwWiEhI20`lD$pi1nV`tdgMP6m-a1qzjrVz{b# zo)(cD^~`mkJWmSh_Y`mOUVIZxuGsCx#;bK7KSjx9m9goNDq%rLtNG+{ga{ zoJUbvP*8PoC2+W#!$g+ZECqtE>N|u=%-ljY6%5F-ixj{0=g{H-{u9V+FWTT1WV{Iz zZzsi@Gx6_EsF?zl4Ma*Y@3(u1$l>x_Yl`kaVuZjI-)WEM%~>l`>9$6E_!XC5Z6vy1T7G>gNSMfw!ogoZ>qYYW8ciofZZQL}R<) zGN8`(lghRtP|6+6V_&wJIv{tF$;W`uOgT73q>@3ySxRCKM1dkX#Ly_%rxU6!LX8ff zN+i>|1^`~r1D7#CximmHBV4s1x&ScrrP3{ooW2aJQ>MC zq{;!Sm@r#Y86+9srhr4VV_x?MfF&o)Wk6UFpTN&xW*Qb`u$8c#Ew>T?<2{6G zp>wKFk#Ji%AyTB`&m{N)zz0MnnXcZl5%n7~b!F;mponV9+I)0r)C%we@Jf{p*tmrr zPXZP*!L2apo3S+{OVdz_SGowUy+Gyhl1-!}x>JD3LCRGJ{7zB1twibFe1Bx#2M?LW z??vs493422Hbus*Hjt;*0k}{+jw>`R=p;vPyekj-y9U_D0#!08(jqeS>4iCJ{pMpL zs9azhE&a?RYXr^(*8+_uy5It?%CPj0RJq|~4=9jAj4q+=Vwg{Afh^`!1x=F)8x|25#E^)nR%_8^$ z|6<9Ak$ghRkU{}hrK$~nNM++jREI2ZG*^XsmlO#E_0I^5?h*o-5&0nEDo7)`P|HfL zevtw?E>%iJ`I(5=%JoMyUcv16N|m3ojOG@F+W6H3f;m^QBSzCl<}>0&>E-Akr3_`N z-@0iZ++4-VzFv>fYgHw}^F;o2-{ZPuG2%}0Xoay_G&cf(kVo1@aaCib`{J0?gHq}) zxz&I!XqQxNL!|5gz&1LKQlvtBY^Bi&^z58F@WD!5>_#gRs#?sE#GJgxz7!5XEyLGI zHJ4t*5az*j2ET2+4y?3zPp4Apv8hJ&Ql$YUD={y^Mn;-|C_5ZZwWKH)2&GL?mcma# z%P88@K$URbZkkYK;gIe*u8NF5GssnG|8C8Zg9GnEWF_9ETon^eB0bRE5Te0xeixIC zCqF!@4W^|;)7cWeJ?;uDky5%o?pGuyMH`fvm24}5T4Ah4WB*OPvpy{5Tu{oMN6uT? zP%%nC^Z?RIdm-JYo)oPV|NFx2!{ zvD)z1lI@%K^l>E0 zF~fv*E-{6VAN}5@3xdt)loKNRmO2sg`t7z9RUwm<3v3;1Ggb16Sk0fE@KF$m@WY3V zcD*9`zuI1c$c|3irG7I9#aj7lNsX0Tt=*#1Oj4jCq{)(QulA9hu{Q(F3Q&*sDdxQRU2v+DBzpEP!*cKiy-se+c; zqnxlYgDU~EKSPXUAmvf*+^QKd04|omOI#IJqWfI9c*QFkSyCmeJ*7mSklhXEFjS5B z+YH^aEV*LsX_LW1$HZ`Ir+hTcJD^6=25AZT}q*QWMiYVJ+IfOvIq47MCLjjEn z;&cJ3>6Ay-^$;(URhUWXI(H6~`6|;!R=N+YVl}6pD)Ft^o4Qd?)wQ9vUWUiZb3-q~ zjmUI~KD0@#^`I#=lZPSpIl5g*WF+{QbKFW~FejGZOH=KOfLEVRq5ymUtqCfh4NAzFJ6U<j-N6uW(Vyvs7kWFux1 zslle!tF0+@S}aoQE08${bPlN2{tBWyK+xrMUx`!O?5H4{BOM2-ly1ELwB!E8G-{DI zwtqqOK-JERU@=9NBUO)OAa97&0!2igDYaFk*8XtU0FV^T#S8eC8%1e2XJXN>b2NLx z(*|%Ye^Be7y{>lJ2>Omj^PDK4ij;$h$!l!VM%emU(`2GHs{u?453S>D+OTb&<-a)ppsH zmCZKEdoQX9@`a#RiJI5n>P9&+QeoK_J!r3HLZD#y10}2LrY>BN$IwjBkWvEwj93UN z(RW&n#7hv+rlXI7vha~WnG)>24HY^VsbX#_hus6k&KZarR5F1MeiG$3%g65>BwBxe z@?*_VSz)TD8?qCSDtr|iLsbs!Cirl2lJ}ZxSMD?brWbskab(u(HIz4-(AlqHN-ciX2WL(mE0gzbFRX1QHDpNK3xuqjI z8u2&OCmX=AFWwYiyq6`5dNe?;5vu1&2m65Fi&9emoR0@t9WqP0I7jLPYQS5c8zO8&Ybq5PE}4EZ`H#a$FiiBmVfCeJ|7{mww)uBNj*rH5-pw z58o;LN&!Ssh3frMb;&rjmqNG~f?Nq(8d)cGQ^Y$M#B?B`iVq?K78PEBZ>+2Lib36T zq<*HqiG-L-Ayi30SLZs70jnL-b|aE? zA^-jDUo`mza*BZgux=9#9g(E9rF=g`mZO;7+xVU^Bv8}~9n3Rp7%kS=p0Nfu7mt-` zyVuy|n>S9JG77tzi8#2>9$-xJYPX(-+t;cdd1{n@pF35#(?->@+3!SUgRzfEJde~5T84<9@ z?=sZv?5SPH5iwPf8Q;UR&byX*9PfB{;k;3s#P@bpNVme1s_5LkF)n2zdNbz^ts`QE zg5x%Cg?mXz+UXqXMC^J)$xdWTZD`!jSM|6T)nQ`%&ydG|QbIDGb8U}9TAP~A6~woG zJ7w@P_?jyh($-e4(-tc&F1S#ZqymIQjbG7*o{7$%2|3uhxiF!7qCnMNL6djptxMy> z)(0r{1U7h=+K7aC`Ds(q$G*PMB!Tl)QsZeSr%L%E=02{m%-$pkaMo3=@>Yc^r*;m? zbWBbjC5B0~b8f6DiB%<_^Eyx{I&@(lQiXjjVMKMeT{K47L(+wSCQFtfv-=l7#)<2` zN}TrxvOy3N=Oq?%%K%ymvC7VXz!>RdXUl+A)Eqs^Ryjo^lujU-!^6dUg zr!G_Tgg)2+<5Z=>T(#=@aR|ZmPWr1qorJp$2UgfaMwi+@PZ&pFVz;ec-J#-xOnPZOVw>tX3+2_N zustq13X@ppsY7_RaAb)T^TTCoc>Zg>1@F>r@A&q*QDQbZGEWs<#~-7_iIc}DyZoKY zm5*HD!zcy4iK_JB#N%;aK=$!+gjcqf*2^gft@F(Q+$~8!HD}TTDd@cnA$c|lX3CbX z7bPSQgWKSBu6O#%axwO?H^+GPvM!dVb^}=TiMwO}p|)Gi&_G3?2jb9)KhBYhGn8?G zxN>avonU)>HxJlo5>z(*9FkKqw+n~tQEPce{sTLVyr>&+nM# z7A{uS{DLYK2x{NK-S$(k0l{O={%{(cpu~jlYRN9iPkQNl=Zv#{Fa?+YE(#|}g0q&y zahvRl6j|K-BzBRYc2TUi`*U%iM+4ka0)Wk?6$L~~v^J-Yn0heyN#THvCTcz^oO3Je zst{^c%0^k2Awo&wxNDCm6bt~02RtNE=zJ#3qZ*`@O4h*Af|&739_#36#!-A66GoL_ z;2hzGgfLLg$R`WM(*hC6djpGj7L6ebXP*lJTQ`AkBrXnvNdw_93&7M-Rc#mnuCN{R zsB{y+AMBRSWNu|w70hzLU1A1;&Fc%2fS?4d0@PaWwd^7VHx2VPg>yD)n+$#Eh6brb z-~F(v2=cU@50l{((KM0K&BalOTj}Tpl{v^$vDEXRf%ni13;%*MrUEa!NhL^8`Rpua zzr^aal?aJ~Ynf15{xSwoL}Y5z8VoeppTMWAg45b$j{u`3~Vj)nigu znqAk#b>xvT2QOCy+YF_@wobh^E0h|PPr6Ab1cdtoWYhNgivoa_a`>n2GtSk0qKQLJ zgvZ0Q?$@Q9%6ZkBNiaHX-)*WtLro-1&{aNI=ta8(R~ySQW-!AF#XRNi700cW%#Gr4 z166k{Tc;|$h)cedq)ME3KxgLrD>o1aUEo&3*0{Y%^=hFRKr@qpE!<`j3%Y#3P%wwy z^R-^NO-Ru%rW9@KKoBM+P}7NPO}l9Jq~R(@1DD%|A?^8Uw}W9Ofg< z0)Z(#8%alfcvBB)%TqGk14P9_MV*)W!q}_6qsoGMC3Pd2nKcD-nVt*lFXEemuAhpG zuE#fVn(|OGlvuqjoS#G>sDX$_~h;;~idfIl>bjfK0mq#Y8@^;LdzhTR&4e z>Ny$-9?+ESS1DUjn-t_aOm&#;Ej$mzM6Pv2&r*51|2WbO{SC`Af6e|7qh2f&2at!< zn&nP&f3R3*)Wn3=uW)QEJ8R`WXMO3!nlqjElQby7pIKoz3K-zYB~G0XaRCp+cd>@1 z^qp~`eU`W_fY^q#L{Jb`muC?hh*jqx`q^={61+*0#bq99APJ>Yb%4AVOUe~k15wQk z2gfC#_b9=YjorpUHIvyrQ%Fs^vKbcDNoK+L=qC(Z_}B0@4$-t3$7=$H`hY~dFqa;L z#yhMNAoig)bbAlVG#lY<@8k%;oFV%=VUcIBdx=6s@HX6fTU3ae6!IYpKJ2WHITHn? zB=7BXb)WlVC(NqPUPiI z*X%>;*dB^p5DV|)?gOp{AT?cf=&})LCtmFm_pQSbSeNaeYKJ?L!c&^!!YbVIf+4yG zgY0vVosuJIe!H7_mdExGpZBQnzSHqtnCmVf&O`j;!H}R>ED=xy<%gs=s$k`aCqJSl zD|2cj>HEeI=VNf59C)04GI|+WzzKu`*SFohtYpQ3Cx0om2n^hI8m@{6s+H%fE~9H1 z{F1zK{c-Cjr?%)%dAF4!XL!eT9B>Q1!lBi^2iNezel#7~0>spi(Op8sRXF+- z1F5?N+NdWFaS$ncusy+rhr5&qrx3nRutUv^!EE0e2H%(CRV{abNt65KsL;#{Xcze*ete&KFSQ+RjajzpC-z~+zfoAiwlpS60cXNbVqo|K6wURWnr~uT0cqj&wB#8Ji?DZ+cohh|Y z4m_U&5254OWl-4q33^}>yg+!?#z!d>TYG|D8&d`e!TzzW!G&m3i!NjIH>oz-a}4t9 zp0pS!CZpSV$Td;)r75K6o`TI-)L0X~E?CW2a_-}kbEch^;JtQfFz3&y;3>HAHULJ% zMuh4^4O4kz$%VZSRGtR}m6ZY8w2~CLUe%|Joj9N?Q;7R;LqxA1T8ggiMC$RLWx|0xdgQMXz zRUQd}5V5G6Y$22j^c>URJp}FS0@le9ZVkY;EEF0TyBTb_{XWWl83+r;VcC11sMV}H z33JrCFsFG)yJhGJfJ-nN7tVvixZt>hFxS+b@!0dGbW{%jxch;QqZ}G%4^Iolrn=z{ zXTZ~&|4@35S0!7dq~hc~jHmf6)g=9AOS)=8{DaahSFP1Y$mhB_D4HDDSBgw5KchLV zZ*#K*FGbz@7J^?8p6#WIwx9Q#a|kU+KRk6H(HEFpUU=pizCfL@}; z25n__9zkF_J6kU^!XGd~LPH>rghZzv#A$gbv<&28kG#T0ZaHLeehTCLxNr>zl*J?d zGJrl}gmef|PH`3@MpJnoV$BSg){hvF|Qt!)Jom%sqr=(tsQ8a#0X`%;1s z(Y1DzZ%fhIh7W;^w!m{Fed;0D>k`DC9u0GP-C1$V;lj(BzQBFvS|r{U3+>HMCFK&1 zyQEXMo85MvWv4C$ZV9XsD`V_J(0!e$-mflH>V&32Q?>{-OVhZ0OLQU!d948qaLp{?tI5Yu&Dw~JPon2yN_!L>C|Rk@&{PGlDk*~~+$ zvT-_{=rgahXOe=I<+`5pL9_l4T`Z;(ySs~nCXk`V64VoDv*Qv*|1wg_V|xxE)aW=I zAXeefewi{voriSVioDISZ8-~)e+hnF0hB*P$cYeT_FhCZa+J+$>;%5&A35Cz1Q}i4 zh?|m}%VOO7G~cV{khbl|Z+FC|ok1$?QQx*N3!X*CY19TDsKBSaxj~pldz=6taUZf= z({Y1uIhzV1N`SpHT2x2ePKNImd3b0FNL>z0$z~C7;4O?ZJ4sHCWJSpy&#)+vOF}h_ z57LwagTELEz5_dxgV(7(pp(CFw)EjA!D`z$pwy7zX_ksV4p@UlhLe;6h0xHXtpp}g z%xE#?Lc@eN)yhOobTAh9O^y{C>2^n6))yZ`cMUf#Cv9GqZtJpb@TakH=g%pP ze-7F4?laM;6IH#0?lQO3SO(S#tq%(RsBbr?^ESNQ_$^5j!Fs%8^49gqWA`XJcl;m( zGV%kit@N|4ZW&NmiZkhVNN(LjY>P`I;fbhj-9c$&65p?=FXM);SamRFN^|3yzp(TY=rcLm>&?POGa zLHWAI`c(M+sZE&aWvR~HE@da-#AAf!DUIp38Zqi0r?(u__uVsu-f{1P#>fcxo_@!@ zH6x0)Ci6@YX|(&^R?qtm!29|w_7*F6lO5XQ9`tMcp}i^h-;CY2+&}aD0*yJXr?EWV zFs<&$QuEwjfbRn8#Ez;bqx;z?of@1)C#s)=8sMOqzi~Qb)R6j!-Sa_JLv)n7=CwtA zVi%hFZkK(XiXI(xF$x>bfah}HIXu|WO#94_kFq(=hF!|mQ_y$@eD~6L_I`MFCv?US z+{G^7Q&5kO&Yb;yTVn}zU4ptXg;wOEMbA;PrJMI^l^&N4UI3u_{zi{I+poL5T5ml9 zvONm%%R}GJ2h4Lq3})fzI{U5`r<1Br>m8$=P>PBfIEZ|PVVP@ys&x0X|EKrvInmP`vkcygH692U7DG8}i1 z#0CE7x0$*xh~8mLoC9m}wqPAdi4+&LVw@}z^ccG{r0ZpeZrDs5H2EMbBncWW3E;oO z+OpvV8$;5i(4?$>8W)^w5C71U6ebODy|EC`hnE0O$D`X_qK>Wq#=I#qf<9bA-s6Dk zl)!qWZpi1;_l?H2lfkQ1i1ovsaSQE5ArNC8h#{P&vrmUDk8Dc)pTw1mSGD@iP%vi&Bt-|LzWKWB&0;zCG8j40L=RD_Bnr^}W;5 zp+jR6m=Ev+y}0cyvnqUOLeEV{c2tZGbTS_ffA!)7ui1bLO+#+uaB!1H;IbE`!IB6Q z_AzVlscYm1+>(z^U4ip@Q1vC0gl!__A=9dHx@@#evTrL7bd!vhcA}?iajI<07q5RF zFfb32FteG2ot(-YkFet$#9a;+-zF4}3fQ@d19q=imUAM44gpZgigZcbKC!_x6>gts;QqO&CywuX+ zU*FP;!~r05g?|WqpwhZwmp%{pgfy;Um;((uJ%yNVp4u$m-MAg;(!)d>SbWz-BBBxH7j-sLxovc`yBae3FN6>q zZ70Qe?EU*k(Uwa*WKiI)E1kLn9GgpQv^5gz7%C}v@OOZT|E1WDi2!ll$;eBAx1U1y zJuuwuQs8o>YUy-GKnLAgJLH~N;#F;wOzm^^qj@!GoSsT;@zeLMw$6DLoK>mod3I-x zQeS=rv|Pjbf%b!OoePnU@m2G^y?CFEmQWWn{nue0nmT;zh0yFmio-6KdRItOG|6GF z%jq2Cr4ZMM(v(-~lW@JZ zT;uU#zh=11Ttx6n;ocQ5R#6b}i=iuw(*Zk6JF^KIzL5lf-kk6TGCgDushpFZbSi)+ z<-w8$li?u$SP`#HxhkYl?L<-V#$33;6cZU2cqF%5&2Gg3?-kP}haKphGuVNONpey5 z%3i08=Xr04I|$SZl5#7eG*W<-o_X($p;3Vat$FI4&)N+Aev2mfx{FdSe$U_Kg0>#4 z&#R8>1#}t3Vt#ee>%LkgH%7S?ccuovF%mT zX72m)prg;_m+2!s(NJ`@2lEC ztQ4tv-Pzs(Lv`E0YGSRcZ&UELbJ~N{8`IfNR|}RNo+yuPMhX<4?%$^B^?9qSnrCm< zt$J(VcA!cyhn5cxiE%9whp@S$FU#ZebWUU3QlzK1rUmDmS~3Z4yftALr^u~XkL?7g zM+>WS@nLSD96V-Xf`{Lw(amd2InuH)No8~m+nxwK@KZastE&fYs_5!~(XdK!nJ#}! zHL|c*i})}lhQ4k!@-dp0o9rFcN!xev+V|CcokOZe7rmogVyglqHZaxbz?Poyo8l>o zn$m@z2hCBHt}tSB`SP>G7~86LSh05%1Mm0l9>2P>c4C;ub&c%rYWeWD&eICF4KJ`H>M|e|m1w#oG~8g+_SB6$mZS)vCGz?-E))O0A#HR$s5U$}iBa^1z<2 zh$u2~J>xa?hik!BWnzZ&&$|o==BK6SaczVkTJEF-EYC6g2_}PnRbKK5j?{jnjAEk=1Qc>1chM0kvDH|{yP`&<(;*sjAudAaplx3@C-F}sw_iynW49nc?KCi zMWG|M1O)Xf8t$a5A%mCxOcQSx$B=q+lDP`9{W5mXA ze{F;l?{znbswfH+QtGkbO4fVHkDicJR>=eH1TN-i@UU*+*8A}M-<8sW0PAHld~=TD zX`d_tAS>|tKi&6}Cu~)8H8P-cL1MTiCQGRNHIB&Jfo>P z+XfxZ49KQV#Mdizyvj~Vb*!(F2RkhO~>>#(y*JZ(fq?w8E z+7RTJi6cJSO!?zVH`?>%W$nq%Y|lZR#kNz|h-bfF_S+Q#!UxqW_52(?)ccH_o==*2 zIzFt^Px(7yYxs7KG|K&J1kI65U5IkZKIc{sj`-W#+rwIJe#*yYJeYa=kf#IH!7Hzv zMtN-+1a@_;pG~yB2UqUQ)=j^L&drA}n< zpRaFd+u>)PL*`;fEoe!p`jwJTsV|RGH9rgD^}*`+cL49XH$|TBSXu{{H>RzUF{mo? z?v180i&h_?@`3^EQ~hs+2_2|1o1uP30)x0=Rmn-$BZl|!udT#cs3m|kR193vx`~Gs zlO*60UzS2UC0(Yze)8a7+l#;50KT7f1;3aYgn2Q(E3WWQl|e{#ozRHh zPUza(E&qmc4yjG?U?v>Uc0Sb0dgsI#==ZHZ2B`@3r9S}Cf@@|qDB9JfF1-J{?D$w) z%q&B3QPNmQ=``$hrWy&5()VV}p7J7PIMjW``p(!Hf;pl%k3lq$PSUlJZtKi8!~BUW z*T<9iHm?xZ7*dTj%UF61VFtY=Q(J$DZ*xm>F$s>GDtY{cVK~S#nq(;r;!PG=@dXyt zHKL2U^!5PEi=3;jT})SIDreh(KclaX<+{UL?lM40Q`yK#rrFn`t$$}XY|n3c2Q$`i zU>P~sFVv7-WIOB}e5Am{Si;p{d#9qanX9>OztAWw>!**y{VD!___@tS`RJA0g=z;s zJ4b(ykue7UvH%d2=@?wgTPSk~=tcLmjocwzzb_oQGce*f?8reoalcA_$aIx#M&ph` z)ij)9zLIu%40$IH#nd{*w>yaqfpO`u{j*L7GGXy6w)@b|?DZo~sZU8M%Fd}C&S~1} zCgC@ytep=RIUlKY&TtqBf6uy-yfwYu`S@_k zBGVl*knM~KJ zBG>9#*P3?MvxBa+ldg5MuICnA&#$=((QYCQw|XPD20J&ghg)N~TT_DDg-o~RBDa=W zx7K#Iwn4Y{NwuQ z>-A~T>z_5RCA9alhWBS9?=N=VUp>6Pg?oQb@cxnMy;9`;v(|gH-TT*|_u8cQ?^*Bl zMel#tyf?b6ftqZPF&n&ty`hl=jbOv}vlWi9;l*r39UIxfMqOv4Z?iGa*@_?8n|`yg z7$2ObkCL$ueus~;r;kd6kLrFOwPQYnVjp6i52<6_NBz2w#%&+X=RTW1`fT~_L&o@0 zG<~VYzFIqcwLN`xB7AlC`|2I@r4{??*ZCTB_!?gKHM;F<{M^^%qp#_2UpmImOw-TY z*l+6&KMPMk%LqTK{eIhy`B@kH+0^;jcKB_-?q_$~Z^v`Loge-F`0dBQ_%k&(W`F(d zclbMa`a4GWJMH&(KIZRI?C)CV@7Ce(e%;^Ww!i0df3J`J-oO3Xm;fKm0AJ$(za0Vo zo&f<70fGAif{q0Q7YBsY1%!44gk28^za0?qJYd(yfZe|XIG8}LW?-aoVAPJlXwSes z5rHxL1NR;aj4cj~s|$?p2;6r)FyZ!w-e%x|kAaD^zXOvnLCKmyDaJtucLb$+2Bk#= z9oips_*hVSanO;vpp1^7qt}BnZwDQF9(4R;(4W79c$i?mX0X6GIBQ36wr6loL~!o@ z;1kD!^NNG>>w*h9f(x$)7u^mnejZ%%G5F-~;8ILTnPy12aY)6EkV?;xQxPGj_lKN0 z7E)ClQe78P(-Cs^dPwcy1Mjc7%#OLmMMPoA!rZI2PJm z9NJPB+S(D?c0IKHc4)`*(2E~KFZ~Yf#DsNehIJc<_3Q}i^$hEa263N&ZVdSEUy-vI-7H*?nL$Zg4+6% z=Nl^;n$KKlJKK8cd`EXfS6_4Am5T#|or8Z}z9AWqjoi37F?8$B*sWU=cc&+&XKp`u zG&3{v_|c<#Po6!Reev{#{JDJo#r(qD!kbrb-o1YJ{>|SX-hEhn|MAm@PfH&^{quF< z<;v`XpYLBSEiEs7{_^?jw;vn8?XSzL-@knOzJdMTV1EDnwYu_ib#?XE2Jn0B*V=!! z_UpgX@BelD{*UARYr}s3FI)eQ2EMv+{vQhX|A7GiKhWO)Er0*d@Ba-B|35DOhYkOK z(Bc1c;r|AR|L^bBwe{~m*T1a%{`CF#`!By=E&YD^>G!k6wFmFk?z~w#Z6$5sM@s+7f!-f+ z-9Mr({n)*Mr0)10+V(xT^+!C(lH4Fvmt$Hu3v zqqVuOt>Joe?NH8_OPCD47*kzin#x(AvCwsr_5mrIp^UUwu8l`n%Wqd)E4T z*7|#YZP>=5uXnA#Z>_(7_1eJKk-;y+-OJbO|LHDWY%2Tb+^J8eOFmTQzO6g{R(#|` zW76Toyf5!X3+t803ZY^OM_-9uOZsa3(RPcE4X$tm{dxeQxN^ zQ=!)PIeHH^jH~}BhW<2>DUWeq2;6YS4zJwoH^AH9{(tcH|5w4=85?QL7BH|?fq1M4 zM`H;->qpn0GBYSW53-3rEr$A#TIwCXb6XAz4i&t=kO86fN3^dU2V3P#Q08VL7wgNY2|@Z#%c9M<^}rSNGv36 zvEVI@EEsP08B(L1&8K~HLmE+ZFMT**-zRA6^w#u_9@od6OpSN^T=3cDw&NDaxIR{I z9o_c>n|ktlyo>(%bmJEtRaJHq9jbCNDeZeqf%sshFm*@}&EyV#XVRs<|6&Kl<1h zt;~J%W?~}kA6Ff5xa_O_4J$k2C;jRcSN|Hy)qoG2eG$4(22Hzr{QcPvWgRWKs`L4e zAs=iH>tLP5?cxD-IOWrs(z&vK4h|n2`?6DdRX_k`-1}A1{&flN8w|ot9ewE#dZM&s zPth(ye%&HrL<;^~!aYIGd92*DH6N4x=d}tK1hDA@D^G@pYUIe>K+O(}Df0TJqFsQxQ13c(jyM8M_?|!(#*#Tx2Cn={@Hs1h%4nYLjyYGh0 zG0~5)X8qoq3J6e|#)A`N#j?E8&s@FZ3i&=8ZFBr!2W@R>UK$00^9EN^sla@P$_Z~C z8=|c}m*)Ur{h2|4XlYQeOqvW=IPj3fq-|gas7i$rjZx$@oH2-E^Gl<(kwk+9L^QTI zZ`cSoXW}xFf)i~Z0BCV}%;LGg?AUB=_ItPN*p%{KjhTD@7hh){4b>n2{~5Cn!;GWF|}A3|Mn2ciziG$_0%De za#d}zxeyyZpg{C(DGWBphke+O3c1`pkQg!BEf}_68H!cmDEWZ zA)6tcnH5;pevP!87V?8~AGV4BQ6{Ynhl%lE!?AA?(NwwN(>J>cHeyMD;j?HX;eeeCWGKN=kUTwPRIb|DPKoMTkktw z$k*YDEvjIcqjJHGMeaLK#d%XHK5hcE_aOQ7pcbdGXDF;BQ&M~-Wzd5kTR~z<5_(e# zpJqQOGnfUPN;+JjEhn2t7*t}ki=yuM!gQ#;eE4Y?u5t`0i=k+_IxX-6uXC z*E2XFU%Y9Z1}bm^EUCHTsV?AvjK&B8!1ahbcqI8 z=(lgXWnO>Y06|D3rE}GP7!A)BX%z?^-oA425cox@WKE@a3QFCdOn zuMlfNJ0Q)XF~>CFHY50`2{CO1M81Ro_ejF62wy~HZ8 z;r%29X){E4T7}?gVdjOSy-W&I4x3juphT`g9Q_lL5w4y{h!Kzr7{%VZU*TU zhqT|41K|l;sm=ij+4+R;hg_0b#BjL=C8NZ9BOacK-+cwEc1hh_2n6oPmcuZ(&vIQ4 z#&k{Q!r;KfQP0n*O78oR`$35>P7$F;HhmHISwEjWtWGL>*duJjnnne1Q%`avT}^|2 z@}`Fi5)LZ+cf$uKM|K&mZG9Veo4P)o#(zE8JD3(boaPPO_qQiXdv}m`x#7Fk+Is030HJ#rWyQG-d% z#@+(1LEU5j((d$P-|Rk_qN7}ZAf+IRRt7Gy5Z1@M8MYvM@jJNn=))9ek{mkGfN{H2 z6nTQ_hpEmvC2xvJF~iwb(m#MJzZ$2Wz`Ih}2A0Y=u638)jaAI^DmSGQ<0(<{>*Luo zMUu0FR}4;g$|mpXDiKaVj}myW56(0wYp)<2{ut#xc;a*rR&7^2|7u?6pxX7bW* zk{>QPa1J#=^wqusJq z38^$+NqitkH$H10xr?YqBT&8YN-84a9ew%=3nU9qgXDT#LPl*6Ac&icTsRD(LG`mn zP35##DhF$7h@Ubro)O;OBUosn0{076C`qsC4sHl)9>6{~m$tHButa4u#WK@=CTA8V zC*yckiKpdPz)$fg+Evub0ZeE||xs<}fmyV1%Qoj4T&WyV$K)lV&MJ z%z0F8R|d@{`P_bS?iPDyGwp8K)ie2+2j<{8{J|miLoxpOa8$BbX2u9A2f>Fa4&w^qe@8Re~Z8}j)at2YooP!$AYTvj7cJ$6xL?`1b9Be9qAb5;D2WETzw_9m?XtSl_02X7;%iQ425x0#nnO z-Q`wEL_p|f<#>3@gff|+tEY?nWR1@EK`y=}DpbM;CSXxbh#Jc6?Lg#o6#CB^gHMZg zRLE7N$kkYpV6k1g+lQ!avOv(_RaDBUeG5@r*W2=NMfq%%A3VmI;0XkKQLLm_nf>y7 zO)I{LzV(ZbpJTfql~$)K7Qchob@V>0DX)v}Tv1T#kb&McxR@K?zso|l9c!&}p81S>qr zrm4j1>?#=j+x3^1kZ;eSALn}QeZQXTgIusM=b@GMimR-xsQ}*vd8nYv}Kaz^8@(h>|GKlzZ%_yD|9$Bfp4AKh*AB!i#brj(z49{<$NAGo%-4{|Z)kPN1 zz(U#)udyoRs|Eqf@R~Bj%2l-KIwGYdYAcAinITg1(t>RcUg9sLkYIVdmU%LC|g^l5F*Po z63gKB8x5h+8u6OvzZ#-J!AAM?e37oZ2!oUPn(&jFs!8U0IdV?_a7S{7?!4c>myYf( ze+92HLR9!TbgV&tMZ%k{kpd&(nb(v9mZ9M~$17A%R2?r*(AE%BY=Ji4U%{%#=QcyN zN-HQi+uuF*=%yZGN8yv|S(?b*U%r4JO&wedD5cwC;L5|w00_ZgOXlEA!nYQ zY}0l-HfdoOHLD5UNkdccmmUT^)=z7V_h|cW^!Uc9`qyLZimsXil9#S#odoc(YZLNb zQ`$^ZvFq=afLQj+qmM5afwO34RcLq^9%iZryNHMFtyUs2@JpWPXuQ+ETG-2e?=ojJ z6^(ddsU1EU1V7ce!mB4`fX)X!s+|~&utvkh?TURu6yy;oOXY2OCwKM%wgZV~HsY+0 z)K|NfzEWpsY6s>=u!iztImftFxdg>p*J>Yck9WB(h(FW*_vPj>ureK>U*Q6;MkD2ai7IoDEkQ{$h@u;@ zMXxy=oohwTMm5P>b!Q1Eb(o;)GO{DQXg<8dHSO_Zn>$su#Tg^F5(`mhJNeX_K+@yj zdt=Bsz~ggiy<&X5nKrk2M{1s@cf@%lbu=MWciUsfF5lHe&2~Kt^r%@KW$$~|OrtX= z%lK3^d!w~9D$q!1{8;%eLh;hk^*v1~q=x(?;<*l*w@ul?UAvl!NXNseV+~i`kP&<& z#mWkLOD6<4l*P+EKN$R{TE~g-2VwMWx6Cg8KK$CkK5zf$r6HVX=913mM zo|=%Lghl4F;0Z+d(07*nUSs%WOCH(FIa=q+}Qu7>4? zp!4l4cD9Q`T+mi+7V92x)4!AEQaXIX&tRBDSUH6!_`k4@{9P}R!%teOw@b{6JGK^| zF}INSm#ZWl=W>cV@}%zENXgV+#@OL6S$NKu{+;i&8EpW(EPjqGi(jA~MGe~FUdyW? z?cD+tJyGY7k?ptr{Z-CeU1tIgGc+&O_`uVh#)VIYR8rwoyh_0GIB5L#Um@$taGPn~ zM_?{(0;x6h1wu$*!ApI-Ha!jND+b!IDj|uJ<$eUZgvyz+N|DR@A9J#%t>I5@sjk&e zqz?brl}SEEJxE8oon@mU;f$+_19i@w$rGt*;|i%{8=ZtN0)P4xmn?B zZGQLN(+8q$oG)W(rIRqLJj6$3!k)J)OWPe9tP)N2_+}2(zZpKM{vQG}L+=j{F-1QG zAoh{JbwSpAd5b3dloT!V|Ds9Eud_q8#QkbNTox-Co2@AEohd?(l`0 zvrJB%cg>{Fnv7Y@1gqAjv}2aDwsIUpby|3N{X=l~I?_`o*5`wC`Uhs=j-B*SJkT_N zQf3(v5`4;#evl~Rz_VG1A|fJ{b)!ITaaPsos5AO${NU}wuu`iTrCVF!Vd$B7v_I!v zWu$W{D+v+aRo;eeZxEZ}@qJ$2a=I&ZlDtA{}jv`HX zuMz^rtfv(SyeH7LnFIl64avhRP7B)!IuFy%R*VQ^+QTZ%zv{%gA*|0Y(LcY>|FH8; z@^PrjPI~CU`w5CD!l*Uzw1~AWn-;e0B28Xkj^i(BFMcyW0Wv;-7L9||@VtS?T92Q` z!D}kL43T>=THD@3zfZ4!t3@cJG`>##!~=pW`Cp)FLtTWN-9~SFUe%u`m9y#gf~R+5 ziLVh_Lj~7fMa0HsW#RWi6fMAHukGE+@)2Zn8u2dI6dhrY9xtxgT|Kn*8g21! z#Z3jB7*5d}AO_zT(SGnP_Z0ia)sC?)b{XRN58gGyN3H*vf(<)&59S!uk^4kWs;GnqVkA|cr-zWaQW!y)J5uWF<7PqOPAGhO&gNUbMq^K~3d z#P@Y431oy;#0Nsq6u}IP5cb%2alkuOpk?_Cq1bv#>gDaJN~dv&glsGC1@d_zf~7S| zy4xm5t*YeeH^7~ND2kg&g0gZ*$&U*JlCf(JcZ*I4+UQN4c>5u@ZnDlsS|S5EIQ-Vx z%=5^!+#fx!GNC z*}5EpRG}J6x}uRpM5Ji`zf0q(v9SYZgwpnIKPHlBW(mTs2AYnfvK76W5!Nxpa5 ziIb6QIgTgl!5A}uY*qFN@)l#fENTrUyJY%#6YY576d0|aAiS=$CTJVhRe8?{B4o`c zR>dMoZz*800^OPOI|=D27$=em$@1#E>IapH>kY%@$=$TNUgo2&8i}6^*WgS4I(tu& zm{8*f9METH0}}Th#?~@LE!|*^H<4^JXiA(i@INbl??FKBh(xIDxsg8@C6mLl)j6rW zzf_(&nFAGt9Q5iL*)3Eqc)P5Ay=*|J#!GS#YbliCQb^$TZ-{aIG|NZUfdO0q<_l66*e`snklnzkktM zD)i2iH?h%uT}jt=-ang@@C*yOZY-ZfHV6P9-snrlN?dx(h5Rg*tz3HU+|LZ!5yhmK zf=qZs#!iE2Bt>rD0EXmJAvi?0!9jV%92F0TR3I(oShX;7mjuCRTt>Q3Ho`W-PmoTr zk=OMVs$LkLJ55SWurvFPB%tMvHFFE!=Q46^ra$ce7A_bDYm!@ zQY_Q&P+cd&&S2FmGKi#P3`{-Y(|0(tjwJuRHrw3YFV${6C8H;ij_7<<9XQA3&j(iXKsK2fFT}g=`skXC91&dHn&VN+v@kMP1Z_jqD%8p0!=o{Gehd= z(%&d=c{a@)eoR^1Kah%fYNI7vqH*^TUgPfPPr$d_>QSpyIz#@9>wV=zx(?- z(nN5wfcvqBw|B+m+nDzq-H=1KQ=FC89-c9Yx}=hkQZHS$JzXFj@L%GGG5au2x#GhN zenlyey?2d^21(=4)~)+7m3u<)$Zwdw2#rWr$+EyTDw?mk$Zt-Q22G(A-*Rf zb`nj7GA_D(EVf=7W5>=k`a%6_qfvV zSMFPkzbo0@OuMA-d-*_FmnJR7*2VG1uCDU$ORm7zY=nkkY_0-4H^E@VRR5v8x*J9R zj*?Hi~`;R&I|=hjOjbCExH8mJ@{-A!DsI;eC_h(p(p-5 zB+rFj@%dD&aHFbatT9EYdepvxXUqR~$zA!8kI$~eo=;9vm;#Tqj~*94bb@|l05Z}= z78l7Yxsfl={o9oY{QJ4^(m-`8*&|Tb^c#z4v~byyVw87^|7R5a*r!p40j_*zXiew# zeb&&!75mXh&70Ek&-E?4SMGE(m1e zr%&7YN}3idZ)Oc)xzBJSbU9zplr1{= zA>ges!q0$|cD7Z30fvDW#9GBo-<@jDebsYQmG#xJw=&mI@(##)xZQR?rDd)R4(_Y; zNjwRt{qYkTNv?soKaMgmINL37y}l-L6ABtYb8%c&tQgNliV+NPj|Xs&0XeMF29GUl zHM&4dO?xEvP-m`NOQnJJ_k97OA1&9UB2*4y)ia^lS(|A!Ta(9b@YaSAKE1+C@|3kK8+(Zz43X~Oysk0x}n@FaInOgUc9DXyX{*RX6s z0V6c%Fra(f*zo1nfl_JEk->ug<{SE%qAZ>!ffzI=-IF6E@Q#a~HLp!>s=YX8$c#Cp z(x8*L)ezUC!#v=})ETLw1vx;mpI&ESQc5s|&iECJ$!CNDja1<_x)s= z>tM5?7th>)`& z<4G4cldk&Qy^5!Df$jhZ002A)BssGh){j4*r1O2&4kg<#Db(n(q|M5MbEz^e4KdQ- z7d-{iJQIbkrYiZ+-0?4XR~`;|J)iGGPbg#;S&XLXW_$MC7bRso-5uExdihzc&>*FL zUg72C$mabKXi$;*wU(rCcUw@*O9;9)5@2jnl?6_>`6i(+d{pg?6I$bsdF*CKxQ{)L z&ok&xfvdbkgybE*m4XZ8C%*}&ikG~;&lZpl862b6srKK8lW02B>lTMP^5CIt z=&J3(Go-@s>i#l}c==~cbZ}f!3h_m*L1KD5JBB7oFi-Uv1OIFZa2mO@W2jwe8@rzs z>;VwY=Q6)H_qgra3CZ4*6M8zhZS$oedB)3H`5OF`d!p(!%IBB_{C};_OM1@hP%rFj z$BsP@kQ=^Av5rZ5`Diukd0vvN@ub5JNXZ@YpHV+@A&kkcf2vv?} z-U3r099wYc^X;gyrAfLX`xxZ2=uf;&^m5W)onvARs+XzLyv+uK4%xnD8N^Qm z9{sOPD2?+)(@;*XsoXQ@g|Y5{irU}qPa$*pHXxLU zyZ+m}5Bt^Of1buG6Ac_5^v`AX;BVHse0ZbtNHFW^ zg}J9XqtLMM}^%UEny3T!fq@E_jUthh-ZuZLR zc<c_i-CJwBLViuaE23Px!~(5-nW#ye#h`d_e}MKnAh*jHt;+kXlQ zs)Kzwbu5)#dcpmSuoxZGJbl?mjj<IMFS0wX zKw6UPVEKH>*ISbwuXfJ~@o=3mAwH8eYU9UTMlSC6&)F_v#I&$C*N)b#8JhYgG)<4B zX&qLQxt`Me^&xa>qTqsRE4|U3=>u_v8w!on#L%!fU*{PxV7sbC14W$=e&{cG9K5p} zp^%mAi4IuxOSNdcY1bJ-fK9~NddD*xbvYN=&;twZniNs0DKQ}=YdXEQG#-9F;Shva z!wXzF*1qPa_txJk@XN42P%-&(9aMHLX(S|BlOGnm`SABxLnQGT#D=Z!Oh=zE9$0V& zDZqwQsEjTs2mqizPYOV?%6pPdxzp0iL@93QMy`BM%D!qOyWw3xpTzf;dw**=8OsSi zJgahbOWO_C;;nX@StaYxG*4PU&1P!HW||cf59j%@rT%?i;7Z=)Z)zj)QNuT!edub9 zJoeq^24<9jeY&qb2%bzm>-o64rNI(&WGrZ8OeuD58e16aM^$Yh-kI0 zelXDLDO+6noB3AxZs)W9&4!`vyF+hAhn?1M^(f8EuD?DOTGw#?G}TYNhB;R=uA`>l z$%^*5TNIcKKvQ|(R7a%=CT9yfqJGO#KV^92I=}vZwy>#*K!wqBT`KcS7v?P9zT9ty z&yDt<4~L{rZa*8^8P%ID!e z4bJSmANshXYCCJMQ$xqx zG$(~tKEyS$!Uk%>`&%yr!Ju`?QBAe#VOfc%vqZ~iR1e@g$v3~=h`#u;{ktjn!_Y3@ z>@Ge|`6CpcnaMmq(5D|bl~70#{PZ!oDN$^fHULSP|GSGz#sR9%zP$N4l?lOVrla5N zO8@vQbB3(V+Bm~%08-`F#_^@ z(SYq~X4TQ=A`fTbUN}Vx$&-k6sbIZ(gKHdqxrIvPR1n8p{53kPdfjDo+T!z$$azE zzkK(e=KV*}|2#wUzh9z{bTASh`*>zwJbif~ww3A!IqClWM$U{s>__;&NLTkng@@nK zV&*f4(bh+<*go+1^ReeMddihMH+ktvbfMy96G}qpuWu*LghjyisZVx=f)dYm?s=YT zO?SPr=MHphf*f0NyO9EM3#y9|5cqlN!nG%8PoKn;H*;?6Q_i1~g2(|h{hzsygW<72 zHx}gQb*9^o$Eid@!N1_da$r`0D2|f&uO40zr%z7WNn!u|J?wtj!AdR66@tCscYY;_4PX zf7a;d+k)C3(7Lc+asI!!H)u9({Q3dI$Ubkl(ikX&sk-%|qanoW%@-q!duXUPPICBD z`-8u)G*+~NXp%l(I=&gzRA>Fe8;1d&WZpyn-ERyjyB5BlBxOOI;Dd#fMO<}69CC*) z4_&KBH&)O%@t0*R2a>s?lq^dq)H~o?Q=q+>YH<(srLMgwToV21{(6bWfLd(w4u7HSB%h%q*-@@9{B^h4hnpXidlQ!GPG8_6vx}W;U8GLui`&nn znv&=PEyAu6R&|c8S1S!ME0*=%{YP90p)=@q^N}DMJ@wVW3&>ke10K80i%tB(k@4=& z!{(lxY@PQzvL;XI9S*RRsB82w2nJ~xsnuna&pj0Qa5*h74K7w$mh$D}hu`|U%YDgM zjj%rkU)Bj3-%nxE+|)gh$}@LP|J^nBoT)r_tK&bnjZf7ut5;#X-%hzTy8J{-#tt^P zH3wp*-u`D86*hY}_`zXs->a`&Noi{Lo4zDSe}uRus#`-|8+SL(1&m?9Y0$pmwf^pLY z^{D&OyPA>)1|9`xms|DxOUeU1l;%ro^7(8o?u0fZ#JsoHOglwFUTEQK?)`jPRuHxG z#zzRNx!knTVJQ)>J7J^xpYBA0))l7*+TY4KSjVh@BNyW$5kR%^KFRh3A8c~8?ZnM0 z4!>nSNzXQ7Vvj=pvyUlj(?~1$6r92MY;T7p+%QF4^R6$Lc5p!1gU@fa<+hRUCla zu@hB3tp~g3yU{ZIId9`(M}ABLWZwL;i&x9!9(^j7$9U#)Dt^go;5CDt0FY!Bg2^TYXi$!Fs8Bt;?NGZ9 zNMeiwaZ(;iMpoJZe7brs#g0JVGtr|;+6s%ErPO}}LG$-#Z$BRGEvhnN>e zGr4@CmQp5HZ6C4f%DHgyxj@}EyYobMdJ%9%QU4DjLgP*7%R>KrkiG%I-8R@xTkQbF#vkF5N{|X3s>Y2 zj~5oX6bRN=0)mLyQ#@(eJY_x&ULJ5O6+nj6`4)L~oPXL5@6_xp47aE7-+tHV3?A@*qZq5hmj|_M+y^SZUU!62Uxx;9Mz*w=VzQzY-!? zl@mhdzGSG6rl-hd?{@sZW;vA1@iNi%1&dR9u~vQ%Jn_QAxQ$Ybg_QTuq1~C6|B1hI2B~qGR5CvX#bp^gcjtoY<8I4sRN&khsE3z zQ&viVf&fs#*8Phq(LxlNIv4=3um`d%CzyT3197Sd+2ZWm=!o7Bn{#QW} zP=_m!w1^2uESta=p+K@r(_4W#qI&S*Hs~_nJHfeaj$D`y9wf%3f+PsNH-9ZB5Krs&o^N#(;Hd}lvjC9yCby+a0B;pN%@k~ju$*#Q zmR5n7jH5_jPCkv_e_LM40)X1i13LIufW%Jnr}Si(qz8-|NlDxA#h4yo6p09D3Y z_O?k{t)?I2@bY9EO(kvrA^{aT1OBTMX38=67|(Ird27m5dbqabnj_)18x5pLOpLT>ME7%=pQFqgk5% z@ApKm>3*d$A}&hp{4VR0>B9S&C6gfH24-bd)6mXB%XYxn+#AQE9s{A&kzg?501aXB6Rl_nCCy{HV- zwxo;XoywD?cPWqAXadnqSahB*#=wk~E)7j5UUQ+L6kJr$S>f#^&~y&Jml@ygZ6s+C zHT(wAR_Nhkwy{FxuO_-Fi`d|3C<>pLrkOeBl*A6l5;Oh0x|GcH)%!~oGwl_PdfJ~s z6abH)6sF9-(c0qyRp~U|fJr!qohIc*Y9?a;5N}ZjFlv6`i2x{dd3*jeGJRIC3SeX} z%j{ z_rS?o#wEgoh1)a|YO=|*-h_R1us#uNK@ zU1i3qy;nD&ySMo`rK0Iz#NCsWEt*zzF_}Wsnzq#~sgx$2B`b*aZa~G{fySriyQL<` zY>?@2E;)SVp;jg}Vj_~*YuRXX?2%6b%M9B|M6#%e63*_H%d=|p>9T{1PFvUn@RktU zH#Rz1G-d|T+m#02JX^(FCNC37)6{F-wg1ed9r%+y46*^}iSU6eLE*w_e0HH^%JtQE zaU!tW?zc^;1?2U9ljXcHpVy|E$pA~ z!--Jh@mB$dY}(9Jf}B5@HX@CEm zi*%v=Z30Ae=lLiA0GfcDVHLpG_8k?Qk}p$QgOy}_|J(+PZP3fTi7_j2Be?hl9mhe8 zRK==^(;tCu)FDMOOF#k|3y)VN% zKtaT-Xx*96YOIs43pCBEztC4BJzOIqL@-*Zx_xQyKAk(UT^1AZIW^X6zY@1bj z^9TnT#feEASdO5=+o-5c0Mf4Z^V}Q3ri_$36w3$>g0f?kG*ELQfFCnft5UR8cdm@X zY0Kuo)72|7)CYIg?{^$*B8z120)878PoIAdZ{j+PiKM*Zq1x9pW@{>D6e*cXDqfRa zF~NgOkJ36nIF|^HIe({(AnQEFL+WN

f zTr#PbCMiD@oUWX=lNvZ2`yF^~0&@o(^5iDU#^*M9KzXFJex&C1(YtO(GjCb91)45f zk=eHr#Vt#vS=Vri1q!|BGNqsEibl#sj=Mx?2vr`&UBQ12OxSixvX0%0A>{X;F+WQnT*A@9}0Hzxo>h_^Zc(&rTE*t}DwyL3VJ(!Tu~yHS(e z=7s2_)-^kS>{hKhU_FKepG#t(#>!v&QsGR=?$dd&Ix4T%f@3d75WLf7U&U*nBKGRO zG=~T#6Ypn`PDgT(XmPJl0J08(ZE{82C6=GZ!a0r7e_Ro5)H-h$5epZ1cr!D)#sen| zx<~9cp9(Oi(ZAi_jo@^q_g?*_g>RjN0(>OO77i{Ws^c{L>!K}t36)iBO0W=NioI&D zF;xHwJ)7*2!v4)T!zBmZ)~fE;&Ulo_$Cp$9P}pB z*Q=X~AmTgp?D&}x?^6JMVsc*X(lE(8(&^N`dO$hi477xJ%*2CKPUO`MF)CbWXn#}r z{EIc-J)xP%TS9G)Ceohoe%|bT{R{6WA6uC z8wau(24itBsjJ`HlkHTIu zuLS1K8N@q8+fhg$aeE2WS#0kQF-&9v{>Z_ z>sr#ECiTc2&MWSn!>Zj=Kg9N7dA=&2&d^{tcBW<=Z9VoO+%Vn1PhL@raY!~0-wIX=F9 zey`fQ*=9ln1Kv&QuvQ*+2f*7t3xVWL=8XH53~3sQPoD+fiQrNjCnBYQCeL}Vuw zLorLq%6yWif35O|=;jr{7+{ezO=SNEj+2X?s=>MgO>KCk27YQ2>Dmfr`(^yaw}0GD zWeF1KaRM~KbTecN39Hr%?tX&9n#jK-vy^UzU8EwL4vg?-Sn^m5FXZ-S4i~B6dQleu0CTRqw-;^_ zXi&IjhcjyVXGn&r7-%_xqhE-hdhQYrUfiT5zp~v+0){>s)2Sc4BKGp8t>Cr7xr>%L z>mjqiS5IFzWrsS>wkHpW#;E|r9V!nw@HvhpMt@wy7>&NM_5M6Q^0r^d(4jJGk^ktV zi#D2qGPdzjoFaxSH=#nW+b;#7`sDvi1NM)j1%4PjY|9$pZ4wB0D&n|%2g3d{u^hZZ zNPgD;XXGDa17E>2%Sdcyy_h7O_bayF9O6G{GEJR*wh;zWcU$^CKC4-&Js_m3Mn?}* zz6Sk%c|Y^{D@Sf;M(=mg(b>j4Ha#^Dj_Eagp9nz(`) z#)AIo%0Uj7?Q>pZ_L%AWkpDhpaUImW0eG0;5x|#2_J7jKDu@7T(+tpR;je?nsdg% zq{`j2?dATLPb*Ifj@`cgchTrxVEjXccCO!VF<5Y!R{uVT*!~Y~N9l!#g*5eaApO$o zA9O~dE0O`n;q zyx+eN7E_m5@W)?E!@$)X3;44B$LXcX&z;sG)7Vax0}5V+j>ZvK(OqqIt@k#XnL^*3 zCv21(zaGoDOT5p+3bs8i&;Z!@)N_DP zLA(zDIL3T%>gzwYQ^P#ie!@puyRm30d`a<||`|SV-E(jofCAiD7z?-^aS>P2`KX@xf+{oNuDoW!x%ADXBaqP5Ii%w}t2Lbt!01 z?T*vHOjmrVXM&g#&Y#IYv{{*@SHt#W@h25{h;JUDLS05^$qhafCk5Vtk`+)XVplB4 zC+TqaR$20CLtOi$tnasmUoBbJDMO*FJ zN)ON1TuG?~_;FJ{vw@au`_rhL(oBjDUC`H)q zBw+K5-7%@H!7K0nM)|TX*HQtvCfRNUjiUc9mqovf|M523+K7FIap+CVT=UD**Tfw{ z`#_Ihixur|j%Y0H`7nNNh@NJwRMSS!)cL(Ie@~}07Wcq>09W#c;^X#!WYfj=Pw^n; z(swkQ2su2=10(b9|>q{oHkNycJJ%ZbD5p6CV34fK}Oj;|P1Y zq!1N`P;7*}U?m+H6M{$f|W-nvc1X2EzMLq_-{P zWeN>yGO}{=!DV}V=XC8Oow6IFHdM8oATY3xNbIQpf}QffpjIQUpZNs9KTu{`Lb}=3 zvpi3Ia(sD1n`);cHL3LTnNMF%(e&LwnM@9qXMHtp%`O@40p8oiG6ko-6$kSV(vi?EJLU|p(jlf8d*1a~4BQ$A2dd6#41 zO;NGV%Zrjfr>tQ2q75A_PO6%4dZC#Ti~i-ku5{cI86Di6!@g`Qa1l8|X`Y426MTSX zX$k<^k7Iq_c@c-A-e8^ComnFJM#l5oJcozJ-o19ZhwFK#<8Y|kMch8>w$2%?nWqyo z-f42mwDYbK=FmZ&XtlVjSkF^Y7=lna{L7{PA?eKHq4?uJJ~Ml-V|T4%-Qzw&>pnv3 z$W2Q~Qmvzs(2^vTcGtD8tRuOqB?+lkNjksl3`wgHol6&;luFX}^ZWh&oB3mQ=P@&n zd3@&mI-XuWmuOowippjE4I!f8VdC4$F)e31(y8Tnl&e-qbB6g~z)&($hcX>p-1a%R zAl&f6&pI662?{x!|HyfXf!jHXB}usarxe$pS5&>biLF$!fi$S>#&@L;ijbP^Nd0w` z$Lr6C0F->u>CNr$N3(wVI|Ya;{(F6aI;47Mt26_-xZss`?}BJ{aJ+c-&fDMeySuOc zj!K{1`D`xPb_WTWqVJjj5mHx!T6S!@CwE>popvFpDEPQ-8yl(1H_i?2f(VrWO7R<# z=qm;Zbi~%;mf*KzVo-N}qk0-6tA8T0aeth^HIW5M$BM6;kIi{K+0=Axk&PhmXh(mq z7GoTl>^C}e$#Qvtu#K`)+D+VNzp_xQ8^gtJk>suyneRHCA_g5OMr7T2@P5#DZK5II zxUu<3FV61no3b^J7A0YYKkGNg{@0WZ#4~nqCY2xlGSLkGTj(7v{q*22)%Gv>Nwe<% z$z~C+?C|y^vK80E3J91V8`*{qhTjTn-xKIowuxm{ zyIRb*Gb!%0*B`RQyd6eUC`9LfGSn<n|;nakK91-1d1x1n={y9a*wof0tdt=K;JL+aY+?bNy+y?6LS8hHl(nW&JGMsHN!TvTQ#tNq-xSaijBhMtK)SS5FAG|qj~J`RSMxE+EZoQ! zJwAZ1rP;T@*nIf?_HNv1F|^|{;gS%W$j8<)q#4ErM})ooVqCfq%ZI1XQII|#!gb?T zf9;0wLs*0CWIT#v{Lc`J|_0gu0_1wiQ&Uv`C=>+!18Hgw5!bQMnbI^lL6q-Ot^z9N#^6m;Dryq zgl}u{%M8RZ7-c;pz;+|FX{gkpe~V(Z_V|)Tao@XyVY?{l0Z9VZs$N+#t+w(SId%zu zBn~#DK{lWDM5Y&{`yg3X_M^T3i3TjGmv;K09G)7(LuuT zZx;vXtUe+Y{cQ#tVXCD^LrU-Ys82(L`awP{l9cu*V*#NPMutiE8Ukp)QaFX**HHi; zr>R?ur_5k=7d~9cN7%rK)BeaxSWi+xL)g*OGXbO-<7*Hrz#TxC!HCpSgqK)*O!%4g z4LWTKXU1t&zzQzI7#pBhUyL*!9w+ic`r`4kj#OKziL!JjPrWcVxbs|{nov6RkYA#$XV4lu%M^%{S~wUFH} zZbI0NZP@<^;VyJHXSwWi-C(^sNfRS}n(ftic&`$8)*Z0kw-uThz=p>|&a4MsGHcWW z$25eH4Zn}Ns2$GoS<~L9&A+=WM0i}By|n0h;sP8j2JM8VY28$NKNGCBxeUkruM2J{ z3%gRMX``)Y#elAibvF8qO@6W8nWN(YD<6HvO&kwmTpJ zf$DPsS9<6Kmaz7HX>3X0!ceTni9OmUl;}-Cr;0BNhhi-bteSVOd#r+IY3LvZ!iI$s zlx-qM;nLx-?2s^j-zKYie0VE52lvX44?BL`+0T;dl^0vpF<9gP&ej&yRfL|l^{Aa=~0c^kwE=&v>i?IzKv}vnDQwYi~ z#8vZgr&%8s#kim`WQAD2kRR&Hf}iqn+ZU0?`Lai7>wOqbdwdCe7AkqMq2U`MpHUgk zKvXM8r0b*FF7{{K$6(2>_fLclz-YyC_yh3F7{HoEq2xCbB>C_s1}&q7j}jap{s4N@ zf9}>{bj`dO3xM@;-TpP&WSMO9f9!5F$Na~b>3k`2_PlI76JztKKpxN#c`c=`1yjHT z?66AB!(X9Sf5`!0>~tl|KrtVsXQM439l<A+)4op=aSV@rY^Edhx+^ z3@B?eL6C5Z@d2HzxLyZ9-o8%of@8rYFdb-4gh$>`b9z(8gNNcupuLA&pRa&2gTTiB zDh#5ET@;{aiLZG98wf~1X`JX6pW zREJnnN*kX>>PF)HK z*N34IS!{Li`mNtUKbCa4K&?Bq>bHJDhn~O ziaWbR`1$2}fObaL)oboEx)J_h2-FzGU;BL$afJ9R?Ts$BGRqf+BE%8xRGQfbQ#?cFdqA?6WJpDbK4;zupo%JGE-pjji5z zhOBg_x>(8Nq%b&^f?Z7*pTjx|Juh5E<|psRbw9gV=F=>1s>zY|pp{Myqwt)yYlNs& z8YWJx`8N%gELQ?rx;z<mF9D5M}V7&>nN^^FAv$7u)~ezVk^-kas?W}J$vH>xygU|SHO zG8pm`H|>MJsm({kGp{bf)jwz`ZT=X2wR3y23dd<9-5=8xo+ClSb{nf@P=SJqfKJBC z92U%Ezic(ro0l7kfS#FLJz>lOA9*b?L2ELsl*4AWCMj|{{~%?~kN_ny`xl3-l)jH* z@@wBOUts&Kby0^qzE5=|ZH-O6b^YGu#LUB;-rr*l53ZQlUJq%aRIb}MvH*DqB{EJl zgu571`4O+}muTkKoz99=n!!$7fdYI9m*7wCZ{?yH>!O8o1LE@`99`%T2UiIpM=*X2 zw`MoT&B7}caAV(uPIuzS_L(tvapb{~)$8gg6;(^>{#?zM9boJW7vm~u1Ht07<3i-v zGkOcTcay`NKme~5jP?U|MA{?jizqeiViDF#?@_|P|Eh1=J10pXjhb%u)zpwbiD;1*V=f3Mi?5_ z41Ne-N=YX{nA+hT3Uk^jz^`z-&cih#_By3j)u8WNl)iKX9+uS92*R>6B7s=`y4E<+ zdG4OrKcWN*D1UT`b-rHx&L1p>duXjve&nM~O%#(;z#cRzIp|K67~=@L+p`*f-PD6; zq#S_WFJOxZ$MeAEC9#gs?pAN18>XyLTiw_RIj%h*)J z>T?hxooVZTTcZp4&IT}?03&MSiJq)Ji7Ow8el)mrV&C!dca{KH*9!0Y22ND#H38}> zSIq|>Xr9)}9%LZ&#YTGF-$zV_M_M&~YUr)-{pD%3E7I!vl$cFzW!PeR^7dhcJZX8c zI)7c~p~zn`wFO+F&_ zf%gwFR$jih+Un&G{&?llXSp{}f(Ls47J9>22$OOI*9_7Hkf~zrOZ>r%V`gqDYso?1 zTxpo53WTmWozRW0O&FlU5+wdgOB`$FZ8*Y%hEep5d6D=vYZx(64ad`vDItdD0P>O& z_R$}8EprsWaYIXM6wcZ=8T4ghEEX3>-8_o(aZ+oXn?#5@DZHFR&=M`lwLn`z!>^KF zzfl@b&`q-odz+PolQT=@Z_)A?EYn|XjsN{ftJ_&!qcv?w9Sg``eZ}- zl6>nmt}*_nEI#M@#h%gi{rA_+^9`dn6Tilhoi;yR~RL$^Yvwk>9;!hCP&(fgBoMhm<*Ne-;ev(x_L+{jUPOl^C1>(=3a zvd%{)USgj-!ug#(*!yztlb@rb5W2XNIrwXEtH$2tpNTQ;O`};EL33h`G}?RIbKhLw z1`l`NvH2au=r@~Bh;xs$?H27%xJkd>h^Yr`3ytugqHyN`r9*N_ILv4;AOz{zg zhtHj4C`iDj5O>n3OTSy3=m|#NZbfMzo%+&%5gILElE~Qc1!7)!8w^VM$=c`^hH6;3 zo4duH%h_fYrc9C|1q*sl&fLN6u1)^Z5A2;9v{5tb7g@ZZHt6xCQtCz(3-_N`m{CFW z-_BH)tnHEC|Kil~(RcR&tKmGO$OAr4!_2!+bnHHJ41M!?>^W3VK}^0yHR~+zZfGI3 z*21RnT-D3`y_ar&8M<&OI%b}QH~8rj-*)6jor@qliMFcd{2Z+)H~RphHc%-A2_5~e zLRNHNTJ@>(hbHu^pqqXMdz&AeQt?BSy>(Sd{V&3{u=Of>Qz2j%Td?N(l3D1BsBUSU znmey$H+{Kr!L;$q+8nfH;VrE2k4kh2w0j>FM6|B`Pve+$@&Np6x*Ms(Elh4S_kvv` z6*?JbFC7i0b;+1F?(WT|S5_uJbl%pR%1# z{z8&3t^G*m_`_Eyr}qAq}#Z0?xlQEeS_I`r4)sI3P-A9$7V z@5Mn)&$MYBaSp;}i9r|_?QHWmF&w9OSdDz2uK2pl15PBV{A5-q*ld|Sp3(U8W&$CT zIg4vG9X=4b-$x2OsoHpBvh=0taOZzb`VKwku5MHA>WS>=IG}*Jp48v=aOBAMk%Ld3 zDam^OJMtslZ$R}jA+mU!;uDm3bZMV+IV-9*QBC>Q+(tB^tD)!b<+}cXbmd*r10Ux4 z+?7OEmeNc9$wu>wH+ih-pMUCE(>VBb>kl{Db(2)bsW%DcU!>6gR&u+f!wJc}$1wUu zmc;107izuK2R>$Fr;@B8a3HJYS@fqL1!LD_cAVdHLMR`m5{VTk*6qi1y|b-SkV{Yk zu&#yFN(}`$ljyF6F(E$8Z9BFwaQ^#PPwHe(WUnaA_4eZxMK^aH4lz5%5P6I3mwcOWwuP|wmq~fG=;A*6?LG_N zzHUa%aHw3@f~YvgA9jPlmvtMQhx8fazq9XnRGByZ)jrc7Q)r>S$-n)<{!l4~@MzqW z<4xYZy8NUa&cDL~i*Py&;gX@y24BS<%{Qm7@$kCt)y^oFKPUY_?a&>C?xzi=luO(94c``fnlK0y5521DG+HDp0{AJ|w!w>3U!oR$C z-zUN!cWfB1kK3StSW@fd{(i*AhYG$BX*t7O`MdA5>%YH#$Iz5g`z5(?)m&uWy1gp5 zyt2yha_Y5GQZNrMuNImVqb{9sM7N>2!n&E{!p4of(I%>BDd^4J9Ok4o{b zA9A`%JO*z2a`&DKZ%&$P|MD=Sf%qVv6XDJYYRoJ<(H}s{o&EuLADD1yIEjq0La2ME zZF1*|r85>^t96T@>@4Q-)lKC+gZC9Y#L&F=Ig}1>qTOr_1*0oGDr$&dfD0G{g^P+% z7~2%J;ud>ze78*ghx;D9Zm)7P^q5KF+MFgOERM%Xl&6=5rZmcr^5qV-$ z7m7=v8;jE>30*ts8@f?q>q!}Qha}_qIBii0PAK7D_-9Qb*p+6I`T?X4=jE2ekCEhk ze8ekUX%TH;%bP|RBBcpsPk)HKv&7P|oh>4Y7Rt|;D>>d#=4_c+Dc%n(YI!q?yPw$Swy86chXB}XjSzr65!~r)X z4YQ4qGSIg=U*$Rfi5`)-G4kaae7|GW1p-8xd>Sh`_(OvE;ojfT z`vY0%EY<8eb_PN_KeByQIh>lJbP8Uv5KQ2QI3VNF>KIdwC&U!W65W-{Gzz{_UPAX7#@DbKD zj$Rl?`~9AD2Er;S1(Sr-H)qF)&=yokUJHbU`&M6R21Lkd0BKE^4^Ab<2{WB2P^cWz zh-X5efhNqbqXMEc4^ry_P39FZw;v=B5wdK}03oDGBWv>zTfcee%>yt?!Hxz=)cByb z_?W&JaoZj3Nk67c&+fgZ=tyTr_(7)P!FAbowvS^z!jP74_Tm57j;z;f^a zaUBe4!H@+LX~0l2<)>}nL#hIzyZ{2f5k07oQy4;lsbxw;g>@mc>13FXICCE3$;{V+ z5lVvmm|O*YvD~_e^ldrBIF?j2hj^2>JE2cu7FKvKCPa?f4VFfyw;`k=-M_rwi{l`W z000O9Odt};2X3+aI@~gN2c!^UfTrk4AR%WAH>jel*Bv;1)xxEw?sz&M|KQ24$ygI} z9*e>Q_4`2zjrejW61|6a|Uy&Tt%K=rH(BbPKA`e_Yp%f=9QH4uY zgdjO>Ur-W4J&>$u9)G7_X(N0DTSqh{lk8y7D^<=i5aAk$Br)a4LeOfIq$K9_q{@jm zq2x#9)U-e?=AjrW*{Y;WjtQC_A~Fqh%+lnXr${6w6k8ul)ltxbc`8g0e+ZQKM%xNN z^b}XO8L>AKqA)A;8OKmJR_`Ivmsz3_#zRj*;;^WM!5kG{$sJvJYcH~nkYu_5h|Zzi zJjhZYv~30&4BchF1&T_7e5NX;l6IL1h&_rYbYaCeNo01_2`s7bRUM4u$j2-YIz_4v z#DoWYOo|Kop_tGv@zyYJC6_`p!OK}?k@Wtd2i2@1-12+JF)8OLFkg#tRO1#ZZ z8^yJq#8Z!PTgDF&?TEmOS)gII_~~PW91ijjp`FAag;7n6MA`{+a9D&t9dcSgDiQb5 z_^a-LELDbO2m^sjLy*5AjrpJ*ma>B$r6SA=p+QR2B7;Lje=4Lg4{8YO)IWd<;l4&N z_-z8CNCaifvzmFw2!W71(*m1>v{`-1rXkAH^_*zL8beV09qqt^9C+{sI@w;JX!{#b zWFn995DG+4n;C>O2e#UL3YB`K0ai84skq9Znu6s30}p4AqYg!2u{U=)lYg5ULK(1yoTwhc2J-` zL9llFJFSb&s$sF3G1G(6@cXC6X=IXW$!tuT^UKFbJ)NZd14-M z6e7)odff=qBzSM{K^r%1{2C}upva;^Dq;qXWo>3d_IgIq;kpZ- z3@KH5NMBOyVpmOXKC%C)^lAyxj%tMi;sQ@@Q6+}_eD>0jO$QJ(pa!A*&gbZfM)jAE zZW6C<$Q}oJch+7RLo^mh=}1D<{ZiIl2=*)1y47Al^oM~V93Vq&pESCBtSg6nn22vV z`D-Z0myt%T=gUli$Ch$evDSCGkhoYPl?B3dRB#ANzoNlK8zCh{2@yfYz<&#>|CtNu zeYT*n2($IzHNq&;*1Wp$1Lz-uiKdY}iBWqupv|O6x%Z%6?|7*sQ$iql9ggId3=L`P z1m0BC9?FszcWIb_@_fv8Siy#o5I)-OcTMqq4d^FMvH;E)H)8P5pkE6cG2lKEfg<@4 z(utquLMufcChmTA)os+p<=eh+3xV4x)DpI9XXy1ikw|$L4IObptV*}r%+8$_;5vG~ zRFVcUvQI*#?>*-Lj_uw2cb;&`R%1<$e8e>2&56*Cyc(=l>rL8Ww?MfKg$hPM`TYXo zM(RaC5TE=Dgap7%CWB|4(KhW}=px-;ejEZ2%s+AdVvyT9z<%qj(`Rq8S@nDQp1ah+ z6RirL<8J@8G#!!}2eLqlG#C^nG$AEEQ3O(vACWTOk!5{wOnXv?ArG z2p#ZiqqXqvvx7uiI?34RL0>8*T7-c;L3h|x{3i7UQyos#byv?UT(tY$~ zXgU+cN#E)sNBX$8`sh5$y$LjDJa}>lQeob-o@Fl&m<{Cm42Bi5?H>HLi*$19> zJo+zrBXW}z1_lJ;)b+n6k}gV3SOxj@-nz6k4jAQ&{&%F0Fe(=?nC&l0 zFno#$mV<2WXFpWy_7ozU5}tAnqSWhdMCWx#t(-AQ7X(R>=rE)LoA^aRs`No*jgmPF z)TE<2J|pyRaLrxM+X&#Xvr7MVUH=jZ%FTDULIoMO9utHb(a$j(MI;*?d5gb*b$xSi zAu-xdJ3&aAv(b|!750a?+AL}eh%#GqM{c%wMNfB}+W z=+<%mi_mQQ50E|pt#ufG(O4Z;f|uHguq7f4L|`KhscjFL3$$Y9z>#{iDG$o_f{b~P zF|A=`Ym^Rvu;n2vm=Z{p$aLU+IbAGzj+#OC(sy-`ZVw| zfjrOcN{#9Irf4ln&|@l?GUbeD93#3Mf$?co50bBguAlo>FkyWtP=546kdH`ugwZOQ zmmU#G$E(Gg1|k~oZn^!N@RzpeeoXeJpy&NOVTCDuS0I0&R*4=2S~zRyX(0ms#SLQs zbzb;|Rs{z-h~OPP(RC}W$nl`7lr$B<0aD$6_WLTt@6-HMV7}#I&E#7{)q`h#9bTUb zQ4u&%k?64N|u%4=yEUCC~O2EALR$8CD4WS@d|;vb}S=fI!bM@BbHI+ib*7MhTLlBJ3$0) zcSKvvub6DniFNpV_C~1+;2gt%-bz2jMk3W&%lbK>eDk-e^>=r~A(f~^&N5$*Zf8%g zBp5fPdsp20gm9vkV*Y6R;fNuN(qqx?-B~z-ys^B?yay5|r{Tw|6u6!u$|-!C?U`ox z2FJ8ihBeV&BMDmCCU0E&qkG9QSXoD{I=3@bcO{<}pIm)^sVaSdhh$sMjqJnPZQXgKugUjV0EnTA0{#!Y-4^oZ(Y0sy_s!hS0tu20mHW2$@}(?O zrMFxOsY-vYuioiiT#Z<9c*s_Mv-QBHJ)FBmX;n%$e@7#!8iiM9j(u#h7 zR+d~4myP>{hBzEdJRI#(7XxXd1VSQNae))>Ry#?Nacu0qCI8{%ax#vkC?u|j-$FD zRrb=`ax|7#Hs$<7>kTw%r?s+Si}KiAn*wSE^>9^%+GjH{Ov>5oZE17uoA}Rzx~uk& z>_G?DVL!Ok>l*a6BXC}J#?I3m1x3@)i71*)ZK>&n2L@q#SS(PUd+$_)9K!Ef_q?`W z<=)&IeW%c}SQx}?r$>jSJXVmMbmlV^!}m1n6;_G_G9HzWg8meo+}ERi{rP?aokUm% z3oroHv5>ULoW2=areS7-X$N_b^1AmW^%BMRxFo4NjPa-RB4tugess+}{_|T)o1Fqe zq6?jEE`>D~>^`0HZf*Q&tKAmMO;xa&l{4x5+Qid`-ZVJMK8h;GX}fTU13Ce3D$Vs1 zXT!@brO%yill~!9{71Zn;E<-MyvOfq=;4o5y9;hibnJ9n_wK}|ia+l={(HI9B&Q2# zF^)%G=()>o;nT9HhM8ZV^ttH=$W}cS<|D7a)QH98XUyJ=98t=Myol_rzPRUB(mWqT zBDo!4+Vi@%iV?}9*(Vuk|8Jz-S#fYCQVfhM#EKPkQ$DYxz3D5R%Xz$M$DJQfqF-g7 zjBL86e)7fPe@r5J+?1Qj$OW=SH-REziuoS?DeOw7;knwnFk zJ3k!yaQ5?OLyNL7dg+1x*#0@vE_@d9-IzHdHJ-7s=h;{*hqe;AD^_u(=!&DF@xKkC zG?O*1C=F(2@d-UNSqx4aUtfRUN(&+rd03|?=!bZsRSO}W$ zs=-(o4#B`U2>|g702xfm63)>JKBz|hFDnT&Y0CrBqU6tqZ3t-~*y(R&6UemxO#96b z*$lAIpPJY?1A)aAgJO+)QRU{VnV^mH(OTDCZ?2a!Kx=a=w}cT(?=J?LYzADUKfLD< zg`>Q!(q+HV%v%4PpmNElvIge%QFqj;cjLn{#N= zlrQ6H5i{24X@ifl+QRtS%8!;qazwtWO8mFV`wjX76h$by&ZlNP;_W|lknM=_^l_C= zmiosgP@2I&z~Wu&HgH?|Z9bCsO~#oQm^XWi@LnA z%Fw=iVBqz_q{8E46PD+mwHmk^oy|eFX7laTo1bz&c%IR)Zp8StfG0Y90!e0BJ~E+n zkikCHC{^z-IoG15HyF}Ro2~*nT{g?$CZ+}PHJ{xtSdaFNcMNTcwq(yGNIEBOb^9m% zcszII%IwCgcgyPH!3c)Tg?pVdAq2nqNZ?XR*udR$G4|F|ZjtE8?djAuylUmRO+i_8 zU28*%;hvr3Alc`3O+qtnXn9TnpjJ*39`{Y5F6=_SR_F~Dd!`c2}{UU_=EDiqC zI_&?s%B9u>yy?VPdp}v1ta@apjhk?TC9f_^sJs(fqr!PIp_e7mK5I-;V_M=r*~n_0 zYxm?y*a=4qR;`Tcq}!h7pur7(F-YCL6_@$;!*d5w;pMN{9Qs z%kRUkWwNChz&(w{Nt8L?_0Y-t>jRw*93pF(|NHO^Nj7$`blt=8mbJ(XAm#QuKNq657@P@uU&Y+R*QsGSkXr;V9>WBENoru41m>(3%>sy zmH2#TOYYnCl-NZ`Jr*G^KF^k6@UtVEU5#A@Bh9-$SBiTc^(|947@9kzN8w5^e%}Cj z@u4j5>8Yc;Ihpui{@|ZaBVs>V3nmMNUrzdoz_07J(Cou0@Bpdf-Rzo4%sphYTilCQ zYwN818+HpIPP8ZM#_65I6_!-H6TXTTwG2c=sxLOLNZv433|{q{ut)wa+{IrtYZ6@# zGDpjHJDxQdU_M)AHYD$kt$mGK>0IxsG3)vSkH_s{2Y&8>aCD(f*!}}M(?nq=KO<(x zA~ukfnP2Muc<8UkveB+gNNGUVLsLY^WXIv&oKob?-Fj?-leBZ6EcQ(-FG;d5;P_}s~BlB zXNhx7g!q}K6L+lCvX{w7d=*!Xz zg8*qE5YMq8=j$wSB_A_Q|FFF0*wT?~$`YF&%TetFC90X~vu)Zq4Z6qYic^=%7uJiNmKTP8{Si(TG(w>A*j_LtcrzH=i5~I z7gx=dTD_ndgQIhseZ(@~nAxVtV{1|&SziO4PPW#4_L{U#K~ttWYrSf0rXIaqg`Rm` z%Y_^ds`6YoOKhnWNR0{FAyqGkL1ms$)9a4e<4o;NnqjA#T`P37h9Vn#{fifrk%rc@ z&pBp?;ZQh5n=-pbIT_Tu52lShQ*!8Yh?sedPdU!_6ULN?_g~D_npLT#*3kHCi-|Sd(Ox(y0M9?pR1~qKv6d|#*S8Ja?7O8S>s9G!3CmS- zv%~VTcr1na^Uj?fJ4$fYl6e+R>|(J5WP5S3+*OlIWR3}Si9w_LoV>8bs-}G|y!ABgfT&K7KVM*Am`XqAg8r<%WR}8|q^($CX(;#~Q%of&K*H?mF8Iw3k`e<%DqD`KMW*79u3%+hki@XBE_`0f2qYSwf0@qt+x6I$X?-h5gjAhGF9kvzx$HP%cCtSzIE^;+Ru1#|o-VBoG_xh1%8z8wl)<8CsoXj3RwT-K8p=mn>b@ zq5ViVI{fhJ2~VoTB`;eplju&1AN#%`Sl|CV(KijtF|PzBtus*tCC>px5wLEMl`G@d z`q-gc8I{(zTvA?yB~;M4I$}WNbg?HuY3$0x_s&bWjQ+}b<+)^EJqs(We_H}zOe}Y+8owTdGAQ;jTF2$bQAf%45v;ZUl@>XO zF)ju64nkbXebjZvle5%1N&&nof}Qcdw6HZhK0NH1siBh{q$vkHz4^jqizDm^%1l0- zHYsR*=1?UJD^ie3cE`Ryy4`w1Csp(WuK?CA9oG|aPl&irsCW`^jf8((E0Zt3G?=-x zr8dlE|99CLCa2c&^gCTF>@}6g!xp6hyY?41zsO&$EHKf*Dsx9}Y9o&A-F8yk?jEs< zzGB%JuB{wqSwBW}-g&83Bd;-~_bUv{o_v{U`1H|u=G_Ba+~oa?Yq|x>Sf$EU^YVTE zGp~Caly`5EfaT3lGo$Y;;Oyg!)p9*v3)uy4{I1x&Y`|uc23T)p3Yu2$SP_=zU{@`+l;N@L z^|-`J7JgMHo8Q!4w#8{_J2^x3!OdW@V*aWKogK^8n}4j5Hb&P9#)*%IFN~&@6>VC$ zbz&}4-;S%&NejqXpRLEWE5bDlSex;T--HcszF4Ua8%P+^{fA`m>(qpW+t!5rPYv|MG6&w;)Tph#Ncia#7U@Z zsybII%}SeIQ>z8JAgE4W9GcX7{!-Q8(k_=x?~%)p_AJhTSES3!XP$1!>XajoBVxWQ z=vqUX%euy9u@ARMK>})E4^Ga|;G@%UipnDaA7P$Y=3|ekf4AZpM(@}!E@_QnV77sP0>k&@V$00Eux6}X7KUt$ zh&4ZS-FyI46gk#14rhkfx5^JWSDVGU3Xy^(w2)=^&BE zGw*zB%gL1sr)S{%RDv3)J zG5|%(Pqb_HG99cbaW?IBu5Mb5RujI8zd8^=cVF$?-?XN-(p;7&`|mX+au)YMk@|4^ zU6H=*qeMF=KA1hbt-GW%wf(-_N5pp$kZo<6X_olP3lx<^WrlzeSJ?$F;JWJQQDt@t z$5v;O{kPY8UbkSsR;IbX`_;~|Wa<2BJ|HV*p|89;*PKc& zex7wI%U_WhY<-C(OZ(c?U&8%JUp|FZ>yF8I0}yCmi&^_P%s2P&c*4NyZuzI5B^pB3 zcUh3g(j+W_wPEb7w{)auS&KN%2U(Crl&qcspt=OAyawhS*#(~fd|}ZO)T=61ToHd? z`mj~OJWEQjBcH+6Bo1I=u@tVwVzv`b2oSi@Wqelu%k3Yt*-sXMCzfw8ldDA6Tu-U? zQ>#(k-|t+WxvT0I&pp%QNJ;JgoM&PC-AB4TgZ@3#ug30TbN?RB(a_kd78IZod~KGJ zq6~hwj8&d&+Sbi>a3y;Ov16q{K$=}N18BGxB#uP+4T5=g*IELy|D1c6IeSHU|JN)& zF!&ZEFDLPzpHmg$^P7OuG!~x6CWU$K_UD%SXRADdNMZMO*I@Ivnkdk);6*^*&iZ)X zbomyTL@|(~6tm~qauRO;&yW96(kk~~IZI@E!1T_F!T{CTOr0fGpKpQ_1FRZusPej_ zQ6*#gZxD+e65VG@Q*q%NJGSn4o1$wNU&GCr&7@Wa$KPg=yr!fE*eB@+ECxVwHQ;=m zkP`oz`U~emwmO!EU$V>b)M>v}gG(7sxys#dPiQ}1nHSi;U-x*CxwvG)2~VzMm0Y^K z@G%ofG4TY_L7++`3`Lr}9$ zOV?O>B~fpI9NvJ+pLQqqv{#Vulz|%p(;GLO-fK}f=>e*ofsQGiuTy>F3HVY0 ztKA9TbBN_T^``;Ra*ZE$ddJ_ND%dd$5XO(1(NEkdXEZeb`P})HADeIl6}P(PZ=RnwOf5ZEBeW9*fMXQrEtEah8n{G<+4^ zojqt)XPB|x;4kkajT_1fmXFTtKDzv?s1^eZUOd*Ybn|MmY1Y%7tfl&UXcRep zU~%s3ZmpgiSxwhM!zAs#e8sgs!A-8yI@~5Y>sg?uS-Mc^+Cx5W_9NaAdv&@L zr!Dz#o9(5KM5(Vm2Fduey&23mSJD_qtd?k_@dW{X#wo_*tHJ!J2Q48NJew62CPv)= z8cUgS$Hx8E0n=w4iLbh|eH*zmzvq&VFcs!s@B(KTf)nvq2@@X0NKc6+^^7{Ob$B zITnHWVr#cBY8{vkPAvM z7LJwE(JIN4TI>Y9@i2}C`UKJ2CE}OQ8YALpJ@MA1ZWb zY<^k1CPL}8w2w)HTfDBt)SFCmmua_@$4=MW54~)&ElX*o5m~?mlXka~%eB|(ZP;+8Y)fDHCf9>6?fWS~d3NV>J-w}S&IJ6lSJbGD~5jQwrOca<46p2&GDV{_q@_=s}Oc!=kL#g$cRb&^N*^~4v0{8e4HZb{&{Uvd#p4!Jo<-J zcr^SJWM-A zyl7s7}dFOn) z2|M5SN_UAB+UVK}7YrSqOpDX64}noHmX6;cysB+`!=v}u-*0&{DUVdS zF$HlcmZw78UH_ie&y;zCMrhBvDL4yMW#zRZYF8r3dNU+ByKlws=iJtiaGfM0Q+B!? zM>EJsiyKk8Sb|X zv%m<~104C@2fH_t2XV?7d=93NZ!OjQP9;I;r5>+~yAqEkl~S`ZR&$RkhM+{1Kl6xkIlFicZ(GSirVB`honladdWJtB zKoAFA;8_O70%FEjhi@OiGJS#2|?6@Ez!y+`geKRh=+cz2$Ww|pVd4JrYV1SOuW4g=}QQc+53(=PeAqP zcDdUT{VJGVlQ&LEUtAF;nWkRvdO03BO+!l$zkj0i>O5g>8rzBJB_s4SAa0J)J0;Y#B#ac;aX0D$`Zhgzkmooz(V8VV$p58Fs}ah zD8(uoOxHI4I2p`-JBOwK?#@s&r9zKy{f6q(*Oy@nqgY!_c0eC-!gL0HjIoiJeFMgB z%|LKgLp73dS$;=LLTIA7^V1K=I!TjqLlH|?S>?);^g~fOz1OGG7s!}4dm;whYi@M) zdD>{Mu#Wh~_YN)&XIJ4t;p^$ATlKbs1~=eZLvjld6fkC0qEQ$i3hGk9a%#f}!8Q=W zI4Yi#Q2~{HI4r^S{f2qP2gwuD5xo39Fm?+WV+9U4disR3zAr)Y-tQy#G?DQRt)^ej{rC4>*F~4k+g_8%C#g}u5Ad^(ElpP37$Ye7F$wuYEk^y2v1m@vT#fqo?Q+F+<4%Q;uOBz0&8%JUY2I%YAA~Xx_h=JRi5>XQcK?Q)X=)G?i{VeY? zYNtma82G4{fNiF+kqPX0Pqe&^k`tkJjMv0d>@W=`q)X(i0#wv8Z`P)oDRnMf)HIfKSMysvMSID%yylkpO0QqFRnla`N7*??+>rpIKQ+mvnFvcM zO;2jsUp%kBbU`vjoFH{!-buMD?t<`H9$#9+6#@sDhA`y^x<~%|j$j8yu#*HfGR-ga zn_nJ~W0xRdM8Mfj!21(~XUnJIjwR}*N()l1XemSeek{d9>O>~YvB((h?xAAJRW@(+ zy@zWJTy8{w9eGL>g5m;Ak)|}F9_-z=tjR2ZAjpI!=OP%=)&W3_LIOpU1;>mvF^%4lGSFs(YRzj)X z9yp>a z<|EUz7AJKg3s$Ro+5PdP53A?Vep@K?JPutR1O2{(Iodw^umST$P}YZ;DlA_V1mJ_V zBu*201Ud>3RDxix>9NSgV`emSA-Ox=Fr)>D!#eXuBOsMX;24$4lgTr0=DunUQ-}ES z{qllSK?>x>D;JAQd?tqyS{gXf5-v|KNeFZJ@B?EGRDwzR3& z2p8t}&O|IW2+zmOP5OpcuIPn{F>r{OIdffBDTbLH)VyMxytYg6n9}aY1oKP0A+!|2 z>SWUa<4c^QpZNR}gu6=b=G7acRtxn_*(`uojRc;UN2iu&>>?Am=^u_~5S4f1qt#*P zHri@;!Yi>v?jd_!36taZop47P4+hwf*0hqJsV_p$ZZ4;HC%^4MSJNE(x+OC@d#|nq z45a>$p)uZl49oh?j(#x3xz@$>J1%Qda~c10313&z1yMPz*c8?ME6x zBm$6HC_Cg1kh*rgqm=v>-zJB#rsfrtS*20&FIAU3TWIW9&2Zv;fw_2Lu) zU%~kw86dWqLRc^jqXkB(*~6FZxNz!l|2aO25S#*VP(YvN=8&Rblwc)S7MS}>;Z*e$ z-H0$HnLuUFMc$@cZb%+?|8iJ0`Rp8~tqPnm=c`8UR8OKrq12AKGg>cDy`$Ei}~3@$3loYIy-> zn_ATy2CbyLV|LTejBcEfz5c7djqsKa?9;D-NcDHziLG%PLI}o=PR=59uP<2-4851LnjKef{=DJClC1yv4MXJMzswxGu^Iq_R0%H{yJ-?PM}dlKJd zp8L%-sSF|7ef*$jx?)Tb;)omi{*53=Pja(5wec$Q~^?_g@2Nu|i+NXoF(;kfn z*PQ^lHu8N6l3Q=FCH>k?fPz_-SBp^nEu}BHXZ2&CHGzHK1pyKV4MbHUJEwK(jdA;z z743m}HvrtJTp!UM%qk6YWG=Qv@ZY2fg^UEVVXk-*G0OzBWk&Pw#y-KhadUyT~5Z=>YG;~q1jKHbpY{Dw$RRS!2r>|Cz-}N$cea~-9>uh$G3ZH=Y zqZ6^YdqTHc?~K3at|M>=2J`se#B2b*!LgV!Lg*LJjTPX=X2f+41V@K*Nd(DwP2E0Rs*L+y55f>o3++#x(M=O@ zHqq@#|D($nJZ+6Ggl&jkH7xw*j>c}$xY~nigX1A;aNif9MlgaA6>2cr=l-z0&DqL8 zEz!_o>47t+=Fi;%BwY5t5eP5H0R-}PN$YNScVYq>5OV+_L+6!gt{?yusP|>#5swl4 zQN(-ecFC)4D+)QN`w`rM#pEUF;mwHtYsE_n^Hcq*6HJMNpT$SG-`6?_N6wcoW1`sj z9G?_V=cTDY&T=}`L77mQkfQJStJ;>`K+Oz9HL1j-+h=xPR<&>T$0-Ra6pnP7`WNdY z_OXuBTWNIOHigyMWJonJVB89*GSTpYzEslZ8|YQ+Km6=FdTYV5U!WKd|F)So(!vaM z7#W1LBN7@jyx(MFygF)cb>N>Y^%-#bZCgUmI~yc+SbvH(s3yQ7rAC|1jA-@?Gy^c# zhP^8nig^dPCd6G0V9&)?2WI_OkJ4Yk42M&hRz)I&9v61X-6)@%!}`q!PtQaY^c{BH z>Nb-$qLFut{z&F}Bk#LGlduRQY3*{d$?8a-+k2yrIJAy$ zn$~ddTwg91zJWvczuzWz(S{2nBPY!Zc-@`vnxSBO7vRRccUUbVqnD4~C)`%LoAwEh z{>#w;Nv+jiJ@|ev{t!wtT*Y)GHOw(}V)oug9o!tA`K|W~YN`im<1=ZSYqj)ac6dFYB zby+5*o+~!F&oB1*w6AUHu|t?y$ByiWN|{H-Egf0|DOWJBy!(e53cI4*&08&ppn}GIc7GG^Wq9vT8^4dHt3?cSs(peQm zyoQ|NMAPYb)BCqAkIhbR2M3g#vT2U^*KvYfHX2mhdOJV(+H7akIKu5w)z3NmTLOQK z8p8&`L2L=o!uoa7cSV1MvzZ3Y02um&k9L0Mak4mL@XceLyUZ8jPBjfqgMvb|UO1@GeT%&Y7ZQ4cOoH>Xeb+7oEsnX>)vMU;6&msqCR702$Ef7J&~()iF@8>XOnPSU~9JzOUAqt|V|`!?q_>w1Uy zi5y6glWxlOc@U5wVK{i%ol<;V*ggXow%N7Hak4$+n+*+65e5&I0Z(%kMR7T5Kp zO88n#8R}(pYt)8%vUC3j{Wz<9C(mN(fBp=B^Q7zaVw~B2X+MA8YF^T;LyiW|t77>< za19%)i+{Q1HRS=-D5u%g>mX+#yYD<5zyBG$yEOc{w(0`w47frhMReSy{#u9RWjwjO zPp2Tr&ROVt*(0yKE5AjVn&%W=o`{R{Dd2o33na=|1M=$3o(e3`z(b21e<)yh=Q4m*} zLHy4XRp&u#dO0G2LQqZL#<$J|Ve>_Iv_$u(di>op)3gY`U)$c32TnEJ@AU0G^QG|5 z{OyNX+sl&a8K7fA?3IOYYC8vi4#VLabfuELoe?{Eqb4wwus0G)&OSvFfFm}{8wB0@70jH ztC0=rb&W$re@eX6EH>Ua%Kcq(4h~cY)e00Eg0zN{qhWw5;$YB_okF=9JRA;O93?J4 zCW+8OZ*b4*tb~?>O^`nHo zARBHP9!eI1h?U)6*SFv;{VE51dY*1D9m}qsnWn<7CNiFBpYpkQFeSSbKt>g3H7vYH zVyH?vB`hnteHuQ`cRv%SIRxRSl)O1_De^9KL={;Aif5&9c8Jm-Ydz&~!OWbs{f{A@ zPlzC-MuRw@%KFyP1*^9oTCZBUeg4olNkE$h3yKB-+-7dhZ_glwTjC)V>txtI}n+D5eb8~tw$yO!@%D=36AMUv}B2j8s~ z;6j7$ryrQV+u~7Ii`8y!pS-3iB&Yt2zSCG{x9n~x)F>n_AXWKEWzo4<(9Xv4+$_Z- ztU)4ubALaz8adc~yzRTw_27^*US)*><))?XCfqGvgz$^c z$2zV>&dpr-@AD@7cyR5~vfl+L(xv>r+nb6Nc0xaM!dufDH+Q3la$oN4__9xJC2_fk z?2GL;8n#@I(+i}YYzE*+Jqr8zKd*P4wI5C0YEV4mc~L|zO?OvDI6107l$N>}+QuT<_8n7bcMs$Q$SwY31g%`PEcG=JoQ*5Yx1j$W`QdNnIh) z*m39c({z^-wa4a;`<7G`M%}1fh}HF9%7Sw{Q91-Y(GWw3U|G!2sL>O4ED4wP zz;0V|EcRRe#}W4yeLueXEn>+4e0sS#M{C_wb;J*SISIXh@>9%R1f7>Vr3u%qjoAJ4 z%kYxh4ShLf(txtCjrjNXqcn*c;OAI->JxXf-r6EDbkn6T7b@wPZWv{oG? zCgttsui3v%eoN+svq z7j!glswjOO9tfbck8igw-d>hD*Qz4*A)w7M_2SV=uW;NZ6)eOe4$5z?o=?|4RCPD828-zGEaRRIiH>_2LoL5nIW|-vS)wwV7 zRrtW?$$Wkkg&{m@ev8ksm`=f~dopABJc+P3AOs_r&!4n0x&?x!4X?74%4h99V3Dco ztIpncsovbry@R>?m}(*1yV!pkAwt|se4r2^wGbhH?^SnizLH>RUOUs860DUi{AV53 z9)M~9&)3{=F~q`c zrG4=tUsn~ZNKixk-MSEnEFKwniR;*h@)&^E%^QBwhs~>pTN5k&E%@%*mejAUqkWu0 z5#uQD3~ZNzV=mCw{8i)|7;H5J>2wA}n~8*0RBRGQhIH zuL-=|2?j(Jg!&6YIOAmL>I#uEYE`Km$?BpRncAiVXdvE2IuQ-hgbz2e>k^>3nbH;n zh$4d>Z?EBI#aRPlSLKnd-_|I`YZ~=x=rpbW-O}WsOX>dBtTg6SbKoS|*?j(~TN8&) zB|*&r(KmSbIfglq@8I0CH0aZL%*hwAE#UXL23=8kViw3?D^TunTnZY zOmh729TJ*&!q)G1I? z0Ds*K>xwsjFkx|ufN+Gsr|h7l2`EVmVYv9im4?(|$X%sLb);K7ZAN%9pwo6RKND6^ zE{u2lv>6B%257fsoleYP?Z?QW7p_QQec~YE6o>@?`M|W-)&^`$7+^^fY}5{-MMyV} zL$Z*L5fscQi)O|pYes3r#WA2HUKoyD z#-0Y{&4Ly+Lr>D+MIk~zGBAWVQv?dU6hSVaLY>X|`>jcyl zq~L=;Z-Pg7m%yiXWV8WyJ_i_R2j0bZPKM&KnJsag1Q91dlt~bD1VoVp0ZvFe;vu>e zyYaVB4LmB0Pd0}F*8;iZYltyV6AaWU~uH&#q}7+c1dg&AX!~J zqJW0-A+ZfHQ2udOuf!t_NmmEr4RnC3hphE#f#-}7vH&ENz`57#e3}9FWUxsxz|JJJ z1p{ozKn1Z_HSJ_Tbrg5m7-So#T=_SwlH z3I-MmbF8=a1fYUh23#6*)_Vw;ip1~d*Z_R^l_eX6XE0*{c5whg`USJnare+M*`XOJ zaZ4}S!9{Pv)F>y0TNHku<_yIP*6+lAr8rN3OfJX40ZqA$KRSaZI_jX}*)psx1G4&D zde8CJ;Nu4?m%T^n#1AeOqh*-SF47bV%)P|fr~zBX2cwVrzR;C+2Eo>*(|<5^VLps0 zvX4SyBU@tz$C@3!XIJWjuI2qEMKxZ;I}CeK39>mv(a_c64UoW{XCF4}Cqc#waPL~D58?`kuB)6J}x^MjE4xx>L5gGy0!%a;tS}Vf++-nWP5YU zJO~eWX~>Qyx&?*!z75#`(uV%clwtLOMkRW%Na?wpHwh5aC}V2|*q=;Fr3C2!3Uf}+ zua{#dXy;u(xW-^8iJ;>Sg6G~Wi(f?Y^1uKZ!Y3G}xMNz((EBmwo24b+8jUoCh@8q3 z?dyQu{IwhxhmylzyXoF`&)~!aKJ8NP*=xp3Y_yih6$n%V1ecD4&+@`@8Bv$W(8xpS z&>8;MiEuRlYEOXEolaePAL3>Uk8p)rkk<3?u>Q#lx3e8GB-uZ+N^=0*h5}W?liUb` zIyA?}c)1>ttEUzr(s)?FIO6Ay=phBd0!OBT!j)()a)j`64E6H_WXB_z^*cnzE^27( zdQ%7#^8%H?CGW5pm36|>h2d*S;1mr->oP<`By(On!SWa=EBa{xx8)dWTx>a96@c23 zx;!KY9$vh6E%ynx19XDd)K&o1nb}r5I~>2n=3{$VhoQnZZ9RYZYQPCEkc$NWUhpOh>yAT zG2bSx1R2LAJ3R^OZ-I6wioKz*xe6MBcP619Q9z!U4k6;>b7*hIFxdx|Fs2gKj8JW% zyVFizb;J$=pABfc3BPUbw+cQJo$Z^GuUVA8psDp(`1ts3GoB1|3=Qr|L3nQK7U2=D zjG)-19~H*^;8NC`4(?7t#CgaNTCYAUT;$$1-3(E*Cqa}!#rHH6oBz!Cq`^sTvx656 zb7*kSbGoedhPkC~c_R`u`%r3?Bz6s=JFBM>etyj`um}-|v;E&Aa(^{_%fqKcW(iBY>|XMRSHW z-!_F1qdaC~F1ikPf1AazMN*DGW+07S2{%}Z|Cc?X3wf945jO=EqDt3)&TkmS!7YIO z2Va=`_g~STo?M(hxp?a5-qQ;&jP*A*w~bTz_FcZb4>Ord1ynCd%1+xoJ$~UzOJN{~bT|*ZZU?{gvw*lTV2|2w#A?{)PGdX^qpDM@4r34*z?_kHD|8noKJxJ@F_W zMb9C!1ThgRVpSl&Eiv#wP;N@WKSV-E-{!G;D&Z#G%FaT!ueUAp+yqobu6iGkIPL? zX|l=Va>=CoiQ-Q!!Arx1XI?bSbw>Uk{MV+wo}Y5@3+9JlobW_N*tY*twxjcvua8`PEQYJ}A4_iFL8RLYe!lYh>uHe+XDUx+rzHQ;KM-C`2oB41cS+)C8Pdq}|o8Xd!J z!7$0`=fAq~d`MPl3?m#_eNQ+L90Eq#2Dil_6e3^8=fkVVR%@ISwe9?l`I1eHZ-_Ofu31c2|3YWQ$P^1VIFH z&Q86C3t7mMU!Hp6Ze}Uslxlw()}roEYAd5(BfemV5H*A9+o@a21~UUzv3ZalTR0Y9 zz44xfb=sjnRu_rm@K2%6J3CRf;)S6ZV{wR={LOt7i;I+saAPayV**Z`77cI+@hl zBW(yah6x{0Ub9Q3Zb9MP8z3m0%QxRvjMpN-mglIY_%)jpjdGe(m`s)XDB#cNLx}_j zFP=L~u`S`U&=G-tRL*ua#v3IAU^W|9X%iGHn<_5hSn;(IuG_P;2*tkid`-6Qr&Lq( zfGXR#is5`l9Pu{aL@Z)dZ$OFTzlALt)SCOpfB%7)XbR|juQK{dz$wM#@r$qpFlQS> z0?wO-K!j0}wM;qrl4&qmd@N_s7K@hBQ-kiUU1M2x6e5!`x_F8Zr_~MELSeZr9ejps z_4aKNXFL-Q482aK39L6`g`^t0KJq54brgZ7$Yg@Xvmf}kF5t5Db(ZvZMqDy|^d zX39mfLIsv->^?)sv>pNIcT4XxL?_AmD4SIF#dG`IW;m(otpvf(pcH+3DEhn{t4KiT zV!Yrhnj~03Q_GbvTb?=c|ZYp|5Q;Bh|oMi|Rxd8XvdH^Ca35@z)m zQW0+(I7B+m8Ad}8lfifM?&qFN7{0H{=s}omL9rGA$irF!_9V4Ou#EsYhQgl49{@H& zXx6{UxzsRx4Ld?kPF=57QGNz~l}98;+|k#B3g{?rKgMG*?3aj}R{JT-2I5-Xt_XBI(@#ekftD^@}u zoqaOG%=sncXf%}PZnAn=`t(A%{Tq4eWg< zKm&!;V8n`<-p7w}e@*yHhrBhHyLNIs-evoAMy%r>iRPw4D}-ZW?GaqU>pZarr{UEy zl_n*fOhD}qGY|&*J(tzsQ6gn=ps) zqoOg@?Cl=Lf=3C1`)l5}Rq#*5U4y~=VW#<&%>u>fU)~$A*C9=}fTX`PP1%E1xGhMc zJ6o`9Nj$+zj0}XxCYbZc55a>Z!3ZywufT53Ey@_*i(#&JV z3~?hITkRtRZ2t3Jszt{^^9!}?5bYOv&2w-)!j)1oS4fF`adB*6px)ef%@sOtx!KMQ zmAC$z0jvSZ1VI&9ua+MvuYn%LIC_f6#P!=MS8=iA1-84Ma;%fxb&+xGn-d1&C1``H zT3$Vg|5~V-93PfN{?i`j2^I^fH3Tnz`wqprHk3B_Rb#6p3ZWl7Z?iE?Yqb94$@R`& z&bBX({mO4jEZ4TQbY&Pr{b&ze&Odz?dGC~iWf=x4ImwCsasB?5OKcWbAQ@+ZfLHIH zdFQ28DQB~ta{2Q(+%lZlK$k^Vk;cv~P|ec27vpGzC}~^q2fep4`1_7ucxMp%ib9Bs zIOcm>gHlGUkcHgkf}yMzD-o!0?q{lRRZjHOBT*kV6ZWO=^JRCRf#0py9T8f0!6 zLWmUuB%%vm?>miX^P#~`Fk-QxlsL{*650qiIZKg^|L_|mp(02``-CR&8qy$@!E+3)@hE*C&bm=4kJgC6ig^zPxr z@hqaFo1la>3rHmaNQ{KTYIX1`)ab^`+-LFDlD1F-DpZ>ek+nU6u)C3Gd_lAchpkfJ zMwuSKAOeCi_KzT8&V20LP$QPp&=w*}3uVG%rNnHl{j#h?b%hKaP8B{*bZ<)>_(0&v z1{29pyS-JRbv}2;-G|+|^l1Ld6ksRFfK{nAqcFkzhA7T-@Z1 zByq}BIML?FE`cvrH~)izjGCz+=w>uMq_=`!mU`?@lEl|UoDHD#i(jbR#r8G@+5>@6 z`xAfer*HWS=mbOLND##>raDUv(u`D9pgd%*KHNF+aJLQeuN<-)38~o&mn`MJK!wWK zibw&FU>yV@7=o*YoWULUrb7Nkk~MS5Z(<=*IEaKAM2-r5B$4vB3Ib5|#HwX=ydmOL zPniX%49>CfMwUDXu1pS<$2tBSgAn1i#FpR;yKqTg+%>iM*S~dSfq0xZ?i~4{=BnCn z-FQXDaTcK#3xXW{QsvwRi)=w}Q=uAkD7{zkl5Mri)TS5E%w!j(B{_2O?yfOjox#d~TUBhV*8Dxfpia z`%frLp}ewfx%2Un_j-kHp!gmZ^B3DaIsFZ1{!PJ`YIQ+_l)9&IdWXgMeN?F@!4v@7 z_;XuKrK3;#VgWgON$W*~)C&jXP52W(6Sw;-Qq{k32aWQmkNLOhP=AQee~ssb0cnwV z+$o$wU&*7ACq--RMdsi_{&Cfy;*0lh@=EXv1{UA=5X%j(G*gJxh-MUV96YUN%P}rN zN|VC>15*sPRr&D`G@ipa%b;g$RetM{?j0NpDC55`DRkkN>cJB^a+DX_g1amOj_rZ* zz|s)v2qC)N#zBdiaA~|cC2X3fpDo``C|}))@~_<-$zOPXMINAocgl;qt69y#PnZ&l z8n6toS{RonIo-cXL4twTW!JFK3OudPRhy8T#7%KYDnr{LZE+A4iX96UEKa?H249}z z^3f2k4ArkZu^`9|egc$u0|2Cf8T^J^sU`6!llgdIQQpyv}QX8@7a>O?EJ=cD);ZML*lm zdq%OW9yEUT_wO^12({pK!*5IFLOUuXpUU1zMbA(%hg6)%b8ds@ydKZ_Z#@^xe=gkl zTy*BS_~CQBNTZ}dqqIk(?5#%m{6@vjM&+4C)x$Z4R4lMOy3)S{yxEoNu+b=C`M>UW9qPh`9A4GXF(%=Zlz`7k3U{03vO1 z25ku*ZArJf`RZuq74z^Fh*h>{MY(v=5HU1V0n3a+ zL(j5$0ckkV9&W=PUe6x>m>$7`9^tMY(b*pHqaM6yucTqGv}dnuOs{-FuVPoP@@%i_ zQLmb4pN3(dmS>-KOrLH+pMF=L;cVZ@qdtOYzp-Jzsb~KW^O$~%f_|&6e(TwOo1=bP z(E)qI0Y}dP=a>Q4f&urg0ngb1ucHBy=%A0`ps(kkU(BF?!C*kwVBqXv(9vM9=<86! z*I}NoBVt}h7QBw`dL1+S`p(g7Ky)b1a45lZC@E$rxnL-zYbbSgDE(-NEczzX@J+Vo zo1B<8xdm_Xy51Dbz9~9-LlGS=F&r-Q9Il8Nt|}O==^Cz^9d0-prizX<8jdu3j?x)A4q(!D?MxtW9AjK_B~b7Qmf;&Tef zkMfdoi|*x7QVNRGi%Q9qitLig?DCr2vf3wA^@X)mN<&jwV@uVu#`^k(`nvks+S>Z6 z$`>^ytwwRP8byz;60=~TVvT>ZzTdf&C?k4NpESN)#%vp-jx z{)DvdM|SK3-TU`?_R|Lra^4&iy*;QL`}=(AZ~N!Nw#m&V+F;|$-qu(BU9V^zeS@9- zZ(hD0?teY>W@xByc(niR`@zBS;kRS&>GYAY@wXFG^r>n3#LU>}()inNQ*T!%-mQ+m zTbX$K|1QUt$3M+Z&&*BFG3LH7<`$Ob7nd2!Ul+cvEU&CAt$zRdef`7opV8%`kKd2J z{5)FzvAeqQW1TgBZvNcd-rD~4>-X|F2c7E&j(~E&q>g|L4wF%ftUU|1nulb@=b- z@6qAG;otqE{k@~z-$y&!N56j_{``Kpws^2O^JjK^cXD)hwD+K^{iwC|sI}#&wfU&E z>8PdYu(j!swQOlVXnDTdT>tAu*%q~Cy{2TNv~a1kh+h6=s4{!Bo)2_Uowx9*J#`GrPpMsGey?zjbBG{HLuQ( zwl}T3r&pfs1?$}+QZo2yAU3cf7O-3K{!Lf5MyAFP@j@Mpz|FZk=&({Bz=JtQDe|i7v z6-yXF$TI*Kzds`uC0oTx9@1WA#N*867ZP}#{TC7i{i+s{L?c!g?%|W<7n7xP{1@-b zS5z&gD7UUIK2RH!UrN=Q@?T2R{Z_Sf1^E<{H&ATLzsF@;%Z=8^pzW46it za~kEi&*xsHR8(5*zu0KbaUo$tz;#qff%?QV#H?dO+j0E`>acm+l;pa-Wl`zeTrF^7 z#Bhh`>$*Udx)ioBq)7J6FdJ1ox03wMGuR`*>KwA3T)zG8Ovcl63r@sGT^V+*;=}ai z%VVcc^|vrzi$zHsfBgvKs8)|YsD8ue>}llxOs;Y^Jo3e0?G4#WShU>-R-)T;#$|(S zZR1BzODy?a0!M6BfLwzuW(FBvMurU9NGuk{`80RFXCNqP7aw3G5+CTZo+MqBvdv9qBo$T zO6uWaKE=;T`5?KNlW9&62j|bA7WKa^Bgq^GE<6uhiSedtfqovx`a$Kr%1Ndd9?~HE z*j_DReOQY75i0}!5lt+p^74hHxSyiBgUK=(E|nZH777S&Q}QPZrP)H+elkmN39A@Z?&AY2CzW}3*}dDYcsl7Ij+1S!x+Mql zPpla@xA9guksm7y>f&5-y*bK6J_+n6<6IJoOY{wt+?#^OwL3~Eb*9YZoeq3mw=I=7 zg=Ql56QtlgvGC&6ZvP@0Jgbjhv@4STDF$(x)pzy5XUVII`z59t2QNCwdYc8UtIZJ; zOWKP_k|D7k$+pkqc*3cD*Q1oku7Q%?D!xOq>>>B`@r!nawm%70W3%gjEx887V4dW# z*@P1}xgWG7NQMbq=;eb67RVz_pwcpZU1;5o*)Z0}!r0zBY!5DnLXF z#w!Y?fT@vuZdcDS)lY*v$$9fECnoKeTn{Z#(U-{28Ir){SJhWlkLkImebyhzUNo*CQODfxoY7lSpwHys5bdI}szVnff z=&Jtp96rInZNhUtPJU(Q_9XoltT?b&P5@WIxHe968Z?YYOmH-;3JKkewtHiq^WjeC zui}BNi-nh39J*177PX8-r+eTJ?rL)z%{MXg1?cL{#6?QFt1{{2H<)zp z4BNzs7wwPeY`=RYSiZVHBGGm!PJxj5m2b`pTWK&Ed1L29*PGn*v>MA?5zJ#v4a2dDgUVcHTfD!{rt@p*;x$h4>m9yf@T%nfZf z>HkR8wUL)tRNjR5y*-a|TVT}`Xi(d5u}om869a8e7`_~yD!p~sURBdKdbvG?h%d$z zP$)j5YSX4qBue}vlA$jM?q|b_*)K*qyQZCV`!|Ml~*JF@K2(m zv}&%Ck&+PUtV(JKn8LpOi-50540|r>X<;)YHFX5P@~4+CecyQ6MIE6O>CNFm36t#= zH}97$;`1JiD}sl9)ChbjU~?&8z*WL^O#;S!o3HP&i$uz$yPty3M)YqDQ^)OHhVRD9 zT(iOE>C8O>b0l%bHzO5WB=nyPc>WiMv||pizdG;D;XD0L?kEX-|L32|Qyy9r>{WJxShH8m7%!-&JUVsUNp$W;vgG^;cgyG@G!O2Yic#aasj+hnYO zMXas`cAJE;#$C53Ti^YFR*sDS2})Wg#KLs3e<`t>!Lg41iQ6FT*We%t9hDTK{GF_` z*YD|mL+U^N=p))}!AvsKBXbk=OLaRk*)HsI-{7~MGK8SGF_mVcLU3N2yeX?wkzSJCq(yjBhucf#%HkGnJV0eU-p^Ro8b z3*Rys+}_6rt~cy%{XZ0)cRW@9AIGn|T^HBPtZQGhYtMAAE$fmQ$<8dH%yi9*Y*+T) zBO%JHYhNQfqhu38NTucb^ZWb!ch2K;&iTAP@7MFGi%QH+j_5N!EOi$3#}y8m6!ao0 zRu!u;O7wGVTi-B~6bAO7)MG4>U5OD9pUQs5aDrm=*CQSSVj1F7{gu+rh^gOwQ@^9q zzEHqk1Y3a;Q<+2`oXQlRDjuA6Iruzv9~*o1vjbOz*s?<^$8Z|6XquRQ8mv8y zw>_0MhY^&W#-L2bc|ygyCABax?7*!TCcox%Glu33NM($zq>0~V{ira_KWG-z=_v%+-M# zWu-yD2iJSym<2QCJ7r0%WQ^k@h@6&$XTZ(mW^;Q$>Ps1g6kk)p;b0DVEK~oj=4sKL zEC>!{YK;mOb&*4+$zRu!s7KMUStKvHLnr|#Mq47WqVSavt1nf$= zRw^J$bk3?YLC5m-t;)F+)8g~9OZ5O)0)U<+IMtapWAj(~W_;>KeBq^E3`dj5lYXXp z+{IPKGc4&wP83^wCd04H&%vokkBBWaeM1{lNh37xi2mDZH1}fau0HwFa1o5Nkg22S z8=!9QW9esE5}|rnPHjF|Mn@?!hQUGN!pw zJ5nCc4Z=jWR-UK#%1zp!)CJx5^knA1asf7~NWOw$7Sq8+I@O2rQ~}gndr24#2AT!N z45zV&q-kwcJBfm85kz48kgqSH z4Gz|1;mr1FI!7|ZX46B@O>HvnV)#}jbrl}Jm&Is))i(r^SB1~llyy%)>E9^h6?$BX z6_0JsfnFf$@G2%{2Num9$dtd zK(^y%EXz%03W=HYY(>x@wqG$ocAmSAX0R)fnQzp6wkZjqikg`RlJ5AOO~MS ze?c)Gq6(`*E|&f)tWD9oBaS4ZQZAaVfzZ+5i)dI??5IKE1D>RH-rW6d%qWg3X*5@} zFt>Y!kWh)f;|%G9HC9bu%S$h>KcaPUB{(0^evPlFClF5HP0hMWWzTHX9(MjY55eS2 zVig||6kL<)e6LUDU{)Sk6D+#Ww)9|LrAUWzY_veOaZwqC{`i&3E#!|OceW0CcRDDADh>oR9>^(s0Uj! zf~XAJP-e4K@I`9JfXJu|>HSR`%U*LaO~!D)7=C$*)>yYlII(t9pOIaSWJ{M()ltt7 z%%F#c%yb|wlfe6wqBCNTzgJI`SDW1*hAeKz{Z)D|K>H(n_~d7=yWg#&^pxmX@(-A0 z>{4rhC2D!hh~yZhI}XrXhpuP4S=U2C`O9d#nOi^+Lr~Mk=;?65Z@BaJ!Ai)KRTx<- zKd>9ZMAwZ|*-EEPM#f8R$j}-n=3+f22`!JSehP9pZOKO+Y}TfP z*{@R}ahlip)F+ zcJ*RQV&<&DG!MKMRrN%;1in~gt>C|dpFmubL zaUxPnhYH}vZP6w`sbkG2T@Np0rIPn&)kuuSM{ABBKzR_b&)e-p=AU z$c@4n7;_igc|3UM9io}gTEeNIZO48z$FPv!{waj4l>g587lZ#lrhm`+ZG#p#|1yML zi)N+4?C#H9@HQ`qd@?T)yJKy%%g^_H{q?Thn_L*7r5OS9YUdt7tlwMP6NmExMf2V% zKl`ni%>O}O=L47~SugejhvZAeBow9b=0FWfdt=e>7D|Y|$>5a@hg{_YC{}r+Gb?fp z1cur)LXbwQKqj|B`to|z%d55?E2OflX*ve5VblIBtmISNH1=C>&0u#6sA)8cpRW8H zHlK|tJy&ydM)rnf;@jO};sgJeAI5}g+s}7)dq|HN60nPxj-g(@nOr<;Q#_19)OnsX zzu2Um)brHoqx-Udp@ziOw8Dj`h}*Ao3M$I9C7!py1=L#GAW?c1ug%sYK_h!#vJLyo z;!9ob;1v7Ka~`P~Uh>(-ac_X>n%6@poef`rc*N5d*Qm$h*X%|2t7JQj19u)nidMz@ zpDS~0I3<=ov!vXRy@Aq5u7tH9%nJ=50~O#1mA0&drtPhlVaqVS_ZH`$?q1&bbmpr6 za@zjd*iO>d1FAa~yg8EC|F1n=@>i;_DzR;34sclewHq--Jj!NR{Y-$guu{CU*nwmcM@>g}2(kl)29gc;puy zQi@Ge1vAA*NmU1Ei636{gMzwFq{csc-OCbkJrB1}n8+d;8Qe zc6h9aHhI+}c4ZnqMQew8d;v~(TlI+3{eJ57C@1E8#|dg75{yn}SLpw}zaCuERhlI6;dVjpE zQ@?#P#jb`~*sa>o?UmjCk(%Q&dj8vT{@SBAYZq~R_8&3RU4BuNw4efP# zY8!Cs<)D@M`?f}{ni)lmD-il(xAVJ8Bg4$CjvRVp=&$JHD?R8BJm$F``540TwzX}(Ez}aDx3T|zf4cdmwq|g!!1nb$_s2f-u8{jb zkCs+E|I;b7`{magCSc#~$Yg+qOG$-mQ4wp7bz_lwy~0}k2gD|_$#?B>L*9P1ax z{I*8eb(3-TdPH^9^%DMScI;`ZHc>wuO7zI3O{o3*oAEV4N}W@J67`0%cdfqdqlSv* zU>h*8N3MwhBMuF@|5R5=rJC+nqXRWT3T@N)beFPz*elLsQ*+4(L%v@Ol{NIqG$izv zBJ$cm8+79RXbGH6Kee|~tbTQZt|HPqfv&lhpnN(R6ud zAlj!_1zFGc8)_$QYo3v!cegSm8+U*M8`%Oa1WmfKQTdrOni5l8{Mlz-ohv@GMM2Ap zBs0`9XHr|xk#bckKC@FR*Z7+D_n9Du$8ni)W-;<}fqNJi9SwtamjY|&e{L!&HV}mc zhh2UFq#PtvFcEt?CR*xr`FH=dLrb-j1PPwCn|iKZYfp_Wd5$BWO17Z{G617H8iS<% z#$Gy^-cK4`SoAI=JJVNeu4LncH<8VV{4csew|~cpPO|N&G|`g&%K#I$pZ6!7?3s)J zGDde`H;uG$u>MpAJvN*fs4VPEwoqr%lq%4m?RyvX*~hXpY2aHB!D{5F*P)$fw*q+* ze$Im7=(VP4#+F z8}o58rgNhfWF9(a$Iq328b3INelCJByGytITfxHrbN_tv(fJ;Fk-z#^cOLsA})#T$)g(qU<8bY?o8l5do_havbclO5>0{=aS)Zeom2~~a)&06EjUPY;cQ$c zoNUCLy4uagKAmcGBk8ZN3_|f?l2iqpAe^iLWk~QP(D-S4GGrHtCr(7s)j9mc?R3Qf z`jYD?x!{{1{ereVEVGOdjea~P*#+fZDX}GX`7G6_L7!}|VfxeI{MXwG9$&vN54QdQ z`ziliQBN2}2R48I%)Ggt!gg${Es+mH{!C(yu38X!XqS0IE5c8QS!2a41RraBeve5H3kx6Fg#7Egs)VN-a>hFwNm<0H3e{?G7Th1 z%OughQ){rUv*Fhb)aS7G-j+@Y?0S%#$|L|(fN+M4ZP2iB*t@AcR2AgddmPkK&1x|) z&BxD2dj#I&W24RAY0A)lj+{0b1iYzQIL?@%73owX3zXmbM*jP81-`3Gtt^+jQq8`()P#WhuSy z?**YTOX>=JeRQ~D*>QOz_d_P-2C>1a{p#mFzuHpHMQ#yEZ(5&UQ4GNt!%sTeeo64C zg1Ulue$phG{a2am!F&HUM()jbyq3`C z8d^l1XSSs0b4|v}UfFE2Vm3d1_IS6hhHa@yl-}ZqiaCDv6HLF=Cp^?B=zZ)6{<9!1 z@qYYvtelP9QYRH|RUznu**n_hSk(YLp#RRQvk{T2B>-ieTIIXz?;IiAoc8LND&ryC z7cIE?ick=@l;Rwf!Xr!x6fqVBmSVVM4o9TBr(Svj1CVR09K*#7)wQ&>Ipda03g3wL z%3FQhH{~?c4NHX+c$#9wvT35+gvw(Ie%gc1WtA33xa(~)ZuThYT2JhS2bRpLj$BoI zq`b`H>p$yr)rMU1!Z9@g-`wgGd-L-^bp^?7je{_B7S$g9Wz6L)0ua91x7d$2Y9#P_ z6HUKf#N4aX2~DVRuTxIDw`})rqRzP2 z-0jsiAYE%|KV-!|UAqzbz+HXw!jxq82}#SmRS)HTCRojFdknmfV8_h_L+gSH%MIMu}Gre)fkV`hBAx-VNJf9K^eA{IOQP zw_}>J>|6K_Kg50g{5XZ|Cv~|+k*EADEp#YMlRzS=m-w&4v*g^bTV-EzrW5+H6S(qc zMa0}7yk8a`RWwSYaqK)@ZN_Iw0UlbvtrJJJCCL10;bwoQs(0|`J?htac@B&VM5Kr| zWqlw$o4)n|@eIJ399hZ-)&qoPBg2kbf`SBw>WG`uG81iT)NIl+K{X;2zS_rayhh@Q zB#u&HdA7~}h02S4w$;MwU}MVpa-^W)W#-z4c79&J3Mm{eDND? zLte=6HsV`O6{>HKWwiWz6;}GP(lupeavgx_DG3Y!fOZC~LXk@+S2{;?*Rm4>gRY5= z<$+O6=#1WeJm7{QWxiPSoICNdW~7B-6aSa0TT9nIWs@GE%FW5TG{0q^Xfjy+((oe> zJ>JySd{DJ!AXGm7r zV30d32Hc(9nXk#JXIjo;T3eI^r^59|s>wGTX;D7Fmo;`J`hN+5t+UJ;D6+WAq`| z@i6hkx3l9*Z4F7^Zot__tON^6%3y&Dq$fK(A!jfH&cc*FQelSpwh~kgLkhtSP5Z*= zCI>e@kd@?aOs|p!R~vqS%@Fj{e3?TgE)(dAjGuoCF3WVVfV$_M-;SrAE5R3FVHdni zO2a&*eg^f-UGF-L7GT}66<{s1UG`ky9qs09(lx{@$Bp{$H)|%NmbIs| zl#LsLD?9w^@|-aX58}@qg@FLXwS45Pcv5ODsm(Uom>8vqF<+0K-ineR4eAE_4zfr* z5A7gMtP>W9vB!2VlF)dYJOfk|apFv~uVj`NLJ8VolY2Pp{eI48YtF}CNLGkm+Eard zUd_X0H3Vq-kV69NH4GNF1#}_*(Xl%?(6@&nQ2+qugGJBz@VxL}%_qfDBTH8H`FXbT znnRP5FnA3yy=|~bW~dsV&}?Kcc|60Bo5(EA^CP3bx2b)zxnW@^(`0{+ zY_XW>YV);}F0`U0^taJR^P!cc32K+zdO)?XFA(O;pp_jPdWOutsRK}|39bf++>*Ij zQ05srFL5xu()Rw#2%nW~wVX!&gc2?ch3TBNDRG901Oa#HAX-YKr7y@?(Sqro=@25N z^&dB~+mh_P*wOm2bKqlp#NyLjJ``XwwU_kh$kzQ|i6=`Lb2pEmzk&Ddn2})RyDStC zM^Yd`2h^7M20t`1ndoN?(u6;=jY-t~J9xL#>fDFSx4xv5Z}9fxFHx802xCGd-GPAh zMu|>~+WPUpbSmkQd!#(|;|gSXm2J5{J6a#Bu>9ctMDKKPH7svt!m(4~v7dnemuCAZ zDeQI!3_!$o1E4V``?-W|Ow4+B^QWD};Kl`NHj=5k`tcDg1R$-zWj8IEG^l1wVXfgl zL29;Y`96pJ;avu>uhQ7t(0!y{e=d1>Lbh2|*<4u3B|d2*(jAeE zT;GJiSGF1*mpBU3=?nKyB(rJ(-Au0@$5|VDXg#PGV6lwMS6Q+DJ6npJ$mLqcv2Wtf z4Tb1O{_$$9y}X9fTPgUxY`_P@A1!WKgG5%T%(Hh2(qYPvH#55KEEar(^u2OCB)?-()_s;_ zx@r7=C19W=U|?2HE8Jf)_v$_-$R)~U!cLuiI{B4yKt7C&( zE34Lqn%r+Oh$Yd>I>%A=M@{Z>W`W(8UWNVgWS-l*UkH7A0%qPX24N<1d;O`+uZ6vG zHN0vUB-;k}`+n?CK;6$p^&p_&)Qj%*0r>~-N<06i==Jwhj+eg`PSQBKZCL{nu_jrVuRa=c zS=k*h_CV$$crl=u{_yvUDwz{U{8!U&CcLbkL^t1dg{j54dP_otP<>hANgrL8!=>n> zH(i1$2YXV7K*b}#Aw*|^dRjUDG}rT8&_O~zrFL61Mx9Im#Cl9t-TC%)>g-;`I~ils z=zHp{mPC-Cdn8H6ZO@GLDzkjU@_qT`J3ae)L)o#JxS6=s=;T3t3(k(ta*ywC$OEd> zp);uFYBk8}{6y%jtwT_h=Fv3o!E>EW@?@Jd;`7JBYUCtptt4LO9}kQh51J%-sgrM}0u9b$p^Vj2#lAVYb~aDHmH5<%A|#_v z5>@WOf|Q`@wvf971LHN{5Y&Rz&C%5dR{stXXGUQ`?y*nYPE19dP0%Srx#pzx|@*OfqjEXmaP?D3QRhnTbQ`-yfb zJR;fPyQDaIl%Oz%BzB(^dle?0hm3@sg?~lH!Gio(%K|a5Tbe+XxLaFrh{$SC_$B`6 zm7jBO$mFZA(KKB8#IGSru>a24y{l(_)+Aw7lK9AhOEI^NFYtDoWD9qYhwL}x*Kh&eBAmZs-i9W^`%40`1}QJ z;G%sD-ujQ=cHJF;Oof*6Z)cCe+1t~QENbga%x-H3X8^Q z#W~BW$M(b| zHB|%kM2RE%#ZmM(Qt)e*C!)lt8x&e?rT^|N|HUsvhtm8TaDr&XZDm2>D!xz#y8+Ml zVrt+u9t|pDrdI`S6;mp^lim~0rRcZ6)3i~E2htgBvK~9UFr!=Z&JA)eNscdIpB`?z zf$q^~5$97;YMLJ^z7lay&0QZ+7Ek6kK5a3Z?Z?y6F>RSw5kyLEz4kje-}^4U(C9Rj zF6s3{;zNt)e6!D&ACgOLexKib*Pj*9?Q*t}KPp$e`Y9RqxLK?udZ*Stju%*XHt)7t z>JWO(o(-QiIFR_(lD#wAJzl6l753ghxoMMHD^N6N{p)b@UFw}D?GLmKG&A-tXgKn&(z76AYRi+4&BB*b?3lg|%wEa~i9gQ`lL zLoR^-sT3l{#iO?gi1ZB-Rk)Pi79&(a%DJeQVC(HZ=j%{7ZjK~YKX6$yQ8W%J&IUIF z^RwfB!N;Cm4~e#xsONAdxYF>qRc3t}$Pp;^VFKX5=;?|qIsm}oPVu@v00+3n$z@;q zR3T(HtlqGUri$yRY%I3nUwpwcTdDXk`D`Wmz-GUMwBCB{JRAHH zL6ga`@<&9K>#N}ET06I@_ZjLc^K|(N+OMaoIe+;^F?p$HTgN6Y0lb7-`L*KcS3Wqv ztTUWC?hzoE4z0M5hcd*{`;AZc#RSRjfb58I+ppa;6A;$(>zo{6zDgC6ihHRVYpbBb z=N=XJav~>Dn#kr#)v6}0_3ys+DQWFZIYZ&(KBO$G;|`4T2;|c0Jfiy{oZI7w#`@W+ zgA_wHxtChErD6EYL#^Kd?9_7ZqKA~7#Kkvrx8p(dvJ^ClVl%OI?_$Rmy#W-;t!}lG zile_@>?j_>zvz>vO@?w3z9HqN4MCpG(jvApS>5LE3YOQ66A7Z3W2sH6w@qm`wJ3y7 zF9=U7_SiDzOj_c(vGs<^a+7M#GOfJ{>XMPyo0xw}-x6*}Ta)fO>P0r+m<||GU8*cF zNyj?H_vih4Zy=#Efx2fJHDIPMq}fl%&<*MMcdn)@E~XL@2b1Je09=%_A6u(n5EOvm zR#5lC2mdGMRzohu5ij4VZX&aDm1mHTMpwHNWkcx{qL8&^%4tH_i0mJ{qs-$|>>4U~ z+Cy@$NQEA!u=RuZ`o#KxI*OLix~>vU+OU)no%S~(Gj4j#gN+>L5bL6uZQ-lI0_-h* z(ySQ|{eXAnNO(6E3Cees0AbF)#Yq=VU8Vlg;+#;5b(5LJx?weCzi7r@$SatN1A5_d z96*TG)J4S?OOw~J)1q8dsQ+;C>*Kq1jZJtj9w*OhK* zBCF<=%JNG@00ysBQat~&A4YwNIbRC}T)2ib1N8JnZ=^l#+SDn>OGG^`&bSg6%XqDZ z=I)WeJubkISYiwENx#qIFV=%%&(?;`JRNxJ$0)F!*WE^E4zSjbG}w3tK4XqGsKv*K zOYzh3SB@ND%8eJQ3v3imF`bFWY7f#L7llSTA{ab!nS4#GE4RI!qxuf<6`i;bxHHES&|23YR9@beuf9;tQ3FYmKr-kt~9#nh$!#sKS2#elSUC5ZkOt!(0y>V>RU*^ z)L2s`mmFn)uv|qBNErZOy?!Rbh)Zj+2nr~cg#-D$BW0AqB~V#P4~m1S&tmi9JW*5c zq+fs1n2gAn$hZvPB2ZCmPC%@gxjnA|yC{+w073U~-Zozx1)^W(KHQgMsJumQ7$x&= zmE3cS^ED%2fV0_W3zqHpF{;(?@q&VukL4TR{ZQgkE4;`}G=pU5akN3MQl z;NgjKFiK<_+3|rE$ED7nu)k{jPLeYp)xY^_4*f;RdUWn5{pVuPP*c)J70Wdw=LUPc ztu%Dx5Su1CMuCredKXkq8g*pLd}9&-ZLQQ2QcJ5Kgnfsl7b6=}baFDcam+R3z5${yZIQJ` zu(4MZ@FS&@?vZN5nhspJUJYVg@5ExN#~H5~lj=g?ddRQ~kwLy=$Mk>7ciDT7tkXD0pWH(_T2afeMQhbL)#>!s z7bs`XqxPWSx?ZK5YkLW@(Od~QFy?|$8hA7uKHzfaV6DQVT#rp?Fg}!oiG(UFXo(DZ zP~z+5;EyKon$-gdnp#gTbY8-j&+F>qeWk5KzMW}Rn?Q+^NhN(^iOY4ZNDEP&t2~;c z#b%@6939rNQN#XP529SZ{ZjPuo(mKs_ioeX6Qk1Lhx1`PD-zFi(J?>8&E}Jt&IWYP zGDX4$#n2k3HRj(Pjhu=NQL~1azr^pY`uQHwd`k3};k``jcrLBHZQ3!s;0VCmB&c2w zBpF<6XEcuFW?Raomr>U@3|tJ6=vjE2guPTvNYjB54O^vsI2*pIDEBZP)me24LJ zE0d?OjAJ-{Z0sG!_pg+VvX#N_dHX>F<62?ae=0J(qBWS>SPsB^8g?2pN`t5|;xDD4 zjq(xFcj9e9DC%;g(0-vfN{3!@U2D@+zFkLDZ9VI;jr?;m&w}>VHX4K5dP__3n($TW zE=MQ_T5buc(PC)IOGr7^q*i1z^F`OK4V>3L?knJ7*YGZGo<$C!!K@e7>v|w+53PaK zXwtt#cQ2a0i^4%Wqz}2GkspcpJ)h-BPuK*|ciDI~_8_$)KD`G!>1EG2BtA*XPzhP9 zXp9u0#IbNNCoULx!pmdjC<0r07(qczDKm~*1gBqrr8};`MN6jtoosa>ckkMlW0*$y zSh(*Hp0)SRW2c#S#J5IT^s@jobBym45@kTR>5Cj{kv88}Z0lBGVGh}Duj~3H1#epXpbK!Zw_6kqp=;L}b8Y2l%nmoXOzy~}cKA!LaXL`9} zYM}>@<>YSEm#UAv=9a$>I7e$#r$A4gXfC6r=$)ZwQPRjkLsy&B1;ozeT9ed0Ge{|$~d$L0Q1>T z-9%ezRLoA$)Pr9 z9QvZ(z(UKrWn|*r_&7~2+$9A^*GU8BRlPD#SgG4P#p3Lqv#7NC-byNm)c1A#DTh=E zNF_U65e=GnOp(Fv%2Dkk_4x?-tW5nqtll;0H9bnl0PgY#wQ1r7nefTOc}D7cyu-Gf zQN%e<8_lHwB9FI5+;JtkUW12R=KozpV*yWFPUMq-DlFo-412F(HQ%1dw_=N%;NnjPLo5U>3AM_20%OIMIC3+_g^59 zdJZdk@*Y}eE*0vsj$}j3Yycf%JMmUyjiim2&b8|$5ej>8oKKD$h@8u`Q zHGk3-!6dL^89p^cYL3Lk?Mnhq4_4gh#l4x+rc5O5(AC>^PSKhp%^H=hW^$~FRn(>5 zf8)gobx+u=P#9D0#EhsZN=v%XZmIZwKkkZC9QT>?g9@*!*vRW{+)Qzo24|z_qjvRkoi^CwXBG*Yt|pz@Z5rzlNqho);b0fI6jA=?*a&)8T`St#ECL! zYyjdI#V9Bvp(%@+cX zNE3U7&!jEsbuj%jmv`15MQU8uir_*Lyb!!sbr>w7)qF))#@tZr90S*2ZKUA~(-7OJlD3QF)r#P; z24eJ19u`N-R3EeHO3T2bWVEEE!(?T7qNK4?G62m{oF+(EbI*Ion=49oX4-vl>i6;V+l0U* zHAd+dO`Rs!eYIe@ZaV(u3I7F5rq7-?T~o;k1fM=>jL#s@xlXRGwwYMyPM=rEu7XeP zKGF7R8Htq$(n25y@)I^4JDX#}ma0_!hTijoBCi(d`>eV);;nHMnsTH&Y*1SZNMrzi zFM~7)_QcU;E8N|H`?=@I8SCtuGME%;uUb!9qX+q0@Z61frhKyZWqtP*1(KFL)zuSP zt*P{vH9&9Bob*Vi@zHJg_&q&iFaMNI_`OhM@7+5;byy$JM8gAN0QXSEpDnR&sMp@I zqtS9l^-JTSDIe!5#^{P8wgjopiVts>KYQvylv-ExIDNQY{nP%wL8v%GWzo(CpBVcfF;q$mh6R>pgU#a&C z?fQS%hJAnPPyMJg>U0EGIaUgD4tAhGx$tdwQ9+SUentEYB5%MklLk-ohk`Ue$6h*) zT7g|w`p|JwePWNf25>dmc?%+V40`PVNVaKY;#<_r43 z<}Yp>qNGW;;*LtWBH}?xd##IoxK%ud{S8te@}W{k&}p!9w({_qA!43%D2J;vHGaQ{Hf=*2EA8Sojmfp$0&QQB2eZthxri#6{NY6}-@?m{2Vb z?271vQ17S>XLSu1sl{0>n}D3`c4ACa!+K{VMR@)Ocd3o6sEvQ_8t-ImeNp7urrh)` z)MW=U`L%26%C+e~s`t>!Z|Z@}U?L#@Pn9?x5EK$b?gW5crte>y5A1Hb+cu}09Gw{2 z@}<*RIuu}SMmRgC@|eB$me6U*XrG_B_G!Mm*92HD*H8Knw)!um>03zHrM8ui*VZn* zSu-g&NsR=6DS6jB#vFnxL4ckoAywi^K2>)sVU*1)>YoGOd@f@YXFUe=r`&tn!`ud- z)x&`}a2MXLbvhydMWm6yfeit)I{@ZceDI&4@~3TqL+vd~1N_c0>A_!JQ|>!2vQ2tR0semMfWLX zYr+!&5G^8*g9zZDfFEO-A&7M z(}XQL$R0PVOiDBkEIcVAP!Lj!L;CQ;E3fwydluD4-tt~^)JO8VJ@^O!OFoYoD*#te z9eCWJvTFtd&=el-wBA-WJKXbID?GL}X&2{DY-<>GJli082 z26)T_o3Q!u5pj{IPaRI&Ui97vo=#IL!l6o%w|oT{F#RF9ZAO++P!tD&(&N=^@A2`? z^Slo07YQ$dK~hV&2VYluNSCe`h6R87Jo;6;-6M$x$k680nOxv~`1?nbmjE}g{5%?8 zJV|#T_+u$5<;?(V-`94~i@w{lM7>Erps<+Q z5xBiKXDYc7&&mW?vwm>J^%eXuV-&Is`9&ZBbmZu`?-?3SQCV!m9w;lhbxjS6lq8ys zh}H!7wSszw-QMgb@5@N~RL;D}^%-MwAmY83nr;+K+ii_V#A`h@xVl?DUMD>&2r!B` zy)`p&ord0g691p~jF2c?$$f(_^*G5b z5(d&qt}_-kKJVXKId<0>S>im10Dp&0o$F@7t!{4?`={>#m=iqoZ{khPYh5!5-UAQo zb%Vb%zvX{ErDM&UDE*_{+4*4ZC%J@NG_~KF&Qs(IqRV)`M251%zMH+y=R;5Nnil9mce#0j-(!Q z!|N@z71p=FQ-0DLNo@BPx3V0Q7crLDG{7jtD4IhtBPHy#-lq#u0=V>hsbxEF=)^NG zooP1ba|`D253a>=gpGTt>-eoN&)Xj@rbGGL#<{$=U1s0J2fO{&^Fuhqf0P%e$y=%7 z+me(lc9l)z0o~a7Agk$7zw46~GW$x1n?~28xS!>T$5A#EsPkgzT;wZ3co5>}TFJwx z_~RtkTTt3az_g#XeVFn=ZaH`I#qcDHV^7Y?zfd zd&}>d7kXFu2_$p;ErR`N(blGnur8ez% zjyE|h^OMKkz&Vet6_2p%%Fiwnf`ntd@M6DCX`_~qL{mpre<=%03vEcXXv^0tWvO$H z!GhDT&ksl2&gQWR19wW6MJJUqH(35UHFq*vlrmok*1s?eA@sc?bwYza2gt7QJ-K@Ewe6ug@tc_*1<%>Lx_Jj08k&m`Db!0UjsHOawBxT~R?lSQaQi1wAf~+#w2!th$#iX2=A%dk5UDj=I{vO8`iS0pITG8oPml}0f z$6V2!r{=KoL#4AL=uGr9bPkzC;#GOYy?rBDvzdI!Ut-W^sAv`iO|IP?0IVyG)dAPX z{qMr1{%ozyLTMvseqUGC&jZAQ20oNp)IvPM;?xti1*Nc*>BLR7p(QA{sA^7U$jrd! zAPD!S(hR5Vx^YmrkoJk%WWRgago3b6$!QbxT=}$RyfiU2ihWk-ZzKW8;ynw;tVPhu zB>?3)Tv6iIJ%Yh)31+Ls5Mio|fGR$Uy=4}hFuQGJY=(HCgO98S#M1lW$`+-~A|qL- z;*4og9Fu@7&8ex6Izd{rCq#%aK;!VV>TPB&08wf?DBrV}G?0LW_)ZG6gK&A}G6&>#LxB8AuI5r=APd6IT>nUMDh)|Tk~iwzTM`YZ%R zV!6lrK=`IR4Z{2gs8U=Ge{0l3cYZj@{A+l;THC@Rg*ep{0Wb4a$kn2?T;(%kKM)kF zu7TVq_4NAu5b`b-r>E78;w1A2NW~w%^82EEIbJ49SfbY6&DY>xu-@yZ-YnP;wtXzq zuLGX46!6q1q+2!cv-5s@X1KIEZ4h_J;bTOCDFKqpwaP%3j|OFDLfSlhi$NpS5ZOZI zq`piih%luOW90~DnazBapN5uU#{$6*YiN+x01$?d^!S}H5Q&w64D!XI>-VYW{nZyWnPBj6EAYs{*}6zCvATZH2Q+&IQ0OC{_^Wpx?&IQD`lMIsC}XR!y9d#K#KB`5^x! zHLxpT@m$G4NSE1FNCAAH&;&1F6Ya#5fsMcQD>1Pq$cd@MT}TF-1~<;{{vndN@QFiH|3ovI&*LPsLKDX>SlUrZA>#GU*TEjLE>BkyC3K z^_~Q0b0_8(%TNE_ii~15Eb;GGikFv9BcJRHbOr+6xx4Ef7Joi~-487`@732+`p#^GF#gOYsV z#Vp4$W)t^cikDm$88iHkZTdw?K;=z<`+QJGT3G`}tt^hllF>q~b^Lp;>FGGBnugwq z5M?B|{#C9TFM>T&!ZbQSBz(IzxZeVmtCMxFeW0=W{u#t#SmKPc#v=?V`t1AiQQBu+ zh<#KHn_35?Ejm)f$~ST|T56) zcV=`5mg$UBqV<{dLWF_R0}xl2Lyh`EbdrK}6c@OVS*>vkSxS(*GHV8HZNa1bYVFT? zE&^(Um`GZ$X4;h(4$N|^h#iBvHlkjW6~#c!PBq z7BP7zu5mA!u-C6aJK!xXSbSKBQmvk(vQrS;o~>^*=(fCIUK-4^UQlmzyr%=y1r5{c z5hkudaGqrfH_8+cnTeirmc@~ld`xz=UrtLQT~DEpF0=wfh=SwQ59bc^Zr)`WX^7H2 zwsjmtZ5VurHZm?{#(6^gR-qb<2*lkv4MvD3k=Y1cjdY!7rQJ{~sWn`M_!2>%90H0d zU|)1y@71>_bVqKhFeei8;C*Ni0A}w1y@!sl>|y!c$oWki=8mp@H3h9?goQi&t-l)8 z@BnI$hCM>R-7GeFR41fVGSF2wU`#~W0-_`w%j}rgO#na(G1v_N(;XsIp_cx4KRt>G z)h*Qs7*V_eZUd&OH zpbN&AO&Y)s8bxM7a8?I+CQLP`49@8Q+}=ueKGV9 zjc_MI7tpAeH-r@;m;ka^P)4MR%l{}k_i!fv|Bv50AK2P#&WAR~Ii$(4NZX8@&H0ct zhjK_Yl0<1I%&A6*P$P0kML8CIM&wWmNjgtSluBove1H4>w`+gx+I8Re`+h&)&)4Iz z(IxUcl($_3z(i65jS+orzgn^s`XgbZoL|k|3xm$7+122*+Ge&yZi-!(6jGD5#RV&O zsf0z%1h5f?ifa0iaO%24*(W(v0-O>_a^PV+CEw)_=^$s#tXE=!@8efq;%V3axiDN=t>|D>lByGNh+41hsXlpXJH^I>3EGK9*~ z`2zN@FtEN4u97vZznLVz+70YU94jBBMuSSwM!dO+d1)<($qg1=9?<}_F3-LFCeSKK z9Ot*7jwgZ(?rM#=ypu+5Z&<#wG6IAc>e~vP$<8(rC8JXYC-;9FY1}iORsy<99v{?o z6(o<5c54<`IR}=w)JoLjrPzghqZEDV48q`*6uJkPXdc5&pI4b>Blb(+$&&hInL#EA zc9&rA;=O_SfgcgClrl+(1R1=*ODmYCQkkHT~2RM6q=xINN2%J!{ccQL;c zTFl8v+;{kX8mzd@AZ+=Ueh%&%!C)SMr2>aTB9SWXq4wFhza=kMV>UgIB~w$3-Oau1 z0@QVp%s*2|Z?122Z8Ngp@K*bO(?Xz|A0XNfEogD>sdN9XJbniE@q}l`;D8o%#`rx` zlfeen#gLXuH?-XfzWxRE(^~U)X%uMY16E}e``Sja43tQWe2ueL>Ga{4zfGti?3b2h zlZfe;icZMji9l$)N@$W4lislEcoIKFgQdy(15(eg*}2gbN>YO65P4-qX)&xwaKHH| zE|BXR@4MY5^7fb;%$?gy=|7eF0V*{9=E+5-lXJYm0hl-X(;h`BOdOl^Qw3qbmBG+t zub@%_bwA0Ryuuncu*p~cawiKOg-ic_&}ug+XyX)id-5_3#v&Elq11B<>0T10RcP4H zgGhJwmrZfXx``)4YKAD0+a;yG4`McLcQ>R4DDQSN@_tnjvcd^iITYLvi^NI87`LB2 zWQFD7#3>O*3CfF7fb@eY+OL(K2)-BP*)o^r%w|K%K(|3IyNQc=iJ)GdM@BInDhb>i zvx9#)?LVejdrjI&+arDaBZwK(8MC!?Rg%l83+Zpo!MD9LdLA9#+MsGeMm#Cf%8~t% z5)IrzDi}Q8`Wd!x`=5+<%Y`vFO?i;wUI(3`HtO{o|vfi(ZPCkNQT zS$WFgk%8Ki>3g{F>Cw1N6scf<8yO& zgef|IIBgtG1J`CP4y^IOeRx0WLD`jSyYn@2c%qIG^L;?vb@AV%$ z7q%2vw|}@Dd8+#7sbO--Fu!CnaV)#l+wVx}`o{);v2Z@{GMNoON>fU8B@*fU>QFv@ zlo4P1gC(~jN%6sSA~D6$qaTZ$#FkxDwOW^B`_q8=U`Nd%*l%|w5uomzWBrg#oYCV6 zWH);~szYiJo-)MW!ue+gUsBN@UfUn0*f%wZW3gdZowM@*^@nvsN{jka-Kw}b zXaLQ74KW}W#T}$~8K7&RKfW5Az$5PNJ6W^TIcRkkl_T=<;ra+*MzOb%hGhIn)0Z-)eE~VurGt~BT zPYrzM?=(SjrQP9Ui1bJTF8RDD6*llNQwgM&qf%F%pd5l%&jk>)by+*4*rOzv_ar=< z)RAGya|c;^k%~7>)VtsbLHC>UNFB=G)}GYiY~B^@V1#mH>NQ-XGztFW9d_Du4N)NJ z+WZs;WneE%mL=vQ8k0#lGCV>G7Xj!32_kU`YZlqNSAt0=V z#hvv7_s}gWqouG`RafHt zV2jrEnqmFN8jap&S3qs&4r_JRxbF_oWT(XI-tb1tu=5=b7aUrRf-YUD0$n|Nr|9mT zeVgxA2RO37nYIRBMI9P{{5I@E20WQdP?>}OrNZ5x+9eL&k7^QrT$A2dIHhxh{fJmn zZ*JU3_l2Qhg?A);J9_B%GR+!c#ZE5+u;(&9F2Y-kU)jL?!(5 zC1vz0SzYO&pM<3Yc(Zo6A1NS`k1Ijn%m5xQY{$)9$vub1f86fymGe7_gkYf!;B$yC zSN}zE5sXr$n@?Bl%+ci=p7tC@+nDr3#VSvceke{tz2zIstyn`UjBSqi*oHBwfpwQ5 zL;A7JCa^MVVgU)Jv+uT6@#SSecKDJ7Dx$pXq0@dDRBjC_0o}^%eG@U@7fjPU6s2)} zsbvdosB=i&ZVh&>X5)E@?YYK2Z+d8me4WZ~sd;9%R?G3%y==*7rw(6tj0OKJf6t48Fp$4dt@Pit&7 z0{$)J8Qu&5;h)j43tyjiyg#(OEKH}XtVl4x^^bTm_V3dqyWynleFSJf23n)^v5YfC zf?eJ$LesHpFOIAAW0xhkN1DQoWUZqHwHl!FwshFPWc~GD&y6^55Wz z=>8S!Ior^yA4@$j>4c=WZ=dfS=-s6Ac3-ng3`3)ZJQ7(;OmM^kv7`wJ)C&Lh&P_vo z;8K0WrHgaX+u52kidxk7!^zWS|9*j@N~Jugf`)^LS~HNPsJZ1R(xR5e-so9}pY^D{ zU8rR*Z-^vh=NfD5YwiAqpC=N`?37~+s3mAZvfq>5T+4=gC*&@|KffNFv6e9NBQ)P} zK?2UBW`jb&dkMMk5tH)$mp^|hX`3+xqspTT&pjz|nRR*C7*;!jRC|K@8GZl!wl>hi z&V3&`+TBh^y#8TjBEWCEv`L!hWeU0cwAUPC|Dz$aFNXJ|W7+2N!g!T^#+u?8J=4u5 zT%lv(ne)}kj#izGsIOKRRZNkW#=1>9rE4ChVO*s~`;L{lTaVQmT{a)tbs?}cJ46;- z8QJoPc=B5IxK_%rZgzxa{&>ch+J{hy{@Sncq}tQN{|k?p{l$lQc5L1Dto?V;@{@Iz zAtZ3}%UtKv5l)W{rhVRo@*@OTM`WZ>p)DC@p+09AnSExbt|yaggAOz01Ng;&)z)IhAmEbWdg5p%M3-efLK3RPCk_bNVuE#H9zUnLww9NIQ4hLspF3JO#RhGQrn?TqU-$Xq`?r!o^!gVZ#q1H-*8_w~^_FlO;P_KLTKkR#4wq#C4fquJ~V%Byq zvrYhcny4p9OQ_HC67Rz7_Cjth9%|0akN3ye%*)gm5hZ6z-`Bi=(nj~)zi!8BKT=)s zjFndL?vh{F$D#9e5oH;d4?bmoT|6E;>bm6f>Gs~`UL_yTq-(^V8c(xooU5MFv<@Ck z8c|Sx?*>{3&|~+^D3vZ<#Qaq~!F^481QgG?Q(xN6X1@ULWym}_gQ_a9`2UgTx`vr3ti=6a?+HhUG{{`jngz0v+m>|ov` z>7th{%I`tP)v$*SdGpqBlUdfa^S`Ut+dPI|mc2;r$k%Tg&C-+V9}G^kO`bt6+WGqb z#7wh9pR%g1v-UjL?|zyr0@3Sr=PMHo;cjO?bI~B`>`w^^Yu~Z zQ}fgr*ORIZw9qTZKJ~qV`+tNTd)7v88~WG=eB2nYeop(DR&g8n$0shT$p4?A6)hdb z(*5fp0{KJfievA|C@mT6r|nu-MDGWIaT4qa|8-|z)hkkeZlS`5(*z?T$>q4F`|5no zEiJGC6uKx}W)GnC@2;@D)WdhCh?ryZ?+z}{)vSwLH6xjedC@lr!)6vRJ=$C@beaS! zJyf}kEY2GnLlQ-}oZb6YNM%$oUL?yMwWvj=m<{asYwN6V!Vp=xxND;@vSsHSDs6`oRp**t9?C;Zw{>oi{Ovc;iQu{vg6{oFU&w)RLxkmLFF zIxDm-Rc$W502#~OBySanwo@_(_xEh7-Myz|klmb>{+cA!SRTHktNZrg2=6R4OWnX! z-T(C0sY0^-ZJV`q3}$q4dB0+m#O=t?xE}l&6PGH5=qUCRE;d4Osa$VLfW>LW$ERHL z#JJ~d5!P6qg@qT3btNR&zdFe9RW}!x766vRD$`DtlD6v(#`%Ri8{Kq+XwEXlzwb8W z%qzo)B~oa<+C03{0HsnV!L@}NAR@*K7`UEDlOP!J*ddb(%9EG*D z$=YP3nGvlF@6%m_v8M90LtI^if2GiK>6PmuINK+FPZo!JiF9YF0?p}C!9{@Wz8Hq{ z8L5F8xrDM1}h4Y(6=hVOuX_QnbFHx&|;# z=ViKdPY&Pl>cG%f=;v6%RPM`OR`kVkX4Ff5A5Y#NG&3lA>OPtK>GE1PseuB=6@Jep zsMaZ2PEbr8=n=vK22o4Fx%i-73*LZ9H2OG%alI}r5cPEQNtjXlzWx_aidJ^;`nWyi zwIVi!rVh?^PWodZ-qZW7;bLPvV)>c3Jn_UMLANV-EH{vS9YJ4y80}bt{J!6dPJg^H z<5m(E#qLh*AGLysRz3F3k3ZOyaPly1D+sd4#x<9I0(eUO8KxF1D8z`GTT>3HDW6HC{Cb(<27Q8 z;kqj%q=QuR#pgYP3Iqo7xOtkbA*)}1|G_+aAac#nc$TM&1f%u7vFECAgB6EaC|(I; z&N0MpSl-zxDrdtIWV)uFY_J zZ1^^5YUgm}e;)Fl*+%M-^+~rxh$yu*mx+fJ}$LBurf&p&597xzl>@ z>pe&a6abWPA_GMkZ~$kpajhcS8awREy)+ZHk6Hu$*fHp^w`$4v=G*B@iNwEwc4Pp; zZhB9SL8#va;2T#jV4`pWt>r_?r-5yXQPdcXX*S$pwov#$TX3K_MtN)6HcUY)I_2;- z_-c%+@edye$PQxNy3aWfmqlZl0?7&@Fs~GanM0Yj#zF8f!xhMvD5Nn9OleJ}NWlCF zi!v72WP)o=<3qoL!8{biAcVq>9F~CPE*)c9vhf5YmA_SI(I;<)D~rLATo6*c=4l%L zp9_n^hOR#tU`@w4;2?hxnHB)#>m!9M8btQ?5JZIRrbFMVLYT6>);Nfj1P*RPS&$%0 zhS_Vfw{S3hwXd_Nv}DUTaDD(3N8GOs5=OeV4!uDH@zf;rKaHm&GjfNdjVwMf{GLz+uc&>Ynp zJO|f`i-b;sO*jbk)MGt?;A;o~0MNALH1p=e{V%K_`&7|%9Hc3h3z1-WSje94xa4Mah*AZ1jf84W2% zlI8=jY_?(_2W7?ucam`zhj|9ygDLC-Z8W4I3+&5@^5uYwy3x|sbgM>W3m0i5seseb z_UbN*(7eNb&NG9G4sSr$=kjDU+~qY2wgZw_TfS{ zNO#}p2b<9Las(w1U!>;G!(Eeb8(W_OQpkogwC}-4!$Xp7EOd8~*ph>XBuO@s5N$kN zQETSOF0}g3`n49?Zfn+_i#Vty6^XaBrTQK;l))(s-5e?0mxkEN0Vh#$r)3o{W)&Q{ z;GV`31F4WY2|pj|H*XZ8SB&2#2B+dIilyl&i^~6Cct0qn+t^?GT4i5T9{v{CP#gyH zRba9OO1rnITu0ZCGHz0U4Pm%bEC4Q59&}Paa?r{2^~GBdgCjKsgo*9f8$CJ`0E^;; zFV_;PZFI&hTZZ0=Arn;~D#-13;fKd~`@O6d9UbxljR@tiV4ig1+qzsa!*BAaC50ilKtGRt$MiDdU$uFQMDAgKX^CD1m{GB zlvL=Z6>qg3hMyOaTPENeNPb3CKSLbC$&PRx1U=hGQmNT%U5CK?sW)AM&!O%vRoPvDKmcWF z33L3qO7khzXDboX?Z6>+!;M)~^`D+k9V$JHz>j#xkv7{zx^d&$#p?(%Y`mxN#sKYc zdJm@UU=qm)Oov)Z;RNz!%L!Dc0WO{t$w|uu+dz!e6Hkn zLY<;3Yso`^wMSJ6z9@HVoc zE&#OtjLSw;a^m|=&K>Z@8|Vz9{o)wF-hIYVgvZ8FX+pM^26H-x7QQlqiPSpF@)0<^UiiSzgyMn3on@%KGg-KL`*!6MMxUZ~X z-K0WS+JCFfd1iT#=?cRP&Boum(Hp0!lSoQA^P|j zXBs4#h6d%4Q>j;mS>qQ;sQ=A)2X@k(Xb?V4cQ^y*Zboa7rtK3?UfACF+>;z!fZvyY z=PVa&M600k5WFm87hPz`9V!`%A@0LH^FP8JG!s&hh0Qo)q2l?5JhQ&)KB?lyH;U?H zO#1CujsTS>pGS|WN}=@j`JPb`)KHl?a(w1!e9P3 zeTO7Zq*x|_x6u$n9AY!4wq`=%tk~6MMJ@(}EMdepY_QD)TtG!8v7q*BjlI(fxEHyw zq+4_nGK-CH;X>ZKqJq_+scd92cmHOtQvJ%6Kvk$e4i?Wr@>6^*%@9HkGK~$jn$Qq& zZdpyh|MwUk7QbDA2(y>Mjl<9hE3a*4Uu4OQbbVi@;b7JEU`G}qmjzuT*}{wsk=52v zyeh(^73_;U;49r>NP`}hy|J`_CFvu#TSGVGkz+f1TSm}##Mt9&e#gzR=iG6*RKXG2 z^Md8P^dE1JzgQ;&I?lfZO;2EkJG#|s;YJhSA6jO;S%}=5`K54R3&}-8Xe5$>VH|+S zT7PcCHkli7fdqn003M`EGQ0g8!Mm=pcR95i-I?lFz2A4r`OM<$82MI#1Z(=BZa)kU zLuER$2AM!6{Fj%d>|xmi!K^sEy*_XCJ+m zPVnr1ei`#P9=+&QEJe=jDAv}ipx{yuJoVAL!8Pwe3#lxg@@LCQaK{A1{Xkds_ZNLQ zw4mxU>?9=cKW={O9KTfFiJGHuApMgVo8A6X^=7+XK)w?+qsD(ow&R95;Z&HrS^z#@ zh|AmyUfw&hrL{2OAzRM7_NIcs5`f6Y9)%c`Mc>HqztIp)behAEsqe#-L0X@3Pit!B zQ$abB)q+o}&p3f+PT7_Ft9F`RulVnm{u&FhvF5ho^!9r32n0YZ+*v+6fVS@nE~X(% za9Sl&c!C(7!1z!l>WU|IxvVStgBG-=gy}P1)P6v-RAZ&wyv&yI~Y-&%WWMNV0~A-b+PBBGa5$ICY$4? zTIn$p^UYR{&qh*qjCqZS*PzcY`&lu`PC5R|Em8VZ_sVN&h8Nnb{8{+*3a~biaU-YX zmLzEI$Vl44Q+Hd~_;S7Hv-s&(0~=2L>O74hWOF~%hgM$bnr`abZQX6Q^S{hjAy;Z| zxKE)8%x$M`@))8IU7htl4H3_OA6kCgai0kWxX=c}q1cW0#t6kIIFhLrY5vT5^-*(R z{;u_FovTk4cD=VThr(dcI4;!AJ#;r8WH`H@4%bXsp}$KAttToWf&0d+3ICH@f689F zIR1I}z@>6;3-9F3gwD_FXdt(=TQqp+k@rdvfWpQh4^Ag-*U4xf&sIOPsi~o5@l~TL zTa;4RaP~!VardjvwS!*0dgt%#cQ}*XVm_u{vtxIsA2(7ye3s!Zrxs2S;p1kHma|GN zV;Q-lw!!!XORLEgzdL$2s=P(S^wv!dCc}wStPRhL+l;p6r?{7sLz51chCHjg>V76o z7vr<#{otwYP4BIyA6WdmJ8i75e(9>U?fI%)Br%O!)Mb`YgqsdzM9$?zX&k+3qaLs4 z?GhATv{a(%iPODq5gW$LBI73Vg2SPSnWrtv`NIJSID{)q?blZILhYcC-vt)H$7khlg3kl^s-ap&Nj zsn0*`(LA!Y)SZtYpWP=-py4KxG$aMVB2}SYi|nW~(Vi))C%`zW<6j zBe)#oAbI|3^sU3_-!flH-`|Q^ct#s4iyx;+^k~G-5Z>KCYrbXsiK7ciz2qGatUTK5 zEk}zhlfQIcw+~3;OrCY9cnT&kS}ka2(dqkOSZQuSXpyl zLpsmRojCh?r6%p;>z~QRWeQSeCj8ULj6DQtU_Ar$qQAYx*zWToP-bn}>yYQ7pfPdIfsU`zB z!~ul2)c!G=s}zOYYOs9YUe!-c@lc(BjP}Ug7W1l$|Gl0Vc1LNv5~Nt()vG>8k`G{mI@bv3q_)Nhlgvh;#D#USp`J0#g)Dn? zkesYx8+Ud?g~9_e5Kg;TVg04xw_aVL%ywM+ArjCBq?%esY|rrcpmnBDJL@A3!q0x? z!%)3B64NJa(>}w7D%_S1_3?DZ+uWy3PcJ+>a=)URv_pSZ&(I@@<`8lMv|9BxR!zKN z%Wt3T|0=OYNEXdmE1+)O86D>?)s`#$O`${jm2S~9cW1h%^<%%N7)AHHnQ2eaTS8u& z=+860^>HM6Th9`p02g)CUx?BoDqXE7)h29rP#OsuEFMLBXq5u{)^gwdulJ4Ts}x;) zZu!%8*XzvXlI;~Un|HO^C5fEk?(Y~>G!4JFXJSv}D_l1BBL2P+(!x8gjGGrw^jzgic!LzE8ys z`92AEVQ#S-g6f1ndH6w5cZXv4Ir|%K;Abxit7e!NN{LC+r(vhl&vpy6t2|Hwt%06Y z(%>OGkiL2GLV^6p95N##R>o@53dBxY^6PH=sQab4Ij`!1b~IzrYjdauap#sK0->B1 zRX19RVoAURs?90OBms&$VI>%u!?~ny+ zNNm>SheZ%{CNLf?Ps>afxQGip(}u?Kp(U!uden8a-$>e!`TheNQtpB@j*pVcS^bK6 zIjyP^Hgyd1Bnd?0-sXPY@NgP*YF{t(lP9U~W8JMe4S->)P-v7Qic#cn&@5S^9Hcs)Wf~t{t~aO!5l!8FCx-VpD=|i*M(g5ZS(m1L zFFf%JE2Kdn8EOHC6=6p!3}=iCPw)S6t>*I} zhm$ch%{8P1aKN_Ga;rpIKl+SPCv`_Y9@?#ylKZX|Adz2Kg*x@`*JS8x1%j(z{2YkU z&DF8Hf=m|YYUGIp>bS@|4}Av}uZLWKPnHOGL=9>GXlY@T>tnZ3>F8`O(wUIDaZB!$ z?hV8H!vk&%(|M6T^23=44U`mf?1Ay3Zh=2>1KLE=UsS^ss9Wu|dCotTb^Op`=Dlnq zQ#07t^u4%`*hBF;IwkiD7Y@}VTuN*aJBiw`pM0Dikm9NR3U+kc*cLSnihq(gxTrwc z;}%I4XHlO_(0c#1l`;%aKgc&E}jT;71GoC{AY!uIH6x$nHLqh zg(k4WL4Q}S<+`Qy#ZaLi^@LF)1}@!@rBlMI_N{@9!beW<^(k`EOb5A%M`R0LvEl1l z?b#AIb}^?yl&zu%Ls`IM^WlCxoT+C{`4q#v1hw%S5KY2b%meYb(!lOq11Gshh^I`^ zX=U`in}tr|xzt{ZN%vJXS>E3*wnQ4wPF6@BxuO&& zAOo#RY#x&;(j~S3jXL*4A|$R}q2B=EiiJv4(BEb&ot0`z&$ir1;livlkPmiQE6H8m z#G|~f^JuMAoz-+M1Im%@gWSTInZfDUD zVo8cWOQvplFBSgp%Qbskhr0r}p;Z{*>8z=?&4+bc$CVfGm*?G02#$t`6SonhJlt1d zz~2!%!OdWk@b43|OZKRNr}m`tDCMVxj!Yx18>102d#fsxG9<_B*N`Tuh0vRu>euBO zE@n-Try{R1;wny0_Ntu`YLI~z>4sC~z#aNPLx7rF8c353(-G@iQ#&=-CP9te>W#eh zT=4pGp4MV%ExAP}&g$l}hYGcQi9_}vS@Fn1A{#VLMXgVh*Bfwry+u%;ucN~VuX5$u z&VGde~fK%7N%}%P>!Ioi+)q zw+hmffadB-+|Ten_TE!xLq4nswYx!p6OYgcBE|94sUj~mFC7Y4m*%BQa?^F?#a4l? z;5v+P>nNmlZ3Z*K9I4Mq=M*p#eLYKeT=dm=0ZL=-~=cFuYtV(^Ia ztJfd``*tLVPh{~_XItJ8RKkV+W)|7r$eZ?5-hw64ZK9H_M))e_5!AqmU^l-;jD{;u zi&`Bf6)3Yn8Kx(+Sv*RbX5CXg)DqOq9U^y(>56#kMa3E-4=WNjl(j9$)sBSR0%?PM zR$RA$0{e#OZxMlLe{=+-2g==bfdK6LK?O&Qqk|ntOYNll5XgtqVMhT8tDs_s+mA`m zO&zWc-MN}b7<&!Kwxfd9k2D3!cuK5$_6jO7VvFPq1-XC%uYHE7X*&f>-WNT3Lc?B; z(j!rCJlNs4M5+V0%?Lu1bz>E5vAF>`DC!?u-;4(#jk({8j@E%}%0c8=o+=9hdUzsF z)29O9t5b!`BA71#W351aLqdI7p?XTf)O@Kj1>};J?~ly-pV?;lXXTJh*U6jLbBmZY z`3|KgoY|~xPCS}57I<)WkA;xX4SEW+?&u$$83eVAhpCKsK4rOCQ=9}6o~mrKOF2kW zR;P^4(o6%nQ?OP2z2O&cT0b}&sR>q0M!Q|#vJkGquRIY!!xld$o)SY<%KZTk&{~sR zG1dAYP0{-l2ST)KwFuSIlfPj=;VKl+B3QLP&^Bo0Nr*i>_BB`atGddiN_=5Udvbo5 z+Ro(j#8ZnC91-?tJ!-nHZ$MB)NOnD^iPH+(gA}SVnXfgB5lF-)_887Ts!trCfR< zvo}vsP|kQxnD<-mex>~2)zjI53%{bC#%aC-?$sB*cqbK{pVFIls!hu4h)HKon+g++ z0gLSDrZAYG7wRO|*8n`1Wf5JJ?Dc7&l@9EB*6m`CC$Yqt2uq|Mjdz_10zQI>aUge@ z(D6Huu=4ot^Ov?wnzf_T{dOAejaIg^LdUGfiih&(UOexK5+;@B|8*+Ru8SI9=)Jm; z-t8Fu(ftg^|7#J}CgWD5CH5NTy58e^YOVeifYRAECC{}H-Rs{8Y3Q+c2 z!!2^%DLpo`P#-ZZ;sR>EdwO*Yq%NNrqXZakX0^r0kpf*|;!#_8skSRmcXcX|3*Y;m z8_R98K9U{lpZ%h>GwX7pT_jGJ*_oTE8wogw_GIlAFUCf|=IvZCJF~Vv2%?=m;bEus z=d%;~^9h4)jTn=@q<1o^K#*twW$D~CnYDA;NqP;3THgTMSLrW;F@U)?8>9pB*&CL=mJZR0`tsT$%n4_uB`X{{gl3Db zXp8X)0iexsDw}E8wu0FA#!%X!F)KTsYHRWS*|t4#D)Dh}*5+(wLXO10EmLN6s@q&s z1Tp!bxo_4Y7Pnz3lMvJRvHvL}@|NH)Kcd2}Gh%tPAttL#9mvhPPKCfWn>3`o+G&^$ z;bq)#EdhUGb8mVry{8GR2||4ycmX6k3j%N0WbF|m)RaV|^kE@OS=6kK<&o*I7L1-N zPq~q&L3xJ0{K13UOSfO+5m-D$RiQG#5+{xmfH#5N(7t${RveF%d0Uw!*uJ5M7{}9W z<*9e^%7H9($>-`rNy0J&39)|C4T7T10?LpS(+UB3d-8mXn1LzkODZ>;zm1|n)D3eTVKIwRuGXtfjV zKq`x49zd&#l&1=e{x6JI(|wz89x~z|)KCuo-==GZ>#bD8g1Z}fk~#!tyMj8-%ikdU z1gjP*POrPT+1i>rXPYq@dqBJ*hj-#bD(|BNt>0B{9U_Lo!kMlX%{Pl)EEP2u0o)at zwTKm`4p{>?xY5it3YnylP0#~42eCfSLii>=AL=e(E%RP_-05x~f?34EflM^O^fU!G5}y^b_00`Iz>x039B*HPaF^+b zx}%!s2&nEN$a1$JYngWd9ZZNjaz+CA?d42t;u;r_osRvca6rm_jPI$A047Sj#TUlsquQF>^9e3L) z1WK*Ub(dFA0CE&6TG#`1kqZDVl_Jk$-6TJ4l8=TN!<@^HRj%n&{yO&Cbjh0FtGD(CGeIRD3$L zXV7S}*2Vfl-DaxsRG#~G7yYJhP0~hbkn^Rm;-x8GsGgtlh{^7tOD$u5#OxwvEP)lY zb!)!wK8up5zJb1sl&0{un2e-qWBi7Q7Cqh@S6^sINPh@QAtq+vUUOI<$$z=h)^a=| zfspDK$(VTCcsdxr`SSqbS<9K911Gi?L0wg^9(cVcFvkGm(S2}N6pjR(eR=z*4S-{h ze_ptE>};m_p~UDV=i#704-pLCGJ8p2tG*gD_`#_?O2_kaN{M>QPZL-r=M;MVRd285 zp=jsYm0_;~Oy$5WTq{th*RP-9?%qf_K~$m^xHGZZm3wN9fO=(kE}-;M6ySXb8mF4A zR~%BC%R2PsNv^5Vkb9mX9$roxOZ>7Uz-M2vpV`ZQ^SMH^Wc|5-%))u7E4Jin=$`kV zk@~({pnw#5JIndON%c0y4q%I2JdvAC9zq+zpfnm8U3eO|r|{ua;OQPr@-0O<5}=_v z^&@GtGGmOWckcM_hS2mi47$ z!iKNkE8q(2i(mY?d*lAI8}PDCip*cM$R?etA)yYr&mzsK~s)<;(8 zlG-Q6m1ISS&vywv4yzM{lMZ2~Cw*qd{CD+z84ccb@=NIbeOn!;qpuv>`kprSY^CpN zl$3KyEzGqJIpX;bgmJb0CAY8YfVa2OIffk_p(o)&bynmD1SGJMM2ai}aw7Zd2uyvN zksn2DQ$MISe17<6LY&L{xz_Y}2fgoW?KxQ2zW)3WrCP0*R(AJAS%MzZxnfR(?k(B{ zx45~7NsSQKx&Ew^Tz8a~cmmoL@0Af7uBUmrp?Be!Pew_5&6g3L@bpm@-d6)K;>Rf3 z6_CI_OfJNb2G%y~MUnAX-Fn5l*j>Mp=u5P>$v(Pp!}pTV%Wxt=Hxs!{a@+0vN$Sj9I(HWt)Sn@Nj4L z1@l5UIb#l`q1LaqqU1C zpe+oWt5#+RC3KBzpf(?2KLT2pCoU$*Lrwb?x-p{T!mkZ(hW=^&3NbW@EwT=2$=-*d zT&pV`~av@#9`%acKx_{Ck$3PY$|hzr@wUd$$LTP4q+MF^hI1 zeO+4L-kop9Ua7o&c$stQy;hxg48dY!zLmN{YEx;INZfUUAefDkl%{c6`cmSg1I(+?iKQD8YslM`^+tUBJIc((2 z%)Qn_+vJ^hojL$fBN;JZ9u$$>>#&DfSBfr<-+i~##plrnIEr;8Q7t?$O2SoIAO+v} zI5)H*=y1WqV~=bWCAoUik`Tu!s_R#C)BLcUjz2q{ViPNNw1^mr5;;5gN-d!jH=x*> zRTRN(GnorhC}8*^mFs9qR-h~`&k3+uM7?TdE7Kyu=<^+BJz@V%eARAPo_ifK^b{3@ zPWR38N*kC*<1u6(ir9w@ZgihIiDERX22JD!SNkFj?dYfOuZj+0A$>jea=pl_EBc zbRp#P?Mp*n4r9&qbnnL*=WIwQ-p!evxw$s_(w;>PGP?=6XQvWwGl^r}Y*u|g&YSpS zbIa@ZpXP@`C++15Mi7V##rFuYx;T(_`JZQ8*RC7S$1`61JUg^kjR#5AQcz-!+N?UR zHQF*!F5L`Ai75fl<157zka3S=}ht( zi_4Io&14yWi*@5}9#UkH5V`C6QEK#nSrD#Widrj|q7`{(actUiKnKTP*C<63L5$V` z?Z1SrC_Xaxe}Ilzq0wI&?XlFLj;_#1!_4!j-x!oM89FT#Qy`%U2XHbjW`Z77E`{9QZUBH3 zssIH=5V4$w1DuR;psl0*SaucW87L-v0Nn_X^_d$y1(uX7JK|YdZ*bd@oJ+p97N=W0OHlIc@D_y{dtg@b-6%S1(A5Sn*A}LU9g42nd4V;kUZESO+OopS}~s z-#HX`1NPGL`VPw{r8?7RA9@EqZBE0#=aF(5+GhD=0RN5rC7o zz@^v{b;cQ*hBOOL39i^2&YuCz@K+_OCqMV&<9OG2QjeUMs!H_8j$R@V|n$09b zrF@M>se<@<`z#7`mxjd&Xo-CMJ*m!Z00ZsMPvrXyL}TyfV*b|As=&C3T#RdE^)ffC zb#0((;(XO0*J}^dkgWwip^uhDD=>-Z5*oT!>UxH&31k~dX=wH{bPJ#$4pY87KrZK^ zO8_rjiEG+`LP>?^tJf$bpWDtGb}oOsA>ZonX=|qQmhLbH>w?|4yw^#>g2vin)*d^i zvsw6p&j=mWLKF3kDKv8Ty*W`&+hzMhlZy7&cB55za*5ruJr;UaUkt78h3x#-zg|Zb5 zfzZ=NC6D=+7{qevx;U7@2=727L!lf90Sok3XuF!Z_!NfxMoV`e&|SMLxwRW+Ji;TH z?bz7;cAdoCxLk&6r$uFhHD!9*B{0+Od76X{egcB|f^p^Ct8UD7gHeIYBPNMpM%Fp~ z?#4=WftR7oQ7@AheU)Nw;4G%aw^gsLlTlx zXl9s0IiIOHB$YIx=#!dbPH7HBr5Z_+M5$C-U*BKuzuSa3luX_o zuL~EP8S=O}RGQc0jmRT{R=DxU_uL~Q&D^K2`FS^|@>IDEc#NvMpHi~lz{O;SI5)5s zUYFqfm?r~7ZUeNN-yt|5lx`AQgoNSND})YZ1)Yq3dj7SX&?KeK=!OYS_^_TPk*d%Y3@ zOrz}f%^jnQA|9#T&{Tso1RMgN;55iJdSP+i5{^$KoV`)Ht4E8z+7->=WaSdW4G*MY zqNaZVpxO~2Ars>I_Ykp9dbyu(?7aU_As7A7a z)K2c-9rIMUG7r1$7NmRCp|284lq2&$ZydO7bf=yH}!lM9LvZ@IkvPPO;j}m)&+Im*X`e!fJgbT;@^AaC7sr8<^%TY-YUllSG`E}Or zkf)>xa3vVE{VZD}k1Wa?=?h`1&(VwZ8S*@PyRezDxisur2X?#Tu+{a6Es*k7%!!F>QA!x$C06wtAJZU@W;M9xQpi{bn+*r04rtgLw1=S2_uSaa@ z+DIS$uv<={aN?Tx96+RHzwbbwx=E#yFl7G#@X9m9pB%X#QkPUgab%S~h~luqj=$&5 znNz!I9C#ljhwN5D7Tr2CdnwWnvH@^}tp1>rHTo|^a}80B6t)~}#cSV#a#&3*aoZ4{ zze_|9hMjyBu5G`UO0Mko^O~b0nJ<3XNvM*Fuk8lzuW~Z$IA%_pvQk?cJSG9hg|CJ9 zS;QXqh~GH=^Z0j8+y{@AuRxsBB!50;!sNt@W8%i9o01K#s^7Il55z-BKy$(dY8N}k zuCeEOMY+mo0iCSA1*qL1P7Fbh=`|wl%KaY@5d(nT;hUHt1lhs$;RXrw{ME()rvmy! zJA$ppgM@du9(H81SQ-`ulvm@6>X9*X>c<6i`DUP)j@Q{6U3OD7b}xT=1jfkCk>oZ2 z!Y#Y+@O7g5Ipl*iBJnDEo+J-RYx_Z#!@d_E0LpIxM0rH}RuEx>eq@L!7WE57x&8eY zPM)8pfC0J>k<^)+Wr6hyGXA0vU?0gym;-P)k?5o5rS^xY(MVx6a9QOhLs#jdI%M?? zKujkf*u77z8E2crNNMNpvj&o1z89l`#8FJcYIJUZ^lUFTTs zfGuah7ATbAFR+ye>U)qVM1;G`=k6}~2zwQ!zSqiy*AnJdBgwH!Yos_I<1(mmrKbo^+_4+$zzY1OGstq(?qY@a zy>h@(W9?cVKqFgHo`(?8Q*}#Xs0?$9&%w|G%A(tz4k+Nb&p}f2RZ8j$v794wQ`jAl zDUz7>Kvxvcm3x zXBtAJcac96=4EMmC__KUGWompmKrmqofHV@SEvCX=_l7Yljb~YA(6*m_!i(e5oovz zmePSc)|MrcLMq%ZXUG3}@yQ3X&4X+@sT zc9%QR*F0K055#Vx2-=xFIM2Mff_e>WmV;|@!iXqZIYwizX)FtO(VMlivtGph$gtZOrBlaSx9)3R ztad?}+1$F`tgRi$s)tvCWvivzXxCrb0W&r-SO`!TVgjH{no z{F+$|h1BF<-#*U9cZE*=m+{eC~iTB>Lom~-9Znd z-)nB9fgupClBjayNh`It*XaNt7{>>uRJ5oo!bJeIQPH0HFO|4KtmJTZj{PO6FUt+^ zikzvfa0?~UmZOU?UhB(5Mw0KogMX5KP2>MtDuz>+IDsogQZ5Dk_ybBYGlYBC9Mz|7 zFFWo$KBgC-VPIih13#RzGJnVQw!lR7rn_s;*HFnlPEpD(){ZF{=PaUYFWf>iL)^{j z)J4|x5#J2Zw3!pNx5#wF_s5}wg?0=DL4^+0N*KZ<_9Y0=d`7~X$uCy`T|3vTkiZqs zKH*18dfDQYDL;?<`&O_AF+LB_L+3ZYgWsl}a%#&rk&sbQ4_>hF9WlwOMJ>B-`klPILO6W# z^0OIY;%U3-n)9Xk^%_pwbw{sg%e|a%@oFj!yAu57$ixls>+Zu>?T@Qolqi^xba5X{ zwUaTXvQ5mP=zFD!nok0##gPdm6%TF6AWxVyfUH@iYSE9*1U`%T>!QZe}K4|NeZ7JO~r zmrUUnT!3KzPK8zcQW}lk|FQD%u}i;3_WUeV{ql6_MeV;$jKja0%fJ1GbASI@>%4ac zVUOb5BG_RTmU_K8T^G3k zT1MTM{*?wHV91Z$mS6~hP95V;pv{}PNlwzrHN`G#i7yW+0FXO9`uB^+0Ih+p1fFuD z+{;??rmL;X?@_royO`KTp3S~geX%(B;Inpb+s$*0)DZW;(V?QD_)e$u3T^Pq=AE_) zo79-Mzw_@2Bvk=eDp^o41^P5e%nEMa-TRU#(`&5Lep%?$<82Mu2I$edQMTAMYs4Nd z;BXPqMtx}(;oM9PV<-F>?zjsgAM=IX0fCUDdz@?x64Q87G{s_UHT zbgvyqgthy_v`TO*+h3xE#Dl57M#Wm&O9d~jAysr9ZUJqLCit!IvO0+y*1iA^cYV=c z7r4zk2KH9`RuMK;;@k%(Nv%@TkwO{RnQQh6C2lFJ%FzsitPerqQ#$qIqEdW2XaV2s zSKxHY#vSq=830Iv$A%@BTCFY~uDD#~o=GJDs~r6=l0U#SliMMenT*_Zj}eP;f3YO~ ztgYGaS?)uL#_D%o@)CMOrY_%2G0_akmvzto^4)x-Ib0#ZBqxl-1|W!^QparoPZg&H z{=zR?tU_<#(+N`TTi1`)(ByrtURrIt`)pb0+$*1wqei#>Y^qCkzP$IBhEV#PK&NXF zsi&h6Kqw#9HE=FXX}N*@aPX2CvAbKwnOp2uK~`7iXIXfE6+esXMauI*7N|IzBpwND zIs%Yro-M|IXCox_5TBcF;V%b!Zwi1w5S9x7!U1~e!o3MP#(+6Olli6Yd>GcGcegV5 zLf_U~TxsxuPE;Gq9v@Ji@w8vlb2I1h-A6Cm6YM^X@?u1}&&t*xD=Z)ZX}^oPz~oZ< zZ!9+ua^__M$72vvNl(>JYLHyVGtn#kN*XWe-&)~i^4}ZPRRM1;SAY)$ms|FM`^JOB zZ2@9;g4@blqyS)Zz<=42T(3|1d;gAG7jDjFl?c%95|*|Au#(4SifsP7)6M-lKO~=z z79FrL_&%6l){(2^e2uDCbTc(j=Hj_9kK=dy?I4^8kP_ADFNOz5{9$l-`lOGms|x5; zg|=F7Blz%rqK$4>r%nGnKw+&{)Za3=_1+qTyP7l>@(``$s|PxIy+TU9@6e_gpclFd ze*BHIDKy}bh7S(C3eY1GGJKAIh)I|to&O4MWtDY&jHcCM-nDwHWx_)r^BVx#0FQ| zYjn})<5Kn{(8rKFbmE3fiYK2ezH`NDpp-tk{^zNV60Z1%2z^=3STR5OCokJCwn51v zSmXT-k1&z>F(?3dA|=aA@Of|AY6g$xa+z5T3Ic8U*@z=n861uWSX)US3saeCG(t06U8Ly@xkGRn7{2biYj* zj(lj9x3lNsTl?`UF#ss#OE6IEukV$gx3&a@o;=NeCp?)cYidjVw(`6SyGy`h1FhnH z5n?hoig@cK0N{(%&o%{5)`OTQmbpL`(H(&ZSwi;ex{9Ri$ zNs+tD7*u38>QxZ_r{f(ex^ zcoGfbf52ucA}{@Fcbp^;k;|jD-iH@`i7>J&#+k^(vTgjnl)6R#o0$;5%q>>K*?6A; zq#SM&&>_1)>{C<*!=5svS; zR45+w9cx@p<=tyl~1~K0FmDG2EVDcX^$O< z+vv_e{`%=J%WbQ;p}(Ci)}=p|Qt2Oz4Ev&R^Q zk|0`at>fcPmP^0@Vlc-daV5xy9S{-Qzp0*PKY?T_wm$82DBAaDYG3Yz&-{oZimoSI zJiLs*FGAFpKC3@@6(q*iL*sbc!2QDC0P6^T32%3WWRTnooag_1a|*bJi1ehK*deZ) z+pjgz8amv@A4G_$xYQfnSa))PsQ^-Q+^Y9CbS~F{M4X5c0MLFY2m}G}ZiBw2DebV- zPEHa2iF9-=34mI3lZ$r%I4)=>Qt{>HzW=7p9vR$S<%^k0(4Xt)W5<0;KEm$|Lcec3 zvZFy{w4_cm#i4Eo401{qqk$2(#RHBY|7{v&IooXEGHt&V$I=Xy^h!~5n)mo2!ytXM zlfLoTWfgb*?+Z#uqP1~}wJ=xd4M|avO_rYqVW!E2ZB~sW^di*UXU66PrYMwmAtCH| zgp>7Z@0oQca?u7qIkd9<@I4t2TE^wy@4f zLNi9kaaquD2BP8lE3+vtPe6~o;i-IZzE2WMMBvs(BACyy6C+ryf4B{Cx5l$CZ@pQL zway%vSYPO>(T&-NuzrIe$HodCOnANX@cVGUG7j#Y&GP={aRTk(btFP`Lwr&3oX@TA zqcn(5U4eMf?sF%2ihKC@GO*i_;&j?QW*(@d=;>Vv`@T{dXlCU1mM{8y;%dpcM1k13 z6ZuY402^52_-E+zCCW&!*CA2zv(&Dw>IA!6eg{+$H#~DAuI;fu-nClW;T%}`EHHmh zn4_DE+eVQ65H!2g%u8oa5)flc1Z~^wImJApGs00@=Y&Yo*43b}lT?y^) zY76TbxG^&rS8o*dp)At=t9$eC)=SSb2blItaf3-|l6FMU((YmInuGpGhKs>JfUPJN zkagL4syV~<+(~KsvVgA#BLDD0K0SXuLpch`I2-)fJN`%5Z1A&fJ3%ZjCjO9I(bd-` z{tyCD94>uG#5lxQJ=SDcyo3vMxbb>4U5fW?OLt&rW;CXUay&8XEe_^1y36<*-8;;V zr!?MkN){@*e|@EK^iWiYyLEicdV?4*&7K+0-YAXvepm6>x%in*L;?4a$}Q~z5)4a| zJpRGq%&e{5$NE*(Su9Ny8L~3dVLNM637JlQ6!hzNW<@#PKht{3ot^^_qa@$i_k2cK5JN{^b&qw_7WOL?GxhnfcO9k%2ef57REyYe{`~14 zB(}RMU^$Rv)OA!HD9&35gs=j>Nd*zV4ynvq$u*_Cm1ezlelohku$TI{eA=tNBHd~b zueNY>qHfjYXN>FAX-A_opXwC8F5|K$G&P7Ihi|m#?ciH8;<2<$DZygc{Atl5Hg+ob zWW4Lk3Ym=QRhDLaMj==7@;yyXxu;%$*AAob-pOqpxbh4o_e0~MOk1k%!MjuNSl5i= zdli;^9HI)Ks5WG4ETVLy)gRtz)upw(qgy5%B&T+&Oii>%J^-Oe*E&Jj^UnK{(z~U)oGXJjFtDj=5)*AjHnWPN=bIqDJ60Yw7 z-J`B0MnTQKR#ZQcb*^ukq#O(;`->ubW%+fANpQ!Pc*b1sl^4AVv2j*OD+)>QXur}c zk20b`RqWSkY|^sNoWBB}BSQ#?d+Oh1qzGSEA!7pSLu~ye8Ma4tdS#Zn zV?4ofmsQVH@#Vk%mM@~;E+!(je#=*}Z!eRIPksrmk z6|yrFZmo=y32JE|2|8qvdx~Uwf<_T9_zH|_yJ7IM#+rnLF39rz6?YEORaBHf@N4Hr z?y9RDI`Q4d`yid8tH}Ap{wu545{I8TmsbxWF2Arp+ru?Q>$jIG`fC5i9eJud#>S+bbon$e3>p(;H5I zV69ez&A}>^(E6Oahe~5u8se1PR+0_U(G=vSC2VuhL z&~a?C7?Qfu%$N;=hYA4Pv6m+eGbZP|Z=^sl5j1Eh4)&(;*3y8PyHIHIkg~22AqpTA zlY!YyYO^(=d+Ma;xK#l-IRC+=r1uQBq}tvQxSGNx&O0%Iuf=@^9B>?}K)|>Yg~WP~ zzCZT7Qbf-eX7V?I<9ooh$+tBjaUq3&W&_EIZpavUNun_Fa!H|KN);GKL-K%W^d`s#l z*)l0&@27n}pR9X7{jJAv9%3*%)fx#o=Yf);IJoXr=_MRAkFAXoybcDQ<~Mqc6GF5= z{P*c@oIj|kARXwVJu>x@D*hO(XwkvbnF-c~?5NC<04{u%V`P8D8%s;R`~k#OV+4U=Opd zMx}mFDh>)ylPa*fj3=WAJ-QG2Wb$we@BZSMHbTg>&*xJkvmfDg>rk{Wfz9Npe1?jZTTBNW|`k-dlP zUE>YRki6Jw;Zy=(C<`Iwbj0_&xdyo2@@uigf8PdYp*<5rM9@Y8j+eEkRmd`H`qYQR zg%~A=s_ekWO%9Fmv?>#!Lli&l_OkqM`yF%xAeP9>G^l$lu_SKoGQ@&h>_7tv-*QaQiEVFIay5`Si=| z+kX#^&R%3>LA6{P1xGQWe|gdZ-`C_Tge3qGkm!3<>919l%mL*wHt za&I$gfPAEc*6;86egmZX-xE%@yulK5LF+02NV{Y+&JiewjtsUVm9?hm*($ex#g14b z5Evo)ze$a(;EvZ7(^=x{8+{6%dt+fpt=O-)3k9}X9~({2w|EzUMT?wbvyj@}Zb)IZfnFp^ZFs>xBOGABM3{JIZQeAiz%3K; zi~56}{7WsiH$_qs9$&DwTLg<9#I9h~thfR-JNaWIpq@=dLBgTC6%qS!q_{z<9!Uv` zZn7R~q%jDcwtK(NxO+KwHnpb0ZxYK4=>=pTpS^b}{`VS{T7s=he$4UOzWQhan;wh~ z>o+glAnaZ4c6gHE^r}ejkx=B(ee`z+d73TQb1d>oYhS;}1+lrKBGlxbNO2+MA3l5I z#{tY`?v_NB=>Gmn@H-NZIDAHY>W92GBVyb^Slv6or@yX(!#HGHQ81*HT@jV;2wkA{ zjX!>-ID+8A2wxkq@8=$6c+`OsNUfMBp z2W0bYO>%&PkN9x=pJ3kiAPyy7gdaw6JCUPN zT1n(+DGdw(QPE8aTQ%_A2Z;t@yPoWgzh5CAQx1Cb>ylLOonBJ7{{zWx3hL!2g#GY- zur=xn{t>X41usNB*E~e;feVQh?1$txe|GI5o{*6AsPw>*Ddh9dw0>+U?`San&okKs z>5*YuqsPgS;Q)XdpL}oOaiQmV_B^@4-bn%$Ddjt?ny|r;gOg8zk5XW-RZv&I?X4Omc%7>NJLMUja~bQ5KV1PtLuYf(;luIYtly}L60&91*!%64N>X`)l#5%S zoO`+b>ap=T9x`>1M`MIKNP9YlvVaRfqjgWI)tfnM<6~AvE=I5|9Uo>L+52EzEolRU zou@%kpCkP`nI?!j_Wltpu5NoVE$j+uVLK=h#-gm?i*#rB7Z;D)EG-`G~9+ zv!oZ;#(UeC8mIwqIh}Xr3XbV?(sX)I6k}PHRD%QELy&a>q{8SIRbGa|+JS?8bz3l&gcm&RnE>$xY_T3#?Pb1pgEuN1VC$}{~`KtjiK z-~yJ*#`vi3qK~0TfgA5K`vP+9xX3|NWG0QLe6!I6bv zia767Pi1P1MKMs>-ow~W_Lw{08L;2?^HoKoRl-uXIyo0Vw}c*n0{~n=`;%Ld)klyb zH{hC_>~x~bSEZ8B6(K4sUoOcFtQb{)(x;6i|J?Isv|mv~sGU7#iqk5+P0Jk51)`_; z<|BYsNedn-->pwJJ$W&@sFER<7nLrP9N(?{azIT{dbe&T7q`!jB<}DZZk{c1$>YmooK1Z%93n4a#9_|cDhF~nxlmAIMoD_Wn0BJU2UKzj_!IYgnoQQ30tdUet@1P5)q zfkAh!9;Swd?l}TPGfpz3d6`lMdZbI93u=P{{Ih#qkD;cX&&h2CLDjVxNztg`J@I`I z9pV@T6{z;mF91E43yc)&E0!N7w|4&Oz3oqvAW@rek^G#HEWuP}iAnefIC@N9>HGV* z|Ne|ga`pmzx$E(-UX9hPE~h`7qD{= z__x|OUx)XP)){gzwH+j+-X-kNU!Q_gp9cM+3-anF=PcI1Lf7I2TMz%F6t*O!KL8Wy zE`q-sIU>~y;?3vUdlZ6a4`|3eTJL)o_4hvQlr<8G5X8l*E`4L4eEocNmVw=CdBxbm zMboZ?;tA+)KCWt~8tWB5@JjH*BQQfuMi0F*)0)MKDL+D*nkE6(eg z`>=8KEou0i}`gSd;nQb&d#JcO`_D24rt8yrS z!{|RjWsAnQ!xN9`k4NeBMR`~qltiTqnLwa25V9WRPF(VT=Ms0+HUDH?z^qsm1znJ; zNGm0rE1A6zVUSjQ&j>ecKW&IE2Y^!~)D7$LZa<>8LlQ*X<60Zi3=_^sd#9VgHT8y# z2Ja~;cVS1$ji4lWJRN46z&zy5%#}<$xSb%dnqyL%t&C+d+=sCRCFeR9iHGg5KHFH( zz^NXTDZ?OhW;Ub!eVi}r^jd>)USOujcIJ2ej3|>ViOKXKuM~0bRQI3f9u&o}fJt;2 z6X*Alz+q-djFFgKR*uYpm@d|(F3YcIqu)OyBHv{Kj4`au)0uWkl`FRG4Axra;S*lR zX_-gT8?eFYnXh1pircJK6U~d;Ik|JfiF9Z<&R5(Y5wQWbpg}?)N}RylNPc!HLl^rRlOm%Bcr{Gf+q06Q(vG!gQF2X3oi1mp83&P+cG61(fMTAj21mOm4ln2pe_RnENJi|J)xX33KJk< z4mc~WlA`v(L|@O9s7@CqOphYx)>C=2XMv!2$jA|qUiC2Kb1hOSz=Zk#ft z+TAunEfEM2AFzJ2herJ`($vu-1q6eQ@|rC<*v~WN8*+}D_+R@^!V2N3cn_P(%5hRj z)eGkOG`LLQPs}GHG=WHNmlwewm2kE+Xt7LTIA=y3_oz-)-w>s6XfLJLGO{DJiWS#G zjq?gFd#_w|UbDh`4)ZMi&}$jt$f;=XCRl6ZIMfvph=j>&`bC&!<`Aw=wQgJnAQgRrTm{+WJL?WgHM;IMKMW#8{9%K*q zR_+D~*ZaXS>`+S_JX-=u)kB1SFrt0c?=J$!(A-7ulk(J2MI3k@s-AEkuH%}VM}=6R zArwwMm4A#?7hufCi@PCgIQ6T=P$QZH2rXQ;09E-4vMzu};;Ot$>wdgvPrN`0%Jd*s zR0xp`vgRYqX&^)=G8_OQ>Fqkgpd1`bn+A%IAc{0xGIR&O4uX(4febzHpO4Y4=>+1>a(@ZSG`#ZV`@Tw?Rtpdf0bCy5np2>>FpHhYdf-n=6e7I zd8kG(qsayswaK}G!QIB3y3qcTpup(jA4{lCw%V?Ud@cZ7R<$4MkKk+Fn%c9A0K??^ zv{(ngChTkwUa4$h&o#rF)K{o>xz5dN4*GO3lZuGpok$C^hejg~ZGx>KN-7JIne5K0 z8x=7^K}NJ)=J#&Yd9c|=2ihNzP_QpN3YMe||6sc>xe8votN!+ZwM%sqs0PSIa5fQU zOoVe$$nik%Nk>HNoqbQ1B$-5nfg9Lda5S-nhX|*FG*Pg0bZvt_D1i-^oB}n}fwX9_ z=v^t7cnLl!Y()c+qfk}=a3h=`ataxlFc$;KVkNw~|Xw%%I^ zkKd5{*9$G8(|2*vW)JXDGX#zVPDw|^ag^h5hNS=@y>wXZOB9z)aMeQ;vkj^AjBEI7{kt=tY9crk&C}j&e zVz->=uVL?sBw4|(;_vf7$#W=M6xfP=riX*D+yM1XS=>#-L~t+Ghr#s#;2O3uajDJ{ zPu2P3fJU1c@j3)*^gYtwpsyN1Mio>^xzmgyjF5aYD zn}lWLEBAVm5DhjcqYcnOHoTc>Y>2XBxkh${6dLLcIrQhHsuJSas8cVSz8?g~1)+*f zP$5&Ey7z{t=`lk35Y?z4ai>l(?8x1pl@M2hM<%F5n!6RR`=KegrSep;dvXa178y0# zyaqk9+oD#jnRBP4ZbPY>DzZGs0U?V$AC!j!!1`oVIUP1X3=gqK*=-$w7d8e;;nh$! z?PX?Ke6NN>Z;vrekj zL4fLAl9WvYAM*zz+YlE1W{jv#No=*9WZU9+)6m)(!wpc=K^`Q{@{UpZ*^-grMvxq7 z#MNv>;%|J}Zp$4Cj1Q7M&65Onq7uMWnKhOubmovLzGnIUPL5un`CdIk)Z+D%e?7XY zrVj2s?POo2M#d*Tarc^cm=bm!1{IFqq&tV618GGyJp`L;QNfHC`fCyP*#)=Es7T{Q zN6{@yus$608GER0pOS=y{|%`xk4;~AgoFq9Qf8?)3ry7|Dhyvq0(-7ReMVUtY3*dc15= z{^}*MXbizuxV|#T7FRWX)6oCEZi3z&k}=ql_7X}$-0k1Dcfa9a&HmQ?o>2dpC&?;% z_dKEI1xZ8O?tfJ>E9Zr%sqOK%ExE#h)kC&(+>&oocl`I9m z%{}0@nA#(Mp5C#WcM1zMFlnc1D1-o2+OB5{MKuAFs zbs7NiR7F*wgl<9iMB-srqx5ZPutU4sojfxV5s^&~OOHa4XF>1oBD4Y!UUDKEO$4t9E>l zrTtyqWaB>NQW`uXuJ|UApgE`BHGuqY{Yn-!bjlHp^3J*>gi|?kus+Z|x(F*6Zc-7FI`9V)TF^FRD9F2VHORdSpXu_ zDmA$vSRF!#3YtAFYsl!xwEtq37V~S>~d|L7?9lnN@&_C>$@X9 zb}CN|EoY1!IOYoeV!k)3p3uMGF03Wv{gv%-B_eFOxmE?x>W$NbfbSk>AZ~B9Y5+nH=D=1oNG=hRN&M;j1s!t+k^(l`4VJD& z$QBbJLK+wf4njpCBXAIk03bxhK{i*Q!WG@+;#(Wh|B(yM6ev<|Zmc9FCtubRI{xp7 zqxi=#+Do|*kU6o2cG$&`xHU5d2h4fX#kbR}3|okP7JM*?3W+XAf!6&_Hb&R!3B^AB z*+PZW|C!aa!-X^uTIIIVLoz$FkQq@5PLTI^CZvDQTYv}hO=p#VSUgDk}MOvJgk?diwPju@y5?6 zJlakxd)9C&6N!I{8$-nKdh(lR&f~3A@&n4j^hX|_-nF;I&}~=>y8tv z&u*P~eEGQ9(fe`tF2I!hb`si9X8E1Ben$p89emp)-fDK;wjZ^i?6>_9T0MWq3aqGm z?^V!tPES$Zu5uz9P*K;b=&k8|cRO6Oh1@s3e+7s9Q2eD4{?7XP9%^!^^+ATqZs=`$ zDxpqNOfZtJZ!3EeJJ$2%{@8@AT>Mhop^mEdf@^#ck^OtOa~^P7uE?263{=b+j9L(~ z4cbPOkLov#6tx%WS)^g=>Uw2qIL5HpSo>4;MYk!5k&^LZovsm;2ORyJ@h$zs7C&Ph z4}FemoG`cgrP4vQZmT}>G@~lK_|_mqQpB!Aw=Jy~dIEK}S0-R3&D50)JbU>+%urA$W z4K-&km#HfzFDBk!O=xYpzk2q0_Q}h;%do#|;@{M%f4cGZm+9qm9kw6Bla>)?m)oDD zCe^k*6O;dZv;W7j)oWw+i=uqG=l!Vu3+KPuD5-yXvae_^@T(tNEvY!lGUe`k)DzdD1@ru|muH5QS5>KYjFBotgfTbUA)C8}@VZ`$N;X=VMJ-@hz`D z{uX?XUqAXce9^<}k9^Rc_vT3-#hb$Uk*CKWn737RwD{CJk3Qs+uBkst-ZYP1ymY29 zMDbKd#-pV0_Tm#Mt8d=Mf2d8gz5QXG_xkb6l@0y;htC4Tw>RF-iftcw_4?wu?{wPB zMx*>QE%lO@;a7ecvN{~>$P(>yV#VH*2=N?-%T*aBc7rM@dX6gLU+6d#RfLkhOi=3q z*do0WWTZWx(q!jps0_PWQ(PV5OT(3!NcG+~o%wNI>9reg%KlSXbv|?L&WV)-@$T9o()BkuI}B4T9%jFd{>@)DUsA(5Izq`ZLz<)11J2g;^O;*WwQ zCJG-+3!zT^a179C%QWl2b8`Mw`)Gff?c7$?PdFM>JG%lLo2&&R+_v9nmUi#i+qs!} ziRrX2ydb?pr5^UgU!}1fTw%Ria7drGQ{6KIRu<`n?xR}o_4a=vq(8McLx!wM>1Lf8 z0+b~A+U(T=f?Z0dp$1gzK#7HP=<#|2aelHS>W)*Uk)f&!5i}cHX}&!&b$aWL>R*ur z*WBOjXS`cZyk%*U-rj2P7qihky2l3XxI5sN4HR-xAa^?-hg{Lrw0W>Gmn(4N8@MJW zzRRrG&y)cyU`}Hpq7kT^jDdh7^T&pr&omb*H4<$?(8KDVRSWR!rlN9pts_Fy>{?TU zt0!$vZFz5I9^j;xDP)}TeQ)Y@f2vgRvq{*o?>T6Ptxm~2E?C*L4CR0YiRaEy$N~P@ z4`Xtr@=BScZzJAN`}*4@b~;C0Na@nPWC?}|MK!N*yl9w!xw7rvOkUWH1i#0WUuCx8 zKpEKKGARpoFV=B$=4ob`LFg(8xkPVbjkE9cT!n~)y~@s68GsqmC={7kgaiGqgwo4X zah-o|g@{DepA$NhFev=yyd6I1mCYxGyid;h3pBLc3#NDg>NZp`QisnR#;A$m)#Oy3 zOYGP@6N%AleLca3R_+IRG*J+ehI0@N4N|&tM7mpn7SfPL6-l+Z#?m1`53rtS1x>P# z95@NJ#R-KW_RG|_)Wg(>%HG3-3OxlAXsRJuKUo5urdLm5SBx?yG@A$=dwLGp#$2vg z7}zv=F>?4)ut98D(2@Q11BP8`sK^b50xnomesMO(agYn^swH7xmawFDU7`%z*gBGbQwF@RTI8i(iUtFLt=Y!? zclE4j5)TaRCh6n{+Gvtpk&0}h*j1EG#$+%*;jbX^VdRFSS`3O~-d;~~cpZD~`h!z` z{ms&Kp_yOU<`Dt8<+42?8rmA@+hiw*j0p><44DGUZqTorclKu)1M^P6@J=x}^4UdP zq1%HonMMtpvc{yMnh7>+q*+LBkqAy3G0^~#Y&8lNvY-7h!#t+xQ)iAMapSc9C^>l5 z-wzEr*W9Ru{z)N1F zxbfh~S{0SFgm&$?iF0pUHE$;@hcym}L~sj?erT&yd-G5%&eqlHe((GrdlSBKF;trew(;_;L-iSn_XY4B|nJL z$TJ0y+K2xbAc~3W$NJ0)BT@3UH<{$wCH+u(PAXd^ga>-_^Wjfp882)42E)w69v1;W zf`{4}IO%3xV2~lvnh&?98!0w-DABdDWF-4u z=*R)AhKtQRw6ksO1ZiShTru;sU6>2?O0i7O(}0{X2~cvh-97zgT|$@9P) z+8KCuno`uYA#bJ`pJ}^$$c+q`K>ThD}e_KGA37*)9`E&)Jk`=m!=U(lQ8L7{xiJ4b4KHpU-dZ zP#hj|sJ=fyhZ}0E9Pk#>;FMq!9$fw?V(XI;DIw{Y4NUSC($;Ad>F3yQKbB{uN%I;L zC{ib9%B9~?KB52rXcDqd_oFlP(tsyhn7>9Foqs6@E8h{S1bMPR`QvF0)S;4+gPt_# ztGfF8Q-l7WuH;l{UofHX#)tqK05yhoPzkxzy-JfI3U{$G+xQjG~vk30bQtAv0`kS9aC^&v?Lxs zdO@f0fc z*2W%*II(A(R05$@OU>SkgSGuI;V$|nxjF>}sC6RzZfJh+(rH3=w?CnU(gjH#Ew9kX zq;SFHF0PpW<0Gg#%Q|IIk(>FuL@1g z8qOnD73{UI`Po&jslz*zn0GdjI=zzJi>lh@v;G;n9{k0_25V$)I@Ji@&PVRM004-7 zp1dTd2I7qnoa-m1T{l1G+a1-Y`+9Mkg|Vm-jf)sVjo#0=pWjHtb|y4l33o|Bn8-#< z8I&q2_UxXDKUptP-4xlk>mT4#_N&+&zW5O(R;l*v{_+ZvVk zdRuHfZP?=6%*X44OAA@{?_n2sSqXEy*O?R+ERk0Y&4H!vnic?Hsva&rDl3Kh%;SAl z+tFtpPqN}eVW{B|Si-YzIb2KI^!#=A3;e9Ol}Qc3%=94-ImZpV3!Bn%3DR;jsep6O zPu{8=d#5^2as%v6DK}s!89Ko32><|$AI`eH>7G1liEDZFZAk5Y!LXK0V?;T2|9#vJQC)5ZI6 zX6Ib)dr4Kh|MB&nQB4G1yKe}PKp+qV0jZ$}u!P=`-g}d(H0dBn2Z4kZK%`4Ap?8h+ zrqa6#(h)Qik){;sB_96od&)ZZu6y@-X3b>H%!io|Gnu`f{d<5`{kaq{a{vkjJOi70 zJ|bd-+vQ@28NY^QgTq|rh>+&6DwNcx5t3onTqug93J`Gyz5zhw%K|81mauGQ9$hvW zF@TjPI2>mjhSe;xHcx!LSY2)@&=u|64Gv-a5_D#9!<-A>ROKK=L6BHNjlf1nqu>KFS|m->Ghk>$&w}N97vRA6sQstkEt{8TRzA;6GJhE83Qn~D#_Co+9+Qbf7)n8IKyG$5jnzYBuAty^r2>lBv-as`8{%pO_VO0e?2xPhsd<^Jtn zVcoDxjWc0awR3-p{}6BO(8Y9N^DT=`9K47jX?qm0pL?~UI(_>K1@>E8WI=6@CZMXk z)&ft=WDEA1X5(EG7I%m|Us*>#q5rH&(w+OJ9@TlkWMx?*){MHjiTR=^|5vQj1$jj9 z#rDzFP*UujHzkUQ=p(r`Ri|~e4GJ+ER-onDn=RX>6>xsj!ukS+7-03Dh=@q?I{}J< z7_c_+Gk1Pk=pr<^)?nx00BTw4gln8?Utpj zSs_>w5Qr;^fTMIa7TrnF=j}|*VrnnC4I(BiDPjbbV$02w94#}AZ0LXa@H&4;0rGcu zHLNUvab^@}7|m<&0uL(U3=@#e6aaG6^8|;M+Z5KL+~ok7uP_lBx z2I9SzeN-NR{S_#;sdEjMRC57rv&XQmJwMq@25n^+#Ma-iX^>lJD1Zz%hgO|K>u$b9 zqrC2+0NrbEeeAth%|V%%Os_4S3QSnltZ%{N>aFidhu}FV8K2B;awKLDlcg zl#1;ddgq?~WgDhE5GVY4lKF8H=XL4=xYAePcQJ>GSD1JIPn}gX5xvkRoxh9ld+{lRkN^ z3E&9i)~Ai#&-ADlxS}@s6@VrDV#K&l?f3NH)9t(X`ht?l3Pd}4(=3zyVg#%^@Ox?Y zch;<)#PQslcDot+KPww6qT#)3UJXt`hO170HezRE4Bgi=|8#`pIWT+t8vL_s*30hH zuyyjsJVEI<{ocWcd3L9tdun@P{>3_Ue+k#-!t)h<|UdT zZJ5BI*gNWn-0Fg6DcQUzp0oI8lX{#sqAS)-Rj|DR_(Puw>y>*9g~3%|-V`90@u9GU zFGoi<@9@CF_d~$f=i|+X+a6P`Ilmv|9*VR7ZnePh+A`)!{e1}b`}>ZBuPyp%cI-3T zNEQ8~8N(x$XG%>%7_|prwP#0S1sFAFpkH>8Z}-v5?W5BkzjyBn{JW1nv>&OlGY4gZ zVts)0i(eHm$L9J>8C(gv2H7#1z#>B1ajtf36qfka%=}-s(%f1pZe;B%O<=lIoYKU+ z{al>=lkBq;puK*i^l*x{Mu7b(xto6E<7cH}RZ%^+j4k+1pM$eh6+z09(MrhZP8Bl$ zXQxVMH4z@C0TB<9P^STbaUl;$lr`$ad!s|<0$(_v24Kik5z&#(#ZO)ahDDqP?49Ds zC{E42d|S_6G9(WmAv&V*l!g=e?Q$`IG*qqrKUnN}zu~3@-TjrIQ5U^L%z1X!c~0ed zZtHp8(0TscdBLyq!qf92@CBCPqL}ZZMB<`U{i5vAMY;1uMc_px=AtU=qPp^;ruCwB z=%Q}!qW;&#o70Q8;7c6CCE*?4WrM_JqxxmjqswOJ%a*{)R?KBv)@6I;Wk>5}=g?)> z+~xaUmmf|qKZ38i8LoQxu6iY|`qZ!bA6*SNUkwIc4PmZ^v#v%euSQ$1#)huO=dM2e zy83*2^#y!A!Eimvcl}l3dP@Cz`qA}_^Yv`t^&IAUKI?j+^7>{p^4rk$(%kj(uj}up z*FV4nJOg2ckFY91SW_pgKO+2eCTs)}eqjikS%j@h!gecRXNa&nNBI4V@aL4U2mZIu z@b7@{-=W06zv};v9{oFZ{&y1i?-cXzEbHHS<-d#8f0sl5uIBz-|N2Kb{r3+XX9@)0 zy6dtJ?~R5q2zzYqa}fIDZt)q_xg2l~CNfDp-`zam8cyLyT$W zTiE$)o$FuT&-v1Uhr3&U`6jSRm|OSUju2nVw6cUfw~zRztBfj*>fMe7X6r0lpa0%I z7M#b~52f96Ke@Zu`gd>d-$N7;L=uiBWeS2vk_)uKqoC4f@Msz> zNsgG?mO&h`cih@IFsvbG9B~{8lAQ58H{nYO{55TyFYk4naV83lN^-ptTMXh#lG<+L zN|w7g<4RG4NO7mCG6i#|X$rJ+r|U|eb7vT8N%6ckwG8ITv~X+Z$+8JK=gGE9kmAjG znj6fU>sr&!o9Eea&YSNuD#cgezZlF{7`)xiR}^+}&WA-47+?U7a}t2#%{Rc^n+32* zEDXfltVv0Tp%5}gIvQSfW@!YA;ypO>{yik}ftaYMf{c{0>|G~K2_sE4>qn*@Pi#Cq z+=D{HJWv?-h*&o?#xpYRdF;!8m#N{2slkaEfk_#`uQEcDGs9D}BGPjrU+2YS7p7a`duMBBckB0`oxT0vfBqcqY@Yx6 zarAq8@8ICz@bBNF9- zR|LX;>1Ge%M*n~H-$(rCp#R?b?^7=c*Zy3l!AAhdr zx34BPu0~fbCua6$KW)x@+Wb1cG5z`1)PJ-&{U2=&%^Y@oyJ*KBw`}dSY;FHfZEiJf z{g*bk8aIBu`LR+x|E+d*yKd^DY~s9N{5)&qJZ11aq3F)mGQk)z#M3)!$SDuA!m6roFDTyDD$6 z^7R-tb*eJ?M|u9Q%JM(;HGgsSXN~VJn;R}$nyy+J|CbuB{`0f>vZdv`v+by_?QhT9 z{pP~`lH5N9X}g&TzlvhkN+UK(Lbl8Of0sSqD}BCK;&V{?{68x5J*){iEcZDm^S;r3 z>9hZ>gHrFmrQU}n&u+9|=DA<$wO8V`UF5l)=)D#0vzFk3&vN~i;WU%#F!9Q6IL@Xw z+NwRmvH|5+73@{zZ&m!vINQxI$xaPptx)t>dfFB-V~dz|y!XvZY3+&Lny%WKmNFRu zFhItlfy4GhkZwYDQmq25=9-yW^G3Jj(dOE@x3+x= ztlBMg3ym&QH8x`{_1{{(*G3DpTi+~q2L0V$9&3I3<0Fcgf=#Clx6&6!EBJW4?cLf? z3YT`FPJ6@8v1}3d@8j)_zrJ9VU$W_TG;K{)8P`7k)X}^%hjSP!)a`8f{jJS+=liG5 z*1aFyQ55WY{|^_vc9Guuj^myAM)x0|-*=ww;rj?L+4Vnko&VjOs(te1!~4tA{k5?o z{f{56FVFt&{P^qk(A<__$ZhfVkMf+%w;8p(Wz=BmL*_w z1p|*otj2L?x~#?{Dymi!?zU{MzC;cp))GZ$UDjSnZd9!$$)0SkB`bjV*HcvJUDs1J zc&pdbbi}vT(+$-4e`c7Nx&C}@?o|CV(>h@5XO?X&|3of2rv%5@2{lNP=$ZBg$VlbZ6j zlirF6$IjvI@v6Eb70e!Lo$12#Kxf_;W4Z3O2{;x}eRT`cBID8rVCMWyrqb2PFuu^6E3w<_Dnv^HE;fcA~+mH}cys zTv1u%NcXX2h5*(i$bNLVx=iT-dsRxqo1i44)S98qx{<~-wf)1 z@b1zM(fX%B`nd`$4ZA9ApQnDIewsGg7jAnif!%)JM~h$h?cHT|nU||x)%-MJTVKdV zv>&L3U%d0>vw16RFcDp-n^vU8b)7;OXAk6lJGEyfozl}Jyw1l~jXfMHeSesmF!~r1 zSj%TzRDxL`v-|GT^WIXnO^NYKUa+#wy5T7Qr0}%bQp`8ciQ2>lX}4t}=KF@=1$)nv4kG}!rEw@tRvI62%K8=1P(fxVAxscgsEWc$6XAMkQz)RpjoZAh=| zuP}8p`|f^zX|#e-Q!;0rFMA0K@Ixi(gMi+@8X$FsYEig1T|l2jKd9tmPJF-q3nVFI zYPKmIFiKsW%|T4Nsi4=cO-HCW>tofM11~D7`1U%?bZ3-{EBNe&Un$uu15Wz6^i+(z zX!D3DI0tUt?txtE>?#+wkb7)pPN+Ql)_#CEg;@<+ZYk-DHv;ng=_;L5A{iSYg{1MPR zq~oYWBR7?gJ;ah3mo(Uut=Jck+Lu0Ex^HVL$scljq5J3;$I_HSZlv>x&X{YJ25Ze3_H7A3RguQ&*Bg%-c1}?TS}?J|KhOcVU3&mHqMcfz^m2Il5AS zeKd6RgE4n|K%ZxNO8+w?YNFV=aZF2H;~o{DTHKxT^$qof0ElZJ6?m#DFq{3wt-`72S>^6eOBfloqS-O6V5uVWuL&b0o!rEyzL3-Yk#Rt5X=9Ry&Y zOSapjqySdS_$R1C-$RME5VghceK%GYPZL+NNx~=3VQyj@*_)ikkkKmshC6He9mV+; zfj^RoU)Q6awqiFLVRU1B6kVq-JF7}BrtBB19Q{<_&8%H)ogk;MOj_D&{`qa^;o5?)W+$Bg$;-=#5Cw&W_znAQ2Ht=5kYO%avCzB~C zAGcasI84GTo@#9Dr&LXX_NdlfacoVaqq9ThDk`MTnCu=k-uwe``Sla2r7t?`@H>OK zs+&A6Txl+UUzGoTFih6(qB_2@9r_GZwEiGW5|trt#S;(E{;2L*E~;jWQobkq?+A za_R}KqY=RAfPgp>b)oH#v7EPayZhMY6S|GMURR(Zb2vllz{+=y>Pl=gULR;op?A^G ztIe0{+wMNn0pwZUp;c9)EpZZehE8t-rJ1V}Q{>kdXtVs3843IGT`v`BtIqlnXYw$) z^@7CA0gpUQHy1RW8BI%I6uWHLdy8_#$N~)wb}e+m7}YwJpe||NH6a6h_p&&sKFs_h zASl6Lc(yG&yY+ieR`}@i)ila`7Bt11vF#C@0aaRkkJQoRD{ID&E4uZFQ^{q@$@+eR z>Q2b}gay4ym9I*~5M}&93MwZmM%kvaVW|RwaEc}aie>=SLJD*SkLG5C!pW#w6(XCx zDV8Uocoxq+%z4p*oIuf9DFoZ&B(5~(25_^6`<>~V6hwoT-h^V4E{ zL}Ur+`;CYaQ?=do2SWWKHAW%CD^3imFdM*KDbvsiM_4XWY;6!R!U!s44Ex0cdR9(O zOrxL6s91?d(U^qA8JXnc@7-AEEy~H|jpa&UCZ;KfS?+MkN%AT<1OnDB77ncJ2Dfr5 zmhXcZhpl+0V1aWll1d_i{KA1k=-zqL&x58UJqZwg$#4Vx(hM=#CIwbggMu`WDLy_A zket_cyY;z%G7M^J9;2NdBN_*tPf6n>BVba^V{QO?{CDC-T+{iI;EJK^mQ4Nwg~cX&_qy4ARcvQ3bOAPm=fF3_1Ae$;~7df>I)l5VD(i zP9ak|2P0(>qt}iVUwGYYK>VqV#s~*gM^VaUXHeFpYvf>=nIdQRi|^+`r@WyDe`!o6 zfGV(3i)<`^e3b20sox!FlLASq-P1{Df!pLcBuC(CI3$@HR2b)wEENLok*S$6lx!id z@|J^hgM2s2i-GcQzA8d`a_zkX%O}962tgmb>Q^xsE2%`Jaat=zy`xda)j-a>lz;gz z_-PZ$6$>U*VZ;7xIlXd)u^#6#mFM7x#t-!sqoT$hfnk^(c7$zwSiRV-d zb`-khsK`Q$m~i%WiH0dO2~kv=F4Kvo1y@6air&yFdrb>kG)vkbVYbE)iBSeriO*YP z2I+RO=)!B{d5L^T1_vUGBPeSQeoNlK+Y12|T+EQ~s8_Vi&`R-t7!}Z9o8e@UIirAu z=GHxqFXoV>(!WzL6AzvBrYsju6W)h3pwi%N#oFX=mvXVQ6VMSjtS6UI$}|^91Im~Q zY)%*SQcx?mRj_1AwIWWAy9EkL0f+8`6`IOt9Ui20h_pCY6mbbxYKADN!U{LtLu?7) zMtg)K7k}rr6uF(L=He?~XOdyw1; zf3h_lg3Gjk_`sM5fk@#29XQDQRtkgH?%(RKy5fNmA4z!uioP)xXxBD6-%La~)T%|N z9`S=_*2oD!P$%TgGju?sK~}iMn{OAd$03o!0-5(h(r0an?*VQJ;~`D>H$l~LqzUPc zIhf(a(n&4Mi~;eBPM9I?*^A-2FBe&;v3gl)EO|#-Fd2q&JMCqtO_4k72dCfLZp_O5 z>wCHFqUULTId39zNRn5?D^Xxe7-*OoWTWtkeGEo9g0r6hSa4w&0U*ut2&rLb?zt3N7_o zFC67XRQIud7}m1=Kn3JhSn8D31okt_k9Y^fDa6>er?HK8M&;E@Y;~f)l}_NE!QTPj zdQ-42zFm~g)QHcJ%E5?L$IJsF+ir}WvoyL20bXZm+8Q0@FEQh}Sx?)s@ndiN$s=3g z*eWhUfxX}j(x}TG{jy(>fjE4pn*}i!B`9B%Z^0w z{_MN4J4hO9$?A3!3(`~u57?c22d@f=q~|T9G`$}Z)SH&Zac9Eqcl!!Qm1nm;llZh4 zMYTq~d*+pm4Okdpxp_# zCxNm~(y&66bQl-8?v@!Cr8)J+i-?&xB@~x{sdxyGu>E^=v5*(th}(|*!s5bVSbcMe zcj>$Dl|=GP0Q`Bfu!4Liw+`b0w@<@bE~|>>ltMI*hLUfw+;gH*SD;)tuw-I981=d3DlwI>IBM!q=!Cm4op^~$ z4mruk+>X3kYq)vD2#_e3oMZS2v{k{T2|?JIiE^0fEKPo}ESGY4&mx9A=Vr8cXWAZ1 z%6^XAkd!t5^6Zv&Uk(8g7MaI)x`e+qISK*nz>;CCpbG>gXq(`WU>@sC%K`q58tmdlFUWaPkM#*vo_Y& zFv2!8>(-R<4#>h^gcLnBRzF43V^xK6cz6${7*?VD3g$hrTq*lH`E`g^1S!~!3bMbqn zjBlDqc;i(pa}ihziBUiG@L5pEz2$tJKVWnP@`f4Z^@q6Fr1ZRpzy;IweBgx@+x-(n z`9UO!J6B;w%6h{p(LURXN;eJISD8{ZDToO7f~kosUN%WrN$wMK-~+&4Ac`a2oxx#p zpPBcPJt{$&)0ViRAuk|xQv zDJ3U-Xh%s%Pq(|hwv|)v0_~upU)E+*D2~b*4 zS#M!41y(=gUEQ!xpyJfGq&|M>E_}0$U3tU}(}7+6vp&jy1yz4o!l(jc*uExBpyVJ~ zhbWU)8s`|SshFe`lFIkWmV-;yE4d&)n}qZ7uwYMvOTc8cNtJQI*Eq#C^4HY{31|48 zDfRSfDwvRumsr>ReBjJf-H9 zwO?v0=G@-m%?gbR7xq7@XESsXJ020qNas(;%lz(FTRv57k`FLmD0P|UH#8GU=Ez2_)WN)A2O+VXfiF(8|A}QQ4nU~tivUJn_uU}(fk1S_SDmfrw^0Y*K#D3BntFT zhzhLFpKp9Bc!;68wr%#9ska&mSPqf+yRnRoQ&Npa4b4XkJ zy-(*RhORG7GDVGRm-`*evRk@A!0N^%UD*iLBastIrB;!mc}(<$QVM~3&HTT z%>TS!`c~c_Z`WcGG+*ts5Li(_U+6z50%mjjfgZ{|y5Sz=TY13Dl(^i^=&gZ$Q=jMG zQ5i`*4*t>@3t~BBX@PJR<^(==l&qVvL4)bf8gwLmjN0WTw;UfOQzZ}=%ScM`&l>3q z3?x4un2(~>Tf{?0L>$|liNg!G3xW`rgf zb*!;(>P@SeL$!5o^m_Q!Ls=oI0e!j^-Bdku2TRI_*b1o(eWa8?DH2H(<79wLRZ5f* zr%|nbSA}1nDU(`RvlA*zT6EWeQ#uHgeIxX}D!NTB*)As?&*a_da}hMPL6(g4Y>1((8-1$7uv!gb- z`C|UYojgwiN!qRpOB31qy2U87ucib@N3l{S`=@`_6tHEurOaSU3?gYK;?ngiQD2AG zMB!B;*^5hPA*MSk)5oku_?A7JS>ZpWw99})@ z=8Or5b`s_LrKUIV^DZNu@@>Bo%!n=URV#62Rqs9XvwoiPvVpr`yl?5xR*UEhH|61t6lO7=K=yv{dIeayhHEMja>wvqKb$ll_sB3_V*xS@bH)i|fG0`i~ESQ-X(0$aB zuA`sUY~CAP>z^CKdNCgrbi4@)Ynz$^E-A~+BNb#C4(34T&r$Q~YGL5~Zk#Xz_2$eg z?$uA+3Z7o{r`BtlDcG%EpQCB4*JG%&o^D3cfmTMSV332WmTpyoR zvfUMO7yzt4W4kkSPn9x7Ioj}rfO9OD%mCsKzx{oEL>Cd0`Vl0UEeQFAg<>2e$7ox4 z0g97f>@Kt@B7S*JHTz)!iQ)OpfhXdCF&9z(jL2Jn2Z|=kAKC2#r+vRa_cMQs!wV{1 zEy52>N|{zPl7)Y>n5hLUOjX=#U~Ckx(qB5^eKI`EMkX?Z841p?&lXAyvvxQmb1zaX zY|u`2S!4Kh|JC%*2@%yyF?)5Ud5I6K5$ogm8%~b;+LkAk<<~zQ9)p=d_W`o=Zmb~u zbG9TW1wxk=9M{3OI36GQLg3zr2VuT1?cm#9#XsW$i!RQIemCF=lW3A669BzZ9cxVi zx7)=%|Be@iCGwP|^WAmnL;cj_?h~SNH+Se;yPq6W{@w>tAj1`|q3R%gQSmU5^Y%S) zVQ4a`s(F#foSs<_Yk~V98O`LtNc*vRb-oOn{+;ZP^gq{mqtnOMbttkG?we^$X1?-S z+TyG5JzZLQ^&FN=G^>D@rtD5y<)H}q87gVlxKfCov1K{@Ko!_#3;>YWGLv|vh>`G) z|F&J4oF{ArP{JR9r@*}t>u;BLL`Z_^DJUsw^bNk*0Ek7ygZ`4Wtua4I282=HSq{6H z+N(}a__|moWu=)ZQyeFML{Oyhu!`dxtXAU56`K{>IDRMha)FVM9P=_Z3|d^CnlAY;KcS05A103Iads>@e;89m^rHG{x-AEk1H8cU|H@{bOpNvX6HCUzt=bpsHQz~5R|xLuQPvSoo`{4QMe7Wc=y;Q(gy<_K zh|QGywfp;ZbeiSoi3KM5$GPhKangTKh3+&1K*U3lC20=>OlXj@t^>@;joZQX27uRb z3BY*4F(DHoKt|LF5rD`ABTShh*{{5Eix^}l=-me9Xi6d@28S}Th2oRsIoqsRsDHaO z?o6~n6jOLz&=&jjpo5R0o3UP8{qke65!G+>$5jX@R`hmzQt17_rlHVjS<#S}4*lwo zj$|*wnIM@%7sb^FVU`E0{6%}0Z2nlxAccTORo|bu2M#$kT^-ad?wz3s@HP@~LvfBU zDf3{gRdDaVr9IddirG+14v4;-nVgeaw%M=A=c5%tA}AZmaJ_FTV4 z7nh1~(NSKABF{@$ew@Iy$Y^D>7DNg0^reTFB+zKc!($NWT~4;c-L=CN2-5*>so5XY9_+IISolPW8jx;6&Ln=y zvzN;27&&YDa@nuHpz;}TE~x0(wbz*>LZ?KW0@4)_A!%y5){-Tp4P3CqFVrQwVZqv? zWq-3{wJwG|yQsEB^>?{bG_*8LqS=({VsCoro32gAamuLmx5J4d4kHrgaT>=+jF(`| z(Q4!6rrO!K{<%(z#m*%Bwh`p{1cxUTnHX;rdxp8`YX>NjsOB7QT`e{6uU~t zZJ;$ydZr+>3+^MJXPAPHIuOSVW`;e-8+?dP+FAO-4TWVleKM&_lDC&VG3@fff_!Z; zhg-4oreBX4!M$tskYFHF8)?8)l52{Z@BRqT8?%&8-OV}LC;V0WshrNt^lbjn{I}^% zgA$yuj;51@UlzG`m-|=M8k!n< zBm4DL=lo3P{GUFG4njXLWe{B#h1b zxY&utjPSK7yg_psxsylcGgRE4VYZPXW%e^ad8XZ!h)mEcJI#dRyRtXDyY7y`m1LPQPciCEo_x zHWuU~EzF7dndw=vM4oW!o?Q)qhPsnSCxK#I=jxhHwGH?EgEEo*gA)X6bE1x_Vw0{kJm72vU&}1b z(JYMFbM?u@Hp$9vqK6vPn~Ih#xrTjiLnIc!M~oH3oO-;`;}4d4iu1EqfHxBJwg4ndTK3!=hTsXXMs=P_m*B9;S=&at8fvm2fp8?$t#!9w_7c6Pqr;QiaMkDa7U6H5>aBCB!J zW5yws4Jz?W?u)aZRD@Ty;XDQLLTxf%MKkS_fM3YGd=YIJJjZOPY-MDxT#SptdbZi%A(kpajNbZ_AvU1NkqL};1s1ApSGKgIyjHPqk9CjT zK0f=FKf7JO;pWmy=GNwxB+paAOD|D{Zch7(`)&!Si{)Gv4vOEz{mGJHp=XvR%g)@{ zu^oD|vGd_%M{{YR>rL{gXDr0cz$gBIj?xuYlD8&9aD7QD>q}@;%??`6sdEZ z#~;Zb9%p4_OdmGmZsIncf!ayU$sRMBZdLMPoKZ36ReO|k-pE1@Mii+f zHwel?!h(P|X&_bCLZNfzSMIFaIB@blbm;Kz+s6`kqE?+OU0{lqu_v+!&t1U1YmW7) zT3X2jyXfB(fDZfnG{v`O4!I5r%zkPJezAl=xh1Y3mR9`Gl^ z`7^rIzQiR-M*>cN;eOi2ot8Yn$Vqa(wpg`?pdPpOGdePWE4Vqiwt=J>Z&1RKS`>FLcVbn3y*2u*rbxgD zdL#O*yJERrY>j@MhO--S7nd-_frP0KO2d&CGyXT%uSe~Chd0?78*^K7Hx&-F&@j1) z_|qJS<;g#-uWJ%{#O+cQ!;~FlmP70q7wZ$PVO(Jw-P&}a74TQ#;WiSh^)R4zTiH1! zCMI)_Nd{zjLp`ZT0v1SUkEu#lj9omBwSoh`ZwE)**yx8;MBO$maWPhBNglYE`i~*i zJF!-PORKgJ-b4`YEh(;Y4EON@`vv5Tzo^wWa6T)eI7O$izod8JwWuO}Muc&hzp#?L z^y~w5x5ijjkvgZCq_$qXt30>F#yCZyXA5Bbaio@#p+pkYsnnM$Gi8KY>QK@TCKFXkQ@cqAjNV2@&5g>%F*`M?oWb38f`N3;_W zBX~-*8;s`6h6{N6NbhjkHG~_wqW3CYB>+)y?6ni*dlY~SfdjSda}2)9{+~AbVn!BX z@TeqWaJc&s&c59zU2U`cpIXF!Xb3-~%SUHW_*iC@M-O1nyo-hC9q9^=++2}j%JX#^cxn>o2S8wO^-S6cZGdUMSh|gd0{t?yygEU zn@jxgv(7O0J8cP5vX7D_Nbm{_LW2p1M&Wv*75%20R~;l)ZA&XrDKBst=}ws|>?qM(_7zd`sXp5ej>+2HjQ;LOiy zgD4r(GgBvN)o!gQ2KniwsEJ@n_IL`pvnR?Yie>hG_k>Ao%#hm{xCNJ2d3quNiayAV zkqu_VCPGKE9g@YQF$>Wuxihh8FQuZnAHhFl=A~OL#H}XsxQ!G7Xgo#?D2TcbpN2vy z@p&(~?Qh@MPCG2@Ukj=6tXi>_#7(?@G#gi%OlM!6nPJI)#(@ogm@~i~l^MXYH{U&&>>}2gM^_Mwi8k_ugVyeuD31?ym;`0JzKB z(v_v}i#$zjY4lsNuiA*F$%=P7b*!Ntc1h4bcttQP)^+{e9OP`^&2zdM7Ypv7ZX(DW z6XZaIHdf}*Tiy>IFX|(ub(oQI}k?PKpFae z3Xt0%{KQumPti^Bo@Hk- zB&D_tG&nPdM`DQ}X7{pX>ZDb2sYO8tyK1-b9?kdn>UQ6bUkMyAU>J%CT8#bmMENG?e#*U zx{fy*q@4r7OZ?#gy)O?2e$piul;2dOp_=1V zLHCfc%>!Wf=WZbZ#bmr1Z2ycvA5c=%04jrYMsr0ufFG|9o`UF@#DMu8d1^?(0temg zLz1vvWtV6-a+*3)R!(j^3(d_E#xw|Q)(97W6kfVu4MpJ>OV`7B3tnU^e529?vrdvCS*K`*85(FgGtD{CL!h($gd=a zZh4?c4b0={P~FkQJ#jf|o3FicgJFu{Jt{tD-5@ok7-=>Y2}-FRP{yx!_cff84a=;k zi6$VoG*>)w8+xSrRueeHZEbe__yG7jU-o8D>{r9;@>g45nBXepz@K26X%6{txbh=c zgGi;ngVfFj<5)t!m3(1p(oIT2BAaC-nQSW&EQOAQZ`hjFV81t&$(T=<*(oi)w zqFv`MpJ%CtB(-x%Dkzpa(J4YS1R`15h(PeOZm<(FipCp7%!|-xvV}K(@xhYFAPuS0 zI?z-Z3Zz(-e8zllgYdgXl=MG`M2;#Z-*fnp0d)sAtFn_otNhU6;X3)RK9n{*>x~4J z!M^^ir2D)*MYnFdNQalP48G>$fQ#m6m!N<&@IB(Y*k0FMg~;q0R0UE&gU;6SE8A%n9v3(rGhE${$uTFU~h{_-*iX@kX%ffJ2@;l$0--l$Q{67zYsNlDICU#!m zHh2br-NY1pTYY>6ROlca+I$x}VIj3;=>JJ0Ir?C zb7m%go!lWSy7VSfRUlPw-}hzT1gxpq-qDUVAXZ#P1*wx^WcCAaaLGcDn)yQ!2=$x9 z#%;4+_+y5bSYj3cI`}uP^9w6Ueo-D;Tb6Ql&{Lt`knJ!&Mgk}*MwBP@*psQuxBh=zrlL}&QZs>=K-EtvpR59fXVb{YwVc6K+do;nnC*YM!?8e@>#;CEo| zila4X@|G!5J&yy#2{Z4$RZwoWjndt#wk;?-Q6Ri_D0dC;!#Lf0N2^Uz z@EIL&I3w1D+IDf;$($(;Ng{C510^@?h25pxoc-Gj7^D^l1=nWBCQhHNJ&EF zKEO6dlF=$bmEqG9W}b6WvJGc|}mD9r~pY>?d8~G>^&VyTKhS z@Ox@1hguujeFo!+33k$lYYQepf~8TT~P8Bxzme6+JBx|MqqtXL~i0X zWum9v*3!Q3eV1Np>y+O4C0lM^IyC47E3-*0AYBK!Yv;>2=C`AqbSTj~iT3enrq2$FxHM*C$I+}uSS-0Xm{XCL;7%3yp32d=B3 zgWsLSyuu80_{36hx7t2Zfc>OT9)J)o@l$*-4d@dB62jCRPZDfC{o^N;sn$ff<$OC=Zaf}^q$J%O0>vkRM{)5 zow%Nd17_;jh(s6eJq}!Jb&8* zHiK93_|-VnWE&BD14Xm@gpq8Rk7w<-B3Gmd5pzlIKe8{6y;&%yG0bfW|AV444`lj( z{P_FWWroc;_uO;Ok()O6-JHo$b0ic^BuVw2`-(Y|q?#*4MNvpKB9aQJq-#n=spwSs z`uz6$cmKTi$NRm#U(f3?3s$U640d??IV?_-v?H^%h8OqD?`&e2am9Zhk1*64Hd%1m z6FIMczW9Ka^O=M9azjSOl4U4GmE;xVLr;yO5egea4_X^nG98v{qQC8~QBg-({Fy5p zYs3#zo`#@Lsy*}=3e`zal;(PBkLOEs$6sX5UyF2s7VcI5(42eGG>5!7TN33|_u7Hy z75HMC1A!ylP%tp6uN!-fvAP@8o1=CFnR0%GQ9A87bNus?GbRZUnRYk1T<%5DC@$d0 zki10W0Bq9+65dA_ca=B1in0odcC49FHW}_bNJn~6LqC!HWJFoXU4gOTKDouh7)_o0rjew=Krjk3B6bV*l`WhunPI4`m~wr+y7{2(4P=}4%Tekb3c zRe#GQ@>T0?qSE%4pPl5y795BiU#@cFQqJBdo)Jom@tO>=4(&HHAtu&XiBzUcy0cWx zE;l_?QKWzPnLFxD$S2j#eyhIGvNizeb&s)Q1tj_m|QS;{+_5ppKSy%`|XEaVp=2Y0%}Y@2JC0$

XgUd2vpcA=5By1uCOHXOPG&K|PRY6AF~~8a9R6{DP=|aN ztchRXx7UBd2{?`=FU*ekV(Gc$DkP$z!#$CR2Q~(a5BuVK>1KM9U_*QB)G}jTlGX>j z3Y9bdlW?dv=cofI)0}gToGbpaC9@V^NHYSgF3yK~Dj>2C()<+N+nYb%f2}-hYHpZa z5%G#Jc>lZ;&trBZhm+!WvbCIUsK#x5EOTGY*(`}GZ&G^ua19cal z?JPO+_UFehAE;ci0r)Nal1+bzqcgbI@OVT5|7VfjgtX>^FFrQZR^&0#m>8TlHMsds zeB9@kI!0v9s?(bM%7<^-!fIx7MD6_z&3j+G;~j;(VK!I(u%T!ZINSUgQk^G|%c#`_4 z=kzGavfQIkob*u-1-n7H{i|~FO1m?X<;>1FQU^`UKj}$!Nv5tk9VRLB2jz4b^S}H* zjUf1LK!SGGaSW86;N!ayahhtdJ3}hGLT!hCELTRn7r~qFlA_&Jk~bv}Go(B9q-KH< zcTo5n)Nh4VavmhSSQVo))XWA=-eHQb0^(K-UD0Ak8b|pWUz`~4h;S5tn1}+VDSt|( zmg%B=fcOFk5F3>YG2M{r)H^`UkfUBiy}!1te_7n zQNn`F2PIkCBlv@)USL9&A??2Je@d6to_2WA878XxgbP}Z0fS-%rn);MrTK$ehJ$j_ zpuz)$G{za=bKJeU)gI!N%t7&mZv<(E6v|6hHOZ^f=Yqqw;hf;RrvleN zQcs*vsoZ$h;(}!yAoLRM6{kDr0n?Ym+w2P&5|>lfDPbvXUIOwl$7RoTcWy-L%1+5* z+{LkAQRc-TEQvRxN(azqxIg`GV+p8DN|D@yWGxI~(;A`q#ENEH$*54oB1PIErQ zt7W+rE_*a&6I(6``jMw;I+u`N4?A^biX0j}SxZkN}6NPlQ#Qc$wVGGphk(=hK!I^_kYyCvmJ^$HR zG{(6i+vXf*qYrPz?J)j*@X^EdRIwn@wS8sRGCJ>rz|QbBFJNN7^uLzh1NqrbR#{i@ zH#UZ~*!|<{=GP(*?0nOGU}21p?*K#x=wHRHM3&r|XwEX4j4O9~>qQF8)o`g-4u~Ij z36OZ5yIbTi8pzB!2D|_MojD$l?UNuKEHlGBoc*{hy@&JZXGkw+G6vH@K7On?_YAe~ zf!)GaJ2ymbtw_ph(!jdV8N3;S9GXPVt$avN`JHtedkRKQowEMUw$@_!o?hrpY|mYo zdDBLaeJ)d~@W9}_F^U(7QXPd^O9?0*BvkNBAO=SFra^*xi3RaNlXb%kGe9E%s(>(dpa&4w}0?d~G)+cVp_mjLU+1 z607Ns$RVKM`pL?F8CLcmm2W)WVgIDeQW8yn4BxMQjlCk5`O@yX!_M4}z=7Q0%vjon zZT7Ak&u`hk_!^+FhMcRpllPz7n}v)^d(~S%^}HIj7hrD+oTex(zYc5IG%{@fAhRqw zKy3Q|J&p01VVQ8Y<_xB*5BBczNxY3qs@ zk4hcCbAf#oJH1XAN8YKju8j3LWtsebrmu3>mb05V(Eb1y0Kkc$h#?e-r=8nx7m)NV zN`!mRBMqVZ6FxDZ0`aJK0uVq-c)O;G`W8tr0x;up=;y1JI(IOe6Po`@>zfP&9!&nJ z0Cbdg?R=yiJW!JyJzA#bR&953-_CpSw`Tc77Q#s%sKd7_95)X>f22P2M*HKh7cOSL= z8XDyjlb5tk8Axq<-P$ebW#ajw;-2MvNx%c^CF$vVWx-?~5S}9 zK18A5EI&!>KD0k1zt`LpK5gtj-Jyr^a~X`Ad9;Ng7Bu7cu;1($RhrC~oy^m{G`)4p z?Y-u2Kawbrb@%#@28&^?`s1K>Ncsu=gmg7|NBG8-9&tnCsH&M=^~Zwe;`_Wcj)kDo zS#q8izPUV!{P2i5aGtFzK$P5XqydSeN|?#LgFF472*&MC%pF?2zxDOumP1e$u;*l_ zl~dob6RtCNmPgKjQByt6M?vwt>2G&Z9}5)z_xFMEUb&>2*JTXxZ42dzo^J~<_{nC= z18tYrx{G&9%U;@krf3&HnECc&p=xXC%;T@&dE4}zvUghRMV`AXzpLV8l28U_7&&s# z=C1u=-aBOH&PSi>&IL;Av`h=y<{#TkJ~mo*F{j^nkNbG%%Q|(B%=Pe4a!Ite!X#?fI1jn;jy?$DX+D$HTf5J* z+zS|0&oaaJ8&I;aaxlxK$8N|8&BYwdFxhxQEOxJZkzszDAkp1|ZdMtmMdgw462P zHZh$eeso+vG4@Z{QC{PT?KaKg`!JH)fdJ}@Mq`Xo6bLyNxz6N_2mYNoul>`P z)o2|x*AP>z&md_`cWYNsWA6W9evA`r^Jn)Tq$SS@PHsBLbC*3af$is@q-aeje}qJI z=bsfWtokGYWA?R7LeLt21HDnO#l)Ng%OS0(g~fZ7;Z69KK*oPF5LP^s<=oJy;ch&t z?e!i&onBw?rs+-{dzENN=|oWOG|K^#i+B~Fb)kylUH>J@g{(X8k*O9K`OEZVRQiz7 zKhopKjIZiCJOsTDXWc`u=bFuiw|s1?=^3B{y(=zXV_ixjI`+$T=!u8zpAWuzaleBw zxn(ozq7*q64amQf+;+dVR_o)=iygH^_wZrI`@Ren-&f3wSo&yp!P`ACGa@)7^0Msq zm-kz#kyRMC%UPmK9wb))x-w~@_;7yvOS1$&(fn!OE}VFYy`Zz39aY z_=t!mvOfjvh^jWBT(}J`%+D(50-*8{dVM!eM*L8(p4cJ{l4L)*u|6@ZTpiJSQM&}9 z3w*ZlSC(ruOGp}m+e4k?gtT?wJg#ws8oZiYv>qjzTtL22)8(q0DQV@*8Q%gp$u$Xb zsP1azkTeBQr$F}qq4{nITA#YZryW12UU+d5#%M^ zy`hxra&A!El@AgdfP8-WQ|!?kSUQ85L)~*t1L?lv_T&VtJu`px*zW8t+jxUI&Ky`i z4m#7gl1qvQ@peF#ORddEKM6G6%3z1|i?JNz36PMu?;@#T5@tO-vA^*_ib8@IT2k#F z&KiKE`9&nXxNQW#wLu9Iux`NsPjTi?9iRG#E4Jj65cFyN#$*qUtwN# z>=`jINlz(fTXqjMy5^MEU{Evh(LR3xCe$XOD%$k5u`%9hP@P3{|$vY_B7OV)Rer`$&j(;BPlFjen z`cyp;pm4nXYPAcs6^M`Sgy2**E*MLa zHZ7Aa;LO`Mz)sVh8gA^2N7jN=F@&$-y+Ut0?Eq=V6pAR0*S~et=l_Fi^U42`5`)8}A~xL7jMs%DzO$%cjDjOyIaInQ`dz z$}hb6SuT}Ad6|xQsvwrH?7J*qW{uw~oe`-1j}@?>M*}xvikwl>#6kPY?WQI~z;%TG zvf^>VNJH*t&Z^Vhff`0n{>IQvfuqFP%+eLfdtl6)r%vfJU02 zEZEo3h{v_!pVQ_;%c2_Ll+Q_?P(>#+=R=tNbT)?XWz>Mf6`jm1f*d}oD|{{!zCWJh zet&akdYHdb%fg!p;O?*J5Zxhne3hp$=5%}IdZ`aW`EEf+*->B%KD_8g;2}#t*f5<1 ze<9*+cuNi}lz^cIjae|^ zE_&Y`bQ)7!EFKEf6>|`r^%RxW<)dB4G(zamtCFOFm|N-fZE-_h4=!m`&}*uAM+X1t7`0kiRkS=W;!c6B=$Jr$U#I|M zyIZrGhqe2rv3VMs$KKy`pPR&T>G+7UgN_#?#8wrNBEL7`5C`lkv17KYx#cO#Y zX(nG+w1xNEO-~eNLz|AWQO7a(HwAnw%Wt_BzxpFj+Ze!kqVVDLp;CUT5rm>rcn<0h zOv^+vzKKtY;W4Wy*RT7vB`aueM5*I_OaX3=kCpw1BA0W{-$xrvg<6TAidZh;EI3ed zoDLa@-o+Y^VKaD#iUhcYF|jB*WcBa{zD>`#0X^qMC_?^5(Vd&$Jk%I3(^>v(b7oaloS<=T>VNy*{q+#-?}tvzO335GwSqdDcX2v04*(yn$!0uvEUNb373{UZp1;Z{*X!I4lc8c_Wi%$21@Mii@ zmC4330Y}jN>|FlWmoMhJsGin^e)C?v&a2cv24l|u`U|5Ww!)aV=_Y#* z4gbrJz&DXW&q?6Ec`JE+$Bg>7>5PDTQ~r>^&8KM_ixPitI4F}7-}oy&UoD{}*#B(9 z2pim;U$Faw6h*&DZsqXzjKjG&_qq-|q~>IXuB z6mn(Z(vkgG3m(kZW2XkeN9Zm?6iK&fuTuUG=80{+#jw$$y2>wRP%!j_&^KKI`O;I9 zDf;$E4zLt$(y()cg}y1dFBtLBqHhR$KAE>#H0XjqQPsDgRL1r<>rWcQW7{w`S+6JO zuU=mG8(26^Yv8^w+q-`VBC|qV4dhgSk<@xQZIr#t8*3M*Bn=tIaSb`U4!QRM@z-31 zn<{S7H5}Usj#~N$>RMuMNe~H;Gws#03i1CCkXYc7Ln3Qd`@-(LXAUgbRe<#z6Q6d+ zzM>vW=V3#yXlCq%j98i@eDT&xCW@XIil_VQy(v3HHG6}6N4p{ZIM$aHt)+tt6S$7B zMBIgIChgohpx-^8~m-q6Il@7^{oz(PL{rJUm~eozm6BBpr> z+9&X7G2SVvi?e}*IE^w}N3tF79DK@0eyRWAiX0K-Z{oq~Co*K zH-GhbD0kN1)=Q8pU(ECC+1AJS*L$(&Xl1Q?A>LNP%>L*teA)Ib7|M^cR(#aPar{yX z{^OR<8?U~UU1Wd77ovOxJKDA^e~Iya`dcIY-7g_KBxvK{8 zL$eAE?q17D{4zbti%DO|nU5Otl?Hz`Ed1^S;}MOA+@fpS&aiG(o#)pK9(hS$;rVMN zuukB;TmN#7K11D_+j1h$!?!*0?_@4}B@gvL`c%r0*ieAqmKr%L?=*2VC{7={^DH-6 z2w^q@1GUMeX8z%XU<@6DKW>wDDkQI-bNKq{>_ffz^}X%CdMm@^EEcRZhIfn2Z7^C+ zmCOXfI1-BYSmkrNTvtE2_XnTcE zxZs?^ULJ54ZG)^@u^=jcNQj{`8WOh>u%!al=qlm9@So z$Ipk7=od~G3qQ|X^Ovw*f{U(cB(YF+`oAo;$a44>ta-jczz+xdo)P3k`{Upd1P%Q= zYec^l$@=^10ko$J3I}kS|4`F(jMBPzGX?$Lcc{M`GN4cV*9rwz+`rM?HZ7FL4Zn-ZJmZ?^YO)3Mtrm{xM?!iyAw)ZT6uCY)a?7Jy~ZF*WO{FBU$b!sqt# zaCq6nUZO>ADD1`4cb{fqV~`71c2`|(ay}x!uvnNM*N;e-iZ;ugZ2FPiM4#J*ypYeY z{FmRmLBMWjVO9|R_9>bzByRp4())E|vIR}RUk%I>JU{%uB1X^V27Jk-n9uHnP@c#K z@@!%Q$p15q{fkm#?Y@_?`OKqURsDqG$ON4)9U02e8!ymjvQh6YoYGUMA&0zrS1$El zE9m`|=U{@$NILkTC#7?`@Pm)asT3we%a}fu7kTfZmJMHIq-aV%Ev45JQqTApuP#&% zHx)cMvn6DhNC(q6Gxr*w9DV?7nH}D4Ku#ckeCh$j{&SlYk}pQWxVXjV4vDWF9OSur zMPX_?W_49&6MVeE^Xead4n@Uilhs$@z7<$s=j=?+aIh?mVOH ziXdm69aWI=H19dEp2hOj0M^5Qi9L?lr~g)Wc>|YvpmA7$IU-|7vDOsuaYlx}?r*50 zSf@|McqFOXZz+*Wc>ieE%P>tNMe)D{)(43}H~oB1&l$tgOfpqU0WmznXi_O-Y*<1?Fwj z&EBVM4&yhSpJ@whkMf57N^8tRFJ$}=Z(*R+8ghI4uuZkPl4aOPpoysE#TR`FUD^f0 zMhY{>+FrfMgSmYwl13U6_F(0@8i*kl)C?M9aNwY54zKvn`I_s)zx=n)9?)c=vLs}y z|6J4VdVK7tUKPRo>&KiMlA#YuY_EOUcsX!L$55Zt`*nW!?B)B1l}d)+5_7K^ire=; zC5mMH{Aj(*nj9R;_-XInL4!^}TOM{SwO=u;UQICG*!J)HPz0D&5NUM!Jo{r0_Nc>R z@d4^FO_hT;Yw|;Uo{3yhVSGMrPS~^hKTGoAU-Kt+`zH+-|ZsTuq6ETlG7U+M@3vg&9$GOH6 z@VvBBdgiC6!=^e2;@$DmH14K{UsFT7KR^GnNYT4}K|K0m|9us^spJr~LwjzgI4bR(Ef)9pyRZ87b7@=L4EH~ikN&AP=~wSnPBLiX zLeFHjNPioXe4YO|OmTIa-+dvu5T`uxpU#h}W|l`Tc%J-&FRz4xqL+9_79LU~rUXvJiKuncPoyqCMKOd2!8j^kskJ zBU>}afjw9e+G0exs3whZ`Pn`OQ`zsl(cJ!D-$Y980fz2-Nk6~X<1LW6v&ND)UmlgX z`6E+*y>3+Ob*5#Q$(~LS+vU`~>*e9y-8qs73(-ch$VK!lu!xnq+NkJ1eHj#~6BrCh zIT5H75KsSq5sr?wBX49&S#x(1mj7%R&I#K%ohsq42@y@n%##{IL8x+fPc7LbE0gu|)7-~)S>hDZ);@P=O# zEKMB@TYu`%LgoO3MS@WFB5>;WmWC;~8sUgweKSejn@LyP-Avp;z}Ti3XnLgPxOIQ- z@=cwS7kQ_1%XW1lNrvM{Fy(RncdXOMcWMx8<_>D~GB6Iq0(A9s3kGsSQ*kd`jdb#~ z`9QWelN1)S1c|#-FaeJ=TwN&~lF*6K7~{V+knEOqyv&h%#t^k&I@Q!)-Wqgr!8zt2 zXG2xpOhb!{;54rmYyHYD^zAN^YAPsIz(vaaZw+g#4q>z!qH&wzbj%PKBhExn@%04~ zdK8WdFS*?FAP1t*ff?z2_5V#h2301z?E43?B0;q-^0oF~_IS!+;^@vI3N7YV^GCm# z@!(Ued>_{>%}b73WmdLYQ)v%(PK3w0WD*CZr0Wgri5!$C3nd7w7xAZ$EALx0dCz1d zNtO!(V4X7O{!X_H47f`*tkexEe>f|duJoLuo+YN#6|=6Gu({Hv+;|L3TI3D5=W^Fb(dB;I)g>BB37d=z-@uGL{P}w!P`*~c+9-wMO0ONpHO^B z_~=kL^XuxF^57?F&%1BLwOkXoqT}{VdOeLD!|6~NBAK0#xDcsI>xJidJm^z3PsEbQ zz__z=3K)ZE^~sAOX#nQk3qI9FkX|{EO`2fu_bAU6k3|G1oe}juogZGukJoCJ7y^6 z`;&ur7~{y2X(t0;;*Zo#LJ|Hfl+Bu6kv9b-dT*ex+LK>!!-pV_(K7DYeL$EhdHnVV z{gxTe6l>KvP_T)Erf}zRv6ES1cYcm5Pa-%LYr2>bgVi7oo-E@+kNO1{TtXO_x&%=E z+6YdQxJodhb3}WA_911E?!wC!kNb|(qM0`c{Yk4W3n-a2fURLG)2tVblN8ahNk}U> z%5zfpG|vlDmt&zDr008)VCEO7d7t0NEN_y0fbG(b!?i?eSQk>WinXtkdeYu35v@d_t(dWl$8+QzyWRagQmE1Yx zIsGpp2~GGnPcGj2+CEVr;BRyT`_BjHA`GAHDEzs14Cg@N#O8TkzRLOn0TbbgXA81b zUm!X5xbc%k^CD=SbhI;nt7Ty3JLxe^myChqm%V%QQ7r)8-`SPy?Tk_&9_Zgh`T9>l z&s%wqh?k~hrJm)#R+t6;RZo7G-$!|Agy4uPI!>RH0JH)_R>ZD%%cEE(q|Yvn*Z&eo zTol7NbkLvs?9RH{1fnr=*8?~>xaCNNK#Ob3wqbJ4e+X6Qoxz{_n{!pOJ3xNtwmX}v z7(SM?x2k=M?c{I)qugsjcym~>uiqe1hp#?`W_e^D7b&$%aGiOw-44Y*c_KM1q;;!( zdT80rr=u#^4RCQks=?yWPb6RJwsP$&kkb2Z zBue>@*h+qO7oCHC{_iWlmvz;vjX|hp`mUW(R5f|b6*4x)?>!RGeaf0@F<5Z$pziG7#kKS zMS~V0CE8Y5f?MS8#~58fpqap01IwgV1z9s=jkvHC7Z%5oTq#cKfc<6wQV@VKFvf-n z&1*xhY*+8rMjw^-xXpc|{=GSuD0_cnXvUp#5xBHXEfv3Fe#Zr_i$`R}U+(u!rAZ zSOQ3q9~zbnDNY{POA5BhH#ztyRpmX#tP|8`+H7S6drYB#5l6XUkaSy?%|w~FI#7$X3Z%P==m=A54MVB1_U#jcA~! z>}ESI0~>Gs`^jN)7Nkgng4jxdbV!kyN?fgw2jHFcmNvYI+Fwz&cR7Ee>3gPfED<$c zmdr~{(1>UGpd2{S1#k|h-|1XO#TM;+W z5qjA&yq^+bn&uM%iCQwLu0Tyzz>%H8)M-OM9wk=mVEp;JN5&jC%mEbJoS>Gdo~*yx zpjT;~7#g5>=>x#bEgAX%7eA{BO_B1FGVa2iBydjRpQ0dUi8!TV@I*;aeZ(@3v@q(B z1YqZSP`iIB>2o)mZ_I$V+9Fh$vfjw%->o2pj+Xtt<789Tm)T4OHMD;p^vL71J|Bwz zL$A0B#R~$Kvt@h)AUdBRwE~hJ>9YZ*8(m$*%#84-U~w9H<{U}x_DbY1&V0b^RmeOu4xDc(=u?K7uyc^mfdF%|4|#iF$8+YRWAs{+GJ{BrO_TWc%fHjA02HRe{n~TjBY2$F;myo!7x}mCn6heG;IVWPWm|BrI}4S z$pe;}{1X?eFpe3GKewTzS>Pc(OdYld_0M;M@V%IjtZzEmfrx9gqFxPV{foH$&;H4T)ToMqeIFW)DO`Zno_;u;g)Lh~IflO66}5tv2Nl9G=nNlM>t!wvL3X&L(GxXQiF2B$Dg0b?{rMphrR5oB5@kPM2| zcC0W)HA%~o+iFsDEZMOCDbqdkD9@_q<$p(#Cb#`ZN9`fG{BPyT{Z$v4UzLH<4v{DK$H>=Q8)rAzwIVf!rOst1h79dN3ooXtm$L6+G?vg?vT?8^* zsWJg9g)b8)J0MkebU_+~`xPZ`4$;`CEV8!=8>X#*kS;n2*v_s5WoQul5%fkUUU_A# zs|2EO5#zU*ieHdSWTzGzwxYmP0eBdT+TjYBaA6uh<^6kEBObIf7&72N`YW8*g_|Fj zz}VQ%*G(|yI%w2+%!nCVDz*9LM7?7G+7N;MYC>mA;6suOZG`pAC33Ge#s+~Lh9S58 zaDU7OWbgwz*8{aqoR9=2Z4n6QfeOvwn3>6I)cCAXBhOC41nb0q^yzV?Z`>({8EZ_e z8dGU`Lepn@u~Ss}yz~E9grP~_(7&dJ>~dLe(`Uoee=OUGle^WpmKqD1HV6na0SN(V zuYPNnj{Ac%#UhX4Xa|PLV_f9pkPDC9LG-~|03ZVEB6s?xz|Y~a z3l@;_$yA^G{h!Dr7k)}Z(Pnj)OZ2l?Ro+SWK{(?As3X8E|4xcb?LRNgmYHuH(^Em(@8kx!i&$Ddmny=?fFR?dgd;| z6tzqat7VS#VPLt40qg`5I|neMa6BbOk_#nK(EP;b8Nb0#p9Ad#7{}NYBM(r8qBKNv zfj1=5bxrt&kZgdg%78O`Gl8^<`t0nYdrami=Be~lz9c0tS($VZ2N1ay?j&@V0038J zu5!%>0Tuf$h0$ES{W*HK`J$_Q0EM{Wk>}Z?^FxEM1Q*s!dLx0np`D?cM(Ks#e$#0E zc2lVvNLF%0c`$>}Onu<4_l(j-)p**|k4S0E*>K)Q5Diwhah zU?0Ac7#=oY!~0>hG41_a3mmQD_$c)qS?&1fuu{q-q(PrBKwy0yWWeU`>R5cd1hMEB zic}svK6t~1B}||}E$h&{0qh2p>md<&NsyrcWhR{71j--Xg=X4vi6+=20i;8T(&j;? zohU5`m04I-aYS`b@*QnDL=`{{III`#Qz`+Tth6+tzmNI?(NRhV1duQsl==c9Jb|Od zVHY$!S^9iu7o@%d8HS>bnWtw8vqQSzlQ)IFx{W>&u?HUf7e_an{AkE-w?v@*X^WRNt!4i%t(^46|BX%YJx1{NXdTbvFut zfe63Na&ygnL!Yf%Z^}9bnzcF(U}rvmd};;Z}}JZ_|KtRe;u^fG_s8<%GUOL|2t$)(&k4_R9YnQ%7|)c zSsIkg`gQ8rR{S%aNWSb2u8$U9XQB&c&D>9q1J8Lqxx;O8f+f1aX`&wwR@_86|y=^au|iD08x2Q^?dCmlF9+Nei=6 zZ{5l)6zpPlP8}mFswq(@tpd(K`c?M3>5<~C#&y^C&0pTBzulf=D4}Al8~bL&LiN!s z84w^6T)$@D=FrCvJH(+r$0IYLxt$9C^3;w_LGm#EaY@BM>%ua+d`Lk6uC#>MfgwqVG2NSaO0 zO&VjtC`&Sjj!|5Qv%~%jz?G6+0h%M>-aW7LT`}ZHkuP@pz+ADGtVs=9I#2A4v2vH^k^F`*ziU$aQ_wcQ@bI_0xI-I2H<*(Z|>~;FVOt_HSMgo-rq~y*{~SVjyvti2uXeP!sdDk)7MF>!%ti;E0AxbXIfbw z;F8#hM>kxlpflSm7+cT)j|e%I%pzq4ZCu!s2>C zYTMfDM#|M_o#=qD8XwD!qKjoejKoI8nw}i#)9TC)n+b2Ry zp(3;ZedR?7xrs_lZ+%c%dDuE^?n~-gY|l7c^C5d_j`?yvH2T7aLX$7QXUFI^cWKSL zgNxKfdByandF>(Pm_;HGI)8L0hVQ8wf1IeHU5lq<+n#?hAIp>3EhTFVXnk8w7#6)#!zx`$xNyv?!seJdPYOxA zFJo_(U|BoMz^Z&Hn)PV=mUXQ$_+FHHz7nq{{i$TY=wVurkIdVG*D0+%kL8QpziC>< zEG&mxWlS>iSF#Q`e8}Gt6DRT_;8e%!S0lak1;l)2?8%MjDnU|%LbcyH%)}2f)x$pz zTwt91?Ib*`8yhOD7szK`NDb^_JWX1#iURo|aAplzeT67GdqLd}5eL8Brc)UVj0u-R zKzLlGJxq+{B2LN%q4=0!w#Dm(yA=U2`3^w0L(~W{E2tZL@;2>DdHKaR3l<3!WaVu0 z_N%2R2u*6u%6Lb~XbsNC<3;L5TtMVY#R>8PKT0-wB9A*F%oN99PV`T;`D)tcrhW>H z?JjuJ`@LFJbE@b>VJ(?O2M?TH5LsLq-Ml_q7QOs{y13G)dO~fWam1J4Pl-_j`xGp@ z>&x@%xQ?YvA*FZBOpeDdr!7+O5DVB?NO|sz!63xUeeu$fBTg#B-08dg&Dg-5c`qch z+b5gERN!v8^}wAhA2hT3BLI*Wfw zXThQ&tO7YwfIoARqnV_M*8~`ww2&Se-qg=m5F=_d1WE*!oG1LspN)&4xPrp3IVfdvQIjgLrfBT>C)Ja@-ynpHF0j}p|3$Jg>V*9;PluH7cD zpD)tnxz?}$g7{6olcs!Td06LxkaE#vXE)OzZ^MJOkb0*c3dD^i-JzpTY> z8mc9wE&AhDvy9yDF}E$C^}Zl1V)I{^YDb1{2hTvrJLEGtfbYflZmdit`|DzFP^w}DB6q@l3 z$qc8i{!FM|flb<;7MJKd$&NH*bi zB$kHC3g;owm@C!lZhQtI6p5tnd5`r7?-Y$fvTd2p$?Vy9X|aG9d5s`Dsn5ERX$bt_ z)!H5Ni|$fMK(@{;s+b)yMY)C@t3*gu_s7+X9c7_H6X>w3)fGZ2D}QHNlbCHUSbB?( zBERP0_lH5%JJ{LOfCa2o8YIqIiL*}4!mP5gcm14o3%Os?(mYSTd}fv?jDcQX$as2!bbq7V?ok#6io1aN zGA3D-uq8-AZ70l=4?e6hPEGhil?bHthy+$C?xCZi*n=2T-qWu0H5zfJWwGwKJDpXO z0*{>cH+6X*pDbQSNwp7Q^(J>(B9ubgW&oYFi6o_&3>nb|eRWtIWhx3?16SNd{G> ztMc@^h2mYuIhlI?-X7a2$HEDQhzF0;kk- zUgU09e+AyegsL@gI^W#)k0BxFj;8#jH1RU1tLap4Xoe9&`APl|s-jG|19!Q2}9@(_}&&6rJ4waznD_q8V$~k6p6`Pr`gjT!~DGs0`CUR*6r6HmU8g zQeS8~_P0c6b4gH1SL5JV`o&y&+qhGSVPM|VA$hA=$D^&BmS;o8-q}Vtr|nX(GT(Zi zKkhl-;+dJ~J}Fv92In;exhv1p;v0jLm(CR(2Png~nq}&AuC@R<^AAv^otqjjP;RYe zeaz|_@7-=zwDXOAk(E+eTs9vkYchFFnswY92ctiAYBR02WQa-@922AKU66veu9pU+gtAn48@rh67?kKO1& zvZW>w(k$`8#v97ndneDCqP9M#k z9MPbg>kpK~{Q#(lEx86b;9(##*89E>Jc8;mCyM3dz*e({B#Kg49UziJHeo|td{ZIQ z=_<}i^I2nsY2Mux$052$@vQE2m&#$dN6c%ulq?U7)tyqJj3pO6RTOX56M6i$s!9ZS zdfVe=2!x8iCJAr|aUg&a>GrIzq;SL*2TB3hwjhg&K(;t9Ti{-3;Z1xetlf%;2snj{ z5S2J|*tU<%JbqmPj2OJu&^uB*%Q^jKH18ka@m%+1+o_wM5aAcFuoltAsc%TEAre-b ze^dgtO$7=5JyZKE$KHSmOR};Rki;0G(ulh_3DTkpwCUX1lwwI1C%08P)bpBT+-Mm) z`}FkxQFP|vP_=&;KeI1pm>GjH27|FC`!cpV!(@vrQAiqFC<)1umNR2XmXI~6#+t37 zRFt>IR+P$CB=rtSl!{iByubPVH`n=Ru6eF=o_WrFfA7!jnn^*ZVhJZqhwi@6E!~P> z!eN;}lU0104~LHf%-O9FZt}EhHAEWEc{nX+EJW=7gE_;HGG{dyjbC^Xm}N0+enO;c z#LL<^o>2o0W|N4Nhi9n;fM}Xq*N62RR*?J=Jo1;x*LA(#mX)_yet~*x<`)sR+WV_7 z+orr&sh~l@7UtRL`b^~davGbK<0$pd@b=tRHi@Y046_Z%vWQJ1v)Y&8imsJyc%Y<@~nC0H*uh}!HYxsf`dA+;9bm+^p6OPx3Yk{chFq|LR zQoMoI0Gw-w@SvVJ{fTK~y&Stp+qv=cZS26g8yQSi|CDqr2a?iYh zI~hftnW?^c137t0e4-FiY{1^Q12B04Ew z_BDVbejOS;b*lGhK-PRpi<2>avH?=$8KDu^YJIR7TlxFPA#2aPq6OH#V5d&DVBc9s z3{IpTf=OI;%Oaq+7W;2lu9zyNXTraIDu>mw z9nb5uz&_EWgVbei22HRDugjU$QqyVt?IqacYLK(6)Wq{QFv~twkoM*aM%yTx)$pR$ zE9?A2wmvm2g3k8+j@4KtDs}ei(R=|O>Oj+361G)CvsFP%Uaz&t)Zx1-!rDZ3#PXp$ zAkD8%3FnI^r@kbG3fRd7*>P~zLr5nZP95tD#uM_lrrpVg1v&Wa{Kl=4s$P%p=I^`R zqgdF?N<%P>*s=x6dPR`+s-Gn&B6?on3(^>ou;(FJtU2KQT#F|Aln%tFumuOk0g8@+ z<)j`l>+vle{U;%UXbLPgP|yY;%5R+zs#udXiA`wQra~WCpmtztAC4h`y z-uWr%o~cQ*1z2Z`5{*PWH#E7^^aUlDKVw1&TBtehEV$jsXO)+4{)-83(6_h8R0m^a zX8~F{cWDLnO%whj>fc+jf?`Uq85`r@tYcixXZ`LiDsSMOy~%Y;t0w^yZwBhK1%CdD zPlxwJr|_Hfu5gbwxgQ9)Uht6E!FTe4A%mZXs=@4fwKXQ!`Lgx}m%d_Wjh=|(4zY3RHog^*SpbeN0a}tH z3HEt`O((M_&nyyN_yLk!9|31`mUpE zl6Kz~GR1FxD8W{0ij`LRadQyT0T#6a&^Kg1de6%7w^$hd@ac9!`hN^QX z>J*H1#%rb;Ag)40UWnAf>!LrNimP{JoDKJvKxb{cHtE&cSKK(od$B_CSoJ69T>}i` zuI81qcv=?O!!M2-?KN%Na`O*0LzGst{x{&Um8<;Sr!Ai64#v<_8<@o2!5vdBl>6C= z4OGK!J|bAj(w~nc^QFgj?>p7q;Q7Mmd@jRN-+aq%nYWgd1!%HWU8^-uLt5Qtj&E^O zE9cldcJ_TK5G+0iqm%=Ajw8%!h&tSAMdL>b7VzcvTH>%w*|*e!Tc^a^Cnc{P?gbPq zGh>-A%d{qX@(&$%N;*d+vm=ZF0aZw?*5WHUr)khO?8C_`Fs&6DvtH4Oy`JIM9E_!z zbp```f?r2=rj}GWzjhb-p#Dgh5eON=if4jd2Bv@018{Xa5xCNMptsn5a8-zOPyuI zFaS1e5;HFspCcT+fVb>9n_rl#E`ljHlpRvsI3d1aHY_mw0JHI{P#@qcug>n=)vUDu zV=Tb5c(P9?H%i5BtH$kn_32`^4qSN>7C@Kcx>H$VK0^#6UZ)|SV^ux3%YD)M)Bv~t zz`yK^*DY^X$+}kSTT(4<9?OO;elRZW$tv;`sL=$%lIV;MND7$Y9uSJ#4zAtDBD)~x zJ6PSx#$ZYL&t<{npRN@lS-kKz^=uZ?^ITHNKc`}2&*&To?hNqc7bNq=-_JUvy&_TG z4Sc-oJ|$Ye^*MMxck)teLp|~XA=jm-^FUFJ@r|o;QZIr_CYvfXt3RKB zeRb{v-*QXky%dsJ2>pIRoH6)jWc9-aN?O(2xCZ#!6qu?ws98I|r z-Tpn6i2I6dB-|O%UTFiSnI(fadH2desR5_3Bh9zjxFc7rW`J#INI+*tm{H&9xT2>qnF@QSdrF+GFDz-Y)oq=;c=EkS~T}DMHZp9ByI1A!}bc zeZh$$^0WHP&*4?=1q0BYo8yFd_EpjnfdPP#GS2iy4j4#Y(#6& zf8GAiM3zSOap)6Q&DgE67pa?qmJj_)+_NXeLxK99`fYS&;KHvwMh5ns%?3y#wyyJq|;qC(qPm z!BvxgCP$QLHYDw2Cielqu~-1c(_^>)+=*S?$v)!OKudG_bML!twRN@+pRnF08XzYA z^2^uG7Dx0vO_=ffS^7e9GR?8_;|Ii|BeT%^2Qv2!pd%;O9$!UEK0JQ6_VB@44EFEi ze021{(F3Gok*%5gI@Tgd#~yj0kL=-ZyL#kv@}Wm0{XknO^4|Pjan(&@f@*9=%^p6> z`MA3H*PO?3;Yk!WD`Wl^Y<}nZF^^Qg$aU7hpJSK!+H9PPpBXW!_*TWIJ_Y#)n@_mz zN&Hf9KzSm;I9ae?gpM7Md?`A9AoKUV6T?rB4*z!o5|thhgRzqGyrI3r0XO$Olhzv2 z8Wwj)KjC%nQ`@WY;IztS0YNvOHF!p2EX$=R6NCVcTTia;cGhVCSeG6eYCQDL%~I)D ze9N`!Qq#!c`n=T01l|7Vt$EuJ6C2OnxHK#>Mn*gfHjf^;;MiN*f@_iUNv?Kpe$E;` zt25D)w;}1ufJMmByMGtz-FMwS{vTZag+je+ei~=~Z!@LtX)j;(zdXuTM-u_2TeC7? z#3bU>c_ryedK)itSgc~*-+?gsP>{hfAOlR`X;(~qAD%qJNkd5yR%4c#@MZgU245(*9!Sj_Nid9~{xCgE_hceKMmR(>i;y&LdzQsakH$U(EEdN)~s=8JGN@ z{n=h}iRKBBE}aiJT0BwyJ8mvhhS6Xo3{J~7YY1I>p`9tCk!93F`TRC)S8bv7O_h-I zzr*Y+b$C`f$5LSYh5b?E!ycR0zx58umfwasHm{4U(}SZL`|cYreCvHw@wqc@LyP(9 zPg$x`t?XJHo4+_IxPdTS_)E)4ETx=u z(fGgN-ImseNY?3_5C1oof91Os|HXNB_LCkmX)QkGHBjFLSOb{gIQ>pD=5v z?LT+IaT}NG`Dt28MGM#>3^5}M@~m#I8)f~&XHf1e{d^c?^YNxEC6&;|6~9Dm7>AvK ztK1(YzpQG0w&lhxx8BaL)LljCmj?crBQSKx&YtcKweo*5sK%6s>1PtURzr%#W=}WN zezSN=i45yn(|milk6>za@_N0pqFV3hm8x0{TLc?ft7&uRhoQGMd%NCdqKRQbe4xXl zUCU#IhD%Ju@KlN0Y>jz$*8{tdWeP)j0ki~yQ4}VuOmIdue;SIkPTopcsLxenRr&rm zyd}6{IRAuE8rB|su=$Caf+WV~`=8Eq{nTp!P$?__2kPqtFfGz0n!al-T4C` zdL&szv5Zx4FD1@k<1|)(-F6Ou4+f)Tj6?`Oa+-t4ATgui{Kr+=9oyf9`B||X?2*vc z?`)BSnwUp_Gb;bcswVeL0*O2{;e4wFMCbwnq!%Wg5-r;MHf>u)f#W?R7d}K?=-yQg zAaH?Vc0hbDIhTYnlf!R{nR1r>f}z5d(VAX5_Oc0sg{saFJf@+CEQB8AQ)9QL-%cZE zW;9*|Py0-`A%2`GF*(iP;|`M5E-%NY3qPKzSjUkp`=4j-{q$B_OLvArIfOK7M`?O9 z=gmKRcWagB9zAF*I1$on|D{un=!PAsW}Dn-`X>W>?A){6iE8~nu`{aco&t|=^D>KS z1==ovGWqO!$A#P&GffpuIAi%5Qc>@{_CW;S+;C9#qnq~`cnY5|A2!y>6FHEU2g&#s z5UCH^b5f^I<-6PfXmO+QcuSe;uHifX^3~uLr$kaG@MUHq03AA{>yHySUcJ&!G?6e| zM~98cKsQl+5|nWj*i*7Vq_%J`?#n)bPWc>KkES1ty8|bNZ>-ug37~idTCx&^7gz|x z8Hldq%S933scy`yS(=hx8(gQu!FBI4-zJ5JR*e$iH+jOUt0zRr6TGEYp_meBDW-K@g_aAX zG9<^n*)nu%R1$(g>n2DqkacpI+mwxZ@CKeR=^;=$2D0CO&JiZvA>Qas^2M;XwvSI~ zVOg!BgYJ@9uAVBq)&hj#0fPF&Ao}!+5LDNrLJLM3HpR=4Y!y$?HPIq+Z5`bX!Hbhi zeS{B|G1gP|+|cAc1cl9cX$wbIw^1&uPYp-~G4rl%JHtSpMd_d35O#rqhO6{|SovjW z=Rz~-k4gIWi|^kWel2{oYTd`gTiF7(ym*fbIUX0%!%Px0&}P_wD@G(eWeLEs*Et*p zyA`HA`5hfB^^zPTjvyuj*l(fBf9US*H_nEk@1a^~*}M4bx3jD8^05^t6R=$dgz0D} zUq*tW>+V~jV^PkWv1BdR(@VlAxef@GHSbrv3Pn_E1%#dakohW}i`S6MgzNM6gxFXa zZ!EuI*Y@t8&j$dcx~+YJrI`OA4np=*dnsKCH)Wv92&Gk#<6RKGbQqX^U6kl5Lf>Tb zANOj#m>uN}M)}3mVyNY!7Qz6ZSmB(Rr`_2WwGsk!zY2u zyUgEQKVUw&%NXj(RZg6H^RV?Py*K>~?chGe|2#9_a5o8Q%P$i)-aHudfl;(m6w>k{ z#q?eIQrNlXIv7BM5IcBRH_vZK>_nK3A@e@Oisf)F`uf6#26(jLHG%2 zj4Jr)hEAkF+T;;gbxDMfYxUpNAW_lFpAcnK_+?E6`~6qgx`|(?}N3ddwJdd zREE{rBxJnpT`8Jpe7ef&S&ZERU*^lslVpjyY+BqyxIGaVH2XUB)s5a93pm2|5vb`{ zpoq1AV?H0|p|M-L(d{@{t-d2st0neQeh_72;Dz=O9v{gSNv5$c!;J^j@hr$Z#_|9% z)CP{Df0ETTDqmA``)kGM=~J0rUvg?&B3h?UZ(bJABn`%e9tUD^56y)xr}zUi7*~)p z#-lq!z%yvK3$L%R&~d`*=|rA*+ax3*F6leVsgne1-yZq6_>Sqm@?IGk)qQriZyS;e z!O{Ur`Z)d}(lJ*Kf2I&mpXthQm(D$R@p8$(B~MeQ`PlTlpNu`^Y%ITki}!@EwR}b_ zgbX|{()F`8w_Tk;@?or#RG+BXwg$okM-fGA+niBie9jyv6_vb zFXu3aJ|KW`Ma+TIYTRer-#${2jPLy_1g(|TxaXN~AKhb%;KL&1!y2gLjm@T~`dx7A zO)O_K4!UIm-2via0UZuCxcIz$_29}hgewPe#enOzIUKXpg^-6t^8bqlgM7Lh$mhoN z-5~?wgnvF!1b15ceU4-la zos&J}Q;^bJrM79*@;|k@G0>ney_CU6zu-Gfb5JQB)2F(LVWPk1y-jxjvTLKMNDhid zY+K32Bp^qIaAq+`+I<<%1{Kqa8n<|4$dRi3{W4Dq%Bf!6^g^0x7JqjKjBF>4wJNZk zIq&4h3y$9F)HgZT!4Dr)g4@x8EoRC)LX(yl?_zgHcD%Sb&=b5n%$emw*N5Gi_8PT2 zzu8_{+WJ`>{>=7`=RZzwWu`;0b^+D);lV^McXk}NiEEjFiHyE~Gg&($5VIwKm5A=2 zOpy_H?z-N`r2-c(#)UCj`xlM#ddPVr3?H{x0M#xU_o=6~18wW4L^(nz{28OHi|CQb z#Rk2iR94{oMEEXZ=YhU=sQhE>wXbC^AbBIgp&**e2tgEHf^-<&J=Rd^kUs zUO86I-YmgS6{

(h^c$ZP2vZPS{}+-C&LxI@DFB0XUdUTKi{42 zWLEzjHXkfs^UMdVPVSQ>jXdn+XUFuN`tFeZ*OQ3MP7QzT2)%I}2mhs_86+|=` zfs%*tM*+U0Ym4jvNT7Xa>j4RosxFg`G7FcG%aN|moDrYFALCU{`U|k#AF{ukOBsMv zgCb2nD!Vom{7LDHiNlRFi1d9)&cz_gQ|-yow?~W~kdvPh;?kvRUmXdQ$*V`wruj!+ zxNYc$U@1>2Kt_JkV&@K^=LomO7wmDSUx-Df>C%rf_e#jP%CRnT#Z{pJEytE}GmfNN zS8Q-%l3%sbPGs>Z!+BRax~IQ6Y>ML&0#!Wv{6acfHm?!ST6mF`b3IaAG0}}J*)R^U zFU@xFiDF+>{CzV(?^flr>bocz>N+S16Mtg8s(UUyVRC-r_sF5d7iz=2rRaT3svwr2 z5ET+psHw)G>T%|@`nenXdA;NG10k92YvsTXPxXStbV33+x#la&3vLe|3MFJ-@)a#D zVx}TNDNtd=6GE9u9aTQpwi`rejgk|9EK1(|X{dBz7phpoQ5A`NA1$&tx}uWN$Wd*ws+ESs!7#M3gy(G~NM9`;9spIpFpeH|H{(YM1f1VuQQ-)8ZDM z8cpthQt!mYa#|g1(j6^%Y362G)(yRB&V3F>5P$`@4kPyZ1WrA0U5r`kAYYq49;`Rc|Pn0R$bCU)U9^yc3$TsMtvILRhoA2+1S59^J1!ac=!} z_|%<;0eza=RVhlm_fz|y1!A6``)xMu*v=tnj(KTqCk#7DmLv3ghJ;NmfBT$4Htd(( zF8MEEc*a!Ks}HGAw{cpYSrI^86=@6HpH+&4BXafSqS3XFjtv_3ybPW)c9u1Snp9ms zQ3uJ)vAnbSQe8XRUc5#RRPZbwBMA*Hh3EP+K55qv{_IoQzv_lUNB@n!N3Pn4A&+U-5CJxumGfCQPRtF^aq zT`Wi`zjDvG+4XdL__B%ke-tU z+q_Ts7pMB)6G5;g?9ssA6~7>vfy?1W(8=V^n@8_E&>*GA-UN9KH)l8br!9l(ch z=AKp5{9p)aEu{Q)$@Tk|s3_q%?>jrHF12ioegCCotn>M|-Qx>4G%u5_2cNF^vjNKI#S0VwQ8SkzF@57f!suFjJ?p^!_7dV^7fbepcUNVhF8 z0D`q5()wzP?5_>L>ey}Mr+v4NXM%j*GWB&|qF^+6)zxQDE3~*GG%2h}n6l$ys zZ~64g-aYEcmr5u^olkvJhADIAOL_iPcnla{y50QW7P)pPv*3(S3`up>wVcs218mMA zY`SE)>;W{;VHRooC%QbXkZmV%IaRi!K9@xl1xJLk0k7U|DhKRFa;Q%kKXyOga77qtG?rQ2?&RT z-hY$OTb#EHFWG6W8EKsxe}$Rxz0rY@Z>eXpyi=3gMoT)%9+fMTc(5 zQ?g3@wrX6(FjnLkBy4Y;yPu5oMRPJ755yKiPR& z2ROXxdYgvp(|M2c)^+bIQBqEBmvvvY`;o9CRSx_3Up!n3hJI>Q!@nqEwB9iM*u)pO$6od}uNX2UNINXHrclT?9GgY%VB z2lRUYH>pB2$&+^#JzViYAN`TC-w^rRn$^-aV7ay|5oO+8dWucqQFCmq}RoV9(W~8iAc5 zaT^3TNzSm#z#k=6CJk-8p$DgnG#cTMaI9XUmD_#;1wuhjomD3#G{Y~l@;&$A`c&0} z3n`P0^OuYiX(Gt-K*dQNSme_E`_cEU%%2@@x;<$2r{P=it=U?)24V22-Oq2l&E8)6 zB2v}*lV8;3@EzLY2>}r*FktyiQ)9h9)R5X_eHDNYEuK0rU)7}LHZa@uqlU!npzdj7 z#BPw6n~sMHIA5r&Oe`gK1B`%<^3ms_aU4EkTENV7{c0zrZ%-fzf=++Be!o7s*{bmT zP8<_}fV*Q+jC0_pQ-J_2_C?>wkUtMfc=c?@r4$Xv34B$j8tXE&ErXkz?aJ{YV^_uk$gjHH9y zf`2FlW>;zIM<2yxD!-oCc#7-{#cnmMZ{{oHhVQCg+Q#C+mYT>Lq4;>bsdi(lv36r( z)3w6*SW#o1N-2Bl$Mo(8%JC6(9lHBt!Ngzt7?*S<8xPaw zApgSc#lc;%X9aFfuimb zBlU2I$4TjGZUH4+ze2KmhW2*dpl9}_vQG%$rp;9&DSNf*qt^);K+VIE4St9on?+s2 zI9ZZ9o+FP?6QT}B@pn-n`4h@I=wlBH(iw?H$Ob62B{^qS{$!S%nJ^ve;+~gfBJ*S< zRy%6Q5k+LG0+hGPFR++I5Cf&Qdg?usdZY4d(rNR$*FJ5QQ)2wJo`=r$z+&TlvpGcZ z*J)$D@FM2vz1()$M5c@U3jqBDr9sc;2kh|MBz6!kS+fDL?0a&L~?L+`O6MsRKRHD133xjOTqJ9>+~5`HbHS|3XSn(sg>~EGlr=POtXKpwAN0#?_u$U{?q87%kIot9gj9z|7E8v_iG1{k2$ZV6=NntFQZoU=t=F;b>qp}p`Z(l=*%(G+`efyWNMQK1*D2rgKd~ZPXlFj$ z`E9&zO=Qj|?DV;T?^gzWKgFNjpscbgyjsFPi+pqAGz>J!7~_G!oC7i1=y~QVP}>4M zc-zQ?hnl`K85o2sBXud<6?lVMC^^A@E&bWXMt!o%pgdDuJ+6Y4&Sa7VS4QWyT2>vf zX(=q)msO%`<|=C|P*+7%KGy0c0&MG@^nCkFw1tlSA(y}q*^A{H3as{9w0PO>2zMyg zl@;ZphO0*w(%UZGId!YpvZN*4GwpZVK~I}O1?F#U^ua}`6K@pdxeMFvPcFaYn=Gm- z_>r5-M#tchtxn1dK-ju}?|ngN77_a)T?GMQPMYcuwe9PmKU^9->5mPg{;T*jMQi04 zbkhEu5fAqI_xzBE-&M<~&~Y3@+tGLnFe9X*hx&={1vTD(DWJ%MF-8$2q>4Z251XNee`HL|6(yV}Owa82Vb{L;bK3xA(N=NRauhGnjBcv?w#C%F4DAB;3FK?aBKDwo?L!y3$bo}Wv!D9VZ zVo{lOe;IoLrQ%_$0-R;XM^64q%Rh`IzdzFx-A$;T*xdu#^)Dv9O(V?+NIafVR>!;A z_p=vIZUK)`M~g_t=DH5)nxw0KK;PM$4EiuH+0I2P(#?rD%tL&MTek|^=A;o-;Jk^L zxxO}cDd|_w9@RfD_E7YLR%nO4FRToGK4soCa*Z&yP?me^?#F2o3`+_bUoTWzQ)UUF z$91H$UGF}UgR%D0MWlfqQu#yuo@&7TgSYeL4?{6065R>X2XpmL_NQMh^mN!%YM7Dv zM7zG*tQDbz)_KwbuWipqZXHI}yh+b}ve09wr=y2l$>KIdATMJQr-k@F051>8!K+B0 zs++J}*o>B;1rD|{i?O?k{rdKT2o7h6@;#fhb#nAx?_2S6Q=%E_TnjB=ESVn9xTL>` z?DZr(h;?mkobV$N$2^fQb<=}@BCWbC+dQL!Wy9HF!}Kiak22(h&*(qSH|5tC2&von z>h^Y6fb@OIP%NY?RruV&7FQC*6|<4m=Go?&--u@x9KuBEsUUmES$2 zKQgXus&ny#tJfgt*U}tGCN_Pin4zsoa4)@mLad7SzH%m<4)WI5K6tGO^dmi_Z3?l? zc>T(3IeCD)hPB4qZ#|M%{aTOMTs_efCZC}>wwlGttI=`Eaw?e9Ifh_2ovJ!B%511p zKNf10ED?~aNGMD7^IgP%J+Vrs((kap&Wp!(Wk{M__f-KcuPi+i^?ZIn(WpV+^p6aljeBK z06;!c4c}?fo#?tUuc18hR67PHAEJi;jnxnceEU{W8?!h6nrCS8z^Hzd(|V`MJ6GoQB>VSj%G<2XW%o(E z(iaISjwgXJ%8MbbTE6}r{fbc$MnwqQ!P6{?-E{B}RS`*bU|Pr_tWB<;2oTHd;~@Aw zWY_Ilxf%}vGh`EHaGWgz7(d`dQwg2nga*R)}i>{ zEV4;`g9=iUzoM40L;v<%nJ7#?rgnGx)k3kUXwc&DReHD=s+N^n=pu2AK_C zom;M}U+DKI!ME9=w-kQa_7^MXv<~MUj7an@wyfo$q9N=RHKpp{0|2h&L>D)gurmkSikn-NQy@DNipyqhyiaY3<) zb!tfgVpzhkzhg1FUySnpN_WH9ut!NKW1aNxYg(=EZcYOR$pmdA0;11&q})i~*0atO@vx5a z@_T3KO}7*oiC3F$9l0t<*w0B-EKUgLq+aDD{%lfgza`I*mnZymFkYGIDn-?Lqa?v{ zw&=Jeh>S79vmpyEWcczqt6`Lv@{H&PAyjrAKHtl1kqh|Io>ZiTw}vb>0jbvCHfdeg zk&?eDeB&WIi_ig3eGs0-wlIS*w`VQPgvj`7@jFWc%6Dq$(@<`cDas+}$k4v*nmFC$ zbP4iEkBM15eCVX#h9DjcFNCGv@|es4>D(XV@Qq*Q^wBfH21~GHFlO<+jq;Df5{l{G zBrTG_)akh!MsT>3c2fu*3l84jFHZEDFv;(g7K(AyS**c2gh&wLn}j&l1PWg*9S@wa zsq?rPn%>kVrLIn#6~-JE9>bkw_JAzNXInlu&2p9fo` z%p35vO#J-W?b0C^78TXzeqDHJMyv)e`X(~h{4bW(;1@daudQbN{H$MzuxtpqK2GeD zM`ec={oN@A36rd_(s)G|Ek$+4m6-KIOe=0r%}WupLWF4mtv9w?mGf{Sk*nwIE;S#5 z1gqRHmNvSr?yQ)T-;4PqX3l{@d0gpoa6*1o(m)gKG>f%>5EVRgk6GzhCc+V{I`QU2 zuwc&^$RdO!iUGo$I0|1)bOaHxP_tBZ8hIAY1`)G2HQxg$c4vXitdxX8Fl=4%^ERvN z2(v(h9ydu*0N{R{dpcno*BsWhws^Q1?v!Bf!@4mQVn32~?wnc9Sc$sK??m>*wX%8~ zC_>nZ5ufD!A#hheh_YZF#|Zw9@MY~pSo4ta?8H7H%5~SRBqiitP~BUEh)iqW47G>y zn0qgw0?w`@xT0HIXt%b$MC=97py;xb$k`E&;X)_OMF>X#$*>|uAL;y6hHzwJS#Y$0 z2yP~Vv&3*$;XfOgsB#`cUt%DEa4iVANeI{BAx{5h9+4nOc$g`%X1&fH@P{(FoBc}%=R6>>tvD`lh5O~cLpf*7#Y@iMoB{bEK;L1bnJG*W1 zWgLQr)Pazz0S|&h_<2lB5EH2)?m_=?$>|zU00s?nTX*r%$>Q6VLRq^y<#Dm=KIB8^KCK#0UCUypd>Qk2N9qDC6-~@vR8OCzc?(V!bBr&n=5UF*87D z5un&_Dnt>~(fb^bqoo$hwp|fv$8V%ce!04O#bXHv;`!PTe-*9=KHgwAx&gR)$X3md z2WN{!Ki?rtnApgph|^-p@}tzZ6Ph68cp_rCD=s3m*QRGC`nJVs5oR?BVJqz0+|J(d z=i&a|o}z0p$872`aHNSacVaJEM+m3Bxt`R;ICLhhRD_9!&|zZo9uRhWw*>r#5ioCP zR!;qGAXba9*}x-X+RZ@d#L61;ZXhBMx|SzKm@%!@;8;oR*t)X#zrX0?e-oR;*!Mrs zxnk^Tku!c4Z2}_pilpa+xIj^($0YMKaQ}P&dR@E&T`nS?1}uZXsTAhFE7Qc-SFgu} z*wMs)RqfHO#CeGxZ09vG(|l9 zE=c|N_TBD2Sy2$++&Xlr@{mo))a5OQn}J6!cP^R>QK!R;IFR~@v&5?7?mx{nrg`rE zy9sxhMEVQA?3$RI^8wxQ-uRV}7{(h?FpcC15x1x7Q<7Oh$`}*%tH2jl z3<&>ZL7Y*B!)#fa;!oMx8|J|4FM34qM21rJKdKi$y-{t}gu~&G+$b|pi3EA*?-Lih z!d01lScY?}usaPat7p5Q<$jK+L~^vM3P$9b!Cz&$Tz5cV^ORho2ijtJQY4-2^;8L9 z$3B${m>mQxLy$q}U z0t>-i-%)p4(RjUF9Gqv(G%?Qd>PJ(M=Pcf4Bia_n8n!nFJ-&V8!$fQ7qYLhL68GJc zk^v$`DK*<(iqfQHKGKt1-t-nBuEHhL<77oP>9x)c4XhDjOR0f>Mq2u3v8Ly04E(U$ z8Poow`~?Tzm`K~~c3fyknrE7>Sv&L7>&6HC7|*w7;)tjC&oEnd4?o)({EG8jA;MiG zpxLx$6#6hdh4!4y*u)+mLCWF4U?Y&a9pgJvd|~TJ)6xGW1qQ@I#eRDm-=A(@Vs=Vmm z9}j0{qh5<%yE%1`(i}HM13hk9>TA1rLO4oZBRcx1Hmn`NiqJc9bb#h%s&27i|R`z_Zk0=mFI zpSpgoQ>b~q(QRm5vu|H_%R7X@-K}MJrOV{(NVhNgd>UvE^6i9W>;_W{;OTJ;wHls+ z?8QzhE7mg(?b*Dm2fdW)*>^+WZYZ}?!TDKFAticw%cR`;Fw9R+B!~CmVImtvI6W4h zP#cYiBV!XkfyPfVYPI#YKirPIuA1%Bhd4(@%vLZZ&ia5Ek&J80Wol(VZeXg2Axt~e z+}RL|_TbxB!NI@W?*4A`PhR#E$fw2S%Z}{3S@%;SF-&o&u_gA z8d&;N1>n5=(K+cRmfrxhK?kg50EJSNu&pnd_!oYfFVmV9q72G8cXwPzDwuIJl1vAJ z4Y=oXzd17X8bCC&o%B3|9KQK>t`w{FqOn%(mW=^$LT*;2N}o9I4c?u;Nd!AZMiNY1 zA2LxUgZL%moYver3A=%;DwYNit?P68NrR7O!T6G`@1^z=O0}QVy1DeMJ)-%}_e*My zQ27)@BAPN_>B}iYECQ&YUlsLiidA~_T&t}(T@~esP>c4Wo(_8$bo=Z1F$HAFPu{^WR?^BLpb*r2F8f(=7WLNk%6B4v*y>pj8hHVpJ7Hy{$SD?a#*u$ zO#7#(3Nh;9Od9Zhavo7vgM1jbLf4PFf6C+RC}f?Sbo#pxq|vOwO_TZ^!M%DaOb?^4y!u% zC;LNdo)JQj7?W~-Owyf~)9*pEmb%BrXg^6lPx;%>=y%H=7hV0Os7p{COi9|-o_@5KWk6F*XsG) zSF)M^y?;GP88AU_Ym;5awam)jyH7NYgsCWmAQf^!q^<}SIz|e${iN%P`b`W^U7FZ< z80M+V-g#m=cK5GISu3|#er`>`K(eF%{qfm|oVn%cPDxqkhK_u&p+L~Y3PbB)XR~$> z?KNoYcpPg%l+}aF)x`{FD0yzBmx_&pTy%-N@^0*p$bU5-cdB10%1?7R*Nl&qmNqit z*G93>Dnf8n+w;pA93?F~?(2o~cm3|Rw{+AOixO;!4iRROaN)8uLVeb4^6vA0*)OLa z1Ff@{la5s?)iM$4G!jP$8j~e0Gy0wv&&I`4H!D%j*>A)-&z01E{84sTTgni^2@rB? znEvM%4BdXM*L-xojbU-vXFSUxTb^&fsQ{M8sT)lfMT^JUVVA>q_5Pbz+K2mb|L1{E z*Y4j_nKAg;S@4)~vOw7ff`6R3(Rb(D{3#Dx!*2PRMF?oop=N|DO_Cgw#kzdvr)lLY zAMTb|tCGS*?&Ab^xz`ykYJb9eCK7rh|03Y*+L@fNZ#mmy9WwYwy-a-3h{PuUE16GF zSj$fSZRD9W3STI#S}(o!rGGl$>m6P1Vdn!Ujtm)o+cJ=URF?at|84#7ni*+jwa9c- zKjjYcy%KwdLp5XN{IPSD`|rnw0*1ZCmIYa$|CCDFMjrf|t+$846 zSUg?-rM%kEZpVgkonzs$l}yytXy+MQW?C$K23cq5E(IP@HHz#*r4E7;qAo)ClZQ~% z=|Xdv)OyugtQM_XQWM0dtVY9Av>7<(WrP&N2rXAG$|Q`UuVlT@VnCjFXQuJiUo7F% zE6y_9Q3*ccySck3XEDbpr9szAS3m79Zh08-p#;)RfGI1*!he~lRz)1q5pQHe@Vb+5 z@=uE0mrV=^z7?YTis02rX7x$%kHtKAw?PP+X|X*Fk%9P^ykAfzct}pxo7|fcXD8PN z=fVS1hG`0FB*UzT6nQTxF9~o7M&*GVT6&llye`~y$<$VDf@&SBuzs(4lj<_UB0;vV z*Fd0Q93?_pAjkvTUEwo`d+N0JHSkSI&aQ11P9`d{u`D@Hn8GkZW+L-n^2x9^HI5eA z2$a7BkK|p4jrSO+Ec+Om#VGV-C_%8k>ZE>Sgj}z|@*!id8nP45m{G7vutGK)qmkl_ z8N+Z|_wo0#s?QxV9*z0QtZW$J=N0pqYZ~)uUGSoM`27O zWlb-nsmN?26Y)M7;TVQI{wBqeB+D$&O4f*^BG#jANQh@xj5p7e!OH_Zb?8imz27*N zB;@1(Y>J)cJ`4x32;1RIjb%ivF@o?dlR2De0wAaWJTNgvg9-ams$AV8D_4c+y#|jT z3w#-Fyg`frg{Cjx(djG5m+{7`1&FCp+Pep2lUN105x5->z9|^<;1B{_MlA23J24SU zvIsdpq@D<-YJ?c-AjL9ihQAQ%E9N^&5bZR?`^Z8k))6hxtJ?U~$jK1e2#n%s+fOUI z#>tJ><)y5^99igMzBYwLvKywU$0DB%Qd1bwzjhIq{lpeK{zCLxEb>}ikM4<8zn{oP(p2WbY~ z@O8S8nqr(ni#O@VJj`3K&SVtk9v7=5(z6u#rzpl$wI{oUCieAo#9B1;&IJ{ zkYSp2CP^2v_+@qJ68~aCK;WOVWa~7QTNtwT@^LEM+@MN14~g*=GQ(gh(SES|DGXz; z1EXBor2moi-a$>gVf$|?q)-x?R1Lia484kg^k(QqPBxL!UeUV!Eg#2AeRc+gLwk5ny)dP#do+@Ah{lH7Iu$6L{}%n7DWx3vZwRbI21n|H2sH4r82F=dvn;;3+5jY{ zfHKYpv8IZ-qQUk69!U(?8x4;A7lOWi;&cWD`3e}F(}=o{0dp^cbh^Ni zT^!B(Kn5c@?k>O4q_X6m5?(FhyF%4o=+nER+Jj!A({Esy!ZP<071;}R4 zAu7YG1LWdSl2YpA9yoa|Kn7irdU$Y~ONj-269l<9Ssk_y{3(Un3E>2vO1wXF>)L*o z_G2C{&g`x!+~|<=b1ah;M)Xs+$X)ZB0eh-k00@73=SE4B92Ea5$ORb?PIH6)nuHMGh5V)K#f(2mpvQ!Apz^GNxU+?LPcE zbhrp4C8NtAHx5ftz`M!d*CQZ9zu{&qzvLdUWl-9{8Dx67re^jB{@BRJmo#D!5#Tj_K*84m(_m24UskLfRC$7hC!pq}lp`%kz9TjhqYvbf>wIt0ly)8Oh2J!TN5*JiBmme_z z;e1*SjVp?u{;9b9Djbfo1C9Q%E#5Xa5K;P85-E@mHgZ3Peo5kL$ScMa8o<+Ez}{sKyO{0|gaX0G-=ly0!;= znT(3mmwO;L54`Ut!UeUYFygl$CNvu(0)&APwnRZ+j4nj_G`4D6PGtvIbzV)#;XjeP z8Em-}BW>vU(|)ySNj8PE;`Xd;p`Dnq&ajv5xQ{bx^;UuSH2qZ$TJ)*sxj%Ae-(7zk z2B`-Ck?sH}YSl&_01;hOP?3KXItd&mnrT><^FJ1NMi;%ju6Zk@e*Yqg1 zyG-mp02+Mrjdrsb^T%!mHe!rvEtEd>)evQgL$d9yFzo@(Q9k)QtKT9)ZwHcwt+_FxvLt+9z}`CK;?~evcsvT8 z;to%oV^k_v-KIC=|9x~?n#Ycbu|*XgWvp35&{r0|?ubdCkfrEg8j~_^ixt3VoPdw* zzy`)(iSKsDthNEWTZ#1DBs?680y0qnXiQV%&Q9CP$AiWNeDL#fA%R`cP|FQ|ACvp_ zsn+c5`*IFne@#P#X#fOaolM;tJG%}3whR7mOK}%AYIXR5zMh&7LgClX15Do4?ua~_ zGIqSKrRqx6!&)ZTtcL@BjdvbRBza3a& z!j{u5IEDsb#UOvP{sR5h*3rF$U$P9KL39?tPb}o^87O2NIChpvm+(g@VP7|wiS!?s z6Kg`C{&{+ipR^0U^vuw5_qR0NA1Co)14}y?V}lRK?_Jsbm49&?{C+E*zD34?0$(Sm zelRHcFSnT?@Y!<&5=}@0N;|dUL?`TYLbZcQ_M++D90m6aiAye)&SEcaKmGEEG`Zp5q$VrD2}4%6-AzZT9dsNL0D;wI^#*Vl+X!_h^dGZXI7} z7=P9<+it_A)G|k6)nAO>1>%U4(CCUyOPZ;^^5!X2z#(X+>Z*`i&dRUAVi=Q?#zTI` z9oN=-+cK+1HlF+mk1zb@wmm3w&m)MGVqd)(Vq!DyX|50nDg4@^Jl`B}XWSCbD)!Fx zU1vc!SAx5Z=9(0r-?wN{nE^oDA!Q^+TQqwBSBU7R37V9dz9IcyoqZ60&N$cgICyO| z=Ua)#0mdOS@H-k%;s#8pcBrHj@76{l+rJ*B`IEsJiFQ{62xV zld9ptNVm}NnOOXA5_fcX8P&5HZP-UQ=)ANLn0*;!DxU8SGL>7+M;OT2c;u6O$%%!^ zAvCI5OarPGY*c|7FUTAY_$i13mwVZ}##)pv;e&})`dcd4FYSqqx7^vUpP za`qdq5{-b$bjE7!H2*vpK0jKYE-NPq>?EEk72I{c^WjM)vpwHtK7?HnKr)tKS1=OoK_IY&qPLCkd@PTk#W%i z<&ZUR0a+GViSYI#TW6Nn3yC%9bO7rSyKW6DJZqqz z$7sVeV?RfL_26ntyiadzl$E{v+oFyr0Gjo!{gAEgtydj+-JiJfxtiaj6Tp`$_VLl5 zm)zyydGg3pCWUm~@(50gg>R4*R%R(7^y zua=n~;E_raC=Y~Ky63-(SmtF5&WG@va&u#KrA@8fZ8&kH{tz4NRP!Q}fD{l|k8iMrZ& zc}{=oQxMRlK$Q&2#Q`7Y1k8I4i3?7xGF->6V6UtObP|u;!Dj&881M!ics|xlL~MXM z5GuuVhOz>Y_>AP;X~m#@RbyR=WcOc~k-%^H9_}b}>pE z;Dz!&#`O+q*U5E>iiOgA#la>1TMcT<;Rc}1;k z*7g`MqfUr73eD9AV-fTpDf;Uyz{R_s8^w}f@iRD_h02k2rq|yn2^`5p%)jF05h3n` zvq?^GC{Ea0Ju=DW*$U~EO$`A+K9^Z%4~fJ0c||SF$UypueJ4aG(#UeAmG}l#vmG9?VOg5^Sl}cqh z>k^g|eGkjgw3wEGj;;2l;YJM`E~*L^3e3o;%i+u6T2xuVvxPM3%v4=sWVPjiNEAxj zJwtw*!&z`20J%H!CeM%xM9~1oy876ZXiv_^S;R3Hk)SK%{ImSyFmqlavuk|N&D%DY z7elGAn@1Z=I)Inr1dO;C4hYv?pedtj^)T*TY+q+dJQhq3MNH%mR0&{%eF$uGN%x+8 zzT~&3Z~VDs#EkD!M9W4}3bAc@w zsE1zKtVrdJzS%E;K~CVVf}a3jt-XY(0R9LlWg(O@IwY@#bm4fA-XJ#`bYG&=1+ox) z#o4O|_psQ5f7u&)2SoA$WdPaZwqWfy$OK!0$5)PG_{ZW5JO~KW<>$#G-En%r&I&&N)z@^jbX2zP>bRW7fD0 zW7pRGT-h`dJA0-Tk?Ufhyl5V^;#bbO5$ zjI>1Ku=OHmAN_7qdABd#kq`U=PbpRTmlhP>%OOGmKp4}Rk5Ta)RZfxOm`)I@?gFSP zKf*=l2Aso!2ofbIi1l;?NG9{c1&x*8Kk3qm8m=4TVpg@=vYct_X?t><9^99g%)}dM zg?pm+tFyQJZjIv|asvg%n8qIh&V)Uk02#y=xhbd)$ zE!Y1&?0@_9*WCbJL_?4HcBtlc??NpQ$6gK-B@^N_s0C850x+u+drN>|vJK2fXF7yxTduwSoUN4A6RDwtukA?`q{VP%Ri@WJ)>a2EB{^*1^v zIZ(~_zTLxDmqma3}}}gYO1b_U?u>NCU5IJYM22!A1WhEQJO~nfO$@} z&Xjl6`^2$Uz&5M`is}6IB0hN?DaGI-x_3zgb&2;#PF;D4vgn8^dU5T9Dl*mOEJIA% z%x)IoOdUd)5s72TdhJSel+IX11HcdbJ07ibAOj)-uU3m`lncF(&)fVGpr!2{JC-7R zk*h~EHXcN~$Q2})5>8~o19+6W`LqFiE2=y0m(;K=2T9$CfrOfJ2$jgsyvNe(()@KjjZk6@?4A2otQlQf zSA8VbVugbTBXMP=*?9_yWr<_eG~BrYbM)>gU2l&Oh5HTb`$3FVHz=Cb9W!Ba=yfbJ z1!8ve-uP~W#}^K-&`W2!5k5f`MtejUo+F5*->a*&02cO7fuyF@+qW6h;RK|c@)rW) zaI=^Gq(oydBs4GSME(4z6bM}|pG^#7_Xj@R>L&*!D-!^m1HH|6h+~Bjo6!(Dr;bT# z=WB9*@*LuEPz93{@E5140cY~pK}m1XjA%0O@}SDbZ6NYQGTR@Ne@ra)Cn1l3Pk+Ms zGPy))a1Jt&vrXCVKKM@rB8E{Ffqe3rDW zCIbX1+Wmq+a{DmNAR(GYf~xnt9#q{q(wmnRN0|(QdN@K-P1AlhxK$61RT2vXUVM(# zALp_N^#VQWt~#y*OAyf%(eg#Ru?_-Qv-0iphM1~A32ENuVuZaMlXm4kwVw z65Nk-ECv8%8vtrx*utwBm^%x#a|Qt^j`@N-f?4k_Rn-CTA8$)3Tlj8;y>hQ;8*Rzw)<7GdJ*Kn`9T zEmXLK`h<<1joAF_ecb|?W+H1e@HvBnWqUb>7{*H=orl_<2?3q~q=glRac2(1;ZPj3 zi4Ju}N*HN58yIIE&Z9fQp{~RmGLe)8B ziF=R7uLzks)6TwKv6uNQ4g)v@(l_+X7|_XkL}p%~i4)YTSIfN-uv?)4#LBrx63v>^ zP2GX+HTbP^IaHVZour)Kg(;~f*;yLEbW>i|b$|$88RjttUU=qpkU+lh>mLm=$BLP$ z6h{9t?EZv>c@ltFLo95M77r11-N;~_byPSa9h-erS+d#w4B%F;I@Tx6;82oUnTb7e zzk^U`mB^eSCVau+?BrC$p2nGE05>L`JDE5?KEh6w0kLL-L94!WnDT|%q zwYSXT$ZsS*JDDjGPmJ~lpaCr#;5V~3mpr&b}5RD`>ORD1^ z%f@5-qDk4pf_V|`FZ{!}q)3A$u0u8QuLu~nXwrFq`Dizr2wu`TOYj*yH{LW{QXL2; z0j0{z^s3^87_8xFQs*@A^;Y-$JyBL(Achbwh^xg!t0XcqPX_>S0!dK!>e=!%<#iIz zEGb$YWZjq-y#O>l2E1=1SJ+H}=<-X>a>ONCCoc zU8kBhE?J*%`CO~3Ak&KA!RSAAyCww;W1#_xxWlQ7BU0*&f@~PnH>^n7R(*YdghO$n z=$~(XCPu?(`oZ}~^Kf}0=l(Q23&@t!17Gx?6c7Q%?4`W-c9)2LgU;;L?B(uTsEu{1 zRFYL!+Y@Cca4AR$4M2tx2;jffi<>>+d`>_v0uYrC=thHUiviO4F=#ST(Gnc@>0@;= z0No5raRUw)MRNyE{wMC$y8Z$d0!SC@x7<2=+W7egtZ~1E&C2dv42-6jkbG3Z>Z=H1 zp%IZZC$|_I4VlZV?w?`@%?l~v&u5XrT`^MbB+d{hmpaLeQGC@UNy#oo*etS`c!0w* zZIaykj?$_RxLRB01GT<2)v&T zyN*B+;&X)nfq?^0(-`MuUC+@xk(ONM%q5~VAEjNpgSli5Hhu^98e1jR5|PW7TC-tX z=`bKd@sUt;;g8Cv$2sEoi)zh_hlfSIanXO_BMIbi##IXPWK|#nN52rc{Ye~71)=*d zuciZH0c#!ZWpv&$xpy#>)2Gc;n1br}T%Fh$0dBCn%Z)*oTVoAD(&vuftOf0qY!U&? zCbHCKuRQrgKzd$`)AvCxK`BajZ4+2JBuu?NJd;Y|!J+7}@kvZcBVViG8>cbsV=xtRce6c{eaALqWe2fIDw@*6X?MDm2o#h!z|9Zmx%x@ zEARWNMJIgQoZi;8zR9zL9ObF~gjmk?LQW?yt~D9Din~m0uQijXi$t!FGG5&*PU^NG zYJnq~BtRr_9Zm6)!v#(r zwgC1~Cna@&Ye5%DLjn2~q^ zVanuiBM6>9kvRbd@O-nx}E zbeZ+9Zeo^tjO}HNldwyGGu#9ioN@ABBWnN}c>ZpK3cX}iLNjBj$tbf8dbH$}aJnqT z*19X3b9L3*{7GKSiM>Ft?@Nw+m|o~`+>T3Z>79SXWP zW_OaBLwA$;iEI5D+6e$#5OIpwS-hB_yP`9vW)Zgh_`}JIFW=OpAICjsS^9D2Nnk^> zop$KEAAHg#z?ZMXImtnrW&hDk!2vOV7O|AIkLeQG5N-gBnbjp)dc8D1GaPnCF=%~H znBEi3A!$?Xzc11k$FCN=6^&!nkL1@=Af;M!*6LTEwm1QhM0E;C$?E~*dw zSbt;lca3vnoK#IPg*a{dT%zq@d-Kovg*e4TMM%pZF?~^fRou<3kZ>lHFp{4s^e4rj zi_Nt3_Wsdf6cX37X8~g@PmfruD9y(;_`amp`%Tu~I8nV>VI-Nt)J6rqF!K>EiM)P# z^m!=`8-u42?RVBE%4~OE8bwBLeQr!#x1wl%Q@&snbpBgM4|?y%$2Yfj=@&xd=mCWk z7k5mUxLJZo!RmWe4$(M((<@PbOOUB^3X2~PDZ#EQ49ujy7bdvx93mX`bk*>aall<` zybzxiwEw0^c8Exf?`QMj4JS$8Csx{vO2NzH0OGXeZm3eN0?zSlS!*C7!{%mLZ;glo)b@Z z3KL>t7t{!Voab7M2q?ReDOFX|syTTT1OF>i)A%{N-0G&CLnK;zmcFMCLq`W*i%ZdD z08wfN+{01kdoi=sZ_Q48ET^p=%Qbxp6ey`Kx8^bc5xCNQOjU0@-pLo2kCkuRZaukq zW2Ur~RwzQM3j9X(Cm*X8%o0pT!bu<>q zwof(IvdV6>tmQnWw~W6E*U{W4d5vw|sHl3^+FAaFuDMlbzS+9fIQR5%Uc>S`t=*27 z%LW{ikg_a_QoQU(@HsI(~h+o~ZqM?(u&YcILw`>Ks?T zxTf=WdO7@xOrIr`ECCX-p$cr^eJsA{S%RJ$B{1nxpr|4!(*DFkzH18 zge0z0s^2?GG3UO81aDjCSZr<5t8?OOidCdIPKkyR`Hmrk>uqFo-w1sc^acqrge)fPSpz~R!;(rzhHD#k`K$p8l|n2V#lk$a#eB9ubEuq zbEtWwB0wXE*iBYC#11S#$D3tbmt{V-Of=Ry#xr4E>t;F*8ih>(Wo}^E*-p0U+L@3} z+kjh;nc1ou(E&+v_(1+LepIf zo@|RVAI;pVY-+kcigmq$oSS#Cd0s+qlp~00j@h%R)z0WvU4K~RN?-j|)680X!(3x* zsq0rWg?Bdi%@v(b4l1=*ayIW=JD%^X3@^mw)?CoIhf0Baxloy_?f zVu6dEd_Wc(xLxG{t-dT9Yt7VcUkq{5wZAMl&ccqNm<}LAFI9W3sHEpCif>)|6fhkO za0eQ2m&RRlX665Hwm5HeKcPradk68hHKF&G<8pI?h-hQ&eaMygjiEjkrX>QP> z^MHeXbMb#d8^!@Yt`*$(0vaaJ?!p6fQf>0JJH_u33nE{F8KN$yY|+@KRdK%#mwM=4k8e*DZm2I z1(c%A2&v%!fIC&8ZGRV#2^QF;7{9wF)c*_|3jA$y_rligdJwJX>@Q+}+aH!b9Zn*! zT-i9!n%~@~uPyoK(}(o!d}2gwV0+*iZ9N@GNK_Bh3Tk69)=+d!^d4LGW+D0kSO{hY z=Ak)4qX+gWQ3RLCWpCe}dcK# zb+8?*m2?hZkt+l|$G}!8Y-dOfCTYNC2Pv0Sur|A8uZ`LfarDZO#?*}--WxD}VcAb|B1 zhV$xJL0w9f^EW1W%y-ggi=N&0nyaRrmjF{>RZ940VCJXDBtZKm$Woqc(i|?y{jtwH zi;A$I5!-{9tEyA3|3$hSM_R9qcFW39k@RFO7!jCivo_u>n{_D)O%$rQ1mHdQgO$^; zqCmDzm~JR!y9m7^=>Vh0J{pSUvMlZ6@C~2YiC~4qJn!B0NTyrxxM26k3tD6uTQwM z>MXhdmTLe;$ZFgbRRmR)iKw~Y$d+r7R|n>WXR3CA)kCkSMv3C?=W4J4G}ALho%wav zmibAGYEfQNPes+4sK~F$D(fhfvtkQkogq+LmDF&_e-rXPZh~-5_4e)yUoL48yVXd^ zTNgf_OS929<Qf$`8FB7n$K$r@laKFSgH$I3}`0l*8o6oAlnE17?7Ill_?i}ei zw|%bhlnxXF)ArrmeuQ^7fUOY}U&jboO~#8sSmuo3KWk z(qp8K`P=xa31-NmBm&+^bV&g%OC@fAQdBd^*Skt@GL5KAmEH;)SJ^5hbj1nSk=PeN zhO6SQ&^$&R#j$!b(^;!>9(Iai9|>3e24;zDdSD?3&)@{{xmCMoPtsn&r|-}`>`G$N z+=OhES%AtOlA%!+ph5iry?npFj@H?k+8V1@lI@(1GoMxZDZnR{N4gNac0E01VInLh zSUoJxPO898x6_(6?3z)_VMX(lTTbOGc#!)m2^dHc{k zU1)7RRt-H7Cfnq*t}%%C?qPwbshEHC45}lWp&-Y9EvBn5pXcD*JA&>fMg)``=aX>9SO& zYAPGHlc&1#EVfIcx=SA0ty>d}iXDim9!S6r zrdJQaiW{hu_s7=vW$44UJ81oTp~| ztlWe|&4j$%q-xEij@*<{&6Jhgv_sAGRk<18nwgt&AMe+EWY9FDYGxDUKBd=u%9ZK6n8cTkZkoqt_UCvFNn=%UZFOaJbxmz;ZFy~7A*HdT;VtFO+uG)KO56LQj!u`#1N(|!_7#5|Dvum1 z82as8`P;4fkJsxz0rh`wHT=2X{O4KwQTY3#*skN0zT>RH<5wfcMIZjwO#glR>7;3C zzj5P7)B2Al#(rai@wwsqI%R3O^3$iPp^-Q5y53TIJKj^i5hE5sVKZgFD(*KYC=d}NKr2jMC|Gj4%X6S#0|40A(_urpir$6^k zb~pd7FaDXI{!QyYZf`klYCLUfIBj}!()8wUWBp-6)pkwcW>M~3amG+_@^neea`DsM z%E#NqclL^I9~9p{C?xC^6ZVR3?G-b0bGPv3M(&NR*r(saZq29qjlH<`{)zo$kovTT z)SRR8ve~6odn*_nkOlw$Y`v}nl!ET(C{eRlCUu3qFL;##zYNqB^(SI3#R{6%7Z0XL z*;cv^)|U)t;Jk)jnZ79I%l%|g^IVIT`qkk~rR!fuTHbvBkbmjLS*M=6O~ft-m&B-(3GT*3tH7ccGj9;@stT?Z=1f zlU3I~yz4mmv$s5)clrIheq{?ieNxMD$}|4U@#<^k%L&@Q z*OwD@nWR_920Q^PNhT5%|7+_lzFCi38PT;)=kigEw>Mo)x7FELz2;{1N!-*+)nP5e zf8yR+I=Du|M%LAWgz$3V;VO9vSLXBTyTNyP~pMwjUfws zj&)b^d4-<#FSSZe4i@F<(DxP=sRo;mx1}2@MGmM6m*kKNer%c&xeDKc-n6h@+)^=# zQy%Y;QGamU!?8(!C}-g4=zO4;@grs=f6n*GPS?{|K5Keb{TKamrB+(|-n`e}8^J@M z`2)Z45%0Dk{cW3vzL`h?`ma?P_?E@2Sp!I(%MxevT`bN?7|Lbm4K&R^=IMzQb$q1* z<%u(pq0NchI)RDCrE+K}rMRM@O0T{247pvj759si-4(Qz5}km(TrL(93Nj_bwNSB} znx2u|W2qCc28SRt{M)ga%_FYz>uC6d%4RU)jGeA(Qn##Qg=W0cl=qsFcNr&~sir+)Ws=iT~o=qdD$1qi7Ca%MtHzvoz5! z_o2>%GS>C2UCXdSq@RHZ;=I8uN9qDZo@M0*-98M`RZl}1D|f=n^7T2A^C1#q9&lTN zyIwO{%FmtTP#@UEqdo(Z6a&7{vIBAB7Zo4dFQO|7xp`jaQ}j&rW8@7oIkL&nv`=y9 zCL0jfE3$&5i8)+HJCd7XA{*eQ7cr8_sE@98UAbLgE>{g2aH)$l=)^yFB4oey7LF9x zt&EI!)#u_$*W$>o7p1gL!>>px8e>EZaq$-*>~WrmhHQ`sbix$7bsOPIgg~>X5z;H$ zsp{L&aOMfcBukJ-+^j?Dy0KZ<$N~J(ohX@C`4Q6EJ66`o5pR!FaK0w`4jo*sdZjBv z0Xc;hDIp-vVv3ose~O(gp?C0Xr`|TJ#FzYKR zB}1fFr0s8xX2|5yE`|A%5QvvqDx*I3&ejgTiZ8tN8t~Qen&J1>>$%YyrRLW3M2w$` z(Z}GS&k=UgLFNQHv|p?f+E*Cw<5Dsq#_j5E?)!$O=}A)yK~-1Wf**Uwla+5Mn7T;94R!}P1|4b{#LHpl650K;S#B@1GAuA}Fe(^UfPuO1^i~Qsu*Yxl;Eaa#=}kRVMaA&@`5-Fa*!j z*2*Rb$HeAPkVPdXts<(A1?$|+=V!a8TR1o-aalUqYpAOsx^3FKAr+Iubz9Fy+?VNP zmhcmSbvm-HJVNpSg>ca|$}o8)sj#@$weDF+ICEfYXc#tfVbaz9RyvDZ)-2|2{u0N4 z6iWW+wugfhWwn0oim7*Xxi91+ccw1%<>+;ba+6dp9|bSDYEy3GR|YxC{R)1%dT;?A z6Va;`0lRG8eOF#he*%%KSLAjghl!sLTqNO1a0l3{HrC`CyN5q9Z*Ge57|!mzZ0vHV z%l)J0AY6r?7w9xszoB*GhNOysxp_G%7nw(#kchBtyG)K4V=i2k#HU|X@LK^S-TWFL zzOrO-D{NA)sphIQFbSg;J@DH7;GLv*S+!s$wqYaUacngj@7~4PK#MkY-x#wm412(w zLk>cJtvUN=vayAFJa%W%#_+stDzxNoc)5u6PoIxADU=m~&FeEG_H}0#x1wMBhQJr^ z8c9~T%aBH0;5KJrq8#s!`Yywt*Cp(5eYLvhKr^fS8yqEu@{Rkl+JSkq()R5w{o8MG zY~s%C2Y*Eq%AuBQD`SyeUGL9}BXfi!u6+&->!`94*KEtQgC#|ViVELy7LMTcTXryg zBUi3#TVs50u*A}O;b}b8;0hJ-U)U`zE-QyL89W*4N`X31?Ft zyGMAbp(==%TB5{brBHFR(c%w+v}Rv`3Xr7))u$nk%xN*RnKB`3EU`adgs#a(iag9; zR~U_q#ZCGb+vuJ)L*R8zcrLY;HyZU5Mj($Dv;7cjjDE)wq{2~LpT`P486#ArTHXZF zv6Czz%fv6pefD<0EQR{JD%GSI6d-}0YW8dWZVKCvUznvos9S=#OF8w>5S6%#^&I!Z z3QdX(P-QqTep6Hx+3I_@LJ1Y>tt38VCsj!^y-e{gZFY^P*o@H(+wCMB{ZR>ctP{>7 zasr`e9DM9~-UbEN7e(Q|8=sR#RZ*R+$yY}jV$BFTAkk?0J$d0G@mOUj;tsNhj4Y#> ze)08h2s0TZuz+vh1})y&Z1x+WAg&M$GMvmj)+BIzDdJ~jA2piDuNW)yB#r$tiv!$n zq+GUNfY_m41l^OxO~bBG@uqtZox0AqEKQb#68#*jKgIr^d7z5^)fAlj0&*Vb+XS79Lx84vJOke!OJMQ zrMOG>6EG_XH2w@+P7E5WoLkKqXo`a-WP-8@WWLZ=Kw{zASiBT~ztSEmd@dmiX9hl_9~^18@E`}}Q} z{LKg@O*YUfnmuw>{PR!4%aE`a6_AT+hCTW+=-&{8ss&l_Utp#(7%C=CMObxK+Z&r#yNnpI}nmAVPR zKOP)4t5*FAAiuF^v%WeoWcH)=PU(^I&LbsX1C1&s`7vVL4o^T;R@5L3QH4j4sZN&x zSs`6=*Flv(A1K!2FV*^>>NRWoRMFMJw(q!ZrF6eYnZvx6r+~u!TrqpnU9=Q6 zyec8LhDudae>rU}I$4M4)XWr@!Z$&Zs8&@n$O@Y`YPJ&gecpRRs0ND5Wr2pdGi5=W zwHG&U&P?E*m#V_`3ZgGH1}TbrN{L5?y~g*2A3l;Up&FMHR1St%cKXq`ugAJpH6_e( z8ouRt`~v+nS;moK29rgNFO{+%Tm|c~gkhKo7-m5*bLsWgB8=TLLMwsB9Hxk<7GS>7 z)k+}3!6aC5K4ZfDRHyssPoNXWo`il?$V`KEd0+Tj;RYZ;Q^qlcfs_fN@+8M&|4>7q)eP!HAZs zJ3WAovQ2oH;=8iVR@)`yJG@y>l(1__qO^iU$_wq-V}goO%#T+Ht@ zptN1w>%6!CF4$9MP?av`Gud{tDpk_BwU;z(QM+(Ui_0_cn<| zqyeB?1B)!m@8rjJ6}WU^Mwq|_a4c3Le-9i$gtauHO%9nAPQgKV@oYkmjxOXs5f+J4 zupJf^?A{fCv9o6B($&T3v2;D5$^`=;1{mfpj3RR=+KHu$fJ0@vchm2_I^Tio%fQ&( zMs*3lViKES)&(%g6tdAp>;CbK8k&p%2pr8R&mO$j*bU3?!# z7(YV;(?W+jS=d{?ur;y_*S}(`&}MJO4j=BZ?NHd%PQj}uwQLrs4gjP?dw35&JU=qj zS3T4+!f1jT>c$T5x)1LL4Q+oJd-vtT1`RCeO7%`=)uD`SxR35oKD4@iIK+MEJ7uej z`>;o08;t9=3u-=>?6y9`VXuENIvcI(4aJzr8uyf!NYRClq>x{9KUADfl(!ErY_aX^ zO;mhg{GJaLEF-G(lYN384r!CBH$Ge-God%pv$||QEhf=&Qwpq;6&8~h+$L4sCbtOV zkwIg8i;`yBlluQAw-?wh|C>0}oo;je&{RDXC^r=(#IBOVrbFvTnzw-KSU0I`c0wO~ zS=o0`Gl8rl`=}``w_&XtlYMa`7x56|e_{_U>XJebi5R${eM8PLQv`+e>AwkW2HV~3 zgZ2EU3)?d{MrSt3tpBZ|#{kR`6t=_sNmZdK>egp#p{d8CpW0syty5VKThU!)rfgld zUhUD#9iJ|Z&V=2V&F>i9C49M7Gqj0o67*mVpy#vN2~CbXng4hCX|Us?V-2fheTL{m zj=OKscm3pF2npMI!uUtnSZXiTK8TSxc9zQvc%Zr^^6 z&Xk{y?h#qzM^y=w&g)OU0O%7l)t_!$n8}lyJ0yHLVx3f(XWdyvBfoyj-Dc|-n$(t? z1IthC{693Ei#yZ*|Npny*yc3MdDxuKIps{-oX>NNP#Z!{A?H-v7;`?$xj9sdeFZVeb1i>J3irVTF}ueYt9!9<>d73_XJ&%?wO;kh?I~`p zZ-}QmeP3GV6emAOo389sf6$Pa{Q;O5*yh<|@?2Tz^{PP_%5aG-eO$5s_}$@s-IF&4 z%ZsdK2kCFuA1bzmpbA=(?J&4xo(hR|Q`W~mZL@YOZ8$)(YW#}aM*r&gACYQ7)xESBR!vstAg!2ecSIA&P&W_ntaPvfBT(hak%=M zR2!>L^wbXM#zc$vckBwA;(vQ==XM^2^8tB(fG%#HBBNIS@jnX{0zVd&9Z= z;}oVtw?asS_kGRsg8j8Qr`)~DoF89W_(XW$>hgZyo?%& zcPVNo!0{LOzrJ(4vZvSt1h2^pI4yHs+{eE9k#J5>YTsjqs=FF##f3%tTZja(Ej zV84*R8~XCs4r5P}^xf(Ef&U4PRKhNd4<0hbR(xtj%L#QFFHoC}bWhnnZ^Wmcg74}2 z?cVX5+gZV~LQsfP_{#f*Sf0(~?cLg|bHA&9evLd7>EnJRbxiVp`(=m2)PDKb@T$W zEC7_P-c zl4SKlgPeWoGcFcV#_~qkyQcxOvYD2BPUHTMD}QTPTG|yyZYqV^t!_w=%pX-L|~v|_L9L~%&5aSn3S0)@jGA0$rxsegJ$YcoyfeaziWt>LP^U^Bj~Gtk^q zWlFrNep;*HgVXtYN*4bG`h*zmVb{lGW>uH$G*I=0n)k9>#^8_g!jhY0W~pv2GWQux z1ve$HtvOpY+F$U4S$d4^D#&~7Mb!Tqs&9IF_^l$<7+tik#jmiq7@Q@?WyXp!lDVl> z_$Z*W@Z+$|z1fWnxr58&c(H%=S+#|Wqr*Tj4;cyMP>sCp%z>uGOjC9ej|q)BIw1{G z$!PXAsjEZ|1=>oVf)x8@S1W{r~R+0l4J$AtV(Z7n@!K4=`P!z`wNRRJ*<_`LZBo ze^(SkZBDaVe0(wbZ~A2`cH`B&$qvM~90TegOtCcJw{+}R$nVDkoUA>Yq?5X3as%ay zK9&J{&qWmD&vWV5Q(hld%IWBRR~*X5zVsA2(kU!*4E#0gm!WdVb!9Iq*53EhT~kM` zFH9@eLc)L##R$T2pxVz3`RmV*QzOAl6lZ#D{(#zxZ8K4tQ-p;JUG@+mo&^28fF=PIo2a7%a zUM~#KvRC#S9?L-dq$q>@LqGVWA;Z243j*s`gA4?JeY0EG72r5khCG$gOiSAI-CU8z ziv_L=Nox8e1#q0C8cf8Aj=uYLb-s7Sz(Ucqu$H?7Z_MqXnW$H8Wuiqx%&oJz?l!{e z5!k#@`ziV559N0VwD!WD6aer58K~%2RPpM&#({s%Z|GkBCkZBKHvwvUn7~{>lf#~P ztw=cie46pNJ|a+c1iK&19|!2;aGxOF$d_$Vund&DybwT0cu;I*Y;P%IGZ`I#d%C2m zX(i%S=Y$s$cVMT{+G8xWRKZ3linY??F?4!c=K zg*%ND3e*rGZmBMU9tl(il0z!b2d8O!r5`D|+B@NZ=XCa@3N)Z;O4(g}ns@R1?EvXU z!&;bMb*hVo^yF=2`DOw+Z~baCD^uC$CyX#pJ>8Ceq=qHIuT_A~o&dS49uYVRkyMv@ z4VdrKqT^ocmrB_zc#6r|{Ry&#_kc3(aVtl=9sSGTtaO$eb`=(6bIZ~#3i8JC*L^qN zQH^$hm%O4N+*?|r3Or;Mi0!{!c)%~nAWoJx+!lP)6^@*}WUq=P#S0ZZkGOyAmXrlH zo&W|}N|IjpXTN@Y*Ap%iBK}%Y1J9qcf)^6&pYfN74k~V4m1&ws zj^g3=WGC{%Tc~fRw#;Br>eX;>TKYGnDyx{jyyQ#)EXJS_J+r`lO{)Yf(KA6MbJ8(I z#3S+pL#JyLuZ-Q@xUR~;?m%&IG)hbVl<6( zq^@>463@>{zAmqbJ1bIP9v~jrrgI7>$lZYFZ{2~8JXNwI`RZ88YeHmuhGDnjngkk^ z%dB*O@Z5w>exC3z3g&A_7Xpak;2RPXr6fo-fb)Z*0mGDtgu1d%7=_%EHkE$OhHm60C_*$w;bYDT9 z7iPB3biZnOiK&<*>Lj8*YP5#qwZ@UDRnkfzaCCVRnjyLLb_%b$CnEe_f8eqa003q@ zP`W;-sRgOGar`n|F~|lyV{{CUTjMbcVZUmzV0rRYVYZM1SdQa@Bxs+d2*eY=CrJr` z-{Ep={-SP)I@1~{XC~a;KJ%Se)fVU^!cTYhBMW*!v{y&Bl&t$j4xa22udKn9R9O^w zkta=)fPs}>I$u;s1`C@*VT&_Qkzx)~gZS~{ov!=;egZ^q)>t%qfu{3uq%_cZi5i1;I zO*3kuT4~VS(O4CL&e9k(P8<`&1o0KBWUqka$W)U*m|5n7JtK&lKEztT)%7i1<-jzj z5~YgJ&y57h1C$pN%d+TT>mImjqsby??sdRPg~(KooeY;Ls?8-9*m9n#7R9b&O;yov zRoi%CvjXxUrcKv_mR)IXWvK$@tvLmd)-P)6WneeYCn_3U14&i;p;Q$**p*;raOXjw z*5frM*nT8qjLbonrk~B=u!kvL(J-v7XG}MiCwivCFAGN`a98xeK!D>M6S_EoBWGG8 zp|$ou#lboB9gY!k$`l6&lf#;1Q4!pmbdbG_h1D?4uQwVM1(zgiXmJw79Ss26qa4W_ zhE%k%mzeo~1ll8!&g@{?qcXjqd=uq)POT;F?jCB$3UuKT$OfTcgH;Ph$zAlzu-tj} zNxbkFuz2c1p1eL5xe8ItH}-Gse6*ta0ms)jQZ2`7?93t7N}Q=;5FofaI?DPF)TV}x zUBjsbL!)o$Ny@Zyu4;h^)}%{m-iXYPS)dewOm|{d$T%JB17bhYmusbZc)}b)Xl^SK zs({f0>oj^j2qoQDf`$AmdyqqcbTjT|zM?;xqQ13*O9W7BiXjrlD|d5ZdEbH27qoEp6hZhnf|U=`+mnJZMIG@Ewynj(XAKNdqGZ&`>$T zRno&7IFdm_KuZk(;Ij1bG7f*5$vsGq z7>;-_%%*jXYDxjiCxCJ%s$5a( zN<`T9+v>f8+9V&4I^nwN&NICfi9k;Xmecw)e|7+YOKnOeFfupM8NyISdgYrak*n#U zwz;h@_aD>a{48^3o+S2-NZS`^m`%wRK)$OG0yRdNBhX)|p!5{DZ~ha$X(+!cuW|xU zZ%=m-7_PG`;YG|+o)-!tj^&j(Hx}ClGRCr7ZEpwjD(JJn+0C%Vs$F$u_GMQ1*=BAV zkM7Z_^5ncHfIjLHO9&U0idLejlCU2dO6u~{J&gfyY{son#EFx=iNx~c$n>OO2aT?F zn~4k^L#}dtskW^2gjPUZ8ySQqA1CSoBIIOiOUGo6w@8VXs_=h_>3z+b36TKoJ+jrG z`jQKes6CJ9iZZq!5E{YR2c;e7K?f#ag&zL;`SyNo3s6j(J zUq6AoK2(tUAQSv8zxEfxN#YJjZY1+O|8e0A3nFs1h1qmX@$zlS1AIZUQ-oX*>%fs} zB|riHJ-t2pNsfC0f%Km3Ox}l0WAbF@z69%mvTD-{(~RV-(06pM*U;J!YSUnCvJ$UU z2Co;3Ff8N8&M%>^*z;s>1SHpEv;2o&XuI%_HOQ5aCAJNvzo6?qbiNBNXo{S>(Q~Xv zkx-2Sh0j303(QNrqMwgu_ls=mo`7zdb6ab4x%;zUS%mr~2>cA5aQ_Fbgc`y8=xG1S zvoHs%^%4#OJ*gG&6rEn)Z|1&Y|#Jt9pOp<{M|Dqp6an=mBrc{1Zg-|bmw z=E=GS<~;8-Zq*^vwI}QO>sL#!Q8%pFy{2xul%<|iIk(ktA31vcTgbaI3FL=AnCCst zOm0qna*Dx|UT<@#jCdQo5s;$Q?z>u%K2^sd;+WAYq;J7_?MttlsMzr$ehLF{>fM5c zC|wdjJ)|t(7J0ubtj4K!1geU8n0S)^e%@gLaBkH23?j zdxJ!-z^pX7UrY1ePnf>wW0j*}lWtLf*sgw}NVA-xDiJ!QQO;W?62l~?`}-M#QPg6# z%w4r}!w=~Juc1FB0)JJ{HzvQ&q4#7R!Tdb?6y^m^!Dp3$$QkQZff(*(ifF{*MkowM4 zX?{_qZ0*aB&{Lmsby}#;Ha2UnF6R+BpZ|l7_d$J$X*$~3*A-2g=jhgRZ{Br*Oas%b zcb>LZP?e`Z${KI>tWR@{L!EzBud9t7%HWllw>R9+8r;!VVt`bMFBMkQ&&aEHL5X2w zP}&kGfim(b)aAUdt^e8goafnp%i-VdW}F{F9W?W>tVVhmY$=^*7E zkb0xn9v}#{2m3WRkj0ShMHF**T(}D`e8JUzIu-f~*`|-DZ{A5yLv!aW+b3*PKKw{` zu3gdXodICm+eIrt0QX)}aBHJ?y@(=orP!rJ(rdlAq|VPqRMQZnwD{0n?D=9KI}l!xN%Db;9gzAuF6We$$L15ii)b7jXx%V~J&aB8HA>%6R2!2k94|)Y4^%Y3h4(>4gl$Rslqi=M8 zU?$g<41|SCo(4_P8l*Tvb!8T~9FIHktS~-7F6BsSh#BpH;TMr@`p7qWlX~F9WHj3R z(+fxVed4DiOq%x;&bG-v5DSTp2F)kILM?M#b}|)usNG;boU>O@**4u5wE6>9e)6;W zo9}lID2?IubWcMW*GlEf9G#lz6e}=r1*+VMfn){0oaLuE^lNvtZ)EM^o2*jh9qYClXpK~D`q6pjW(Au&*rnm z&^47iV(U$`5`X>72u^>-y+44RMDzK-DN?%+wc3s5W#FxHK77g9nKYq5eg%LobLTF- zieB=6YQyqzC0jpyJFSpcC4G{voMkJKxi|B7bqRvry#NBK~2+pgiA;Hmck{%WitEACoIQbG<0}Q&L%;BG`0kBQPXun2n4Ik;cZ20616+v9xp7Zs>F?uWY%Orox$*?+093}8n=d` zfFZbtww{RMEn^E-UqWBp!}C#x0>A86&WEF<7JXm69r*_zL9WW{KFn0y_?1Nnz{XKM zdLZ3pEnztU-~8EyhUrV?oVtA=1;Urq_(Y2R%SPuum&vd4`jBNDP0!hBL(oOfj{PEj z?`tgQ@}2V+T&NvM540swfrNQf!4vti19BzkjBg@#_?1Co-E@iht*)da)v zJbm_Q2s98>ZXmD`kReNf)T^#)?bK@9*cBTm9i+k<(uJ;@PjBqXjO0sO6{=p~mlfCD zT4@X0+`DN9=0Hq^ex8&VPt@X_4K4r9WJ~zIY(NJ5P<)(d-gx zdUd>lU%XB=i0h%o8T>~XLAfzOR!zitbcyV57%Pzd(U@7TA`oKz$zYvN*pBP-1nCYV z&NkFtgO7%7m;F(onmapJ9-1e+3)U8fgP-%~8qZ47Brmj?3l{2=yyG#Wg<$+cO}4Cy zEP`U~b5eSEn>o^?U4BaNkS_>f#T%~4uzX{n6_Ab4)Xo;LWk?gW2I)HQlEp0Q2KkF3 z6~~Whr8-kdQU+|^$S1J?^};;N_}UN+ z08WWLBN()fyR6-quGmpKd1ktC^)Od`2-} z$QBUnACVqa8yWgZ_xF<3j7iX(lAUZV1b2Mt+ZT&y4Iq$B>mE~TTrY+zwR1IA&5<_x zg*BFLRlf;W?3Utd1#JmXyU;HWt;Vrp_*ds>6C(5uER07lKgF&pS|m3oI2#gbwiY)p z(|D(Ug)};{_d(#_D84R(t+q^DE8SvkP(X#1)oCqehyQ8zBhw)NwWFK9tc?3NJw&x_ z#74!7>}C&-5w`Gx!Kb{dx5RNiRGrcBoP^o4InDR10%PE@_XdUD^(h5KMb?z7f8FTT z{dNpFv)E#!PPV8(pshcPOx@JH1--Wpu&MMm_UW9Pi8&tujV79BSU3Q1Kjw8^>ET)7 zK)0xbZ{It50~EKj+s%Q*h=;CD#?7WX0Qaqt4k4G_Rx>bPd4-%kdebe_trel)%3?zi zfTgIFYrq%)=<%@Vht3wty-;r1ver};k(84;bSilBwT@Eoq~7qWd8J~oyt2;)bYpA3 z;8ksyV&s;&V=#5i$IO7DLxmB7E3t0QaGE`rnNYotP#H5-xr~Z~*w6%*WePc;ya*Ci z%2JgCLSU1(PdX1cDrXLGRmN^&eyw^7R4_GzRz4xQfc)C>L7fa^XCAFTNRN2;OnZ}tBfnuU9hl_wy>jwcxv{~N2QGdyN=TbMs4j`WJ(dlR8 zaA$sdv(yn;B!?}Bm)gqTvh`ilQd#Q={j;^%^$b(quvI<7F<-bmh680W5|;9hWpcbf2`q}LHWm=7vr9CtkP zp>WA*w6;2orbM9JvLoUbm1i@hNI|SyF7$q!%P806b}`(ohbQ*z9X_u{kRu`T3$h9! zN!ib*JpDtuR#*U;)$ePxu7;`vjlY;{i{IBu(Y0IQOOE)&hv#W&AvfR! z+u<~uqhk17&Bf^Ax%>uhS)6N`Oc}mW+?|MnebZ7#n%l?+1_#5O7*xUFFJLPTbGR3g zd(kmq+3BB`vuEdr8@7vDtL6@l#6XOM#lB zI+e%AmTRtRVegWgBv?p<;EiRBVq6I9%vROyuDeuTf)_xW2Eu}V@{zwd-dBn;nSpCxuM;E zZPgR)nW?oyzGpNnROIW#0`2jf8?jXI?bd)~xdFaU<nqF?9rVZQaeD$G5)U(m7OwX&FkKM4dA#_d^j zM2b2Fyrw3do=xSEj=O7nx!&!gKEi#D$xeFHLK;;Pl?@e!C&oYsK1cP$=}(`{rZsyO#|c@ zCmC4krC2R{6lwrT97N7Ge^LsN<(KW{ji_UQmGzUP`$^_1i@AzU-c^7pr*U4JfCWK_VB<07Ic^8BDU92D<$}li1 z1~stLBYWkxGH1`Dv^o6UzjH;Ct^U|6U%Br7l(|)&@ch4ROrA*oau+nCy%EHJr0S$VQr&g@5~|Rft;KE^kQmrm9u<*nEyr1;toZ1Qg>}=-G|0cWnfDhlKx;(4!`94YO?IHn0kH#wGiC zP0xVA1Z8#AMhpQQtVZoD-Ehk;#ytTWw3$P$`s5_edgRaB&CYaorm##2*yE3+T|;ao z&w92}P!pbF`+ysbD|83+vr*ziiL^m!y}_+4wV&)H%|4mxdZVPbsJ1sonU!TV2N_BPkx%c0j&9*4)x0!kWlw`OkGyNObP$Kxt z4~cm71}jOVd)UCkGKhb21O68P6;_99k+tiVot{eL?`klL8y--#<{VqMZln%z-QY8< z1}BP{l%6{dz8QUE|JQ29Rng#*`I7m9?G}Sm@5s?b`6H`=x0ek1r+U*vD~p5}c1RjB zTw3us^nQrA=~W}gE6GkWpeQkJ8nsgs!*If;4PIyIDFBwcKoTPQ6?9=WV=5Bp+xziJ zIn6UyPT6tA6`!RVIY2NUb94FFIA~@B4z%g93CbS#7n4`cTt97UAyL{8*bNDS%3mlA z{Myhja|a}drXUHoF5DVd!=9yQ3nGIvLf0C+WCxHMeF9jhoZ4C0V6MvNaCYvGp?eH% zWMJ^zjql79L)rfDiop{apK9!B{TI#~cjnp!e2PxWBS)D@Ye<`IY_KvY2JP=H~0+0yuC zEw83!f`GMHW%jd3#NdW&B=u!maQr9q9d+fVUVpW&Wn6d2Eil(BE{RH8l2#*C!GKNi z7DriN9eph1E3%KbiY=b1{IV;RwPPRBj0iO>R{RCE8n9xyp{A<+|2=AWZ%P7 zP#QkOxRDJpo7ejPW4%|X(%Q^E-bnvFPmvuT1#hr_aW_P-arPk-$k%A*u5WpdY2E;Z za~pmdRcn$T%+x*r839#yh%fEJlt=+->|bns8F!yYG@or9Km~lbe-*5GgcaMW8$$oo|q64M~tsm~^kV6>DWy_?5avoq}dgQMN%hl6?Ev#xr~ zkQxmZo1(^mA$r?o<9SZ_=fTqL$8i6#ZgYbp%J949RY~%(eSB{jO?Rnjg!==t zck8`8?^eX;^*Ew&vzczf+FI%TKQ$)~)k8ehA|7nr|w8_^v;6djvIk?O{>Z31RXGp+xUYwSXp}n2<)e5==j}wtSsM%qeXXMq5W!q$yzgN zT6Q6H_@H`+>j~jhBLTE{0(D_yS0%mEIET?0id{X2NnTxj2}|mrzoKP*h(zW0W#Xzc-xmc=_7siY*c(Op1_%^!Nf@s zK}zkp^7}YjwoZkW{RqT>eMetE9E_fb;o>q^1b2Dquwre?Ic`JbT~TQ+r>vhUhjpdAU|Ez4Q( zQc?1Y3*_`2(ZP0!#kAsoRkuoNM|KBvXiQp@LayHzXAhOqQWW?i8uFKvFSi<$-}W$n zkY*gPC8&3eST_P_a`NPrlWoc$^c zj9_|Qj6Ev1NbvvRFBMBXTnTbIVclHI>v4;%niRxS7x7naX8!lpm)$`ddIM+9aL)Y> z#c@Qxd~i)Ffp9nOvdoYo(ZcaYy>@~HY_=J|0sz<<@k$>003ZGIQwPx>xTd&LA3fDI zS6vMV%?WL(rM}b?<&OXS?m;mU<2RoWJpXg|W4~x7czUT{eO^8ys4h0W=NiZF@Mop; zGVa{RU#JT4bp3%R_P?)*|B;s;P}>3dE_cy+0RVGA{O1F+VnAc-g9*#y2|m_0J@Hn) z0if(5{d0!i7Tc+vfn$M*u62A=elYIIHx6p$Q`*>6+#o zpI_XIP8s6v1aLwrC6}PpO>F#oe=c5B{!Q!6UU8rWpS#j=?%LaU?oK8G$rb#UJpxI+ z*#VH=dLY#aXn6oI%S))r0|Uu$-k1ZH8JT*W4SS-a$t#j+;&s7*->4CF`F_?AX~nGi zw9%cGGUoBLMQ-UJ|I~w=&LPezfbkizOgyGI3(Qr; zgl#axrwvSHdu}Tjq`MkuZw;7MJ(qh7Xz5^b5=Q2zrmXY${=57}JJWJDt-cpQXo zX2Qy__fGv5D@p>VGWNkk;YHQnbYFwUMM`q2j4T}PLoZM zd(4C##AIHxm-fN)6hE#}=$Q;PA4|yu=lkP!nB#1Kkx5lJo6f0;S zU;RiW+9*X=zt%E%;6UC(m+OjdaYTvmFpR<6g#5;O_RH^ce38kKJ95}f1;rSq7(GNj z4W(+k^(*cxrD(Is$%4M>UAg@FfnOsNhU~0B4apHecRyrFD?US4tWNCS$uWNxrjWC5 zWQJNdQlqV%`MFLbvgx9Rwo(Sw!^|j{8(zc#-F*;t#7{SJMJ;fWhi9VH0gVehI`F*& z9Vb1ffNWrz6qY|yn^GH5rLi|&t6@!v>EhH3{+)^{L7vyX;)GSL3OG4b6PPYZV?k!R2INo0XLz(rV3(fstGUV-WnD>K= z9V`MTx*yjVxm(BmNa*6ZXV-wgx4SP&nfIqYgbl_e+~`iC{Vwp28yD40rv2G=P0tb4 zy^^|%bGy!4XBy7--SVfo*-(an7IAzEgCHql)a)PYYTYF@inWq_#HIx-QL~fT6Z(|? z)Ety0;l4g*ody@sUSisoFV-YlMaM@gCL^EL=z=3_Jr!c3t?ZE+IbmOPd9jW6H7 zP+edJ9GN(mk)ZQ|0COR|=@cA~K?t!g6@@iu%n^??BGuzOmBEh%JeefAKuiz3Hq_L} zUW95a(=7SQdfZ+-f=9(liheMfE}pj~9W*rETONjv=8+k$l=v~4Rvre`-fB(maScJ6 zJ9^gEQ@FfpAr6Q=3%Y2uD=&!)Q_Co; zsW317RS1epbPR*Z$8WTlM>je?AXHsYYPG`T%&M`?`Y}0d9(^&Rb~1YfW}MjU%v1r; z5kQeV?xwA)BXCFOSR$TNg1#8sTyi5KAWFXSjAn{GIy~v7^Nld_O}>sZyR5#pyY{LR z+h9ST%096a)kKV*$QgP&yA%5t^WGrADP9Z|*N8n=ARTSc`h zvr=s_(>IF(Q~GqrtAC3r&c{L$Pxj4u?pMk|${nwTsrfo{9#?lZKYjL(GO?Dpfl>Zk zSI^zyE)m%IXQ4GTq#{$;Bu9LNzIoio9s4?a5|@)^Oad-mk?8(Kqg>rAdM7}3zI#%@ z^J=&N6;O2%B5;N{uGm13fg%JNiYWf#nT77V&)?aishuN!$;y7L=}a=fT=r$Ma?rf> ziV8&M_E`DY3Ep@6Gi}k9mEq{cp`SAeflqWIk}+28q41d?@t`=->>Ejj0^!%Eel1uA zUqSUJDiipl916_&ADS2YK+g81VQHKGX@Y5toIj>ct)zU?+Q=c7;MpBEjDu+v5aYqP zvdSBjpyUU^6yCpEXsWskE#Cg8f$-;&*8AQI=5f^EpeEq?wvx{7C)aWYK~wDBjF(6S zGC-L1FJ>AVg8_?JeenR0{PhuF=b$d!qH&cURBJAEwLkm6d(4X!#6EZ?qSg`FcT)Fl zm08QGA>Dc%-QJTH+>A5+aNbhr`C7VRb_4gCXok4W2bR5VSzLWeaJ|KmCx>pgb8fhz zd0fjSiJ*4=4q>ho(We`uQtE}-rd)nO6TxN&DE>@y@=JD#MjC2X7D2?G(2MdPZ*|)_gQuC-o!$Q^0xU zb8=ikOrYvVoP?W)DB0sFf9aECLATry-Yl$zj=6cxmi|n>@*bObUnjeE?yXMcZv*mf z7wDmxAVDvbw5{vj2)cRQ!E65xR5ohlL>;n`!t58&Xyw(WuU44r1n?*@DIQfos16jv zVMcI75!+j-CuKQcg96$O{@jgdbH2IVTP$rT2_%#tjl7(-iZzXKN=HH1TiR_*e=j(x zpTAe5Jwh|X^Vi+=f=E9BNSiyxbjE7|-|h$JbD*?dy6P-II++J7{fKU(;j8RA<5DC_+k9nF71fypo)KoJ z!0vqmmQ3ZR2*Yf+&A-eqoNj4=D!0D$-W=n?lfQd=-Gg!xR$%pY?9GCjLkN_m_NJ@_ zdJax(VdsA@?dIY&fi9Wg2AlR-Nd=+M_#T zpYqUUUG%A6z~$7HT&cH_@;ZMoFD8f|D-;NllZZ8rQ*Cp?Nrx*QUg$~6dYqv1?!8bQ z;D^&@fQl8OjKxqKEq37}!+60911M z3rul=rAP&&K#tow5fCa=XK7BfWfY9_vpk!X;D?OIuy-zRW!pV==P|sUO5+cLe$-eL zo#vy}D&nB0eV)9_`1^b=fUIq@NqkVU0gK{@F4ouo;(NJ6PL+Sx?G`Z$xP~6=N#&la_E33u&-wa>4ZvUP%_E&DaC*LlmZDjXV7MwOx<;!sIe&;S*zB z<@)+z+4Iv3k4nDjCWCu4DhE}DnQCF<&SsvmM~5D+_*Ym!LRK6Qemv11AlXdrIkc=B zlUtWW)HkOr0tQ7QAF%gxn=;tA1~J9;kVz&qaOk8K3}Xz0VAr|M43Gi9JGXvTlR zXgvUen{l2U+N!{Vz&uWim;^jzSk#k&zsm+rJ{~WOSiR?ohCE1zq?1LnYfm~7p>yQ7 zB7y7`lgb|EA!DQjF19RmKMM^?$bIhd7>5Z4OO4f9{Gv!(r*f%*r1xt7Ejy`zfDp#> zQueyUp(gGaX86&%BLJ8z@(CQmKtk*K33QStgPUDi){_aH#O}MX0FYEPpQ@Uk)&=fX zxH-a4V84OyUJARSjgU@1I0DN(i-n>ZAV*t&n|U!%%rWH*;J|@oN^@^<3Gd=pw6Miw zK0si$NV&6eRV{buM;#)Lb=5M<7_<;}Q@jcnho*{`u}hU+kg{x+KJ@379D)rDGiQkx zgNMKe0ISx_NFsv$G?QIn0CkBgz!A+6P>YcKMB2H{U}^F(Kpfa(F8k8YHsbnHTb~tp>4gK798XNzw*OYtjtSp8{Hn2B>?ehuI_;4PSMGo5 zQPX~i9v2N{|Hi(SOdv{DTgX;X(ra$=Igx)Yej&NE^GOAub%Db!(_T{wfjTZ~|M77+ znhQziM3$zIJOBv9+Thq8>NJDB;=ZU{mJ4At28>bV;nDmDIs^k$gm13^Rx~jJn$@df zLUr20AaSueVdD<%S0k8KisEaEcnc7d2^2T%&=RT>j#$;cSg;cSM6NNQQ)Gls20Dg> zJirP-`bvm+5qzIOzP5qI1SSF~!oqT=0k{v)$j%he+!+BZMl`rjxK#joYmksy%l(Pb zr!gt~39I*qh{XTT9U+@0&ElI};X1-1=d_J@k4?4A;|Jstr9}gP`aiW1%V0-y5@L$M ztxn-J%|TlN4Hjl_3v_fUg*Rq~cUAytOxXya2rFas-T?$!fCe@slmK4H=aP=FG}Tc@ zJbKmqK1ta0hY;LfJm!m75-yRbDjJ6qU%Zd%?3;}Yv@n?|gRTi3ch_f068Nt|{0b@> zowaP!s!+r#?zs-0Amj9Jg=>n)qfR*<|IKP?k8wc`xd5X95Vm8EEYAx7aLWJ(xNWY#B!J~av-8OTDqTwon>KJ>qYXQ=7_Ai*m zc)7rnU2gq9>p(-nGV+-l9-p@zuUwkj;qa`~xr2A8RQ5A+bT_|B|F-3aj;VbUciXwJ zYY0)-XI(rNLe+{4JbhofvP#oK;%4tH>D%Tf<&iCC%KLnaZtFgx>PE)8%H(qQuWdA{ zdMFA4{1|TAvC3uHY=qnA>;T8boOaG#dBR8calFrqwV$jy?}x|OicmB=PU!Ut!U+Jd z6ZB2oa|X*Lmcp%Ttg}PHd~IUSRTpSogn3q{?htiJ0;K?U$4iH3RSinuJ83om`Or}z zh{c9Im)IRlY92b?#8VWyQ2R4|r{B*v?rCd2-*q-_?1l4A>LDE-0Wa=*Y=w&C$@rGv zJB_(Xx_{rVgKEU+4t7ds1EGPQLLLA+Kzm7eN1Y}Rz~iXEF4+~a?ct(S`m#_r;)YPz z16>WzadmaU@JAr`0L-alH|-o#QuJq-_=7(#DI%RDiP_pquYsotp*KB3qE7r$YneM? z{pLPv?l5!3*=#saju^gB>XQ2^hIl&e^mWlFz3?uf6MiM}H|Nv>`d)^Bgv36Uxah@_ z_1q7()Mw-TuFu7&U5~miopkB?{bY=qE&5XG+-i%kO0rOdSrCudx6AkA<3qy(E4x`? z)p3dc{Nz^N^!e!qzWN~Ypb8IUww1&xi z^M?o5&$s=G6hD3C9jHrHq!jd^f<6A~lkfiCr5D`wQcZeNRpOJR4u*vr42;p5jr zg#aOXm(J?b!Vl7-^wVP#((6G2$|X@CjOrmEjcqPS9D9i>0!S-MFYn2yKFFv&_-mg* zKL4D>gCQWQ8B$Pkh5{GGLXA!j@xce5vV z`ylrw=%T2IhcQr<-b{NYEH8@&)0^S4$d1g!5 zCB1obfg1!Pjc zK`Gn`46p_o^gnJl5g^oC&cOiiGk~&aHos%71Uc9)2Hmfh!m9QRmI?51u5WNMyeUq; z>3c>MjJ_4rd+Va%?WpzOL@|K;LjAqNyKNQW)vLk@ZM-o+zG*bOEaN6O6L{>S)*-S@ z_MyTQP(u{d*eYs@#HMq+=?(zGk0HPSwgdpr<4kn$^<2{FCgz#u(Z%LhXYReIMUCK4 z%Z4qVdt1I6-WMR>UtKxRF5TLZ)M4cu$BztTX98^BqL>(zTV+>}cvq!&clD$0 zi$)LPjSygp@Xxu9hmRgT`8%9l%WI20ZcYJpi7XVM@}aj;_rm2T@7{L3{@ZoF5~a=r z_!-{XoEJSL0-)r_5-X3-8Feifb-(xS_BHCdA&%O3`;-&#?AhNwjB&rxcBiR_I~7K2#3m9F1Hse)4Xy?F9MpDgeAIORX%Zc9uDf$Be*;Y#v6ar?n#m zN8@=u1LakZ7XV|Ik0xFjzfkjg%*{mUpt}2vCv$vITt3Xu%Xj{gNv=Ke^Gh!t`SgA? zo-%pdwT+V4Nj^R9^+NE;4`*t?=%99|UF7HZ|4iTWg(%@o1 zF8@D<&ODy!KaS(y9d?=d&N=tyYVNs@#5PNgXhczDj!=%~NYb?nbJd6% zT!pAnNu?THI)8NPT0eh(ACK=J-|yr5eSbc$&+GMia*YLzQ#%ZLcSS!8T-AGnrq79< z9?9CIzG~|Hswd5aBn}I(<>&`Q-`sQkk-De8^{Sh9X8|?fpy9L*hXeE)$R6yO88I01 znYny#-_!1W&wuW#-UETb0fYJa%j>T{gVj&E{)M8%=kIJJDptwgM%~=E>amJKo)vwu zX7B9peJ|V_4%gGvjitaSNqV$amb7xl>e+C~-tHk%w<`y@_~Y>b?90`P?uptvc+WSA z^;=%;yWU+>D{qdz7}MLhvUk3$x74l?VhHs8^OU0hT;FAQ@ooLU-9`Yl;kAj?+oN9Z z-anlT*{r|6x4W%@wQ7(4`oPn^Rs1#BIIBC2Z4cLUxTQY16gl#JsqRQ*$@R@X&9-ms-cDk{tXk8Gs>87w)i-_`#k8L52ZSo@^JsK&rt0H((}m92FCRYW_B85+WqkqY8zeq= zs&$;^+lh`z{QU-dQT9!PMH*I{t_kg%ZIe#nur=jLzDO*EAj1vR{5BF&W9bGSP*Lol5 zA|hcC2VSSD9&8z}@Ot{<>#@%5d;hxadCYL78qKRrhlIZGD|{Y^KKu2)>mPfvW}xch zA1WNEnlQFN_fvQ!-EcIq+}d?7po8)uIKfb+IqZVSy+R^AmJsASrfkaTAfz={Q~S$^ z^Uiv{O8Dl@cn&FBS=p{S@kyF~F=8gI* zsm+o3p{Hx<^9_M>f@Vv*GlnG}d@+4<(HTLZVY;lg1ntgxHF%rKa^auJG;+N8N*PM<@2K=@wK?XNti5e!QzF*vx+8hus@ z)gIPxeG*yJ{2iK=m8Q1gh1{U!*)i8VWvkw$$v}r;6s**)zx4f9+dDJ#wOi3A+Wup7 z0^9vjq}PHq-E=bKKT5*gV7rCMjkNxqBJE|^a#L)A&EL8e+m>PL$xTGX7!keYMDi`3W>e|RtA zVpcm||An-9M)6&ZU1A$AM1A1<4Kj+N_AEO%eZg?fcqv_ zt1uR-`%0-HNAWzA2gq~NfYccHam}%z0>v$|4eruucxeu7T(@T}e#)cIv9Sh5^m@6) zZ&pdA^5imD^b3*8!P0Q_qVVO&d}~x6CSd_&c1hu6d6J3;{#bB(W|gqI4`aOn{@;D+ zaiwT8TtPyI_Hu>gpVIl?mQ6)j#d6S`lZX;fj|P=;j!hk-_3Whu>2ub@>D3#JuJqL6 zu@_tiauZRR#847o?xI8*Oh-YCO>N(J2E7#3p3DN%QDwGh^*-bkN4#z}2hrkmVq~YH9K**#*W^c`(3Oc$ds>h>CWQY{jL=b=J}4YZ9*8HJAe$Us zs9CB(u-W$@CYp>rMT>xPr81PDv0^VtrVRSenrK{;*QKy0L25_KTy}rl*QfL7LI0!o zHl-r$sE}=Tv7#99R9tgD7d`j8M5~UfWG8_ryJ48pCD(3>h&$97?z_T%Kt14|dBT=J zUKC|OO?3Wj`qWE1QUwZbL4hRPmmPI(UsAgDm%5{_(R?`S_K*P+c7qrP2Nw=Hp7(D` za#X85>7`)k?eb7N{EsV=)e+$zSC!Q*QH^JumAj(S!$Na8oY)6R8yquUK+WZct5LYl z&GvfHno=NhaKijZo&G}&G%gb^R$KicGfkzR4|8(yuCZChFme)E26-7~8DAdGeW+yL z*NG@?2?r>%Z`SS^)M@Eh#?KN9jjN^bWR}e>^SL6rB=13+3xj;W3EV&}P|Z}U#2M0y z154v}N;wde#tBhKvNPO7?qlbW?q~Yom+nL{O7WNzTmZS(1s+wbzC~UTCPPV7H-Z(d!UgLq&hWfv6Y6 zb-m-19UPAcVixHCpzGn?d%ziz%L?Ju__}zrk#j-vlsKQF$5Us4Y=KYtD?o3?-96{5 z27p@kD{pmw!;e3l<`3*67uMZr%;|ad?PHA3nlSjbALkyq|2H?i=i%Rjy9F9tsksn# z9rN|V?c-Neh;Cd8Bcs{dR7q>Qh^8C?@bxmjkepGFn+KLAC^kXH%NQjHHbM?{E_z6u zx&E5wp#FTPBH2!VsuXPaxA#?lgi|N;-dB^(kQBxssBeH6fHsV-^@MkS9*iJk3(!Y@ z#vz=8{8DWDtP>Yz;ayKNTX;C0bEPc5b9hi?|8uA<2puUrP|)EqCP&&Of$4IH!@|Bh z#P!ruP6#)h{W1uJNyoiNu`$MXO0!>0gq_FloECwd%$+a3ISshtO#tYAc0vu3zrRnX zQY|+c=AsL@q=c)hv-#{Qml%F-@dYcnc%w2WH*-DT{5%8=@-^&rDxrQqGSr04knCI2k;MNZFGb3KL3VS@5-Yzk@3d6U^fFAY)M%FKE?wq;J-O z8ZForiR159ttE9o+-g&LPV(1*h0TBzckR#8R2Q&bT!y#x(DOB?- z*gl8V`l5T-{($RO&+o1}!!27oAmj`X%8wN;obXyYis~)rP>#Zkq=A2%(k)(K1G37L z%Q=<=z0-d9wJV};K=M|7aa{Mxaf}$wELeps=QaKSM_(boUn=-3!7D+KN?`scuGO$PlS_K)mL2Sn;^Ttei!N!hIQ7eay)<{2keC<%XxX5wp+~@g~d>7|JXUK{Gwy9cNV#>X!&3cEGNb+aSwf zBq}tWg5pV$y)Ju@=Y<*I%4dz>Ar#&e0j0~30y#37!kNCPCuM_In5gA)8oYfv0%9mn zglBDoCozvkpz%^Cxc3p=GXy-Jy2%VqhIT_$E`cMWfXmKXs+LO`I7f`u+nW>jD`k}a z>jB4xb@D>cR~uomZ;|g_LwiZe!%hcL63!SKVMyH35dwEj0_SqUN4emlwmGTe7=Dp^ z>Y}}2V**Cer|g>rh9#)JQ`aq-){}oZMkJzKM(XrJpz0!l1=sBr8^YdzQ`q~@iz@^$ z-1c~!n*{Jc?JhRKRjjCRvIioD>h9{)leuoMne|w9eFfa*@mtYTbou6<4djqrbia*w zina5S%G*bETM7d#*|16gMPbJjiVKkTST+f@3!*Jxq5?MJpWTNTQK7{n*Z~=YNHiG) zk>@m#vz@jBf}?+-_&Z0qCoQ062`CRBCN*<2iGyfofwk<)h)Y_B><#zWFF$cuEvVbU zM(vetR?Rr17E5UXlsj42{T+xKabp=~C5HWYU@hrxL57&DpuiPhd=yz?STR62 zU1j!p7c}C>QQR*&vK%{$f^O2%J0OP`v#js1QR~!Wlp39Y4Pd8*@;6f`M@BgywUJAl zgkY@^kOeMov6EBPG8{Ln>H3Ob?(#-G2sz+8_>Ab3+o>W&<85>H;b)N(613_ju}dVV zM$DOTueXeB+rA$6h^1+ z6&M!ohOSHhq)3^Gd%ke|ZUC@PRCV4XqV@;V8Nd{ZL#$-bG_kejn+&Z+Wg7}XKe@^+ z6XqhdAz4D5iOTizI1#?dZPNI?1Iii|O!@^eX9tNN#xz3@#lk$8B_!RDi{%_5^H_Z!){Y(HBZeVzpvA^W1Pn$O!R*9Pn+0U{ zEW&z$xq1)OQJQoZkFpX$ZA7ru6u6^IH#1_wuja=6{ZKQ`0fJ<#G7JXO+PxyV_U!f;~`$60CuO!faqJ1?V)AJj(oZ#(**+ z69qyrKDuQK-!@hGq2d zwt;(@u;v1&zB7z+1m&O{$Owaf;SX#{0cjWaoJxVGZ#Fii+(>w`8r>eWU4(LtTj?Rk zW^km7%YAJ!h~jQnI&{7=Lp(%cr);SsaIa|F0#K_c(20L}zZ$+lOxSi6Pvc+y$9BTT z8|=tbeZt;O^M&GO?T4k-@tLk7 z_ao$PdwJdPG+2SXiea`NiE6L@qcU;T?Me!6uxW#MFW)w!-GBOe_|M^(A?*(-HNF!L z`iCjp4n#UT^VCYayPd_$Wuj+@$n8?(=#-EvLu9hhqLD+rgUcQ|WQr7dw4=m33-RFV z_8W`Hbn$pF9hCthf$!Fv!x;Wo5LuL=eLuVz;o!cGy6CvA{gm-6)_8$~4$jH6ZWi0S zpg{hJ!hF)&`sJ5Ta!2}jk3&Z>!sG*8k85`dfq%N7a!e0DNHI^7k4Z)v8|1?`^!ax@ zMkY3q*x}{MRNTdOH|yE@y@NoK)@}Bbi#%X-_ZlNOP~`G$m6sWVsRKcIq&mdS2?Wyyl5ShPv z2{Nh4i1<;<y%LL)pRO3P#I5`I5XZwE3ag(TQL8A-KVc2zr5@fUdty_*D`i7_ zUp>Dfdd6!yxhNhtd}hXddS+~og;~bN3{#-`Ue=&A6P#+LYp;y;Nyvenk9l$+8j4i)6Qt`W>Lf!6_YpWGxDT1Acl zj^?(p9(q0Xs7sB?8MQ6X4r^NxAm)Aw83%Yjw)Nylx}4HRb<8!MEFb5F+~ zJ}c6kWeR40zRXt$2S;0bNhbVv^Y(YMY~Qzg`CeR9hI4TBFNsTwFHL8i(Fn z1CpHISq8g5XG2t&Z}$6Qltl02U-Rby*2$QliwAyEFqIV_njeR_xZ_+8TMbt;g!b5twEe#J2Rz^0K;+k)Y6rX2F$laCfZll*|U z`fXSk{GgH8GejNh{gbP$u1>eE`tRGpI9m3NrJhCWBP_TN1)fs&;pJl(^ zIp{cDMW}swhm1u#wZWPgcmWaa!TM9YO0NY@NMpn5}Y{e%%nqXFHz?hcJ`Uvr6!3?*KMtA78>a>^B6ED_?NUIN;Mouo*enGW$ z;ite^T8YNiJ1sRGu{~Kj>ps1FbnneNF)hC#`{sE`d)exeoT$fmi^=+RHJ9Bp;_}T; zjnz3TVRpVesppV5HoRE!$V|^+5a+L3@qT!--a3wq)OmWNtHOYuz2FpDSa_W@lk5C$ z(Pksv*aOJaU31ecQNZo}E6Fw?x0!Fkz9QfL>^rh{kKxu0g9AvAZ@fnkQ1hY@Z}7+Z zY0ll}X$Ky;l_cI&aZTUT@p$|1kN+J{Zy6@&*2x7{|3; z17eJg)4}~2u>7_eV~m7a4dc28CX~avaa3Y#7tr=Zf+8Ut{k5X2(I?8lRb0>_bc)GW z0_T9!r(r8wA#mLWt5$@DqN8mUO4F&lg(h>0z0mHfi1&4SuMaP(bP4qv?=MdWVhipJ zU;cRfN%n1A?UPTlzIvI%`i0F2sp}8xIegq^siW@EL9!KL(Ga*#o;90E_YO7TVX-|d zZ(qHA^LiPhGyv8DxA_`6g$>DWJgWaq!?>hB<21?NM53`iY`x8Woe-+=GCkWezMwKz z>t%(j>|#YeK|NTCA-rp0$fiWNn!v)qBMu1&kS%Gkh@<0Qw?ym+8nxQc`i(3Ae`We^ zHmi9M(h{=QzT8Qofu8V7x^`?<@aS2lh!DDz5a1AB8dBU5a`M}J#ft7R~mjCha)nmySzG-sXTbxbi|b8wu@fN+Uy=kp-<_uOIT-$u-bxEES>$tT&jlT>sdB_)^<*ucSh1G z{0nrvGkZ1{`cxPBWa#G*1Xd3PZ@UlaZeY=nZ-O1nMecO%=&$r6YF(=7DNo7jAU!!s zEB|I;}v&jK;X_1<3=6}TwE^GE=zLI%u8I2>mX7L-1>Z78cDBHGfb{8-76^7;ptef)yhMU zZSm;ft=%h#OkXala5%3mogaeHbD7E>GQ^>4B^6do2sB(r$Ge)PRJE5y6gR;FM?a^X za)RhyLkEu6SBO)l{ft|inBVJ{!;tP(Dqovc#HXX+t7T12J`119q?OoJp; zV_h-i{6mt&gn(EjO$$|eui!+Dn<^XRL(v6r4Hq^9yJZ3T!tjTZw7U}TA?LM-<**l% zbKn$(lK7GeuX}|u`^CO9aB4?&yV!};SbB4^8jnz<~lqdNTqHQL?45}sZ(;r?r`BVs@t!D z`M3oVj(PkrK2-P`R09j9blw>3S^ircx8& z%UYosGv{d2A9TBTd3Y4d5jxqNhH^9>joUDb7qC+O7wy(4Iy|$uzA8r4=M|{)q^w$$ z1ux}Hfi5)Ewq$a>yY~sFN za$_#d-RCP;o4GCE(vq23%bbQq>yxo3J}`8$wlOHXKqfUMCP>!H`P-F#x(6`v^p}13 zT&BGV%h%RpvXH=i8SP)76t?{kbX|vbqKL0auq@c!aBOWCX zILKU+A(KOPdo`|ISeYSdhH&^t+xqFGe47vbRYFt=sH)%y`Q(beo`)dX$pf1j$grbqV~NvXTvit4HSP%N+^w)~2Ns%nt1Ysl~>b zl4z#1Ovt|uo?iAy?yYr=Bzo+zhk^vCj%h)3HKeac>77g|l6^J}Q|_(!$$7FF6Y182 zi&%X~49VS%Yat-Qekob#8oA3>CCQXha(mp^L!drSeVUOKwj$9F{(G?)`x0hL(~e+W zhU*_cQO!@Hb4kg*e;+f>NZ|9awC`61I0Dxx0r6k0ex!6*m2g}i4sna9u0fYGP_BvW z)e#{5T(XK6{%VVde(Rc*bs?{@#D~xfmM21Ngy0c z;Gl@eMd8Ze(``kvtHR-9)oz7w5HMsLwlFkLw*+J|J%3jVDW<5S9P|+Y*`aZ}P8q#U zbj{f^@H!T)MTMvf`AzJ6$6PT(W_)JB?NE=><`jrx9U-3ylQdGb{k7Lrg9%fy~l zmZ(oxr&t#UUgHW&uq+8zoq1vr4^?NwQaY&Tg#79EO0oomkIano2rH37)aCq3K);CP zmwXSSF%KNI!o*2PwONQ#I3z2TCe>HE?$_DG@dG0|%A;rp#mv2syN5trQiSCWPwX-j z2cw6!x{P=tX-(;<7#=QoB2yGtI2<&c#01E-qT^H&<&NIUgV$eTJZP#EAs1T;|CXR>B(Www^p3DOJ7YeB|fY(DICZaXZ-vV{7 z+KM3e+cFWU6y%=a)~fT!EKuhl(2T3*uYZI;DSCWB_*ilsnVBnX|ApK^D3r`uIf3~2 z;dRY2yEA9PJg*6AKBg<1i8NH*Qs66*m)ea>|1D>;cH4tDM!#SCu== zHyYGiV7!DUry%C@B(7U>{dK@{ej9h>a{eQ@_kSNbO7V!m+~qvNGj+f!QU-a<@I5FI zXptomo4EXAd{HY#Qv^BNCQzqB0(npMMa6e{(Qpq4b>~w*PXS%b_|$rEdLB6N2o>md z`hA)~Vr#Ii`kEXye1s^N_1QrmjZe`){EptTpse6(i@CpehICQB<|knP=VjxC?O8(M zoK(d<3-h}kBHdi9trBN7Crlx#&-5VMY%prSqC`usAbG9KKtzaW$IcHPUQjX?0T3!j znOf-ar#W9T@TH^8`J@kW8J1CiY~3=b=qwZNMCCi8UNN814s!CHlYR9G zJjZH2bD>zVnePZP8vsNkZtELR!1RJ?&Z0j+FwPXH3Hod_mEYCDbzI=nSHU)g!Jk{* zf4(wIBINT|PbazXR%!|K6`-<#h|hKAxyc2NZV^6Yp00?iPlbhuj8j*`G_K*O$0&ONp5;NOz@zbE=hEj zh}{>iJ1&JL%J~Ko$g$V3T`o|s;kWc~SXK>xE8^XW9zllHjp5u)Sv}j^Z3|PUH{~dC zz2)js6J)z#N|xxt$=t_#dJ0>w_a0K13CxYOMYzt(FB_M*L&dyg>5EoY+aBT_`vydXyO3fywUUmH7 zXz+0dGxcUp>hO^d$K{r5$pAp)kh@a-rSy+ERc~?0k+iRjALvM` zU>bEd#PtK24}zpE_0`RZ|?%+7lu{V>xP^JLTI@QULo zC8>Dz=03b%_*cmjp%=3q$~lDj4`w*bK_zqGzy}D(0jhH#AYh=dY%7n+@$l zFBWrEZfeG^K*tCnv=mMS8?iMhC#f)J+o_zC9amGI=NRXvyk9DHB5-cq9LrqM>?JaN zikUrNB(f=NKhd*X-@;Y3TC%JuJtO4nE@(AKljpoD!~}$n`0QvhOgA~V@P??bByDK? znp=bwKn847cT4USd$C4`mR+q$t${ze+cy3PPTC!25AWtcy8Uhho)$0&c}*MPP3z#R z3Fh^?OgF{kh1d8WC(5qbYIq(`Idv;{9cvU){c+89Q?&Tri1L@Vf2i932FA5S{C{ZO zh<0a>((`uUUB9K08@NEu)BBpa!46#Bp5HBlRdsLnD7p^)b~yI?1K}p@saL=1?zm*m z$UR}Wj_9ya7b4Mdg^+W9MtTO3IdYT(#PVdyd>SqPAATCJhwejOeAgOyi+qlvUg{VaD9e zgNEL`Fmj-lV+H)MnW@%<*tZDbe{5#DQ+%NYRQPWx)yZ6Ow?P%3i2{iHfaAWq)%XLc z!5lz2)v(O6n?z5-2-ISyknh6I8l>eJFMsLc(}{PRf>Q3cZR`$Bad`3W!x6{&^#5*- zD{JrY>oIw8aeVm0l;71crn!#=)7CF(7||c66?t;t824w~owW>!fLZhVY#2)L<;`Se zy+1fQ(6u?KT7W|h=DDPmE33FxI&T*d>1KBSUJC7Bk6r9h#e9XMWalcBl^$0qS%N#C zWcY_}>eXLbJaP0|#kE%<@lOjcVMDYN|62LTIs82sxP(cck)?gPTzQn}n)Uix?1kt1 zpDx`B+VZsQQrQ8(>lT*#dO6GEn33BrQp6n_p52nBmv_IAshr$T+GMsYU?7b%$sp3K zLD;lT8*dB%N`$$lvZTMpYxGxII)KELHz(FG8oJm#v?FL*vgb;eIo>?IYqmg7j1BYC z+jui0i2e#+II};%<4v6rQOInj?=f?ikxeKstM_Yt__j5s==JYT|I7YjW_|G(<~<7*qSn96{qbO836hH3TX!v}9j?+^@34jpd5yJq>vo+Wxz>s4<_Ac_p!lJ){uY_Tb5j92&$#lOzY8P_ zib|T_+P3O-<*&Og_BHXXtIqs-Q6?aLeCIqRNx!hseGC6gYgVri=+~_uZSqALr}m#J zcy(t33IaiiP|sJbrf7luwkqEul@DdPbm}mnZ}{N);7O8W9hDEJiv$HArB3W~39pg~ zt=MZg4#wu6P@GNBckU`0FoJeN_MqJVxJzGN+Dem|VYn7+#)4@sC>TJ?54(YC5ps7#ghuZne2ey?fC<53SVgyD*0R#XS1 zuR;V1*B&{Ha$7vX2jk(HDTc3(R0-h#72u+_DBE;$2(69&&L2=c%TwB5zbS&=w|s?g zX7A}(B_GyJyI*qTw}mlPweo!81`6M2I96qEhhStsv^Y4|xHN8NklX`R58#MlG7rB7 z1&ay#jK!)X3;9E8bd2{>qiR*p5b~D7YQ&f=LdPQ2UP}_OnT;&0|68V=5;XN}( z>|dJDeaS`zb{*2Oir||4krlYX;|S|YP}cC-K`%nHdihJ3{pgD#p9Wes$vY9jNF-e>Ewe+_^4f1&h0^BWmh%IKgSZ zsA2bV3!2?uAc#HOEFpvs3PQCUlGW=yx0x zEm9zAgl`MaQ-(g!`jB1&)1jeSBwOm|Ruk^4ak_!E<=(;*fG}AM$L!o(Nwmu?^Z0#D%mh&^_?n;G&)!ak73$L0SjC$bB0?> zX)60uprMuj?bg@%gj~yl8AyrgzAWD{wI&!i%rOynKwbwgOP0W~n_~+D=ytL||JrwW zXY8B`GnF^G{io9IBT8nLR(yp%whwW9{7Y;EYn#EmTxkXB1jCmE)0P#TweEnRgDIk* z*b&qb_1_g(mhE%U3xHkyprpleWJb-e zEZV(k}v!V;!xY!72Iqh1?mSN)dsK_YMsgDPVhZ<4VzA}g_meJ)HS9!D4n)w_aW@2OsGZ%z}5S!`#}Hxkj@S9**;tP#uV}( z+#r`*&$3726+-cvf(ja{m{a>H$ksv3d8nh6rEJhHMR=UHQ4TXN+0a4vCtu{+r`{}e zt0vxc4yjZrSX}8Uk+L-Gg{V&#DTzzQACa>|R0NrmwK^KoDwy3 zudui6o{nWUgp!_7;=IsvXD?b)g8v%m$X!~LZ=6%8ez20pH^ zA0%RHk>HpzI7pKDXH~A*by-T6jU#)OId1wbulDW(6YtN`n%<@3_5m3Q8j#{3LnV5v{7`kNG}(ix2j9tPbHa*C-^ zo^>{ThC}@f9QD;cv#<$~oXn{#lX~KO0c_s)rtwZDJgy#d%5N#Bp zG?@ADiVZw*;y!hlTRTxIStun=-9vNwJxBV@#2j?{^pGZlSp)iGXI19o?$r6ug!whs z(Q1Jgb)Joe4n8w}PsRDvyW7G$hxDfWNH(Q}dk8j=j5YE`*{4P=K#5O&tfRMbg?u9YS~Y@H)#u zBa{*(LO;|npPDd*4ucY5WH$5zoahKP+gqaVhz%dmUhW{%Yuh0@yLo@oS{&U%kpg<}a&Wb4j3&JG1@w&) z_1BF-3`5Kf!;Ri@rC?M&W&x_|FwlRV`b5*$47)zIoRJnXvYJV6ygnJP7)`ao&^|PK z=M`lE3Du}UvzBt*?0&o4{%TJW&96~XipJg-=;oRn9fsO&NI+_6S^uH=JTAaybHIcd zDto}dlDXD%%%wVjL*XNT@}U-k?{WnUGiKVmekCQL!peUN2BOJTY-E3U~ zZ>^@Z=j94VkRS3H*sUN`gAf2wX%gDWWomFt6)PC1L6xu#D)$+Mr#WtPhJ)ZaRkqAS z+`5(BZ!Vk{7E4yhpn_fj8Lov%R}dPk2K7BCrg(;b#j1dK01c3uan z-9k~z6gozWv0Ee#T%*AQ?8tBGHLJ!MrbID~@@nYZd0^!Jkrg6=T^9tG+)tKpFw@lh z;eL{ggIQ><09CgiG%P$#RmtUTo$1#Z28h^#CQ!}6l)qdWr!qfJ9fPPHD|M98XHt2- z0B_CdLhC<}emCNCE=N8#RP9vfNa+7}nYO!!i~0MEjq}Y27^OBzSC{fn|M79DT;rO+ zS7dq0+QQbg&G>k{Rw6I=;&pM+p%_OYtaUq|md$thbF(e67V*^Qp7rWlf+)>zd`57e z-%u36j2Unv2mFLeAspQXd%-;U@f zc5%p^N0xUyTIRF9OoIrE!KfnXna|p;9xSsC|9-}U>&sPmUk$P*G|{MFGe$V(8h{>D z=@SCFrbc|ugIH#_2j8TI+*GkeX^l7HND+!S*PLYk@`bZi@=nknGTG6+)s%fZt(80LG zA-%ayrWvKeFqfgx*QDpa#@sZdvz)aZd;0o(-vK+NSL!%h%BZJ8!)uNstJ3Gk0w(OQtORx}tfGPR$;uoz3~HhvYLB#rVo zVOz8sAP?nh@=6I(-5M*$WMx1j=Dlyee%OYCe`!s_zMBcO&~eU+YzLO2pBhmLjX|?0u_{ z*uKjj=_-4vpIbs|h0;!Y7@0s*zqtd0<(7X$?)=NDPz*zjMaM&DrTPQ`X`UKtQJ!!; zI?b#&bX=Md`vUabbhl2bvcO%Qt=MeUvx=~^nmakO{Sakcf@EX*%10p`I6b zH*R+&tfQAcm`R1d^gT~!+P5;8)icX~;yL;}71aV*Ei`-x&F_Us{m(CBGI$Z#<)pF@ zAI$^cQo!`w8|ZYg{#N}jg0eFYBbOGbQT;}6D9Qbk!O^>E9SkdwXQa_jS$bgx@QBx5 zusqxJwV`Ia`V+d~|3pC7F!YQAUttXN6FDh#7JYfM7V}_jKzgOQ#xgvOmjJ*LzAZcIq;3x6jQ>B2)!7?8a+=UHuO)l!i!iTI=7U_~S zmZK}@6n!QVb8V82@|l@l)Kzw%fj(wXPX4P?K}+MM9~$sF4CBgl`Ngxe!K@OZ4ioa1QFlveRPcnA9*JxDA zdG<=#0HfmHk&;EoJQgJ|C!e=Ut@9h>pq4J&P*I_)n=y}|5N_daj!jgM_OdiMOzgax zLpQ@vH(+NxLwpm~9-lXNN=x6FWL08a*}r!TxSBb=Jj?~!%ibB-!2lbp8*egu~Bh#e68AE|%2z?Xr^GvjHkL$iuT$khlmsI|Ne*h?V zJJ`JIz(C)j6zcx>KMwu3wD<0hLn%JGUtK{dBp1Q6YU!pCwq|@0EJR!|MVNi~eDM-d zU`OcReabaE7YZ(MI9Zsy-vAON1@v)_DEjg}BYDvJ-_k${t?Zxl?c}`!#)I+8G3&f% z7cVZY$9+#R{FU48k}^GbRP~PE2fD79@6iEU*#q(_~tJcXw) z@6^?SleY&>oa3Jw81O9pb>b?_JsApW(Be<+oK4ud(KD0r9|LcV>)y~49L*qgUD~5g zb4h@?B>Nn@x_sPmwNst8=QkBWz1sN?a!4KGLcZ#9zehFdYUe5Lh2Mbw*JV5=-MOrX z2L6{O``onSN#elo`URzyH>&)$ZULHM*Un$bxw3MMfBN4Z$=!jIg}?fee)SE&Bm?}F zrh88&<*g)K8@Q1-VCUIC!1tKWU1)58I4Sw!4u;0{d{g>P1z{&Pd#vp8={x@GgyY`Z zZP!*-Us>64r9J7_%E2pxmtfB7AJ`0M?9uJ`Nx8H@irmGZ0qoad?kDLU`4q~8CH9}ZJR zMBE#kI7-|z16S^_EJq8?)Ry5WwX6>aDz3ztJ6xp=!37_{l8Z~HB%eP6GA;@_94e_zJznDoE2aP-o^&-OLPlM}{&Gh)~Qk370E zWP_ys=Mmd>5f{|VB=~^`uyAZP` z4W6pAWN&~f5dh2@0Pzf{7a5TcNMRw$b=}G}-AaGR=u?7Or-x8`0j!U#l#+UEs+jXmkcQVgf6JO$XcnmAgqtA_YvC2P<68U1tCA(MiDKtr z2nh{Lu4tJI^VTF@j~+jdoMxPV#y>mL%~ry zH|vDC^z#ht{lCrsd-|re!SLgo_va=*?h1eLVD^8zF4wvRUi=)bHTm^Q8bKnis4mo! z9`>ZPSZ+Nhvf_T++Dt1ePWkMK7dHdj&du7YgpD>IPc0L*FF(Hd* zn-;y*?BX}38uO6nzb%e`A4}M(PT7S(V(_61C!?xIF*z%dVY<+JDd3H z>-%cxMyk<;zb%j_T!<4wO|t_+R*C?Um0pSOSu;f3FL{EJ)iw{#V#Zoi9OXrUDYG`* z1{8)xQ-}|$&uzHCL~p`#)k%)a02>n;daRifv4l@$g$jaiRRA$#y-Aza!EiZ)S9huf zgB}D|6;-rEvq(&3+J`+@M-Cf(d8O0MygP&&{_k%6wyKk>ki0Vahp@d~GCRZ|Y)VI{ zZle;JF=wLveFDwVm^3-9{%lDle{5nt3Tbir$H5j$OOd9+^t}Nlr;1^VL{jro#H!7* z^>F2*ZymwglR#5UWH;jy* zH6>ZOOxiU?rtH|9$cJjwSgEJBfkG-doqDXK?1+|@6eQ-S^E?)~P)hfJ&S0)JP1Uf< zacdJg`e@?zOx_D?GLOfn7yimOEFYl5G zbf<7KAII!x{buaNa+|uJm7Q*?AHEvBy=hV7zfa??rDmT4rBsY0zv_9vp`|4(mK@tY zUaVvrPbp#>FwMBZspaAr>#6mEm0zG-tk?C{hQ~xah$1K5D>Bi|lE4ZWsaDrm4H&A^ z+53C9+IH;INvBtdH$nwBBwmqdM6Ste3tLU*|UU}}vdkq;WO*uavOn&~@ zP@+$Y!JGH`i+Sm8MV@X^6*azC?SB+cb+cK-XU{Y}+i~e?#nZ?m<0(70DzCtDoWe8% zWi0KRbY0fN%wAFRcf|k5f&UiK`Cqw?v_wg4#A~{EOYBdofw30#8}{E!OPz~QBsy<3 zLNN8LIgBU00v)d{W6vPNLU?zVCn`@z=N-W1)j993WkNAUWaZp$=B_BbyWO8svnfGJ z{Wv!B)=-H&L?Km1C{SW>yV1Dy2Qso%LFs&mWEhX-8!(SBE23Z$=dcd45H8cG2b)fV zQHa|1qoe^bTOp!u0f0G9xvNH!ldx%cWNJ~K%3(&H%_b8;z%sGg@6k3ue;!h)A4|i7 zij6c$onXWonSqdrCBsPcP+x8vKAdjqqCLng%LH+rHA_-(h>Lo*1=MzwhB8p%7>@$b zl_xaGF2y0^Xx<~GP*9RY>PBzUq^%|x=Z(g?MZ-mD&B`qbLN|aSxj1$&=}#4+{1ine zlbeL)(=Z)eI4M9Ml!^rk@zSms+hv5JpdKDgN;kp_3=n!I5cUC>7W-RU$-015Q=Y#Q;jqeyZ3`>KXX9F@olM{Y7u+Gn3LH}|$B&OVj8wC3XcLN0S(=Z)NQc_x6R zf#CrMW;XDX&6fhxwn9&jzCmy+NvuU@BqDy?2F9WrJLPYftjHu#8WwsyJ)wPA(7qe+J0dl2||<_*b^>s7jgRwKf` zJwBo-n*II32O@&4$OnF`d;>OKqt;wMn;LwJA_+a-D;9wF4fmUOG*ukj=0i)8AA#6A zSyR5L&!`G`T2-TS>sVwdm`SvFwB`DZF`B}jIfS2yKo6$ zU+-ZxoNNdxjq|y=(~AKiM}%DYA~?2t+uz~Zq>d{ub=5F*0Aex*Lu7R6={CPR;b?VG zYW4Y9?R_DQ41pQ%Jsos23)LG9fJ=^iFghL6siT!Jh_xp}U77%xyXBfPo6FK{!LMQR zaAJ>_`AL2I*Tiy@iHkItDvDB_;4?;`v6o==mC%(Gmp!!5%p^d|`83uU4{Q7_!=PQ+ z!Gxejx!4uyTKte3Ong7hE(w+dHzID30~nwhzEH0#!U}KnEKQzTrZ@<0S(v5ttrynR zAqK5bB!mAFvcPkCgD^49#FId54X?;_lMEn3sQ+>wYBk?Ey{};*`+~NlHtA*K&JmOQ z-(-Hmw_3 z=40!O_49BUv3HSLp@HhcXv+++Q&SU90v|+<=m0W*Ozfe3Yh3ENZK0?(Xz)y)i*AqN)kY z#BT|Gw5#y0x62*oYeNT=BQuo_-xx66C4UZm?~jX-n>K;As(JXv0!Z>EyUH8spV>b+ z?mCVzYs8*8#R+j)=D4_-I(M6bFX`Mb&_pkC|HcC|rBO z_aRG0%mtMZT!hXpOQhbZFN6S*$R~){ip)_O1FrDX){30l>|H(HFbL7xH|z<$ZVb_w z4prm)HB8_6;Ctc>37!OZ6`nZm$bc2*>R*XQR)zd1>5kMr3fTP@l$oBwRv6GDRQ}ga*O<9oz?$2{c(471pXvp-{Um?MaDB5g_%jU7b z0X{zLSxCsoXmJpm;`L>oJaq{Pv*(R#h8ztO#*+o-@t{vS?W`L}h{VI*tZHqIX<`>f zeFW1eM@fXQb^sYZI;@!+EW4nud%a%rQ-7dku--)OwmZf!dx%-QC(OecLk0}Rs+vwX z>V!7_*(B$ubRXqF*4&z!ew%8B=9nn(q0TLMJ|XN+r3z_KD|$dIeZ&x5D4v)zIbmt7ERM}0|Jt(?cZ_6VW-8E+5cU2J*Viy?|97_fuK_4fks zTrZg*VVlp&JvRZuU|wJgAZN%(YjkrE51TH?wZ+3u(Im%&@KE+ITNdn+p=)6@9|6Ya zZ=hGB5gp&rJ#@UeIV|xh{*5PUo`HP(QQ|4%!6}~P1P$ROfUz@_z`31VIAY7g5()Uq zF9=ISNu?RNv1x|vHE%c#Upp^^&!dr=;rLCO{&TZXU*6$=1+WujMa_^yufHF1x(*GZ zVYzayduUEL!UtF0kCeHpPthobC(N0QFb_uThn>(j_~6XDn|ZyN%y7TG*Hmd~`|Mx zVKi2{HQL6_iDbakA21TCX%|oj7Hq$-C&LII?O)jB4Bm2;^PASSdFlbzW8i6ev5k3q z;Qi;0e>LwhvG=W3i}+eUPqEqswHn^*a5wl|LaSu@0xq#vQr>V&Ss_HTPk+?NsZo9y zb~#Jy@=ts~6ZBiY5*i}eMs-c!z_m~hh#F(8w`-c4CvNlf;Sdhk3ZREQ57?8dLl;O+ zeTO9@@s}um{N$36+p@B7$@yw=OV~a zm~6qM$;*ANihCvV3t^f`I4?41&e_#Lh;AXlGB?rgz)y0L;vOD!8mJS%yjFvK4hDNS z_Nfa$;I+3S<9&k=piifwSzMCBz|6K=sAcb=Rg=S3CH{smF zCe%Du3mX&xE&&7?SgW);#Ijr`sCzk?Hy|J(2>=Rjofc=2>0j{i_VHK<6M_** za^PI~Y;gtLQ74x!@JTpY4ozn0jsG-@_zM)d(Q@3gdQ}XX_Z7%@E z?$DVpX?U+J>Q%k-y+fs;o86Hl6%u+U9fV_Ai=>jUsJRbett#)jA*0nml8id67~CLe z7?FXlYoK}o{`;K05&qNN=k_Q0O&5|Bb@9;lQ~6FdQmf>)hnW~W4T_GvTTCHn2!K&2 z5K+8kXV@0~nhBzW_6?sPOB59X51=0fs7^%||I1BP@vt`4xqHtu^Ez#9d%}Jn<>ddJ z1GL<3gp>w{Tw?RJb3=9(6J$<&4*ugx@I#ZdQy%Pnr9Y+j$j|RWZ?%ltoz4#n0~J-a zYAHeX-MI#A=Z0Mm`+JFr1lW|O=3%#ov(Ic@Fq)Z_O<0S7DsxKf%THB~h~iQe?_O~9 z9mMD8i46i^#54C|4Mb^a_&DwPTG)1|9=ez zLVFbc%I@Ar`ZktPdmU09G#!IrRC$uIrBD(8HD#Rc8hK^HQ1iEv3K6_Yqrs|=E>EW* z)df!^L;71wU*@S;EEy~r6o3fYqrdBFkIMn#Ps=&x%NL3F753ci?IdssTEf?F=U%h> z4!mtlmm6dJsu>zZZXLIGRh$r92-nhFB)5wqUe>DaoH=yK0Pt@{YHLC$-8=ijw>L&C zclhZ=KwW3x!;UE^BYKzC)Hd3U#m@et_n-VPz+RV^ca;Tue{Js@h6rvBQDmrfp8B8y zEaf?+eZxZ;myn|?Hfwk=o+d1x`*>-!{&9KXNec^FF&O>Id?`40n}GZAqQ#Op;pmom z=ApR)#O~LE&u`UN-!Z0$7eB}O(EfC+UhxQ7yR@V0_n97>P(Rs)(p!c41(xAUYn3Vh zsu;gc=s2LRe)!UjrF5&{1D{VjNaFFZ>e;kd2PtbZL>>@D1a1q*hwDa{6nNAAam#YN zHCk=Ecja%)0OI6l|^5c=${2F67WM?L$QHd_Rk&Oe%->8RSm0!9UK3tY8dfA z1G2`s_xqD$9-kglBDwfoc1t76;Wdd7V`K{39`#k|UPr1_XT#+l1Q$KJtd^oAFS6z| zYW3SnGe|1#O*KP##Jx8T4mIfvYwVorF8vj${vb{s00dUg7e}sIt;5HT&&}?>XbW%o zUm!#P@Tk?JpVr@H58n)EJ~7*|F@`13deh}hVX|i72cO?KG<^5=>->nfkIOy%BWH4& z7T?^yDfjts7vuA_eDMi2NI8HO91wqc=t1%7r1#pl{`X~jKwop=gAkr*#V<7 z!sh|wnvSIPsz;a4D$WzC$Pgr^l|{-tH11Pwb!MgSvUSwYQj1uFu(~JfXCEb>z@k)s zDYTx=Pe{Wa*ZUnlTE4as$mba!xj&daM-iD|n?kQ=zO%S!yE_qnaWm5~3w@@vdF3U% zX#c@$<=-?Ipl%(W7T2FFOv1Xl?Kuqhh?q;pr4Jn0Z8nz|7(!isDYHXr$*((Q6A;NF zh>2!D2d6-OzXh8bTrsLmo;-A#>`X}Pjg&29Q7Ov-arR?OPDemozV7Hsfg_h*438IpK-(Qn7) zS#tnDv8Te17v3#+3A3kuqZYPV9;dp%O#}xV&p6ir1qhqsU1|=PQu1jDH^#9-^fCmZ z0vq@(A8eELTX1xh3NV0gJmf2H%X@pDhW;9}z6y~Vdo>CzU)L_UIw@{lSJNg4`qIVR z_xQ_0;OgQT0X=6SlN17eA5B@M-%t!*8#@XBuvmo(A1Ncbr+c88D|y%VLW1SGjo!ca zI*hIHUC0|-ly*9;gZBdqOzgI_Me)-<>LX<d}$Ley_rjSRNz)%^>fI6j@tC8w$DGVKqda%JxCgY?X&Yt zTcqz+8IUP%gGD@;^18N%wB7!uyg)J7FU#J_10$<&y3l!%zy%}h*#mq@lJjd&5_W~! zgi|Z60bOL3`uHk3UTw-7kDx2L6|}ijI@1-aM`Q-8vIG z^EEHQTnBJX%RHL@6C>?iYw*IeQrv&AM}Gg8^I1cF!NNwXdirMw?^haUu+2I_^%`J4 zClfk}>;%CPV1^;X~Y7F+V z*EW3|7^dC*5FK^Y)S;v7DOm`;&g5~Pxb&gHM-IQ&vl$PtXhKTc=kW-2&+$|MFRVBh zN=j9L3eq;eUe;*R55ACDVK)8Kfi3LDz#(cB*ZLgzS{UOr-|fsda+xh~8e&_GibO4S zq&|Q!4OF+ZsSfR~C0<+-R#f&#p1f?U{w2;y|80V^Y_=C-qj)Uyn)&s6bpuKyH_0)cEP#IeqIKa~kXzg8o!${SfKtL7rp8*d!hIXNNgyDlXy9g^7>8&Q+%zD8V z@U1aF&Ik^BE)9<`}`$VYZsw>~hqL??&HDMe)IVa!HpQinx1>gc+$#^Q!pqDdeZ`&1*BabNT&88>a03pee69LJfLer)uZ$D<~S z!+*LvEtVis;aK@V{ZvM`E?+z1Alms=oeTkDL!{4R)-j#_!p!hzaPWd=xN_ zNi&ZfO#IBx-3tqLA-4^j?|qNJ4&P>%%#e;wN$ z>frHAHjE6t(YJE>6Av*t`-5&;>>^t+mPeJ~J zr$*GyRYzRcdN=Z+QU`l$E@aORO&24(4}@EnDPlj0QxCj?2-h;0d(RBJd@$<6>}lzh zQWYG@ojrz$UW-Msf*d7!UN@{9ZrenJ=VfJO>|Di4ex(Mi7T*8!{wb>xtMdAIPf?;t zl~RJ($-^rvLyl0zc>4SJZ^BCt!`vjKeY#buusa05HLuR(KCJw1Xp5(Xo@oB*wsLp5 z>uz&Hrn^l?bKLU^qt#iRt1^>o1J}>@{`pMLzEDFeYP(;X{lPryT^UdJS=Yb5&yn}9 z7;(DMd#oAAuAvu~XWAat>|n2dYbh`=!`_z%3Az=L;lT@YTUImozSS<|inr0&PxuUaxE)G}x!q4th-+iRh9FMo@dKI^jpj~!Rs--ZY$a?MoF$Uw}x^woq;w!r+ zY6S;weQr6@`R)4dzxVh|$>8kAqsN|JoZ1z1zG=`CjmMYHKK!!(;oDBNG5Xn)TY6W} z--haTX6?x6?0R0+Et}PJmmu)}_YY8H=&UP@Ok9lLbzr1(82 zp!hFw$qLWN8U2c=fS8B{yR2iBpVu{J7-IVeE$tK`v16<|gtLpgcCX6pKQDk{#-NFz z%KxI`%$LZVmVj8z3lvA5yhiARlO?omQkodO~^An@m|j0o>ju7raqLL3D} z=V318IsC~{SNg$j(zE{U%ej(@GLlv3;zKa>V?i5dVmO9k!Lf}|hN4#D@F?Spve7)b z3ua4k`t3<vjI}3CUoP$CTxM;)MWIG!J7HrCyD? zKy+ihL!Cc;cGns`A!W>*vu|5gNY?42Ig!mNC$Aa59z3tjL|wU#StrOjF1QYdGlp9g z9oC>-?{|$dP%>DEe^~6V_6vL1mrNLd3Qhi6W!CdN#7+k0VP1@C0T+`NNu5&Em^?1g ze3?uV-@bsKYs0}cB~%g=_Wshl60f$S-qOKc;gv`#-7L`0F9@$pR(&Nh{UbiLW9DOW zcT{T7HdE(uPMt>+m zK_Q|sbF->YLKA&_3^~omtO+pZoGi=;Wj!|0{l#Tg?=c%=m~-!};b^8Uyz* zvqE$ySM1^hKD<#(NeHN}A?74No9U{#aaPXx zs3pPS6OcklPAVS?aBY-b;Hia;?`i`il9A#Mxi~%`o<>I%(@IA0Xdbun_K@6x2%O3a zCxL>l0K{tn;z?Jrhh%&cSt4OhyjJ>Bm$g;YSB+lmZdi|anSfUmfh*)obSM#6O_HK( zy@QW&4Z=A6hHg3VF$=UBKa-jzTFpl)#?ZZHPY1@SBlkVNb_tLXO}SQ!3jd3hKqjFS z7=RKVK~1f=14%e55OI1SP?X!N2CpX*9Q4y7^MARjo-LmhpsQ)Y zvk9iAJkW)UJIMzPMXyI(Xjqg)4*=EUfu{Uw$c91}S4{19{R3XT!5XL-tuVNT#B-rq zCgSDTn>>El5Fp;TBG$83$yL1Z-}udcl~6sQj-Hl;84XM&UDuuy!;_&MzpF#s)pC|= zUC9IH;dy(t?FsK|ImUYHBK-+AB4X9iKtnocNJcd=5PJN25!cpOrF6uN zU~*I5_1kHGSJ)S&@FhV9u_69Qi{n%-=pHP z;|s%cT0BY>9*|IaWA#QCI#){4IwK1Bd$t{DFE|Z=1gh8w8QpiX)sTl8T|?w{v{FBE z;Jx^WZV5w)&TVrF7Id)ZTG~|3LzlJAP64O~pbVH$H8R-CYZE_ZT**a9G5nQy2$Zjl z6oP&=HltZlB{+H#N(oV~a)~%fad z4##K6SJF_o1UUiA3i(2@A+qb2I8+(FV1$NxF^s+`>@b^RC20jmMtUtyHD~XdM%no}f{Sg3=uW z`)`2TsL<1;Tg@X3glN=cOnUnD;8Rm_hoK3~nA@~X_=H5i_bUm}=hfe2D}FAAq0jp#vY$kt1OL3DAfNjh?|pl0j`gs11PH45$_WYLZ|TqT$jG zD1HrMDQr=rfsBJVHWt(%q4*@C0BCvcD>^Q0lz-QT+>bksw;(??9z!$M(}vX@3#EO{ip*HEhTgmmbV@#+()V)@j8@K;D8AB-lUJFwy>=z{^Gt^@}3z%UpklqkR=%kUC6Z-OVebL=&6 z=V9f@Td%8y=%TTwhv#w8SWuHD*2jN#T8Op;M9gw=bpVW@OV|LQF<0you&izX#be*< zKyF3TU`uw$vdf5(3lDZ3YPF%E%z?JDzw-Iqhejl%HRf#%pIU;yA5D87&|qnN8M{D_5Rb`iw~e1UcDaZD;FP>b%7C7!h~T<6y@zD z`onN$32CM29xp2{7_EHZ0SvdL(05ew&ObF_FAHN`F=;KxcO$1cGPJO<;IBVuXakkAZLW2NjRtf=sCf#5~al7bT-JbV*pcxX?5 z#kbH5IVCJ$FGQQ(F;;GHgtBr_rr!%qiG1#B{W%F+YHRWv^HCDYkOWP1ds{z>3&%rG zJ^f)e_QMQ|3{8{wH_95pij#*WjO~zmW7FC>Py^uszk~RNPl)6CJzBvi$_0h4uCGrG zBqTK2nt(S8TPo`^8lc>N>qj51>p~=w9=uiv2Q9cwEa7-lMt|e-JLWHLqtQtKgU6scjfTCcm|ul!n~?lCPwo_j%Lfzdr{WsbW|FM@rl26`2zd74Xk^ zA`&F}ijv+Gxh?qo+DdqQHSP`NR|A+MF>FWZb;`bP03bB}2xMEVj*~ zd22vyCvg|9rDcz_AKNmfEF#d1NRh^aE-t0}KL_1CJ=>M6;=g*ZA+^IAXxm zw%>~r7hxGrmd79`8hf&~Ge^4~Gxv2En(Z`{REiyN_f}=5#A-fltTOPRC8tOi^y@i0 z1!~*Ua#10Y{EVJ5Nl29IBoDI4oGPo55P(z;Hq7Nsq}04>TK z0D)-sMfREOQj1$?+@?6by&@3vkJrq0IN0 zWdTLqGCqC>m~e~qvNV@QRVOop@G)XDN~_DU5)npbLOj(nIjd~dc$H%aBT47rWcg_~ zPBGd4aW~4GJ@{l4kSwdrGf^^=sg-f$QJ#EqtBXQ~yJ3SVyqRg8`s}xPH{1(7^u&V@9om>8S5|f!A$Lrve<3eH zSyL;>AXr@2$RB%FJNOih5F+bSG}ou%L+)nFZ?|E?i(I=_2)G7EEf|(;-CdOGj18^A zx&o9*%9sQtHJeOkK9T8DAu5IKx1qpQ&RXSVX$16Q#TpgC+)rTlP+E=1asCYTVCOn;yXHb^qEzmk}XBIiD`cR60c<0%d zat#H=aCD*Y?CUd+I=5GGl|1D`rb;fXGRH%{Zs|GAP+3x62b6U%=8NsCc=z7n` zlNj0yU(3?2j(V&7mOM$9_E{KZO0j9M@!`uR)u;* z?6=EA?S5zU)1^P|4aMn9QKcn|ogLq&Nbm?6V}71Jru`WjOm!t@{Cxn#k{b)fRh_pV z$xmjevO{ERmu%Hx0vd>#mu+o#QHM(zn`U~JjycO3H{D4F$}+^gt>nY&2(WV@N2*Sl z?y{}Y&CpOCytx`N@Enz*c*A!*{k-LtT8Z|&W|c5RQ|_Lds*RRxQ2-gxW{6psKFhsw zPy+k&y@s$mWc&JXWl-5MM_kz0WgQp+8$-l}qvy|PFVs+RMC0)GV7dKbI?Akek5)z! zw!(Z+SGJOHa{mVdk~P!^ys8S+UR@i=P{Iq$>8o2m!_V4Av+5 zvKjJZgszt1FZt7xwdK#);r7)%05IWG@v|(1Vt#L@J>pY&@l5qfq^#Yk8?`tCvXU1m z9AvMYJn}CQFYy}Zq5SO3)y=*L*Uyf-FPxaDmYUFYmX7i5fqAV_Lkm)KnvNIe zo8qXSkMGxL-+TL4+0^&dU5~x~?5M2+BGtj-Qrp@?*y4 zU4^dqDSOzZ%Lkg?t9_wiF;tsTneHNAMe0$-^rRDDO+?YtM~tCL(1z}(=JzgV4%r6l zkScSrx`SemM`?N9Tf{8**JYaNB9*0n01EicmO`873Wi_4M?u zfal^+S^Ac4>=yze?RCG~A#4U2LljA4{otA<%P_9>8Llz0YpV!JeNVDV(LQu|$2dDR}1r z3m*1zHn>^JE-i(0#(r=lEvpR zXx#=-Il}*y`8^os6c4Jx29PyH-AEt4ocWXhAp(D*5OWCWM4`4B6aLcG97`P$X?#xn z?zT;OlFFxhR{Kral3s!&LcFFikLWmLGL8_d^&y^lMiIIPbCm0Zh_3c@)m*TU!yCZr zykufc7m$SfgQ!Q#nfoJ2afClM+xo0o7{z1JYKbTD7u7h)13nsxb!17MKfM!15c>4j zrMIpBwbULND3VbOruCWk`%IH?vu%=Homby|a2G+3&ENiNina|n!b`e(XxQCF(H*bs zPfY0%jKg#6oKo>NhPTNcqkv1*+=WE>qAqOmo+a^g!N+^zHT(ADy+A(3f&S7xzmDDG zV7Mh%Yq8fM2&;C^M>>M%0g;Ipmq=g+oe=Lhp%5OBRwfY06IJ6%wxD_@%9{rHa&@vy z9xTNmPo=%IfD2*b;Y0UwV~UNh6iLccA!^*@o>ECUt=cLEyebePOI5BA*b71sp0v6G zavfmCT(afZSSu}-h@DJ;9I)F_2^826Ni)xTnC+e0Y8r815Lb6BsqX_S~0Uov#@B-9ZF@v&hm z01z8R6&wks$mzF^V2OZ@E2gc=0Q0ULN@a@*5y9TyNwEKtk|f0p8fa)aQCA}sc9h+2 ze>CN!kmbCWsQ|E@Bl=_nkR(O6HC0&zh;W)m95V_R<)Tk-FE zMl>rFvAhE^4lvR*t=UfTX=UqDWG>Xmq|ch~!o=-RF}F+_V;8Jh|Hfv>1CaFfp3CUW z?cdxsnpzabt}=_npShJXiR|(sh(~)mg_@olnv$n#)FGzN!d}sLN+Zxqzei;$lbJ88 zEANmX7K|P*D2xpz2kB#<$6S`@+cAsM&mYW4j({+Mg4;zL3qA)MfhPdWyiL?kvX~MI z^45-{X$`U9F<((3TjtcJuhrzFfHd(uXw-;AI94II&&Y+3bqq-vjAv44I@u(yzX!^K zUit&l9Y#ABO?zw99|4bp$8l3vz~w*f=St%g&5 zMn_{Um{eBT7!%X)tsxaXbR^}3wq(yJ5{b4$@osYt_Ag^fM{QNpK`4~p&jntfNA z3OyW9C`TEBnrSX6hqpk}|#{;yO?M?6?`9hWn^i zn|4C$W#e^-I1}4R zP=q-yvCQI`g;)z&EI3ufx)RTPrG>DGfEp+z@ydQ@9gHm4q`_6Ww9NL3+XB43^A9wBYFuVX|}h# znpEE0F9fyQ*`^T1HL*ZGd&N$^(0U7HQ+H3#g!?O($)5IK>CJ^Sq)9IU(wkxdiZjZ~ zK=9gS%qCQAjnTjiCPx%t+99qgkbGjY^d`eehC>ZVQveJ)?IG5CB%C;k5B#n~EF4G@ zmat+Z7-~uO!9*ppESt9vJu1a=gHe7d{Rt3LWb`rlu>Y0p5bCq_5}LImRah@j18a72 z^D1sTio2b~d}-;(0ZfI3S}CUhqo})CJ6`mjXaa_oRoN4;NoJdO&BzM`VWuW|LEseX zy#I~UB*Y~Q;VPdrXo z5)np|C^Ttu(E?;^Xu-8XTymVLK=wopF{3=x)C5cdfS^BSYNGViHj^z-*B!`gI&L33 z!oP}?GU!=eCX@8r>-rH=lB+|Glg~ofu@nb@skCOXd%#^r@fw8-brk9{$?qStj(K%$ z(-JV1>L9rXShj{JH;3D;KuWZ0Xpfhv^D3$e4^wGpI&p%+$odb2|8!qhIhH5xJT{ueoO0g*6UnLm`_uw=os zstk{!uV<}d-;;d=<<=N%khqQRS z%AOf_{$O$r(N2c=&YZ#wo;Z1B^yBME;@Lqn1q^UG0*!}Jt#gi6sMdU#bW4_uYPp;Ysa)HMlYrO3Q~I zjfV)fiN6}tcsu!dEXZKb*JSD%%zKdSC9Lxj)k&_wsB7?!t}|IBwfCIGlshIC8n!gR zH_bklYPp*AC1IZ#II*9L)wucOqDv<$x^DeU5|bNK+-Gxwc?q%+o!zu%57xhsiK zcsIjHTRD(c>b|d65kbSo(0E#^b8Oi@p`LWNUUyhREIDcmch@aHRK=yoYHF_r^hkfbmKH34Z2wa5 z*%DiL`ql&VZguIDJ8pI6M~UZ)2MqE`_KqAs&X~y35(43G8TsGOMSZ|GpVRo?4{0d- z!-JxVF!9d}bOqz(4|#>n!gH%FAY7dRAmbrsn@Pr-XD?ij<0>SOHaD{$#gP;% zX2!g9EPBKKeoj#cUaM)1!Cmn)U|oqGxw@I-0~H}y`mX-G7We0a)USbmn?tD#32yzU z)uoq>^!czGJz-3xvl$esq|6xG^rf^i2$PS1ywDI2m!XJdpv_Sj%HWYJEg3rnOy_tJ zJLlgsJ|O_$I2-tlU~^ghV&+X{VpUP|&Re?S62-o^BGxqrGL@~OKP@#@nO!DOE*Tx) z(0-h6;NNs=c|&KU$Ta*}sBVVRH8l2A;xBMfZ;a=dirZ#85l+48*1h?y2Lh2gVsU-X z?f+}<-v62Y|NnvSWM;M*78}DhrzvMDNwp0#A}X(PN^{65BuNz7<}?f=6(yNe2sxHY zwK;_lB@r@*L@A0&rS;wCulWA*-jBQN^1M7Q&+W3y+R_sxe2x9giulr z$-GatRv&*oQ^VhKh==jcFO*Zh60T(7owwz6UPGX$mn@$SSMU1q!)%B)+8?;Zz3*}8 z&wx?>R_hKqZ}aj@<$@Pm{nb=YLhSs~^!(#XjSZ2Xe{WqHZ3uo9WF!lOn$xq4 zCqMt$?q;&*abZRjaKHCJ^JR+@1H~RB`wW`m6wzy7`+e~vhk3j<4$$>j8lI5g* z+Kj(DLhJ&J>(8aQ4*2lk$M=~2wdO2jFEIXW&xkO>-V}g zp9=pq#OMI9g-EKLEdGKE{IxpPFRmT~MXgOw^F6~J=-NjYvq17jHZg7T$!pIXky|>x zyQypcHM5p1Qr?u(@0=0lo_HMZ`17y`D5@? zfx&qeDb*A;`x=`LP)Quz&m}o2zO&E6f<+)%Y(5*PRsu7M<)E7;bcq(JHZlD!9mSGT zkUSaiar5O)wR46IJ(BL{P}Bl6Eo!gzj?Ya)n|p>4u)34`8T`$Ej9M%K3UUuDu#R^D(p#K18*_GXWK)1ee19Q?x6Hv4#-<)zRLm~9_|s1(q5 zL+N;oT7{lf^}L#%w_T6?W*BiKRKEqWDrcU)bL;E>yc4&2s#&?YV~5ZFJ^f~n#z~6W z?tsK?Z*eRKfpwg{63 zn=btl3ohun(ec94_EdG`M|sny8!vY(2-l*+9O|rWc}RW!#3Ap@x>69btvaC%ZjnOT zuddI`F?BFuCYH+sHYvhC;OxqpA% zw?_a(SU=@sPuzxRzfNE9W&Amabszwq(T2Jczd(?M_DKuC zU^Po|CH=5hwna)O?+LbFuk{i4t}{B1zv3seqb_5tf>t%0*B5|UOfC$IdfccpOT1VC z({g4dqd6VYNm$e}#A~1}TMXW@fL%_w$x&6BhggkX(DFT;?B+2qv9!g@Y3+*wZ|twn zJk;c`Kqyt8P5>sh8}$AuY=3j9w6e-& ztmS_wwI=t~!US|WCFK0R0FaY&xdM5#V%x#0mlqp?FlauzndhITJ=k<>TTP|;b;p`3 z`;@Krs)3>A%srQsnm2Pj*mwgD7~_+H-C@c`T28k*cZ!s^Putc-i{)(l2xn6~bV?{x z#iQK<*bU*WyZfRTo_)Z}a-SKx;!`CM``gMMZNt9BeqiN3!HItLPGs?XnjgMfIq2iX zx^4@R-4_|%s!ZF;-8u)H*Gw`G7TA*|XF%JVID1O5b^#~8ZgC29&pctYIqcvauR4z? zFm}+uErGxElDJ8DI3FB$Y#uRyowyt{m_c33lL=|r+Z$9jSpXdLu2EM0Jm8(8b`1bsB)%+R z4Ch^ifSx=(+YMiO&a)dlLuj%P!BJ*nl?s+$FtZE2;(m0mu#sd500x?L=h^9G$I|(! zJncUSxHWlsL&)2^(`ATv&%*X<^~e8`T~*Y&DLIL!lA8zLK9k3? z;UT-gdNp_T?Tj0uCO@c?^MF9McrMhlW@)cyhw_A?ovvnZ!?u_H=u<1URmAtcfeSa= zNYspD1y}JAPs{5^Q-beDZgoF*C2H(T($8V$SC%$n=Ll7<7L=B?`{yqmM6l&i)%5IT z^O&0LW*Sa!e4~JICf+8hRa2E}R|ly-Ow7g{@B3y7zU-Z}Q$6uL)`dUR+Fe!SUB34R z_kh1zWO^58`W{1KZk<6buxOp%_U3>ZN!U5MyN3+c%ESc`I0$Yjlp&GBrJ1IfCx{SR zx>+x~(BtgO0;tvkYv_ExcXBQenE5#Vf(vRjTYpXOqUNJ{e(!Di?GeQn(DzZ z-CKe@&(Z8rmA`v5mXiMci8f#1kVSVBnd>{;x>kT%TUcM=Ea1UbH|ThkSSH7n1u6M2 zP)l9_ynh4$PGg=Z0e1q=6LyIA-#IFGt<@;lp|IU$wq@_zSC6}caz;a4S0&x}xoVjZ zDGsCbl4|+AYtQcg2vI554u1NuAz?+}2tWiw*bQeWVSDRXGE52($)|je$O4jPuL56Q zrhp}3;{cP5ZTF6}0~Gjo-(I-e@pF?S9kl|x?O0R_13X5Ahj*qgdH%QV`>;m~q*v;! zlMW^n?GxmxdQJ@$QFC|6WAW^Dxo2}@hoFo}ncp5@{`H8hfc$Ls2Lqwvy4s>lC(^JO z^rZBy7?PNXE1tU|*T;H>77q_jIW7=9MvwXmOVMrWAU^evS?tVQ7u@G4}Z z18NMwt-n>Zqs(TMg1Ek;t$_DH2b`4^(L>NbCSSh>Oh0Uf zXn@53vIUyk#(>qi7YM!uuyolpATH)Q$WAc#Ycz6yMuekA-Ft607&{^rAPLvi1T7K2 zea?6m4|(TT_O{aJZG0KoYbXrQl1)MqoQP06DS>)D!rt$P0bt&~Bnn%mO)B|=U`J$7 z9&Z{agWffnsbA7*|8)9A>F80@Dmwb1Y_@*2_Dd?-&SMyS5Xm z^VWuib1ypqm_f9b;dpH5Hci9GQpj4`j@|y-Zq1%Z5y=M%bLMVP!jvZ}?MN8@p~M%! z8G!|s4K&Jj@}QfC&wvitkwz)VVWA$+=jxF*MDZKO1_)6q0XoF$xPdY(oGB=tBHfQciV*-mL0rL!e#9LOmE}w)l-+20K@+!y`4@ zjy(8Az7?Xz7ZNuDqdR~K`wuxz0APJ?H$B@>2H3+;z1QJ@>UsrZlI|;@J+!q9W3G3? zMaSAp7e^HGV7D5Mbya%guL8hYu)QvCJ6z$%4i~*zF-s;kvEf31=X$Aq69C3lb9TpA zz>@J;xMDnnK2znAJI9a(y1SxJcTN-ebm(%Wp)1a=B>n8)-H>77n>ZjLAE?qh6X8h7 zHD(>mpLL}K)dB6TlYrrgY)FUJ@ewj#%9e^*NU>0@yidM@P0o-Z^u2|*3UNL(dk-3F zl!Zh9w}f+0g^Oqe*n;17W&TRhmBr+1GMg1`;o*l4*8@;^_2gRz@YU>6)W=e<%xKSK z#llK0K$qO8wAULh(Z{k8hz?|*h;0Z_D_lh4uc}Y5kP|{Zvv&L_fYv80{!y7^p6@s8 z`LvYn@psX_gN+bY$ak}9Mud^(?OHG@eD2jsVa3%UR!uEXE(RcnWuM`9qME7l2`pG2 zORKQ!V?2oWjs3Td0%PeGMBd4@N>;FAY1b04f9;@502Fapm?we(7S~=2u`u8xr;-Qx z6t@%+yzq|prQ?x?J*s&2gPDa${2TbmPxrey>a4f66VKs>F8xa^DLntFiIvI?yHv!| zjp1J>kCy(;@SX=%51>AW!()pw@E<=42)$)%eALY=bUd~K&VHK z1a$5iMbWCg+9easNc-A^_zcT({W3-jgu>lCvlm!ML%$Pk)xG0)Y!|(l>dr!o?%`YS>RVqMncEu*}falQWtY&O$`gkfQH%RqEa- zSb6~>l@O^f1V;XbsV}CA4B(wusZOx)ZZcBt{4P7B562JzD)9i>;|=9oL~JY#$;iuu zfoP+L2`o6W)s5lKnXeKOAZ-Nc$KDr(Tm#5=i24yIk6KMSuMI6`t)P~Xu;utfJFmoA zvxGNttYhTiXYXTE)wmfqt!zyeC_ybElenVFyiS62gl3D>8|kR!oF;jY+wKliNZlYp zD~e<@K%bxyN&&EHAYsCU*yMB=3sOVS7;d!sOfLqSBWPuDkQ`VHE4469kRnvWf=w3Q z%N{{XQD?>EqPb|(+lv$--aK*E+m%?SijwDm($<43jxK~VI zd$m|JeHKSQs;vueNeakLv19x#3C~k+7Uu^MZNH3DJHRpKsAe-IbVP zQp`p{*l36drL$_**y~`03=K7dkFs1C@b>WD@}{hmZW`uhA=}*caI=xTcM8$n*Bdf| zKU|o)ZD`TdR*@?#BRG|D86oZ*!I}dxxX^-2fiY?KSE$;yz49r-vPzfw0kh3oYtHTk zrczaB<@l7^J6qXju@bvkbH~v*DkPA#N}1)6EKlihJW8HZof*HH<4|0SO+S6w^T@F6-N6%Hyu{lYhh6;YP0IUT_Y5Ffs&7P zA;Q~$y&Oa_AoNy>`ki@C$R(}eHTnWgx*)JU)S`t-y2?^42BP@Fs?touK?|5i3X+NS zWU*j%wH4c<>D|KD`5G4D!5e3rn2jCJ%^;v9qmy}ga_J3IU%Cn~i;(qAdr?1fTTTDD zLmXe|T?Mq8#{4jawQt=RGPUYJTxWk>GjvSI2tRwnfBjP%CYE|D&JHVxe zmRr;$7i6}S!o8ofSB0RX78X9<9lI{bl<^(B`lzyffQ=adY?O6ai&o|XiaM~3_Pi~E zd0p$4!b}M%;Ck+3qD+Bd&mVH-zSgR_Z`)6;P?_~Y^ajWiT8~=TPAH|EdI;2N5lLYy zL<`$^1vtFGGAjr5RSS`Q;i&`P(iKF~94_@Af{Yo4i&;f|)GMuku%oGl8*OMSBno>) zcY(sl;+k4P5XB;VA6re#LKGUUY;G>XFG=uslZye!4q(AJMIPH6jmXqmdJT8CGDJ{& zM_J7z1j=pw@I(iSMUih|<4f5H9sn@``a8fKy3c0+{=te#Emx@tMNU9$t4=5(8do}i%y-@v1Ahlaxw zCs@W6>?@&Lbw>d=(O$?2&aG-k#R(d7CQ-r%0(Q zdp|u_oxX8LCpmPD4GyHR)Yq#HX1NxyAwGa(yCjv}!SAeDsr9jW&0np40cTg({m+3PKnJu+%h98Em-t)DVeNSC1-v`Q7|-c{M%7wjx?pWb zmN#@KK;*#3c)YsH3!vJ95M9hx-(aUIwBs!wAHmUH9lUSn&QZgrD0Wlb&ZUqncWL2a zS|NX-XChGrgZ9<3Y6Xkv4l2ni+1N@7B2zD_iM0CI(uW}xN7_D&$47(PK0FiY4bCrQ zEfPCKA9g0$F92ZO042qQ_b+U|JcW~-S&#x?xY?`TqvdwVY?PG{IAAWEl*!B7zHguD9LCF3a zJ5}HLgQ*;xDYKRJ>)To=wo2Mm@cN-tnyYm?Zq?1=;>@!ghHm}$=u(7t&Su-Ti&h6} z8A0UtBbzp>zNfYftiOAG+I)_F$;xHs{UYMnR92!KT%B~Aa91N~B50(w=v45F>(m>^ zcu~n7x7{B*|9yDn`=Pr`Nf$m3Kt%fS1Sda?Jl=UTqFk1!8Wek+e|`6}Javai#)jVUqymW4Wk+|RH{awb^{R!nP?ZgP3}5wG3=Q|=j>g3SfT+IFA^AJ=t-VN*2R({1|VYa+OAdW zO=0ePZv5s9RF-`ULzstg0YKTf1$$Lb!(sO~M=rPW-xLHo(yg8*8I6nvx zmDAE<+qY$!Yu?>`foI-l<)5Zx$`!H`wlcxW`@ejP*dJ$5yMDME(l$7gz2i&a<7aw0 zP-U8gkt~ZeW-`dC?6>($!E2~fNl_!3*H>RIgg_ONn|@gGL^R{Qa#<}uVmGoFe+03dg$ ztm*TkuLIu8kAL}Q0RU<(50^!9CKD^|%U`59U^syh(Lv1h`PO6LT95{i`qcToJC-L_ zUr=-Rb2@=!;@YeIu1CJV&i(d&xf97e@?$LY?zPif8L~{kc>MC@Ox1Z*IHPztnV zx%&QkUo=%nf3O(o`+KqSuJ7T6nisx*K0ioT{PRVmaCGDA_CF;Xt3$3w|6c7oI`#MG zwCdBp>x*}%By%609{u4=jam@nNkJXMguwzrvX@KG=GoL#==x%|BC-)IqX5A4lD zhLrsTUkP0Vx;ds%<TKL)Z^NoI@Ha<@!dP2HVoOF1u65RYe_QWopV;) zxUYb@+(0*H{ECv!4z!49F4tZE-9hC!9w^sQRHVJT1Fby@oGA1|p4@2Hn&a+OxOP(E z{L-q{q!rA3;eqS9(Fmw^ot<%!Vy5CKAiNbae?IBg;3S%1G(cb@+!n6$Is{ z9#2%8TQ_9NI|((ViGgUInEeycYhU+!+bv+wHAE2*7Q^Qshs0c;E4}4XM;%EVS>0CW zc4yC$A6hMeCDRfJBhvv7I3kpWLP8eoyjFmH zjBU8>@4HDSl6e-!cLW7U;D6LCbT-jeweoYeliESsw#<+N+Ih(Vc|R+TFRf~>HGS~h z;g34M5uiTWP2bVA#Uyg6vGvpU^gVJfVEztdP? z)sd8?GFH|Df)Gq~93ck0oC9sR%Yf8<@cl1&9wdyal07jDg!5eRH_a@C#2p%9ItO0z z$pKFv$@dfQv%;h_FglJnx7phl+(v4#YN+#r60y2^xeQU9?3BL^Zd(m%gcP~!TMJ%g zia(+YLMjOAJ2_i5NVj)B=%5-!9}9}2DSMu#lL*JLes~h*NTcwg|Fv= zpyWs^pf{Z=|Ebp7iK_l%v(o5NQcQQFdE{EbE&Dr__z+0`-aF;{YZhTSHpkJ zK39xOiZc)yOsCV+SrFM~J74vQ{pdKB3>3uMjHL0P7YZOfCCLb++1axSt>7I5#>b<* z9E`*gi{!-6@wHMWbh`)g3@$CeOe8D1&;;wNqq^@DMx`_{*N68dHrY#n=(Qw5vCyVN z#+9Q`P9dCH2pN8=#ZgC-wHs^Ws8Q(GcaHvbI)QKd>55)|CtnUL3f|rE!8;+SkGS&i zgej~x1&5}tSocEIjA(`xO0l^RwHmN5)0riLz|b?L#wh191#_+77K6Po;5JLvqN7f1pLg+Gqj$XTA(gT=Sw zpw!Kt5ikl> z#d2DVj?}f9zPU6&!cdhaOA!hJrKn?tA$QxYM7nk?G{itLtn`MR7=c(qL^><`=P9Gh z6c_}^0Fw}8EZ5xerp4tZ%pc1~L7{#Z*I6f{m0LZ%xVm?tua?L<}ZBc6@oDeyv73M~IA4w~mzT>k@Oc4yh z*)ZJ*81=w*lmJW@J`fv1_9Tct((Iw*_ydZ5(`@4HcQff<_VkGFb$xDw*DPodF7DouHlK_t%GlbC^?^ zXVr40e@_(b@K*&$kMam}^GSkiUF1!=6O2U+r-Ofbu~gHBa6!UnC=yz2sRKj0|C^$6 zFQ4FC3o|vBwWi2IdIr4)jLwAoqmOacE~d815* zLNMENf{-LAj}0Z(9*1)0q5d(ZRZcJ(bIi_88VJA*oTAFj+#v_ZSa1|*1Q{P5E>KeH zAX7FJi8vgl48^wVf=pKFt~(2-RRalkqoSdaeW~aZ>h)xqUs<@`Wc6|jlAJ&EFHs%l z|G4QD(T7C)O#Ab@)aIGRS?qUU$b8hS~2b5>uWH52yj+cvBr zM5S#%qfAw;PwCRfht5N39bITf7#3!>h zWH&|Dnn$1$ZFf>M68kX*qIzcO;q%S#?@gv21*V1N-~l0#CvJ}1JFmtgzu-8ip0<9+ zE$=EI{GX&3LqNIE&Ay4PH>E4JHNITkKDOGa2|_y`7)qOlPzY!Vv`jO-`s;20@O5eV zwyplb(m6>)#RP%U1QQklkddm6ky(T%F)*)CbDTM8V##PGvbBk7bMLv9vR#y-8zY;UJ7D@W8`?d6WQ&t%ttk6BuDn z-vyx8XZ7Fk%U2YMKCf}bSp-WW#yy4*DMJ0Cgr`tp)-3eD((*!MjHb%|qUnd$LM1&5 z%!JTlvGIl>6-Cd48Y8r4s>`9%AJdqGnM06uFlJZ`_63-G6p+?SrI$4|^c(3~CO{*P zWK@IaSUZ#0=xrbVBEq&Rh~9wQJi-pq6={<20rL~n^Qsd<(6#A9S2J#Bj#QG;uw)`( zOPLo{JO!m;J}Sr@S_3PIbi$N@^3yjPjuUunB`Yeya5{pGCNlh$_0Wv^BTP&bmQGHiAfNowECG)Nq=I2+4im&vPF z%ks|+mO;R$=94@%d5%*#fVIT42^&*5{=rGLWc>S|8gPdAF2$>N~BmSY{C+1 zWO#0WC_<%3zY5<>2teX@L(N&%yg{^~vNaTd%-^)iFT|}gpCo<$=*z^|Wo@#$_kEBc zJCZANMGBk|0LU_lbt!D#>aGt9XYD7A^vHI{9hL!M11YPT?hu-eHp@?JBZLl$GcJ#A zec3IBD;R4U;#-eC7P| zkj7p}ER*vmoA{gX7IBKS7FsjXi#KkYQ~IW-r&RPN>@&3N*gp}z{1wqo-iBDV9l34+ zZ@GGo1f5w$NBaG+4pT1@Y(4+^=GkA}`Pt>1<P++w5P7Zb_2^VLbr)xkf9ySzlpglEDmO(2M%{&&V$`s?dG6r$$txI+egSE!#9;Dpk|4gO>7Z4y;7diQ`p2_18wSL6wIXfvXCvY_@XN%6Y`y0e z%A+h;l2{fFf@%J#SM99VQkNcMr?Q!iTI02a)Q0nv275IW<&SJwGC}W8eMV5D?zlu& zv+(3Wbr_t~L>&)3CXkLnL_WE1lkTT%BT~NdT{UT3*^8{5z(&tRBS8Y?hPSF|k34Pt zS{i?2#-)lY1)T)6FZ*-_EcgG_XqNZ)|E`HfgfN?azX zw-k$%%wu71h3JO2xP@_Lk8+HSK-tD`f5OfH8$pyyS#t{E3ENMYaTUiSiqglGw@ud# zsXSG;QA|;9Q2=3;uHJ!{ZQ2kc*1VN}UrjX!J~0RnP5krpygC*S4oIgwmG`?G$lg@q zO^`fN4qV@cmde1{L^|Cl01|}LXA=A0G+;E)$wHKx3O4T(UiBpp0#~NaR2EbPXqB$k6IW;vs1(ayK zql)F9Xlz`Y{(MbC>^D6o5HA8X=h-u_1ykR5X$*>FM@v0c-OoE654Ypt=!-_tj5}== z*|ZRmTHBobmZGw2M*^QjwrD?qX=Ch=7L+adX`OHHR8}TkdwmW%9uFVLeV4Jhtr@16 zwUI2{!}-VVp1<33GSaX7E#(sCxl)pggM;}(EgKJgr!gUzm6c4(?w;B%nNii88W(8H z`+Zs6wLC4F(tkJgLGWct@_81xvieTrEm6}-^2J1RYV4iHysvoDSFE6^iGDiufvwRy ztrnf6bI?x4W#ql*yVdp$ou#bNQ{5l#Yf3)uam=y)XYpQ$W$3)WV9=KWoA;dDzVFi5 zVgE6EQtlk{>^Kbh#e>YS+coBhTE9SyB%(4u&MoU>xByf)a7DjlmZ&u~OZ@Xew7e== zzH@!{&)=2V=`S)#D;h_a8?S$ReSUeFmwnof_1(@N96e zY9bF6(bG+WeXA>mZZuw2jxZmuRMw+j2Axt_Td>zzY2 zQAum84^juUe&uc6roH#7A2kKMku+$i=SEC4Ex)`Hv2!H6^P{9iNtUtMaCH%m#b@h{t0zCqEllje|gO{&aU5u9WGXk<-_JBGR zKGx}~B>u?z&m%!x`Ju%7c)vvZ5dS@UYk4A9kb3CIQhjrd0%eqY?2=bx&#}wCNpeAj z{yC0%r=#jb1G!-3m!9D3NfJ4-?O5T@AVHd@R|r4y z){sYO&Te>UdHz19(3_XOZ6}vqiR`VsHRb~kt0>EH3ah+T(tBNxOMV-Ar}o~*f!h@W zPRDERy~{jad-i2dj>oCT@Ff8w_IFOT`Nz!ghF;_6;f({Rf`BVuH`KzLuQoiqRsSOL zdBpv9N%FOYdp7vDn&%&m?K>BL(|e)CG)?|Q>$icuCmze&dyhQ$T@|nT=$PN1Sp`a9 z$O#ctix<^)Imf$}zwp4p=wXC}UTv@&ig5z~p_J;N9LN?#bT=v2**x3GuYKNTt@+fu zTPOFA=P;#+>s0Pnak3Bq0JsSSvq}e}2Wbi}F+-k6YuBB_T}6}aDPd}JUZ36EfS#E9 zWBa7%oUC_odm3hIhx~J0V#n-{7Z}99{X6>2`>?X-$oQdW2Zi7h4`y#9uEOfR3&sG6 z)ngomeR0zhWg9V1UMHP-mv>?aECkPFr+U2m(%ils2-s=x=~>!&)Y*lyotew;ogej@ z`*Nn0<1eJv-n4jg;>yMB{Wqp^&V6|})wAMrx?lP5c&u)TN^`>2zfp0V&Q%IP0sms( z$J^%|C{rJYia$SkbmB$gPszKfE>rJy@del2zXxCK+cp2;psP>Z!AO`M=ZZ^T2aDBq#1T%n}`z-!#o##FZL+WTY{u!4vLivf2wRh^ab z5CCBO2iVR1yEZ{4px0rYaDG=e9#yN9=lp4 zD@9n$HP0eg!w2K;n!j}CrTvO> z==!+7WZ&EVU2U^i9q!{8FBf$RqkdWUqM)|dv=@x*|i7$k{|i0Bz#C4;KsNV z3>98?Y}eC}1sp648Y&G6b=ch$OPk5IFK%zdd!v*0uJzwAR(*Z@T!SJpZ}aI&XXGaJ zL7k4~LW#T9liAyQz^7Q(Uf)gdF`8;h8{R9AziVo9gfQ{$<&AoAzL%=K{*j5>HMe?C z*Tx{-WnY=+R+c=gN{OzNnee-`ikUb5PGJF>MqJ3BV}hxWC5^1xw~i*(#o7Pe@AD~h ztS?N(S)+W!{Z-o=A@k)0L-pJ@mpp*jkJa4c$qxGJ^0~l;fKz*VXWHL}?QIqMp{{zvWuLv4o(ThRB71scyo{&6*B@xsF^-Or>C8&o*v7mU6SUIC7(1CsCkh>V;5;xWH} ztT|OyqN!T`~QnS-a60)MrOHQas1 zJYE_NFe%|7v}_{-YS zTg^;u;5M6Ow~|>g6+%KZzNn7;Zg#D>JHbWHjCw`EXzW=3^yJNx$BE4eu|`ic;pavr z9VklV^L$Hd&Wx2Izw617+!I;nCf1_9u5~+J zdQLw#xs(&w6!Pe9+#^Kg=i2*^1?ylfOXqhRNf+-GCoZ$(TSEpGN?reCuWa4F;&dO| z(yoQF_SH?8akDk=FvvAK5Ak1f-Wt5?s<8Tw4zMp*;>lrP?W{2AP-?t-Q&KNiz>Bmfe`PYpFivb%TA zb8=?Rry6$t1d^}bMG3{voZ7CB?YwgRk|st=gI#mrYoh(e%Ma0Fm6zMJj4lLq;2@ABZ%_Mb-e$&nrgHm1E_9VpLC3oemW%m3^zT#BK=%< zdg4O*c^H>X<|Z?^(vIwOE;plso7K(DUf|}!GV;h77Z@2ALozONGm0uQu6Ac!TgbQ$ z%M_3^Z!j`%hGgF6W>!{Y-s#S)S;)K#%c>`5H8QfAL$dC3vmR7rJ?hSSypZ)2#uJfw z?F?RL2=5t}*HgiJ-p%V@;Jtul50SH9F|uEWWWV8Nk5!z?9`DYcT*#h+