From e6565f901039b3b7f8f1e0576cea033f3a2daad6 Mon Sep 17 00:00:00 2001 From: Ajay Dhangar Date: Sat, 17 Jan 2026 22:22:10 +0530 Subject: [PATCH] added docs for ml --- .../cnn-applications/image-classification.mdx | 85 ++++++++++++++++ .../cnn-applications/image-segmentation.mdx | 91 ++++++++++++++++++ .../deep-learning/cnn/convolution.mdx | 88 +++++++++++++++++ .../deep-learning/cnn/padding.mdx | 91 ++++++++++++++++++ .../deep-learning/cnn/pooling.mdx | 83 ++++++++++++++++ .../deep-learning/cnn/strides.mdx | 86 +++++++++++++++++ .../ml/max-pooling-vs-average-pooling.jpg | Bin 0 -> 164329 bytes 7 files changed, 524 insertions(+) create mode 100644 static/img/tutorials/ml/max-pooling-vs-average-pooling.jpg diff --git a/docs/machine-learning/deep-learning/cnn-applications/image-classification.mdx b/docs/machine-learning/deep-learning/cnn-applications/image-classification.mdx index e69de29..101d9d0 100644 --- a/docs/machine-learning/deep-learning/cnn-applications/image-classification.mdx +++ b/docs/machine-learning/deep-learning/cnn-applications/image-classification.mdx @@ -0,0 +1,85 @@ +--- +title: Image Classification +sidebar_label: Image Classification +description: "How to train neural networks to categorize images into predefined classes using CNNs." +tags: [deep-learning, cnn, image-classification, computer-vision, transfer-learning] +--- + +**Image Classification** is the task of assigning a label or a category to an entire input image. It is the most fundamental task in Computer Vision and serves as the building block for more complex tasks like Object Detection and Image Segmentation. + +## 1. The Workflow: From Pixels to Labels + +An image classification model follows a linear pipeline where spatial information is gradually transformed into a semantic category. + +1. **Input Layer:** Raw pixel data (e.g., $224 \times 224 \times 3$ for an RGB image). +2. **Feature Extraction:** Multiple [Convolution](../cnn/convolution) and [Pooling](../cnn/pooling) layers identify edges, shapes, and complex patterns. +3. **Flattening:** The 2D feature maps are converted into a 1D vector. +4. **Classification:** [Fully Connected Layers](https://www.youtube.com/watch?v=rxSmwM7z0_4) act as a traditional MLP to interpret the features. +5. **Output Layer:** Uses a **Softmax** function to provide probabilities for each class. + +## 2. Binary vs. Multi-Class Classification + +| Type | Output Neurons | Activation | Loss Function | +| :--- | :--- | :--- | :--- | +| **Binary** (Cat or Not) | 1 | Sigmoid | Binary Cross-Entropy | +| **Multi-Class** (Cat, Dog, Bird) | $N$ (Number of classes) | Softmax | Categorical Cross-Entropy | + +## 3. Transfer Learning: Standing on the Shoulders of Giants + +Training a CNN from scratch requires thousands of images and massive computing power. Instead, most developers use **Transfer Learning**. + +This involves taking a model pre-trained on a massive dataset (like **ImageNet**, which has 1.4 million images across 1,000 classes) and repurposing it for a specific task. + +* **Freezing:** We keep the "Feature Extractor" weights fixed because they already know how to "see" shapes. +* **Fine-Tuning:** We only replace and train the final classification head for our specific labels. + +## 4. Implementation with Keras (Transfer Learning) + +This example shows how to use the **MobileNetV2** architecture to classify custom images. + +```python +import tensorflow as tf +from tensorflow.keras import layers, models + +# 1. Load a pre-trained model without the top (classification) layer +base_model = tf.keras.applications.MobileNetV2( + input_shape=(160, 160, 3), include_top=False, weights='imagenet' +) + +# 2. Freeze the base model +base_model.trainable = False + +# 3. Add custom classification head +model = models.Sequential([ + base_model, + layers.GlobalAveragePooling2D(), + layers.Dense(1, activation='sigmoid') # Binary: e.g., 'Mask' or 'No Mask' +]) + +model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy']) + +``` + +## 5. Challenges in Classification + +1. **Intra-class Variation:** A "Chair" can look very different depending on its design. +2. **Scale Variation:** An object may occupy the entire frame or just a tiny corner. +3. **Viewpoint Variation:** A model must recognize a car from the front, side, and top. +4. **Occlusion:** Only part of the object might be visible (e.g., a dog behind a fence). + +## 6. Popular Architectures for Classification + +* **ResNet (Residual Networks):** Introduced "Skip Connections" to allow training of very deep networks (100+ layers). +* **VGG-16:** A very deep but simple architecture using only convolutions. +* **Inception (GoogLeNet):** Uses different kernel sizes in the same layer to capture features at different scales. +* **EfficientNet:** Optimized for the best balance between accuracy and computational cost. + +## References + +* **ImageNet:** [The Benchmark Dataset](https://www.image-net.org/) +* **TensorFlow Tutorials:** [Image Classification for Beginners](https://www.tensorflow.org/tutorials/images/classification) +* **PyTorch Tutorials:** [Transfer Learning for Computer Vision](https://pytorch.org/tutorials/beginner/transfer_learning_tutorial.html) + +--- + +**Classifying an entire image is great, but what if you need to know *where* the object is or if there are multiple objects?** \ No newline at end of file diff --git a/docs/machine-learning/deep-learning/cnn-applications/image-segmentation.mdx b/docs/machine-learning/deep-learning/cnn-applications/image-segmentation.mdx index e69de29..94a48c4 100644 --- a/docs/machine-learning/deep-learning/cnn-applications/image-segmentation.mdx +++ b/docs/machine-learning/deep-learning/cnn-applications/image-segmentation.mdx @@ -0,0 +1,91 @@ +--- +title: Image Segmentation +sidebar_label: Image Segmentation +description: "Going beyond bounding boxes: How to classify every single pixel in an image." +tags: [deep-learning, cnn, computer-vision, segmentation, u-net, mask-rcnn] +--- + +While [Image Classification](./image-classification) tells us **what** is in an image, and **Object Detection** tells us **where** it is, **Image Segmentation** provides a pixel-perfect understanding of the scene. + +It is the process of partitioning a digital image into multiple segments (sets of pixels) to simplify or change the representation of an image into something that is more meaningful and easier to analyze. + +## 1. Types of Segmentation + +Not all segmentation tasks are the same. We generally categorize them into three levels of complexity: + +### A. Semantic Segmentation +Every pixel is assigned a class label (e.g., "Road," "Sky," "Car"). However, it does **not** differentiate between multiple instances of the same class. Two cars parked next to each other will appear as a single connected "blob." + +### B. Instance Segmentation +This goes a step further by detecting and delineating each distinct object of interest. If there are five people in a photo, instance segmentation will give each person a unique color/ID. + +### C. Panoptic Segmentation +The "holy grail" of segmentation. It combines semantic and instance segmentation to provide a total understanding of the scene—identifying individual objects (cars, people) and background textures (sky, grass). + +## 2. The Architecture: Encoder-Decoder (U-Net) + +Traditional CNNs lose spatial resolution through pooling. To get back to an image output of the same size as the input, we use an **Encoder-Decoder** architecture. + +1. **Encoder (The "What"):** A standard CNN that downsamples the image to extract high-level features. +2. **Bottleneck:** The compressed representation of the image. +3. **Decoder (The "Where"):** Uses **Transposed Convolutions** (Upsampling) to recover the spatial dimensions. +4. **Skip Connections:** These are the "secret sauce" of the **U-Net** architecture. They pass high-resolution information from the encoder directly to the decoder to help refine the boundaries of the mask. + +## 3. Loss Functions for Segmentation + +Because we are classifying every pixel, standard accuracy can be misleading (especially if 90% of the image is just background). We use specialized metrics: + +* **Intersection over Union (IoU) / Jaccard Index:** Measures the overlap between the predicted mask and the ground truth. +* **Dice Coefficient:** Similar to IoU, it measures the similarity between two sets of data and is more robust to class imbalance. + +$$ +IoU = \frac{\text{Area of Overlap}}{\text{Area of Union}} +$$ + +## 4. Real-World Applications + +* **Medical Imaging:** Identifying tumors or mapping organs in MRI and CT scans. +* **Self-Driving Cars:** Identifying the exact boundaries of lanes, sidewalks, and drivable space. +* **Satellite Imagery:** Mapping land use, deforestation, or urban development. +* **Portrait Mode:** Separating the person (subject) from the background to apply a "bokeh" blur effect. + +## 5. Popular Models + +| Model | Type | Best For | +| :--- | :--- | :--- | +| **U-Net** | Semantic | Medical imaging and biomedical research. | +| **Mask R-CNN** | Instance | Detecting objects and generating masks (e.g., counting individual cells). | +| **DeepLabV3+** | Semantic | State-of-the-art results using Atrous (Dilated) Convolutions. | +| **SegNet** | Semantic | Efficient scene understanding for autonomous driving. | + +## 6. Implementation Sketch (PyTorch) + +Using a pre-trained segmentation model from `torchvision`: + +```python +import torch +from torchvision import models + +# Load a pre-trained DeepLabV3 model +model = models.segmentation.deeplabv3_resnet101(pretrained=True).eval() + +# Input: (Batch, Channels, Height, Width) +dummy_input = torch.randn(1, 3, 224, 224) + +# Output: Returns a dictionary containing 'out' - the pixel-wise class predictions +with torch.no_grad(): + output = model(dummy_input)['out'] + +print(f"Output shape: {output.shape}") +# Shape will be [1, 21, 224, 224] (for 21 Pascal VOC classes) + +``` + +## References + +* **ArXiv:** [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://arxiv.org/abs/1505.04597) +* **Facebook Research:** [Mask R-CNN Paper](https://arxiv.org/abs/1703.06870) + +--- + +**Segmentation provides a high level of detail, but it's computationally expensive. How do we make these models faster for real-time applications?** \ No newline at end of file diff --git a/docs/machine-learning/deep-learning/cnn/convolution.mdx b/docs/machine-learning/deep-learning/cnn/convolution.mdx index e69de29..fad1675 100644 --- a/docs/machine-learning/deep-learning/cnn/convolution.mdx +++ b/docs/machine-learning/deep-learning/cnn/convolution.mdx @@ -0,0 +1,88 @@ +--- +title: The Convolution Operation +sidebar_label: Convolution +description: "Understanding kernels, filters, and how feature maps are created in Convolutional Neural Networks." +tags: [deep-learning, cnn, computer-vision, convolution, kernels] +--- + +The **Convolution** is the heart of Computer Vision. Unlike standard neural networks that treat every pixel as an independent feature, Convolution allows the network to preserve the **spatial relationship** between pixels, enabling it to recognize shapes, edges, and textures. + +## 1. What is a Convolution? + +At its simplest, a convolution is a mathematical operation where a small matrix (called a **Kernel** or **Filter**) slides across an input image and performs element-wise multiplication with the part of the input it is currently hovering over. + +The results are summed up to create a single value in a new matrix called a **Feature Map** (or Activation Map). + +## 2. The Anatomy of a Kernel + +A kernel is a grid of weights. Different weights allow the kernel to detect different types of features: + +* **Vertical Edge Detector:** A kernel with high values on the left and low values on the right. +* **Horizontal Edge Detector:** A kernel with high values on the top and low values on the bottom. +* **Sharpening Kernel:** A kernel that emphasizes the central pixel relative to its neighbors. + +## 3. Key Hyperparameters + +When performing a convolution, there are three main settings that determine the size and behavior of the output: + +### A. Stride +Stride is the number of pixels the kernel moves at a time. +* **Stride 1:** Moves one pixel at a time (larger output). +* **Stride 2:** Jumps two pixels at a time (smaller, downsampled output). + +### B. Padding +Since the kernel cannot "hang off" the edge of an image, the pixels on the borders are processed less than the pixels in the center. To fix this, we add a border of zeros around the image. +* **Valid Padding:** No padding (output is smaller than input). +* **Same Padding:** Zeros are added so the output is the same size as the input. + +### C. Depth (Channels) +If you are processing a color image, your input has 3 channels (Red, Green, Blue). Your kernel will also have a depth of 3 to match. + +## 4. The Math of Output Size + +To calculate the dimensions of the resulting Feature Map, we use the following formula: + +$$ +O = \frac{W - K + 2P}{S} + 1 +$$ + +* **$W$**: Input width/height +* **$K$**: Kernel size +* **$P$**: Padding +* **$S$**: Stride + +## 5. Why Convolution? + +1. **Sparse Connectivity:** Instead of every input pixel connecting to every output neuron, neurons only look at a small "receptive field." This massively reduces the number of parameters. +2. **Parameter Sharing:** The same kernel (weights) is used across the entire image. If a filter learns to detect a "circle," it can find that circle in the top-left corner or the bottom-right corner using the same weights. + +## 6. Implementation with PyTorch + +```python +import torch +import torch.nn as nn + +# Create a sample input: (Batch, Channels, Height, Width) +input_image = torch.randn(1, 3, 32, 32) + +# Define a Convolutional Layer +# 3 input channels (RGB), 16 output filters, 3x3 kernel size +conv_layer = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=3, stride=1, padding=1) + +# Apply convolution +output = conv_layer(input_image) + +print(f"Input shape: {input_image.shape}") +print(f"Output shape: {output.shape}") +# Output: [1, 16, 32, 32] because of 'Same' padding + +``` + +## References + +* **Stanford CS231n:** [Convolutional Neural Networks for Visual Recognition](https://cs231n.github.io/convolutional-networks/) +* **Setosa.io:** [Image Kernels Visualizer](http://setosa.io/ev/image-kernels/) + +--- + +**Convolution extracts the features, but the resulting maps are often too large and computationally heavy. How do we shrink them down without losing the important information?** \ No newline at end of file diff --git a/docs/machine-learning/deep-learning/cnn/padding.mdx b/docs/machine-learning/deep-learning/cnn/padding.mdx index e69de29..515cf8b 100644 --- a/docs/machine-learning/deep-learning/cnn/padding.mdx +++ b/docs/machine-learning/deep-learning/cnn/padding.mdx @@ -0,0 +1,91 @@ +--- +title: Padding in CNNs +sidebar_label: Padding +description: "How padding prevents data loss at the edges and controls the output size of convolutional layers." +tags: [deep-learning, cnn, computer-vision, padding, zero-padding] +--- + +When we slide a kernel over an image in a [Convolutional Layer](./convolution), two problems occur: +1. **Shrinking Output:** The image gets smaller with every layer. +2. **Loss of Border Info:** Pixels at the corners are only "touched" by the kernel once, whereas central pixels are processed many times. + +**Padding** solves both by adding a border of extra pixels (usually zeros) around the input image. + +## 1. The Border Problem + +Imagine a $3 \times 3$ kernel sliding over a $5 \times 5$ image. The center pixel is involved in 9 different multiplications, but the corner pixel is only involved in 1. This means the network effectively "ignores" information at the edges of your images. + +## 2. Types of Padding + +There are two primary ways to handle padding in deep learning frameworks: + +### A. Valid Padding (No Padding) +In "Valid" padding, we add zero extra pixels. The kernel stays strictly within the boundaries of the original image. +* **Result:** The output is always smaller than the input. +* **Formula:** $O = (W - K + 1)$ + +### B. Same Padding (Zero Padding) +In "Same" padding, we add enough pixels (usually zeros) around the edges so that the output size is **exactly the same** as the input size (assuming a stride of 1). +* **Result:** Spatial dimensions are preserved. +* **Common use:** Deep architectures where we want to stack dozens of layers without the image disappearing. + +## 3. Mathematical Formula with Padding + +When we include padding ($P$), the formula for the output dimension becomes: + +$$ +O = \frac{W - K + 2P}{S} + 1 +$$ + +* **$W$**: Input dimension +* **$K$**: Kernel size +* **$P$**: Padding amount (number of pixels added to one side) +* **$S$**: Stride + +:::note +For "Same" padding with a stride of 1, the required padding is usually $P = \frac{K-1}{2}$. This is why kernel sizes are almost always odd numbers ($3 \times 3, 5 \times 5$). +::: + +## 4. Other Padding Techniques + +While **Zero Padding** is the standard, other methods exist for specific cases: +* **Reflection Padding:** Mirrors the pixels from inside the image. This is often used in style transfer or image generation to prevent "border artifacts." +* **Constant Padding:** Fills the border with a specific constant value (e.g., gray or white). + +## 5. Implementation + +### TensorFlow / Keras +Keras simplifies this by using strings: + +```python +from tensorflow.keras.layers import Conv2D + +# Output size will be smaller than input +valid_conv = Conv2D(32, (3, 3), padding='valid') + +# Output size will be identical to input +same_conv = Conv2D(32, (3, 3), padding='same') + +``` + +### PyTorch + +In PyTorch, you specify the exact number of pixels: + +```python +import torch.nn as nn + +# For a 3x3 kernel, padding=1 gives 'same' output +# (3-1)/2 = 1 +conv = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=3, padding=1) + +``` + +## References + +* **CS231n:** [Spatial Arrangement of Layers](https://cs231n.github.io/convolutional-networks/#spatial) +* **PyTorch Docs:** [Conv2d Layer Specifications](https://pytorch.org/docs/stable/generated/torch.nn.Conv2d.html) + +--- + +**Padding keeps the image size consistent, but what if we want to move across the image faster or purposely reduce the size?** \ No newline at end of file diff --git a/docs/machine-learning/deep-learning/cnn/pooling.mdx b/docs/machine-learning/deep-learning/cnn/pooling.mdx index e69de29..bb08edf 100644 --- a/docs/machine-learning/deep-learning/cnn/pooling.mdx +++ b/docs/machine-learning/deep-learning/cnn/pooling.mdx @@ -0,0 +1,83 @@ +--- +title: "Pooling Layers: Downsampling" +sidebar_label: Pooling +description: "Understanding Max Pooling, Average Pooling, and how they provide spatial invariance." +tags: [deep-learning, cnn, computer-vision, pooling, max-pooling] +--- + +After a [Convolution Operation](./convolution), the resulting feature maps can still be quite large. **Pooling** (also known as subsampling or downsampling) is used to reduce the spatial dimensions (Width x Height) of the data, which reduces the number of parameters and computation in the network. + +## 1. Why do we need Pooling? + +1. **Dimensionality Reduction:** It shrinks the data, making the model faster and less memory-intensive. +2. **Spatial Invariance:** It makes the network robust to small translations or distortions. If a feature (like an ear) moves by a few pixels, the pooled output remains largely the same. +3. **Prevents Overfitting:** By abstracting the features, it prevents the model from "memorizing" the exact pixel locations of features. + +## 2. Types of Pooling + +### A. Max Pooling +This is the most common type. It slides a window across the feature map and picks the **maximum value** within that window. +* **Logic:** "Did the feature appear anywhere in this region? If yes, keep the highest signal." + +### B. Average Pooling +It calculates the **average value** of all pixels within the window. +* **Logic:** "What is the general presence of this feature in the region?" +* **Use Case:** Often used in the final layers of some architectures (like Inception) to smooth out the transition to the output layer. + +![Comparison of Max Pooling vs Average Pooling on a feature map](/img/tutorials/ml/max-pooling-vs-average-pooling.jpg) + +## 3. How Pooling Works (Parameters) + +Like convolution, pooling uses a **Kernel Size** and a **Stride**. + +* **Standard Setup:** A 2x2 window with a stride of 2. +* **Effect:** This setup reduces the width and height of the image by exactly **half**, effectively discarding 75% of the activations while keeping the most "important" ones. + +## 4. Key Differences: Convolution vs. Pooling + +| Feature | Convolution | Pooling | +| :--- | :--- | :--- | +| **Learnable Parameters** | Yes (Weights and Biases) | No (Fixed mathematical rule) | +| **Purpose** | Feature Extraction | Dimensionality Reduction | +| **Effect on Channels** | Can increase/decrease | Keeps number of channels the same | + +## 5. Implementation with TensorFlow/Keras + +```python +from tensorflow.keras.layers import MaxPooling2D, AveragePooling2D + +# Max Pooling with a 2x2 window and stride of 2 +max_pool = MaxPooling2D(pool_size=(2, 2), strides=2) + +# Average Pooling +avg_pool = AveragePooling2D(pool_size=(2, 2)) + +``` + +## 6. Implementation with PyTorch + +```python +import torch.nn as nn + +# Max Pooling +# kernel_size=2, stride=2 +pool = nn.MaxPool2d(2, 2) + +# Apply to a sample input (Batch, Channels, Height, Width) +input_tensor = torch.randn(1, 16, 24, 24) +output = pool(input_tensor) + +print(f"Input shape: {input_tensor.shape}") +print(f"Output shape: {output.shape}") +# Output: [1, 16, 12, 12] + +``` + +## References + +* **DeepLearning.AI:** [Pooling Layers Tutorial](https://www.youtube.com/watch?v=PuFNG721zM8) +* **PyTorch Docs:** [MaxPool2d Documentation](https://pytorch.org/docs/stable/generated/torch.nn.MaxPool2d.html) + +--- + +**We’ve extracted features with Convolution and shrunk them with Pooling. Now, how do we turn these 2D grids into a final "Yes/No" or "Cat/Dog" prediction?** \ No newline at end of file diff --git a/docs/machine-learning/deep-learning/cnn/strides.mdx b/docs/machine-learning/deep-learning/cnn/strides.mdx index e69de29..23828f7 100644 --- a/docs/machine-learning/deep-learning/cnn/strides.mdx +++ b/docs/machine-learning/deep-learning/cnn/strides.mdx @@ -0,0 +1,86 @@ +--- +title: Strides in CNNs +sidebar_label: Strides +description: "Understanding how the step size of a filter influences spatial dimensions and computational efficiency." +tags: [deep-learning, cnn, computer-vision, strides, downsampling] +--- + +In a Convolutional Neural Network, the **Stride** is the number of pixels by which the filter (kernel) shifts over the input matrix. While [Padding](./padding) is used to maintain size, **Stride** is one of the primary ways we control the spatial dimensions of our feature maps. + +## 1. What is a Stride? + +When the stride is set to **1**, the filter moves one pixel at a time. This results in highly overlapping receptive fields and a larger output. + +When the stride is set to **2** (or more), the filter jumps two pixels at a time. This skips over pixels, resulting in a smaller output and less overlap. + +## 2. The Impact of Striding + +### A. Dimensionality Reduction +Increasing the stride is an alternative to [Pooling](/tutorial/machine-learning/deep-learning/cnn/pooling). By jumping over pixels, the network effectively "downsamples" the image. For example, a stride of 2 will roughly halve the width and height of the output. + +### B. Receptive Field +A larger stride allows the network to cover more area with fewer parameters, but it comes at a cost: **Information Loss**. Because the filter skips pixels, some fine-grained spatial details might be missed. + +### C. Computational Efficiency +Larger strides mean fewer total operations (multiplications and additions), which can significantly speed up the training and inference time of a model. + +## 3. Mathematical Formula + +To determine the output size when using strides ($S$), we use the general convolution formula: + +$$ +O = \left\lfloor \frac{W - K + 2P}{S} \right\rfloor + 1 +$$ + +* **$W$**: Input width/height +* **$K$**: Kernel size +* **$P$**: Padding +* **$S$**: Stride + +:::note +If the result of the division is not a whole number, most frameworks will "floor" the value (round down), meaning the last few pixels of the image might be ignored if the filter can't fit. +::: + +## 4. Comparing Stride and Pooling + +Both techniques are used to reduce the size of the data, but they differ in how they do it: + +| Feature | Large Stride Convolution | Pooling Layer | +| :--- | :--- | :--- | +| **Learning** | The network *learns* which pixels to weight during the jump. | Uses a *fixed* rule (Max or Average). | +| **Parameters** | Contains weights and biases. | No parameters. | +| **Trend** | Modern architectures (like ResNet) often prefer strided convolutions. | Classic architectures (like VGG) rely heavily on Pooling. | + +## 5. Implementation + +### TensorFlow / Keras + +```python +from tensorflow.keras.layers import Conv2D + +# A standard convolution (Stride 1) +conv_std = Conv2D(filters=32, kernel_size=(3, 3), strides=(1, 1)) + +# A downsampling convolution (Stride 2) +conv_down = Conv2D(filters=32, kernel_size=(3, 3), strides=(2, 2)) + +``` + +### PyTorch + +```python +import torch.nn as nn + +# Strides are defined as an integer or a tuple (height, width) +# This will halve the input dimensions +conv = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=3, stride=2, padding=1) + +``` + +## References + +* **CS231n:** [Convolutional Neural Networks - Strides](https://cs231n.github.io/convolutional-networks/#stride) + +--- + +**We’ve covered how the filter moves, how it handles edges, and how it extracts features. Now, how do we combine all these pieces into a complete network?** \ No newline at end of file diff --git a/static/img/tutorials/ml/max-pooling-vs-average-pooling.jpg b/static/img/tutorials/ml/max-pooling-vs-average-pooling.jpg new file mode 100644 index 0000000000000000000000000000000000000000..d500abf8b8fc39365726032e0d72e44c99e73e2e GIT binary patch literal 164329 zcmeFa2|SeD`#(OLT^LK*jeTo0gRw=~*X&zV7-lebW5`l=LMSRxlqLHTMMbMUD*Kit zBnd5)Xc7N=q^EkGKHsP3`8>V8zyI&|jMqKx``qU~=Q_)Eu5(}S_nEUkv_1i1(%070 z27$pK5E%Fatxt06Y6TLUK_ERn2@o|11cHK?!BFz8jROsafT)0TY2Y9nfo+5-0q1vt z!-U|3^}~WdlpxS?Di90^K}k!az}a7)hGc(!f_xMD%{j&9c?s|g;sON35B!e<4)OsURF3O?_d6`-vPm?LD`^eC|CdlfrFuN@Ol%7n_Mg?xygU~P=Wz@ zsUXzA-JMJz2p9^5P(WZ18W;~wVGt-#0l-aJI0y`dKq;YAP>RnvlOx066#QsPW;N54Zme$( zi$Fwb)#L)3^dc3jjJo6cFo+%s#DYWNpxvO4g4#)(V%kYYN$}5Kh1#d<*4~gRmsTFj zo!vJk!CXKQOwx9CJ)^~ZimqegY}|5(OiO|}LlRMUEzkejg&>h6{KsqtB_|9udVMU+k7{E4_jKJYP(0s6Uqa{Q7-KEQno2Wm z1QwX(Od=M3h!}vQ2*EzG676)zExOW;w<(Jb4oCY4DEjD%BHWvM=lJ%kkxCPe=3Xex zW!u7oRIitpfHlcf$V3)J!(ZyJ;Jdf&?Jh}9s$7jW)Y9hClM4<#k#5g%(j13X@W z9n>ha;P0C&)?M8F`74G~)=gGRN!C?V(>!mlq}y!KW9EMSDt?8w_dSCq7E2FCo1c1H zvc6zYmF>NuL&ZVG^D*?%@I~PR%0^=$ca-D7UO46(2g*h7irnO0<>9wj2dUi;5xO-X z6kaJ^j?3xrJFfd`d<|2sybdz9O36N7EODQxGa1?6ixV43bh;v!9AbdhJj_B%Gb>|=}ub?^TjPQP666ZQxvPaO~+1X6@HUbA_3)7RyvKe4={^Wn-%Q z6Ot=a10U{vtYo21M+u5#bkIeFJ;tPtIWCm)mz){X;ZA1nV}F{md?L2t$vTMl@O8I_ z*oU6gf&Hw{94Y(+Wzs+ldLKiFnL)Lt8J3kcA98pSZ|=u!2}gUYMWmb$ouN7(RXTsj zlF6i=?SS!_BHe~I`B;`F58{XpbT?s7-w2sc$z8+i4?6qq1u`4XIB5*unpA*45`(EWj`HdqE&7-Z2NP%-( zofu04Qg%+OoHp#P@bu#w{A6f>gbip)=u%{r6Sud3x~fTAFnF zugl=~RCqMJQ>wysX<1Gr>wT)JG~np2*C=vJmwGlzm16j530^K~>E2J1QxtWt-~3ja z)0WyG4*J5xVxDWf6R$DX%M(g4I(=1-)NF3v{Z@K%haJk-z;# z>$t+8O0|X#sU*ICPQ3Y21s?QTlrfbd>`4EenabY6{xj{J%$#C#sb^R<&mN5C$vCPs zbz%gnD<{3sJY7`Lo}xY-!0GWq=*jDS3T=bunwCA^McrSVBThC7*QTFeHlp_n=Ukk6 zvel^cvg!&GeZSEDzV00{ywlN%SC(g%mp}PO6$iVXr9Kvt!c5f$OQZHnR)kGmdp}ru z)oP83(?CuKKVa&e)wGbToc_$ z-Mm(HWz|S>z^y|%V`4p|rpkm`p|&@$c9UZZm#7L~9XltJ?`Cvb+Oo|kX)i_1BW66e z#jCeoog-K3rqd=dvu+aNlH!y3Rzo?n1~NV}=S^A_d2ZIcY7a%c()KzoeafM}ycGtm zi8WZAHy1}!%8uRku1{TpJ1s=^*eNbfo!=pF7I|8cu$IwdM(WpMJMfea=We`5*jl*X z0)Ew}L$TLCe{QpqSuvnPlN8HjMOQVWf_Vua92wss7@Nlw{56Q17axb2`cp*3@a!=D` z@k8N0j7}=w=zc2xln0w@yu+il45Zu9*8=gk37EP1S_3piS#ug_R-O_`*dMEjC`#tyB zetjAjy%G`IGz{oIsxgSl3x%RQ)tmn$wt^;Od~MwHY8AxsIfL(W%9o?bJ7*tt_oD{8 z&ZIk!!J%BIsopp|;k)HO?Y(48I+IMJz6X7;NtFWEIwB~UjA{F{gE{{=bFY_T;PQcC z!@|NK(Cr;lm%8Q*d<)A6HWHkQd8ilhev$j>*Bt$-7*}W2MXMDSyl62d5 zu2>uoDG6qCp@?nQ+m}>t?ED^E$Z+~X-TtDkHXCo&ZmU+w?WC97C;2OB4*4BR3f`l1 zunx;XrBUyGt}3#YaUF_=f=O0>w-QTcf;^weo)_#Ll+q#Y?xuNmIYHHK zG<|cjCMT2{?&%%AeMY~{C7wB15gZdP^e$PYekyBw^U`pdR6d)pox9a2AuibQUTyv; z>Qhys&*6_D?%Cr=ltsVr!SwRNbkS%-6}4l;Cz(t;UmKk^Hts%`_eQYD8&cZt>E>(S zb}WoO@Gi&Hlv0OMd>&W1BJxr*Y(Q$@j%(Wd+F8=u!J?l$!)q?6@0@w(@2^J4zA#5{H=DLGwR6=pqhM}cEjH}H zfy)vVPZ1y*p;dP$x0#xwr}Psz_4saHW6Hd!-FAC*(QEBP^beCL&5E(=e4;nJd~_VCqy`_rk+ zB^}qJGIK^wwJ5fL`j%dlBq54p2m3K^^+lxh&2+ik6-H$~WxPa}GU%m=RAUYaSb zRJnZSP*oo_p+nE~VDNhU)>#JkqzdJrsD}Bo`_?jUY+G=X>bY6!(H_;ryX)~pYsY=2 zZGwDn%3dvv6uvyI|F*2GwxsulDZ++@UK!&>y!kq8YR`%i?NvA9-F>p%>!2We5GRb{ z$&(lkj}t9EyLMro7Th!H?KKFve%*rWBnHJw2WgX#g3CR5IjPqg`k_)%LW)|nH??a{ z$+4Ac?KrO3L9z-qc3U@X>vk7q#584jQ%OkL^ifXWM=g z+Ma1-7*gx`mm0f|87;VJ=YaH|2M` zMN;x&3#d|eca$Q8L#3%aHFiLPPBdOLX7ad~j#=3*wQe?w z;ePkpdP5abb&r;@SaGZ|pDX>X_f%Jv=g0gD#(c^zq+RH}XRfjPsL>%uPDS)MXf=e# zORIM|@Tp$fIAcP|T_KM&{;F%tMn*m|SwU;b4-bu4*3@mwiW45+PGqeJQdv%A>+ z=PHABZKGql>+hQrf0B&_k_OBb@ zGPl^irYBz(snv)AhnrAywBk)ax^-$ATkD?AuE0# zM@Qg*C#L}Ag*l97H?M$Rlaara4Lkq@mf~d}L4v`hqCNhlGVU8^zEY9;Rw$*@Ua>Gg{xPN4RlSK_ z%j^&D@9V-HSLsko&<`si^;h&}xaIn1ac^I6*kie@A3jlrco%4X8iq!EOd+k#$z=I9 z=YHs@(oG!|D7Dn~*AGs2Iv+%k%W=FOP`nVY(w=&=RVDO%v+QCJ_4~j4NVxPaEWuh!SJ({dt8z-u5S~ zGDc%h>2EX;&X<1hqR*(PY>5h6PGlD`nT&nzBuI6vs*j;+Hjg_M`G|7wi9-<@%y|-u z?04(^J6lL6{6CzjmhLmxb1J|Z!?Rk2JleR96rT9tu08eEO`lVt-%Fd?kBku)baz!+$et27kuRpv@L(#;&ALD0 z{OdO@iv7f}KKd7vm>q`QS2G^9C8SX-FBngMba(f4vvz%@UMBBcwT+ANSjNpkqwB+E za`Tm8g8PtK>ZuQSOikx_x9V<}X*}m&h!j=digQc&G})pPZ(?K-zHRCnl;^gm%+hM5 zeO>5aP+4}N&0Nvc$zrZml{;t?-4|K7T3eU0tZ9S(mQyyW@P;`y-*ej9L7gABkZjeq z(Zwz+$#1=GnrfRc*zNz;%q-u~y(1}gE8(;&ObW~nf<~-^Y6togx_fHgP+mDRAloFz zNl>L4Q0d&AaeHKf5Stpi7Z>qp(t3AnjB#A!;PE_B_II6gMwbT+ri(?gOjx+_RU--< zEma{=ocmuuVj~SBt!^&O=#I=zgoK~VqI{O7bxun(z`#rJt@63y!Ri5$3fsZQtn%W{ z#kxZ<=6n2>!xzHOJKTHms@#3B53I$eVPQMvYslP*cq_-020p^Q>@`+X=<^}son!A^ z4~vAi(h~e;K?jv_F;lxm_glT-<$b~TEJP~Gr=-x8%5+Sg;qt8Ge!4OKhwm#}j~Tr> zmKw(^W$6c0MrK=+&g|M7xtFJGw^YgQ z3O^M?Y2Ne;LBgZmGCOhfFTC^@$5;Aer$|QKYez0sjzVgOWe+`gS=WEN*rTSuO~b&J zx42#anaJ*dn@LvazjZ6L_`@3vOD7kp8KNRsl6AR~w)1_+4kD&6^rZh`YnvfADNMk# zXF{L)M6)PvPJborEOwvbqM`X9l>Skc(%!OvJF0Y+K%6EM;1<1vaVbx%#=Jdv+G zAIvBGH1DdlK|(EoSK+=^e~JN1(ptU*&D~B;fwylZ!ge?p9*X$%gu!TcyMIU7EwOV1 z_ooHL%^ElPhjVh0s!rYgII|8KvpsB7XEIiP#XUn?wpX=B$ZH*R>S~c< z@duz|dzj68K}GxM1SwaC%#+6A`fVSiMZsM&nvQT+PcK>+Nm?3;dpM2p?#A`@4HRBW zlV$1YZJ%>G+eE7w{?sMY*Tr50&S3^wzYO=Av*&N`))zO7Z;K*-sp6> z*7{CZb`L(jvGlI*4c%+X=O=fp#+FM2r#X31jte;#y0bD9X~tgNT^>AJI^=e(%t4-8 zdM!wD>7&B{&qLy_u+09f^SLu==W?8i3KB?I?w6I&$Ge)gKY2pb8#w>gMPi`(=`BUU zMwl`9u%e>E%(0n{3MI&*smiUIlE`=EmLf0mz$Ym{Q=&s#aI>~H&sUUEFBu?ZyGpzc z!gj>!x3Gn^%khS;gE%jL(Cm^SRoXR%4>YW@4apr1do-?eepz|7w^M&qviyphjCC0Z7A zOs?~C(3n@o@?8Ij3;pm|_7mQ=#wTu%nfYae_bKj|LNiOPoGwLkZOrGy#UJu4=hUmT zywnLxd{d$2z4Y$UqR;*hhs)9=X&_;j_gZn8Ywa|D_x%2Y$x6vNVkl*x;D{yb0nUZK z3=t-MrWfHQMd%#IfW#0d@7MkI#{OEGR|Z4ElO+-}OLnPpeNxz6fT`)V-Wk(bESP^? z$WXgjP}|WlJnP;5$xDY76qXeS!6O`T+OKyw_}{xkrbE4+efo=O#4w>Cq z*bc5gBd_Jn0-IWyIk4^7r-p9#*}59Hs>$~)NC`n%H&syNgeMi^<6OekHqQKnWLg_l zpHxAMD+>>)po8OHM!OFyk`7>mkpo%C#rJ`>94p$%BkZxqsJwj78Sg$!@=4^hwGDsI zZ5T1>ReQ?uva7u{)uqZR!T9G{0;!5ldXE07@+R%=M0VaLzQZA}^7modV;OQ-t1Ve$ z2Z=hth9@FzbGXaeet5g8#Z)vsm6}6A!WN2{mrQtp1_#yPB66k zetJJsRntY%%;Fks?Gunp+Co7OH?1?@&f;yQy66{~=f$8+RXM=AidO3Di$mK8Q`Vc- z9+F}A(QWNee;o?yMZSzpxFYu80FR1xOXYbE+Wn!D<5yAxPRw~SUbwlsTXZ6=+flOYrs2g$%XQ4S#LIr z6oJXgXXu)G2bzwM2_oZs@$$u|CiPpd=jGnI+|_GhcCx?*bn1rn4naj{1Vqo#xN>0S zRhds%)m!_09OOgBl)2^?T z;V7BjC2<)ym6&WiGH&bL=PPQeL0DC0f12LNW2RJ%kECjmo2lZ%o?9EPuIsZjS7Yfh zE7!nin%1Ri_c?>lhlfe|eRQjP=wEB>bG6sfHjz#RekOqSi5g0|Ko`oc^6|uT*}9lu zbksBBwLF8~v8{Hu@-HU@SVyMXtlG&{I^=;ElXtEz7QlyQT}qsb+)t?}r?FSCHt3@H zt({F?-s7KeU^C&mE%++QxfL{jDmqch^T?4LJHvB>qmU_%diO}5h23v+i1)nQ+ z>>@qD)$A*JSeTz1%TZ|_d~s)>LdWGt4n3cC&D(e+S0a3-mQ6k>y1A9;N3o8~iU!B& zB!ARQHbA!owK;~JZYlrh+GSK-O5J~We9?31@!+)YwRevc6k4yK{N9vq;S{sL(De0i zobbHt`cyEsZSs2J>Wfd8i(G@_EGhOP?d+S(_JzEBc;2LC=M?*H?^_p_w!lpc*xut! zPWCb6_X?r!9LV!|GV>;6HN#*AH>B)7_)H>*}b9Zjcv;_z> z!9ZEanZ+p(F3SdE(pDp%Hcn42Cx)r;+VM?%j<|i7E#CyEa`o=|wGR*Sv?RBs9eGFf zX0TdQEqec!;O^XLS6~(`x&9EeKEJIaB}n}_C(uIR^)<3*!d%E zpbe-<=q=#T%!We15C}`yoo2f$kd7$EtWRC~mGoNYu8E*%DXAr5bvsmGP$shqo zL%~!~br8&*@*;8Dt`&pb(Ql75l{d3y-A}u$A$`YusiAl`?5=9DgBY4}Pgj)qxmo?& zgv$HqEc#Ow+Y{RFym_|r^u*0Mw!BF2I4Tl6f?@z<;b8=W*8%(#LU{+pN4^$@v7@$9 zQcD6rB?T1}Mo9~t!N5_^>>ywiJvjmk`2h$DgyJDzF~GLMSb3g3Ro@O{$&nu|{A&Fbw5F%wJ!?q^!{7e9V{l0ysI+MMlbr zNJ4ERON)Rpp%{Q-{8lJ17!?sozQYF#K?R`>X8ULR#rl3plt>7`lJGzpPTpQ5ycY>6 zr=Wnv%E`+h$RiNoS?NO?u9JW|0?0gH4*IpT3nD6F%bGxl3efx3cFcnHdQYtKsh0(~B3A2T=e z`5?VS=GSy$77l~}%txo@*45lmVcV0X-VH&WAQPxa$S80)eO6*twGa9H zIsyE9hr`ZpUr+k9m4^4_u5V>SY5Z8FzSCm9jh+T*@z!s(*v#9Tg!o2pQ5cj0pr~@v za)92-puV~M6+=Y;is`F%QbYp>SU` z4A9KIC@a+VFV`qYEaHoDe9^}ZjUxiB@kP^qR*yG^o6P|tbN^7hxyFobf5Zs%5l0wI zLIPRx%>eVm@#7n70CfR`hM*uV-LTRAnz0*O2421IpL^`n9bBQtk2Phce;HqVYrlPH zYr~dpZ;_>Z^Mh^?Hi!@i3Mqd_AR*VGH8MZ&g#qzyuuWRBE)JCT3P0u-Cy?Kt$n5I9 z%UC&Jb)VzIHKg_7`xjgQGiKpOlFlKJ{74qw?szZ1h#aQ?tcML1FsM?EP|^TncI?U) zFcl;_lIlJXbQd6bptqptC}|vGb-{Qj3>Ziwj#JWY#-m{Z!?Gj7VWFr)5HNUiWEu#9 z(1KBD)Ru1^q5#1VB6o7rI~E+N#U8HZQi_(=6{TObUO525`#Z*lGd|hk4q@GGeuZ1p z9NFb0L(uf7tU@sfJ`00n zKyllF!+6sIhnQygtPk3r%A!{tG>Tmu^bv~sPIt|ILU*NrzO!M0g}>EZ4R0bIVL|Z3 zBh5)zPam?~`_=@b6ahJ9WEC&~;bDsm8n{$Mp@B;UTa?9*^Zd>Pqfk;Cd9sLp$@5Eg zh~KhP^C!7_6A7dsgauG5|Jl~=Lu9<_acQjWNPoFkMcTA3p>9=%f92{u>L9JI{STt2 zODAQ{y_KZGxv03XWS-f{d~p~3`-(!;B2uL1Q|9RC2|!^%sEAL0Ftz{5lCpP>9C9hV zZasA9b`Guide_S8`+@H)=_AY2i4LTl(8q4onw0p{*!Jmn$-mH&IssLOB>7=~%93s+ z4<*9n=>a{tqijwgsK4zrPyz_$449TjPVRC!NEgbGyKoLC6Y${}%~jmex03xT zQzZMHDf$&U^B-(c-r<$So756~S~kKHX77s;<7*>Q$F%r|jA{EHKz+wtB(~dl-N_V^ zCJF@ALQ?E&3)*$g7dFfKv4q++3v14z1(Id^uWeo9tS^HC?C24WH0a8=2@n*Aoz^=(hK3d+3jvK z3m)eWQtS=l_M9BATTIw3%3^e_j?-+HAQBx34hGDB05E!^2&iAsmmn-Z8uY(4UD**A zfH#~kMvexsY~NWj6!+JA6lg~B8`QUUXUEsOFth*+5sMzl6x%-;;P?tT-#B-Lv{ZLm zf_{xBISrwIdf~-(3Y7desY7<4#ZV$BAr$c7s~}NMy$}`4OE1_n@7>Lz8)@0i9$y1N za865-#H4xdcqiV_bL5-pun&4T{)q(dW6fkj$g!ThL-KdE99CeiHPuQ)^S4Sud%f@S}v4*(`!VK@{ z5X+3yP7AE}d8Lwaq#dn%IPU9sh=_OcIC)hWfQ5tSdle20U+7XgE^ z&4&LLBu|zK2>Q0(p?V;cHiREkeC_d~m|FY=9D7<~gHto?Tu{cAy*pRo-4@L9udm3e zlcPB6UgCctRZ%vfOtd+iuu@EW%vnaBViE&C6jyXh<7{>$Bn}wMqk$tFIH)$qbWrZ} zTYc>HvL}{ZjagkW3}uqDY~M)m%bWy2pGL`{F)|pG%!ZQyC5^&tTuR&i_bvTD%trF5 zKOLrE;Npdehk)L{)(wv|JF`gF@w|qGO8qt0sQ(46I(Dyf+|1k4Fk77cV)jocBM(jK zD8)Qz+-Z1A=Mpw0FX90zqW$~H2vs=XXdv6|??z^t|M;#?!?y2?_kGs}^Fz3rb`y>zTiy?aUR>UPQ`Uj@It3~#b^48>I94qs4p^108jKIczgLNV1OAu z;AT@)`t6M9M8pIB7MwlS&ks)|kz+;XI{6bl0ww(L9?pW~@;R%J-#4Yc#@KKXNnxEf zq60<4xnliX_ab_P2)6#i)F1U4%(xdhU*>97UAR9IPueNVf+?cYAvphJy5z*99K8ea zew*no*VfTC6AN0JP#C8~Ur< zB5@{0I<7c9T}`viq6N;3u#`ERHKO&&7+{-86Wl5#NTI9)Yp=Ke5E*_DX-Dq&svA94 zbu*0!9NAKBJgx@%H&(-qlFhw>T7s+aw~vR%wuDO+Z+qs zadtXKgPjtdt1o_|twZC}M z1EhddoTR*oE<3#N2mPG9fs}V_#`oKZPXglaAQ79gvDWGuvn}k5{-3oM#?%nVUQS{3?6`tWE~Y1WSteAF-}0?SzI-C4 z`2{j+0_N9ufJ5ucbTF31tjJ|Vy3U8_*3Z!M_;U4J&$m;AU*QPez>HAxGQf-wqaZ_e zSdrg&$hZ-32{^3&E6hk9jgkFlFr)Ph>ct5$nQfBQ*I^Q-^sTg_5_iso`H$opvu^`U zIx#iM&V+VdFcrSNz~1@x%q9Dp+|;;!rm!@+d!{Lx{+ zO_%tT1!blzz^*T0M?VM76OMuHva}<_5(E5g?^N-?Qj11UUz}##Iol!-IM0X?ar_rF z`WG|;;MxCIL8CDMA$s_mS8M|`0x%e=mLGve$=^7`0MIB5b{G}%=a^9$TMq=L)%l>F zR?4xW3bIA?^z8>*h;Fx6b$GHnYGijoSVLj^GU%jI{Es77sBmQ!N?sphx_Z!!-@EfJO-gWpLh_)`Mauf4G|`Qt_o|=+iFnJId)NG! zE9|^WGjvl6E=Dg(ob}DP=&R!o|ErLZ+2bv0Y<4D`%iBqjheO{Btc`jld}m01=)V4S zhV)lKMynH=cWs3czP%Q(jOPigG%FXgy?oE!c=bxp`3$>??fi4c@(IeDeT3xR^szEJ zR!zVb^=%y+5oC=Uy6Jj|zRFG5;Zl!4h(uSwsn*@&D2gg{qVrQa|M&GhkdU=S=!78- zKx_YnjQ)j;{v+||FAx@fsB{09LPkFt^nV>>bUHuyV!m{L#f`~k+S(_k8ST6pS-3~< zS12O6hPSdNjQmH)$Rj(eSy>{VOHocNG=@LGaBh9i{Z8k4M6O#Qw>O7)@;8QR6Ed>4 zW`s?j4#i}-T!?*ZeWI;m@)<0FOIUG&_Y$MU*w$tULQuQ&0Ak8S5>h%(55nY`yH%EXs26y9vtw7GktPj6{PX_IK`*K2-_BL}faaG)=cm z$I!-h1`oEg0mtI1^pLHUc`c@%-qRo5OouUt>e{2CEb$Ukka)*ago8h<7AxDY^U^GSVUY{QiN@SI~&=1N!Q&qgnY* z_qX4kyUoPHLoub`T+*V@dxlT`)=62%vxN89YLdTa#B{npFZ9^T?L9EYiO}HQJQ`_k zs(gqt@bg40n_jq|1dX2j5j4U$Im#(G;!#LN6wVQe!=V(B(vEm(q%2xq0qZF3=qQVE z{0BiJl$<QBeLnjEXcYAs+(G^xfBA}{d`+~}*LcQakfiV z$q@4l@wjAjOnuRQB+)qIC)53k>ujd`5H@J2da=mvE*#{>;?kvFO(P}B%ez8Zb&mtx zVm4{_*YPNN_;-G6=|9J##=d*tC-A7UpTeW!x`Xa~5I@9DoV_bj!mR5Bzo4%>PI32R zkldrFMtP4T-#Frb5|29lFBJ7J6!m{R6!i~6re9I5^#g5B6cniRnsFKru%lT)4lxq> zu_w%T6z`=oAxaGfe4|X?p;{2(KUeOrgB@Vqz)RnuTG6?isFwQ%s^#qi5CU*+K3F1v zL6ZO~K#u#@QP?ly7Y^KC(6!HU0K+~&H24l&6IR3F@Hhm)(+3Y=X8_>l2&^J95Aq_p z>S-bl0=xvGCzj~`>kzg-6Y$_?`2v6uoh;e^B$2{j#QcEeDL&qQK#hE9EU(WHq_-Eq z*7#jL`D%O#MUcD^Qa)ZTAP~i)%}%l%_>UvE{~s9%Uz-^)wm?6jC?UtY;6cQDU^loM zt^^-fpkDyi*x1<@Ak-6Z8{q&0&fkONm*Yk5WdV3YtQWxNd7eBQL?iPrs|KY2 zq7ngz2Z)yhKzD7lo;)65J;HxC_vF~0#Nk<#LJ*M5z)-|9o~m3IrQUf*}Z&sqPoL)NAw=XrA6m)N?3 zh9NuK`QLl2v#(yJbUbt_RU?5yZ_V`jOArWQusOQ_3GqYD8I8fpDJUX=g^12btfD;d z4(JG60+bJcPN<-Ocf^wiewL`s@WCc&)Vs@>0eaz_;YX2uY;@pZ(l2nmB(V_ zkn-}fvPi&jB8^m(!vPK&X_O*HV6$N$5ukH4~1IOTiRM??fH40ZU= zX&=|>-`TDp%`Y*;q&^Y$=2*hmXlH zQSlB-;zu@ssk8ydm$kwkA}?QbWsW`%@aflhI&5O3 zlxg?vxbn-1ABq6H^&Rm;@z)SPr2hx3C4mk%&5kl-0jV{ID7x3#3(dl1#nP zwpzrkte?=z#`&Ek{UHeb>n!O%PW;%!XC8Duo!I+UD&9@fmZc&miNQ6V+fe8FK85lE z5<_gn!8bRe#>~UZ347HelCl|iaq|$AQR-^yAb+EvYUxdEfiYryPvbtJA*rwjCv^K> zA7{@p(Kr(L{J7NZXT(`9g>??WpMf=aiorIZA;_6dtUcXWTLLdE4X%1b^k}+M-X+ysESPbqRjLj zsezIk-2t9q&8+Ozxn<|~aHM%mdwyf5HhCYOG1HgTjvbr5Z&;v{=HE}9HI!tQdMkN- zR8nHkv)n#42qFNic_2`5;#g3V^^B|i;|vRE&_cI^$0M3^a%^+AKVbhZ@8h3cDvUYcD;){~)diunfOWtZhODka`Db%&A)y>P;N(vr zIJd>t#4}74G>w_JKYbd2AXq*2vrKSg5iYhnG*Bk;DE8WFnH$NDKa?IZk($K62>DOE zk4o?X>%x%uv<9dS$))W42xj5=Hv;@J7r|HF$L7+IFT4+6X~?hSeb_OMpaLhTUhTAq zTQkLXkLvfaNlJm0Q_h;V;VhqmD^_J9-WAMAxf%pSxNCCB1i~LwUI^kMO|=?MoD{k1 zeDR;)eK2xPR&RgkayYMZ%T}SL7mHEiXHR`MKlxwfeV{0m`Bl@$E|FHRfobh~8U4>k z-8kvdb2d@I+Eag&O`M)A+VP z{Y&$G@X)Fr^J{P&ky*MA=dEmCU2T2yq}JYWpY7bQSt`6b{Mh`}wgW!2s!u=AM#T8J z*ick#yLpK+&)Vx)vHz9J_DzSpSLK7*Kkd9lyL~)i-;*w_u!ywP#zpZi!=t(2A%OM4 zyy=4bN!G^{*#r0eQemtj2KfCkyc`l(^n^z$;(-+<&S*z8;PI0|$;#r0IUJd+kUpv7X7S<+^^gXNsBD;f&94!16H|uEp8#%{%(f>56~jQvTuU<_!-u0Ec0} zBnwVetv-4^BS`s*=asBIyWo@1-Ice9=TAJ(kmm1CB>r{M2d&FykNDX|$e_&cytqGv z{C*RgOnUOzfcxC=fleO&8w1I~XttN#LU{`-0UcYyQX&-ZTw&VN74Kf!vj-x#Ege)p9d z@$-599&rAS0P;t;muxKl0`UF!<@h@C|1S#h6?5JcLhzgF`5ycI9hKyNqiy~o6#w_z z=4-Y54vHuLM&u?}R}=3+!U9yWfUiMnUw$tJ;7tVn`U>*-%1-($%pYw-`0wQZoiX`S zD#6cG;pPOX+vCaXeVEVl#>nTw-l`baqqZ-m+2Sl()+0ufEi+Ndf0at`Gg<%67;Q>| z6x`{=bAGwl!eim3BYx!e=mh(YN=S2$wgtPWK@4LQu+wfd2nvBv|MZ8J9FvBIhMIcI z7Fy~pz&SM-*zT8-f|8b!k`@Tt^4C8bTlK<#U5vlms+WhnGc%Y1`10tGhMWuRrC0se39sLM=A#ZS$GChyjZrC}44PPr^(W^Uo@M~X;2QFW=i zM_Ap`kr;V0r+0GeHW3+FjE1HYE;p~bkzLC_D*9A?!{ZB63v&4UzD3cP8XzBTFd)JA z`}%@m6u?%#ROB6l&EUX}!GI7jdTLr=$6&Isz$F|;!Ox6VV=={cQwm6{oB2khq~=sz zVr7#tcO=&LY!wue)$ofvk-H#_(X?>7+|WBoWl4$>k<(hleZTAPCsXwbIJJ7ZwU|Bx zYe5|zgDOD?NW?)Ba#T?{w7C$80ys#$1Pg{>sa2UEeGNq>EN=XoVtWLzpoTb8YKuMM z(G(5glF{lXs7vB#b3qkMED}YQs;CkHhzJ{)DcV{rLp{Yp6AWj9QRhNV?#Ttkl|Tdp zz$Z0T;cTj!U#>xMaS#E71n>>h1PPEuFa@J3Sj3`5SO6hJ*wmSrqQP*G_(@GDO*B6$ zhFvuQAt4@P63xF~gtdY7nr1scC6fTZI#xAKJ-Q(-{F*s!0aFf~iBY+n*69}$!OI*;-}21Dd9}~1~DK_RaQ${NRFmDy#SU8wnqRW0TBQ( z2_UFVnP8f#S|)(tIjR=swAs`#K!AF*raDYZI=uKKb+`at6Dkoyi=c^7kE3Lg$c0S9 zHNpFH5!7)pG%*&caIhv+EP@FRRIUU$FkAqp3THyl0_V9!K&6G30GT9Y3jp77;aH%a zG^s(FK!r(113A$nw3z5i;!Nms1;|w-e#!)9Y5^rjWHZTT-vd08iv?Q%6#>Y|LJgEc z6J{x$p(?#mofL3Qag%IQPIC!ZK~Sc3p4w`QYm;|ZDg#&@=8J5(la8^K7(k(%nWWj-AVu3SOFcVA_m0KK*Xa{<< z2pkOGF96C0bSnesoCT&#Ij90S*qjz92yHHtKyAo3JEYxR$*dVZe7gFD?}DGM&ukylVS|+&dk37#VFS(q zcikI>Uf*~pr;v_I84oHKeT7g|F1ZbsdUMr0^r|RJ<$a!4mDS2CD@fmv!q~I10cr1* zosrT0Nim_XeGal|1n0ZgjMdTkXgP`oPh}*f)V5xr0_kMW^yL6sk510>N#x&qePj$Y z-TY|lW7L(V3SNj-{qSltD3vc4Q}^~K_W8^T5% zr={-QP@{XCRPH0)ofIx(>Q~i&so}L-)ezNK zW9MXgm=6pHvpDNT!M5Uk9FE>Pns-CyhUZ&8ikGWnD=Kdvapvv1oWIBxKdx2Kbl>Hq zc}C^svQ*7wn~X~bJ@1WiEkjzaQ?%0iJPoZVuXWinXG9e*G{JaDzv-3VI;h5D_+=8| zL*B#bV1p=6n_>2c?n?3oZ1J33oDZQ+8J9d<323i7k5n6X20y)ie=OAP_(*DU3W(Ie z)A>5MdiYa{-uCT&$|XxrW*B`yr(^5nG>KI6%_>HU;O!xN$9O6jS|0-Y?dcL%lV>hs zv-U;0Zwb*H@X&9sIM$x%fpLjB=Hqa(Cbf<2%*WAzHrAv!8WG4-In%ZMLwVJm%Z9mE zo=m2Ul?s-OyDJYItg5-_@tm(FIdJqLdSY-TiG!X(Q~Q3Lu!mKjU}%8KvDV~4%+N;# zQM%W=)Ax@L)E;R{?v}kywCrJ@4ZvIsL0}}WVOCyJ-#f4~-`Cp@n%t7%=sLV7wZb}U zZ6>y`q56D<>zV$H^O`i})I)Ot94x-K0uQkE&~UK7c@nFNX7|0Hj+8B&r;)_%Cn&)9 zD%D#m?%XWGJ@(}9xO#P*lUeR&!yV3tQD^Ju)S~j}A22YwHfmP2g%6}fMBbYDRLjUW zOi0y<#N-^g*#Tvl$rgpyQ-?NCiQ%A45zAKLkB+`^8B4BvDt~0T_Q8DdTc^yPVAI86 zZS^uyf4`-R2lHK-kJ*Jb+)3^^&8ujw^&n(;9fas&cv@ROW^caBM{)k#&EPVh70gZx zz5KZ-y_+&wg>I>slv~!PgD@-DhsPJ6~jWr3pXGxIE;p=9kIY{dm7B^!bTyPpdwszerDjDT974@yzN8)ng_@YokfV8ygTpMBLNDLhWnAuB zcQf97<$0_%I(A#L|-8=9Dkxdh$286@R>8zM2AVo0(N6p9+9|}!P z3UjfzExK{hA}0K_)3i)QB}{SZMd9fdB4n##O%n}dLdzsj1XyecFw~PR4q!w}06QcC z7!@o8QhXAaGgyG(fW3u-EP=6{MGOLr*Xf!KpaiT1!ajrd1${dA?q!T|n^x#q=G!}N z4xa@v@U}r$3CFzO(X#RSH_La@`MS`}Ke#9E&gqqbNu|n&FHti#rRp-!$gK+tU9b*X z(Z;-2h)R%^VkvoTJJ>W&aZ|(jhMM14;!Il+s`I>tGw~%)$$O1g7m?Nb%Dm>4v`-g| z5nA@UbNV#=EJRnfR*OJ0B(r*^ds1 zx?P#jswg}#ZIr~#J;c<|b=Q4PuC%Fs;_gJxbW9>|OHIV>Am`n6{tr4su6ZsEJ>T0u z%{mNjjB$3{=goH$T~oR9Wq8%LGzO}(=KdTjuPoV@mdZWCp4Bo8+vdHym|VQ@i9nr@ z_qg|9r8oTUn`zEdNwuJKL9bSZ@H6S1mb89{IPL~BzaD7haV)&$ck{z@4>^A3nzyfq z9ER<$lTLC8YT_V5l{#^DgD*|roV{1AS6yqLQJry%o~5tniv9MzODWt9fu9V$15^x( zcaQq^22a^uKkw<*x(+gZZ-sfyVjBkaeN%nU?-TudqqE8#@8sHShmvjOGDp)cGh!aC zT|g;e&qWt8_M98>udY>avf{jcrO%VNe8Zvro}u8~2R?^f{y&z^GODfSYx}rsDHJa* zMT$F=;%-HQ6@rD}f#5Ar91^U!LveQrP$=&1?oyoMZSN=jzwfuKS!ZRPoXpvKu4{gK zwuodie;ev^jF~*`?St*Gap}_huU26Y9eu{n+UD7MX#J}p(GbX`d*_l;JDty2pN=*v z`T&8j*BaZaIx^3Mz7~s`PzXUb3!Ji`f)f1A#n=Y=rwUR#b_VflvBr(K8)_FIvR~}E z3lRFA|Ea4fSS}59$YNZy)jzm30}SIkk;uvPuwTS@Wf(&Jp_y`zhqd$Sg(h>a*;e;m zWA>QGR_7qz^nC!bSMq)5Y=(9TV%e=R5VqR&{=~8Xun?JOE^%yffw48|b5cC+QAIcYy<> z-$RKOWsX_Ry){0?=_+O!&%x{OQZgMBZGehc8tb82eTPgOCU0H9J zJv7nZL*5QH-<2>nc)a?U2IMB~F?cvK8>&CXKC?+t`n$*?Px@y-qEaHIiSh5liZJD* zCG>Gm0Jz+iV1J7F^m+Wv>8I4vdNXgAeD`|$USP!#U9R1X(Ow{h<$eVDxKMIYu3Ftj zFHJuawqX!QL)JzJws-68v+474MXvu|I2P3l9BSqU;HuACN1LY|jhG z@6Uf_TTUeoCzDew4(#nlsp*rg_aCw`&kU|qKKk?}pU5sopC*@7u=*yNnDx%X0-T|= zi>N{CIle#DBg6*&76oWLo#q+`|3DZ&dXL&}=YaQM-)u|ReFjU*c|YxjJ!YSeJ-Gdc zvOM=63M=`sfPbwNAF7OIMHa!YDpU4TyRE+gZ&~jxn;uS$wqpob1bkezDWT}iY9quh zvh3L4a5rsBRrzT9Z+Dr;BjxYzJ`;Zm6poT&UC!OKKu`;p3arF1u0UvT!NnD@IdT_~}Kbp9Hbm>7>lXU}3O^YHN=>B${C zX?H(709s6|*!^u&SROXbKGECXAxmgeMnT4eKxA;1fx$?I;(MzNeS~Efw!HDV?B>nkX}uci~8L~ zC*RpGC;kq+y}sIP&$cegG}!Fb=3i)$w&HHy7#LpDc<3ECVa-F>o#jsq_`L#h(IbR! zkgp7{uz$NtlajYV{Q<6mEVlU6D-o_ab4D9O#)LRGh<5|Co!Ov*vHyQ4&d9#0$R66< zGoB;&W{=MAg%X#d#WJRGdBMy;*5qrI`*(k6hWp{e`xaK^SN>_iH z0_ljI1Ici$q%WL1)hD6$gjO1zhlg}Dkm>q=!v0Oc zKWT^5>d4GYit^)4Bo0zmB25Ffm-=O2F>wkoIDVAdlDs6>|B;VMN{Xt+QBK0d5mbt_ z5WbE?;zfOxCD$b(e`$cqhx{mKFk-8Ksi2YfZ_!b#KZ2GR&4f~|j~r6KR75U4kRtm7 zQd6Vl%a)@c{RO5+VL|{$kianQ$1HT_m2T})7iLzM<{<`>_t>S(rSGgz+tn(p?$EY< zT;s}C6UPiH`=!1f2%iavMo4sQVN({N???%KX}s-`g`ArMqaVGM{!a1~>21Y%LwO9t z2fe@3+<8}iT3j*y}zH4YJTQ=pGe)&Qfsk?t+1%|=yTL!f2p^Sl45)@u$G4#2%?ns47uOV^g5|POi zQSEQ5wiCXME4BEN8#w-BJ2Ll>V8)5{MBHIA=?`VWQEa}?rz*LXr<->V#Go$XuHE5mWY0-Nmp z>?k-p)wTR^Ug09BEjYldj(%F-yuB&W;p*g?COU`!uPvndjhqtrn5lxZd2`u>(n=@_ zXMP=+fX869BLW!zZ5S$@t9BB{Y$Y=axRKBVhV9{j@ zdt-(m&CAAdnXLVAL19O)t*-+rtYKG5gA|FVJnR_3C;06l&DRvgZ7=FZ20zS*%NH5d zyBN(nymuaubL!Q@IVIy{)3dX&ma}0=O}vm~7dNjI1}i$rVfMR=;v2M)hU`1=$X&q5 z(|{R*cP7kcYjGA5yt@4kL?fx#np<6}4l9u76>7s=E&1HgDm|QUJy&$Ql=P^#_V|c> zjpF?wT6@yVPH=(*zSmY0`d=XtCb&a(9Kj&7*=(GWvf`YWQN!N|IbC5MX3Yvd@fSU6 z9UhH;@012;H+SMYu{-dcC-wId0R2-=9{6(pS@%cn>RI>V7m&siA>2;sTAs!8;{}-ZJ)ye;#+MMcHg1j~->K8%JU>rq zX8ME+=XXa&(tRB@vo6hSX0t~tPK4aS&5rLSt*i(!>u{OfVBdrb3A!1pZZVf@L-YH# zn|N_cgsrq3lZ#3h1{UTMadM4CxV<$=#Ebcs?pi*shHn8WaeK|E^kVI(4ZyRJ9YfX? z7+$*qVkn0x3JZ;`;X&rH@z`Y^>nFtu6m5%Q4Z)lnKp;Y|X=vr_3_eF{473apZK|(3 zBkEyxL)pp&Jd3%8ap{M}8`KaQQ)S05M#cAy_qDA8VO2nHu~b^rMAcsv{Zb}|Fz*$F zHFZV~!yESk*~V!S@-OGuM*&}ehZ;vI`sqx_ur1H4=}EGxP0WLLWjI(X5gK(#ckbldDD!Tud3D$ zGf>na6^OP))knsXf8GxVUct+eJU0CiWN7=}2-4^+P1neyLOPH7$dU5@g*`m3WDG^2{^>NsJ|eS{y*G-?jRw1gxvlwvK^^mXcu#SMm<0s{^Cy~^tIr;8N?SC-c?p0;g&an|M9YRG6dvV;$)EEwH; z>)nX$7TX@njptlJzuy)0eBLOe^*%F0?0NO4Q*A^W-1Q3Xr&lujuhG!DNSYt9_lsMO z=1?{9Q16ENgmaB2qJIQXXL9MJ2rSBgcuYE0W|YZR%zBCa9%YgFY*jgMdx9-BtVuI4 zRcKvnUei=hq6y#6nbTGHqK?2R=iB%f-f)Ngn62k-$~#HPpaGv+FZwCELg7pRedcHF ze4xhX@4}9oaInXG19=L-hAE9OxT-;I`P1SGF#(v*zht|oYkmy=$)ezlKGe^N44l#H zM4|6>_O${pp;?_c@%T$Xe())QjaTm;>pD%N%Z=6){a;5jPC8_&OLvjBNXftOQj$^E zJ#M*q2-zPeN@VIhm!pxy{$y(|Y_~~ha7%eIPDPm@~s@BUC8^@Ro8%s=80c=gL zA@Zf-tcRPJ&dd{4E7S`F{B{*m&EP7xuNwOTD(U|uEC<@D*VT4Gu}O$fZhkyJyBwz| zIureRdAi|}+$Z7ntn(pq+-4zCYxy;;CgvpLxdYLcC-Lq%2`to3 z&|7gIK%YzbXyCkxjn_h#32O_BX-5X{X$u6LZUfl`18JgMYpw^I@U!V#*F7>lD*~j3 z4!_evVsvCGr@DOXYdCCNynP15ycL6c`oFLs2)BNX+^p_ObLrWtC+Me!*%Jju&nQ@> zm`;z3-0V^G107g?9J*4e`A`47ir6qgLnGs9InuV#dNK*kAiHZLa0LFRS!ZJnz@ zU-=WAd6($s{7Ck^sSqDdk_!sUP9$hOf2rThhc#p6v2<#tS}YjUK})NbGHKxf{;T8> z?Q~m`EF_(WX|!4(9fTX7ilcsmjgr>X4aVEAe647*?k<8~Vjsvue$)KucxNX;9av4i zBkCA7|FOx?=;W-(LS@ucICUlEsA#XUw-}gaW;V6Z^o5x!ePU%28dFg(BBT1cXw%7k zVCKH_yo>`(IS_IvKEYT8e$Nt*rT=k|2iQ#1X{lD$CwTeC&Y^x#&y>ZH^?sSWL}`)( zj*1e8;7uqNk@Vr;>%w*A^EwXwKKZzGeftU&&Q%6zrFTE`e-W21tn@{zL>C01dU zf!?1nc8u_->X;oL1W`uBK|ZS#F{mDD7IZ0`^){Pb$e9_%fSy`W*s|aK2znt z>8~chH%xc0N~^2H4Mgy%9UI>*uh6VtNSc{OcuCVlvTd8YM$$pF=BjiSs+G%T+e$tp z9+63~4N8meMhGa}b>{V%iAcAd2qyGh*5I4~HFg5+CW2hvS$-$@duhVs{H0iS!N}ET zyasJM!gB{T!WGDO(AtFKcZhN0YJR=M>G;I0gI}vHte)Xj#ybaBF=i325nGI0^w0Q2 z{ z%I%lZR2nyp{ZvsZ|0y|TKK)lw^$GzoZ}S4BHH3Ch&34tr&kScr!>ZYgGtM$I zuU1wYBEk$RjQAf9`yVA+P!7bkCHq9Dx zs`QuLTWk3vchZiBj-A$h-d;S+@8N%A2;2JUs7yX|PqAWXk<)Wu7bXi2>FRARQ8QID6$!g~~# zA6w1hDOSxhp7sJ~z{Jl*wSZqLnzSCiMQ4;O1ojXQ!mM0Ui0thA1KjUP*!LDD z8qxR+Q5zMAFpF&m*%Yt!$y4FL&ZBmuuMrLq)9~F6_j^$3_N)+iC4i?*q!X-NC5NpB z#2%GRRAqsfFlVexMbZ8i+8!qqn^3mcA4m{~Luc+@|O3r}q8n*455zPZJXACTJ}8_}a(BT{K+W zE{Ei!PCI3f_ z>KRwLqZzBb@eH$&Rh=W2dAvmmO)|G~sX$AT^4b8#r8<`l+ysBOPqF$uOVwd^0O0fK zdzE11uk6ppkV@r0ar4EiaWlE9)1povjZ&y}CyoX8$;`z-YwF>flGRiDDTVAjQVH!| z#cNe%G%s|{S)F0=U>TjOm)bx}29n1yZqP>0!9HqY0BCac$&=c^#B<5X9jk_WYH`+a zm94@bHks0wY8xEqY|L=JmvGSh`?~{Z#jHh)xY6^hsr2~iR?Ks>-HSL-{pYgCiOFoR zzfB$fI)OlA_Z@`{Qqzes-2S+-n4x`r@w4@F6jjm5!mlTIo2Bk74PAyr1J{^5W@MgC z{1PNDh3Q`TWiBC=9WFS_^w;Gpc27+;I%~pLN(&C-K;<^o_MFPM{bacygrf0ksd2!h z7PY$a> ztLNdV&}!^d>hSh86x{L}KcuxBxj!vBl1%fZ;6T4{StoWUU%@sU#LZfm z+aT6Htq0$(G!5Ew8Y%>EZKJLt`W;)tnwfYVE`UGd4{S^5@CMF__O+7rvH*4sKctj_ z#zE9GBC#1?+XH{oRn?J)Tfk#=M%JXacSID_Yu7xn2)-X+OL)n%atP6JZIVIrI`{92 z12qLG>ELJZ?D%n(6k8%9XDFYTlKgOw*v)8mk(aZw><+0#sD4v6wYq*2j^;g<5zw*A z$h^prqeVuEFUkrw9{1KxG&ZCiTk6-1scDIkeo@W4u%Ab_+q30I8)gpy?V>oFbh{-( zs{(ED!gYNt@wGv-i=J?!2JE+$A~kddajH#4_>)N+Cs3fLZ}>nai`NQ^dw^?vB0*1* z`nuZnB7&hb8O~nlao;FXq8#Sq_vdMPDdSJ)Yi+0Sz4~Ec@OV_n?~4G*u$CA1GF=u^ zpGUHO-C2Nc!k(aodDG6&G2zUH`2cu)?V^)#F0cbEPs_s6C<@|6p*@_cQ=?e#>~5Db z_%*I#zP*~kb*`K7t=1%SW3hJWT4`u{pBc2VsEiPEd+5dQaJS@h0=M7e8J89QB$+NO zHT8<|b{N$cQFTyTXlaMqI63uzPgNG=Y#@|_D&E#v@SD+`>8Ik7()AjmI08Rtdii?( z=MNdr#tVu@l9mKmbk`cP;35zN7*%7R^B;<&tMUA^)k$&I${Fu#3Lg)2uJMvhCyB6V zw~l7h+cHYpO?C(H#)7(_Z31k9l343=!{pl%FALrZJI?Z$-}2So+KHkAmKJmF1EZv_ zgcrbG*W%+7 zs~kZWQL0~ZEQ;^WV#M{{1=}@bj9(jn@T?#?L}mSS)Qm_PKLx+ydNYE#OexzqPq?54 zK$&hfWXmU<&{RPGE79h>d-*#%RPfk5kC9hj0ZHF*1Ti4@;4pB=a6>V5^<~l6bW!A@ zklK}v%&`b3x>WX`G{!*1BPYQy!m~ovm5aoSw$(@Hhz#N=Pm?tu!`nvXiw>2=1$Z=( ze`CNT_lU$IM*>O&NCE{3;$R|~D>jlaT|5mgq{!7*K;lI~nL1$~aFDxx`m%gT2BRG5 z7wYTh%l^9ngORU^BM4I;xxq+^!iYqebP939ba6zGfC-W&LbJllj7KRC*2kKQw>94R zv8L#vj-jCQ&Es($?@0xKueT=yT{Jy|nO7L=vuKvem5a+|T1BVu$d)DJ25M^J>jje( z;*ldc5odt9!N`o7@i#tpj}~%VsCuR~YmMVvB#vQ-VSQt@L_%_r9z}c;ucF90-t0Qh zK5bQhuK_@A?iEeqHV9(aM9x{a*IT}tSd$+J3WKI|*FY3By8&}=Ty%=uOwC8uSj|fb z`3J+Q_{vcV-UNlolE1M+SqXg;i5un?8H85O@ehk)Bmcn>gjDv`|DM!8Yk?`v02fJZ zg;n5L=^&qlfh-wEBo4WPtOBY4@|O!#>-@VeGF?_Kh|NHbqzw60I_1&%XjY^s9CA!Z zzDRXpku4 zEyoj9P4oiI%z{4-txbM%oH)?u&;6|T3a_)BuWjHgMMs|kuw%4~v^uUNrU#vcB-AkO<$~rsBT*^%8VTi@n7R$<6r_@>XV6a(i!1QdauoM0~!7E!E zp#!o3>n5ShW<~Su{`#ToMU;gXs^D;mm)Ic1d7p-i4ChzUDHjG+%v`GOV;MfXJ{43e zkE3Q=3YzYOZwIEd1lsNGx@Lr0Q-a!z>p3$HqmI3=#;vPaQ^aC>(zwZ*nYn!(h(Jf? zv8BZ3im>0^huS2Pk@i!+02vwuUFoJeiOx!3U0Q9S_!QCMWd;@sp&)>S%S{K`FD;y% zaji~u5wWC=4D-=@5dhRq*whl}@wneS)cmf4m-3-?b&(av&$^=2O-(&iiQ760`64{}wGwljW=9+f7AF6I3 zS0gX{MVG5Hj-3jrlsp?zn~*n&?S|ndDMRb#@vT`Z#}UT8s%ugLL5FJjo`n9B=GTt|&Plj=2j=BTGHicUL+|kMu^~wrAwg$!97{p>+VI!_S}Q^)QDGD~^ zWk1I5WXk;3Cz3S#S+-aUttsr#4RWCj&7~+8rta0wQ0gTwd1vF2KFQxqDlx_Xp3@O+MW_T*$y@e45APO@fMd5JXb3AH&83LcJYolquy)+lG&~>LsusE6# z#`E}bd~R-Q0!otHl*+#FT-K!aqS$JJ-hnvxi=NvWMP)99Z^*I@eR<8#3URkm~makYDnSB$03pe*|WgW4ww%yPXXX13^lldGhcbsB4Re*^SH48;&Gnqn7%oWY=+ zUVy+3wE&hXicJ=3(lN`H-^k5Gz>UMvoQZ=n**Z`A+{!Z<^{=1pb0Pe8XF+!QYlp%g!@1sk)ACr!xcvh9o2it9_``&Rh^EievjRXYXgk2s#4dk=R4t|VhBlq z&$%@;tBvj_AdoD-pEsR=sFSU#G$S@=>@uoff&krjl?volR!3vbMN^y75lxVWuVtjT z{~wAFR!O1Je7T&3)68{gg@hqrx_^B@`t0j3pch|Azrw!I)P?n29tt$2+lNb1<8#R~ z_u6EEg%0_J9=^BPID4i&8A`HGMV3@FjRI~goUfl23isTUJ=DHtejF|n=}7ExoFk0d zk(f3P8&9N=u^!YgK9Ig@Y!q`5zmg%`jS`BX)jJd6YR`%L7A*<()o->WUx=cs=urY| zCtv#tLolul1>)H^X++xkO9`4rLf@hljX$=+yQ(bTry1F}^hk6h&*tHGhk zd5TvVzkY=>`a(EUHCn?fP%zZA@QNZvUajR*Uo+Qgs(JYOPb1?ejnHN~Id?k~MStz@ z>-}W;q`30ME;9?Bp#rIR1&ne?bi6dEATP{$-z_U}zzsB4W!d;AxvYmLDho>m&h`r7 zFtoOVMZE@_VDK~K-8^IO*8y!V6Fkw87CJeXOxq4mG!f-&(ek|Gd!)%(icG%^2CuAz zY`q_(Q?b2KTf;AQ`z~0z>IHr8_-fSgt6wZhM9cR;PUvafy8UNQ^)KpmLA$a0o}Ya0 z8fF?L1XlwtR}(v%^}JNL71%{oV@HW_#Zqu=uA`X6+#>DiGp`v};fm0BFwZOLlCZ#i8gyXI$B4bLm zkesDng4H|W{d2HLDtcQtkmU_T@{|5r`{YXqbr`$SXe!r2z*vq-rcfnpMxZh9ETUE{ zelpah*n~tVCP*M3h(jDRzMo1}kIX<^fmK%c+NUqT1_8$({dh+>v&# zY+@%-{-z(z#($+MHy%+dgq^-_d$$`_*A&Fp)SUo(WJbmFi{{Pkrrnuo(q)|WqV`54 zViZ(G9`GOb`T(OGkZ2BR#K*1VE0EdmY4&!{BQIwe)9$t|b-Ge>k%PUq;NZQsGn7>R zHi(-C79M)n_N!2j`=-CCr9b`Papci$rAwNiOxqe!%XLlG1*P#kbmcZC9r|mDq}aFG zpM^Z9RWlMg^+DHI6y|~hTw*F$WH_1LQ12mmnnN#l^nTP8QqNBBY-&YQdR3ra5n=UR z2U=qalhdEu{EVx6#npQaiCX6qiHElthti%77cCl}$`sqbWKpizjmh=I|2BT^Tz(;W zSC=Kd5&o5N(<9i+1$YH4J-$D0f+hSq1~e|MsRQnfg0Gw43@^}QP*~7pWiWmJL$T?a z8jSKx*-XTmuOHs8v1_ofVDg6!QxQP`JImlvg1nU23uNX9lP;nVhkBj42>8W`JncpELO;J;x5bV@eY?hv(}ob# zn>DpacLutGh@u`dqHgN?=H#y!MeHPUd|PN-P!+0|C!_N~G3VCv)>97o3%3axkgtmf zk$R6m{oK#%-qv0)V9uWF_qF{~VU1CROg_QA^u?6t$SH~p#~C$Hr-2W4&EIT)!Rr6L zvlk$CiJx;=tsMM#SSepEpAT;Gyc_ihT|5EIveq62Rc|dicg#p;#HXeHP8nlBJMb?D5ux1N@mAH9x-{7wVtT(PgM3fd9g}YH(fs>y;E4;nT zwqLR>=^?A^r`d-0z=|Dq;=iys#ly~kLzv?j=xRC# zxA78movU9q)Ynt8Cs?v7tVMyuKH!a(tIEmwadye)mot`TCs;3L8F>ZUa&!-<{2S&D zKYMSyj_LH}!RLQp^yn3!oM(8TPfvBn-j)MSHV`uQ}u51VA$`j-5iRbH9pj{%VW9*vNDQn*G&M?n_av^ z#tts4tZeTwNb&U)mR^5U+IYOI>pzQ{0s6wKS$jgaUT8^Fomnb`_i2as=}r=SaZ1n_ z7^YeI?06?d(dv200FR94lLSN)N?nOmxts@A*++yL329P@8b$Y6Lz_D@VYZo)vc!q( zLpYy3{5)MPnv4M6ckIPKs zFs$uEv2L_6C+JssuZ+UaEPc-2=$H>F5Z$^Z#Gk(b%f9x#q}61M1_RJ_zD|ewg?mL zP&hqM+6^GG@6q8sb|y0r+%24k0D#uZFMC7z)rMIKYRG`;6F^l6hMssG!pDVvYm+{P zFK^#2hZmvy(lO>Dw(mIvr$1Fm76dFN+&D;Ss_OCXcc4c>y*#E3n%aWo5+xM(9gfpQ zh<~j>$|2}O(NNs(z)dIo3fvw`U(Sc*Q}-4zo7I1Jw_y6@mJ8}Nkkep^Nc8E^N%G^c zxbema3@6pLxHF4)ThNT;pm_bInc*UYgbQ8Kwb$2XBnp~+`2b&n4zqe~-CG1aM(r7a z5+YEr;*E|il6!@>0Q1NOIeZcH6>xbjHvP-z zs59@hraaB@cqJ?J@1jINW$PgvvGdD|`Io81v~}Ifc;qrbo>`qG+E7Gg57;hV0}KXd zC`Y<6R13HeR~{PqSNu4fpG<7+`*E^t5A_c*y)=m%lN8zSl#+OpJVChh`*+zMfR+AZ z_X!U|E*pmR#Zl$H7k_2Mi>q$ICNzo$-^Sm*uJQ4V7`t%fG)uJdd{^e>W`#rQ;k70} z^nJd84T(XuL#iU#0mYe2pQ}IZ5%6n&t-_%Qe@Eq-D~3M3ZgkU?Q>y6$<&{H9MI5F z^^jiM<8e3C2P$I;CN;iBFIDHQqKe>`)Jc4<(pVP-zWYG{qt`l$K_&diLW^DbxE08| z+ekgNy!KX7HJtPQ^}7+6QoZKj@$-yFps%@l!=PRCiZfo_W=V<3cft?P&?gRn< z1s*x39Ai^Kd>XzXN!1~PlSR+)MDVrG{l^rP)@md9vV~m-2D=!*SDnj#H9LeCzaST=?gX={fi|{$<4Na$ zvfn(Gci>)aeU$CdYUB_E6(+@~k_cR-Hz(Aaq0`&jAGiT}_X}65*7pLt&kqs@1Qr`b z5zm9ff&0>97CP4F1bXx>U0_)c3A@WzKIp*VoR@Z#I6j zK@UG?@6HDTnv-a!yEuV1bt*H%%nA8dop22CxPKFJJ07t09w(vy$VywtE9S%Xc*1Jw zn@Lt_q9Tq}t7bZ@iA*hLQ22mgd!mu=pTV4??vouz?9S{C#JGDm6-!9$X^k57T|f=b zu8ihm;5zG!j0h-0Bgcr2a=E4JJDGpGmM< zZS|O&SxNzuPgD6=E_k%HEUTcdkpiXv8wirBTmbdL=3vFV0m0CXI?*fIBKez_zLlr z>3y~Jo(=Rqmr|GC*H{o@bA&H?U0Iv+SwKt!1bF{L8TMbpiuA_m4dM-4pu@YQ`#rLcK->LyAx_bq{qDw-g+$hc31|c%en;(q&xOK*%g)@ zGp&mtbb_x9=7oOJZ49oViFOs|O`M3{PYLu&_AvHlN@k4ZdHNdEmdkhB?}^SP&%34`m@XQ9BQHt|l|$cFFlY zVaBzHF*_`=my5`h#Y0Fu4s?9b_D#(5@(szrnP`2{&>N6exVenEvRbYI1laO233PXI zlCodN>KiaEr2UakI;k#>f0QPCnDQE-RWZyXxBjMXLMS?gVd2*wjlq&$A+In$h%#e@ ze+ElVZ^kmeV18J-ziC}QBCb|%hw0~s`D=e}l751M(OtC0^{aTw?RcrwQDX0OW8?J@ zm0I)G-S7i!LFU>0S*8Fz6)(xte3~=>hIRni1WS@TMgxg>tBZM}1n^CK*6eo00vHQ) z_pwIM)&_3de%7G3CM%|@H!8s5B#7;m_)0`cyo%XvZO}*TG}n1v7%Ki`E8b)Z(AX)? zCa427g{M1GZE^wR&7KW2260)P_(gd_DG=ZskNg?TW?2pb-^EAWK5VmGqY!iIZYQ+r zO!9*btT1n^_MTW-{|4z{SwZcP^AoW`5E!s^R?T*L2HC`yNH!Lt(L2#K6wRA2R~2$I zt3m%L!l^MJVR4|cGSF2CvpZB+i~_#(F`-}JjTp=E`Y_8?W@!5x}LW6wYQ^J zRQ@pl_tuB%+}^;nhfi5ofQoOkA$`1?FY5*)22M%aN~DQ!Uk5^6OmEnVs|->(r6;2% z5=BK+kQZp;k3rr`2?*CK3h4>eU3KP#NHc`^i+iAtBIFhqzU3WxiuCV8hL*l%sG}i% z8oEiJHmzBwcYO$=BFp-*wD$Lg_`H{H=0Q*sIRSV9LY~w@Fu$U9AD62A;JZy`WnXYd ziGC~EBhRGZw}6IDIORGAGb4^p9WLZm+q>aE!0^1eQqWnPZYkK;CB;c&$eg}{8M;!z zLFhp4wDiOex5IdUqr79hcY4$7cb9S4eh|ryD4iJgGB?+7wW6bm&D_@qFdZcnGP#~EnSLdR7zs0$D)gT9Uf=XZ+^^P`@?CtTHtNWd?eF?rX`==^*_GbG5Cs@?MiwO@HmJ+cJFOn132uzMIQk$u93-q+el7b)_tN__ zmVys)+Thg3*C-Sp+~3;b&Hj|o7%M3ud;!laoyyem{_ML`WhQV%8o^fM{)Mbz;|wV; zHqpcGK>;puY%mWJ;u)IZ8Gd;)SNv>K;(cfhobVCbk&noVotYgF4Eq;2#8z^-kO9q!7CP`K1WaD{{QL zDCVsNxd1>5-hN2hEN@S8X*)3CrkUV|TS^tBbP4Tmf}ECJ_H* zE>-I*<$m@ew+!H%MTz<$Z=Jy%wZ8^kYIm#shsgnX9vJ{kWv5FfIlN4xPC1<0;#md6 z1p}^SK@0>h+AoN&Un`aypR8zQqZiil@K4Q#hzfLr)7Zcn-3q~R{_?>?;4JJYBik&I zSdK0AHOW^5?rC#GnftEuK2g>152)>r1c@SFfWR)=-@KBrFNB}2*GR4#UMKnqZ=QlR z!>8RkJRPrwzd!HV2?M6TOZ#`bBc#32lNTOeFMCvR*x!#7XZp?F1}f{;Sj`uvUk-ZA zRw^tEOED>_jIYZRO+IE9=f`)s@P=0j=o2I+^(MRudfiqe8)>ZPqLe{&y|b zg?hWL6^!d$c6rFi)%QoOGqQYrhIjRT0M9VbW$x!#_HmIVn|mSmSIoA*vwed^+6Qyt*&EB}zm*6xp=Z+p5Bc zinzp}+1;I4gUZ0_pLAgF&V9QfVvlhJDR@HF#*_p*37(nNXWeQ4X%ARNvWw`4vi0M3 z9uHesY{i28FxTonRG#nn8;=7aX_LKwo0t4>rutC%BaKLk!L?6EHo|g4)Jf96)|CAR zfoS3H3;K$mi$0%d_(m}!3v+POj`qV1g|F0U!f6NVx{XO{R^XyTbAWQ~?ZxkkzFbCWto&>QyA9^W_;#Jd1j?w)7|vC;2)7y~um zply>YzAwSsCPl$1CgZ@14E|@NDt^F`jV9O0N0#LOuefg{w15F8Dij5IbWtAeSKP1v z3i3I>zOlk1#Ty^1OgH zfErpEp(2RK;H9{6ScO)94Gy4c7^niM&(sOUz;wg}jbL-AXC&c7dI*J=BWq?bNcoV| z5oX!Ha|bX*%Kx33^ur48mCnJlQ#S7nXeBzi#4sWGOyi(l%+6<(ChH!JDwSmFnyzUA zgxZJV@3-p{7rxbI;n-YYb9)Gz)+B%t*~Gf_fFu5PF(3=rFmbG#Bd}h3tGD_@XwC<{*UBe+4l-+#P3?ayv zCgbJV5^S&En~iRW;C#ZM1OlN(pBC%#$1rVLFrc4jg&s972c?p{*&0~dT;><$P5NFL zeHl4OlP8NYZL14EUzs}VMrjrUHx#GpCIiDc`}AFC<_Z(n(@hM41o2M6^=exqJDfIX ztq%-lDlTq1^i<>YQi%NJg`En=xzpKJxz6aS7NL|Fr$?_PSer)C`e~Ib)ROtyVhBL1 zg6|4zQzxg9dTo_@i|;X6WhnC6<@a4-3v=UhqOXw`cU&|l%^?=`SX2lnKD5BZCBmoj4Pq_Gsf+cc9olA03yEa!oKW|wEQ`_a#rmrz16lmaF z3*au~O=WG(I1*7@UlyEC^tCutVWEnRtvc9>pJMSpS&aCh?)iZ@)h0{4@?sEbO~s~h zyCNV_EvbJx`fb!vJ#am3U243}4u^L&B)fu;hY2jSlb(Fw%L8)v^ob9$c)ci7Fto_x zQMWAxzX)i&_&eHs|Kf9;RNT-_TiWUx;h+CdW8{bEV{`}t z($d}C3>e)tx*Il{QKM^=-@QNI-|u_=I(t0M&hB#_JNLQn*L7Xb*J~WouQ(*HIx`!7 z1n?Ao0+}@u{Ls31*Q3qkt5ucxwD1SEc4_V+W=x2Yu8t)Ha3onRwsP6&h}_GBA};U$b{ zyjiB(L7a#x-(m_JN?)k)Yze5T13l~Je2ErNtEo1V?s4DqdYlqJ7HUfU=h(~ z9u>jP8GJ{ad{;J@0$ax?qGWB`Ze--oHYQy&=IR}rTMN$$14(D{0mNFX927%n!X!!# zyaw%pVZ#oa^O5QT%tAFD)a)@I81^OU=Ln!Z2ljR=6g~TQf^pAo(`J@0)Rg;b_y?nf z_8f_wi5<76?GwJtl#j=?Xw1{d$(&PyDQL#g-2E3%*Y{2jLxfEBBmWfLtV-G$OtGSo zINOhtvZ92MQMB=&7@)^9V1BDzD$oBvP>F99tPzW}IQ}o<{dNAlK6Y=ZZYzLRtJ?ZU zTJ;xqp=Y({iaJ;Ak`W0+M~y_0Z1 zf4>lTL|=0=_a)^OThnF&57=_bpiOl?1cJg}?>(|-R3esKcV%ao&v@{>06g&iCx8jd zMkD=<F3|rzDE*l596zk-`|nwyv9;k5U-7Lw>t&qwQ(1@ z6}w{I@_~73v1#A(FY3#GJHB)jKb)*SHuQXPYIKR+vDUE~=k(LsL$&>O3%ws#o-`{i z_|8&-pZ-Y{&$xtPM%ETH*S*{3yLZNH1purr zN&J;|{4VocvAE|do;~OyWZD~hEJdSow!Y|Jj?J`nZ+Gt)VEoU7gN--aInCIT<%(&e zTS>B|v|MM~FHr9{p;_XM3nwPX>LHU>t^W>{Pk@~~Kl{12Fe}b4pq$5R9Ez6<24_nEk^5EimjEYGx|rpM4gH(0$3VxVqO!PYLqnsNd? zxBJ*TQX0f2cWQ|}nEkHoyyISrcw^{}bu$4r({!$dl~$9k)zkYW=UO#Cc#u0eTB(o7 zO_(`3u$A1vB)-xmb={So_p{FgpMF9N8c{5V4B>+|z&bc*G%shzTFaTyhUH%^hrUPG z8>_twPb!~)R7vwUFd-BG{czQ-RHpo`O@(x_l8nnC?Ikx!at^O)5GuXOo45N!TPL@v z#CDroPd={MD5#@oF{Y(fwF1@#2Q|{oi){Y`u<2hwTM0 zGH%1g`z|c^Xt{CeindzswsTADrGT`F(P`cE>i!ruxxR4chKFqBn@MZz-b#89V>omv zf7Vq?FGNiKuKFry?~g=u&o$XlT1|cEfBRk6r3q32A9jeGb^? zh(B+eBWIEkUEM8tyG6Y5_r4foif-w4mH65zarDEeM^f9LLBYb-tIA<5Lw-`z1c_z>15+Htv$B&g(BO^r2?C z$vgkGGZ#GnjAaL6fsy~sDK9Mzx&Hk4Z2i^l_v@$mq#wV(#-`?<#^wG7z@C2i{l0UY z_YXduui`1Ys}>tE|FXgT*Iq>_J?4mXlcoOC`K#J8j;(;v0<*P+dS2oX406=yHiNG3 zlyz~HR7}82T!@DEj>Z!XWacZs14@uhpU4fT+y`SPjdF&@f%*94LCt%ke}Ed5vt`Yg zXGAZ<-(#Zs2S;c>`ox;8CAO+NX8icyq_J9%Tfb9MKApZrk7RMTEgcEe^|!o@6?+9y z9toG;jk^C(C_GzurzFwC@67zU7D0uM@QS=YR-QCf8njb9<2q#+t08h&j&{{R^=e^2 zVBg@(_=fi9#5q~V+ElY5{Ey^VwXWK&BF(SfrH9+&R?O*22U3Uf-!GG+U_ySP!-9*( zwJ{r@J8 zrKyuv<{uYq`jOm=829uTf$@P#8uPAkX&V=FcI92DH&ZAorbfKvT%+wp&y;b|zCIg_ z+>^K2@lH%p<{v;}cqq|?(&G*fd!?5b;nS`E%`mn906R=2UTU1(yk{KY{Hmwoq){|` zl&6ztNeMI=ocD){*|%SOvLNi_>DMVch@=TP^7C#d?@}dz(PQB@%()MD zpOch}1JSvEjr)_nwcvK5#hNRrmqXc7)$~TDb?4}J@_C}rZ3gaBncgsRTNxKt$0EGh z;QZM?n{1G{Y54DP@3#_T^_V7kuz2v=y(0a#u1JsSk(}~e<&0yPPku)3a1GD*rU<%> z?1)WHOEGhwgiwsAPnN|$K%N@x+|?%reog){J`(ErVn+9P_}D|ARYE3dyzive&)%R7%e?eBH;(TEHq*b?Hboi@27*JIZjG1Gye$xkcpnJ%3*+ZR zGg_$ZZpnWDLgL*Df^`LvsdIwGWlM$YuEbG)kJZRGWgySKKCnAZH1%u`B<0mL2d;F^ z4U>vbzS$;$NT5iIhm=E%E_;d<89wf>u-);l$*?Jt;xOA$>&5b@bHrvu9l4V{oP^Iv zZEfR@N@r{3Izr2nM^vPuG2`JLysW$y`3 z%*#-%kdgh7=g~G^PFPWSa&^V4evSDD7}#eY??`T&9lcjKbdR-XUuI@0wy(WJnW^{2 zi9YrA6Ac-Cw7aY?b6eiI&Sqy*aekIDu+M1%eTvD@RgfjLO-M`PI~87RDA;D`*6(nK z&rbNTR<;&<(wF%0x+`u%$V=p(Xi-fgs9qg{2Stqd{3WA~rhj{p zyPH929eD`JTBr8oe&I9DaZffw^s4qYm4tKKmQIy@k{1gflM;uzoWlHRj?5eu(W%jF zV<=6i^{SR}0g@kcpuN2Q?b1eC$0=Dn@iH1E5@&=GN)U>9=^!J_n4zhQaI*PQcR?<9 z6IeIQ@8aB&wbgm<>8f{D+X=y&BdMAtGcg`>(uz^Dd!1g9}6jVFVpXw5B7 zmQ<&v7wbeyF7gylJSdKR^W~%Sy|Bwz)!i>lhwFtyi$@~I^$Xj|LKR_Yh z((%*+26p)Ef|6Z6SxH}RUwR6p`!dCovqa19eNAZPkA#*hx2>Qy7e^@4itTmHH~pH; zIqFZReuq&5t@Sxa`aD@5ew0uJzngu+#I&ifgZa5#z%R6L*tdVXr~C>?qt|@nDW`R} zbJ#EaBc#bR2~J@a%ayo3nDpG<0LajOblllbK&mEo@!592j>>1z=LTIGpUkvEqk}L4dzsq9$Zx9@cziWx zj&u_``$B=$L`Mic;1X}Q7CXyA9749X^prFt!Q^n`k1a?voA*~G;pXZv_|pLs5pp>+ z_7=XL#$Vl)t(~r6WqG7XYuCX_@XG@98$uz_BdG5`=wG)F?=^?Kvo~YY?pQboHp)HO z#Z{@^cnL40*w+EkT+Nx53G|9{0au8|aO~#RF8Uu#GcDjkJrC!lSUwbn%VGyRr*R>UkW-z&oyfDLTZelC?}gicYg?q}z4ov`y> z^1zF*jXYKnuaUR@KVa{<;f0@Goj$3V$AysfvVL2#j&<`BL(rj{+#7NbZi3wkQ+&zf z#s=XRmT-o-c1fy(G9bPVS5!le7}dwKhkMm5A^Ak4H4dsY#uu+>fGQXu`wrOj(q=NE zj-#mG$V5>k^`)Feznog_!KGk+s!Os^UM;nriwcOb>aAOOzizFdT+KeQ%XdKt@08P7 z*e1vn+J9%tF5snf(d14jMUh{%ofDUxYRZMGr40iT=;3O|`?jM%R*8G@qH={_)hMk- z4h|?7oT}Q0fFOe3X)LU?Bd!+ma zyxR92$Bva=;pQA-`1Ib=ahu;-7Xju}=YgP{Au;#Kw z?Ik;~ueiA_rID`0NXyw=czSo>#8wBC$Q0}w#_d}#F+v>yqGUE_$^?pU+%Xg6ozjO} z?!;wSPG0nmgq!bTj3vn4FW#6n(a`}OC;(U${VRlKBAH1)*!;A-Zh2WpR##5G;=XS! z>s&a%|8AA=B-%rSU8@ZbZDwtSNEVes1F7gr@;Yeu1X*`^DDwO!Z{XD<;c4r{XrES_ zhgoeT?FaY;ZS%R!K`}I>mgm(KyY`8jQB8ci5%}A(aG>6blm{Hv9p>wKS?{aYzU&y^ zxVYs!nQG{SqFBg{E8T>k^CQi^Er;sNa8;=bNja*A3(KCZver?|v+flySPYs4U=AWv zeiz@7s~;qaJBO;%&0KTLB6x52W)WRnUZm;=f4uEW^eMVhAg$XeC>p4ne*Zs!?cKY{ zxLa(XyNZ3gY`+}8U^74y3~4i+e3ep%6XHv;kG>2gD3wK*`U>a1MEI_)5DDU=)}C#& z@muKxhK=Un?rRAd%Nq@JqCN(~&63cs>k4X}J2~tCjG8 zjGS6U^+U$e3MMy!>Fly)O8(Ek94QooL5c%o%Ie_E3M12MkE}pVswH}%UbqlZntN14 znmS@|FIuCBrfMcW=eoKfWj(N(5FGiD>lpQn7m?Dv`pw`0=EAvN1=m5 zSDxmTq{X;V;$YhetH{51&TCZEJHG5XiLz!-L5|#1c!+t1Qy_B81@@QrWjiyDZ2~Aj&S%TZ-m%3pPDx`H<-ZwQlrKE6v>Ig^FVFjHCEw_%1zRM%K#B zcm2fazD@gEvAZ>5m^9{>1Gb&~K>g3HrgEdVz=O9O(wZtdg0GGPw76tUH~(19{xOv) z{nnRln`v^$Zq9gyE6kiZa4P;B9o2ccFHojy6BbX0#&&Rsa2&%sppB-z{WM;LpkQ%d z)i?VCuipn?F@~@H!+FKxkS8CbEZFhoqyFknTXX?8tmMm?Ud(ZN_){U*NEmZCUYiU7 z+`s8XKM!Ccr>)q7s``O>TcDrt6q7Az?B>?P^A0^)!p#})0><1p7Zjz|$mYDG?6j@b zrRMtrU28>tprpj?yWB!H2RW#SCTmf+r14?e{7Ca;bS|1 z6O=sVd~&V^aSYd%t5HD!ds^k05K=pb?p6m=GX|zbYc$Fp98{1ISv9X&NyK{V9r2ej zOD__A^tiW&8WKw0C4Vt5AzJS8rR3}jy-nn4=aqBgG9l+8J*LMkK%zfk)_YeFTIMNt z9f~x2Hix5uDmv-Xo`Df;Z8kNEr|8}xGYAEt5mk>4v*|8`P;atOK0llJvr=>vPb-JYf6O6Mb;_5)u+)NAgFMdRt>lk!&#2xsUscnA&D|t z6ft3IN1oilLmE9_W2vz+fkEiATJ{e3n2yHe@od}$_q2^hL1FD?u+`wB>?@Z+hFk_K zYb-4Dg{0tvj})|?531~m@?8Ua3mk)-we6=7+OmP~p)_nnj=G=`3*vY+Y-GO;?3&s) z73b(#Qhc4ERLXZ_3e-vqUN+`)d4;H~|73^^c0eT3MTFXDl^JS+IdUE*Mbv{Z37zeRHj@oIa^PPWyq?aWw!djXiUo^Z?wX}AQq)Mj7*MI|c zYG(N5T<9H!TR3tR54OA1q;OfK_P<|p!x?>NpC2@MQ&$RBz~}z~LfA&ovT?!k6&|H7 zKNlHFhd83@-S!f2={_;00`Z#6S?f>Rl6hVHzfJ^s6wTW(dMKtykrP$*9WF>%3_4Di z0h_;Di^aq(<%Y`U4vb?CnVZv%xOVbi+t{B4`U=1bIx^i|UZPpoeBQ#$dxWh{e#$Vv zsvEgMvoF-uEP6zXUXbvIE9HIQr!7}gkS`K!Bs;LBy=JP4)?Oq78@eLv2IVf#pWIeW z{oM&CB+V+~4nBn7r*RXGIM$~goIOGVN_`uo=bCMUYtTR)r)!_sq4{n3qv2mCpIB+9 z3xFxX45RWL<>o@WJiI~iGjYNVWi#mfoSKysWS!=++*x`IkILS77*k2hy8Ni2iiP;} zVPl;&SggN=WU7I;X!KEu&o=>j2bk;cu|bBWena6%ZgI)f^=5YVGvPE`hZQk(IsXf- z!hZmH^3%V~C4ZCkTN&XKAW-yY99qGGnR5-2=^io<`E2RYMIn7EQQw{&T zPo}>k&q~oJlDBbMWj$DE)NQF3xGeV(9*>&#!70J_fX8dIFB=VC1YZuY^o!eA_evkD z`uG>@7vtabldJQSL)J9Bi7J+`Ne*LO*LJdn76k-G?9Z_)ReWwUR?L`oO(uBI-1?2e zifoPJXf>-lQfPx@E9@`v=Z~XbH$7!K)IN+k!WP5#<{ zk?5{r;&#)qg9xF;H8Q=Y)s0FM9CErTh@FL2{}OuA_X9s?WI5$atjau$8x9%;ZKZRL z0&DhESx2@48#NLyaaNvCFnSR2i2df!`gQ>u!G+8;EPA=(t$3vx+KHCTgeQ}lI#N@5 zO0tp|b4wL@<@0*=+nAV92Erc6NT;p*c%egj?R+N>LD6UYcf zOGoW1UM~}$XEZS^VW{ulP28`RoyzO3VpTEvIbF^Js%5@uWM$R%ZK|i-oVk5l>h$%= zWm4U1{rI#JjCG;83m##-g;Uaj$EsvAM-+69a+ypwdY-b00?!4yZ{LqkU$nu&sk3T1 z<4q;H=ITnbLD35@{O33m%JcKWis!cpb=AC?-6i+TGT3#-N^H6Q)N5>&8$5sel6 znT|CrGNmJzKk6wXX?vT0)nA|pVCBaFw$Sc%fagBK0Yr(*}OD%HsF<5Hnf56BgvV%xlLzmQ1NJrky`~SlPSj z_(LP)JQMX^N|w`lxP*z+D?IJRQ5{2T1kZ>4&m8?NPOz)vhJ}WXzHp#!ppb3%iJ@C` z^HHA>R2PLa67n+@-@pd!pNKAF%7x`RrR!esOz`c6wd#BPs3X1%hEYq6+OOdRH&Gyl z@z9Q4gHHw_*e7b<&_+NtUt`~dg_HPcvy(NA6lyT@`<}!~D>>uFJa&{$qUHd;7?65=~hE>5foP*SKY@gc=31r2${7GVa z$vr+u-K%vWWZ?e~kVWyoawCY@$69)wQlY6>EqjQ?p}^B@%TfCyDc315(Gk9ss+4kAC84}}PPrKYB_heCUM0TjJlk6>lEnc$BAoH0Pto8o4{ zjHQ(Zg=t!PZ0ppywX|cRS-)Qy*AmXfoKfR_f1}SHnTROh?^pHNSxNzAL7TL2F?QA%j zTjsoF>%)I*rZ{$`^wjRFT8(_*V-3nz)<Q^9H%`DCsKBY>q0Pd z7N6j{RcmE6rD1n6>R!h9Td8`gJ?aBYTTPc=-d$JxMK7P4iAKJ;9ff1p(pJ-`*f(+f z$<^?3T;B4WzLVS37m${P<;L-_^g3JT#_ygAbb*tFJJ$U$53QR?Rq94&LYIohi^M{~+j?I$3_t#vGl@T>z< z6;A6w&5T3T4AkMjX@kTa)fDIQpY9i<5>yJb!c{ikH+<~@&Le?&ucpsyQ(#-XAJ#sA zvP4u3E|g`8wAIQu&RZ7jksx;Oe$s_cm!q0Ob`Zj)h#;Z+%axX*BaSYyug9&~y%mY- z-SaakadkH9YXXU~uk22OBf;Awi>Jf-ktA~&spnC5?4!< zVr)DnCeZhhV(toO?o8in-%ohYr9R;q_!0kM$QNVnI4AT_pLTAMRLpa3wDuAtv?mde zF?D;>6tPcR4p|duD0?>lcWrZCm;^4E*HC035;`xICN}J713!RV*; zsnlqhehx+~MKiVHvlr=!qKu*XP|4cc95ovm8~N*HMY*X(L#}!&w$yFqFyk|8R*T`W zMzSCk{@D16uOl)t)>NU{{LWH4Gh=rz#^CLe7uX1ti?hKqS^6@ub!K#!U{60MYpH?+ zBj7c8T!~HHH>45|FFV&h*{JS{()5IyD^?!cXq>`gk_^EauK^J!EP?9nG*2XmYiLNj zAUhipkH%K((O5O?VF#1xSae?cg5#Ih1frX`V67e^?*;?cllx?Uc5n0n*3!fhzhm| zgq{n=utHQooa+5(2NfEmN4M2d>f%OyvF}J*FNBkF7tN`g5LlzhPkXPn`}{Kh`(=bV z-e(N&Y_sPBEYGFLUU)BV58UtZ!O>gZ<>MqwIB^b@E?8wZ9!Qy)EPEp6Kh{r6@>lR8 zYwnCwO9flffcN$J!|{gsLGIEW$QfKCzQh_D=5*xa1=4175W5L6k`#Z{mq6ykot85;#5-eUj4H(b0aTb1m|qNO30qVbO!)2c(Zxzu*$sjP|(9 zNkrKgS})LnTd`8p?@O*Q2W*quygCVO+(nPbZHp+;9kKp1&HkRZ+d9)5o4R_|Jm43K z)Mq7rX!|Dy#Ia=0=Oq(QG!x-c@$_^h4bm*|*16m9shTS+F}_K@2&6PkDL>Kr?mI5s zaAtf<`Sxr}1ki5(nOQM<@Q5_;Pnfxkl+8uVQv6^We&^m7m#H2}P@TG#xp7SX0H%Dx zxYSb#TJ@EcmL{qhpZmC(tRcc;TWc%&vH0s!+f@bq<5(9~8OJ|GbA|oMd(W%<89c{v zQQYMu4<=T}goMb_TkNVnQ&!bnE#Y! zbw_4m?NVA&qD5qM^(Gm%*N7n#ZxM((LPAjL3a*wIj*0Q~ES&u-0?U-75SCSWx3*D= z?y+4*@$4!W=nZ7Iz(hIYXwyIwR^o&F>`L=a96^muX03l7Y&Cf!%1%3Ma7I7sP8Oek z94ePcrZFT+_&k#(?okY-B#;vPwjT(`!m^yAg-h|y9?py5=rIovN`%0amDQkyYLh#| z49ry8tOC;FQ9xg(23M6A>e~t({@ohH9|EP@Z#u z<*-phMKwOE!F0vM4R*%z50JnR&(gLwI~&yYGKUImF`WQpH#rd}{auh3o?PNc$FJ8X z;uLSCeNra-0sRfb(`&S>pq^>qt&kC&knFDT`@rOp?cZnQie*#9OE=e(TiH<8U#+uF z8J@~s6*g*wNex-W<>pSx`OSx=r%S4{yy7}h{V?8Kj#vj5j4sO90{72&nr#zX5(}4M zn@#(ZwI9K#g4f{_z5)?PWcB2ad=cn{H2^;3!T10M=CdDYErNBt4A&y{7_8vW3TU|< z?*8#$3}s`p`sU60nsBaLp2vBycz2OfzP6TVxT?#mL)sFdL6zia?di1SrAdKTd*eeN z_NN0w6lJtMT?@!AEz2`RL=)mu6Y_FvB{d_RCPA&$z?=EajuDz$0Cjqk#*Ckx!Wxb~ zv&W6Ficf(*rd_Y{`m38*{kPc?;`Pxl*JeEiEUA~BIVk}Gz`2mP9oRCe*oNoei#hJ=I{Kd1-Ha2?2gj|I zp#G*lIBCChfAk2lo(YFKS+mSk+r+@$=>$Af z>LylJ#AF6;+CATrKU&jVUyFqpA=W)u&1+B=_A8DM45doKpRGDQ=4gFAO8Y0Hk;$Lh z#VLS+Vrk?SH+Pum(2v3< z>Nf9jqz~YpT?yGkZTwhGLMj7FddD4jJ-QTia2xaw@M6cuZU&QIei<-^A-HGy|0IfY z({YT@RYK+I)jz<9<(=Ej(A&3YF2Dba0Qyf7z{&v+SpM^}!U_1Ff%o(5tdGAL5=$N! zT8sbSkpU3pW&rR@ukm3x&5fKqn8`egXNW@Gzy=2PKWV4U&bxgKL~&jDf{(26y92_P z7SR?y%JohPFT+NKm-^42Q)yD*gAurCiSyLNk~ZJ{4x;$s;90{>AA^veO#|l*xziQj zTn3Rc%rS>z3TSw1<)^#m5kd*&$I7L9_d5@zn|tzhL;^Dp0d{Zk7bvN%WFl9&3+Biv zu(e(Ku`P@$uY6D zwJvNk^5<%bs=x1}Pn*xcb}ODtC3WLxt9H%o3$}7qlKKq0qGwocX41J!DTl$mcu%tD zaKbCL3?wniL+#D651Z4?u-KjX;3!6;J;cDvV-CljuHb;KXOq|cRk6H7@BuQtL_IG( zkX`GB2<{xJ1a5cKp_$;B|w^o*?7VGA_Iqw2KM>8Yv)0&yqm+Rb8RaU@xh$u z@K=(yNv{l2&6+@tTQ%I_V2x#=CYGGgE?H6*>#vjZ;exavelUOja1OY@1C}FY#adFt ze#wJV&3^H{UQMC3Z%bdS$RFAi$hN7;v+2~}*?&Kc^)d=As~Xs>38gd1sQCvNGTQE1 zWmmg6#A*%$>Fh1GtoQcW#%J@*PHc#LW2VED0qwX104ek7mA z=Z_co;oYw&S>y74{M4C&i$2ChY~qV3iItx)U|sZX{|aGocA#GOE~VJw;9cIfc5`4% z%&XF+&I_A5IyDXLrI2uF9(o= z)#_7s*E7z7yVo%cTr>6ou$AIYnh8*NuHVUQ^Rveb|9N1bZ0P<00=gu+J6mM6UoOU4 z6iyYH)^551FZyK`*rhFU5e=m-D;4r`a?GrSr>ssEZQ2YG&Z_k+;nl6;_n+w9QJrubr;jdC zXyi(#Zp?VDK@e$hpk11|RBo-o!a`h1)!KfHM;!x5srrY_(}M*Lh?~BN*ju?1OHnzK zfU4aXiXs@2Ypfg{2KI_z2P=qv7rv{y++k%upkA%tRrf1pe-_yMJy0N0lEK{khVfUl z7c=uj>*b8*)xK?K$w0PR#CEy)S1s1Q=r)A{HX1i7OG3nB?1nksbxpb+70e{lED_se+@iyIP4+0yF)hqf@V1#ZgvJ&HWRfV~Gh6 z%W|wY{5qn932W1xz|G`by+j%`0Ho$n>2y!!2J5Y{t7!>%ZJ*F*F(m^|#j|)1Jvw^>; zV!2_$Lz%GEMlzIQc;vNE;6_4I4h6u#hJ4)Kt(-3Zg`Mil(7eZ;$zieULi?A>RZ1Zi zP1Z8N5++dpY9$P$$2*UXlaW>YolvO8Ibggd9>i`Uu&Om_y0ocpz6l`S88JN zF^CXU!ss*fL6)cPcz6|T7>K-^M=p_sS&LUzeP_3P#Zn`Cgu|RkDskP% z(ag^Cm2Ddp5+-0dicW69xvtMKRG)E|;-k-ls%~to^zKU|&;Z8gQ@!{TZ=(@rqrr#?!M32wkUvh!K@AOra%RiJjjRu^^CVACU z{OvtUt%&0!Lemadx^Fb92skSj3~LP*l+ieR86=~FJnKRViHZfJgL903zi>BxxTjFn zoREI&7o=-q_GDS%obt<5c`srl7y}N~S*mj+NQN5-mxGfZOHj~wa!^N?7Syb^)yiHp zf?Wh9q}Bz5dYDXI3k2%v^hnxrc128XPT-Im3uKYa;66{6p4Rt7i0B%&-VXS1$Oob& z^-Xw9YC^iORBIf_qX+X&J9s_wD4*{#m_;qHzJlDHK!-7b0`CAsvqG7$Z_c?upzy8r zLbh|noMj-|K{-`fDOs%ru?CZAiR&pBdjuyAo^Pq6fu?~YI#(CXShpig)-4Sh35P{B z=bS9O$vA6yPyH-k+%jf#`JhOT%pE=XB&@N;4YNi4M^$&we}GhVszl}^{YCFx9>d^U zlWXxw=W>-w&Zw%g4xVwvr{mRuOuRH=V^_L&q4V=;t*VO6@Tr?+#cJ=4i*I@sLwX~X zldGdXth<5{Wm;(-!_Dm9C@un}R&g2dxT6FZYTs2l5gIVH$Coy*x4x<Ne0fCqBeTf|9d}#r!4auR3&+PX3Sv%C4 z@a)us|8{oVXsnxqr95TYDVdAJWVf^*969fPm`z9H66Vw`!#s2j~P6om} zt4=lJY)4xDEM+}JKvwLw4vKu3(Hz8RTBUf{Y37@-m09==eXOxf6ICat+ zH-Ue-0N4#T6W|0O{)n5s=p@%f9+uA1yrR^`GCDT;z;zPTLN8=NHVGJSrhh z(w`^3zbt3$Y@#c|Pr+aK2e@ppM}BMBV&2q`nTt$bE!IjtxzX%N-YYx}tlL+}x?~H& z_?>Yw>)_MaEyqnk)!ic7g2!!p(M>Htho!r)$f{V=EF})@7w&({O)4E%GSM6ZaEC+9DkV*(lsA-(ZChEw!fzz3Q+`NLa)p{60nuoPeK z31Vpj5HLdR^U>@B0V%?-GbYdc!+4ipv^!N-_a^7XZ$QiT1 z%%B zAdPEjOH+bXkC0C!w$w#oU~kTqPE;jyU*dGBh3;#ag_k~z&OQ-gg-ibGI5jwYW-vQQZCc2hcHWt-fURsCeVk-Kf7r+G?e5KEz**A$DuED z-B#z3*hG!Xjt2ixb9LL_Q@1#ir@_DjR2}))$URaIA+c3;>wi}91T|`w;&fX6GkglI zJ`{5fdYjfFSns!j*zhzp2u?{)@s~MsPwqOsJN^d7jAyvc|d$>(FQ1+ zyHZ%5ne@id)!3b&KZ(2*^o}b^j?GZCY*0Q{ZGDP77^ja@@0Md+3gW&)8(^mP~J#e#)tW|u3GOb&Xp2+Le1;nZGMei&g6H%e}KpLarFq9e*lGlfKG`# zi`~sBQOfI|H-VnqrzkzM8Hj(^jCT(63ieuU;8VsJavlF4E|X11kvsZeenBtZw#Q{o zl@#7wMLY1jY5}3$)ZdNYmsXoy$8_0%XOJ6Jb zQ7QH${{R_Y8iyI07+C~aWa(`lI8X6u(?EKv&!PZHnR;hr(%t%o3&HR?^KHgVjSq;| z3wuA_-h40Ei5yT%KfB|`$ZofiiEZjDNTAbpVK%Oq45YaJzM4;w#D*4a=j7d2Y*XQR zMa_VB;%(mlq3bQ9+W5Y((NIc(7D`)+TPd_S6t@x_io07WPH=Z9?i6T%Qrs<2B)D5} zcXxLuNZ;x2|E_!2{cyh|leOk#=FFUPp1sfB&wi}y5K}(Nb!Ri2OKKPEkF#^d8YkI1 zEsY#LgefvatUM@Gm;!vD6{*vUk9FsNodmT3;|0{QyE^syo-@ewYnZ$Xmd)C{{(>}Dj8|V!D7l{dK&yH9 z5EBOX%ef8?BF8{yZ!9JjBEQ{k!Ce!1qU>%Y#Ubcdj^6 zx6(6lD!_GgA72O5^iDi%_|CK8St$hJNEmpXH2dspcUcr!Aia4#=kI=z1qat2gAyev zl&KsE`4PPzx&CZ62{YLGc~U0fc>8cKRh>5ty2vuQ@85kRV{h@M5xr=J9&!;XlnI)6 zMHke(Jx4mx77===_#fvI$Id54>;87xQI{b76JMwTEvD@~iHMku3A6TC94H#yg~yhc zKr~0DR!htwLajTfLLhIy=CuQ+swa6~YA-rWG< zVSUV@mz^G51!Rn`vH6a>t;3_R4Bhsy;N3Gz>}y-D4rZl~Nm@^)illQt{r-L@V%f;* zB0v##EhqPAt*2-ckM;Cf)0mOd36|f<>E|k=# z<>SqH1rP-ZVq(Gtb=Xk2^PZ$ElrJn>c z3Cq%AQrFL42*YIXu+y&iE7Yc{)@QL!A@i^E)Ub6mr&N6^<5v43J0r<4%dj zWYH|9z=HtI&U74mZa_7nvvjnICZ+2Iw@o>@$Ey*|JF$x!tw`td$w-&y*I@lC`qc*x zj_PjJX$QS>LqB8%>{sL2h zW}#snSc);vILVx zSDWa#tA-CAbq-Th&8>%S2*N=Lf>$}lXa{F@*2gf@``18DkLL6c7$-(CpfOIp%krHp zK6SjA?h#Pj_1z&&>o%jS((a4QlWB9Ab8dy)WlihQ!)g+?>Tf!q`IDzM+d2s-cs@sl zfTmHm@kYb?->1S_2HfiLsKO%(rS}#mY#XA+s|%5lLooqmX7~8MtqgI+t*%~P3AU|z z^aA25m!1GSc{$g6WPcdx`VRrdRr}VvS%&|D(203w>|0Wu$(j~kyY6cNa24Nnjec9T z?5CmoS?v7I^%1uPAWdlfxAX&8uI+KF`9?)-UWN$;e#!3 zFtIjiaB+N3;{$CRH2i;B{o4Fl+pX_>EeHMFMYb)r3K21vDeeO$ut`~ffMpJx@no{l zZZMlMN8@JzRS#u;0W&qlpZe*SmStS;`j;FzMA!Lu=MPoXCP_d39(KK+6|_3e2Tz8n zphziK55V9_ zC*&D~tP`jG^jWRQk4oqJhhQBUGswtv|K=FC{D0r|2Obg4smp=B(nzX_)Qh3}_vPg1 z*ej|R*#N+<(>o#tkVDS(K$4wu{E5Z~4XK}^pI95;7_}mzNu>}o7o|mR3a@$ z7XRh?NXITX5pOmqGboprr#ttG-gWf0?g58eYWB0Z)CX6x)0Nw4sZu#&gMSDku#&i^ za7%#SAN>zKz2$0sel62!qs!nlwddzkTn$|6=Lb=+-yudGNfY;MZwdNou>V0>gq@C{ ztdDX*3UatlLpA}=73%#Dab3Ir2Vgwcb`!wu`u1eIeX|8FqZ_^c4=mUKr0&ze`%HgK zkF>uF7J(V0k(*t|MBKeir&vlq^VL3iNu6i&6s2by;u$d2v42^ql?e^D?p9M5%7iU!DQ+iT$2m79BRR<5&EjWrSu&U0UJ*Z8>@U)P!d_Zjrb7+uFHDyD#|)f$)#yuE zfwvm$62dZ(dPX^thm3C)?@Lkupw8mcKf9pF$&1KC<|wrYt`DHQRwuvk?>(DaJevTP ziN!N!*=}#MO$Lk6e`g-4(UxB6$KBr%*FO%!trn8mY zu(snB0?a3a1hfXaH#(NZ z_iVEDkG~$LWxi>cZM5EjSk%{tFanhG1xSR4%1lxhGNWhK7D9k+R&=K4b~I?h`6^`+ z)u(8tuJ*Pr+lRei$3JWyH>)VahO$iJVyF%$OOp#TbvYBoOxzXR{l=YVH}mh9j?(Ty z$EXR>nVw-U-g=K{#EOJ0=5JAJ65iGtZqqh!)Z8k_%nXsI(Qsr+l&EHH7Fq6Im3iz(R;V4 zoQXA#PO~+fxXVdjOx$`zxRM7B@gj_87@6r+a}x~BD&`t9VLy}au$&5E5Wh#3@TY^S*1{hYq2i~hhNc#>(N zVodRfRuilg?6mG-(ZF!LybaEd82H2M{FyBcPt`F~K0A?)cK<_Z7#MQ0^exI}DluTr z%b$X?6-XM{4}f03oFvd)lOq(Sj(-4z4JzV(qj>W9EVle)De74`3p)aTk1bb3iXuLN4B$E_bVQfhLAsHX|Aew~@ZofFXik2lyFSw{H!AAEs1aD1ee1S?-SOF|itc9pYZeG^@nj%2>)cTM!O&Wd}< zlb{oGQu5i$$*b5}>^Ctu+L)?+#8YAL@#-883h~*Yc;5VH>?S;89wHAXb@=R-)ZZ}U z>T?+fAH6)q$G9lzru6Z+njCkFP~a9z*l5b!bHL7$;B1e-Tjj93u=&c!h#f7F8plo9 z;SkFH+07uF3a$+=82)96ksnibXcAR{a`=wFXiLZ-eKDAa{;~L5b*_th6gEDqib9CJ zl})0d#oVahRy$(znAb7Qh=?)}X9Pd!OL$g6&_@;8(pRtX#8B|Gbyc5Hx?HVcS_^(z zog3<`PfY;pddq&9$z0t38apN}i3C+d1h|2p<1vhvEdH1Z`_U~BNx0x`W8a_R%}k9{ z|F8$r-qL0ARUgeDBLt%?$xtDB_Mblds1#PT_J{jtT0RM)(~QufFtOeE)u$ zH@`oV2ofRBUx+k*Wq+WL+m;#!Clg5_c;A9$^=If5=6PUaP8~^>5qWXJWMXB!sx}rR zkPkVQIS|M*_+hxeGR2M?uKH~Y2*mcQmNiM)?XWLa;ArZ)zy;fS*uYdR93|vUGXa_x zmd<}cM7Ea%#77;-k*BH3SRg5~!{%BdM5mqsR_A@kMWRyr4gXJ`hAqIGcNT1PD&<(w zWRaNJ#^J|wBt;xDQGZSUA|UYfVRPz6qjJ&X>RlQ??l&S58keg-M{_GH+@J+FBObkk z5X!^vkGKTuA0O1N{(>y{4RpnCdVQ5V=#2LJwZ7*2mej|jDIe%CXA{U1Ei$D#ZJ1cQ z9{<{5(?&DL{|mbB(buz$=l+Zq+Cs##$C7v_xg@yF>ceI*p?TJ|mVU*Hlqpyz@2D_t zDcyP8^YyyC(lL-#fo`bP;kfSq*M?bwS$GM##nLT@j4)8H{&3trJfutnLeG3CkGLw9l zyRqZq3$v(M&y=y7TnMSeQEd+oHEN8ICYy>w6yMJjm$XFl!Qz=bavm%R_7_PiupWes zQY5j<+2Bl1!mNQPBl9y7nO*DLp*+>wn8a}e*fGUAsBvC@vaNb<*&14040R&ma}SXk zWb0cZ5GeLP%hj>B+}qUcnGt2(<(*p49ZKYa%v})*rXJ~md8bWAHj!^uucmGhjKuDG zIg1Um$hFZ_tPY5%C?ivwgJ@C7aUS#qRwuZM7nPc z6X{!-weWsDqdoV_OgLSEV$9Kgs672wqeNe$Bz744V!LJE$!MZAgm1;z_~G)$x4wP8 zZRP^)pM&2jKm7C?yXIZ_G3xhu`um6{fsKLa3RHK_#U3L6+nKzQdYIOben=BaC!)If zEE{q)wQXS|i?niS8q=NWX1XnDyTQNNNH1bZxvCgb$eLb5--jK_#A%Ca>4q!$?}X7f zH7U5ArpN4om<1YB#+oZ*PBtH7J!Hk*4zG5XMi&PwV0%lh9k?@>C7EFth3Dy#4-6M& zYGs`OJ5T%f975_+`~J&=bJdXCu7MWfM)|RR$@b$#SxMGCouHoK{rk98s+v`Sm>a@$ z0dS?_pMpQ%g1q~#*~uJ+m_O@t2E#aB2IE2V&4M7_;J;qZG1_r9J*~YQBy#C;gnT zSxZpQsh=&E>@=~UFG%+LbyAEpnHd@cUY)pO-O^cu6dyA8uDb}$HX_4Yh}?cvNhT$z zMh>s%CCLE*rJrWM^tyu#T7{Wmw45)d>*~DB?nNq@CA_B}Qr>9P`7M`}D{jW-d=XM= z!)?CPy~a-x#Zj!>3HNyubZjpT*V&L96W;fxEpKgbu?%?ih$akwOTdiZgsIA>0-)w!4 zW9IXC`2hZVp5(XX{7SAGb`VGHt3?{a4XKCVvB$Ntb3@lgmH@HQEEtxZ$l{OoZUhMm zHD?r|`O`Rgbom_UwTZ0-!juk-Nx{=Op=LRhwMZvb#$Z*agr_^;C`G@iit&U}38hd> z3{44__Q^+8AypOn%qKX)Iqui`! z-N)~LziQa-=X_Y;fRVo?6Q}M!zO#@m{MaoZvmOruegLJu>?@j}{gBCM&g@$&m33V51AOOvUl7+zg%jkw(@ zk3VtC8EYPkp1g6Z@i=b0ie;Oae-UmCt?eCC#p0y;74AH|bLI1L`X5D=u-?i=gELF} zhTqrmU(QoUame`KA)AF-<(Z%n*p^nO#6<&}Eaf`bAeT(gw|LsX<1&-9wf&Sl+8hiH+FFPk|5nyXyurB^O{j%tTER0%JOai@OB<5{ zS4f}TN?`XxJ+!7%JX{S9z)`b{nteQ6^K;R9A#sZkJ%s*e-;L{~&sz^nTwJ{_9fmm6 z5(~U%UnHY@W?n?IvDsG{8%G8eC!`#W!}Zpn->KG!ycCSGp|F$1@|8CW7YmE6q^OaR zH(c2-tWLe;lF%#i(wjf>*g*7k8tg23dYl3Sb|~|&vPn`}p-`TDk>qF9+;dhVGc#Oa z#15k^6oh`qxba&x2y?B;KbVCwGIUn+(HCXDB#X9m=i!$4ku1#0s<$$WR!0uA@UlAF z=ErAR5fM(>efzI1iFAWJW%M){cX&jJ^3F${rNI7xvmbuDQomnPs-Oc8=ku-Udvs&Y zyNgiLU~Vk4-88q}jDSOLBo`$=m}x>#9D#hf$hsj)7|1P7K?uF1G+iT|Sm&@qJaNC@ z(iI zS5R1cBnyU`7fUb}8YDIMn;~{5wy&3C0IZ#gsRo<;}`mHbS$ig|q z22*M{)bg*i`@-H&DinN^aBR02W9m%~KR+R0-`TV8Wg=m$Bvp20iT%FnFEnz%(F9xI zswErj_qZu7@47D=hhrAcG^jJMsX^v(JQG>7M8*yfX@?KmIBC;HrJprouJ99WQVaY* zq95Z*Ma;e%IGT=%gjGJ9bVEBh6b@Pb!=%7`1|JkHS$O zlUb6qcuchizyuJ8+?Y8s-59$30dO%pvaeFAf3vhp-gEib8AxPuw+r6b+^^L(u^9x# z97f)+!1ofsZxmKr&cg@YbR-aAHxl_{j7-JJ3#{0HgoPZ^f_#d5(;mf3qHphBqm7ff znLs;GZh?TXBV}c@#pZC(0%dlNk2E@>h)~aY!5}cTIHYzhxAI*vKMkNx9`uXJ!o_8^ z^H~GGLKihNPLw;qlJeBD?5B$Da5U;jr?efniYm3U*!N#Sxxm|QN)y$BXh%gs2>Y!e z#G}FR%yGXF0nkf7PXdRLI#Dd{BTHt_{IpqfKthsWd_nr<3&Bs9tEqnJ$@PhgN?v`}r9@ypM-&m&CwZ` zV~Kjc{>3bSE>DLkeG-cP$2d7Tg4#7 zAeHAo&pf=-_Sp^ML&e73Wq-KyXP)y%WpPQ?0`feDe)m?!X%SOz+uwp<3`%0pxLi(t z6Mq(T?KoE{y`F9M+Tk<%w``IV2pwJt8m`_oQzWOl>JKchk+C27-o`PBQEZMQBj!8@ zfGQE|PJmywn_fFC?bbJ2X)x$}qIdfonKW5sxYcmOd>>>JKXJRSAwkB~{d(%5IK15U ztSn{0KqQDi{qs+GrSnpP(Av2siI8F1NS@W~;*>Qo6o!T%Pr*WKG}AZoz(!uYx3b0y zDtK^HFVD*`m;;L0i%ZL1m0a1sp#4;Nn5@Bn%K zNVXQakx9m#rg;BYRa``$DMh3WWhIaC#yW*GYdq&MBXQlgxu0&O z#VKZ?N|E#;ckEFIi*pvWa3|=sZ3VxsI>0-y@<#VOn7o~4;qyN`@)F=OUj}EZZ0o`+ z`(14FCDTP2up=8`qb#agC)EhJinZNvZ52ts7Gqh)Ks0~OoimwtEJw3s1s4uMQ(Gj3 z$5a8WTuzy&Hz6)|Yn&UL_d(oV90QSum%(*yLzhly-i;r+C(ATU zisGs*&unHHL<987yP~^S#{ITpr{y><*rb0lu1IWTuk)8b zs9-xfEVbApB}s`ap1B$&<<0kwpg3h`B)%1U%UrY27tHD4Y0;3En96-c^n}S%eVvIJ zyLzfdZwLOS4~Z4J#b?W3+G4x12YB1>d|bpks;A-R(m}7jOD?BEJ1jlX>N) zT9$8Y>(RTsd0M&z_~+8WX=8Ua5H*k)u55R0%n~B?=#fEs@eI16m&+@V3l4@CfwQTb z_tdY9O*eWg@z83);FDp2rCRYV3|%Duo%j8>cQfO7|@B z;n#o3_GBCXVYeQTvX16_G=xXS{d{+%TBCipYPl5zC)uo_Iv>5YO}Ql%Q~KjXZcf<7klv+=Cne#jP(2$S74Olc zQ>iawY3#)%<8r>tLH;3lfOV#ffhJfzq>E7=$7s%*$!^D6ats5Y@T1d_1x1hrUhs1| zef-st)UTcgS0~tJRsZpc9Z~QGzg|dya^-Q>IE9NKy?fI#RZAtJUM^<<>2?&KV%$H= z>-~sH0K^3Z`rEp4k5b?+7NYmQDGtjnbU_>C4$ua~VHg58bkoo#z7nXUokuW*tx5M& z7ErLxM8SJbpNT@7BrdG<`uW>-Kqc-KT_BoBs3KMtz-mbnc`Eh+kVs+kD?(H41BJiE zP%hCwybv_nc~}He8q|LBXtvF7JR(N#8Xm>^^^zW~1qtRnn!9{qfBu3D4$Qt8mA9+K z`~}sF-|r;){e~=A_eQ@i`wKD~yWdgg;p)5o_2mASyTF7Sd5aYn71Eh9}jChP^BEKSwom@m8}KtnXP!Ez^^i=S41 zGz1im7p_wdqgh9cSJGdBUQ+u#Z%f5Ebcnb306Q#=h}Z&#oO>>;^k28-=VfLdLX7aIc{?0U8Co2D2cw)q4@<|}T|yjv zXH^7`vy>Z|DCn=U^HOQxW$ah%YbH=VZ@ccj5o_k1F}?-H7{WD~<%)CfKVJPBqMLy& zi{uT5;Vm0MuJW{m6S=O(zt81f#F>n|6e1G9L@gE2I@Kmed}_>r03$`!2Rt=(nKu5I zrRJ3DC#9#r*n#Mp=QVI?8ieJY57dPfam%g|&!x1rrzUq-#RVr~Y+y5y`1M{$9JnPU zekIGbyS@o$G77EgrQ_*;mV)TzSS^L1Q2$_C8J{??v160!7M0Q;HaURi#&MPzo&r*B z<5z(CtM&y9Oe-;C6#a4gLwR`#(dB9e+K%O>!_U;5YSQZD>YCBHYxr-C1+OBa62qrg z6!aOp`99Moi+aWSyIeK%Ve`dW?Hel-0>wp=7M3m<4JLka#9d)=(dSb)5h_S@xjO=| z7jx-+Vd?Ti%-C>Qf6E$iE#WZ}TmN`->P2F*90_q!cV070Q1|^%XTJK}Arz2?TNm7LOYaL=wXKKPJtKcDwnBl@3# zx^Y|Q;e!;!X84Cg?CKhh+V!y9a*3X{4_!dd&=6gn93ZL78)#`^LZu*1Qh|ulc1_&$ zKF{;P?k1Ff1)BzfVz=76W{w{R+pcDsEsVun6Jz^Nrc<4*CyisOuGDl)gEf~)u?hCf zEJrs7%Dv0eQ{GPH-dOnjOBG~@9Q|0l_xXT_{JCgS231*H%y^LQb#=ULIy}d zU5fpHZJHOm+cZ3cyU~ew36o|)`^G#;b3z|60)*{7lkF60h{)~r_JY(UbhpYQ9i#QP z;4l_&%_|i9J&%-|bnX2G$AO3U0a?U>aKpI%tIiK!o#GlO>spPLs|Y~)E5w*&stF`| z*id8a2i zoGd$Dcw-iNPvQ)e*=%LE7+zA`frkeK+|ujreF7(Z0Ha)_x2T0N_tMx~fyMXUlL$Gd zKVjnVo~dnB`rjf5$X5XYP9V$~_7mkbn;)(8f4U}E=7(p3hME5#v)J*xf*Cr$f3JYP zcyd3n-{4{<_y@3}x3`V8-F&=R3Yzj8f$g}kjM*5x+W4F-LULH9?a z7XRZO^^NACB@5pgB6aScx9#6{^I)B{g_BaNeweD2&s-d&^1moW^CjxE+** zL=-D|S#i6-VJ=iZ>IOVXg~5<{e@tu|axwzkj(ZdJ{*CCS&^#|5HjD*|N*AGCB3osg z@8B0Hj@qa2L&*F^8A?Zfi0F?$MVvehTF4Pq7qUzJJm;5h^0j47d!=GH_c=Gu8=Jbd zbh*CQJ;;x)uI`@f0A#5}4aGtPN5i=U@9J3sN9~j$$qeY}CXA5q>6@1?F?Q+*boc5{ zF2>|6T0;Kpc6Rl`$dCAkoU{#Oxd`-3Hm@~m8&a@6b6jm+C++}-vu(urTqCX?zjG8& z!J`E5I>H#{+$6R~Ih&UWhB)19iTi8RCKQm1nSgKsue+|7Z;qX>K>LVchT*){bv3A<`=s|2_f6PZ8K-3&nH;Bw1;q_z6esk*xmw{AKShfoy>zYMr(df zwjdrmI-J)Z_#qG-b#rQm)BUCWQsQt)7uEH({{eQVN9B5qsm46Dm8T5(R8usW=2ZyC zLqhE`9L*2U9JA-xZDrk+Ota5{N@++qvzyOU8E|{ zYD#yXggK4u9yv$g2G>d~^G0L$2T1Lc=%irP-4M-5_Y#&e=jM!u;~xgouG%>0kPx>j zRB?dnB<6K3Ooq4}EvkQu$h`*2%~p%Q zU?9egPbOQLv3W9xBf5qfYMy>6`xn&m%kKTy-A#+)6Eea1FJAZi#qP?}{mjkPT$Nop z2k97huLo|m&zDBx%tR(DeE04IxiqYd`yJ#;(Mqu$buk=uQ7q6qUpZiav&!`iD#pv_ zv8b4WH78!y}blrS^SH z#@r*vUly(HRo~s-4YbD`3Kl&W39iJ9Um)sTerM~zi`1MKd9!#9TYIw0lk%Xk1blR)-Mo>G$=k*oD6tc0 z<2sy$>MyYw1S!yc98*612>cm8ao@Ks$$7EtVRZ<9+N|`f=e=>HV}IJ`f%1GuE>fOj zRGVdel#8L>dnTV{oZYbwZHr$O>Rb|j!n2=Yt<;zEk!~IYDULBwJowrwyZ0p7^;%)!#tsO?+j=dk$KT9>jCLSx&Hz-Q#jz~ABvU+UM zC!l%K4OCCD>K-m6&G*;+6lTy&M5%2{yo%MYkchsLN{?!?`%JsM3Ps)~f<4PqTG6vQ7ag10rd8l1ui}RFq9rVEZ!?W9)k8>&hSF_V zR|=)|TyfF!GZGs|?RTxmm`4Gvs602#t}*`GsXcm5zLN<)5yvE5n-1`!Z^y*f zrJ6oD)sb-{YodWzcLR^sXIjl)x6H~8e^0pGP@uJS^uo-p!H6C~Ewfvu%NR3NV_>NN zWKMDs*2aW|9^1y?FAGZ1%s?^wEhf@-O0S#3!&gVXM(QR^KK>~`!x^iY?~T&g#{{+) zeW0oOipzNvv*$9DGWW@yTztlKbg(@^mS|iG$f^GgG>)My!IPRdrW+}pEUZ7z*sLsSCrr85EajEaBz%S zt`CfB-3J(yPwtHMP-EN}o|4wHY}Gr|n`l7%+38lGoaTM%)AGc{Xp{n2?m z=PvIR=jO18o1wY8mwOAw9>z`|-*Aqx#z3)KWtb#Mp_yI(sQz^Jp2^pfOXioq z*LlFsi^l36q~TfVOV<@ZpE3M6z2KCPB!XW0k=`F@A$0*VETyS@TwXe&gQ~ z0IRwoSld~y_sPz4l=}-RCk_?BX}S`=7flSmOP5FDD&G~c{L&vE!o9;Q^zMLc={L$O zT>fu6JY-8ftGc$&KwWbDY|{o&o({`Bl+ex!twsc6yvjleQhEX^3eTVvQ^9zir?6p{A@7}B&#C{Y5nC9Gm?R9WcMc zebZ(3SS*h11s`l;9%Uc8JsfV1ITC7pF4i{~_9@L-VMFU}nys_$L?xHVX9l=;fKRCB z4E}T=Rj?P=dB=HF9?LrT3PH_e6vn%7P`BioO*Mk9hUB0ErkdK7s;6X*SFxuGPq8vT zdnEBGxDwOwed@SRY4#aK`Cky@;oWMPdT`aSGq0Au#P_;^S%F~C*-Q2lV`H};8b#;( zs_-n8V-pwyqox~7g8R=F1m^_UeGWyWt)QGhyo_x;4ZcQ+lFA|EF87`S{=+rmv3S_M zsq0>pn=nd!`uQF*AvL>R(<%JVp9(4}vhUul2Yx7Dt~|qa^MHK3k~1A+U+Y%Wc1uuv>QE2bAt^8i(*79{CwI2>pDyUHk=<;@_gj zA)qxTj1|XT9|!ERt=acydCrjTEPNr;T+{Y=ncd1D%9@IC&_z>5a+yMJNTqbh{-UL7 zss!f-Yx%&Z9?5VPp^p6TlBU&?zzCBV-KU`MyVozQRwLPt}bS01|zFC*bv6zbHy>RGA zZYyZk&!MbN$ln zbA9q*Dm zxozwfKGouAbszO$(#T5&^V!z=uMK-M(57%HM)Ot#XcY5=ytxu~MHB1|gqDC+`rMTo zUiLq9a)~C~#4noT`)QlaZ~RmBC|RigN}=xNynL&saF361jT!i#;_v&qX0vz}#XOQ8 zUTz$>$d{}KGS~#pyhm}X%i>)pTV~rEx^Yv!jwN2eZCp$CMj8D>DFDLvV}X}3xrC#6 ztE?A0<-H-`ZKmsq)4?*PaO1Q4Jv*Mb<;XiGwxtAK6VKN&h5rv)hhN?RJ$-u|QsR~A z)QBwp50)M=4Idr;0c0_+aPfoTKP+YHJ`4BN&~D)SI{@$WPk?ULn?%_* z=~tG!2uQh}T{;uG3~BBeXej_737a}YC?SVz+bD8P{(?LNj5g&@JleaVo+px)J%y!@ zz<_xz2v5ttOj!p0a`FM@Oi{9Ri@vMn3_NXZ*?=hmnK-Z4a}}15mc-(MPRD+4$$j2t zVWhg~S)yD5@h1dOi7tv|VcLm`jVES{p@sl>AnF;lvrIjM9bc(LJf-D!t*vz5zb6sG z6BEIEi{V!*{^T8<&}-RuoUg*^pMZXe2|alqn1LDCmx+Q)D?<4^2@nPQAW}%Hm?I9z zcW0TX0>0TF_WUxw!e_Zc3YJeaAN>Wz(odUG{8s3?N-HZj*tZg# zz9ZU8Np?N>`1=~$cfj(%#JN;X@CsKJ5I@`EbkQxD6QrSdb4ASPyRFuuCFmYc|53%^ z@Y5HO*#@nO^3lF-DUvqGES2cYRXR{D7OfP0LKw|9F3WGl&C}0(;=?4JYSFfnW3hTL zI*&(KR1~%6^X;Tg%S91lwLZF^bfO6ZT@Yq%hk{SjswKXawK2#}-xFcepVpe+eV(|j zu|Jkm++%3@UFP>+Pd*sOc+RR;C!hmE>kv(r_Q^yw!k;4{<2j5Lr^tS*@@5(8wZU}j z!yp)St1%3fwxBnGXe;I{gcK#I(u(5TY$dqO0qeYi$|G6vC(qolMuT^sEesAX1y_?R zmK5QdFZXKpsXe26a~2uV{(|bq?-WukEkxex7=2E1PrV?SYHeXFldfY0mHf!&tnD+r(Zub}c-eLiMxn@BqhbaY;P_uu zd3QGQvDG5o+;ym@Uc)xv4jbpcZL<0+Bf&q!W^-icV=!4kaN^!{)%8rwBOFM2|LC(W zAfPIuzHmZ=k6+y%R0GZIkxBc|_i_O4q$jB{@wMF4!Z|E*9Kr3p*t!0>a*Zhx@&{|k zHcf8?NBZ*o4N^uu4o~c}beSn})S9ck!q3?=gvObX?zO&LWvvwv1^Uu9MD%=#f*%}- zcJ!Lp+R&!+RsL8PHSKi4c7e(_@nF4_6~S54+(Q5&K16V!s#9KhgxnQP_zVGwD{m(A z5M|vX$nBN`OPAIynKb{a%1=g?6C%+sggxfdKns)>D)fQRQs{z;>3}iAuv6-V_zNO9 zgZbC2+>|}CY|>(v(2AHmL6ygwgBywjzOzhHLy>tK$N-_BHO~N9Ef0b%*@_9r+=Z@Du|uL?~5(SWW2j?|2_TeY8bS z0>y-0Wxab26e|BETNH>Hs00!Te2*%fQ&1ohi$@m-qR+#{_*b{=O}TH)@(qx<&~o-c zOQ_tlX1_dN>8|EctXMC}=f9B7P$xhsI9UclI{6M-%YTw>7dU}xugnt~svBWLA$i_i z=vzVaT>s7JqNd;o*88KHeVSu-DJ9!bg+fUY4Z|`nA=Mz6=clDp_wLN8nK}ss*A9I~ zCA}yeNgrLvwIu@@{+wX!VfLITlE&a(rHm8~LF5X$mO1Cidww(Ck)>FBW*W^*qmEQH zFkO5P+RHSgVRp~#@c2Ne>Ga#RVkXs9#TjEWqJ^^5%{cytXFdeQfhfqehIUPgqxkLH-y#?YZ!10|t2&UXf199B3V``j4*K?o1m) zUyjclQ(O9Jwpy~zaLkDi*lq*KIJrlQ0zQnz`qP*S{u67N|%|181uH_Zs9;aD#3 z>@6&ul&b`ynOt5-S&+TNF!@icVidvF6(snPckhc!#~SN+1>VF!lN^ zIkxKaz5mU`3SO?xW#qM9eAVt(riZCtf27Bx7iY59bsXDCv~(#*9A8HN!brPJ+V7Tv zaBnmnk$s8gLI;bWtHAS#h}yS|T>vmji&UGe())Ixuac|oYX6N9{aU$hOdu{Pbxg=% zdcEKyX#DhdvZ}}RQCerCd^e%&!IFM5&TT<1}YA2XDya2Y&GVKv&yQA`J@l zf^=0mA5o4xtbX;HG{IeflS(`bAMmnq)T=9TysPbu;5p6jiO=ows6|%pk44Q$8Z(@cCH?OP0~Y1$kC0DrSn1q+h0(q z({feAcCL2le*uYt>)OP>pza-j%+$YNmcJF1V1Z-R%LC% z27yb#SY~Vw_`1DR0fgN#1iU~V9_rK=eWU!V!V&5up+yO%&3Vz3Uai-zeq`tCR+``t zf@kU4TXl zr~>_s?sye``Rqd_5j+H(0Nqi7Vmi9RG=q9jA13z%&6I$CTMl6OcfJ(u^sQ(DkmXA7 z6kFTNwQm%;-EiRiD4z6~>8X_%)E_eD1VR~J%c#95Vh<##qWC`k4^TR6$DKQl_JH*L|E z(bhdGf67is?U%Es<03#T0~^h`f+P*dBSy~tlr0ozO<52(=&TG{s-x^-m4V27 z+6TpGWwU58)b9oH{(`#hbFEfwMLtjeLy(`86-jDOo}k%fs=lRLU2va=1atH|jx-d8 zT2J}9a_GxhZvvIxS{F%Q8lLNpC)D1QHsyO}dQowdci4R>eSZyClWnICb!;ug%ii zY>SEQ$<^a*UsoDOyolG`CwAJq8R1_l#z*IMU4966Kfhu&v|t|=Ilx<9oJr12%J6YH zNd7|JliF}q>uxceeatd!)6>|yDu*l51V~G~Qk%>ucMy<<)ypS$Wv-H1xrGba4Twz< z5fY#1f1+p{OV4U#@0>i+2%nV7D%UnW4tLY1AO%vHb=h8Gyo-4yjQ;dhop>mCOY*6H zVaAMi!Det%!*ON4C@cSOrBR8eQBQA6pesK-Z08L8$uav^{AvL-eeGE9+iAOepKIr) zyOs92?fNf>PLbk^nz$W6frJX<^@aLnTE6(A2I?z%|Ee%h4CVPR4O(Tx*RQaOvI>MU z#b`kos`MF@;?kkYfl6!{&kKL{Wtiv|Bnc6OyX0&vrdsB@(Kiz=Jf9kVA%q?eK`flR4 zWa+*5O_t2*&96{XpupjhnU9;FKxmw-B@3vG0QS4K3`t^2ts%_*f@P$n;O6_&R~Ya7 zF`mBicqP0eOoqV_-e*qZGe0yCdgY#+Yuokse^|QexTv15y_Bp=Ez%{W#L_4oE=z~7 z#1adrNOvqHC0)`D(z&!CjfjM#bR#9*2oeJ7_r3ai|Je`RotZl`cXsZX=RD^*N6Z=Y z2E<-Bc#Yc!ly`C{$&%ELTe<2e=E0Q9CV~w{zFF*XP?xi9sJaPbJ16@!UBy9`rKx7a zdN#HE7vvc4VY2xH41S=(+@tn{hSt#g)m{DC+2J$(qx@u93r$A?_St_<$Ca&mJxtay zzrQ8jX#|4HIJ#%eOPAb@=;SpmG%Q@}68rz9#3-mTr^Peud;CJA+J=M#&<-F<9>R+B zkB+LpKU{DvyKT9kb$(tq+j?6~Wl6o)$>dR6^?{cl>+nX#AfIr=&3rEq1Ow7Mp1Th|LGU;2ql)$Wmc{RpnJEVAzN z4AUH|H?dEai_XUKma{!Zo+wQ_8CB~UM7QTief6mEwqKcbA|@VQZawOeqm$UL|M8Bq zGXhb1WH8_tI$m%hUfJGB)m~;jEJo~Ak~8>2m2P#dqc+2@y}V+wu52Y{SZ4~4Ge+h# zy|LCJkg#vNqXk3nHb+J<=n_FBhbXZVF*L8%p*`rL!{i!KJ|!_%Ur}EU4-^wm@_%Uk z?fZCsli7iEpJVnq23-M2%avGKTG}@sS@Y}Z0XWt~Z~;oNK&$Y1^w>rK>Rt2p&#GI} zUzIyUxLDK>4Lj?5o>|g8YBI{x^JG7N&XA0kkw5$StJxzl5&3Nrh8u~yW#qrxMh>){ z@ICgyyDBnDlH|caUVyMk38O)ODaCN~jiol4d)p%_Fv-aD!KjUG;+e+v1J@qqH+36R z$EAYxruu;3^|!yN@=SQO&PsE?zST51qU!;^dEwIq?IqxE8ttTISH@=|}2!8qT z^-mh3H>b0}+sNtp$Gm01z8%K{AcphJLEgLTxx^o2Im!FzFsa%7x>Mafrn^KVs?161 z#kO6TsIQ6HK-4$;`aDXPXM-t*^;jpa8Yh=4jQqh0Q;{@$twKj-uaZ>9vk$ zX}dc=N&j;R$NBRT{SNV3LPuCfTTR|gTjvJnZ|0j?pRF>>5j^FTF?r26?qPMQYi7PE zd963->&=9B%(!&T?EO5GPepxb$GV(%O>!wHx;wuYg^am*9-j?d^NeA8#c!QgevelF z#8jW$I6nJ5R{c}Asu|k6XAA%%Fm~t3W?)PxGodH4zo}+DetD(5{%U@^_j?LzbyVwn zCENVX&_wZg@h0;7)Ik8{f1nbpqJsa`(H%5=ZMWLRT%a7%`|I}Hz-UzB7}>m4_xiT% zN`q`YU?D3kYiiaXOuO(ciAJK-f8^fdcP-WhER2CZmcE3o8|{N0yuq@OA-(3mk~;`2 zl|R%$rTe_e7UK=(jW6~^@~HCt0|_@x_FhydRaENK%p~hC04ikM{mcvZNo#Pu897L_ zbyF-Bv0GK9SK`-Vc{-KqYVB$B-&rZRQwWf3tV$H%NDy#74rH?wj<~laSgH-7G~f!O zg9law_N}ZCUf%zo$>w%A@Z<$xnsx4M8RwL?YMC2NE$CFP$0;pDzubEh;we;*7aRL( zIh{14@6n98t`voR{+*`ZRt?^F#%%M+UN{&szp}Awo37(8=5FPrZ19v#4~oNMNa`Vc zP6c@sYpd1tChaYs(^KcpCwO8HeHND96?-zz#s9VjHm|&i+6w+2pPe$@kZZ-U-8r|u zby+hY2(iaMZcF_?&{WxNx&MYB{bx^J2|%0Vp3d$a^IYMhktJd2ouFHl%=QSGHy1`m%fr~�dPxllsdfX-SDt z_j6{%b>}Xg`IHRaRoS0dH^U)-d?O$!^e}O2aKValac6V;oES8yn(T`IiC&V z?GDXG^`FA?+_8>qXIpesv(@KU885Qf*o8BRHhEclI{;U0_VvOo4?U*#S+y8U6DHj5 zrLm;bW7+CNL|txPpzp!$&iHut-B+>`PdqqXEdE?_%pV_o_#|uf zySNri` zN2B~_k=N)alK#VcB3G}B^OLo%QtaNxDkc%Wt$DxMbEh)I6MW?*LFOX9IuQ_8lRETK zbFYn8r>j)YQl%_oJ~hTYjx3|GNC9d4?2W+cqLTV^YbuMxI9FTJN6-hgai5*9VE@Ct%roPuVVVto+t=H;KKI4sZQLcnqSLsyI$$1Q7xfK|UZn5Y8^h9d8=2_l7c&F*B)9 z%Ax#Slbd!o84CTRaKN1tuhn$ZCzOd_9kx{y<9!v|g%O%_A%eEw)m_^Yx16+#n|%1; z+VP2g0CsWe4zXKx-{8h-h~ z*>zvNFxX~&P)3!QpkHE$@{9~a7Ww?4e*l=7H%r7(FZSUNntSZY9|dB=e#6N{8{({= z)+Qw3yfUgXAnayj(hu|ApR6T8PY^5P6Fayzb3Rz}ZtbtkJ#6hSe~5{^Ly6MB!dsW0 ztdn(KtE~l@9OwG|vtQx)=$|#{x{-p^M!u>{wG5; z_>`=|Z>Qnq4kndhxYM|JN;8#qOXS$Kz^?{CpdxC>5*H_BDGn_hIIRn@M5&Qe@kEha z$7lUB9Mo3R*Z-lf*Km`3?y%xkkSiLFDscv<;@fBs8)q~zv*C)Dw^G?d84_Ea3Hiu- z8;{_Kt%jXyEpOu&4+9mk_yBW75y2wGAWb;WoM?xB`JMR%tN;ROMN%s094iWE0-&}T zv;;8VLpe}Gk@<86Fb))fws05@ITakYI3GA$m%~_a45*5+n}ldrT}UV_*bz>hUlAyD z;I7fc7|SK^*WvJ?+IThzX*d-ouPqoRVkuhv5P428pNV#BWZ~E4Dn(N81W;^u{_IS3 z;M>yg3ubOINK%rq(jVQ=Jf1E|zkkVH5I|VCkWd!A0uXGA5-uEA zpg=HG@lU7)1y&R;heM$$3WzWjI29L|3dV*@2@b;1)58XGRj{z(58;+02(%IS8ijb< z)5;kq9oLAp?i~?<$bWw!fk~_=A&Otm<*7wfznR@6*RLen$(08LV4XAxkFo=J3?+d8 zmg%s8hAO=)t;Y1v-JG_}tkkq=;&&BWP2MG;TUrwkYQ)|cKArTe(4Hp$N((zBDeHMuy7kD_c z2Dd+(-^~1WoHm^x<{OfQws=^mMA2fQY)R^!%RT|Ki;JyOXH8-tf6pO0hBtiQd`Xq~ z^;>qdDjyjrIVMAXK6sisEvy{pE}HR>&&+$wK484gWhI`ktMRII#9tCG*rMTdyJO^3 z2>yuYH=(^zf`uLB_h)m@qTl8p5*sy^AN2}WUDh`#eg0ytCf3gkoms1*aWJk9ypl?Y}0D$BsO(xF1ogsAjJR)9VfeqrjA`9b%uYPdj1r&lNhU z^7;TvS`V69a-dTHdC4r*Zo8ktR4%6Zt=*Gla?{VVQN2bGX=@%rR766TS#pe1P+xaE z@WXY+!kVS!#!**c@`8aR_Wg1><5?4QyO;6Ijdo7rnB>!WNB`mnfT|x`bQv6@StIq@c=8q$a5WwTLL5d+JLN3W6)ds3$yyqatD6LfU;(wanVLFg6Y?-9bSJ1I|0=+wle|D@aWpn zgBMW0X7+Kp4hyIo3*wqJZ|@|kc^SkVmwotnSOv-nlp-dzweOLa z?vr`DN$^#<*7M2HBWGjJlG6P~IxVA#EeFqy(A;&U*0Fd$v(bdQFG<34%^wouNMlDl z8R3W7v)fLo-ID4@vfvky5+mhGRj%ERU%dz7xHjz3L~%^K?S6f@8_9JwdpTjP>^|A( zxQ;3@tJ+@OHyF9#Dg8R%t!U227Y^~lG;NP&MMbF@C2AolgY}f?O&&P_w<(<7f<~A} zx-*;Eq0PTD12jKuXekN?&IIIVQDCZWe7JB1GKCd~+=M%nOHmC5hF~i~+1Mf>g&Zg@ zh_w6dP#9SW+ymGvD?&klW|U2?eq#+L66jj?4s^D$nhuk_F%H6ckQ+!4s_pq{-HGMB z?FZ%}y>!iT_Cm>A?3L26uo#wH>|@RBF}}DG@fb0N@z0Kn-PNB3`r);2PkmIP?0+9; z34R+7A8DeKypbhU=2bfEANnZJ+M{PZDU!7);$4(6UczL!CAP9)A#B(o9UIW|((%w< z{=o}#qqKNR*rT1`<3$g2-vN8vw_pk<@i=qKWCq`DB`+ynhqob`I~F+8KWqFe8E>JN zp>@4zlX}zG#Qn#7k~v)ro=R8Y5%tI~3EkgK=HA^K|G8uwo^VGgxEuj1K!(0D?D!he zIPonyLAc25tzOHoF5<4SIM@W^n3a{#X{WOsWdKG#+r&*llW6tToBj*;HhmAGdM}R( zg*{8Jr@dn9{j^W$RT+&L=x(iB2(G7k8QFdtM~LUeG+Orx?57%&rXq*>CF3%NUBX30 zDOzjZI*q$9Zi@i4TM0Ml*t5~>*Rs_Gds(SzeGA7Zhsh?6);hv;iDID|%o4-)Pa5%C zgJSn*obz$ROx-?E`^6p65WK9p$7#7|+B+b(rHx6#vgwX@DfmM{C@OCKbHb6=r?0t< z>5RYsGWZKXrsBM-;0mmH_I&K4TP$g^<2A{$;+Yncjon22hb&bK`=zDdJVJECfv$wK z_Vpd&#o8Xoa0XAmBaiC+C7mN0}?nEy5MXT(VWvPCd(vIf;1sUyIBBsG|JdMC%kE#!c|v;0%-MUTSSVzmzD@om^(O%#}T}7qIeu|I#b-0r@7b z5iMVA4GYa3r%$6aRiYwQ_^f(E`2~o?S9ucc;xi9qt4Q`#`naurdUMw8_(3(g;lxlsmT{hZDCg2l*3(wCOrR~I<^kL)e3A;SU4`9 zoC0^d&<~?u&O;ylY71Zg1MccVxp79isKcrz~3t{hfFvd$Tf$`DAh-*KBOz}YR zjWK&Sd4_fmeLVg5>?=Fpul8@;_jcURovw|S?VxM)>=~`^hbF?C{j3B(eZNxXc);iE zedsYrf@YF8TsQR*KiHS-vS%;tCwwL1vi%_fNV}}n)x|*jY^O2t-WkzlOeq#Q|)CP3Dm zxJ-%l?{6$Hd&2EK7vrs^Vzix9$86>ldtLX{kU4%8ef|bx$EvII^9;pYFozOsKt{b@QOi&y!G~Z z9|ioe)wsJ}v;E`bxx_+;2$HM_sF zvMsxM>cONjz8C4}-VZSBai8?j^-_QH`Uaou=iLt*hq3vmB&8-Z+=DXVh{Ypchxt&i zrgR8s4q8?Y=E!uOx7;UA#iFd>;P{+n1?rmmTc& zd9*+4Yu<_WK1TYE&R(4oKJMFDJ3KM>U1U@OG|sf(2CZK9o}%Ayf=&820wm@d%3Kb! z1#k4LMI~>-D|rtoS1A~$9weUgnx$Lk)!WnBddG&gw!7UX`!!p|7Vq5{Gp|5UMWKT+ zUP&JA^&p?XYm+PB6LGAW>ga?>cgxf$%ooA5z4}4;*MIhc-%IOf$jKi)OW804D3lA1 zWL3b|s3-)fwd(R9;RtOAK8V0AnibMet*H%BltYl?Ah;S?9#;VC8(LVYMpZRHric z|F}gkWYfX;y;k~sImAs$% zwT06iSiqBWRR=T!V-f;Bx#WX|S=|1=Qjxkf_E!mlkrom*di%G5yvf|lM?f{5?E89v zgL)gd)t^-3QlO=s^8#Q+Za)H;We#SZc#6e1aUtTT=Rd38m;SAQ)0J9gxAXh(UsslZ zmQukkv)wIp5;7k%rAFWq_PXl+N;&GQ{DH*qL+ z$*Aw*Sjiu^+^fG0gI!cpM{obOnDW22@IrCyOy)Yi0QG%W#&qyPwK2I@?`N)2SFL&K z*C_4}6XUQ*D2N;f5Dz2}E&x}A36~>UG}u5v8f>AhdWuLBR)ry4wh9=skS7HnMZtvw zX%)^yFj-WljsP=Mbe2MI|8H(7AXKBbvt!!VYPsj{rvr4t#90~%Mtvv$b*21oLBhMK zknOk(pa_cI7^nlgw{u6fy8x4W@wa>}Fh=H-d~p%s)}E3_z=eh!ZlG3$ZYU|dwbO@g z{|T%}_3!-Sben-p)+RIepKxpW{QZQx1Xj<-XZ%B5T9s}8HdC!Jm4!nqEZ6*J$1l>>`rJ2#&>A&6e{r6cS&N2fmj{U!dwEo_WTaS^&Ex*QorPL>W z2z6Br^aXfGcHb}of4i&q??MV|Hz>3Qv(f|<(YyLP$O26g!PfW1e+Pv9*F`->I=F$j zdm2ze_kZOGiDyP_H~xV-#s4~6TPO+=l*YwFTM9?&m_bPAa)MW+qif zM2|6YeJ1d+ctsVr$PdX0AI_{QiMMTSg}?Zu6={mwkIrS9m0790%&f*Noms>NZ8q~s z4D2dNr#C$IDxEF z^)#CI-Bs-FHHQny19M?1T0$0g8TMEQ8I}kqLF^_TEp-VH-he~P+I?N!8Ka7?V*E36&iYBu3PRc~G0WYn;5GB5KSzNe zdgUrW$@oj0kM?AVg=prhu_W1xkLsl>Z6od3W0Go(Tjr)|c|xP4eWZeNCSAJ^syP%V zuf0ap7K`1~QB8~UE9@@KYBQWpe55~&?6|To*M3>yj{8_k5cRZH7a7O-YaUmA7MNtS zah-roz9;b%qIn}CvhTd$vKf8LsAiImqYhb!GZM#rh0 zD(pA~`;R6r-+rI3r)R_g%!OQdBx&vfk3F@>07oK_tL)48mtWA?4Eb--9N~T2c|u>v z?6cSW5qOhP8s(`dmZ4|>AqSY0lpMN{Z#cr43f-Y}dK~0PXqa0*mv*S4a43Nu7!YBF z6+$!NC}au_ZWt0-!iD=+rKu1ruZbFJ(FQ5%!BVIML)j>!3tN#;fbKa2jSeonhrOo) z8e}0e`flu-9(r0@dZZh*w|g5|QZnV#>?5c`?I>$4SK7rd`xx1pw8SfGzZu6EQs=&6 z<)YM1!enjI*-Oo}faN!us?c#~*9dNOJT7O#7KgSSrlDu=`p)6bsWyg;&@skTk)qSz z+L(NiJ)dsJv{pO$OY%5X^H#s1Xlu9hlYg~Dzd*W*iOfgAz3s%1(KuVAS4@03W9k3`J@+U%;}t$47<)T5cdlZiw%br)BB!o7&0)T@%Gdcq zd{~1zTNZ+J&tQH$pIOb4A!+%iR%MtmG2)}_X}t9-I+7%r5x!N1NEb3Eug7T#U?#F) zM&r86yM)ztq=rU|6e*Hnv@rdG-e1ZbWfjZ8VbsH(xP49>#-0`qB5Vntb+R#|>;3PJ z9n56|NMG7c-)0n<`Q|P6&3YwCVV3I(+BaYQ9P~m5NqHMw^=8LZiMkSb)bWMpQ{DKLHVCo!`I=5LUDI8qhhfXBxwp!fDW0_iW zdEr7z>YQSlx9g2w^Xr=rkR_(PWAF|2`FrCAA9_-Ja}ZyEbM`rdiPq}FS4=hYlIo1x zSCYeT7`Jn>?pJ(EOCkkh<-_H==*>WzKf9n)i{G+a0c_wyJ&jAznmYLYo!uP|s zIq`d&kNyL}BKYG+u#FO2PwyxEWbI^)6W^(uNf4S8d9OL^=#peuAmHcP;^-a}m~H88 zn$_IE=NqxtQ*DRNpUH8Px)7mzndcyKK=*W4RGy(Ca(lkJFZbxSM>z-{Q+0w{@Iv`= zCfMKkS%}VtRGUz3m1GG$a!iw}m$>%%sB3QVtz72hBTTWq+nkS2)%v%raLMm|R!LoP zTnk(G(%Mun8%QsX&C%W0LLHxD?NvEJq|qr`?+U=tfNo|v7%8ELq~K0<$=Ab21hOIs zT*5#a0F=prq(mV#3M&Ae92OiD)euNe0YSq>4h3Z>fbmj@^eMr}!U`4`Wp@eK7XFv# z^-m-s6h}BR5ML2VuLjcwDRi^&Q$O)6if?W2ZVS0FD6bXfA$>wEghkb9(mnIT!#`8# z-WaFD9U$m-?Z=;;uFz82d}%jpE;Q7wG5}aeJ*4LIYxnybB7}}?@uATBW?vs6()x)G zpk0*7Paj%^D^f5$h?hB6CN{^x#Nmj8&I!C$xVCag)T%@-U>?Vc%wFs--%~s^e_$^f z5&i+nh?l*zA^yO}K%xgNRXG<<_>?b%*b&GvZC{%H;*(#EJ#b{h8}*!M*~~4jQAnW{ z>U^JWsV1qK`^tSpmS<%8g09>sTzr}Lv2~W5zUc5fNx`8paxeI|*a4#aA7ucEWcb|U z4^0PuiP0rpkvbyvZFT)z%uJoSPB=%Ft~0TFwO^eVzsICm`vMeE!SL>><#eSf{yEZ%;rYH)GT+rJ?W^Cbm{kX7-({y&U~5@kKKapP?R4BS zbTepDMXY`3*xmNoH(PP5`F7X1#)K?t(WUCZlbOo=B-HIHBaRNf$P!zxL}Vg=rt+-o zOO5e9jg>{C$JZMZ$4H@ZRB&jO@0CQKf#kB$3ZtC8;M|>WMWw2olLNYTP4qcpX&*@J zvfYGdE1mT)ON5sQL$(qUtnvXJ-Dp8300wbg5QX13yPwiEcMssf_`#jVkwf=GZ>1m+8^ z$2?Q+7bVWM_lU(M<8b}%eq&lr5Q+8|fPRfO@#k_qr<%B~9GO4aKPfBMo>hu1F^mNi z^p&Ui#0)#gR~E{WXqlNiW-LgAPuH#QAjZgr30 z@x2D>md9zWHE}jeyOvQ$mQ!zdOZv9 zKirW7l#Snou&m$(o|4{YsYxFo{UW&MBcoqm!uQ0K{&~_@&?#2vX80Mz3ixOydf7--E%$<{hl=*;@1cVFw`6nH|?5>nn!)_m#`65ri`;M zj;)bF&$Y(#Hjx9}!{C3A4Ib+h-NpY7QC)4KZjnZ1Mh?@C{ zK*7~ibfb(i!Hm1w$b?fPczD$U!-T^ z9TQgPsawCkzrG`W@t{T{73}V$vNy*ziLF0B%I!}^sJ}Iwo}Z!+?cLQ#$~h$y8s)de z1WD1ID$C_1WYu9J*N<%T)0qmJV#7Cg@I13Og4TppKkchsS&Cvw@7vY)8#aa-)X)!2 z$b2oU|K)Xt$Np}d+EOO6uLj<`V)=tZ_T>5G#r^yBPDUPBThX*kkroke%h39qbdxv= zB3_H|k*#}5_G!3`o?E{CtUuL0lhCM@*nX{=DbT+=>gD&qrLM;5xVY98iE}2nwQt!wZOX%y0mm76iFq zv?WBi6g4zS#SKKDK|qm_h~NT%gh=_2TqjUlI1;x+umA$Z2K{q}=yCys5k+J%N{1Y* z0L1R$vbF1i!H^0TE=V+6J~kQ)u3$mnD?$sXhBD#8SQrdSE(mZ&V3F`rUG5Yvc=Q&8 z5|aOSTZ4q@0Z@=7G@pt}kCjB+;BF`ovX2bI5iTsz0Ad4qbXZlQ3&04r77Z3wMYsY! za3wm}63A{E#;Q?ms0)T;HQ1nG0I;C~so+3T0VC+fy_cZ@3yj`EP{MWe9s+!sz-qZ+ zHLOljVZ}GF2Adg_mSQP-5G+YrEi_8RUFccyTOsN+J1zbl4 z;4l!7O*Iq-;DiviATWwbgH;9Cq|G3LrBtjya#b@s4Xh4ND7+j8Vy4$k39TWAhw@Vb z)*PfE6@djumjVON&|sl8094okix6;wvv32%DP0Kgg`P$}@IR}b0vH*}qQL^F<^UO5 zsVGr^qr3#iB`Qo1V3Ym5^mp?w1jf(S0?&jCMgp$}Y+zKV0zOI+0X(HURN8+_kV7)y zdflMNf4XBV2nt9cCB6dCPjWrDBGnKpzXA#oNT8?7rIQei54VG{aODGzcc`U;9!!Tz zzlu8)2iXvY!2JdsL|GKwfX9S_K_l4M3czp*t{|{RWePZu3IZ6lJfR5ULIR{P8!H%* z4?NZ)AW#sf^+pp(1CYTG_ymHHxRw+U$_$hqB$%xL7$l%OPY!{y{u}GR!2k^azBW(= zB^wJ|qk>G|C z;N|1c))Nmzra)7?K>CkBBLNeS?MqUm!`NLc9N-yi1XkFu>J_y9H>zv2h^@v=s;t zf#tx0&qRT7fi*;qh=d?A6#!`pZDf#`QApsBEOc0QfqtpO`W-D-k$%~8xM*=^q=zE!PlR`5+97-UG77%Ar3jC4^Gf_ZA zI5`SR%*M)vOYk?alXB>9R0%$-U}PvnLMMz=DFw$)0lym?4bo$^>keh%Ag9!$4~`Cn zD46G*MKEkMG`}Jr1yUpj4P~MLL8+9XR=7q! zyaEJ_9R*E=(!e;71#lER6F~)K168o$0$_mh089nXfa?@mB0>p-%Yk1~Whx+XdPn;%3a-J%6Uus5TPG4(5g8bS!Yu(I z@&SK@ElN=Z_$8KyxrA|0X|Ms>B+$?yGn8N;8^C>G6?_X!BH)lCg>KC0^(HQ~{(Il_qyKB&ASX-4|1Z-FS}?n>XLcwJAap9~Wf zjf@b@u;&kR^J3o+ItG)g)_#(|w48N+5J*+FWIMb4NWJH#VJzh749`*;m+4C-#g%&l zhUht!bwhf3qAX#psQUmsUs3qI>~i}XIiU5r2PhgSGw+Z*mpEGOe$sv}Nt_qz6|u&u z<*&HI=)5Q(KV_tEe3NQd)lQdHRDuc2WuaaF`D;?8w=Pe)kEl}qt5;|?oc=OzZjRgL zS{=^pmoL)=Wbxji)Ndtn(5oZBGM`%2@^Hk?pZ08EvQ*AvHu)8Ib@jDh=`EKv+_4K$ z@+>#Bv$C2ylkWU*k~@CcpD^-vSY@xhccZ`XLO-*}C!wsZ-jaioZ zp|iPhOmc9ad03U7vok;R_e#-Eo!3eoQmIQjlNZ>nboF+E`8Dr2gKkywf$fO!cGeDc z6;BzpkTx?gnpcB7X;r#r7$j$|AA_EJuYPW&xGVKD>&%DXL6r% zDqEbjGvDdXVxK-5rGw^F`3`=!XW;0*VwOkWl`T2g8h{k;GLG$R#}_u%%!trW58u=! zbv}~zf5h^_eawcPV8jgcGqw9{xY3LB;NBIzXSM#TvCo0&U620EQH3j93$6P$wd3F% zz^E91@n?R?b+PqPKsc&h*lD*H5uY{2CB&06`dcK#T#z^RvPk7CZZLKp1@)kdyF2)- zvfsBHS!iO`{NiLuVw>p56Z^+!oj9jEvRNRtkG6JfWr+0aZ+x7}(975j_j-A9S6_4U z#r~FKdnNj-#wGJLG5)}i)wwG*!KV`RwDWZcyJaIf~$#@0)20yIDcC`D_`lp)*$F4IsfI9QnTr9*CdSj%J!*A{b$81=XT9P{d97UhcJ8#} z%_F073TU3M1<00_&sq*qvo-4@F8ihVmlp`T9-gp0`Z}yAnI?$EZ&AU+P-}jUaN0UCT<~c!ZXbNF^$70 zjz;ZdrH|47%{&|t1K5g@aw!T!AT_o?78pK`Xg+WScx5PRgB5|@69T-q^4ZJ;0m(ib z;0<*z5_r#5MB+w&6D?387cGG6Y3s27Iv((#yGShXnnalCgyIMW;pm|>3UE;HI7C7| zcPLzsiyUZ-14(X2q?Vr#M&iRY_|({-6&%_)+VBcW4$8mw&NpZfIbh1_!eCSc3JP2b z8u=`c!bqZ20QZ7Lv%uI`Xf?PZfet|N0js7I@JT5OX2RX$ynb+J$tGg=-OMTXhk0bA#PWz8r~CZ_KlN(egjWRg+i7)9>eAe2K8V(Db+G>=+Diy4H`kS4mt* zSI_$pN-;g%V#)&YUY8=tlMQ?jBXI8u^%G+H$aKm(9J}by#5cy=*jXkM7quCW`%@}k zCP4E&i2IrOq9MK8)Q4KmV@Y$_8F&a+a@z9wrNdam;`e&GHm(>(V-oHNxr z({Ck$nPg_^HqWm3PZXn1gMlT__m#bGiL|6lhT6CPSj{Cp$f{88bY$oC9{sP~!-$2m zE9gFT`QA-@$9p;LS!Pjdh7Ae;eayJu@8KT%TE}?%r#0adJtT`T~gf!%7;oE$8>6K8QSHjjWvMAbydZFz_KL20yn3 zNdA(%4s4yd+g`-`lA@VTasfR04f|;i(s-L+cAuQr4@U6EV z8-Egl{exB?uKLlQaibaWtZUU+F|NdLtzl@Qo(CEjRE z9q&KNR#a=4Wu9YbFQvIdwyLs53vg_LKWVv5C7vI)IdSH0)a;XFdE@ghw-whnyEk$8 z4*Fg4DsmWeDv2Zw&nl;l0kml(|idLWO`{DwCCiEAvKVg zm|uhGtE%nC+z-3{{A&0(Fsf7_@ak1DbBV2WZK)y6NjgVsI(2Oca{61}aAVP1yvro= zsF$+yC1f$Th6Y=+Z$@M(oCPetU751$rHQS&oT)32XsB_<=In;{PgKPfB#6Ja(mWI} zzhb%WUzzMIP&;hP4nBfw={_578lAmmdx!UDB!zW5cQ;QM2rSYv2#2XCKn=@LiMR@G zcGSI2?muv1*V{QP90_IS9X=P+2@7-irZNh1L;eFPz4evcm$^RCXb%vt{X@*YJlA^s zN8oLztj}kD*7(8eh7}+WJfUgLWx6-H)dwrQxmn8?GP|++3-swU{r7XdHMzE4CAs?g z+KGod#D7H*yi*da z`H3kz0k$WIL3quK|KPq>*li)bhNt&dV_wet_bOpq9ZdBGccg63rR?L#@;3_lXv!~@ zj_f~+{j6c4G0bI(p;@qNx07Rx$!ZX03Rn4>V8kPN=xYDYrv+*d=UYVYTe=aq6@R=c zEvcdL`nk~AF9y>o!Vyj{1esHqnUwcMkB>G zHvw;D;$c}iuEc55|AE3>Fgfkt77ytQ z^+pjTwVyAheia1M&i?#Z|XXe{7NCx>=y-e!q!X?@TTF zHPIZkV^*wVIBh|?W57j(c;;!)_ks|=hh`5^V%uUA7()~@z!B^6y%Y6$&-fqoD{8&8ZD4+LC1T&V8g-w@@TI-F@Q#4`QR_UJ*2Lq9 z>Rr>{W|}s!ZO6H)@Hpiru0uKYC962YQg`3*E8IC6v38;Bm55_mqxhBBXRL9jZOIS3 z&kvKTp2p;vx$EFuLIy}z(leRC_N55H{b13ZsRzlu1D`Ih;+&`mwGM3;{TIt1>ezh& zfx4omFJhZ}AFZZCH3!E6Paf24J3nbkt-qgX$iA?Xs{bmsH@(K5;>+T@$A_^-Fr8?I$a1^JpcNq>Di&~tixIeaB{UM;1ZhZ^s_*qU18tTX+gD#ckfiC=49 z%%3Dt;M{}DTsLAKKE6Ij=5Qr?D>qiPt8388Uea1T#3N~)Gx-#)ay65re7`2)&fs0w z{o`GVr1g&WMx}B_6S10)I(RbsA67o5%eK#VU7B2p?MyIKSjn7>my!0eXOxokOhD|+?IQt{?bOLEk8 z*zvFtt|OQkYsdM!&3@w6QR+1xxBqa@&UHmC$Ca(c4Z9rk{!RR--m~{#aWc1ZC=SYd zR+B2WMwNYw2--EonjSq4#mTrqKku&*_^8@LipD~*qb5goK&v=)x&Ha8_ zhi+=)qvX1D;jhJRJF8-W-xRZ|j?BdG$)uGX7mY>UQ#1T>BgXsm@YTZJFRv;)bXxn% zSNS#ONfYLms#YVxKd3yP)MC)I8(x{zM0CqSZ}GCX4ozC8Rt2~OL;{m$O%vi*49sES8S*0@%^0m>c)ser#QH5mx-E-X>G>{dZxSw6INj?T9hmL zR81mJ^k*(9ufks5it+>DI}}l1K3A5_G8a=YAmX`-+|J4SjEGK z-)ZislE3i%k*+dGR`T+R9sk5q&xGT?rx6T(5gAlU%K0jvW9ASVD!0AMFBa7CnC7?m~z46vraLF5Qf1*;xDj6e-f z4O#=>sYCd1fW~G3V}V7Y;FNA$$PyTp8a@sRw*^5Cz;yt21;A0zNCYgD7V#Ip8=|xX z;375v+5t}Ukq9#Y3Vo-I5)30yth^h_N`;^RgS7<#TbK$4B*N9es$t=OQ6a$$xL^=D zgaR;&C)m>(iS!6JnW?{vhByPE0S*TrcFl1PTbydN_ z+kKR_V`P;0_W+>UPeDSvq!%N)9p#qp=KFls($yO5OP3p*fr%Q&O{6 z^nVdjBn0UeNh#?D5v03eGy`Fb9$nJiNJ@A2fKk%jqhWM6(xCpHeV>0| zdu{jb-Ph+j=e!SCUSDML`lyjx#F$O{I%WN8PXHkwWe4aog|pjU3c{ zQsb~XlKM1yx0Vya_0Qsl{!sl7CGc`Ye<75KL;I?(2}?krmUNzDv#MaF;5pHu8M`M~NcC+>`8HWQB@4zJN? zmm2sP)aDK5dY%lB)^+N5b4V16K$Il=-C#T*c<=4>rW>ST@~`v+wM@allatiQZmTI# z%Rn%eW1U@#OSf$RLk9lu#Xi6isW5F&iEp{FEP!6?5U*QRS}+p9zT(>8+q2fK6pSS- zo?C10+EAR*EXR#?f)hLglu7=~?ThtWK9b}5^Sx@hhCkb-&_S*;PkU2o+LcZw# zNziY{bpQjHD(=$dbf#<8l&-vy|d@=ly(JT6Z zZn7GDN6kjMOoEp(YGZXZV%pDulU%ys#?6LbwkGP4VAFIRxWrj9G;%ju@?^q)&nd<` z{6s<7uhhs+R&eA7hX&sJJbI-_g(JLAmd%rKxW~~aB;Q7V zBj0nn&e|bcm7ed5kBUuTNgm&D_nH#mC8;Bxb9DHs5F4_dhb5b@L9!~R*Beb0O#GC?DV#G;eR z#JPV2v}T1?$|ah7btFSw-vJVdvG>-Uu*N_+@z1BT!{Mw=T)P%`wpF|}r(|}4uMnN~ zAdz$4PN8qohW9tyNBf1KX#I`7 za_dw44(;C-Ys7cR#_Ys^6ZRhPoE|LmoU(cShWp0t7%kV0IIk*$tbV&A`Wac=glzIb z^D9fBN?;R~^V-4IA-Q2+%LZ?`Lcf#iuuPLt_?i5-&bwk!XxZyC8Ae_Qf#bmQWN7WG z!h11tM%u17gVS!`8}6dB$`@|OQl_y>$GzEc%@Td8{6>xElm^{6n@+CpCa z1*19!7O1E^NP6LR1n(3DG$*z6-wE3Ud+kLXP@Jg@WAVyCwsn*io%{3Fku;#E@#&DXsKhe}GafUHqSa=Vb%bNHh*0 zTY^J#l0*H6emnxUVd0e&3%anhQr%cg7nyVs9y)lXH1!!$my{JAl;2)kJS1y5x#H-F z=jB@vZ;&6?FlLnI`3v0`Ff7h5jJJZ0TX=z0p*Pf428oO7iTYtY^+j42iEgYV?n4b# zVJ1c;>7z#q8mY*ryp#%SB|RnqQbYM~4>N}J!G9=!9hvdp14kMixz153kP1U#eN}=~ z8sB4wDd-Zt4kOogoiC6gdXxHwI5Z!rUg#oM|0NpbZ0IO#Z!8FqTGRX2rJ5*x)&#_? z$e;;w?fzf;*9RmHfa$+=e7U9$26Bu4RXWfDxwc2DKd%bkBlRle(-SFJ{1}V+ft3OA zZH`YZRKz9S%To5BG{d0OErq!%tU4c~69`P%n+FSxHWUY=G7?B`s6j4OmWnc;{Vse@ z#bxa}XO&GC4Dpo>CA_mn$&FDtg*iR&v3rN(JY2n+2F0Bm&G9n0K+kSmp8CkJY0j>} z#2y9ovp z&}PNl_{KgxNlxILC>FS;8zE;$_Nmp(X8R44aa=5}g%4Gw*I)aT4c5D!@JH5~ansqq zN!NGec?hRVZTlOjS9bT-mCrb)R!W^?0o>@4tqc;}0E$9?{RL zZc~XOE#i%2DmVs|xc(c6GA@rx+FYE)U7vm~JtH?`*$KrJae+K4w^rWCyelti1h2jz zXz0KX*XC`aqocuFjn4Q(36n3Y66c?z+!5ap2SYY(3TvilZ#3G#(QX$82uY3=IJTCnNAmKtk*H^anhdK$O+EcNHSB0G2!vz zQHE7y9O~aN!CY-wR~75W)$M{fEfOFb?DS^FW>U#9-OhxM(hF5%qqmA9Av z@`w|{IV(cjvq@X1d>r4ge*yX>SbZH(4w1sbfp@T<)@J#Z=Dmyiu5hu#&AZlmGGAl$ zP+fmR{LWiE?xa^-)ytW_2z7AwNP8U?G*KyP%-Iky;cnqKyJVkig~mT@Z%>ZCKj2f( z?J9*+4fZ>a#)GKM;_|keDAjamPR&gn2+reifqTWq^ExIuF}fQYP7zF7ODjbsllv{( z37a{*RaIY)2JqePxj7P#)^EPy`r))bI51ws{fov4eoKJvWyj zc+$+@u;}?mv&h5k%d@JN4;{4SCu$43@Kt(B;o3zij$%9VQD=8&@^5ZGU;1;~#?XY| z?8M$q)9m<*w`+ndN$qAtM}+GY=m``2P)f}fu#0?N^a@zPO2YL}TD`_Q{@1Fuc3u9< zA=9zBCy@(!BB-&Q2)L0$EGgIG#m*D&));*ys>f#)?|TTW_XsR+$YXhf%kg1vTEH(a zviVumqo(H6=UWLzn(@PGP1n4m44psv)k=d}?T30QMzv7uI1l)a0T$m1cGgA-+Fh57 zN#o-dv`Vk;%VgLO1hw`w5mWos;wVE=fQN%G+K1@R?@aY^+(LL!O#}Wp4+v~}`DTjk zmb@HsSa&T>e-wxngZv6`{i zK9^MG{z5`%k`l$C{gysu6t^~>-~e_Blsl%qe>w*XW^h<<8~N|_oEJWaQw1$ zc+yVyP7_X1fyoo!sy8qrie&)&^6juuhPpTZ-Ry1$m&DJ!b@%V#r=Tq3_PZ7PQ~g8# zu5W;vTp#}JXa?)%kBeb1%DD%En6LLQz9zr(o4H54`Bpf0jAHO*&#SD&=T|P({=0>0t8lN7PDH4{i%YCG0xei1)5H6vOFjz9`8EdQ;jJ%J z_@xWewlhCmzvivm`z#9f?dr_5uTzP8jw7zI27hU}09kr(Ayv5(c~P844+8%3a&Z2! z)Qty_#vb?$S2L=7nqlSID7zD5q|wtn8$P zeG~wm=U54Wxkv8B^B$7Iu2p0x5BX^E#bUoUJkvIJRx9la3pk(|Zja)3eAkLGn2*mZ z*KJ$fX|W3W-2zCG!3|JiNQ$s`fc!z^!!|t5#rfoQcQW0pl1|favu>eO0MisegzJz~ z3A7IR%!rl;T$YMl;A9OAy`~k>p|D#atvSVntxfv_0=E%V`tuC4=cdsUt5aoVUtiP+ zb;TGQn4>Rwl--vh>+e6nMnJ2g_mZRQ=YG$NMMcAv#*4R$@aS_I>2vQ7O+*86(UXc+ z{yqmT>5X#Y!!uT|e0I`?%td8OrVTDvsp18&-TlcT+)mZuh>8|OReB+iPF&}>o`}Tp zx(>*cIqc+Ppv*lduC&u;rZwN3`#vF}`oshJ#-}^SZYsxhChVaCP&Ma;V6X(UL=J89 z;Wp&d**fxcIG4H1bZE#!j8o*{x2LTZRbr=hqSX#y*4g^yJQi2u-FAH}zV?8bnWZ*h zr^#B*pTn|z(A@31UYQCyPr?Z6x_)Hcqi&R%Qe zzEjd;kqT%PfZq1`$Jxr%I7D$k)ZfA4ITfH&)KPLOI_PadfV>=&B!}&6wOMR)&_>U& zYG&?#ZI6vTlh(cRL-PptXNdh*C*BSR$#T!WmX16`i`HhzCn`V4HXPjst@zORhl6dJ z?X_A(t*VnwnYwngT{0e}ZO!M7%=uz>VQ?>^?GFxpmVBH06#14vPB_fw;{nYBjlR|+ z4O`8bXCmIUviBaS(Gpio-2%OZn~L>z?9AE~)0(8L3x}?Q;~LQcg&wXpFizDCWDOeN zh7yq&(2$3dn&a|vtIf{eNhl4)G5pNBtHBBWiC-g5CJ^ViFQ%`|kR>n8*gkXtTx&RB zU0src2XzZSSiO2pR}@&-o9lX`=0LiU)c?)}vjBh%UYQr*^ziUDEq(MoZ0S-u5dAI4 zA}QBZs)^M*Fa(^V*%141Q*jTK&{uRUu>lkS-aPRCRhq|-9va1tA5_M7BY8O-qz7ky z^1#V3IYG_0c11=&k%KR)N_ixvCK1xJ#u`{&_?|6{cyGT z{y^%TC{dwEYfnD12QrKZ8;YXyF-+q>pB8Tt#NFWT!cC;<0H!y41MBPRPMGOmXonFzM^(hrHjA zXyO+cqt;qGj-T3#ZcqFzS)9qDKGtLnTQZu-9e$xB|LzqTR}W$NZsSp-^HSy)T`NX0 zoJRy#e_Hv;*^YPet50T)?9-9`h6o~ubpFPw*G@h+=-QHs85=eD-jZDtrdp@mCx<38 z%<#b~ot=`3+4-;k6wRd$MLVxmjXfJC@gIg4!s-%eF{}uYhifhuo?lTfd?!9FL6tKL zcY5O$b}77YtEgn(%`!!_LVv*gmT$*2vqh+9g3G0qTe9$8P;ToWO`dR_L5f^Jo#)qh z2|Aq;UswUj#2N|WDn*&&X@#rDh?sC_dA!6MGBhM$-6Xvfrly$DJAgK#wW))MjJ77Nic)x2xowjETVWqcqg7?zcx5z0B?vx~247q=7b^Y5nsA7LSaPpi&e zh1xDgQp39PF^J}WD8{JFY1tGNk#$-NoYS(J+?*S1ov+86ePZ{=je1bBX8JC&YTnZW8@7 z?uZ3OO|;aZ;z7DFnHcA`H{XbaG>zT;ud2^#@rd@MIR_Iqk)OtLqv+wFy=-je`a^*l ze9nGDI7>bSZgfb$uiS)*CLNNtCSvK?*}Hgx)szwr+VY|f zmdjNqT8j7)HKHB#) z5()LYxz-O|=g9$f_>K%}{)Zwj$@cAsmmR0J@G8X4ay}h0IzGs;IQ;Wd1GpfH@y) zh~NAfoaQf!I{esxpW|q{OftouTY-JKu$Nj+;n_2(D-e1xht+*S$p5{Sr*AydoCM>3rkm@X*W((y=03$|84Y z8C=xMOqQXk6PR5zUtO_s;~8g6mh176l+XJ<`y>MDRGD=7{bd~wHOnxnI&) z_`KZuL01SG&zDcTWJj*YLC7S9mw@mYd0u-wFioT~_qWK0)%!G&c&oTXcTg-*mi;%f zUYW2{S^oPEb+{g!o&nl?3_$C=cE^#I!$2Aqk4=G&s8vx6WeAx&*D#q`!Aj|A>fyp2 zr(G?y!r0d;x@kXpo==jMd{Nw*8pp{NQ(O7kr& zli||bIW<^}U_u$-6;U)=tRhEw_LG8yA5vov9QFn3(T#$HvtJvV+vT_`(TK| z<=Z0$Sg($=t4dO*K1^UKTj09-n^6)i2%;?iC1$nRZZPmpwvn^Oc@wtvv|lsi^Gv4t zZ*EedC?j9pUNvyy91NHWk>I%)2^EJl>9ac6UY#@m{5}b}cgbsp_8oQ*7(r;L ztTu)m5*@^{5R4na7XcpL!PclWtA+AxgqgP9Ds}*3d=wO z$@w72P02_DI4mJTs@&hk2bkP%RTiHl zDh3C6PMevF?N*BLb1IganTZ6+S^NqCj*+C93Lb*v;cg;RTZR`%#$*Wb?bKHn$#k$@ zgdD8sWvR-np&a{@ENIE?sTOtr73=nZpp-KvJx3f3<{4hkRrcHE7tI>^kdtu<`Ogth zWwIJrd`64yzF-U$DtB}Hm(5mZU!aq`d2Z%J7>))l##FbQX`VJ5dQLfMD_|n|u~L$~ zI%)o5Hv7`uJLhfRz=7gb(n!yx$S^}bdxvXQ_^%DaJfl4IwfAvIa{ug@Wi3TVXVN_f z<|Ie*ets($XlvUu%0An|tQi9M_@7gjSmnR!k=GiLky4eJU(s0qe=Z7BGG^5X)d*n= z?R(FL3_-tQD&xgV`zjj5fGASzs4l#3(^X-KpN|1XWHP|x<@Af zwR8@MsK3SHPs1}@9`5-_)lWXktJ`UGLO{Bd?DK1r?Hk}AYP(L~+-MMB206Ov&Uw2} zw)<3ZDk@(3+L<(!O_@>ca5m}oHVG7Lk@1t^io3DmpS;TdM0h9g`}@*_cx{uB zdufa4a2j^xTYAL;nVscr84OD1MCAarrEqQB6dpZZCn59!1dlLC>cv7 zk?$C1+E@HOxM-mLdpAE7-v=T^w4M4zLEHUUfx$X^SEX540&rDk3b4IBk0Qa1q5tD* z38X5z(S^jVU*>tlVtVi4+N9u>5b6apFujJK9qLCTqBwQLjKVa_7?90aP>{sC9Kpq?ozCzhE98 zx;PVJeO)ILKi_^#Z!XOWbNcZh&4;JgBEn?ec&M->FxSWes|M1ZcPOsX z&H-g5tP8+6cKX2DfN9;Owx)QnMwP^xRtwugp&wjnceXm#deeHiw}yht1?80jdhJ&a zKW0)fTmNdh?-AN$8e9e9R_Q~8R?rOG5 z8cVkb6=KSxE1ttw(f+HIFkzy?@lJ zpJ%>AWD7$|=f;ffU;vGh&+M}3Q0d>sCBOL97yMP_&`&f{$4kAo`~HsqLkV?<>+x~t zPPLz$M@8`RDl)Dh zlUjDqn2)=J;JlW3!};%0L$?DE_3yr+2l}4yCNLz~PyX|u-|sorFQ$`SO2q^KTYnH8 zpNmCU!OJ!t(_9lcYv=ye%o2YxDo$LyzSxm099rvgteYP`@f;^ywH$S$pLx$b$-4f>M}R6pwh!*AQPxb|#G?NEJ8Snd&gwR^_A6;P*8SIKjJ;f@NiW_NGt_1tEc) zv)_WuWF2A#b2~y3%fdj{-H@P}+NvsunurDb?6|cV1_u1X@SNn|YqZ@kUFubwNv84Z zM5Wep8#kp!Mdf;{Ag!Nt;$J1~LBSYq0#>t1QaCCGRu9pR0?y;(CZ}XV{>+Jcx?P(j zM0z8NwHs)ZeNx#Lt=AeUs^zIe#m_A`A>lI*-ql<^E=SnxaU-5##JT+jIN4i^31q_I zLHCM1IC~++K?4F!Uk~XpTjbsa^k6X=5x+>29IV3++{aoz&ce&R-Phu>q>fAc?R3rS z5K&A`*7Z{|*~jD~+wnpYdu>kz#kpPMxwF@XMEw==q?sNq6_?_PKVNwq!=U*rR(mrJ81Tzc*O+Hs8Uwl#29|J=K|;W z;E=2>>Lvc*C4qkWNrnP+f-ki6?zJ`$-qHjmf4Lh3iBfNEmfX;jGTNS%gBSxiSMH&i z8ZGv2h__A9MK!0Zz|M%+KBA$Hj${&_mZ2zIUS{4+GWA#L$ewP=$-di^>5XMt6-|`w z$T5Z1el$_KJfo5Q0(}!VHs##b+;&7D05VgFzX`L$Hzk=0m{*y-gu^pSP5>nx(8DHT zQ9tLAZ4ytOMl$Sgk+&OfvtFB|{1D%4sPz2%FQyXof%ej=TeFw$`>z1s+5_*Xi~G2> zkN`24>}*xVp1b!%I1VYCLoluNHWjXt{y#GnHX8H%BeA)N zl#ZHhl|ZuKO*J*<_oYmxV)hdKUAw})3gt>+GE16BGBm*#a1qr1)|nHc=2NNti@5K% zqmf5C9BQJkJI96{`z#Y;uXIo^^+47xBuIu${Xo74&e%ENwxTBUs?!Jmtqjp4!jU;Z zn+tl<+Btx_cJgVQ%j*$Vujh1aBo&RV%5AMbIof^cZCb2AGdgVf$QWH8a2Z-}Ws6!5 zJ2m6#(EQ@@2Vh+zrZdO25_AvhuULxbaU>77;_jv>wehC%JM5^XrSA_d^;?9)GqIUyNyXISFN2jL9~NDovc5$p&<3dnO2=*-wxckvgd{?X3+q!@OX`fX4AylxDBj@!nJEI2&p9OhRf@#ZK7#C7%ePw~7 z|2mL0j3Dp>hDNc<`#1UY$UeTnjIT^O@Bf>rq$|FD{4bP;><&U2|D^~Ck)bsdOOx?;R8>L)ri5q+l z8yAf^EULbyy1g2|FN*$=`Xw`Y5C_>YnKZphdrXPspVok7c$S2{##3%osgUH+o-kMdzVYNm7 z4zvyTmP?OmLTnE7*=)g!l2d6glcB3GWx0!5&!(2Et2%5z&D_t?*>~z899FXCl2g)i z)j11e&MCg0iqjj6I9`?bi>ZWhGs=GaWWP|-q?!U7GCg5Q5Qz8YSU=nAOga7IxgyYX zjrDfXimYh1dGghyLY+R8gJ_|Cl$_lGN*tS^#^4l%k$}S7sbDP>k7CqXp7K?7kc{gwaf(@;A))v#e-W2BuOTD zJLVp&eVj1wKh0Jc6?xaqSFgcyceQ-m<9<5EGvI7Fm@^@fsuT9{5FpU#@SL&3cGz*t zak|;79$OSwVxPm@7|hS87XizX3JT2HyU2eY^B&0h*(6d-|?g)*?C0xTL!Wt4^ zN+w??y4KDVZ!4>W=Y~B}S=NM~r?FVspo`Rkvt%;vMQVIa=a7G$1aia;!!D7XC0jAi zT-Bdsi;ZUZNsrSdo=62E1q2lyKe%0)+N(B*$2Ip2^UCwYuP^2Cd#`oQ4J9KH;FMlCkX18BhZb1Pk;+rYq1MuOj7w1kPI)2t>Mx?G!2G{-Qk!jp2QjBBjWU1W zc}7vtC~VviYbGy7c!ym8WjuG^uNhQqy6pXF*lYQz9n;pWG`~VrK2snd#54B|+iAAh zA??*oidak(K0e-OVga|1S_Kh#;&7WNJc9tDPERjm_q0~32PeiqX4Jcd6aMmv#B|j{ zCLk!u#c_iQJ(R<}rcrp4S{h;Q3wtRYkwFVb#S>;K@RlsP@N&LQnnryXg);l@$H%y{ z)5>arXkc)iYUQGM_1HyNpVUy-nvB}(7IqIL_o_$ZLcowdD?Q=<6&{g}Zp{KT}37)j(1YGVdV6XR7*-C_5o+{j} zqDmCtqXOM89v=I9=5Ky5+$|+j3CE@fPt}H*|UN_6RWm$gS-61l0L>3d$M4 zEps(2poEYtMthTWmtd;-x|vC{6gQ@M>jlQRIY6G8s7}x{GnSTHslJ@WBMcIS?->Q^ zyUsE_{1@44l5=1ESOExLcx^p@ri_90g*8K7i$X}2+Q}I&;6PHkH;BRYY>mbju>AWU z<{ooSt;<`=!3ruqSu>4N@W7e}eSCEb|9!WzCa(zjERYkmQCy@NSJ)~0&&y{EEmIKxf7B*o{saE-`MPV4sdcp;y@WBrMLTJ1^&fQf6w!U0;HtxHW zTY|X&CjWlcO6mNaBha#91iq%_8m5LI+gjE=h7fHGSdy&Tm@j7FcSr5>&+b%b722^o zwFuSe%eS4=?inD}%2t#XQnR4TTAcNvpPZ2K@S)x8LzA(2B%v!jPhR)muv_$9?et!| z`{}M`6Iz2@%BCp=T4B`r?{V3~?GnP~K%eTu#SUSRp#P(wxqk#WsgY_rOMhe+SCuoI za)01ST;rW}ToPvZc*LFadPg3vbH~TU;A+RD>!omEgX3K5AC1i6{G$ww$8>?b5AG}# zIy)1p4`Pq^&`Gw7JcJRt9p%7pisNY#&)#o;mVq{YmRMtye;a#ft)kXKkZqbrw1*|b zzd~{AX2B<6YRA=pv{Un#XWslG88@}nC6`#u) zGBvqe^cx@OUoyIJ4-HGqd8%G*+&}BHdAnmKmCnK0ZQ4pqMbB7vKLh=a>0X}9+T{bD z2H#|^&Js!oBasu0yNrQ7`EyZv4qO>(`U+e(WS#Nm8DYD2OoK~;t z84v3;Xo7h$ox9}Iki)32y8FqjGA<7lUNZIvd)GlGPhnMxxZ+l4PDy-`X=Cc3txo7J z&hzK=rGSts!*_PA)s2AbA)p^bHI2adJ|&Sa4=u6de<1XIKp!X_6xt=`9lJ%EV#nShy zhyS*bNLu7cj~qt@3ChHXi>8Gne7SwLvHAPPZk0LHbigs%*6!;lgQq-Ck2{FAzMTk` zD!e>U>*riD`WRuBOK{2$(wX5nY5(f`letDQSI;V_u{pw$Sx~X_=MI3r;THp*=hDEs z2~}IQYKcVxXdbaLcHFWtnuHAXkQlYSdkIBtd)qs#A4uVRD+H6Bui^|nA z+QWjz_!dPy3Qa#oLmdoHoow!b+%7f=SobGdGE`G zVfe07jn}X>DNcwlW7R5|53(+ z;#Jrbfy#k0zhfE;>Bx4rjd(q@2RexlBB$>`7J`J#)YSQ|1kNmmw^B*jqPAW23}H%; zUumRsFGY*M3hlC`j<`-ltvT5v&aotMNWs0#6*aQSw2vG2u=(aP8;l<8+U%#vTI^%W z%y4#UBYo{1%66Gghz9Z0^J8euXAL-qeymnjPL#D(8em!S6)Ss0*3DOEv|LE8)|H9= zyTirW9W_Nao@7N45hj?3nS0JVvhz(`^_7L6Mc@`XBUf?wJ$JdhY+i^NR}cxQU^kNM zwiwp^Jp4X*)=D#oX(Wq=!Sno*wg)HcUoHcC{_o)=LC{8>r7BhEDKGEuef-A;AN53W2U66`HG#)*a__~IT;tai_JU<=9S90cK!xs8JTRpxv+N??%t0;wOs2F zqh1^mjLd%f%Xr&o?&7klm+KyyaQPwbWqH^UYyvBT04|03_psb)^oL7-U#cU!2PlaP zlQLHrbs_`AaFci>W-xc8ZMO$;{e?)p6wAuEh1FtsLb(vE_-4B-VdA-rr zWgu+>!wvUXYHi$tDhUc>*+YxB4_77?tzX>^uWlx6CNE;u3L*iUa;^qLsPms~ulw## z39$H~JtDOjwctQbh`RJ^iP!J9LT2jFYnGiNLgOSRn>16rW%ygoTF#l8oG#IZa;*if z=nh}sKbZf6&yTD!Vzkia=yv5>zYw)r7Q)^(0 zXsrfRfL&9b^_4>Cj7TkyIBJ^Mdt^sz_BG{OtMhj)Kg*8^dp{OcDm|SKGi4Tgr%pt5 ztnh7EgM-3F&|=ni-*Yhy4!-tM=Y8V)>OzNY>++=Pz_a?TX=A?5W1Tan`r?edBq;?u zcUb9AWVdr2Ah;*QX(~JU^Bu?ynMIc=vm9?maNBy6M=Yo5&-#y6japViU>84RlVH`K znDWI$)_?nNW*|}qR)=vHZRd;O{LiAzPQUiyPu8G4o^jm`0HZ_N2;;bAF9)t;A0ou= zE|>5ORs@G%fZ}RjNbZQ}=jj|l94nnqM$kFKCWelsPF(xVu! z7p~Tx8QA4T_3Hd?nxN7>Hqavjt<}>J^xlzNWL!B2{oR}GE@U~=T-D!1b#zP-%N-gc zwYUS&X0)?1cJ#XyCWx_t)T0gm#O0dAifL3IO(egP-mz)ICiXe#5}{?}6IUfi{?aPq@{%nV-8b3nuRHZnRySsdJ0?tLsz<;9Lm~8m>|? zI*vRR|NohE`Cb?cSvQ3Iv2y1nz&cPb_bvF3 zON^kkb=sMqt4ORfGO_CC={30=_vy^j0PZ%aSN7vH%PQc1D0W#LR==v2y4XY3!0Pda zU*gvpJDmv5;zDq5(p<0Pt>!e#6_}?3W4ERJjm?0hsnW-jzFUNDSa>5(qd|!#SlD8;4r8YJ zpatRnnBqDexo7^{;}gwB{ov4k?i@bswn9y@ z!GGTG=Mn3D>Ob90?VJ?Oj_BWWo7H(3T1wW*ynO2iWzWQQ9`R}Qpn=vpJFefh*pTo~ zl@z;Hc9#vU%k0-SaRBTA80}D_Z(dbT3f0D=dBm;)jiP*{IC47^Q3eN!De;{?wg15PAV0&WinW@0Fuf#$6 zqKwFt^Mr6AdOS8BLOmAC(?{Ot(S+wRN@MJkdbrvOM35R0O;LDY0y36c)oKe|p*Y&_ za5g0rzFDbVz8>$v13zD2v2dR?tiYh(WcpWsmZCP%P@a~6)c`AaA8~pZL{L{yp3}&F z>u3C0PW$<3-aVe8sOH$^nXbA8>O*?U^Q*-_s-(oK*?sje?~CEzfovg?O89(gala)6 z`^aK)pJkem9CAAE1ugHOI=;U3;z}yNcb;Pjk*^Z~GWrm0rKr74+Mg9|q8u5BM`ZpC zmopv}61V_jW7!pudyh`x$3%R(=FoE(S6SSa5Cku6zfvY#Z`jvbg%WT&Cx8E#dhq_s zC}D7S0A(FlW~FmZyN_v6Nt5Qhq1xc2jDbUk&!n$_bz=J+rm7ePLrcquH^etRt<{$4 zC&Wf)&oNUVM`?b>bIxwzLy>o*#6>h<28!JJh@ad1WN18aaABklMx_N8doa)DXT^n& zR*Z9HeiI|c%TZcLTOfo^k`!1?``K4+AshN;4$orAw)2@XsgrqrrFX`ZRUBvQmII*v zEw_K2BK?BDnL&x%;2IATeuOQ0L)0b_3Wv~_jKyYqJVTR}UkRL>+i`pv*<>a^mE-l3 zxvewgq!JU1r)*Oe4sT5v#%hs;?R6tc%t^Fmkz4D9J3JHBJw znq*V94_3${UUCo}2fA6hxcU;QfBZp;CC?3+h<^;r99c`cxxy2=X8wgmc;@CKnSxQ- zPT{M}IA7X=?kT_-k2+a`XqGV$MiVmhn{B2m3hxm4gWu4f&XD@&GcrY}k=A(;G%Gmq z_iqiCYQj5A8C#0N9yixszKq?BadoTN7iM_Sl|)t^!A{4HpNp7r=aD3Ob3=USXv3^U zK`F0bns?jqS20}m8s)Yfk1L(@(d`2})%opXE+kZ$Cr6r#GHvOhE7+-MzkRKpK`7KEenLj4P%SBw%>#BJL#$m zCwP~B@Sih(%sARWi_lOumXik>-6i4NlqMLICi$JoN&>&j{b z5q?E`T}l6%gr4w?bg5opzI0;fo5aXhNU|Lgy!VFi6%stBM1WkblOWl7NR}A=7hNPu z@W13PlGvw#%bKZDzyVr?7Sb#1w}!PzTNq^nV8xskAeD020$qBLKC3IeWsKe)tI1HR zln#b2j1pF6xA24AVfqb`OIzXErF6$aJ*;9eVaeYYO0c8}q;PTg|E_A99ymZID_2sy$jfYgO^t(7tq zuJZos0+v;j4=`5v)Q==rmsyp5*a6%tEpI~4906Zg-!dIKi3+rNeb;HA&Aap;D`k%1 zS&ttCnrbZJ{3vm^*k_8D7)U(`?pQW9rrx6JXg*#4Gta(SQu;DxGheHbdk7&dpiAjr zH?ZQeZ^<(W{A%fy(rqt`*p84Qa0ZP|i?R(yA9uIy-l2m^I0kB1L^T zW#y*%8sVrKbXJGP00dg}BT`SOMS8M+tPbT>8An5b_;HS5(O1j`-t&wZj`w+wnIB!nSPbO2X!fHk<+ zBqZuZ(C*zYKrRJaqc`+i%y{l)SYlS>mR&cYy@j&pXzgRT!3~`k0LifFwOd_!qN_d? z4PAsP9L?59hLqd(v89!?ihqJ33x^O4r+QXDTi#L5Y@EsUsDxc`5}Z*ptpWyG_-7%? z{1vD87q>5%XM9tPexI65(ktb9_iCHa9U+3MRy>cuaq9i!PRMY|93gr0+G=8Ar?BR4 z%Oj8Qtr3ppy2L+;h_GQ!5wuc2hGawz2fRssjGv3LZjWJGKs0C$(0ngvNDa;ZZ6Ka( zNY|oh#&`pq#=~-EKzIj@Df#4w8VLr5b~cUHt`$Sx+j`t+*{X!#k-z1_JB_tEh@tzA z>QdZl$WQ{W1FcanLes;{pHL~d%xk{&tZqhorcpnl?R4@r>m$=m`i6_{{`#6XX1LhlPO)FfF1%h?_WGWc^he~*w<7#5b{`j|FHq{#0cuK z7d*@uPTWnRojJojv>ir@{6THe8?7|GWyk5we}$pXx?s^C3(IS=MV<5Z17mzq4t!kE zZIBjy$HP`$aadt)$7sc+m?9j%>>oG3-A@>b*qCpc=UQOT+s&LU6d@ZL?v4?hI%n|* zI)IQ__?!Ewi+f7A=m1Cmh~uakF;{>gbeN|VJ!uIgcYwHoLsvRTSBbdq1A&EZam^Q0 zBy3QJRfR1QkMaGRQk}2$vPC|n8Wl?WEqXQECY7Zwb_dHwaXJDz_R)eAy0+^-e~3^< z0+fkd=LvpJHc`$|g>{CqyEIDejm_Iqa|6-$A9Aq)_7Cp3OE=IdbPn0 znym_OY1FG3yh*KTLbv4ty4#Nowo`|)=ETd7BR&;`X$=zFrwM$Rg@NCoBIyF<%*YaX zX=I565?C0CGy)MY6NL7aBQdTz$g(3O>Xck6k^q-2AK4Gf8mWb(PzK5BNWCE;=_8IL zdXpGPjDh^SE05HmW}yW5vMU|DTf&SL_DT@`#OO)3MtAtmujuxZ;cniQ;jiG&!k@@f zW3~}FyVvCQ4gyNWg*p7^6#R8iu5Z2^$*Cf9Y3thOZN-lau8u;myMa8`zc>l$@s58X zpT<5*!x?c7-9KACjZN_+f9KSOryHIYg!exZ-s)>s{Bid^tq9P3ChdRx_dk>+tv|^3 zOlEiPmLFKL^lJz_X0VTSiv`D{`l52#G7{hfqKBLSSgIQX_=aRx7AwBjaW!#~`|?F|A$gr`Xqm3Eb;X7KYn2~P|o-vak1G)(WM8)XKd#- zfWF4YGi5p0{}&Z3O~eCfA?<)P&-0yBXehhsX88}}vF`>>=dV>S=B?Er_2JDUC% z;O6s*S?aG!SU2r%M{V@Bdla@6>I7qg0Ag28UY**CD|wM?w4dh>-X?5#O2EOHqLj_u z{$y&6@3Le|xwvm=>*^$RR}H5n!lzUCmf9rV+U~Q-_`m6sx^Oj{6VsTK?@iBDhfRil zpGq4@!O_3Qrjg%P+yBw@)nQG4@B33!R3sGXR7&aY5Ks^h5EPIY2nYzH2ctujkQ9)R z6p4`|M~xmGqZtfF=ja-Zzxn=re}8aY=h}5%uWg6D?&mqrdG7m$2DRw6Vy-{q z0!#<~%}>+<*=7DWgf;J88K})v4}b+FcT#0lOky5lLuuBgYIscG=zvbzT7-JZtEHdy z{o$T(7&CqrG*89o^k+EOWtwSTci~F12eu713F3^CSFhUdgT6Mmk1fU5#f|H0{*ZwV zQhw^$V_@9d%6!qO-UCgxSaGLMUkJhDkcdP>eDK!q;>v1 z_(~~9*@+`sqCe~6b%Vw3omrMwF=Hmpl$D}YtvIXZ)1Z1__%FlBhCYhIoI*{$6u-lz zyGO}qj%Ht%XUFNCYKod3db?IuU|T=ei^@+)VN3kiKl}xFoJTlac!SL9#TBsEe>S~; zmUn#RjqSYGA}m*Y>vW!m;$D}@gM|Hwv7*LlIt$|3Q?YoJHI}l8+W3>8^3KJS`g9HO z_G|1VF~7FeaJIignAxO9%H{DyfSY{);_6kyweKd&|L(mJQxsgumU4stNeK}@IE<8N zLT#OR3OL;FLVc!ou3fx)3cUe3c-(l`ooV3m@_#qDj`Ef8x++=9%eB0kI|3EzRz7G+ zwhA}#wPcKpXR$Gtyx4p*mh=hCtL~rGP|=0J`LDr;5B21{f8qXh<^f)drfwrCCCEz$H zh6Tthot}9TFkD)K&4M=sL~i{BAg-g_q__p*eE2^0%}m4?r_synzPNVpv8I~c=o_*A zRFT$P@9AxZ2-TTg+a`heb@oYV&5CFn1pp72QD%gnDP|BPb28m~EhbM>m#P!QfGp+RZtOS?hK493|$ znd@)zsdtnksgOLMF=^P^&JFD2+$tLj@F2^s$`~em@12t7HYXg6?cFv*JFVn6ET)`m zousITnWoRKT5)5Y=P4})p?=^Gv1j{fwRs`OG$%opji(H;1{a~h-}&8yXebxeEY-L$ z+IqeGA|a|nAyX-QA3C4 z_vw*~XflizCUqDqguzOm^T49s6n^k!M5MUQg$o6k5AHP!3e*okn#N$DyeOD0+wI&I z3U5z}rYM8t^RHG3f5rmuu>(jO0bT%Kvlr{NFxrA6O~=fY#mhZdoxwuhg?(m*zAyOA zd*_XV%BE?wo$37zAye`P`+Tm>)or6z;HIw-E!%$xd?0dcz+#zlo@ru|v}}VD2=SyL zF2~4v6=a`10_Dnlk<22BW`c-Plv7j`Z&9cgKOFkHNy1H+@!YUJf$uoi$yT5E_H*M{=(=kDRvb9yJ>jN} zmB$7aLsFUf^$BN8u9oc9rH}*T#NF7|$wQYlz>SUhhRF$FX=w6o(wE)?3hCaM`9s;4 zc?83m+WZS>+aupgy3m-uvT`U>%3HI@-1>*u-d1@={g~g2yWj}@BeTpE8yt+;5e#Cf zr=b)oynyCLhcft(B4Q=R0{>p)d0&1I`88!2oUCoN4JK>_juSl=HU+)?gK~ z?j$Tc3OZ_1XT|>?@}X}!I@F5VSg`eNY>o zAV88FadN}T1Y3lbn|D+Q-DhF7*L;V|;=G~_D@`&+!=pq1{=jShP2_def7teU_0R$k*t=D*z1aok@8I!)4(YwU;egFGXRv#Xa{I1T|b+Yr>XgxWoA+sz;ZW8 zQ;$z{_7it^QqD8tt1`7u8SnChL}HR}mFQ=_FbI13iJla51wzVanYftO!eUl(58+-hwH zPY>mPsN~7ZP*FGIL75zICH#)x0+5%{tiBvOkfqr$`;=Uc#C$#$b~^o)^t(rhvPe9a z^Jwv0=fLbd^h?{q!MSjjIt4*NW9e=Oyj+eyZs_+M7aD$*x|HmAl6nyuE(&M(;mqhozyF$*G)&!kJ(TyR; z^jNpqcQS?6m&cYWPH4@h*n-SQPgBF!(PTRyFE+N>LpFSp+^i3Fyo+CotH97kPAs}H zeKP4kH~|@FrVxbmuYuW>yjA&w{z-R%H&qEP^>krr*ny-RsI4C=a&i(OD!DtaC!^A zF%jL~UWa14{@CH~Gm4TjPa#AR8WlDK_3F>wmvWk=Pby}sfK2o|lAsJhCSFwc^ev9< z8CQ~slp&QhsV0M|@pJynIh=GNBF`8t#zkzB+4s>oOfm@b!+i3AEh!oA4HzHDcvYpv zqfXBR$V zXu{y+Uq_4E{5ixFw&U}WMY03Irx;wSUbfr^{_%*{MhZE=4udwZtA-bJdRo8FpJPQCNFEoA`-XV1LGR4j#hVtt}#ZK$a9W$*j zc+|i>DeP_!CB;?+SHCmgBio?77dvY!V`RX~p&nf<#pAHemx@6*C1JKb4mSp~QuT|y zo;x&6pe{~~ftWM+svtW3vSguAM#J4G?iD8jIP{9LNRw@+Y0b0c;57Nfp?g+CJP27v zE<@MHe+z2aZF~0d>0Dgv3hUBS|Lw-rE&pkVhyMi+OWkm%30HthdBLmYH{-l*Q|3F> zHE*quRaLLqkjUiA@9ZAQt3k@qMinga0~J?nT7Co9?{Ut*5dGgtBE0Et9M;sOYE+_K zq;QQ*4%~6AqY1#qTzz$uQunGQhWvn#6mMsU=$XmFgZDqh?dMC%>w6GVetaH>4CgyP z&OW9*vl3g0^D~_Yj3LREDiB$Ej4L5PbB3T6?yklyPH3#I6=j> zZ6z|JrI}*yF&mLY+(GY<(}BNZW0QOh-1qd$Wu2Sae<0Z-gM^7z!Sp6<=28q9D#Js^ z^2Du{cMx3-T*VvJVk9nOrC!IgQ*_Tk?zGUTXnXTiNRujjzy^Y^3VlHAfJ~7-P)~?& z@Y2$Dlvpl-!)FUTrp23Iooj~JZD{*~tWXAa>=1Ya7(g}?_6c6zbL z+a-fMi)8dA%3-3(ZnYP`*vTcHen;_&HKnN3p*lZs$Y}$MB~kafrJN1E95@+{^3d_k zj@xP%Vx4zqIYHkP+Z{@%r5&77?l~zbzgTZg3w6+|8o+73|Hf5?x2#xWpP1IH9`&v* znsVbnnJ?=?D|K@ib_ZxK8GRnGA>L5B(o9IV$K38!^~aDEkzXj< z?T)e4v2)=S-uSwNl1ErC$AFj>k1D98T39|StlaF|v0N9o$+n<(73LAHv}FHLE0)zx zyfAPJ-YM4#11z*th0jdQN129%omYxzInee$>8$%X=^LE@^%A&|yW>yt9pFF5)*{$H3RtZ0tobLs z$B;eRc0Oz+7YeO?3CySy+HRH8fMlv4@|&0~tl5$uERZKI`d{|dP7B9vH%|C2y3{z% z5fdSpU5`u$E!tBwJwD88ZQOcw#_x7xGBVCPcK@q(ZdUC^Fb?b`rs8Altp}XleqRMW za>EW(c%nL?w2RNDEsa>Rz1NpY%%CNugVhkVs^f#ntU&)(;O}u`>J2xAkEL9Us`fEO z2U}OK7vhh^0;*meI+*+-iCV}yk_)KnIEym*ZU%{7SyZ5UzcUwgq4KybzmAdMO7iUm z!T9FxD;qy! zmj(g1u9a#B>-<@3GHx-ZqYU~e(c_G@W)W+lc5luj?Xum=u2#NWWqA>ssnsDNzJOI%!c{YZkzG3!uS~r5veC?vHvDIKVWidP z9t}|5P^v}-mYHWqg-q`GJB-h${$V!P4jSj*17!QvK+bV4UeIB!u4@?9&f6}bMgfta zj;tw4t@{=#8n~!<>-M_-)Yw&AeUi{=wEBAolkln||>{JJER5ga$QdYWb1&<=2Vl)}yWkIGZf*ob~iXKN_hrrg!$U zg%|FHygZ!+7HD`)3K8PxniL{qAvp{)8B=`Iwe-h1u=USI_FHlq-#Gru*YXsS4@5OG z8dnDphigvQj5<@U{#nWSMs1avBFVQgI^{ZppZg38y4+sA|5NdPqnMWxclTv zkm~)@OMv;s8+=K766VA3+}@TDb5F3cv+ssHA=SL-3pcY2nvPP{y^*U5?LnT*VeYGk zb|NzX4R3w{ubabV@i-OX*?EYq&o?s$@K<0Llg=Z&IOAbQC6= zT5yYcU>WiH34zYPNc0_q5%+qze?MnM8DwL#pGv(V?ubam!QpsMr=hK`_qoqH-otk> z+h#U)g8`&y_+?5uWjQ|O<@sd36(od@+=q$t>f26$C#$eKFX>eL#;NRCdvT1YcQIru z!BM1W|A7%GZJRVs$!^ID)<<@Iis_hrpl~lx*3zE+v??vf-J~SLN1!ifj<$6Z3%Yv} zpxw4n*T-2@8KPstn561e7B_$AlYqUW$2P=+Umi^qSvQsb=WKj^}?1^5*#%qcy^(_Y1y+#VYcAig$eB zJ7QUsc2Y|t8x3>bqa^}|7k!U5J#*)(&Z>Nz(IKho)<9e5sAf1-eUeT2U|rV8%|suW zI958Xr8~#$#nD*f?!!@+p6I<9Kh%04_rm)!=`7cE)S_b9O}$yk6n`dxs`H9u($Kt8 z&s^y~rmauPDP0&PFguCg9#~ZtZ|JJs8gAQvJotS(+<>%AigASYlAI|T*>te>OV1Fm z()Ie}jXo9KTIN2V|&DTJy=8T_8!*ewX~!Sz8wi z9jOdaK3F)A=qOtn@(yA2wPiN^aj8)HuC`11=N_S6 zuJVQqluFl?GANPlJ7eBdEa09z)~-rcun0+;sb0oFg2#VS&XoF8RT=SZWPqP}x_@_f zz7PruX;Uj2G_Hd;VkROy91na_nhh5H_-$D;qz~>weYNd%YaJhU8!4NF3L+fn#IO{%X+CNHb=K%Fk>Io+@0U-LWI2P4=5IVW^u9^2 z*i}Tbn-V^{Xg6EDyi_rhI)w!xFj(TER+M1YT@_=sSA0ctcD?9kO}LBztpS!S^@J#3 zkr$TAnUr<}ya@l(F6}YHcKx(%!&gJgW1_6L)E)w4n0^q0ns}{3zZ9sgP2uePVqIUK zGjE)5ZutWpv~5`s@fEhQfKR}tVG~cL`(BM$pg+qgp2)&-!QmJ;6`zV2VwChN6BaGB z6^i8z+V73csMou9kkl7TojD50G|G#P1|WJ!j4KV3?1YdS2UMcb{g=rJDQb2#aP3k* zG7xa|DbA1bhc~cuV~;_F=wS#sJ4L7?#nxV`Gf~4HZYFXEFQ6IaHgS*pT|}gfl}#~1 z4{~noQFC|7S+-Lzyzo#>uY|5JKDT5d)>zw$&*x{HL3Jgf8VV{>B|a+lUEmYZOa#8( zjJY{&FKc1T+}5qCPy2#RUfxl{JS&-2&edDJNpinSyQ2K-&m|4dda-Ppr0TKslSHZ3 z3qZ@m<>E9nFkI)Lo3y1dPxp>T`pMMsT=r=6c%8R*lxbS7h0lvIu}2}6EHHd zzmAbfVr39b@j+l$#kJXZq+fVQ1L##m#;PQ1AGqxkwR#xSJLyfxh&HJ`$1r>4_r;0F z#!Kz^LV|paW;0qA_t$wwpxNUV)>IH7cN*=(m9>q!^$X@w``b*$+tk-lqU(G9QNPBq zn*LGvcaEZ@gsq3f<;x<#>YwHpKKzyROb;)nnin|;A)R|$KjmD(PS)v4xd5Ita%FeI z>0R+uASW~P<}HGK9>I<_?B>7Y#K5OdZxYS}9}=t`@Bevnx6u5b-om$+1XsxSgg=w# z-=65)d`2*&&zGJP0vtl|Eb!o+|7B3lgr3Wq_yq~$i_h^y4iP={P)^*oUa+Lr zTNiJ|t*Pg822{_mhU_&G<{I=cgz>BD_+})<4QP`kUlSd!?Q? z=BNA*X32=cZY_1)aOT^ZMo!)OT>p_Z=xzap6q91NQyB21$v85>YZBc)8r{#W`N~mU zSEK(|=4qWwZK)9ZcPHBf-#!+*zku2CoY!@v5{ugS=BsU>=QA;5yq!;+jNSM)-zbY0 zlh=^IukpWt>%J7BpepIY3C`iNC?L65L60Bv^M*V*{;yo91s=OLMy9kKM}`oDoQEh; zruuetD4XQIiGrA?^l^RkSFOffhfp<|VPJQ9f0&FgJko{8XL?97Ho8&8wH*0_{#AX0 zS*wa(6*PHZs&B0^-sGmc1V1wiG$Yz?TTH=3JJMJ2!IX1_@zlXYWnr& zSk+ggiJtPCBDwFPjn)m(RK;&L8Zz1~Or*IK*u93UY}%_;iD?|n8Mr0s+R``1T?#j( z5%ISCL2*&o^wf2bJGM07NvuF2@e4uX7sM|BM>p1q z#;P^NQ1vjq$Bhwv4jBph6`~-w>yX?_1{Uf1iz3(sZ2X)as{QgWK(anPjCzhmE~O7g zI2_@=!+)pd^EF)CU)6BDDmgD|Sd)R{`x1Gy3Vh4?n9w>6-HoAY-8&H|csFDBzSJO~ zQ?RX53fXmg0Pur65OqV#c8?S>+(G4_;wLH&Jd{V!Zdk|I-V|?K_5k{Bx5!BD@pN3! zRVZ>%AbIh;XY#OhI*wmJ-r(5p^dlPI55t^H9B!RU->yKm4&K(SD4LnJOTjGhC3xg` z>y<7`_0cCjeY~RWw=E~hgK+X=l!Z3cXZYQA_kXt1sNq9eSZ26$h&|aC)=Vu&IL<@X zh$Q!0KAa6W-WwCW(g>XceW-(Iq?A2Ut?kg4oR+;E8O@0(RTErX_!=F>oYr0Q^3&DN z_My|KQ2i)i37j*R>e;l_7Q%EeGe~A{@;Kc6xgOLZ5teJ?Q&fc6OpTEJc%Z6od%NC& zLh;r^BUVKwMbykPb5S)C%0IxLMjZ=Xu;_cJ`{(jgE{~@s!fOCaqm^=LV##pG-Wb}0 zq;j#YnO->SEI|p_4D0)^r>-$J4UjeQ8eI4)NRA)6ypsaB6wWW$#+0@mLOLym|5000p!;3Ii?%Qh2%<24CO>)js5@)`4zita+N9Z5%NLj8N?hW5-HGJ97xkm^cR)J)_roO0kg(1n zIhKy$V8f9joxI$NYD@TYi7sngU+=@qiajki}i|xy3qDy8EWSTX;MWJ69{~ z==|h>K#nVay>-knK!m!gmT<==Y*Og=j$72JyIZN`q*XIS<0qmqZp@)XMhWUV?Yhyu zDY`T9<7UP#W1HI9r0{#|v}7ld8#?fdzG z;dzhWetCa`>c&fgrqJ6zfa-1E|F*j|0At8CPje8#Wa6Hqm5SsmZmcj&`1!jTS7|6ByG*J&v&t$Zua45Z$%gPAdO?#o(- z^Y&=gk1yR$6_Tt_Y3Wizt8@k3ottxHr2v+f$T7})eyqSG>z(tZeH>eBY~VKhOM|Y)v&XRH z919w8|6WJ;M>>ET5({NusG-w*?Lo69Gx#g$@_1Hd>$rDE`}=1~o;f~EqXei!orDA0 zVam;<8~TiYd2Ym_eb}!&GmVC>(BRZiA>=Or#q)E-Y>)6_a~gHWsxNycGGL9Wwa%B$ zzx*P9<$h+g(|RdLQgsZd9eHL3HJe@;0~t>WB4v4fQeIb~%dL+=^R8=FpOVBs<3eA9 zML*8@vPU=QG#&`$amos6h?rc8c6WZNkpqu?s=B?&^(A_MyP?XeSB+5DP~o%3_UdXt zCSVi8I8>qMl@(J+wXUtLhtG~i2XxZ6e(q`2_t`V+kqtHWXo1*WLcp5Y$sLq&U89Us z!)fbDIweTEbJeT6*-gX_Om46S$JSP|ZgKo(ssk(`S-lhG!Ml}P(syDwOYRgDNaz)R zbb)j9F!D|MMuMiWEXp-<+m66MB*GILnK{ohGMTOA^I%GJ9MmTw6jjkf$-G~KuXT}k z%0>?5$@S8Djzdk~a(Ixsl()!BZr6V!Q<(y*4Z~ zibxp#d_@ADUM2*ml_M|uHBpR$(lq{rB|{$}kbvt62sOAYNM*G0d8e^4da~&DoLeAe zK)()ViDB##C4?ygy(febO*8~=`JuS3XmS+}T8Jw|2CKxD>xsv%xw<;NRyYPeAiuF( z?)Dd8<(i^>XFPwT7oJs&P9L-v5*J*%5x91TpfUAAJImP@J?}H|RntM&L7w(cGOBmK ztWT(g_o)Ge<%1hY(pzy`=QlUxV#VkP6*`lR*-f&PLk3xt8_GU420|dkHwd*eQ_3ZDtsjb~ z%O3pF_8_~elz51?jCA$+0z5bmy2vX? zK-H&=F7p^j?`Yd;)}W59cPJyN`*k&fjMxGq3Vo?Fw{qnD-O;If9w;8@-uuP`;=wod z2wd@&m3Egx5xFa;_|2L{-HpsVvV*A(z2Os94RY~u(k-Kb@N@sN072@#N z^5UpKu}F}zQD@AZKxt9$z_u0lbbiAp2|xN~)K6z7S0~wbG89SUEyFK`hAXZQI@Awe3$67~np|f9 z5Ol2G=|37SGE6Lh-h9u1^nNb);Q7Y0Y@QL4pB~Dv?)r;_9LuB*g-AiGT&-b=-Ffs@ z=$WWNP|hwd-5f*pyc_t#I%ZyE|Ah;aEVXa``z%EZNKUF+$hTsn&B?74)0(%OxO!CCSZWPfFA$4**f~)iMGK-OG8$ed{oFz{c@yKO zH*hBY{y;3-9bUJwpr`uMePjKC8jQD(q33(Dm9)0#O6+#TyT)ZuQpcP~0qJeRh*zRQ)IX_mh7n--Nz& z!anOoSQtSQ@8+$4Zs%VJc2RE#KGdu)+#Ns5Jm&oixZNz-5&h=ZCj+s;Ex*k9nl;*T zXoD$_T-yPhO(5IJSenZ$KA|~-OW;AD^OT9|&!QEcw(%Cj9pNXD8?q9~vY`zF`anzN z@joM5(~-hQ`cLi0x9mxo)@{4VZk-`>SE6HcN*1w~)Q9nBGpT$@~zwN`evljQHS_v&FDHt`y z$K>m>0nGm5NtXBv2>)ylT?I(8k72J{%kqtJ5r|y|NXVfi0d9cX>CzKO_0(m?d@Z{94-p2e%`y%%Wm{`0(R-AwwFPped zJIiOg4tZ0Fi{?dv3t{N$h~aB4pn&FzCat@SG?LA;(UDqFq`y?CUb5Z%_e-tLw3q!q zM260L2U-Tqvw`YYja;{_x*Q*&{|x)7K5x=}3;I@y18oakguCC-U8Rz;agLT#RufcY z3wz);Fgv^J(n26!8{Khz6UkCdcY4NBU1~4;|h#>9L8Zuz$nH|8Wgjo6A zW#mk|(`W5vCcFEQb!(TMVCHp$@8f3|QZC5Ek^>`}l-{Knf95%qaGNxtY$umWuB50) z1&BhG5DwVxN7ZhWtwMb^bJI&4-J33A6s@d^dXm^DgT~frLJ_a$T-zu9oHLiWJFs9f8&KtZw&{M6~rdVlNGCur-spBwhC=s6JJ5;jEKs6$=o08j+l0Jl&yOV?FZE6 zdTP51Xr!xfoCpH}qw*-fQj6(=y$o*~Jr)@qE4EFqIX{<6!(N=kauHu|e}=lQ$GFMj zo_P{41iuYdl(Hmaid~J4C_hs$YpM`33@Qpi4n^S$3JN|K6=AjyumAjhYS*Yb+Wgt{3=kqF1S?)UqEHGgj?J%;$0X0}l=mX983LXe zd*H0q6hd}UJpC|KrH3{m7+-SWjCFd5Tbkt8={2^1z^`?EuSICsw&p&2PKEA$GMW7~ zHA^shlMZ8z(zOGNJ7AAzRLj~k$eZati{G|5Oug?i9cZ zJ|jY~YJi@Wq2g|KaBfFOIlR~w9Br~l58!vfX@55%L-cM-_lMYS7{uwiny$Bk!}j(g4C%<(Q9Iz03{*PU+QB zf2$F+Jim<-uR`4DeXQ$}>TAX$XO^~yc757~79t$$P`+E{i_iS?RKfdItaUx+q=u&e z?~>~HE_7#M?9=s)Pkq4e*Z2U>eMiZy(fo}gpueVKg(_{>iM?Ooe5ATkfraFnDfv8 z)^^71r~DhFx}9-CF;V3X4kPNYII%HBM>mQWc<95mwMQd|Rr6X!%Y{GEGR-nRV*l|F zn^YS#yH_i5BS(P#*UnUO;GYA#^ddBMr$B*)#y>BDPhY{iv#m%tyO1E_024=l{1<)a!H3pN|t+fa2 z0nhGZNvwDOHZ`W8bVrQqB|bVjuBO3Z#Jrp9O0xzu9lp=Wvh=+n%IUY0`*qiD(c^`rSCpI@1bMsbyb%~duxaB&K1MFk*By|LoCAZfQk zMJCUzupgW?B6MqVJBRe>22rub9buyK^C#>`F5*A?C2;gMi5dI~E@mX^ubph?<6;?64_^!!xaq zT5ylPaBAu$8&mnbyVLJF(nFO!kjnT@f9H2^6-Wf8S<8 zR$DYqImq@TgnK*A@RKu$Evh_J3gxm6Ad9HS6O;x|j!ONuUVWzxg_%MkXBL&jom=0r8?u&CVA!z8L2OUlaN39qUDmoR@ z2+w^IJ6v;5AWQ@ z-di>{mee_DHh!AXo1Tw*)h1nr$WNGs85=n4=~q-}KiH=Dso^19E2{u3Ehl;VB+V{!_-i;wI%3Med(FHAY-;vXtR# zU5vJ0(K*^@_ND$QjHQWdd<8wOe2T}Dn`NEr7G>bZSQ*GF8N%5E(UEi3Rk)@32O(5@ zx=2OEfd4th;bS+JbF@CTgXB`zW2kYE;Bd5#LqnAV4{qlS1HX+K3y*(b%&J_`G|@4h zFSzQJhvLR*Tr(($+h>Za~fPvezkZp(*(J^@m%5) z^*$>23*gHfs?a&6F>Y*eXK|Dn{1RRF!1`G+g-@r-_H;6t%h$$h)=P^D*GqfngS4Df z3{;W_++*k^h3Yq9atNlbO0y~z1xp{IK8hk&gv`G^+AotU z0R>_gW<@rFmX1iJ>lXisxvjszN?n^Rw>Gx?s0|^)UNT>vurJ|T&OLZD7q3m^u~ zOs3YMDLWtEBsK?ezB&!Rog@+u^^^wYDJj|jPW9|?`!oo)hNp!Ba2EF4O5wl%kxv0(zyEpTQ4xw%$^UtU+$8J)zJI%M)BGmE zIOHZ3Mb^#yWTklSg5b9|!+t3-8UGqT8BR}~VxDhpQieyJs<22+O7696ECt6{eoH;R zBJau^GaVoNzMqS^c<6fsq6AIr%`-oh@x=tlgL|x#PlsW@(cT%?iQc?v?D9?7r%UG% z%98J{T$7e!aQr{}Nc`gY#C%KmkC4!qh=olVtUnct>Byzm)vIHPU{&XaF__|3wUV-`=V%gBBf}`&=2-CRKoU=dbIU0M zbezcFJ>tG3?Q>gA$0RyWUR1OMNF!}Vn#8}p=oEQgv`$ayUtjWX^rw2{4{ofFSW_U* zlt5%UT`~*Cse1TF&cTZO1+NP+^t9)=nuW}9psZ2v`IA^X?giV+k)s@&(M|=DvFHUB zvKSc1pYBTUNEM0POd;@E0+ev}Wi<>Apj@TM0Hwy~49_fbF8%^^WekS{3E=&8Z*bjc zDwn*d_0;Bwzj&I&&B&;*EGPZ!_J&6BK(Ln>_BU8WK@niDYCR*$5sV);30jBFmir98pT;<9+Uf%MBmVMV)%!f>D7do3V@M)5x%y-!& z!QP+N+I?j8i|ENrmu6q>r;mEnZ1J7HJ=?mb40vX=-6#t+=*r*74#QP+DgiiK*(jC|e?Tn$eB1+@7dY1ov1zxo!lld2%uw5vJC z^%pSH*zRizJ;q(Bo=+X&vkAN>35sE>503P(aMMe%0sbJHJA|C~PWrrr3)loZt%mAy z>!fj(uu7$Ogx=N!zs%SMy;Hpf+4zu(h^(7_nVQuCRRVMMnvBEJxcA2xZK%W7k#(-mOxw0DAw6^oY{|Y;3_tvm zPbSxrJw*E^BvlPOkb3;mZZP)mPe0F^o67+i{yc4`!%cWZN={A$iikbF|C{cg+2}tb z&^FfFCMDe80DlV2l^*2jP(9J_m<#(001?v4Ib)h@w!Z*E)&6a%ON7fF$iF%3^zb}l zHT7EvLA>JMaB#7rsWzj`&T2DUR=Tre$F!Qjzk70xP~HCvxTFy<`+7$K`T3e)a~E{D z&UwSBdU0&5rNbkmQaVGNC$#v8*g5PRpR`2aOQ!ApW?B2$%ow2OR?1^sTn4AwdmE5_ zTq!O&<{|D}c7Bjaz{%1=ergur*rm&r-Ux&6Ty)!nHj$=(%tZgW=WP72XFw>@=G&Q` zfyD>ZM7KsXqx6lM0(pQN4sK^6J<1F1#YJ`>etpv27o)s-8go+)1l=p1dx^gAHOm;! z{*d`UK9Ygv8#yucnUv~@&8AN_T~wWGPEMpXoAu3+3WeE650A&4I$6en>_)~>6;&T1 z#rPi^aW+8W(14^s!Ii(FQwaZf822SLqIWFOBMn!f*gad z%ZV2V)n)N1&_+(`f#3!dj;+jkNsQ zhB9u5@T8F_4t*h{5#$RjL$wdB{2r85HAgge3#hAj|4hVX z76^}UAqmObAN+Od;a4}0mOWH*wbPE-J~`K%dlF_9&N`9&!(Y|ow+o-2xEH^A2I>~j zvhhwZIM-fynH1bLK7T24UbK)DqA#Uq2rE!Yi*KOV$55L&%D|((J9(8=5-X01c`M+ zG03K*FO)@OID1=NOcP0ZrYs?>*8Ufb);w>p@$HoW(YISa*MWrMGUH|gwIzYTXZF`m%UWp+Po>&OdFu* z%&4|ph3PVC)}roV{T_TEgYvo+C^+JKV>6QM7uyqvvZi@}E$pL5O7R=Zmp?XQ=*;Eq z<3q&`Y$nC46&9N(YJPD(%CP;uoWS$yRj;Nd));cdzhbqBn0K>u8F&6!U8jM_DWzJ$ z_QU!+1MZ2six=LAjI(YbnjVGD0g*4Z<&YSw*T2h)-V3WXNWo_=RApvdj%3(3(WAlN zE;)MAjZI16`O^p9G03H$r;HlfUml8{*suGG=Bdd!7{>OXI%i}^UuRs&C0ZTUsM#L8 z0fth@Kd4ob_Tx48qb&F3rzDL?fA(It_&5G1{{j`9p#<7EJDr%4VI$p+E>YqKRbezu zdunW29rf4b^Dq3ITO|*sLaRpMF)4$G{0m4qf)M@`X{df7qxT)un!ePrAH`(lNkv`f z0gW>0^sfA`7=u{-%f{J&bhl{1Ekh&(Gw-%);IbE&y$oBx(|38Oo(|UvZKo;DF0=+EzL*ROs4!Qz@0 z7@sItn@;s5Z(mMz!@x+{_jma~@n66Tw@ApE5}M`ShmDU?sP(q6L=nJKOo3G?$h1pr z%SSl{|6{cdMn|wq_+g~j&H6(L`#y_6!+){U)o;>d5znD#9}u?G7*lrNn)apC0+u4YstS{V;TulWt0t-ZuQ;#7CoDvB^Hl z3&qaWn&Zh_)V{EKD?p7v94$r=V*btCD4zEj-ur#LA}=O0<~@X9)3u^Of@I#M)%<3| z=NJKev-){BG|Ajb`XN+)!U#WOpOJDXvZ(jmS}F+oy+D_#%57vqUDs#|JU8Yh>GhRn zMD2QTlMjE${P04}U*)>u=*}J=OUa)z@(tsXd36P&jsupF@f9 zlT|;}G-jJN1zUmcxd|hNfqeNmr`YD=MzNXOs+%ADmCyCR^kGzG0A@($bRaNhyS4>RKO-(I8L56>SE zZQ>A*O&Uk9t3sC*a>3GOd{t}0t)dGu=H2VwOj~r!9?|zc=(a8IqhpIU1Zbp^?t7IS zm1xI!pEan)4x+-5muY_iYzjb^18{G(KRY3O4Wdo6xcEd5uWiY@1JoxycnIfh#S52| z=lVP?pPY`U{KO_8T}yiBM*a~v*@GIHO~3!UD%Et4mE{BRimBot8EvUSPdh~g-*ytD zKXSg34(BWEuebiw!K?V1B;e_=%^BI9^!rqM&Oage-Kw1n{kV%a4W%L-uE(DjKV_f> zic1mB`;qm#!R*-0cJUg6x@*d3*dckVnR_{vzWxAZOm=b*+v(mHgo*E zDLBu6?s9}*UPfbMTn+C0EL`-^TJ+?-&Sb@?m97>dW=Z)PRBZ`2$ z(BFO0<|E)gBh!9!-3IraeDq77^>%ovJGuO*WRCBX;psVYpR*@gOVm~7?$qjc7lIJ7 zGK0T>G-}mqEBx$$;Iv`R+z@n!tqsCrI%Q8YlG%iE(n=k4+DkoC0#>de2svp{WEN=9 zhVViwzvf!=sUsmttx*}zCAM4fEoEHAa@gFRCRz{fhVR z_X^G1C8vtSCc<$0`;c;Fy>YIwOs&Afw6*G{4Ho@39VUoRKFauIQRdJV84{7yr|qUX z{R-8@l_Xam<-CKWEn0D{$+wJ$<-;(H-=2|sF?0#gRu*Y zZw4dd8sJgPH8w4e1XC-Tg^!EUEC|)-;z#dw=cT{oI+IJ2UspnK|F{ z{jQdF!?ePD>cNU{AXv%^i_Y>r4mY=-A)8@?bS2pqwyD&lvcENJy4vZ(n;m(JjTj2a z4>hNPuBe{i_;Ts=+s(7hLS(2QV6CGi8W?;0Y+3j2X`oAn0C`27CDtrI=bEtdGH%Ul z=ao`iB8J(;FMckYn~K>-UQ&Pd78P{~#pP$8Op=kdg1Tu5mL=%+2_o6tQA6gtK`OnTi}5Mf z{M*}UC_`elS(-=W;q)5WES3vKJsCPVp!ht9HX~0V`!!0lQ{sKj#5V~5C^p8y=T*X2 z=CpTM@*i?O=cQX&pf9gKpf|tP?lZZ%s(u8ZEhVbSlG~VW?ek475O+?@*`AhU2=^_G z_eF~VkK+id_;wep;gfF~nyPd_!L_E6OW5Yq;PR%R{o+RIiF1Ux`R+y|h6iVr;N`S- ze~O*ztoD8loY!H|53E8y>cWm6@1|y3-F_CPFII25vUTg&oVtOq3meMVy&u6FD^=KB@C@P54wVKPCk)<}XUAqLjmRGN)*cFvlua(22dy%-)V3^<_SMQ=VytS%# z-uh=zK`cAi0NY!BP}bZNyRrsDTRT+~?!*P}w=&-pWfEa4)>nY>7TpR*B(vm{j~jSPDss zxLOLETy*j0DL&ddc%=68JcfkIx}^>8t!&n6TO!ADm3S^>7A{NpwmOpXOT7ybH|1=x zveOf+USKI4T`^^dg0_&bqo~z)lbH=A#+OCzY}Q?D1-m7q;bzXi$L`g=iBVZbwzwm+ zE~7KzSKy1uD^@qDT$K-nW9qNu>5UpYPjL{?06Q8?AA|&^^lTu#WBP;9P-`GR!(CXa% z8{FYU@6nk%ZSO4Io%zJkCR82S50R2R11x)Qo3zAr!K~3`3`lJKT-=K4m6T}lF$2#R z7t|EW!|wkT6VK8oT1Y>C1Y}iQS9!}dQk_B+kiEcIl__n^XbO$V&v)fsbt2Ja9EaD< zi&BMKRJKM-;y=%s#@)IP&?R8MOi!#HBHeQF?ILirBhQ3bPUKk@=oSb|sjgn>9F%y3 zk<&*3(2ObsS+eepN&A={BJ{095=R4X{&@f7KM&!@^xFqNV`3&cDYf+)klR~BIV4dz zbmgG@cN1;$j%}W@{-<-=qmJ=e0ToB0QSys4H)S=I2RN_m6#g=w;JSRGZ8JF3Dk_&nwLta6xT`J{*qu(|(urpGFIbkY7e6`-Q4guNbF|@&bMo=R= zE-u=BnFRzxdF>1$FtO3RSW~{2no+=Y(A5A84q#d|vafz!gd!3|N2F<0b#Z7Ut(dLs zcB zx<2m3*c6@=Dw{?du-mRLP|wa1<@_*jjc|Vt_-;DP61?n+ZR#5id3R0U>nju+zaNksr#l6$s_i`nSXpl5QD$e z(KyFfWTxC_@Jae-;?GZ?$A5@>9xvhlBIX-Pbq4Sjb+SqPIgQyL<;tczj4Y<{W{lFn zH=Yv^v44mm3ES53uPt)2v51%+kUeD4=en4Yn$p?yxepx|TZNzD>5hwi5#v4JEYpAe zb+>Q2Uw!{{->eQXx95GJd~deSU6#J5Z&UCHfP1i)H~kFK=u}7U&Hp-Us3UC|_LjUo z6O;kz^ObcJmJn|K7J&QFbJiz2NC0@;9Xx$FLV8KoSlRQx)(!XCR|rjp4KfWlQ#8rb zvn3Qm^f_lwho|sY$jDmR5M5$1{bzUyoWo!)gd)%2%v08Fy@yox)>$;V7J=kYyjMb) z_<9f9Z=o!THw=17RyO3bh{m+|tMDJ!!tTql$Z{bc_=z7>0hw!Su%ITx&c;U3Sh6Pc z%*%ehgh%R2#`Nn{NlKGo-TS!+AJ@J{Y8Cb5Clb!j^`?7b+3kzw%KKF7DwPW4D=On! zKK>YWnx#27WHl!zZ)ryzG{`E2hi_#&by0pQvd+1G1epHbD|z;eq{sz2r*^qF2oY2L z*=I&7(&r6XOPW0u2lLGtTN1J}RH>g?vnLp! zm zlW?KY#N`Wd7IhwHbr|WjKZ<7Sy?0}ImF7JAA|V!TV(Q#|U}~l+^L1~8`?o}osdAGq zyE=+goK5C>+j>!Z4h@PaU#8pC=HukY{>kvPsA~7=* zi!x3NIYP(i0@u}Y@n$|yBESUkV$M`O2?`=de-2@JB6qeSEKeh&1@xjoDD)0^4kE3+6S}M4ix7{A_pmBh?R8-c{RYslm9$ZIx zC^ZGF-Y!?wWm^_RhVQoIqgKA0SpKZ@Fz2n|Z(ai>$riiHRkflvh+!V_pSD|Mb!CrS<4kcBBEp)&08ZqliAcGCCOF&09wdy=tk=-xvK9|)Nc5ETHczH z)ai9=8}7W78*aaIj@rBiyYf#ASmNiiW=~W_5|*X;0eX`4JsOTD+4; zxi!-1dKoy7%|}A&@%e@sgI}Phg`Uty8Eso5aHk=8RTrpWX}L$-Zq`a4n$cSbF#UpLNImk_|tXrzUS*#DY^{`q)ue5!9Dq^imcu0ted44p@It1^}zKe|i|Kgjrqc~Gpj_0$ zo=PQsGL~Iug_45*mHwok$vAEanJVviN4O^9~?mg>t60Mo#p753i4jVDM!o( zQU(6DX@kGUoR+_rdd@jv4hhiN`d)+mThS}B_Y{}gf`Y|zl}pejI(6MvlySnOnrb3J zN5hIEly{JWEy>>Ico`s!u9ArPMWd|TIP5N|8ryxdMtIuK$kYD$D{ed*uMwb*aE=ha zz;-!7xq&68rg3$~n2NznpXRzY*Cf3@I-_<9vL%+7dXFHzpz;wFZOz@k4{jEHHM8%k z(hzw+V!HJbDXfBb=ruH5a5ln`RMyvQKz{WJmaK1(oAdP%P<{XWWb~my|N0TIXId2n zf0C{XOiupl6`Nw%mGE&_Bi_)8=<3Q)L!O0fb!+*+$O@8WFRPx;cn5NpH5 zY>_=W%*-rt&-_cUMHQRaPud>J>K;=M(SxX+)Ggir0(~JFi4+a| zG9l@n<|gp`MehW)eXpn1L2{#8ByMZVo0#H6)(qNI+FW!Epdii2Lt6;!%akLunpcr= zAYeE8M1 zPYG%VAho=7hv{XmW-HJK5q}RJC!HYf98a%5I4>!y^Suquitrgs62>`jE0ejQuD7y+ z%u`?`gSz6V)0~*l(`Xo6Z*Nt4_x`X{D5sLypompO+rW@`9rP3`37Sm0f>ep_Z4DGL zPYLZ7A-~1Eh^P9(&2SN;v4Wj%GJ~Z+P9eM@Y7q&%OJc2xc{lF3+jbS2=wdPV-qvC1 z?^>?p{(SG|98d46sm#tstRyymMXno5ozK?y1G6sqR;DyS^jN;uR%(${JxpzE5Ao>; z3}i4@%r0qOJu-*-mF;w)iE_OFAcb>qP5?;vi@og|5`IW-(8UXKD)(g0snLO0w~v(z zOL7wSho>|k&{zb1>l6(=MlzK%bsM`2wEkOExyPCN&i0HxRQPltxaiBDHx~y<(X-}< z-&PY3;`psyEN9G2ut7Dn_>$%Tzirx3U$JiO$X%@L9ib#_`}l6o_?d;@4%kqcHqj*e zpS>D2wIVM~QVbcW#bNKZMTl+r-`$U44whM4UY404<~DB-?BYH}o|Gzwe^G#`&f^oc zc@X^SdM;KXd_Y)i{vKB%-h&Q$lHx$BgS1rthSD)j@?7ksgM2CU1=xv;vPGTCdu%raLI?& z7B5ba`FF#rs`@F@OeO#OhMNaYCa?k0uKxl}5T zNjx5b-?&r4mz^d>qH-t#{MG@nXITOSdrysk4eC$JHy9`2>K6qGu78JfDI9WZ^I6W| zj3pcJDakq7>I2=ez#>mfD9S*eb-H6PFyV7Gj&}P^Ri@{v@#b`PSD#cQ1k6uU<==vGsYR} zf{;mYm;qj`jTfoAMh97SZCcE#SrAWOFH!xTwi@)Pr89UUyHbypQg609%sqv*ygK;N z@{48cg(&|QlqSi5CQI!m9Zzc{Jb{uL=*)GAiODBn|6`1vom62n{O??x08}lOB}&ao zeYvi?LnW4r;{9bMM)EI^*IS4V!gtGel>Y|zRWj!|m0@u<4fKLyf3rOGNqHD-^wEDpk7z372=^?5eRx)&M+M2Lh3^DDGc6@!%`18uO~0JT5bJ9ySjN1G=5 zHDITf@uL>JR5yu})4m##Vj}^y1AxFEQRfcYSC50t2_}6^$4?_8ozz{gjRYh!cdmg`e34$J8ydwu&sY~WOg)`H_lgls@owRswR#_qtelv2VE^)5qf8}s~ZcD3xIoen-@k2jGG+Fp- zy_D|*EO#R6Zi<(Ynw`|RaE{SXblIHC7OJK5d~Q|omn+U$v+A{%o9Nplc$z;RdFj_I*4A(_GK;!E42!v-|i6^gy-7Ax|fyHe7N3>)-a`AfQ>7 zRj+0HTl3#i^s8RSYiK30Tx9LZoC9V|=P@04#C{8fP>z%Ee8vJ^T)MfOAz&*?Q6A_< z_}VP0*}dxk!xVmx3p%)lmMT9J&aH(H)z>}v?C@eHSgTecRmvqW`Y4IM%FP`|Zm zoSO$MlnPw9X+0b8dg7d)tDQEd{j#Y9CK9}JvL*;yMLXC>q92!F~m8;vE z6lLOmE9PoClBRQT)hTkAxmE5^P1bhVC&Sx0>|PB4X)cUn4$ja`gqeLs0|-)vG3ysD~zD*58@z0g694wdByohaU~ zM7Oo+-LgHq{Xs3pFVP75L+xX`Qx_(DdSa9BAXHIhIv(A8Scu^(T+6Q)S+DHA$se9d zQ`BU1n;hfh>3&!S)@UTO32=$|Yvn5gkCZ0VT8d`e4hj+|Z69A7Jkto=LlO__+AD|Q zu*qyRl4?Z>9JJG4qMzTDISraT0z#bdYKlDC zr;OY7l6!6UQRn6VT{;2(M1(<=tTehmd6GlPf9ZroUt(#C@BH;rXMd@vn6h5zI_$Jm zH6cFOIhs@66rz3hcS#o-DI%kSwQ(+1aJBA`GX zlFjHuT%3p9+gr9RT@GIFcQLae4XtC=z1=Vc2+^^)YiK<||5#|bl&%0Qemnue$*p=b2r3 zAfu|s%}SWOAMPA*6;J*;+%kD|-)UCPo(64NFO{9WPSqb37r7U*TgeXR%~zCzTiTsm zA39^q>qh*vx+6ZS#T%5VqjDy-TE6v0&x5`re7NLgDV`cQkX3p+a|0}c;a9@l443bU zM2ejAbUI^Ls1=j>94wuXxepT&$-h^Ucn&O1`v*edR`O``Q?}n75d!86jWmnlt$QmY z&D+HDU7#M!frNjkx%YXxj`LYBRtYzVzE)xNm(oK)DJs+ zIk6oRAsY!Br@~D!^~vthK6lv2fG4{ib^Aw8g&Jp!bF{xONirrs+;m`;`l`tD!vsuU z;eELHTP;G$M0_!(&797dl~DrSj;+7i**FPyD`rnN#;N6*94rR0@muEXxhBaP1YeRa zU}V*m#1t7KcVhKY*9{95gGHe_<6=HzjX7Iq3Y`-;=Tp2K(+BU73(&3j8nQz+@y@II zYEOpEXg+R)Xk}BVXm>?vrzy+8tZc=nWE(ZN?-F_KsA-v@8=xy%UU-`0Pl;PC2rZ{!s_SH#P}Q zB1GGAgWX-qu0D64khU}4y@P5^JJ#!CkTBqVZFai6tqTo@de z-&Nz_W ze2K=Wy$LZbK7u`t-A$0*=a@?+@7XM9qoGGbDNlHQ zUo&Un&=tXPLqH`2-`U8dv?x1n{$v;ZI@|;+$n1B66J-+-O**tS#-lLC0#6feW-Y1| z;m_x3onph+w$@)DS%H#$XvE|VGCL5>L0pNOUh{gn6Q5iPp|JMcC{$KzQ|c(!Rv-$6 zg;6r}p-Pyh`jQytICFR0*r0K)@o;obht|9Ue*{E4R6)OkT0nL`-PWcn&;`nt9szMY zYmb2aL*PAQT7}Cm?chnV5sraca8>C*NY=C?Ak2s>+_xqX1g-~#dW!dEt^Nc?3s7#s8(-TL}`Sn zs8oPs5)T}6GRoXmtPe+v=JNT%Qvx5Q$d6L(8O{>sWORQI8!}dk8A85I8c!U3tH>VW zb4(n5&!=#Fd)*w!zRSMCl4z7@k}X(jVe$HQw_6h3e0KR^pE}IjZL2IY zuw%7FCEuBMzra*NDD3{r9ET-EM;o+4w!ZE=ZsaZ57VpoEQH86k{scXqZcrySkknE-#WUo@l=AMA$3Z}rGhb5dLLma-lCSx?EA zo*wrynBlP*r9Hv6MSQ>u!tH|$U$48B5Goe!{=Olqq$`|i46wxb43c^-2zFTITE_eE z2*AeX&>=akUQ4ko6CehCI*?~9qED>Q`*x5MK0y74xsD+CbBMi5i1~u(9Ys@JHp@(k zUqCv3D>fT_kYPBj$}fUa6qWP}q)hL!I2~u>od2^{WG+!*7>>d#>z*U`)Pxp_xRG-i z@4-EfGZF+b2+2ORzZbe_1mo*L_%3XGY*1eJ;}i5k>d#@@r=$+e{2 zb32|vNJ?XykZWDHxX<%iB8l%8nED;PL{^fx_v$`PPvf|UMpg(zCCy#jLU~dUYk0wU zXY41PIykalId2?M;9jR1*|_e7^y`KDgM&fm2&!v$l1Kwjr$dA99#3MnoIG=#QxaE3 zhK&@-wH%-v#%;pyx^`v{j+zxg+EP7kzh(joa>p8cLq5`|q8N{HSK|3)$5t5TJr>Vy zQG}>{i#0CN0m+<`g@cFBC9SOb!iVMU$?fUaquis%OTwGdsyhn{dE>tLC#MsY3|F3* zZ+J2kB^a`_z0YSHw{5J3RvjKL%r-`E4)5d7i@}!!z99C!vLGw#-eMaY_Mo=IdBHrd zE{mq2*C^kNg_O`&TeyC^L?qH~Iv{6h1XfG8d4-sTWA*)Qck?U-X`c1Pan4|ah3WBn zu)2lW9VR#9FtYk0tN1m?v&u+j$Qiej=g~Jwtwlws{r2^uQDb%ErT(``Gs`N^gv<92 z$qwj23gH?jH^oz=zL=RUv!IZDJf)e*b3eBd=&MO8zo%T^9OfZ#n>~T+<@Bh)Hg!| z`+@|_J9mr2oA8`jUksP1?ydlSh;|e`I6?z|WSDT=e^n1Wl7Uw10Jlcq5GqUx&K%FS zxzt}5u~f+%DXbh@a+jx=o71f<50F)>lz`fWf%@(Ohk-7G%~g}%a`leOrEZw1PRAgz`+0S1d56KItdD?uOWT8~2dhFvTYD;~`nD2&i9(LY zZ^U=H&+l!RKl}xnXYGU6S-hHZr#~lru5~3fKb#C*ss36#!2VF+aBJ%1exCUJ8Xe!o zbs0$KU`#fHor)>20~3Q1E+$`eoN(Yt+PtvT`V}q7jqT7$Cl!AQ!L8ir}6CrIXpOJZ_$SY)q1awMaZRE6)kjR$&3@h1g%duCp4WT#Rn8t258Nf@y z_Tv&~_M)X6(L>Wi$pYIfms_Z}@)S8t&1evo+0y4VF>*k(&#H#2bEyl&&r$J~VTcfXqd*_fmauFAQtaCk1qDa*cvQ}{+JfG;35sySa& z1ELd*!n_gS)4r+sDDj^pm(N?Z&;FPpm$mDZHPO;A<>2r!B#xp;N;)>EFZ<0xCI++e(Elwvc9`eTt&Cx+KzoV5z0oHtU z5XoETW_eG1Iu{Y1affzQAP?G~{4FIDU($w9m^!g04Z& z;R?tk>Ww<J@_S@EK^ec{tPE_!BkW)nCeu|md zf>G+}RAJC84~G|tEt7rRJ{|+$%~;dQSk6MD?@qw9zohJKPc(Ek6`R2&_nnrTH1%jK z1!rO?-8dAo_sf5gTCe{iwf4&6rWeNhCPL0SE8c8lyzce4O-N0Q`}(St^qILxSjZk$ zV(kpu&5nl`?IS?0Nw1^2?5iprqS0sTr?OW2G@~op*Q&F9<{9zT zzkHTm(eEk?Jazv{|Kj*g@*&cOyW9w-kJka*A(5aQyz~g-sGm7yGwsrZVWH9;q`JRs ziU{QzT_J7xPcV^cLGvB!m2~kS=Y)LaC8pS92enwa6QU>=XKE@a)#<3Nark$eBf(o4 zA)jW&xjf-XG3k}Ye7D!>mXQ+?S_v^smW#7|bB4@S=%qk<`#PO+^_%ofCf@0}+InS$ z?NoO7CkFPEKJWPbFbezmP~L;vUZgu)7)i(14%@mO$PDFEl~dOg$^^REDMFvKQo$CR zJ|Cv1*n=VE+jh95bpn`pKIa6mzZ^q{4h||(UfJ1pS9sGfjS1ET@CCJurI^ONMku)U zmCRGL$kHA|-5;I4Z`)yU*7`;7=OGeiq7(pXQNVW=DqS>2=pO@ zX>a8^;$d}zM{KZ*M9Vhj@H7Zp@X)@R16=I^frW%Ro}B1q@RA}C-Ff4%J>VNf${>qD zz3g$jYhHF+?L85L`#9Z;?SK7k&0l`j)Cdd`ALXzTioOT0gOoEK0h%|Y;-Q>kr1?(N z-cK`^kxN=XMYC$n9Ea%p7p|a7;QpDgl%=DT)2DhKF#*Do@}T2Hcl zWBT-v=k}oZ2PD)^VT)gxX=Fox@U<3ayHIqe#aixFkSB0^?m#cN2^^I9qkY`J=$%m9 zh^4uCBaQfrID@^-_!?z?`7c#Pppz*GXKRW-1MnhAJX#oOd|pwy-dv~jpyZvS_1-D) zR!n72#dB%@M!d*8)h*0B>w)ZoCh!=g4B*|#UP0NsEz5KmA|4IgiS2I;+CT-zPF=he z%C(nF{}luU6r&>RJ@@7(oBUhi0iv=moCV_=Q81Zceb-~*#;7b$P|O`XZIbVWw}bKn zQUc}N9D{8*S0VfQRH9+@zzaX`XxNUroP1slZ*Gn*ws97ca_R0@n-nFye6b1OATG;IIct@x8agO7{Gd;70%l z>>@U7y#`T`A};Sl6J|OC(q>N4m(h3amKPNAszHf8q3~WFhwF1qHNcQZz)MGUrjQ4@BDro6P2noSdq1u#kbU;aFqa9$ z>d+pmhl@G;+y5)VB6+~n2?TlHIWA?3(RDUGz_RMX#ev2l=T4raSE1pyZ&jwyPfRaj zuQy&Jm%TV10a0BgNQD#GN!TNRntum0H>>gM0d-P*z0<6)b}b(4d4YNc>Vk6C>djpw z#}PS@>Fv-2Vi`E8&w7_5u7lV42sqWl1e&umif^K-0HU6N;efnjNh{*6$#%5n0dLiV z*(-5ZP~?^anm=(4Toi>?*0K&;^9#Hd zn+Ud`0McC;NeDlqnhFI9Q-efl$hCkon4e;)$s_wHS6#~lStEWlmRB;buy2wSuFD0W)2^Eb-fag)s zMSPIw5Q-$i3H%^;v@F z(RTlnvBacd>kGJpu$|L3S}=QIJj`qU3PC;>y1XWawLJ;N`NVV9&&$a3iKqPF)Ra0y zp6brDi5ztjja`^5^j~|@{+Si=BD?E7ayY!YsAwMH67QknZ!t$A1)eAtcFEo14T|rPJp!WZk!lwe zWgnYTq+vY^_sl(b|9YQD2sLy}7scY#Ya-$+5vo(yqW`Q{oK|@AIeXldp7vm|E1>F4i_AsscuI zCF@tWG8lrYR6GCJvMzQr(Zekv?ENKY5~}JTm-CPVQ*gfQ{r8~`VWjl$-2a_HS-T~d z9wE_#Wf2~zWKdCA(7q{$c7C(6x9c&Z^T+=;z}109Zeq>0t9a)j3yl~5rd}mQ!GF(^ zo4A^K_G`PC%$36l|lCJ&kna^m3?;@O2q@$DGeBZ;4uyv|fdJxY#HqN zuED~_5Uoy4oco8jF{~5DR}&t`O^nk4+>0OdI2XBJ@f_M_;@Zw&O-OH{+=yy}x+Bx> zQa7#HDL!wsbm%_HCAeXjBP@TWOdkEg(S=PPg>;XJWvbL3|F}En%$Zi>?d5!MDyNdP z;s+a9G_-3OGt+IRFX9|65RF>MB7Ob_($1awb52U~{8gFkf>9-OkaQ?xqq$GoSlm)B ztE?Tg&uIf$$^o%idMJ1I|4aktvze2fZ`g-;;36x{$E!vcYVMXdVp7Q}dw82T$LnvW zHvgz+3_cj>J)hTFlqdeKPl?r@fNcvQo6f|=`Q1z>a`Uc5NC#dv*HgA zpVzq*5uBT$h5UjrSn6Tbg=Y$!9on2`N;kHT&cwzj#^zQVV&(L6YC2k(*+Q_MhPk*< zWY72CAreMVJ5+-iH)9FvRu>(%8p*d_L%dT-Y= zz_&{O`Jf#a8erKJlbrmdmG+fr2=t{0hmiZ(SwT5H`KAUL?A%565umT+z1=LGX>oVD z@3ZU{(WNQaZi9aL3AvPRENhlJQRjkPuVTDi)ayi^LZtTz-!-f(z9UMcb|2H$y6r?zI*fu0Aa_x8K^22{&2b zS$hH%{}(m|)EfLLyXAGb`?2v+3Beqt@C-R;lt|R1%K#r8ij#02pS0O|b}OJhZRY|m zN|OS0%8a{I`b0Gp^_IF4LHE=_MvF#jhCbZ#w){Grvla}q(04SIoT#ywz~PxL%iAsG z%gfsxg-?WLXGqcYL2GG7YRjrBa=7G6eMX{QD;=yOcrEwbb=lPOAO^M1e{(MA6SlI( zl12{Ky#rnMP`|K2<W5AQarV*Is4K{}hLNIe#qeo`d^UmHGN zZai{G%L~GP+V%$U13!&i?c-ZiLKrIGil+Jnb!?hnX7Tm;H`gtTV%abk`Ph2EX^qOC zul75~{pJ{4o;V3VM=oeF1&hV;*)yl7DoLAoF%n$kFRVoy`^)+^dqh6p`0CK)Xdct0 zG?R&7y2_ErKMPCAgfa`Ax2unAo>CjWp{S24?lBot7;IaJNEJ181QU<-^->cTKTh zCRVsW|)O4UIP&Lnjwp?8O;ch#tjKZzv z2%S=yiF&sl&GD7X2uW?GrCi(PAjJWTVo;?nNTD$Co#kk27nyVdjuC@4dEcCx@5J3P@h5h(*RdiAd0`M8u6C`vm*F#>DF=vpt2K41xiA zh7t&$Ks5PN-?3$P4p}#S;oy9XA>Q>R(@&(5cvr>#PD`|N^y^KQc(&o~B7+`35?ZH6 zCtsnpU8t9YMREM)iENoy%3y!SsK)$OK{JQjdBPU?mH71*+1V2#g=5qsb zLi+iqt;v*?3s{UqWo>U3&f@W{dK}>%iW0xZLPe~ss#pYZDDJ;8s&^7A=<9{yi|n)!#HWM7{Xd~U3W0X z0;`67m^d#d&XM~K6tdC&qEJAS#_wDE^=&LI0|7CBBcr*~`^5X5J{OW!%n}t%zEL2W z>m5~nE+NeYf4lxV*Wm`CG0KO*BCPvdbgT86$ejnbH9s?8%IG`KY_}t zeu4BZLck)&HWQw);8hp%@TmRD!33TP9$73#LUN_2@Y~e3Vd39g+$RyrA+yFd`|D3| zW$->ro;(E-gokWH{}||oNagPusNmlwr7YBQZwuYuzr^ytk(PTJ9%1>5J)B?Kq@q4O z&MI7$vBi!$JcJg?>kJ;dHcZ<4%Jqr$&?@#|sJf~2(wFT0FeR0$??Gg>0J}ZAo4vzD z6|YTkH8?gWnOW`g-xo1Gqb?FP@T(~?Gu7nKZyRL~2mhJ=O+gb*O@lsul2%)MRNtVS1@vO&&1eYW2|roXV&$Q~_UU7h57;qsTP~ zCySXIOnxKSgFj@*c)!W_d05m3(0KPV%O7)V%Urn+ziKlfb6ZHm@z!(wl9$}5g8nmt zU{-U7K5{>l$0lYO_v8`qbkfOQi!%4rp*XPJ#cYDIOlE8=-iN+SxS-yn1QB3IF}WVV zS!AnYbQ_(atDmUGont|FFEiCISN?uhJ#bQQ42vu&{mUYDV`x`#2P=~D%dH2H?;>g+ zt3{Y_;z@Dl*j)qa`nQVq{KXPAii^OR3AS(UEi-bWxD=VoT!f*P+W?{)n;&6`i*@$h z%&hd}vJ5rzm`lLMc6Lt4rst`7^1_mW>J*K#YK=}%FKc7tKGRK_y)65a`jZiZi11F& z4&LI}Hy&+kBlXi;JObyqY=anTwH+soDuJ%WF?e3O1y^SXN^8wAeRPpzDW4lUb27>` z1BTX6gYAQo?q@SheYpH4*|`&qWV3Swn6ak9G%u_|hjNX=AdnpZP~q5yelxZntWc&p zOLf6yEwANp5Qp*2Nah+Lnh~qt};^e@H zs2g&9`xnqqyVv8dX5Ndw6Ms|qz`vm{w3M`3asAI2e^iaB5b?*v=f{76gET~=^*kG~ z6*TKbKZ8}qnKub%5|bBBWv5Mzv%MT{M+;v#3oEuyIK3L_;HyD{M>dPYX;^q}_Bs=0r2x4rclT`l8)FA2k)EoQ~B%^TfL34n((tG&bmL>HA$g0FyD($OiOHLCm1mWTEq-i6EisR^z3299-16>Y_EP% z{?b7Nh!%riSWbHIlngXE9Cwvu?g`=Mcg2zy??fuU4p2}g&d9c9i$MW2HT*w?A2rc_ zAAH?vci5qP&osBQEx8xD4B4USc!#F(G6SV$@r5KtnaS8-o0viFjwJgf*H7YaSxOmy z0mN-A{sR6Vdx?l&DCPe_M=f_gKP2)$q5(8s(!ONQ`AjVBknVsk_jYYK1Bln~Q>afJ zo?f8&f%rq-M~pz?Fx>)P8kP!C9F{<^r_iMib>1HAskCNa2sCeY%O#BUJ6B_WXk+IH zXSivqx}u=dBJWtC;+JtJM&cs*r-da31B=s4kmtb~+)o8KH;UP4*YVJof6Abr`Pwin z%RAo7-$~i(jag}1TgKQ{9`%_2zLGv2+_VjgiWTGU(!AsmkelKd5f%F^rNbQvSb!eQ1-A< z&Qrm$DAtesBBDif1_IyDB78d8C#djBju+f@5#)RB0h#&Q#zH)GUB>ow(7vC)>!rEwfT?NLO?=KwPxMUt}G(e-h=nMzFQ%E#5TwD&F3{UVNPa%XAr-3Z4TRR`L zI0|Yu&tjHU&hzFdmY5}8miEn>g6lsE!5#S%$;TzFN>aS`!z@zt}k9rbD|a;+SY(kO_=A({xyb#tj)?lZ%Dt?z0-1 z@EOL2<)4t0pTJ|~JZ)`obY7tGY9!1cM zrAi)vtX`%wsqs1!k#2sW-pXy2zSD2%rHQh4{jKr8TEp!bI>kRY`p6&#ci9$vYCw{7uCW^*?j``M$7QVHLfKQCl@_G5z2Zi57aZ5j`T>0|tLyXg)F>Lxk3YB*G{$l#H ziP}ZpI*9SdMr(yMy)s)1idm19q4uc}`WWqnZe>=cK+oYPajg+OT*nRK#+{_oqIkT>D z!AAKh?NlWFA{&yG5N0PZS0`KJ*d1C&LKxQZ<7cFfV1LoepK{ESc^X!{t5&MMSFfaG zH3ar|x2S3nqpO~l#eFk$pOB6J{pIS`{?A6JGwimZr6g~dB7ui4m%s`lTXB5ex~ zqt0$+??+0m|EH+$j%(t1{!SHcpcFwMh8jSr5v2%7@4ZGLlt4tfbScuC zfK=&7M?j=W@4cgdAS(Jh{CuC+^H(l=d%HWcvv)hQGxL6MfqCO`rg|~_?{b93BI-8a zzt;4_^)CqZW)Fx3eR8=R3(78k{TDNkKt%|0yriGCRW<{ zE2}^Rd+i^E>}yfow|L8l7OG4&#hp_!OOgQ*?QZz?z~NpEo-6-#alqmPrq}5j)p!~e zSJT8wuuufHZk9o>a56uWAJ{~6YS3uVge9bfymnUqTvxgHYUx{S_hh#P4^u-C@0)`r z{mGb=MJ0-g+gKvFdI>_$-zDPnY5=A(@#Oxu$G=_r>qPOOVtf&)Yc`eje&KYR_6jT~ z;>x?THf_nbl(daP-GnfnS+>_18%^1>Tf1MZSm(gf-z(A?$Wcrq?em%6nWQ%{D+1Im z*mAuiUqvgoDh}?P!B&yI+frVBGB0TEx5%7)G`K^LNJ!NL(8T#H$n2vB0k=5C2P^DE z;}W%HVofXqcMgP=*v=&Iv&JmT3j?far+e{tAR>`946l9|&On)@x-znU47?Q5dHJGc zcg(ZIoAs&T35R9U*zE8sO*)wzek5G}p*Vlv5z{d~{m}O7WhP`f;$itCqMGm8p&fV_ zNKnl%A|j-+d#P4f?1!*2g>eo7M|c73ZjdE75_pO}G?bzUkFZkGW>D%dhhU&N`CQ8C zL7;xxVnbJ4MAKi85=A|yOebnGF^^OoN)%zGFF?^f^kqIpLRbYb1ldZiR+Mhn6S0c; zmO4wyeKzw2f1Ic>$icn5Gmi5qoIwOS-&3^9y7NYA1r;_V zH)>Rd>%HtLtv|zu)B9_(z8;Fjh3sLUGvv0Jd?YnqK`n*ds6{NDsPLgd8!7;{*d79| zk;y!BT+O)xU{z$N>yN{Sgte=dR(dpW>};>^VU74Fq}4u{u*LN(v4QQr2HaUY6O#_B z_H=sE6QiZ&v3fL6i}pNSebK%u_I{OiqwapN%v0YPmQ5dtxgO^v-q69+sQX$Sp}xNrmp_!P>&r5d_xjaKG@tix z!iFD>h^L9{{`F&Clj)&HSdE0c7%Ha-0jp@~o~fx%_sT4c(wECW8lydyR5(R7??L6fl}po^CZsqpO)Y4#$JfFM2pnpM?1}A|_8=lb* zc7NVJy@KasE_$3Yh%gaxC~f&bT>IfYCx|tUbB<-Mn#b)RJ$|jMB&poKF@3MHcphAS z5OiSnQdpKr%^5w->VF%+%EXx@OP?p7R+6B=#L>XZfCk{K_wt|MH|6Vx`p>!lKn?z^n*y7p z5TTch)5QKXe?fABw5sL+nrHh*6_tdgS*?p}j`|lFAhfgdt0+`hfnGIIbfxwJ&=p&ZtQNaXyKJc-9_@K|i?`&6) z2v%3#qV;T@GSogYl-lrvvJ{*enJtKRpY<$_m1uB^Z4OU2DX$N_7kjVRo+|pIgUQ;6 zs_=`MNvhgW@oR03SJ{mgk{GFAabMh@W$!cO?(ShvN-L+uKvpjutw2*rzsLaGr%6oUdetYx{I}cihTgNkddDlI%j2B>DdyjUEyIZ->Yrwhhq1MOC z=E;XjWtkAZSK2P^@;;oxD3fB?J_o(0!3M4V=uCao|Fv&6*?^igb4h#!^jVkDbCb+= zp7oxWxBVokfg!C7=xL_O3T->r52m%*n!d%T$jt&*SLy1}d&*0Oj4mQ{)wd;CUe^_aV2jAY(HolPcii3e%s6mse#mZ7XiF%nrlze~-^&RYc) zqRt=o<4ErrqV-!Kn7nebmkoGDt;hlYbwjtHj0u|vXh5&;M)GwFcdcT_qt(;|FaL$d zg^!%l3LbOONmMwn{fM5HJd3jPxVOb|WzwHqpFOgq`F%=8(T_lM)sBC3A*qqD1+V8# z#{*Z(5DzwNedeOH7rVzE<;IfympQqT87pB0{opT!wTG5Mj>|)iP76m;T|MVzALTr7 zZcBJM$Apdl_sbh*6SPp&)KU|QIH2FW9!lb@cdgan_q)0uL{$jSCfyzT4RJ3;yz zSr|M$zKT9A9hSx)hHEzSRkCW#KY5g2A^*YkNss1)PZUX1kN8Cc^K5Lxf~&_EdiZIu z$-~K4;)Bry{h{4n6cc6)TtT2G8^luhctJuBy*OJrWsv)mmm1tj0&}p%lrB zTbit`04=S0+&dL18ypJUYSciFd&zjIF&`}6GP(1I+IL{n?Nm}cR1REjIN4n|M=KWN z^01{0izcxu2Y-^5Q@KY*R%EJNdf$TWEL|+hW8pC0fyH=rtU@IiBhWliT4@m~zg0*U z066!Y__X~=^*nB}5TC2U|hRK88(-u>dygxuilEgm10zRp-tkJS~tEH;9l z9%;;Nh0^CVRZ@Tf$)A7cKRY*7x-ocZibp!qQ_$;^z=J64`-jg&Dte7a$2@y{(g5mb zBV*u|Y|4x67U>+vdlqO@8;WmE*e`G1>)w-a5ORE{KD;!|zDojx9&=cW%#pdFqrhU-u|G8q0sf-$Ey|)dKid2Bry*nR(OK%am*J;|Lc@r8 zoA?o-2YpvvdMsv;&)lVW#QG+hEiI|=;8|vtd8&tPnB{bb*$Vv0t~Y$Pjn~`0f9r-> zp*`{=^S3mPzLzE;W5T=$*a73qBe?tm(iFqq6O_xu|>88s-&Nqz?b+HvTb?E0i6)9(a_9l8>k75+{I> zFi||%o>I*K00QFI#*_Y2(BMia9JiGcmkx|VvqT?)qlXZ#=)p^%xEyYxbvr(BJO!%c zMJODjjDntjry&FYuSYzohhccvzjtO3imHt7V0kd%980oANjX^#{GwWp3z~YB+dg(?${l1Aw z;!FPc8y{gwMdGqnJEl9xO?ycN&S1LdY)q>n}DYh(jFjY+5>d z>a@xq)J(aYHE<9qH7YS@>H`F0i9IpfX7C6q{gZ656XSQj8oM--_0X5P8IUVzhxglki8hifCA>Bppxbkr;tYH(xq4Mn zHv6%{G)-J5a`~rz=J2epRR2NNEbBv%$IR;X!Q(2LU(G)a3^&5Mr5^v(<__Q%&z2s>lS8u=F1(4*FQT}YJ#oj`_Mr?HhM9`|A@zL(QpuyaKvE$8%= zZsoI2vbit~ra&J_m95TSRhu9d<2}+;>HvdHn?}6%+rwd=f*)&>?7kEiooTYnYEGravM-*nNWqqyh<%RN-QUUAba3NHkOZ0>Q^KXb^p0XN z>pyGt4pDqv=6XG96!nOyVur4A;ic2eP@C7Q*`~E?d=Yo7UCT_q*fvx$t;CpnQ#tw3 z%I(i-y$-=wADGu?!b0ymSJJ(?|)zX0J?EsB3=F-!6rw-@K4G@ttgZuaNjy^%iW zm1D4RwM?WIJ(K8rvQwK~%&szz-9ML;qOOz<3m3m7u&^SzNesNTy-ijRD8?%k7M_bx zOFb-O3vWz|^b&y(s1v#@ZaRFpN*z}g=sQu*D0=(ABqXFs+pcX|J~wAB`&wK8SBlFc zFW;epxv2d3Gq>~sa?8p(bly!{kAT}&r9BO`LX3A(I}6o3Jsy{V11f}VB=#LO4?FQM zc=%dY?c18XSJY@fbWS=TnYVf>AY-yz6M?jIEB95rceIiuyHygt&&~}yu=L!nX*iNJ z5G(T@eQM^AA2%g(hok!jqrOwYh-B%@ipas4Fx&2AB^hQC)~1g3kmM_?+47*osEis} zBXr)GA%FB^{+1#q3${(M%I$CJ-gSN^T(CMDFR>R8OQ$Oa=VfL-P`|e8+uz@MNGZQm zj*#9Q%RclfMpRaI^#loEZybEEdsQDVb11T7a#vICk=q%z@UF=d)^y%kA#vou@pPtS z51)7^eS%V49Z!&8=BG~wFFKDyaOx+{18j{W()O>@_6;6XmppMz)@}avC4=w9oJLd8 z+__Im%2|`Gyk~_+=HZu~GHv>Vege)}v#11|2z<#g$YO0A16l{lD3D0sPyFy)KBfcTV2OG5|Y9>}mP7lrqyp`^vMpT+YkrGjHgD$?)5NDaUr@oI? z4}$-KekvIK(!BmHahyzHs&HtTowV?D#sbWf-TAUtaZ6fW5Q_EpRvNAk47aE*eE4eM zdXWMCOz5-FaZ5}@XXe#Sh{{UOt1AA?OnE^uS=t_jN;%>`L*Yj)em5E$7|+CLF3Jr4 zaLl|d8j!#Ca?7yIqy1RZSWEglm#OlXO}7s(HCuoGB$SFMWKpIq|BCA_oJ_N+gXiW` zRiSx8m|0ng**04afGl-}Xz(LwBT|@qw3X6Bm zazn=jY;E$I9b=KIi!uXVU~cm{HL(L2-f8JLTpO44VD3t@T=o?8H&*oV5XL)g`NHVl z(ImQXwCHJq>DWfvJBG@7G=1e$(NndNmOKn@sHB8dcdZJEMEax6SYYY`>+to(UqP2v3oAc(UuHkhE;@u1tBMdqR>3v#|Vg zLpXoKQ?ZR}y-Z=MK3pHp%j_0;GSPl=GGq-|*&6G{=ztp9iQ)1&^U>ABXp1Mz67lSG zCchrNd8TuxlZWr^oTif0)VbH7JngFe(0lttsZTni2G5^At~GM6mXVH2Wiz7u$XDU; zb+Yz+Y9nzyU^D;tYE#$Ghgo-%e)#9T-fH>mS*ghN?lCK8?Ao<~>;6~AUMPE`S5}M# zGH)A=)7by6S$DA&rqh~~t{N&UK$pBu%PVNI$R%xO<*s&V@$+1h`IpNH>&OvlP#kO`bSpH*`$4_&eYAvGGR6H`cSiAOZct3BZyD z_#$XS8NfRFVB;bJYF#|Xib5LzG63uMb0WnFFbIPZQb`G}YsCQU>EO6*aROj_OCZ4z zL2;a#2qNOm@c^Dn{Wh4?BQ5#A4cucSMXH{=Gb*^CyOi<~gob`o%3_FPvfwC6CB)Q$ z+OC=;-XLS&wo@tk#V5xm)ikOoKM)8)nZ6co-9i`snscH)6%JYrMX2-j(FLo5&bwtnRg6{lkC45Pb?>dzZ|zLBB(M>m;Pt#d z+~Ze*pUyw_W!!vHj@YSLt)(+IW#$_MeBOe$tfM}~i!TE@jQI!9(h|{$u6{?p3Vx(BRsVvUkaRmI4bkfR`WIGB!=B#ZOD^$ zb|4I>@yJo^-hI0+!Orp;ZZ~``_h^x4n$eFp#j||wxYa;zQ)D-IkLKwisV0I(bdwQa zCxIm3mv;2P3Tfp7c3w%QQTIpu_(5!HdglK6AW1xkH*vt-qWa+F8(t0SDWzvRYBndy&!)=UC;OYEA4kt!e_rZ^ zMaAH=i5uRv*=p-x!-!O*J{JoN;w||D5ycKeil+hxSP;S+1SuT^6{^V(rN`$FJbW0h z4NBF)JWzy36ro5uvXM}H2jH*BZAHQ06U@a9Ww)ZE;6(82T;=s(e7K=1T)Z=0ICiLH zU2Ik6I6~Gcw;V6267{X2!kMEdOQN&gyB1pbWJ#X7qF}rNl}m-OSDG@5Z1^k`)zInF z+;GtI%ouHYQ?fy#VD}5FhCXiU?R2V{Sk(YIZO>$F`66A)?<;-F@1^gYlFodst=&mj ztxpaqna!2Vcq+zsXE&`1WxU)-G<0bFRk3~M3LASp^r`{*K=fnXkz(b-?O_6}uRs@7?-CWndE>oP)0r)#SS$MYnkFmrqwF* z_!vqSdQAB)nbN*4%Y7n^)!KmZ6QAA2TYkSEpW~%7rv~Qy8MGk5 z5*~N1y~6hFXSb|o&G&SiCG~tNW6c-=Vk4ww>0LLPEa%2=Urb~~ANe0^7^1y#;N(VM z%V=tF(_F`Ikd!ASXL{WL1EBj{=kxq@^?kgZ7f&&{_u2m3IbVS2_1i#JUbQ6|>LIS& zTqHZ=n|E-Q+8Q_|-n%qZ@r7tMMGpONLqFL+g}WoRp^*uvMGHBm z_4>^zZPuWr+=sWZ1#}G;vuYl7AvMqkj5?b%QWsmHYPa`QwcVoaG;BXiio=&|Jr^L*WZ8!#GlYdFrYHWP~pLB@~EL$@2v44i$6`E;ZrMjv>mHkJepaw=bY+^rTOfWiyyuNhW9A!MN+qiMl<%# zwYCgr^8hdRtl?%xf~@{5$B(JpY@?xpr*elsILdSC_k?4$+T;++M!Vs(_jzec%6P5;rcF`tfAy4U5kKT}3B41}yC zg0jFzwQ=1-9((K-j+KLxS7e8XyZukUt2aao*@>J!D?CBm4hQT<3fb&-NE+;?Li=>245 z9dPDuv2S>#GuE<~u6`P^U_d?CBe|E{8hXX=+;uwgy^ATdQI*kS8z79{cLY;M!U;^qZppKGD+FGykQ$&KRE zq%;#)`aSj1UlEf0*0lvggL7dlRWg(-WIe~snJ?2E!JFb;R9Fwz^!e8HoZXQ}5duqC z%P`;R+q$>ctCV>Zr%tmpj7Qnz@Ze*1AOS?nrGP!(3anoLlRsFRz}1Z|tgp>2)ZDCi zyYBc4h}yClxX?&bR(I`GzpRtT0toxf?;^kvXeV~`5V(mx)VugsLeJIlYxrM%^TifoMY=A0SC~EmVx_SYe?i*7Ee|!kw2Ob%&h?w$1^?HW z4LlTh5QvNlESB5+Z)_!@(&l;pJxC3(<9FM5LnQYb2~@E%g;IYu1(6kl5(rRZKoQF* zoE55E`whR2b~Z#8udl?3SVyIxNDw*nWB7ohA{-7;q(nx2sBuY%z@g$ldTby>(B+mb zpGy+Yvj2Qe{+WC$6qPPIYVvOk+m|=;2iG;Aobc!W72U*_Latt4D8$MGYk)^rt_;xe)fYNAxs)*EuGtu990Q0>D>aG?X%8V^E$IJPrgk>@cB+JEYt_+A?%-L5=|)(E&RUzW z(DulVKYe7Z-ShPqHKne77M`Amt!TddmT20}rwK9TnMD4#LsrwuF00qG8%=hs;fjf0fxH;K z_RZg|NV=_=%@QQK%f$veSv!qoYWCgQ+3%qqbq;xde4p&k6QefGNYUsX01v&d=;w2& zit-rok)N*XJaF~Y$qM(O*H7Yj-sYY*r^h zlg@AX`)X9BM1>E^m}z7)Qd*jf2tw+~VeG9rS~K9bK$x$7+Wa8+b;UxpSB<&v%#ZCl zpL*2fZAV_KS%2qtE^yz`q3H^`>`r5OY5}IW4mG`FuV0`DI z><6`(LinAKqK^f(A|toeH_^!tirCj>QiJ`mZ065|ZQ}bK3Ar&I)_fV?cyezgPWx6@ zNk+MMzoc>MQ|>)WF4b?dFVm>tB$NMixw-Ykfw{m1TC>i)iMx#t64_v?RAP1Trxq3w zlAsAyR*(bJM08M@EeO0t5z;OV_<;HNYgLDPDV{agr5$lt9$VEN>^}6OmNkM77Z%&4 z3Ax!xS(T6R`EfOs4BWCf=-m8sO!tC1?6vWVYQT~BC;&Vph%UMJR<`-5@nj>HgG07_ z#qaU0vs=y@X8`7y>xXUppc@BaR${aKXlVdCKsn&b#wa--S6tls|NeprZrv68@ zaB0zdWzjA#S^6TQhDN+7^OZE}M|r|t)7%a=KBzvHz0KD4?-A@-UEU|${PTrhFPJ%t zP4)*r*KJu8vlr*FTKITrs`u2WjPj-)Fnyq$CT0)_zj$#TrTbhjqNHP%>d-6oCi0`* z<8oHxiDH;T*SpHvHHQ#n#Z4cPPvum?JF=>_>~|Z_x!YLOsbGFH)a}$XjFDGZU4M&y zi{0Cyl*v-9{VFB6tDU7=365>kuNRr7y_26~P9pIQN@eFDiRuhz%$VK{37VsXzQ5~I ztxU|0e~C8r0jgAGTDFeCe3F*URB)SPIsiR1$pFJn=~_YxVb6ydAhB=w~^oIlU(0>Ydr_4 z?)H+rW%X_Ki6iV)J#1+39$#KYevx9xUSiLg(@4vc-+vy$wR$#Q9$kbHfsA?#NUqsq4T zLL1ws*s-N-)dwX`qZO!e@0BAB-A!*6e`F+f;b?D!FZMn$Tc8s)R<9lWi+$XY zc#7z!U*Z6}N_4n`=7^)cA^wxDj;^d>Mz4{Kqj&23qq^<4(BK0l#Giflz%SAjSu&)KP?|0D{I)q^<-!KRrei$8D|;;wC|n^m7vlCMdxL z(fV(Yc3hHW_e4WE?He%AT!gbyKS+JFmLD3H05&Oo2rWpUz?DPk1b~~2f@lmhES8Q^ zm!N|eEeDi3q!Nj;dkPAM(E*DVFmwP!0bo*ZZf7HMps7e5V@_@>$o(R1Jb=DT2Vo!& zCFv){pjg}it&yYy;8jP&GBk(|jw7UCAoO4ug+5>agh63YL?}N-2^B{H*n-Ft;5aMs z&>UcI*1<&-f!AKMLoxs=zGO)X1`K7;gDa{FtDA!X&e4Y=B9_7V+U0;11$dloRPVwuF-(MnQyU0wAb?h*Bsw9M7x| z9DWc1bEN}=h!awfnxzR4To6SGCo@ndn+_5R!R3HZaDr|QFia3e9LR5<4TX~G_ZLAT z5+K?zWfT!8A_odDA%K+nxlmRZBBC5_P>K=?z_Es;>I)>m`+>ap0M~&OfBHycc&Y*X z3LuO0h@2uM;D`v)E+Iew*~vrXaFQoz0;2?EE}}r2gb$FyTsZ!cvq3N=Qb1(;`7!1jo&V zM5O{t15s42O`^#SB3!Nj083GuNS_o)I0y(P08^u+`39n|M2uMfw>&QYMF8ujzX<=| zz_?Hh6h%a-nkAvkNPQ$8L9fIK;4pHhYF?t*a;ZlkLN9~Ul+~0-fbd-1;G7~HH#fi+ zPGG_P8)^p$7@7mZ!@#0=eWbE`P7yF85CV=9etE*5a%oQk1_7*7ZV;Y=lV1k|K^o_T zazZE*`cr^?Js3%#h%kpTh^GMZQJ_a2N{Y-e2fJruP&iV+PrwQTJSqU7h3C`*Ks(%4 zARsgj=w1M?0~RlV z*Az??$C0`gU{ImJr~r~lq4Y>)eFF#)C%_g8fPobB|E2&+qJ*R%0p^Wg2jD0ipoiNE zm@ojpoEyrigbIZd?u9~90m3L?Fo@`j(0}cT1E7{x0J{Om^8{iD5ZtUR9x4KOJit&T cpv!px<_ll~9poQ_fF2;1t!tO$5dWS2KO22b#{d8T literal 0 HcmV?d00001