From d0573edbc3f45ec404b877359fbe814e41799838 Mon Sep 17 00:00:00 2001 From: Dmitri Soshnikov Date: Tue, 12 Apr 2022 10:28:51 +0300 Subject: [PATCH] Add Semantic Segmentation section --- 4-ComputerVision/12-Segmentation/README.md | 46 ++ .../SemanticSegmentationPytorch.ipynb | 229 +++++----- .../12-Segmentation/images/navi.png | Bin 0 -> 39345 bytes .../12-Segmentation/images/segm.png | Bin 224616 -> 66220 bytes .../12-Segmentation/images/segnet.png | Bin 298711 -> 73731 bytes .../12-Segmentation/images/unet.png | Bin 77166 -> 27886 bytes .../lab/BodySegmentation.ipynb | 423 ++++++++++++++++++ .../12-Segmentation/lab/README.md | 19 + CONTRIBUTING.md | 6 +- README.md | 4 +- 10 files changed, 606 insertions(+), 121 deletions(-) create mode 100644 4-ComputerVision/12-Segmentation/README.md create mode 100644 4-ComputerVision/12-Segmentation/images/navi.png create mode 100644 4-ComputerVision/12-Segmentation/lab/BodySegmentation.ipynb create mode 100644 4-ComputerVision/12-Segmentation/lab/README.md diff --git a/4-ComputerVision/12-Segmentation/README.md b/4-ComputerVision/12-Segmentation/README.md new file mode 100644 index 00000000..76a4a57a --- /dev/null +++ b/4-ComputerVision/12-Segmentation/README.md @@ -0,0 +1,46 @@ +# Segmentation + +We have already learnt about Object Detection, which allows us to locate objects in the image by predicting their *bounding boxes*. However, for some tasks we do not only need bounding boxes, but also more precise object localization. This task is called **segmentation**. + +Segmentation can be viewed as **pixel classification**, whereas for **each** pixel of image we must predict its class (*background* being one of the classes). There are two main segmentation algorithms: + +* **Semantic segmentation** only tells pixel class, and does not make a distinction between different objects of the same class +* **Instance segmentation** divides classes into different instances. + +For instance segmentation 10 sheep are different objects, for semantic segmentation all sheep are represented by one class. + + + +> Image from [this blog post](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50) + +There are different neural architectures for segmentation, but they all have the same structure. In a way, it is similar to autoencoder, but instead of deconstructing the original image, our goal is to deconstruct a **mask**. Thus, segmentation network has the following parts: + +* **Encoder** extracts features from input image +* **Decoder** transforms those features into the **mask image**, with the same size and number of channels corresponding to the number of classes. + + + +> Image from [this publication](https://arxiv.org/pdf/2001.05566.pdf) + +We should especially mention the loss function that is used for segmentation. In classical autoencoders we need to measure the similarity between two images, and we can use mean square error to do that. In segmentation, each pixel in the target mask image represents the class number (one-hot-encoded along the third dimension), so we need to use loss functions specific for classification - cross-entropy loss, averaged over all pixels. If the mask is binary - **binary cross-entropy loss** (BCE) is used. + +## Segmentation for Medical Imaging + +In this lesson, we will see the segmentation in action by training the network to recognize human nevi on the medical images. We will be using PH2 Database of dermoscopy images. This dataset contains 200 images of three classes: typical nevus, atypical nevus, and melanoma. All images also contain corresponding **mask** that outline the nevus. + + + +We will train a model to segment any nevus from the background. + +## Notebooks + +Open [the notebook](SemanticSegmentationPytorch.ipynb) to learn more about different semantic segmentation architectures and see them in action. + +## [Lab](lab/README.md) + +In this lab, we encourage you to try ** human body segmentation** using [Segmentation Full Body MADS Dataset](https://www.kaggle.com/datasets/tapakah68/segmentation-full-body-mads-dataset) from Kaggle. + +## Assignment + +Body segmentation is just one of the common tasks that we can do with images of people. Another important tasks include **skeleton detection** and **pose detection**. Try out [OpenPose](https://github.com/CMU-Perceptual-Computing-Lab/openpose) library to see how pose detection can be used. + diff --git a/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb b/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb index 2968bd9f..b049b40a 100644 --- a/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb +++ b/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb @@ -6,26 +6,44 @@ "id": "3AbTeDP5Tbou" }, "source": [ - "# Semantic Segmentation\n", + "# Segmentation\n", "\n", - "**Segmentation** is one of the main computer vision task. For **each** pixel of image you must specify class(background included). Semantic segmentation only tells pixel class, instance segmentation divide classes into different instances. \n", + "We have already learnt about Object Detection, which allows us to locate objects in the image by predicting their *bounding boxes*. However, for some tasks we do not only need bounding boxes, but also more precise object localization. This task is called **segmentation**.\n", "\n", - "For instance segmentation ten cars is **different** objects, for semantic segmentation **all** cars is one class.\n", + "Segmentation can be viewed as **pixel classification**, whereas for **each** pixel of image we must predict its class (*background* being one of the classes). There are two main segmentation algorithms:\n", + "\n", + "* **Semantic segmentation** only tells pixel class, and does not make a distinction between different objects of the same class\n", + "* **Instance segmentation** divides classes into different instances. \n", + "\n", + "For instance segmentation 10 sheep are different objects, for semantic segmentation all sheep are represented by one class.\n", "\n", "\n", "\n", "> Image from [this blog post](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50)\n", "\n", - "Almost all architectures have same structure. First part is **encoder** that extracts features from input image, second part is **decoder** that transforms this features into image with same height and width and some number of channels, may be equal to classes count.\n", + "There are different neural architectures for segmentation, but they all have the same structure:\n", + "\n", + "* **Encoder** extracts features from input image\n", + "* **Decoder** transforms those features into the **mask image**, with the same size and number of channels corresponding to the number of classes.\n", "\n", "\n", "\n", - "> Image from [this publication](https://arxiv.org/pdf/2001.05566.pdf)" + "> Image from [this publication](https://arxiv.org/pdf/2001.05566.pdf)\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Prerequsites\n", + "\n", + "To begin with, we will import required libraries, and check if there is GPU available for training." ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": { "execution": { "iopub.execute_input": "2022-04-08T15:48:06.861688Z", @@ -57,7 +75,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 2, "metadata": { "execution": { "iopub.execute_input": "2022-04-08T16:03:32.933989Z", @@ -85,12 +103,16 @@ "id": "D4if75qwFMpJ" }, "source": [ - "## Dataset" + "## The Dataset\n", + "\n", + "We will use the PH2 Database of dermoscopy images of human nevi. This dataset contains 200 images of three classes: typical nevus, atypical nevus, and melanoma. All images also contain corresponding **mask** that outline the nevus.\n", + "\n", + "The code below downloads the dataset from the original location and decompresses it. You would need to have `unrar` utility installed in order for this code to work, you may install it using `sudo apt-get install unrar` on Linux, or by downloading command-line version for Windows [here](https://www.rarlab.com/rar_add.htm)." ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": { "execution": { "iopub.execute_input": "2022-04-08T16:47:25.071036Z", @@ -104,14 +126,21 @@ }, "outputs": [], "source": [ - "!apt-get install rar\n", + "#!apt-get install rar\n", "!wget https://www.dropbox.com/s/k88qukc20ljnbuo/PH2Dataset.rar\n", "!unrar x -Y PH2Dataset.rar" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Now we will define the code to load the dataset. We will transform all images into 256x256 size, and split the dataset into train and test part. This function returns train and test datasets, each containing original images and masks outlining the nevus." + ] + }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 4, "metadata": { "id": "Rumy9ldAFteW" }, @@ -128,8 +157,8 @@ " masks.append(imread(os.path.join(root, files[0])))\n", "\n", " size = (256, 256)\n", - " images = torch.permute(torch.FloatTensor([resize(image, size, mode='constant', anti_aliasing=True,) for image in images]), (0, 3, 1, 2))\n", - " masks = torch.FloatTensor([resize(mask, size, mode='constant', anti_aliasing=False) > 0.5 for mask in masks]).unsqueeze(1)\n", + " images = torch.permute(torch.FloatTensor(np.array([resize(image, size, mode='constant', anti_aliasing=True,) for image in images])), (0, 3, 1, 2))\n", + " masks = torch.FloatTensor(np.array([resize(mask, size, mode='constant', anti_aliasing=False) > 0.5 for mask in masks])).unsqueeze(1)\n", "\n", " indices = np.random.permutation(range(len(images)))\n", " train_part = int(train_part * len(images))\n", @@ -139,52 +168,16 @@ " train_dataset = (images[train_ind, :, :, :], masks[train_ind, :, :, :])\n", " test_dataset = (images[test_ind, :, :, :], masks[test_ind, :, :, :])\n", "\n", - " return train_dataset, test_dataset" - ] - }, - { - "cell_type": "code", - "execution_count": 15, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "kCjj0YKcGBKr", - "outputId": "8ee469e3-3ebd-4d5d-dfd6-bb18eec14b3e" - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:12: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:201.)\n", - " if sys.path[0] == '':\n" - ] - } - ], - "source": [ + " return train_dataset, test_dataset\n", + "\n", "train_dataset, test_dataset = load_dataset(train_size)" ] }, { - "cell_type": "code", - "execution_count": 16, - "metadata": { - "execution": { - "iopub.execute_input": "2022-04-08T16:03:58.247264Z", - "iopub.status.busy": "2022-04-08T16:03:58.246853Z", - "iopub.status.idle": "2022-04-08T16:03:58.256661Z", - "shell.execute_reply": "2022-04-08T16:03:58.255964Z", - "shell.execute_reply.started": "2022-04-08T16:03:58.247222Z" - }, - "id": "rUGDAa61FMpN", - "trusted": true - }, - "outputs": [], + "cell_type": "markdown", + "metadata": {}, "source": [ - "train_dataloader = torch.utils.data.DataLoader(list(zip(train_dataset[0], train_dataset[1])), batch_size=batch_size, shuffle=True)\n", - "test_dataloader = torch.utils.data.DataLoader(list(zip(test_dataset[0], test_dataset[1])), batch_size=1, shuffle=False)\n", - "dataloaders = (train_dataloader, test_dataloader)" + "Let's not plot some of the images from the dataset to see how they look like:" ] }, { @@ -215,65 +208,39 @@ " else:\n", " ax[i].imshow(img[0])\n", " ax1[i].imshow(mask[0])\n", - " plt.show()" + " ax[i].axis('off')\n", + " ax1[i].axis('off')\n", + " plt.show()\n", + "\n", + "plotn(5, train_dataset)" ] }, { "cell_type": "markdown", - "metadata": { - "id": "9tBja_1KFMpP" - }, + "metadata": {}, "source": [ - "**Let's plot some images with corresponding masks.**" + "We will also need dataloaders to feed the data into our neural network." ] }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 16, "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 203 - }, "execution": { - "iopub.execute_input": "2022-04-08T16:03:58.268348Z", - "iopub.status.busy": "2022-04-08T16:03:58.268002Z", - "iopub.status.idle": "2022-04-08T16:03:59.237853Z", - "shell.execute_reply": "2022-04-08T16:03:59.237161Z", - "shell.execute_reply.started": "2022-04-08T16:03:58.268300Z" + "iopub.execute_input": "2022-04-08T16:03:58.247264Z", + "iopub.status.busy": "2022-04-08T16:03:58.246853Z", + "iopub.status.idle": "2022-04-08T16:03:58.256661Z", + "shell.execute_reply": "2022-04-08T16:03:58.255964Z", + "shell.execute_reply.started": "2022-04-08T16:03:58.247222Z" }, - "id": "IA8ziDUJFMpQ", - "outputId": "7d75d54a-c066-411f-cd48-4e54d669d091", + "id": "rUGDAa61FMpN", "trusted": true }, - "outputs": [ - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": { - "needs_background": "light" - }, - "output_type": "display_data" - }, - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": { - "needs_background": "light" - }, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ - "plotn(5, train_dataset)" + "train_dataloader = torch.utils.data.DataLoader(list(zip(train_dataset[0], train_dataset[1])), batch_size=batch_size, shuffle=True)\n", + "test_dataloader = torch.utils.data.DataLoader(list(zip(test_dataset[0], test_dataset[1])), batch_size=1, shuffle=False)\n", + "dataloaders = (train_dataloader, test_dataloader)" ] }, { @@ -284,11 +251,11 @@ "source": [ "## SegNet\n", "\n", - "Simple encoder - decoder architecture with convolutions, poolings in encoder and convolutions, upsamplings in decoder.\n", + "The simplest encoder-decoder architecture is called **SegNet**. It uses standard CNN with convolutions and poolings in the encoder, and deconvolution CNN that includes convolutions and upsamplings in decoder. It also relies on batch normalization to train multi-layered network successfully.\n", "\n", "\n", "\n", - "* Badrinarayanan, V., Kendall, A., & Cipolla, R. (2015). [SegNet: A deep convolutional\n", + "> Image from this paper: Badrinarayanan, V., Kendall, A., & Cipolla, R. (2015). [SegNet: A deep convolutional\n", "encoder-decoder architecture for image segmentation](https://arxiv.org/pdf/1511.00561.pdf)" ] }, @@ -369,6 +336,13 @@ " return d3" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "We should especially mention the loss function that is used for segmentation. In classical autoencoders we need to measure the similarity between two images, and we can use mean square error to do that. In segmentation, each pixel in the target mask image represents the class number (one-hot-encoded along the third dimension), so we need to use loss functions specific for classification - cross-entropy loss, averaged over all pixels. If the mask is binary (as in our example) - we will use **binary cross-entropy loss** (BCE). " + ] + }, { "cell_type": "code", "execution_count": null, @@ -390,6 +364,13 @@ "loss_fn = nn.BCEWithLogitsLoss()" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Training loop is defined in the usual way:" + ] + }, { "cell_type": "code", "execution_count": 21, @@ -451,7 +432,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -472,7 +453,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "100%|██████████| 30/30 [01:11<00:00, 2.38s/it, train loss:=0.601, test loss:=0.62]\n" + "100%|██████████| 30/30 [16:01<00:00, 32.04s/it, train loss:=0.593, test loss:=0.577]\n" ] } ], @@ -480,9 +461,16 @@ "train(dataloaders, model, loss_fn, optimizer, epochs, device)" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "To evaluate our model, we will just plot target masks and predicted masks for a number of images:" + ] + }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -502,7 +490,7 @@ "outputs": [ { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -514,7 +502,7 @@ }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -540,6 +528,13 @@ "plotn(plots, (predictions, image_mask), only_mask=True)" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "There are also some formal metrics to evaluate the performance, which you can read about [here](https://towardsdatascience.com/metrics-to-evaluate-your-semantic-segmentation-model-6bcb99639aa2). The easiest one to understand is **pixel accuracy** - a percentage of pixels classified correctly." + ] + }, { "cell_type": "markdown", "metadata": { @@ -548,18 +543,20 @@ "source": [ "## U-Net\n", "\n", - "Very simple architecture that used skip connections. Skip connections at each convolution level helps network doesn't lost information about features from original input at this level.\n", + "SegNet architecture is very natural, but it is not the most accurate. Indeed, we first apply pyramid CNN architecture to the original image, which reduces the spatial accuracy of image features. Then, when we reconstruct the image, we cannot correctly reconstruct the pixel positions.\n", "\n", - "U-Net usually has a default encoder for feature extraction, for example resnet50.\n", + "This leads us to the idea of **skip connections** between convolution layers in encoder and decoder. This architecture is very common for semantic segmentation, and is called **U-Net**. Skip connections at each convolution level helps network not to lose information about features from original input at this level.\n", + "\n", + "We will use quite simple CNN architecture here, bit U-Net can also use more complex encoder for feature extraction, such as ResNet-50.\n", "\n", "\n", "\n", - "* Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. [U-Net: Convolutional networks for biomedical image segmentation.](https://arxiv.org/pdf/1505.04597.pdf)" + "> Image from paper: Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. [U-Net: Convolutional networks for biomedical image segmentation.](https://arxiv.org/pdf/1505.04597.pdf)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 14, "metadata": { "execution": { "iopub.execute_input": "2022-04-08T16:17:45.665392Z", @@ -640,7 +637,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "metadata": { "execution": { "iopub.execute_input": "2022-04-08T16:17:45.692880Z", @@ -661,7 +658,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 16, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -682,7 +679,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "100%|██████████| 30/30 [01:45<00:00, 3.52s/it, train loss:=0.6, test loss:=0.609]\n" + "100%|██████████| 30/30 [29:07<00:00, 58.26s/it, train loss:=0.595, test loss:=0.572] \n" ] } ], @@ -692,7 +689,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -704,7 +701,7 @@ "outputs": [ { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -716,7 +713,7 @@ }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -774,7 +771,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.7" + "version": "3.8.12" } }, "nbformat": 4, diff --git a/4-ComputerVision/12-Segmentation/images/navi.png b/4-ComputerVision/12-Segmentation/images/navi.png new file mode 100644 index 0000000000000000000000000000000000000000..a61973e25dccdfc2dafbc96fc58b03665f6bed9e GIT binary patch literal 39345 zcmZ^JXD}Sz8?_Kg5G1S=y#%|f_vpQ?)pi%rONfvNqIc1IUA?orEJ5@{jp!u7t`Y>% zEzvi6d4KRxr)jYfY6u<5mkIrz! z96IrPacXZ;;IBOA>73y4bnD%b%6U}epUSv-Y}!ah_{u=TWTyR0am-8$MwyRoD8YQ{ zQ|VZO#d6V`!_iL*T~*ryWs@1c-!ekKMwkyLcyE+AE#|*oYs>C0NNNm*eTns$NwZw6 z%{G@8X;1JS$_O0CB=^RejHdea#94Qy1|8!+<4av$o4pnFgce-fxUG2rz`9Z&? zc+L1p&gS~s8)z+LI$WHeeGPkCV+y?d7Mx`!TOZ~5I~uYctz@dHyj@}g5n`|U@NTUx zURMfKHZu&>n?}T}tT@A&kQJRl+O`O%d{*mhRH}}PA<%bir#h|-f zQBe7~ziO&;o*mfLRW3kTOjzxq?M!FWD_LG`+2J z)j=J|_9Va>K9=V3LW*-QRqK_iY}R|*5`C_g_9NrBaYFE`Tk6P?Yr zI+B}_F&|!;&3^A`@v*9i2`&ou7@8Ixj(N8~H8A!8-tPm6bA5Td&e`4CqQqkR@r^<2 zr1WSbHcgdLjqOc&ex{1xtA7pN#NDlvjTs4Be;GZ$3?G-)l5}K;E}`*5$+$+4UQEP` zWN8JrvBtvAs^TAm{ZK6j*Ge0^1jotW{9DT)b2B?-VXye;$P|pOn~VLy8qc3Ue4+ga zL7&jn$dH<^@^B9)b&N-tpV$5x>)I--d8=b+s*z^28(--Mp}5dM?mH+F5_S@8HD!eF z?BDD~9djqve%>l+4_i1>y4OrD2DqzTpT?G5BZ9(G{Jo<_>d@Tb#t|lte)T?8{XT_O zxtPt9hrM|nH0nZ_W|>|p?S}=;fM#C~z#^N+Xi(?kNziEQd@p6&{CxaT zzHe~*MupJch4koA(9z6BCjV8}w%D6{{H92=dV53Xq0)&o?s%9^CO<^r|3PW$*#94N zorUxcITPBt9^D*i-g-A(r9T~e+_5SAe7>lHmPH2V4OF@7ktikGoN~zg4;bQ zM_J;`aR);~`YO|}%SM})-tc#xYtJ)KuS>XS{zCK&4T)U;t{KDPcGJD-J$%oVh4l3F zl9E_&E@WiBS<5Ub&ft<;tee(Ws#Is@G8KyHO}ZpK|7};XIs5u%A0L)iv(lEaZ4MsP z%{<&1SxVlKIWVT~t;tO)D|^#(vO9l4-E4hmy78T|#EQdB!OPE7GHO#z~p6&H2jDXV}f2LV;FJr8Hk3V9V+SEovJbAKK&#g@-rpIYh+1)IPYl_D*v7hsmX@aHQc^`jAE&pQBuctETy+TPUHIoV&!#pu zHr5|KraktS9A3JRg2k$FX5?yd!)xqCo2mQk&b`?m#P^YYn69;Uz1w^f)<1pAx$T1{ zl9Whs`)|_B#^&JEvR&EupQMR5sG_+J{=JPU)~R+mx-xvCd3MsIvxHPIe#cvrbNALg zS)bc^V)@lcDj!!GVXmX2qiu06iEGWa$0ZY?hy=&%#pZ(6JQ8!|3ff8RRp>%etMf+peVS;-9L;+E1UQ z3*;Z>#1e28s_jC*GxU&jn17JIP;o~lA6hjnu~g4zy2~D&n@pSAOixQ5wQ&6Q(!9eJ zK`6SLb(g$0iyPDO48yP$*)sJ3mm8s?d`=mo^5Z>-DL*$?rjQbM%Z`}=RV@C5R&yny zT8Pypsz+Be{=GEwMtMCC#v=j5(dsP%;YQ)ttE!xGf4KGxxZ*E^=blT>J^wkLj~}#_ zNMw;LKXCY|p{ep%*U0WUGQdiH8>2RGW>v|~&F7%iGtAEN>tR+SLwtjJ*rYOamI78% zG0*Dtpvha@gQ})yNp#8mYj|3Ta(9<>H0%~OpOM1pJ?Hq`-1aSu<>@o8s}H+jBxoAV z`KXM3&nNtwi3ERsEU)cnnY!V2N;@)4-nXe4wJjD<&>%gjR=F$3jHHPzYVltp%CY!f zu)oHqC8cS3d9JasF}CR2<*6T3WMDB*%&hL9Mm!}qJ9k~(@n`pQ2Etl)chs=^_jB(r zp)M|Ff}S{Fkp(hUHpkPy>eETQ-s3h#`i=4>dXS-paS}F6fa}>U%&SU^P+Wsvt2T1| z{jj2hu96usPayXZr^O@#S024pTzxTk`vX{|2*`59O18|c06d;Eoc)1}d-o~*9f+4( z@pkU79@Y4z(tRAK7zAO*`y_ECVn0D9$B6e=-`(UD`Gu5sxexbtX9s}tR8HW@HG(eD zUrx>Gu^;yO>*T+$+{JRL*rYr)ELDJvEn&6x78zdpJ=_UX0E*1`Cc&tqlbzJQ!*oLO z;;*e9l~`n9$-}W3RZ@&RL0p(c2id`zfD-%tN!DI9_8|gaBHZV>A@fjN)kf)p#+{hkl`@H;OwllRpo-^ z8p^@YUKE2|>-$uUUt%{#r$RJ_AO+sGANOI=WIOIMJ@7%M*y!(p*#v214bycUFZ(}F zzjIp*YjXJ;(nsecNN;69%IhcZS&>^|Fc#K4s3`XI^X*SV&!%rBfS@c_ub=SXQem|% zoF4&tW|RHz=mO;vc+NH+h{^OKG3c^ml8F*hU|;uFz!a0IWTKZ_g0K-X$#}}iOeO&9 zZ+#1NSeOqe-VsCdlqpksKlE(}-y4l`%z+hsyjAmuV{9ugA}pQwTsWxZsDJSCTpe`9 zzNb1%RjEGk0mQ_+cKvyA^h~G&$&T*T9OF9Z21SMd2RvajX4Gq+a?Mh6Zsa*bN}`4V zuW|{9thjbZEn4r_Yig4~F!YWD#F$cAZ7My+P)*kToGQ*If8PiRT>H*zbxY8;)lmbw zlizz|x-Ne)@KXb{tHUi98?5hoGrtf_TQ_73L3$IuDJVNZ4IzSC%bK3HD8WPAYICJ7 z8Y`u?J}nE|ip=1gwKv@AQXtvV7!(Mg{PnC@#YS9S6|sD)v_U@y^t?d%xJ=7NHRD}n zlMN)N%Z(MygUUZ~Q%A`HCCXS&)mLy*eiZ6dJnyof$(3VjEDVvQoY|=Q(D@0VuGr&p zB!|m>m5wnZ=N;=)mj(dwK8hVcnte^n!SD*~jIbia3*B-{vo=-#swGx^Ps}oJ?+=<1 zR`(v9)fZM+pBGjjfHcwfmW0WY2O_%>NQfqb)fT&ryT)J6FiG$4keEAbauBigVXR+( zXzJ$OQdTAZ$JvymmX=pnX|Mv&TBM>X1VSn1<^Cb}8+W_7c6KRSKy|h^s*&d-z;86A zm5W?Zfnqf54^rNU6-$}DBooTcU&+Uf+9HBDmskD#}px@#F&Egra{5c?EIT~dgkbfBlS_Xri*z9L&?w=E0 z?L>x62phi?Acs^PR)No1Lxm+o*=k*?JuJb~C(xJ|(&P0D%G*A?VsX8i6ZqK}`kT&} z0ItKGtbC1g%}IH=@6_D=p5wiZVrY#8xZzeF^!Ls`V%qNUF(u@tIAmjM4~Fc|hNXP2 zK1v(T;1u%0?r$UtM>h4p148>C@2=#8xFItT)#kcx9`-9f$ydZfhx0FQh2?&x ztl!t7z&{AKW^W~x`cVsnqI0HX{GD_R{n@ilLXlrpgNB+aUi{*#irAIin{#pyifQ*8 z5=Pif|4cZPca$5>9**IF%EFvi<>PQLqW7{7-MIC9WFG8~VzC75F}mwiC2kuA@zTbQ zNZitpK2>&d{+3}EA$=n>qvL?Y=)`YrSI{8+JE$tb)$9E=^nUFMq^Q*#@^5fo5L*_9 zC_Kz_=8tDYhj^NxO_|2|F_`7yq9#aeZSS6}VH`pDsBlXD#{T!E)hq=6JZb2eRIDaG z##Ej? z0}sd*o~)PH*@@6A5&w8n5GRf%-K5SS#2DoM=obx=genhFw6%QTD&o8a<6{fxW7T~49sr5gD>XiB8NzCCLknh?>WnvL-c7I7 z{NSh>Mu+ShYAdkBkm8LeR0>MKx%Qh3}3G7 z&cJ__E$c&|bE6dJKv*HR%P$Wx>i0Uytvk<$NWW~{O)pIHJ*R^MwROua$v+oonv30A*p zS{Y569Ek6855&A4kgQM7xNJgtfRgJAX$8A2P{u9=CqMiB_p_Hqo=2g&&QofJ`)m6m8xgf*^mgq0a8n z%1bbxF%0X*6^+3NT)Rds6{dGR1R5|@0l9!h6EVcC1OLUekAQpVx<CwC6)RX;coo=V-tyjc8;vI~^6l1%yv(6~Fi01n(A^`Etg8Ti<Rub1Zo~}W$?!d0>DB(EtSxX#qV4Wk~zFqCe3cqMC7?`bJM%U{AXVGkFmfO;6<99%*?-WxQn~pmAfx$wlX;h%bRW^L+UGAnvsG1xU<$^Gyg| zGAXX_)&ANiAze5I&muJ!4dnt}oj*1r9Br8G6+j{lrQee<+^0nM6nm!kz%@bOb{eBK z4zm}Z0VWB!TsN7l^@)ie$6P?8jNxsLf58W}x0Fy?a2)qhS< z6$n{$j9m(4UT|#zfh_%hO(z}|1#HO!EhjS0dh~dK(po0W7)j6imm;(&kB#$nEeC}n z<@tr>Gml2~u#H==-Ve_XF1zls16r7KA5nfJzSgO;uk6>|B6?1qc(F(f1p#$;pf1fJ zl<3x>h<}AhW8v3vLw8fQeKa{ma(s26>eLs3Xk%VOxmbt5!Yc=#DawdP|4L)S#gV*nRoADfOii?(Xz2Kp&q zUl>9H5W^)E-zb=?7KMgvZQkUD#x(T0h7 z8(uVM!ARYiq<#++!h%x9ClU5RGAWZJkP#(elRM&|jFszom5~!MNEC7Iyj0Y~5M!~P z1GO{-dElg~=ccRW6GPN~tQ+GL&e^5)_JUPRjTcxlW%o$%b=jJ5U8Omn&xW9nyvo`*{aHfxtvz6@3DS{=JfgBvqo%r!fX^M2>G^NdabrM<1!s|745*A0Md5i zv3XAi#n-WB9eYTF){`1JelIsAa0~b&;%@AH#@Ot^ORW~-XzLI+T}_9l;{-WNaA*>{ zLSpe4JWcw$j?{shoyRg3>q*a0=$JSjn_Wsa=pdB#mepk43?JfmeM)h|#tS>I4cP)X z^GeJ5zxyrcFQu**Uvd6KgX7qP(jkGegb8*qt(wQ$XbZQg^xz*vGz53Z$%t2}!X+`h zZA5v|unHu(;;50|hd138&J-b7s?wK$TZ)^^x*KbAj|aKhK~Jp(H=gd_UBW3-8R%gg zOOW7sr}K&RtBX73;f-$Af)rm|(^e7N9T^v3{bn+YpN|v4@5dcYvX=pGSsAxlp{%dDVGkFN|t2 zVK)p~3&ILN+pTvOxTfbodx9P$Zp%9irzu*frVIZO?hy4D86w(4Zi0?PAMJP4y=P(U zxJXojC`H1Dh)=+@OZ^R-HZlzbk%vESE}VyPDP+09qM?gS;# zs-k;BiFbrMys2r(i+;aR;V~WN^#>(Ri_Z)+g*g0F8N7>5f)D9~@vk99XjQLzzbw)D zbpGTae4&Q_+u03&`u?-D+=#KoA7z_+u94ZZ#+%reng#QOO#`n<4WWm~YdUXqXll^r zFzE|`ktm~k(1IwA&ZOXxA~nhs&RpkLTN)A(^<(UPOM82aqG;+JAK~Bdf6FP8J5a$6 zLM!Y85@}r3&_JF~+;mZaKswx7Vng1VAj{iI(vO*0oZutZH&3M7vLx~13F$HNV-q|{ zYU&)#cY{_Q@miKTS$S5~Wj;gNpkfj}s&`Kiyp`rnXFf!d+rEG#GxRp#!rh~D1U<%* zEN9>8ylU2r{Kg6$^}dc^CDQ)dZr$C8_0~2kk_w(Qc(Ojd-C29FLXdIDHhXnW!qY{L zPW(7gX>jTqZ%lfusTzMWtRrnR`;H84sO`jQn}NtFXLsIXigKYtU0to$fdh@e<7J*# z;mCK@s*v>mK3^ePqZQ81ITdB%PDnkoJ%Y~`k`cWn^%O&WqL!toE#M^|){T9kK~^gO z>bR6ZiOY+)eHa3YMCNkd?Yo6dMx%Z5-QU}_D(;N_(C{jv=Xq81n}4wmFaM_(z;R>i z0qHtQ`T2E@Y`lacX8l*Tp}#J~Oj-lf5tL#%YCKZ86&>r`Zb2>f8?_qa+5BiIw3bKD32+&e><%RS(;!b0qL?>q1E2nu%BDCdC6(RY_}Dq zmkaaXKNNj~{!&O)&~;uR+z+<7k1hI$9|fCcmKQNf%D#2;&SFwD`d?jySD z=DJ-r@6CYBGndB5){n@caufhb2QL%X6Hc`^Gjm>Ih2{Q;Sc73vmyKITh?;EX8hhva z*Ia8~@1W)nu_yYx#fT=HkxDKn`b%J(UG4}O;_DX{4z#SE&e~xlw#<{;ZYhMIrDJq$ zz4I+zJE8|MA4s#)f|_tZqZ%LeKiT3a`|xV-?0!6MZi?0DNy|qhvY$?b>NM`e%PT*M zo^E_4TjR@!4N~Ea9zj(b#LiMww71EPChD_)tey4)o}M?CO6fbVS<5^+Fin7Ly*Z%& zg_YoL`J`XmSUcKO|1;r)SJZs=$=eb%bI5}agyBr+07lFK)ylww;{@Yut2#Q`Vbw6>Y9y@EUxwym6q*^D{BSWvdA_k+=OeGa>5Mz5Ddk-15|3 z0F-l5YaOp)t{ctbf-@OUpp;8yRME|W!+#fSu(^2IbXzN6g91ZV)lzG+ zR0QXF(^vZRSv28HXJfh;y*O7$Ab7zg}m+jprtmyU9%~OW`Hcra{;mFKoce^ds|Jb*d-HW)5 zc~nJS$8L;&aa330n3W0BKKm4EjW<997-vf|>UnLHq-6U`=xRZd&-M4r42MJ6GRd9N z^j)LHA80lN3^hv_wDuQ=d|zp>IPYlC*N*a88m4j1%f)J!ql1op5;H2hliw;`t=Yl_ zuGC?a;iJAcFC3>i6`sxuYjrPonw6qFZIy2=vRN-oJ2%#3|59{g={1A-a4cNWO5X98!#gK*NZVLgCvzrxo9-FFv?zf zw-+G&i@nv^PU zVoJ>6=Mh+UEl^~dimtNLfa|Ttjg2PRk66%gr&9wha4ASNa#&@Ox9HT5UKd6U)4m{L zU6~CZ*qt{@qwk&&3J_7G`S*!Tc|O@G3kNC?6;RIe&{R{x0;}@8>qJ?gdYqt+v;Woa zf7=^Lu}-(Hu_KpoID~eg)eQ9Wd&(%}@x~)l<4Pr+MA&*cwE%UC=-1>!>4jpXVV8Jr zbzkLV8pGKLLv_|`W=7;Y)25Xb@qUwR<Z_a!!xC@8ZnL9uuSi5|*GPSMmDg=iH!h%?%-x zopVK9qFiwqcCXxS)DC#M;P7xu4^J(k<+4<$UHXSUhmJ{#CbceD*O~Qt*rfZsB z=wP6ywWI$nq~H@2ZsIC$3BV3U7S6EaoGJnv+y=n(dGxKH$4Ht6x9E!r*yI}u0?T)XXSM@L5$ zJAX+pOV{DaTVG$B_5u0+-W?a7kO5sE zG^3C(GnR0#dR2iPo9x|By^UHBG+NymBoc&*&aP=0mjvOh9 za}M3JZJ7H`)7;rHCm})tVc5GxsDB>mKKmPh>UHy9q>n`+6RursU32R~K2*wd?DZn! z$0Eb>5?Y;uE>#?FDR(h(SR)l&E77B-;~}Lv?R_OCs-}-Ij`%mKf|9+p{$;QAG`IP%w zNG1()O?nVw7$+%Im$Ur%%V{lj@leJR(vAFF=a{&i@=2qJ%aIc^SY_xQusX3HSP`6q zt;yEc+P2_+DldpW{mRr3Om^P9(l|eic7Wq6s`fRnND(@aMK{JuaUQK&i!Zow9mvCr z0Bz7I-=o?ZOYU-Y^~p{e*s-wIH;q5jk$=i+ECp}s*E@@wP=F> zxYbv6(rC>;J+&5z>+~7A0Hnp)$|~(7Rxc@q5f5Wcuv1=Qll~RQz7T)hug1$ z0?QgnNgX!}qU`r2Z0R1O#ntcci6QWBYBn2d(mM4X+%ba5NZpktN8dXYHcG>%rj9|b za;kfJ1ejYdtra04vf$u=(p%UXr|?fIx;}%i1dC?96I%J6aXL@6#e2ULe;bkSjq6Ze=dAlzWo3{KK`pBKfPJoxz$h8 zr{Ht}DPedakD`HVIf+A`-w>On(Kmh`A$%W`#D0duBZ^nr)5Y=zHVJ{n*FsLA`*K0tMo)i=m zT#>RJ&xe(HdfVonh4umxybsq|Q)aPe@(aIu>gc_-mku8;7B)`7B$YOvqj~j|x0ti} z({b-jQ~KwBiGdt;7TypL8D55>aVFSY>@64=6i>!o0i1*JwU!T1Ua*xDyY8Q!?XdX3 z9I4?EA(u0fKHBdUe$T~u%t~xu{Ywe;WJ;bo!Jm2da^G7PkN#7%@e!n=u!HZQHSqte z{@-i9ahvAN{cST3Mpo8i71LT;IP{DU2z(D~FZjfW&PnLHQtPOIbb+v=x-*no_NHY1 zGjX`CPLb%vr6xqVNqOxwJ2{31wpNjFa$bK_!NfUIEEJf*_@b*)m!(QF$%s20>Z=U8 z&{w={0HGDD1EPhJU9&rVEJ&SGf|dW1&?_dhxIKPzFODKv?pf}gRSUq$xiky)DE`9aOJmnthU?-?f%tK0XAnpr)sW_6!YAG) zaxGO$!qMtkeAZ$?1P(nY3A*Zc!g5|mWX~I4fwFWixGNgFxNtm0F$Bsv8$Q2bC%q+w zu7Z>7buEF2td#m)_dR7eJt0cp2XT!Q^RBtX@D>ETqyQVg7UlzCb47i8hF!b|{^a#$XpMaOC3r~g(i;>^8IMDLvzL?AiXNc~S( z0h7Lg&(NmAlv>u`4fPvlXn|K@cXVJgid)nQ1zXbv@}Jl5N?cu%?yhgJ8ja(wuH=8F zJtO2Zi;(ABkKfa_Z}<6_eyU9T8Ig;;swy68) zIa&SJMZqS9I?0~(NRz`}_Q)#$)F3W~)`09QQJlj|L_+GWbQ#?olK#(Ku-%|T{lwzZfc*iJc6^3bU&WL@5L}3t%@73yi?lJ zM&}B@w>xV)R<~R|Gq?ocajX{+&XGzcW>7 z**6tkGx5ga{Ppsq2l$Fg?61H$Y<{rcA9_+jV9;TN*HtAF@--SssuuE#&x}&8d-Imy zD)}!1l~&4}Nk7MinU7f`ocN9gDmJyij$Z>mvAx&z;dFV)&7*l>Gyld=9X}A5@aK=o zH&Bx&7V4D0w6L=fgXiwcfW7^JFCs^R`wEYwx%zwSe z_4q`Cf&gH1E*9kJgQ{x?cq{1k?uDle#|j8W{B(D-RMLI1^x$p9BdCCErqZX!mK_Un zt1U|kDjbgtTs^xqvxpH$@0jdaecK{I;&$en*t0PcNew26KPRuNKmxJAX{8guXS7_= zT?_#3@tE70<`SM*LX73X7=hM;crV1cf`9G(i((@6y$wWv6(_MoXF}K?OGIY=q#HNA zo~BZ9HUr6b?%sy7l<7N6rda3T;40V~GLR7@3jv*Ha#KI}?5_1{7JwwhABnXI!^C*F zIwF`QYB~_N{q>-HXikhS7GQC`Z0sQLZ~D09_j$CzIj@TX3*2Ad{Pb_kD~W}Xr~Pxk zW@pWe|B1JK$>|%&%fmc!5N6kLu%#2K+&$|QqN+x}1^&#3 zq!L+pcG6p@=zia6zshEe;*69K#pE9|$6Z|w6`7eT4+zWdynF#A)GEAmq3mMd0%zAk zly&lc>ju$rwj_ZK&ws{Qy>^PutO28ZbbB>TDDvy$iqx$j3Rzjv%2;MQ$jWMB zE}|dF=%*y#4HOh{^gVofmO!Je{^JoqCh+_2B&WX1M{>06QCha~IE-bsVTWPP?TNRt z`VeUGAQU#KVd<`+b`<8w$Z~kWq!Z#J6U`DMC?l7n14qcjg|6=qkzgA-Fkbqg8Yi`Tbl_ z<{KoO(~}AXNLYROXmarNNlA zTP?U*1X>yC7z#|95&pQ|32zDCT+Q>{lOzXzs7dk)p1>es#wSJRt38i;Zypg*n;rB!`*$m$^`Oih1|iV#Sjkn@6kSVNUC%XX}AZCKiQL2 zho{Wc=!`+loayjj^LkyAyKEZbJuJUu;KU45R^4H&}OEELZNdg*tmr`|4;3!u8Ft$a-|$DqA1 zmB}xX^{#PgY5@iiu8FM!VTwP@MJ0$N{m!bOyK2qqzv-I*cEgGpbWr$dxR$59U1@G5 z%>NE@%7+e~kax+>aYJ<%rl;@$*R<9I!>U0-XrUV#5n~V65W@5P3__3N`!3YQK8M`> zS-5R@=fSq@b{+V=O|kl4xC11FkpWW6TYewSxZe!~cxg?H%Vfe-T92}=N#$<7e_OS0 zwsV6T-$UBP=_^p`=z$e;vX%5H`GUrNEc#!slmq4e&5NgLmuKsPGI-myU?zcAE~JDt zN&0;%nQ&f8@S-&7!0Ke)qTI#$)?`)s;oizF+<;P?0gfq8xY8S}g%VmcUnkEtkK;b^ z-H+GTqyA_%+Ev=7lf+@9!OP3bc37Q&eFzuG@*mL#<#M8kv_`-tx>?r9Y;b(F-CVsDKw`P)29|98-vm6I}?0bpyU%vk4@o!{9NT=!BEM zL8Ne7L;^ifAfwN-w^&9_3MxI%zl`+BuPa?#Fx~qozeC#Cj+$-=Mi}a}y+i>@u9vOv zRo-I<{!4*n8D-);${ne4T$E%eD5q#suQ}9zI6ktgI4U#CMbx?;aGk~TtUg?l0JcBr zouc5p7Jok^X-CQMPh|Enw&E%c9mm>SQaNhEog?^1BD`N+j*Ws@s!0Aq_Gg2m6dN6U z9*nl+O)-mVOs(=Yi1)Wl#kEAi;I!N*b|U2KTJObI2I3ysIx9s_$L$M0PJj4M)w75C z^d9ggeYK-s eyX^qN>CdJ|v)#GzeEh)3Ct#@3@11n5)$L8{XzLTXo@FKGLJ9|&O z>Rx~uWM|cMX+sGkI=)~mzj`A5&yGh#U?()^7+-$T{!-61@vDlXg*w~pD9qdE(HAq{oA*)rm8Aa z%0V1xCNmq7nS+Fw5u{&$Q-1cZ6cn5uj6$BCu3TNDozOp+$ouh6;g}d;P&9Q?QbV0? z=(j_7^A0+ZJh6AVqR8eGXfSJM*2;hA6eXm1fnd*A)|MYRHGtipALx2qmbC|AFBl*# zkH=u%%0ER{qTl9$F^bp7BAn3Tw*wveBzQ6e%R6w?w=41r_vfW-QMZ#a2YDHRqei{Q zGq=3tJx8C8BJWuoY&O|2eU}{qM=ulWsT+c&|@$T!~*6Xh$W=4OL|GwSG23h%9ksITGg&%|FW&& z^Ia1aM40SGg+Bd99nA-&8ee$IHKgzU3J*qHjWk>oBN{!w=mOy2r^cnGT4ce{qQ1M`8W1NyFBaw@q{Q%s-e}Tj*Sfm{*#Y6^om8f?;3>g7X(G zkd1&4Esr0fcKWh#3Zn5}JgByLMz$&Q>-gg9Xa?!~E0fEoPmFfJ6=)4Y&)xO2gtLtX zJBXI_%X-c;?FHjvjJdguX9^2~q&+$!(r@!$!dlj5b-CvyJ@Z0s9P_X~p-aeO0`6B@ zHc8?|w_BSXb&;1xk3w+F2OX)gv(WLZl1~!!Pl{HA;A}S$0v8HL0YH$%Q**O)wg|j_ zH#Xw(>NTOB)x+)t#4u=yMHb(|3$6TZP?ix9xg{LjDM73C23St$`y2<7yvKPH?G(=< zw8W)zonfuBc2o5*g|VzNA+z}va4p2irf7lzP3e@Y)5+}~6oW-#67)ZD-#?bJ7x@0{Pg77*XKJEG)&{6E(ALUuF5yd{YcW(!GnHv9KdHFG5)DzzGE6DKyHw&q7jh1 zwF^g*O@?6~J5&QOA)7J*VqKXvxc%w;Y-h*CW&A!`=iP|Yi@#UL!q?C$J+H^kRGqZJ zCdM!N&EBxVC`HzS;H2Ai^x2Ztae?oYuyAh6O=MC+b{Y)XO}J|a&o`Kvxr-jCy=T09!inZA9=R1HwY@A@{enI`t zXJQglIAu^3eX{euhXMjl8P<1Hxwj^T#H`_uB4Kl0mBbfE!z=GnfqI13ZXTBiDKm6; z-1}Z$1X`O|YCMw)Ni+N4`LX5X+*`1W^auR_2q+&Whzv(G0)B)8EfvjdU9K+8TK#Ee zw1q7Lh?})hpxUrunr(`*uvK<1yb3_FxIQ=T9DzQ$l+l;BRs<~#S^f$jRi>0uXFYga zOl&J06(SZt?Bo4;q!k++)l7(C-y9btDo6e=l;PI!Q*Rt5eyUS~;a~&pY%?7sMi^;> zhGiJPF5R57lz6_hM&8LRL4OJ?Lnsc`nh!fm-@c;w8*F>4>^p(y6~^x_)&`tU3a5v= zUuwBLiwEUh_5rUBdpxN1bMrqH&I$&r@||BOF{DT`e^&t$SR)5+-*bT(REsl=6qPJ7 zp-YQ5ySJvCgA5^M^D8SW^9xTzVd~@-MRWSvzKXB8QN_rp5Dj4o7IZ#E`E7=5R@=_$ zhj4ifba?1nuMEw(_}3t`r*7N1NAfxVUklasqH!i+TcZU)s$DAO@dD;jzX6n!h+aVU zR$|9)r^nCi^>QK!$g9UdJeb}{90e{fr{~a1m4P@p6{rq^{jJ6N8o$(yXZc=VLRPf0 zfKDdQS5CZUWkWYYHoL3GE-G|Hn*Y+I-FAkr;*+NVTW~Do3z<5%1SoQH)RDcThuc}k zb7qa#J<##IscG|X7Kdtqf~A2@25jWy{wYVbmN^UR+v_TAY?ZbUmx&$}Riyg_6-D^C zTK<$z$299O{{6cyD@uGaEG{_sK_|b=*5u_XgG&0CVIa75woS%+XVy#U++W|z)6LC^ zqI%@RTuUq{z|bEv;e8#cuVbC|lM+^GCUaM7I{V;X$^uoDE?fFfrkKOhykdYC;cM|6 zXx@wywI}+?F2Z^hF#(`m8T!z;3I+;{SZ6V!;c_`rPMyguKZeFXX^MZvFGdy#+z-jj z%;YIoEjT98$hYNV$W0}dtCpNU$UTEsqFRfL90w5o3X5kO!604oMh1p`6ZED1L@(l* zwlzRP8wJ23&U+(@D+BW+pXV4Ra&O=b~GME`&RcR3l@{lw}aWKNrawc%fHM0g-@ z>}wAe!Na&Zp`?l>_|U8F%?|D`%AoXF09R0lfB2~3K|mbnTl#BItLgahd7kSLELV;v z_$I}y6%z@n;STB68DX_nWEC=v%U)Gs`UXn#6NxscGv06Cbm7cV+GVuimskY71i=#fMM~n z%$RxGSdub?pp`{@C))ELeN< z9%*Bb0yfK4wvdQEafOR4{BvG(^u^Os&W{lCX-*`o8*<%l_Mx+jSN1H@NwsEipzc6o z{8{UpxCiD}N9RRoAqPeh4qgXx6Bm##^X{rwAF|MM_Y zQ>+IX^y2GZ;u||VTT1hDSJGjRm~_l@W<4MLC!^I>geZV>Vlq7tsTNBQmn#-GXx=Y* zfUbGMpdpnsGN79$?R4@1r*CO0lUIU}4GSZzwRQbAfs`|q>ja@1E!o%f-gtS@V3Kf& zK`>`q5Nu7j`fxC*JKNh6B2v#6%()F?9d_%h{IVzZNSo-Yrpm3au8uk_Y{BzOJuP05M=|p6rB} zCg7rJr&)g<+;{p}ZE#8EU}^Sng^l?(dQ4vhT>Fs(VZO$uD~L%p%x%p>>xi$dl&pTp z4nbw-wCxDh+jV_eIhr(*9%;x=W^J?CId~|x%s;Skab4o zR=ePm!yH|ZL$Td6#2=JJ^D0;|wF7!jq1D&{-t#!=xJ6*?RGDz^U1P6a@ckT?iVf>S z5zBV22|B~JsM1qbk<8s_<+Fky-koikDfY=|_zbTPwS=5+Z&4BM9th(EWS&ip`YT>X zuHB^!D`WNx3^Xc-e#LXuUU30b?OB)vGdmAwZpoJSidrZbbIMbvPTd|;)1~`&P_We7NM>*YHUeW5k_VTjg9NENY?bR8=aRGLR z)}o{iDerGGT52{z=ISTvGV3{@I(b9x)fcVXDXR-Zw+;ecox)FtqH|^@)%|RK&u*cC zX8^$&Q~kEj1J!hmS~dl*H00Tq(a7TQp0q0ra12KZEL_bO(Qfh$y}6;W;$#rrc&8ix zL0kwq1IO94Im7$~|LD6`Dc*zK$=+vx5M8c3t%EXWS_`EnQ=saN5`Qv*`XmouSoW(( za8fZbgA#NMjsA^8AnO|+4<*iQiV9*{QqG=fz%o)&_tV1Wn^Nu+WrFTu2xG}&a>OWr z8i9ozDsBiTq;koyzL;bjA{72xMWfL*6ez_xVx)97^l>2+_eea;A#64Gy=?shE!pyq z#ZU!$g!hZ3+XIW$NJWIG(Sfx99}{xsdNj5M;yez8zoUVFW2iQYx24YfeicWh)zUlW zAD)9#Bu5Rl0g$#Er$1Q)pCRAU8VeafTY}u_;KykYCc&%lz6fif>sE?%eQ4_=y zI8y23j^|1iSP=4&ATg4;MA>qn3-uDn$zV|RyHH1y-}T_BqKm|)idNTa%_4%oLsr&v z%8k}a=Kt3MAceJ*3Guqqq7_P3p7`fTC@tREi%UFE8}%*4MdLv4miz$+i}VbTf=a3? z%1aSHGy~gcL6ydl;c(G8M+}DiT*z2l_0hVq9(a)WeGe2I;_?7=bCsscrxa@1bNJC+ z+g=;r6?uJsHQ#aQuUE{-HpZ8ZZ6*`aTHifh4itd97AV+s`%bKk;ENN}R>Oka!i zc#m7RZ~c1rN_iaDo%7`jAoIaXZJNR5lW`%%q{PHjNSh){hjmC8#2I8-vs|~qkg`96 z$a1T>hb+%%Wd2u4gy$=V8346zaC|-Ey3R_@F@a{9LWN?cruq?iA;DCXs7LB9#mGUK z1BhVu>lHKl%(q-(6U)$j2nB|i5V5kn5*^JD4AqqQr${R^tV;pLAlJy?2e0}UFHNVr z!W1!ZP%0y^ATsqlNK3>FTw_9Gh4i+We2TPikfhYJdO|;-H{!s0!tcBetxl!SMCl!!xVoey}iTtBV>f8Tz7#;1;XNdYRO!K$@X$%8OT2GYUE zBb*it_WMI4u@f*J!G>-(;mco~lQ>IYf#himy`U3OwahCScT1)njrp{}Ep+ACRQSut z-FN?XWr4^UFFiif3f18H-MG6!#-HN39qCiC&Lw--!Mr5%PB&hG9E`Lah}Y3> zXy<=VkHKBERT~^`GQ1vivuBen??~kqfikC~5qfoS)^?A0*wmI9bGZ|<`tVhx%-WZR zr3bq4UMGKxUM0Tij0_pmnX@E1eN`&NZ#XT^@6z+N206irvJP6Q zM-`1z9$dCv>DP^~`m#Q-@P}qThxasq82|}T_!mfu=T!%nAh!(LcWUppc6b{Ct4ed? zBjP1`BsB^8X}C%w^vcCL4-(ovuJCqMx&C?LXWx|THO(f-^c|Re_l{o@^z4X;lU2$d zzaf>AeayDm!}1@co{aqU!QapIh*0<6W~p;F>}|s$;!uG*iVx!>)3Tk58ask~J;HZ9 zo!#CBzjbrlUWtaVw0{%p_MTd_R^(RD&U-O11CnCe^ROXuIpv_Ws%-vyH;Lgg(-HQ; zhA)orM|7k=SQGS>!vI7Li)9kF$bn$eiu}6bGGF)u0Y?!y(>6KUxL6;G81AIyarXCR z)&rlsBMg@B2=mEK@A{}@W$~e7nndA@rvAWcN&Y`3=6_#LKK{fuViCv3g=EZ771vqK z&FPJQ3swc6NVs%6mP?or+P^DP7&~U1s1sl+z%BU!)a@WMgl}#{hyJ;GR9CKVW$dV2 z5>W&H_H~f>DKA^)#FTZ)#Oi~;G8cI(S00t5N5tnk7m<3+Sjzw;_TOmW0q$aMz#5Av zI=-IdHF0jN?<-&io!*mMW*}FjODO`UL#mYHJmS$1;Qf4Sw92Q}dmDZwFI`3-t2$8J zAZe`D68FUkT6*XGCn@3C-ZdS#6_Ci!|ed_4A+L<2<_ObQKI z2J#7Ud~+pC~p zk$*GD@)$`Z>H2yk*xy|Gb9UP#KQcz49O+!}hsN2d{L9!fGQJcgGCe zM3NYjSI5MaxLyJ`VM z`Z<@FB_UM_toCdeMnmI2B8b4@^S+g>dnNFQXCK0ReP4<*_X(cYQ9Qmg5)6VC63PVq$Ee!?K&B!q21V9B!8TLZV z#(4ngro9~%g?CaCcDGy?TPRQ{g4}XN9FfOBWGcQMD3J-6eJIXG0WY-Ty-b=?Q1TQ>J0kuqaNcDwR2f9KO2C22Luz& z=Xrj%+92OrPepksP0@Ih$+&ot0*7LK0w`IN7k?zPhKWP+nFCWbz7rg`1f zT+YZC>iYk1?nd_!zT1h(rEftQMNg6GvC+eWFRsb3;_j9dpdvn`!aQ|`PSgN8b*#0& zU!mgDKV&ongbC_*#3_=#1#uz`3UxjPzBzbPv^+62bt{%b_yg>JsC7UOa01|_FF!8B z;e04MR)kHM+GCU6L)z2k5AH4epVQ5U4qLv^+OnVDfFyCv(P~>~WF8Fq~=95ElKEj4EkS zp!J)iWv8#V7d(p+*$%%&0JAk+F2mp|LC7QKxqHZOS&P+yWBTe9T=8~CdPW1NaeI3t z%l^SFTw@A;{Q>wy-xe_j0=wYr2=#!>u=%LJb2dr=YUT>vP>$fp(JudBHUBSk9< z=A6~aA9%GCJ2fNw{kzNO7^Y;d1oOviCRSGLk4)JgFHN$dHH3#At+K_L43}ly#hFAh z>hhVgP{ieZd)?AA_Hy-BzTxvZ=_~5alf?^m-Nv{Ubfhkb#z#^rl&7Sv&|d#f)wYb* z<0wX`ByvbYO>O6;#!cU^-&f+fs5dXx1W4l_lvu=&kX4(sMyHfwxiF(lG+B2=y&V&x z2+VR2@(v}MhkfFjvTpaS8+p5!mp+*IP;?;Zvb0DX#PyU9BfHCFe));s49rdWD7wF? z{k9-@Sk=pnY_mK$xdK<_te@gjuHNYKjb-Q#d{I~hjm7ur2FRkbxacM}`+r>+Dhf4M zL}sDt>xuPUf7_Y?fm@9Y?=#}c(I7tX^~1(er+t?fe2DL1<;2FM<_$KNwx4F&Qez;d zdSCtnkxuaQv?HLxRSY2ZX@f%PZtmwhY0WaiVbM4#Wx{Ic8Fd|fYN_mh^Vl-(%B+yX zjeEKQOz;Xv3Yir~Hvh#DwU+^Xz239iEQxKlmTf7f19w`Fe752oHof=OS2Ui`_>((+ zw8W|SeTAHl&Bu_c1FPS-7gKz!%&4sFx7(lp$s>BslY43JbL7vL+kC|n^!anJ*6!Uh zalw7b#Hs&qAGV9@ANxma{LB*uv5Z9nBvp^DPmUD+?e*2;GvQ-nV_OKC%UFu>PApd!MCi^Goc#J?5tYlY3I1i8f}%k z-+bfIbw?m10A~47le2U$&d+!mTsq#U=<*z$y(G?D*9eUm4Z}K zR|CgT{83{Jw+4pGflHT`>NDs@b%{=z;GL)-ZpG|zbxSRN;T~of!^nYig=p&ZaNug7 z)piW7`IW4e;1)etB7S|7UdxqU#6X=G|H@zD+h<2nJ>eRB+s1rEPbjUnL@fL{Z0#vz zef%#$;6h8+b{L6F+!kzj!iduiIYqob0#-3v0WHeR0tQAh6t-~gy0UiDM+-S_Q(>d` z-g#LJKR0T38;IPKnDs85Eh=cJ;_}=N+u3AEcP}) zY$uN^IGKU`FP}dz!M4b2hGLvxE$VClRhYPOn@3B3*;ZSXT5Dt_=AZVqM2&9Ezl!S5 zZX2aW@z|IkKYi|rIBbu8QP5nL#9y|&>_ zoS_8~+D*KD9{;yuy)=Lq1@;gh3z`!{b80 z@{zPS}Ou;2JY*30d*i}YHfb(%teh(iY>)Mhse zrrFfY#pU83<&gQ#va9VS*5nW5mc^)?U*Ugcp7#;L-;HRME%7Qv7Sls0)S3PR)*=Pc z3#IRiw4hCVM80C;z8~+FP<)NS{rti}90C+*6&?5sltVImliV7xuO^JIYc%?Q&a9g!rcO0^1|w351nlW%1!{={e40X1yYJx@kmR! zppaHZb)8;t;|g(j3!p&G|C4|$QzfQ8m=vLtNG-tK#y#+%e8ub`fgUnCf#->VU}GwY zrAqaW&JhZhRb9(g%OkT1)Z{>_Rx-kgHB{=nL(uhysEX{L$A=`%hnhTp+{a=`6SO{s z@7=XZMeE1Jt0<(%o%0FpOjKSruV1FITJwE)n$D^VIonNsqJ^N2j>Nsh4;`V_o_XFf zlpe_!f?a>7+Jai@QsQV!=nY%TvtZ>6%CgfY;?Z9XV22U|Qt&)CIz4^KSBi66Y11kg zx}`F0XW+i+{ZiU5YtI0~-)5G7Sb|ue_4?*i)7kEymh_e0u+gSfBZlcwyX4`V0yPww097FmK_` z;qt@P85AE@=~4h!!o3is(tF*^pi;E02~af@qZ@Arx2YfiQYoemD7&Cp#3W*@MJfv}@QqQ9=NfI0 z^;Z-98iE#_2yJzY8Ngz=m3N>DP79%|_J;uhRi7dwDsrY1#7A%5K7}&3zy#Xf@rMvn z36hvOR2HK+yEPZZ2h?{+mU}yXv9Mo6r2=j^#0lwSg;c;7!zUb{Q7qtpy;wvCo@{TD zm93SO<#7E7?OY>leLVX@Cw!XU+qWt1efZSVf>j1fFQULhoCC$cBa+PZ5i+23Zn;^n)YUGJyHDWLJm z)+^kXu~HF8qY-!}Ark-kP&ERQD6i#6dwcx$5Vz_p_CBz@>9z@JD1rCfF<;S+)+c`| zV)%9I&pjlqJZJaG7bXgLR@UO_nIUP&tbl2wg=@FBQ_{IVNW_BfMU$~`W+?66ds5%5rcLf zff_1wy6NHXoqpG;2pmqTdlH(pDKz=$$cVmW-0DXkLAK%VwR0tV~FiM9Hq99mCSHO z1nhaEdI%=QzkfNC>`6aK@)%?Qb{v~6p&UjTfJF2}J+YSpn^&-$Kwc!hGhb@qnBMJl zp(#Rm8_t__i{Fi0|A)Mu|9B}hja6wIe4bu=LZqXjqBH$nqLc;hc@6guJ`1G0x}zwo z^I*9cJ9I96*w3kz-1=V;i>kpTjj3$?XKO%ld76o$tcL?Us&i2-#*a%Pu&|!Mz(hYUoU!+~_60%rz6MLT6 z-b*I%T+J`EE9VmUe2Xc<%FOe4&1Ta7^2eUF@0;Du*MnickFGI6f<=b`6y^$_LZE zmvMxD5pnKKc6ye3ipv?HL9mw`DGVmJ-ZWmXxxh;%~)kW9mV>$3ABT2$sg)c-d&88iirm6Y$pT;IR>A$+!ex=79-Uws7FS}KbY?Y|wxeg4w& zz6x@3$g-SBINf(26gtT>gc_s8938B8WZtcRI z!NTy#?;^;V5*+u#)|gisqt0p@;_kkqVTGX1*>-9SF$G51p9488gy-TC z!*PT&`o~8eqI|KXtnDuYLe;W$1C}~?W!}TXAfa%ct5l2M`oPF()%P^Yt-7Y?I1YFCjRa?W7za@-XP^-ov&t!sF1AN=6?U#vCiBM_(Vk=#vfmh zP+gKB`B0m?944?6-l_V9_hKBxhbQuas#n+zGBu^uUnfuDB=f?I>}jp#WQpmJvk)Rw zdJ$;I9VbFOYbttV3TD^Rp{COMx&_w?)Vkf1aua>MD73=LpZsmNJ8&@fZq0U4(=dn$ z;_Fhj*XUQzg1n)NbrXrYa+xZ}CZy+;W*7^Me|_7%GnL>eJGNQPw3`XR-h1*NqIst% z12O>tOWu+QKI^{GII~_tTQ^jC*ll#o5Yr-?N-Z~VT>I$gZ@zR;72LAHpRVitPDS&> z-Gu+aZ^1%Y*vme*Ckegxk>AxQKnbQ6QkD!UO<$bE^T?Xa|3)*I5R+T*=H$N3JDM$W z-Q-{4`f&F{!{=N7<(JQhhhjF93OWO8~GUj9t0aiI7|&=+$(>#7V&X zf&2SwrI8S#9i9TsNd7vq)0F9EYoQ!%U#soHNw@OnFZtlnLlZzqd})Z2S6}qYkt#d) z>q-K_MPmWD!3^3%>$I4C1v?M1VnmK3m5%s z+pI&0rEje5yo5}jn}M~hO5i!`S^(`haVbp$kjEGLzyW&5^?SuYlm@{FL7$UX9D1?! z2I>8~VB{v`i%*NaD!#8UIo{V9Amv_)EQ^XWd^!Cv#cWL}X~`qgpd1Dx^bUP`IGxka zzw#`}uF?*g@&RCz0?Pq)!(=miqms=uuD6e`^EVwj)m<_8my2O%ew_fL^?KE3Vf z_*ehc=sK?dy(bNqm6n#if9pa{7vwpL-J$>j?F9$Mk)y0U7(&x9?V(8b+@N+H-;v8a-9XKR>@f*P}*ga+RIXv8zx1G5XHteV;-pvJyWDG9;_L zGO(+S&f9!6J|@R=QkP3SSBCSEvn`O+h8(4BJ^qdLgBctDbm6g?M$~v!T-6C0U-@VE z*Ge2vit$wtFMs5irInZ%q=Z3i`3d~|URBZ+@AVNc{c{?vDOiJ#@vezaBVPXP|+T>|kOM}a%o@lEzsme`2K;oQFC zdk&u)9@SR%mA%t3atjHKN}1*@!FtUe*`K7gp3Shg&aG0D6q1a6`a~B5_56P=fM8I! zIE*Qp2%>AcBCCY@wBMB)pChEP=2Y&j&*g3lQ<4TIf^yhZxp)dSUm4ZLzHCywO_$tA z#~rSJTanaa5n%xB93Dw%%EqG~kqpEXeb`PO8NYOY1y*z%_Rja5?)^t6?@Q}GYy<56 z8qTR`vk$pH!vJc4f7*&zsiSvMmkPs`a&=#bj^RL=kdRa~{Q52Vvrs1|#dEEPJJcI; zai`fa0OUdBA*(EJMERwM@IbVIhz=ni-Wo-ff`E!t-JGs+ptlt*efa z%&A>+Wc(*jUbq^e=9dYd=|F1D8>_`@VS$kAeR%893Hv)Cpgbe7iHNv}kpw(DyU$iT zCW3?7L`ybA!$d81?Ugys)y7$K&M>~WyE(G@iMI3@01P}JBHz~zAD25fV81nH2#!*to0vTHWS_y$qad0CHM@$+7Yucea3lXvBo}gg=6U%d%hpWYA$K@_l_K%XB#G9+pUQc&Nyt!%K#XTF;H0rq z_!@BtUd$uHI~WI_$uI3|4LQ#C2YLe^Mei(^m8MVv8U7&*>b&K83u^|A4zMqfzjgsO z>+`lMU<1$*=94&<>$(l$9ov9GBV(Exc(fe1U^4UOAfl}T}(BIGD z(Mt&EkIS65T>rAejM-LPcBMFP+Dp5GVhQ&Rd5ad-(PCm6&qUsh-d~d;lfFY3YjRSS&;~Ufx))u6 zAGRpVxAYh5B(!b4ehv~z6kx4ej9>QRXPLcf<|BAV3ap`<(*r-{1fd4{%Uc)8Xjs32 z00{cE-f$(}H1)fXW%6*?JAtsAol<{QK+DOnZ?=^t!K(zT36Rh;jT8${ofptSJm<=% zK$IePbv9mz^ceO<85JfNAH!{C#2SyVbs)&};#N*lFDI{BHU33X=;u#;tJRzQQ+b* zGI}NEcBX;RQphXpP;$omnPh3ah%}OD%86;VS}5_}dvhw5XHN%Ghk7E7*UIs;Zurm5 z(i5Bjb3c`Q4URw3UUf`!ehciMR|7{5`0Wo|c9pR7&Rjv4A^-F3|IAQ^vr!<`3)5>v zod_k36n}31F3~G8-OU@E(N@qk%}S_MkRM!F=a?>gDryh*-_!Ws^sSIq-Kb-Yahv2F zcVqAkUENi8o<0p(&6@6cwv}s7)9H(^Q1y7#+*Vq=hhWSi)arqZ9P0U`oL{0lZ=XM! z7_@t`DB-HR=!`0z8+pujETT6gcVfka*VmW$4>nX2z*>vN|re^zv;8& zW$czgR?+w7YuTDk>OK{*+d#I!q5RQn`fYl4zpd-W#`lq^nU)x5ROiCGT1Q*Z4tIYW z_uW`*Yn3?qd>rE(X;2Lj4QASw#EN{}Ko*gsZ?G$*#yizdvBn@{rdR!Mb z`nkcd6GypvSSS8qFqB`hts#zs2YknYO_L7;$VTPh3Jy~0E~0dN zR3vZAq&z9IRzS@JKa&6uzZ_*dU!f~`|RU$Wazc4WTGiFq_qm8dudsQ)iq~tL*saJP5wiB zh7(x{#_FN94orFJOCdD+0Sw=2D8BaWD#64vvZ{%$Y|d8VA>VwC&K_@tKc}-(4nm(T<}JHG&Pv<1peIVyOKG;5O|y zED1fm9z^cwCvJJ3A-QaCz%<`Od{dh)WcZIsarcITf1-qy{Wb_z&s_rpOIUs-KWx%zE;MS9`N`V{^vWaLEFV_xpc zz`OczNlH7%@d=V9QlwgrKIqb7ZRLVmFW{R>???mtl~``!>FMO}LHZ2OT=+{@%~fc6 z5QV0Tj6ln0K{}*|D$MK60Kvd-AjEyd!Qj$*mEcH$PyQ)ucmFahOIk@|b!DH`x-?Cq>i@QD~E6~_)!}Sq~xpmAlhFvF!*Uw9AuP>C-NG&=gxbp zF(x9E+rY)^+pJuvmIqp0_@@p}NSLw@0aq0YmBwY>%udb-9H~`MLB(dD4R_fg;|5d^ z0)j|@8t#u?7=?dt`fA4iDwvLip^I077-?c5rdcKa#E zBy=wGT*9r!zoU~(Jy*|WV%hr_L%taVKFxac-aYb~u}lDo>L9diX`}I$cR&|&VYtVi zFDoy`cL5&j&Mx}!XRSUwFV|^cxuTJ1kpIiEQI*6D65$p7{qc|^c+~jrS1yP zOi{lMW=5<#0*^>L&*2JtQxvypN-yuMf9^aSYGeg~5UN<+Ke=YHgvI?Ypw#hg~-RqHoFO7QdmMiC@EUHeXf zLldb9oZOV}_F9Dp={UnQ$Wr^Sc4lQ$i2eZeUB;M}Xn+Oy_{m%j&V@SKSxRD?|M>#p zmd(XECu^pmo+YQQ)*BSrfPv`*WtT~l!RWUtz=G0=n|DR6?+j}XyuZ5I-=0)ViS<9u*@jty1 z#tNGrLmI=m^`sUI9l`%R2$(7?eQM{vM?DS4FzgPBq;>cXyj11B;BPCN<|rEoP;oEL zNrsSBqyo30XQvsxBYMg2>jSiiuV^2iBmy5yGTP?#!CMF6HUM_k#QS`&ncl^Ty=K}L zE|nWk&ZwYNZw{;e?-epco++0FYNd@U zL2+};Z)EY6jEfOzV+T(%YqO#&zCTb^gv&R=uUqrM&vhoA*bGWF5Wij=-RYYhqA!ze zQGGkVxcH;ES(`#JI36dcWfluzU)K#u!-@B~bhk|~5Ijo0ew1)0D zFRj+8P^*K4%+EybA%nl}y$cg40`f?Uxa8h7fB_vq{^{NekLtZd(R7_o+#~gNHLFm} zXW^WQ{W=xRBtJM@8;(UYeTW&Su|wfs82AkH1bMJlx@cJK8_{-y(co{4e) z-kugh?KV11-fei-1WcO9g2JmDs!$7MEQGdkA~pMJI0xO|+JSUR9)rrT^tO%j10wqq z{~4s0L=z7Q|KRDBs_}J2ZO(C!f>^L$FyF@6Qz5M~ccpUN2Ej1VLWi>r;4mKGN`g!z zbS_2p$ZJ0`fL_n}n-Mt5(Fb_d)$%vE_7Vaw#l91-!CxFH>nrVL~l2T;9t zXdoJtDR-3MFT4ih=BUCiZ_SeD|mcQCZ)wxjnIE%XL5<#B4d=({G%Zt=ct$1qi za7*9Rw9WlRt)(6UT)mI)v&)3!NS$n_y`&?O`!k}Cs9Vb-+7cAQ6Mab4l z3@C%f}VVYcu(Ux(_!t%T`DJN(_CHHAIna?I-&S2ex`LIkmkf4J!;{>P#!vD z#;WyMhb(xlW8Zft`Bfw&+F-CS7FRHY`2;fk^WTw4!wL$k+%7g~a6?;c^(EZ{GOCn;wDSv?-`6t|HB(QE&<={*{!R-e` zA81u@s6!iY!K+5Q2F_>YY26PWKJC>&JUv}XekkEnklZ8&GyE3=79Z^0?3okKux=Ld zs>>ZpV!FN)*gAjk!re+TIFpI=j)ccR-;T_@*N7JzG94bxs=jhy_v_3!;X1FZBGy#h zJxBI~jJT>`R2~bk<#0H&U&^P>`{103yCDH81@;!>6dZMEt7vQM*(NYK^Od2I0Z2tq8TR^92&!z! z*xXhgn3O2YlNmcg3ilLz-7G|>)vY>%@YdPEFq>>iNM{qk+RWUlL_^w4S_kwK4V{ED0f>Cb_->5W6} zLimH&oVlChCs%X;V#Jr?3F!O6p*=JmXf2LTr+p(MRQdInYBXuJ29T%B9}<7j<+Z+x zZ&Pi*A*qRHLb?}oj6q*KtC4wD+WCeQ_bv(i_~71ah)WLF=#90SZr!r8czyf5|2~Y~ z;YZT$lFm)yaqLnx^Dmle8VYRU{dRr@J-+&#=-I2o_Q&4bNJ5olz?bh!_hEQ(BCcZZ zWI{C!XNb7XIt-mLGt#`NfBu^kWv=&Dsy9?^Ndi#CQbGYCEYi=lVg$s5Kpg zg)*-|LTO{)KX-14SBI_a`FTuVN|7*Yk25(oXOwi7N2%42o$OyYl`^K;2OS9+FG(fw z*FB$-+Ha95VlEYpeCsrY9aqBJ{g<3W(y96WdO2FOA~oG|re#ryFOgJOP*ua~y6#V< z4k5wCN}KgCv6t7ESdYiM{YO`%kJ>clCMy zYSJ1iE~e;&94(%GMQ^9N1Cp9Y5CO7fW8haA6Y2?Nh{yXRBCJX_q2-(tGLl)(8FaO& zL>AqJ=RS4;&-7zrrvB1CGy0}Nm>aax2eX3oemVxy*8!4_yXobDj1{Tx*A)~T5G~AG zC;BlGf2TO2x~8@or=Xw~fJJU|XF5ph8mCBxsRvb~!;WN&5PtbWztX1*zR?%*rGeE~t zdYOJONKAE8(h0Uwc>+0CrcF7ASBIi(Kp1Io!EI;m%d;3 zuY?I&b*AhFMjt&a{0{pC!&CCW+ux{EFL<1qd301!KkHi z;PJn;3A>Gg=6*ntpabD9E$cN@(xfU&%er#ZW)EqMwjs2C0~EA^Z|u%>!ddu{2zX{N z2R}&G_>1e6z@5#NX8o^iziZIPan6Bl!6XJ6G`q8qbyY%V*q)9a`I*A-Ye58089Gp5 zqMzo;gdAra;N+nEji{H-D5U5NPj<3CNB8lX6YM&keO2`MmYTRG3ev zAWGBCE-4SEs>CYvCproutCc&z5s+O?&Q$Q`h+gx&>KgU@NIS3v(Bjw)71fU$LqP8b zJ{b0Gmfmynmd105n#7~a5es=)BNWK}n@8D9K?16R6LAbquvo261|^5%goQfCpH>`L zhQS>)7GM)kIqYlB0A9eE$&A|qwv4n`=}oE1BYrD+QJ5|&jBc**i4T?0;@}_XA=3zk zt2}rBB*2}vr~H65Ze-pUzchmww_&k!8z83@xuC$%4!p*rrJIFJ8wcynkmA{8Sp%e{ zowIx6y5rK94DO)N%pIyrecxx3Q&P5zb(9b~f?$0$Nrhy^11J9hU1$2tjF5NQbzv!= zpx10|lgLAUJ8L=ZbF)>jgL69+G7HzvVUV9#uN?S8?1z{!Rjo^`eaOMm_`<5dDu1;$ z#1H-L`dZx{WoZK-qoDD-eTer6OWdb_}QFQb~d@ZpoMA5zHNO>b|Q^Vvj% zA9|-cPbX7BVvpLPr`>XCIDs?lb*l!I!k{i6k`3M}SUsu;yXiOL_HOIK#GSnlg&+LV z#JLang8kPOY2snaLw&{Y*W_sm z&&f~^2D8tX4?af#UxWY)nd0#TutLQA&kvYX5i{;5U+y9{ldG3}evu&C;0bxTA^bTC zZ@G}`*~UCPh@?~_J%cy!1K!Pp6H#{8?2~X_<`rQ+ox?McM^PHVZ}Ey7Sr8piQcis6 zx;Up*rQVnHxYJ(3#;Dx<@S~Tn@79>Ym@a)$)}CA1q{chTe3z{#xB>(y7^urPpIT+Z(*IvS zlp+&S3IIa6(zGRpb}9Q!L6d4p&RvAn~J=pT;D{5Z2&zj$#6*XgBcvobFX&r zUj|OjH!(+&0-cofS}(V#7JyW}o_oJ4?^tf?!yV7YyLTaDd>#r}*MMn(%T#9ftOeMY z`hTVKi}cu%sDB3Ez4-cmF%_eSw`hkhwj7;MouhSQ_Ky&9x2=X>F#Bdh0~1R)Ir+)E znM^l<`#ga|Jdz-17VXNyA-X)MpwI3^g=uM&AjDqm!bd-0*OUm-qQW%zm@5WOmykJ0 zQ1-KLr@@jXV4;D0(J0+TlW!l-vG~Xdr$Gms8q=Nve=Q3`&>(&eZYpB%kzFQ==U>Ag zGD>7P%t}YC&saQ@33Tu4lp323O1pDE*grPGb1ZPwRy1>Tb zfsDC%6LNQqei*UbV;uVY7)Ny**_0_-L{A1Yeyb24yLa24^kiMT$BS0D^yMB@!J`Wn zF&d!Z1;FRqz^!o~D(@_-s(z5TbBJ!4$cGuM8`B!$w=irC?1Gf38 z@ju%A&0ebvHm$qACjmEiy1z+QB5f|BbV4UJC{iET@lTg1*AARHYAd>DLfk>OmtsDJ zf;C0>Z$o(moO;iK6gK_!z)=vn)n?L`QEOe!9%^n>H%8y}5=yC5CIR&p}7=ACXbeLQjV(Z!0a3d>z(!5d8D6bgS_tRJMR+ zL7S@gi2gYPlcoV*r1LRM5}xvYb8W1j&RfOospb!9x?m8&B_mT*jtMw>n=gW9dIhdg z%##i8Pjk?EIq}l|Ycu6TMHN8<(AVjelS;IxJwNG(cN zaeY;-498DO!5@S}GH&A;R}Qw0x1w#GIm-S#NH$Zn{r=S&kY`*5uNHvMYY-0ax?Y>+ zJw6`B=+W&Tp_7(%`jd*BMM5Z%$!VSjM8YbkC=sG4An0wP(W5)=@ST_i}(@Jp0K++_)pbIw7shy(#82uE^; z11vcsARq!tkess;-6bhGd)KG?aO3yW zN2W>>OMvNyn7Toq14(BcwSn=XdVa@%eYPP{1;)DiLxRbPQ}ROEk?Zoy5iNAV)rY6p z@*%9%Dx9xZ1nIaM91O^DKs|(X;|<+^XQY}&M8_V-ahX?(Ml8yYlP*Rk+o~mRi`uYI zXOeQV%@aR-#13m)gSgw z+NIE-?8O=&l*qGXshZ3)%P+H;G5RdV=jh!d&4BAE8)-(>oQ;b?iRGi9R%J>{RGwsx zM(RtQCdkZ6=D0y3KVZ78-F{zmV|OdTvSYlmPe>Vln`U%wl`@aFClSu%<+(yYYJGmb zRWu-HuH7##Gg3bgez;|u^x-;PR^RaCbTdyoz|XtZ7Fc%E!a!yg8JMyV>r~Tn-JI{q z!D|!Yhbujd&^Z|>cWEj|51ZU<{fuuU8$%wl)OI2As(wmuZZz4nRqt_{JfY(^BR6Hu zl^LpS5Z~y$f94(@Y5UJL)gOl+E!1jI0YQgid(Kj>6o?z*@$#dGq8S}_+K%bSuH_SZ zwNR>UuC|c9eTNeHMGGs1SPKp9iHVG-v7IO9`785#%wIlAR-bK3ZH3q5AMaQ>iJP?( zCD(T@`_@9=dvXP`CQ`cXRWMDa=aD~mX6-M-$U$sEt);_`4438v_i4Gj|Bj)GQ2=HP z%Fq@J{{9ZrSitiNu6GdY373_TS1!idKS*`_GI4L(ZFk;3G-5xroKWXW!0)4E=Lt_H z;JMNbM;2q;O*7IRQw~6JYzti)-m zM8jyg{tFveZrCaoH=Nt~8gcwpImG`ctBq?yf#1Rgst#svPy zE@!Egt7D{QJv%?^;E-hdhNNlcayu!c7_X# zaJtAU;B2BdZ$~9Ah!BhKvwt{?=ZwWVISZ`roa6J|4x_Sp={a+6BkZy3g2h1BkMy}W z22l*XBJ{Zj-)w!3ua3c&j;BGNyw(8qN8We&e9l~n7$2}=Tv)Gout2`BES1xKwKn^=vT1MQAqV__fB?p&Kt0L z?|G^Vjg4=>O<~gL)JTqMtssIX+pD)%HRM-I1-}c5_=4hy)3UP6(_I-Pz3Bz5i4z6H zSUO*3u%uR)NKvNZn^D}0h(7q}$rxB-mx6KVa0&PJGs+S8d+eXd>&q0ImJM$yGU}P^ zkaDu^J*>az$O&6;54)H!Ic4}wnaONL`eKzdazRMw{dveymg_N<>x=3@+W^~kHYs}g zmP%<^;icTXKY47&uLQFhBi;z_ve*SOF3T>tZ)>kQZ3tAH+6OI8RC_Re}ZT2UCgH=j-oDWZiylIs$~zRd%;2-|N(IHH9ZzD^*K zXWNzL*_Wbg6N=L##sXy~sH66?)#tWiozS^C|9H6nx^dta8qN_?x1BkHn^DMoZ!bi@ zYNsO!8M+rn7hLmFtq3=rq&*;^3h$QY{0aj|_47T=j)HJ@+!uykBgy?&@>LxqX}Fay zYX3nUS)iF_j?^*I9PL)O+QRRfcBHB}-vc?fAZAvq*3{bcAZH3$(dWb#Mvfw(53kfg zYDiNj#zf6i*kiZujoCdzbwwNEYVy*v+UZG-Q6@tjahxijbYzHNHT^*3{)0hnKZsHL zvM)FND5{c+&J6T^9uNIPI{w=5z2=w)! zU~3L8f>O`kUDTp+xitc#|C|#$X3eV0*Q_{wiz8XuQTrhfJr=4{x+cFwE)X+Vl%}0` zH%ANSkSQ2>Wu!3^o!=FTf3*O&Du);Z7H~Ry{qPQ?h7T_J89(;staig?#wYN{p%a$f1-b)VYlyCZ4@ty6EQ59U{OC>%wOhk zf#wD`|C(v{uh1L`;F3{y-i%pu>eR}^8B#6w;b zo_$`KLj_25nmLFFSDl_9y8O~3u7o_Km{&hsxTCY6&A3PG-rC#!o=%t01cE3;o=jTZp4O+`tck#?Y`oQ~s zPW+Jg^g{%UUf;3wn09`3mVt)Og#2wjBs%`Var0e`I{XPY{_RwvS%aE8AH>Wxi2g$} z_v+$znmE8LgmO&S%B=l`ISSq!dTb#fQxRT^me$H5lAz;Bct6<2c~;6t>T&!6_F z|Mq(o7UU=ZmktK};f5y9qtS0m8A${CmDQqC&B*tMbhwGi1k6@1>!roTug~&moz863 zK-(a+{WrsQC7?4yiIj|>fU8rV_|Q#brwB~KcYMIdRHVM(JVbgIA16&9U@LExl+RUu z{ABoqAzwJ!>cm(t;GngB+X$Lq>6z8X7(Oao&9ltit3?ljUp^E>x_>V?RrIRkH~Qs3 z5*7=3zBUf_q_9yXJ-RbI@DdQCeX>9dsM#=keIbuQnnv+OVh>EbsV8K^@Mbm9g*+P~ z1SsRZ=QsNv@U#VkE8cHW2gIJupB&6e0;_V{Ku_4adwi_L!E0KSAc-D)(&_B-6^u|J zFH#y)B&cdkN_RniY4;dn=D$0aDdHwkbu1Xs$p_>~7t(UKAL)_~PPd)9vOvtvSZFvK-2~`bi~<5-gar>!b?thw!j>(8nH=-59_#Mf8SCu> z`*bem$U*1wIjh{F2Zs61)zH0(`rKzbkvm4Yv{y1HvTmPSkF&8tGgY{nUd;xN7V`+| z$AU@1WWarQsyBia6)j015Nau#6#eaI@^Qd8MjTdP^A<7m$SA#jjyi&&Ai~P2^M&jT z36vnoyA%`d{?E8VaJ67k`;!-G?L!H9bYcCwgtaHQLspEVOFb^izkBv6d?I%;2otiC z)f!j$k@1z(jQKHKRsVuSWsWN~JgK6d8gq*&(RF2w)tWeuot=&2CZBH9%ESMZ=ydz$ zP{UADr)Y$SmhTyh#uV@9>1xMWM>%vjPC?)yn9^gc;1HF*x(3Iipcc(XiACuH2d~a? zH`3aSQ`hCl6cu!KgMUEgh{<5+;{bD{qxhTIcn?IT+4d!A`jl%Ktb)nw>)kk~6Bk%R zodO;YcK&x&9s!_whsbUq%-5gy&DbA-N5Wan_?zmtAM6;m}GCjmIS(jx5WJ^Qok{19q)M zgAe$chwrMOl`Xki&IHzfAqDrXmJX_CT=VXk#IUe0YBYVZ3M?khrB&fl(IJD1K4{%t zDeqGpJo%XZP1x;h?;rwE>VVMSxwrSQ%0?S-tLS$9X+~zn9*(>}-^vjFVlu)`m_3D$ zP7&Vdr9TQ{OEUJlmvl|6dy6NcR$eKg`9qP+-B~xeA#D;!>%b26*>RXku5SV=d;m*t zX)}S;;2`~Hx8~I#3(!(LNc$46g_fxOMs8!?Kpsk^&gXDuDN8~*`p++<+CAv^1U6mT zB&LBdB$Hn=1&de_^1(#VeJqDiV)>#(^`ED2UWbq|fXEh^a`2mw&9RKd@HDLwI_*}{ zS&axdc45-b8pkX<0!rpy<}}+;q{n3U~HZQ*;YFVCf5JvvhdvI z+Tz(QMpgp;W~`9@FV`EMtUY4-wrU)d2P z*qa1Y7=U_An`$-lqq>Cb_ou>ytO7Gx0k~bb711#-+StVLKG$?&RUwEKyUV&fPz18m zH2CN(_fp83uQ$(X{@i#8uX#bVvG^8;G(4M_{KMEG%)G&0nxj&p>tZ zB$ya=GN{niW$8i6(rEJ-r1`R4~6H5&j zIi};8X+bS(ro^!Toiu|*g0P-V1VYy8>4T^|X=(C;h16TR;=(W9(YFw;dGbS~T^H5hK@I2ikxN@v8qAYl79K8mhLUc|9%~8PxHLp< z*aJ17EzwBb($rKMtnybM_j4UT0)!(MT`m?GN&jnJzpng|%^RO|8<( zzIQ?iuYbBz_8Xq=d(g2l1y7G5jlui<@f4WIgj9YXmb)wcmCX1~!4a5PbYd@F5qGFT zlRby-)%$GS3#%*@SJmv?a_hrpbS7=2IHu2UKz+x<%h^cM({d*kgiK*c!DyE;$yX(e zxSUO|MRU;@sGc27^iy}lOtwH&^%f<$2fpc)L8@)vgKb>i2D>DYR5lDbFKEVSIt$X@ z@JdaF0W}p;u9_HeYEq|h5#5U^fnSC{WeS&r>;#zyUer+dGc>2tM>V(PgdK|R;j)J{GP8K4E5?dGf*2_w)@RbbI)KR|=+WV9n3CdP^q6Z`iJjAl zpatkC3jAoxb{I`U2MX2SUOW+|AbI1kY$d~pBHourH=G-{2&ZQ3KSZRYOS7ByXhhZ* zG-uq6J31tV1q;ge2TP29T6-^aqN%t$H2&^;St~alo?h`TBjcy}obEHo`CAl9(ZQ`u z%|8+^x)9|%?}v5m^pLB;CbO;zXr1tIr29$pe$}ZYAwT6fv=kwx! zsXagC{NSdE-pRr=)pLq_z2m;~3~j3zE!RkzUL=ytlk((t(6Zc~zAtz=5Jy%l1?OEy z1dQ8@ubGJ&n9Y!*jp|Gj;ZIX+|Ei(=749)Jqc5`S{~+Vmjs*&>o$I1aY6sRm*R?SN zu!gD=B=_)2NHCl<`uX{H_PP? zq)&d1?%kp!YRY3vMV@nKVenCxA8kCW52CnS!_9mkDJ*XH6V;OU3nWd-1tz3vUY zT#^0}2z!>Sz67c56;4QQzyfars)!pdH?@fOlkIZ$BEiIJ$;6KF=i@uUf#TZ*BR+yv zGJDN-e!PXWJ-&Ls)AWSo#*VBIl5uqKO*QG#@G>KJ1wf}#SN02>lcjo9n*SOX#_@A0 zusQ*`{g>W%<0yF8z7$?%L0=;TG8JkGb%57%o2hz2%-6qPFhJHZ za-ZskgnvDFGq#00?}$mI!l^~$w+het(}f*-;<$1;h@lf)ut}_a$=HRfD$Bbu47r+3 z7v>I0Dvijgj;$Nf>&%dnt=2*mlNjBy-62c#nB=Wi%Z1NJrTT21;)4rweF>**V=I$B zYZRw-kONBua{B`l;<8F(D`rf8H*n^w?BOcbrirrVq+)=y7kdWHmW96Cpb`p*GR~N1 z3n~WVX2WN+0(B682Z@j{N;NoGU}}j6=ulWt)0sk+GK_wl|D(qBMi+FL^M(o0FZh1a z0o+s)glF>q)IWW$XCd=<0Ur^w{GMrt{jSO7-54?z&4p5L8EEbxdtv^fDL}i2Sg-Ky zlxe#WAmT}2{p#ME$)*UIX<(Q%s?NX12 zya6T}_=bpch)I~QyYiQR_Fo3EjZ6)yL6SYH#)P?YhT|6(KhCP?RbC1!UYwKv-G=y-R-A!tVw(cV}A;>>o3gurHT(Ps(g6d z`=VXglez})znEdWrcB?oz_Z>6-$Wd1yhH)2g$}K!G%l2Z(^E^4W4ilKVQu##LKhE% z=XGrmn?XUU-c>{0U3K8*D%c zRTbCqdw82j6Hjaf9b}{(Gi)jBsxa+Sv1K`_8h&CgD-4~)jcYNxu*jG3}2kpb!^l71g?0giW6s8Mu{dHFs+&+by*hA9 z0tu8P9NfMT=<+`hMDA^cd{?@{R70)nlUVhA(xB&+~z;J{Bx&Kidlhdn+-2{XaBa2(ADC literal 0 HcmV?d00001 diff --git a/4-ComputerVision/12-Segmentation/images/segm.png b/4-ComputerVision/12-Segmentation/images/segm.png index a190cd330cc92b83c91e08255bb0947f603a37e1..93a00b7818a06848cae2791974d08d358601babe 100644 GIT binary patch literal 66220 zcmcG!19K(J^ERB^@y51op4i-QW82Azoeekk#Zjcsj`XMg{y_anSrH8nL| zQ&TlpU)??ENM$7%w-Vv1rA5cR(i z|C+%38$-IP%7{bM%n+Ua8z4A+*Kvh_KpFgBgB*1%H~%+5Kv_Xu>g((4@7w$5*T>uE z|H;?a$KQ{y&wuK#{~#g0-afxR-`_vq9zWmSUSGc+pQYJ>)RdHDB&4HUqJIt!7-;D} z-XHGo?wJ{x=4WT0AD?=U`a?;o+Cn^(c3Z%=C<%=QCSf;e!19pVo3D#Tsn6#zxA3xtkpq zQ^_DlWo=EZIgfxP7GVhvqvz>aWsrASX{nEwZ+)s)dtThOi*Mh_f=HRYX-j0y_ON?j zde(A_nh<@rtVYCS*-~=WL|r~QGIB{=s7RJ=oR71%tnKl}LJ~WF>OPJY1Oyp`tfZK_ z*ZRe#z2o{A0qiakQZUAeWC85Ktvm!SQ`gI?Lj@$YK21^4cLjcU7^!3U2%FXD9Kdur0S@xkBz`1dX8Uo=&t;YI`yH_-JSTB>zh z!Alt+StCG5Wc>KE*|Ce(o(k7ntpGrok|=)024BeIyqwL%7dMD$jTc?sB;0 zjt@+@3jltB)A5~Cm6rrp)~Bc|+xjs%zIb7gpZ@8&DL(Bi(pMhmho$(n;h!#*z3efd zEHW@eE*JREgx(WzR>nrpih*8s6o>11rVn-aM8{+gX@vLc}*P>I9;Ew$rVH7 ziUuy@1L8|$wGBQ<5OHcjE=Ed0u{@hUw~%7Sd`Xo?wcI9I`$}EgjI#cn%R4lIS!O3B z?Mjh(cGH6Pg$re z>#aVG&9#lW(iXWM_Qu@Hoof1tf?`GJT}xf%sKztuL8A}}^ud{-=o-!Eu39N$`--{VJ1 zoTPfHkcovtTqfvK8_g8XZ21P&t^O*`A<$@NPz~dqtGy?!VTF-sr=G(L|3Y#xznnxU4$ZOl&L!YNTV(aFKp=2dg`{KoZYw?44U zmEFh{ogQk7yjx)wYsy&2S8-f=xoSs(quxb7qn$XqC(U61sz@O`U9)xIRIAw!6#BOp zT~bsourAi;W&iQyntiQ-L627Fbw_My-iaeDBay6)k9UuOrP{=o^(D%3P1L=r-)Cs` zW>Ds$d+sQ4uP6vo&;m41#5GX8Fr0aqJew@i1ai@#(r>ADD1DGZNOUC1a;-cnMRC{N zTWx6Yt$E_FIHOCd7ZhI720C-UxViJSUoI283I7V)mJ_ffad4Lzw@dr!YGN00T$XHW zg8$N9sLn{N=lN{=y_vuY2KgT`U4NbbqhXV7R=7lkz|_FTnAH*6B=~Br!`S{z)K6r7 zrBbD&KyTihP@2oP-q6aA^~V#d{bCvmQ(Tp{fMBz(-owK9@?lC`^N1fvrP8|{TMAvn ze9@bWC%tEwf)QUWTD88y6CMM1-R9L<^7uQadKpvSEKOL9$M0q~mDw|c$m$!aqE3&ZesDPGxM>4<*>=6Qm9oLmA@+xHZTGzzyk+^F#zKI%Wcx6wdsqkWiJsh3GgJ;rp%n^ zG>bj4(>)!EbWt>UZ9*7V_?B)w5x@@QS~X z{jyX-`_Qesj^%s@CT+~^NH-j2$BS28Jq-+^r8;O!f#!=5T#V=Wx3DfJjx|)@JxnU$ zNkGq*9~}rGB76Pu`WhY((AM)gduk)(lGc9hL#$=gnZWGVdVr_iAxHp>boEXD=V>R6 z^sQP+YcYkFXPCnTUs<;HR~86rMM|`(g(st>Y_65ya&jpU>>ATrC05i)FT zO)V>|(4x`09QKD2O~};yLBxME#-LYg(BWt}9&kDD(z@yAaF!=O*s{@619Xe?#SJbe z!=%t=VkTeoKN@0~$o}4-$a96lR|yCttzHAI=v5~rZBHJv{_yGT7B16Hs`^xKNpf04 z#ou@c{}pi50eieNLhx9AIvO0?+;Q^pdivao1>|WQ*CPfhDrNP?0!Bg!+~sEq=duL+ z6Q9+{nP+1=1}XJ@5pM>~VtLl>ZCgGc|L(&O`nLId`?J@jIxA~!Tro`IHET+Hw@e!x zBqSDraejIJqm^dWG9h5Tv-|HytZ<8m>+8Eg^OH4*J@v_tI%Q|;I}gjd#CVeXj%EZP zFb@NmZCd@g|M>czv}jZ#^4G)pHb@SIX0dT~O5F8QXP85Q44-vu#-EUgF%jwqh^=A7diHh``g z$i%6X_-z`B(Br*5X)R=`y055dcoQTAfhv;h4KpBy5 z+q;VyoafgqnCKu<&xDP|TT$4RbWaGR66W*O>N=cR6CCjRx4rwcd02~8Hj$cn)Grz! z-3|ru+d+n?@u~?44ZMXNZrZ&LSGt**xG)=kBoN`C0iJ_6s5lH28Q{n7Ii4%7TfxrK(;5{|Kgha!F$$~H4L_-%a|1OFgJ zNU5La>Th)q370;Ae6inKEIE*D)+K$N$O#Q}ZWXRnj@4%nquN|QAJfq9!_l{xMFS?g z_wzdSHk{b6%gO=XZvB<$pyFlK{;qc)MWif{{n?u`D7E0m1}7&g;alpIUY$Vj8*XDe zxVQjnu5TM|BLEWx`7QZPEk!cCn09(|Q~mn} zts`W)OOr%lC9)6$rOR(fY1>SH6#j?Gk~ZhOvzzmW;Wmx~Uw}1M&zt^glajHFnPVK0 z?v=)-o1VJcB|NYtv`c#;mmchv^M3m*C4OLg>B0KSRQIG18VNf1353=6k)MeM=vIwb zl@vHRE;^7dTB3gYN8qv{-4PceOt-Jk$t}3>#8UB5`W0Gs=#{G?_yOr<=f8A8DrcVF zApmH?(KXj$UFqkKG%26@?|%xL|F|w}Kj3uZ{%RilM$*()q-qO`$1T(!pzpmxURF$R zi#~z%KVWw(z(tuZ!2*tP+{TlHZlf1t(1Y-e8R>9+_PVU~HT zFUQ7<>4{(6ZA#9Ibem@rJU1;ib7mGR`9~dMaqo{K0n-g!$bYY05Lim^#(32w3x$3G z1d+sHzyqc7vTBRE(0D)OECQnh5T0S?|Ie6_fTUCS&(VQ0`SZIPC&&L#n%q|$xqgdr`i6dJq0O)x0@`^lBx9HUzx#@UOiKu;v})%9Qk!N)o5?a z^zJ4q+G?tA2-*?`GGD-hD~XveNrVEnN)JjD;^*}}Wzg~)v!|#K^Ug4Vpyezg&<2^$ z#g@RL?O7Oe9)lr@amABLwzHKCbZI4S5hO5m{)1c@hIYjH1i&|<=m=k4S6b{gF{!l@ z`eTu4y2X7fK~~LWA@F>!Sh)4#^?`oj*O^L8<#NPAn~_;;jb9kApE0b&Ftd9Ke3X&Ll?c2X=ho?A_H+bP?y-OaokvV!IU6s47;Tqi+QE>=-_%l<;MIS zm;yQ{neM{(fq!4EKrfG!2oMUOF2U6AEQQFVB+9CAOez)je|=o2FLG!mbGu$?qLQ&E@gu1^OuZaJIP=x$gY=9TIPf9ma zu8tB__hlG@ZyO}Is*_esUeg0z{**N$QxqxZRFgfeHH+2B%qKWe^3rRAxgTT=B_y3r z@hLfrK%>=6w2D=Gek%O%*j3R=* zf~@wY2r1&unj;pO5Pf0+$?87QfK4C%Z&oP=|LE(}pE{zjSpVUpgZ8Yq2Y$B65l7lf z*+5q()abnB=tY5u8wIDwk{emfVgNHO$B>?{WgAX}o~ghQHd$7gY}UPs?q&UB5J8qb zFfj{O5)ri9f`2enIi`h%*E59?{6R0PCb5@$v?7ekIq7n80S1{R_@!4b|H4LX{JZwc zHbFlo0VNAvM)ZxrwCr#g4FAapfbm1NjMATgRM zt9H{o?=|+z^{|@vscISBsqKlR=+@!B4F??s3J&Bm_gh__k7yBzR1W)NN^X!-W@SL&s300$zAS@#>R$RfauHaN4z+0X-r%xKX?p$OpVwZ?xXS21+F&S|PHqo}u zztEpym(=t+~FDZPIMi0wQZm#n-0LCy7#lyMuH zG^``c4nEd*(it3z|XpRLpWBQ&y$DFA<5c?lA8i6j{ZM~TT02U;?J zMNm@O+Am^hbEvc1z)|INDVXCKh#v#e0Ay%MR9DpChN+6F;DndUCh|PHkhqcFD3*HZ z>53bSkP;mCX#-W*dG0fZf%AR_Cmm?U)}#^njVYRSCsFjzUO+RpVxT}GZ8-v%q5ioB zq>Y{xX`sa}lcfp<@eoB!%+R?9GBmbhCaB%iS1M9dPBkse6txJMV4YGtamAh9Szo?j zg(fUWUf`Et9mLBKjP4-vN=9J;SS`oK-~Y&VnLmwBpVD0@kdyrR5O}5zYMBX}TQ$ku z0Y9%x6kRk4@o#RcSsRk2cddQ+XXWkXuM9d5#ty3Z+`Kz}{q?hU5z{BO6(AxB_zT)- zGU;8ciRCGCW-k0)n2rIAwKAdyTYKFFdtR^dh~|%XGCfc8smF-DM&L{c0s5yrPcjVz z-_idDX;@dXZLK0QXpEq|clQfZEu7>jDf+$tmo;FsvdS*gy6k~|{QEtpr=tAm^@_WG z1m^Nc09o`<CrY4w zJoU5sWfyooxqxA9t(odc%8;mFXHTXfX$eEpDX-ciz$ekDteD5V7r;@dBXc4)*uNxL z^gCZ@O&6X2j^KwnCMywd#gIrjDRY`O-6fG79HVLk^sO~ID#f??{}>ldhQeDni;6^2 z5y4Ht2#;(A+iTwr;bhRl=6$ZMhad!xrQBMYTyTc*6FhCu4~5X{zFkKcF<%+YsFllP zTfo;U)Yy?YptQy!qB|2w!9M?ut~;7DEzPlVZHiep@v#zLLAE=~CF%2oT3&*lpYyF- zl>S~3Cm_=e;ps4T)fo`*-dbHP^6~V02gZ|a-C?&pcCZ8RxIN-K2B*JnG?KX{@^*AS zq)ROZ-1zzYL|i6^4#bG;f!=E4MyGo|nhvP9e1^M}-KFd0x9t%U^&3wrwTmx1kA=I* z3$Fj551K<K0qHzjuY{!;0~PeXqUwHlvDwU^yZ{jRP9OUHGmZ;#a> zhdG@RJTHhAv*72J(7a3E%{?-XQ)#g7)*>ncGOf~&FuEq3!30y88Jj&OTauY78iJT) zR$|@d8maDsyqaFlUdHSMLs`@%i4mbx+*GiXbey4_(U=ga5)(Pmg0ynAT`im=lNN4r z*$bEdmK6bO4q*$Iu|yQEFgygg>*O|YHoU1z4jt7~6!S*4_PHS&)iajPC5AAjx< z2VuKJASJ11nRDR{cy+jD2RRnT@|bdKSy@>j4rMR=AlJhd3pc3B%IbtM!yQ7$PGmoH zh_o={l6>6CaViH zL!+MWsa=%Hd*Ox%gb6QY6-q)+8Qbjc``g^xXbGSA#bEK>e7b(^YMh_sX$;dURxmZi zNh>lYmCo^cmbweugak_kKmtbuxx056Z@}3Tzy%eu;N=kO`tv~I0>_=M&%J42Kf!TO z+-c_JZ*Dy{oKeCL8sEbr>0(6YATMC$1Gs~`Y5n+uLaJ$9K$+vgaY?JBbp-#ua$AUK z{kM$B*AKKx_4=L;{Ta*2#!e|f(pY>Ha5x$hd!ZlZHZLaKQ*Q(}LzmTRGNt&iY1PjD z<8pbqdG_Mb&ZAv*Zp}*?M?Sh;K(;!F}jlVvJ7;%T{`o!Vhhq?-_58?~{lBWNrC!fHS3-(t)HHZLwlXbG{okD0`KbfbBHA zfQ!^TELP{NHm&hFl=%`3CDb5TLr3&Xt8q)lf=K`(>_%xRV1^=FWE)?cU)q!(s z(Ui8&{F<;TkiZ2r8j+6&T%(Ucqp!~#%|S6Myn$ECTARJ0X4>k@Q~x&`2emp&5x<}P zD@l5;w&$d`Vx!qyk5Gc#_{aU}4~NmXwMI~OK>+FlzBbL#MhE3zvqVjgEP{p_9#C6m zvD=x|jviUnGwey(l^$ct)E&c{zc$jY*RLs{_VS zYl=!C((h5M-tO`}bfE5m8U^5J&iKl@WrgH+T`4j%Upu*$j^@MAWV;GFE$lSfK7s@2 zp!ke7+RDi0hVw&&;&02%dPw~5UDQ+XkdF1RN~1wd z)IYjYYhpyNV<3+;o2nEr2IU<0P-bxIKIc-tP{A?ZrVpO*nj^BM3#>})4^H9YCwzM1dn3et}r$prTLd=`1!;QLk{dwET z&lD`AMm{rcniqX^Af0&78A>zh;uD8v)n;@BHg)x7+Bz6sG(TfaD_pvzv2bkyN~A9k zH0Jfx;JOzHe!u9Wo$a~gFge!LUbCbDVT%zF^z-Lo_GSMv`Nr4os=n$NfpAtY)Q5Bx z+IhqB{KY^fJ2?6|x*)p97dg1_z(&1`{pRGvpay-G z0{#94;Wj>2ZP&{2yf2gM&8&6l20CE^KDlAd$>Bi`{~-k4Utznu=15s~Xo$LXa`Iui zVi-c0mlq9y`wx-+T-Ocr3Pr^hhI^xL(?eq}RV8OW?<>b1txFWlgr2sFQ)mAH#SE7D zKB?*($YQyWYe)#Kp#}Rhv>&jgI+`t!A61>z`L``d7 z7`ryUeCU6UZhoJsZEzD1Sbm9kf8X+p3+(an^q3laKel?$8X}PM@Hs8+hlwkwd($Eg zwBaVG(Y3rmL!NM}WA~kJ+#H|xvYOK)tTqtp?(&^?%yw`Za;-hrY3%QRv0grXhAq16 zZxSKNF%<5;@MDH=cH=AC{S`d?SX|90NQKbs3V5dC`P68SBeqZ*2L$8UO@%-yoeDoZA*D$dU7Cd`5X0?Cx{6y)bjjL;f; zjiE|O#=^7lxUNnBSB=yWw{z%sS>h*&RO=8`PryWHO(OhyoaKzf50nDGigY}Zz12S5;=}TW zK|%QiimXLVZ>CWvWZ7?4%IwIR1B$lx^&;5SWqd)|TzF|mD{e8`8e=mp#YgWZbJVM zh5LXWuT!6Cd~v!-9i#0qkL(x}P1dybi`(n+=Ked+2!PV)(TN)ns77L!rqdR0b7xpM zz4hE_b*%r_>+7$V=X3Y9i{%aw`r^a+7~?%HXAR6Z^Z(TXxX)(w=nA;tNQ7G}TOQnQ zdkw0wzC4>>?roEJ)QE4~(=ENdcyf%?ixqYLfkZyTxJ5 zJ3)e^r%v?LkBsa&r2@DkE1x%=@g^d#;?QOsTG8LFk7*1n_@Q1hB~C7#!P!CW?Q&%* z0s+b-;s|6o`29lHED@Pnpt`GIKAQ~i|DG~)ygxQC812{qKQR{;V1-``8H3|M?YY>X z8~g65-PxZ>XA@41N2OcPS12hr6}#qAe;aiWiqI!C3|72I3ULk+*O2Z~ zUdnXi6b+@l_g2BzvtZvW)$Ay}mqeT-q|J~?*}w6`Je&VJ#;uOM@@rEOXC=W)A;=Z; zvUsJRC}ZUzk}C<5N~kMvt2gDLnw%mZ({J&6xy9qN2mfHJkdXJgll^hNh<6(|K{p9< zw!`n7rS2Lt;!C6zkD89F)0vaUnMn7Jt`I6xEn&eh1p&P2w$ia}tp4+=mG146J*@sY z+}3?B=4&V3pEm}kv77|Tan}_SQ;jf|&<{D~&G(Is)58?%%E02UI1pE}+iDqw@T!X- z=h)p&{i!eymUXLupJ3>Jxlf%RqZbSb$foJNooVNV3((G*JFF?dsIFI^XdoRb8P z5fTW`*T2g0v3^g&Cq<7Gc8V%^g>D9OmbW+6sMp!JgS<1D@spuT5ZgQ10FlM&p`{4b~ zhlBi4znts4};t)$xSF1uBT{6U`*ed-KlM(~CJ9rmgT6LZ=t>u^lc)Q(!wI zG_v@@cpp%X8i-GZ4iQZG8DPhhiw!V6fgA@j4;0(nFF(!0s&_`=o=Qte*N_?&oy?bA zTP?r0J-!_8_-9P{>%2aswXE!Dcl^nu7(@{Nb6K*u+zJeyMK#{pCQzyhc$tOUp#pgjD98lcj_JWJ?25}en$6*GwOBf+P1b@cI~K@mPzF~>B`*h z^|s1H!XB$@Gkc%i@%6gjC_|ks`K8m#FDN+FTd$CtdrR2++sBe_=WYGq3Kkf;v5S^m zZMz>leI+z|GRdF^c+34wi&qM?iUTbu$N6N z1P-&4Ef1gUEY+dK?moV|uC8){Y^bwA2d^@0Nuc^zXHZ_z)eA_xy;2z%#T5rQ*As6i zH!IQ*g|AK~H39 zM>k=B_(tSlrE8=%vbb_l7tP6+bwSP6b+g*hro^dD4AtSCdk6*QXPw1(*;Ij)L&b*K z7=9BxJd%rp>*NO2rBH>)?>HcD%iPQZhN_R3*XbuodieV7c~i6J=H;Bnw(6GGx#Z_R zWzomNj8s%ID@>chCoyH`Irf~6N70c~sm}-7!Pi*8>UZSPowt=E7Ng3M)_oU&9iID@ zncuIZ^)0N6&ee-EuoHGxmt%s$Kt8=emD%=CKrpS65XGtLC%`Pf%fofux2BHH$TAGYn z(gU3k0Ds&s0n8p%p$o00)+Q_H85e;a%YQPY}*} zyl=?MPs*>Rrq#YsEqhpHydU%iyxn8=eqd-!yU?J9>*abbwC|ss%s4%su2)r<8E(Aw z+D_kf$nVgDc@Ikudv`X4gpV^}vaZej<_^DRrT&ELsvIDJ-x>U|KbchDM`U-y^@bK_S!i z5!2j`AWqp&z_OoCq>y#;{qryUsbJd^GYDXRszkS^c;q05;vl`A3i(kD`DK4(PGqurf3pmE|t^S>#D zA6j`=wX^r<&0EdQThaQTLn;sM$ENnx*#W&G!AYeIG8!qldh|_1^R^C&!`}#obkMr| ztvo))Aws1d16&1i89>xXO7iyTUXKLG!h?YlFqf{`m>tUwjs^w>I@;&UJvis#)0Z)8 z(;s1l^y}E_r}m!<3iYHZ`Q2u$z!?T4Aa1CIN3}ickxPgfZYVX&ih&Vb{M}Pv1D^$D zfqC+YaiF4~F_+_waM$Orrk|N1rzWwYn*B|dlZjS!<_`-_Yjx;vP~cVR666(IV0zUV ztu|EHi21Z}D(sdlso+kQ*}XIauI-vl+C|3VXQ$_2Bn6$|6=E06@mxy&=L4zf+$v%vx5kO8oWQWTH6t^dDx^JmtlDgF8$!^M4#Q zJk~3s?O;poDtm)j=0ndEK5e>MLcD8cGu^}Cj`YM#^5|MCVJ-K^`_WmhKXB87?!{rr zn%@XRk>j{T`Im;IT_uE!BL(=0@^a&3#`FloFH)Wdg%d}52MHjCh+S;0%K578{=nTt zL*ulf9S{slgkW&#bMc7nZp1^{KL+=~ok8P(|IF5nMEx??9$fY(dg;HRxtT+|%i66j z^+qWU(Inq3N7!pF81-^Td+6_ronMHp<)p}Q>>9j%Swo%2 z8zM-Sk$21q?aiN;z-iVruT`o+A-oQe*A1~?fh!-U10Ej@L|?*(LEs`e=_d%{n+WY! zQ-=oDT0Sw34)ddUO31OCV&BUv*}(nfV?E;eDlLH(-_%-basVWVHz)c4`$+p~6%$OT zOG6M(X1^F%+kEcUbyXM24Fakje_k36y13gdJ5eDP>Bas)fB`KNXz8s0LovRwS%cTW0WaK?7`M?3ZzkB#*do>ZiZ&pGu_Pk*2kzV-e5C$zH}TJvh32wNsN){d{j?8QeNN?QX$67WC&}^Eg?D!7YT+A8qji&Yd+w zLG|{QXW#wM<5A7RvHb>|PxT^o@8r=^S1&j_tPV?*3=KrxC6Pc*!rhT{qJ5U>d4Nlp zZeFI4{Djs)KCs>`QQM}A8p(za`m3-h^dQN073a5ye41g+7E!38@@@?z3ODufCn08tNjk5pEr5C*LH)57pg3+F^dGJehlL-6JYb=43$> z3zs`#&b6*~qA$W0gz!Dr1X+HC8bLBCQ(3onf%K^;ay1@t^5DB1(IhQJKOwhZs^eR2WhyjQ0cFB&_YzBj)&*BoAs61hkoIQmEZw@}x ziQT1w;r5p9H9<5r1YKeiNh>**QG9EMNWGVdDUs;u~u&f1j?(*hSUvQJrA9xc#z?qNAt;3g$Cj zNUN5cUo99#M35+QQgu)9SS)iTwyY5ccv5T+_@oj)1Z-I0Emb}wX-YKdSD*+(+|Y@h z&5qv5z89i$Y1~STrLfR7BMh)TIJc%gaH$1*aWJ2{5Tgh-1u+B{A2BeG_mbITv6d>0 zCEtnrIvJ40wk`BzJgr`TxDl!A+T1wLH}j05>Gv9oJ{e~nk^Y3Mucxxb zJfw_TwZeSQEcu+7jhREt$LbQ*DP$Pw)khJ8#<3~8yytZO2Jn@0zu0@WKg27+N{FF> z<45jBV5*+Km}r2Gwi>l%>AO26#EPMK=8u$*Ww$3UOV;z;Eq|TtluVDr65le(BVT`K z9HhJlcZtaGegZW{R{*Kp95Focq36^$$*;iH;9h!`Xv=kq(FNcy*=XQnItzx>6s)99 zOH2Iq@bpzNU(-_&pM?#*3UOuICq7{HNi5?#jeTS4SO2sEyl}cuh~6TGH&GKr-+Z)Q zI%#-2MeZy|n^Et;cLBR8rfj*$80^q22sk16jEZ?sS17SK8r}`B%X~Yrv56yj_cU8; zPW_UK;I24(Et+g@C~rHqnuN7|I@~OL2J}akJ$kRGen6%Ni}6L+Tm+#*pSn%;PB_9Euz1E{nOa^qlr+Rq_cWOwj$3IT$fmbQ zh_6D77@z#HA!qWVoFOw_|9;~&=VZEAV4_gp#kL#tDtVjWo%64r;8D0a7N~-?ako^T z6E>o>{}%$|I|;pw_^-fciv_l1{8Dq=us;9EnS<`NtM{+3pfXqLHI(rloA-*Tp&V6= z$p)aTj8?~UZg7s9?A;#aFv^9rcN%>uy-F42eoI%@G15ItDW_?)mV2ZK4l@E3WlG^6 zY~=436J!}2)LT?$|G81gXOVhBJYDx1pUBRnc`zhRWH zT03`64M`y)0}wt$+x~HQ&lD^eLt8BqVrYk=4Auh9gktj(ymTN+G@olCmMQ6oXcUWZa z3+dYP^W~3^KjX_qy?@b~l^{P7OL&pjoj5jEBYbtunl`Xy#B=}TGS-k8Wd92(w{vTT zS-oVY?o9ApRQmd7RNdxz)$sH*7P%cX&`Ksce}s2Wgw$|Iu;tKt*u`D{~68cKaf=a`H=Tf>M=jVl$Ak)FIitL zU5jN?Mfa8CjPZ)6F6c~(sEJq4wH4U_Z^>8m?rOGBK#fwK9AS$pfDX+)76zRcI#g{f zMWnAB1P0cJEOq*ww+3X`(|yB?|3hPb&8t`1Kh(jbtn>P1&yy^K3%ovPGkBV~gxI@n z_EHYJxLv1(IPq99Z*%;;fw6qFQHu)>w0+&Oy7N;)=r&g#eN^8~uUmHL+4R6toOk2z zUU!h%KZM0pa=9AVJRAPdfTcYmBw`Oyuy7H5=)T4>!D>W`U}Z zw=!=k!CKPMtSqynqOjIgK!sj-Xda=UPqC!JHG#)ZEr3e|rzqI2sdD(7&7?Nb6&DBF z)4TI9x|)q+v5+clLDMobs+mIp$K6uC?~nh6?OqLWGT>>;`9?w$6~2U&nzBsT_~&kZ zVYm1#)LKvoVWMz*%@kTf?$wE?~;BKri#qqlwkIzvwYOwc=Yq1t7$02 zByahl51a7wP^)}c(t6`*lyi)L%vk|iJX_^?OiSI`YjPU~Q_G4KULh8gu=93P-y`XJ zKmjqXYySFHmqx(-Puv2&a$>D7s9y)1a%`d(%ocRnTH*)L8lF>)nkcg@x@Lljj1&W zgY3&1sc9@)oqP+^Faqe|GuA5d)3nh?!O-qZuR0a31iH3NMflV(6-=rg=$N_-7R6yo z>s_Z^ttTvcmarmk9@##ih2hT_+TC*CKUDhibgUM#MVO) zn`i=0SVav^nPLSj!DC5O?_OVDY<3DKmf}Sd+)5(Vg_{Cbw_(vAb+s{}oMHpFdq<66 zD!aQ0Q4JlH$|E5-Ti&UP90ig|+BlW>+ z(_Uf~AMIw}ibLec3!O#YNUFd-61kq<(5YB6@3%20>V?iXec(Rb4l_&FS57`k&qLzT zeQqr|+jcBI>m#E9${;`*7FGRym2nJ8aB-BXcH_!Grl$LBU&>#@&5Va``wHgV+3rAq z^VjCWpv9Xv15WR+W+sph0l3^d+4_8^U)N=g12ivIXE~{T&jhLnE91XEa+Z$ z=6DV;v1e?=P>fY@`|%q6Ae=7$9#I)1`{9#Q0m&ylI&|~8i$_8w60l=6)fNFPZgwU@ z5>44bq4{#6ozC4H43qC?tLzW-q9sun>Hl}m&E~XRud0I$m%cKc#%SW9RqqtA>oL@x z3^%p?mM5SFub`MPskCQnCA0h1qdPSGV#^T2wQeu)GZSYtL4^c*R2Vb*St1WvW-LIC z@?%IetZIC>SoI|2dgr6#Uzj*{BRl@A6T-FJcEZuxW7*A12&QJmsY~@cpz?xW!TR{_ zx3~|q9_P%R@RMh1dwXcxMtlxhyjC*XTPMXEp2>@>3^FlQFZ-(|L9VW<%EaojK)sPg!?q-qF^=!)|RFsFQ&vx-!G zl8yx^;GaVUMkQAo<7$>>;WN`KGxajES8s5j<`k-*@s8NoG}Ir=U$$(1Qf(4PyJGT@rn z`-;`!#H&U~As;1(jEas{wN9ltuc1vzXBH*y8L7?T`~dXqZT}TAeS1%=ACAwyWx|Qs zhykaiYV*%kOh%{CTo=%paMd3D1_ z1vb;xOTqx==P7cXNE0|>P<n@37oZ2QK3*oSsOU)J(ZY2HD5uE$E_E#h4(-n7j1) z{N$ffS~K9Mj7P941bkxFAMGi<{0ooU$K)`Wl08NQfcGX!hLn&pZN4kSR@7b_v$}9vvmr z-XIdGXr@sa(ORI#`(dElq`K+Xc^QSb@{2QFCS`Ye9Bod{S zU$=)QAjKe^wD(W_7|~Wzo^3=x;#M~iP?IesyX_*cjg2{{)y%!iOcMNq zGJ55R0~Q5d3MHyX9U#Ts^Ub5FrS7TZ@g~Sbaj7?Vr$Ez5`XOeFKwO27tjX2eJwT)* z&)`{wGG|&i4__!LtLiLqe^i}RFCEkN>oShmG|;=m|NjAzKyJT6=L{1NO)Mn%vUIcz!-U?g7C^}oT=W9^Mka(G*~bqxx{IxE2p44WZz zF~O2{AW=5+M&DqoRj}1GEg5>bB4>&~G}W-%_9b}rl5=a} z8mY6(4so{CqN!@CT|IIlPJ@;J0 zIa5(&(Ew&@6Z8+N(8JTYG116hfMEatAOJ~3K~#M?;y8Bja_Y}vP36|m7gF~Ux>Lb( zCkLz%-y_QCr9||^o~`ZIZwzY#fdDX!rWg<h=Td9HI$D zlK~Ga*LmgR`?nNcW<i(p-_3|VLPHprJ%j>|o|Tf4kA?|mUYkRhPI6oltVyQFe+p|OHwtoAb9<5Jwk;;& z!NiVI!p5aO7_2hh)W?oDu*Lr-A>Ob3`hUY3LDR&UE}Ir>HrjrxodA%6Fmu~<90$W` zJLBp!YWsfrgR|p7xm;3@Pl<(<6o{tYe>_nHh!~XmjN(d)T#{iUQ<-htp#E8r=D8KR z9GgT1^)`WJZUmuUoj?@7`vV)9fuZIP_|#5Z8j(m zAOyXh5thySi^XMsaXFiV^oGL`VH-{YA!!TdZMtp;+dX{FGKVrWHa zpHh6|W@%$+3HFm6qNY1T(8j80#rvb_=>KbB#%e&1TMWp@C z=h-#vzvpveYB2kr>o=id`9@cOreV?)oQWQXsiMOORz_QT z9^}R_WXytS3XTf!io(s6r;~c5Cly7ZB>CP}|Dlj=$Sa>r+kRx~CNnlJ-|E!$9{_C`^m_dWKOJVM6 zj*T>fg9k*lKSG-9h~G)pdVvfhKQuYZbyHOeIq??O(6D>)?%x-T zVjK&$ket)U$Sn!@<2HZYnL<+gP{=^0D5`_MlY zZ1?nnSDydjF$NvKL|8jIpd*IW^S&IE2X{4aw#$OJb=K=ou*W^?%x7nE+SENJ*o2;g z3T0prOUjHWe7b9(&Tx5ArHAKVCuNAH>UAx{XenZAR#88Vy(mG~wFvYn{|?ql1ZySv zP+`w#H!UkQn!Gg#t=!33NW4tM5q)UKmg&1S^JZ*XODEjt*7oan*i0a5>ekLk>Y^xY zVKqxwsTbGi&C7BpV_7s6<`{uaA_VgzGjGI#O=Rib8APbXlpmQ~*p$-wxo z$O7G6;gNCr=FNp7-oF1xkK><%QB!sUF7<$TRx&i2vgvwBFZVPA2NtDA64vloVNg41 zc-{y&8jKr#?bSBQGDhvTnrLKuvG!rNV5u=?`Lo)&A zm;hQ&qCzyq-oE}OL_9|)>sD|8H0Ke~tY9o4h zQLuKbD&^!8K^DZIoyDS$`FVYbYMss3e6v|o?0G-GlahA>dCG~LG?-!Jz16BtpU;^( zI+o8^wyj5;AIVc7^w@9~x^aQKTG-7;)?VQs32Bx@!} zq*=A5l#3KP6qQ2Lu$h_YX*09T6i=SBtPqIqci4XY5?DiC7zXilCKo=YOwpQ?RVzoE zTHc~RWsgVk+p_(!p9z&)?UkPuhV<$-YAHdbgZ|qRuOqQ`&PrU4mVzv2Xr%P7nno{S za?;fMbB3u@7Zif78f{f%o*NUawTx-vcujSuw2;&PW4Sv~O@D@JAHH-SURB**>$!yL z_lGsyrus&DtDT+o`_c&)pTKc#{q^ggo6X(qdOo^d-<|ar9!w+iQDk!DEHP=y7+TNO zzUr~G|JSq=DYz{(Y{E9iiAIl%P7j-?GfX=Pf0*=&dUnfIUXmq)+w<-E)1pV8r*^ts zc1k2qn2*=^O3YOe+TX75D;E1Ew*C4wuy&}F83B@3IelCgr>7Je9y2R^wu&=4dHy8} z2mRw;O6XOr(|2!fSy_{!sk+8sxk}JSv`_aZSog zm^Q`9;$MraDX$g0(qkowfJbdo2n=PaDPJoWADs;tms+ zmSI?iB@e?4W87w~&lra3dp!0{cYT81(|NAVeLnu9+4M@u=a{Z-9~?K1kF)Pa<9LrL zN-3)Sa12W{9eUyFZ}N4lG8QN6Hw+xjmc{JM)(b~8nG{7<58y~ggE(to7pz~c@7ccLW_oMCTPpN z8tn7hS8eQuzFwZ(-j zuTNBVs|0IeY&GxBOh#twxrpug_>b6{ip@{mK58^Rt`8c)DyaPkhVtX-c%L>`epH3~U5E1%8P<@Y+Z2LQ#JTvo1~s`AI&O86uNN1c@KL~;6r-Z$g>54Ql^VEb zhgVmq>bR1EdQ?n`3iJv%^m@)NjcD$kVCdpSWID?0OrPM zZikNK;nniymSWKTqnp>(`T4u{)iQKZ&oQc%825&d5>DMg@KYUZKF@UpYsbfevi)(s z2QjtL%t0c-iOdQ;*gpDi=`LtcX0&Q+rBaVV9X%7wBW`zcJbyDkX%Zb=tt~{{soZ(6aOLkG%XFu*M*{fvOCOS`>{H6nnooFCN&Cr)6@#o_=6rz*V4WTymNA;%KcN zxd{)dwGtX{MAN97F#?`kUQ@h1NZ!(vbIVdw_0mW7QV{;3cU z?UcKj(s)X)B+~f;6+3D!C*9xa>B)Mxw~eK>5E-mt=i06KA<7W5L5Ji)Jq;tD;4y-vf*GcY$k#Y&LQj4y zo2ESWlW+$;HjN;ual~xoIdvV@QV_Nk-}9UhIcBLl3sw;FQd(-}wsM425Wy1)Q^dji z`uP)8P=W>tg-LQn)Gt#KU`78of|g)Es+>vYl?uBt(JQU?{^yk-=_F<6v^6-cz|L8G)=|2?psT= zRI#HXAs=&mw*uc?6is;xI89aiLhuc_HFT@8;bv5uE$*S(8r1&0@E89)hTNKTY0BHZ z(*w-4rf1;#aywv)p08lmnAv#{SF zBD2=dMi;}fwD984oCT85!D|%CmTcRSIr)um-~*Nt8sfi+?fS`b@{{8iZzQ%wb^LsptjQ)x;=etH5w;ES9s<$#UZ(xRS%dQk7Ax$*tZ3R zqqv$oky{F4Lh+AULJbu~s&3PXh)~cV7n|AI1MLN)*4It2hWfSEBY-vNY@lL|LeRsj zHf-}wPtT^O*e`$r?$z?9Od)7_zf7=ZT)#Uzr}akb)vjz8IO=pD< za4E#&@R;6}E(J_@i8Z0;+OLKII^CQ_)*dfg++Rs|TGVCRN3th@^X=o}kuAPJgg47< z2-&aY3}iko%aHX^J{{Bv9#_bR5*|kl+y`MTopmn#QAt#4leAMUBd4}njVHtLWH1ZZ zxYnyA^s&$RwI`EXbk<^XTKcE}BT~?|YXh=u2X*50k^S9zrL18&2o2Iyv zxIJkSUcnG&5M;G&*);WWCx?7ZLDuTV5UU;|Qmqbxi3viX@?Up4@Vj-*&8XIl?xUK7 zHTe=f3Rv5EsZqd4A?URI`tWu8in!YQv%}L<*n|?&eFm)Ur~B#6=kxmc**n7*!tsq= zxs}-z9Hq3sN(jFqSlc;noY*!vw9euPVghKIvV5X;j@)UW1!UKV#N8_LN&%|rx`M6K z9gPc7cuRawq*mmtqX6VVaT`2gvXCGcSY@8+vhXbZ)~#15WPO;esSe#7SI0bwXn=%c zE-tY~_j^o@JtoR-IUdlMKr`}l<=Yd2wV+oL-CB!P+(5)b8rzPH1!JgR#k^AOvDPeR zrRwf)z?vfDZW#j5d|sDIgZ%c|t>}6_O9)GwZ_zS|nPq8Z%&JR@W~$b%O#PM(`eB8? z=5IaDG-(eigd}2!dAik6SC#~{JQfU$8*G4D%`oh;lWw2tnVSmKeCL;57bD%JwDv-N6NHAz_ zp!kjU{+0EtXkgIG14$^|mCEmJ1Vw5h>*ch&%8~5A&yRw2dX1eRosD#M z+vFYS_WDx{yX#H30D`jKnobqv3yrN}ZU>yaowFklJ_Q_DUpR){nU@(bk1baPa|`GM zHg8x5|NC=7KEvD+EDCpyn;lKoQPP+SB@eGC(U zK2cDkaP9o3EBXc$kMp?OS#q%U@#gmSHf%3Fv1F5|(X8JAHIOTqUmbn}Qwkk!I4fy% z=c#AWPoaMbue4T#&Wx%CPkjk%(!un13`GPcdK7ne?`pZwYw2hw?J`gWEw9oiVd(C` zRSrR-!zcSqSi>D0w_Q1kT4^zcqI6i~vshKN;%zxnlVrXqW2HaA+TW*VfD*6D!j*KB zGVji4XO7ZAwn-+H&wQuXRm)z~jg!&$_k?*2-!so5V3X{+abnrad79b6;-qiE0&jt%}yRk0V;EX_SFozB@l>SUV+H z;~Ag?YybS|_T!RKZTaz!o12@oHCB#0!<-Z~Xl+2P0Bb|P>w?08g%!RA6Et=%op6Kl z1lKuXkv8gu%l*FQn!X>l{%pT^w6++`ToH_CWq$#CM>i^xX;tFS(#V%t zRL=V22Wo33=;Sq1vc;hEY-tEvtL6&8o>mIe*1!}&my7H9fviZrgi)x=Kpnv2iq@?~ zfQ09TuslzkJ%4p#P+ZoI*^Ow~FJaOK*`hTK!xwa39BwISa*B{67&pf-#_uIAiavY) zhXb`WF*!KBAl5Yn8y-gmYbYH(WKHc<8VcR^V(BUMKVzg+^1%5O!eI@(_CQV^fPCL!+y%bLp zta&UE(KN{<9MS1fg2=FmZgp!dWIkW`JjMdrxuQ+?9cEjzs}Xlv*>?0FsIA$iX`uxn zVM}R9&Co3iv$3t9o2&_$i!uHDY>RMymZq-Kg$mYTS4lU_h3fP+e~Ehev>p$v=@?Ci zi}y1m zDof{oP)79YuV}S;)+lY{uA8H7C$h8|FX`6*HVEtbGxtzoE&A|vto9k!qUdqJ8c498 zV0p_!j?d8qr3{opx2t!TaTl<*ta8w>*`U=-eM%@3eBEp=f_oQ1-Oy|cIuE*M0v1h~ zQlQR>D`*nV>0?w}=cLHUMWlD{r7$BKzv^kWA=o6`pY``Mjdj8O2HZhahf-%PFGLP$ zRz+11nl?6|1u?9#2PM39;iUlUDtP?WbX_}%>KkN{;MU>%*bzkXfGwY^92=Yd0;p)2T zQGyaIBK7U(*EP!&lDlP6!Xa09zg)jRRyHSx)zz!eb!H^ZRMLZopeB_*It8^OZGY~}MIA@x*k zlZl#AHX0N$?dIWD$YFm&k4&;M&HTK#M6LA+41SQ?DiKJfg=RszT~Y10y{N$>3X=tOE$wt=oPzhKZ@ zf#K0yb8~@00`0?Gc}ln&FLZ7&5MfcMug zU%otoj9xk0#;h!pCgcTj*htDoA(Z_8VC_#*(1Yv4wtPgec6$2e>Jq5-=JcFxJI>$y z_V2eVz}f}HY80$prOaFIG*-GMtx%rZ!P*Gzq+r{~@7e`$9!EB@ zhqXHVMJE3TJ3rYv$+(P5b@obC- zrNd-vb!q`d`wyIFN#9YLE9IqGasOuHg3D3pFVUkAB463 z@WaEfHh3(sMp@%0bP6!m_#87p-(Wz?)!TUy=g2=la$zkhVQI^-Mxi^wnywS9>H2+G zvowiX|CvMA6eW=stE9NjiRQF~Jsa0xmu<{TzAw14gbiIUMR=C;;`;TmHle?WtF(?; zEJM2E#1f*Zoj^T^nlUaf4C1Q{5GcA|?uK6h)|8;s!gD-N3CD4ickDrJYFjGcMG?L4 zv%Zf1;rFUX==oFza+}~D*bce5-pt+C@AVNX0ioPSkb5uRs+1!unkT0p^2xvVq246F zL3i(!xO*q%og95Hbo-0%B3epyI{oyq8v7+tm0;D}sInl<#Aq{IyDXsE{Wq;15o)p? z#v^&Bv)Ws}>|0B9T%86)Q(VubloS+MC7oe=Blhwuip*TW&HIYPE;*Hy;7yJBg}~v) z5n!ZirlJ#ZeL?%UJ5PVMA(|>1OSvNxpj|2m)*Qn)0}~gpMyI3G{vUg1+myDp#qn+u zHZw8VoJ0r^NK{e|*LZ25r71ZwD0A$LQ#tC$vG44R?by@r{|WB;uMLQO(BA2J$vfGQ(RFej5)Nse<0*{RRb8NwQr>Z>CDg3V!s zGI_CxD?GPrX?+3<3)=?$S~YImRi*|E4?t9nR@UcYL(F~Iai`1TUSQ3#$}e87t^Mb8 zFkb9_vyKR`mFeAU_-lu@Vq?mm>$k=AiG1*W#H$(bATB8?&6>U+mp5f)!qvs57&gTd z)_#0C@Oje@w19@9PxwfY+-!%+M5Uyz%1}Sq3{rFq%XFOWgY$#0*7-I)Tdnua8V0DO z`1U%KwM1q8fqllBuys3g0S>4%$|#XFj6psQZL&u?`yzNc{iNsh%(G4(G4q?p~0$4L_N!FTKYSh~hP$I0A zqVzr)rSD-a-?`sd`|a^y4NmCqJh+|59-km>aB_HDz53L-zP`En#KzjqX!bK$6TXic zLX;rB^o21DlRgjm9J4qSdZbF}vZ>m< z+EE&7*al%=VzxC~QzmCxN5L{&$0>vI`PSx#EnXkCPER-Y6m5$HHJAOJ~3K~#O+^+xhxYb_Y=wz{0y=#HYE;NzWTl|+9S&ves7BMj9O z*6zU?O8?V|w#+673hAHFO?%fU21vle+u~sUe6sSN3y?yZN!+BXD&gmHaG@rn*Rvj;{ zDVAsBt$4x1TjlbUEfmq3TCxtd{x}zgSoHNy@(}`S^lK@~ehg*f4)loxTmGstt53*$ zheWUDoQ}JKahQfpSlb~wZta~f*Z%40o*Lw7V@RvF`ZJ8ZdQVL2JL?zeawG8~Gl=t} z^@r1H=3XopvA{))W)&M;03N4uW!8$gZZjCq@UprbU_>W%GmB>EfRVk?>`v}w^z{pl(%CYJIuFC%=7}l+vRp!owTWgO zk_@!9`)t0^i&JCwLP^C+-U5;~N#D@L>>D=Myb0xBRNM4DTUIY@K@j(-+9nQ;kUT2^ zYm%)s9b5ZFtj&L5texG))*chqUh9Awfeiw=^zk_N(#z|~&DGTySR2Qqtd9P4!dmGY ztXa}_Y~&nGhtoi0CVe;{Phnb}vd1vQ!6KLOen_rVv`x-0fqs3aL7p%VsWOD%VTffq zzIqHSv{_BvF+}#V{!#)`%^{71Vb+T%M*yV)lZW-t_hS|-_4YQ}6-1dp={wFjnQMEP z8mla8Rg6ieV-waID!^9}G>)Cnq3K0h!B?5f1ro;|VXbt#ip!*0v8017=$1glWWrNR zMLV9fdP+7D+S-Ez{aA7eYfbdy-HT8?#nL;yd%|yID_6T zC2bz|XN0wY{Dftc*BDg2kwtshb~sxme2Y9n6`&ejL7rCOw8cZAO(+6#|C#;R*bTmtVwbEBuTi7YmA*`8(6h5Cb zIHr7@JZT_xoU?(f0sR$?ox!Z$TpKjCz?v%aF0d7bA)fncTpvhSLRzFP=_=H)ElzPE zE~;sOjCfBiLsq*kcS{l0Y&2?-wT6S!hWNM=ba0-&Kiy07rX#Gs&t|Qmi=p+muT+4qaj3DTb)XA8%5jlaGj9_pr4nHc2W!@Cv@nUL88!!~6sDIp zok>%v`8?=^9D05N*pKhLTB}(?Y3XhdcIe01NgBb<2yv`u!>Cu1s*(+Q5Mg=9`7~t# zZRfVZQ=C?h-%v^#FX+U3kNSMJ>Q+pZooeVFAsH|4pjPgrJ$P&-t@X*)erYXzn zW_b@`MTqMYAp04hh}w2~>LRBMBw@|k*f0re&z}7X);@o)YwGOtVgfS1e^dn?huZf% z;pT$Fw{MTHs^Lv%a(R4pb#r->&azPgteNtASSvz*1qp5RapEjQoYR)DjSv@s=%nE4 z=nDCxNa4G^#wxqAn;&ldao|gbEJ=mgSNm@^59x^sYesQ}HI=%Zsf#GCT*sQ~l4q0FvxrAy zt^G@*nhY0M+t6!OsIF_{iVLnW)&#+B!Q)@;Q1H}|&wnnexcF4ky| z4cy%*LHo%%)dp^QRNZys+5&4b7*#vT2%8Z8!L|TC9m%R2zQPz{ILkN)6-0u_GV^u< zvG~sz8&0HxlDB0W;>aEUNBFw#O+pZNyDWmX*FpA#0GV~^2AZRvlt{`E+kY2p-uxjK z^s$J3ueuD7FE~VpJ7%=JyQ;dgc4u<)=W+6Bdh=(P&9cNrnez{@hS8puW$PAS#5sLK z#dR+Ik^`Qdf;cDV1DkHzUl$24pvOd)W;?bpSR~vT<|BGC!Wu+ckZ-_{(bYz(k-aAs z%ZS<XUA=u+}y<3L0$Y?JAk;STof)o6pmFOpcW5ge~2(53C6lrt|r%KJPtI z?Ln-GW~(`wv@jT$^MrDRHMu)$PCC&=#e5(&jk;UQG7;aP1J_?+t>73KL3i-s3vyWN zSSw+V4c$5fxYtJ5GEjycHxDansX9OP+WlliP6B7kd~`0@+|s-kI5o1&)FL2kHlnak z_8CfZ^{K9t_afjbG`a>QZ^iYua7ZBw=@UllV{XgQhdX+xYN9rBQQI!fe-mpTf8c|j zY0YnZ`Z+$E&%MWiwGGok^VDks+JFD%lC_g#*URJG<{*ue^wX!4Fq|b>%OfZBhgieD z;o6REjK4YmA9dH-lsL9U`hY$Z*eQ;pHsi?A=^q{z}#n8T

NCEt`>nHF|EDHe{JE zFFG2mwY3b_G`hX8-$j^!AQa8?BPDwS!uO!t8Z^s1OJOH6WCi(1vCfcoO@c>j^b9T- zA{^55digG%S|#fVPJyPx=YRSHxQro620;*%qZxhm<4!T?wZVW?eQZ+TPxr&ouL{a* znJl_Y!1mr3B4_+{TxCl$iNAjxB0rKz>)J|-nol-X^T^Cs&j+qqJ<#YymiSPlFylId z_K`5{%!Gn2L1-QmRg?vxA=CONFu$Y4GeFN4%u6#i97^8Es3?n-yi40($w#9TV9r~f zg(hFl_oLYW z>4n8C&wE&V?+VVzISZ!^J-=F5u8Y|i-6Qa-$Ay+iJ@;bU--E0XD&mr>3eclm(BP!w zx)zvk@E8f=>{5v#)7q&d?_FyR24##?A_4%BX#9{L0LJ79<}_OIDIpBr4>yV!v}It; zd}mn`#4O>`B3J`*s=Yzvw;Ns9Zk143beX`}FALQhgu`}>uY}xb>lD?*6Nil7OrOW% zUKH;IC#v)?N$SOy@2&N#SPSuNChRYc{Bu|<&tgAmHF*z0$)Fq;=@RVpgetc#D)n($ zsjT>Q$$)G#W7`fUGack@+C<$oV*yfaeV88R$=C0hff@$Z=!A<=We*(kJ)s`pG%Nm@ zQl#k@(MjRVvVy^pE}=8V5w=CJR^riiR+;=Wz0{(IXT~!?O#y*iQOK@INOz;lA%`je zpJQ2()dFuz!fuhjsCi&ZSmXkI3t8$)Ul`xuSz&F`_^Gq@rBmWnS|r<1tZpnJyc zA-Gh{aq}0vwJbSMWMxboLK4`r*33uB0*$5I88l}2f~T++kc~lwuP0V2!E*sN73i+$$Wk_zx%u~jQpR%nxs9dbTHlg^yy%8oqT9D^DBm_7?K?j zcz7FzyBJc$x0JOrLrO~uh023KyTSn`3Xpio^+97Vc-51DqD3;KG<7>JB-p$LO&ow7 zvL0ocu2aIYY~!DiE$2#(#gPZv5mY{3%4ITZ3!4Uej%&||1a=0S~bi=QE(Rpeu<_ukH4IzW&Rwo?|P z86uFl3mqG&>zyF;Jz>C?v~(G3KyepOktKIk2YlpAu38^O^CF)Yi$y=#{6jALX3<2s zfPA5hCcBbpWGf8mPcpO66g(fT^krwS1vFu(xy&Dz zwF=s#ks`*+aMDhkY)*gM$NDrq2rRo84tJ{6QMH;tf=iN{Mh{~;IW3+a);5w<0r&gR z*67@}<1bPCigIg^!#%~o~l*Qayx)8=!Awe!kwlQjoxN^k>hCZep z?r_o-R9RL>?k>oX9122t+;C>ek_pzJdT_ig98@uc696*Z*dJRw=a^v4d|kRn!Yo?PJyCC%ij0o45yleDbhD9|$}AnRUOcP;$5oF4@Nxr#L>esv zQ@!@GY$#DjUhHmaYA5f0Ji83Dm7Se(Efa| zjv0^^5-*00ZllV@&bN>P?d$<6@2zy&kmj-B^x+%VkN)5yu*9b+7A%XLHcQ4{p~A}} z=cQ3!4UZ0ewWz>;HjP?b?#$X&;s%&IX8{PVFv!53^R9J16 z=w)`u3SEtZTR2~5E0r#@AqPjaY0}Hq%=0s>X=sv$rm_HU4X=^kzd43`cDTR%_wd7X zdg2Bbg|phjwc~q;*8Uc_b2`u^2VGXfj zxjohtcuiV+jSKD;Qsrp84C}y+u^d91;}0MHTHaVaY`X7=Y9;DCS`}{sAxD35^zeAw z^F{aMmYjjfCJFvBqpGiNfR3^*1F43sj8NXtb~f|6o#Q>kr0 z`pu?lZ2JFy!L!$%7vPEQeLg(BvD!3E4Ismwb@t2JYq80?9vxv=H_&s~ygaD9Srq4M z9Bp1B2!~?`aBq&1gzA;UwurnT`B@Cq2|Va5gg;(=tO&dxQ}XHTA&ABip`4y_?97@{ z?a|Q~tp;Ow?=}?sfV15EcsOfPmU?!5_7>k%#8Lq33#UfKcCFQMr;>1Vksnp70hO*P z(fI!eYZw^(6xZngJDvOOa;wx2{uEfFZ0+!H36GZLlKyCCj9bBJC%EE$DBp@_*_Mt8llnUH4YNW81-O6fIXHp6k9izg` zVOy`RLG)cEo}UnXr{shRP8Bst6x#f(%MwehQNl$y6npDn?T^X9{alH9&Hqd~;S>97hZ4)6&XVIAfx90kpB>uZrz?l}h~!!J5^iG)Aq) z%urC=1FYeCacQ?|MEU{2n#2P(CNBgg!wA;kLd5PGu_bNBvLqV0P|5}mjLz2;tUI3H8lVxPg3#k1|BodZRsa&^ca?xO3=@s6q(8xU;$7FY{|PllduoVWSKW58-VD0AS;&6F$ck_Dr`u6?R<>B4(?&NNHvwWC5Jl;B#tKCzk z-_(8vYgA6!r|UdH)G&_W2xJetx)^s&06*y!XP6}&U%;7b8-^!4tSI1s2HcOH% zVDQSCsxZKf9SeVV-A+L^OZa%B^%H-}oNbXv1Da5h|5Bk4({ed8Vw)63&c5fV6$>|} z?}7ooq1Uw~*j90`92R1Kz690~gdEEnU`-l69rPafNeE=iqB2LFzq@{SeU8U69V5N# z{J9elIzxDFb1<+Q=7VC7jR`mIQYuwC`Gt=6W9oh|@}&kTn@%`q&SoKirafiXmjrjtsnFX}c+!{JP^tDKap z6<#Vn-Lf<0z!9nb0L~41K#^cgg7aT_w{v92r6#g9dKg>KK}*|OgEa~zC~yl1aBmJ+ z6+5X<+=(BDXBKvy%viDNU$N8<|8`G8uD;?~LWyuWiHCV$YY3TM;a;PS-_Chc}Jc{Kg zTVsg@lafuD^Ky76o`nkfZ086prsTnTB&kD>%`c+K?fPvG--T9j9G2S~i=n7T!sf6l zu`8jO<6;}5yFzDF=!H}KbAQ;@2-b{e4{NejidKRLi}s+#A_uK-jdGW@q>bGYA#=$W zh%!ezujp)?IyGTs((XT2iK%Mq&vwIM8%yVUqTfhKZ@xcw#{4161l4pxO6ZJ+SX47D z!#=w{uw_C9-ZH4Zs6?Zr{2mV2xS+=;K{3`Ow1ZN?8b4a@%GM~x5?I^%FIdww!Sg9B zxJP;iusUG;LHA+d(rMq#2T}DW5e5h(ig+2vpxQ0v+aeXypcpdhUnp7)EM&2~-f4x- z&4F*^%oPeqR^a1F*P5LIzal{>3>4Pl1|tJ3O{u8gXK-(g6;L&TN~%J!;w(My?as%_ zx1CPDVanBBA?TXna8Kp?;Fqjzmr^KC@*_1V_KS^;HkpJ;>0Y78*_vh^52`#G>5eFW z>$HY5f7Lk1g0?(y7b@&S+ca|5FqD~&MmpTLf#7LdS1_wLvGCPteDE zy1n)(2$9l_rseHFC|d)+Ag#7ZS;u z>;-LPF~ToECE!>pe=pcoROQpvecrZMLebLI-I>VZK3WaWs$H1Bn(eEql8Bn%%^&T!Q1ZyxcxT9q4@v7vyPXF=eu!j3j zGOTHwt^JR%CUp&ay&o%7v@!yDeyun)1!p@->`@(nK-%93Bz<=VeV-WCfI|^10DuJg z_FrMqXlQiwi8{9G{AzJ-5C-Y1lOM@f$`MIFWV|9lC>^Tt7IO+~V37E6nvrXU0p}QO z#6~BArR6jWIp>K@dE}r;iPQ?baDyPva-1pGV<~vaW(bANmP-kkz5#1^fFf7}w?qot zw^v`>TCd>moVoSv2_B-io2*U=7U`#~WOpqEdXYhvQy0)9GzFP~s-*pQpB2GLn5`hYdP{_*Px{RXC0Y6<}RwG;cPbhK6%g<87gvX`0c*?o!{g|2RC4mA;PIjV3s{SaP^F6q*7SdbHF&IR znsrW5;1LW#B;2M$Ebz^oz`ziFhpv(l0h|L>{fD}%|4AcT!ye{v$j-+hjC?tWBGeM6 zvOqyk{7OZQXdiz1!;~ZORk}oH_H%`}I5zt0TkP z+LZG#49RARrs*gF7NC@V&IS-!^E|MaYxXV#5GYv7G+kvwTV1m)rMSC84R;CU!M(Uk z2pSxM7I$|kh2rj(00Dx#7KZ|%xD}TcDK3}y!~F&4oPGApp0#JqT0GE@NHv39V86W{ z$8UaIaAkPRNDt39l5~?M!I|uTwDFo{#-RX#KLQG;$1n$Wi$P5{k(2s#8J~d6EDoiK#*}VEiuZNAl6?`*utEzVMv3*LMb|44>t=bIwEMxw;~$I-o`PCwZGuUc>?I_-U`60=zOdMv1@7r`E#oFQ2xpci!pt73RF~ z91AQ0C)?8*ct~TK_Z-L8I z`1A};6m?f8LQZUqR7lxaa00zZFaR1;4puD+7_~C|-V2OpG{w7+Cs-IyEj;44l@}!< z68J)bHI*Jc$0b)u5KtrsldOx_?F z@xhEvh~$3N#OeQ!# zSxz?YMUVyQV)xt-Q=WY)8u)c#1Wc)5x?Oi-j#aHVXzkZ!@nzDul3&0-lZG^ zEx#@8yA?=eXG{9{=*J9@zHr`1vwCTM23L{~)sUdR61{gc_p%a=nmT@5btV z*}_)e=`d8%2|P7}Bx#^+i+qHsTWS?bhOCi@Ic(@A=d%oOIsOM~Yq^;tvM#m2d8yjg@rI4NO;D~2VIr`m{a={**$nuc_ z;dOKk7~VxM;#^!v44HI_G~~=pDwF}{h2@M6)TYm|K@qN@A}qh-O7`JGC}jUx{I^*e zvk@okxNH|Hh|$L*XT;O|d7m|fmZXv6E5hu>7$c{<{{ao{*4+^oN<^OeDO*}N&AoSm z|2KEU-;YYd;U$0cv^37GKl8C<#-c&7dX_+0-~{veAVOs1 z=6m~lap>b3PqITT2GVG3GE5Ln`8vBlu79>+ar0#Y;^ajEy?!+hZ<0FP{`z{8AOhek zZ1c6I2EWT}xl5SsP%Nk#+_WuU+%aD~|Jzw`i<4qkuKZ8bS)ymns)52y2@2#ClR#}Z zznx9l&M^V)F1bzOHMT#Q1t8m!w_n>Y1weCdFSnQNM3@GtbEI(Kuu2Ftl#o`8AZG=Z zH?hSMdDn5Fr|MZy^(v^i?g{a(v=6P$@RcIIOQ5myrN(A^5kbM`#@lFQDcu!Ml8V&IAq!P*E%BXv0n(b7 z=f~u)M*P*f+Fyes2>w?Z&Cy_)5Ui2+0}U@|N>5qT@!TQvTg5Bucoq%Cx>ZSc|6d;1 zQ*Ixtm@#-6Z|JI>8mn55GI;ogS7P#R(pNL2U%L{5UbiYPbbxJm-)DXaq=p9U949~h zK3tDN$UmnqP{Mfqu&1xCTs*})GfW7fVro-&Hjft<=q-iU%@X8D4v@vQd)zsCZj;#t z^U3iLC|%HPM2xJB`yss7_`e0ddU5}N)Uc6eQ&h}1WX9@Y0#^FduArF{roSuf@UFO@ zF&QeJORZd_{_OH398dY=qWt@s4vV7syY{5Weg6FjOJIXa?vSQ3cHX)uB^c~>+j>FHwfrd%y z0!}FU!oS_rVO{rXx@xe0wwk#G_i5x~^KgEOw>zMKt*T@@BA{^yl4woi*h3wlc0zJ_ z?ddXY2~RRqd>so?)D((-?O2$qlfZ`M?yp^2$1z+Fehh1S^;CohD{1?~t=J`AW7~DO zXFlqT@9qOA{B+jtf4LnL*ht=tpBIeqxz+7kn!rvJ}uvo zVqNB6kNLT1=2!M;<>Yj;7%Rz`QYT51H8{CE^#^O@g?JMzB3wjey(wMKJvSE5)8yfBQlI$>Sq| znzVKe;o|jC@q6+so0ewZlR#E#*7WnGKh`=Lj{7$T-FwY^nQDbyjoT|I&_P*RB|9m7 z7h}u?oAr&FO||s&*gvQf4K-pRJ@!_Tudn5Qg@~GI5B}^_kW}Ci@FNZo@Q= z&d+vFF{UFd>J8HdX@nErxNlEATC>L&%JvP$LU>Er`|DW2iCF*T4TN*#b7ODuylZc< z9)ggNKqO0wFsEj|f00`DASDQHmoFgdO($f}0Yo#%1l4{d_G?Ym(KoN{7@o)K0TCQ) z`$pIw+1>{r<-2=4>laZ`A-osbl?ktTm`rnr{pMV$jB^!xZPOv$^fGhLGL3o_LFrc0 zPTg8Sk??eShw@3AsB&kUhA6{*VzJ3nY_GjHkY)*5q>&=z9uMj9(#W|CLWLyLak5lP z8Bg#N=}7(nvwlL%<;<^K+4Mrm0HEH{bsh~#bpd#Vf!dg@K(W+DRt(^c#&?C%64=Ud zcG!t&19HgaFE{%PF)6iGzpfc8C2D(6t8Tq7}z`}tq|wa``G|A^SW zdeRC-*OxiS$$bNzxOc#U5$-9I+D6cemdy>RnC%t1$Q8d?0z~Iq>4SRR5H^lg0TGhW z%7LPZvCi7y{SRPD&R@)Vh^_Soa4b3U-xnMxk)n|;Fq;{D%$to$>$Rq;!7qF_|1A$X zqY(SdR`sBw6O;hYaQg3glv3ME90Td(V;RLbY8davQ0X&?eh-J^i7mvXBvW54L%^4B zoGr--V|CtIs9N(?Ac;SBJ7;18;{qLVA-y4`mf?V2ib)})Nic~0SUdu;j-Hyj5Dkc* z-PS}eK4XsedcN^_etODsBB03c3VZ|r`GWz(Qs~uyokv`xJ1&QJGoaaG0RJIyO3Wy3 zag#bNsA59dp$r54mfvcY+LE)iI}RV96+R)9hQQlrPR=CORKiIytEVx=bZ3%oGWb?u z@E0d~5&v6bW5%$&P6G{oE@>25+r~1VuritFV240JBB0m6*j-#6NV2wbcn?dy7K0Yb zSzq|WW`2eIx>baJE6M~csP|F+Ss%-##zVaEIT3O|l#vj2!@+sYT<>QGkCRO1>Bs@Q z;G@?F?q{@Dh)Q8NS#qAo4-Jm(7F8w|1ko1@x4M<|wY<=8D`$vY4E*-&sOYyUP$2Xc zoNQK%(8^bkHu|gB7ukyS(ry6+a{cj&6j_5^iw$x2Rp9TTE^F*KNc^17%W`?~*_?I} z(54XB*^NU{D9WrOj)6?$i-pSzo6H>CC6>%hnK>GqsP^M>KLB8eaL|n%g&1{q4d_TD zqF{KZFG;Q`&kOs2S*T)hHq5$A%Lm4)Bt`T_4&P0%x}GKn9%+3eL=%cDaw+-w8q+kw z=i|2p+F6vT3w_3HfuZFBOJTO1A={slZI&Fmho)ye1UP%v@>yD(HVtdY`*~&IPgIco z9^10zUN$eF&(Tujo7`T`=z5v8_ZErwgMA_{W)ny6lGXUHxQUVBjW%MYba``&REzgP zU5E@BViV7115XO)MCG5EOFh(`o^P0E%*eHeNi8ORZOLah62jr)1&(P@KPF-!8^-N1n zjk)yClIoQN*b1+PYCkLS)(LXYQ#4}!^CqJ1yodm$Y=$&yK+b30U!qkY&Tr?NnSY9) z2X%-;S^Jj$(F`rw;&uddwcMuSK{}msi+|I>nWLV*|>|7vK^eL+C;mTD*E~%d<$MX2Mr18 z99%}Lb^iFAd{J+Yif>0`2^|FOuuKAF+K5dbte`RYpj|(b}F@8 zd-@3B*sA8T*`rG#lNuq;6U0rq^oY;hmOqbkX-AWBxaZ!*boXDC{3lgo@2hWO{1O#P zC6T5xKixDOO=ixWJ71P`QQmo>I?(xV>80J0CGa&2JE2S?9w6VV_Ga z6<4kK$}&eR>lbO`Or{v|*hzAlqU0L&f7jHT6KSW`&&dOLvMvTgRF$>;dwRD_^mo?; zI)14Z!oI3B_?b*qJaO>r;3irfDIg0er%3ciOP{g z{%jf1Yz_`CshspDV}9fCGGZ)iFoFEQfsxwrPOO^9%6kSH79r=QuhbZq^50ycuCi3z zv2Y|vtW9)PIKc?ro#9b^+WBI|!)t5T&Bg)b?71@d!CSd~az0CSA@t(+lT(zOkp@j{ z=4(F~(&~t>p1jP81#S>_e=URt6y#WA+g)IVz%%=z(3!stQ-9?>?3ln zBQ+KUdeF1w?cfNmwGOFpkTPsqV<~;6GCTZr6nxr%1WVLZ0 z0`32vX(YE{iojBu{rmHIvY(hSU$DI6158aK-*>=udPQICHr(vI*zSB_zBUL6qJK~F z@iph61YnO3dQ}nVA2Rt%SphNj8BY$ON0oit%P6lwRZ^ z_Ya1b)||m{03{eNByH`zvtW{bgLD|`U^oErFEFpBrH++zeV}z)hmCTrrA1e`iys>m7l!qm%BN^H4>q5-^HC!p4JQ^D<%jZ z*0UN|Um=7@GiOicvs$M&;cmXD$o~$+`+hr7`jbRn^jdrfi^n>_5Ch4AEtxMbwQ0fD zMYU?F-rS~t-BD=A*f&Za(A9DY6 z2@5uBJ^u2R2q*$m{i>yxeLAxPUa(V3MzZTD$h7X*+uxTQ7i>zc9+c)MIe*bc>ELfO z`6(6hZK3c_+*d8>ul1kCFq9Zqljli#fpMI6n`--{ya$xP+5Rs(zRz#tjY{CwPdIZ+ zqYUfGv(iER`OFPSlQvMwVRz$Ihx|{Fm#kSkW#M>%UqH|^5A|1irzg~kRk82=2I$o+#mc^ha0ULp%Oy_3w00xu+MIP^@irFNh@(Di>#esFx&`ETd%mvf z_)2+$`{9dU_#t}gKb4`Z2&IV0ui5LKRktgrDs_T@gOb8JBIz)s_WI#pjwcjft>(-48qgd zYDYH`w_rlvSTaG38ddk4ojSZP9K=Ro;|06bD7f@BQI5qSW zhi2x1i>gD*8h>!i-t#!dbcZ1nNc<@vD}OL`tuDUgn86GUbCGIdvUqaAhztK!?epPy z_eoE2)01eQSeKaWkjIL5ueTcenbfu1V?TbtVYO?axqOFDUWg$0uYbUsesv@JlurFC zo~qaa+UfK&PcbhBY64AJ0?`G~cHvb-caQmsR;; zyR^f}RtWO*gKlE__GG=q%}aPEieC70tgh*detyaEOjDc1{}Us+u{V_NAZynpv&^t# z0QFayM|*;apkdb$7}Iy5ee8-8M6L+~|2(RWUlkGxB!V+_vLadD>$#yfDc45eUz8-Ku+W@&PHYRd9li zP_G4;zfdX>fGJ&R3fwNI_6r6iQAGm|6bY$uyWV3CKKW#|pg=ceu*-^I6tI>GH4-@r@zux^&Dy7 zyFyKAY80cH$GLIxoGxx-I8dYu#~*#6($HVu>1he1*Ugs^vgy=l4y`as(l1 z0$v+VF4jLPNXTFhHA$ZdQ{#8&?BDTBjUEuRWyf)=n;rrskK1i_@mvWqPnch@cbvIK z4q?crE;4#g(7PVGDKXe6P7$`f17|&=kaWt;!P*CA&9H@ z&=Yf4tnHUF75-(%@+vjK8pGtA7P7Vm@+~t21WYn__(s@Gnc;CawN?Sz^dS6ZCxw|P z#5I5ZLl|XF7c5wrExuh)IYvj|>h|xl&T|6r@h987{N3;_v$730@}^U@Ant6)J{7g& z092@Be)`ujm;4j-DQF@z0IOQA`0QppX4+ezODwBXfD9s9ZJ01W(lG~8FsMf8gA>$E zAgg=M=>!lH^?f2|jyhbLE_YS_jgY{-yj(JGY|`(b_SMd~d){6P7&6a1fmNcc5|I3> z?~EceXGzJ?vDDh=ugXrZ_m`bG{UE*k+nNqs$nQGhXX)KiWJenU0m}Aq#;ZVYz8~HF zX|DQ-W2{MKR!|3ZdCk%APiut9pV5AhpN&NiU@n|!I zgGVvzB?yh533hqS39K-=iG-H}#>I{@-+uSzcS~)p1f;dRe8)lwu0{=_Oyv(S@r%*0 zi^Hq~sLFn0wTX7(MAz2{7NQ4fuc0%wk=_dhRFOWZsZfPyvi#W`Z|1q~O|}_c3Ul4| z7p0}UESdTqq9IL?qg`g6KnzmPV;Nn!LQ4OhG93W@uz`Nlg&A%qXv6#++-|W&e+Q~p zfcHITov4Le5(tvrPghJ%5)IoSzRM>~*&`lIbL!B4>mt$R_U`YIp8c}%8%B$7+xj(y zwF9DT#AO(0(>B>Bj5f|T=JU+)Oc!a;l*LmUY)!V>LH&x#9UAtzd0@)-#}uQ0FQdV- zfv5h%WOLOb2Sa|^ z&#)QmoS`OHq9ur%hURWMkQ5v4D_=nGj21&rsoD0PU^gE99ZE0}(<*wcpW@jsz~h zU_bF0TG(%M>Kz37@AUd>w`UBci4vlWv`C+ja!dUNhIFwe^))hu{|9y)JVeHJU|zp% zZ8hk~Hz#bv1*Tvvdb*DZCRw)?3TNqN--e;Vufnr~xVTsQ`?&l!d&q zHz)LMZD=UxVZun~wbDpf(0Z&QUZ1BXuQM8~)xH>7vY&(P)EZKT={aqJt99FrK~UZ^ zg?Sj0J;2=yqiV706s(E?1*pPK+_S9D>8b%e)Ms>%@RIYHsVB zGpDr#{VKe5+qbHag;T zO7ot&>tM7VT(@7bPZHNQ}zjpzeUVc3wnEt#`~#LVq3qzjSu`51-R*W1?9ba z1NmM*0xXuT3?1shJRBaJl7cxB=B`@#cHf2fybMLT)9XOh#IKEMBzCt@{R& zk?7yBwY7OOtib2Whh*`KM?6s~4!weGb6q@k0%CXd$DN^@hACY7YOqxb4H#LGB+Q>Z z-;W+r%i?wER+!?U82SHPfG|Uiq$gYXhA;tbylD9lXZ*y!lF&uU@HT1%!RNZBH}(m! z=Uo?P4J??bZh|2(xbQTEW4$l2gyakss+xy0?1F*w?~obE!alKxS&#xIgVku1bg0G2 z{nVL9tJ|3)H%FXw2B!d$^1s;pgii%!S_zbG^#u5gW~$N)-@&F~@#LK0F%jiJ_H?QC zz>%HB4=9-B^bay%Y^3C+35r}8DirOZmpbg(f5-M7UAZ~i7Tc0I|~H}sg^_}ZXf2Bt*UfcAez2u`R0DLoe5niWQiqgOW{F* zejB(}Lx0Wiu8}tqAb+K9uJ8UDsQ`GQgwPZqGwOoAw9#2(8APx6%MMpQZCz7h4 z6wHy+LylQ8VLGu7lig-k7R*tWl1!(f|B~#J2jJw34NR4Q2)5E+Z=j`EixPS90Ik@U zPaw|UgMmLecA}Qo5CY#JBB@VgaG1B&kf(p1Eg%VXgDb>T6@dBUjD5?3Fe3qcageRh)M(l7L``jEl|4%-u-oE%%M5a>meFYt9)OM z2`SdYfM2=QhS^Wtr)(qNA0-?-#rAGUtBn^I&Oy};g)g~1)GtvTJK z+0!R?`4DA}!%>R8njM%rp-mH#W`5X1C9l|yYJz4$?65tbTr3hsN@OpdFPxKTVx!7Y zC5uP36(}e3%UH1>POc~G%JWO7rDP2CjB5J{I~=-@_NM{r2T$lGGaX1`b_#e;X+Ke@ zTG*(wfm_R$pkHxCMi~x-slt(tw+Ar_wg1{WO`1e5_~d%VgaVGFz6I5sJXG4N7RrK6@v#3U>6mBY za%G;&G#W5XeipV3SLc2(a zXqt-t+eq$R{crj@oJv4#@lK3vRVqFkT)4FxXib-%Li)dIg4oXoU)DhSyV<2$6|2C0 zEjALC<({UAlPtHiPwXKiseLo~KRD|^=1@H~dmAnY%8^^qfGSf$29r+UHKp-1&4}fTfP(zHnG+4* z=k{gky@r!_%c8Y%z@vCpdzdQ7De5p>dViiee{jjj9R7?0(cx08q0nLkr(;YU1=GEZ zV=}30W-t=Z56o4?ghl$WQC%JEg{6=f@SC9h5VU4c^EAtp8S&`vG-X%H>z7JIHR6;1 zml*O{2>;Ew+zcWLQ({dCG= zLwbKu?#{!8m|BlfH#pBEjjG%GG(fL@js7U%oU;16q&uOn&FL{;a zmA&_66B=frh*b)BlL{=PMn8AV_#I$^N#@3u!@5{r=3pRWQXu0PJ60{Ih?EbF7%tz6 zo4S9TIg%_S7P!lU_m0*@!gWRvyj4oNnzSgtVsIw0w{pmSgZTJ+RETP!W*hqdQ{cz#z+?1Vey;lQAx(!hy=WG!bQomAC0kOrH{0{ zQVS^E5n+r}q!~*qnoMNgXb_bTP~KCEiTvQq!K}L@H5M7P{P^>XN6*yqz7izg+##9cu+qO;R!_{e=Z8gbgva1rpE2$}d9tP2T`i1r@UY9?$C;eUQvx6&|-8t+pPAky>(S%nTfAh;a;}}u568lm! zvQfW7xQfE5@yNIqDp%hO?hR62189R!ue#g!xGK8Vu}jW>*r7?R^-qaW83A?kUYl7@ z^*E@)917f z^~KZXA@O0qnO8_bduu`nwz+B=?FGN#K-PnU6&6P_jaQgRm?ElTnH|g8U%_wtjx5D& zHcXdJ#5K`|6u*8&*WXqC@I~VXuX|J!X$*4*rr!DnQNTv*tEeFNi}L*x;7y8e=Y*SL?$j1BDM9 z5+l-V&WFZ>@8S`}%P>F{?pl)?iwQ=AD@EdjHWfeM@;ZVm7dW4S+0B!;vt>N7yVZ6q|mk12%n)m}9bTdgGX5j2M<&~6hROClgP*^F}kie%gE0P-A z5~E$85=sjubG$j~m2k&!Fs0FVs#%3o4>U7tN$y(s8s&DUSo`3V#A&A+@D?zS`ll+r> zcb-r@c+={i{FN2|!;OK(tCbp9i1Fvc>ko*stwUV134~>Ls_{2wvBG?1Sf;#f=X6#C zqH`kEB6ko>8|#uW#1XR%yn9b2)R%^j0o|F`?*j#f*tb#23s+DGy1VN4o3S{(ej7>> zOpDi|5RCIj7S{XU3`5-u8g)8UWG7w0lEE?gkA5(12kXVFqBJH3h+`~xxfOydq`skl zn2Kj{wlKdDb++03mE(y4Dz~Q9Tn|-wS(ByVV)K9cP?*CpEmQ^USUuMtoV}p;0(je+ z9nO)!BiMRV;M|kfVzw~^Hdo?CTQ3-bXumobVcu9AQM@Pp;KmEMygY1M{o}m8a_sfW zz1$$J_n{IXdSsSMm;MUklW-V~=y1G!>VY*1@bC|1y+K9#9wl^22lzhT8o~oxZd+Rf zTX_<=!a#*4dcfmWRDGskz@>UySoD8kZ`B-Ys+8zG>w<~441D^>ca8mD96kI^KA>9^ zm`aZE6rJ%^QS^D_x@1_PvKqy3CN;Q+(bl}*rTFq(>3X&fknZi9lLuPlz4=Frk+>5* zeQu={8S#)dYp?+Xvd`zj z@tm(T+tZjZEKyuFfANPMk(oCQva8k@O8}p^?U-R`-A6~E`<1%Ce_3v8`RiSZhDkYP#J8YS+K&ODI)gj0&F2?dhy zvf%Y(os@QUe|NcYSEBh923OB2E5-p2OvxEd7>+-FTw$=_j0*2F<5t4_l)=f9V)83g zJEC7Kr9R}VJ)VPLh!<;!Y3TN0p72+ru}WWhwU=EgKuV;v3lyX{ON!uC5Lm~t9C#73 zT(_|Ph$_-geIb^@the6_ znw5lH2Q8T1q}SAxgjy$to^nE}NvnpRf*x9KJ^W_{z4qm&aUIAZPFD`mciSk({Lg6QYZ}jE7)EdrHIA)1sZ<^Y1sSc|CBoW;c)dp;Cl;F4Wm}uko(A z?uua!q?aG>FUkh}k7Ck-b+M;SA)+;K&4FwCda8E!`gL^eiw4mmZN7;UGA=6r0CaXg z@X_J96lgH`@A%jD+Zpey`a;~59wpLEqno|~6%D!1P&?V-zj3&BW=o|623z&ddu`=_h_ z)t*ksc&w~h{dsjypKe`FK`8u;AeRSjS2Le9Jf<|LF9##IvI>j`mi{R|AK#U&4r;8P z9vEF=>5^}-sdlB?KkVADE*_Vsx-7AzF%2nIYKZ>Q^-@CX5EI89#7m*4z%H$1CdDae z`3&49vM?i8tQ{{N58A+^b)t++Bf~2S7DU}v*VTZu4z9$(o6IQNI7>-xh~teh#sT^_ zaGD<)1w?HhiO0NNvs>2e6sksPLWe|m={T(aL!zUkPJ=R!o`x=+a=9zasdqz~wYH}98G`c%8$3oVndC?&(w$4UR zpKT3(v@6qe2qStbK{``&TxNF-OCZ;J+m=v~a}V}3b)Lws zp;W}FBF#s`=Ac+GM_UozP{iP6V4-ti6rn`@&F`t;vy##seh)PX z2jsdXaptt5ep1O~-Qt12mkyH>Nb2GH_9L8RiozB9s^Sk%PZrSLB202c z0(e<`9g{2{<^~PN?XSd5F506HNEWo0qJ~()YAR-C%&rx>a$0m%fn@R8>B*v2=6gS? z_b)w!D$m`*_o}W<>l4;3pSZ4FRs;O%3qoF;@UGRp#A1co=V(&9IUSL}ov<|CH7w>% z;qT3CueyF;j%RUC{dfK#524=vsMZ}2Fn@4r`o~L{3MstW9f`211bDoL2oqZE6||Mx zV!xw>aGUQ7@2!;Z%abqucY#7?VIL!m0F+|Sc#Jx|uF{lorR71jIv()kA2MMtwBF4z&*{M!Vr}Lp3K}bzp_w#^-29>e8#W z5EuR;m`3)xXdVlVUY%i%vHzs5oeNb!gSqAL#Sh6^M9{S^E6a9ZfFk~B znhc+0qxjQ9-~P9#^?T=e>VROx>Sv(aYHDXf?SL;9aQW8f>GAOZ**)j*oOPk z-&T7*Z|DP6&pL*g$Uy&biM#6#y&@^$wouy_LcaQdp-%_SmJJ`vI)paSI?T*8wwg`U zIjlC$i2mFLY8++&#Si}j%3?5N~mU_f8~1JG~1N(d71Yv2ke`@N;sB)yEhp za_seXqeJ|#Y39Ct{iu0apMi_p1@}wy!qGKPipxK~-S9*URk!roKu*TIU3q0zeqQW< zw8MRL<*jCpy;Uek+GR^Ao*x&}7F7NUEn_L7444rJDJ1Pj%{&SfF(J$id8BUYumF~< zQp9&36STY}AL`*yIlhVNaQ&Y+?1<)F<2_OKY9VnPNoCMo+yFH>^wk858iNi^F#i6B zt)$*yA`I`c#qgpbqyXa=I-wE#rms?se=_VCtp-Ni$~34s2%;SuL|f_DG-p*Dy;l+= zDmEST4=(;T)PZ+q1OjS+{LU{FiXeDd3Wn7F^8Cpo6T$=&sU`tn(mYuf51@;@_#{?% zMO_7tQ;rsJeWhEyZr=>2YMgZj$2fJ*h6r8S*JMtECg{yoX92!(h=50H+!hqz>;bmf z$tmIuP{w9C$`8WsH=N4gHX6`vDFc(uE=cDX;xNuP`udbZ_nyPIh#p{YuqS1J^&-O{ zmL)}o#yh>kL8i-ME`e9_+h|DYty?58yGDhaBwAWtN`ogm){GF-yxxW9m1UqRrh3O? zk~SyKW;b%;`;Gns#E5rVITGzz0V)!9D0q{HZ6!~eU`eF61 zM)`-c9>ksaMR9WKnu$s387TVkd)IrY=B44$6_-TMy=VK^6ws0w6nNB}N+wj%Jh}ea z{^9JQ&bpmGF6~XkKiYZF>_ko1vBjW1-bKv1Ysbmbmgj{y^6duHd4>onC{BFR_>`_< z)fXnJMs>HKUbZ?!$L0G7pIVOEI)(?YDp%BY>pE=pL?`7U^5c-fJp^ScRv zRBZVcf|Qf~WO47$x+vos<7@73DxCXkVm1l(UrfS7KIhNYf_bQV?aTvvip<__5A4__ zjS+L{XN-wjGQBx{i$Vl3V5@slFYB`gbBu}RSo;w_sc?Lb`E{a#PQb}#@C5-ENkr@_ z281KB`j(dDw>1tJo4ZQeCr$>NW%K*!t|zjo>g1WtPnNH4NA3osSHeEk?zZ%UnwQ&T zy^7Ro*AFcUK@7tOh0C9==o@)Bg-sFY>@88i1~U(IsLy+b;U$#Yo64@$4m=Wf9Y_?- zzk7Q}kNgg?wQas=^LPDxRt7AxI#@Yw#5$RdeZs=rQFuMnygr%oyy0yz`8S2zJ^br0 zj%{VeH-m5YxTK(q+7_w{oG9>`;sfOxar%Byk$PrwiKZ^VQzG`Er;U!3e=$L@wydpmF*9nsZU_b__x}u0mrlTjM;~jwqaO zhth+oUc;*7tS2m0d_3(Z5t2`U=yl0tC;*_ZFXM(NpMRMR${N3@1A;xFh1)GrQpi%wfcZ94s*(jXuB3)Vr0z znG3Rt>*SpyXJrVpdfET{nOV!i2QELKpKh#rk8Tv4ZM&0(o6nN!m8*mRs-}VgVYC8F z6YlxHOf@8?P3e#v14}l+pz>9Fgi91`xxH&hit|xiZ_8YxYSeWv9V-Gc5%By1?G9?q zE58TAKjBL2s=TRxSWRF3=a`;2x0FA;JXUve@Bw-Pb!v-#xh=|yMhFdJUxl7&jTXhk z@XSxCcnIICYU|mtxpAEfDS=DXEvb9U7k@eu+LP-Jxls)Vj{G2mXtM-UpVohf=R7)S zkFmc_Jjk;-Ucd{hxIMQ)5t&jAOJ3L2v3Wb8@>3Q;P80#qm@7%b(sGIhguch;FBGpp z^a+q5MU%et3Ivs+P++TeyB4v_qX}!CzBPwf+)lnhuWM?(3G{lzh`b$@L$AB?*d9C2 zPmn>i2-1LLSFgiaFI!W}BLUmeY7qe4&F1@q8`sbKFKMJa<^=6B6^xf%zNCLr9EcHz zB(w}hkek8g4_Kg5EWY!OQ_ZwqQXe4t!GPC?%N&!F4+U7j_6FpQiRtQ1Y^KH+NLih> zgvt72H2HY*@UHpx@@MleREwUoAuO5$M0+8obqdz4zXd&vqY`f=)dPUg@eeu9dogcS zWuQzEG!Z29q@skPBhgI^lE3#v|DOxsawTy%8OiQwnXsMvk!kNE{|E{gs-ryDxcigb zct4G^t3-bJ|9bo8x5~b-@0x5*wrz95#K}6@JYlkHvTc8}PVQ8b-NcC}yUDhDd#?9- z{)K1%y05+0US9jYKZve1Y;*i>gzT2l)VleBvvwd3-3$i==ZlW?NfJ^h7zNw}TIJ*S zsP~Z=2lJlcwFS9$$65ZW7Plv4k|rimP!F?t{tKNG^ljfzKZc1d_szGvKYfi#a3BAG zI_ff3y2d-85#bb&c#;Yb zGy8)qHU-s~$y%c9n)Oe^HTBD&n~FwQM902_hgw)e+fnJMMj2Rk zXW)x`7P$uQ*U)kSp1M=qiThv(MUj z94%OClFA8;D1`36zcx10{e|y#YEMRy-!EV!7|%*x{^X3)ksi577&ekU4%rPkJ0|e% zWIHSmd;XBr()>$iX{ZPx4n!8Os{Q4E@Ow~c1=QA5awrZ(h^JMpZ`~Dy03P1Huirta~7 z>Jn1yl?^iSu#A!Sk-y}DVLdAi3j0AiNls_z8K}1lrxLd6-`hy0x00sH8Y|TlKjCx+ zlIyo%rKuMXq03;8<$>4P=h-n&F20=dW$zDp|rO7 zCu9^Tf-Coac#=Ys`^b)^7}e=q2YvxE5Zb%Wv$PQb5f#)e(O9$qUgrnbHCOezD7O3? z?z)z2{eb^4$9uwfb0p++N+zSRQUZoBu1nP`&yQ-aKX%)VNm7rK(cm4wan<%gAAWNXxgbQIFWhUJBcfQ>~lR(yuI+{*OnSz z#79qWE+Ja($CUP;#i|M!;*&etTUpJE<)>LYsHAP5Tx=GPZQO(xxb@md@;lr@A8$tw@66`$TqYOXLjRBG?_uN!vF zYi~6@9=iNJrsH0t&)95i?RAs?X4-C&U+eP5t@9@lDIc~Q{{W#+J~RmatJINyc-*Z; zt2z++jq8VRRvD|b8G_3kZt}p5vJPdq&`mMJWn%ds9-e{eGz~&D5)6()5VA#Onl1_s zr<|NsZ(`@=CXwkRF1jMs8CohvIJe&pcAekSR!ahzR~=#50O|2gw*0DFCcKW127Yi3 z5#^AxG~&a1qD2a#RN;{+!Lc5}h$N0PNw!Gskcd4h@f%+uT8rk6qf9+2ut`tk2|sYX zpRi`x#yyAALC1BAFaj(&&V#)xcx97Ad>5xx&S#6!+z@l}o!le8IL^f_K8-2da%4KO zAbJUu!|;;EX|Eg?${$VHGY&PkEw!~vJKdN`N6DJO#X`<9l;?^e|JIy zJ|mti_h0psU-u7w5!l#qW8{pLYqC5_l=3jk_BbCSiHWmr1)=nehcz|S#a2KucUpaT zArSfV{4!<1pzX6u3o|cVj^TutZbX#j6sBu>mXH>qp(%wYv}?plH~|fuqQXPE*SbBp zq2>~JNT7t6{Gys51qf^QX&?h3ynx-oc#4MVp(rrq((nCcTTq>f60jexA>eDm#$K4V5Ct|Mh6AQ&#+GcthH-^PHdK&K~ z$G^*rRHLZV!W)kstBEpmffeW(^QMb#al%LtOvAY63}j$-6*&UE{#kMd90ig(_m@=k zA4hc2O+V3t5X-+1&c+Nf=Ebz(?Xc|^LF|zUTUR+_I@ZfD*OmDXT7>feJo+_dk@|7n zm~S%7xMwoOblGt-`jHTC+0cWFjjmNeCosS5CNl`@Q>)uKV1|g>QT}0}X2IsPbJctE zuo)Q4{LB1c20toi9$Su10Jo}=fPN(}s-dj12$yNR7&?19CPkLEx_WKo|az zY_0%T=4JYG9th-}@kfVei804XUzZ&+FulpwEi$(4vfsbf;Aa7q%W-DxCpu9AbQb7? z2FhAAQ6elv2BK6|{o{emYn==Omkk%wBJH(N0tKRKEZSe`DB}@@rDq*3U{mb$8G?*z z^I<`NvXSVLV$$29{|wl4d})s`uDw!5&b=_=iRAeU8PzKlQ(;qUD&V}ol$LhWby+RJ zkBY+Z25B{$HC8w`@UBRh%^p@A_yw^AcB=x1sqExcXoVx0O#qfaC$ zK(d%4%H;W9FuYj`Wfw}g<*+me+8oWQ#1jP^9;>FJUhbyJrJ);T^wz}5yLoT?AjXOx+h8>z7~_Po zS+q4j^Pa>1DG{bjO4=j(TEau(bB`g;YFG`)>?fMwoT!1;m;*F%GM)Q&scyF56Ncw)I$eELto_%@`8 z`){W?Ld_t}44PKo8no4??8Vpg5)%z?XVf7c7~Rz$U*9bX&+BShO-l{0)pO?lJChd1 zbMBc-H|<%VjLqY>lLndQL=2eH(*%RfTGwqByw;9*EaNkKzc;O-ueYtQ@r(w)$e7g2(#>zj1HgcCcy|BHzOWtJH zaPmXp%vO^F)BZSx;=j6MB+A>i=yBKftvpwcurEzESeb_J{!=%d%SCrrsl(MS%N64z z=qLyHdUqy#`6Ej+S17t`CS13F2m=G-WdX8r;X4k34%6A){M zz)}w_jEhL!TtH+F*%v0bF^ABJ5GH&(g07e&Jn++l+Krah^D&b;W3w@XD zkLy=af$8ItkNACzX}a=AQL7H=%|02{N2m%!p8T#5Nwea%g5tZ26_G9a*H9Moct+h* zied}~pRr!2!q#QFsx2N1voBR=p#N)U4T-p}9Q19n^iM&}bgKXGC9C=^Wm13hBK++; zSGXZn<&zO6d>){9v(2##k3}aSZFkY3@t^RN8-63Gi#K7XFmoWowrWU+D@n(-ty7`A zwbAU02b8OgxM1YYWm1o&VO7s&$yntmN}?k#N`Jv3Xp3rZoX?YTF&qBzSR{MY1mRi?moqENH z`+w`TKYs4gGuDOhjt9Ql>>|hwfn8tL$n#<(3O-HUvN3u%A!3D6Xaf=j-6Ez=MG1k$ zDjs+MYDkTP=xg;G9Oy`afi(&n_yy4P$$0iI!G*j79B3q)i7!^6pJ|JJO=WWYgz4K~ zHvW8n_&Fu$iMM|R6e%rNRl})j#A6HIgaN9pxL68L#!w}Sz1_v>qtmn$Evh1ieW1sv z=#Akq;gao-Op9_5q%`|U)p>G6cWrnHUGMI86?4_ySvjp#Q_-iBIQJZcxtj&wGS+{0 z8xMohW9p^Oo;buA|7SrqFxEdN@u%z`Dpu5h;cSE|4x38=-HA+>@67HY!H}j86UG;8 zJZFwAkROv<{@CwR?ZzpCk_*9sq3!>yz2v;py4(?w(MHv%7H<#BiR#4%bf(Ei&nMy` zr*>>m=KsaZ$^OU8YgoFkjDh5m?M%BzkW6=zw_*8Z&5VUX_Pxyasi;H;rpw95R0>33 za?J+ zfZ$T7=Nk50-zR}#>R^m)j14J)vzPdJwpqk+P1J$ z>hH(G8qqwFM@aYj`dcKHMhWEHd{9^o4bsLye=73I*vSNmw43>x6U&>?U{%wjZ^C-p z`FxWyS|3?N1#BKDImD~6nwRgd7bO1Ka0OI=SCvzcsEMMx@Wv?8&Bo#RS`E(91}Zdb zOmHIyo8tNDp9IQc&?FO)@=h#KCzUXeNYvw{bY6coov0=!C%fCZI$}g>=;~^SEFYN@ z*a*>+qG+!m1T4|&8KM-HAS-9a zaM97EREfU+oe>tkF-RDiuMwEyTaa72^RmMRwrEeey1VOT7N7N` zWj^S2`Vn0*kbcCCjDz2rWc^uM5ZhJOl{4a&gwk;$QdmHU=uX}Pk}gBEn3y0nv*iN9 zLckg`qLhS!(A4A6)o8coNYBJ7w{BCQA`t#Skd}UE$u_kHuTK;)C^kAKRsWY)I>3Up zua&;Dyq0|_o~YNl_0ZW*l=oBIzR35DXjnQOvz5OEBHvOlva%WI@1_lUD}C<~ zioQpdIK1evQCkgoPAVZ{Dq?T={VQyhPk8_Q)##x%n%7chbTn^7pqv2M(i3PN#JlbL z(&|BfCf|{lT#KyVRKj~CT_cY@8BNFDT*t9I>l=p%geyDT50PhfDsQp@pkA{$q)XVW zsMA$~JCneT!>v;_g0r(k1JstZuWk4*$0lx=%(as7=qj>I8^XCvykgnIRSB{?VyxfD zv9hzt5`0YCQaiVjnHI4q-rW9#pD^$6m&0#CS^Pkaq?m&kF#Er<4t|gS$2m^IracXF z_?-jr36bBIF^WR%zwT_T^}0ec*e&qH`#kle)X55ICVuYSiuSgATobD6 z78iPlt;n8|)0LqJoKm_eDz+1xyO>Rqf3zZ{pm&CxDtvF}i-W;m>{b+JLCSz}oozBMV5x3ulc+I$8xdqmQ*z*S zVYoeJ7YZc*w7b8btyKjc5#M|Z`{Tw6s#*7bq-GmDXlVKE?hyT~(KgGmcd%kfF2wH5Qo>F|UNN1&Z!g1q;qQ$z!hN z!*(`$R)p!$PLRO`JNyWg6SncHnt^Acr5N~I;A((fJb8^6N|B>0S5QqxPqOmeYYpQ? z)|Z-n!`Brz$9(VhWzKn1<$b0uIndD|$*r_hTP_XnV1Md|u`NY=V(Q(Q4*DNMaX(cZ%JAD+4!5MY z*|hnLe)Ta5os73e+bKVZ1LJuet19T6)3)uRz+9~5tB;qZ|3X?U)2JGmesQ^lZdlU% z$0?}xm%L!8O1cdncd|!7lxXM%p6tELz;DDrk&Td+GnzD|V;gmjQ%uo8liB--2Xmm% z1k~riUZhH)Agm@})2wgHZI3r#MIBWi(cP~Xd^Dv*(26jiduV7%yHchNj33V4=8Z{- z8}W-p1a^bO+vNefpL6eG-79XHbFoj)AGpisWZ&_h#m}49`{0YOz;H%!QU54XxQ>su zzwRL!_R-_&4hI(2z7Gr4tF`rrz<75oh|O1MR$G1(P?nl!qpNjZdIB0~ChXs`)G$%^ zZc9Z^$IG~h{fLq_(F0|~md-gJU{^4(vPy3-S% z3F%(=gy+OVLXE4(%=x9OZ6g)R?${Sxlq@?QAr97A2RiI0B8lXr&?~w6U}?Ur4q;uo zER?{XQvheAg`ajp)|UFu?n0-JheRF=*>;yu;wi3Lk%p!)7DwouBeP%~lyBxBLiFSV zz)m)&7m-M4zEHCwOTePK+vs=Xv)8jPCrf`L|0AE3=kM6j4deA^IWTVNjpI&`DCBb1 zVJu}St2Ge9)eDty+acvr^AKGZCZk4ALjldem4mohykWK~-4YO0KxHxEeHVrL@>4Nq z&Oy8yGCnjW1kk`5ig=yQjjjYaBc)_)U`h~TO0)cq@>3|7T?hN=!OGL19fa6V zJ>!0MJbqPT((RURn@14ZH87UcAJp1#(`fmmH0Gih5 zS8UJT#S7FK#$=M6JiRw?uYs$p!gVvbFd)GU(@78cR0NVx_`HQFNS?bGcM$k78IeDqB&icojWAt3<;;r^50i#7Q^ef6eldIH8H#^p-llaN1G2h|YNIxNB-Kuo&i z#@#IgvfR__dRolqV?c9xd+JVsutchVcjSxd>W3i&CWdkA<+MbF=?&pR#gZ}IfgE}F zxU3~f$7fwxE+@d#yLu!fM*D5eYQOw{x=$Zxo1XAev(@?MsSWAz9n_+{l6dEsgaXa8 zTaRAw`~8=oy~Z+A;nG`{O1spClLLS&XBMyY1Ey(>wi(*JD#4EL?%d5)D&!P&7m!>I3#m=)1m5!wm z3z5k8BVb|?ORVc{2b_L<;Gc@N(o>2>vA^!H>HpCEgUBl}>;AmvJ0)s(w9t(Oq6~)r zemHSE-dc&xRAxo4B#6_B^2S$B7o4@AqBvnAOA`2MSjUPO+L;m)OdFB~jynUV<^2t; z?dyhbl%W{$0CS^i`Rhw6zLwihCLPvbT}>^XJcS(oEB>O2c5DCCw;HS_N$W_i+`|eq z17`nZVADFL-OC`ARx8)IQ2WX#O`$3zV9UJhQK2~&kE$2u`b(AJhgD)|!tqZF^C^_$ zNvm0^+a{$m+lKAYRK~T1eQGHKVjn7GO4?H1B}>sF>+*<99wDZTzw8etHlpjvU%GgL zYO@CozC}(TKadRt{6mI^x-t+w3zVyAPe(1mJsU9pgDN9OE4CQX`VI?|(eBT>s5zM2 z5uW=kgK#VsU!EPJmJvM;1jJD3bw7HVSu!XV3wkKIYFBZ%zG{Me3W}TCt5s^;b8D6eo$vqJ-jfR zGfyyBTpZ{7>e?3J1Df=w6Cixfsz8oJRg%3!aE>r6uvYQA4OrXmcP1B<7t5a5gjk@O zA23?=ccSlyjYk6_;3o8f+Nw~k+M@!o%ci-=s`xvxcI2yUv#!aCEXLTsFrhCH+&xKh zA0ZkkOPLsXhQ+C5AZe_ zA%lUW9<0IwTk1q(-$+mCd;-B+3UH%a1Mhn-Pyp(d`^UFEZu8e3QIM$(vaEjs4AA%^ z$hf*~puVM{`*#S0D2O1EXv$`JLqvFWIQC_~argx!+r&%q7YQ)uk$9SZ?aqn>SpqdD z>KpnqZ0nn!Y)d*i-W6VIT6fZ%Jbto&$_P%&g!)#x0FYQa{iHI{<;x=`n7vu`l(xen!^iAm}W>7>S)~E z3nlAxbyT?A8}8$T$-T8Z?&9iRzt4iDgCT^Zm7S)*Fi`T97rkoIrzBV#>^d_mRAlxa z8JshJ(Sj1Qew8+Mm~+=g4XrtW2#daV^pc)p-;Vz1;`OAQC>>xx=C{bxeqR8^r$f0J zuwZ`!7nN%r9x`2$=3@HQk>A>k1dzi%_H6?U9dcpfKrD48T)>YA@t}yRy=ucH0j{2G za&Tqbbtc)PkvXZ%oPU)a?DNbiMBcY9$ICc;P8=6Skxp_vvU0wXa=b>0kEF?V7%wU+ zTEI{hH9O4vg(HZ9|D-+3_?&IR$`Q};s#MxH$N*6Mghs?4zQo@%5T0Z(3tGbcibk&f{*4iQQEaR8)Iv1huy{{{z#{H zt;45X%BBE}Pj)L59`V%=+g(>LFUClnrx*0Eti^2A)>=>#{vpg<@bJ*)paBmTxL6^$ z&@Q&t@vLB^^C#C>a*hLKgW^gd; zIS8LZfzBjw(p^VvvmUOk#I0_BjA@X=E}|u)48n;`Cr8_63460G-)P$N=yOPfso@Yz z8G>p#=}iv@=H^_UZe5&a$}#kxZy&_FbIH?#yfu1w{O9F=h#9FWQWoQ$U$U#sfd&DS`Zb^5i&d;fR+HhxUX2zp0<&j282cGTm1?zpE%X$6zZt2tYCCPuOCnvD)2hwfXf-Rp9 z7|$i^1{{sZ1U9;$x@Ny#_n|)};~_3pW+{px6K(t#|2dJJ=||yNn>w4sBX~!(wF~{u zbFoBmhHj`)69U(OFA)dj4m|+2h(1m%UgL;nnAHK{o=Ning8bejk7Nhv;neJv8WY5( z(~nUp$VY_r>dlIQxcR51iRVUm{_C1fr=0@xe z+jsnH14X4?MK_iA_dg9Xe)EDTsa}`&UVunjP9|s0TWhv0`xbi(V`HBxqJ(BNt%bO+ zEt3{#qri_@^mvH8=@~*xxYj=gW!rh39BUm@g4C#AD5#T2?=aUW+@;^RJSo1=fW4aQ z+q;xYS1X3(>tY6<+H~TWe#n#ZkSVLAVx2}Y%7U|*Xb#J+ki6Q2s^d>+9hEwjSu z87u2telEFD5(cq2^LkaaGSn*@z_n-wtwe-HG3sDf#SlvE$Vw=n(4CXZ9?7}9LfuB5 zD~tvt>m!;0E0JuYm#?g7>;+D}SBGx3uBCGB+o_+;Jj{)VByfrM7$)NZTYLKPZ5+V#F z-&C1!F-%Ayj54-ez+bw4olGO${=ao0K_Q5KMn-u+&@NsjZcx_J(O=fe|Od>Z_6WvGt!GJCnzO!>drpw({@UmbjbX2&z9 zsXvF!fyUPG+>f4MMDW7G7}1N(Axg;^8S4X(DsV1WnWF+dTygA)Yt&9 z&Q8Ui`1Vb5`lVD>zpe3expliqQ(s3b3fce8s#>%WgHTWR{f6Rv0gMO@ypOB*s6lA6 z&172prYZwCXHvr$bT?D9?V^ymYhi#@kIyx5Guyte$Ul(RJ)`urGIla$jQ6kH0aO1_VtSGQA~Zy`-SgA zNS0i17{Hfosr6aA@#taUp3)pm*sf&eeR!Bufa_6r^qvLcSOvxtqDy93%rBTHuO-0{ z*haD%8Fs9?d-`zJqE{&GVv2$JUd3{5``l~=hG-x?d;S6o)T2W5P{?!QM`7LV$uLKp z%SYbd^z#ShpjL;IRek*_U_n+=6Y9Qn1V{IA;h@?NbNQGrDdgz)LDX%e1q9n3&VDXp z=lVOv1;iNoS6QLXOZvxx!3Ft0s~RbmQ&W>lBoUxdG?z{2>D|IEp4Pbb)Rr~ea_VjS zdv|NFQY9|ef7TLr_rL;oTEP)EU+OdZR_2tRtb2*}mJ8+0mp8>%WI~|_S6*1%mCC&B z(Be#(&hD917H^HQ?Cs798)DWIYv7z2SUnn974tBt^XBCj6r0J?`nD{wFbW}l>cDmq zJhe_#h!=e(LJ#Te@$8qGXZ-SVe{yQ*<1PD6sb?}LeP}fLG9@x*P)+UfxX4$WRoq;{ zBp2d>?Y3LE+$%);cd)r0kT0TrU3UkO(H^I(>3YVYqH3+8W4GXlY%h!x3S1dSJPp|J0e?4AZF+uf6+^ z?MP#0-XPQ}iS}9@-_kIl{p)ZJo>>iC8eN+c^%5cZW2V#bgE4u*gW%90%2wnyGQNyO zrt9@8U9uxrP?z3RHLww~yf*kK;Y_WPV~O2&wu27{=oTh@(U9(A?7dcEkGMK9Ls{#tHH7?EEFhYQ5g_RhkOt}olsEO8bgD*frkJT3tv8^JzE)H&3e zFXj~+2eyo!ZWTwkR{0OI$1P2GO7$(FBHY+R7xd}VhXz`{X-J1mT82NhT47=w6VT^m zhh{#$e$ySV_OZ>DiDsJSsZEt_O~iuDWDltMx^B<$Uxv>bDY}cEfD+z_E}^z={=TkOr~P~d(v2fw zf=}91lY~eWHLb8QAe5^AZDGZUA9v}X;r^_w^9|6%`a(GMsqi!Krs(mpUklbb5y@(l zt0~OT>#N)vh!8mYsvxVyHSzUpLI?}8oCIsHo;H>T?n0oqBi6Tfcd`rpygCNi-4 zv{vE z5c^(6ODl|*66W{Qt!|hn_;TV^^2VBf0j{pI6s;ES+6$ciQ_$)%+R>eD6-xjYv0w^@ zhtQLFDk=*6BB7ILFpeH}D2;XzU_miO9)^280*H+^y$^duKSgelQ8 z>ghEbgFNGaPKQW)}I0lpY7%*4De2KR3%tf)uMzM07K5w0Q3z6JyM88@;Mn9+O9cvv<#?IUW? zWt)@PgK|W|Cr5LUQeV)IwvgPEQCkE~CLX7H8NZ4;pzn0gu*~j@clECvw?~1|bKI`= z-FA+E`B;nJRkDN!;M*vktVhcF&|G!MJVAX+jgxarw~ zND*EW&{MA-nGeluw4-A^9`a{ajT)rH;^1g9S<266I!U83X@)lLenS3`?~Fgj1@LW) za)tBmXz(askO>({iRxORrEmOJS+h;<5DoSiLGEwvesxEYQ2)LbBdNqs zMYJDcRB9r5P|PaZ&e5qod*!z=7kmUS)bmL)*VlMTIM>d%-Ht4g#~||g?lZCBWGJb*FG`U#|b=ukk=*icPesowU(Flv1h%|AG{B&`zsjXaYbw1@SXq>0Q zZMG_tzPi+VN6-GY(d8v!&#j$qR&+9r?P#$v53`)9rDp_4M4rx$R#XQDaR5+?x!6@h z%eu@sV%<`+sNA4HPgv2@09og_`h7t_$T<4-gQFQ5Yf0aYQ+|w~;2+n9`wVwRrIXA(@L54~ikw$b>mivI@Xe5(JcbP2LN?+WbS3O2U}zT-qp8=lJj&eqT~G!rSex8gUae@!=-l57fP6fNzJhIm$Vo`I*fN zqO*o($|I$Onl%jY~@#glk^zm8K+C-0h}VjSmDD&h~rZfBI9*EDthDx`TQ z$S3c`*BgwhZ?PF-g;v2%#_|iXi6d-iBzt!*rJ?;Xs&L=++rHgr2h~OKa;uNc1;2&F z+-Ur1aV1MXV0f{;M~z0O-mp(pJt|?eb%1T3$#09+%I#~Obe4SfsY+r+!f36bLz|=d zF{^sqcI}=-XImClzi&R7AHgfU)cFDv{CHYge}C`m-JuV$YPf&2@%6npL<%p*L~rl# zeKPQ7d%NRUc#{Rw{lf*4s;h0*bQwqR#z(wN${Ia@C zIDoRZw|BdP`nO_lk~LHj21tkU^@=3ePPOz4R`j?3%AzWdHG`bCPx^7{4ML)byQb3q zOCX7Y52~)J7!%2rpUvyb{<&uWhG3m+ZusI(m@XKA-rCt5A1Dv$0jmLxN_Gw(mw!wg z0-Y3{2UnCp4SFfp7a!StUUE;nA?2Q|jBW&9iOBlYnt#i;e#hs)K0`O~P|;8;f!#(w zht03IHe(cjb2iBdgGCd-pK%CpExsrqEeN(bK*(P?@;ygC@*B+px3qpPBhNm-^7X9H z!p3o;ni#wLLWe$zVn{87P4i&_i`!8^UE>tvxI3RddH18R0M2N?+%9M^mJ zBpVMZiNis;7?#wtKT{$gq|ZM$p`759t!E71gUva<#;|SW(;qae<}tA0p)Dr8h;xWi zyDjkL^Xnxnu!stJh79t2-@7R8Ujl=LFB;_ac?}E4$vcR>r78c(V#@Dd3A#>sZ-aLY!ld9(Hx!<;m8q=C8YU92kg zEhv^klgIAFrfYYZi{E6!x24wwKpkFfCusETHsQ{5ydrnoRJSx`xdA?>e+=So3DIPC z2KzU`d*8yWnN*2e{#bFRu??-I>@n}ZzoqfLwjUMcfj5=OX_sDX^p>M)%Em41e5xwr^Og!&>@YUIq|<^QOH(8LPZ;T3)g4E~3=S*`}pg58{<`#ga;njDR|; zC;*zmt(QA@vOpNR?TP?;j;!HG33{| zbd$j@#?Z=Ck(fR}Sj4d>ATau#_iM{~`%m^?$_ptM?}MYudJa#MD4&5W#rNiR7_b~( ztmqMs_J1^cUb~-+-hNw;Vg)Ha_BEeFE_(a6-9K2POBz?rWpA2Dll9@09eqC!fyFtL zdnSH!GQO;LzKOmJhBvdO45D?R`zIIT#vLl(6{k^mDz&(A@#jl3juC(UXbX<)+&XIM z=UpyR1*x)B3825*1-p%J`#Pw-R~Axhs(>RoWTI)(mo3m}=*&zvGf>y+T{7=$YFvEF zec(Z7&b|)k#gk-_ykECC#b5yA1_QW|l~8a>O3MBA_L&GNNU1M7-p1j^KJaC7gG#Dd zX3TA3Hncz6Ouw{s)_j7Lzg>wj&nMSRX+1HUlrLG_x8=u_sBKyPI!!Vf%r&;PSJAe= z%v8Vevrf0qcf{H`Tm-+uicpiSNQhhlQ-xK2g6O}Kg2YIxmVx{l0W6IXND0A>FzeSrz-;AE^qBu&+UpU8*Nsh-ag*$y$P#7 z=B9_bl-0MiUncbk>hImlc$<@sxy52ZN|9S@gGkL{Fkvml-D9#Z z1L(GrV*6S~^|>+8=9M;QuOi7*1A6Y~w7b14*Zuu?lN#c%z<-_~9&QZ&NpM!(%3+^_ z`QTPFor9RxMxg)4+{%iN_eWl|-6l(2ZOvI)1~4nUf-tt&XOEGN_ReQ(X##CNuvDif z#Zz=rk9BtHLhIcjQ}hEdmaqWuhP zGWGY(%p9mGMoMmf^ynMTX<}!48EFbSwX5sbI666s88QT_cenrxTRsEGx_%sx7ORmh zzR3mNCK*6+Yr^c_+$RlU%=MDdKx3(4GueB4Eu#5P|8J~V(L`hje2G}8uDYmY`0ju0 z=6c_=IgpOKC^~2@4c;LL16lHO+ZNXq4%l6FhpHNO-OmQ-_gJ24WCt2-0aNWIeeuwTDRHb^Ut%* zAH}!#NNB00%Z8nmRWd!Kn)rAhyUAhJep{yQgiz)fc3dqi{34^BdT!pPyUC_EmI`tA zaYgE&nJ%+1YD$jcq@*mDYV^MJUvcvp&Bex_#R(I%l#oB_as{&{6Fovy9sf*EI03sY z>AkSs&i>^tEaoo*P5@pw2EIB+r!I3oUjhi8Q3GKnT%JjsUoA?Vasnfq=tiY3Zj*9# zX#clmhX!DVa3bhXwi!4$&tRi4=9xT@?+tHC;_F?TrlN4rFbBL5B_ z4Kv=CFme~{Y<;=9<7GlMEJ~TE-0Yb4tly4vi&t?>`It5&6s|@}(FOS% zn@^$;2)>{X#0nmGoS=aziH*!#1U5`pZdZT+0&A7Sq}=0n?bN2-P+!!^ z?D~cmil9yCghFO)ZY^&ux2i9H&~`C^@oZjeq|;Y?qItc_s*Q91XJAKwn@#Zn%!!G1 zSQoeCKMoa3;3PeyY4~bqRB$!3ap1yhIq$@HTfuE<=>6QiSZ4+ECFcg7c_rtB3|+S2 zAr_I990SBI6GB6AUXL)R)TusKoG%-Jqlvar2uoA zL|QKy2`LE)$$G3_@BwH{r@PEidWfg`-%HDPBvdL`1>LWIa~)H@^5Pju)ynC$OqbxM zYxZTr2~+pkYwod>>pNexe`?(QBuOKap!zWs*50qTy$A^L?VAwIrtK&Cfto)yVpb!k z{$J)3tLpN%(!83f(uGfNuJ&WO{k>1nRCgKc4@2FW>i5g!P9dI0vj0Ni>v;P0lERcm zZaNt*VHG=R6i5b=_;K>SGINyWp}m;IDWd zC)*|QUl2IJA%mrCYH>Wx{lwkj%;)4qWy&B31bz9fd;l(J)UeBF4N*)03S8mtN{XjH!n+H><6@GdIg8fx$(DaeUnQ$kIW;C^cuaIX5<@&kLX|`=J4O ze|@jU>DctZ$?hq_?RxNbDWMJDaj%$v%`KLB6&G{YMD2)gZYJE8MmJk z%Xwt9+~Q#A+CIxunE~d3JVg%NCA*0Hk%37{%c&k!q8wU(wQG{Q9(o+(FJu9tY@f95 zSOu`fb^W)6?hl*n`;YJ=y7Y8)K*>F{ni(JDZ8#=7$TW2 zgFe9Tr9}IM@OSD{w{upt+|)9sp;3)Ed(ugL+cIw8&MX;x_3hA1By)4G!Rd$py49K6 zu4T=krP6pcib4zS@+7TNBdu`;IIw4d{!zfTo67s{X2f_ikyRs^MC;S$D_ftvwfpYW zP6}zMnbmB$Jae|;YZ)Ju*W)D(w8QQoCsNk-!i*Ik5CU#e{~;5`F*Nk;2c2XJ$PiUs z*D?Ion=cE4U&=Oox3CU^*9Agi2fkz6n7PTPr+$_x-i1?c!@0g0`uQ2`pi&X5^5gX~RXW`aUD*A^X5$BMi{wQfq( zQ#PneS*0FOe5GS~?J53h@f;T<%TxG@M^Of~`e`u$d}7YwY}wgsn8g4A*@O4W{~}Q;IOr|(d6K|rB%#RecNSh*|{Ibr^Zo?myozH zF>CabE@z%f%oWvm#4bw@QQWyqhPM;xeJKd(YL{I+w_w8^+W$K&JC&)?TL|h8GTqou zeqxsU2}S4PZ@}suu>G#Y6B=3n7>Wd?{KzG8p(<;gucK_-RUdby?7Ma>f~D@Bw)MZ} ziSM~z-(@MIxs=9P*tvjBRA0ZVDUay>jJ8~ZPX4Ha*>Gh~&wVl11w`TL5_N!h&8EB?T{6Iy#ksz)Dru1%l zAchMap?F6Bq`=#0KTgL6iUi@zShgX9RPh0!wK<@ziu6oNHxC`JQm6X;4Lsj~$0PTh z_%@iO$3}jB#qFmjf97*?e3=jVPt|#&xj(zRx7pLbs(6Vy|C{NNt?+QdAM%bA>dyEy zN6>Il095=D`~TJ0XNLV==X+?sQ2noQ`AKHJ(K2V$XU^|BhGLUAFLRB+(gr7IhiQ41 zIz9{&$r7wvOzu@(Q(-c9EZyYsu`~^*>&JY3+QJok{t>h>CUs|eqR#k-2ue0z@hele zU5sRD*hP45_3^Vv87o=JkY-Mn^qr$DbQeKUNCqsz2eo-u$#OusW;WtQSU{a#alIsv zu_@cF=7R&3`eSJJgXqqC-YfjGA+!*?Ns3X_{&oDQ(`aT`K^XB}zBc=ZLDdmP8?}<7 zDKol_W9&s^-!Icx)+436I|z||c+u1SD4nTkU41~%fI_ZIp4oV6`uiabhVPwe92N_W zrmHLAguct8v1)W;UUtr)9!x9gk@UAd{KzrFVvJTO)A|dzTerJi=T+^y7}xveizwo@ zUy!IR*{tL$+|g~gS+4jq3h&uRDg3>miU2(kiexkN{=OBxcp*L>{?(CVo7GgdNg^^L{-=t`ZpHo_vh=}gbagMDm>@=WaNtj` zQZYlvw$NSM;wac*q{asBC+305$J7U>jeq~>R?4Okn5xR4N-U3DNQoMpRPda(uV*Tx2cM9~|sAS8-E*iP~Sqo;K2A%RjQiM&wx*c$HR%Z>{| zDKsL=+20^!%s{s!GYwsb96ryqf6RDfk0GC%Nh*VRSN)mC_*83AFulx`Dj7XcJ31Gy zcxAn@rE48Cf;c4%feZsmg#oxXvA?pwdRGK7X*|aGla2M>2Yx>i>~=ZQVx=k8{~SUp zOu%TaJA*CrPI9zJZUzbC6F803z^)|aYc)sSXBuK1d2kUpz^^xz!T zzNKC&7)oT$i03#D-J#3Q(Yk4Ur4m2W^aag!6j8KBr+Q4=O@(5h!ZTdD6}{IrjrZ%l zOa!01`>KOZo)%G~hYBvr$>5V+tB<0Ln>u|kg!}xy-(>omp;eJ1jrUqP!Jvkfo7?bI$1b2=o`M4iultF| zKEGNF%^3kogj=ilh*##uj+(aa+oIQH7*`3iP93oN>u&_+GnCa|W4sfU(3caItcP>D zUeJ+J$rM0)@zkYbr@S=AWlV_yD5%WcY`!YcXxMpN~eI*-Q6PH-AFgm-QC^Y-F0ryoW1w={q6h#?>*x< zJdXOzeO+sYaK)_+rjI zzwctbSYfTLtr;2_8RQtzxU;Bs&uf5|*Z*_E5w#r{8@_ZMX9cV@=_eO{BgNGU)4&(mWH7MBhG zzfTg3tpESZ=dn%c{J;Om|9vO_f9^?Ip;qK8zvCYVo-kDl zmbh=~;BS^x|K8LO!B<*42zt{JjLv5<o($FIdVg|JiTH=>xr6w`A zoT;klvu@Ri)aS2Gj|C;~be9|z&jOexycngJL>M%fKYf@%nIWb8Vc!aNBK*Eb>4G%C zO2+1wP^&YhR*w+O3_|%*_AxjU2g-)ZCfrgOX!|FOO?-km!>Cc-^_BZx?T0}+09%Hp zr8Fs~6t2JAirqyIK@*SlZ{z48+l|)DtGBLINfR`>AqlAWM;`m?NU2t)L!y86a#Hn~ z*}ir-MCy@}STE0 zc-?JLj?n&;W@9-#jk+vPSJVzh&qBk*7l~hZoVG*)0v+ym#|!#CUY?%3kS;{XoF+M~ zWvxPQ&m60^BATw8vT!XwT9h$NPwuS{aM{Z=Dl@Gh7flad85GeWn$FhSUJj@7QcIkU zR-3dNtr3gR*i#cS+B_C2;^WbaX2Lq1&sO5B^jTF+(o#~~E<62jt(&LXc_X+Zwxbr5 zKL68M-?xfe8H-CS4GnV&E#^wpL_*8wFLB`^QO+GXySux)SjeQn=o;dp!Rr^e(6&OO z;C;fZma$}pM@D3%rMtU+_H<|S#^ex%4;JOu)s@wui!LA8=O7M(FBvf;80ne|y|^yM z-`;0uXTN2-?PoM@h`&?zHM@?Onwb2==6?;s(h~&dp@ID836=q+hxKc8z1r4mb6<0u zk>l9#bjafO>Qu_1Am$h1;c+?lT(N4rJ70Urfg+UU_DZFn@FmxFXD+5>kV|)cyIT-i zCT=e{@>ZJlqkFj6=m1WQXtd4!&hxzKAUq->M?iss?CxZtQez_1Wy8xQiC(u*E<<{H zp#&owsK}Z7Lax(kFaVd+%NiM!F zP{f0o<=W=lgJ+XgPJEPF!F7XpPCMzq7 z69ok&muUB3Pv2=y?MC10u9@HK$6J&0*|LJb8!HdT!PNkv&tXnTG$wnM=?Lax{>Wap zt^aA@A37>3i=`T}>!Hz6csMvX1Ozq&hnYe-28Fcy^IWk=T#j)`g{X)q7w(MWQK*ZK zDBhS_3RZNfY}Xt=s+Dr>hw~L&0s{Gj_m`{-LxcbCd34CJSWad8UZP&UoG*ojJO!M7 zCa>Fd+r#=NhPUkqhOdp*x-HIUHPh2DI~2ao?N9UCj((~O2s551V;mZldgaBi&=k(Z z<>g}4i0p9w;mO&<1W{0FlinAtH;A+3u18Nd2NF?uL3c%2Zu`AqXi`P;evmC|=e>Cn zA&8&-VFev>jfhU0xVS_@5as0M+b`N*GI80iHRxAfX%)$EH6?_AI@YPT#E7vx3GV7( zqcPJE`l#@I?`7yG*exVFEFk0JX|!VeNdzO0^ZS-LN9HmPVFe@`zEq=}4|msZcf}+;-PDC+d-LilO7xemtE^uM&&g z{rUDtDNlTBfgKy&@VjIji*at=QF^qKzUbK3dOSoZ`)E-VX6*9-=aj;Y1MMmU&{*E< z!7uX}O@STtkxc)z?N<(vV`z1^lk!IAqiHg3ZfA#8k$c{XB!>3q$>)LDfPRsGG{#&2>7-oK{ot!z*~dw7NK<$EDF*gX3d^_g44#GGDn-Lg2s?hXtIbX{s${eXITXJL zLpbsHjYRW;5m3e&)OrKOGdS%?PH*lO^h20>7AxBBmshM?#^}45(VD;LqXzC3zCYcv=s!6^2G(Ia|DC--O)muu!2^sve2W1Qx4|PV-33e6(CoGyiQgSxH&h z|1pkSu6aN8`}X$sDM>W$Gzs~=nTg44r3O;kVvzo`acTh>nPLYpJ0t{&usshlTm-EN zeYRop>u-vZKVZsq#tayN2KgEQg`^(%uHXy60|rTd;ryd!`{&1)y7+v>qRu1gwj}7T zst{PZryF0kSk^jvW8v$z>tUL;7MF{)77pR6q*#a5Av6lJu~fDni&Z#m-}iU-$J012 z_S0;{@$k22h_uDXoz<(WtE;B-^Ye*Cf*sFSpSqw31L^zdd3-?ZvRM{@(!OPx5ETpfSS_8iSJjya5IAy(51Ci@;dpN~ZU5(r+iI}96f>dDiPw^Z40XGOkc72qS zkFxQhmaBYB5=BK#ZEyj&tMUGF%1xMr_b+d7n6$#!95=zuXc#GC`(CheZXY>-_Lxnie?TXvlkDU z^Gl9QPZsFW#kaV6wK zgbmG&Kfb+f^g@dw=s^_A<~6cU2eem@qk<&&`$NMEjPlY-8UEMH(#rN!RyXB5@<^qr z%7qFH(XBPHi|+Rg&l9;_PN(BpLhr{MlK-7&Am^4R6F-0c%n=FEv+Ki%{?(9Q=YkKs z&g=Z4DE=$aBpP=pC$IC9O6QYhve6@XS>D9h*x%rhy**)lVtu(pIO#`W&|aHcA?+XU zFN#So^X*<;{6{K*cu3DB-*L9f^y;5y6!<@Lczd=z-~HBM{3fJ`ZaS4K23)aB9+!%N z9WLNo0RU*N(PrcJ_O|znL}w%m3yVUAG%PrnbGf&e!m`JixuCQ2e4GLz(3mj9l&v~q zFE1ca>~oD0wl2V)kz=|X{C}TVR+-#|_dzsKS!?+-Bfv!1ESF>q4Usd%qSnj5O@;+$ z!E(NcA_hCz+h5Np2(0Cb!4)euBh5D>fo}0QpZY?#o}9M?!+-WquHs%IUMSYe`|2b- zXQ_rnz`IyxQER={%=Tjv1Z6x+04c5GtYJkDj|2G32^jdNK&eQ{O=m3+W6Ycta0{uETg%Xx9~{b6-z2(=qc zfj}U})paAWyyfAe>L$d?&CQL9iYgL^y-Yn1Cv<5_^w zr>Kmj(M7Jy#@lY3f}Z!&-uYUK_Hlf%g`3vW=~C?j0ATvNgYJ&!KFKlAQcKIqf@?#P z1*h_PJv&;<%UgRBD0AT1SvGYulsFmxsjQfIqN|&dYewV)P zfLMHs^kG>{VngUbw>!PvJU=@@I$t}anLu&~0r%{3FLz&c``CfJ@COev>Y1u1D<1mT zZP58?5h}R2(t{)bujTsj_8@X$NNLPCTdw^V`T^Iz<>kDkvgMpRX(VWH5l&9i%?j<% zW#tSga*s_vC<8&{I0fFTUbY1thl{p{ZfQ7JIC6!|)k3+n0Rj)%&7cJ=TFoZ=z1j)> zl?E$qQc)|C?jF9JoWBU|@$zqn7M>wNW2I(i$7Eg{Crt385kdj3YcPHN*w3;^DaC)l zASB#o1@ez*w_3BY=ABlkr&3s@)x*iloewtZ?4}gMdn|b0VE;uh0xl6-US1wP zB2+MFKX=uSrJ4mjk29e8_~VFjp324MC(>#2f4tt@2duF}B6!v)WbwPKyHT9Nasgnu zS$?hgmjC-M?PXtIpLa(GPz#J>C_NJCoOWOZs=w-Rt^ed~;Jd(k?|&8zkcxwd^}-2& zMDYJ52Cn+aZ_wd#vkQPE;!V&(e@x2-Y%2bv&#cjlGj-l?&wB?4F2}P{b?X9w`c-4V zv9J4lywN8`pyz#xRf)jleOP}msC6!9>q0*oqdFefT@e=$a9(N1kPrD3&$YFgQ&u*5 zQqiIpPll|cZ}Ak4K_lprmz#@-$LYJeTxX$Ds!ms>KSfeHS!__^us?dVSe^HV0R!Hz z@f+YB$dek)7BTr>9(LnCrLkMx1NA*MV~6#-OwRfP-#lh4g@u{9qIEm`_LlY1xehwD z*&|915T|t1RSC#n{iF_4ElW)Gy{|Jn7{};tgyymmv^U{OGAdio3Rf=J#2UN8{D)xF zZ?h7z2di3JTeGu4Xnd_8HGcy<0ys?zi{JQY#Ecl4N}isrR&xz|Ciw+l7@4WV&wY!& zC!=GeY%?g3OHpJ+Q~1}^)cAK11!=l`2uldBic5%@nwe6C`*Vg$!GIGm&$Yvb)1e2p zrKF@(IkZ?migE7!Czcrqsm-x{pZ9H9j-N(6oy-vd_{)5y{>8%!%6JMY#bCO*-b|@P zy?Z^pe6+0mLDTAO9bZd($4vzfgb>&gY5Na>aH$R6UD1GweZ^nASqUjkc01yyV5iDN zoELv~e$^g~<8!+r`}KNIu@mBAd7RZRELX0J$;P(>gd=qE{%l2MjMn*$rfxnld(q=& zjKgO2F+*%C%*gm?DMCsycm&RabJ=LLSCG}8r~T!6G=@)!fNJ)L^1*!~KQl?^oPEva z&wJu~I(Du@ccl)*8@}KXBXJAjWJL%PS!e#4t)xoj!U}L{QlldnDP;T;6A}O@tgpe= z+eLm%2n}xF!Dcy6ipB;%<=(a!^%!tx{4Zj8-D16uL>F3_xoLkQeM&0oo+%Ow=Zg+9|WFs?EUUqv|iEili-vU^_r&Q1tw z+Lcr=*V9w_>RiY&t5T^J)$YP?0!zP!o^yHVROgck4#9dNLInWJulGyL;9clBbV@X3 ztL`V|wPq8AHZ)pSPzX46UN6onMY`d+ot!9EoxY#|HYsd5pwmQQ@c*y#1%H4!s&J_J zELHGXL?m*Lc%_5(QN_H&L%uCITd}(XudP||VoLULYjgByX5`blZ_Z#VJT)A_N{$HB zGi`VR2KH%A0Mxg!R5exAKqvDlpr4GVuuzaNqk43C92p%mY&KTuBJY2KLe%kjyE8R4 z4Yk3Z*A2vcPa-`ej6H%+LWuS$ajJlzDF|vh(eNyLgf)dR>wNm;-o$`SfJuL8)_G8r zot4h?Gz0QRB{i)9@YtnqS!>QG<%B-3R}zF?bpV6^T5l;78p~avP(Dc$f&9nmWFD9f zr*R4by3LM9+BR)_SFVZ<+#V)#qjhzx|EWYixVaU@Qr{+8uL+X04vRN5zfTXEFDcTD z-|c1b_&h@wO}X56$*IiD=;H}&30qp0Cep1mTCCNG!DUUjY;_0q_KNZl9`=lmjsn~y zlgptH-~a{<2NPKe^78jjZ`ob>0!Paegu+r%LjcdZf*XhT*F||2fC8vbO(%3=-}|R4 zn5StIeaIF4fU_GX+YC= z|1Fb5f5zh|DJkho6`m_8ZbY^F_VUp2w4b)1>#`P#@&&obEdq0;(T0J6p>hyn&gePr zUoJBdEay|+*Gwex{gG|7`}zh>U}yMt8BJn7^`+ z)}B0K@vZ#B1O-@#PTle0==W#HkFCcyC&W*x| zN`s3?47i0a>QBp}({DIw8H-x~FnB1fV9coL7!`2nhnI>46t---FlF5SW%ycA?u^SM=08Jz$I9NV~8A3e-HNn6ZxU*D4LlXiYp5>{x{l~@< zQS_cWk=#zlyaHxF)e6EN_NJS4yM}}Qxh;NM5B`!>Lt)6)h1MM-iH>;|@#kF0&6ZZ0 zMVM;VZGH}%oIV!IX)?FFWyPS4xObM5Ei4f4heO6TtxZ+h1LH{ikJ&^rplZ68$E8wI zQVRS}CP2$Nl#aFlss(bkQLEN0ivRg=x&C_x00TWP+8T`qeo;2~uPy65BqixfC@F2# z{hon^izxeXIMw`N6WhU%4E`1YW@a3XGPNh{*WP1vT=KD5flubfRhZM1F7G$q04-kz z-Ac;Ssz<1ro5sIpfwU6we1`;ToK;~(QiQ+KDB=&mn|k0yEwIX|p<@%P9s=S94(kuf z>4os0fHHHPX4BquGtOhvdL=$PesDLQ$+vQHCmf?*{uSe{Y%t-!cQXM=St_WnTD@*P z0@rMiytG6GCtx2W#)|h?g@;CE{=R*eCeyx-Ieid*c~Z%&TeBJ6y0@N0E)Q+jB>ocz z0|le&bN_w$3jfP#ZD~d8_4>4di|3Z%mUSbPGl(CTcH66GwTh%O4hVLQzsM#mAb4MObNnLU<9}|7kxOG^ zLSW&e^Xk7n0u%&>pSTw=FvNOv(1hNXT>zU2LBLfncXz5XlAAFbPybASay77l4etNr z@EKs6Z-A~mU9jTQPlgNh)#hv^$-;aGamFuqw@54OQt6n-b_=B%6ZqTCgEba7(u#iX zc_BGmh-O6U?e>^vj~-EU_El;HM6t0!k#Z@#Tnr30+r41`BoYPmuRuW5Vz-<%U%cF^ zp%p14c?a5jwmd-KurTl=Rns`Eo)7b)Dw_6FLkPUF(~7aT7oS-Ek>nU(hlmi%XtKwf z2Wk9~Rm11K)2g3GxLr2TozK)-(R23>2(msJlrhVg>;jcos5cqesCGN2RAdBRZr@)Z zZ`*z|FkG(tx(w$JEoo`7?2rD|DkZl^7h_^$a{{Uuphqn)nI3u>0w2I+narj8+8~;8 zOP{+@fYVh+tS=OWAfg~8hkv_Eq^4GG>+$iy`Ty3<&IC@}WL8N>-6lZZ3ilm21B*i$ z8%M%o=%M{lp_79NpdsJ7vPX{MO+u`3((kHF#ppkXsr!mDK1mPkLlJsbdA;2GeS&hn zSjTS}mX@KAP2RL`0`L_k8k$HoLeIqmPlmjvF~I6#WW>$LZ!Ht3)iMcL`gg8u=hN(! z3|r9u$nrVS-{-uel&^#u zwD`NFE^wstYc*QLP34Khkr!DmOAvbh`F>DAK}fimCxJ9J9Z1wuP*4C&U@t&OQLof% z1EelMT3Vm!5J;vgzP>P9yT|wU%`M&;h^*DCcu{Bqhhrwk2F@%gE9(gqr^nqf z8$eXE*_F0mpKhY?c_8bT%G?}OQJ)=F?$5Zmxc-tQc;$G~!6_+*HdR$sRzS&ecRC?K z{2}|8Q3?G&knoeq6@qh>m71E`9AOB*bwVpCxn^rA%Q@Coy{rOUDeiZa#ii}W>}-SM+231R zTgLsr5a19n#IArws@3kvmA|j+vLWZR`3I1uv{=5eTTGiAPUgrLsi@5XMua1vk3Veq ze5h&YiU}tZ$kuyy6P98AhtU{7;^SEGTB(w|YDV|664SZVc4A%%8qVD0*%dP7^{=Zx z<4oVCNIZoy2GAQ^%Oq9uN4ssEf6F{vEKjTWoboy4W`7(34vCP>9^I9}wbT%2B#Dj( zP*X*a_-28dd&JOjdgm??iKEu2$JZh%vLF-{=JgR$mBMZyuvS=t16GdZ`>xVSdicR5 zS*R6JZ%8GHGlZQMywAX}RDGpAHA{*jJWfkZ?ca|E!QXq9NIG?7Z%}60?DsgC!${zV zb$XkWDVVeB%@RF{8R?znGsSa3AmHsen#=@%)S#GjdFfOR8$DUsQ9zc|m2dvMcyQMa z$hH7nV312i$0D47>jnxAklbgBmGV%&h)+@o67!euxnNWL_lgQY#@MnE!p>vGNg;n& z5{>n;TA;|P&@9*1ZjRhdwJi^NK5RoQTxO4uyYN?C1_#2BKlB|l%zNHpNM2aEtO`}CZ;i(0<_^V?57qFRjVA95ME%9; z8Qe}dye6TfQrUHzjYN%)^&36Hw2k&pV%g5khUS`_Dp;;JXTaEfdP6MMRa2WH4b_qa zlbL?M00IIZ4hD-ml$t$}2WkjA$_uQ0v!5g$F1YM&vt{=A=!yhnSU2)u zt5#{9(`g_ygYwOyN#_vLGt0ho?_7YD;Ut3Q@dJ`AAW7kJSo2!mnrn~J>$SQ9A|;Z* zwIt9&596bVPJwfe(EbX$SnY_N=$k>uf;TJ zNDrtw{2tf$`yWL;LKhrQ8Lx@TTBND;S=MU}fYhK@@ACSo3n*QtAAa97BVZzOPu>ej zv6r;4+I4T5B=+TWVIJGUH!gzZ{^;DcYx_OCc!`OL?d|PFN5~g_AtxVZRaJwTbW&|5 z2HiK^d&&B=^koG=tX;h1vdPFeIN_@e)@#oI`T%SX<4cx_#S&%;9zfAuVq#*-%ko)2 zaul|z0GKH-s~b1GU-%wY1HKaDc%Sk9Yu01G!(XNgMd?GjWtbF!u1Te;va9xJXjc7j zTN;03Bk0(eDvzMPTz;CpVc8FoGzysd6qL#oP8$*YI2S&LJMZ=KxD(}avW{QY05sp% z$E!iCRt{=r<%L6%695)KS&NJucHET5` zM#})d>=H||f&%hhN(KNZNycibs%|<;(I?ej_l{mLB1&7NUbMd5cLhKJg?a>F=N#YD z(^H`RyYprO7l*xf$B#A04zTr-etzo>eZD*X-0ZzSngS3O0Ik^!Mt32Gd`bxPV#fG4 z+I2|*Had;$hNc|5fLBOwng08V+s6JYku4GNL*8Dsu1Ej6y{=-cYo&n0P|@?!sb!SF zXrt938aVV^oW!pV_KSLYzGi{j!!N}0N!xI(jplYnM%#ekwNhvCX*>KiE;e?5B5k4B z>7*#r{WyZ5{Sh$6p6^av95&hwTC=-08wJIz-bEIBu~T>-P8}%w5TDvo-r9iMr4LI! zag=L-w^~cbz``}VGl@?4tvKC6R8%xH7uq63Nt)xtsMj8^mw*qAT1Ko7qPb91A}Gjx z6@v@3L+ee5Ufl>#t^qB>4v({c z05o~e-57~O7-k_#D*8-dSh=}9$uP7z0v8>CHbnr{{38AnZEC#ED=wekR*&kwlcg8d00a10efW0n$ko{R;D$ ze&=}le^d_1pMz^?6MTD|WG#rs7xTo(&25?D1U8Pv647mRDw}#@WVm|Ag3!A-L}Gz} zU-Kq#u$dAfvf!fKhjr_+YU;}|n+0@us^|0SNo5-W3JMp{oL&&fv)c(7bekOx~$iX-1L5yKPu?WVL1pE}eo^HXaW-L*7MFQAt#Zk#+1S+SL!~D*8Rp5Ig`>4WYkR z)H3+^;pOZqvMlD6qx)B-Hj*A-;`cCGF8mJY1bP8rYbEJPv)bqPYzf-!nVPB;$-+Pe zIJS7IqQ`o57!UAVw9WwUjv~`l*k95t^*`mP;}f!+5R?z58i6vpb~7pXb^BWC+ui+R zT4iM0xuyL6-FED)3;*=%df}H$=lNo5Y;F?kr}GxmEc!EtH@3I);{n{@eWZ5oZ|6a$ zqe{jDvn9IP$YN`Z&gaW_T`w2=x?-*QbH~Hegp41&C;!G~ zR{#rh&AY9cj|V_|H9+9Qb2O`sT{vFmF{rNJ0v zVu>!T8*%S_dqF!C62-I>BQ*#Y6d9qmD#_PUDp8U#W z6yKB^V&(U~$*|IHSiKn(S-5Lk@(z=7R-gZQG*hZp3NX-OfQbiSKOD^*jJKSF?bO?x zmr}kx^ymO$a+1EcSjrm|2kpC!KY$Ck4M?L+9b2sWFfs8Xq~N|?f~^f$AE%?p%5b^e z_in|$wuV;OCe6?RpF4d&G$hX4-X@Xi?P3;{VwKZN)J?5`NC3!BHazi1HpW}Kuc2np zqN!ThJ3JBR*$kI&{TM#4?Ir+9j_2!XbVuV!vw4Q;iHgpBL+26d2 zbuAIs?)7yIK%s%8fxL&?*T_^h;^Y`CuaAGP6d*5w#VhY|Hfzk~j@}}t)|=Tvs>2KI zxdw2^B`l2PZkIJ(w8+)=M~C$N;T%_lW%s&x^Yoek=!_Y@0H z{_Kd{&fUKkKEd4R56{6h?*S|cfZr=1jcM_eZ}`wBgSX*zQodYm6M2a@8hMf^vVh}X z&nR9yD6^M8$=>acfMH=^;Ht_NQA&YbI7`>rq9^MRS7!A+)g&dKHnC*yn%UGx!cT z#dJr*KGOLgR0^+5ZqXXBj1Z^n2vT>2K9?3#DZ4mP>t{a}R(J6%-It#h)>Xdr>|_xT z^@>8Ln-o89yI@kBay`!O1aLc_{=o4RvhL~~ibH7RHQRoCEH>|AWRuedWOX2Xm+874 zW;T}A!Tb%e?hwda?QHKr_&%14RfL)7>v-c*s}@`A9~>xTFtZ6TMCp~jq{V$81;7N4 zfc|7XHrIAt)^ZirN_2GepMa$c*pxYwpI(q!fuI9G8$NS87H8o8N2s#EhVmg8 z!R5d3%kHKuh)p3Qj9VP1qchH(K}~l>$zr=QOTTa^i_wECmH+Q9qg12lJkq&kdrR z7SFwfAbI_{%t&+BoB25RAeFj@0&_SRmy?t8a^4*zmrIMS*?j`)1@JNIfzKb-JuZN( zL4(c4J0Kb5kRR$OB<2^hdvG8CXp;5c7sO2lH~)&Z zz<5I9yHx~oH8D1ZN>d{<`r^v~85Na~VEHe5fBCJ;{j8iSxsW(HwG-D7t4z>n7Q|;y zu7}l?B{|XCtg9u)&hC!T%@+<~NA=4=8p8V63yF36w1d?|Hn!2VvbW*-PbsvWT;pJV zf#ogxqtyE|j*T+Cwq~1+_P-)ZaoO8_9F6{nO(lyeCyFEx<{;Y`O8m z{h5ZLz(AiNV@QScgiS0{E8^ZAhhy>3@XJx6i+rK|iGnyq(&e$7mB!}>-xIpzn&+FD zHUXvQp2r4o9$=qfr=Ee~1(?zgifIcv9&|>>!FE9MpmE)^7BF&=1YQ|yM9BbX>2kd* zMGBXUSg9I(h^QS^i{08@5%7kEH6=yb6d0ZB^k(*R)7WLn79G ziJ$!-j~055u*j!(Ul1*rm8#&9yGe4?t60*Jnw~RQ6o@75^98jv;*n;vK+ZMnZOPmc z90Z#autNrYa59fh2H9;OyL$@-21J2FBcddjULGz&NP?C!tYt5lVMK7TIwQlw{^LI* zBGOnbl#>hCKXq-^SPUAFL z5_pY8RT$*0ke4!Ci-|TGKmWnaTNmJre}?X{Ea}zYPPx-xmaan)=}I;> z^b<&DP82*`!eYHE`a3~0@9D(W4bA(vdZ6^Z&g#{5c?4KYlHu8kDQ#Nc-2pnb6D6?T z?&U!(ge;%Vd9_?x$!@*+*c9_6$@}%HKN2@b%%*7%Gq>RuHFqN~wo@MAWL!c`O-Mxp zxYvN(gE~u8@H0sd47jIo24eTZ-<%F>$ZxT}l^p&4hIqR4RWG%ON+>1Hm}EPb#CTX{ z#0{{oOoRkUbz=b`0fmrIAvWq4)`cUdba;fA-z^1moNL#fW6vVvJeyp>6@uY?X#n2! zX$YaWE0EB%ZhzVbxP}nk^P9K%$nNg$L6#4JWZ3f+6bBM>Qlklfw10aZ2#vVh=DeL zW8#1HW&Pd?s!m&4;!V%;cBW82SOqx&zbleQCN`%1VYPmbe@@dZy5?C*9e4z(ublWX z{Cdcn!GW&m zVt)NW`z4e&8Znufh)kbxae>sHW>EkEsBXRG+}}Ww#NUGkO|(b_OvAtKE#N2s%{JT! zKpr(FFo86(jR1|iZO}WRX#-&nELd`%SZ_sdn5`=y@&?uP0R9pqcAZExcnA932b4*W zGBrCr=&`c};vg~;kd+5Y!JGX(3oQN{gLw~`_WV}8@S%=~srg=NWJFp*mnOBHg~8tS z&7VIP1Lgu1Z?I)0Z>(m0^JK(W0rVAmt7VdwAB~CO(K2zbFV~gYfifcRUQbxBBkRL^ z)4Bo`Q{rUiD}l##jIU(^CRg+N9%ln`U+LegeP}g_v5eoob0!Yk(k7KH2?&Hl*wMe2 z3-+0rQYI39yyH;ksf-eGoPNxMo6}*XUGCiXMMp&7drA!!028t;xr+G^%T6lLC+u-2 zbC_-UaY2sfr!CXv_C~~?KXym@CEI=3K2~4)p6v2+i81Me->|(c2FY+ce1~pj#7KmjYq5kTmN+&le)scF0b&_%xzk`C}#BJC_5aP4r_BfJIjtqT{ z;-haSA=90e+d6Z>!sB-`U!455%wYlg=0^P1{i<=$*W3FOhi`e$d1l9|5MYNF{_}`9 zti|#f+yFHNJcB+v07ULsk;s@lK6LSK@*dng0X|MbYN{pLzKl4@CqJpl5wK@)xL^V= zRgKPKQizfa&elfGhce8|AxHLpM@}+%^l)hzlMq_iT#IDONn6g<%UHw^5j9pJU+{uI zeFbDC@`R>#gQ&AD-FPq|7(l^W=0*faSd(UJ|*1H!T6Ym zDSaT>b;zp-XDo=v!>QLxc_VVDdRnv6SDowU?{L9LxcrYPT@$~sug0EjvI~BztAmwc z=QCMA#8k_tq8a)YelKaZ>>IXO@G(wfgwdlh>%8#Ux#RdnPCmVmcR9g`ii)a-&EkBx zNh}fqpTcW#y~OhEH@ovV7R_r>=d(F8Gi!OJ+7V}aF`5@>V!N7HM)sr|1MMvDNfg_G z7S$=l2`hP-d4fkwR|jpVC0T=Xy%1A55lvV|SVnrT+Wtped3f7=R}K`$ke{EJn(8Az)JM)d%RzVy z_uR$GBH+mW{4sbNux;U_!E-9KJmH4wscYA?`X)xE8{2Eii#eNdoo8qg1XRvqg9$Do zW({7A(g;RRYgL2}i~k_*OrfcOiEtvu(!P4k{MXBga5WSIiQ12^pC^?+e~!R+wHWMR zNFvYgD+#L4Gh%qx!|6h-T)o>dn#1(&wg!Lw?52lLpeaUFC<*K5(+{r`gOib+dzT!{ zN@HdEKG=ON&>%p3&|?9KX}_PWdu9*@T3`%!T7^q^(z#h2lQ+-3_ zpRlO+#uSo84_&0I&U}mQW^GA^56_LvK2`;pjj^$wO|AU>BQ|?pldX{}w$LI>;@96b zpIu{&4p5)X$u5!g8hguXw%u!c`;LvPHwl@UY{=O$C2)+0F1dtp7gf$S3PoP>qLxsivv3){DNWavu$KzuclbzzWaYng*t2_7I zW8khyJi)ZKnDc3FVQzbyTS0)F?MG)AN$+~YSXz?T^V1l|n)3=>?bwaH64q>-rqHfc>0Ps?7ULFdXpG+d{5+Ei5 zsgbV@Kf(e5dp;Bm6_wd-7@dMIN_v5gN~C9SXvocGYP;IF-+H}O3n3O+9MP7LLLpNJ zP~iiwc7SX*VY#?$U{O&~7C`e-ODnx!s|SF68usg^14If^O@5gB-=*RHYJccl1-}ZR zrVH@F`lR`fEgiItYwd54xjB)w2R?d0nWZT^CZS->;&9vhr7C z;qqV8s|&v-o=>l2Y6<5wjpwM{hA1Q1qY1 z;ku#52@Pe1%ci$96J_5g*cC>MiRAl?_P$fpz^Bch+KT3Vn7lAr z+JC7VV78)F|J)!#^bzcsuoRm|PDroWq&-D7X^H43TxJJEOn{f)6+-|5L_{LoXReF_3j&MJyX=ozc#d;n$0UhOWsv|B!{aK4wobQix@Pv^Jco- z?;N`5jzSY-BPp!jM&&qnz>4IKvxlm#?$y(^94^O(*8< z8x^1!(q=P-_|aaGlf$;P@=|Pd-iKZyccBaG5HCXUIJT@IhQwuF#_xdu`va8H$vlU2 z{EQl6LV{Jm(^@vVW9Pw}d3nh=%6*Q^!3+dA55z!~4&A9SpmdB7Fb%f+DG8({eVKpE z6plsbh-@Jlm;w8+z%eVCBD#*rZXCX&F%o(#V2#+ zGHx?!+K3n;_9cm^Wnb&5OCpg^MKe&&A6}FwyQ?i$(n+O&4Ka_qISoL4YzMXg+y^(i z09v?GW%$W5=yAjI24SAcfj|yra~~P48=ETT)9h~wT3Ubxw@?OykO}7#`11nU-{nW; zS^|F0$3-l?KU@8{l`ZejTVKR?_x6DOJTNh$ECHn;BX1NZk-$^1PrlLF46Q~vM>;uZ zu%to-u%BwPwhBlOGa}GvV`GR#W~;7nu*kjj1ZVoxLwBQYTK9ARiBk#;Z0K9<{d(yQeUKyOPWHVT`QO zkWPHP=bsHtq|q$Ng)A^FN)Npk>_4=o?A!}Yt86fr7M{JY@#8(ez}fhBX<0_y2Z^m~ zbrO!`=gItErzrk-j(*)|JRoJLQ&)AGpz#txX7#_?FrZG%%PMAU#7wDaV20#+A&q~Q z1Rtt$CfFE}cZc_7l#x24QI;pbG-I$;_gGXP2fLTdo;m)h)~FXgeHZ7C9STEnOoSE>)?iRW`nLae;4XE^@O3E#r0tO!np4ZN&YUS#i(p0HMg*}P*)Tj0RpN_sUS*> z*Qla(%acS{p~tDbdkRCM0dcHT_Gz-a19q0*15fd8Bzpm1=H=*LNAD!1@T`Cd430^{K?PVoRw59?Gs|*=6%P>JDC+U6 z5v0=3WJjoT29j9O?UQZQc6OQ+nXe-kO|NHyB=K7tmr3kDKMcTPVP=Cpat?e7Oy4Hvdl?0+Kfde zke}dtyJhjRX@Y1nRL+kRPsU&^2UfTzcyD9@v0t(ItO_|)e>wmEq39fg>*~TV+Bl7E z+ew4Qwr!`eZ5xf**tl^Tn~kl;Xlxtb`Tpn58*T;EK5xG#0x?Qug9i2w%^ zGptueiICAE8nb5_CLNmyD_pPcG~OpoX6CxMZC#BeY#`2Zs>zk|fXslBL&Swe|A3ss zbW$u5LWN}Q@UQ}&DHtsocrD0zVy(2b!fvZ(M^+GrLfEw&$W@VtvLhS_X9`&_tk|JosK?f?LZK|2P_hgAnBnnGJ&IGWsh0XGX4Cp5600Hqwk~Cz%9HF}WjRnH z&}&<1mC&XM=TEQdyOU+bp)!jbf*S|cUESj7_mzIQXcw)L`OO&klTh$-I4N^B)V&ye zjmj%kCK|I~9TR9b)pW!YP7FER)ru-88?5Vw;J|1>AeO>B5LSr41JHlC;R>Yy7CVM^ zN=mxw46; zbsnwQYt#upiZYf~1QMJ#NjxIN!h0*hO^HqGf6}fw`=qr9U29Qe{&c(fhOJnly;ums zLAv=xvs!Sg5Su=08AtzbL2q7@fiAmu9PhHRvzTM!3W>)4h*hQ47OWIaT7da-yI*wn-DyT&ppocwk>in@Hcv zEnVrnBjOm{O5K#s;BzteRrBU}N?FGUNSDAQE(1f=i8MN-N3g8ucMZL@xK$+twZ5Uk ztBZ(492#SaN6xtgJ{#gGo-fP~2rdqlH9!(~o9g`vLayc~+7bXyplK zpguO#z-UzJ+;=^0<#7gdubo2|6oMi858YO;HG-*%BPB8Xk4PWh3Kx-mrCA3K3N3bP z5`Mk60GjFZuwpTt%MV`=GXhY5dH~KTl7Q$8@mew`e+x`+0Ch&wdy`;s1FfE|o-J^4 z=ru&8T*t*b{Cc07zTo*HT;Rl}pOW&M7W<&*9KnTyh(iq_evX1RpI%n*#c2Fsa+?29 z?{uj;QC-8FYJm#l{tlOofE8h?xU5~H7Wx%R(r&Yp8^=Lgdj&vF)QTh!7ht46xRktT z9tH=CG+;j5kl#PKErnR#(uJYnlbiT@oNoRWWZzL}tKGUZ5Tf}xil3`5CaESyK_Kd6PS%9hB|A`$Uu|TI&GF9E{L{-)CeA#l9Ho7%BIF2$0(3y1uEuRu{TVqtA zy1M{SSQtEZv*oM_!0H1wmp`F=X5+`bjc0~J>KLAd(XuIg4zCz=n>U8A!q>23;Jo0V zJ0S1Ez``;BK#0h|$%DyEU~>Eq2-{ywkLN~{sXc%~{-|)sh->vzq-x@vHR^lQgVNWu z@Rl`c%2iaza{ci>2A72`A`kw4r9mrhMwfELwd=t;cGt}29d>lrl03; zY1mhB8^pkTSoFKHc(rQ2KjV)jR*{$z2e`ZfcqvWQOqX&7GHS?fK^{HUE|L@?m>C`& z@{rlg5W9_i(dc}Ve!_=VZwkXGeL01W6;_LRz*sD&*eD8NJETgIO77#r+^8aB-gn>8 zMma;=V~ch#aSS1XNO3K>-u9pQU%{;--l{u)eksFtv8D~BM{brhYef{Gr8e6QA4=|d zb=*mtb{UVMm~;iDK=J>Q6W1LkU@RG%m1Dp=`j&Jqnzri z@mP52H(@cfT__w}aD9=+8nV@wbp`W87={Ii5p5Q67L2{BOe&`gw6nKV~8k4gnW zLPB5ZfT1B|KRnk)&08>d0LzyyY&;^66=;0_##2N_mQ*>0L`dHrR^$V?e&?^U=v!+3 z^ubV8E=E+z#rX^`J;wj;+W}NtJ1*K!|76+s6PdEU@23M%3*ajd+3>!nNwZ=yYzA(v z@<8Fsa+ygVg_@c9vLxL=tSt2OB9i| z+btHuzzS&5{rK}Uh-=WGmDu$ERxhA=f)-(CXE;lgBog*f{yRiw>0h5rF1p%nxtQwq zzuXSUPm!!M&HUTjYu2Z3X&8Ov^hy=moUtnkY0Z>THAl6s&s2N z=l>I57u^wp5^jahs*HK876SdfB#Pjs0C#~5JEbhJB7;g9fzw+zsbtcXqUA1&vbxn| zAV5x@pMcM2EKkF}{4Re%+|43~Ns^tXo6Azk1}yX78<@~;|NwmLbDH+){5Ro`f2I3mdlukS1w)RRtRyg;C+kD!AVm=<-f+%knfEX_QK z@Gsg0_v^%NQ$AY#~e>=GU8I|@xMq{AX zS&DHA>sp3fc+WE|g{&u{kpG*;??piPg!s~e47+|k_Y-@$o7;6BKcqVgW*AJi;t{z2z$}d|uBcF4H zOh*lQEG+VuM;_HZ{6Qp3E2vHcHBDze0n=P00te+zujtNld;Qyef0R%u@_nMTv5wQ| zdm*^6C-vw}*GQ%>YSXti28V+*MFYJS$AeNzZ1871-*Tb33nTln)hhDSIb^~K!SlmJ zj6$5SB=?dIh3$)@2XvjH=l&C#2|_Iz@Mqc+xg$sXm zNvM)0jq+9Y^Zb>_vOMGi|D0|Mzk}SImEm#uA*|07gn85j+_7Tt&-Px+hDB`4tan*q ztu~5cvh}o>2b?;hGe~xMpUh*|-WTQ!6p zsq496=-<;+A)PNf4{#zQgVJO%7Rd@s*}T7{H=tXP{4|`x9feD-ZrwI7k%u=O?ItFd zX_2I{@6IM}Yvltd8Q3p|u!jq%%GWe|GdTd!-T)vMibGKT3=R(d#bzP$rRQolCIX4* z?Fwijx}Dq&qASi+s#n2ckH7N^wdCLY!o>x&Uw5zX-?_U&3t8Xjftp+`M6=vsESIRJ zY_oq0-O=Q7NZ*Y~9`vDjGF+P{!iy0LY|O)}uR<9c8Cn17ZJM{NacM#k&iqvs(kbpN zVB9)Vj9?f=qHQ73%QOs3gMhxc-!8H3mXF7JsY<*2ZErOBbg|YDb#!W95xf*f zfA_6HnFO+1pvB^)CFc7ff%JR~cp+(2LkzksqM?Y@Sc6LkQo1>hZ;E=0gKqI!Nh zMv_SJ%1rw`+!+jG$ssr6PIxIAVFPr;q7~g1-vV6(VD$_- zVYr6r!R=MJ3aY8nf^(wrpz>raC~VYkg27Tkhm-LVQr=CBWt$M zlZqSY4K`Vmv{G9W=(MX+dOyoBeHST3@6>Sdy?n4JLY2qhW^K`t@X^tB+9EGkj(OLU z@OuywtR$kXm&?^P5h z)_OvR`35nth06jZy`wk7nw_-IJaHh~&^lLTq@1ggMo1&DKe?I|@YWPkNp0_Ys3aY& z*tnSw9ubn_iukh_{Vu_*F4KsXQYCyz^80%-6Ein^>0fz2X z4vU`mPc+%EuK6&5D#&95Tm*tRq>r?!O@Se3GqL?h3=->bSx!-eDPijVgao3>1uprZ zCGnN3`{H7D-0oG9Y38{i$UP=0gW36AI4?9&N@>a81ipMGba$atsK}9eZ^HGi=`m7| z>&{S_9zP6rTPVM-%_Ccv#+%G7O4JCer81#5)%*mlO`yjJz(!{i&m(NKfmwt}Ic^ry z?2NHk(9$6JueTeDvXC^-ptULy=AtxVF~*12P+f+ZroECan|XP(UVpiVmr^)ve}H*?{p zlzoB(h6L7);w)+iXrhDbRoghm-M!b6pZQc=DA~J3Y~TwwpR|8}!qad21Kq?|K;i_P zZI;TF$(1xr$o>x9Zr5a%2HAP@5eWV zjcc65+6)PP)G4|ag+PEVC&Owja%6oj+7f}Pp|Dd~QqupdHqf;fMG4j{f(C)Q@0WCe z85$m|sg$1Hda-n}9@8?=G9)7-ryqNT$T!CiF9qEi<^%wR=xC*IL#X8Zbcj11NKxLq zfu&p8h#VvZ#9scf{HFM)+Isk&y zTL7Jxx&fd*)W<3>ri2IA3&gl$VA>^kb=Zk-r`}v-9GBhII-L@z)X)wij+D;}QU;=&^ZGi!V zax6ALT?4|=H}iLIn}*V;81FCo5Pm@hMW??oWb}duk<CkE15o#-+ZFX zG^~CULh}41IFv|TQc5vU2zUSyO~5^off50gltfMAKZB~u!45TVL~EE)&T#@dbPLxM?xL`7`d7$Ka#J3Q({8p$#LKhai%Ms#FK+U53-4gLj*XzQ>~qM$yXJi!Jm?)FwkKr_40JQu0h>@*CF zEnhV5By-+dZk!o%yj}_{Z~Hc;Ph~2v0@Ji0w^Kw_;2NVntG%$+$+qINk)$j?m$H4*RyOlcvnGD(~3?RTBb=q3CRBCIYqT#8!O8AI>}M*N zZn$PDt=o>L*<@7~st~$cBatDY5dC!)*vo2;%vq)x_|& zH|H$u`88!1GekUzIfQwFCAzcJa954Gi<4BVALfQ4APC|D!$bp{oo7IY4s!e{F#h(` zcSc38-56xRmQa9AnVL7v;tc~HloxA$;qgdf!Z3&#ku=?r*8N}x7n57xx>#rQOMI( z#wIAX#9uCS37LiFhxlf~r>Wpb-h?Poj?CCJ!vx0AzP@#GaC@@**gxM)1}q$fsm*CH ziOwXyhDYIKHp$K0axunh&KRi9U`**+rj+7%t#mSz7^U^8iCVnm$08aG6^tIrs09By zOqt*-;Onhy0C91UThf^62^~V9nIn>FnLKTe#ys7CZ^pDuM9@ydMrKfAs)sYNgqTTu zX__OoB~4R@8XSxnT|j`GATc*aVLfsmKsd;xESs26wU%hs4tB@A+9Md`sCds8qQrs| z$lKF=Hj2u}k^&jB65<_7ELXZ7ev3p}Jw2Qt>!U$?+i%eRQ|TJj+5rDSZ8XoTt_=7Z z2ma5jf!3+bR(BVs#y3GqDysjzX-5C|eFK0%6}YSWWDS3meQ_A?aWp>Irhbc(gciIJ z`$yjnmw|fA%7(=>=h^g87eTmK*#;G1Yi(Gq-E=bEx4PDg1 zt54CPUkKr!WZQ`d=e{RVZk5;}hY?ap0TpDIv;876WwfP!3#K;a9VJ*j>f?}Mw5;&=E@FS z?d(~NWG=f``joLwezL&ZkO6PioF#P|!S9Yf+-6xcKuY$KGbMGLBw@eTd(T_O|C0)}Muns?;T`<`wDP@oarG zzhVdwy{~pob5#56SAKZm3yi?0jbu6*#&<6-9Uld~pn}^>Q~GB-5!Sj?4`vi_K6vno zB4JW6^EN*l{TVglK9C$G?^s)~U+wYBTT*u83wLZ}c&(qN#tefd^Sg<7oG2&O_!luz zJhUbV&-LC^bn^4W%Y%?<0p)opg456c14fzCp?b5~<8*4?osnO|u||&B$;G6VoJ=GR z>2?gFV-pVxo#(QH5+rK7UBhz%g0YT7%~yaKXR6|Q+qgIz2+L@2Bh_>Dh_rDGh_K-u z=0xP!HxbQgy8K;yhoP|7;eLX}fM_pRS46QbUchhN;tM*}=OF*FQ7SfVsqMhr8_43x zCdsH>_v3kIm!0M>KJNn)4dbe#t)Xx}*H4$bs>O@Gixy7A3baCFz0AX=enoUndwGSC z2dv&F5}2&P1@G3OMa|_)#~Pse_kf)IRzX6~dRb02ECFYXL|g1X@JCXC*yBp1lipTk zS`ySzBqRRgzT&b+u77a!zGlT*s%)*Fqd@H@?qzq<#aBC$H12G!)}kqV$ouMFGH(x8 z3;kMFY=d~L4UWNkv-yUD-73EZ!asQ@*_*x=w51Ts=Ga=FfbmL?9IjU0b5mc>iCe#m zp4VIK-zg0&0w(sg)UOMc2276d-G~nAsZ+^Z1hSkxfzJFkH}j!>YUgX}#<*HKk%1}S%uRb) z`xd%&`xuv<=0T#{u*bQyptiZbd(8KZf@1Wf6FGDQ#YKM8xW1b6kJLbSHpA10>m%x3Q|~wjafR7Mh_Lgz2yRK;qv$?G0}&+ z=onbU)T8C!RZOf8yZ+|JB!UTB#vi9h-MevdsE7{+T#TpLqziXr1}?&k_= zkJ>~C$}Y|$SPE{=_G%ATL};K7L>Rhld02FB~ zRx@rGg>u^@Jp9>RXdV->wxuvw(!^?WsY`%g*&#dfwEU_d7wG&|AvwIutS#qHdH8LiUw zdzOJRf9cq2GR&N_%f->m_})GDnjn)4NFMl~yzV12r&-H`Dtbe z?2xg)8e%*Qg8xOAwX!;PTh`~iOl<>_{|M)rZ1>)~a3rDz%h|&4SUeMxdoREFQUzYG zm%B6V-zPwS8K>QzOHYBN=C-0D9x#ynUqc6I>|l>`;PZ3E(zO#gYo&HsGT;wDov8EU z|d$UoX{W3rN>14K0yuo&8+ zQo+GjvMP^`Q%cEaALz)*3h00n0$@dIc4ksu`f`aZwmJgQYEQs<10tBXYeX24EH^6q zLeU!Xki;3u*yy{%Cssi@mA^YXh(7tmEu*E`lndu6H2B{o?LGo;Bn+$rW z3hMr^g#h=qgcMLIWe$%zkV6B}40P&t!~S@{-sTUAL8ne?W%Mokx`%P(Tv^aRdy(v>%%6K#= zTM^kW)fmg*%8Z&KPl|Tzf#*J7mvPP+$t=ej#jwN5wYsRS!sj=#1->?4nZ9;q*P1Id z*T0;>+5j4^)UuR^nnjRq*LU6nPwtQw7D@y{(4XqDEsDE?<~TB z@1MpwAn*i}M*B*RPEMlgZWLGn)v0D*umn6E@oij$^Pnpj)l6p7|X{$~umO8E9 znd2Sk5Yj+MK}45dA-efqBXXNiDRit&qHMx|~*Hf?%IsSERW5}N-k3LaE21J-X`mpk(W5nmocIJg?_>(-FEmZ{^)LTJ@WHDvya%-8FGp+r5CDzpSxb zwo79tTXf-A{MuA~i9yTqDV^GmN7c1mXp}p{;AX(w5F_%&;(-VLTxH7S#iP+ zOY5AFwzanZrMF#Id%#=ErGHkk(xA^b!!|C-83glk?$>E*=ir%g>j9R{XSb6eyJtz( zrmEX#tJmZ>Oq|SRV@Q#v^||c5#=BhkcCWn|^$H&a(BVzj3Sto+dt5p7=`Od!%jwtg zdu3<>!)C(?bB;JoBzm6ORe4~+l2miRQ047)!dHEqTy5Nw zvdW~oxvyMug%gR|<<-qjc06z#_LfK9H8rzmAWr1Nkg2kVI)&9`W^_Dt(WZYKn55!*C6UVfC@kaJ3h= zmqSnek*mhVvdxm;!xF%1`*@7P5HHv-)ET_L7&UDNEl&CTwE9k1=j zP32{`R^k+H7L(r7(LA%D*X01CL(dXLHO<4AjSc?`3Nc~GdrFBg#&do)XQPd&#?6>3wv01$Y^cuN<)PDYgz7v8hs1ErmRr* z+vN2Up<0@HCt^Tfx{@t6KpEF8!asp5Q0Sk);ll?IuNBZCT%=vgOt1Ne$aXM}I zy6}3~b6EG&c(;ndr3X_nbrkCAJd#O4?nf~;dIxyE^=UWGMDrVMB z=0Hl;aus&}eDwm)IV+-Yf-BhX(y7w~xl^>}mwq5jdDmLg^zTEt6d=0C4%0-NOWy{&$6a z3JcE|GJet_Yi$vUBrD4T6RF`p)t&yA)N4x^a0cIu*8kQG`^ne#qdsvt4YVA?xI8z+ zKUO<9{qU2W*^!!+hV*1SyWhb)9 zjgW+Y;&Gx}3o*^R7QQT_?Baxh2=*?EypwV|mUM2ocO*V@s5#g~@VCaHoFu^C_jK&{ z+AYDRBC_of$}(#|Ws)`aL-$M6%W_E)c zi?~7pq%@0PVxa#yeJ9x2vZ(~?3@$-{6Bk_!_2iI6eoAOh;2~~Dtnd8 z?LLnj`>vBIY1ih_`4Kw;vab-uVo2aPo@P2$_2;|2lZ|?Nj-R^!wf(vhp+|C%XOPt- z^sbya3F&x@Pa|(BrSx@ts+?1Le;?R#wVCO*vt*>st}Oj!--nR7%yB}1i5Wolxt_Z| z&^}R;wr@Z)YK=Z$Zq?Lop*n5d(8kPhU7EQ;Q0U0|YFki?Vp1aA#M4B!i)5Pf{&JVg zntrlf+^4y@LEA3gz$jI2=MpN0oQUT8(M5eQzZFSwfrQ5NGb+l#WP-t}CazL|bo#IAM(h8wYV& z4voy`*%4KbEE}eiQ97@;hMfiqje+NO%wWTw7^REZ?tumG24hxf`Rr{?bUEkGs?B0+ zw%Q7N?jCAI#w+fUkP2!C%b7_iydV5`X7kQZt`oGG<@jhDA?p;~?*Bmd5IWDB$*)Wq zCH~5aBRsP$2Cpug6XFpXCGgL)rHA|7ikx37bxNVP);bQd;9r?DxYv^04Ht`x#uo$y z8mP9}2h^93Y>1-Oo?&T2UAVq;bx(hnVSc)CX_`YRJ9IR5?$)r6%%pLVWJ{9CgerhZ zzMYddK*uaF8#oZ2f4ZCb2t~Gh2%9XjMu#2XTt*u$kqh=K70cqaLF6%y1EtG?Bh+;CdO7 z3(dbT?r0+!ohp#VgfOU+WJsg(WQnk8z(yg9hd$CNP_&G+ITW|TdU3>KE2qpUm}vz$ zkc?QM+nU3XIDLGvL7mx97U=4-ojRQ=Hm9P8o z2YxD-6+l{AD&}&zbFnil%rqqxnv@NEO`boRgat1~?Sfi9Ex9Gr;$q_D zY^f`!AtReRy%j;^ApzBmOjTtQSZc~ekMy(_x2~TeibPw}g?Cd^h@}C$D8s5YRDcPV z{2~^ECnGN}{sVyV>kk5ZbG%)4`hlypa2x5@!U9W6HF0H$cp|%iLIB3iAqEz;08NYk zJ@DGi3WhpFaCN#?5Lp_u(3xNEb-zZy165=0vOR=EzHlecfa~C)61L6Tsh2%rrgnW3 znbqRuN%RUP?G!$ymGdvngTU# zxql%gtpM1|4+g)YquBKWf6{d~2Ly}%FCd&7j4G0h<#FDFwT3#kUJU!987cqt6_)x8 zoDT2G;tPLaCRdVU#+?9E`-nsr|iS4}5q&*W?B^+PHk4X^(8szki}Xaxa`7x0g6$FI+V*+wHtm|EMWxsf2b-lAkWb zRhi)U=GMLmDLV%)qq8bt9t#*O@(wQB;9#b!WINSxjida8o#)RVn#>``cZ;mytea&*L_;@an`r06OzbO)5 zcrCHU;Y+5zL)C1XxfX#0U)M^XHzrKO=mRFjL7C7DkLONbGp9$i{Q_0z1A5M@I4qI+ zwn~@RFuba(0SARQOk`CwC&%%F?PEtCAahNizi@$OsUO`8B!r8-wkGHF-aKVLA}lUh3i~sY1CIZ z$}M!*nKbO90itBoUzA(NQwLpM!R-#TY%m+5oBZe_nqT@%f9l#=;l8Ya>Q-C3)nxPT zexy_z@hWhfKUP^7imUCG8E0P5RHpa7@MaS})nRp1XYd$0)4>YGgIZK!(X{@|D>#lJ zE8->jS*rP9w=gguOD0t$l!qv!slb+8FRuc+~y9@|LU7(5lLEIY`AyPfuTtt?9=N3Ow5ixNvOW-SE6n znwiAM^YG{pK;}4|XKFBBe!>#1^|!oIe>53e%X8tO5ygUQX>L6k`@3{5da^m+syY4y zEkLPs^4*`yL#=39*Xk-cd&tQ|T>l+=`) zl=NIJ$lzi>q+^P3$#WhvrKWOTKn8~N_)qNS8WR@vo@ z)CP#7qsG3B-lq90rfB5ze3l2xz|64DLowkvns4|BM^yQ<(7eET|EV7OGRQE7-b@s! zy=`MuGCGwN1<^aN#$G1ex9^0DWsOO8WFy)djEKsuL*iOY zv<=qw8VJfP-wd)1y{`F5b>91$rDi9wSSnNwl99!HX4=>6WwnPA0#UQw!d(h+uB@zF zT$(ZFNk!Tz$e5^ozUoR2Y1$D1ZEr9a-HapO{C7A00esh}au0_}`pU3Dn&8CIRN_&t zFr*zs3@RS=SlZI`jo0!AHtt*zg`6uHx1B0q4+mP^u*RX z6{J6!MTbAaf|Tv@@`oLOdIqpcV5?W;yuFD)AHLW|t3oZP$n`z2*nHk~4~%(&XIS9I$9l zpOZy@{^vVBTZiXYj4xK7{OV6xfJ0dj6-Pkqz)I>@X<#=;KDSG=gAO*{?p3S)$_jS@ zQTzby>w7ma-Gmhs3+0&8M$e5X9#qj%J9`NA9`EvM^CDp8(qmFicncD;wHt4`2%HZVo4-^Dc(t z&(^X_7oqSzj~AIHbyL~d1S1Q;I2X{X5zYd>ALClv)yCu7RQlzB+sXF(Q%0N8r|)%O z*HMjH)DG8WnOu6+6Z2;xs>zlqo-tDX!7wwAlU&pb6!)Q6GjGS@+?G)0`|Y!f3$t5eo|gV@vam7!d0GOiEyGr}`w zJ%e_F=}IHdEhU5+Vu*HU`oGPxj|4Q+ROu?q#hN0Y=%%#hQ^fT_`#*oeehra(IQdX> zh!cTYfth+KF#sKLNGY*!+iWx%NJUmbdAl%mNzWF*fp-n13Z&A;lnx;3NHW6Q7gUxk zrNXckv2-XQfP(RGPbzkzos?wtnP?e!$ndIU7lUyrwG%3@X10ZrNCzX0>)YuilJO%J z9G#dZ8)J&*(-sIdpw4@ah;K9sEiHZ3xyhy+#ps-GuXqZBt%Jaiq07=NDZP%QulP8w z#vT+Us=aQ*YPT}#KC1I^i(N#lS@K^@6_&Z7T)~QiXmIuKp@bdXtLEqS1_KA=;LLL# z56|TV3r2j)K$EM3-?s_l^s(a(PD&(Yrf&*S#wDAhtRxMSjs)c+{biirN%(wzbPUD#lLBN;B6zp0y^y5ek@rYROUEHuQnSx~; ze1A_4foURzO#E95S8{r2zSYGf&%=7V_HNpnE#8W1wy-a1V)KaBomB6@OZDa4_YSH^s^Um2>9kumm8m{$uD z`|3{?HiNT)Tg?TMCB43IT$oMa9?HMfs4lc-kExBfA|0j?OzmF`ZcryMnssBz& zRA>fl*f{Kn-b~P!Q@*x+4KWq*r*YXkGJ_GVS>_vmHF#PC{X+XiHu#3)U{GmGT;<^o zf#ZR*k~NynaKYE4zWwyQ)D!&I$%RIccm1<6a@l6ZkKS+0*`7@Dia_ zF~ML&Ln^w!7pWbzfF(~mxV^{1-6^j}o^BnTotxqH;wmj+ZPiR7#o5%!v*76MbuTnE zdfRR6MiH83DS56GLeNa`4-CU=vD+F>5p0M9&*ryrT zzEy3nQk}g+Fsn2;^DT;2zD9{TvdTjaw!nJjuOTU&4mtn@1`%91Uvt!k%hg#FBQg;komIfyQmIi5r*oQMw!xCdtPB0%3GB!cPASAhS;ED|1>lkB z=;%y9kN`^_X$FYzmFd-%K;q(S0h|d@%cmQSR=+{Br!|Zqt9p>(mj|`8PO*U1x|(H; zs!!1?NuRs|G#nlr0d`ESyI-5S_B6cBzNe3vt=S^L`gMjVqfY-G>=*Pgbk?Lz;y7-h zBo2LKx;tS>ON9(G32*4>WJhN%Jz;f5CfcAtglkX0d-cP_WPpsU-hPXLbevV=4UE{d zdY(4s4vow^<^aIi4=3}Mo9)(y^L){s$){`pIRnr#1p3o%$0G51{bIoD_zCcd>bsmb zd2G31i;x6bOl7)#yaBcAfNsFlKXSMnTQH~oz7W3i$IH9T+evsem{R6f?atqwYQc=< zgP(H+@*1b(F*KieDK}hB>@~+}vI_3s$-eLct=6B3i&QDN1(sl!g%EM)qPf zgl<5(3P^+U0EgTk`7D&@H3v=-*1Hp6&RW2eLDe}it>E4aCr)7fln3L97rzbX5f)WQ zPIDs7O>4jus7zvHvcMH&Z#XC8IW&Gu=N29M%rAmX0EfhgHGA$j=ks}Vego~-hXbR) zMo>CIpTSG1kguC9w%LcCRhOE3#Qto9=N6gN|5lo&;=5yHFxP#CE`@p?eWufqT6`@q z1B03}=xAa&V=>wX2^lfPo1ow8Sg5fejOnNLd<1b1uZ&(tE?2^HER%rF(<1-qKI=$j zLOn}8YZZ!5QB$pXDP=@72)aTpo*qNwNAQy&E=T7NkEC<7k)hfI&Z%iztU`Wh0ChDC-(NjU0vMD!Z0{# z<83e8_gEnrvXIEm{bRxT&P}!Qon3!64C%xa8ag~CFsu)bRG6}z5XxR;xnLGDhpow3 zfnO&94{~;|*ps_KLyVxbKad8bBBf@UnueIwQZ-+0cYd&8-P}P|bGqo%r8~%urmhd3 zydcj>9p=bd=3Lm%iy$EOj~qd}p_6iAF647@U~w(3LwzgYpSj9Oom7eK<}C(bEG(FPn} zen*fyIyayfBFD0MRn4e!IYP6aX5I-9M?}hxwht)}bi(bxlu#JM%^eLWpwurB#*e^W z5E9{!?(os_CLm0}htp;$Il0CmnJFvIS?DMHs-eGowvZBN3Gx!2+1}L4h^2gTanAia zJ*(>x(iwh)=B_%#VkVVzM6wl)uruu6XGV%~gHuH~Uns<^*}~pKjszHJdfsw*0B{k7b1Kq>rX;#YLbT>n6AX_TWvmf_3f@90d$l zX{7>fuZZyk(~yW(m2ccG;lVYNh`vK)4$QU`GF^vjG(0M;M&Bzl>a^h8`(`N@t?>&MJ|78B z8hV1Re|V^SM5r;VKC?2z#uuZ-{Oz(pjx=kr-ynH2(5?H@11!Rgeh*R_eF@~VO&GzE zcLo-k@nSLSxSCBHxET0*-DF!On@@vK^<~vkg9&t@fhBDy#s@wu>NcwI~_e=z6I0%0#TzVAQk}xn725SmZ+BJr|?+CrKNyW z-eA6w+vPt1$3Zy0UI9yd>7|##!oslEZl;ZY+59D-bBMZEpd!`e$&*u3Qm9E*1cd!M zc?J;IE)O}tsL=1!^)LluKmQ;w3Hql2qfymCXNk{Zlybas=)j%}=Z<@vd{JS3FzEMq zJi&n9?Q~(kBuXJJH^!+fK}C`Tb-LZqpYQ>Ng+&gB(}lgf1ZASCdRbYy%k7ScjHpqo zW?Xz+ojP?e$U%BBxe-UDxyKCkU`~yIs6+W)uXnQKsZ$XMpT2q1<_|yo@QN$0 zxPQO^K_pR;m6bJa+_>1-*zx1Wp<9_ zN+5wo4?p^HKK|U;a-`k^_j_)-%B&Ly<#6_sm6+-{C)^a~U_<1M6)RV+UH#?#_uSj> zw%bBNLfmdQeo>i%f`a+;=llJB^o*S?N?G&OSD%0W`G5ffZn^bVr^A8Bh=~aPKw#p8 z2`+Sv?=a&{@R;Mp&a%z4_KHYhXSyXa)LL*g7Rj4JMyA|o_9f|i# z^m#H&>E!FI$yMT{rk+|YV;f46E59^<)rk!`N(lyDm#QtRxnnV4;=`gO1uDmpQ&v=} zc@27xyjCKrrQR|~M0mNlkO+{BO8XcN7`OL{f2=vZyNH-^@C^L^vtyDpBd73V6B*%=w2u104Y!fP9YLS(+OJTGK8z^ zb#MiQfF4+v@_ml4Ac}K!tI@J`e4{u=WU04w<-u=p)WCE*)NC3mx}s!v^^h3U7v&b_ zKE1_n4D&3XiYPKsH668aOeC&(#YK3F7q zzewJ>`P^aC<8-NxE)Cj*Izr<-v6wXl(Wvi^o6zgA*RCA?+BMJ4>N9-G^+P7y_{@M_ zw^otELm_N5v&aaZD$Ud+`dpT58VaxGs>M(%veONbtaUOjq)HKTI+byLak^$3* zaz}`W1aC{HgGm#q0#=Ow0PWxCX(jW95$vw3yX}fA_VTSXD zI-MjDIfzwas!=@7JYSSqV5*R{UfD?X<_38k-YzOU+PdH(K ztnz#>udBSG=mAMnT^3dF85-SVBFb=3mS2HRgkZ-kp}8U6Kz|V`N-BNw(-9vT2kCAq zMtW(1#_0;u@>;r*7o;0WxbX03hajT@BHj3G-G~Bz?%)FwJNZG1omgqtBrE*FH7x`XN(qe0oaX;Sct>J5+Q# z;SrI8WT-AkZu{;Tw1Tf5TBTM@HAUi17hTwxyo)pR=8?6VxT|!p)dut=sWf%dxqX^w zdN@~y1}z~rowC~z5`xrzPD?4tRs=&em7-utv08@eV}`8}6X)P0Oo%k~XgWO`gNaC> zGZJVXYVFiGm&QjqJ>ze9taDToM^G+t=(Be&%P`B)@t8F#+WS`pktB;I5!bi~ny_?} zOU*hr?Mz&+=6gbZ<}h{=a|`p$L1$9^2o4|NU#PEuieI2sVC8eu#p_N$=yOZpT0)ElM{R|EA>s z8~BNSVE7|23=DXOffhMF=Xo6`Q?}E*RQXt+PSmmX3m-w9UVP$=1hn;%nbp*-~J}j+_`h3qM}fZ zqeqXvzF;?WX;9fHy;X7au;H^2ryG*IgNV>kXVZ$WrfmNzrV&cL# z-az$+3>^yRg>Wj%x(k2C^y!E^Xwaa@hzP`l4cl2=2EfIIijID*uBoX-h<>5a^uN00 zqc``hSeLwaed_*K53L-(X2I5T2Q)$G)u>a5N_UC;ke9TkAmJSEJs8MXpR_9=fuo4+ zYPX1#!m&a#wl!&E3=y>=H>+XQ8eFso=IS(rYa4V5fr8@IgBOm20||b!U-KSr!EK0+ zmf>}qhgK8)Mxp8ZB6(|?QFu-*dN1+2Qm3ZyT#c%=YDd<_%!xVG_Ln633^T$N=71>D z&8$G-lH=cgou07t_?Cm&Cs4hh3^9rkXkd^z1&3oFn!oKW`piLKdMnJ#iw!s8l8)`OI$XBv^pB0OX;L?Xdz zpfD>=n$yTbEiE5!1=yf1+woHpn%GTnAH~fFAlNvmx;w6Y)n=S7mO0E%c7L%iD=}5g zD&mSx`p&ODy=mI|g=u9Orl5*?fRlNjn@h+!ldRAdLOTb#5$ z^H9Kro|QT`Xyf6Ws1@cc>SnrGj;>{ckC5$hrXm|UXM~xaPEpP8ZE#h)xW;IIzFPFb z?$sC6Vn4k@1jW*gT$IWpXJnR_bO!^&KN+?uz%t0d$heGvL*J6}!>Z%k-#fAX*>7Ke zZPyAdL==5ym$)XkHtij1Iz&`k zI-^?EXzVh@fULiJY~9!S3CElTN44~iQ@1|1b|EJ07S$R#{er@oYff%W45p7^la3@%{e6aY$CW+NBA|BoH^AN0VIIwFT8N4FaeK~jXCb=!uBA@+4c_;5NO zO&1}}cu#~&F?C(pf8oRzXLf#lK4D4XhD?9HCg=eXI!PvvO)v75p&R{t@cW$O$x_+T zU`8qDC;wsynr`wkef6_r{k9>7Q{u#fS*Leq94z3A&wA6>CvJm0lMJy<&8Afx5f0F1 z#3v$2K2589WSyE`@&6ZruA%A8AWugV9Nj=fR}-P6Iju!Z_1d0DO;gX5=Po|5{#Z#) zo}p!%fql6t@9z2X{Y@(s!|;GhKIkZATu-7 zWtctcwF%=KUFx>-m|~8vFw>ha^J3%h8nxY3FsU`IUawAMby4BUjlfqYzP}L6D=^Ep zCLcUkoC#qSB6_;kZ4J3g_wDey{cRa^qi&rLMGL8sn3g!RPGoHRi29Fry0f|%A2ifm zMaP$)+Y;oJis|<61CT4QDHBROSbT2Y+j5|+$+P##HDe_VGtBiE#=4&S)i&=}`$L;F zmt*3=MGZ+U4wOxuIlH)|3{o&UDhdo1{EftwX>Q)U`LoYH>)Ep>_$|Ug6_j9b+>0;z z{r(9PCRDFk9o>2IXyR-0U+K`c@wHWJcM)Q$^zIsd$Ms5x%=vw17A^{A<=1{}Kv<&& z^hy+g-~Gd`cNV>S<&{@H{P4r*T#)bS)2FATq<}XzYuXe|0ChfKeE`2>$BvIY`sh3F zzPoqt-Y1?Ih$Nu6cCGBj{ztIWqI0aKaoO3~Lx&CpYbCb)+ww#2fuw>^Aq6<3Me$9y z3#0)V(8*~#+CK#Utk(WlVGT{X6$RekF#J2VZ740uHFecjUS^#%q)`jS2#pF6D2Wm* z5JTDFaMBfcQ4Ff8FBlL+DLg#F;dEjb)T4d9KRhA=qAM5-mXwqf78RvuWYAs>lNw5+ zmzX(aM`UCqeZ`*RHhs5o*|KGK-+kA0efnT<`+UCn^XKK|=8m5*AwE7H5j0(2wQAL- zO`D#2>Z$e}I-uy>+}v5SX2FW4Or07Y9*)eBtz`-Sv55+XZk|s+`Re=5nD{DBKcq)R zN=l%3-G+i~yP|Hq!gcdCiqm5XQbAeC%;_&fVUM3U0W~LfZ2>tfUAh$B>ekzCyXmHz zs7pDntgH;x(=_dc7hZtQM1}2`=+DnT|NNV8zPaO$J8rn~Mg+kN{PFJ#|3;uVR72MJ zR*|)z>~&Y15gO!-RI%jKGn;4a{&42DcRx6>?xd2zYpPopx>jv+MfH|WgU?b6Uf!{2 z#Omqe*1wThn1bpy^~CpU(mhO<;6!zi-UR_dA#$d}plgpZre?aC%6h#an1jJX@pP)w ztd=uMlMKHI6(cl_uGuoW9ykHIznVMZ_Ex>34Y!x`f0npz=!$8hzkFr+sjUic#2Bu- z8~3j6hy2y0BFKT2+rY;(EM*nB8^;xe+f@Bvp@RN!+j&Sri z2-4ECPnhTBNWnd@ec$>*Bq+kc;*{}Q7Y+Yv#*-_j3|srkynQQAm!+$w5hA;rR&OZz z!IO-yj_(-$`JB;TEI6EYS`*AR)$2#f;k+zDe>xHFZfkr+tBAVLjmOGT#(uM4_^RnMzg?W^%M$}y&zMHn)@kQ7>4JbN36P!i z`FOfogSiWo%^JZb-Bc{-QmE;vYKA}2_0CwssmV%W*|}ATn|vHBobH^4_*ATg?iePb z!@$5mpt~^Wo>JQn7^6N{om2%#2mA|!q*Va*WWlfYM zhoRAZx^!)iGn{ml5-zKPq{6wuLCKsLF1W65)X^O<>22ij%Nln@{q`}uTcuk}#A~ay z>{+FWD`?~!r871z8nI%=xHYeyD8ImKT0LjXy-j+Dm>}ak-4ZJbK@z+o98TLR^}{t0 zGfNIvI)BfKN!veMdumrH?}z>rWx=DF4pV3lR;7^~4dLn&)pz%NF=XYe@f+Sr_2xoT z!QIpKOWlMpZWmYY#`>Khr%OZhX`A04ymH!zujlU0J|+oVZ7t-1b~i+DF4U7|WH=_8 zw&=4h4(nC-0vh|PAR-Q}X-zL8r#m>^sT(rQb%IK-N^&-fs&jYK-Z4R07qm5}wvJu9 z;E9z}2CkX@;>Lx`Pi`#WOEq4t6&)QD8g8nF#`Ck*E*`x4<$2$IobNA_IjKv{<_?V% zQ&3dH!or%w)}n?-)T$X8qd-=o_k%{Sx@|p%=;HV)g8SZ9S63G!p@hFYz4O^MbBC>% zx$xkZL6;e-3HP__Q$vnMqrlrRLF-74KBtA`G8%#f>RFLZQ$r^>+r>1#v-veHl@Cf~ ztB-uMKkqCAN=38(@~}mty&?qEoE7T|_8yM8_f}`8*5J6JeYQatl%vVn?=26F@WefO zN5F}r4X&y!`|Ps=TlYWyz+?15QNX~cAe=pOX7=paRjO10g@XhIQw5y^P2IL_+n_;% z+O=&pr1XGL%Gd)#sms)82gZ&0vGzjTpqGrKK;w{IbL0c>ek4&zw24c+sNP zty>QqI8eMuAno7Zfy(4QpLf!vNheR9!sc(kf!4lX7tx^tz_+Vcuim10^ZNDbhlY5- zX#p$NKLt#J{%61_vlfg&NF6K&t^PRn=s60W3m*F6`?E=jZl@3o1{6h+WO!ye=i&91 z10vnfH-ZD|(!#o~Y0_!(@L8Q}^po&akV@@ahvtCwSo?loH2>4;! zRHkS>nPTdp9=9k6s%D%^PF=9zjk#z8i120X747kdTn@ z?z``{Yu9ezlTTt3&fwie?;bmTeDL7G?c28}=}G5R(F#=fmxc!_t|2$Hf!;lYzb0L) zHPNWzvh$0Va~E=(JpGtlqn1Pef9!n)fK}D@{;Av3Jq!#Tl8S^lt@W8Gcdz+-a7UF);@OztoQW2_j~{MeD~vU=G=XDtX*rZ@5DZw z>-71%?`~C!hQ|(ggSR<&*{r&?_ukuZ;)i3S1`n-PuA)T-t6&SVas0gnrTUZFyT zfdd8@JRCJ$v0}yf^XL2Y?fdu>PZ%MP45sq@xpOO*uP9NX#Hi7uDLGS}nAJWR{|!K6 z>4HNyHLp;AWYZqCVk$*iBP7A>mQ_vGL(M_u!%M#Wc;oWnaZ$W|$g{6DFI}&M6lHQL z8L1EQGO}V#Aq``yj(Xp z=&+|db}039h-R|tLV#Nec3SOjQ9^U-T9_s1jaseC2+Kg`PH$47R>LBXm(ao;nmIc!&m+4rl7l#FycAJ_3oj~!z{Z<->FE+r^nLb? zYQd#~WyzJDot~a5xwR?*@x5xaex*{wAeC-yM~WfEgs>7qcsOTex2?gq^%ACtQhY?b z6lsG4MtF2)(HlN7VrX$8vX~ed$k|~1v6*zfq!?L7i!3Qdh`a~~@rls*sV#apE%Ic% zC6br9%*^cM%nXlHiLgdK6;>(A5@zA7Eh<0%Tv*joN|;SCrMsQ^suyybIU$_4Hz@vi zF)qA>DGC|ZC{_`U3Phb(|k36pdon75V?BFiX|#kF7?2sAmD9K^P2LP9Ea5{Q%oilT$ICDgCF)EG^ zkCH-T0>X=0Bg$KfJRAPlhy2rvvoocolP^-%mmU6Lts4L%nCnqJ< znJ4Mi^1&s`#gvwKsd7;K^cVX!j;>aU3$c3G67+ewv0`Agu;LMtt#){+VNE;L3@aBc z1!ZJpCTFL4WTm7vx_!k){cE)eK?%AZD%#^s(Z%_Qa6SM;3+4(GG)@R9&V|Q|ku={S zI;OYAKN5{M#`S1;dxPb5uwVGBBC{;>} zDkX^Kcym;|DJn_|kW?+4vvhs(#aEte zT1*Oa>)NfHv}9Lam^rvsXt_zvdR7fCic}U}j1|LB9ISvuPi*M0DPg*W%$5)l%Lki& z?qo8D3F_NYOpGYWN0cx{(mh2Z6=yBQhe7>DNa4IH266URDm5Kh|BX6_s0BEn|X0Ryd1SXjJU+0nc`<99+U7*%EUzZs%vf zo|Li1b*bIrjf#!X)bRJhq@ZF_H1u`^Z#9ELz)ey)tHy=v){=Y_y1OVO=Oqg#wyD^l zURb3vT7*O951c=iuXr9YW&dG7`)lyyG^1}6_9#1iI$lAfEJ#gF z9Y0}0OiZjwkE-!Mo;taF^~$H})am?2XOk$oJ>J!8)?EDQr=h*NN#7g~)1uE_4C^A{xDzB6pdkkX|~V^V`*&YwR&K0bc%;K5dQ zJ5f>9rAw9|eBhu#fq{W@X3vI;IBV9d;NW25#OxN!Lm~e@(0f1I7*W(e_+b0iEnBHY zpo$)~%#X%30_Yf%0~^hIASf{KvGNt4srPJ~)@@t2ZvE8LPt~qn8zLF5J)-^hT($V8 zfEFoeBtQND3K|RJ&&w`p!ZU~Jr@;be5hTzodJ=D+-?4d(u6m-QqVC;K$ji@l1O;Ho zI`f?1Ns(dU7LgX53kwbb%M?XZa(YU(E7xJQSvk=zSu|Y~Y_^QNTvetgFl|8GDwxNxD}ZWsU1gRIb1 zUY#>5m?pd~%3g(+bY3udJQ*MCOjx$T*1lP}{(WV$Bs@sCGj?Xi?YrgYOb)2?IRDd~ zLqlh}VuEI!K2WV;qeTms3MNUEL7sSx*R!*;d-mvY_3G6%YuDDSQR9A6Qqv|)s#K|R z;lhO%UU*^3)TvgBg~Veoe4-*yH(!5--GsL>G^Y z4G?VLguE(baqhcW$uM*_!4w@FZsMt?>8_m2{2UN;huIn%5N-j75qL${GQ9c8`B|tZ zJe7!`kWiBYhFqjOg5;2)tVD0drIfoaXTC`nL#%-%V&kIBp%$HPsrPeI@?}NfxyXPJ zL=bu2t1F3_sZL%t3lf~IV9|`&GJW|#xu2Vnkdf?^U4q63SS)d2(Xjzh4#A9(s_A;R zntwgxUV45WnlRjEFC7{i3~tT~$?n{AS1zWfO%RF%MZm#Aggn)IKQG;@sqkVW0)s;> z4lqf2e}mWEn&RcOo0$o>Gm|t$vxw%RVbSs7MI5}zLicz1RB!Hsyeza&pxF`?7>2oz zDj|Q2oy!^b6kW0MQnVu^z--lcE>m$P=VijWp_Re|g2HXV=vEYDG=edx|3@s7AAbB1 zsHy_ik*m0qa?;o(VK5$AWk=$9%&E|TU>wtf74*;t-IT;kQgj(}HdA%o$w*CMAG@*$ zVwfW!K0G?gL@S_jye88pjy=%l$yw?7idPiG_~7uO;nBf@1@_*ntNFTe?Lp#$+-ybH z?Iv6CsOX}B;h4kF7aGSWxwF&Vxq_xg*n>jt!I-*=rlsX(DWP3M!{2dvk85 zCFi+4W>JU=2#gPn$@1i8p0WoO3yY4n27&t_nTyv` z+&OpCQr+ZD@o_;B#eyTuJiVHFKQA*!c0=fJlRY*djOkr2)0La$%2nxg9#eE+Sg>G* zp`l^Ht8QLN^X6YoxtEroBWOaf&0Z=hHpUiWMLDX5d~U-4X)?OCh$B4A8o+Mh(iwCr9z82fJi#I3ZQn!(&isj~?IiKK> zm#kk{pf?n}~*eAOSa_-!@mpgR0dGnU<#G|098@-K~>=#WIS}>R#W?l^r z40x($gQsfNjf##EB@WJx%k8?KoV<9+VpIn$_qQo%-Fo%+?%fM&?fd=T3_k_^bMUnm zz4vCk+yO6>JvNAOhI5*lmz(_Y)>RqzZv{E*;o;%eu3yu5)fV7@!=0CtW4GC(BO+y& zC(v#O=LD5>x?E{FS+cIgL`7;&*uHmPLJx$t6Z*(BOv(hgUn;6uY7&tLZ3my`}XY%KRz`z_029_GBYz*uU=iT zQYFkBK@g@+o%->|AA`=dYu8TpdXtipUVHsDi`BYe!-lxHILuyfN>;j}9-ha0VY7t!vJNMa$AZ`ZT)pD{+0gs#cSJ>Gu1BChj|T zJg;)m74L0}jxGY`L$0^3d1QIvf(2{WuAMk>;%l$HX0}-F-@DhWS+o57{IX@sf|M4G zi^HU(hm9EpeQWOAci(+?_;9K$%w$4BLfd~Y1@%oE_6HS!!GrBo>FX)m{ z>3J_k93s&DNn=$61Tzl{S@4`km)YBuhC@b=?}CX@1W3rsZeGP0Lu3mlSlQbQV-E zToB!aN)Ts865T~I(##>A&EBF$rjXpLssj8K($*Mcw9>56#)wT1rBe%I)FBgEvyrZU zkT0cy8>48tEKO4rI$l5*z+dqaA*X3c3j$LsNvJ6mL#Y%GB_!Kor8jKp{Zv%YE7018 z$c0u6qUuu-$c_381=6aUJbUU7V;=(_e`zjwImOG(i9}K9 zD?Y4kk*$lT^>R@VX%MnboUGH!R5%4uBzRkFX-cElj7C7(|4={14?q6>z^tGLa7c5~ zN<3_iVgfOx2W<(CKpKoDJmwV59tOJS13t%jFmq{Qk#lWfOB8@D@T8MS)sVV|PNwgJ zLN!PhdJu!H*@`lCT@!g1;?Sp|HHi~R+cOs)MMDEY9PT{^u4t>rn0sz&bLiw}zNRgq;zO-VfGNvwR&3(3H0Dfo|dR{~1z0jW~ltv5c z;FPXg$wh%~K?+iQ^yEKTYmiywObXCLj|xKpqBMH5QQ@IHRWllp%ngKts-^F~czFR9 zN+6X7t3fZ4LKyr*5u~zES*UT5HMLPy)=I|ZGf*=6L*eKxy2g%*qlrQ5OmI0+5R1%o zDcYKJA-#A>`9sN4N1y||>~$ul={XBei^J0=SoribktL*NFd7ZgSp{}w;Xe=5DRgHJ{RGAWXCp&El^OU#G7~8b!=axRI&A|)`W(HVupa?E?Kf< z(BQ%S`t?IUp+DgbzSgm0XlUrBO`8rJH~^=&apT7G=g$|}ZBKfY^iKnW%LlliD8lRY zwr|&d@7{ehxql5dwrD)EBN_(<8UVjSg992jY|{9-mYOPLW@IF#B$#b{Y+RJAsk3Iy z%E`$!5@Uk=cIJOA3i_WpDgJXoL!51Fht?w(+W1X+l5-#U{F7@J&%tfNg^ytxPX=&IOEm{;pQs5r|W|G^mn&jsr zjR-?1q-9=Pv|16AxZyqch;XRpoX-zu@BAXLPW2+4+Hq#9sEQf7_D#y|v{3V~@e^XB zVwt@LGa^a8K5$^;#*NQB^UUjSykR^b0iKCg0t25meR{EC#mGRzcGBu${QfV#*s^6y z)22W zW`~YrI4-d0Wc{#VB!NVkHCh%(P(eSyIcX(+GqQ!-p=$66C?BdV&hl0xKKTmpc_@Es z1U4EG(W(n}SqRW1yDD1HY;3h%oW)20=W!@}FelnI-bSAZ5lO+qiQsrUFWEHSu8U?Q zAwz2tHTJ1cVxVYbh`~EJ3Bo&c$;z47r(@t15&gqPk~1#@b%tpV(5a?Dy2-}z7M&;= zwFRrJVb@JmSvV+?Nbk7vAc0o!Pxeq21T}7f5?JrT;Xo=g+JsSG{N37JM3d?aIcPf;dw!wYDWdHTdjoQ+;& zWwh2;8``5>6ofHA7t-mOI?;mmr-B3c{39D*-_AAb1p3(yKNl9@MwV=-nTK-FNw z{Kb?J>BGMTC_Ey?B0{ZUq6O+wkS+!CCM$0;=};{KQ|Xv;#PpzJ19dS(HwQ9BA%SNQ zy`ZxKQ#*D}2;?Q~q0AwJh>1%}=|~nH8Xj7dv^QowDM=CudwNe&q|bShx)ymNIiO62 z{)FBGcLGQskQk7jM{4k-n&I9ffE6D=wih+3!;84kLYWhOR-f;6aT zK7f{o)xlb^fn!5|vKx0yuOc4>x(@Y%&Vg=25_Q- z6Hr+*lr0e|`0}W=WMftXx(kIurK9B`GnyBBUe!tMQ+WjFM6yGynj+}2V1f=uDN{$2Nc62#SYZqX*cxi9|4^VF3Vj|7vqF_P4=p{RXleWQXMFlq zY}3YJt(qzhJ1t0|(nsUu`?qf{U0_$ul}C)yBZ8?5MB7V@VeI1ml|8X{pWN;HM3Yc)cz-D( zSk$~(Uw)go>&u|pH6veZr`hf30#|nK^zma=U7q#UoUrgnQIx*@_FGWUTD5BR@86$p za7vQP>6|@lR&H+Y%vrONl9CoISODjC~N=fU%`*ZbDox%>C;_l5i#Y&cQV z`hNI;RtX5OJlo*eXBsrUmymYq_=TfKPM`hp(vPRkUB7YD>CAUJX~|NE2`}S+1pl$~ z;=cf3PH^4Hd#7K}{_>e04j=#aE3=>nfOncKnHiZ@vpE#BQ-jJBtu~uklEAEpV$pLT zM6^6!m#!#*)&OUAzNYH=ZnsC4^Yio4Q!#(jolYm>*ladgmJvTFC`eU6%(T2*C$FfY zsygg;kIdak%J}%R1I5Zz8a{e#KtKRy+Q&O~eDTE>ZQHeL)20nnB+}kXOq@M?cEySn zF;`7yGt|NARjZC4KR$54KoCEw0hwjG>GVhN$W$gr-0XJVTeU&Ie5*v)SFIHv(>T?e zl#sUYT_GYeu76i8G#D0v*M;5tzdV(b+GaqXr=NKSrUjf5?FUnQ?dsKe^X5fIM?*sB z5eN+N4jee(@pwR?t5>g1xBkei(2Jl6iHS32%!rGN8#!{M%}UP{{YQZ01D__>#4x2` zN5+LO!=KPJFgeoBf@TsF)DSivEkN!95i?dbFgm&kN$i8YF+gX@0K%Cfe+r>=Gmx&~ z;~Y|vK_$vXR{0%096UOuq^2;np&e}A>o;!BaATeCdes7WaNc8OI{W=DcvwI?l#lvO~hkSJrsqS zQa53|qc{omCEpOuLJ}ezviUj}KdBQ7O(6RV8th~2tZ-@tL{q6CI8Ves(Nijdnb3at z;m5B*S9J&yt(5|OM7N*V{AGKx83ZGa0hQNjy&lqGbomY`ut9;*{WsEK3^=0ci5X3o zqM$A583~?lbJG0AhFJ@ap@9T~ez4g}Dx5u{f{Bl5OWc?#7SaGv5*p+owF6~~86ILM0_bs>4@4xfY~{Q6wWm^zlq6Vq(9f{EZECmmV|`BoGG>Nk!09300%(X{0Hk zzF9l)nu?s6f+LMf$_tu{Oc33URWzM!3RM&|7UxCcf7Fo7pg}^q*vDH`(X0@yq83MG znf%zXhdByr%Bn+kA!{c{^dv_?l_(LZI7C3ECbR?OM-x#VR2L*c1fq7-ipb7LL*^6p zfdGO^7D@e&xhu8SA$uGyf(gjN{UU$NS~aH&*o-I|rB z&i^=c)UYz8%3=uLzIp4dx84d551%n}CL3==4mWPxc;v{D!9#|WEKy?Gv}y31L4ado zV$dlXdXQbH|0i+n+O@@tm%x*!n*JSNe8P>OD`AK#3Vh{?m1@^)aQ(`?qesr%xOOiq z)2XVQ)#`|ejyZGYv@9$1bJ}=|u!iB0cw|L)fwld{;-3)_w{Kr$P-rewIljquW>I7X6 z`wbVs%<*~I*$dg*>JuhRFupI0I-WRweC5iO4H`7)+O;c4Dd~EYBnbKW`BSG%$<56j zKYo0Pk|jw6FxBIe?B5Ht7dBtnWb^1L9LBXtAYxLC`}sTx)B>T1hB!AkKuXwmh%O=ri30~jiN2yyG7`Z!(A9IYq~wr5 z;n64DC_AF6lrL3*`By9xN{d?124{u}Wi}f}2*-vTNUi%e#x$`Z8*<*5Cq$(dfbypR zy4XQQFHQkYg-W3Vgd&{Plu1sJ3zLwXOeE$j;Ps%-R~uLvVP#la8A!2Z%D6V^&pYojd@ZfrW*k4{r4$v}Px z%ab-%E4uK*2r^y7qP$rKbcCpM@0<2ZqgLSvB61jK(m#FGquLZ3Col;4CXtV*oG!73@4t*PC;WBfviNPBYc{c z1V9KPkQzr!R=N>^X)_99p`;>61+m<82^$?CHvSNK!v?8v3aLm)(%;bSusF=5_DvK&am0_U7)ZlcEMJ-50ij``?a%Xo+3p#?pnweb?Kwapi4*<0=1Y^BVspw1T zg6|puU4BGNk$5iI3F=%@u&lo9KeD32jI3$s5LHLJQ9Ga`Oo+gXV5w9E)(E7iSz_!+ zY$Re$P3=G?9S5 z5k<+QgUs{1;!WSN+jHPVRKw>(TRx-E>$YNQcGm2rOLId4r%#$C*{$@PGg^rrvDV(- zw(a28U%&FoE3I3%Mk#16IB)ak&av67V@8Y#4UbTH{pgXy?`~e(w07+_;iWRZJ{=U zc6K(alQBSl2UM6bUU;xyN#u*h#MZCdDDiH_rJruOUAo5&zgP$j4SV{jr#&9`nKNgR zK&8(*68^JC&A$u}wSymj62{mfT_otLD(C-r^jlH)mMd2>z+n#w4$jQZW|IQ5S2ml8 zb1I60nP8Gkk|cq^VKh7Q^S!c15(L@l@wz=whAC<3De38H=^6A2XiQA;`1qK}C{0l< z77OV#j)zeR3U%PMYKh4jM9ScwkT`+-soUjYZG4H+t0RETX5$!8jwmNJYb+xsGr|3O=!0%Ni9hpZ!FvW+r?i6wGU zm`Q=!Gcv?R35-@??Ld2WL>mnlA~T?ybU%>@5U zlX0V!Vi+6cOB(~p&wd)>8Ji&(0t*_1Rm6zQ(y$^KSOtCY>44%;N(NsX23D-EAlg_$ zmZYGy*>Rx&v}djkN~g_m%UCy2R!jgyLj+%*)EyK7Srz2wtDP?z3-KjjU?DyS4o;mh2}0C;%hhaY|bY!Vr>9vhowG{20w zMiH3a@l7S)FCuU7s*Q*Fq3dWP%0l6ogtQ?VBOcH#g_|#PHa%4qf#55MWzOcc?-T+_ z|4=5R>V1N-sm)GNIFta(fn;M5C>qPlmm^7wqB&V0jjh1c`ji9RZKFGe9D4;31^M1h zK)qm+X`@SwtN<#M6-VV#{*(i4tO%F`6WbV1qK%$`!GRIyk%lE{9v)CL7S^;drqMXQ zjUBTZ(SIahEkFqoKviZ3l)o>PFE`e1MivwWfvo*$ZwP}k6pfmT8qoOZON))FWu*2U z8yc0R^>qiy#u8Ghhd^>R7KmFJgdAbMv?#q$JW9wiVa2f;8Mze{WE}irBU%1afw3g> ziY)QES4r8p!+rKb**Dt-RjW*E8i4I-G9u*vc;WsBADfF6jqBb+2@C?kcFW$48#i1$ zeyV@p!PU!GL-Q&Uj37PRcJ<1YMT-`dFJHb--@YRIy1Sw%>(;J4d*al{zJsb&t|If? z-Q@cdW={@|4jS0JP2R`*?eVeEJzwVS0i0KTuw_@y+4He&o{y?u2O}C@X40*@3l}bm zDq3{Fuwhn<6%+RTOS3u{_pC1|;I%LR@@4x?k>(;H$J@;Iv z&Yj_Pvk_M~JpMG`t7EnSvMeuMvgF4fPve-mSAPT;Aety}k{~`?zcDX6u3kuVJ9$a4 zNfL;$Ug5E_R-5V2p>LCt9 z$l>5L&Exgvo-joLIe@zTx}otFNk>=5o82En9Zu#*NXVM;9wv6l9oH z>(7DLHA$32O#RfJ6oocR72SY@Tkm5ndNfK?hxs9n2uZP>73P+~ z7BX_f2D*!^j19*|ppnA26{Nx@&=XCJRgts8q#|?8BC(7Sf=mFN?&Y%w*T`WZxqR^p zH})WoQ7GkLWWYAcr~oW80s;|}MK%(!tuU&gUyWb`Ms5avuSSJIzW_^EP$$|w)MzXj z^HO{@e-3pTwCNEGI#$5IR z;iOdxrXP;!mS|x}!G@i2ieOA_Y`$FqSaH4*nV!Uf5yDijZvzl+*ba(Q5YDo~U%Gy1 z=qr|pfKyD>L*cWHs^CjyBxDhMdZzFvZIl_?jGyeR5d%AVG=$|(e~e@WzkbmO1!sPS zUj$OK7U(wvM(Up(F&TW-q^&US&tyZeuPz1E^TlJC7-IV(vptLA+W^QwlCT5nDb^Rp z^$4;Jlz@e@9daw|*1|o?MG|8m8G**b$Rwm8rvV%p+kY@v4d8~lbB`aryK8sEvkgLC zd{H&oaYoY>`hG)l@|{&1-Cl38zFo|*v4Se79C!HmciT2@XwslT`wku9p1_Y_Up415 z(le${pYC?MCrq3e6CF+5kK>LVJ-T|$nirbC*tTU`K{C6Xu7wNdC)~L;xz7O4H^;ml zXR+R0#3DsdUiPsc?ti$~Ql)bE>m4+!gI3sAybI^e&q&W4K5}Hy*rJjyoIibT#p+cR zDpVLWXpq@#MiGjlELymbp8Fj(3?Xx7&xX%DX3UtNz`%dL?U6s@oc!mXe-7ulFvK|f zH-R`bh9N_llBLU*s&?^Ag4bmhd54J>IMYHx>>;6!k9U4}?%Y}MTVJC8CHT~fAAb~v zf+(H*Bb1zkdJz{f$zRl9J}knSb5Jj)1ak49Q*WT=-CrWf|<#_T*j<+fI?q6TB2r4Fa z>`*Q=Ow=?<y7ViY5T^jjhi$wu?0oZHZrfLW~5J@G)c0WCrp_f6cj{x>-uM( zefH5uAGK=L>P09)dSeBAoJMITpf5DspMpujhVO&Z#UW}yE zG`kEliN42X3>rz-Kn~g4Hq6Ab9H=@*1h&yJ@+{Z@1QzB-8w){1c4gPMJ!}(pcXl+cr+Enqbm6}MELD)eWX*68k>==PeOL?*9DO% zk2FGI4s`VJhaZ0U@yOhHRHghKklDsYT29au*h!}JSRl<(+S9}&g}}52R5~)H>Bw}N zG1KWMOG4#g2LT=`A8fu%*u-ZchIq#2i&=1%HX{YmM-l_aR4I*gHK}XRQFeeN(9%pD z6W4_Crc1i)p-^Uwd>c+FB8Sb$3i(rROdf2=4bf43((UvHDz$*2@F@i9{bAi{BgM!n zOI0e!&8Py74bctxf4w~lqhXMXPcc4{$~b2<1sy+ff+R77VHZOQMs*4{mX{Hkk{g0y z!zs#*wWN`=Z!5?fVkqnZ86zQU43;N}=nE{&4I6$MpvZ;s4XIc!_`(Yc@(K2z2j