From ce2caec9571f41b8dbf30de6d9eed95411939979 Mon Sep 17 00:00:00 2001 From: chuxij Date: Mon, 12 May 2025 18:50:54 +0000 Subject: [PATCH] fix train bugs and add train details --- README.md | 128 +--------------------- TRAIN_INSTRUCTION.md | 103 +++++++++++++++++ config/zh_rap_lora_config.json | 15 +++ convert2hf_dataset.py | 50 +++++++++ requirements.txt | 4 +- trainer.py | 59 +++++++--- zh_lora_dataset/data-00000-of-00001.arrow | Bin 0 -> 4266024 bytes zh_lora_dataset/dataset_info.json | 32 ++++++ zh_lora_dataset/state.json | 13 +++ 9 files changed, 261 insertions(+), 143 deletions(-) create mode 100644 TRAIN_INSTRUCTION.md create mode 100644 config/zh_rap_lora_config.json create mode 100644 convert2hf_dataset.py create mode 100644 zh_lora_dataset/data-00000-of-00001.arrow create mode 100644 zh_lora_dataset/dataset_info.json create mode 100644 zh_lora_dataset/state.json diff --git a/README.md b/README.md index 912fb3f..65abda0 100644 --- a/README.md +++ b/README.md @@ -327,133 +327,7 @@ The `examples/input_params` directory contains sample input parameters that can

## 🔨 Train - -### Prerequisites -1. Prepare the environment as described in the installation section. - -2. If you plan to train a LoRA model, install the PEFT library: - ```bash - pip install peft - ``` - -3. Prepare your dataset in Huggingface format ([Huggingface Datasets documentation](https://huggingface.co/docs/datasets/index)). The dataset should contain the following fields: - - `keys`: Unique identifier for each audio sample - - `filename`: Path to the audio file - - `tags`: List of descriptive tags (e.g., `["pop", "rock"]`) - - `norm_lyrics`: Normalized lyrics text - - Optional fields: - - `speaker_emb_path`: Path to speaker embedding file (use empty string if not available) - - `recaption`: Additional tag descriptions in various formats - -Example dataset entry: -```json -{ - "keys": "1ce52937-cd1d-456f-967d-0f1072fcbb58", - "filename": "data/audio/1ce52937-cd1d-456f-967d-0f1072fcbb58.wav", - "tags": ["pop", "acoustic", "ballad", "romantic", "emotional"], - "speaker_emb_path": "", - "norm_lyrics": "I love you, I love you, I love you", - "recaption": { - "simplified": "pop", - "expanded": "pop, acoustic, ballad, romantic, emotional", - "descriptive": "The sound is soft and gentle, like a tender breeze on a quiet evening. It's soothing and full of longing.", - "use_cases": "Suitable for background music in romantic films or during intimate moments.", - "analysis": "pop, ballad, piano, guitar, slow tempo, romantic, emotional" - } -} -``` -How to get an audio's reception? - -You can use `Qwen-Omini` https://chat.qwen.ai/ to describe an audio. - -Here we share the prompt we used. - -```python -sys_prompt_without_tag = """Analyze the input audio and generate 6 description variants. Each variant must be <200 characters. Follow these exact definitions: - -1. `simplified`: Use only one most representative tag from the valid set. -2. `expanded`: Broaden valid tags to include related sub-genres/techniques. -3. `descriptive`: Convert tags into a sensory-rich sentence based *only on the sound*. DO NOT transcribe or reference the lyrics. -4. `synonyms`: Replace tags with equivalent terms (e.g., 'strings' → 'orchestral'). -5. `use_cases`: Suggest practical applications based on audio characteristics. -6. `analysis`: Analyze the audio's genre, instruments, tempo, and mood **based strictly on the audible musical elements**. Technical breakdown in specified format. - * For the `instruments` list: **Only include instruments that are actually heard playing in the audio recording.** **Explicitly ignore any instruments merely mentioned or sung about in the lyrics.** Cover all audibly present instruments. -7. `lyrical_rap_check`: if the audio is lyrical rap -**Strictly ignore any information derived solely from the lyrics when performing the analysis, especially for identifying instruments.** - -**Output Format:** -```json -{ - "simplified": , - "expanded": , - "descriptive": , - "synonyms": , - "use_cases": , - "analysis": { - "genre": , - "instruments": , - "tempo": , - "mood": - }, - "lyrical_rap_check": -} -""" -``` - -### Training Parameters - -#### Common Parameters -- `--dataset_path`: Path to your Huggingface dataset (required) -- `--checkpoint_dir`: Directory containing the base model checkpoint -- `--learning_rate`: Learning rate for training (default: 1e-4) -- `--max_steps`: Maximum number of training steps (default: 2000000) -- `--precision`: Training precision, e.g., "bf16-mixed" (default) or "fp32" -- `--devices`: Number of GPUs to use (default: 1) -- `--num_nodes`: Number of compute nodes to use (default: 1) -- `--accumulate_grad_batches`: Gradient accumulation steps (default: 1) -- `--num_workers`: Number of data loading workers (default: 8) -- `--every_n_train_steps`: Checkpoint saving frequency (default: 2000) -- `--every_plot_step`: Frequency of generating evaluation samples (default: 2000) -- `--exp_name`: Experiment name for logging (default: "text2music_train_test") -- `--logger_dir`: Directory for saving logs (default: "./exps/logs/") - -#### Base Model Training -Train the base model with: -```bash -python trainer.py --dataset_path "path/to/your/dataset" --checkpoint_dir "path/to/base/checkpoint" --exp_name "your_experiment_name" -``` - -#### LoRA Training -For LoRA training, you need to provide a LoRA configuration file: -```bash -python trainer.py --dataset_path "path/to/your/dataset" --checkpoint_dir "path/to/base/checkpoint" --lora_config_path "path/to/lora_config.json" --exp_name "your_lora_experiment" -``` - -Example LoRA configuration file (lora_config.json): -```json -{ - "r": 16, - "lora_alpha": 32, - "target_modules": [ - "speaker_embedder", - "linear_q", - "linear_k", - "linear_v", - "to_q", - "to_k", - "to_v", - "to_out.0" - ] -} -``` - -### Advanced Training Options -- `--shift`: Flow matching shift parameter (default: 3.0) -- `--gradient_clip_val`: Gradient clipping value (default: 0.5) -- `--gradient_clip_algorithm`: Gradient clipping algorithm (default: "norm") -- `--reload_dataloaders_every_n_epochs`: Frequency to reload dataloaders (default: 1) -- `--val_check_interval`: Validation check interval (default: None) - +See [TRAIN_INSTRUCTION.md](./TRAIN_INSTRUCTION.md) for detailed training instructions. ## 📜 License & Disclaimer diff --git a/TRAIN_INSTRUCTION.md b/TRAIN_INSTRUCTION.md new file mode 100644 index 0000000..df08e07 --- /dev/null +++ b/TRAIN_INSTRUCTION.md @@ -0,0 +1,103 @@ +# Training Instruction + +## 1. Data Preparation +1. First, check the format of data preparation in the `data` directory under the root directory of the project page. +Prepare your audio. If you already have well-labeled audio, that's great. +If you don't have labels, you can use the following prompt and utilize Qwen Omini to label your audio. The community welcomes contributions of better prompts, as well as annotation tools and UI. + +How to get an audio's reception? +You can use `Qwen-Omini` https://chat.qwen.ai/ to describe an audio. +Here we share the prompt we used. + +```python +sys_prompt_without_tag = """Analyze the input audio and generate 6 description variants. Each variant must be <200 characters. Follow these exact definitions: + +1. `simplified`: Use only one most representative tag from the valid set. +2. `expanded`: Broaden valid tags to include related sub-genres/techniques. +3. `descriptive`: Convert tags into a sensory-rich sentence based *only on the sound*. DO NOT transcribe or reference the lyrics. +4. `synonyms`: Replace tags with equivalent terms (e.g., 'strings' → 'orchestral'). +5. `use_cases`: Suggest practical applications based on audio characteristics. +6. `analysis`: Analyze the audio's genre, instruments, tempo, and mood **based strictly on the audible musical elements**. Technical breakdown in specified format. + * For the `instruments` list: **Only include instruments that are actually heard playing in the audio recording.** **Explicitly ignore any instruments merely mentioned or sung about in the lyrics.** Cover all audibly present instruments. +7. `lyrical_rap_check`: if the audio is lyrical rap +**Strictly ignore any information derived solely from the lyrics when performing the analysis, especially for identifying instruments.** + +**Output Format:** +```json +{ + "simplified": , + "expanded": , + "descriptive": , + "synonyms": , + "use_cases": , + "analysis": { + "genre": , + "instruments": , + "tempo": , + "mood": + }, + "lyrical_rap_check": +} +""" +``` + +## 2. Convert to Huggingface Dataset Format +2. Run `python convert2hf_dataset.py --data_dir "./data" --repeat_count 2000 --output_name "zh_lora_dataset"`. (Since there is only one piece of sample data, it is repeated 2000 times. You can adjust it according to the size of your data.) + +## 3. Configure Lora Parameters +Refer to `config/zh_rap_lora_config.json` for configuring Lora parameters. + +If your VRAM is not sufficient, you can reduce the `r` and `lora_alpha` parameters in the configuration file. Such as: +```json +{ + "r": 16, + "lora_alpha": 32, + "target_modules": [ + "linear_q", + "linear_k", + "linear_v", + "to_q", + "to_k", + "to_v", + "to_out.0" + ] +} +``` + +## 4. Run Training +Run `python trainer.py` with the following parameter introduction: + +# Trainer Parameter Interpretation + +## 1. General Settings +1. **`--num_nodes`**: This parameter specifies the number of nodes for the training process. It is an integer value, and the default is set to 1. In scenarios where distributed training across multiple nodes is applicable, this parameter determines how many nodes will be utilized. For example, if you have a cluster of machines and want to distribute the training load, you can increase this number. However, for most single-machine or basic training setups, the default value of 1 is sufficient. +2. **`--shift`**: It is a floating-point parameter with a default value of 3.0. Although its specific function depends on the implementation details of the model, it is likely used for some internal calculations related to the model, such as adjusting certain biases or offsets in the neural network architecture during the training process. + +## 2. Training Hyperparameters +1. **`--learning_rate`**: This is a crucial hyperparameter for the training process. It is a floating-point value with a default of 1e-4 (0.0001). The learning rate determines the step size at each iteration while updating the model's weights. A smaller learning rate will make the training process more stable but may require more training steps to converge. On the other hand, a larger learning rate can lead to faster convergence but might cause the model to overshoot the optimal solution and result in unstable training or even divergence. +2. **`--num_workers`**: This parameter defines the number of worker processes that will be used for data loading. It is an integer with a default value of 8. Having multiple workers can significantly speed up the data loading process, especially when dealing with large datasets. However, it also consumes additional system resources, so you may need to adjust this value based on the available resources of your machine (e.g., CPU cores and memory). +3. **`--epochs`**: It represents the number of times the entire training dataset will be passed through the model. It is an integer, and the default value is set to -1. When set to -1, the training will continue until another stopping condition (such as reaching the maximum number of steps) is met. If you set a positive integer value, the training will stop after that number of epochs. +4. **`--max_steps`**: This parameter specifies the maximum number of training steps. It is an integer with a default value of 2000000. Once the model has completed this number of training steps, the training process will stop, regardless of whether the model has fully converged or not. This is useful for setting a limit on the training duration in terms of the number of steps. +5. **`--every_n_train_steps`**: It is an integer parameter with a default of 2000. It determines how often certain operations (such as saving checkpoints, logging training progress, etc.) will be performed during the training. For example, with a value of 2000, these operations will occur every 2000 training steps. + +## 3. Dataset and Experiment Settings +1. **`--dataset_path`**: This is a string parameter that indicates the path to the dataset in the Huggingface dataset format. The default value is "./zh_lora_dataset". You need to ensure that the dataset at this path is correctly formatted and contains the necessary data for training. +2. **`--exp_name`**: It is a string parameter used to name the experiment. The default value is "chinese_rap_lora". This name can be used to distinguish different training experiments, and it is often used in logging and saving checkpoints to organize and identify the results of different runs. + +## 4. Training Precision and Gradient Settings +1. **`--precision`**: This parameter specifies the precision of the training. It is a string with a default value of "32", which usually means 32-bit floating-point precision. Higher precision can lead to more accurate training but may also consume more memory and computational resources. You can adjust this value depending on your hardware capabilities and the requirements of your model. +2. **`--accumulate_grad_batches`**: It is an integer parameter with a default value of 1. It determines how many batches of data will be used to accumulate gradients before performing an optimization step. For example, if you set it to 4, the gradients from 4 consecutive batches will be accumulated, and then the model's weights will be updated. This can be useful in scenarios where you want to simulate larger batch sizes when your available memory does not allow for actual large batch training. +3. **`--gradient_clip_val`**: This is a floating-point parameter with a default value of 0.5. It is used to clip the gradients during the backpropagation process. Clipping the gradients helps prevent the issue of gradient explosion, where the gradients become extremely large and cause the model to become unstable. By setting a clip value, the gradients will be adjusted to be within a certain range. +4. **`--gradient_clip_algorithm`**: It is a string parameter with a default value of "norm". This parameter specifies the algorithm used for gradient clipping. The "norm" algorithm is one common method, but there may be other algorithms available depending on the implementation of the training framework. + +## 5. Checkpoint and Logging Settings +1. **`--devices`**: This is an integer parameter with a default value of 1. It specifies the number of devices (such as GPUs) that will be used for training. If you have multiple GPUs available and want to use them for parallel training, you can increase this number accordingly. +2. **`--logger_dir`**: It is a string parameter with a default value of "./exps/logs/". This parameter indicates the directory where the training logs will be saved. The logs can be useful for monitoring the training progress, analyzing the performance of the model during training, and debugging any issues that may arise. +3. **`--ckpt_path`**: It is a string parameter with a default value of None. If you want to resume training from a previously saved checkpoint, you can specify the path to the checkpoint file using this parameter. If set to None, the training will start from scratch. +4. **`--checkpoint_dir`**: This is a string parameter with a default value of None. It specifies the directory where the checkpoints of the model will be saved during the training process. If set to None, checkpoints may not be saved or may be saved in a default location depending on the training framework. + +## 6. Validation and Reloading Settings +1. **`--reload_dataloaders_every_n_epochs`**: It is an integer parameter with a default value of 1. It determines how often the data loaders will be reloaded during the training process. Reloading the data loaders can be useful when you want to ensure that the data is shuffled or processed differently for each epoch, especially when dealing with datasets that may change or have some specific requirements. +2. **`--every_plot_step`**: It is an integer parameter with a default value of 2000. It specifies how often some visualizations or plots (such as loss curves, accuracy plots, etc.) will be generated during the training process. For example, with a value of 2000, the plots will be updated every 2000 training steps. +3. **`--val_check_interval`**: This is an integer parameter with a default value of None. It determines how often the validation process will be performed during the training. If set to a positive integer, the model will be evaluated on the validation dataset every specified number of steps. If set to None, no regular validation checks will be performed. +4. **`--lora_config_path`**: It is a string parameter with a default value of "config/zh_rap_lora_config.json". This parameter specifies the path to the configuration file for the Lora (Low-Rank Adaptation) module. The Lora configuration file contains settings related to the Lora module, such as the rank of the low-rank matrices, the learning rate for the Lora parameters, etc. diff --git a/config/zh_rap_lora_config.json b/config/zh_rap_lora_config.json new file mode 100644 index 0000000..6057c90 --- /dev/null +++ b/config/zh_rap_lora_config.json @@ -0,0 +1,15 @@ +{ + "r": 256, + "lora_alpha": 32, + "target_modules": [ + "speaker_embedder", + "linear_q", + "linear_k", + "linear_v", + "to_q", + "to_k", + "to_v", + "to_out.0" + ], + "use_rslora": true +} \ No newline at end of file diff --git a/convert2hf_dataset.py b/convert2hf_dataset.py new file mode 100644 index 0000000..81b9872 --- /dev/null +++ b/convert2hf_dataset.py @@ -0,0 +1,50 @@ +from datasets import Dataset +from pathlib import Path +import os + +def create_dataset(data_dir="./data", repeat_count=2000, output_name="zh_lora_dataset"): + data_path = Path(data_dir) + all_examples = [] + + for song_path in data_path.glob("*.mp3"): + prompt_path = str(song_path).replace(".mp3", "_prompt.txt") + lyric_path = str(song_path).replace(".mp3", "_lyrics.txt") + try: + assert os.path.exists(prompt_path), f"Prompt file {prompt_path} does not exist." + assert os.path.exists(lyric_path), f"Lyrics file {lyric_path} does not exist." + with open(prompt_path, "r", encoding="utf-8") as f: + prompt = f.read().strip() + + with open(lyric_path, "r", encoding="utf-8") as f: + lyrics = f.read().strip() + + keys = song_path.stem + example = { + "keys": keys, + "filename": str(song_path), + "tags": prompt.split(", "), + "speaker_emb_path": "", + "norm_lyrics": lyrics, + "recaption": {} + } + all_examples.append(example) + except AssertionError as e: + continue + + # repeat specified times + ds = Dataset.from_list(all_examples * repeat_count) + ds.save_to_disk(output_name) + +import argparse + +def main(): + parser = argparse.ArgumentParser(description="Create a dataset from audio files.") + parser.add_argument("--data_dir", type=str, default="./data", help="Directory containing the audio files.") + parser.add_argument("--repeat_count", type=int, default=1, help="Number of times to repeat the dataset.") + parser.add_argument("--output_name", type=str, default="zh_lora_dataset", help="Name of the output dataset.") + args = parser.parse_args() + + create_dataset(data_dir=args.data_dir, repeat_count=args.repeat_count, output_name=args.output_name) + +if __name__ == "__main__": + main() diff --git a/requirements.txt b/requirements.txt index 03a1352..718f060 100644 --- a/requirements.txt +++ b/requirements.txt @@ -21,4 +21,6 @@ accelerate==1.6.0 cutlet fugashi[unidic-lite] click -peft \ No newline at end of file +peft +tensorboard +tensorboardX \ No newline at end of file diff --git a/trainer.py b/trainer.py index 1c7ddba..4ec1235 100644 --- a/trainer.py +++ b/trainer.py @@ -64,7 +64,7 @@ class Pipeline(LightningModule): # step 1: load model acestep_pipeline = ACEStepPipeline(checkpoint_dir) - acestep_pipeline.load_checkpoint(checkpoint_dir) + acestep_pipeline.load_checkpoint(acestep_pipeline.checkpoint_dir) transformers = acestep_pipeline.ace_step_transformer.float().cpu() @@ -90,9 +90,33 @@ class Pipeline(LightningModule): if self.is_train: self.transformers.train() - self.mert_model = AutoModel.from_pretrained( - "m-a-p/MERT-v1-330M", trust_remote_code=True, cache_dir=checkpoint_dir - ).eval() + # download first + try: + self.mert_model = AutoModel.from_pretrained( + "m-a-p/MERT-v1-330M", trust_remote_code=True, cache_dir=checkpoint_dir + ).eval() + except: + import json + import os + + mert_config_path = os.path.join( + os.path.expanduser("~"), + ".cache", + "huggingface", + "hub", + "models--m-a-p--MERT-v1-330M", + "blobs", + "14f770758c7fe5c5e8ead4fe0f8e5fa727eb6942" + ) + + with open(mert_config_path) as f: + mert_config = json.load(f) + mert_config["conv_pos_batch_norm"] = False + with open(mert_config_path, mode="w") as f: + json.dump(mert_config, f) + self.mert_model = AutoModel.from_pretrained( + "m-a-p/MERT-v1-330M", trust_remote_code=True, cache_dir=checkpoint_dir + ).eval() self.mert_model.requires_grad_(False) self.resampler_mert = torchaudio.transforms.Resample( orig_freq=48000, new_freq=24000 @@ -101,18 +125,13 @@ class Pipeline(LightningModule): "m-a-p/MERT-v1-330M", trust_remote_code=True ) - self.hubert_model = AutoModel.from_pretrained( - "utter-project/mHuBERT-147", - local_files_only=True, - cache_dir=checkpoint_dir, - ).eval() + self.hubert_model = AutoModel.from_pretrained("utter-project/mHuBERT-147").eval() self.hubert_model.requires_grad_(False) self.resampler_mhubert = torchaudio.transforms.Resample( orig_freq=48000, new_freq=16000 ) self.processor_mhubert = Wav2Vec2FeatureExtractor.from_pretrained( "utter-project/mHuBERT-147", - local_files_only=True, cache_dir=checkpoint_dir, ) @@ -578,6 +597,16 @@ class Pipeline(LightningModule): def training_step(self, batch, batch_idx): return self.run_step(batch, batch_idx) + def on_save_checkpoint(self, checkpoint): + state = {} + log_dir = self.logger.log_dir + epoch = self.current_epoch + step = self.global_step + checkpoint_name = f"epoch={epoch}-step={step}_lora" + checkpoint_dir = os.path.join(log_dir, "checkpoints", checkpoint_name) + self.transformers.save_lora_adapter(checkpoint_dir, adapter_name=self.adapter_name) + return state + @torch.no_grad() def diffusion_process( self, @@ -808,7 +837,7 @@ def main(args): num_nodes=args.num_nodes, precision=args.precision, accumulate_grad_batches=args.accumulate_grad_batches, - strategy="deepspeed_stage_2", + strategy="ddp_find_unused_parameters_true", max_epochs=args.epochs, max_steps=args.max_steps, log_every_n_steps=1, @@ -835,9 +864,9 @@ if __name__ == "__main__": args.add_argument("--epochs", type=int, default=-1) args.add_argument("--max_steps", type=int, default=2000000) args.add_argument("--every_n_train_steps", type=int, default=2000) - args.add_argument("--dataset_path", type=str, default="./data/your_dataset_path") - args.add_argument("--exp_name", type=str, default="text2music_train_test") - args.add_argument("--precision", type=str, default="bf16-mixed") + args.add_argument("--dataset_path", type=str, default="./zh_lora_dataset") + args.add_argument("--exp_name", type=str, default="chinese_rap_lora") + args.add_argument("--precision", type=str, default="32") args.add_argument("--accumulate_grad_batches", type=int, default=1) args.add_argument("--devices", type=int, default=1) args.add_argument("--logger_dir", type=str, default="./exps/logs/") @@ -848,6 +877,6 @@ if __name__ == "__main__": args.add_argument("--reload_dataloaders_every_n_epochs", type=int, default=1) args.add_argument("--every_plot_step", type=int, default=2000) args.add_argument("--val_check_interval", type=int, default=None) - args.add_argument("--lora_config_path", type=str, default=None) + args.add_argument("--lora_config_path", type=str, default="config/zh_rap_lora_config.json") args = args.parse_args() main(args) diff --git a/zh_lora_dataset/data-00000-of-00001.arrow b/zh_lora_dataset/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..f553fff36dc39e8d67b9518b19cf89d9c0d9dfc3 GIT binary patch literal 4266024 zcmeF)dwh@e|2Y0RB%N1DtE44qNz8d6<~-*)kHnnkJjdqP2#wGPjnI;`BrQox(vq|! zElEq#LRv^mVj;fw*Qa-%&-?TF{eHLK_j|kj{`v}w{$Mv|j>v>(i zeED)%iI9-ckihNgkn2NAg`@R14 zT037SR~RyK(5MRa!Y5Z4G_dcu@nZ&#{f`I322T9@&VX?f69;;#!q{41N-+)95-at$iPTb z-F&v!kT8DmU?0_>zWoPUQz0R>e9mWlUBQ6BV*=~u%%#hht)c4z>$Tj!p7SN-D*p3( zyI)|ra4}%nEB@!Qf${$Brw=J(xwikdY(=jJ#tPg5@BN=2QsDU*%P0T+o@>i^{Ljx4 zh@HUW!21Jh%a@RGmRtXC-#_eMuLoWWEH`A_z!8D_D=f3`-OI< zDN!;c@N?#-ga=-ByV~Qw^C6H!4ZJt-*%ZjJe{MJZbLao&>zW(>elp`5wRVIqSN8g2hBr=V8EGL7_>|ihXoZ=!^`v}9RL?BO_5KC`{Gl{^q zbSZ1tNH%*o$Z?7&<)bP?1tMukTLK?p0uz|YBGTEwR(6rcG0sptu$`woRj5Y{-59_a zl3BnC){(_d_Hmd(E^)17xt$2=(2P#RGmo7ur$@;SvtuC_4>qY|}fLM*)*&LmP;${IG3%^nVNoFYouXqTY^ku;<& zJxO2!Gg(AB8`#P&@;JsBirXNCQl2W*BZh7aU<}DDUQVki4JOd*%JR<U2o7ur$@;SvtuC@&iqY|}f zLM*)*&LmP;N?^OVk!<#GkmD3lN&zWD1tMukTY8ef1ZJ{`bT+V+UF30$GZeqk`lmcq zs7DOl7{C~kS-=X`k;P8-ahO6bajhbDI}y~O8J&n{BvY768f)3ac5*qyNzPOHX6v7d z)F7Jn^kOJU%w{pG$z&V5IY0qtDXBo;L^xGxKx^U{#5iV<$|}~gg&g*Cl+%RVV*OK& z%0$tEF7zXjY0P6e8Ej?;d&%b%7rDBu^-m>g(S%rfGn`4Ju#`1yB%3`PwK0y9}eIvd!^F7i0W8H(Fc38g$$s7DOl7{C~kS-=X`k;P8-ahO6baqVr^ zKM~ZS8J&n{BvY768f)3ac5*qyNzPOHcI%&t)F7Jn^kOJU%w{pG$z&V5IY0qtDS3zW zPdHU+Kx^U{#5iV<$|}~gg&g*Cl+y$X|MirkGEuak3;jrB8uM6A2AkQzUh+A`MXtWn z`lk}LXhJN#8O|h9SjrkUlFc3ta-1Sc*+nWt1tMukTY8ef1ZJ{`bT+V+UF30$GZeRP z6iRujP>&e8F@P~7vw#(>Ba5Bv<1mF>;@WWQp9t#Ej84Qek}1q3jkRoIJGmUpWU`Ij9H4-+l&oO=6HZkc(3&^~F^(CevWoR=A&31OHH=}7_;n8_m2*}ztIk;gI4 zQ2asbpYl|p9x-%d0AomI0V`NX7CYI;VG6m#wNz|6$Ae#2{Vkk+>W-+VDWE;CVKmlhd8EO3!PE{Jvnm7hAjv1t~iuG(Ehy5Jo zG$GZkf67srC|b~kek3xDc`PS`&Fo+=`JCb+SJ$xqsYETB5KC`{Gl>+IvWAUhvxkEm zr-)KDt$!*INkiJwlLRI(lSQPnfvxN!k7JyncrELn@>HQ7F?3@9V@PHJD_BPsJK4u! z3c19!wXJ_5s6#V45zk1bFqbsevWe~Fa)^_hr*s|bpNiBVn)dW!C`rs_F{{ZWa2q#p z?6^MT#`Nt!tWRWQ_28r6ClQQ-U_J!51;MRiup$JjVXztot6{Jj2CHGP8V0Ljuo?!d zVXztot6{Jj2CHGP8V0Ljuo?!dVXztot6{Jj2CHGP8V0Ljuo?!dVXztot6{Jj2CHGP z8V0Ljuo?!dVXztot6{Jj2CHGP8V0Ljuo?!dVXztot6{Jj2CHGP8V0N3|2Neza1NVO z@a(viX`*Tv5vTmeeFLXG>p_c$&4m$39L_{K}A!+lZtky%|qnK9(2R!WR^9nX;ur zLLQ_Uk1&Qgr1Lg`xmJGUA~#>Cq$|UDg5|tH4&QT@ z>#lKrBlQW)kurp2o@E0cagg7+`r43?yNRL$gP2NS{*zbP&Nmct<#o>Gq&98o&mG$^H!-w3m#=0PqCVJ$mJ(4aZ9N4Noh)8 zPLk22@I0IOjH6uOrW->-?kAe=jARyp`9|Jk7e7$M4L3P=mWS!WFlMlfOg<(sm&hMn zd$UvbsYgc=c$}rY#ty#aG*^{zo-lQ3&p@W|4D0xSJbtCrEg>OyQj0bO<^Y*UDlfB* zuQ*AGvd)R6Ix+NN0`m#X@9{2s`I$iS-%3@Q(~GgphBKxYDTZcHbQ*V)N;oZ%YtV^rWF zVj0XdmJpav<3kSc8>P*EaTj%H#{ed?h*!wwYXWm+Tw#uja@3?XeM#bJ*76?vI6-mq zSlmWn9*masW<2wFku7{d0hcLju8Id~#v=sgxR^saZ?lIVxya4o@}I`UF^bu&WD}oq zm_G@j#I3X{HGc%c$9HG z#cJLmm!AmC1#!!L@}H*kWHc!}&t^X3C>OXXLjDt&=b<|znZ*j;WEVeB#0~e$e;%d_ z!wAgbu#8MT<`92yZDsjSJvx%W<1FPh0`oI`%W1B9K>kyg_6%eS&#;aU$m3T6b1&RU zE!xnJiKOx}+xUu;lz347Q=P!P3VoQseAe(Td-<6_;lGutG^ZD13Cx-B0$F^{G5(@V zHTh2ydXUJItl}*K^C2AJJU2$le;Uz^5zOQ{Hu4GioFg#T!M!w~Geen98n3gH?>NIX zHRL}J5tzqdFw7{Fu#a}>NnHeYj!D{9GqYSNm%B=IzBd5^&S z11Bh6TmBPCOL{Y&dA!ILzMz211m+fakY+r>80L`9+w9>-E^>2S`A=iw7{zQ>vWZVQ z%%6lt$$uKsmEkWnL56OS((}^J@^DGa-3oh%YUlTf=3z0Q>^A4a`}l% z+|p3~)0Cc!CWYtO%x4_s0yj01|3uTBk<4NRZ?cOYDB^}_`Om|2VHh)5MkXI~h(EZt zvHYhV9ZBGEmhu`q_?FXL)kOYNm-Y-~3eT{P56I(JN;Q@L)S?ajm`ExwvyHDfNr`6i zpX$WWhY8GQ4ezp-p9$>r-%3@Q(~Ggp*}@kTaGA30eGoK zB=amA_=to2&ea{|KT&jG5K~#qt8C{R3c0eA{HHc;>CYq42WQo{I}_-f&mc>h+shc^9!?JHUzUF zm<_>fFi&G}QxMz~1UCi2O+j!|5IlqsJgo9>6Bq{zW3Vs=3uCY_1`A`bFa`@_urU68 z!a;DaAh=f$+$#v~6$JMRf_nwQy@KFgL2$1i_#1@aUmgYj@+kP1M}gB2gWXZEI|_D3 z!R{!yDF}8)!R{#79R<6i;4V?HI|_D3!R{#79R*L(3ZAz1?-TU|j}-)u6$FnJ1dkO2 zj}-)u6$FnJ1dkO2j}-)u6$FnJ1dkO2j}-)u6$FnJ1dkO2j}`O{?h*xeiGsUC!Cj)@ zE>UooD7Z@$+$9R`5(RgOf`4Qioar+-`{{pO^(Xji)YrnPibo4!Pu!PXUD#5mL^yM?486l0-5oq>@HD8Dx@0HaX;yM?M7g0fiJ1 za)t2;C5&()h$M<=Vu&Syl*d%joCzLS4i6D|F zqKP4vIO0hlktC8yA(b@J$sm&~vdJNrJn|`^kRn2^G(Mq(5l#ew>wiTNO$@Qb5l;e% zB#}%Csicuk2AO1$O%A!_kxv1I6cI@N(u5L5I1xk=MKm$Q5=T4g0fiJ1a*go`C5&() zh$M<=Vu&Syl*d&ZIPbgu86G0?_YqUiZLo9K` zlRzR#B$GlaX{3`uCRt>YLoRvbQ$Qg_gj{EQLJ1?B2qK9hniyhxG)>12>e7TM&GOCI?Y zP)HFWHyEE#0@tJqCxS?#h$ewe^2n!vLW&3!{?ddJ zMmP~f5=AsI#1cn52_%w4GAX2zMmiZ}l0`N-)YrnPibo4!Pu!PXUD#5mMIpgc3$L5kwM2G%>^y zM?486l0-5oq>@HD8Dx@0HaX;yM?M7we^2n!vLW&5v!}x>}MmP~f5=AsI z1g=LJM?486l0-5oq>@HD8Dx@0HaX;yM?M7xG)>12>e7TM&GOCI?YP)HFWcN(8i!U!jVNTP@)hFIc=CxJwgNG63;(nu$ROtQ!( zhg|Z=r+`9=2q|xTLJ1?B2m;sNj3SyCVu>T31QJOinG{k*l~0tzW2 zTh7p$uVE z;6b8jOiS9*l^*nGBomoIpf8`#QkJuZ*V)2{e8L{S=39Ow(3fAJq~7>yZXk?uRH8Z! zXighq>A|B6W(-rAP2if{3t7%80)6?LY~y1-V=v$GJwJ1Xz;(S#>y5AHX37yxWoi>m zD>~4HN9oHjCNQ131bXr%tYS6m30xC=JD>6e`}v+D{6e57FQG5KmYcYha4J%jhiFDS zIul1<1`@cQ_#|erfW<6hHERj<e&86t@;iS~T2Fj4<*2}YL{f`}w4w`-61X0F0;3tvOf2cL6*BmB%M&T)Y&^uwXtK}9MPxJG;w4G3H-z9YRD$S@L_$W)$W5i42C zdfs3Q+X(dGUvh}RwdH@|G#9wcRr=vF+(iUcsYwH(X-!w+8Nw*WF_q~&#Zq2i9f2PF zEw-_p-F(eqPVgINxl9SY@O6Z74^^l^U7~45dwMW{5sW2?=>)EE|1`^ai4APx9k#QR zKo9;c$M}^$I8O6Okoytc!pKH!bSr9_j~MQ7yJ00 z=)aF}igWx$ zaXs)g+`w&Aq#98)q$zEQr6&VPWFn6tAF+qM9ONfXbAe)ZCQESx zH*+Tu)T9ATXh|$x=*+> zb%~}0ZRkQA{TM+K(|MA4EMXZhvVnKlPN47pjQt$oD8F)^5_;dOxSm_NgL{djKFw%N z2jb|(AVxEVSv*B5%UH?FY~($5vYRhBz##&C_wQWdO19$vKMad#~X}%5oR?@E}n%r7fN4PCNq`$wX!{ zpJzzp1zzHHw(t>q*vB^<<`{vV`vRr(y*F?Rw{s8oQJn^~B$jSG!T=H&!&FjO$g`~A zC0^l8w($vj3H00Fag5`f;WAh2dvE48%5xtNP@8Dl(1o7#A%WpcU^??y!gB=r?N@k> zx7p5T?B^gqaGX;F`t1^W-s`!QJE_0}RO2C<(SbO6)1ToaGKpEFvW(|h!)v_3yX@o( z4iMm7)&DLn8q9yvyvAH^xALm7Voo*uQrGnh{rFYq$!d5d@WkUf0EVFG>jFP!B( zCH2xba69*KKUJwqeVP-?BMe|Dqex;3vsuUrUgA|Ud58D-n7w?*F;4Ou=eb1baB)X@ z?&CpfP@hJ$q6>XUU?gLiLNaq%LOQSTI-7Wp5BQY*{J?Pv`GZRozuUeQw^D%zs7@Uk z(Uf+?(VyXr;W3h#$pV(KhSzwLEI!~PKIZ^Ga*8wjN%0DDo>1WBkT>Lhe;#xt^OS$9>eGK8EXpbm{_PHQ^ToxTj`F_M|hQ!FNp)x1U)AMi1|`HF8i!YTfw z_nO|ZRHPd9Xi6*E)15~cNFtM&$y}Z$jTNlr4Yu+TpOVWre8*3m<}XS`$Tx1} zcFGe$O&ZdYc68zq`Y?oXJWdJ=c!m|EvyQjO<`X_=AK&o3>@*Hc(U?cC5!xwzbL4M?Ce&-TbJs{=?<4!73nOZcWHJ#}}Zw51r@g(yU zi&@U|WU!vie86tL;#>0hnO`_Z@hW1DvXtX)DpQpxn$n)`JW4-?F^Y-IU2&b?Hn1`TLQCmx|MgBZnFrjo)ltY9@SlgTEw@d^9* zjw2NC8-H+_tE-AR%2Sd1sX-m0X+t;qFp!~)e+BPS^2PyXV{NO8xV zRH6#isYgR%=uB@0GlDTp=5gk*nCHo018=gGYvYB_;K@NNQjskw;92dEwrkv+y%5y(8h~i;d(3&pvVJKsn$TXhh zDVC7Vt88Km?~}uB_VWWL`GX4tegSh8*KsQqc#t|YpfRm!PaORj$zx1q22b%c%UHwf zWU-A8*-b77_>n^X+XJ)P*qV8$?+>CEP7o?#^!yvbI!^D(*X z;}Ab{hQBCLM~&r1Zs9H}Q=5h~qZOU#Mm)oqz~jtfF3<2RFR-4s$z~^?vX49t^9w~3 zt1I8QmRq=ud#K7oG$Dp|bfYH&7{w%>U=9m-mgjhhOx|S&yZD?u4swj&xX2Yz@{Le# z<4*3Q1`pGMwsfQ?y-8p!(|D5kEaEwy=M^^bJ~`~+OAeCHasD9WAu-1dl;KY9<^k%^ znAXJ7mEQDYIFB)dr&!2Rp65kgBa08&&0fAHpQD`OPfFGkbKFcAcXKb*s7G_!(}f=N zV-SfJ|>s_e9KV^IL%*_t}o`em2%w6{nVr(t>{D?k1~j%jN@_U z@(jyZ#ml_PTV(So`#8Y&6mXKW6l);nxP?0i=YAffE=_1hH+s>Rp^PMnCs@F z@;dLZgU`w15JxykA?LZ`VKK*T+(ktmq&oF!K}UKL&p<{phABMBBA(*~*77=U@*X*S z$w3bD6NQ}N5?3`8bKJ>2L{OdDG@>CFI!Fop>v^At;Yo|jn1o4m~j?B;9oImQXj zP(<-Y;*K!x=02)Wn}=vhdwS511V%7{NzCMFmh&R7uz|OEmygKhTaI#^Un$}urJ}_h z<+zszh~yz2rX`(tltBzNKD^ZHT1@k207sOl3CnSjci#k-?j6<6}N!FW>S#KXZo5lx`*8xS4WUC z(~1ss;ZgcBj0sFd#j@;P5|fFu0GZ(QWcHe!yl+(AVmsKLX;(2?%+Vjx2p%QWV& zh%{ERmUV36eRlCB-*AYZIKdx;v=wud;dbsKf-2OZF>UF}Bg8X=5j@5W=ChO)yudm( zkj01W;cLF*FemtxKPlNx%n?R;?x6~i)T24E^q>y|7{O>JGn<7hC!Lqrz(%(6F?;!z zA2`OZ{LWvLZZGC2M+NR9l3FyR6=X-wSIKOj_ zVjaXCw-Qbz9-tOcG@%`F^kp!^8P7zXU;)cmO$M*AnJw(#a}IEXpE<=jE^tMxxZ@5g zQkiN*(SR0oq!$AjMj{iL%9AW&C2LvF8*E`4Ief_>e&QESbAiiT)luAW7ZFsYCJl(D zHC>5k2%{LsRHpM3OL>8HWbzi<*v@Xg<}fGtjk8>)L?`=JgmDj5s6kz#X-0c`Fn|$^ zC5h?G;%S!i5*ygWJ8WksxqQnpe&r9&Q=+q+=SIqLACc6dKFx@s6OWR>XdYtJV+2V|=Sk+Vgk`+Q2Hs&iIef-`4seuTIZuf=`Ns9!${pNG zB=u=VYdR1|F9tE1Da_(2Qd!1IUS=cjv6J0=!2u3Y!0%k*${zBKo4A9!xSv`yB8K*K zrWf%HWjx8u;b|7Lk{5WD&3wQva`}ow9OfkFDBe@daU*59i+gyGD4NoiPIM=p0gPlK zGnvmbr11hT@j6@hh&}A%8xC`fLM~A15i!Rt+|E7RM|B#|l32R&2m?r93{y#AA?rGnh{rFYq$!d5d@WkUf0EVG8(#vz(`7ytw0b?%{r_ zQkVKPCzeMTz)(h!#1v+;kQKbdt7P&H@9{Bv`Ho|pXOneJgII0uNA~Iy9mw?TDj4!x_V4 zBr}r*EMpC?@g`Y(z(;(}0e<8ZXZVxi{pCEN+(9L(QJZ=+r6nEd#b6Sdz+`5U!Xj3Z z!5h5IRzBhrzT^-;bDARlqSOF6PZ{o_GBtUKhP0#&U5RHHdiuvALcw?x8Amd6*`&p#wb_z$lWK#uLmVmF2udChzb*JNS$*_?Bb* z#(6>psj*zoO_bw4YEYlXw4ei>d6WdkGKCpDNh*t3#Vc&$Jw7CdFZhb@InEzkqU2yT zmYXO`I1f;VMl`22o#{?rhVvN7%;qT;lg4UZBa09CnB9EEHyq&8@ZkGL{O84w4@!K zc!WL-VH}T>!UCRQ1?jBgEwcH9&)LU!{J;s$Qf#Q0Ba~YxPX($_mnO8KBi-mje@2kR z6U<`~&yvm>Ht-HR_>3>f;|G4^SI%?AFfm6NZleN~h@?I(=s;I`(x1VMW(rS|%2J+V z4H<0YJ#zShuQ|w%{LJrM;;P|djxg?|5|yb%BU;m$9`t4~!x&F8PqCQgJWmGe*~|y* z<}1D>pP%`Ka}*yT<|s=!?xr$TiJ~d(>CU6{V;G~D$V{Flja9tJdNSFBvc8Y$+uopA1@Dm7?8OFHogeHp|k#xj)@o?!*6d6`T$v5imI$9Ei|fZzCo%UnH5 z%u$|-+)oYa5KSAp(T9NyWh{>|oq0S=m5HP_4QWDKy3>zgjAjCl z^91ur<3-l9k+;ca2YdL2qx{0}6j5xfoaY8^=U%E(i-%}J3u1YML5yNNlX!wBS;z`r zCX>y)%MNnb%Xbv;8|S#l731VQH&dSbsX-JE(}LD?p$|hD%S5K}Bu}w~bY5i>TX>%w zcC()!ILRMeAaH`^Rb0odRNz7C(16CYraf`=XC#j?l^Hz6(=1~Ruam_#K4dq!9NHntYCOia#kiSTltt=_VX=ADd04JQF@A)<5tRXFZWZEhP0v+aXiW(hBA)FnaeXQV-+v+DsPd^ zr|jbZ-&4Rz&QffunBx}iAe{Sokh(OX9o^_fUxqT0B%WXa&$5!$yvpmm!wxzMh<|hg{!zHeI zT+DGN_YgsKYSW0;bfq@~7{VAPkjzso<#}FW9dGhBAF!LR$>$g+I71P|lf@lj+|7Md zp*9cEl=k$X9|??L0+X1@(=6vjUSR`o^DZBe%eNfmIKNWFMM_N4K zV=b@q7F+m`kNJXw{6ryVxj@O8a-N&GlL)F)mj*Pa6`kqL5XO+iRAw`m#XQeC-sBy& z@iCwB75SXt4ClE_=~;4~vfND-YEz$RTG5W~^kW1Qn8I}CvVb&RWCL&W9^3hp&-sR< z{7Mm*C^6gEgmOFg63Ig}q8aVz$RiA5G?PeX77JL!3SMR-@A3gV`J6BLjskw?BE_Fn zV+o}U<+-0)JWNw!=tx)kFqH93VB=L-GlUU5#ti1OlohE1`Ia9z#;^R&UzC1Y z%u$XC+(#s}XhE5fjcg{HPub7+{K#>B=N!dS#T~a2P9+|o z7Ev^z9dYz!FvA(oM4n&)%UDeYud$ge?BH__aD<;Z#W^l;#X@n%9aN+;)rg`2E$B!u z1~QC9CNh;LS;R`#vYt2C!ZvdFl0*E&FP!EAm$_<@xZ^G&s7g&55KU{k63-AuF^;KB z=P8!*0_(`+Ew-_p-F(eqPVgINxlD;?>{}7WJyf9vb%~}K?dib)MlhBnrZbDDS6jAt^*%wayyvYOY}%vL^N7kkL#2&Xv5 zUld@*Hb8T&cFQGVq-C6>uIuIEnuqnoevIk2%F}RPLd=^s3b{3l7u8lNGeH^RFWh~Hit@5Ns@lIc^@v{ z@Avn){4ST@f4|G`a_jQG_0F)p_T1y~dT!U(^LeLdXd=BtGwBU_mp-Pow1K{(9ki47 zQl$y3IjT#A)PRnr1OIkJ*XGmMGw*_dYYc2DKwK_rG>PNKBe`viOOgv z?WX-y1hAL$p`M+YcvGV6}&(~)#6HKo((Y`TQn(k;}Lim5lNJK90J=yy6m$71gB%bTpkn&FE}8k1nHYsU!8EQo4f%(qI}vPtz2dNw3j- zdWYVpPiQ@r(N6k}{-oq7?0L$hdeo4Pqm!vQokthZ6?7wYp1!&dUuYl2i=1OAgR-cAj-;k^I-N@w(&cm&-9%lfH{C;n=ph2GS6E zghta?noKikKD|R9&`SD(zM}7GC;dsuFR|aK2IWvb9Zttlb2^VMq1JQ_-9Saui|(eu zG>k^lSQ<}L=~Y@p@6$)Ln!ciMXe;fezbSP(`;BT*KGmm2bRwNa7tv*OCEY-`P&evB z_t8)qK~Kby`9n(kHZrzM=2v2iikPFSF(-lj=}?YCy-(Db#{4r7Nf%-9jCy zC-tWXXgEDiPtio0LbK>iT1p?&=d_N#qcZxL_EF^-tU1c2JZeA<>3BMwE~LxpYPy~} zQWv_N?xBZh6pf*0XbMfEIrJ7Sr%&li+CXKroqnYQRCOk6j&iAx8d76AiO!~$bQN7k zH&YktPJL-0Jwl^t96d+VXa>!rcW5PjL0{7*+D<>wACx?cHAgvAK!;LeYC@;ddDNP& zp_`}!b*B=#lLpgB8cP%Cd7449X#u@YtLZEHmbTDO^b7q(sjsl+D4!B^1T~?ibOv2S zSJDmCo;p(r^`?7iC_O>rX)?V?vuQ3ZrVnWieM8^VHu{Brr++AYHfxUR)8TX!HKk^B z4qZy^=oTuX+o(6)LHE;edWt5}RC<}_(tLWCKBjf_9c`r_>38~*D!t0OqdaOrjp$fv zM$PGbx}2`3j?|5c=?=P^9;8w93{9cw^a{Pe+^H{C}M(`b5*rqL{VjTX@oT0vjXCfZIv({J=QCB4S?R+K}B zQe!%vPNuV{1+}7Ur~`GU+o>PjM-R}WG?t#H88nC9pe3}FR?%0qg?^%6X)h(sWzSPh z%BLf!37tfzQ46||+RzQunM$ZH-9-=3L-ZJprx$59&7+01l$O(H^bKvJU+53oPnBP1 z&r@xxPe)NxI+f0(3#lcwrCaDW>P>gj0D6cXp(kk~y-agy0liJjX(g?t@90PRo&KVj z$H%4`RF@jivDA#tpmV7uwWe#SBNfvfbT18}M`$EHO;hL*i7M)L*(3RAVZl&(jkM5%fX&600PthcrL2u9!T1Fqy8d^u2 z=_lGtNpG^>s5;f5JUWb;&}r0yE~d+<9bHeIsD$pK2k2oMK~K>$^a9PMg|w7b&?mHx zHc&bJLi?%m0`?naQXUo3k<^sVqzkDPT|w8=&D528(*Syi9;L_W8G4RhqPg@oEvHrV zIc=a#w1a-9Sjd{Anv_k2bSNE7&FEZeNp0wAx|upq54wW}(IfO2jiKl0d74S{={;IW zpV61JiMG&A`jb)?vF4~Y<lp^ZRtAdK%J=<-AzMiBt1#v=y`gPUZq9! z0j;LB^fhgvZM2*IrnI+Mb5xfK=mWl$a+PRG)TbSj-o7trN&Jrz+g z^`Sdy5DlSG^bAd^bQRr9 z-KdoM)4eo=hS6wxj;7OV^d>E)59lNMf;Q0)^c(G?e<*Dkd!BOWP&$TArqk&hx`ZyH zYp4VDq<(Y{-A}`41dXNVX%@XfZ_&H-5q&~m(H8od_R;~W^Z_56GAW;qpyTN@I-Aa? z%jgQafjZOebQcYz2WbR7PUGoCnnMfe9a=`8(C73GZKGdlKP4~c97~y$P4($0I*HDt z^XOu_g07}p=r-z0186WkOpntTnn*9xJbIhnrxo-$eM#TZkMsw{hwL}1M%k204d_@p zmCmJ$s1;pJ*HK3*raNg64W&nE42`2H^a?GY_vk}fMPJg_R7Sh#FG^X#exsU{O9j-B zPM|aB0=ksi&~ZhrT~2N3CTdUJsUO`>!)O#eNfT%?&7e2vUHXVVrM2`eeNR8pUaGW`HAh)g zmlAY1HKEh!e7cOTqHC!=6;TP@MGw*l8ck2rWSUB|X(276Pv{F;Pv6s4`i1sWm5*6- zltcCCaB4(N=}fwquApn^Mk=Ci)SCv-!}K_frDtg>O{cl^Hm#t~=_}euTj>Y-onjSh zj9IhF*Keg(R7+c^XWZWMPJf4w3&XOpXpCZ z`Ghq`xm2GHqhsiJYEBnW8@i5ep-$A3Zl}9x2t7vQXd=BpvuF-2q7UdZ`kKC@a{8Hm zrN1d{HEWIvr~w^G$J0r47F|MZ=_cw(UFmk}OZU+*dXgs46ncr~&^%f~AJJO+mda=c z{YrmO(xGN@lkTO5=y7_MrqT?0l@`!qT27zS zM%qe0(Qf*S{-LU$v+n2+YD7)wL^^}cp_X(t-Adi4g!<6EbU!^pV`vghr`hy6Ev9#A zC4EVo=?D6S_Rv36X${|7Q7#=u$52x`h0dY#sWn|kov0`Erv7w4JxC*I9KArZXfC}; z@6s|_OM7`)vx{n6aqx2X( zLsRKhT0l$aeOg7I(FWQ|yXh}VTE{t-YEo?~q(*ciok1<=B5Ffz>1OIiedu0#fQHgz z^dvn;)9H0uOiSrQ`i$1nCi;Q)&_7i9E6%Z0o9fb`bPSzB=g@_8DYd0*sRQ+-{&YV* zM8oMxdYYc6S@b5oOUvnFT1)F`3;j&{sM31&8)Z;ksz*oA@pL+!Pc7+kx|VLF&U8E7 zLl4p;G>V?4XX!m2?f= zN}Z^f?xex=C_O=AX%f9auh0T|pH|Tt`ieGFIqjmqDD@lG9Mz$GI*g8_6X*=Oh}uv) zx`8@TS1P4@X(&BLPtkaKfnK85Xfb_ApV2z{hRSIN{YL*#`bO3qH-d=P8>Gp~iF~oknNTMRX}$O}A2a>O*(YeKeGY(-@jWGw5|%NK5EL`k20?&GZxP zq5YJ!m5)ssluL(E6FP;?q!x53T~60gCn}--G=LtU;WUcI(F-)2-lVr_DSb?z($`c@ zztBF4ZJc8%gR-cAj-;k^I-N@w(&cm&-9%lfH{C;n=ph2GS6Eghta?noKikKD|R9&`SD( zzM}7GC;dsuJJ@ejgK{XJ4yWU&Ih{wBP;0t|ZlEISMR(I+8b%{&ERCnB^eQc)_vs^A zO<&PBw3T+#-<0|T`;BT*KGmm2bRwNa7tv*OCEY-`P&evB_t8)qK~Kby`9n z(kHZrzM=2v2iikPKeFa1lj=}?YCy-(Db#{4r7Nf%-9jCyC-tWXXgEDiPtio0LbK>i zT1p?&=d_N#qcZxL_EF`ZSaXz3dDMU!((!aUT}YSH)pR{|q%L$j-9r!2C>lf0&=i_R zbLcHvPM^}3w1LWKJN-%rsOnDE9OY6WHKfLL5}i#g=_sR^A*=TU3AhHjz`)SXJ`P8v)jX)H~k z=V=DbrUmpqt){Q&TiQZD(J%BDrS4+QQ9dQ;2x>x2=?uDvuB02NJ$0rM>P`33PQ|V=zOY`Yn`k2i(pY+)X3!jZgO<=zT18*c7W#>PrM;B&JA0mLQa&9)P3R;#jatx!)P`=L z&QwBu=`MPJ9-_x+JiSP>X&x=4rL>$rqi<*%{X&1xeyY5OJx{f%J{?6(=~OzCE~J*! zmTsZjs5jk71Lz@ogr1~{^fJw*1@ty8r(0p1<@6k$HP3x(QcF~{o52ftoV^b}vM-Ax&YEI|S z1=O0Zq#LOVmD1gGKMkRg^aMRi)95u?MDNlEw3^n?M%qrl(ce_*PtLJai|WuJ)R<1D zv*>)fgs!A^bSrhIesmu_NW&@%dn*3dfIOh3_HO4`SMqv}+L^5`&X zLZ?v+x|lAbc62>;q7u4`9-xP51U*I1&3+<=Mf3e>vlk%vL zj-;k^CS6Fa=nA@?ZlN9oGzf&)RwNJ4%C@?(cLtJM$(fsj-IC%=~Y@pAJA%AOJCC#+C~-sv@h+` ztz+LF?fVq4}=EuB@&5`hu^q_&SrXwfTCZuetiVv#-5-{ehQIco~V8(s((MmsELKnU~gi zd7+nBdYP%0+IqRMmt1?J$cpHkh;&?lfw`6%+nz!b8d!n~!dYh`Z>Uz7f zw`_acy0`8-zQ73#PGE2XgA*8>z~BT1ConjH!3hjbU~mG16BwMp-~z~BT1ConjH z!3hjbU~mG16BwMp-~z~BT1ConjH!3hjbU~mG16BwMp-~z~BT1ConjH!3hjb zU~mG16BwMp-~z~BT1ConjH!3hjbU~mG16BwMp-~z~BT1ConjH!3hjbU~mG1 z6BwMp-~j+l6N#PttEWIqzI>hXx7<04v2j@bWF#JpD{dc7IZ_??I? z%OfVNj<|MRMAoK=m0Kf*{2X!49})WwM9fW1isFo?cWa<(ElO{oABiR-P0CcP2&iJxTG~-$^m6a&mO7 zksJ-`B*%t=A5L!%q1yN-XsvIlwD#zeME5}(!RgS&KSB^QSR*oL$RE~xhSB_1W zSB`PlRF1Z{RE~@;m1B8vPnX<5FYBDXG!r^e`ZsnPo8)JW@`8t?W@jeGj0MzecUW7pu+ zm_9r;I*m?^`r}h$-SesO_{*u$>b2BJU6>k6-c60WR;0#BpQXmmuTo>$cd5}~dukN? zk{WCGrpBnK5-roJL`r6rSX{SC^gpCZG(ECP{Me*QOl?*rZau3?1N)?8L4MqFJb zF21QsBo|eQMLnuSzdlvs_%}-Q`+-Iu9XOpYM@aa|J!Z~bwHvfWm zszjd;t3;DetHic-Rbuj{DskhsDv`6RO052)N(}p_N}OLMEe>R)#r&MKD6O9s$23ff z@?+Ct;>l@o{h4WzeL-5RYLym4+onZ}8`ENc$F!K&JuQ0mPK(BOr^S{*X)$3~T3q{h zT4aq&iHtr~l4RE;@xsz#5(s?qR>sNVA3*oJCx{+4QS;D>54|JQ0!`d76$rc(7NPp=*mv#Q7S`PC!4LG@U5RP`8oLiK2I zTJ_j}PW6~~arNlcrg}8Kwt8&2rFu;0Qa!FMsUBH(RF9Pds>hHa)#IEI)nnh2)no3n z)uZ@@>d|Os_1HYOdW>IGJ=!g;9+@kv$BNIZ$KbE4$64Q3kG(sp$DG~OqsPAL(J;A2 zY^qu##?`73ZS!hG#-TN0d7~OJ==d6O#;G-8&)GF%_C+<~w##e8;n&oNjW^ebv7Kwg zmBlrpdcPX6?A{tN@WC3<{Lvcm+vplGYkZC9I;BQ5m{B7(yjCN|EUXc2-m4MmAJvGZ zpVf!~>ubcRn`^}G?KNV?FEyg`pEV+plo9LGGGcUQMzqe&h_pmTynAFu+;dz;G&?0D zcAb?G(=W`3POUSde!GlVcT+|@UX&57dS*mw-;7vtPe$A|I3rFPo)J5r$cSmrWJHJO zGos+-j95D-BStOAh?ehWM9PYcSo~>5^#3X&ntqoNKW@v2sk<`b*1Z{#A2nl5m6|c4 zX3e;`Zp}zOq-HE?STp)HsTs#Ns~J1atQk`-s2Mk3Rx@(1t{I=*STlxqsu>sd;H1xq zf5F`~qt631qsb#RW8333WAeC~apUBgku$w!tbVm-412R?oc~VEIIz5C%wJtIO4rql zV>Z={@~t&v;?FhX`afz$_CGaaRcdAo&B%-vIhnD)Ff-;Ikr};?&5Xt;XU3K@GGoH| znQ?8a%*bk+87ptdj3FH}yYTP0EbSmoj6; z?93QEKQqo+k{NqH$c#CkWJZrKGo#_RnX#!nGsf-AjJA6+BjZ43EU#QE2Gyt)XVj?` zdkSjB?89rtZO7D#!%wOe8&9tlW6!Gf5zq_p(|sV^yu_ytY;(Hr9&u zWwm1TPqm`;@3kWB?^^M0N>vtmt%fR@6T+E7mp7ipN`IMXQ!s zk$PoTEV(W#?rNVECw0q;oxQSRTK}x*Ffc0$hGxauky$b7sjO)ETvnvKm=%j>Wkvsa zS`a2p?1ulSvyK!uN}v{RXfU;){coQYsd9#YDe~l+Og{U+A;Kp z+R@_I+OdCM?Uco|e z>O}S9>%_8C>cqga>qPU5>cnrY>%^>fb)xIdb)rG%IvHsmUF?vOvX#H88NLybg-u5b7JRZIWg_(oak^< zP81a7#M&M?F{)2aw7e%LQU>S5;zx3#{}VaU^qHLaadJ*fot_i7&dG`V1v#bkN2%epb|+q%(fYu#x4bKTgor*2F* zP&ckk&5f*#+*nyBH-;4E#yLmi#=c{6W9~`0QG7;jG&(;wHeZ?>D<^fF*n9d%Z;|Pb0cGZZY+O0HwJx>8)tly z8++E~#_Wx`aa(zA9KJI*HvXO)WB<;LD=X(k^%{AxEITg-7UV_q!}H>|qw`|ciFwiW z^t@TF9zJ67pLBt7rO`M#f+hO(Rox}B*x~&`seau z^ox1X`jxy$dm}I2U7Q#9EX#{#tMX#k7kM%Lo4n{$mKXJZ%8PZs<;COs^P*Ksexz2< zk0rJ9czIB>c!*}>cx$x)r*{S>&5De z>&37(_2T?%>&1av>c#vn^`f+-UL12ry(k}0FD4GD7uS!d7ujR##j0oP#n2b(MT?pB zV*lKFF>g`5=(V(7G+tRRwtQYMCVX8luKm7VWc^StR_?ABL-y5+bCL^UU)6$`TdN?7 z^9rKTp#`zIQ9+D9z98D2S`eA%6vT>)3S#i(1##9j1+n+$f|%2}AbJ!RM8kdsvFYA| z824a7w0*Q7GM+4m<>L!t(3FBWV@5&jd95I3FD!`L-Yba1KPrfgpB2Q|^#yU|=7Olc zqac?3QV;|GEQsbwh4EWjVa&=bjIOzb(I8P68;&fDF~=1~n^OuS{p`Y6dSPJbt^7-Ch_=b`{25dkf>Fs2@A4)Q@R3>qm#W^`qdB`mwfQ z{TS7RAISOVhD(b3l$P9--r%Y`d-o~ondneb(x+Q-mnKb`B(}XWbKA6miSlWa$|gLL z=uy(X)4zVBL3;WP?TSi!7bQ-(DShjt2e-|BBe8wZ^IPUmPjoElR8*SSHv55XuRNJ3 zF6vv_z6bx;hv@~~)60fGwPnGK#MW_x6Xg@`FPk+vv2E7OtqUJWoSV2LQ8wi1L}^j4 zlF~luTjoDnHflJ3W?uP(!3Y0%$FALaCI0>9t+Spgf9=VGZ)SdOdfBTZ%ier)%lu)9 zZErkQ@vh4roK`;el|;|>{H5ZeM8#bJ#XRgpqyPNZQ9Sw|R#AWGa zFTAz&ffu(8e(d0T?a;ns_gQ&E2{rI<@c9{=bL0=}qZv?(EZ* z_fxiLL85p2JIjVmq2m(&{tXWK*3r`v=N*0Y!FO?PqD|tG^#A2gzC8Rtf3j@K z^hEC-C3pPi*IQ>icJQxNyuEAt(oP*qN{iB4@rc_cE=z1*IF|nVd?!;RM!pWybV z<{tbqrp>^BKlCW8s$z|8eeQ)s#e+Tgi1^$)_qg*vkH1q<`%XP7R?op>!iVHD zIIn9-Y2V%~nFptBnLlRhlfx6+A9$;5{Impfs=5{bpKHBsY5U^dol8o4au6z3Wv}+V zDh|)QVdc-hz`qmQ$1P5DDM|F{T3XVVcmIEXr+xY8+vYu3HgZt;le5$Ry*k+>74NJ= z-!5#Oml7B8*srd57!^x`&-uT{`J|iD%by!rKH(|8pdGunKe%!_74%CONJ>dZd?)8oc$z zNB{E#QSq3HN=r-ldjIR~<&%c6d;j$=OFE{rGJ19^=9ysoLu~7X^_e zCvrs*F^clkN#_URXhHz1g7Y7nSnt zR#e=l;%z;65<9q4C(S6IIR9T?zfzWTpNf52Hf8SC7a#cd;i~vbl=8gz-y?rAM}GXn z70-kfzg0H!<;3lM+ZXrg+cUlV^+zh66St0drEKy8iPFBs306esqKtt%V)T4>ivoKU3f-Fv?%G_``|AxZF31vkeyiM{9aLy zqAnbze?8iYeRuFPEa_RoqPpYY`C#gx1Yg?n5icZqcP#D3S7O^k)60fUOZ4vBp=Y-~ ziLFx?Zo7Z@mbWMIfG_X+uk+b8|9awY&cb@IZ06XCrQDsfTE){_qEla z`+xdY+%va7bNe&5KXdyt_kU>2pSk^++n>2BzH9bpZneB(9jN7MxmvE4tL19BuXFo4 zx36>iI=8QL`#QI;bNf2CSEzY~npdd(zr2{mE7ZI~%`4QrLd|Q-y|%pKl60>v_u6u= zE%(}TuPyi5^8fupdhZJJt}yQk^R6)O3iGb8`xD+3_J7>!=@n{Tq2?88-p}p*+!Z&w zdxe@;sCk8&SEzY~npdcKg_>8Wd4-x+sCk8&SEzY~npdcKg_<+eoT26nHD{QBzD6RTWhgRRl#)6%;`c6hRRbF~=MfK@mkoO;J?LQB%}ZbIdWv9COrk9`E1& z?BD16IqRHt&N}~{vtHTjp`zj5EBAf9ulstY@9R!2Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^ zPc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^Pc2U^|9@jG|Hnu7JVixI75)2T zk)maa<}aGBs9(_{{^w)fzC{E4QrS>k_{_&bK3}A$udi6hXT$xw{r%cKZ{hd;{jtP< z{^tMS*P9pn_djg;uU}h-{`>Q)ZT{yM|L61ne0|Z_fB$~xp8xgh-T(9JJOAtR|9pM@ zXG;k$1GlOe7mqNTPCn;n`nU%Bvoh;3j0(mwo@1!zVx};iHlE>iKBkAiS)^}K z(ejiqlu_(THAgau^J!ul_c4n(e84x%rQdu-Ma!@{gDGbx#&H;RoWo?M(#m7Jz&mvF zD}CoLDq4bK1~HuNsp4QJat4iD&mBBO2XFEzKT_nPTa*=9hcdQd32FY_{77N&FUpFnLmAsJh6AYOR4(KiTA0aGyh<0}@h1y;4IjXo3}Gad z?8^jBqJb+Zye`h5otJozujpld6Ub5wq?8eiW-n?up0l`&X71t%{7j$4oqtwl zJ%&-iSjKY<^<2yprqjkVyw1n;@HdN?#FnRop^RczsyUKLoKF+exQ|)P;RC*5F8!8t z{#l*Dl(Q4#IE*^ZVKP%`v(bKhwvJN`F>nJ%&-iSjKY<^<2yprqjkV zyw1n;@HdMr=loN`P)4yU)f~wr&ZmiK+{Y~D@B!a2mwwAT|E$hn%Grr=97Y}IFqx^e z@)$4h4&D4p-xZvHiW$Ukwx^1NnaCM5ay@tO5FNb9r~F7^;$M^%S%)&VVGIXQ%c)$* zHMB63r+AevzT;08TFLomO@=U%O7>*}C(*!_+{_Hxd5QPv(bKhwv(QGZruJ%&-iSjKY<^<2yprqjkVyw1n;@HdMTJO7k0lu_(T zHAgau^J!ul_c4n(e84x%rQfQ~KdUpCa&}@Ihf&8lOlB&rJjM&WLpQ(DccAl6F@qS+ z_Ed2&6FGxMuICOOqJua2lpiTt&G~0V)}f4T7{dY7aw->c4K2*%DPE$Db^;uJg~D3}Gad?8^jBqJb;9nHjY6 z67TU9z0AL!^Upv^8Nq1wqK4x+i_2){E*@bvoqW#E^jY8eXJyu77!{0VJjYPa#Y|y3 zZ9K#4d`u62v&bOlpAv>Lie0JZNG5SUO-$oHW-*5k_=dUk+rar}bp}(;PK@I)>NtnV zOr@2_c!785=2!ZbI{y?ih~aEc6$dksGic;`?%*Lhc#}{0k)jQqe^z82%Gic696&9n zav|5y!c3mxRl4|&KUrw7^Usin}hgDGbx#&H;RoWo?M@}C|u@t|WT?l-Br#moqq4Ko{NHq308*)X$VX2Z;enGG`=W;V=hnAtG1VP?b3 zhM5gB8)i1lY?#?Fvtee#%!Zi_GaF_$%xsw1FtcH1!_0=64Ko{NHq308*)X$VX2Z;e znGG`=W;V=hnAtG1VP?bsXS1Pq78ZF6ev!947H!Qqj^%uAq>Y#PoWEFVo}!|4DeM`u zC$*f*_1w=3e8OB7@8f-VY{6KLps*jzwanl-y7-Mn=PfE)gW>GPVVq7AcT?Ew<$Zo; z;lAE;$fi_s2&Zxdckm?d@B@W?TvlNyJ2IY=xs2Or=PkZtzWKesl8q?r(Xu~vT*5RS z<#oQM&jLk7%Tda)>Bj5qj(d6)4XST>}B{WzYB zDD3C)Ft73@g~7ipgV>sJ9LxFKNE%spJq&XFSO} z{6IhZU97@Tc4Ry!a~ZeM&RZ1r#+c8Z7Avw5+p|A)T*5RS<#oQMk9{kaqpCdf3~EGqd14_xR2-gnBVEYs`1YV zc4q=-at-&;!G{#~qWIT9QG-s2}0TFv;Uu+PNK9Ly<9=5}WBHa#q` zy7AA(jOIWJdq`YL3yQvKF}G0IAL2E>VxBdPe>Pwn_F*CyFqH?H z!xt3xepq@fzY`JTdF3o9{% z9XNm!Y2;QO;|;!H-t~=tHl(nR!hRgjMcmB8yvmmpCjMm^#MX@CSPFY2+(;WQ^ErR9 z)CR^sBiWN$&gFXUr?CIQC(LE>QsbX37|Riy#kI`fIlB0b!rlgJFr3{ujMHi2Zl2+N zerDmp#y^`<*tg&iPUQ;j;7Q)$2l{Pf{4y#XOrE|7^fE z?88JZU@8wXhcEb>rAHY5Y{gz2O#?SDlNb4vKUiW53KO0iPejLw5+|0wg%9j*w`j=%8TQiPhIiDM8<7GbQFP7TI z_-7=0Qp>qq&;7i>C(LE>ZH<4nU@S*)7S}R^=jh@$7OgP;8P0AT#_2S1H_z}sKeO<5 z#y^`<$swG|72Ls-yu%Ol+urzRC_6HqlevuBXy+}yW4;}Xe>P%!_NR_Zn8u^L&e!xA zZTwTpw(QGsT*ys4#4B|356kRm{47_BhwHeH=lPi5 z>A$n_&j@yB0%vj!_t3$I{K~&7jej;{R}Q6~tGJ7&d5@o1Xcyz3GIr)*PGK^)GmE$B zVS!zZe>P?`2XYdZ(!%4s$+z^~&G=_9+fmI4T+A&z!fSlRJY$T1Heeg}VImhWl?R!_ z7yQlAyBq&(#a-#4oF60qf8oc-c3>~+M}G!TObMlwQI0Loi)_hV zWXtHHYHFyZj(Qqsq={x)Xr+yII+#NzU3Ak!FGce>KK&U$F(s5zMmZH!Qbjd2)KW)1 z4K&h3GcB~zMmrtMp_4AU>7kdRK8{a+22f1lnNg*bQBDPwR8dV0wbW5h1C2D%Obe~F z(M|_*=%kBodg!HSUdN|D11P41QpzZ&f=a5WriNPTsHcHOnrNnlR@!K%gE@54MK?Y4 zQqCXU)DWQ}y%Bi4|DypfWmOAQbpphn;X`z)i+UZ~popjMn54{x4=lJwz0L7G0 zN*U!;P)QZl)KE(u^)%2(6V0^HN*nETFo#aM=%$BWispBG`ZIuHN+_j_aw@2#ifU@8 zrH*b~>0tCtY;YLoY=OI6nOuKrtm0p6gXcITch=MKv|lQb#=vG}1&f zEws``I~~lSlPlu=Fvl~hqp4Ykx!PXmoK(M$`iw9!rnbLgat zZhGjYXhFxPKLaSHgi^{Vr-DkVsHTQm>ZqrIMw)1*g;v^Vr-M0k(nU8t^is5t<5PH! z*#L?up_DSpsi2Z7s;QxtI_hblktUjHp_Mk;>0l0>bkR)@y%a6%`1EH0#gtG=8Rb+^ zNfp)9P)i;4G|)&B&9u-;8|`#3hfccariWgN7IA#~Gk{`BD5dc1wQ?$`q>5^4sHKj2 z8fc`6W?E>ajdnViLnmEy(?c&s|8ji#Gk{`BD5Z>YDyXE2YHFyZj(Qqsq={x)Xr+yI zI+#NzU3Ak!FGY(wKK&U$F(s5zMmZH!Qbjd2)KW)14K&h3GcB~zMmrtMp_4AU>7kdR z#T=jh6rMF#ObMlwQBDPwR8dV0wbW5h1C2D%Obe~F(M|_*=%kBodg!Gv@%N)Y11P41 zQpzZ&f=a5WriNPTsHcHOnrNnlR@!K%gE@54MK?Y4Qna|^)1LtpQ$i_alv6<^Ra8?$ zEp^n>KqE~w(?Tn4w9~;HI_aXD9(pNS!tv?P0E#K0lrqYxppq)8siBrS>S>^nCYouX zl{VVxU=E#h(M=D%6fNoa^k)FYlu$|;b~>0tCtY;YLoY>3J3jpx zKrtnhQbsuyR8mDXHPli^JqS>^n zCYouXl{VVxU=E#h(M=D%6mI(a(VqbnQ$i_alv6<^Ra8?$Ep^n>KqE~w(?Tn4w9~;H zI_aXD9(pNS&hhEb0E#I*v$2#i%Bi4|DypfWmOAQbpphn;X`z)i+UZ~popjMn54{vE z@A&j*0L7G0N*U!;P)QZl)KE(u^)%2(6V0^HN*nETFo#aM=%$BWidJxZ`ZIuHN+_j_ zaw;f1XR?ZFYN(}-dKze?iDp`8rHytvm_sLBbkjpGMJqZ!{TVA}4YN=TKOqU&}P^rtrMx zhj@}_d4>1*g2MXzSN@={b#gzJU?ob}kWCoQ)@;Xa?8~7XLmj7Z4(BtO8<@_$Jji1_ z%k#WJ7hm%;bNPpU*2#;o46Cvp8?zbZY{!o5!2uk>@l2xd4C(W^n8Nz}Chp<^9%UBK z^D=MqDc@6AoBz$c*2s&{pXFJDQVP$W-hxr=$S&;7!5qy=)N?i$a~V^(l^HzD6FkGq zyvF+!*5*I)Cw;7s7oa~&u`+8jgw5HC3U*<4_Tw;)<5bS#JPOaczLI8cXC{yHG_!e) z!ZWZx;v0UW$l7>*7G^01Fp%{rV@tMWG`q7W2XZ7Qat4KU`9)mGHQdbIJj9bc$4k7$ zyL?7rUH%7st&JCAF$SnW_u@8vO`Xa~;&8c7)_FxBYyV0G4^@a*?8hEsS3{4R{+AP%RN6FG%*xs2`pa@augFeh10o!E4h*B6xQJP^BA*ufw%aWula#r z`GR%1N|vkB#lVkh=wJV$UWb(~J&+4Yxj4YzO?_wgXJc!t6n{9QihdwyXq z^I8Wlz~ZdPT9h)B%@{=myRr{89L)(#;%v_2a<1n#W>8pvKgu)A=5;>gD}Lg4{$>H| z;DuS5V%B8{!`OlfMl+WEnZR+JOg-mu5mzylJDJHNJi%;UqOkt{gzxx`zvyEPyfBNg z9ILYdWsG1eMpMaN97HWAavEoG5tni;)3}F+D6GAo<|SU`J-*;a{$L(Alk>9}OR^Fr zY{YOzvMrU2VP6hqBByXB4P43<+`x41=P{n*IbP*W3TyAL`IUc|&-!;EmSkC0Wj!{b zoNd^FF;sB?M^MMLsmw27G`IyfsthxVSe(T=FSeoTojkVa2;cQDKW7(VW)Nl-^ z(7>f!#T0JgHtyvyp5s*t>+SdXoUizqe^|)6cS)9GW!7R{Hl~~%7{gxdM-3A=p3}LI zE4Y@zdiyr+!B5(2@AMq96QCM%!Yt6eT%d!#!S(gpilu_(V75j1^6R71R&Zd#8 zxq+LxlY4lWXLyBoD6F+V<2!!jPZqG|U4j)@l{MLbjo6$Dc4Hg|a0sLU@m{tuh@0R%B;ou3}!R7U^~XJA2l4wu}q?#^SOd%ZsTt5<58aAdEVqB zzM_X;_?tefy0>Ck2C^<2GL$XYiXExqKqhbuCs5B>T+G$n%$?jz8&B{wFY^wc@f|<& zJADQk^Ymv0)?@=VW*A$sExRy|L#X9=PUb8cxQy#);T|5~5uWBbUgHD4i}_bG z=2?nWSci?+lo4#p4(v`fhcl6rIE@A_f|VUA@{mS9EJVlbPr zCEKtwyRi>79Lprm;9MG+%=O&HeLTvObnpsq@F8FE3xCshO>- z}W^BXG?9N^s$RQlfB+jLgE4h}NX<-JB z(!ndd#e00lm;A)vEV!;~jsdL1nykYRwqSd9V^8+w5Dw=!>bZc)T*D2ta0fGaf){v$ zcj@9wzU4Ritmm3z8CGOf)?pB3Y{gFO!9E`GjtM;1~X3 zp+T-WR%Uh9W-vo3X9vcz9|v(5$8rLvb0JsJ%rtK2KH8YYi*)i4U+@jT@H_Kv;JRZu z22#TM3}qOj*qOaJkV83=6F8Z(Y2;dNW;%D%#v?q#E4;^Nd`%C(^A`)0y6#wsHCc}h z8O8`I*o}QTgd;eHlR1s^n9L2da2NOT2<^<~4Z8S}@A;X(m}f)xRxHD+tV1aqGlG$f zW)BYFaE|79PUB22qKTWhgBd(PJ5TWvZ}TbN@)NzxGuW7CF_vcy1~G(98Ob(OvNs2F z6vuHAXL2r=GKE`dWhM{v6dkshtKHYcmAR8#*WS6tiYOV$S}&;nw{8{aU8-ioXqK*!zEnKb+m9V zk1&g8nZxURz?b~YU(7qy9LwS?%_^+J#*APT+p#NSspfEw=QPgdd@koIZsZOgpq*!U zp4aK*W4@)Ac{VZLScIinj@1~%ri`S59U04BjOQp$;!MutVy@y^ZlRTjd5YP*OegR0 zIY00x^OYHI^k+F%Vl4)U;-y_1{ZKCS8@Y4aVKp&$qT&7TXgX$-|;(rhq>lh zk^!vB8f?HYwq_^BuqOv_Ftwb_Ib6aOT*FP=$~`>7v&`X5-sMxe`H{cqx0!2>Wm%Cm zSeuO)!FKFQ75i{7hcS`UIG@Y8n(Mih+qs{1p67Mm;X}IlhF_UyxNDB3S%G5KW_>nc zBs(&eaqQ1w97!E#axqtN9aFiTyLphOc$rQ<;1j-~hq=tRxoeK)ScTPDpAFfJZPT~I&-t34>7~yWt~&;>Dr>PG8?z}}u@if805u%J@tnk2 zT*5Wn#BJQg13b*r%;8-=$;zYt4P%-U?g5H@E^c3>>~a~QQ8$ElpbgGPY!Ec4jXQ;z%ZPB4=<8javIhrn1jjRp(>b4uY2qgC;sG9I7SHoCZ}TbN)63t? zyR~D}pXFJDQZ{7^MzJHiur~*DG$&Ed*<8$JOyO2$@GwvC3@`H<@6*js{7Ii}%(3)m zDOP4}hOjwXQNb?k&VC%mah%FooX2HcNi(-IlgD|Q*}TSEe8e~WM$xv$8w;}(0~pBq zl(8k-GMe4llLI-D6FGwhF5*hA;b!jUA)e$pUg9m@s4OGdLhdsEG!9Ki{k!9`rj6mDcX zchSa^yu@3)&&Pbt_xw)Z9bIz_U}aWgJxUqI)>N`5`!Sv)IGU3=hfBGJW^UmwX7C8l z@+$B05ufutKk*m+c5=s?HI#897qjEa~!8}K38x(H**^^m`OX&^Clni z8DH@ezcJ6wt~-{cm^E3KA(Sza9jRh}4q*bvaUy4OF;_E{7Vcyw5AhT)^A4ZzCExKI ze=uLA>y8yzopsoNGKRAayD*M}IGkEeoJ&3C}$Kqu_xm>f@7)Ubk61yuHhE$;yxZ^7SAw;cln&}`GvX6yPGl3;;hJ8lrogf z7)1rUvJW*J%?V86Y|i6yuIDyp(8i-Y!)#vXL%!lCe&=r%7-P({G{vmT5Qeb@6^v#q z`!j*#IGK9R<07tNDt9uIM|gtSyhJCT@EyPL7kzejY!+iVR%Zjs7{OMIrjorlh+0nM zG|u88F6COLaSspC&eOcatGve-{Ky~7Gu9l-Vl2r@l&}%Q8OgR(GKPIQl!=_enKW=I zS8xNdnn|3^1vGLs*KsQ|c$8;& zfme8k59sD6{$_zajW?EH1y*5ghOh+{?8I)2qng7wj(X1H5+-vUH*z~Od4k!@;SE0E zW4_@x`t0SJV{w*Y6;@+?%Giq0?8+WgGoB+kk+Zmn%W2|9ZsBeo;%Q#ub>8MIVK4Thh6x0HPaTuU>zaVHNjix+v5_xOmf_>NxY-N!Y@vaG~F z)@1`WWfVJ8#l9TK1Zp{nvuWgNZs2C_n(ZU|-i9E3hhSvH=^h zITh^2I1bV)*}TCAe9D*n$gdRb=elDVR$&d+VIwwSOGdK? z)f~*>Or(x8xQHfhVtGv(We8UgSxCQ;A% zTtPFpaX0tzC{OS_Z}Jge(ZetNO`ikYTd^zyS(gnN$`)+Jj#P0V6F7zwsOKy$=4x){ zPVS|RCwQ8dd56#Vj-UCRJ_j1}^k)UuWCJ#47+bL|yD*MJsO5N0<}4bxjO%FO9v#3pRcNOoXn_GCOqQOBvA$%Qm>4Y$zBgFMbtyvQrO%jf*S zT#61h$Fe9(up(=%b7wm)488^p5tX+=Y2lnYkp;(!(4OpXK7YuAnUOSBiVsn z7|VVf$Pv_WCKqxUSJBMP+{J@D#f!W~Cm-<{-!qr_4tLG56w5J?H7R8?wqa*>XD<%q z5RPUN=hDcPT+7Y0FoQ?w;1%BDJwD@0e&TNyoZy;c04uR3>o9~Z*q+_klYKda!#R$6 zE?_d(a04ye!Azdu1>WFYy7-cB`HenDxaL@f6EU<&Vu7PwcdW#ktjC57V+0lK#=acF5gfzGoW^-f<_220i+g#5c4qSiU3|&+{LEj> zbBuc{mSI)ap_Gjo!AM542M2ICM{_)bn^qh@h9_5H0Jr=*tzd0 z9q;z<_s8^NOz(w@h-eW6K@hzK5ky3bVMZM@GG_GNd+)vX-aA1M1VIo)kZD8@f*|`n za_3&p^X%W+YwiE`Uh9)}zjDW5=9+W9-|M{QJ?D7@Ar}gw1j?WSYM>4p<7;$6H}pb( zjKCO7!$PdVR_w+B9LFhK#7*4AQ~ZVO8!Ww$6Jf}U_fZ<qHP zfLU0I4cLkOIE+&`iz`USL%hJ>aP7{=MgXFaAH`7)l~5h^(GV@r9?9r~K^Tq+n1Xp& zi7nWRLpX-BxPa@pjVE{wmmZvB5r7cnMj@0!MN~s=G(;1$MrU-#01U%uOu-B+!dmRW zK^(Nyn~`Biz=vvdT4@Xh(i*3V+clJJZ4}HmSH3I;0R9O z3@+muGVlnm;MR-%27g2#2JfK+Dxe1H;&U`ZD|A3N^v4K{!(`0C0<6MT9Kdm$#(7-B z4cx&~SZ~%G{1A*7V+v+rK2~52w&5U7;sUPVS7hNXp24XfYYriZ zf&&HdK0ZPf)I$@rKrA{T5j`;k<1qvCuo!Ew0lRPnXK)$U@f+^qAzs3*KWh#V$c=n> zAI0%8YT$D;Lup$JN$EUKbD zzCs&xKo@jJZw$o*%*GO|!g}n$9(;$hxQaB~!2>+UE4UA0-60z9qA-e~EGnQT8lolI zApzf@H~M2FreHo+U>!DN4-VjaT)?l$!hQUKSFpjnwn7LTD2NYG5*1JxpP~t3(Ft9V zivAdkv6z9ySc6U2jsrN1A8;AJ;VvHIPuLLlJbV#>e0U!pq6{jdIzB@)#3K+4BfQ3<{t)K0G5> z0ajxRc40q`;Us>-4g8KLc!|H^IgCAzP~<@ol)}fTgxaWwFVO~F&>ej-2%|9`GqD8g zu><>X2q$p{KO+qf@EmX8GMtYMe?;P46hm2jf@-LT&(R$1@C|xnAckQ)CSxvEU^DjM zTO7q1oX0Q7!XJ1A=MkJ^;g4YCLP3;71yn^Xe2y>hH98>`{V^1yFd5Ua5Nog<2k;$E z;5;tjChp=-WDk{eM-Bud9C`6R%Ahi8qAtF`S7?hw^ul0_#5hdHY%IkF?8aeykJGq> zt4PN~`~}xh>^Jx!9MQ;+;wX>m_!JHB6se4j=5Nb)mV?6IE>S{gkNwAzvBU3z;!%p4&lg!cTfby zP!8460AJy2#GwnmK_3jqB+SM_EW>(i#$Fu5Ib6j}WZ(h*z-xF;V9g;KdGQ{Kp(HAz zHX5TP+M)x#K`I7dG^SxbmSPn)V>=GwBrf7tq~i|$z@KoM$ht!q9LSHtD2Xztf_i9* zShPn1Qqc=TFdnn87%Q<3+p!x*a0XZK8*bx1{={E!o5Z?96!M`EK0q0iM-69_Wi<7=Nprm^P{0tX7CB+B6v)Iwb}K`auGiar>KQ5c6ASd4Yp zj=lI6CvX~<@f+^rPrQcnbUrrx5P^L70A)}SRZ$lW&Mz=tT0DyWGDXpC0qh!ph05RAkmOv3`K#y0H75qytx zxQHA09nbJL+-7o)MG(S}2SxA^Dxn5GMPoEY8+1WW48jPE#Wc*q60FBA9Kvz@fQz_- zG(5mdxXfa|!53kO!n-Jjk5LVE@EMw-1=`^o^u;iY!9>i$JgmTG?88x&U_% zcmt2w>^B4=3b|1bCGiPrp*|X+1zMvMQZW#tFac9B4~wt{+wm<<;4FT^b=<;T{0Zkd ztT_ZA6uI#Z-bWc!MO`$+muQVRB%&9FVjQMmCKh2CHefft!)aW=&$xvQJj7pcpUav< z2qN(g-a~PeM@=+96EsI0Iv^SSFcOn619PzqtFQ(8@jcGrGJZh@?%)ajhW9+y93qel z@1ZbCp%OktV>H9p=zs)t#~_TwG|a(5tin3%z#;sAi@1iHxP$w64ww0?IfNkwc~KZ2 zpe(B4Gc-jjv_%5CqBn+NB4%L$mSPu;vhjJjjm^@F6Oo z78;=i+MqqUA_e_13R5u;ORy4~unh-r0zct8(r_D(@eH<*b%#*o#=9tl5AhKyqb|Ng zYqUdWq@X7TV;p8;5msO=wqX|z<1~K8Eo9*yp5Y~27qRXTiFZ&CMez|nMs+kmbHt$& zlF$=vQkMI(2;JKJ}hg^6M@1q1h#wVza#`qc?kce*R zi-8!8X;_F=*nq9rhi`Eb7jYAJ@DNY&2F^=(ZG|x8MPU?2X?%jJsE4L#iv%R22L@s& z#$y(iVjZ?%C%(mZID;!l$9+7(3pg)j&%+;4$d3xJNjTKMq)DN zVI?+U2lnDSe2??Ej@x*Q=XeeGW$bwbBR2}+LzG2D)WoOw0#>7>Ti%jzw6D zZPp5^h^d&5RoIGsIE>@? z5kKKq+`&`4f$K`nu?R#c94L&^_ypBa2aWJ0Vv&Fz7>MB*gQ=K_#aM@(_!h@-3P0gz z{D%8@0q0fhH{?VpB9RXtpd6~AHtOR`G)FwTq7Q~*G$vps=3+TEVK2VJNu0&c_yw7G zjMs2q&3;1wB9RLP@F6OqChDOfn&WG9L<$CAB*tS3=3*gMV;c_Qdz`@q{DPbK9navj zhBXI&gdi94q6j`h6?}@%(F9+kExMp5hF~lvV+IytDb`~bj^GEJ$7S3^Iv(I9+}5(@ z5R3@qMSc{+$EbnN@CBNoE!yK7^u-8F#B|KTQmn*g?89;Vh)cMJblk=tcmuC>tT}`u z2KiA4CGiRBpb@@8E3`*vq+%e(U@B%~0ajuyw&Poz!cVx08@P>o_!G|SS#tOyEi^W)hjo6C)_#PMV3w}cu9^onehWAF+9C9Ha3Zeu`qY^$v z6MT($bV4`uz#xpp3@pTQtie|7#3B5E%eaY5+{IJ8fXgP<9U_ny1@Jyfqa3Q?Gc-e6 zbVMS0pbv&&BIaNzR$~KpVlR&3M_fZXe#b++z-xGHX5AqM`B4PLQ4SSR3yshU?a>9v z=z{?mg{fG8l~|80*o%WWfuC>#xA6c^@ET5Acx{DH@IqDxo^+qaj+LJ(AG}gD@NuFa`6l5?inrhj0vM zaRJwH8&B{WE;~8LA^;)CjY24eil~O#Xox0gjn3$f0T_nSn1UHtgtgd#gE)$lxPZ&J zg?o4or(Ntf_#gxkcn3vM7FAFS_0R;(5Qil6#t@9cc+9{YEW<|Z!4aIm8C=FSWZ)5A z!EHDD4gQEg4BkTtR6q^X#ph^-R_K6k=#LQ?hsl_O1z3fxIDq3gjq|vM8@Pj~usy6f z_#qfE$b-TtjmoHl2KWN4&;|+Ufx#GqNtliWSb}xfiNiRBbGU>XNW*=+fa_k?9D)#z zJa`u$pd6~BJ{sdIv_U&`MIQ{u1WdzhEWrwF!d@K1SzN?bq#+BB@fx1{SaS$NG~Pu) ze29vujfQB7mS~4gNWlP%#uUuLe5}A4Y{NmE#06ZzugJn(JcHAI)*M0*1qTY^eSCx} zsD~zKfmn1xB6?y7#$yKNVKLTV19ssE&fqex<2T&JL%f9B0oEKMkQ@2%K8oXG)WGLx zhSrEjB9hS;BQP0run5bs0b8&S$8jFla0{7uh$nahuY;^P#NZtiKyj49C#Zuj&X7MxPc7(jwg5y=Wkhe2uB{ghaxD2vZ#vs_zG>%0bS4? zy)hIMFdIv-3hS{0d+;63;wsW`2M_QZui$=&b%$uYi^3>|vZ#QXXo!|*hXj0s-sq2! zn1cCOfpyr7Jve~xaRI*~3-|E{UcnCY+6p0Xpdda#NmM{(e2ONBMJIGcD*9tE#$pB* zV+}T8I}YG5e!yk?hP!x-KVe7M^YBFk^5K1ah%%^*>i7)J5RXKppce*XI3{8amSY39 zVK)xr7=FYxWa1&7;V-y;$DT(ZVo(6Z@e#_SI%=a4TA?G7(G&eJ9HTK63$PknunYTf z3@7muZs2!3!AtxN&!g;lgdz`$pcFnvCDcYee2F&bg6`;xK^Tqkn29A=j~&>DLpX^u z_!((do z7XH91I3MR63x5P77Yd>zDxfNA;d6X}uh9vq=#QZog~^zXg;;~_IDqeP0_SlFH*pt# z!oFv}AqRpHj=XpuWl$M4Q5Rp}E3`!-dSNg|VjQMpHkM)ocH=O<$7x)`Rixt~{(|cX z_8a^Vj%egZag;}Oe2ND63N6td$>@jS7>h}mjrmxKE!dA^_yOl|6~E#(p5SkIo@Bov z2+?q$5K5sEYU49BMoYw^GrD6CMq?tTVLldPEq34#PU1&g#IN`b_wXDpr&x0cL>L^% zhoUHpYN&@sXo^_GBMH4R4C65sv#=P;u@QT46ld@guHZLh;t^iK;|JCpLJ@_0D1Z{E zfLiz*U!n!#(GlIyAEPiCGcga#u^L-(04H!BKjS(w@jITvPP66^j7a200Te-LR7PEV zf#zt9j_86O7>se4j=5Nb)mV?6IE>S{gkNwAzvBU3!1WAk4&lg!cTfbyP!8460AJy2 z#GwnmK_3jqB+SM_EW>(i#$Fu5Ib6j}WZ(h*z-xG(Wz8WPdGQ{Kp(HAzHX5TP+M)x# zK`I7dG^SxbmSPn)V>=GwBrf7tq~i|$z@KpXk#&bKIFKKOQ4(cP1@+Jrv1pG3q@ovw zU_54FF;-$7wqrMr;0&(dH{8a3{E5Hdc8+z2DC9#Se1I}2j~e(KEf9~+=!#zGhY^^J zd039M*o58KkK;Ix>&V1CJjP%68(!yGcgT$bD2fkJ9+glBU!XNQA_*zzhd~&F=~#r- z*obY|k3%?xOSpyK@d(fGH(W08+6v)#2SrcNFX8eNdmaIZ#(OA+()bwFPzw#w5*_djdY~_cVHBodK2~8fc48ln z;sh?>SKPrLc!4+YxX7MI2plMkk|>8yPz!a@1hGg!D*9j`MqwOgU@_KVJNDvRoWN;Z z#&5WfKk*vQm-yK5Lj>~S1C&8UR7G7hKr_UnD|%r7hGHBhVGfpK6L#YuzQbvp!!=~$ zG5&(nWzMniLl9z603V_}s-PwspfOsZBT~>0LogDPFbxZ^8r!fRNANw);UaF}cRa)2 zaQm5aEP@b*JSc*XPzg2gDH@|G+Mo-1Vh~1PET&-=mS8=0;Si4F2VBGzq~QTx!sQD4 z4Za9N6y8NKe2i+SgU`?uEzl0%pf84D3?^b0=3xakV;_#<6n?}NTt^oEz#Dj6WxpX1 zQOJ#gD2Y!{3-!?mEzlaBkcxpAg$bC7d02!s*p6>;0%!3PuHzQ&;!ikVW6dD|p~#JQ z@IK0*D(a#kzC>%pArZYW6yq=jGqDKEumQXA9Zur{e#R|i;358k`!B3Hgdh^{;5`&a zdDKJ$G(mI3p#zf94>Kfppx*W4waL4b~i@kO%qk0X{?p)IuY)KpV72 zSEQgnMqw)EVF^}Z6Sm<1PT(h8M;dP9F`mJ0vhEOy+;|s-@F6}zWz@x&XpMI0j1=_5 zV2r~|EW!$`#Ww81VVuU#xP>g-!!x{u>n+wDBJmCiq9{JX$Ec15XpT5^LK1qSFNR|h z=3*JvU?X;6ACBQ1enAHA;t^ir4LpBi-60p=!}} z6*gci_TgKc#6{f19X!NSyn%BXudNV9~(4cmd~h_B{L%h5YycrBDu4Q4^n|1=^!4x}y(~Q z!}mCk>$r`_c#hX_&tT6Z7`aghAEGQOq9#7Y7if*nNI`E5z(|b6bS%PJY{MQL#P|3C zmv9UB@C>iul*z}2FT(K-isBJ<4jSQ0#3BJbFc8Br22(K;i?I$n@hy(w6n?_b_zm~*0?v2X zZ^(&IL?RzPKsi)JZPdq?XpVSvMIQ{sXiUIN%*AqS!d`rblQ@f?@e4BX7_Z^}JNpd* zh(s3D#baJ$EvLogzc7x_^P zAEO37!xw0VwrG!U&=(^x5z{dTOR*B0u@A@bBQD_@(s3Jq;0?U)v*r+v801GGl*A{f zgGTrYt;3P0g0Zs0cV;ZHa}V9g;E(a3{BD2g(uiu(8x zEzt&@k%V3tiV2vB`B;Lr*ofWu4rlQ*enlGY;Sv6V`$N_oBH_ThD2fs&kD6$R=7>c* zB%vGnVI-ztE*4`2HexIG<9l4dFZc~vc!a0;8{UstbI65!D2Ng$jY{|wP4G41(Fxtq z1A{OYGq4cLu?AbQ6Nm5vF5@OLaTibV0xpkPcZfh<6u|o^jdG}l&(I8Q(GiL0fj$_9 ziI{_>Sd9(XiM=?AA8`%o_#F@N0qL*H|UN57=m$_i6vNz z&Dep1ID*so8ELqOKkyt*PucVELnPisQItekR6z|iKy$Q15>n9{Lofo9Fc&MZ5!`y*6av}_Q@jgnUJSw9O>Z2*zA`v~%4}&oV6EF))u>m`=ABS-YXK@AT zc!(GH8?Mj!*a$!r@}oG)p%SX2J{qD0+9Mf#FbKmj0aGv!E3pN8aR|q778h_GxA6q8 z;qroWECLXM+$e-nsEBH)jfQA~*657x7=U3IjVYLcMOcd+IEbS-i3_-lTeyekaC*sp zgAYOwfp<_8Wl;sSP!CPe3~@+8Zw$dGjK>Vj!7^;b9vs05oWW&WLk1q<72N(}zri07 zh{1a(feNUBy7(N;&umG#D6$fw}r*R(Fa07Sn6!wZW2R{TO26<2z zrBNAm&;Vbc71|&HJunz!FbUJK086kAJ8>ANa1NJn18KOA7jS*ennMu6kq7VM1C&E` z)JJ1{g*Ir1uIPi|n1E@RjU`xtP1uWLIE#z8iZo;)`=8k4l#Xpv6Jk^1yLCH9`~@2q~HhN6z7mZqMlrmC*2wyvKq z=w~eYIg@_Yrk^+JXRi9Wvwrrj>ko7Zg)Sq}r8K&nNS9RUvNBy-r^^d#}oQdav6LbPI-VL(#1`x*bWkWa+jv-I}M{6LpKGZd28*y1HFiw`}XSb=|tJ z@dcW|pa~3`z@P~Xn!un544S~82@IORpa~3`z@P~Xn!un544S~82@IORpa~3`z@P~X zn!un544S~82@IORpa~3`z@P~Xn!un544S~82@IORpa~3`z@P~Xn!un544S~82@IOR zpa~3`z@P~Xn!un544S~82@IORpa~3`z@P~Xn!un544S~82@IORpa~3`z@P~Xn!un5 z44S~82@IORpa~3`z@P~Xn!un544S~82@IORpa~3`z@P~Xn!un544S~82@IORpa~3` zz@P~Xn!un544S~82@IORpa~3`z@P~Xn!un544S~82@IORpa~3`z@P~Xn!un544S~8 z2@IORpa~3`z@P~Xn!un544S~82@IORpa~3`z@P~Xn!un544S~82@IORpa~3`z@P~X zn!un544S~82@IORpa~3`z@P~Xn!un544S~82@IORpa~3`z@P~Xn!un544S~82@IOR zpa~3`z@P~Xn!un544S~82@IORpa~3`z@P~Xn!un544S~82@IORpa~3`z@P~Xn!un5 z44S~82@IORpa~3`z@P~Xn!un544S~82@IORpa~3`z@P~Xn!un544S~82@IORpa~5B zznj2d`bS4VM?gnFM?gnFM?gnFM?gnFM?gnFM?gnFN8tZcM_{*yS&E-o(J-^DTxN^& zo3$uv7FycuYz4E?)y=BaGkeq6Y-bCzc_DyD8cbOIX)-3I~+5EF+O)r}T-Y`3rX*T?US*1VCUcNEg>h5HTzD`yk)X8qe zIN98Hovg|GPUc_A$xf7avZ2+StYTd!d)~;&HaB;>ktWzq6CwNOrQ>y`8M_U?=k( z?PSL%IoaS@PF8-AlRaDMWE(d+S*M*&mhYgGT|eezGtW3#!%I%)^Q)5`&2X}T_noZV zGbelU+R4_tIa`OE&XzaC*{(%9+w^?S)}V;9d6#syBOg0k|EkVb=2K^T+|b$9HgmRi zZJf=~$=R-a<7`uVIa~cf&gMDF*$z!~w!Sl+t@J`?d$_{cR&Q{&xE;=x>wvReKI&|f zPdi)Pi_YeL-PsPNJ6rF2&Q|iNv)zB?Y%5(|tc{P0MF+ds#V8k>_>PO!DePjdAG+B7 zaxT`hii?$~<6?I|cd_MPxmfF17mMuZVi&r)*!Z3i zEO)V`>s_qXb{7lZ?_%e^bFr~MxLA#!T+DuPvE6AdmU7p{iav3%tiN1rv5Tv<$l+?C zL9TW-($z-ib+u}RT}E~8-ONAG%}zwP+0Z<0R zdf3edo^-Qv=iThd6*pUd%gs96akIRS-R#;6H=FL{ZVkNL%{#!|j)c2ge}}u3Dd298 zKXA9TAGuq*Pu$H>)7`Grceklc+^v2qck^uLZil+KTi;Z7E8WlC9u9T4)nnZ)ZmPTG zn(J6?banvoBOM$HOcfe{|BCS;+dxnedB2r-M#F2PA}UW;$;ajUY7q| zFS}91%VwAKvc~1T%(t4C9sktJ1~>Au^3A>MSsO3g*vZQ}C3{)E-d=WnkeAIIg zd6~~FFFU%>%LcCWvT_@}?8y!WAJ||6_0StmUdk4ww|xNt%Pe1yPG42Ef30Jt)p^S}Yv-`;pXab*U*)hnt#jDY4mqq<*Bln!Gl!iUki*7~$YC`m$LS?ABHvo4eP?njG;l|5HA8;=GRyz3O8XfAg{D zcYJK~V;@U+>0|kwbJ`8BoHjckr!|hqX})=K+VKK8ZE&%iR=!M5d-h3A+gLNFb^0u) z<@++HU2m1sX12>|4HI*kPxqX5v|mmeI4q}?8<*3bOwDQQ=jOByOLJP@wK?tDmYgNIqmW7oVNB+PHXofr#YN_?TV+bP4)M+`r*Fj>F~8f z@A+Ea4}7ikN51y3qOYy4;cIdAeJxiLU%TAW*CxmNTHP+b=APmR9$(R`vWW{0l!j*TT=n#`#%| z1Wx*#_;>g5vy>rzR&IN09`jP|!%ll*P&EPrdV$lv@|`P+$& z{x)={zg0ZwZ_khU+vYR=mT<}6^8e~@H!}Qf_I-bA{LJ5c-}u{cw*VWQGr-D+1lY6a z0Na=^z&aHPuzV#0?E1$6HnVDgHT*Qdd>RGV(PjZQuuXuK>l9#5z6r4Py#lPmpa9D| zD!{Hy46x}l1FXTq0P|iMU`I9tSpOXXR^~u}Jw6&>YflGQyNdzlxE^3v(gSSjy#TBK zG{8Jx2iPIkKZuT>MRH}*A;=be|@0!+#YBp_6OSC?*eW4 z4}sSDr$CGRCD1OU1={$#fmZ8DpgF$^w7o7t);&j%6$=WoJCQ-QG;ff#DimblC4%f+ z*&rKRIml|%4l?^Z$aXgkvXs_ARXg0BVH>ED8EMU*q$#9w#{pUEn#c0<=-1@Hx38e?32OP_4-E5n}bvg_!4+5Ib};#QNS2vC@x1?BVkeTWz5h=NW3b{6p<>Sg1|T9cp#o3pMu- zLhWGbQ0rYW)JoO}wfpr#ZRHoC)~02sMaPHQ#e`6sm=bDr`i7e8&`{eyCe(UP3AGY) zLhbJ2P+Pt_)LL&2waDF}cH!Gl8~=T%)%r2ioPQ3ry*EOwdse6wdl+hW{tUIHe}`Ht zk1z}O3$t^fVKz2bnAOP73w~bo?=BT)DHX!3X!S75svBmD8;4no7GV||7iMQWhuP?E zVOFhAn7tVsW;;iRS@PsCD>6IGG8To|!c}3`Y*Uy8?+UZi2g7XS@i41$Hq2gK3bXCM zhFRClFe~&R%+j8P+59(Q*3>=R0)4~nR7kiDj|sO*?}ppUBH^~RWVj`k54QrAh!f>0tGTa((3^(7M z;dcB$xD7rQZspH}+p~+|w()wnb;=00eD}lc`qOZm`8wPhxu)I|x>{^`&o8B@10!th$OvmU zF~S@(Bkan82%EYh!s>5`FwY$kc4&Wu^*tJ4rB6rL!=EB-^)C??mmXoc?nT(;ClNOJ zRfN@bjWlinAcE3=htt=5~ZOTPjbd^ZESUb`tejaIczKS&0*ht&o zA<}wwjkFRyBkk^hNLxN4(ppc5w8$Bec42;`jb9#Vwbnn0Q8v0klvQgQWpBQYvYqXtEIBF4iu8!GjQ&x!aCnq88y{uC)1&P4yeJ#FEXt~^ zi?UZ+qip-$DC>G8$_kx|vb6J2HvejrHT^Bh0)LOPQ;(x;_{%7(fiS^GdWeycKOeccSg+ zqi7rWBHGG1#n=by+J1IxiJQz-swwcr*E8;zH6%^W8|c?J!>6pJH+y7 zWlUO?zHzD}ef{k8{bSyKs1znq#yJY~ijVD3&^znEthAj=-~O#}i_`W@&;E@2Kl&;9WH-v3pWNYD&kXM1I}K(b!SXJAK){%pohXhE96>UfaaB?c6mv zsjGuGXUyK3K6=hSZ|>OM5f_^h``^P{qNR6(UMU@TKk0jSJG#a8N*}$D|2fh}&UXCg zH#p>(Q&&2w7B2kuT~u~7aMbqxU;gBpvH$+b^rfpE-4c>|{QK+7wUgfdwd}Wdh)s@b zo0J^yU6)7P#8J<2d(TY%=V+gOBMmoLXMcjXXKa1@W%f=VxiNkBG)Kq8l=$SX$?^Q# zk#%5Z_Q7wP)TL|31b&^qY3zf&3;z3ge8}g)J58TF))AlBo-a>)vUldJeHrr(I5Ma1 z$=I{V(JuRe@kK~Zab(OLmp*z?`mB|X+cQ>Y&Kt<`h;t-#Y~LZ}?K{cZu$61r;vDVb zV^dO-$p8+U;5mY4(3sH zO#DCBdgJ8S#BS}9lDlvavR7r-*sj@!XZz@kdCT~>MBd6!9Ty;&JuIwtZ= zaC-#Xde7|tWt+yucV%P6C${ayGr;D|)r0sP{@t7zbM~k0S(dhQx1)Mu`-G0&Iyf>$ zjr(VLWj_(UefJ5miS1Kk+sFUAH8baIWm#se81(kwG=BTpup@aI%ifp&UB(&fmZXoI z<%sXey6x7D4eDJpnP<27#FXr}CGaHncBd{{o3U``KVQFOmUK$?K22Y`HFL#~{~WID zuS7D>i~l|Hr8x3)M`b?~X8%_Dgf)(DQezWSQoDF(Y#WpPoR~R&L;B(&j^xxt2P>jo zeA^WE)acCJ?0_|6(#LH{-?+)qHaWIi2fl*Kc+Tb1oIA$RB`L9EO7`)cFe!8V#_VIj z%3+cI=SeYR-7@ctskX!ZQj*0*Myh^w9PTRLIdux>~TRQv6GW$P^ z75nJlw`MM%kTIJ5^v`d!Nli{nN@brWC&i`m8D=dX$o_=NcO9HoCAZT7x<`xz#6Nn%m;czZrrKG?yRHe>uUN4K`g9r;RRjaZ#NdZnXV zYMU+{QyiJg_hbzkn|5Fk5BRgxf6ixL{`16Nj)gTWecjCLrQDgbTK3bMBQBLEsJAD% zy#K@A`yV#6qrm@uGArm^_w8rG^WEk}*?Xyb_RW?&U#v>su{m?kgtXo3|A%+{|Fo&I z&zz0|Z0q#(Lkhm#-kdZOIOinCXP=S_zTM~l{I?@x#=?wgBX#E1nOkRWow>75r#f@% z%&jx`|MXH^XKsDZt?#+@J-5E+{x^;3dv1Ntt?#+BUp4D{Zq@Sab)Z_VTCQ5ITCQ5I zTCSgS>*w71Ik$e!t)Fx2=iK@^w|>s8E7Wv_nyyg$e|a&Bu29nzYPv#ASE%XQa$Q@V zeM!2mE!VZ>y0%=`mh0MbU0eRYUr4XJ!gN=d?h4agVY(|!cZCgd=&rE;<5o{yp{6U; zbcLGk=hpq)**ClE3N>A!rYqERg_^EV(-msELQPkw=?XPnp{6U;bcLF(P}3D^xO0D}N%{YyJzct8wnxh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO z%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=Qlw%nH6a$9c8ZMiMC<+j|G+j3iO q%Wb(Wx8=6nmfLb$Zp&@CEw|;i+?LyNTW-s3xh=QlwtQjBQ&$f!$f3vp literal 0 HcmV?d00001 diff --git a/zh_lora_dataset/dataset_info.json b/zh_lora_dataset/dataset_info.json new file mode 100644 index 0000000..7f715b9 --- /dev/null +++ b/zh_lora_dataset/dataset_info.json @@ -0,0 +1,32 @@ +{ + "citation": "", + "description": "", + "features": { + "keys": { + "dtype": "string", + "_type": "Value" + }, + "filename": { + "dtype": "string", + "_type": "Value" + }, + "tags": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "speaker_emb_path": { + "dtype": "string", + "_type": "Value" + }, + "norm_lyrics": { + "dtype": "string", + "_type": "Value" + }, + "recaption": {} + }, + "homepage": "", + "license": "" +} \ No newline at end of file diff --git a/zh_lora_dataset/state.json b/zh_lora_dataset/state.json new file mode 100644 index 0000000..a055cda --- /dev/null +++ b/zh_lora_dataset/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "76c203d4bc1fdd7e", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file