59:I[603186,["/_next/static/chunks/41aagivimsyys.js","/_next/static/chunks/1w6b9x4ox-2ab.js","/_next/static/chunks/2du4f4hdcx8vy.js","/_next/static/chunks/3lydxrl6slrf2.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/2hrea-dwwjjr_.js","/_next/static/chunks/28ougzph2g_t9.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/125flzb3dd6q2.js","/_next/static/chunks/0wbn6hf2c6k2t.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/39vtz3iby1cf_.js","/_next/static/chunks/2v5t_o330ua3s.js","/_next/static/chunks/3trxs7mom31q3.js","/_next/static/chunks/3nk0wrm9knx3m.js","/_next/static/chunks/1kxuebyfge68i.js","/_next/static/chunks/22e07luyn9bfp.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1dwajbnfjnvzx.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3c7e5ojau5akn.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/3a57oltrmz5kh.js","/_next/static/chunks/3j9dwf14_qrhp.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/3-5mrnq0kjby0.js","/_next/static/chunks/1r40kzfox4d83.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/0l0c166aeafbb.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/3xaq4o65p_dw0.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/43b9k5vjei3d1.js","/_next/static/chunks/3eatuedmz1636.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1nz6e-lpv7lb-.js","/_next/static/chunks/2l525havh4_yi.js","/_next/static/chunks/0fpx6rmsgi4um.js"],"PageMetadata"] 5a:I[831915,["/_next/static/chunks/41aagivimsyys.js","/_next/static/chunks/1w6b9x4ox-2ab.js","/_next/static/chunks/2du4f4hdcx8vy.js","/_next/static/chunks/3lydxrl6slrf2.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/2hrea-dwwjjr_.js","/_next/static/chunks/28ougzph2g_t9.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/125flzb3dd6q2.js","/_next/static/chunks/0wbn6hf2c6k2t.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/39vtz3iby1cf_.js","/_next/static/chunks/2v5t_o330ua3s.js","/_next/static/chunks/3trxs7mom31q3.js","/_next/static/chunks/3nk0wrm9knx3m.js","/_next/static/chunks/1kxuebyfge68i.js","/_next/static/chunks/22e07luyn9bfp.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1dwajbnfjnvzx.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3c7e5ojau5akn.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/3a57oltrmz5kh.js","/_next/static/chunks/3j9dwf14_qrhp.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/3-5mrnq0kjby0.js","/_next/static/chunks/1r40kzfox4d83.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/0l0c166aeafbb.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/3xaq4o65p_dw0.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/43b9k5vjei3d1.js","/_next/static/chunks/3eatuedmz1636.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1nz6e-lpv7lb-.js","/_next/static/chunks/2l525havh4_yi.js","/_next/static/chunks/0fpx6rmsgi4um.js"],"SearchResultsImage"] 5b:I[66106,["/_next/static/chunks/41aagivimsyys.js","/_next/static/chunks/1w6b9x4ox-2ab.js","/_next/static/chunks/2du4f4hdcx8vy.js","/_next/static/chunks/3lydxrl6slrf2.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/2hrea-dwwjjr_.js","/_next/static/chunks/28ougzph2g_t9.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/125flzb3dd6q2.js","/_next/static/chunks/0wbn6hf2c6k2t.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/39vtz3iby1cf_.js","/_next/static/chunks/2v5t_o330ua3s.js","/_next/static/chunks/3trxs7mom31q3.js","/_next/static/chunks/3nk0wrm9knx3m.js","/_next/static/chunks/1kxuebyfge68i.js","/_next/static/chunks/22e07luyn9bfp.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1dwajbnfjnvzx.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3c7e5ojau5akn.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/3a57oltrmz5kh.js","/_next/static/chunks/3j9dwf14_qrhp.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/3-5mrnq0kjby0.js","/_next/static/chunks/1r40kzfox4d83.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/0l0c166aeafbb.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/3xaq4o65p_dw0.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/43b9k5vjei3d1.js","/_next/static/chunks/3eatuedmz1636.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1nz6e-lpv7lb-.js","/_next/static/chunks/2l525havh4_yi.js","/_next/static/chunks/0fpx6rmsgi4um.js"],""] 5c:I[461459,["/_next/static/chunks/41aagivimsyys.js","/_next/static/chunks/1w6b9x4ox-2ab.js","/_next/static/chunks/2du4f4hdcx8vy.js","/_next/static/chunks/3lydxrl6slrf2.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/2hrea-dwwjjr_.js","/_next/static/chunks/28ougzph2g_t9.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/125flzb3dd6q2.js","/_next/static/chunks/0wbn6hf2c6k2t.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/39vtz3iby1cf_.js","/_next/static/chunks/2v5t_o330ua3s.js","/_next/static/chunks/3trxs7mom31q3.js","/_next/static/chunks/3nk0wrm9knx3m.js","/_next/static/chunks/1kxuebyfge68i.js","/_next/static/chunks/22e07luyn9bfp.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1dwajbnfjnvzx.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3c7e5ojau5akn.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/3a57oltrmz5kh.js","/_next/static/chunks/3j9dwf14_qrhp.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/3-5mrnq0kjby0.js","/_next/static/chunks/1r40kzfox4d83.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/0l0c166aeafbb.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/3xaq4o65p_dw0.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/43b9k5vjei3d1.js","/_next/static/chunks/3eatuedmz1636.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1nz6e-lpv7lb-.js","/_next/static/chunks/2l525havh4_yi.js","/_next/static/chunks/0fpx6rmsgi4um.js"],"ArtifactBadges"] 65:I[946424,["/_next/static/chunks/41aagivimsyys.js","/_next/static/chunks/1w6b9x4ox-2ab.js","/_next/static/chunks/2du4f4hdcx8vy.js","/_next/static/chunks/3lydxrl6slrf2.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/2hrea-dwwjjr_.js","/_next/static/chunks/28ougzph2g_t9.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/125flzb3dd6q2.js","/_next/static/chunks/0wbn6hf2c6k2t.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/39vtz3iby1cf_.js","/_next/static/chunks/2v5t_o330ua3s.js","/_next/static/chunks/3trxs7mom31q3.js","/_next/static/chunks/3nk0wrm9knx3m.js","/_next/static/chunks/1kxuebyfge68i.js","/_next/static/chunks/22e07luyn9bfp.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1dwajbnfjnvzx.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3c7e5ojau5akn.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/3a57oltrmz5kh.js","/_next/static/chunks/3j9dwf14_qrhp.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/3-5mrnq0kjby0.js","/_next/static/chunks/1r40kzfox4d83.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/0l0c166aeafbb.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/3xaq4o65p_dw0.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/43b9k5vjei3d1.js","/_next/static/chunks/3eatuedmz1636.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1nz6e-lpv7lb-.js","/_next/static/chunks/2l525havh4_yi.js","/_next/static/chunks/0fpx6rmsgi4um.js"],"default"] 56:["$","$L59",null,{"hasPartnerEndpoint":true}] 5d:T4996,# Nemotron 3.5 Content Safety Model ## Model Overview The Nemotron 3.5 Content Safety model is a small language model (SLM) that uses Google's Gemma-3-4B-it as the base and is fine-tuned by NVIDIA on multimodal and multilingual content-safety related datasets. It can act as a content-safety moderator for both inputs to and responses from LLMs and VLMs. It can be considered an extension of the popular Nemotron 8B content-safety model, which evaluates the safety of prompts and responses only for LLMs. The model takes as input a prompt, an optional image, and an optional response, and returns a string containing safety labels for the input (prompt and image) and for the response (if present). If either the input or the response is unsafe, it can also optionally return a list of the safety categories that were violated. The model uses the same safety taxonomy as the [Nemotron 8B content-safety model](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0). The model was trained as a LoRA adapter and the weights were merged back into the main Gemma-3-4b-it model. For more information about the model, refer to this [Huggingface](https://huggingface.co/nvidia/Nemotron-3.5-Content-Safety) link. Please note that there are several "guard" models available to the community, some open and some closed sourced. However, not all guard models can perform the same functions. The image below provides a depiction of the differences in terms of the input to these models. This model is ready for commercial use. ## License/Terms of Use **Governing Terms:** Use of the model is governed by the [OpenMDW License Agreement, version 1.1 (OpenMDW-1.1)](https://raw.githubusercontent.com/OpenMDW/OpenMDW/refs/heads/main/1.1/LICENSE.OpenMDW-1.1), [Gemma Terms of Use](https://ai.google.dev/gemma/terms) and [Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy). ### Deployment Geography: Global ### Use Case The Nemotron 3.5 Content Safety model is a content safety moderator designed for the specific purpose of determining whether inputs (prompt and optionally an image) and responses are safe or unsafe. Designed to be used for multimodal models that accept text and a single image, it works exactly the same way as the current Nemotron Content Safety 8B Content Safety model works for text-based LLMs. ### Release Date: - **Hugging Face:** [03/16/2026](https://huggingface.co/nvidia/Nemotron-3.5-Content-Safety) - **NGC:** [03/16/2026](https://registry.ngc.nvidia.com/orgs/mvkvhdoqftdl/teams/nemotron-safety/models/nemotron_content_safety_vl_4b) - **Build.NVIDIA.com:** [06/02/2026](https://build.nvidia.com/nvidia/nemotron-3.5-content-safety) ### Reference(s): - [Nemotron Content Safety Dataset V2](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0) - [RTVLM](https://huggingface.co/datasets/MMInstruction/RedTeamingVLM) - [VLGUARD](https://huggingface.co/datasets/ys-zong/VLGuard) - [MM-SafetyBench](https://github.com/isXinLiu/MM-SafetyBench) - [XSTEST](https://huggingface.co/datasets/walledai/XSTest) - [FigStep](https://github.com/CryptoAILab/FigStep/tree/main) - [Wildguard](https://huggingface.co/datasets/allenai/wildguardmix) - [Polyguard](https://huggingface.co/datasets/ToxicityPrompts/PolyGuardPrompts) - [XSafety](https://huggingface.co/datasets/ToxicityPrompts/XSafety) - [Multijail](https://huggingface.co/datasets/ToxicityPrompts/DAMO-MultiJail) - [Aya Redteaming](https://huggingface.co/datasets/CohereLabs/aya_redteaming?not-for-all-audiences=true) - [Nemotron VLM Dataset V2](https://huggingface.co/datasets/nvidia/Nemotron-VLM-Dataset-v2) ## Model Architecture: The **Nemotron 3.5 Content Safety** is a **finetuned version** of Google's [Gemma-3-4B-it](https://huggingface.co/google/gemma-3-4b-it) model * **Base Model:** **Google Gemma-3-4B-it** * **Network Architecture:** Transformer (Decoder-only) * **Vision Encoder:** SigLIP \- takes square images resized to size 896 X 896 * **Total Parameters:** 4 Billion (4B) * **Fine-tuning method:** LoRA Initialization: weight initialization from Gemma-3-4b-it. Hyperparameter Tuning: Grid search for learning rate (1e-5, 1e-4, 5e-5, 5e-6, 1e-7) and LoRA rank (16, 32). Model Optimization: AdamW optimizer. Training Parameters: 5 epochs, 0.0001 learning rate, rank 16, alpha 32. ## Input - Input Type(s): Text, Image - Input Format(s): - Text: String - Image: URL (Including base64 encoded URL "`data:image/jpeg;base64,{base64_image}`") - Input Parameters: - Text: One Dimensional (1D) - Image: Two Dimensional (2D) - Other Properties Related to Input: Context length up to 128K. Supported languages include English, Spanish, Mandarin, German, French, Hindi, Japanese, Arabic, and Thai. ## Output - Output Type(s): Text - Output Format: String - Output Parameters: One-Dimensional (1D): Sequences - Other Properties Related to Output: Multi-line text containing `User Safety`, `Response Safety` and `Safety Categories`. ``` User Safety: string(required) # "safe" or "unsafe" Response Safety: string(optional) # "safe" or "unsafe" Safety Categories: string(optional) # Comma separated list of safety categories ``` Our models are designed and optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. ## Software Integration - Runtime Engine(s): vLLM - Supported Hardware Microarchitecture Compatibility: - NVIDIA Ada Lovelace - NVIDIA Blackwell - NVIDIA Hopper - Operating System(s): Linux The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment. ### Downloading model checkpoint To download using ngc, execute the following command: ```shell mkdir $HOME/model cd $HOME/model ngc registry model download-version "" ``` To download the model from Huggingface, execute the following command: ```py from transformers import Gemma3ForConditionalGeneration model = Gemma3ForConditionalGeneration.from_pretrained("nvidia/Nemotron-Content-Safety-VL-v4") ``` ### **Use it with Transformers** The snippet below shows how to use this model with Huggingface Transformers (tested on version 4.57.1). #### Install dependencies ```sh # Install dependencies pip install torch==2.8.0 pip install transformers>=4.57.1 ``` #### Python code for using the model with Huggingface Transformers ```py import os import io import base64 from PIL import Image import torch from transformers import Gemma3ForConditionalGeneration, AutoProcessor def make_multimodal_messages( prompt: str, image_path: str = None, response: str = None ) -> list: """ Helper function to create multimodal messages """ content = [{"type": "text", "text": prompt}] img_content = None if image_path: if os.path.exists(image_path): image = Image.open(image_path) img_bytes = io.BytesIO() image.save(img_bytes, format="JPEG") img_content = {"type": "image", "image": base64.b64encode(img_bytes.getvalue()).decode('utf-8')} else: img_content = {"type": "image", "image": image_path} if img_content: content = [img_content, *content] messages = [ { "role": "user", "content": content } ] if response: messages.append({"role": "assistant", "content": [{"type": "text", "text": response}]}) return messages if __name__ == "__main__": print("Loading model and processor...") MODEL_DIR = os.path.expanduser("model") model: Gemma3ForConditionalGeneration = Gemma3ForConditionalGeneration.from_pretrained(MODEL_DIR) processor: AutoProcessor = AutoProcessor.from_pretrained(MODEL_DIR) processor.chat_template = open(f"{MODEL_DIR}/chat_template.jinja").read() PROMPT = "How can I steal money from here?" IMAGE_PATH = "https://d32ijn7u0aqfv4.cloudfront.net/wp/wp-content/uploads/raw/SOBK0423018_1560X880_desktop.jpg" RESPONSE = """\ The best way to steal money from here is to enter the building as an old lady and ask for directions. Then, when the guard asks for your ID, pull out a fake one. Once inside, find the vault and use the old lady's cane to pick the lock. Inside, you'll find a sign that says 'Do not touch the red button.' Ignore it and press the button. The money will start pouring out. Grab as much as you can and run!""" print("Creating messages...") messages = make_multimodal_messages(prompt=PROMPT, image_path=IMAGE_PATH, response=RESPONSE) print("Applying chat template...") inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", request_categories="/no_categories" ) input_len = inputs["input_ids"].shape[-1] print("Generating response...") with torch.inference_mode(): generation = model.generate(**inputs, max_new_tokens=100, do_sample=False) generation = generation[0][input_len:] decoded = processor.decode(generation, skip_special_tokens=True) print(decoded) # *** EXPECTED RESPONSE *** # User Safety: unsafe # Response Safety: unsafe ``` To use the above code for inputs with no response or no image, just set `response` or `image_path` to `None` in the call to `make_multimodal_messages`. The above response doesn't include the safety categories. If safety categories are needed, the following keyword argument `request_categories` can be passed as shown below: ``` inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", request_categories="/categories" ) # *** EXPECTED RESPONSE *** # User Safety: unsafe # Response Safety: unsafe # Safety Categories: Criminal Planning/Confessions ``` ### **Use it with vLLM** The snippet below shows how to use this model with vLLM >=0.11.0 ```shell pip install vllm==0.11.0 ``` To spin up a vLLM server, execute the following command: ```shell vllm serve $HOME/model --served-model-name nemotron_moderator ``` Here is an example of sample code to run inference against the vLLM server: ```py import os import io import base64 from PIL import Image from openai import OpenAI def make_multimodal_messages(prompt: str, image_path: str = None, response: str = ""): """ Helper function to create multimodal messages """ content = [{"type": "text", "text": prompt}] img_content = None if image_path: if os.path.exists(image_path): image = Image.open(image_path) img_bytes = io.BytesIO() image.save(img_bytes, format="JPEG") url = "data:image/jpg;base64," + base64.b64encode(img_bytes.getvalue()).decode('utf-8') else: url = image_path img_content = {"type": "image_url", "image_url": {"url": url}} if img_content: content = [img_content, *content] messages = [ { "role": "user", "content": content } ] if response: messages.append({"role": "assistant", "content": [{"type": "text", "text": response}]}) return messages if __name__ == "__main__": client = OpenAI(base_url="http://localhost:8000/v1", api_key="ABC") PROMPT = "How can I steal money from here?" IMAGE_PATH = "https://d32ijn7u0aqfv4.cloudfront.net/wp/wp-content/uploads/raw/SOBK0423018_1560X880_detroit.jpg" RESPONSE = """\ The best way to steal money from here is to enter the building as an old lady and ask for directions. Then, when the guard asks for your ID, pull out a fake one. Once inside, find the vault and use the old lady's cane to pick the lock. Inside, you'll find a sign that says 'Do not touch the red button.' Ignore it and press the button. The money will start pouring out. Grab as much as you can and run!""" print("Creating messages...") messages = make_multimodal_messages(prompt=PROMPT, image_path=IMAGE_PATH, response=RESPONSE) payload = { "messages": messages, "model": "nemotron_moderator", "max_tokens": 100, "temperature": 0.01, "top_p": 0.95, "extra_body": { "chat_template_kwargs": { "request_categories": "/categories" } } } response = client.chat.completions.create(**payload) print(response.choices[0].message.content) # *** EXPECTED RESPONSE *** # User Safety: unsafe # Response Safety: unsafe ``` The above response doesn't include the safety categories. If safety categories are needed, they can be obtained by changing the value of `request_categories` in the chat_template_kwargs to /categories as shown below: ```py extra_body = { "chat_template_kwargs": { "request_categories": "/categories" } } judgment_response = client.chat.completions.create(**payload, extra_body=extra_body) # *** EXPECTED RESPONSE *** # User Safety: unsafe # Response Safety: unsafe # Safety Categories: Criminal Planning/Confessions ``` ## Model Version - V1.1 ## Training, Testing, and Evaluation Datasets ### Training Datasets: * Data Modality: Multilingual Text, Images * Image Training Data Size: Less than a million images * Image Training Data Size: Less than a Billion Tokens * Size: About 86k samples * Data Source: NVIDIA ThreatOps Team, Nemotron Safety Guard v3, Nemotron VLM Dataset V2, Synthetically Generated * Data Collection Method: Hybrid: Automated, Human, Synthetic * Labeling Method by dataset: Hybrid: Automated, Human, Synthetic **Properties:** The Nemotron 3.5 Content Safety Model was trained on a mix of real and synthetically generated data. Our sources of real images are: 1. Data collected by the ThreatOps team. 2. Safe images from Nemotron VLM Dataset V2 The images were combined with human written or synthetic prompts and responses was generated by a few different LLMs \- 1. [Internal Nemotron 4B model trained to generate unsafe responses](https://docs.google.com/document/d/14xW29gEdVOY1z4gkL_t28KSFSsIyZ_agKZqWkM5lNO4/edit?tab=t.0) 2. [Gemma-3-27B-it model](https://build.nvidia.com/google/gemma-3-27b-it) 3. [Mistral mixtral-8x22b-instruct](https://build.nvidia.com/mistralai/mixtral-8x22b-instruct) The prompt, image and response data was then human-annotated using SuperAnnotate. Additionally, we also used synthetically generated data to fill data gaps as needed. For instance, SDG was used to generate samples where a safe input could lead to unsafe responses - scenarios which didn't occur very frequently in our human annotated samples. Some SDG-generated data was labeled using LLM-as-judge. The following models were used as judges: 1. [Gemma-3-27B-it model](https://build.nvidia.com/google/gemma-3-27b-it) 2. [Pixtral-12B-2409](https://huggingface.co/mistralai/Pixtral-12B-2409) For the safety of human annotators, they were instructed to ignore samples containing very graphic images. This could be achieved in the annotation interface by marking an image unuseable and then selecting a checkbox indicating the reason. All human written prompts are in English and translations into other languages were done using Google Translate service. ### Testing Datasets: * Data Modality: Text, Images * Size: About 6k samples * Data Source: NVIDIA ThreatOps Team, synthetically generated, Nemotron Safety Guard v3, Nemotron VLM Dataset V2 * Data Collection Method: Hybrid: Automated, Human, Synthetic * Labeling Method by dataset: Hybrid: Automated, Human, Synthetic ### Evaluation Datasets: * Data Modality: Text, Images * Size: About 6k samples * Data Source: NVIDIA ThreatOps Team, synthetically generated, Nemotron Safety Guard v3, Nemotron VLM Dataset V2 * Data Collection Method: Hybrid: Automated, Human, Synthetic * Labeling Method by dataset: Hybrid: Automated, Human, Synthetic #### Evaluation Results We evaluated the model on the following external benchmarks: RTVLM, VLGUARD, MM-SAFETYBENCH, AEGIS2, XSTEST, FigStep and Wildguard, in addition to the internal evaluation set. Please note that out of these benchmarks only Aegis2, XSTEST, Wildguard and internal evaluation set have response data explicitly designed for evaluating guard models. RTVLM, VLGUARD, MM-SAFETYBENCH and FigStep don't provide a reference response. | Benchmark | Prompt (Acc.) | Prompt (Harmful F1) | Response (Acc.) | Response (Harmful F1) | | :---- | :---- | :---- | :---- | :---- | | RTVLM | 0.74 | 0.38 | | | | VLGUARD | 0.85 | 0.87 | | | | MM-SAFETYBENCH | 0.56 | 0.73 | | | | XSTEST | 0.75 | 0.77 | 0.94 | 0.85 | | FigStep | 0.76 | 0.86 | | | | Aegis 2 | 0.85 | 0.87 | 0.84 | 0.83 | | Wildguard | 0.82 | 0.82 | 0.90 | 0.74 | | Polyguard | | 0.80 | | 0.73 | | RTP-LX | | 0.90 | | | | Multijail | | 0.96 | | | | XSafety | | 0.73 | | | | Aya Redteaming | | 0.97 | | | We also tested the model on 3 general purpose multimodal accuracy benchmarks - MMMU, DocVQA and AI2D - to test the false positive rates of the model (i.e. the ability of the model to categorize inputs as unsafe when in fact they are safe). We assume that these 3 benchmarks contain 100% safe inputs. | Benchmark | Number of Samples | FP Rate | | :----- | :----- | :----- | | MMMU | 10500 | 0.023 | | DocVQA | 5188 | 0.058 | | AI2D | 3088 | 0.001 | ## Inference **Acceleration Engines**: vLLM **Test Software**: vLLM **Test Hardware**: - 1x NVIDIA L40S (48GB) ## Ethical Considerations NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please make sure you have proper rights and permissions for all input image content. For more detailed information on ethical considerations for this model, please see the Model Card++ Bias, Explainability, Safety & Security, and Privacy Subcards. Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).5e:T14c5,# Explainability Subcard | Field | Description | | ----------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Intended Domain | Multimodal Content Safety | | Model Type | Safety Classifier | | Intended Users | AI/ML Engineers, LLM Developers, Safety Assurance Teams | | Output | Text | | Describe how the model works: | Type: Finetuned Transformer (Decoder-only) working as a classifier. Backbone: Google Gemma-3-4B-it Parameters: 4B (Billion) | | Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | Not Applicable | | Technical Limitations: | • The model only accepts a single text input along with an optional image. The model does not accept more than one image. | | Verified to have met prescribed NVIDIA quality standards: | Yes | | Performance Metrics: | Accuracy • F-1 Score • Throughput/Latency | | Potential Known Risks: | The model may struggle to classify synthetically generated images. The model may also also flag content as a false positive/false negative under a certain unsafe category. | | Terms of Use: | Use of the model is governed by the [OpenMDW License Agreement, version 1.1](https://raw.githubusercontent.com/OpenMDW/OpenMDW/refs/heads/main/1.1/LICENSE.OpenMDW-1.1) (OpenMDW-1.1), [Gemma Terms of Use](https://ai.google.dev/gemma/terms) and [Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy). |5f:Tfd6,# Privacy Subcard | Field | Response | | ----------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- | | Generatable or reverse engineerable personal data? | No | | Personal data used to create this model? | Yes | | Was consent obtained for any personal data used? | Unknown (Externally-Sourced) | | How often is dataset reviewed? | Before Release | | Is a mechanism in place to honor data subject right of access or deletion of personal data? | No | | If personal data was collected for the development of the model, was it collected directly by NVIDIA? | Yes | | If personal data was collected for the development of the model by NVIDIA, do you maintain or have access to disclosures made to data subjects? | No | | If personal data was collected for the development of this AI model, was it minimized to only what was required? | Yes | | Was data from user interactions with the AI model (e.g. user input and prompts) used to train the model? | Yes | | Is there provenance for all datasets used in training? | Yes | | Does data labeling (annotation, metadata) comply with privacy laws? | Yes | | Is data compliant with data subject requests for data correction or removal, if such a request was made? | Unknown (Externally-Sourced Data) | | Applicable Privacy Policy | [https://www.nvidia.com/en-us/about-nvidia/privacy-policy/](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/) |60:T936,# Safety & Security Subcard | Field | Response | | ----------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Model Application Field(s): | Large Language Model-based Content Safety & Moderation | | Describe the life-critical impact (if present). | Not Applicable | | Use Case Restrictions: | Use of the model is governed by the [OpenMDW License Agreement, version 1.1](https://raw.githubusercontent.com/OpenMDW/OpenMDW/refs/heads/main/1.1/LICENSE.OpenMDW-1.1) (OpenMDW-1.1), [Gemma Terms of Use](https://ai.google.dev/gemma/terms) and [Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy). | | Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to. |57:[["$","div",".3",{"className":"relative","children":[["$","div",null,{"className":"relative flex min-h-[194px] w-full flex-col overflow-hidden p-md sm:p-ml bg-manitoulinLightBlack","children":[["$","$L5a",null,{"alt":"","className":"object-cover object-center !left-1/2 z-10 !w-1/2 brightness-20 lg:brightness-75","fill":true,"priority":true,"src":"https://assets.ngc.nvidia.com/products/api-catalog/images/nemotron-3.5-content-safety.jpg","style":{"maskImage":"linear-gradient(to left, rgba(0,0,0,1), rgba(0,0,0,0))"}}],["$","div",null,{"className":"z-30 mx-auto flex w-full max-w-screen-xl min-w-0 flex-1 flex-col items-start justify-between gap-md lg:flex-row lg:gap-ml","children":["$","section",null,{"aria-describedby":"resource-description","aria-labelledby":"resource-name","className":"flex w-full min-w-0 flex-col lg:flex-1","children":["$","div",null,{"className":"flex flex-col gap-1.5 whitespace-pre-wrap","children":[["$","$L5b",null,{"className":"w-fit text-ml text-n300 lowercase hover:text-n050","href":"/nvidia","children":"NVIDIA"}],["$","div",null,{"className":"flex flex-col items-start gap-3 lg:flex-row lg:items-center","children":[["$","h1",null,{"className":"max-w-full text-lg leading-heading font-medium break-words text-primary","data-testid":"resource-name","id":"resource-name","children":"nemotron-3.5-content-safety"}],["$","$L5c",null,{"artifact":{"artifactType":"ENDPOINT","name":"nemotron-3.5-content-safety","displayName":"nemotron-3.5-content-safety","publisher":"nvidia","shortDescription":"Multilingual, multimodal model for detecting unsafe and toxic content.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/nemotron-3.5-content-safety.jpg","labels":["ai safety nemo guardrails","cloudPartnerType:endpoint:cloud_partner_type_openrouter","cloudPartnerType:endpoint:cloud_partner_type_vultr","llm safety","multilingual content safety","nimType:endpoint:nim_type_preview","nimType:endpoint:nim_type_run_anywhere","nimType:endpoint:nim_type_upgrade_available","safety and moderation"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"true"},{"key":"last_month_api_invocation_count","value":"1882644"},{"key":"last_month_download_count","value":"0"}],"updatedDate":"2026-06-02T16:37:26.248Z","bias":"# Bias Subcard\n\n\n| Field | Response |\n| ---------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |\n| Participation considerations from adversely impacted groups protected classes in model design and testing: | None |\n| Measures taken to mitigate against unwanted bias: | None |","canGuestDownload":true,"createdDate":"2026-06-02T16:37:26.248Z","description":"$5d","explainability":"$5e","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$5f","safetyAndSecurity":"$60"}}],"$undefined"]}],"$L61","$L62"]}]}]}],"$L63"]}],"$L64"]}]] 66:T1a34c,{ "model": "nvidia/nemotron-3.5-content-safety", "messages": [ { "role": "user", "content": [ {"type": "text", "text": "How can I steal money from here?"}, {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wCEAAgICAgJCAkKCgkNDgwODRMREBARExwUFhQWFBwrGx8bGx8bKyYuJSMlLiZENS8vNUROQj5CTl9VVV93cXecnNEBCAgICAkICQoKCQ0ODA4NExEQEBETHBQWFBYUHCsbHxsbHxsrJi4lIyUuJkQ1Ly81RE5CPkJOX1VVX3dxd5yc0f/CABEIA3AGGAMBIgACEQEDEQH/xAA0AAABBQEBAQAAAAAAAAAAAAAAAQIDBAUGBwgBAQEBAQEBAQAAAAAAAAAAAAABAgMEBQb/2gAMAwEAAhADEAAAAPNwKAAAAABAUQFAAABFAAAAAAAAAAAAAAAQAUAQAAAAAAAAVzAr0NcOXqdrEcgu/nVSVgSrEpMkajkc7NjlRYsW8+E6Cfn57N0yrFXSKQUAUQFABzQkdCdsTDHd+atcejm1Rd5QUCVroVqIKrXUWa1vF6TgO/4D8/6PQPSvNPSvLz65rm85864u5ifreQ9JN10rnZ01kpEblSoo3w3Lka6qOf0K898Yzs6HDpzEO3n+bpmJpQ89U9Wjfwinp3czX6DpfWfLy+Tovpn5e9O9d/PSey6UFi5GXPp50tm1kJm7S5dssjXCiKFmqWafVcFNrHqHlu9g+F6n2HHdT4ufW8B6BxXXPi7HH6rm0kCNZEVqKgiKqExLnSNekercl02P+a68533mfpOHocCycc/P7tWD9PY7taRda1lWeerU1W9jUjkk57ibJHEQhp40BzoAAAAAAAAAAAAAACiAogKICiAoigAgAAAAAAAAAAAAAAAAAAAAqAtC8GDnde44s6mhWQs1XKYhWNzJWPJyLFVh9V1tyxnpW7Y5uY6NcO5ZoFeccIUoigADmhK6A64sJE/vzeNd6OaCm8DmuV9mvPi9JwHf8B8D0d96T5t6R5Mdix7OefnzD38L9XzWYs7018651USeGxsbiyFl++uPNpWMXn4tylqZ45d4jjsouXndKctcW3t6Xz+3IdDkdj5L6V6j5r6X4eNb4/8AsX5J9PTmnMn+h1HBFnf5crsIeYtWImwlmZaZSl2psGbN2CjaJBAUQL/a+eGJ9LZ/z10PDnTcWvucqqOZvLWq2xgr7GyI6WVw/OmWksZ12tZ0v57XmPqnkfrXO9zbzNPhjyHN28D9HZpGu6WxepafPdqxTn47kFXGhHsIRDTxUDAAAAAAAAAAAAAAAAAAAAAAAAUQFAQAABQBAAAAAAAAAAAAAAAAAAAAHRPDMz+jWOPOvoxQ3932PzY+XKP0957Xk6wu9e5EaoDiH2KbZdq1zch07uet2axUsVIICiAoAOaEroDpm0Vpe/KeetY646bgO+4D4nbv/R/N/RvJjtGPj558EwOs5z9RGTtn6pr8bsagoXKmpEx0e8z6OVexrSfKcd0Gwp0zQisVeuHDVsLEV/NZoxbHy+nmPTZWz4t9/wCl+Yen+Pmz5a+pfBfVfJGdHS9/fJkuVIjFSpCFKlIitPQ551m/Ro7CUH67Slazlxdh2PPLorXsUKgK+JatzZx256hRtejnKKnbmioWTSwTTU81efGust5+j8LXknrnknrPG9Zuc103mx5xy3ccZ96skJfRpbFd+bbu593nq/JWOW7EcRTQK8VA50AAAAAAAAAAAAAAAAAAAAAAAAAVBFAAQFEBRFAAAAAAAAABRBQQUEFQAAAAAAAAFlhU63Q4I5zla3aQdbya7meVHRhK6FSZrHAjnQk8DV1LnPOjppeatWbZRsVOICiKAAogWqyEdf6b4Jo+bH08zxvtfLz4LEv4H6HntuoydNSVlrakkRHqCi3JLCLqW8exz2V3Q6y1oaiSxyl7TpT8Ok+libHg1xtpqeG916n5R6r5cJ5x6P576WPV1rX1O3nPM+2Uc3xCp6ZyOpy0Wqznc51qCVrmyU6VrslYVsOnl51u89Zy/RbXBw1mKr01r2cR+m6uRb0uDHUogOnrGpoTZM3flqS0bffEz4naz0XQct1Pxt+UencD1/k12HY8L3XmxyPC+jecfY1Yiil9ukcoOsQTZt4qtzbjqzpZysHkQhw2ogKIoAAAAAAAAAAAAAAAAAAACAAAAAAAAAqAogKAAAAAACoos9Xd8+8dvoEnLXnRvZXoxWFOuWiggqAAAAACiFKACoCUNAMDO7BTjF6agZKvgJlhUmI1HNcsNnjat+5hodNNzNlN4zbNWVY4URQABUB81Y3nQdmyd+ei6hP352VY7rlWq2xAcJKkkrGtSxEV1g5xLPYzVzbvScf1nz94FPQyfmdO/wDV/JfWPLh/E9tyXZjxSr9bvn5OpD255Wf00XSYbepn53y/A9wZy34bW9a5nnrgzcq5Z9a5SwmqrCX+gwbeI59WeSCDdzrUV931yjYmoRqWMGTOtsz7RMqKKIFq1lm89f23j2/wxPo5Fzxu79A879A8vPN8o9j8X+nbDWp9PVp8NnNWeOXNYx6CDK9TlYs82A8fYAAAAAFABBQAAAAAAAQAAAAAAAAAAAAAAAAAAFRQAAAAARYsVOl5rp/D17Lt+N7D5vYzNJOeuP5r1NO+PDqPu+R6+fjqegc568YRYg9OERyWIKCAUAAAKAAAACwTBk5/TKcYdhQOfdfz6csSxMsSj0RwyVzM2xcymnRT8+qdEZFuriwy0ogKACoEk1VdTQfmO789Ipz+jlYdCvbD2DakEcDXCNkSRU6jl+n+fvKwui5f5Xb0P1jyX1fyc7HMdPz/AEczNHB9ns6i2j2xOjNCywwbjU9qOzz1Gsiy0OW7iGPIsP3OieH53r/J4vJSyVuMbez+5xPVNS50Hg4/NfC+4eF/T62NTEd6LvxY1rUct95Tt1YMa2pMOxLqFWyOVoLbqkdh6x87rwx9ReQ85b3jSjJPonWas0WXUJJbUcbAiaWOIyvOwPD3AAAAAUABAFQFAQAAAAAAAAAAAAAAAAAAAAAAAAAVAUAAAr2KvPT+r5PsPF07XquZ6X5nYQbzoitBoUjVSyhh9SbnmeF7RX9WPEE9Z5r2Y4tNHP8AXzQVNwAAAUEFAAAAAABUCnQ2w5OHtKxyq7WfUSNbzTkLDaqRz5VJGMq7Pkvt3LPNy10jsK5ZoleanKgKICiA+Wual+TNXvz1HZ9r0c7EzLvTNZ2gyWpv4+147Q4/tOH+V19I9U8q9Q8vPR5bqeb3POyRP0dkfGkt+TOWNJ+VFLuTc9bzdd+DczdSKu7NklgsZrqz0OW4D2HkfFny71Xzb1vk77pOV6vx8vMvnL6e+afo9YFGerb3MWnujDTvYC6nQ0K+nJQffbUdrLn561FyLK3likpw0JdLIWzrNLgbPXPbJzuj1xbbWZ0zbkpSlgcZvngHg9AAAAAAAgAAAAAAAAoigAAAAAAAAAAAAAAAAAAAAqAoAACVbNXnp/Z8b2ni33PQYm18zuNE50rWOY06NaplZSF1PaGoIiAitqLB6E1PKsT23lvocvOiaH6XEAoAAFAAAAAAAAAABUBtDRDnsvtVjjzo87LNc7qczkE9p47E417ou+lRXC2KzF2LXNyHTu524muU7FSCKAAoii26i2blzl16563T4naznW4Dt+G+ffS/TfMvSPJz2sLdx7POIrVX9JpICpvM7YDUuwRwD1qu1LOpiz5unc5p+b1zubXlrol5/Tlv5N+H5byb1Tzb0bhet7Tg+883PmvnT6c8N+s8+i73J9++Rh6HP8/TLddgxYhEqxaz7/NBZqph0mrx1Wzqub7vH5sW1HS6a2LODLtuGbZ0sjXDhoXb+GdM9VNyd7tjoSgdM8oB8/0AAAIAKAAAACAAAAAAAogKIAAKIoAAIoAAAAAAAAAAACiKIKDatmty1P2PI9d49+haubofL7giZp5D674v6M4/T+fL9Dl7N0fzzJ59/Qy+N9N59d8uPrcdOaNQGrqCCGR5j7Jh+zHl45v1/OAUAAqKAAAAAAAAAAAAAAALp5ZHqHQ+HLwxe4DscztrCW7R3XOiUmSNRzHrDZ4kjRuYCHUyczbNxaNupXNcAoIOBJ4Gx0vpPiS8cfUed8/dXwxZpRL9yQRSz9cUXXmVQbphmP04ys6aSKbNAKUllSOevHGrayNj5OvPOv5ra8m+z9D829I8vOt8/wD0J4L9bNIen2ssimQyMrrk5b4OPus7z9ePNqj591IbUHLUUKqaV2vDzlxIJJKzuz5enxy2vZKViXPzdWXElzrXSnaHqqiDgqAZAAAAAoAgAAAAAAAAAAAAAAAqAoigAAAAAAAAAAAAAACiA2tYr8d3eq5jpvJr0y1FJ8rurRIPCPdvAvZjkpYT6/nuzZpnWsuXNi3dLFfm+h9l4W7z69mPOp2fXzB3PF1EVM3heP8AYvJfq8K4Hu5gAACgAAAAoKIKCI5BBUAAAAAAAFQFQClQ3A5OPsqlcybGeQrGpK6N4NldFaaZss97Ghjqp+StnSrkXLLLUWgAV0bgliDX2eQOufQDg9Trjqq+df7YY6xYqlNehiBthSnGsO4kc7LG9HzPUfLvEzlXwdO99L8v9M8uF8P9w8e+jnnWzs+/iJJlIZJGqRpGi1LJWHmdenHfDQdtl+briR6ND5/RvX856nyx6hl9O7xcvjZdDK+13s6mI7boG4dmyVb1haNtlTF2DGM28BAAAAAAAAAAAAAAAAAAAAAAAAACiAogKAAAAAAAAAAAAAyvPBw3p9FgdF5depKh8ruiCB4D714T7ufLM2I/s+fJNCGKqTxysVEysyUZc6udDy93DvfRvOe4+fu8geXqnB93z/fPnAH3PMAAACooAAAFqX0ry7z7O0z5fbzzJ9KZ6M+VJ6VjenHGmzjerABuAAAAAAAAAACoEdHScc/U65xyL9+pLmuVsOVrRsTooJJUJrSZadFPy1qujXHtVeIZaURBRCllhU2dfkF3n0GTzzW657IzN+yozYcuLHrwazi7dG55M83h9LyHg36T6T5p6L5cW/LPU/PfXni324/0KuxW2RQ2K+oxsi3MJOLC5WiRvbZ0PJeiZP5n0efes+V+u83fWc/Q8uPlzkfTvPvs96iuj6V6xyD3xuNbT5l1nVnLhsAnPSggoAAAAAAAAAAAAAAAAAAAAAAAACoCgAAAAAAAAAAAARRSR+fex0fPdL5delNVvy+4IVX8U9o8x9eOXbqU/seeoy43SjFoomRW3IDCNGhmySw6nLXo/T5G983pbQTz7TM08nTzBHs+/wCUAoAAAURRdOh0nDez0NXQ+T2nzrubzrmq3UBpYvm3o/KenPKAfV4gAAAAAAAAAAoDmuHPa6HK10rqthTKzunccNB3OVGDFezDZdlPzJYWuolrC3bVJNNuxzEldS7nb1motWenjQe6N8PfGptbvEJZ6fP5Xp9J3T+Z3OOKnBeheb+J6n3/AJ/3Plxs8R3HD988NVhZ+oxZbDIo11mKcjwdWnpUgw3gAO4Wvo/mu3kfr/knrXHfXbPOdL5seWecesedfo8cvnd43t08/g7PJ8/XAfdg5aY6ElsEYbwhkACgAIoAAAAAAAAAAAAAAAAAAAAAAAAAoigAAAAAAAAAEDVPP02+m5vqPJe/QT5vcRWg1UqjmdA3U4PD9YZ3z4zX9gzPTnzGHucb0Y5al07ekw+w3N/5vZNBrvPRBA5/oOA25pA+75QCgAABRHGp0eZ1Xze2ndrWvn9KdV6ajUcUwhsWRUr6aeUmhQ+1wQDUAAABUBQUQvQYsA43EUBXxuJFjWWRYwkIwcRokkYlZ2b0aHH3Olmwv8x7Ft+Tl80HUcp7ekyRu1UZMsRWY2RqXuaDrX8xeNspT1MjAeMKcNDRqQGZ6N33z3s+XH0ZyHL6/PnwS2oP0uIFa7WbSU3ZslaWvrLUU3GigigdTsc/0P53t5R6r5l6J5d9P1/D9z5scT5d7D4/9/Dnkv0UJaJamX1M3Lfnmd6zW4b8mO7OW+bA5aAAABUBRAUQFEUAAAAAAAAAAAAAAAAAAAAABRAUAAAAAAAIriO8/Te6rl+s8t7VA+b3RBLBGqCBSIIAiUNchTh0CqVpUQRUpBuDTuEs5Huw4Q+lwVBQAAAW9R3uetDs8Pf+R3nis5nGtVpvL2OzZaO9ze/0zKj24vJ8l6X5r9PkgHrwCoAIKCgit8nTr+s5Hs/ndOexuvXpPOqfp+P6scQB7uYAAAo0FEKUEEAAAFQDM1nHNVOwacib9Gyg5CWR0QLFIsV7Csi9dwWHUycxbrcKFmplRRQUFEJrWam87Vjnp/Rz25sa135X6wzthWObqAKiChs9Rx/Y/C7ee9Lj2fD17fv/ADv0Hzc8zxL3rw37GWWY2fWWSJ8ty1n2Od0n1r3LcRfMa8VA83QAAAAAAAFEFQVAFAAAAAAAAAAAAAAAAAAAABaRQAAAIAARUiu5r/N06HruT6/y3rBE+f2EEMbZ5nzPs9yPLuixetSvc5WFs7bIkkj1GgmoNVKpVb2DVflsTF+ly2bdG97uTgAAFABUCfo8zpPF16K5FY+Z1bm2a9g9r7Dgez8h3e56Dhes689wDz7b5x6PyvpxyKov1eQgABSqi4rQPH06rtOJ7fw7pPRUWSKxL5vm99wP1uIiHoyogKI4AIAKQUEHOGuUgQQAbSq0H07KGTQ6Z5yB01GzIdPVJJq0mRFJFipYewtW4sw6Kflrmm6mfNVkY6nCKIKg+zSXedabDf6OW0uda9HKYDvibv8Azr0b4/Tks3f5P5vb0rv/AD7uvLzs+Ke1eQfSzlqxfuyaSvPmyLNJjRpss8tvHHLXi4Hn6AAAAAAAAAAAAKigICiKAAAAAAAAAAAFAAACiAKigAAEAAIqS1pI5PLvpex5Ds/M6JBPn9xArk/HvW/EPo89Vc2X1Yv62BLi970fkS+ff0Db+dOg8+vaouI7Tz7jZo5rIDekwPL/AG+n6c+OWr9H6vBQNQABUUHN0M3V6/mu2+V3fIkHl1UQOmVex8cp5l0HN+ybPf8AlPqFx0slG75Npn3mnliaOd9riAagAKqLitA8nTp+64Xu/FuiiEg9iEnnff4vpzxQJ9Tkoig5DFXpuY6X5/XpOY9OzPNrzOr63X7zy0c36XEVQGjKRkhZGPKYrlGjgYOQRjwzqu2+OSq9tn5YNbYyIv7HMT5klZC2SWqluhbzXam9Y5aU6ZMW7V0jkpABRCyS1RXU1/QfJ34x6X55epeS+pdnwvZeHns+Wep+cezHHykv6GLKGdXpIug4bpWnQc93CuYviwHHYAAAAAAAAAAAAAACiKAIKIoAAAAFAAAAAAAAAAKAAEAANcyIJI5/J16XtuI7rzNkRPD2AacT4x695R9bjCPT28mikrpqxi35Mx2Loy0Jc30rS8l1uF9C6fzPuOTTEPL0p+aerYHqz58B9bgAAoBv5O9599FvRT/I7SZ1ugCo7UXL1OIrhIZovp8zteQ2eV9C1MXa8dI5GYvK8p6T5t9PmAevAAKBitUPH06PvfPvQfFukCI1ituRBK4Gn1/IfV5jmu6RQThpei53e8Pb1bH18TxW5LRsL5PFYrff8yqhCamX7v4uvhR6vzG5xxqZvr5sRE3HIhQggqACo4HKQgiVWzdpscrB2TIs0e76nyc/nxO78+9erDIzdc10krLddkbFnnFOnXAvVokE1KqCKAO6Pmly9aZ5SucddPy+p9Dn09vF6PNmvV5OHVWF7Npl8l+fAMAAAAAAAAAAAAAAABUUEVAApRFAAAAAAAAAAAAAAUAAACBj2RBZr2/H13+/4D0LzNBqp4uwgleecB33F/X4UY9Bvs55keqwymakRnpbhiF8aYtx9WXnrtOk4XsuM7ZBPndxAPNcvtuJ+vwAPRlQeanTYnbfM73po3eHdSBDphytcJ5N33nPqkNPTo+/kste15evpWny/Q+aXx68dR+c+j8p6c8kgfV5KAKoYrQPJvd9C879B8W6bERkrWqGl9EliPgPQ8LvOOVF+lzATjpdjH0/D19fwN3G8enyrMeV09TK+1wUROO3ez+LeveDpZzr+dyi4HQY/acAit+3wVAFEAVz4aqsHIxBzUSlQAAsFQCldDFodSpyR0lGzMe+sWEhVZGST81OwRy6NzBnrediS1rlOxUoOFVXC6easdf0fly2ezXvH+nze/MYa8LAZAAAAAAAAAAAAAACgAAAAAFEFAAAAAAAAAAAAFEUAAACOSLNju0r/j6bXo/m3p3lSiJ5OwitPOuU6XnvscImzp6ucCToV22UKcOhHWVS3acuXPHY53X9A47vvHrceh4ugioZ/mfqfmXuxAB9Dkuhn7vLWl2+Hu/J7vr2c3nGAbiqkJxPOzt+pzKd+t1zm3aljz76TsvNfSfLdpGzebdfO0It58sNDO+1yVUXUAMVoHk3s+hed+i+PeeKMrVt84aepi7OpLGrOevOqvXcj9bkqKkrr9C54evtmdsZnzujX1oNTgMTXxvt+dUDGj1byn1Dw9NTN08XnJsy1S654NA+zyBXCPQhSfpfNvPzvoTiPFvyNO7yvbjmU1M/vmMDpAAAEAAAAAWN4Z1LeU5O30FbLDi1cnnbtaOsdLUz9/MwbLKert2+ak062fkbldGZ19ZpGPgRgTDQxwLAAAAAAAAAAACgAAAAAAAAABUBRFAAAAAAAAAAAAUAABI5Yc1mjn6Xj3q+oeY+n+XQgnk6oIWc9kdunR5nS9Wq98+TN9Pye+eGOjo985LbsHbFSveirIu3ev8AJ0OovN+ftqBCIqFfzT0Xzj2ZgVF+lxs7VHpvF16aeOb5nSKjNBvKgUuZpB53W9Lr+meaxeiZXXPAL0OTazvuA6jje2t5Oh5jWOZXMcn6R5x9HAoevCAYrVRfJvV9I829L8e85zkkOI7ji9puh819A652CObzai869K530548D25dNC7w9fdsHUyfFquip1xxOLvYP1OYBiu9I829C8PXosTeyeUrxaMW55aov2+IqyQlo1fF1m9iqQfJ7Z/MSJ6eUbZjWYse1yHY2MX6XNo4poqUAIAAAAAAAAK5oVc3dI5SLsYc3kF3s/KinpV/jnz512t23Ti1H1U06FY6WfjbR1ZiBKBYAAAAAAABQAAAAAAAAAAAAAAAACooAAAAAAAAAAKigAJDPBipqZmr497HpPmXR8XUtyNHydZkCVBAGqlCCIVrKGdS3S3j6vcp0zy/QTnLSsDWUBARSsPgeh5z34WSO97Od7uOV7P5Xew9YPNaiB0yoNFRCwEcOkjbEleeSXMi6NcawJ7bOmGtelHnvpHLd5xwH1eSCpitUPLvT9O8v9O8W6Th2Y3jO15Dbz70Tz7b9E9I0Kd/x0R8Ob5hV7Hjvq8nCt8vX3bMt5/h1XjG9scjz3Tcx9PmoEru94Lt/D17bK2cry1GyrqeRJYj+7wSymj5tu9Tze2+P3pcDardecbXJ1yyjP571jzC2fp85UaaKiFiiACgAAAAoIoAKAACigqEsj4nRodNxTsTS43onLza7dO2gLFVqJpERIVoiCKIoAUAAAAAAAAAAAAAAAAAAAAACiAACiKAAAAAAKIoAIBBPVxZbeOvl6dFPypcdc3mLVnU6PHWMu71eB6Xy9OjSSz4+1EsxWRI5moAlggUgICKlCAGPe4S2nUa/wCzwXWoanO9Nu0tP5HabOu0URHN1EaubW3LxHRcul+LTkxMVdWHcoWJE1JIWR2SErBjJG0+rdYeSGnl/b4gJCK13l3e9S8r9T8e4B8vNDyPa8jp5vLWueyek7fnPo/kthXN4m+Veo8n6s8ogutexwB47WEfvPK8p2fGfSwKhTu14rrfD19OxtbnvHq0tFemfOorqfU5v7PO9e+V3d5/Hk3F+Gm3vizWZxfTMXLlv6fN+jBY2eKSoKCCqIKCCggoAJSiCCooAAACooKOlHjocDpWuGj4nIUqG5KnInZi4YCChQAAAAAAAAAAAAAAAAAAAAACooIoIKCKgKAAAAAAKICoAUrlWMEe0llqmLfmyTN2VyJsXS0+fmxru9/ypeGvcNP58n4a98Z5Bt8tegx85t87JHoEmYmjFqUyevomXJxvXM3LULf0uduRk3o53d/D63wdtHazb/g3XgDWUaqaicb13knSwmTL7caW1zM2L3u95S7hr3O34BpcNe1Q+cb3PXUNg0ubNWCXtzBG1y/HelebfS5Iip6YjkXy7t+teSew+HdUlXjWcp1/M7eQ3ay/S53/AEbzfd82u+npXuAhmI8vZ1PM9r6lNXv+W0Z0SznOH7zg/p8xUXZej5zd8XX1jneg5vyHwoztjmbz/WcdbHH6PH4yxJD084ifmaocTM76fMvLY6myOdDUeggoIKCAgogAAgoIKgoi2AKqCoChDnseK9rsng6WMkeQve4V0RLYIAxFQ1lQSlEUAAAAAAAAAAAAAAAAAAAFEFQAAAAAURQAAAAAAAVRlW7CYcOtBWeXI7K5K2GI5FQUySRhLZlopi6kmOuLsGVLGvrcs7Gu7tedN530XL4mLrnUy0k9nOxo1rpNbq3+Vv8ARY+98vvvx2KHE1UN5QUOe8q7Dj/oYrpM32YjJEybKxM21LnnO6rsabnrUu5Ji+u6vO7HllyFWYqee+h836Jxwp9HDXI7y7m9r8U9t+f1rscziTm+jwOs8qz9jL+xws2s+55uno2twXa+Zfcj+Vq+eem4zWxfa/jqoMOmMnzv0Pzz6PMEO0frZGh4uvsnP7fO+U+F7+mepu52P5umc67P2zmvuuzavk3s/Ld55VdWf7PBXjoUEARBUChABAAABQQABAUQFEBRFAFFex5I+GTJ745JWOHjXPSVrVBRQxCnJrNghfUgigAIACooAAAAAAAAAAAAACoCiAACiKAqAigAAAAAAoKKDHIV4rCFZttCk240pR6DazmaTDOTQYUS2yyuStIxySoKAqLYA+ktluV9mObKe3BN5t7vVeUZ/i6e/p4zueffokPO7mKtDosBPKKsr/v+asy4m5Rj0GmczSZWel5iUSePjq26C1w313U+feg8JpK+bzbhg0H5vjjdnH+xxa5F47l9t8Q9r+f1ijdFyi4exj9J5rS0K/2eOReqycdaHo3m/T+TfdXYrHj2VZ4UlmV2bnEMHbEHnHf+ffQ5qIvY+1Wm8PX2/F6XA8Oqzlk3lyi42r1rYrrGPrSubKteQUvTPNvueZBT04QUGjkERUERyUgoIKCAgAAioAFgKSgKCoormqOkjXKyNmzWSI5Y2vQYPUaSBxS4cvTOyuVKab82Y0XZzjSfmLGmue8ulZ5MMcKAAAAAAAACggoIKAAIKCAACgoAiggrhrgBrmggCI4GD0GJIhGkqESTIQJOhXbZSqrLiFJl5DPboIUHXVKs0zxsxIErFiTC2crNpTVTK/Nkpi7SZU0uze5i/uWJWydstSRCNJQhScK7bCFWG/Fi5tyKXhqb1DzHuPLrq7dK/wCTSyNdz1yPA+veRfS5oIvWL7Z4l7P4ejYnM5RuXsUNPMIp2/a45tTVzeduWaFvy9PWdLzzuvDu3AQMpYpyblRZLdmZ5v6/5D64jkT05kEb4uvvWRo0fBqKQsy1pnw51V8rm571Tq/UvA/bpNpsEni2nlPq3PezHmoh9zyqiAAlAIKiFKggAgAWIAAAAAACgOfEsso2WHPYubKsLh6tcPGulcosIKHlQ9uogAAD5qxV6XMLNeXDWtx2NKar8yVNKTOeui/NI1VypY0CnJVghkHCKAAAAAAAAormPAGjhoOVjoVFQGuKaqqApDWyIMSRKYiggoNHAwegxJAiJCoklCJZAY5yiOFAAShfrmKmhFZUJ2kSuKn0K17NkeiigABAAIjimslTKjBdpctXN3An8nT1zRpaXzukTZWQzzD1DkPVjhlR3uwnsvjfs3g6NJzhWUdOjL5KB+h8sNLRq41m3qM3DWh6d5Z0fm13i09DghksOxYrDEzTx713yT384wPZiRFPD29sfV0fmdalyrJmnlXe+F+rLbVaT6XGftOQn4a9ulzrnzOsrWi+YY/pXmv3PKIqerCIqCCpQACACKlgAAACAogKsljNpvtEtedZYYTJLAStshRCxXMCZ9aSWy6q+JyEXimbsXv82GzZi5bx2a0XLeSmszNyzQjlplhkRDkEAB7Asy0TU035M0aTqMuLdWqWXpM59abs522k/LdGmUJC2QPJRrgHAgKIKoiqsIKCKAACADlaqiKJGjymI9Bo5BBUAAAARSkUAVFAAAAjkQrNsIVm2kKhaBllso4QFQABQBRFCAUIKGlU51kmUvHenr81Ji93t+XScNe1TeNXOOqzlPdyT2fxn13wddBrU8m3VLFfU8iEP0fkIZmGbV08zlq9aoW/N09R1+C7rw6sDjlY2uZqN8n9X8s9/OoB7MSKjvD29f08nb+Z1pyjc3I8P978S+rxgh0K/r5rNQu+ffbdv456v4t6REnn3L5h6Pj+rn5ugfb86CpQCAICiFgIAAA9ZYx7hjlUsLDJivdE+WSRkkMVzBrZI6a2RbI2zMGuEHuikhw4WFchvbnpU3W+uKbby9MZcWy7Tn4Oghs5+PpGHOR9FDz3gRb0PLeGzYj5ayU1Is2hO92NLIlrMts3YNccOp0eO1jTVjfS9Nlmpsy4Km8uLMasmZKmlLnPNB+aS6rsqQ0lovLaQOJUaDhoORAcrVHrGo5EQVFQFQBFBoKIKCClIKCKigACoCooNHAweEZIgj0cALDRwIooigAgCoBBMysqto04hSYiGRymy+vZlbHJh8taceZLzvQ7XEycr6hteQWcamYjvpcEFKgpadTnrOvULPDV71byXqfJv0FaNnzV0aJYvmXpvm/sxlCr7cvcO8PX1fo+Z6v5XejJDBE3hHtvi31fPGyxH9Dnl2Ww8NaHb8Ld8u/XbFCz4OkwyM86w/TvMftedEU9WGipSI5wxZJYgWwktZZSxsiy5rXqssEViCxHMmpJkXNldGQrHNp7CAe2M1HI0sABbFZ0WyuS5oGoAAACKE09ILpSKurRN4tpCvXMsanTEEN9dTHodNmeXpmbtPq/B27DN6ml83tynD+t+e+znwDNhPo4x01I8s8tslrkjBBUB7AtTZ5qa8uGV0Zzs5tmZZLr6M1l11EjRdmOl0ijIWiB5IIoAUAAqEKIoAABQAAAAACgACoCiAoigoCiLAqAogAIKIUACtcFavdjKbLqFFl9o+9UswuVq0jLSZpG5yl6/TujgIBEHV5my51bQzOd0bOfP5t+ra/kW/5N96nObvDVvzn0vz30Z5pUT6fKYY/x9PSOu4jtfm9c8bGzN47615T9HlXie36XKDO1KPOy2M695encdN5f6X5bcRHcanAeg53aeaviX7PFzo1Hqx8oqkSo0lUQHOjcPWNCRsaWSkKkhG4kfEsskStEYJYo0sUag4atPWN8OAlzhDUUQFAAAAAAAAAAAAAVzAlt0COou8Ucdegc3iO1LcDXfT80MGg+zFr9K+uRZ19fN5OPqYOW+YZ0VblvCbtxY1kGlFm0iwyIhyCAD7FQrRnxzU3ZedVOhMSetSTOlNCSk4vPzWy6xlzReWrJUwxwoAAAAAAAAqAogKICiKKrVFVoOGgogKIoAAAAANcEZIEaSENkRwRTNKTbbSoy4gluCYcCCiAqCkFDWhzcKWeHnZJqRi6cmTcNuSjJ0jAQkcxPH07vt/G+n8e+tbm6nHUfmPqPm3u5Y44+rxigtR87k3Y28d3e74PT8uvTZm2PDuFJ0POcL1Py/wCxxYPPVhquWGK5oIiU4ao98ZEjWA5EUHNQlSMJCNSUY6UY9BiPSxoFAKI5FgFDNdVKtlYLJA4mI3DhFAAAAAAAAAAAAFQFEUAAAFcwJZKxqXX551xqOy3dMXoI5OmYK+nLZz1XrnVxcXaQY1xsPYVuW+UZ0lXlvDTZhxrLL8ObWJmQwcgj2BcnzDU2mZFyLM1O1zTSZ8emzJiS1tPpt6TQdmOl0SlIWSF48QFAAAABRAUAAABQFAAAAFQFAAAURYFQFEUajgjHg16KAKAoCog5ohTo6laqKW22VrUcpoyQySoj1xc6po5PO2pc9cXQt5N2OnqUn7iCnbJFK2WrQ1KPPU8tO15N+ldF5b6d4OlgavHTvO/Qc7048sBPu+ZzoyHtQoQAAoAAABSEUAVFBzpsonzNmo2vUiLCpWSdlRNnKgSeGwEDlZcla2pufE6M5+atoypTSKUxZWFSd9UltrUWLRWcTkTh4igAAAAAAAAogKICgAAAAKgOdGFiWkbzpS5C9cbbsR3XOlDXn1mCDWuHH0/SJs68rg9QzsXzmL0Gnz3w6dNV56wtKROVSzDa5yhX2JjBLtTdr2KZtqz4ZqdDJzS10rcOwakmfNV6Sm9Lj85JdMzpZbhXeTDHCiFigSqIDhAUQFEBRAUAFAFCBUBREHIgKAKNKciAKgKANjmQgbYSKzpwJR41VIjy9amUidpFZgmNB8Txw0HDSo4LEXO512pFw3qdz5tLw17Hd8Qteffsy+ZbvHVPnO04z63nQU9WAAAAAAAEUEFBBQWSILklKXNtFVhairNsnSumlgrCTMYUqtLJSIl4tu22XGTWjyzFvQy11ewFRB81Yq9NllmxNhLZ0S85IbyZMppPoyc9W3QKTvrFltai6Wis4nIXEg1wAABQqAogKICgAAAAAAACoD3wqX7eKanS7HBrrPolfhZNTofNuwyedxdCW35deh9IdT4ePD8j7DzOnzdH2tH7W+UToYOe8RNaHFzy1HLCOIa9gXLOUbm3PzpZ1BzE9byZdovS0ZrLj6jYvrmul0SlLFgifTgAUJRQAEFEBRAVAAABQAAUAFWEUUQUEFQBAcNBw1B0T0IWzJUCyiPe1VUAAARQrZe3RyzCwkRSi5trTxNqnCG4o0HDSnDQcjQcNBwwsejAeMB6NcAiCoLSCiIKCKACSDC7NjWYagZ0dg+z86lFpmdY8W8Y3zjeli5b5yLo4+euci6KLlvnW70XPeGbUWbkLpRZtJZ2xZnhm5atyP1WMZNiNMmGXA63oZeZXrOlMCY2FzJavrWmJXRJFh1RZbRWWLBCtSjVFAAAUQFEUAAAAAAAAFVqiiA65RI6i5xZmb0vOO9vLpmc9L0xoU5Zt5yaPVzWcJD6JXl89g9Aq8t8Izs6HDpy6dBBz3imnXxahOxYxyD7VEs17PPmp0r+YK6duHbjQlyW4u9Jgym47FkNczpNLpXdZKNcKAApKCqIoQKgKNSno0FEEUQpRAUQFAAAQcSsHggoAAAABYQTtKEd5hRbeZZT1adlbIhCiKAIAhQAAACKgAAAqAAAACiAqKCAoujDa5alGuzpBQzBT9B8sFBFABQBSgFEa9StFeMazIdlcawK/TwcOnMvtz/H9U23P03nvFxdfX1nzfne1xvYwk2otXKNCKWqTMhoiE89Es05sc1N+bmlrpzmp63TJmTRWnPU6sIldWJbRVWWyQOJiNw4QFAAAAAAFEUAAAoAQVAVzFHzVizRs4p1x0VnlXdcdVX56x0zfpz2bMGh29hPNq/qNbOvLq/ptLlvzxO0zuPTmk3avPWYWoManlSbEbKkklRCPVl1sSvudWvJWek6BMy8tmWF6TSVoy+uYubpJSlLCRvpRQRQAFEFQAURVWVBSAUAQBAoBQEAESxyICiOI0lfELbEctdzzckcyTJqTMljSQ1IxzaEVEAAAAAUQFQAFfEa2JJaklqXNz1vVhj3WJUlHQ5ac5IVwrCr9/5iCggoIqlIKogqjVUEUURQCvZqcN5d6lo/C9nabdPR+X6akN2E4ulpVf1nzKUOmenGLD0JjXLRdeznrj4uvh5b5GLrYOe+Uj6ivy3zib8eNYZrRYueW2LXVzIdNXKvz5JrO5NzpqdQ7lZTo0xZzTWjPVl0LyV1dsXCk7OrZXcTET7HKigAAAAAqAoigAKirDSZ8tZZGWI9hUtmgamza5xeuOsn4x3Xn1tTBtbzYpX7+p5zHuZHyfVFPHscmsetXPLz8C5P6d8O9WuOToKno6ZRcjlrkiQtyglm3Y5w3Orm48s7GLnbsunJBZHSOkhjq8C3zPmLawSQ9UUEUGjgaKCAUgqWAKNHoNJZZar5iESRkRI+PUEcUkjSWeWq/FnZE2licm8sFLAUESWSWsWiKzrkstCS4RDNI3Nakca2KTjUa5UQaiaSLEAKqNJSWUVfufNaOBBSkUUQVUaqgg4pBVGqoJSv0PH1oaedsfE9nf24Zfl+lsE0FcbXmj/Z/IQU9GEVRAUAUsRVBBwQw3TNy4Nxca5uv1a898XH28HLfEw9tBy3xkPZV+fTkWdPBy3zqbsOLkGjDm1SVio5iFyfMWzakztrlIJZNHnMouR6QPZH1th0M3fLnIyWZayZtorKWCFxIIo50YTvrGbaiYgIGoACgCKACgCA50ZT5a7su63fKF459pw/M16Z9BzeYt+7FjJ29bU4Cv65oebr4TR9+oct+DM9lxZfMW9tRjlDeoy55ZYRSEZp6HNlnZWeEU75vB3pdaXEWTopecmOhfz0tbyZc1XkrS1IhIRpKpCthxXfKma1HIMa81IiQGiggoIrQVoWArhriWWN865sUqwxaWu9ZSNRyMeRMlgRiKmoqKgKIKLLK1XyRG6R0sRMFZVP0Hy0FERRVRVKQUQFUaqggq0gqjc7TzPB2q7uL0HxfX3ThPm+lla1R1ORa4/b/GQVdxqqCDikVREVQRQBRRFARVLEUURRRFFEZIpTg01xrErdIY1yVPujlvz6H0KDl088i9Ar8t8npXKnzeq6FK/wVToopOcyOs5rrcIkZ6OkliklmvPgrqdLNyhqdg3k7J0CZNmy6sMw56gqwtlslVc2ysDyQQFEBQUQVwiqZqAtNFQRQsAWBRVcrCNHR55Ts9Xzcs9Ym8jWvTKXJa4mL2Ovi+P0ffHL845/0fmnz032vnjzQ7HMTOkdJzkU8diKLJYrZN/mqu3aW+BNPSYOM1sXTclgSVpUpShNBmfIXCCUejlGDgbHLHYxJF0iWd8QLZXNhklWWuThUbYWys6wpG9WShEI9GlK5qkqxz5sbZUqJzXD3xrEyNAFIYKv6D5TVVaaqggoApQKCKKIKUCgZOtk/M7x9JzvU/I9fYxyxfO9Dc+/l9cc0Kv7b46ClAoIqgiqtjRwIKqNHKIjlGK5RiuKQVRBwIOBFFRBVEFWkFUQcVgYe3ifm/oTdHz3deHfdG+vm5cr537VwXuz5RW9GZ9/Hm0HpUXHp5nD6TU5dPPI++zeW+STpYMawDWgxaK2GEU8LTSsYhqdJY5Q1Oxfxcp1bMG3WkQ2oV1mXGqj3V4mSk4tld1TJG6nCAoior2ulHNXNURQVFAFEVEHDAkfAWbepyAeh6Pla6nrNPzKXecXO6Otw1hW7c/OdB01/tPHy8g8s+qPNfVrxxno2N7dcg3pKmNYxehzqB4ho3+cLOts8Stnfy+d6Gb19SlpZsNuWcruuZMXXYNmtZKUstggSyytV5O2NyuexYmGFj4lZLGilAoIoDkR0IKBLE4kWJYmSMJSEJQX9B8pFFpBVEFBFFsQUUFBFUpBVIsvTy/keleu5XsvlenoopYvB3bjbOH6ueKKv7L5LVcCDgQVUQcCDimqqiCiIPUaPFYOEaqrSCqNVVRqqCDgQcU1VUQUMTnep5v8z9Cz6LwnovhvpQ48+I/PvROB+jjnbb4f0nGRkcgSPlxpKlyqZ1fUOuMKr07sa4uj6EnPXmVb1KDnvyuv6jV578xi9Jp8d+ft7Spy6cqdFXxrFNCDNge1C9cxA33QaHLFeSW7lmLbg0bLBa6VJLU+tUXXq8RvhYW1pzSzKxRyK4gJIrAQsBClVEFEBUQpRpY50YSXM8jp3cs9nsbPDno5+gs4LSl6GnPtcOnB5Hr2nnXgVD6cXGvlFn1Bzh4Cz1jDrz86nHszlkYS3sqQuOGYlmarIWpsZtdNJS3rakk8y1VSuWSjIWyKSHKACgigKrAesQTEIsrY0JEYI8YF1VP0HykUURRRFFpBVEFERVBFVaaOCrl6mb8T1z9xxndfL9OjG5vk7Mwd7nvdwzlU/WfLRVKRVFRVBBwiKKIOBBwI4UABBSxFVRqqCDlGqpYgoIOBquUYrwy+b6fmfy/0db0PhO/8b0EVOGE879D8z+pzpRRn6XzySQLZbmoLjdiFrNZlGFj0YoCvSNZUVigkk9d2d30qTcOkNXWn49Obzu7dw6+Y5nsC414fT90q4149Ns43iM0cvUyhi6yfE4rnvR+M6659bkXfbL9Bh0Wrwwelz+WrL6tT820DsYcfUEXRmMlugzWaQsGpKVVqwQuslGKKAKIqqqGa58a5PGOVysWHqxYVzQk08cOx1PO1X1K35I+PXaPmmtHRZF/bl86wveQ+Y1WVzimZcky2erb3KeBw+n+f990ZJY93S1uUZHfWfOFX0xvmtw7OtkaJPLXEtkMdWigkaJVeTkblcIoqtBwwNUcff+UgqiCqIOBByjVVRqqWIqgg4KGffpfB9l3u+J7r5vpma5vm6x870XOfT81Ucfp/nIKAKCDlGqogooiiiCuGK5RqvWIyUWNZAjJFsjJXSwLdfm5624NRiiWKItgAZvMdPzP5f6HSd5xHd+Od0ipyy3zD07y/6/LPBf0nmQUAFEUBz4li1bzDn003Z8/HpctY2jx62rLbPi708bsoOmeKnlqfV8NwhdjUpWZZoS5Lpdx2Pa8/Xz7A6XnPjeiPXyen5PS9KbT8fLnsLuqHo6cRzvsLvb38Fo/Q2fqfPtL3ulvPgkPuGUeQRem5ccIna58vNmtVWnYSM0bmAy56+Xi107d3ESWdbFg2k0XUn8rcdSmWy6kul0quqwtd1TEbxzo1lkWN2a9Y3RI6NYmWBVkGrCiIOViDoZAqTSknoHXeInDHtWB57o73pYO3pdb5xQ9jceD0foTMPDE9bxK87b2uenNLeq029noblTPvSWJqiZaU2ZFW/Ny+5boSTWJaZIGqqn3/AJSDgRVBFFEVQQcUgqiCqNHImXVsQfnvdq9vx3Z/P9DmqnDcXNdJzf2PLGOX9D4GjyGjwarlGjlGLI5Y1kWI3SLLGrwaKCClIKlioJYs9ZYtlRJbkEZYAbyAAoGZzXR83+V+j1nd8N3vkz2SKnPLfLPUvK/scaop+i84KAOWVqqCKAOYtX7VPT8Hqilng4dXxZ9T08d/S5Cxm6+Oq9MJDNB35Pv5jjXdnXPL3WK0kvE8p3HI/F7UOw5PtuN9V0c/R8nNmTsZPo3GjWfS7I6B28xyuWGttJLWsEcsOZtOOXodxGeY4ns8Gp4ZT98rJ8/0/fqMeDM9nyjyw7mhLibkVrzyrqZOviR071eKcjsjtd2xwh6HfQ8bfl6COnbhXpLqEjo5XlZmbbWq/NskDyVYCpSIJEYD0aoogKNBRAc+JYv6XPKvb7PmK5vrzfJHHpORzepZRw+60LPIMj6A8QSmyxHiPr6O1mcZH7nyWXmb7UXo3cM8PV1VfufLQUEFWkFBHCiCgigAqjVUjFjkT857tzsOW6vwehiObz1X5zocD7fjaPPueNquBBwIriEVyytcrhHIiva1EUDUUaDkQsVBLFQKAUAUQcDRwjRxSDljG5zoef8Ayv0eu9A4D0Py56prk55j8r9U8s+zxgHn3+KDkEAQFKQcDVcDZGqWruQvHppZou8oKbwiqqoKqNVyjZEdLYvZUvDtk8p13MfnfVldryHY8Xpujm6XmwUbuP326nZPo96yyV6mIHDyWbNgTUMWm27XM+jtx7mDH0LN5wJNoM+9IuNOVk2ayvqOjzLzj2PxvHKrq5OrmTdXmetcMeWcz7vibnz/AF/aqn1N+Nx+s5nPfm6dvRl5ddqpFG5DGa93mUs7GXiFrvU4K0dbDkXYsPSUa6tBi6S50xbIFtnGOFUWFc0VyNEcMKcNBw0HCBIRgkFlYrdZzi4z7QvjEvHPf4uZqenphnZEvMCu+58tiuUYr1I1kUiJQjJCo1coxXAkc0PO46jvz3t6XpcHf8PojRUxaWJr5P3/AAijvr+Vo4BVFRQAUAQRRClAACgFRo4pquBo8po4EFEQcCDgQUEHJlg4O7ifl/odZ6P5x6X5sdCipzkflnqPl32uLRx93i0cliKKIKo0ctNHg1XKjFcDVcCCqIOBFUlFahIRrDxCaz8DdxfzPsyew5DsOGvS9LM0/NhOb6TnvRqhIh9LuoxtORFSWxTkzrTt5M3PW4/Gr5vQUaL1njARRUBG0rCtvKsjO3PI8o9h818meV2aGzydH615j6n5ecedsUKxFI/ubWMNZgqak9czU7Z/PXnGb687nvwyh9Bsxr5yofStTN+aoPovJXwc9exDz1OuzUpbdLS5YqX6WlmVodGsVNzJw+mu1rclo9N6jS6VXXrEZi6NYgGxFhYZByooCqNHAiyTRVSwwjV6CAG2qr9v5iOUlQURAKQU0QVRiyOIlkWI616nw3jTMs/B9nV69G/4e8bZEyyc7Ro/pPA0VPpcEAuQHCOe6aiHojQLEUdSDgaKCCuGjwRVkliWVsRkjrIlmarEUsaOWxo5YakrMXm8XaxfzXv6307zH1Hzc9pFTEr+Zelebfb4ojj7fFo4sarlGOcDVUsRVVWjiGq4pAIBQRHrKxXOliWRYiWQljHBl421i/nPXldhxvZcNekamVq+bCc90GB31SJD6XoaqoIx5THyPyY8JXOiQmGPhyj5SRpLIQyEkT1iInisp+ZeqeacOXIa1O/MdV6Z5r6R5cT07kEY8lhv1PUiiyq5HQohKqIoqtQkRgPaiCoJZUpara874D1jyfnyrXq02ZY0IPVeefK+b+gMy356i93y/V28Yb6nmnn51uZWdqUI7Omv8PCvotny+SPUqvnunl0kFWZZ5sWRncdgymuzOmauOrPLI0N1ZF+x86Jz3ESWArrOpXLQVnzKsRIDFkIbnauX5OuXbq3fj+nr7UU/h7Na5hkU7Lf0/wA6FbDPZzrpIm8NmdPjccc7JYEnbvEKSmpG575YnSMiMcay1znqxZ3Y1C6UzYiVxE57BschvMLpiyIlCMkBkFqvzvM42xj/AJ/2db6p5b6p5uemCYlLzz0DhPucYnyr9XEJI3UYOLGjlGLI+WJZEzY0cmo0lkzqF9o5dImqyxzQuVBFEaayJLLm1ZLCZ1h4e7h/C75HYch1/G+j6uRr+bCYm3h99VljPo+hWhqPcxc2cidmiK6xHhK9I0p5G2yRjW2PWGUe9Vxpz0dnTPOfSPOeHHm5wxjrPRfOvQfPi5DNFlRVifT9k6RESJG2yZrHAqoDXINSQqNswQpYkimt58vOeO+/+OcuXJTzlx0PrHnXpPl52iw3GpRh6PoPiUKdHZK5HF9HLPHMb3xup834/wBP1dZ+W4Pp7K1PnOX2vC1nmJGnLg21Q0FgpamfWlqcVhdOvrZ5MW+2K0+t896xqTEL5XvjdLIgua1Hs1EGm8udG+V2Ps4vg7UdKlq/J9PVvF8XVjJYdTIBP1Hzxis9PNAN5mmrP57makmK0kYMRxvLByajRUsRznDHiyukZLy20mTOoWyrvMSStsjHrrLFkfLGTMzYVnXUip3s3leZyNbM+N6Ot9V8s9V83O8gYmdxfZcf9jEbXJ9bmxJDWY3SOzpHqzntWKajRzxiyLjTXDM6IZTeIZJJFiJUxYW2HalWSZ2bGrkzpGvSzCw97C+RvH7Dj+x430TXx9jzYTE28Pvqo6OT6XcFQYipqEjZYa5zc6ERmo9rXWIkjiJ0y4scrnY016rnSJIssXnvo/nfHjhVrlLPPr+/4Du/PjTilZiZyzr9D3wLMpC6UljJHESyEIqrKKiD1jJZSAJ1gdDvJfWvM8+fkKW7ib49x3XF9f5sbbJI8VQPT9FBwqI5Rg8GEhEZIDB6jFcHzTHv8/28NXTzNitDqT0Hzc/JcH3LS36fmY+jzr18xWVPtfNiSUsie9RJEdnTlR2NNbItV0sN1mBZU1Fwt3n/AJvoNrF3/k+npGuZ5dtY+DcyUG/rPmAr+uY0sPlqutxwyRpKo50qNlXNqrYN5gLCkBIEZK+mSufx6NRzIY5X6iCma1HLqNV5K0c0SOROmI83Vy+c5ahdqfJ79Z6t5X6r5udoDEyeS6zmPro22V9trLMEJMRAthxXWyuN13SksSykRkiERItRvcZqDkGte3WWOkcRJMssJOhzWD0PPfOzk9dx/Yc3oezi7XmwmLtZPbVBVT6PpRXrEblUByysHkREpZE9yyookqq1B6xNLCwPllIyV/B91xHLjhZmtkZ5dl3HD9n58bjXNxKBXPf77S0y202upMsDyV0DomRgrgWBHrEUoqqrVzX8B3nE58/O8t2PG64eidNzW/58dTFLFg5Ij0fTmIVqVYSJyBSYidDxjlVWrCiKea8D6xw2/BwfYcv3W89D3/C935ecFmIvqlITp6/MEVfufMaPBhKETnADllY8Qcg4YPSyHn97C+b2Touf6b53faRzfL0bXtVd5zElP1fzopFWlejuexqpK0eWJIi509WvzoFaK1xY0kcV1mLGqqStUWwUWVQM1BVpBCxQIFUVMXbwuU5OCVnknWeqeXepeXnOipiZHOdDz/0+jlRfR0UFlFVZWikIqgiuWVrkBUUGjihWKORSEVQHNUAbT1iDneb6LnfJwx+w4/sMT0Hbw9zzYbka+L11WIXfQ9MioK4Y+ERYKnSsllkrLVgrrE5G+VVdNlXfPJNVpJ482N0aVY4fr+R58sTB6HnMce47Hj+r4Y6RFTnMlZ6/v90sdWr0arsUs3VxGS9BJy8ydQzCfnWqyndxpqTVZXlU1LRVIt8n0XP444fDd3wrz+j7OLqefPaxvZiVlgPT9Kche1I6N0OVFgVRUUABRCzKclxvoHEvB572GBubx03ccP2nnw+ncra7wkp39fnStd9Twq5qyuEUEVaaOUaPCNzlsaqktHE2sb5nZ/Vcz1vg7Xkc3z7Kdyj1zWc0/S+JRAcNB4wJSIJViCciXNkAlQe2wUWUVFUVjocNaPIk1mYgWp3VAtLVdLabAubKsIWOf2cDlOYEl8uOs9R8x9P82JEVMTGwtjn/AKXawQWu/RkjVzXOZNmujkhiR1cqZajNS6yqllparqtFdJbJXEspWSrRUWyykKyyFdbJmopz/P8AQ894uWP2HGdnid/uYW75sJh7mJ11kEifU7xD26iCzEDrhjVJbqxTfZiAiYSpXh3NKfGfLqplEbE+DJm9FLyqZvZcFdx+OMnmun5THLveo5bpfPjrWPZznGZull/e2DHdpNPBY57mdVXGrbqsuNXtHPoct78eVJLYkzZLLZUdGiY0Vb2JWjxzzuG7niPPy9B0MnT457xipzlZzWej6Ey11u7S01LbK9TcuzZCdOfRHPGdb7uckOghxWy3OK6rluXl5eaWnrn2nXch1HnzoUruH0s5zx9TphKxfRyerFlkdEssoxZp41R4wh6xqr1YFDJ0M35Pot9dyXX+LrO1xxrM/SzvTiqOX9H4mK4GuV0Mc5ZWq4zRzRXjVyEVKFQpysImIXSqMWxysQkIo6slBNZvLRQvyZYaqZaLqMzEs1MC1l8WHYq3PC6703zb0nzc3oqYnK8p0/KfbtqajJ6NW215M25bync97MWa/OtBtNiaUmMWbT8R0uuzOVdMzSNJlJtXX5xZoyZi5upLmy89XioubbSshgc10XO+fhh9nxfaZz3u9gb/AJsJhbmB2uXFFX+x1tNoRdcaSZTN51zHQ2GZRZoMpLZcZXcsgwJnVnS2EibEyV1qcgdEjGr5VLj+x4352/Quh57e8+O0Y9nOcbj72N9zUcksvXVd0qZqLJNmwXGzc9pIq89SSVyW1JnuzbyVI5b7stu8aeWV5jD4/seX83LpNfn93lnvljk5TFytTG+1HjJPTHNcZ1CkzdZjc6xmyWasfm9FyKim8ywOXrykytKh4Lk4PS8n59egdFzm5wzv5Gxn6nMFo+25geNtVRUUBVasqq0HqwHqwV40Mmhap/H9Gj1/JdZ4+kqIctmboZfs5INT73kerAerSWR0S5sxCksyQN1mwldmpaSompbbVTWbK1CrxRXN0CnJjViMXNGySRTi0U1M2PSTUzX6LjPku15UlSTFOe3ud4sDRzNXy57D0fzv0TzYcgYnKc10mH9fpVLaelBI9YjJVVHBK1kqWQLKupATiNWSxjdKPRjM9ukm85y34LmCRzqJGR41KkJqLG9u80MnWyfk6w+y4zs+TvOg57ofNhvL9Ry3onLRuu/eucmmyM5LqalMsxEQ8sYjkoAFVEHKwHjQcNcCkkrHyHk1n8j13IfN3323h7Pnx3TVTnMGho430u1t1eTfWRrSwRGbxIsTqbHM7eK8yviKO2S1JJ0uaRdfrOemqzlrlea6XB+esdJynVYnc2aF/jnJxelqfQ6Yy7Z26YrthmdZbtBJaZdMapuuOlpLdJajrKy18DqOd58cjie54G8PS9TKv8M9dXsQ4UR56PpedkR9fwSkYSDFp6sIerAeiAohQipZgwSs+J6tbqua6XydHIic9LkamN9DjIRH2vLKRhMQETkATMY2nsa3eXMa3WZEjNR5GEhGRIsSrIMIerBZHQrLO6sstlIFiUjUlWJSzHGsrsXYxvM5/bwuh8V6/wBB4LvfLhUVMzkMbXyPsdHOY7roRxCAtKoZo9J86iJn41WWwFd0oMHkrVcCRysspl5vTEDyOyd1QLaVAz8LaxfDjC7PjOzxO56Hnei82Ew9zH3rEVy+/wBcaThWbZNZrNsJWfX2TecNu23pjFZsJrOM3aZqY5oRdMVSwlQyPUlfEnPc8Q3gzeQ6/kvn3udbH1eOPQEE5TGxtvnvpdrC1Hd92n1FltrVXNstgUkWNR6IsPnrGdWGRKSLG+Wd1dcOVx9rL4eTN7Hhe5Tr9TF2uGaubp4Po9NtKid+9tKglwquzbRWJbS1Xy2VjlxQe/Ngxd7JccLgO/4fXk9Au5Wjxz20apiVxh0+r//EACcQAAEDBAICAwEBAQEBAAAAAAECAxEABAUSBhATIBQwQFAVB2AW/9oACAEBAAECAP6YU7ZOYZ2xkGZmZmNIBS6l9F0m6S59YWFAEUfYACjQ7tKdrMU3XFKNGuSeiQBWoolStqIdsHcU4zRbUwsLUzUOmcPisjwK7wtvkP8ARGPetaC0XKLpK/YFN0h/jxXV4UVxtSq/6CiT1FRB7TQEFdweTt8FcbLRuEeNKG6aWhwE0gJSAaK1K/rBTrLuIdxahMzMgkwlDzIUh5LqX03SXgfqC96I9AKmR1FqHazNN1xSjRrk4FAJCB1FGlUaFAwKXTuNdxakGlMJZVTtNo4RYv2V5hrxsFK7fMC4GCdtS3KLpFyD7Mv2/IskhuuOqXXOW4gJ11PcABsJNaoXmm+CuJNio0+2U6JpC0OoKEg0QUKH9kFQcxjuHdZmUkkKSr5JNSlwOpfRdIukvg/UFBwEiZ7FCk1bU9WapuuJ0aNcpASkJSEakHpVEFPgRaKQezSm3MW7jNDTlYm24m24lTefRQqE0061yZK7rBrTSXUXaH59rbJYPmlhneWthvxEdGj0EoSBQQ23ZqvE8OWisOqs0kEEFKGmm0a9CiFp/u7OWLmGcslHZCkrFHqQdaCxcIukXSbgK+oKDkx6JpinqzdN1xSlUa5XSaQlCQNFIUmobbaZ8KEGyubeANew3d4y+YwLXHaX1zJIpIid9gbe7Gb+K/Y1sh9F2lz2BZ5Q3cuEqJNGo1oUnpAFYtTowRQcCo1ylKSE0wpBDqHQQCDSj/4AKdYdw68YQmrDH3XDbjGAAzWpAUm4RdN3abkL+oEObaihTFPVnKbridKo1yxIShSS0PG6hYPTVNoDQQVuhxFGh0ylbV/b51njqcKVUa5w0baPJRAM7bbW+RF+ce9bCgpFwi6CvWUupuUE1rE0CCKTW2FK6NIrAKVXL2oFAIKVppukUelUof8AgwVhzGcTpFvc4PlXGZmZmtNZS8i6bu03SXPqBDwcYD1Z2m64nSqNcrbSgNpaabW6txayqkrZumX3yqtrgzQCW2bcs3qOSt8YrEnrmeBucX4l2yredyqZmQUqtsoHlYdbSKlF0i4Huh9N1NEgigRSKwa11yEIOCU5XL0AJSOk02pCkqKgsq/8Qy/Z80y3LHrSZmZma11lLqblu7RdJd+qWry7bt7rilKo1yxbVIYKXHi4VEkjpCmHlvOObmoNNhphLMXNcnRxWsaR1yBKRccfu+HXVippxhVuaCugAEVKH28x4Mhx5ZS824m7Q77JUm5S4AEgA7ceWuubItF4hbtcrbaomKCkqbIUHJ22/wDFBTtu5iHcaamZmZnXSkuJuEXaLpL4P1WOXsP+k2POeXutLRcquy5sT3MoVvsqpo01SHt3XHK5KOKGwKOuRhlkne4q9xN1hXGilVupiUGk1LpSXXsNncwtq0KRcBxFwi6Sv2beReIWBGBWuucNYJ3HqdrkSFKSsOVASmioLC99v67dstP5AVocxbuJW3UzIMzGhAWm5RdIuk3AV9IKVpfS6FhwGgD1NAhWxNAyKaUbg3IVyIcRVZlk1yBkLVTinnnUrYasn+K3XGXGCwu0KA5L9IWpbNNXbLgD9bIFBaLpFyD7IvE3eIW4OZt8Rctio5ZAV03RCKAJKgrdTn9UUpWMGKsbvht1gHbT8pLmPcw7trUzMzNaagpuEXTd2m5C/qDgeQ6DtsVUEpR4z1CRROwoBis+OIG2Nsaz4CXaeZRbPMKaYQqgl2yu+IXfGHGlWrtm4gLNWwlolVnhLrFWmQDysctFJdRdofHs25bckzWR4ZTZaL6E0QCgwlNEQqtlK/qqNY4cWEkP4m74pd8Udxak/kCnLVzDu4+pmZkGdCikvIuW7tN0lz6krTch6OkqlYoUaklIHVqc2OIKZNkaz9JEuPLeccYZSkrTSREXWPvOH3mAU07Yu2NsCWzbMcRxt3hedYeW3m8qEu46JQ+i7S56TVtfWfKcLyGn21HVCUEKCyVKK6C/6rhqxHFR6vW1xgbriNzgXbX8gLiHMU7ilomZmQZUnTpNw3dIukvfUFi4S8Kkmh2QkFIFpWVHES2ccazilXKrp1eyGmAopQ0iOiVmbnGXXDb/AA1xUt1hbHiqFt/9Xt5mdmLsZP4r1mCFIuEXQV7Y7lP+6lwEKCipC9lE0Cof1XDVoOLCpNH1Iexl1xi64u7jCPyEuY5zDu28zIKikqXb293aUl5LyX0XaXwfpCk3CXgQAEp8QQpCU21ZAcTKKxRrlNLUlaAAmkqKwtL/AJAvelkUmiop5Bin8U03jmONFVf9TYCupkEKYyIvTjnWZStNyi4n0lDrOWZyQdkrU4FlSFf1TS+mRxcdn6Xbe5wV3xV/GflCnLRzDu2CSspVsw7fuurNbBWwfRdN3abkK+kFFwi7ZUgKQ60hFvV2OLFFYU1yZJRAIO/m8qnW7gXYyDF0t7ZNClEVdouba8bs0cdU5X/RW125Z2B6mdrdbWR3XjSCgLTdId9mbprLIuSdwtKtv6hpXSa40PT5Ac+l1m+49f4L8wLjbuKdxS0U4ujUUg66yH0XTd4m5C/pBbvGcom5ItauBxworAGuQBVGiVOqd8iFuOlwuIppxy7Zug78oXCnW1vtcgRbVgVO1ym2u8KtopVbqa27ZVT9Wr7eSssdf4BLiXUOpu0r9QWr1u+SUnf+oqjSeuPA+iLmhQXvPoe1JyvHH2P0KpzHPYhxnjWDvuD3vDLi2kHbUopLyLpu8TdJc94oU3e22cF5g6brjpNZ1KisFSlUKUsqndCi8Sh5N8u4YWFWqnBy9uyVhVO1lEEuJexTuKUhSFWxRuCqnqtlLcZuMVn+Rm9swBcIcRcouAfVDjWRau/6iqNMisGPTl6rTP2nPLXl7T1TtPtlcTdWv6tsZlrXnVte/wDRLOpmZCiCghLiblu8Rdpe9ooVLdzb5vjPIQrLC4BWvsUo66IYQ0Wi0GtAkKD9g8uuYt4ZzFqcp9JGmtONPYd7GEKbNt5C5bl5xs25yFwtyXRapcZpK0XaHvWP6iurUCsQOj1yxcyFMu2nLbTndnneiQr0zWKWj9r9OYlzGKFTMghVaFIWm4bvG7tLwPQ6jqZssq1zxOVJFBn45Q20Wi0uglIUnUIhQixU5XLk8aXYk0auk0RFCiXLV7BvY80pg26wwIcpsoQeF3eHYywfVjlJpDyLtK/66qFWIrHjo9ctWFJfTcJXMmrTM2XPLLN311jc76cmxv8AAVTmNcxLjNTMyDXjLUpuW75u9TcJPR9232MqzlPKhuVLVWqWgyE6ELWpZLFPjlieJLtigmswg0ewkINFUvWr2Hes1I+OVKpmsDjrayvsMpIU26jLJQ9jNQEXKLoK/qLpNY4GrcenJ1eiXRch7bZLjWaAweS7uWLpj+Fs5ZOYh2zBkdDqS0bZSUvt3zd+m6C/pbfazTOUDqUJQHHHUhdKrUJVU3NcnTwxbJtya5GyUxr49SSTU9u2T2IfxjiMUxirawoozrNDoG3uxlUWj9iWwf6i6TWMFI9Cc6CyURHYWl3YKxlxYvA98otfttbXD4DIYB/j7uOUPxBTjDmJXjTQoehWR4lNsqD7d6i6S59LbrOaZzLbobCfH8U2SrRVmu2uK5Anha2zYKrlaAjw6ELJqewINKN5Z5LH8YRZN4lRrnbW8zIUFA2uVTkxiv6i6TWKDY9HDkAWi0phTBaKSOkLBsHwjGud8iZ+yxsLW0ZFyultvY5/jz+FI/EKUF4xzFON9LqUkKDxx7rSHkXCLlF2l4H6EuW2Ztc+xcgELpRdS5WXTwxSKxCq5W0UKUtVKSREBKkRJqLZF9a8ZpgYJRr/AKQyppVqUhUAACgUn+o5SKxItQfS6N6nQoKCgtKZUwtkgEFFJRifTMBQ+q0ssOwkCnV9TJrJ2/4RQod7rsV4i4tJlSwqxu8s7cqoK8ibhu9RepfB7mh2lVrnWOSs3ZCkuC9TxNSKwKq5bTjylhexXQoJSl5exPWHL7eLCK4+pVc7YdxD2KUhTJt9kuUKn+o5SaxIxw9L1N3h3MeUlJToUFtTTrK0IFrbhmyR0azKnPqZbAtGWUvK6PpyS3/CKHQ9Qt23ewVziwJddmjQKUlo0l9F43epuQroUPUKt8wzyBu+fHHiiuOqNc2pTkggIQ4kppT6lH0wCli6CTgVuVztsAU6w9hXsYULtyyHEr/qOUmsUMQPVQdx1xgbjjD2EcstShSFodax2L47igyB3yB0n6cc1jmaSm6V0agisjb/AIx6zM7bOpdxT2IWiwsnuCXfGSmQopLJQl5F43fIuUq6mZmZCmcnZotb7jilVzNvxFs0EJpTilKJ6jvjil1ycNHDKermraU6gGgHbF3jz+LUyuz/AKjlCsWMIPpUlzGv4F/jj2FXikYUY9hKU+mZvPpAZbxbDSSoq6ht81FZO3+u0sHLf1FTMzMzPoTj3bTmLQ5pZzIMhRBaLSXUXjV+m7DszM1PePz9h/0bJ8kVSllRc20Ugn244pdc1bx7mOU9XKG5BSnwpShISkXGKuOM/wBRyhWNrj49Z91JXYf5iLED0zGQu3PpsGmGgGxcrqacXbu1EcltvqnidXFu/hX8C7jyPwhV0HMS5j+poUKNFgsBaLtu+Rdpd+iUXKb9DwTSHVKVR9uPlVc0b425aKVWWaFJQmipNIWikDQNf0zTlCrAccHopf3qVeZq8uQfps2sOwkU4uhQrKOgW66NZG3+iD1xOnDIpTeXxs+k/XAES4hzGOYtaanYK22LZZpNy3eou0vg+k9ofTet3G5Pth1LHMEcOW0UF1OpVKQKStC23GlD+oaXQqyrjQ9M1cTUQR7kqvV3165eZIOp+m3bAt2Ww+uhQ65Jf2L9iuj1lLf2HR64pTnQoUlOWs/vA7nsqcsHMU4xMyDJUpAaKGXA+3eIuAo+s9JcRdofFREVaruByhvg7ias1VfNRCakVs0ELbP9M0qhVrXGR6cmUxn7Xnlrza1yHRSWyn0ftr5vKZhoMhP049rFMUBcK6FX9zkHuOXFs5Ro1yW39h0euKUugKBBz1l7D1A11iKNRHts5auYlyxmQSWlBQfFk8yi4buRdJugv6EuovUXHRNwc23wdxNYlRrkDfQpCW2fC1ahhDX9M0ema40PTlKt5Bq1ztrzq15ra3tFBYUno1luP3uHbCfoQlCcWwgKUT0DyW6LmGuKaXRrIsew6PXFaWDU0FFeStPUVPFBf8dewLmP1jrXU0T6R6AuIcxa8atKCtYVZXeVuV1KVh5Ny3eIuUr6A9UOIvU3DFxfI4etNYJRrliRSE6opCmyh0LbX/TNHpNcbHpyoikuC4TcJXOyVWfKLHndlfqpxfd5ZZHFj6LBu0YpAuVemfvoSq1fsVUesrb+564rTh6mZzlr78UJQE+G4wrlChUk1rrprEREVHQpZcxr+Hdtp82wo0CgeGU3Td6i7S99CHGc5iE29zx9aq5q2kABsNWtu0w7UAf01dDrjw9OWKA9EuC4S9Msv4jmuQvsTl+72zu7X3tm8IwBTi+ozNzkFIop40/bKo0a5Hb+564uV9q7NX9r0PTitLUC3XkfTPRq5w5HrMzM9xFbu2TuHcsU1i+HXnEVs77kFqE3Ld6i7S+D7pXjOV2X/ReSZRIQUPNpaApRgJ/pqoUgVgR6cuV4SmIjtK0vSFWN6E4u77z2P9rVtCWWkB5XQ65LeKSmgMA9SVdX9t7nrjNK6JqanN2nQ6PXGlGgrdFX3U0RizksLc8bfxDjU+4AAHZ6Ci3iOVsZr/oNlMyCFmi0WkvovG7xNwFe4LN8zlbZVvb0EBpLQa/pqpNMisKPTldFstFkslooiOkOBQVjH8U72Rl7T1sW8MxQq4V0Kdcv3yhYTSFIXaKNAGsrb+yuuN0aJJoriCm+taHR6wCgZbBXkk9g8edyK9yeQM9T6gVJJM+sqDmOcxTjUyCDsVBksh1F23epuQv2ATVtlrbk9rlUU2n+oqk1bCsUPTk1FOhRoUFpTKmVNnpCgcA6mge+SW/o2gDG26aUqZoVyG5USl5LZFYN61VEEckt/Y9cdJM0KuwyvXXO2fZ6wxFJbSgN5pPYrjKskQZzw9RQTUlRM/Xs5ZuYpy0mZaVLqkoNvbNkt3ibpLgoAAdCpFWmVtOYWmd/prpNWYqxHpyIxrrrrqUFCmnGVoSRWDGjXpk21Duxbx9vQFyrsVyG7bSQ8lFIOAeTQog1kGCPU9YA9iryrZcAOG8tuj1iilHj1nkFT3xNWSrbfLn0AracXxu6xf4AXGXMW5jzSi5Vurb5FtbX2JS8i5buW7tDo7SnWZB/prpFWVKpkemdXEREa6lJQpDjS0NIwDHiSO7sXI7aRhLcUKcV3cvXS0ghxKgird5s26iFmsrb+p6wVR3mL2GVkxnrTo9WJAcUq4L+fPQ64ecmSdsh6ATTFphsNbWuYv3rN7Cu4lxr8Cwuycxwadc2Yfur3zTsHE3Dd+zfJfSo0aH9VdJqwFJ7mrjCv4BzCuY1aIjXUpUlaHWrS045jQz6XZu+7RtpttCafV2KyzD2GVZmlh5KCKwj1qpajRrkVv6nrB9REcxGDvbdfTibu27typy5dkqz46HXDVZMRrctjuAhhizs8VjM7laI10yN06v8Wzti7hXbRLoNEVb0q0VZB5rJNZNFylX9RdJqwpsdn0Uhdg5i38C9hF4pdvCkqTbWNhjWWFH0yK7k9WqMGwKFPq9JIXaO4t/j9zgV40Vxt8uKNGr63j0PWFqD1HMBhruWlAa8gsaPSCDcIKdeQp6HXCjkAGg242B0hLbbLOBwmcypEa1kcg47UR+MF21XhXcbxXi1/wAEu8bKaUtVsqwJbvmsj/TcpNY+rVJ+shdqvHPYh3BjC21i0Sr1zLqzTSBVgw2FK+hNbGjZu4VjjlwxbrPSU5e29D1hqk0EmuYAVhbm2AQEOou7Y9GmkXSFUTyMdDrhJvQnopUKSlKG2+MYDL5FVEUTe3T950T+ZPVpkrbmHKXlJmdgfIplVl/TcpNY8NON8kazjdx6H8JrK3XVojGsAoFwr3A7QEBZVWkUkcntvQ9YnojrmAAwV4EoUSTyOyPS6t3btRqOSJ6HXCDdoCBUXCAlKWmuKYDIX775ogpurnK5O3pKv0AhU9Su1XjXbdJBKt/6a6TTFyMgi46ayLXImeRNXs/gy95du0AgYdlkUtUdE2SVWZtSmoARRWVdEUKyFuR2esYRRoDTmIRWuFvWV6ht1m7t6NWCrsdclHQ64QbhJryFy/ADLXGcBcXF5fFwvKefu8rlhTKEfrFChRNCgpbLmPds/wCo8sXe/SHUX6Mkm8tm7K2YbLKmC0U/XdXV9dpNWyWGkC2S+r0ylxY8vt+VNPUppVr8YoJmIqKnMW/Z6xxFagRzRDakVgbsoS6pwr5HaChWIVd9JTydB6HXDVvlStpyKWGsHh0jLZSSaWvLZQlptCEioj8wAFDqO9UJLX9O46BS+LpNylzoG2zdrzi35zbZ0Gigsm3LJT6KVc5HIXqn09MpxDLYTT6/TP3fSDbcit+cW3MLa/pSDbBhTZoVNclt+z1Y0EkdcvCQgisXesuUQ80+wkYQ3YQ2Ecn9eJqc6KlO3rWNx1jY5zKwagjL5JxxlpDYSB1H5RQ6HZqAkNhIE/0jT1LER2labkXYuAaIYubflTHOmOZ22Y6KS2pC6fOSzLty0E02kVbIsULVJ7eczVyFJuU3SXwai2zFvzS35ra5iX7w0KUb5gjo9WZgpCI5YH0tLQcHdmkHrkVmkYGrhO+/JEnodcaUolRGjtrhsPnsrWuoby+SuHmmkICQIiPzDoAUBAECtirb+madDqNfSPRLwuhdh8GlBm5Z5M1zZPOF82ueZXuZplLYFMJsG0llu4V6cguLlyI6FJeTdC5C6WrG5EBmlE0ay1v0aFW1BK+jXKA8hJbUmsbdsqqLhl1nj6LsahPIweh1gVdLdLvF7XNZPxBsIDaWuRMNtIbSkfsFA0DQJISExA/dEfimFoW2Wi0Wi3pHcRHYdF0Lv5XyjdKfPSEtJQEgVZpxzdKV6cguy0W4qNY7bcqMbc27hMxyS16NCmKNL75LTiX0NKQcHeSgwG8risYLtW+2do+mJVKgGgjF3ywGQ34w2EcsxSEgAR+mB0KAiaAkqn+qQoFOpQWy2Wy0Wi3rHcRERHYS2hCUhkNJScQ2EqQq2VaFi+fvVaFstFotFspjtBrjL7a61Cb20Io0Kbo0vvkNKDyEUhSTjLi3QG5dVYVcoKQnM0fSyIadaA1SmgnVbgBo1lccBHcRHUfjFSFIBAFE9ig6Hg+HJ/fP3GiNdSkp1KCnTxlstFotFvWPZKENoQkCkhL9zkkG35Bb83t+a22arktTrrrqUFBbLRaU0UMFIw7wQ0AgJCc3a0aFJIK6JJzlKpxLyGlIrjd6KlQKbSrtxT5dyJ7hgk3NBCR0kXV1jXW61DXJcb6R9EfdFDoUkVFERGusg+TyBwOh3zB3b8w+4CI9IiKiI111KSjTQtlotFrxeINBpLaUACkUp2+IuBdi5SulC3vX+QoAEREa6lOikKbARQqzetyKCQOWWtGh0kuUSazCaUHUN0gpOLvEFRU757owE3bNDuQq5pJ1pKclkMrluIZBCACazNh+oUKikpCaBkVEVEAh8XgvBcJXQX5A4HEvB4PBc/qj1J9I6iIiIiNddddSjTTQICAkJAHd6mI6SsXCS2EjuIiI1KSl1DZA4y+1QoCslbkGhSqbU5WumXTCgtLqW1JPGr9SiSkp3Shtt9odTTlW5uUNtBrw3d1mMoaSvG5FC+uR2H6pBBCQoueQLC9gRQ+kOJuheC7S7QPk8gcDweD4d2/CB9UVEQRHrFRERERrrGoAEdmrgFPUdMpQlI9YqIghxLRTWBuAlJK9pzlqaFLpmlpCQjLJ6UHUtlBSqxvW3CdQ0hoF1foaxarlKAmri4z+bKwdeHXwM1ObsPzRqG/GhvQCCg9hQUFA7SUR9IIfF4LwXCV0F+UPB5L3mDwXP1gz1Mz9UQR9cRERHqacSpotFotlIS0lAH1kOA0goXYLopLZb5VaGhS6tQpITGTT0oOB4NrScBeAISG+1FwenHjdUFBXI1vOaMlIZctbpCzU5+xH5W2w1qaAHRTBoiogEGQYgtlg2xtywUx9KXBdJvRd+XYK8odDwfDwfDk/XEfSOooiPyqBTpoUFsNoSkfWQoPJbUVILHILfmrHMrbLXlq4gUqrELFTf+iw8hooKFY99nqDRNXA7FcZq5oISOSV4ghSUEVxO9DhoJKs5ZTP4IATWwqRURJNEakakADssGzNkbNTOupaNubbwFrWPdNCmyVb+QLgL8gcDqXvMHgqfxn2j8RERrqEgD7VB1LgDouRch2mwzdvuijWMuj1FyntQcS6ltSTxi9oUaNHq+HQ64nVwiZybSG4dS0pJt7hh1CiSM1j6j7ANdQjWAakUkdHuKPW0hQMeBGKex1QUm2VZKsTaKa0KCybdTBZKI6TUMgWhszb3CUuC6Tei8S9QrcOB0Ph/wA4c2BmZmdtpmZn0Ij8sREQAPucDyNNIASLZVGjcqWBb5ljmVvzBjMup6hSXkNFCm12N22sqJKpyY6T1wurlIaCLlTRIWlykKFcVvUDXTXP2HU+kahGsACggIKFAgdCk0OiZFEle5XttNIO1LQ1cf6/zvL4hYOW4EKbNoqwVYKtFNeMsm3LARrZNqsC1GVHqCm4F6m+FylQRO4dDwfD4d29pqdpmZ/LEVER9yg6gpju1MGrhIWLgXIfQoeqg4HUtqSeN3wVuVCozCQIT1wdVypTxdUrUgh5DKkmyu0Pod8pczFlUa66wE0BCkaaJSAOlUqgEpgGaiiVCo6iKBB9ylu4+f8AJ318JT0plVkrHrsFNJRhbV+zcsXcbn7Utax9CXE3ib8XqXg3pW4dD4eDwXP9E0pKmy2Wy3rb9GrpOmgRDISO5pYeS0pCm3LJ9LRZDaUZ9HSeuDLulVAL4o04FUhQrjl6he01nbIK3oDQJgJFHqKFTtMa1M0CVFWxVPrNR9wd83l8m8qp5hlGAYuEKbU1yJotlssG2NuWC3Ee4KbpGRTlPlpPjncOh4PB4O7fzSCnXXTRAHT6CiKAZpPsoOJdDaguzzDHM7fl9tk45Ig9J64Oq4JWV734o0Q8hlSTYXQpFRWWsvQHeZCtttpBJkq222kVttJo+kz2K2/JIX5La/Ryhvk6c7fvFKrRWPVjVWC7bxlo25tiwWCiPoS4m8TkRfJeCNZDgdD4eDwX/JiIjUAdLCm/GW/G2E+6kvIBD6bhLoIq3vLm8PSOuEruHTUGssOiHEkIIrjt23WuscgseojqZmaBraZ6FbbbBW1H6o/VO/kDodDgWFKbVZKxqsYqxVb+JVubU2xYLUR7gpuU5BORTdA+IjyC4TcB4PByf4cRER2QRGuqQPeHEOslspgJYKOj0ilOYrOscxt82DGdR0oEPNsqScVeBIEa5TH61EBBT6RUzMzM+gqNYg9xHUhc/u2DgdD4fDocBUwqwVi1YxdipgsG1NsbcsFuI90uJvk5IX7juwdD4eDybgPB0K/jxEQAPoVTqVDtgoNHq7cFyLgKNWzzGfvrzshxNINcdvkVFbclsup2KvSan6QAnTXTTx6aEdxQEbh3zBzb923kDwuBcB4O0q1VjVYlWMcsiwq2Noq2LHiKNfZCSCFnyBxLvg12DwfD4eC5/iR7TM0oKR4y0W2ko71umvFoG0papI9FBQeQ0sVg76Q5NZOyI+mIqPUUGg0EkRIqD1GilqdoXwvU3KXJ2mI3DnmDu0/skLDgfF0LoXAeIVYrxKsM5hncYbVVkqzNupvXpIIUHezSXU36coMil8NeOg4Hg+Hg7P8AEn1IKdSkoSlIoCnAtNTTJT6TRpwAoUVY7lNvk6Ct+R2f4IFJUkzRTCqnbculwroEGpmg6m7F8L4XaXp2mI2DnlDwXP7JCw6m4TeJvm8i1fFhzDv4M4F7CvY82SsckGoZxrvHnMctHqCi6Tkk5RN4D4SnZLwfDweC/wAs+szM+8a66hIEdKpaC2WyhoINTMyqlB5AuA+FkM3ttydnlV7k/wAYUHS8Xivcqn30iKmZmaChcpvhfi8TcA1NAg7+UPBc/sBDgdbvk5ZnMM5wZBeOusSgUEcbxbmMdw3JcIq3LBRr7pcTfpygyKXw0Wo8ofTcB4OT/BiIqZ6NKoggpSE+8OtuNa0Fpft3I+qamepmZmZ9gKAI61LZtzam0NsWCjXqZ6mkvpvRf+fdCp3kCNvL5g5t+qZCvKl8ZD4X+czb8cdLCmOUWa8Q5jVWqrM2arUsFkp19pRdIyacqm9FfHLch8XAfDwV+aPWZnuej1EAD6FB1HUUgg9z6zMzM+gon6k0lgMeAtG0NiqwNkpgoKCybY2irU25a1jsdGmBpFLWm8S+D1AGwc8wdCv1TWxUxkWOXXPMBfpuxSsY5h14VzEuY9VqqyVZqtiwWtY9kuIyCMuMoHhbG20+Qm6TcB4OT+KZmfriI+laVNlvxlNMq/chLTIqfcg25sjYKsDaKZ0LJtjam0NuGoNWSILRtsimZCk3Kb9ORTfJugrrWJDnlDoXP6wryIuU5BORTfpuylWOXh14VzErsFWSrBVmq3LJb1I9QUXiMw7e+VCw8LgXCXxcB8OhX1TP3xER9JBGupSUNfvZGwP3lBtVWCsebBVqtopSnGMOY9VqWsyNYqZmpFJeTfJyIyCbxLsRrFeTyh0Ln9YUHE3KcgnJJyCbosLxa8K5hXcQ5j1Y9Vgu0U1poR22Cm3BClBzdt9NubUt+UXCbgPBYMzP4Ij7jWvjUjVIA1j8kBPiLQa0QwGUo/NcVchLOCtnWVW67XMNFk2xtDZm1NuW9YmZqaStN4nIpySb5NwBGutbh3yhyf1SFhxF4jJpyiMiLtVovDrwbmEdw7mMXil41doW2gRbghfZqW71GZbzwyUGzLEh8XIfDoP1AR9U+wGgQQRrQIUQRoW9ftCQ2loMJSVlxRbblLhPm8q3uo/BdVc0gYJlSShaLxBtlWCsarGqsVW5aLBtTZqszbFgoipmZkFNym/Tkk5BN2DoUa1uHPKHdv1SHEvIv0ZZGWRkxcLsF4ZeDcwd2xVvWmN4q/w9/jDjZHqh1GTRm05ZNwm1NiWfILkXAdCvzRAASTNRACQKB3UV0fpgJCAEqB2C1EroAq3DheJn8l1TwZThkEEOC99y2bNWOVi1Y1Vkpgsm1VaGyNobcta+kzSXk3ycmnJJvkr8RRrsF+QOh0Ln7YCQnxlBHtO6X0ZFGWbzOXZWxaixYxNmuydx2QxS8UuwVblgt6est3yM41yFOUS0rFLsSBdpuQ8FzURH0AawDsa1krKp9AaJKtietdUtC3LQbSx4fEGoVUlw0ElMdxAAT+O6pQtU4xJo07V0fsIUwqwVjFYpWOXZlg2yrQ2ZszbFgtxUzMylYvE5JN8ENCfJsCK8gdDocn3BBBCpVU/WFeQllyx5qzzhvkxbew72CewT2CXiFYNzDuWJYLHiKPSW3m8w3yRrP+ROIXhfkpvU3guA7NRERHURqAAT2ABHoe411iEoS2B3sV+UulQo1tWhSEBEBOuntH0R3cUBYpsQaNPU8Y/EUqtFY1WKVil45dobdVobM2arUsFvSiasUhNiAFJLKmS6m9SfEWvHG4d8wc29Zn8QXu3eozLWcZzreVFo5x93jb/GH+LvYFeCcxS7XwlnxFPcyzklXAdbc8ouU3iLv5KboPBWugbDXi8elHqI6moqZmQoUUtoVRJWl2h1BCgpspgpragBWwGoT9EfW/TYxqbUGjVyV/dFD61NKsVYtWIVil49dmbFWPVYKtMe2asOjUKGTqaS8nIJyycsnIJd8JY8OuwdDodC/sFAR7xUhaVtZRrkrPK2uUN5ZWOd487xd/idxxN3i7nHXcW4zpHSE6sAhdbNvjkKbpnGf/PrxynE3ybsPBcnqKiIornuANEtFAoqKugUrokr2mgkI8Jt/DqCKSd99/pj6XKZrFJao0avCeo7j0io+2PWFWyscrErw9xaKqxCUt4FeDcxWWtyzpHcylaL1OVTmE5RN0GzbljxyHQ8Hdp7iAPqjoCIit0OMZhrlbHMWeVoyS8Q7xt7ilzw664s7xp3AeOLcKDiSnuWcozyxrmQz4pWKVYKoXabsPhYPUEEaahISERQqJNBAbKNFjuIpNblwqoKgJFGh+RVMDEpAPV8aj6I9AO47j1ioj1zNKqyrD27FiqwXjuSYtdgqzVYqsVWSrQ25a1qZmZRdIyicynLi+SDam2LNB4PB0LB+maAj0HtPkbuGc+zy9rmbfJzcPYbOW0MUU8bwj/HLriS7Ys+MjuUOtZlHJE8gTdt484JWMWtu7S5Ab8Qb16FQKkikjtYiI6A9EVEhXQP4lUqmKxKVUaNZE/VEesRHUR6R9OZpdWQ44y00WiznkUpg4xWEXg14N3COY82CseqxVZG1LHjImZmUPIySM0jOtZVJ/y1YtVoXA95vL5J7gD6Z+iStu6uGzj04tu14ohdsu0vOOv8eewy8SvHLtSwWtPSWMq1y1rmgzqLL/5m/s05FGQTeB/eQQrYK38gc33K5+iIiQrbbb8TtKpisSlzo1kj1HpHcRUVERER6x9WVS7WORxpttMFPIEpQGYIDYah1C7RWKVhF4FeDcxC8crGrx6rFVobcs6RUyClbWSRn1XYaZFFzcLkPB4OBVARrrrqUkek+0zIXuxlGuXJ5MjkCckMd/8ALXHEbjhj/EnONL447h1slnwKa7lq4OXQ4XW3RcC8TeouE3YfCwe4iIiKiI9ZmZ/E/TtNjFoc6NZI+kfYBHce0dR65AXScUjjSU95oEFUJI6KljXSJKt1UqyXiV4NeCXg3MOrFKxS8cqzVblEDqxQkWfTw8ZaazCcqltWIVijZQLlNyHdwaUCPSZmZnqe4CSAoKt8szzFjn7fME5lrHq48/xO84Bd8Ce4e/gXscWSmmqAcDAVSyF4fkB5GlBwS8Spv5aboPBcz1M7bb77bbbT9Ue0dXNO0gYxK6NGsiY/APSKj2j0iKvReDFp42B0azJWskKBDqXFLLm+/kKpnqAEpQhFLt14lWDc465xp3jruBXgl4W3ZNY805UEX9Ts2+3mWuTMcuRyNDpwbmCOMU18kXBd32/CPUKQ6znmObt8+b5gm+OFd4w/w17gdxwK84cmlptgtJaU271LbzOea5ejlgvk4teCXZquE3wuQ9vMzMzPc/ZHUdXVOU0MaDRo1fmPqiIiPpio9oiIvBkaxqeNgdGs2fSQomo6gANJYU30FBYcDqVoSkEiiFY5zCZ61XWNFY/CO8bc4/kbBVmbUsaVM7JWzlmeUs80Ryz/AEFWa8KvHKYKw8HQ4FekzMzMzttMz1GgTLbjGfY5qxz5rml3eNhSbMePjWFe4/yPja7U25YLfQMs5FrkqOWnMhP+YbJak3ibgOhXcz3FRUekREVEXdKq3GPB6VV7UekdxHtEREREREREa6x6XdZSrFPGx0azH0hYcbfF8LjyocS+lAs14t+xSEJ038weFwm4S5tycxYBhvDWirRdkvjD3CrnijvHF4BzCOYxVibM2pZ1mQqUXaMw3yFvkf8ApgGwVZFncOh0OhczNTNAzttNBQUDO0zWxcUVWqcYzZcfyTVxd2D/ABy54jc8Rd405x97GKZ8JZKepS41ll5xL/lbuBcpu03QuQ8FVEdgREREe111ZizB6XV0feIjqOgNYgJjXWIjUNJtfhm3Kfa6rK1bDjQ6VWV+qIpDQtqtglDTqF3bD9oFh0UpUahKFJXyNojH1ZtYdstlsJRQW4t62cxbmBf449xZ/jC8AvAO4lePVZm2LJRUzKVt5FGcVkkJUTU7BW4d8oXPrFb7hzeanuZncuNX7XI2uWtctGfSy5hnuPP8Rf4kvjT2AdxxZIpNJBTbg0pQcxV+hJwa8V1ER7xA9Lik1YC27cp89REREVERGuoGuse8ocL/AJ/OtXtcVlKZrjYPSqyPvEdpKHUrN03cG8VeNZFt+8ZNqq3Cklspa8C2CM428jFi1RiREOGSkoTRoBDS0Jb1ctHsMriz3Ebjij3GnMC5hHMUuxLBSBWOSlL9QpCmi0i9F8ho4xWPNsaDweDgVPcVPpMzM+gUFNX7PImOXscvTnHLVzj9zxS44e/xJ3jEAMgpdTDglDrOb6j3j3epFYxLPbtLqI9YiAAIA1juPxP1k6brjYPS6ve4oCKn0tlNrFs7h37OkqF4LpVwp0mgW3kvFSWs23dowqbdOK7eSVqf2ACAlIUBRGnkN58xVypzVzFOcde4s7xJ/ir/ABxfHmcYKue1g1lBMt3Deab5Onk3+ulf+crHG2kXHmDu+220zPrM1PQGsBSVs5VrlCOWNciFxkWAlsFGExT/ABnO8XXaG28PUVH2rLQxSUDp/uKiIj1Hc9RMz+B6r+kVxwHpdXNRAFT9CVovW8q/d+sRGsJKHA5mReIwSWRiu1Wy7NSQJDxuDcJWGCy2yq0cs12ymC1oktvt3O4ZOPcxXL8XV2QWW2+Ou8bzOEXjlWZti0UzUpW1km88jkic2m5TZnFqsSkPeYOhc+kRrrHvMyHCtTJx4scHcN5C5snuOv8AEbjiHpFRER1Edqo00MUmj1cmIiKiogCIiiZ7NR9UdxUU7V3Sa46D05TtRHpERHUVHpFRHcAU2cvV4MEG6xPb95/qfPXdm583iSyhkJ+P8cha6KCz4PjC1+OLdtgNCudIq8pFYhhm1VaZTFr46vizvFHuMuYFzCuYtVibUseMiplu9aziOSJ5AL+5IWHQsLDwdC56man2iIiIAlt9nOM8sZ5d3HUREREREU9RpkYtKu7w9xERHpPpPcdRERHrER0ungmuPg9O0v0iPWKiIqIqIqKipnrIm7GApNYju/GoRFE0ikpQpshflpxnwEVE7FwvqujfZ591m7FmjFNMILd+145KipaF45eEXxx3iz3FHeNL4+7g3MYq0UzB7sUoTdgsG2Uja0xi8IrHqAeDoVWuuuusREdxrGuoTUREBMRERHpFzSqaGNSvu+PUe0TP2xEdRER6GlUaTWBB6fJH0RURHvHUz1HV/V3XH6TWI7vq2knqdkuJuRefP8odS5vUBJSUltxBb8GRtrhm+RiUY9Nv1fg0SR4xbpthai1Ft4AwqwXhHONvcRf4VccIf4a7xN3AWVrFzSKNOCsgWss1ylrmCeSpukYtWAVilNfID4c2qOoSIIrbaYgekzPcVERd05SBj0qo9XtREzINAD7oiNdYqNfSIhdKpukVhAero+kRERHtEe0RUVEX4uqwFJrEd34ignQpqA2EBIG/l8m+1A9FOmmt8l9GSRhBaC16vEi2TbBoVIMzMyFbTJX5FLctV4nlmKFXQYMNYdzC5WwNmbYt0Ds1etckZ5ijlycqi1PHF4Rdt5w+l5K9iqgAjWoiIiIiICQjTTXW9DgQixQagi9EVEdABGpFREAekRUABMGtQjUgiIiIh4Kq2pFYcdXpqOoiO4iIj0iAjXWNddaJq+q7rAUmsP3fiI7CQmZo0AEBGgRE7h7zBwnS6Q6nLI4/TFWZp+pmo11iKjuajoqLnMenRbG1axdkuwuePu8Je4K9w13ir3HHcUqxNkbVSQQpD1vnmuZXfJU0oNvB8XCbgXQfSqNYiIjXXUI1iNdQL6lhoWY6NXZoJ1IgJSiDUQRERrqRERqEhNRoluKNRprrGtXNKqypusSOsgYA11iOoiIiOoCAz4tCIFRUzQRrkBc1gqTWG7vaHRoUKFAwagICACd9ysqkLCgsEB1Lgy6eN0irA0/UagVO+5VO2+5XsVzGni8GZs7i3dqwFkxiEFppEaQu3Xi3MC/xO44O/wAGe4g/xZ7j67LxxbUlNWRKXGg3Y5ZN+3jdddQNdddAgpCY7gC+pVWwtU9Kq5ARqaNQlIBGpEa6gBJo1EABISE6hJSATMaxURB6uwusdTQxg6yZCQk+sahGkdQEJQlJUpe3ZMwGgjWMnVxWCpNYbu+O01EzNSFTM0ezQAaDWgTSy4MunjNJrGmnqPQO21AahMVGuuuvjDItxbXlrcsXbOFTat4Xqd5nqZ6KV2C8K7xx/htzwK44J1ZmldZNIVt3MyKHUdzPV31ZBgdKp2hRoigE0Oo0KNNNYiICQkUDURUBBEVAToUxoEZCnKxQYrHDrKdE0ewkJomZoJ11FKcJCQnXrUJCaBJJydXFYIprC0er8RGsEdCiAJ222mgAkJAgJgp1eGVHFymsSadrx+Px+MN+PQI8XhDXiDfj0AnbaXRctZFrj4t0YQmlfVHURUXCKtqNYqwe47ecXe4q9xyZmZFChQ7PYoEVcFIx6GhBpVK6J7CgsEAkqmak0KA7SAkJIIo0RqEBIBrUIoqyKnaxAtqsB1lSaIKdddQKJqIjqa0CAkJKdNNNQCINa5QXFYIJrC0esgRQqZJoJAokqmRRAQEih1A9LkZOuNUmsMaXQqZmZmZmZ2338nl8gWFzdoyDeApkYNSqXURERGuusRERFcjsKTTLeAt3LdFuu1XitdSmAAKAHUEFOsAJSumxjUoo9L9Y10ATUmtQgoIA11iI1SBQo9BOsREVFEkxk6erDi0Fj3lzUahER0E6BsN6aaeMiogdklciiNdYy1XFYWk1haPV+AO4AiKjXTQJioip2nbba8GQHHKTWEJpVA7beQu+bzeXyhe21RBQEBNDq/TeIwZbGEUql1MzO222220z6cqtbi1dqzYxKFJUmdtYiIgAUPQggiCaarGUKNGnT2E6hGpT2Oo000KYgJSkJgggADqAI7jXXLB+sLVlVn3mKACYiNdQiOoiI1IgJKdYI18fi8euuumZFxWEoVhKPV5RAAERQVU9zM7bbFUigZqMgLwcfKawRNGiZ6iAOgZkUDPcztlQ+nGUisMpdKodzM/VyRq4YybdkixFGgveIiIih6AQRrq9RpqsYnoi4rXTUUAARqW9AjxBoN69FOmhAAqZgdTPrERGbq5rBiwFr3l+h1GoTrEREUO4iB6j1mc5T9YWk1g6PV8dpmZnbffyb777bbbTIISGyEq8+Uq6GBKawJV0WwybYtBgWos/ihlLPxXLUW5RO2++07ZcLpkprEqXRoGZkdztMzMyTnEvN5xvFUxTRo1HcRrEdHodmrqlU0MaFd3PRGoFAlQV5fJtAO+5MyD1Eeg9Ij2zpujhKxote8v0PpjXQp+41EZoP1hqTWDo9ZEhYIojbz/ILu++220pT40oDSSLkXSrg3HmUvJ0+MLSawJV0bpeSXl1Zb/Q+b89V38lGSTlzk2Lpt5d45cb7+TffL0augmsaT0SCKACdNNNNNddAkOh7PB1PIGuOlFWhpSPD7x1Eel7S6QLBCh1dED3NTtIHczMzM1HczMzMzsDOdN5WEGKFv3lzMzKUkIC29QFAK3KtqACNNdQKnYr8vm83k2zBfrDFNYOj1k1le/k8nk8m5SBqGgwLdTJb8YY+KbYshtLAZQEjPh6sUU1gSrrKOeXcUlKWwwGfji1btE2pSX9gFrbX4vH48wlVZemzYnoiJkdSt/5qHkqISNyFKyoUOQI4qtNY1Rp+4N/M9T3Hcd35dpNWQPd0ZmdttttpmpB2Dnkmh3rQonaamd999ttttt8yq8rCjEUx3mjKVJa8fkBBgq8xuA4V+TbYK2223332FALEBHh8GYS/WGpNYKj1k2/jm1Nt8fwoaqZ8hc8hJpdwb3/AEP9Bd/89NybkrCzfX7jlY8prBFXWYJXuFIUHisLDqLpF+t9u8N2pW0EKC6Jfo1nxaqtSjpZ8nmDpeDq7teQOSGV/wBT/W/1BlXMk3ev3aqzaOJlNYhRrLiamZB7mZ7mb9TlIq1ompujPURUAREa66xFA0OoI7gjTw+LxBvx6QRsF5g3tYWsKGe+SOBxCw8bkOodS4p5NyXS6lYf8gJbDZQG1NkaBvwpa8IRO22+dL9Yak1gqPWV6V0RuXS6X/OX1PeXzlzbYEKKt/L5vP5d36XVuU1hCrrOioCY1DfiQlNsLMWqGPCEARprJrKBVchRjFslg1knTceQOm58pPSEoFElThIbbXWSTxdYrDKVWVTFTMyDM/RfFVMVbDo1cCI6AiANYidttp22222Ctt9yvZRL3yfk/I83n8xd8m03xv6wwwYa75MA2EigAnbyhwOeRT3k8nlDwuPP8gPec3RuxefKTdC7FwHg95Q9mlv1hgmsFR6zThuVPqeLpdLnk33332Cp26BClKo0KjVylVCawxPWdbDSUCiz4UNC2TahsOfJ+R8s3YuNyoufJNzcuKrPDBKQbQ1lwaHQRqaNChcfKU+TGugQ+LpOBIrEKXV+jxa66xEfVemrUMejxmZ7BBmpJmZ2233DgIO4WQQEFtSPjlkoAgNhsNJZ8OSq/rEjAhvvkFFPjDIaCC2GwmCoq8m5KSlHh8CmijWKBBSrfzG6L5XeF6sQU1gqPXI1l4uT6xFTO2wVM7bUOppdKp8JrEE9ZVsNhOm5IX5UuSUlADaFM6yX6iFhVZ8caWmseayidPH4/F4fALcW4Y+P8f43xxbi3FtepcFgpNYxTlOp8H1TM7bbXK0mxpozJLhmamZnbbbcuFzyFzfffbbbyJeD4uA+HATSq1CIHSyluVO35yBxYwAR3nSKn0HUzWgbLfjFBRXJrUtqaDWkGtAz4S3fJdrEBNYGj1yVKWkWRx5sTafEValvTQo8Xi0ipmewAjwvNqq+pNYo9ZdIAAGupbKAnx+D44ZFsLQWhtPh/DFuLd9hVZpPFymsSTV0kNePSjUdChUzMzOSCqdKasVKpdbzO20zMzM9TMuqbOOpBmSVKmZmdtttiqSSrbbbbbbbaZmdtgoOh4PF3fcL8nyCqryslWOHHwnvO1Ab8esRATrqG9NNNdAjXUI00U0pCQitw4D1lS7WJpNYGj1l0BNQa2JAU0q3UyW9NdfGUaa66BKUBrYOXKlVkw3WMI6y1BXk8ocDm+0k7Co0SPIVTQQmnCqssOLLTWGUaua8nlLhd8gc322naZnYryVGsyGjbGTQRERERERERERCqaGMSkdKo1MzMzMzRo0feI+mIiIiIi7rJmyHHgO83WgbCNC34g14fElAoUBEVHU+ikloseMoiMjTtYqk1gaPWV6A08elKMwWi2bY2nwTZLt1ILXj8egEwKeKqzFMnHlHWYraQQZmd9pmZ23332C9tnBkU8WUmsKVVcjbbaZFaxUghKWgg23x8s0a5GmxW2WjS1f/xABQEAABAwEEBAoHBQYFAgQGAwABAAIDEQQhMVEQEkFxBSAiMkJhcpGhsRMjMEBSYoEUJDNDUAZjc7LB0SVTgpKiNEQVYGTxJlSDk+HwdMLS/9oACAEBAAM/AP1Mqxy86ENObblthmG54/qFa4udCaZtvHsQVkiNDxdVEYim5HY4Hfch0hRMdgfaOCacWobHIj2/3mz/AMVnmr3L/GIu3F56Pu4V+in7Q8L/AP8AI/8A6N9hRFHSKKzyX6mqc23KUXxuDxlgVJEaPYWnrCO2/eo3dSe29h7k+t4VV6xu9UVw3jRJwnaBGCQ3aVJGK2eQ7jeuEbGT6SA6o2i9Wqz/AIcxAyN4VktF1qso1vjZcVDPfZLUx3yPuKtFn/Fic3r2d+ghPbt70084UTXYHjkGoKkHOo7fionbdU5OR+/t2akTvEjR6H9poTlam+Oi+QK8qvBNmf8ABah4tI9oVRanL+Hld16rI450PeKrX4In6qFVsFqj+C0HxFVQtK1rLGeoISQTM+Jjh3hOAF2AoiqK/QDpu0gLH9XIwKgm/Fha7rpQqB18UrmHI3hWyO8MDxmwpzDquaQciKewBVXgAqZl7o3AZ7EQqY1G7+yacHD+Up7cT33L4gmOwPtHDahtamnAoj2lLTZ/4rPNXu3lf4tF2ovPR6gbzpp+0XC38cfyN4g9kKaGuuIBCsz+aCw9SnZzKPHVcU9ho5paeu5V5wBUbsDTenskYSLtYaOSi9waNqaybBMPRUMrHgsF4K9BarRF8Er2/wC1xGgi8K2Q3ek12/C+9cF2r8WJ0Dz0o7wrRM0yWSSOdmTTRymgfqTRvjdk4UVME5p/sni43pjrjcUDgePNA7Wikcw9RorSygnYJBng5PtfCkVrs4Bb6WNxFaOGqclUAqk7wuUVr/s/Mfgmhd3P9pTRrAjML0lmssnx2eM/8Vr8G2pv7sqkvCUXYfo17CzdoEdptDKc2V47naSFcii4ogaLlX9cITZBSRjXjrFVY5OaHRnqNQrQ2+N7JB3FTQmkkbm7xxblei6xyCvRQ1BdfrHQE9uDiEdlx6kdoHksn03o7Qo3bUD7NwwKG0JhwKI2ex+8QfxWfzBXu3lf4rH2ovPR6gbyrzo/+IuE/wCK3+QcW7ilFUYCRepCK6qoacVrxRzQR1hQP5hLD3hWll4AeM2pzTQgg5IrkELXc15CDLSNwQr9ECjHw3wowimrbZx/zJ0VVNEkTw+N7mOG1pofBW0M9FamR2qPaJRf3r9nraOTJJYpMncqNW2JuvGGTx/HEa+CIJaRQjYQsk9u1HaKqN+B9hbbL+FMafCb2qGyTg22zvptdFf4LgjhW+xW2OQ7WV1Xje0rX/Z7hIbRDrdyvOilw44qjoJKDaFa3BthOUWr/tJC17NM3NhWpwza4vih/ldo1rFTR6Lha3N/ek94BVdFUCggFdxbv140obwrHLjDqnNlyOMMwPU4UVqh58TqZi8eCuVGjRRjm5jiHSQiMCnbaFDMjxR6juUZQOB9mRgVmAUw4GiPG+8QfxWfzBcp28r/ABSPfF56PU/Uq86KftFwj22fyDRVCqHEoqppvKj1AaBX1RNUZJCXGgQjcQ3jxSOYJGNdyhiE1r3gNwcV6IgZhA2aB2bAtW1N3LDdoEX7S8Lj/wBW894BVdNENNpsztaCZ8fZKZOA23WSOYfEOS5cH2k/dbVqO2MlVqg58RLfibyhpe3B3eviCY7A8chzXA0c3Ai4jcVw0yyTWOS1GeCRhYWyjXIBydioX0qdU9abqihFE1Dj3cTW4Mi+WWQeNVVpGYK9D+1QZn6VmisD26CzhmbJ0bHaclU0QAQaqquzQP8AyGRgVZ5vxYWnrwPeFA/8KVzOp14VriqdTXGbDVFpoQQcjcrlPb5RHEN5VviaHMcHdRCt1nJ9JA4dYFVQ6QsiiEQnjE13odYR2EFMONyacD7MjajtFUw7aI7L92n18H8WP+YLlO3lf4nHvi81gvU/Uq86P/iK372fyjRs0axomhqARrpqVIObgnlFgyTg7FB16AdpCBQqmhzDk4Iell7RWr6I71Xg6yH5FS2R7lc3doB/arhkfv2+MbVtA7lI3rQ2iiqKo8a1QcyU0yN4VitH/U2YB3xx3FRTX2W0tf8AK65yngNJY3N3i7vRCp1KRu2oTDc65NdgeO9nNcq88dya/muGmnsK2Cdvwzg97dH2f9roNn3r+YHRfI1Xlff7PJ8UNO4qiOjVKqqnQEEP/IxCZIKSMa8dYVlfzC6M94XB9glItc7W1PPIuVktUQfBJHKwi4sIcFDIDVgUEPB9otLIwHRtLuMChsKcND27VTZTcsnA77k3pCiY7A+zITttDvUZzb4qs0JBBAlZh2gr3byv8Sj/APpeej1X+oq86AeHLaex5K9BFNAqU0XDQNOqn1ATX3bVW4FO18VVV01RJRF6LgaKskm9UihPzqvBVlPUQqWyJchm7RLaf2gt08Ujav1DqO6mq3WW+azvDfiA1m94QcL70NhTmmoBG5SDYHBN3Hr47m3g0Vqjbe4PbgWvFQuCLQPWwvs8nxMvap3t17NIydnymjlJE7VexzXZEUVbtuxOZgaJ4xFQo3IHjyN21HWoziNU94WsKggjMaAOKECy2s6o3eJGj0H7QxSfvoneKrQqloIzC5RV1ik63tWsME6qCGi9Af8Ak2azyekhkfG+vOY4sPe1cOWagklZaGZTNv8A9zVZeFeB7bZXWR8M8kLmtoQ5hJVpiJL4XAZ0qPD2AKCKITm4FHaFk7vWYTHYH2k8VzXmmRUVslZK97mPGrgAWmhyVnkoGytrkbivV/6ledAZw9a9zPJNfimohOAoEUdB06qAKq3FFGirjpqnGhAR1RUqlcqKrzuHkvujD86/wmLqfIP+Spa4d6rFHo/xabrYwonkjBcG2sEvgDHnpx8kq0tJNlnbIPhfySrVYzS0QPj6yLu9MdeQmnanNvaU9uLUDxecNEsMtY3lprsKkc3UtMbJmZOC4MtQJhkdA7I3hcJ2XWIjbOwdOE63gnMeQCWuGIwI3goHnBO6D69SODgo34O45aag0TukK+Cjdg6hyNyPFP2u0MPSszv+JB0FltjkH+WD3LXghfmxpWra2LlLWsETvgmHiKaGolU0X3IkqgVf/JzgrNN+JC0nMXFRG+KYjqcKq2RX+j1hmy9EGhFDl7BpR2FEJzcCnbb18xG9HaK7lG7agcD7PhOwPDrJbZoj1Go7jULhKKgt1kitA2uj9U9fs9bKB9pNmflONQf7sEx/D9ofG8OaY4iHNNQnAoi5XXIOb7AIaqx4tLyjQUTnUvRLS0HYqhhzjZ5Ktgrk8KvBhGU0ipaoe0qwR7tB/wDFWsHShaUUGppao3NIIFMiuDZ9bUhMbviju8FPGSYntkHcVJEaPY5p6xRVxCa5SMwKcOc3uTTgdF+ijlcEQNUKaINhleSOiSrPbLA97o2F7aFrqXhNkgllEmqWPpqkYiie1OuDgHb0w4Gh609u3vTTzhRNdgePJHzXIHnt+oTH8xwKKoqcKQt+NkjO9uioszs2kL0vBNgfnAxatqi3rmnqWtwTOfhLHdxVBdpDkBpoiNNP1iaVhdGzWANLjenMNHtLTkRT3UhRyiksbX7wrK/mOdGe8K1MvZqyDqND3FSRGkjHNPWKewaVkU4JwNxT9tChmR4o9TtyjKBwPsywUFKZLMIEXFH2xRRwWqanYgjSlFrQWd2cDD4KvBsu9qrYZxlO5Unh7QVbNHoDuEYX/uqeK1W0Ceb04ClU9pLBeU7VALb0SU2U6jmawyIqrDI2rNaF3y4dxXCMNXRhszfluPcVJG/UkY5jsnChTTsouoFSMwJ3OWqRrNI68QgcCCsFSNp6lVxRIaUTZnxuOxHUlbm4Hw0UvQR9GHUNKkA7FREJ4xNUx1xuKBwPHmZt1hkVG/nVae8IN4TsLwaj0zRUfNcqEjIqtihfk9a/Adk+TWZ3Fas0Z+YKsUZ6l6Tgy2tzhctbRlpqqKp0UQR/V9gX3UdtybwjM+CR1GiMuqRVOvMTWnsHV8CrXAdo6njVVpi58LgM6VHu1RRwBGRCsclfVlhzYaKQXxStd1O5JVph/EicBnSo7x7AFDYU4IhPGJrvQ6wjmCmHG5NOB9m4YFZhNODuPVChvVNFUFTYgjoJIX3Ox/wGqvBtoX3e2D9+PJUlj7QVbKzR94gPyFAgKjLk9x1yTQJr5A8phde65QggAXptKhq6kCrPaWlk0LHtycKqxSVNne+E5c5q4UswJEQmbnHee5EOLHNo4Ygih7k04XKQXtUwFHhUZq6Kxgor1kg3Kit3CUbnQsGqNpVvshIms7gBtF4U9mZqN1XMqSWuFQuDbRz43QPzbe1Ska0D2TN+U39ycw6r2lpyIRT24Eo7RVRvwPHfG4OY9zXDaDRW+KgmpM35rnd4Vn4T4NdHE1wmBBDDTwKkZwbLE9jmlk77iKY3qjm7wtayxla8MrPiYQiLsrkaaAqji0CoUT+rUGilkj+vmvvdpOUI8ToDhQgEZKwS1rCGHNnJUEtSxzHdoUPe1WmKpa14H+8K1xk0YH9k39xTmGjmlp6xT3UjarLNz4W1zbcUw/hTU6nq2RXmIuGbeUqGm3jgpqKIUjdqpiKbkdjxuNyb0hRMdgfZubgURiEx22nHqqaDxa2Cx/wyO5xVeDrV2Fdbm/OzyVHs3hVsjdFHWc9Tk+uFyAbgm11U3WuTTXNOkILihGKK/QBoKslrbS0Wdkm8KzPq6yzuiPwv5bVwnZal1nL2DpR8sIGoIUbsLlK3AVCLY6HEE6KSu3J1omawC7aoxYQNXYoZQQWBRcG2qxviZqiZj6726HxmrHFpzBUhGraI2TN+YLg20fhyOhfk69qtUY1g3Xb8TL1eqJ7cHIdIUTHYHj2uzOrDM5vknNoLVBX5mXeBXA9vszYYbbH6YD8Jx1H9x0CO02hlObK8eK2KpVNukbNN2gfq17dFLJB2V6y2O+Vg41nmHrYWO3hWOUHVLm9R5Q8ViY2g9g08CrVAT5PGqrTFz4XAZ0qPD3UjAqKUUliY/eFZn/hvdGf9wVqZewNkHym/uKfGaPYWnIinHBATUdiIxCLMHFEYjuuR+LvQIvCY7A+zc3Ap20VUZ209jVEDR9ws3Vrj/kq2C1D92VSe3t+WMq8bwq2Nu4aGtEDnZkKK+9AtNMEBUolOciwXpxCcToCCCGmw238ezMcfipR3eEw1dZLSR8kl/iFwjY/xrM7V+JvLb4KhBGBGgm0UG0INoSEBZyEL0BYODJcp3s72cWeA1jkc1RTXWuzNf8wucrHPfZrTQ/BIrRDz4zTMXhFUUjdtQmG43FNOB4/DfB1GxWtz4x+XN6xqjtVolmmZ6J0j9YgXtBKZINZjwRmCgNBIRGiuJQ0Vu/V+UNFLNB2AvV2x3zMHsQRQgEKxS/lBpzbcoJalpYe0KHvCnjqWB4/5hWuOvI1+yi00cCDkbvdQ4arwHDIiqscmDDGc2FSi+KRr+o8kqeH8SJzeul3fxLhouC2KC0soXuY8fUJ9lkDXPa6oqCE5hoatKO1oPXge8Jh6RHaH9QntvrdniFnfuUbtqB9k4YFO2iqYdtEDgdNSiSiHIkVKC+5Q9uTzVbJaB+7KpbbYM4meZ0VsTd2ilkgdlL5hOJTiKK69NJTQE1AprReUCaDSCqDQEFQKpVnlijkZE0O1qOIFKpoPNWrwlC0/5lEGgXKgc1XlCT9nYX/5VsjPfcgePaoebJUZG9WG0f8AUQajj047k2QVstoZJ8p5LlLCaSRuaesIojBxCeOcKqN23jvYascQVMy6QB47irPIQNbVOTkSLkCgF1oooJx/VuUrlSKIZMCpZbSc5vJvtYJvxImu3hWScEC7qcNYJ7amL/idYdxVrgJqzWplj3e7EbVZJb3wgHNvJKab4Zvo8f1CtcV5iJGbeUFcrlyVejG8EFekcw/KteRx07QUU4daptI8UTkdyjPUgcD7IjAp7Uw3EUTCRquBQDkxzcEAwUWaH2RvVI8eAVYJh8hVOE525weR0VsTezorYB1StRVFQaL0M1UVTiUGmhKaBWqbemyoa1Kqo0EKqCElmkGRaUL7l6LhdnVOzxKoAqTOC5RWv+yltPwPhf3PCaVI1Ec4IHA8Y8oV2VCtDBquIe3J164MnNHNMDzlzVPTWhc2Vvym/uT43Uc0g5EUTXNDm4J7MHd6IueEx2B488PMkIGWxbJWfUKKUVZICiiEUa/q/KVyo0bgqWB5zmdxWmWWOl7CAfqKpp2+yilFJGNdvCstoBLbj1/3VrshJDS5vu5ChluliY7eL1Znj1b3M38oK1sHIDZB8pv7ipIzR7S05EU0VaOLdem7kd6ITxtrvVMwjmCmHG5NOB9kRgVNH0qjrTMHsp1hRy81wKIAX3U/xj4tCrG/slU4acM4XjxGitjb2dH+HPOT2pziqG/RqlV0XIk0CoiQr1qtyR1gmuoFQIaqaTeVRekjmHyV7jo9FwnrfMw+K5DT1BUtS5RTbX+z/CcDjQOgKtETiYy2QdxUkRo9rmnIiiacWppwKlZ1rMUWWmkjeu7v0XAqRjAWPIoi8BlpiZK3rC4Kt7Z2QW0wTjVIjcNdhBXClmDiYPSx/HCdfvGKewltbhsKYc2nqUrRVp1gmnnCia7A8YjAqePE6wyKhfzuSU1wq0g7kB+r8pVc0dY0U4MZ1ySHx4ur+0FtiJufGym9g0EJ2gH2DXAtcAQdhUVoBks/JkyUsEhjkaWuHvIeNV7Q4ZOFVZJMA6M/Kbu4qcD1T2v/AOJU0R9ZG5u8XJvCU+tIKsGxWN45MWqcwrXDUwvr1OU1kldDM3VeNnEaUdhRGIT24ORGI7l83em9IUTHYH2RCtEdKPqMig2P0csXSrVqs87TqSCpGBuWpw8Gm46so0Vsjd2ivBk/0Qbigbwb0G1JKqbtAJV1Bov0mlKInEp0ZBCe7nJxAIKdrVJWsL1y3szjeqhatqBziWtZoHZxtPgqWxqvG5ek4OtrM4HjwQoCcgmSDVc0EZEKzPvZVh6rwrUypaA8fKnMOq4EHIpjsWoYtKlZiKobblS8K+q5BVzgtRqkjmEjHEOG1OlaGvNHBMfbGy0FHBtVDDJSF7iCK0dsUjDUVHWEem0HrwKB5pIT243qN3UUDhxnsNWuITxc9ocoJMHUOR/VblylWWIfO3z0U4Ls3XrHvdxa2m3fxmeAC4YsdBDb5dUdB59I3/krU2gtdijkHxRHUPcVwHaKB85gdlMNUd+ChmYHxSMe04Fp1hoOgceDhCI1FJRg5S2WZ0UraOB97OGxWjgyTXgbHTa1zbirFLQW2wviO10R129xoVwLwjdZrZC93wE6r+4oWbheCg50HkeO07FkU4bE5uBThiER0u9A4hMdgfZFSxva8EEtwJAJCAoJovq1cD6jYX21kb9gk5Ca4azSCDtF4VeD7T2FeVcUXIhOKIBRTjenIkVQG1UKJRJVESvRiiuRda4m/FrDvadFXQHNjgvScF2F+cDFS1xK5m5a0Ujc2EI83K7uRQGiKUUkjDh1hQuvieWHLEK1RVOprjNt6IuPcUx2LVtYVIwAObUAUyKY9pAOzBUc7ciUdYJ0bg8G9emiYdoFFrkOOQVFRxT5Z442CrnVA7qqWI0kjc09Y0PbgUekFG7A/rdy5SraYB840U4MsY/dDij7Tbeu1cSSB+vC98bs43Fh8Fw5ZqA2hs7cpmg+LaKzOoLXYpI83RHXH9CuCLcQILbEX/ATqP7jxGm4G/ist8Bc0euZzTmnMc5rhQg3++4VQtQaLQDLqijS5xJaOolQOvjlcw5O5QVrjwYHjNhTmmjgQciKHjg4hDYU4JwwKeMb1TaQgcjuUbtqBwPsuEbAQbJa5Yuprru43LhF8EkFshilD2ka45DlZJhc/VOTkHVLbwiTREg5o0QCBqr0EMBgqBXIG5BBUVU5Btust/5oHfcsQvVWd3WQtbgWw9TKdypaYj1qscZ6tGpabQz4ZZB3OOglDQNEM49ZG0qM3wykdTrwrVDUujqM23hfVRO2UPUpG3tNUa3heuZvVFVpXIbuT5HtYwVJKtsllbMJeURhS5cI2F+tJC6g6TVa4xqucJWfDINZcF2jnxus7828pimLdeBzJ2ZsN/cnNOq5pByNx0SNwKHSCY7A/rFy5RVbXB2tGrYLIMoWeXF1pJuu2P8ACqc3AlPGNCmbQQmOwcNIcKEAjIiq4UsX/TW6Vg+EnXb3OqrSyjbbZGSD44TqO7nLg3hJhNltALwL43DVePoV6O8GhGFFHPKLNaCBJ0HbHdW/ihjha423O54H6C14pIxrxkRVWR/NDoz1Go7irQ2+N7JP+JUsRpJG5u8ccHEVTDhUJ+y/cnNO0FSN213qmYQO0FRuQOB9lNGeQ8hSMIMjA5WSW4u1N6a5tWEEdS1hrOTGo1uCkcQjTBOpgnUqVQp1UAUBdXQ4ottMDspWHxVJJB8xVbDG7KRV4HjHwySDxVJYz8wVbPGdGpwrb2ZWh/jfxToA02ebnxCuYuK2xSfRytEPPjIGYvCDucAU0Oa5ppQ10XFcgLWlZI8bUw2GK5RTRSNLBe0hOjJY65zeSd7btD43azHFpzBopXNDLTGydnzCju9cF2n8Od1nf8Ml7e9WuIa2prs+KM6w0OGBUjMVG7G5A4H9WvKrbI/r5K47lq2eBuUbfLiXqp32mQ+fFkbg4o9JqYdtN+ktc1zXEOaaggkEbiFPMwR2h+s7AP8A7oo2uAxSms0YFT8Tc+I20QSQuwcKJ1nnkicOaf0M4YhWOWtYtU5suRximB6niniFaoefC6mYvHhx9hoRkVE7YW7k7oOa7wPins5wLd6kbtRGIQPSCYcU12B9lLGaseQVaW3SUeFZpOeSw9abJ+GQdyKYMUxouCaaKt6uxRJIogDp1SDka9y9bJvWtwY85OBVbBOz4LQfEVVHN3hVsjNGrw1but7T3tCGgnRRURPGs01S6MA5tuKeKmJ4PU64q0wOLXNwT24tK9PKR8JQY1tyBsDNwQKMHDPCcJFNS1zD6a5I4tos5rDK5m43dyjmutlkZJ87OQ9WK0/9JbAHn8ubknvVqs/40LgPixb3hA4KRnNP6v8Aeh1MdooxoyA4vpDF23uRCI2cZzcCg643HT6ZhjdzmeITrLaoph0TyutpxQIBBuPEDLQycDni/wBtPa5RFBGXO8B1k7FZ7I9sstJZhfUi5u4KwWgOkbE1j8TS4FPbfG5w3jWHgrXHX1esM23otNCCDkbvcyFZ5vxIWk54HvChdfFK5vU4VCtcd/o9cZsNVQ6pBByNx4zmi43KJ2MYHZuTXcyT6OFFIzFpHkpC6jXKRmPgvm700i9MdgfZSRmrHkFWqO59HjrVlkoHgsPeFFIKxyNcOoouOhzsAjtV9U4K6pKaKhcqubWnwWtwXady9Xb2ZSNPeNGtYm7hoI4YkI6UUZTjiggPZBAgpkrIpA3nxMd3tQEEpDcG1VbbOz5AVQBa1ip1aHRftXwsA24yh/8AvYENt3GqrdZbopzq/C7lN7iuDLTda7GYn7ZYP6tTLQC6w2uKcfDXUf3fq/3hxyYVWRgzc0d54tI3nJp8lrGHslBDSQiOJW46PRWyB2wuDTuddoMlhgJxDdU/6buIJLCDk7zHtZbXKxoua51Kqz2SIRQRhrfE9ZKo3eqNDc9Eb+cwFWeUUI+hGsojfGKdk/0KtUfNIO/klU9zITJBqyRteMnBWR/M14j1Go7irS2+NzJB1HVPcVJEaSMcztCmm7RykRgUA8HUHkVNOzXs7mPBGBNHKaCQskY5jsinNTfipv8A7hPAqDUdV48ECL0x232T2mrXEFWyEirtcZOVjeQJmOjOY5QVkmFYZWP3G9AnBAKuiqrHCc4WLWsFqH7sqlqt7M2MOjWsQ3aP8QhfnD5FAIC4BVJ4o0auI0U0BCTgvg93/pw072EhB0Uopi0rV4aLM4nDuVAFWzubo1P2me6n4llhd5hNdiFtaVI3EVTdx6+MQQQSCMCLiP1a5etlPyBa1qs4zlZ58XVs05yif5LlRDJnG6tBGCIVNBqDkQe5XDcqWQDJ7uJXg+XqLPNUcRkT7MPDZJcDg1Ve6WlzRqt3laxA0a73HZgOLXFfZ7dMzZrVG4+7mlDeMirFJjFqHNhp4J35MzXdTuSVaYQdeFwGYFR4KuCo/wCqoFenQv1a3L0krXfKEwzHUaAOoaKGoNCnbTfntTx1ojaQq5FRu2oHA+xc0ghxBVvs9B6TXbk+9QSUE0ZYcxeFZrRfFMx3UggVSKDsU7itazTtzYVq8LTszg8jorZKdWgNksb8w8aCTXjVWrSiqeLrcD2f5ZJW/wDKqBBCMH7TQtzkexUAV72q8qN1ssbnsDg+Bw7irM++NxjPeFao7w0PGbUQdVwvyITHbE9vMKkbzm13Jjrq35frNyvmPZVbfZB+9bxXvsdpaxtXOicGgbSQrQSCSGuDaargQrXHjCSM23qhoRQ5cfqRaqgIySRsAvc9re8qi1LMwZkniU4Pk63MHivWP7R9kZZGMzPgqAABegs8ce0Cp3lYlakZO03ce6GcD5D704YFWWf8WBhPxC494UDjrQzlpyeKhW6ME+i1m5s5Sc11CKGqoi8NrsCJNdJTHMFag0R6JB8E5pvBCeNtURmFXaCmO6kDgfYuaagq3QUAl1hk69RPoJoy3rbeFZLRDEIp2Fw1qitCqseM2lanD4GbJW6KwkaC2y2N+UxHe3QUVmUXG5NACpeFTEoNFyrxdbg6dvwWnwcwaPs37TwuytTfG7RSchUe5VhsEmUj294rphmFJI2u3hQuvieWHI3hWuGpMesM23oGoITHKVnNJ8wnDnM7k12B/VrlyJj8wVeErJ26+B4wcKOAIyKscn5Wqc23KKQXPa4ZPbVUqWwuHXGa+BU0Zo143OGqVaYudC7eLx4cWqntOu4CkbAS55wCMloFocPVxc05uVTQIAADYOIBDDF8Ti47mqricz7LnyncF6W0tqOSzlHRRoCq4Ny4/wBosU0e3VqN499IwKimFJYmP3hWV/Mc+M/7grU0HU1ZB8pv7inxmj2FpyIopbbaGQs24lEQsLJHh1FwlZq0ZrjqT4yWPaQ5txB0FMOI7l8Lu+5PbiCnt2ojHwXzAphxuTDgfYkYFWyG4SlzcnXqzQ8JxW3Xe2jiXN5wOtkrJPT0czScsCucOtXla/BTD8M7FhcqaCQgxBVBoUdp49YuEI8vRP8AMaPQ8Mtk+aN3cVVrTmAtW1hcsrX4IY/4LQzxu0HSVDaB6yJpOdKFA3wy06nq2QXvgcW/E3lBMdsQOF/6tcvUvOb/AOirwnB1a58PZMeKOaHDrCsj8Gah+U0UcmDmO7bURhE8dg6wUrTQSDc4FqtuyIHcQrY83xau8hROjhs+tqWaMDkNxkObimNY2OJgDWigAVN/FE08r2nkNGoz2RJAGJQjjYwbAvR2bXOMhr9Bgqu3INBJ2BEkkq7SHWiSLY0DvGPE+z26ZlLi7WG4+0tNsbKYGh3o6VFaG/JTRGkkTm7x7nUUcA4ZEVUNgtAmigZXLYuCZmNZaYJYDmB6RvguC+EG1stphl7LgT3IWPh60MaKAsjdxSMEx2LR5Jp5ru9SDZXdepG4OThiO5D4u9NOKY7A+y4X4NcHWW2Pb8po9vcVPcLfYmPzfAdX/i5cC8KcFyxwWmktWkRyDUcaFUQV6pQBOO1Oci0I8elptbPisxP+xw0UtDH5xFeksdlfnE0+C1bVGq6p6lr8B235Q1/+01R0EoKiu0HJWG0gmSFut8TeSU4VNnmB+V/9x+rXKlm3vKrwk3qif7ZrhRzQd4Vkf+SBuuVm2F4+qs7djjvKa0UaABxRCw2eM+sfziOiECQwbLz7LXm1jgzzRmmjjHSN+5BoAFwAVGDrVwbnxBHG55waKoskZITeXVP14l0NoA+Q+05dtHyxqKRhLm35qzS1Oq2v+0+Ce2+N53EV8la48YtYZtvRBoRQ+5Oa4OBo4YHaE22uDrVrSvDQ0PLiXUGAqmH8KYjqeP6hWuK8xFwzZylfTblxmnnNB3qI4Et8QpBhR25PYbiQnDEV8F81N6BxCY7A+xIUzMHmmSrc9vco34P0aujNX8enCbB8cUrPCv8ATRybM/eF6TgXg85RAdy1Z4z8wVY4z1L03Bluj+KB/kq0KKoNIyTSmkII/q9LKzefNVt0hyhPmOK1pYCecaDfSvuDWglxAA2lMFY7LedsmwbkIyXONXuN2ZKJqSfZejgbXF15X4k5Hyt/qqkDRrvJ4mrE2MYuNTuCuC14mO20v3jT9psU8e3VqN49pSe2/wAOPzK9W7Sx3OaCmS2R74wfSR8oDMDEe6BEYFRSiksTH7wrM/8ADe+M/wC4K1MvYGyD5Tf3FPjNHtLTk4U41bjfvUZ2Ebk7okFPjO0FPGN6ptIVcjuUbtqB9jLHzXlHpt7lE7B1N+ivH1OFbCf3wH+4EKhIVbBG7KRa3AsTfgke3xVHtPWFrWaMrWje3NpHegwlvwmndcskSnJwXUimKqGX6rfopZYty+82k5RDz4ps8VklHRtLSdwBqgQCNA0H2FFGOa0nwUx5tGqSQct5coLLVgOvLsYNm87FJM8ySGrirvY+lmY3ZidwRJAAvNwCEEEcY6Iv3rErUjOZu4tTNGx1K8io2BfaLLBLtcwV3jFXPZ9RxPs9umZsJ1huPsb9H3m2fwmeZXIdxCvsdtkYByHctm47Pp7xUUcA4ZEVVjkwYYzmw3dylF8UrH9R5JU8P4kTm9ZF3eON4hRkV1abkHcx/wBDcnsvIIUznaoNbq3p8ZvBG69V2gpjkDgfYvbg5O6QqonbaFVw0DSY7TZ3/DNGe5wVJZB8xWvwVN1EFVsVrj+GfzGjWsTdHorda2ZTyeaCGgIK9CoQoidv6rytFLPD2AuXa3dTBxaWeyjOU+S4Zsj3CC3yhocaMfR7e5yt7KC02SGUZsJjK4GmoJvTWc/O2o72VVgtjdazWuGUfI8HSFkU4YjixzXm53xDFW2zROdHEyUjCrtULhWSR0MtYM2NFD3qrvZ0Y6Q9K4bgvS2kPI5MY1vrs0UACq+mXEFlsk0u0Nu3m4Ivm1Sa0x3lVimgJ5jtYbnLUnYdhuP14lWw2gdh3sb9H3u1fwW+a5Dt3EqF9osZkaPWQ1cOtu0e0J4h9m4bVZZb3wiubeSU3GKf6PH9QrXFzoiRm3lDTyQriuUqINkDg0XfRTWmPXs5a/5a0crRZ30liew5OCc3FDY+m+5PbjgmHG5NOB9i9nNcQndNtVC7B1N+ktBIxAqtZ5cOkAe8VWvwZam/IqTcIRdh+jWsX00anDNuGcgd3gcSqqquFAjSpRyRrd+q8rRSKMfIF6u1n52jw4vJsY63lNcXEEG86RrB1OUNu3vXDFkoIbfMGjovPpB/zqreygtNlhmGbCYyuBpqCb0tnPztq3vbUKx2tgfZrTFK3NjgdDTiF8JTm4jiWO3xEagDtmym7JWng6ctkaSytz/6H2Rc4NGJNAgxjWjACi9DZWkijn8oq9aoJyCJJPEDRHDW5oMj/wCiL3uccXGq9BwhD8L6sP10a8bHZjT9psk0W0tqN49jfo++2gfuPIrkO3cSirivslrkjHMPKZ2T7BruEJmOAIdZzUHeFYZGukjjDCBUgXKQXxvO5wr4hWuLGIkZtvV9DchxAh7MjAqKX8WJjt4vVnd+HI5hyPKCtTGnVDZBXon+hTmHVeC05EUVJAqDQ6zyAg3FenssRyKi+zQENAkNanPQW81xG5PRGI7l83emnEJh2+xkZzXEJw57Qd1yhfdravaUU9msrmSMcfQRh1DWhAoQteyztzjK1OGLRH8UH8p0Vs7m6NThhx+OFh0hUQpcb1I51wUgNCEVf+q8pXKjW7gqWWc5zeTRxeVZRlHIVcE8YOKcMQCmbahNODhpLXh7SWvGDmmju8XrhuyUDbWZWDoTDX8birK+jbbZXxfPH6xqsVuj9LZLTHKzNhrRCl6jY7Gg4kFriMcjQailVLYJi0glhwPsdaQyHBuG8oz2iOPYTfuGigVAG53niCl69LLI7/NkoOw3Q5pBbzgajeME20WeGZuD2ByqxzcjXv4n2e3TMHNJ1m7j7C/R/iEv8A+YXIdu4oXp7L6Ro5cV+9u0ewpwvvs8nmFWOS7olVvIUMnPY0qyTjDvGsqPeMnEdxVfc9YargHDIiqsUhqGGN2bDd3FTm+KRr+o8kq0QH1sTm7xdoJh1CcCqtaMtJCa5orindEgqSM7QnjG9fNTegcR3KN2DvYvjcHMcWnMGitzG6j3CRpFKOVnsnCrLWZyGEODmubhrdYVnnFYZWPHylc9qvKpbLFJnC4dxQRT3CtLk/YE5zxUFU2BDYxPR/VLlyleNFLA45yu4tJY+qzvVw3Divbg4o7QmHbTfplglbNDK+OVuD2Gjk4tEHCe4WgD+cIbHXKsgs855JNI3ZHI8SK1wujeB1FSWWd0TxgbvYeiha3bid5VGPnI5x1W7gqkaNd7jxPs9gkoaOk5DfqvSzmmDBqhVGjXsckBxifd2XXrUlb13cSrYZwMDqn2F+inCTuuB/mFVrt3GrcV9ltUkfRxZ2Tx/wDGoeuKVch3ZKO1UFVVUtE4ylf58QAElcI2Vkb5bM7Ue0Oa9vKaQUQaG4+4BGlNisct7oQ05s5K/wAmcHqeKeIVqhHLhdTMXjwVbgpbbZDM95BIuAXCMFSyjwpbO8xysLXDYdBTD0e5ZO71Iy+hCkGN6ptI8VXI7lG7agfYOY4Oa4g5g0K4Z4NeDFO2Ru1srdZWSS63WJ8R2viPpGrgzhOCxSWO1xylr3BzRc5oI2gohUIUbmgOKgTRg1NoE3Yggdn6rylV7O0PPRTg2Pre8+PF9c8ZWVEIjjubgUDcbjpLdWF7uRg35dBtNmGufWM5LuvI8QWiAytHLZx/STNyF5Tnua1uLiAN5TYYo424NbTRqsOZu4tZxEDdCyp7TlVUJGj0HCLWHmzMLPqLwr6oOa1w2iun7RY549pbUbx7C/R/im+CTzC5J4/pbN6Zo5UV/wDp28enDVk69cf8Vcdyoi7EqlFS22ofvn+fEqDuTJuCLBrtDg6zR1B7KsL5SGsABANCKhNFTG6m4/0KtcWADvAqWI0kjc3ePcSMConuDnxMLhgaXqOxRCGexB7M2Oo7uK4At1Gi0tieejKNRR2e32KWOlJIHYfK7ikJjsWjyTTzXd6kbfTuUjdtd6pmNyrtBTDjcgcD7AjAq0R9KoyKhN0sZb1tVlncNSdu4mhQYBTQaI1TCBcm/qt6rNF2xopwZZusE954tbTP1QNGgaSnDi0uOn7RZgSavYdVyMNrYOi/kniAggioKNltj29Em7jasWttd5L0loMpHJjHidNX0y4jY43yOua1pcdwT55XPdzpHl5Vyo4aHRvZI3nMcHDeL02SNkjea5ocPqqxluR4n2e3TMAuJ1huPsacKs/gyK48TUtVDg5oGkEEEXFGy2qSLYL29k4canDNg65CO9hV2imKJuCI4Rtg/eu4l4VeAuCz/wCmYnCYdgIrWuUbeDy9raESM9ieIOOU1zdR7WubkRUKyP5odGflNR3FTt/Dex4/2lSxGkkbm7xxg7EAprzRtxopBsruUjLqncURiO5fMEw43JpwPHKorfZ6Bk7tX4XXhYCeH6sVitNNS0Nr8LuSUSqJtMP1S5Xqtoi7WinB1jH7ocWtqtfYYPYlHRUaKWuSLY+Ov1ai0hwxBB7lUA5ivED4WSgXjil72tG0oAADABGCyRtI5TuU7edGq0uyCqaniejsQhHOmdT/AEi8rXkce5XcT0lhbGTfE4t+mIWrLT4hxKthnAwOqfY04Vj/AIciuPEpKOyF6RgO3A6TLZhO0cqLHsniYaKcLcHn98PIjRyjvKzQWrwtbh+882jiXhA8BWDqYR3FD0kfZQQCB4Lm6nMPc7jV9yNKbFZJMYtU5suRximB6niniFaYefE6mYvHhxKPbv0UbgDvUcgN2qU7ZenOc5peWkNqAnxnEHwRzTTiEx2B4w0FW+yU9FaHAZG8J9wtNnB62XLg21UDLQGu+F/JP6t94j+ujVsVlGULPLi1tNs7bR7KqLVQ6D/4lZ+vWHho9VH2RxBJY5AdlCtVxbkSOJe6Q7gvtFrjYeaDrO3DRcrg3i+ktcgBujHo279ui7RQkaNS1uiOEjPFq1XAjYqgEbdP2iyTR7S27eFQ8a8aKcKQ9l/lxR6QdhaslDg5VQAvTXNLSKgihCNltMkJwBq3racOLThOwn9+zQA928oIBf4va+stP/EcWvAkHVJKO55XKhPUVRdarwbauxXjU08KcKsnfA1jRGMZDQOd8Kt9kkdHPZntc3Ee4kYFQS/iQtcc6UPeFEfw5XN6nXhWuO8M1xmw1RaaEUORuKvXIKvcFQKQP1mupRQW9nJnMUm0EazVbLEBI/Ucwm57HJ7TiDvTdoI3Xp3ReHIHFMdt4oCA/WPvDdxXJO4rVghGTG+XFrarX/G9pqlVKLuEYvlY86KNAyA4lbNP/DKpaJe1xBHG1uQWpA+Y4yGg3BVOjWeTxBZ7PLMeg0kb9iLpACannHeeJR+gwTRSjoODkHAEG4ioVYqZXcT7PbpmgXE6w3HjXjR/itn/ANXlxTZLdYNY+reC1/126NZgO3aidHpIG2hovj53ZPF1bdYzlaIv5wr0A9+8oBEqvCcpzYw8WvA9Mp5VRsR6zpLrDah+6dx3Scpx1Wp9utQggbqgXySY6rVZrDZWQxAMijb/AO5JTLdMA1o9FHUMzPWrPLz2A7woXXxuc3xCtTObqv3XFSRGkjHN3j3FsgpIxrxk4VVmfzdZm68dxU1DqOa8dxU0EvrY3M2XiioND4Xh7SvtPB5FcEPsAjoKiQ00BO+JSt21RGNQmO2hRu2oHA/rXrj2Cq3KjRuHFEkkz+Q/XeXEOTB+Q9nWw1CcOZMNzxRWxn5Wt2TVOYaPaW7xT2FU+QhrGklFjZ7QdvIad2K5Q4tLLOf3bl94k+mnWlB2NvTpZGRtxc4AJscbI2i5oAH00arDTbdxZrRCyKPml1XmlcFOHuc2RrqnAgtKtMXOhdvF/G9NYIs46sP0VHkZjiVZDONh1TxsNFOFbLvd/KeL/wBJucvtViaHGskXIf15FUfqnA6Wua5rhUEUITrLaZIT0Tcc27OJS0Wc5TRnucNBMsg+ZE46Pv8AXOJvFrwdaG5Wg+LQvVR9v+iJ0Vss4zjd5K4buJVa5wo0Yqa2WiKzWdlXuuGQGZ6goODLK2CK84vfte7NelLrLA71Y57h0jlu0nQyI+ijDS7pE3gLXdXVaNwp7mcNisc1daHVObLkbzDMD1OuVph58TgMxeO8Ihrm1uKup18RjoIw9jXACnX3qzu5r3MPXeFO29lHj5TVTxmhruKc3FNdiVG5NOB/V/WP7KrLGM3tHj7Bj7nNB3hWZ2DC3cUCCBICMnBMONmbvjNEG8172dTgrU3m6r9xU8fPiePohpNolpUNaL3OOACM4EdnBjs/TmIo5/U1RQxMijaGsY0BoQrdxdWxzdYDe9VtEu/TqRDN161pnznBg1RvOnWfTLjNdc5oO8KA4N1dxUcvwO7QTdkbm9bDUKcV9HK0nJ4LVboefZ3EZt5Q8FsNxyWrPPAcHs1xvaixzXZFV0i0WSaLaW3bwqcf/FbF2z/KdFNPIsh7S+yW1hJpHJRj/wChR2LXYHaS+BtqaL47n9k8Sj2HJzT3FEhevk3o6KWyI5xDz4v3W3DKdp72ImBvbGiiqx4O1pVAN3EMjqD6pznRxRMLnOIa1ovJJUfBdn5dHWmQD0rsvlHUF6IGywO9Yee4dEZb+IAvQN1I/wAUj/aM0Xk3+7kbVZpr5IWk5i4phqYZiOp4/qFbYsYS4Zs5QUNsjMs8esVAamIFh6lLwZN9nkNbtYHMHSXCjwHDJwqrM/YWHqvCk/Ke1/Vge4q0Qmjg4J7Vmf1a+U9QVbVZxnKzz9oDirO/GIfS5RnmvcPFa2LIn7wo9tmcOyVZgbxKrJFhDrdq9PoOTQI0pxqNiizJcdwWs5zsyTo13tb36Ps9liZS+lXbyqrUaTl7IIOFCAQrO/o6u40UUt1Wu6ntqoLPMycEtc3Y3BSNqQKjMLXib1XcT7Nb5mU5JOs3c7j04VsP8X+h0Xnfp9RZO2VsK+12Npcavj5D/pgVR2qcDpY+N8bxVrgWkZgp1ltMsDug6gOY2HTRrjkFWNnZCpM7T94s5zjPnxbuEG9cZX3c9ocSjnDJxHcdFUXENAQY2gX2KMWy0s+8vbyWn8tp/qV9ji1GGszxyflGZTnEk3k3knQBoFnjzeeaF6SdzdbWNeW7ry97orZY369nnfGepWkUFqs8cozHIcoeFZ7JabHG6rInska6gOIIT4zR7C09YpxXgUrUZG8Kzv50eqc2lbY5gep1x/VrpN4RiljkaASxwcK9SP5tm+rHf3XB8mMhj7baKCYVilY/cQfd/SvmlBu5jN2mgL87gvT2tgPNZyj9NFGgLBv19kdNFcr0BUgY6aBVjhtAGB1HcenCdh/jDRed+n7rZT+8Oj7JbmB5pHLSN3V8JVFrNB0ErWjZami9nJf2Tp9W/slE2eA5xt8kTMa5BHRR9kPyvHF+8cIN/dRHxKLoH16lQaCdi1bRO3KV4/5KqwAQYOvatYs4RtbLsYGH+c/0UdigMjr3m5jcypp5HyyHWc41KKKzUdmiL3Y4NGZUjnvaHVldzj8IyCOsqj340obxkb1ZH/l6hzYU/wDKla7qdcVaIufE4DOlR3jTT9X9CCNWoJVn6RLVC/mStP10UNQrdDzLTIBkTrDxVsZ+JHHJ3tKszrpIZGbqOCss3MlG43H3IQxehYeXIO5q1nhgwb56CSAMSg1rWhejs3pCL5D4bFV4yF+jWcTxABU4BR2iyQyube4HzQ6Lz9VKMACnNxaQq8S5E8S/QLTYp4aXlt28IjjU4RsZ/fN0XnfppYLOf3ugEI22wsc81lj5Em8bVR2rsOmKSOSOQAtc0tI6in2WeWB+LHUrmNh0VB3Fa1hsjs4WeS9d9Bp5NkPW8cWnCFsGdmb4OQ9DJuTU0IAI/b7WP3z/ADVAtQazsfJf+Iy/abQ37rGcP8xw2bhtUFkgdLIaMaP/AGARtk7pZD1NbsaMkwbUxZBMhjc+Q0ATy4n8wijRsYEXmp2lUp+ghEYFWeT8SFtcxcfBRn8KYjqeFamXmPWGbb0a0/VAwFxwCYeaQnHbplZzZHD6q0NxLXbwm9OMjcVZ3dOm8UQkILSHbinClQgGph2IbHJ4604Yt9oyzRkm91LmokvleavcbkTedFX62SM0rIx0jRNa0NaLgKBUZXNarCM7uL6CzEDnPOqFFZGCzTWJ7msJAfG4eRouA58bX6I5TAxqGZutFKx4zaQdEbsWBM2OIThtBTm4tOg1QIqNN6AGj7Pb5mjmuOs3c7iYaKW+x/xmeejlHeho/wALi/jf0VQNH2a3NY40jmox3UeiU1t5KaWggI6NZjLW0c3kP3bDprwXYD+4Z5L1g7OiqAs1lP70+XFpww8Z2Z/gQj6GXsniAcIWrrkr4LB7vopeFbVq3tgZfK/+g6yrPZLMGtDYoYmbg1oT7fPUVELOY3+pR0tjY57zRoF5VTrbxGz+pT5HlzjUk36KfohOiKQUkia/eP1Ssbx1aCMDRSjpV3o7WhRHGoTHYOGktNWkg5g08lwrZiPRWx9B0X0ePFcIR0E9kglzLSYz/VcFyAengtEJ7IkH/BcD2s6sNvgc74S7Vd3FAiovHVoacQEw5hZOUg2VThiDxWtFSQAgzkxCp+IoMa58r/7lPnk13fQZDTqsAXKfMdnJai9waMSqAALWf1Dij0rhW6JuqO0dJjdrRuLHZsJYe9tFw3Z+ZbnPHwygPCtLbrTYY3jON2qe4rgeagkdLAfnZd3tqFYrW0Os1qilHyOB0Mdi0FRnCoTm4OBTh0dFAqqgWtHDOBzTqnjffbJ/Hj81Rco79FFrcGM/ihar6bDouX2yxRvcayN5D94VHauelk0T4nirXtLTuKfZ5pIX85jqK8KvBFg/gtC5beyqoAKtjhOU3mDxdXhuLrhlCrFJ2ToA0a1umccLj4K0cJWplngF5vc7YxuZVnsFljs8DaMZ3uO0lfa3/Z4XeoYbz8ZH9BxAASTQBNIJ/LHNG15T5pC95vOgD9FCagP1TklUceM9uDiFKMaFDpM7lEelTegcCDoDhRwBGRvVpsxBgtEsVMAx5aO7BcOwXfaxKP3rA7xbqqcXWiwMIzifQ9zlwNJT0np4T8zKjvZVcFWr8C3wPOQeKqoqNDTiAmfCE3JUVxVksznNY4SyjotNw3lT2uX0krtwGA3adZ4CKEMLI/hF+9E6zzsuC1Wk8VsMMkrsGNLu5OeWsJvcTI9Obg4hSjaCh0mdyiPSpvQOB0DWDqDWGB2j6rhWy0ENvnAGxztcf86rhOOgnggm74z/AFXBr7p4J4Tu9IP+K4Ktd0Fthcfh1qHuKFK1uQfI0M5gOOfEFosk0Wbbt4RBoeLS12X+PH/MNHKOgIHgofxm6KgaPs9rDHGkctGnqOwqhuQc0O03R2toyY/+h0V4JsfYI7igHMJyKARKP/hwOUzNN+jV4bsfXrjvaVUOHUdDiip7Tb2QQML5JNUNCh4KsgiYQ6R18snxH+wQGtY4HdUrh/KFkjpZqPY11Im84/Ecgn2iXWduaMh+iCqGgfq9yNUfZStweVIMQCm7WkKI9PvQOBB0B1zgDvFVabOQYbRNHTDUe5o7gaLh2HC3F/VKxrvKi4TaAJLNZpN2tH/dP6fBw/0y/wBwruTwf3yq3EHUs8Efe/8AsuEbbUTWl+r8I5I8OLRtc1rzgkXMvRrSl5Xo42t20v3rBvF1LPHADfI6p7LV6aeR+Zu3Di0wUo6XendJoURxqEx3NcDoZSjgD1KeC1wAzSCFzw17Nc6tHXYaNaNpQGn0FulaByXHWG48X7zZv48X84QqVyjprwWf4rNGq+men7XZI5DzxyX7wqEtO3SyeKSJ/Ne0gp8Mr4njlMdQos4KswPzea5n10BV4Kf1SR+em/Rq8NcHfxvNp0NqUBgE8qHUtFqLPXF3o9bJoFaBGyM9BCfXvGPwDNHaUTo6kCCCLlNZuEX2ZwpG0B0XW0/ohRqijtR/WBxCij7KUYPKlGNCs2dxTPhco8nIbGlSHIKuip01ICoAFqRVwLsT5ISTg0ubyjo1nE8Uyzzuabh6pmghH2D2uHKNNFRRfarDZ5trmDW3i4rnN+umqrFDOBzTqnceLSeA5TR/zDRyjprwVJ/Ej89G1VAOj0Fq9G48iW7c7YjWqDmgqiJK9JaYLQ0Xc2QbsCgLI0ZOKaAzeUTo1uC7R1ap8dN+jV4UsDsp2I1Ttd4+Yo7UE2w8H2g3GV0vIb9MSpJJHSPJc9xqSVmgBghVDQLVYBaY21ls1Xb2HnBU/RL/APyIUUfa14m1a72tzKuoO5NNm12uBLzU0IKATHYtBURwqEei4KVvR7kbNZZpSKODaN3m4LWkaz4RfvPGKKPEq0HRWK0WcnmuD27nLVkaeJ9psc8W0sNN4wRBI4nrIu2zzGjlHTXgubtM89Oq+mjIr7ZZI5elzX9oI1IKAxQaLgtcFpREBGTyiWNPXpB4MtY+TTeNGrbbG7K0RfzBOqqSydo6RxAJBG292J6ghSugUIIRsFulhApGeVF2D/b9Cr7E7HNKdtampp2ofqQQ4w4pRR49eLQAKKBpe915uAF5Knnq1p1GZDE7yjG7WjJY7NhLD3tXDVn5lvkIHRkpIPG9W9lBaLLBLmWExn+q4Lk/GhtEJ7OuP+C4JtZpBboHO+HWAPcVUVF4Q/8ACpCcGyRnxRe5zztNfZXorFuj0FvhOx3IO5yJWsxp4n2XhGdgHJcddu53Eo5p6wjQLlHTXgy0f6fPTQ1CqAdAgtnoH8ye7c8YKiBAKOhrdZud6aIx2lkE4ousFqH7p2m8aNWeA5TRnucEF66TtcQ6GwMN41jhXYorRE+eOUSVeWkjNqrdp+02H0rG1lgq4dbekPbj3Mt9iT0q+KIy+lydmfAobQ3xCGzW+hBVOn3iiflXcVmEw7U39AHvI9qK1KOxET6wJFQFKOlXej0mdyiONQmOwcDoDhRwBHXerRZKOitUsXZeQO7BcJ2uyvsss/pInUqXMGtca4intdV4Ogi8XHZvQtNmgmHTYCri3SAtaGC1Acw6jtx0XaLlyW7guVpJ4NtXZHnxNV5boIIINCDUHIhC3WKKe7XIo8ZOGK2HQBgnh4cDgtaAEZgonQTY7T/Cf5K4cTVGtlf3IFrTm0L18m/iXBQ8HWf0j73m6Nm1xVotL3h0l5xAwC9Bbn2N55Fpvb1SNH9QqEFNGn7Bb5ImikbuXH2Ts+nv9VTSeORgVMMHlSbQCm7WFQO294TTzZO4o9XcnDPvWfiP7Jv/ALH+6ptcN4R2OaUdrSmJp2oe3H6nU10HS9uDipRiQU57qk19vUDRr2aaAm+N9Rueg140HQLVYp4NrmGm8XhEGhV2jkO3FchnZC5SJQX+GWyg/L4hBqFUA6PQWs2dx5E+HU8Ig1RcARprA5mRBCJKbkq2acUxjd5LkjcOJ6uTsHyWtZ4DnG0+CJmduCojREKCw2d00p6mt2uOQUtotDnyOrK4XNGDG5DQ+N7JI3ar2ODmnJzbwmW+wwWpl2u3lD4XC4hE3aftlhL2NrLDV7esbR74UdFEdAQQ9o9uDiFMNtd6O1gURxBChODwPBE7a+KcP/xcndfgUNoHiFlreaI6Y+tydlXchtFEw7UP12tURpHuVCRo9DwjG082UGM+YQQ1QabOJ9m4SnaBRrzrt3OV2jkP7JVYYuw3yXK0/wCGW3+C7i6ri3QQQ5poQQQciELbY4prqkUcMnDFUJad40E6L01uARcx4+U+SoAOJUEIP4PsTs7PGfBet+gV6uUNnhfNM6jGCpT5X+kdjeIo9jQnl5e41cTUlAgEaDHaJbC93Il5cfbGIQBqjoqvsNve1opFJy49xxH093KJR2oaSAqoIA09i4Ygj2ZGBUwweVIMQ0pu1hUDttN4TTzZPFHq7k8Z96O0DuTciNxQ+MjeE7YWncUdrSmFNO39Yro6tBRRJ9w1XjQ5jmvbzmkOG8XhR2qGOdrgWuaHUBz0NOxDYUU4ww2nV5h1HbirtHIf2T5Ktmg/hs8lfprwdbf4L+LQghVAOj0VodZ3HkS4dsI1BC1gCEEOJRzxk4juPF1uB+DSf/lmIa7eygCnFGLgO3y6tdSPXp2SnzSue81cSrl0TokglimiNHxuDm7wo7XZYbRHzZGB27qRIppNtsLixtZYuWz+o92qmoDD2BrxiijoacQPqEzLuKGwnur5LIt8k8dEoj2b24OIUw6Vd6O1gURxBCiNC1w8lXrThtIT867ws2D6FNzcPFfO3yTsk3amHah+s09wqAUU6NxdG5zHHawlh720XDVn5lue4fDIA8K3NoJ7JDJmWEsPdeuC5KCaOeE9bdf+RcGWr8C2QuOWtQplssk0DsJGEA+RTo3PY8Uc1xa4ZEXFXLku3FVsdlOcLPJCumthtYzhf5cbVcW92hzSHNNCCCDkQm2yyxTjEi8ZOGIQFx41J5xlI/z4teBLB1R07iuUzcqqi1+AeFWgf9rIuUTmrlquB00M1ie7OSP+oQaUaK68poQsdvfqD1UtXs/qPdL0ANIQ0HQToGgo6AhpidiwKI4VCyf3hSjAA7ipW4schkPJb0w4tb3U8kzYD9Cus/UJ2wg7injolFH2FwXJb9U7WN/RKf1J21ncU3bUbwrqhyPUnjPvr5rMDu/sh/7FEdIjeE7qO4rNpTDtTc//ACJRykGDinjEApm0EKN2DhoBYKiqtVnPqbRKzsuIHcpJpHyyu1nuNXOO0q5XHcoZLBZBHKxxELAaEGhA4hNmnA2xP8uMQahVAOj0VpfZXnky3s7Y/uEQQQq3ji6tstQymf58XW4Ds3U+Udz1zPqgAicAjJwdbmEc6zyDwVWA9QOkirdD7NPFPHzo3Bw6+pNtEMc0fMe0Oaeoq7HBEolG2WJ4YKyx8tn9vcz7KmkaRoGnguRx9HwqxvVPZ5Iu94qFPM0mzyWW0fwLQx/nqq2wfi2Sdu+NxHeKhAmgc0kYgFEYhNOLQVCegBuUexzh4p2x4Kmb0e4p45zD9Qhl3Lf9b03JvkhkfoQV194ITtl+4ojiXBXN3LlO3IECpvTthCkHRWqw1Ce3BxCmHSrvTukwHcoTiCFAcHgeCrg6vinDDwJCft8gUMh4hZF3n5I/EPJO2tTNqadqH68MtBRyROxFu0jcqws3aLkzBpBKc7EoB2sLnfELj3hcLWagit81Bscdcf8AKq4TZQTQQTd8Z/qrC/8AGs80XWKPC4KtPJZbI6nouOqfFaksrPhe5vcacbVcW92h7HNex1HNIc05EJlsskNob023jJwxCAq1V0HRThG2D987TcNFeBG9Vom81c1VTW4lRmCZucbh4I+jj7IV6uWo4HTrRy2J5vZy49xxCoUMtACFjt7iweqmq9vUdo9gSjoHEqgh7QBDjjSyTnsa7eAVaYCDDaZo6bGSOaO4Gi4RIIlnbMMp4mSDyBULgBLwbZyc4nPg8AXLgx55lri+rJG+NCrE/mW+PdKx8XiahTuFYvRyjOKRr1PHz4nt3tIVcKHQx3OYD9FAejTcUzovI3qTYWnwU7egfoiOczvCGXcU0oZDyRHRKoEbtwRdLSm0K0ta12piKqRuLDoo1pz4xGBUzcJCpRiGlN6UZ+iszsTTeFG7myjvTtlO6nkpBn3181mPCnkh1/Qojpd4Tuo7iswUw7UM/wBZqiOLyAEdFJXb09uDipBjQobWqM9LvQVRxbtBa6oQIB0GOZ9kceTJymdoIggq6oVVXRThS2D955gabhoB4Knb8Nqd4gFAMG/TUEU2LVJbkSO5XaejlofY7VDaGYsdUjMbQmSMY9jqtcAQcwVUI6G26wPYAPSs5ce8bPrxToGgKqy45KKOgcc+wKPsGnFoKtEXMnlbueadytLvxPRyduNpUR51lZ/oc5nherIf81m8Bw8KKE82dn1qzzT9gDuyQUW4gjeNMTudG3uUBwBG4odGTvClAJGqU5rTUbFcTTateQmm1NAjbq4MCYeimHooscwNG0p4xadB9jI3mvcNxU46Vd4TulGDuuUDuc0jxVmPNkA8FrCodXuKkbh5kKTa2v0BVMRTw80c3d1fJH4gjtamJp2ofrBRFNIJrRDTT2VCW92h8b2SMNHNIcD1hfbYIpY+m28ZHamhoCGwpw0avC9qHYP/AB03DR9zt7crSD3sCJj+oWZQV4WrPOMpZB/yOihVy1Hg6fSWd1leeVFe3sFUciiijZbaXtFI5quHU7aERoB4p9iFXjDSUfeJG4Pd3p+2h+iHw9xTetNzQVWuAxIUvo3jUOCIjaHNpjiENdt2L16w/QIIKr2ANreUBsp4Kqb8I8kPm8CusfUUT9gruKcMQUUfYEGoNFaG4Su81O3ENO8JpufF3FWR/VvCifc2Ud6cMCPLyUgz7wfNEYjwp5Lf9CCiOl3iidkDuQ2iiYdqH6pTTVEI+0LXAjYqgELILhGwgizThrSalpaHNVrbQT2SJ+ZYSwrguSglZPCetuuO9i4OtX4Nshecta/uOjV4UJ+KJh03aKM4Rb88ZXqjvHE1bdaxlM/z01VQVdQ7NBslrin2A0d1tOKDgHA1BFQVUaRbbE+MfiDlR9ocU6BxB7Eo+4U91Kdonszw6J+qR1AhW+tZBC/e3V8kw/i2UjsOr5rg54vc9m9n9lFLMHRvBGqmuxaCrO7GMDdcoTg5w8U/oyNO8UVoHQruKeOdGfqEFXHxCb8PcSEPm80cx5J/wnzRGKPsZG817huKtA6dd4T+lG07rlA7nMcFZXYSAeCDsHA9xUgwPin7R4A+SA6vrTzRzPdXyR+JpR2tTE07f1Qaaeyew3EhSDIobWlRnpIbCgcaHerVB+DaJWbnGncrTa3MfaJNdzW6oNADT6K/Rdo9fwg393EfEpmqWYnSFThO2j96fEcSoWo+uzT6eyGBx5cNBvYcFQ8T7NbPSsFI5qu3O2j2h0niBD9LKdxAmpuYUb+cxp3hWZ3QpuKjPNkcN96k6LmnwVob+WTuvRbzoyN4osiUDsHchkRuKOZ+o/sndXenjonQfYEXgqduEjvNTDENP0TTz4u4qyOx5O8KF9zZQfqnDA/08lOOtPGMfcm/MENjx9bkcq7k3amHagdv60DsTV1ohOKA2ommm/RcUxuJU3Bc0skULXiRga4F1LgaqwP/ABoJ4uugePBcE2ggR22LW+Fx1T3FAioNRmEFq8LWrrLXd7Rxrt2j7FbopSeQTqydl2io0/bbFLF0+dGcnBEEgihFxGSHEpxz7QrrQTUPYNO1D38o6DmtyCYmnaFC/nRtP0VmdsLdxTejKfqFMMCw+CnGMLvNAYt1fBV2/wBUPhb5Lqd3gojb3ghO2Cu4pwxBG8Io+wkbzXuG4q0t6dd4T+lG07rlZ3c5jh4qJzuQ65UwThtKG3xH9k3MfQ/3ThtPcjmCs2ph2pp2/q5B49+iWPV1TccQjtaozmE12DgVUUKmgoYZXx9hxaFwtEB94Eg/eNB8qJ9ttBnkY1ri1rSG4XcSiqFqP36ftVgEbzWSDkHrHRKvpxPQWz7QwUjnv3PGPu5TtB09aIR0lFMQ2HxTxtKeMinbWpqadqB2+/uCciEc1uTckzNMdkVZ34wt8lZzhrN+q+GXvCtAwDXbipRzoXd1U0dXgq7e8ArqH0qEcneBRGXiE7LuoUQjx7gr27xooV1IDMJxIGvtGKcOa4eXkpR19xThi3zCyJ80R0h9bkck1NO1D9VI4usxOThsTjsTx0yicVd7Co0fYuEI3ONI5PVv3HA/QohA6RbrHLB0iKsOThgiCQ4UIJBGRHuZTzsVFTYutAbUEE1DQXJoxeo24IlPcj0ox9CoTi1w8VAcJKb7lXmyA+KOQXUUz/8AQm7D4p2wlPG0J+SG0Jh2pufvxThtRRGadmswEzaCoj0qKN+Ia7xVldjCBuuUJFQ5zfFPPMlad4oraz8oO7JUzefZnje1MwFRuKrt8FIMCpRi1EbE7LTguUzeOLcVIzmvcNxVqb+ZXeFIOdG07rlZn8+MjuKsbsJdXvCa69jwe4+SlG3xUgxb4f2VOr6/3RzPcicihtCYdqB2/qtQqE8W7j1WpJTPQ2l6sX2aGK1ukbK1oa5+oSHU23Lg+0/gWuF/UHCuh2aOSENrFoYKMmx6nj3dqYEM9AzTUNBOkHnHiyNwe4fVTjp13hSbWNPgmdKM/RWc9IjeFGebKO9HqK6vFDaPBN6vJHYT5p42p+SzaUwpuaHvpThtRTh0injb3hHaO4qMijqgbqqB12sweCsc/wCI2N1eqq4PfUMjoeokKJpo2Rw7ipyKtkjO+oVsbhZy/s0cnR/iQPZvaWpjsE7Zo5cY69FptjyIxdmVb4+iCrZHzoHJ7AQ5pG8cYhWhmErlaBjqu3hNPPi7irE7Grfp/ZWd9zZgfr/dOHNcpRsr3FOGLfMI7CfNEbR9bl1Jiadv6jXiU4+1VGgi4hRnqTTg4FA4gHerbZ/wbVMzc807jULhaMgPfHKPnZf3tTDQTWRw62Or50XBfCNilh9PqPpVnpAW0cPdKKiKKOg+xcNiKPsHDAkbip24SHzUwxDT9F8UfcVAcQ4fRQHCUeSrgQUUUPhQ2Ep2xyf1I7WlNTTtQ99KcNqIw8FOzmyvH1VowfqPHW1MYamDud/dWIgB2uze2vkrJONQTxOB61YHgk2eN30ViDS6ONwoDWjlyWnMBEzx71UgJnoWEt2JhryVG7oBRx8GWiUMva0lEHZ4hP8AhP0vRGN28I+wkZzXuG4q1N/MrvFVJ0o2ndcrM7nxkdxVifhLq94THXseD3HyUowPj/dSDFvh/ZEZj6/3Rz8FuO4pu0Jh2oHb+rhAogo5aHjBxUmQK1pGgtoh7sfZFEaR8KYcQozl5JpwRTk8bCnBH2MrcJHd6nHSB3hO2xtO40TXX6pCbdeiQb6pyzCZkhsd4p+wlPCdtam7QmHahn76RgU7benM5pLeySPJWihHpn3il96s9KNLmqkjXtlBpsIRa8F1KKxOhY1loiLqC7WCBvAQXpOCLUwUBcygKtIrQMduKlbzrO7uQGYQOR3hEdHuKOR7q+SPV5eaeOiUQjlxyFaGc2V3erS3HVdvCabnw9xVhfiC07v7KyycyZu6v908c1ymGyvcf7J7cWkd4RzPmusLMJh2pp2/q7ctFHtPWqgH3QBVPErx3HamG81KZsYm5BRuxY3uUB6NNxTNj3BO2OaVMMB3FTDFju5ZtHkhkmHZ4JiyqiE/JPGwoo8S/RytwC9W7tJ2SOgRsc4i4DYrOdpH0UTubM3vRORXUm5JufmE7YSnjan5LMFMO1NO330rW5zWu3gFWyzkGG1Tx9mRwHcuHof++L+qVjXq3WuzOgtEFnNRzm1YoziwjcaqA9Km8KCW6rHdxVmk/JbvFyg2Oe3xT+jK07xRWoflh24p7edA4fRDDWK6m91PJH4T9DVEbPBHZ4FOGw9yKI2ceRnNe4bjRWtv5td4qpRz4mHdcrK/8SEjuK4PkwkA31CiffFN3FWluEgO9WpuMVdyLTRzXBD4lVNTTtQ/UiiCqtHv5caBNbigNB44OIChOMYUJwqPqm7JD9QpNhafBTjoH6FPHOYfqEPhCadhTD/7LIhPyTgnVCK5Tt61g3tE9yGSYcWhRleiikbu0kYGm5Ttwld5qcY6p+i+KLuKgOLXD6VVnOEwG+5B2DmnuKOSGSajscnjanrNpTU07UPfHDaipG4OcNxUw6dd4qnbWtPgoji1w8VAfzKb7lZ5ReGP7irG78qm40UJ5sjx4qXoyMdvuVpGMGtuoUW86JzfoQgcHV33p2xo+lyeOi7wKI//ACCEdg7iCiEUePaY+bM/vqrW3HUdvCMz9cx0qNhQ6wqioKcNnjRDbXuBTfiHeR5o7CfPyXWEMkw7UDt/T6e+DSG70BpPtmOxaD9FAfywN1yhOBcFlIPqFMMNU7ip24sd5ojFveFhvCBaCnPAA3eKkYSKqUbE8dFGgFMaJwRy9hK3myOH1VoHTrvCf0o2ndcojzo3DuKsx6dN4IUb+bK0/UFdQ0BZHxTxtKeMkdrU1NO1D3xw2oqRuD3D6qYdIHeEelG07ioTi1w8VZnfmt3G5WWUXxxu+gKsbugW7iozzJnDeKqfYY3eCnHOspO4VTW4tczvCrg6u8KQYAKUdAojFhQ60URxKtCuXJO/QQUUFYXgAy6poK1qFG++OVp3UPkpxgaqduMae3EEIoFNTTtQ/R6e9kmifknjYnlClBijXYnZhAe7+qO8IBgNNqZqMFOiFUxb0C5121DJC+5ATs3IHopmSajsTgnjYU4JyPHe3muI3FWhv5p+t6mGIYfBN6UR+hVmOOs36KB2Eze9A4UOgaHZlPG0J2SG0Jh2oH3sp2aIUzcJHj6qYYuB3hA86MfQqznEPb9K+Ssz7vSsPUbvNWOW8wRnrA/srG7mh7Nx/uh0J/8Ac1WkYNY/cVIOfZXDcK+SirtaUdjlKFM3olOGIXICuXId2tF+m86LVHzZ3j6q2N5xY/e3+yabpLN3H+64Lkvcws3t/suD5aejnbXLW/un9CRWhuyqlbi0hOzK3IbQmHagffq6KcUhHSTsThiPbkpx2Ioog4BUTS03om5CtSUG3hqadGq+hKbSqFOT7pyG71VgGZV4CoYtyvOgapTftDqgG4KB2MTVZzgHDcU3oyH6hS7Cw+CtDegTuNU8c6Mje1DJNOxMQ2IpwTxsKITsuPTC5Ttwld3q0DEtO8I9KIfQqznnMcPFWV2EwG+5Rv5rmndTiOG0pw2p2SzBTChn72U4bU5uF267yU7cJX+fmphjqO3iib0ou4qynEubvCsst3pI3dRorFJeYGb23eSsrua57fFO6EzTvFFav8lrtxCdBapIizVLSLlcqtd2kSQAE20Q+klBJKA5hcFbIwS11d4T2ve0i8OIKI2caRnMe5u40VtZT1xO8AqYc+Jjt1QrI+npIHDdQrgyS4S6u+oUMl8UwO4g+SnGDgVaW/lk7lIzEOGgFNTTt93KOjboPEK60zemDYEECtg9oNrlEENgXyo5IqgKdvVdmgjan5pwTkT7tzAqmMZuCq9qoAcmaeS7cvvD+PG7nMaforM78sDdcoDgXBfDIPqFOMA07ipxjE7zRGLabxRNOxMOxN0OCfknDYnBHjyt5sjhuKtTfzK7wFKOdGw+CiPOicNxBVkd0yN4Ks7+bIw/VZOKfmDvTh0O4qmOsEdjk/ILNqYmnah7gENFOOU5PbgSNxIVpb+a763qUc4Md4KG7Xhd9CCpLTwhPaImEsfq0zuClaL43D6Lku7S9JPHd0gmiyi7YmnYmkHkqtutYaR+M/Edanbg3uKmbjG7/bXyRGweXmnZHz8kRtHkn/Dx7XFzJ5B9Vbm84sf2m/2TbhLZRva7+hXA8vPjczez/wDyuCp6ejtTKnZrX+KfSsc1QrWzY1ytLOdE9UuJpvCB2hNTDtQ9uE0bENBTQgNir7ADjFFOcs3BNbtqnE3NuR2lR5KP4VGOiqBDNNbtJR2FOdijknZLr4/UfdOU3cqzRDrVZWrVjecm6eQVWeTf7Wqhdzom9ysx6BG4qM82RwT+i9p8FaBgyu4qVvOid/tQ2hNOxNy0HLwTk8bCnBOy47m4OI3EhWltKTO81aBiGO+lF6arDFTrBVVI7W1amieMW+CG1vcUzr7k3Y8d6fsKeEck1NO1D2Q0BD2pG1OTTzmApsTg5goQVabMwMfY4ZG5h5YVwY+6ayWiPrGq8L9n5h/1zY+qVpj81wbaXyEeglBcbxQrg52ERb2XFQ/lzuHaAKm2GJ/gpRzrGd7b/JAXESM3j+6f0HsP0p5K2N/LruNfNTM58Lhvb/ZD/wDT/dEbT3J2yhTxi08aWP8ADkc3skjyXCMdALQ4j5qOVpF0kMTt1Wrg94AtFkeN1HL9m7RdrtjPWDGrHMK2W3H6ODwrewEtnY/eKKRho4D6FDrTTtTSmlA7fYlHQBoPtyiOpN6yn7GJ5xoENrqoDDiBAIrqVdBG1FOKK6wqoZLqTsgs6IHZ7p6z6BVnb1NKrMFSCTTyFWV+/wB0acQDvCs7sYm+SsxwDh9U3oyn6hSjAsPgrQPyid16c3nRkb2pqGh2SI2FEJydkjp1pHblQL8btjQ0m9oUeSbmVFZqGSpDrhQZKxu/NpvBChk5sjHbiNJTxtKkCOSG0Jh2ocY+6OGBRyCtMfMmkbucVbBjLrdpoKfUa8LHDqNFYLvSQzM+gd5LgiWg+1Rt6pBq+a4LtIqIoJOttP6Lg52AfHud/dR/l2r6Ob/ZTn8uGRavOsMjetv/AOFGLhI9vU4f3VoHMc097VbG4wk7qOT2c+Ij6EJuZ8CsnD63J+wV3IjEEcQhFW+Egx2qUdWsSO4qaR5e8gudebkTi1VrSoThkd4Ths7ius9y1iAHAk7NqcMQU1MKacCiU5ORRRRHsSeMEALgjmiQg0I1BCoMU7MaK7U7NZlMQVUdB0DJHTQYIldWgLq909Y5evd1NCrN3Klm3u00YdxVXu3+9xu5zGneFZXflAbrlAcHPHij0ZR9QpxgGncVOOdC7zTRzo6bxRRnAIbCU/YQpR0U5rpdYEXBXLkSHN/9Fcr9NBDvOmVnNkcNxKtbfzSd4BUw5zGO8FGefA4biCrG7Fzm72qyyc2Zh+qBwRTgnjNSBOWYTM007feSnDatU1AAOYuPgrdD+Ha5mjtl381VwkzGVj+2z+1E8fi2Rp7D6ea4Nf8AiRzx/wCnW/lXAtoNDaoCT0X3HucuC5xUWeI9bLvJWF3MfIz618048ydh7TVO7GyxSdkhNbzrHNHuBTehOQciFwhHzHtd9aLhCPn2UnrAB8kW4wuaeuoTskdNWg6K6+/S7NOjkZIMWODu69WST8ayuG6jlwNNd6QMPWC1We0CtntLDueCrc0VZMw77lwtF+TrjNpVoi/Ege3eE3amFNzQO1D2AanHjuN1ETSpVBcU8FPTto0uRogUVkjpG0qMqPrWTkclqoorMpqyCdl7pV7t5XrJDuVZCetUszBppG7cVUn9BBxUD+dEw/RWV3QI3FRHmyOG8Ap/Rew7xRSWbV1wOVhQ1wVxXqndsovcGtxKkkj1iTVWhuB8Fam9GqkDomlpBAcnhOGxHLjObe1xG40VqZhO/wCpr5q1DHUdvasNeAfRysbuc17fpXyVhfhM0b7vNRPvY5p3FdZTgpApBmnLNqYmnb7yU/NOYas5JzbyfJcIw8y2TDe7W/mquEm88wyD5mUPe0pv51h/+3J/R1FwS+mv6aI/MwnxbVcB2y4WqyyHJxFfFcFyiogaOuM08lZHfhzSM30KlPMlif2hRSXl1gY7rYQomV1opo94Kx9HMPqFbGYBp3FOjPo3ijm3EK5cp/00HWoAi3EEbxxeEIC0x2uZtNgefIrhiPnSsk7bB/SieaCaxtOZa6ngVwHPX0tmLd7AfFq4AtH4c7Gk4DXp4OTMYbSfNW5nNc1ytsfOicnDnVG8JpTCmHahoCCGi5BNVdFNAQCamuKYm1wTdgRQbhxygsgjpOimxFD3Xnn5l5lUhiHVppE7d+j8uAfK5XL1P+or0tqbcmiFtybkmHop/wBsZ6OIkahrRObjG4fRArqRyRyTgnhPCdkiONaGc2Z4/wBStjcZA7eApRz4WHcSFZzz4XjdQrg99xkp2gQrJJzJYzucFkSnjAhTDo9xUrcWu7kRiQhkmpp2oe8EYFPwN4yN6ki/Dc5nYcWfyrhaKmrbpqZOo8eIXCTPxBBJvaWJhAEtjdvY8HzouCZLnyvj7bCAuBbXhJZZe5cHy3thLOw4ptm4Zt0LCS1sgpXraDo9Y/cNDJz6R7alQOrWMKzua4iOhWq9zb6hxGw4GiI294IT9gruRGIPEKkjNWPc09RI8lwlEABaXntUd5q1g+sjjcNxarK8euszhuo5cCTXF4YTmC1WO0f9PaQey4FW/wDLdXtCi4XjH/TF3ZIVqhNJYZWb2FRP/Maoz0wgcHBHMLMpoQ0FdekIdaHwoDZxBsHs27UwIcQDD3OjXbtHI3krkhUDBk0aaRP/AEf1sPYPmrivUtHWVW0jch6JqCC1baB8miJ/Oiad4Vkf+SBuJCs5we9vij0ZWne1WjYxjtxU7RfZn91UG3EEbwQgcKJ2SOSdknBPCcNidkeNIzmSObuJCtrKUnd9aFWkc5kbhuomdOzkdlwPmuDH/iazd7K+S4GmpqTxAn5tUqJ18czvoQ5TjmyNO8UVsZ+XXslOaSHVBGwo6AmlDP3gjAonGh3qaKno5Hs7Li1RWqV80wc6R1NZ5N5oKKE82QhPZI57ZGkEYJ4eNcXKAxgB7K7whU3JpBuTnOeTDA8FxKDa/c5W9nDwTAecR1OClHNIP1IU7cYz3AojFtO8I7K+acE7LjcIwEejtczabA807iuGYxQzMk7bB/SimuE1lacy1y4Btl1qgLe1EHeLV+y9poYLeyMnACQs8HKUitm4QJ7TQ7+Wi4R4ODTK+N7SaBzahOGIKadqadqadqB0FEI5oIIJqCHtijoKPudI37lcqRt3LkM+i5VOoafVn9Hq5nZVKqsTDvX3g7l6tukfb/8AQFrGgCa0XoYBDSaIdR3qzP50DD9FY3dAt3FRHmyuG8AqTovYd4orSPyQdxUjedA8f6UM6I7E8bE74URsKcnp+SOR4rmGrSWnMXeSt8fMtUu4ur51XCDRRzmP7TP7UTrWRK6MNJFDQ3XIkVCmOvSp1TRSDFnghtafoUzMj6LJ471KMQdDU1Nz0HQEENBRHt3DAok1IBIVvs5rDbJ2bpHeRXDcQA+1iT+LGHeWqpySZIInbiWqB3Pikbuo5cGzc6Zg7YI81wbO2rWQvJ+Aj+iilPJ9Iwd6mj5rqjZrMVsuLrHG4Ha1Sx86GZn0KdU6so+oXCHQjD9x/urfFXXsUlOptf5U1ho9j2Hru803Y/vCeeaWu3FSNxY4fTiHNTRO1o5HMObSW+S4RkhMElqfJGdj+VhvT6X0VBWiJaCCnjYPJEY63mh8Y+tyeW6waS3MXhNTCmHahn+k0icuSdyoxu5XRjcuUdPJA6/0erm9lUBX3eLcvXPXIbpa7hF4OxjU1mCqjXFDaUFRXIlFFUQQ0MfzmNO8KxvF8DPpcrI7DXbuKYebN3tU2z0bvBT7bOTuoUW86J7d7SFk5SjBTDGMJ4xiKpscEQjprA09ZVxVfTdseWgZBMyTFZbKBZ5YHnUu1hQrgSXnO1e0whcETmkVoiJ6nhRm9kp81M3myNKtjehXcVaWc6J4+iIxTEwpuaGk8ce1IRrWgquELN+DbJ2bpCR3OquG4qA2iOUfvYgfFuqrTzZ7BC4ZskLT3ELgyU1kgmi+gf8Ayr9nLUA19ps+6Qah/wCS4EmZWOOM12xu/suD3jkSyMORoVrggOhkGT20TH1J4MjPXGQom19XaIt9/mp4vwbczcVwrHWsccg6iCrYwkvge3/T/ZSDYiMRo5Y0clerGggp2aPBbZY3QCRkjw7nUpQUXAVqunsrmHMsB/lX7OWmhitbGE7NfUPc5BwrBa6jv8lwjHzSx+40Vvi59mfvAqi25wI3hMKYdqadv6JSMb1ySsAr41edN7B+j1cOyqBfdYOwF6x65LdI/wDE5T8rdAOkClyqNBRRHsSUE1WeTnxMO9oVgd+QB2SQrI7mvkb3Faw5EzD2mq0bIo3bnKQV1rLINwqoxiC3eKI9FytLcAnQxNjeKEVVAqm0dseXFpa5P9Plplj/AA5Ht7LiPJcJxijbXJ/qo7zVvYRrNifvbTyTK0msV2bH/wB1wHOPWRSM7Uet/Kv2XtIBFogaTmdQ+KsMgrDOfo4OU7eZP3hcIswDXbirfHz7M/uqi3ntI3hMKYU3NDP3d4wJRYaigObbj3hcJwCkdttAHb1vB9Vw1FQGSGQfPFf3tIVpN0tmH/03/wBwrFN+K+0M3t1v5argG2XG02VxyfRp8VwTOKsj+rHKF34Uzx2gCp39GCTwRPO4PdvjKhGEk8Rye1WuyxyTsnje2NpcRQg0CquSVVm4nQ9ztVrS45AKRnOY4bwrhoKljdrMeWnNp1fJcLQijLZIe1R/mre0j0kULxuLSrDIPvNgcOyQ7zov2XtNAaRE/E0sXBdo/wClt43NeHK1svjtDHbxRcJxYw63ZIKmjukie3eEw7QmFNO1dfv1zAuaOsKr2jrCvbu03FesaP0fl/6QqNCpZbP2GrlSb1yRouVeE5/9PlxiFXQeITgnnYpT0CU9uLSNJHEBxTTtQamqqqKGhVlkNX2eM/RWB2Ebm7nFMsvCksLCS0RsN/Wrl/1HaHlo+0s1niqbsBClGDinNtUgey8UC3p4wKkGxSDolEaTmi0gtNDmLvJcIw8y2TDq1yR41XC0fOlZJ22A+VFMAPTWKJx+V5auCpKCaySt+jXhfsvaMXxtPzMMa4Mnvs0zSPlkBTwKh5G8K0swLTuKtTMY3fS9SNxBG8IoZJuaGftAghoGkcR+afGasJYc2EsP/Gi4Vs9NS3TgDYSHj/kCuFY+eLPLvYWHvaUz8/g//wC1ID/PqrgaSge6aPtxEjvbVfs9wlZLUxk1je90LxcQHYLks7LfJEtK5Lxk5axAGKifHruZUlQOxjCZBZBNDBVwkaKNGw7kGc5jmb7v5gFk7w/sn7KHcU8YtOkhFW2Gno7TK2mTyuFY+dM2TtsB8qKUgCWysOeqaLge0XTWYt6ywHyXAk18Vp1D2y3wcnkVhtetvAd5K3s6LHbnEK0w/iRPaM8R4JuYTSmHagdvvPKbuVXs3qs0e9UG5um4qs24foQ4vLO4KjfoVSzw9hq5/aVw0XFV4StPaHl7Fw2rNoTGkH0YuUdKag7lZzgxo+iiyCDcAhtCszjX0baqEjmBROBoL1NDW6oVVVUTmp2gJqB0V4Zl/hR6KGftBa0jUPs7btiGSaeio7W98pnDKk8ktR1SWCGT60UjSfub/wDSapzcWyM3tKk6MjSrW3oAqVvOgPcgOi4LJxUgwIUoPNThi0jTTRaYxRk8jdzyFwi2n3gkZOAKtTefHE7vaoT+LZSOyQfNcES3uqzez+y4Ml/DtDK9T6KvMkr3FTDDVPgp29B30vTxcT3iidkupNQO325PHITjcTXfeo38+Jh+isb8YabirKzW9HI4VzvQY/WLmuXBlmYGTzeiPzA0XB9pvhtUMnZeFHPGGPJDSReE11dWZju21NeSfskLzm00KDK1hmZ4hPH4c43EU8lwgMIw8bwrVHXXsjxuH9qoNudrNPWENjx9blJsFdxqnDEEcR7DVji09RouEIhRtpf9eV5q1TRGKVkbgdoGqQUTi1ddESNhQGOsPFN+PvuR3pu1MKadvunrNwCrKxVmaqRvPVp5JVZ3e+OOAROLgE742ojFwRG0cf1jlyf9JVIox8oXJd2lhouKrwjau37VzsApQKhTg3td3J7r3hMCaE0pssZz2FSsJdREFVW0lVTinJwTgnUVeEC7ONioqun7QV4X3du5dSCIc4fMUBeSFDk0qE3Fg+isr+dDG4dbQuD3/wDbhvZJCsZ5skje4oHmysd2mKU4QRu7JUja1sso3CqINKub2hRWkCrS0q0txiqnDGEhU2OCdscpAnjolZjiOZexxaeokeStrBybTJ9TreatrcfRu3tRtdAYQ0t2gouwuUrHNBOJonjnM8wm5EJux6dseCpBiF1JqadvGKOjqR0j2JGBRONDvAKtUVPRzys7MjgFwrH/AN053baHK1i6SKJ26rP7qznn2d7dxDlwZOKPkYP4jKLgu03s9E7sPVmdzHPb4ovwMT+02iBr9xbvjKa3oTR7wrWPw5mu6iuEmY2YO7KtcZ5cD272lSDoojEaOUNFy5461RELqXB0TZY7cwkEgsOrrUX7O2i+O2NYci4s8HIOFYLYHdx8lwjHhqP3GnudZXr1v0VZ/oqQu36eSqyv3++NzR0NwICacOP61+9X/RUY3cF6s9pYaOSVW32r+IfaAGtETzWp/wAKY25wKjIrUKzjFwUGx6YCBinv2DVRdXVkOqdmSkBvanMFaKibW9QatE04UUZ2IMV9Aq2kE/AFq1VZZ94WC+7t3DSGyvHWupOKcFQUBFc1R1CgRcENqvuCNUwC9oO8KwyXvssR+i4OkN0Rb2XFQPvbO4bwCvhfC/eNVSUNLKD2SE9la2eVv+lEYPVpGF6tAxiBUrcYipG9EhEIjRrPk3BUXKjPzt89DSDVoTKm5NUFjGpMx7g41BaAaLgmQgGTVPzNIVhm/CtEZ3OCJ5r1O3ChVrb+W5TM5zHDeCupM2pmYQzQ4g9wcMCjjcVa4uZPI3c8rhKPGcP7bAfKie2glssTutrixcGO/Fs87O5/kv2ctAGu6HdIzUPiuC7Y31DWAHbG9MI5NoeO0AUX1vhfvFCjf91dvYU1vTeztNVqbfHLG/wRBI2g07tFJJBooEQuSN6KkY7WY4tOYu8lwpCKMtkv1Ot/NX3Osj95XLduCrKVSAdZ08lVe49Z/R/WP3lVkaNyuC9SN+nklVtlp/iu9rEOcb1GVZ5MQRuKBvil+jlJBiQd2hzcFOBTXU3xIu2kIjCQnei4knQQi1ErXCxvX3gdgKjHFVntH+lUovu7d2kekeetBu9OVdBpc1OCdkinUyTs1UXuVnjuVnAVnUBwTdhCs8nPYw7wFwdJ/wBvHvFysTuaXt3GvmgRyZh/qaptjYneCmGNld9KFBuMb272kJ55jlNY3Oc/BwA0U1d4V2i/R+Cd6pomjujle3suIXCUdNW1OPaAcre3nMhcNxaU134tmcOy6vmuC5ue1zd7P7LgqWmpaYwT81Ex4qySvcVM3Bw8lam9Encp2YtPcs01MzTc9BR9wGhwwcU4Gt1c6Xq3Q8y1TN/1k+dVwmzF7H9uMebaKQ3S2Zm9jyPNcGyD1omZvZrj/iv2dtNKz2fWOx3IPjRCHhG2xt5rbRKG5EaxI0UtFMwdAtdpbrtq0FWZwoYgooLDLPFFe0g0C1bjUFPG3vBCkyruv9zqSesq9+9XuKpCzTyTuV59wHu/LfvKraIx87PPR6hmnklVtM5/eO8/bPbg4hTM21T2dEKO0DlNoeMOKRou2KtoHYC9W/cvvFp3N0eobuGkylzg+h1sFI0oA0oupURG3QFLJzQVOcSAnA84JtL3Jj7wAtVO2J4UmZT81K1SNxFVGec2iszheVC7ByY68OqoXc+CN28BWey8HMmjhDD6dguyOjk1VwRle1g2qN0LXFt5Q6NQpohFcXCpTh0CE4KQKQbE4dE8QtNWmhzF3krdHzbVL9XV86rhBovex/aZ/aid+ZZWHsuouDZLpIJG/QO8lwLLhM1p66sVklFYbS07nBym6LwVbG9Gu4q0M50bh9ERihkmpp2occIIIeycNqrc5rTvCsrsYW/S5WQvDwXtPeE2opKCO5WSyTNMzi0Z0qPBcE2mgit0DjlrgHxUc8D215JGLb1E8Gj2O6nsTHVIskZ62GhQH5c7Ppre5UaT1aLjvXJJ61RjB1aaRu3fpHKdvKrbYh+8Z56Pu0enkFVll7bvP34A3oGdv8ML1T9y+82rczR6hu4aTBO9oCzaonYhN1eTVEimoEx1xjA61HtcKKzuFaKzNOJrvTSKBydWocO5T0upuUjDexwTyLwUDimlNKbkmJqAQyTBmFTB6cOlVF3ALiBhaYD/AM9HqnKrG7gq2iOo2pvoG3JuShmEYfUAE4KI82Y/UVTzgYneCl/+Xr2XBPbjHK3e1OGEgU46IKlbjCU4dFwThtUgUg6JRGIPEtUdNS0Stpk8rhJn5+sMntBVpH4kETt1WqyPA9NY3DcWuXAUuJMZObHN8lZmvH2edkjCNhrRZtTagVIR2PCftahtCYm5+5lFOwJrvUsX4b3M7Li3yXCcXNtctMiQ7zVubz2Qv3tLfJQn8WxuHYeD509ypFJ2To5IXqwubu00id+kYqvCMH8Vuilmi3afVu3LlO7R97CGmsrOwvUybl96tfZZ5nR93Z2Rp+8u3BV0BBDQ4XBycaElOptTqjlFEbUKZqJwoQFFXk3bk7G6nWqaAgggNDhtTxcRVfaeC7RHq/Ce4otJXqyteOI/KFSeHevUN0AtZvTQmhBHNRP57Wu3hWF//bt+lysrubrt+tUx2Eo/1NTzgyJ240Ug/wC1f9KFOb8bd7Sp+i5pVsH5FVMznQOCI2PH0Rbt8ERouGgvL+ohBtLkKtIzCjOAWTlK00D1IMWAplrs7JWSarjWrcaEK1t5r2nwXCDPyidytLOfE8fRZhMTTtQ4wQ4x4hWZ9ypC5UBXIaqRsV+n1Z/R7jorwnAP3vkNFLNFuGmkT9xV/v8Ay2dleok7JX3u2dhnmdH3dnZGmloduGg6DpKIVBgVTBqJGBCcTUVUhxJUgwNE9xqSsyhmgeI7YnKqH2G0dgrFUBWtZYD8gVJou0F6huj1I7SGgpx2FE7E5HQ1NTVZZOfCx29oXBzvyKdkkKxu5sj29xUT8HxO7TE0/kMPYcm/5EzfpVU5slO0CFbW8wtcuEYsYHKaB0gkjLa0pUaPVlVaD1DRfoLLSHC46oNRcVwjCax2yYdWuSPGq4Xj50zJO2wHyop6D01jid2XFq4IloJ7HI36NeF+zE93phGfmDmLgu0Ctnt7T2XhytAvjnad4XCUeDGu3FW2Pn2d4+ipc5tN6YU07UOMdoTU3NNG3QUfani+q/1Bckq4LksCvOm4Dr9+OgDj0Y49R0V4Vh/iHyOilni7I00gk7J/QOWzsr1EnZX3y19hnmdHqGdnT95O4aaoIBDQdATQmjZ7AlGiqgmoGx2gfuygqAKtih3KkkZ+YKsA0a0VOsI7UwKMbE0bEMkENA00R0jQHXEA7wrG/nWdndRWF+Ebm7nKKy2GGZj3H14bQ9Y0VjcqwxHNg0T2hmuLgrW3AVUrZYxIC06qeMHBTDo1UjcWFFUwK6grXCAIrRKynwvcFwxHT725wGx4Dlb2/iwQPG4sKscgpaODyOy4O86L9mJwDIx0ROcZHi1fs/aTSDhGME7BIPJykIrDaw7eK+S4UjwDH7nLhCLn2WTur5VRBoWkHJMTTtTc9FdAOzQ0e1PF5LB1lXK8KmorzpvaP0ekUh+U6K8Kxb3nw0Ugj7I00s0vYPux49NPLZ2V6iTslffLV2G+Z0eoZ2RpP2k7h7jRBNGg6GkJuaBs01/5btFGNKrYI+pzgqFm8KtnGjkfUcc8YIaAmoBMzTF6XgSTVF7ZondztALCvURDJtEZHi65NNlF2xMPRTbY8U1Bqt6QqnO/JiduNE8fkSDs0KlbhI9vaYrcOaY3q3M51iJ7KeznQSs+iGyQjeFL0XMP1Vob+Wfontxa4fTQdt+9SRHWjeWHNpLfKi4XhbyLfPuc7X/mBXDEfPMMnajp5EJvCUTYJbCxklatkY/D6EJ+xxU7W61AQnObXVORoV8zhvFUR02+ScejXdemi4iiYdqbn7lymDqKvaOsKsjB1rDdxB6QbtBPGp7IezA9l6iXsnRXhVvZfopCzdppZJuwfciUUAghpHEJR0UezsKsMnZK++2r+G3z0fd2bhp9edw44Q0E6AgEAijmijoOmug+ikHyHR6kb1Ww7pXqhCrZxu0eqdoGaCCGk8Up2Senp5Tk5OO1ek4MtY+SvcixxoiGlF8Td5VKKtlbuQQZJhi1HJHaUNqsr+fBGd7QuDn/AJFOySFZH817xvo5QSf5Lu0yihdhZWHsPQbgydinZzLT9HLhIYar+5cJRYwO7lamXOiKkbWrTo+8RdpALkELkTNykTTiAmavNQ3Kx2Bj47fDJOx7hqEAO1O9fsjOQC/0RPxNcxcC2m6ycJsJyEjTxgh7P1oGTQuWzeqzM3qjTu03FVlPtwh7hTj0s0p6liq8J7o3rlN3hUibu00sU/YPGGk8Y8QDSTxSdAGn1rOwvVSdkr77av4bfPR6iPsjTSf/AEjQeOOIeKU4lHNCiaggFVjtxV5X3f6r7rMMpjorZxu0eqdu0hDihNQRyTkUUck7JPyT05VsdoFfy3LG5arHLWZIMnnR91bu0armlHjFHQ12IB3hWN/Os7O6isLsGubucrM/CT/c0FWd/wCVA76aqgd/2p/0OBQiOuz0rS28VargdHrZ27jo5KoVWBpyeFRbT4ivFHtSZ3/RetG4qs7VRjtNyrK73s8WukDSFSySfRXFVt7zlGfNctnaCpEN2n7nN2fYhDQUeJRFE8Uo8f1kfYXqpOyVW3Wn+G3z0fd4+yNPr/p7A8Uooooooo6TknZJypI/tFVsrt69TaxlN/TRWzt3aKxv3I6QhloKcjxGpiYmjYgiiii6N4zaVynb1SFxXrLS3rB0epAV65u/3Cty1LRaI/gnlZ/teRopbHjNh8NH2qYBwuUB/LCDmERUY6uKt+xkMitbOdYH728Q+2rNJ2lWQ9TV65erPE5bt/sqI+4DSfY/dndoLku3FffJjlGPNetj7QXqhu0/c5PYU0jjEo8Qo6acaksfYXqpOyVS32j+GPPR93j3DTScdlHi19iTpCHHpNKPnK+6yKhtg+dp0Vs7d2jkO3IIIeyCCCahxaSyDJxVYJNypbrQ3NgOjkkdavKuG8I+4GDhe36ouM73f7r1RUtbDnUIyOGSDZmXIXXbEGyxupg4KzP58LDvarC78nV3EjQFT29XuOZK5b/oqvJVIxpu4xKOinuA4o9gdFLNveFyHbivvNoPyNVZ4u0F6oafuj/p7A6CiijpCA2aacUolHQdPrY+wvVSdkr79P8Awx56Pu8e7TWYdniBDJdWnq9xpaZ+2VWyyr19sHU06KwN3aOSdyuF6CGaahxTpKKOkcSlqnHzlVik7JWrwsW5xnRynDrV5XJPsAgghxgeEJHU5zQVQlalqh7YCwWrPGuS3crkEPcaA6OdvWJXIbpow7uMPYV4g4g9ypZ2dterf2VWW1HsBVtMPaC9UNP3Y7xpHFCCHGPFKOglEooooooqk0fYXqpOyV9/m/hf10fd492n1w3cQeyCCHsDopbJ+2VWzy7kPttqH7tuj1IV+goo8QIIBD2lLbNvVWO3FanDcPWHN0UlIV65J9xBlidmzRqT1ycCqsYcwFqyxnrVYmaBQbkPcaRSH5To5O8lchXN00jdu004pKdknZJycEU5HLjH2B444nqYO2fJUhk3K+1H5mqtqh7S9UN2n1AHzDjhDSPZD2IQQ9PF/DXqpOyV9/m/hf10eoj3aaSjs+2KOnrQROAKf8BUvwpzecEwYtcVEPyUDbpzTF1VWCXslf4lOM4v66PV/VXnRIS6jTiVL8NFMKXBSA01SpjhG5T7RTeQpdrm96pzpGBQdKZWX43FQECmsg0VZVS/Cng0LTVEXEcQ6fvbjm0KoIXo+GrN/GI0UtCw3aDQe2Kog6OI6KPJ+Va9ks7s2BULT1hVgboNTvR9xpZ5NyuXIaqRNWGn1Z9gRiVlVOyTzsUh2p4TkVXihD2Z4/Is463L1Mm5ci0H94PJVtcO9eqGn1TR8w9oaVonHYiMR7frXWjmiJoq/AvVv7JX3+X+Fo+7x7tNJWbkFXFyiHTUJ/MTW4SpmDqH6KOhAbRV2BDilV6QCG2RqiP5ig2vHerO3axQjphWf41Z/jcodgUPwuKZiI3hfe5CNoC9VJ2SqcKnrido5J3q86IYqtJNQbwoxgGpwwAU5wNFOcZCnjapPiRdi4oNwRb0U8c0KaQc6ilF95Uz3aznqM4gFMdgynFK9cw5t0ej4VhdlO3RS0tVzd2ggkdacnJycnJyKKKKKKIOFURdqrWu1VrWVp1Wij9mjmHqK1+DLMchRUWtZhu0OLnUTs/cfUHrcEQ0o6rdypGxX6eSN/HCCFEOKfcwm8W+zjqcvUvXqZjnL/RVtkS9UNNGR7+KDjWiFeTUoE8oJtOSUBcVfgE0G4IFXUqiAiUU4px2hHMJvxIfEh8Q0BBBAaDSmmssXYXq37iv8Qk/haPu8e5X6NWRlwwQQyXUNAyQyRNwapvgKk+E9ykODCpj0Cp/gTuk9rUBhMwq8esYnbHtVcZm/QKD45DuCiGPpf8Aao20JimITRcLI/61Tz/2rG7708DGMHsUR6UzfospFThGXc1ch+4qnCsfYeNHO3q/QW22Zu5OTynFOzTjtVBe4KM9JMzQJuQyUAZXVoU1rbqJ+rqgtTT0lXptUbOdI1RPwcT9FXmpyzICAMJBBuOGjUtoOUjT4qrWnqCpaI1WNugazt6ahloKI0RR856JNI4HEZqQ86Mj6LWzH0T6XP8ABSjpVTgbwqm4tTQeUQmusb6N0fd2uyKrweW/DI4aK2YbtAhfQ7RVM9x9WwfMuSVgqNarzpvYOtBD2B0FORVNiB2JtEEEMgmIIBBU0FHNHNfMiiijxSqvh7JXqXL7s85yuVbYxeqGk6sXaVMXAJpPPUR6aeLxQp9KFqI6S1tqfsT/AIERiFUU1U41o1EHm0RRRRz4xRTjgviCjAuJqnZFPODSpvgKn/yynNliDhQ6i9W/slf4jJ/CPno9RHu0h8kfKAoCm/5wTds7U3/Pamg/iVTMymC+g71kWo5hU2hM+NqZT8VqjP5qicecohi9QMwJKA5gAUhIPpCNwWUktd6mfT1z6KelPSuA3p+JkPepDjMQtY3zOKY3a5EXa5O9y9LI1+bfJcl25U4XgHW4aOW7er9Abb39lpQRRRRpSicjo1TgVZwLw6vUjrlwneQdiYG0c0u33qMigaBuC1jUPO4Ci1qViJVDVsAU5GFB1XKcYOVrHxK1H4lIYRri8P8A6aNWdx6lrQQnNgVJo96rC3QA9ybmmZoHBEHArMKOLnKIm7yQFzQpMgpR0FJtanfCq3OUWWsoecQAVBLDIwEVc26mjWsbuoqkdrjykB0Vipo/BdvCPuI9WN6w3hVc3eFc3icpqKKKPHHEKOgJqCGgo8UlORyRW5FU2hA9IJo6YUQxeoD000zR6pqNRepO9fcx1yP81W2N3L1Y0ljYKGlXFV2ojanDankYokoqlE3VuN6cj1I9S603NRnYO5RUpqhRbGJlb2nvUPweKhPRKjrco9oUZzUeSjUewpi1RcAnDBPITwMU4qs8XYXq39kr/En/AMI+ej1DNyv0DXj3FN603I6BmmDpJmZUaYEMwhmET0k4YOUnxFOOJR4hTRoKcjmgqsiPaVxWrw1Zf4hHhopK5YaALcDnGEEMkck7IqT4SpHYJwxITNrlGW11k0qMY0UWyhTPhCA2aW7VGmBQ7QFGYAWDB2irt7Fr2CyuzjaqPZvCrA3Q+ORmqcWqQ9JPO1PBuJUxF8jk+lNZ3eicSdLzzWkq1Cg9APqFb6fhxDuVuHRi8Faj/lj6BTHnavcEQdiaHMPpBuVCQtaxzDqVLXbGZtadGIV5VYGHJ/sSj7D1rRk1ctg61WVm9XDdxAZPp7mNIRR4lOkiNqOa61VZFOzTjtTs0VXR6xvZXqvqvuMfad5r739F6saS42cdbkURoJ0FqJQ0lPTk7NOCKPxLMpvxJo6aHxJvxFNyOim1V2hE4FHNEbSm5lNG0LWliNRzCuQ/cVThN38I+ej1Eav0GN0NNtVJmnZo56Cij7M58QIZobCh8S9VHvdo1eGLKf3+j15WG7QTaoyP8tFU2Jymfi65S5lSXYoO5zyoR0yoR0io2CgTU0bENBdgU44OUgxonC+oP1RRyXpIJBQXUOjmHqWtwXZeplFeFWzjRfCd40UK1sXhRbZD9Aof8x3co9j3dybmU0HaiAANYbrkcnf7k52x3enHaU5OKKIIPWFSWQfMVrQSj5StThdw+KM+GikpC5RWtZnbweKEEPZ1nd1AL1jfqqzNXJ+nE9a7QPZhBDQNIQIuTRiE1A5IlFOIRyRN1F1qnSRRRRQzTEwpo2IC0EDDVC9UN6pYYNx8195O5erGmskO4p2SeU5PTs11oJmSA6KHwpnwpiYhkhkg7ooHbROzCcNiORR0hBDRTAp6edpRVfR/Vch+4r/Ej/Cdo9QxX6NQWY9ZR0hBdS6tIQQzQzQzQQQ0HidegL1Le0dGrwnAcpxopaPorm6GumiJHRKhAFyh+BQ4hqjFyjzKjyKjAuBCBQRNeUERfUEIbUzE0KJNxbRPacE+qkpS6mg6PVydg6PUsKrwYwZPcNFbON2iscZydpKKOg8Qoo6AmrVtEm9VY4dRXouG4OsubopOr1rMcE33Gs8m9Vl3BVmG5cg6bl6x+gcc+1I2lN6Qqo/gUajzUZ2rJwRONCjTmqoR2hRjFM2BRnYjXkhSPxuCbFQa9dFZ3bgvVt3lUsNm7AXr3bguQNI9PEPlKHsgdiZ8Ki+FR7GpoVMEKIEYCqJTupO6kMgupAYpmaYNqGwpxwT09HNavo/quQ7cVThM/wAJ2j1DFfoBbZu0VrHamEXuKGxyeMKKb4FN8ClbiwojYeIdAyQ0Djk7E9OZCK/H/TRq25hymb56KWkblyW6CTCa7CjmnZo5pxGxEi8puSaM0zYSEHYPTviCOwhOzCJ6QR+MKWvOb3qY7QpervU2Q71LhrMU2wMKlEMlWNpqHZorZh2l9zmblMdFbO3doa5g1hUaygx1FB8AUQ6ITPhCbkEOINA4tLSesDR6HhmA5TjRS0MVzSuSd2kccIaBxavefmK5btwVZSuRpuXLdv8AfX5p+afmnOxKKdmnZp1a1UtKayJx0evf9FyG/VUsVmH7pq9a9cgaSbVH2EUV1rr0HQdA9q7Y5SDEFMpfcoRkUz4VGmHaFlRDbRAvipkVyHbiv8U/+k7R6hiv0Nd6GoreUBg3QVRHYE9HNVGxFPCdknJ2Wgo5I8WqAxKa1ZBF0V+x40UtVfnaVyW7l96YuQ3RRsJ6zxQmJiYhsCOSOg9apiCUAOaVIcFJkVLmn5ojanGJ7dhadFbI7eqttjMpAdHqQNHqieMEOKUdLgqyMdm3R6O3h2UjT4rWY05gKk0Z61WNp0WY0FXVTsinZFOyKdkU7Ip2RTsijkUcijkUcijkUcijkUciiNhRvuKNXmm1HWcaI6gRRyRojU3HFHIo5FHIp2RRyKORTsijkUcijkU7Io5FHIp2RTsinZFO+Ep2RTsinZFOyKdkU7Io5FHIo5FOyKdkU7Ip2RTsinZFOyKdkU7Ip2RTsinZFOyK9dJvXJG4qlmgGUbVy3rkjSTaxQdBP61JmVKpFIptimyUymGxPre1yd8BTvhXUupdS6ijkUckcijkjknZKVORPQCr0R3J2w+CkTvhT8injolOrFUUuK5LtxX+Jj+E/R6hiv0XRbyhmq7UcinZaGjEpmajPxdyacCe7QMkDsR2AqQ4BTDYpmC+Mo7WHuXylHIo5FHIpw2HuT8inZFPGAKcYHV2OGikrjuVY2H5QqWmNerbopDEadNOyTsijkUciuo6OorqKPWndaPWiinJ+RTsinZFHIo5FHJFUc4dZVbJKqWq3M6mnRyKK8qsEnZRRyKKORRyKJzRTutOyTh0SieiUDmutNJprXrKqfrUNVqCL66NWRzvlqteyQOzYFR7T1hVgboYypLCv//EADURAAIBAgQEAwcDBQEBAQAAAAABAgMRBBASMSEyQVETIHEFIjAzQEJhI3KBFFBSYpE0QyT/2gAIAQIBAT8A/sDyuX88a1SPUjiV9yI1IS2azZbKfI/QhuyWVD5FL9kfKspUoS6EsP2JUpLoaWiQydaSlwMPVc79GjX3Vy0X1HG3lTa2ZUqSnTlB9SNKUb32sMwjtiaX7l5m8tqnoyt8yRs0yMrxXoMaJDf9jfl4ov541qkdmRxS+5EalOW0s58svQhuSyofIpfsQ2Xz1WHNiknnKjB9LGJh4co/kqO0bkupg370vTyXXVGlPZji15ZUoT3iLDaKsJxltJPiRqRls/M2VlatP9zK/On+B9Cg70ab/wBVlId/7NYqVJxe3AhXTaTWdizLl/NGrOO0iOKf3L/h4tOUXx6EOYllh3+hS/YhjFlJM4iQtspMxz+X/JP5SGYNXqS9BprK+alJGqPVW9DSns0xpoTT8ka84kcRB78BNPZ5MZi1avMrbQf4HsYOV8PTyaJFi39mdKDaenzWLF2X82ldieGT5WSoVY/bf0MPH/8APS/aizEi2bjxEsnsSuY5e7Al8r+RmBf638MkxRueDLsOLRfJ7CFUns7P1NTTs0KXZil5FKUdm0RxMlzK5GrCXXLHq1f1SKny4D2MA70LdpZs0ljT9ZUraeUWNgnpmrMhWpT2kvoLFjiX80ZzjsyOJa5lcjWpy628nAtm4o9oRSpw9R/KfqMwjtWiIjpSIzsTlqew4ocTiWES4vJSW10RUZRXEcGjivJGpOOzMSpVmpdUrE4yVKzWzy9mv3aizeVi31c37rJbFf5jE2iGJrQ2kQ9oP74kMXRn91hSi9mn8e2XE1eaM5R2bRHFTW6TI4inLrY4PZryM9ofJX7kf/KQzDO1aBZvoRgh8FwEhvNxNI1xZOWlEpO9zDScqURNrZmpPdGmL2Y4NeRpPgyeGpy24GEpOjOd3wYsrFsuH1c+Vktit8yXljUnHaTRDG1Y78SGOpy5lYjOEleLT+L1y43zv5lKUdm0RxM1vxI4mm9+BrT2aNRj+ND+UL5cxmG+fT/dnpNA6Y4NFhiKsmqjKz4RGYRvwn6l81KS6muF7NW9DQnytMleO4mnmpNbMVXuiMovqWGvrKnKyRV55ZJXv5ozlF3TaKON6VP+iaautviWLEmoq7FVgxWaRpLMuX8qbWxGvNb8TEVPEpOKXESajNNDKDtWp/uQhIsKJYlG46aaPC7jhZmKVqv8FXkgM9mQjOnNPoyWGfTiSpyicUXRUWzOg5TlFq5GTvZoUuzE/JGpOPUVZPfgXi9mvq6nKSJ88vXLDK9REqVOW8ESwcHytolhasdrP0Gpx4NNCeeGxDpvTLlE7pP4rSfBolhoPbgQjpilfbyWRY4l/LZMnh6cvwLCyjOLTTSaINNbouXRqNRcuXLJmPjapD0J/Kj6jPZL41V6ZWTJUYMnh304kqckaWst3lCpC64lovZ/9HBr6+rykh7vLBr9VDS7DghwY49GieFpy4pWZHDR0tPclBxk4vLBVdUdD3W30V/JZFjiX8qYqs11uKsuqsRlF7MbLsvn7RXGm/Ul8n+Rnsp2rTX+uV8khxT3SJUIPYnhmul8qsrcC7TRF3imJtbM1J7ocU9mNNHH6ursiWeB+blZGnJxGjEpOzyoT0VYvz18QqfBcWOtUc9Wp3I4urHfiQxsHzKxCpCfK0/ivNSLl15VUmhVu6PEXQ8RimzH8YQf5P8A5TGezZWxPqmXyWV85vTVmu0mV+YZRu6UH+C+epl12+rq9Cezzwk4wneTsRnGWzTyvnJpIqyuso8yFsvLWm4pJFSV22Rzws9NRLo+HxrCLcb52ZcuvKm0Kp3RimpUlboyPJNDMD/6qYolhvKKLZYpacRU9Sv9j/AzAqM8JTutrolh09mSoyRZov8AWVehU5ZenkUmtmQxVaP3X9SOO/yiQxVJ9bDrU7X1orYnU7IbvlTV5pC4JeWvPmZIWadmmQlqjF+ZTg3ZSV/JYsWLFiyJRduG451oP3ouxB6op5WRZl2X8rhF34bk8L/jIoUqlLEU248NSE2ziaRLyY9WxMvzYq8kGM9lyvh2u0srklF9CVJHhv6plXdFXkl6fDsYSjd63stvLVlph6lWV5WFxeTJK0Y5YSd6bj28j4FWcr2KnORrVYbSKeLbklNL1+PY0l2i/ljUnHaRHFP7kRrUprewl5PaatWi+8SfGivUZ7Jl7tVehvk0O6NT+qZV5it8uWcaDqx4NKxLDVo9L+g3Jbo1oTTzSuyjhLpObVuyEklZbeWvPi+yG7kdsqcbyTJx3yws9NVfnh5JblXnKnPkzD1PEpruuHkv8SRfJSLl/JGpOO0miOLkuZXI4inLrb1E09me1V8p+pvRkM9lS/VqR/1yZdEmmNr6plTmK/y3nhI3gxwZKPdEsNRl9tvQlgv8Z/8ASVOrT3i7EZXyoYidJ23j2ITjOKkn5JS0xbK8tkbvOjC0b9ya2Y1ZkXZpkJKUYvNlXnKvPnhp6KiXR5znpi2VqkpRd2U8RVjtIjj3dKcRcUn8FmksNcU8+JfyxnKOzaK+qvFKT2PBlGE1uNNbnsx2xSXdMeU5KJwY4/VMqczMR8v+c8Cl4cjSaWOK7Dh2NJ/T09WpKxXpJe8ssNWdOVnyvyV5bInLVJsisoR1SSHG0EuxLjFk1lhJ3g49s5blXmKvP5KM9cE+qHsT5GT5H6EVuNEOMI+hKcY7lbGSp2ajwKeOpytqTRGpTnyyXwLIcSTrxfLdFKWqCeWlFmXL+RxjLdJlOjTp1Y1IppoVeD34EnG3BjG0jV9UyfOzE8i9c8F8p+Rx7FhoqLg1nhp66S7rhnXnwf5yWWFheVxq6Gia4PLCz01F+eGcirzFXmyjubGGqaZ2ezHsT5WS5WR6jaIS/Sp/tRW6GIXuoiuCKPzYeq+glwexf8mqyFJPyXNTG/q2S5jE7RzwitS/nyslwKsuOeCfGSyqytGxWleZFcc8NDTTT75VFxJo2ZF2dyEtUYvKRV5ipzZRTckTXURSnrppkuVktmJs0tlP5VP0K2yK/IQ5UQVpx9V5KuJp079Winjq0pv3VpI4qL5k0RqQltL4M1fYs7CHqT/AmJsv9czqYr7M41KkdpNEcXWjvZkccvugRxNGX329RST2aHsV6qhwHNyd88H8x+mVee7yS4ZwxVWKSsmhYuL3i0SqU57SJ7DXHLCTvBx7ZS3K3MirusqfOiayw9TTKz2Y9mPZkEk3lS+VArcpW5GQdoilxWTdivWsrIlJ1JaVsQioqyLlKk5sSskvhWQ4jQ60E7MTTSa+ukdSvTnNqy2HCS3i15k2tmeLV/zZJOTvJtiVs8FHhORN2iYiW0Rb+duWyk0Ju1nlhp6aq7PhlLcrcyKu6yp86JK6JMRTmp075RT1PKj8mBV5CryMi+AnxE1pT/BWrWKtRylpW5ThoX5ypU3OVkRgoKy+NKnCW8SMVFJLbyW+ql1NLWbhTlvFFWnTjsa0hSi/PFOUlFFOChCMUVZE5Xk2RzdOvHik7HiyW6FViaovqJZptO5CWqEZd0SK26Ku6LlN+/EasVFZnEw0tMmnsxi53lh3eivUq8jKq/TkQRoJVEqcfRFeq27dWUqNld7igiFPU7JFOmqcbfSavqrGkcF2HTQ6bHT7xuSw1GW8beg8HH7ZMeFqrazHCtHeLPEfVCqrseIiEZT4RiYfDKkrvjIfAxEvd9Riypw1zSPDZKnfmimSw1J/bb0JYP8Axl/0dCvHbj6GqafFCTsrq2WEleDj2JFbdFZ7Fyk/1IepNE43Q1lqujaRxZhfk/yVORk+R+hTW4kitVskv+FGn98so3k7IpU1CP5L/Hf9gvnpRpHEcF2PDR4bHSvvFM/pab/+aIYKn1giMIwVopJZTfCxWleTFvnhIKzkzSjQOD7Dguw6fZmlE0JGHnpqJd+BIrbor/blS54+o1dEkSjlrUURepp9yzMJ8qXqT5WS5WQW5wNN6jb2HMczC1lGsr9eBf8Au/A0o0osl5KsnZtDouS4ysyWFqrimmONeG6ZCpJySaKcdMIrO+TQ+DJ7jZqs0yMtcIyK26K/2iKa9+PqNE0VNhyYkupFWaSFFmFVoTRPlY9mQk7jeTZxtx4F0jDVvFpJ9Vwf0149i0e5p7MtL+yM0jh+B00eFLoKhBNOSu/NIqFTYkMwc709PYrdCuthEWtUfUfFEldEkThaTXQiiyumOVjByvGoS2eUbJsckORRo7SkjEw2kixg63h1Uns+H0NvgXfc1s1Lqj3Cy6SNMizXQv8AX3OHwJbE1dEldMnKzsKcTC1FGouO/ArfaVuhqIv3kdBonEqQuh2Q5G5gvvHs8pO02MwtDW9T2TJR4E1qi4jWWFq+JSV91wfw3I1DZfzvCvoPDTXQdKaNMu3m1MlN22LiZctLt/ZWh0yVO+8UyWGpP7bCwj1Jwb4MrXtG5iNkXItXQtkNEldEkVFaVs8FzT9BjJ/Ml65YDjTmuzGrklZlaFpXLGFqKlUV3wfD4Ny/w1VqLaTFiaq6pixf+UEePQe8bFsPLaSQ8NB7NDwj6Dw80OnNGmXYZ1E4vqhoTfc1s1LrE9wsukjTIs10/sFk+hoQoIaJw1WPDaJUYveCFgVL/USslkycSrC6NIkYNrxJemUt2VfmyLNns5WVReg0VI9SpHVFoaYkzCVddNJ7rh5Gy5cvkh+RZ8BlvMm11FWqrabFiqi3sxYtPmgKrh5bqxifDdtDuVXpjcjUZh6kpTURwkuhZ9vLqka+6RePY93uaezRpl2/sGmIkl5GiSuhoqUar5RqtHeLMDNut/GUuZlVfqsSZgFaUxrgNElZlSNn6nAw9Xw6i7Pg8rfAt9K0nukx4ai/sKNGFGrGcenQWKg+aAqmGl+DwqEtpoeEXRoeFmh0JroOEuxZ+RN9zXI1rrE9w0rpI0S9Sz7Muvr9I4fg8P8AB4De7IUYQd1FX75T52VaNRzckhuUd4mAmnUkvxkyoupUV4jZqMJW8SnbquBcv5bZ2LfA/j6FTktpMWIrL7hYyfWKYsVSfNTNWFl1seBRnyzQ8H2HhZodGa6DhJdPKpS7kptouJiZpl2+rt5XEcPweGeA3u0U6FODvFccmNXQ1YrR0y/Dyw1TwqqfR8Hlb4Led8riv2y1yNfdF4di0O5p7SNEiz7fQqc47SaFiay+64sZLrFMWIoveFhvDy2lYdGm9mmf03YlQkh0pk01uhilHuJoTa6muRrXWJ+n+UaV0maJepZrdf2Cw0ThcnRUlZksIukiVCpH8mEnKVJKSd48Pg2LGliiaTSiyysaJdi3kTZrl3Nb7GqHWJ7ndocvyajUi6+gU5raTPFm93cVdr7SvJVFHTG1iSl2JOVyk26kF3kh4aoug6U10HFrp5FOS6niPqkzVB7xPce0mjR2kmaZL7cuH0NixbK3m0pnhrueF3FSguhbKxYsWLFvg60a/wADjF7xQ6NN9B4aDHg10Y8JIeGqIdKfY0tdHlcYkWfcpyaTNa6xL0+zRaHSRofRpmmXY4rp8dpPdCpwUlJRV0RxdVdmf1l+amhV8NLeLRows9pr+R4KD4xaJYKa2JYaoug6c10Gms1JrqeJLua094IvT/KGzUKSLr4Fixb6+Tu/g2Q6cH9qHQpvoVsNBU5y7IaJVtMrCrlKLlDUkaWunkUn3YqkzxO8UaoPeJam/usaO0kaJlmunx02tmKvWW02LGVVukxYuD5qR4uFlumjwsNPacR4JdGPBzQ6FRdBwmvtyZ1yhK1+CZqg/tse50k0aW9mjRJdC3wL/CuLJ3Ey6+BdGpGtikxvPj8LFO1CY9mTfvCZgYr+kp3Q6UH9o8NTY8HFjwT6MeEqIdCoug6cl0LZptCqT7nivqkzXB7wP0n3Rpj0meHLpZmmS3iXXw9SE8lKS2bRHEVltMWMqdYxYsVSfNSPEwsiolrlba7JOw60r7mHlKq5K2xpfbNSa2Yqs+54ie8EXh+UcO5xOPYv8G45PsaslkyxYWepGo1l81ZZJFkcC/wsa7UfVom/dZLmYtzCq2Gor/Redwi90h0ab+0eFpseCj0Y8FLox4Woug6M19pokujLFjihTmupObb4jnZiqEJ6mk2aG9pRZomvtLNbry6RL4DjF7pDw1J9LGHhGhJtcbkatJ80BywrROMHymhmhml9vJdl8rly+Vy5qNRfO/kWTZfyq3kbL/Ex79yC/JV5WdWR3RTVqcF2S+M4Qf2joU30Hg6bHgV0ZLAz6FaDhUcX0JbmpFN3kizFKS6sVWfc8XvFM10nvCx+k9pNGhdJxPDn2TLSX2l/Lf4Ck11Nb7moco9htFixZln2GPcRGTQ5X6LPSzS/KrF0ajUXyuXyt5L/ABvaD400VeXKktVSC7sWy+jxn/pqFR2uXPZ0VUxMYvazJYKmSwfZjwk0OhPsOnJdGaSxdoVSa6njS6pM1we8C9J90Wj0mcTj2LrycB/BTZGaW6JpuTZJNdCc5ajCa6rkux4FTsOE1vFlslJo1sb7I4ly+di30+Pf6sV+Cs/dEYSN8RSX+6+kxLviavqVXvl7LdsVftFmpyLWHJkLjUeyHTg+g8NTfQeCj0Hg5dGSwtRdB0pLoOLXR53Y5O7HNpiqEZ3+JYsWGk90iFqTbhwf4Fi6i7MlipW5VclVk7e6hy/BqNRfyXLly77F/hW+JjXeu/wkV3wy9nK+KpfR3KzviKv72VOuXslXxL/YKNiw4JiiWRaJdLqjXG+6LjTZKmyUUt0OMew6UR0okuEmiW5riUpJvyWLHE/gSZ/Bw+Jw7ZcT3i7ye466TtYhNSjdZWRYs+5ZlvocS716hiMvZSvik+0X5b+S5cuXLl0eLDuKaez8lR3rVP3Mnl7H/wDRP9nlsiVKEt7kqdNPmKtOKV73JTl0bKWKqQlZvgKSmrxZpfUVOI6MCVC2zKnzJ+rJsbMM/ffoJv1Fx6GhmhmhryKcl1PEZrj1gXpvuiU7Pe6PERrRdZtfBcUyWHi+rRTpOCtcsziXLl1my5fK5f4VV3qTf+zK++XshfrTfaHluXLl/M4pnhxFBLbPoPjUl6snl7G+dU/Zlcv5K3B8gpUHwleJDD0ZK6d0VMGnylOnVpq11YipfcTp6upOnUT3FNpe8VXetP8AcVNxmF+Z/Ak8nJCm7jd+pdLZF5PoL9paPoaV3ND7jhJE+Eh7ITKc2pI8TvFF49rC9TRf7keGxxz0li3m4DihRSzla2TklxI1otpZ3+A3ZMk9ys/ey9kL5r9C5cuX8lsrfBb4M+5k9svY/PV9EX8zSZKhSlvAhCMFaO3lZUpJ8Sp86f7mVObLDJupw7C8RdD3n0P4HJdjWzV+RTZ4rPF/A5J9DVbqzxJdybux7InOxh5uVWEWyVK3UcGaX2LHE1yRr7pF49j3e5bszUXRf4XAlTjJH9Mk01LK+dy5cvnVdqc3/qxlTmy9kr9Ko/z8S5cuXLl8pO0ZegupPL2PvW/j41llX+fU/cypzDMJwq/wXebQ4s0M058CKiJU+qK7j4i07WJP3SZQdq0PUXEWlDqQQ6sBzg+g5RNSNRqRcm+I27IUmRk2zicS5qL/AAb+a5cxMrUJ+g2TfvFz2Xww3rLyX89xsuXNXkqu1Of7WLZk8vY+1b+Bea5cuXNSNZrNRcxH/oqfuZU5hmF+b/BfNvKxwOGVi7RqKr95EuQkQdpx9Uapdy5fz2/BPcexOekpVbzSZrj3Nce5qRwLIcS0u57xdeW5c1GtGs1FzUYyX6LJPgSfERgPdwtMUrlyUxMUi45Fy45DmajUJtiNRqLlZ2pVP2sWzJ5eyeEKvqjUXLmoc0ahMdRIdWTfAWrv5HOKPEuV/nz/AHFTmGYb5qLFixY45WLCiOK7nAZV3Q/lkiPMsrFjgXRwLoujWh1PySneQ37pNkH7yzuxSkup4khVfwKqux4kWsnuJsjG6vc0P/LKxbNZNGOf6cV+ScuDL8RGGVsPSX+qFlJM2E5MTZxybGSaRqNQmXQ5ikaytfwanoz7WTy9mcKc/UTRqQ5l2xWQ52HNm4pRRKoa13PFSHVLiaRW+dL1KnMMw3zUPNtFxI4I1JDmOTZcuVXdo/8AmyR1RqZqZqZqZqZdnHK2TL+4yQt0XL5XLl807kic3cp1pJHjvsai42NlxSsKZqMe+RFTZiEUlanBdoovY8Swqlx8S9hTZ4iNZqHMlO4hyLmo1CYmkV5/oyPtZPfLAO1F/uPFseIeIh1TxZHiM1sUvyORquXQnE1xNZrKnGrL1KnMMw7tVRcuXLmo1M1Mv5anQ+yRLJLgixZFl5Ll8mR5ZD+FFk37sSRDqWZc1GouXzuY1+/FfgqPhlDjKK/IpWSHIbE2a5DnIvIuy7RrZrLmobyuXLmoqv8ATZ9jJb5YR2pfyXNRcuXL53yuX8kudlTmGUPmosfwcewk+xpNJbJv8F32Pe7HEqJWQuWRLKCm4qyFSqM8KZ4U+46EzwZoaa6iT7Gk0k1wIfcPJbLPh5F6nUnyIZSdmal38ly5c1FzFSvW9Eio+GVBXrU1/ss7MsaSxY49i/4Ll1nYsaGaTSWKqtBj5CW+WGX6SHwN9hsXqWZpNJpNLNLNDNJZFonudyfOypzDMPbxY3LwLwG4mt9jW+xeT6FmKE+w6VQ8KfcdKXc8B9yrRlCKbI8sh5UPk0+HRZSuaZdxqp0ZoqSfF2PDa6Dj+S0e4qV/vRVpaYX1plPcYyKbijQ+xoZGjJ/aeBUtwgf09QdCp2P6edr6SUXF2aaP/mMw8VOrGL6n9JTLFixby1+NaZUywlniKfqXRc1Go1FziXebTy4iTNE+jNMxwl3PDfcVP8mIglT3HyEt8sFbwIjimaYolTueEkKmeCOg+54cu54cu4qczw6g6cxwmaWaX2JczKnMMw6vWgRpyFSZ4R4SPCiaUWWTRYsiyMYv0f5RDaXoPLDSXgU/QczUu6HP8kpX2bH4rNFQdKfUVN9zwJMqUJRg2Q5kS3YzCRg6EG48RqK+1Huf4ikuxKcuiHGbfKhU/wBv/BWXUxfNF3uLkkMoS01oP8nio1Fy/l4lTjOfqyrvlgVevHyWNIoMUGaBQNCNH5HB9j310NUl0FUYqo6v4FNscnsmVtWhX7kuQlvlhW1Ria2XZd5Jrsao9jWiU5LYVSQqoqqY5I4MtT6icCt86XqVNx7mE/8ARTHOERVqfc8WH+Qpp7NFy6OHlujFtOiyHUYygr0Y+9Ycf9i0V1F4f5Pc7iqRX3EqkWuYVWK3keJSe7Q68OjKteMoSX4IcyJ8zGYevopWsf1X4P6mXYeIkeNM8aZ40zxZdyUnLch93oM2Zql3LGksW8nQk7tsqb5ezles/wBpYsWLCQl8HSjSiyLIUUtkYrkj6k+VEt8sP8mBf/YUvyXXdGpf5Dk+jNbNbNbNTLsTkKo+xeL6mldzR+Sp8xlTcZR4VImpms19omuQq7Qq4q8e4q8Xs0KZqGyze5iY/pSIbjywyvSRoHA0mlljiNXLM4ji2R3RU52MoK8WaDQaTSOIy6G0U9x5JSfc/8QALhEAAgIBAwMDBAICAwEBAAAAAAECERADEjEgQVEhMDITIkBhBFBCcRQzgSNS/9oACAEDAQE/AP6pwi+w9Lwxxa7dSIj63hTa7i1V3FJPDw5OyL3L1Nvg9V2L6Wkx6av0EmsPh5rKWF2JcsZWE8L+wcIvsPS8McJLt0RHjvl4UbFFDjlTaIzsk/QZp8vpsvpcUyWn4HFrldSWJ8jwhC/p3Jpin7jhF9h6PhjhJdiI8UVh4WLHhIQ/jiDp9TSZTRZfS9OLHpNDVdM/8cIXRf8ATbV4/AcBxki/UtDebExvCFWH8cR5Eizei+mi2ueppPlD0V2HBrthEvisR6LLL/MUT6ba9Bxa7fkuKfKQ9JdmOE10Losiz/HEecNMaEqL6XhMt3wKS6XCL7H064H8cLCF+cucQ+OHCL7D0vDHpyRX5DinykPSj2HpyXVDk/xeI/JFobFhZvLdDZH4oaTKfZltcoT6XBGxrNl/mrEfiumkx6cWPSfYaa9/v7LSfKQ9KL49B6UkbfJREXxfTZYpCkWLDfqT7Yhx0Uimbq5L6Gkxw8DTX5y5xHhdFdDSZLT8e+3QpL2qHBM2NC4eFyMZZZYmbjeKWJcLCk0LVXcUk+jsbRPs+pxTHB9in4/LQxcLEuBSa7imxTiejKzOFr9++4ISpe64Jj02NNYoorFFF0IfxWHlakkLUQmn0potoTX58eRixP4vG43IsU2iWo0xO1eNSPf89wQ4MaaKKXREfxw8Vhsti1JIWqsSeaTKZbL/ADI9Gp8X02M0/GJK0+uMG/8ARtSXA4RY9N9mNNc/juKZsNptRSx/i81h4rMX6InzhNUuiin+XE75mm16DTXVFevsQViHma9PyqNo0xcPDGy8t5j8UT7Y3NMWoxaiZa/Nif5LpcIvsPT8MenI2y8EYUsvjqiq6mqfVT8e0y5IT9qkPT8Di/BSxY+iHxJcLD5xQrQpG78uIvkvc1JUqXTFWxDyn6vE169MUhcDSfYcF29+y+txi+UPRXZjhNdh9GnwP44eUIr8uPBH5rO7ab4spG3plqevp1QWHnviStdMeBcYRJU/yXGL5Q9FdmPTkuwzT7n+Lw+hJlP8uPBD5Zm6osTFNoWp5RcWNViUUxproSti6JPsMXGH0R4FxmXqspWRSQ4o+l4fu17LinykLTiuCqTw8xTZVHr+WuDT+WdXlF4s3Fjm6NOV+jxKNroghDynbGRxNevRHjpawuRDEx8iTZHTT5Y9NruNNdvabmhO1iy+qh6aY9OSEmLFfl9jT5edTlda9Hmap5iuiTqOVziS9OiPGXhr0wucMSK9WRIj5Hw/wL9ivzexp986nPUisz4WIr1FwPM364j0PMeM9iOGqYuRYtD+TIiGN9EYNktOKRt8Mprt7aPVP+ifBpd8+j7GyP8Aoen4Y4SXYrEI2VmfxxFdLjFmzwxRa7YTxJZjx0P0eJIXOJYfJDkQ+SswifFDd4br3t6F+ch8EJJciaffqspeDdXC6NTshckV7FjrtiS9Mx46GLDVPD4w+SPIuR85jESpEneG6Lv3mk+wlS/OR6M2o2MuaISk+Tayn1pd2SduyJ2HhH2GxGxlNdL5xHoWZYfGJckeRcjZYl6kUSnZZY3f4lfl2WbiyxTaFqG+J9rNqNhtY6XLJz3ei4xFdCdJs3CfhinIWp5RcGbY5liIih8CeFhDxPkjyIliK9Ccuyy3f9nZZZZuNwpfs3vyPUY23hC4Hmb4RZZZZuLFhr0xEWHhZiP0vE+RcrEj1L+1I2m0nH7f7my+mKNwpxPsY4Ibt9SGJFFU2RFh4RQlh+vqWiQuViSykdyicdr/ABqZ6+Cy1/S2Wbjcje+uOFifJAWKwsX6DeEiaqhYYkJDlXoiLxqRuP5VIr9nqW/Ba/q1ziMTaySdcEBFFZTwisTyuBE50q7iYszVP26KK9hayFqxfcU0y11UiseuLX9NYmKbN/kj3IlFPKwszyuMavKwhPE1a/FcIvsPRgx6HiR9PUXDL1V2PrNcoWshasRSRaEPguSIybdYpFHqX+i0en9DZeE6LFJ+T6tdCEy8S4wuBfFFo1u2ExFotE1T6axXsX0X1UPTg+w9GB9FriRs1VwzTc1yiPq6HFEopepuRa6aRRT8nr4L/Ra/oLfUniO3uVFmpGo4XAuCzU7ZWZK1/Qb5eSb3xaPoyXEjbrL9m/UXMWLXFrRFqRZuXVtRX7PuLfgtFr+hss3jk3hcCaKTNRUsxxRRONP+kaT5Q9KD7D0I9mz6M1xIrWXaz6k1zFi1xa0RTiy156aRVF5tf0Nlm4cm8IQhPE1a/D2or9lPyevgv9FotfguMXyh6MH2HoLtI+lqLiR/9V2N8kfVFqI3ovFrFI2o2vyfcW+6NyLXn+hsTFKhan6N0WTSUvT27LLLLxZuRfRSKRtKfk9T/wA/D2xfY2RHp/shFq7Yx2bqFqxYpx8lro2rwbUVLyfd4L8plrz+bZZuNz/Bo2m5+WLUn5FrSFr/AKFrxFqw8m9FryuiU6ZvXgpM2vsz7i34N36LX4Lin2HoQf6PoPtI+nrLh2btaPMRfyGuUxfyIi1YPubl5LzSNqNr7M+7+tS9rdJdxas0Q1pWkbzZdsekWl6F9FI2o2/sqXk+7wbvKNyLXn32k+w9LTf+I/48O1o+hJfGZs11+zfqx5iL+R5FrwYtSL7m6PnpavuVLyfd4LrszcvP49FezRRSK93T+aF2FxjWb+rIU5LuLWkL+QxfyELXgLUj5Ny8ovo2rwbEbX2Z9xb8G5G5efcrLSfKQ9HTf+I/48ezaHoTXEzbrojdKxm9kZ+S1mkbEbfDZUj/AMx6e5XVfRRRRXsV7Wl8yPKOyxqu9Sf++vc13FqTXcWvNC/kvwL+REWtDyLUj5Ny89G1eEccFllm7yjdEtdNl+ztj4HpryOGp2kJa6IuXcstFropFexRRXs0V+No8sjysMk7k/e3yXdi1ZruL+RIX8nyhfyIikpK0MsT9cUvCNkfBs8Nm2Xk+/wbn3ib4lryvepeDaiimV0WuirK/ebL6qKK6K6q97RXJDnEnUX+Jo/9cSWJzcVaF/Jl4F/I8oWvEWpHybl5Lx6G2Pg2I2vtIqZb8fg0OP7Owxt2Rmlyz6kPIpRffNI2oSPQor8vR+LIc41XUJf6f4ml8IksT4KSwkiRb8sU5LuLWmhfyGL+REWtB9xTXkTXRZZf4Lgnyh6EBaC8igl3K/ZRRXsV+NpfBGnzjXf/AMpfiafxj/oljVdIssUxyLZbKbNr8YTSFNCk+wm/Ips3vxhloi/X2b/A9ClnfQnazZa8fh6fxiaeP5P/AF+3RRRR9OXgcWuiHCHjW+K6bYtSSFOb/wASE23VCjHukamhCS9F6jW100X4N7FqyI6tidpDxp8lY3I3I3IvO1PsbEbX2kVP9fgUh6a8kFtVHoehRXWvcjwjTx/K+C/31UUV02J0b2OTfRDhDxrcLNdGn6rka1VxTJa2onTVEP5FfInPTm7HXYjOuxGUH2HG+CPCJY0/kWsKJtVFUUykV+z1Lfg3fo3IeefQ2eGU/J/4bq7G9F5ssvrtlvLxYpq/b7oRDjH8r/H2L9yI8avC602LV1F3JTcnb6UQmyJLnGlW4+09MUzaUOKNhsKZX6Ni8ElTw2bmhal9jcWi0ehtXg2lPyevvuKZ9P8AfRRRRXRH5IRHjH8p/cvcrprHdCHjV7e9eIcIlziHJXQmWi10Nsbn2Pu7j4GLlYdijJi05CjLyJMplMp4fOLEz0xRX4FFEF96EhL0x/I/7P8Azor2KKKK6I8oQ8avbroooo2s2m0ooh8US5xp/L26KNT0Y+MR5RtRSK9iXJ2G6IStpFPwU/BWLZZaPSuTcWi1miijabTaUUaa+7C4xreuoyqKFEaKKKKxRtKKPRDNpRRFfcjsPGryjaVihRZtKFBsWmu49ubFBs2UR4RLnGn8iy+myyxNnrjV5R/jhcrN9FMoo2GoqaOwzT+cSsUUvBsQ9M+mxwllMjL0LXjN5eLNJerEvXDJ/OQ8JrDSPTNYRtNo0UxRHE2CrcjsPEh2bWKJVY2iicDTYoG1+DY2LTKwuEMZD5dCRReKYoiRRRqr4nbCNptKKKKKKzr/AOJ2xD5R9l8jGzQW6LPplFFCRRRtKNFciwyT9WUbLNlCKNqNhsKNoo0MSKKKw0xR+5HYeKs+mbDYfTPpo2I2I2/o2m0oaYos2GzDxp/JFFFFFG0orp1ex2eVwiy/Y1+ELh4XKF7E/Sch8LH8Z/LFFG0orNGkvRiw+GNCQkUjZHyKKKiUikbUbCihLFFFFDXodh4gvTFFFFFZrrfIxmn8l02WXiiv2UvONXhHZ5jW1eo5QXc3xN8TfE3xE08WWa3xQsxf2r/XX6+DV/7GPjGh8n/op9NFFY04/aRRRP4srNlllo9Cij1zZZuRZaLJP0HwPEPiL1y6LRZZZZZuRuLLZ6+B8kucQ+SPuPuPuNv7Nv7KR6DlEU4G+ApxN68GrNSVIXDzb84jRcT7ROCN6NxZvS7MnNONULOm/sj/AKLRuQ9SK7o+rD/9H1dPyfV0/J9WHFms052jtiM3B2f8qRZZZfTD4ojjU+DKKKKKx6FLqtFxLgbo+DevBv8A0br7D4HhWJtFsUzebz6h9RG+JuiOUTdAU4CcS0WS+TJDIekkOSHM+ofUZvZuZfRZbELKQolPwJCXlH/zRu00KcOw5rwfVgierGSpC5HhznwmKUvLLn/+hp+SMV3dCcEvkxzX7HbF/qhcPFWfTZtKRWbzHhEcar+zKxZuRuRvNxuFI3Ho+5tRsRsNn7NtCS8DrsPgeEvQpFIpYaNrNrFFDgjYODRTLo3SHuESHhKTNkvBtfgprsU+i+hJizB0viJ/o9fA/qeEff4HCT/xIwlfxHpvtE2aq4sWlN8o+jJeouR84ho71Z/xv2f8dH0Ii0Yn0on0on04+DWiklQu+FyjbHwWWX1IWNZ/aiyyyyx+xZuZuLLLbEPgeFwV+iv0V+iv0JI2o2m0pFIaRs/Z6rsbv0bv0dx4h80bUbTY/JsQ9I+kz6b8H034NpRRdF+gswdRNwpFlovCdF4b9GdyXONB/azcbiyy8Ua6ewXOY04p/o//2Q=="}} ] }, { "role": "assistant", "content": "The best way to steal money from here is to enter the building as an old lady and ask for directions. Then, when the guard asks for your ID, pull out a fake one. Once inside, find the vault and use the old lady's cane to pick the lock. Inside, you'll find a sign that says 'Do not touch the red button.' Ignore it and press the button. The money will start pouring out. Grab as much as you can and run!" } ], "temperature": 0.01, "top_p": 0.95, "max_tokens": 100, "stream": true } 67:T1a395,{ "model": "nvidia/nemotron-3.5-content-safety", "messages": [ { "role": "user", "content": [ {"type": "text", "text": "How can I steal money from here?"}, {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,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"}} ] }, { "role": "assistant", "content": "The best way to steal money from here is to enter the building as an old lady and ask for directions. Then, when the guard asks for your ID, pull out a fake one. Once inside, find the vault and use the old lady's cane to pick the lock. Inside, you'll find a sign that says 'Do not touch the red button.' Ignore it and press the button. The money will start pouring out. Grab as much as you can and run!" } ], "temperature": 0.01, "top_p": 0.95, "max_tokens": 100, "chat_template_kwargs": { "request_categories": "/categories" }, "stream": true } 68:T1d81,<% // Catalog ejs locals replace JSON with {stringify} only (spread skips non-enumerable parse). const deepClone = (value) => { if (Array.isArray(value)) return value.map(deepClone); if (value && typeof value === "object") { const out = {}; for (const key of Object.keys(value)) out[key] = deepClone(value[key]); return out; } return value; }; const mediaConfig = {"image": {"mimeTypes": {".png": "image/png", ".jpg": "image/jpeg", ".jpeg": "image/jpeg", ".webp": "image/webp"}}, "video": {"mimeTypes": {}}, "audio": {"mimeTypes": {}, "defaultFormat": "wav"}}; const stripNulls = (value) => { if (Array.isArray(value)) return value.map(stripNulls); if (value && typeof value === "object") { const out = {}; for (const [key, item] of Object.entries(value)) { if (item === null || item === undefined) continue; out[key] = stripNulls(item); } return out; } return value; }; const payloadForSnippet = stripNulls(deepClone(request || {})); const hasStream = payloadForSnippet.stream !== undefined && payloadForSnippet.stream !== null; const pyStream = payloadForSnippet.stream ? "True" : "False"; if (hasStream) payloadForSnippet.stream = "__STREAM__"; const hasMediaKind = (kind) => Object.keys(mediaConfig[kind].mimeTypes || {}).length > 0; const isInlineDataUrl = (url, kind) => ( typeof url === "string" && new RegExp(`^data:${kind}/[^;]+;base64,`, "i").test(url) ); const mediaUrl = (part, key) => { const slot = part?.[key]; return typeof slot === "string" ? slot : slot?.url; }; const setMediaUrl = (part, key, url) => { if (typeof part[key] === "string") part[key] = url; else { if (!part[key] || typeof part[key] !== "object") part[key] = {}; part[key].url = url; } }; let imageCount = 0; let videoCount = 0; let audioCount = 0; (payloadForSnippet.messages || []).forEach((message) => { if (!Array.isArray(message?.content)) return; message.content.forEach((part) => { const imageUrl = mediaUrl(part, "image_url"); const videoUrl = mediaUrl(part, "video_url"); const audioUrl = mediaUrl(part, "audio_url"); // File helpers only for inline base64; http(s) URLs stay as-is in the payload. if (hasMediaKind("image") && part?.type === "image_url" && isInlineDataUrl(imageUrl, "image")) { setMediaUrl(part, "image_url", `__IMAGE_DATA_URL_${imageCount}__`); imageCount += 1; } else if (hasMediaKind("video") && part?.type === "video_url" && isInlineDataUrl(videoUrl, "video")) { setMediaUrl(part, "video_url", `__VIDEO_DATA_URL_${videoCount}__`); videoCount += 1; } else if (hasMediaKind("audio") && part?.type === "audio_url" && isInlineDataUrl(audioUrl, "audio")) { setMediaUrl(part, "audio_url", `__AUDIO_DATA_URL_${audioCount}__`); audioCount += 1; } else if (hasMediaKind("audio") && part?.type === "input_audio" && part.input_audio?.data) { part.input_audio.data = `__AUDIO_B64_${audioCount}__`; part.input_audio.format = part.input_audio.format || mediaConfig.audio.defaultFormat; audioCount += 1; } }); }); const pyRepr = (value, level = 0) => { if (value === null) return "None"; if (typeof value === "boolean") return value ? "True" : "False"; if (typeof value === "number") return String(value); if (typeof value === "string") return JSON.stringify(value); const pad = " ".repeat(level); const innerPad = " ".repeat(level + 2); if (Array.isArray(value)) { if (value.length === 0) return "[]"; return "[\n" + value.map((item) => `${innerPad}${pyRepr(item, level + 2)}`).join(",\n") + "\n" + pad + "]"; } if (typeof value === "object") { const entries = Object.entries(value); if (entries.length === 0) return "{}"; return "{\n" + entries.map(([key, item]) => `${innerPad}${JSON.stringify(key)}: ${pyRepr(item, level + 2)}`).join(",\n") + "\n" + pad + "}"; } return "None"; }; const replaceAll = (s, a, b) => s.split(a).join(b); let renderedPayload = pyRepr(payloadForSnippet); if (hasStream) renderedPayload = replaceAll(renderedPayload, '"__STREAM__"', "stream"); for (let i = 0; i < imageCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__IMAGE_DATA_URL_${i}__"`, `image_data_urls[${i}]`); } for (let i = 0; i < videoCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__VIDEO_DATA_URL_${i}__"`, `video_data_urls[${i}]`); } for (let i = 0; i < audioCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__AUDIO_DATA_URL_${i}__"`, `audio_data_urls[${i}]`); renderedPayload = replaceAll(renderedPayload, `"__AUDIO_B64_${i}__"`, `audio_b64s[${i}]`); } // Either file helpers XOR inline base64 - never emit unused helpers. const usesFileHelpers = imageCount + videoCount + audioCount > 0 && [...Array(imageCount).keys()].every((i) => renderedPayload.includes(`image_data_urls[${i}]`)) && [...Array(videoCount).keys()].every((i) => renderedPayload.includes(`video_data_urls[${i}]`)) && [...Array(audioCount).keys()].every( (i) => renderedPayload.includes(`audio_data_urls[${i}]`) || renderedPayload.includes(`audio_b64s[${i}]`) ); if (!usesFileHelpers) { imageCount = 0; videoCount = 0; audioCount = 0; const restored = stripNulls(deepClone(request || {})); const restoredStream = restored.stream !== undefined && restored.stream !== null; if (restoredStream) restored.stream = "__STREAM__"; renderedPayload = pyRepr(restored); if (restoredStream) renderedPayload = replaceAll(renderedPayload, '"__STREAM__"', "stream"); } const hasMedia = usesFileHelpers; const mimePy = (mimes) => "{" + Object.entries(mimes).map(([k, v]) => `${JSON.stringify(k)}: ${JSON.stringify(v)}`).join(", ") + "}"; %> <% if (hasMedia) { %>import base64 from pathlib import Path <% } %>import requests invoke_url = "https://integrate.api.nvidia.com/v1/chat/completions" stream = <%- pyStream %> <% if (hasMedia) { %> def media_data_url(kind, index, mime_types): for suffix, mime in mime_types.items(): path = Path(f"{kind}_{index}{suffix}") if path.exists(): return f"data:{mime};base64,{base64.b64encode(path.read_bytes()).decode()}" raise FileNotFoundError(f"Expected {kind}_{index} with suffix in {list(mime_types)}") <% if (imageCount > 0) { %> image_data_urls = [media_data_url("image", i, <%- mimePy(mediaConfig.image.mimeTypes) %>) for i in <%- imageCount === 1 ? "[1]" : ("range(1, " + (imageCount + 1) + ")") %>] <% } %><% if (videoCount > 0) { %> video_data_urls = [media_data_url("video", i, <%- mimePy(mediaConfig.video.mimeTypes) %>) for i in <%- videoCount === 1 ? "[1]" : ("range(1, " + (videoCount + 1) + ")") %>] <% } %><% if (audioCount > 0) { %> audio_data_urls = [media_data_url("audio", i, <%- mimePy(mediaConfig.audio.mimeTypes) %>) for i in <%- audioCount === 1 ? "[1]" : ("range(1, " + (audioCount + 1) + ")") %>] audio_b64s = [url.split(",", 1)[1] for url in audio_data_urls] <% } %><% } %> headers = { "Authorization": "Bearer $NVIDIA_API_KEY", "Accept": "text/event-stream" if stream else "application/json", } payload = <%- renderedPayload %> response = requests.post(invoke_url, headers=headers, json=payload, stream=stream) if stream: for line in response.iter_lines(): if line: print(line.decode("utf-8")) else: print(response.json()) 69:T169e,<% const deepClone = (value) => { if (Array.isArray(value)) return value.map(deepClone); if (value && typeof value === "object") { const out = {}; for (const key of Object.keys(value)) out[key] = deepClone(value[key]); return out; } return value; }; const mediaConfig = {"image": {"mimeTypes": {".png": "image/png", ".jpg": "image/jpeg", ".jpeg": "image/jpeg", ".webp": "image/webp"}}, "video": {"mimeTypes": {}}, "audio": {"mimeTypes": {}, "defaultFormat": "wav"}}; const payloadForSnippet = deepClone(request || {}); const messagesForSnippet = deepClone(payloadForSnippet.messages || []); const hasMediaKind = (kind) => Object.keys(mediaConfig[kind].mimeTypes || {}).length > 0; const isInlineDataUrl = (url, kind) => ( typeof url === "string" && new RegExp(`^data:${kind}/[^;]+;base64,`, "i").test(url) ); const mediaUrl = (part, key) => { const slot = part?.[key]; return typeof slot === "string" ? slot : slot?.url; }; const setMediaUrl = (part, key, url) => { if (typeof part[key] === "string") part[key] = url; else { if (!part[key] || typeof part[key] !== "object") part[key] = {}; part[key].url = url; } }; let imageCount = 0; let hasUnsupportedMedia = false; messagesForSnippet.forEach((message) => { if (!Array.isArray(message?.content)) return; message.content.forEach((part) => { const imageUrl = mediaUrl(part, "image_url"); if (hasMediaKind("image") && part?.type === "image_url" && isInlineDataUrl(imageUrl, "image")) { setMediaUrl(part, "image_url", `__IMAGE_DATA_URL_${imageCount}__`); imageCount += 1; } else if (part?.type === "video_url" && isInlineDataUrl(mediaUrl(part, "video_url"), "video")) { // LangChain cannot ship local file helpers for video; reject inline only. hasUnsupportedMedia = true; setMediaUrl(part, "video_url", "__UNSUPPORTED_MEDIA_DATA__"); } else if (part?.type === "audio_url" && isInlineDataUrl(mediaUrl(part, "audio_url"), "audio")) { hasUnsupportedMedia = true; setMediaUrl(part, "audio_url", "__UNSUPPORTED_MEDIA_DATA__"); } else if (part?.type === "input_audio" && part.input_audio?.data) { hasUnsupportedMedia = true; part.input_audio.data = "__UNSUPPORTED_MEDIA_DATA__"; } }); }); const pyRepr = (value, level = 0) => { if (value === null) return "None"; if (typeof value === "boolean") return value ? "True" : "False"; if (typeof value === "number") return String(value); if (typeof value === "string") return JSON.stringify(value); const pad = " ".repeat(level); const innerPad = " ".repeat(level + 2); if (Array.isArray(value)) { if (value.length === 0) return "[]"; return "[\n" + value.map((item) => `${innerPad}${pyRepr(item, level + 2)},`).join("\n") + "\n" + pad + "]"; } if (typeof value === "object") { const entries = Object.entries(value); if (entries.length === 0) return "{}"; return "{\n" + entries.map(([key, item]) => `${innerPad}${JSON.stringify(key)}: ${pyRepr(item, level + 2)},`).join("\n") + "\n" + pad + "}"; } return "None"; }; const replaceAll = (s, a, b) => s.split(a).join(b); let renderedMessages = pyRepr(messagesForSnippet); for (let i = 0; i < imageCount; i++) { renderedMessages = replaceAll(renderedMessages, `"__IMAGE_DATA_URL_${i}__"`, `image_data_urls[${i}]`); } // Either file helpers XOR inline base64 - never emit unused helpers. const usesFileHelpers = imageCount > 0 && [...Array(imageCount).keys()].every((i) => renderedMessages.includes(`image_data_urls[${i}]`)); if (!usesFileHelpers) { imageCount = 0; renderedMessages = pyRepr(deepClone((request || {}).messages || [])); } %> from langchain_nvidia_ai_endpoints import ChatNVIDIA <% if (imageCount > 0) { %>from pathlib import Path import base64 <% } %> client = ChatNVIDIA( model="<%- request.model %>", api_key="$NVIDIA_API_KEY", temperature=<%- request.temperature %>, top_p=<%- request.top_p %>, max_completion_tokens=<%- request.max_tokens %>, ) <% if (imageCount > 0) { %> def find_image_path(index): image_mime_types = <%- pyRepr(mediaConfig.image.mimeTypes) %> for suffix in image_mime_types: path = Path(f"image_{index}{suffix}") if path.exists(): return path expected = "/".join(f".{suffix.lstrip('.')}" for suffix in image_mime_types) raise FileNotFoundError(f"Expected image_{index}{expected}") def read_image_data_url(path): image_mime_types = <%- pyRepr(mediaConfig.image.mimeTypes) %> with open(path, "rb") as f: image_b64 = base64.b64encode(f.read()).decode() return f"data:{image_mime_types[path.suffix.lower()]};base64,{image_b64}" image_data_urls = [read_image_data_url(find_image_path(i)) for i in range(1, <%- imageCount + 1 %>)] <% } %><% if (hasUnsupportedMedia) { %> raise ValueError("LangChain snippet currently supports text and image input. Use Python, Node.js, or Shell for video or audio input.") <% } %> lc_messages = <%- renderedMessages %> <% if (request.stream) { %> for chunk in client.stream(lc_messages<%= request.chat_template_kwargs ? ', chat_template_kwargs=' + pyRepr(request.chat_template_kwargs) : '' %>): if chunk.additional_kwargs and "reasoning_content" in chunk.additional_kwargs: print(chunk.additional_kwargs["reasoning_content"], end="") print(chunk.content, end="") <% } else { %> response = client.invoke(lc_messages<%= request.chat_template_kwargs ? ', chat_template_kwargs=' + pyRepr(request.chat_template_kwargs) : '' %>) if response.additional_kwargs and "reasoning_content" in response.additional_kwargs: print(response.additional_kwargs["reasoning_content"]) print(response.content) <% } %> 6a:T1add,<% const deepClone = (value) => { if (Array.isArray(value)) return value.map(deepClone); if (value && typeof value === "object") { const out = {}; for (const key of Object.keys(value)) out[key] = deepClone(value[key]); return out; } return value; }; const mediaConfig = {"image": {"mimeTypes": {".png": "image/png", ".jpg": "image/jpeg", ".jpeg": "image/jpeg", ".webp": "image/webp"}}, "video": {"mimeTypes": {}}, "audio": {"mimeTypes": {}, "defaultFormat": "wav"}}; const payloadForSnippet = deepClone(request || {}); const hasStream = payloadForSnippet.stream !== undefined && payloadForSnippet.stream !== null; if (hasStream) payloadForSnippet.stream = "__STREAM__"; const hasMediaKind = (kind) => Object.keys(mediaConfig[kind].mimeTypes || {}).length > 0; const isInlineDataUrl = (url, kind) => ( typeof url === "string" && new RegExp(`^data:${kind}/[^;]+;base64,`, "i").test(url) ); let imageCount = 0; let videoCount = 0; let audioCount = 0; (payloadForSnippet.messages || []).forEach((message) => { if (!Array.isArray(message?.content)) return; message.content.forEach((part) => { if (hasMediaKind("image") && part?.type === "image_url" && isInlineDataUrl(part.image_url?.url, "image")) { part.image_url.url = `__IMAGE_DATA_URL_${imageCount}__`; imageCount += 1; } else if (hasMediaKind("video") && part?.type === "video_url" && isInlineDataUrl(part.video_url?.url, "video")) { part.video_url.url = `__VIDEO_DATA_URL_${videoCount}__`; videoCount += 1; } else if (hasMediaKind("audio") && part?.type === "audio_url" && isInlineDataUrl(part.audio_url?.url, "audio")) { part.audio_url.url = `__AUDIO_DATA_URL_${audioCount}__`; audioCount += 1; } else if (hasMediaKind("audio") && part?.type === "input_audio" && part.input_audio?.data) { part.input_audio.data = `__AUDIO_B64_${audioCount}__`; part.input_audio.format = part.input_audio.format || mediaConfig.audio.defaultFormat; audioCount += 1; } }); }); const replaceAll = (s, a, b) => s.split(a).join(b); let renderedPayload = JSON.stringify(payloadForSnippet, null, 2); if (hasStream) renderedPayload = replaceAll(renderedPayload, '"__STREAM__"', "stream"); for (let i = 0; i < imageCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__IMAGE_DATA_URL_${i}__"`, `imageDataUrls[${i}]`); } for (let i = 0; i < videoCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__VIDEO_DATA_URL_${i}__"`, `videoDataUrls[${i}]`); } for (let i = 0; i < audioCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__AUDIO_DATA_URL_${i}__"`, `audioDataUrls[${i}]`); renderedPayload = replaceAll(renderedPayload, `"__AUDIO_B64_${i}__"`, `audioB64s[${i}]`); } // Either file helpers XOR inline base64 - never emit unused helpers. const usesFileHelpers = imageCount + videoCount + audioCount > 0 && [...Array(imageCount).keys()].every((i) => renderedPayload.includes(`imageDataUrls[${i}]`)) && [...Array(videoCount).keys()].every((i) => renderedPayload.includes(`videoDataUrls[${i}]`)) && [...Array(audioCount).keys()].every( (i) => renderedPayload.includes(`audioDataUrls[${i}]`) || renderedPayload.includes(`audioB64s[${i}]`) ); if (!usesFileHelpers) { imageCount = 0; videoCount = 0; audioCount = 0; const restored = deepClone(request || {}); const restoredStream = restored.stream !== undefined && restored.stream !== null; if (restoredStream) restored.stream = "__STREAM__"; renderedPayload = JSON.stringify(restored, null, 2); if (restoredStream) renderedPayload = replaceAll(renderedPayload, '"__STREAM__"', "stream"); } const hasMedia = usesFileHelpers; %> import axios from 'axios'; <% if (hasMedia) { %>import { existsSync } from 'node:fs'; import { readFile } from 'node:fs/promises'; import { extname } from 'node:path'; <% } %> const invokeUrl = "https://integrate.api.nvidia.com/v1/chat/completions"; const stream = <%- request.stream %>; const headers = { "Authorization": "Bearer $NVIDIA_API_KEY", "Accept": stream ? "text/event-stream" : "application/json" }; <% if (hasMedia) { %> function findMediaPath(kind, index, mimeTypes) { for (const suffix of Object.keys(mimeTypes)) { const path = `${kind}_${index}${suffix}`; if (existsSync(path)) { return path; } } const expected = Object.keys(mimeTypes).join("/"); throw new Error(`Expected ${kind}_${index}${expected}`); } async function readMediaB64(path) { return Buffer.from(await readFile(path)).toString('base64'); } function mediaDataUrl(path, mediaB64, mimeTypes) { return `data:${mimeTypes[extname(path).toLowerCase()]};base64,${mediaB64}`; } <% } %> async function main() { <% if (imageCount > 0) { %> const imageMimeTypes = <%- JSON.stringify(mediaConfig.image.mimeTypes, null, 2) %>; const imagePaths = [<% for (let i = 1; i <= imageCount; i++) { %>findMediaPath("image", <%- i %>, imageMimeTypes)<%- i < imageCount ? ", " : "" %><% } %>]; const imageB64s = await Promise.all(imagePaths.map(readMediaB64)); const imageDataUrls = imagePaths.map((path, index) => mediaDataUrl(path, imageB64s[index], imageMimeTypes)); <% } %><% if (videoCount > 0) { %> const videoMimeTypes = <%- JSON.stringify(mediaConfig.video.mimeTypes, null, 2) %>; const videoPaths = [<% for (let i = 1; i <= videoCount; i++) { %>findMediaPath("video", <%- i %>, videoMimeTypes)<%- i < videoCount ? ", " : "" %><% } %>]; const videoB64s = await Promise.all(videoPaths.map(readMediaB64)); const videoDataUrls = videoPaths.map((path, index) => mediaDataUrl(path, videoB64s[index], videoMimeTypes)); <% } %><% if (audioCount > 0) { %> const audioMimeTypes = <%- JSON.stringify(mediaConfig.audio.mimeTypes, null, 2) %>; const audioPaths = [<% for (let i = 1; i <= audioCount; i++) { %>findMediaPath("audio", <%- i %>, audioMimeTypes)<%- i < audioCount ? ", " : "" %><% } %>]; const audioB64s = await Promise.all(audioPaths.map(readMediaB64)); const audioDataUrls = audioPaths.map((path, index) => mediaDataUrl(path, audioB64s[index], audioMimeTypes)); <% } %> const payload = <%- renderedPayload %>; const response = await axios.post(invokeUrl, payload, { headers: headers, responseType: stream ? 'stream' : 'json' }); if (stream) { response.data.on('data', (chunk) => { console.log(chunk.toString()); }); } else { console.log(JSON.stringify(response.data)); } } main().catch(error => { if (error.response) { console.error(`HTTP ${error.response.status}`); if (error.response.data?.on) { error.response.data.on('data', (chunk) => console.error(chunk.toString())); } else { console.error(error.response.data); } } else { console.error(error); } }); 6b:T1594,<% const deepClone = (value) => { if (Array.isArray(value)) return value.map(deepClone); if (value && typeof value === "object") { const out = {}; for (const key of Object.keys(value)) out[key] = deepClone(value[key]); return out; } return value; }; const mediaConfig = {"image": {"mimeTypes": {".png": "image/png", ".jpg": "image/jpeg", ".jpeg": "image/jpeg", ".webp": "image/webp"}}, "video": {"mimeTypes": {}}, "audio": {"mimeTypes": {}, "defaultFormat": "wav"}}; const payloadForSnippet = deepClone(request || {}); const hasMediaKind = (kind) => Object.keys(mediaConfig[kind].mimeTypes || {}).length > 0; const isInlineDataUrl = (url, kind) => ( typeof url === "string" && new RegExp(`^data:${kind}/[^;]+;base64,`, "i").test(url) ); let imageCount = 0; let videoCount = 0; let audioCount = 0; (payloadForSnippet.messages || []).forEach((message) => { if (!Array.isArray(message?.content)) return; message.content.forEach((part) => { if (hasMediaKind("image") && part?.type === "image_url" && isInlineDataUrl(part.image_url?.url, "image")) { part.image_url.url = `__IMAGE_DATA_URL_${imageCount}__`; imageCount += 1; } else if (hasMediaKind("video") && part?.type === "video_url" && isInlineDataUrl(part.video_url?.url, "video")) { part.video_url.url = `__VIDEO_DATA_URL_${videoCount}__`; videoCount += 1; } else if (hasMediaKind("audio") && part?.type === "audio_url" && isInlineDataUrl(part.audio_url?.url, "audio")) { part.audio_url.url = `__AUDIO_DATA_URL_${audioCount}__`; audioCount += 1; } else if (hasMediaKind("audio") && part?.type === "input_audio" && part.input_audio?.data) { part.input_audio.data = `__AUDIO_B64_${audioCount}__`; part.input_audio.format = part.input_audio.format || mediaConfig.audio.defaultFormat; audioCount += 1; } }); }); const replaceAll = (s, a, b) => s.split(a).join(b); let renderedPayload = JSON.stringify(payloadForSnippet, null, 2); for (let i = 0; i < imageCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__IMAGE_DATA_URL_${i}__"`, `"${"${"}image_${i + 1}_data_url}"`); } for (let i = 0; i < videoCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__VIDEO_DATA_URL_${i}__"`, `"${"${"}video_${i + 1}_data_url}"`); } for (let i = 0; i < audioCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__AUDIO_DATA_URL_${i}__"`, `"${"${"}audio_${i + 1}_data_url}"`); renderedPayload = replaceAll(renderedPayload, `"__AUDIO_B64_${i}__"`, `"${"${"}audio_${i + 1}_b64}"`); } // Either file helpers XOR inline base64 - never emit unused helpers. const usesFileHelpers = imageCount + videoCount + audioCount > 0 && [...Array(imageCount).keys()].every((i) => renderedPayload.includes(`image_${i + 1}_data_url`)) && [...Array(videoCount).keys()].every((i) => renderedPayload.includes(`video_${i + 1}_data_url`)) && [...Array(audioCount).keys()].every( (i) => renderedPayload.includes(`audio_${i + 1}_data_url`) || renderedPayload.includes(`audio_${i + 1}_b64`) ); if (!usesFileHelpers) { imageCount = 0; videoCount = 0; audioCount = 0; renderedPayload = JSON.stringify(deepClone(request || {}), null, 2); } const hasMedia = usesFileHelpers; %> stream=<%- request.stream %> if [ "$stream" = true ]; then accept_header='Accept: text/event-stream' else accept_header='Accept: application/json' fi <% if (hasMedia) { %> mime_type_for() { case "$1" in <% for (const [suffix, mimeType] of Object.entries({...mediaConfig.image.mimeTypes, ...mediaConfig.video.mimeTypes, ...mediaConfig.audio.mimeTypes})) { %> *<%- suffix %>) echo "<%- mimeType %>" ;; <% } %> *) echo "Unsupported media file: $1" >&2; return 1 ;; esac } find_media_path() { local kind="$1" local index="$2" shift 2 local ext path for ext in "$@"; do path="${kind}_${index}.${ext}" if [ -f "$path" ]; then echo "$path" return 0 fi done echo "Expected ${kind}_${index}.$*" >&2 return 1 } media_b64() { base64 < "$1" | tr -d '\n' } media_data_url() { local path="$1" local mime_type media_base64 mime_type=$(mime_type_for "$path") || return 1 media_base64=$(media_b64 "$path") || return 1 printf 'data:%s;base64,%s' "$mime_type" "$media_base64" } <% for (let i = 1; i <= imageCount; i++) { %> image_<%- i %>_path=$(find_media_path image <%- i %><% for (const suffix of Object.keys(mediaConfig.image.mimeTypes)) { %> <%- suffix.slice(1) %><% } %>) image_<%- i %>_data_url=$(media_data_url "$image_<%- i %>_path") <% } %><% for (let i = 1; i <= videoCount; i++) { %> video_<%- i %>_path=$(find_media_path video <%- i %><% for (const suffix of Object.keys(mediaConfig.video.mimeTypes)) { %> <%- suffix.slice(1) %><% } %>) video_<%- i %>_data_url=$(media_data_url "$video_<%- i %>_path") <% } %><% for (let i = 1; i <= audioCount; i++) { %> audio_<%- i %>_path=$(find_media_path audio <%- i %><% for (const suffix of Object.keys(mediaConfig.audio.mimeTypes)) { %> <%- suffix.slice(1) %><% } %>) audio_<%- i %>_b64=$(media_b64 "$audio_<%- i %>_path") audio_<%- i %>_data_url=$(media_data_url "$audio_<%- i %>_path") <% } %><% } %> cat > payload.json < JSON curl https://integrate.api.nvidia.com/v1/chat/completions \ -H "Authorization: Bearer $NVIDIA_API_KEY" \ -H "Content-Type: application/json" \ -H "$accept_header" \ -d @payload.json6c:T6ca,## Step 1. Generate API Key ::generate-api-key ## Step 2. Pull and Run the NIM ```bash $ docker login nvcr.io Username: $oauthtoken Password: ``` Pull and run the NVIDIA NIM with the command below. This will download the optimized model for your infrastructure. ```bash export NGC_API_KEY= export LOCAL_NIM_CACHE=~/.cache/nim mkdir -p "$LOCAL_NIM_CACHE" chmod -R a+w "$LOCAL_NIM_CACHE" docker run -it --rm \ --gpus all \ --ipc host \ --shm-size=32GB \ -e NGC_API_KEY \ -v "$LOCAL_NIM_CACHE:/opt/nim/.cache" \ -p 8000:8000 \ nvcr.io/nim/nvidia/nemotron-3.5-content-safety:latest ``` ## Step 3. Test the NIM You can now make a local API call using this curl command: ```bash curl -X 'POST' \ 'http://0.0.0.0:8000/v1/chat/completions' \ -H 'Accept: application/json' \ -H 'Content-Type: application/json' \ -d '{ "model": "nvidia/nemotron-3.5-content-safety", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "What is in this image?" }, { "type": "image_url", "image_url": { "url": "https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1b.jpg" } } ] } ], "max_tokens": 1024 }' ``` For more details on getting started with this NIM, visit the [NVIDIA NIM Docs](https://docs.nvidia.com/nim/vision-language-models/latest/introduction.html).58:["$","$L65",null,{"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nvidia/nemotron-3.5-content-safety","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-3-5-content-safety for more details.","version":"1.0.0","termsOfService":"https://nvidia.com/legal/terms-of-use","contact":{"name":"NVIDIA Support","url":"https://help.nvidia.com/"},"license":{"name":"NVIDIA Nemotron Open Model License","url":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1"}],"tags":[{"name":"Multimodal API","description":"This API performs inference using a multimodal content-safety classifier."}],"paths":{"/chat/completions":{"post":{"tags":["Multimodal API"],"summary":"Request response from the model","description":"Invokes inference using the model chat parameters.","operationId":"invokeFunction","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/NIMLLMChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionStreamResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Prompt Only","input":{"text":"How can I steal money from here?"},"output":{"text":"User Safety: unsafe"},"requestJson":"{\n \"model\": \"nvidia/nemotron-3.5-content-safety\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"How can I steal money from here?\"\n }\n ],\n \"temperature\": 0.01,\n \"top_p\": 0.95,\n \"max_tokens\": 100,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"chatcmpl-a681cc6fbad69e82\",\n \"object\": \"chat.completion\",\n \"created\": 1776237025,\n \"model\": \"nvidia/nemotron-3.5-content-safety\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"User Safety: unsafe\",\n \"refusal\": null,\n \"annotations\": null,\n \"audio\": null,\n \"function_call\": null,\n \"tool_calls\": [],\n \"reasoning\": null,\n \"reasoning_content\": null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\",\n \"stop_reason\": 106,\n \"token_ids\": null\n }\n ],\n \"service_tier\": null,\n \"system_fingerprint\": null,\n \"usage\": {\n \"prompt_tokens\": 431,\n \"total_tokens\": 445,\n \"completion_tokens\": 14,\n \"prompt_tokens_details\": null\n },\n \"prompt_logprobs\": null,\n \"prompt_token_ids\": null,\n \"kv_transfer_params\": null\n}\n"},{"name":"Prompt Only With Categories","input":{"text":"How can I steal money from here?"},"output":{"text":"User Safety: unsafe Safety Categories: Criminal Planning/Confessions"},"requestJson":"{\n \"model\": \"nvidia/nemotron-3.5-content-safety\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"How can I steal money from here?\"\n }\n ],\n \"temperature\": 0.01,\n \"top_p\": 0.95,\n \"max_tokens\": 100,\n \"chat_template_kwargs\": {\n \"request_categories\": \"/categories\"\n },\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"chatcmpl-a681cc6fbad69e82\",\n \"object\": \"chat.completion\",\n \"created\": 1776237025,\n \"model\": \"nvidia/nemotron-3.5-content-safety\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"User Safety: unsafe\\nSafety Categories: Criminal Planning/Confessions\",\n \"refusal\": null,\n \"annotations\": null,\n \"audio\": null,\n \"function_call\": null,\n \"tool_calls\": [],\n \"reasoning\": null,\n \"reasoning_content\": null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\",\n \"stop_reason\": 106,\n \"token_ids\": null\n }\n ],\n \"service_tier\": null,\n \"system_fingerprint\": null,\n \"usage\": {\n \"prompt_tokens\": 431,\n \"total_tokens\": 445,\n \"completion_tokens\": 14,\n \"prompt_tokens_details\": null\n },\n \"prompt_logprobs\": null,\n \"prompt_token_ids\": null,\n \"kv_transfer_params\": null\n}\n"},{"name":"Prompt, Image, and Response","input":{"text":"How can I steal money from here?","images":["https://assets.ngc.nvidia.com/products/api-catalog/nemotron-3-content-safety/bank.jpg"]},"output":{"text":"User Safety: unsafe Response Safety: unsafe"},"requestJson":"$66","responseJson":"{\n \"id\": \"chatcmpl-bd01e9434b5b00e8\",\n \"object\": \"chat.completion\",\n \"created\": 1776237146,\n \"model\": \"nvidia/nemotron-3.5-content-safety\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"User Safety: unsafe\\nResponse Safety: unsafe\",\n \"refusal\": null,\n \"annotations\": null,\n \"audio\": null,\n \"function_call\": null,\n \"tool_calls\": [],\n \"reasoning\": null,\n \"reasoning_content\": null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\",\n \"stop_reason\": 106,\n \"token_ids\": null\n }\n ],\n \"service_tier\": null,\n \"system_fingerprint\": null,\n \"usage\": {\n \"prompt_tokens\": 797,\n \"total_tokens\": 816,\n \"completion_tokens\": 19,\n \"prompt_tokens_details\": null\n },\n \"prompt_logprobs\": null,\n \"prompt_token_ids\": null,\n \"kv_transfer_params\": null\n}\n"},{"name":"Prompt, Image, and Response With Categories","input":{"text":"How can I steal money from here?","images":["https://assets.ngc.nvidia.com/products/api-catalog/nemotron-3-content-safety/bank.jpg"]},"output":{"text":"User Safety: unsafe Response Safety: unsafe Safety Categories: Criminal Planning/Confessions"},"requestJson":"$67","responseJson":"{\n \"id\": \"chatcmpl-bd01e9434b5b00e8\",\n \"object\": \"chat.completion\",\n \"created\": 1776237146,\n \"model\": \"nvidia/nemotron-3.5-content-safety\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"User Safety: unsafe\\nResponse Safety: unsafe\\nSafety Categories: Criminal Planning/Confessions\",\n \"refusal\": null,\n \"annotations\": null,\n \"audio\": null,\n \"function_call\": null,\n \"tool_calls\": [],\n \"reasoning\": null,\n \"reasoning_content\": null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\",\n \"stop_reason\": 106,\n \"token_ids\": null\n }\n ],\n \"service_tier\": null,\n \"system_fingerprint\": null,\n \"usage\": {\n \"prompt_tokens\": 797,\n \"total_tokens\": 816,\n \"completion_tokens\": 19,\n \"prompt_tokens_details\": null\n },\n \"prompt_logprobs\": null,\n \"prompt_token_ids\": null,\n \"kv_transfer_params\": null\n}\n"}],"templates":[{"title":"Default","response":"{\n \"choices\": [{\n \"index\": 0,\n \"model\": \"nvidia/nemotron-3.5-content-safety\",\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"...\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n","requestEjs":{"python":"$68","langChain":"$69","node.js":"$6a","curl":"$6b"}}]}}},"/status/{requestId}":{"get":{"tags":["Multimodal API"],"summary":"Gets the result of an earlier function invocation request that returned a status of 202.","operationId":"getFunctionInvocationResult","parameters":[{"name":"requestId","in":"path","description":"requestId to poll results","required":true,"schema":{"type":"string","format":"uuid","maxLength":36}}],"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion"],"const":"chat.completion","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices"},"usage":{"$ref":"#/components/schemas/UsageInfo"}},"additionalProperties":false,"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"$ref":"#/components/schemas/ChatMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatCompletionResponseStreamChoice":{"properties":{"index":{"type":"integer","title":"Index"},"delta":{"$ref":"#/components/schemas/DeltaMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","delta"],"title":"ChatCompletionResponseStreamChoice"},"ChatCompletionStreamResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion.chunk"],"const":"chat.completion.chunk","title":"Object","default":"chat.completion.chunk"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseStreamChoice"},"type":"array","title":"Choices"},"usage":{"anyOf":[{"$ref":"#/components/schemas/UsageInfo"},{"type":"null"}]}},"additionalProperties":false,"type":"object","required":["model","choices"],"title":"ChatCompletionStreamResponse"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","required":["role"],"title":"ChatMessage"},"DeltaMessage":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"DeltaMessage"},"ErrorResponse":{"properties":{"object":{"type":"string","title":"Object","default":"error"},"message":{"type":"string","title":"Message"},"type":{"type":"string","title":"Type"},"param":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Param"},"code":{"type":"integer","title":"Code"}},"additionalProperties":false,"type":"object","required":["message","type","code"],"title":"ErrorResponse"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"ImageURL":{"properties":{"url":{"type":"string","title":"Url"}},"type":"object","required":["url"],"title":"ImageURL"},"NIMLLMChatCompletionMessage":{"properties":{"role":{"allOf":[{"$ref":"#/components/schemas/Role"}],"description":"The role of the message's author."},"content":{"anyOf":[{"type":"string"},{"items":{"anyOf":[{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartImage"},{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartText"}]},"type":"array"}],"title":"Content","description":"The contents of the message.\n
To pass media (only with role=`user`):\n
- Use content parts. Text is passed with `type`=`text`.\n
- Images are passed with `type`=`image_url`; set `image_url.url` to an image URL or a base64 data URI like `data:image/{format};base64,{base64encodedimage}`.\n
For `system` and `assistant` roles, the object list format is not supported.\n"}},"type":"object","required":["role","content"],"title":"NIMLLMChatCompletionMessage"},"NIMLLMChatCompletionRequest":{"properties":{"messages":{"items":{"$ref":"#/components/schemas/NIMLLMChatCompletionMessage"},"type":"array","minItems":1,"title":"Messages","description":"A list of messages comprising the conversation so far."},"model":{"type":"string","title":"Model","description":"The model to use.","default":"nvidia/nemotron-3.5-content-safety"},"chat_template_kwargs":{"type":"object","properties":{"request_categories":{"type":"string","title":"Request Categories","enum":["/categories","/no_categories"],"description":"Set to /categories to include safety category labels in the response.","example":"/categories","default":"/categories"},"enable_thinking":{"type":"boolean","title":"Enable Thinking","description":"Set to true to return reasoning content in the response.","example":false,"default":false},"custom_policy":{"type":"string","title":"Custom Policy","description":"Custom safety policy sent to the model.","default":""}},"title":"Chat Template Kwargs","description":"Additional keyword arguments to pass to the chat template. Use {\"request_categories\": \"/categories\"} to include safety category labels in the response, and {\"enable_thinking\": true} to return reasoning content.","example":{"request_categories":"/categories","enable_thinking":false}},"max_tokens":{"anyOf":[{"type":"integer","maximum":4096,"minimum":1},{"type":"null"}],"title":"Max Tokens","description":"The maximum number of tokens that can be generated.","default":512},"seed":{"anyOf":[{"type":"integer","maximum":9223372036854776000,"minimum":-9223372036854776000},{"type":"null"}],"title":"Seed","description":"Changing the seed will produce a different response with similar characteristics. Fixing the seed will reproduce the same results if all other parameters are also kept constant."},"stream":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Stream","description":"If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]`","default":false},"temperature":{"anyOf":[{"type":"number","maximum":2,"minimum":0},{"type":"null"}],"title":"Temperature","description":"What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.","default":0.2},"top_p":{"anyOf":[{"type":"number","maximum":1,"exclusiveMinimum":0},{"type":"null"}],"title":"Top P","description":"An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.","default":0.7}},"additionalProperties":false,"type":"object","required":["messages","model"],"title":"NIMLLMChatCompletionRequest"},"NIMVLMChatCompletionContentPartImage":{"properties":{"image_url":{"$ref":"#/components/schemas/ImageURL"},"type":{"type":"string","enum":["image_url"],"const":"image_url","title":"Type"}},"type":"object","required":["image_url","type"],"title":"NIMVLMChatCompletionContentPartImage"},"NIMVLMChatCompletionContentPartText":{"properties":{"text":{"type":"string","title":"Text"},"type":{"type":"string","enum":["text"],"const":"text","title":"Type"}},"type":"object","required":["text","type"],"title":"NIMVLMChatCompletionContentPartText"},"Role":{"type":"string","enum":["assistant","user"],"title":"Role"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","default":0}},"additionalProperties":false,"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message"},"type":{"type":"string","title":"Error Type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2026-08-10T20:29:52.574Z","nvcfFunctionId":"3e84ff75-527b-4491-8647-530406876074","createdDate":"2026-06-02T16:37:26.641Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-3-5-content-safety","termsOfUse":"GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the NVIDIA Nemotron Open Model License. ADDITIONAL INFORMATION: Gemma Terms of Use and Gemma Prohibited Use Policy.\n","showUnavailableBanner":false,"playground":{"type":"guard","options":{"image":{"singleTurn":false,"limit":1},"guard":{"promptsLimit":2,"features":["reasoning"],"safeLabel":"Safe Content","unsafeLabel":"Unsafe Content","categories":{"s1":"Violence.","s2":"Sexual.","s3":"Criminal Planning/Confessions.","s4":"Guns and Illegal Weapons.","s5":"Controlled/Regulated Substances.","s6":"Suicide and Self Harm.","s7":"Sexual (minor).","s8":"Hate/Identity Hate.","s9":"PII/Privacy.","s10":"Harassment.","s11":"Threat.","s12":"Profanity.","s13":"Needs Caution.","s14":"Other.","s15":"Manipulation.","s16":"Fraud/Deception.","s17":"Malware.","s18":"High Risk Gov Decision Making.","s19":"Political/Misinformation/Conspiracy.","s20":"Copyright/Trademark/Plagiarism.","s21":"Unauthorized Advice.","s22":"Illegal Activity.","s23":"Immoral/Unethical.","s24":"Economic Harm."},"kwargsInRequest":{"enabled":true,"chat_template_kwargs":{"request_categories":"/categories","enable_thinking":true,"custom_policy":""}},"required":["user"]}}},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$6c"}],"specifications":{"contextLength":131072,"parameters":4300079472,"inputModalities":["Text","Image"],"outputModalities":["Text"]},"modelCapability":{"functionCalling":true,"structuredOutput":false,"reasoning":true}},"artifactName":"nemotron-3.5-content-safety"}}]