Instructions to use phgrouptechs/Denglish-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use phgrouptechs/Denglish-8B-Instruct with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-Instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "phgrouptechs/Denglish-8B-Instruct")

Transformers

How to use phgrouptechs/Denglish-8B-Instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="phgrouptechs/Denglish-8B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("phgrouptechs/Denglish-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("phgrouptechs/Denglish-8B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use phgrouptechs/Denglish-8B-Instruct with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="phgrouptechs/Denglish-8B-Instruct",
	filename="Denglish-8B-Instruct-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use phgrouptechs/Denglish-8B-Instruct with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf phgrouptechs/Denglish-8B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf phgrouptechs/Denglish-8B-Instruct:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf phgrouptechs/Denglish-8B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf phgrouptechs/Denglish-8B-Instruct:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf phgrouptechs/Denglish-8B-Instruct:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf phgrouptechs/Denglish-8B-Instruct:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf phgrouptechs/Denglish-8B-Instruct:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf phgrouptechs/Denglish-8B-Instruct:Q4_K_M

Use Docker

docker model run hf.co/phgrouptechs/Denglish-8B-Instruct:Q4_K_M

LM Studio
Jan

vLLM

How to use phgrouptechs/Denglish-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "phgrouptechs/Denglish-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "phgrouptechs/Denglish-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/phgrouptechs/Denglish-8B-Instruct:Q4_K_M

SGLang

How to use phgrouptechs/Denglish-8B-Instruct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "phgrouptechs/Denglish-8B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "phgrouptechs/Denglish-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "phgrouptechs/Denglish-8B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "phgrouptechs/Denglish-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use phgrouptechs/Denglish-8B-Instruct with Ollama:
```
ollama run hf.co/phgrouptechs/Denglish-8B-Instruct:Q4_K_M
```

Unsloth Studio new

How to use phgrouptechs/Denglish-8B-Instruct with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for phgrouptechs/Denglish-8B-Instruct to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for phgrouptechs/Denglish-8B-Instruct to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for phgrouptechs/Denglish-8B-Instruct to start chatting

Docker Model Runner
How to use phgrouptechs/Denglish-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/phgrouptechs/Denglish-8B-Instruct:Q4_K_M
```

Lemonade

How to use phgrouptechs/Denglish-8B-Instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull phgrouptechs/Denglish-8B-Instruct:Q4_K_M

Run and chat with the model

lemonade run user.Denglish-8B-Instruct-Q4_K_M

List all available models

lemonade list

🎓 Denglish-8B-Instruct: AI Language Tutor for Vietnamese Learners

Denglish-8B-Instruct is a fine-tuned LoRA adapter based on unsloth/llama-3-8b-Instruct-bnb-4bit. It is specifically designed to act as a strict yet friendly AI Language Tutor, assisting Vietnamese students in learning English and German.

This model excels at identifying grammatical, spelling, and contextual errors from user inputs, explaining the mistakes clearly in Vietnamese, and providing perfectly corrected sentences in the target language.

🚀 Model Details

Model Type: Causal Language Model (Fine-tuned LoRA Adapter)
Base Model: Meta Llama 3 (8B-Instruct 4-bit quantized via Unsloth)
Primary Languages: Vietnamese (Explanations), English (Target), German (Target)
Training Framework: TRL (Transformer Reinforcement Learning) & PEFT
Architecture: Optimized for multi-modal integrations (Text, OCR/Images, and STT/Voice processing ecosystems).

💡 Intended Uses & Ecosystem

This model is the core "Brain" of the Denglish Omnichannel Platform (integrated via RunPod Serverless, FastAPI, Telegram, and Facebook Messenger). It is intended to process inputs such as:

Direct Text: User types a sentence in English or German.
Transcribed Audio (Whisper STT): Correcting conversational mistakes from spoken language.
Extracted Text from Images (OCR): Grading handwritten or printed homework.
🗣️ Face-to-Face Speaking Practice: Role-play as a native speaker, engage in natural conversations, and receive direct pronunciation/grammar correction.
📝 Test Generation: Automatically generate tests from A1 to C2 levels as required.
👩‍🏫 Strict Grading: Evaluate the work, provide detailed scoring, point out errors, and provide correct answers.
🌐 Trilingual: Understand and respond flexibly between Vietnamese, English, and German.

🛠️ How to Use (Quick Start)

Since this is a LoRA adapter, you need to load the base model first and then merge it with this adapter using peft.

Prerequisites

pip install torch transformers peft accelerate bitsandbytes

Inference Code

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# 1. Define the Model ID
base_model_id = "unsloth/llama-3-8b-Instruct-bnb-4bit"
lora_model_id = "phgrouptechs/Denglish-8B-Instruct"

print("Loading Tokenizer and Base Model...")
tokenizer = AutoTokenizer.from_pretrained(base_model_id)

# Load Base Model (Use bfloat16 for optimization on newer GPUs.)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

print("Currently using the English LoRA Adapter....")
# Kết hợp LoRA vào Base Model
model = PeftModel.from_pretrained(base_model, lora_model_id)

# 2. Building a Prompt (Using the Llama 3 Chat Template)
system_prompt = """You are Denglish AI - an AI specializing in face-to-face English speaking practice for Vietnamese learners.

YOUR RESPONSIBILITIES:
1. Provide concise and natural responses.

2. If the user makes a mistake, point out the weakness in Vietnamese.

3. Always end with an open-ended question."""

user_message = "Hello teacher, my name is Hoang. I want learn English today."

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": user_message}
]

# Prepare input data
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([prompt], return_tensors="pt").to("cuda")

print("AI is thinking...")
# 3.Generate text (Generate)
with torch.no_grad():
    outputs = model.generate(
        **inputs, 
        max_new_tokens=512, 
        temperature=0.4, 
        top_p=0.9,
        pad_token_id=tokenizer.eos_token_id
    )

# 4. Print results
response = tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True)
print("\n--- DENGLISH AI'S RESPONSE ---")
print(response.strip())

📝 Example Output

Example 1

Input (User): "Hello, my name is John and I is a student." Target Language: English

Output (AI):

Máy phát hiện lỗi sử dụng động từ to be. Chủ ngữ "I" phải đi với "am" thay vì "is".

Câu đúng: "Hello, my name is John and I am a student."

Example 2

Input (User): "Give me a test." Target Language: German Target Count: 1 Target Level: A1

Output Text (AI): Hãy viết lại câu tiếng Đức sau đây theo một cách khác nhưng giữ nguyên ý nghĩa:\nInput:\nIch bin so froh, dass du da bist.

Output Audio (AI):

"SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjYwLjE2LjEwMAAAAAAAAAAAAAAA//OEwAAAAAAAAAAAAEluZm8AAAAPAAABbwAAimAABAYJCw4RExYYGx0gIiUoKi0vMTQ3OTw/QUNGSEtOUFNWWFpdX2JlZ2psb3F0dnl8foGDhYiLjZCTlZeanJ+ipKeprK6xs7a5u77AwsXIys3Q0tTX2dzf4eTn6evu8PP2+Pv9AAAAAExhdmM2MC4zMQAAAAAAAAAAAAAAACQDBgAAAAAAAIpg3IwGnQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA//NExAAAAANIAAAAAExBTUUzLjEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVE6iBAxbe//NExFMAAANIAAAAAORuUDP0TiIUQDAzT4Tk76J04AU0REKUDFnAAnQRRbmEJ03f0ABGfETvX64cWfXMIAJ/QMDcWZO9NOACRHP5QMDfd4mibu7uBgYIQfAghEsFxCDg//NExKYAAANIAAAAAGdP9K7mgGBu0ARwBBmPEFv54D2DeNLFY59vaRsZgvDyiutTakm6hJNQ7PZ7bC8FiNM2fg3ZHhWUGzepoJUhRtpPQ9eLai6koDKKR50e41BHUTFW//NExKwAAANIAAAAAJTJwg6yEkzj5OUy9IhYwpyyUKknkJgC8NWcTd06UkamWnFISSBi8JplSAC4pNNnnQ8kieMeixdE1JkjFnBAkckRoYXGEMkVEICCLl2DkkoP0UV3//NExP8Zwt3kAEhGQUjCApnJlnr3SGwVp5mlFAZQlRznQcohhdVBaTGwgpLJrHKNg5Z2SXR6ZdtcLF8pAbNoocy9yIUgX1x5x4PvZTUqizt0kXOWQshCC+6T6hLnmRUI//NExOsi0xn4AnpMvSB9rp1xSpKhA2IO+oIQRXkJHxaZOJ1fMSKaGo7NJI2SBwkjAJ06bdWkKCd8IxFaIw2oSEZOF0RlGqBCdQnkps/i+nXy03xzz0633zlahifJpshj//NExLIgAxoELHmMAXQ3kCBd1j2Iwmx0GJIY73UZBMB0hh++LyCGPpE7VzlufAkIAJA4tE+DCyLQzQiaJ2Ju1fR0Lm7n3AAAlJNCLNFnh3VjNN9Ff2rbVY+WdOPUgyoe//NExIUdIx4gDkmHGIxTkrFzFvQpAMSMhPzijh2Xh0xWIA0gbJAnjvdfCS1YgGj6GCYjjoQw/SGFZK6u7DJLEszP2KuMLE5/d+BY+wcOUo3dj7wGHMLBGRYcXRREuD9J//NExGMfMbpgAHsE+HWPB8nj3hEH9WGFh/lz4DCxgoAw/EBzMphh3IwJksYQAQA54UBWL7SoIMjhK2lmhyQBA0D5MjE/bi8ShIwkc0MEAmEJoRlE2MJwuNAYHSYUBFZA//NExDkdixKMAHpE3LKTJygPidlfVE28QEhGIxOvtFCdeUMQkbT5ryXbqpHVT0mbed3dfXTuqNpefs1E+36/T7ztrpq9G3V1FnQqeIGGsN2FHxsYdmI6IAXAKDT4inR5//NExBUW6WK4ysPSMKEBgSYuYWFpdALiTFyMLvdfnKpNozZ/zRitHBZwYJzkZoBAdlHEl21CBASbJyQtupRe/VGIQSAYJZ8aNYXLhgPxSt8/jiFF0+kpQF4ABn/bojO2//NExAwUQVreNsDM0bDs0/4WgWxg6qjeX7X7AMCOG8y6eKRoBLTWTuts/zNc+xsnGpZUgShxTQztNWSMsxjbkhF2a8R9v9x+ve8sIs1fKBajm4WCG6incNW8NNmwwmnZ//NExA4VWxriLsGEj4rzOAg5kjn0eEw5yXcyquyiRqfMaQqdHMaYz00KGc4Y5SsZ2Zm3Msi6V3/Re/R336XZFVmM2rfqf/9P///6l4yMaAoMTjhSqoUiA0i6fIKb4CHv//NExAsU4jLjHnpEkNgY5r+5mIGRfLaWHH2Bt0pGZS8jcJoQ5fpHtsoRC1Oy1a5lbXq29eR9G0PeDMm3vqR9L5LIZq3WY+Z9S/9wrC7wIsmAf/9Mltq0tSb61FSWgc5g//NExAoSCMr6XsGGcvWHEYtz44GIa5YYKZuWvPyUeHHIQUTaYW9oXhFT6JaCDj2y2B4y4xBSIqsXh2vd+i+5aUB3ER7/8XYguMN2VYCUaEPAlGB/KukPCtM7HEqlOmwv//NExBQRmT691sGGcM05SM9+/fnD5k2RuyRXt0+JH7lw3a/+4ExgxgICAgbQKaCtx4Fb/We//mcO4K//+p91SqAFol1St376gxIXgF0UxuAwuKZZEhVFgFAZDrg0k8RE//NExCARuFK6fjPMAKAXHhCWeDR4q7KjMRBIeZCT1B31A0n87/RbWGkaNGVw9tTHt7W6VwEpJJG5OolKRCCwabmyQld8FCR360MAddQmcshgA3Jj1A1aqndujbLc+1HP//NExCwSMVKhvEhEzrhgB1RICuJrTUCD9umINH0tb7LVqbKCccc7tMet0K2221uoAHzwAgM3MgivC6iO7oTpTd5oARCtPGA6tlPe4DJoODhZWWYaoLh7QrGSvCiAZaXJ//NExDYRGbLhvhmHKuf/X/iI77EENbt0MNjR6s9d3JHGJAT24Xg2Ts9p9VKAQE84g3op/+uvTcpztZLaQQ/QkwkXJ0nPLIUezRpJihQKCgxjbAP1C2ZBM+tn6yBQYMzN//NExEQSCWK0AMlSmGn//tXVX6RwLCgBpgqyDPWQ4UsRFx+El5NfzJcmvmA/Gd0TTlJhQMAgMgQLTk2CQKDBwQEGhJIugUSVhxBlI1v9J84tqHk5b//yxpWAAivNADDG//NExE4RkWbAAKBMtPZ/3VdOw5tV9f1vW8ZI9waj9ShwX9DGb5Sjj/mX9WdtHEgoikY1OjPYpGZOPIwBAge7kCqv6srGy1/////kFYgEY7H07colWNjes/l4IKC6uHXa//NExFoRUV7CRsFMuE8RTv4YkIjB6t2FM1ZlmLTyt+5S/QwUvqgobxK7g0QIiYiKuiy8rE3BU9DX/+S+eDVnsbHpbY423KAsougswCiNWNoV7iQwkz/Jg3WdC2bzVVjC//NExGcRsT7SVsIEVpzIoWBoRAYGlgqKA0oO1jSx8iCobLHi06HSQishP7c7VDX/+jFw0QDUqnf7ZY23LaA2sniLqHQazsyJheFntC4gk8joacODwXINOR2q4+DI3FmT//NExHMSaLa9vhvGJkgCGrIPltOblw+x/mlc/9/HNYOoKK6ySQgp3cvR1i2UExcBShwBCZO2uFgoMbVx3KGusciSGkUrI8A4CBMWUYgQgDPhQMM5Pwh7vZro29g5G9G3//NExHwSQVqxvkBNQkCcHNQwsLvSqH4YEAAcCAkBCi/9ETxANL2/G4ZkNZSkyUkOgPQgMLSt6TARjDUddNIqlyYFiyPZZ9Lpfra9bYavTrFetLYYXdY8jxJpI9VMI4IW//NExIYS6L6RtE5SLC3msgDzVh0KCI8pLHu/tNaBR44P30Vu7t/Rlbk0nGBIuCPSjSeLUccRQsL5jgsW44xsiIX/mCtdyMOwtAlCCA01FU+8gLf/7spuR6q1w7vV5+jo//NExI0hog6EANvG3BaXOV2wJenng41br3iAA8AFMbuoGkW19QN+4bnlh4H5UvPu5cXw3EH0YZFZG6j0ROB1Y2YQhBIqRdFLagCQWQGkgVCKB6Z+699mVpTnAiAAQOIH//NExFkbIbKsAMGFaBew73qHbW8/UWNe8AdNX///9f7VoYADrFlgUCe3SQlSfiMiNb0ZxETYXkmphMj+L4X0lywKx3KxVKG3YgR0cvb4kTS14dxDMiwUSnBzzjVNtzaj//NExD8TaQLiVkvYpDZWhwleIvo70///////SjtCC3aAOTwV8ZOSAlllkcc8KRPUYarUZWG4omXeGZkzMjqTmJ2dJE9zuelzsOmc5ISZZ/98vy89NCSJ2eQ5RN6HMOYf//NExEQR6gLxdmpGVgYDH1VswAAoAAchrKkUpxGvxUUH1sHg+8cAOD8HomEkdize0//ZnMaiVqoknRZo0QyIlefke5tq+75do27Kg467Skof09tDq40mAVUA82AU0Zw8//NExE8RAULZ9gsMFLSKLRqpCD+zgoLHLAmVWwEqmFPnZYSpUygisl6kMW5tDGldZR+xfxIKkD6XYsg0sxCvW4D7k/3zP//q7IVAB7bCC7+B80JK0wM6RBOCbx7hVmvT//NExF4RwUreVmsETF0JPDjTxVxwFgCeFHlEnNlppLUSkVA4aB+x0xorLiuYDIwVEKjvtWhLZMQnlI/1bVqtNKbW2Ny7AUxXBL2TwxzTWNImqjrmZeRm/kdeSlu02huG//NExGoR6F7iXlvSRDcrZi6+XzUo6oozRCoPBQOB1vUvdxooHYd/zqzwCwZ//WaEQ/y1HBmhoQX9AGI9AFyFro2R2jOVK7EBUNZavuGoxhV2bzUgwciwlIip2Vc3rGjK//NExHUR6TL6XnmEctwiJTwKxFkaSIK1SUsbUePLW7+C1K//9bkMAJ0wS+wMHgEWo41sKDzhUSbTXcDfZOqTzT+uS4YCFK2tf/6ymS8xnU0rIY0rlbQCFL6S0CsYzyzc//NExIARcI6hPgvGEDOVOWZ+b5RLf////yoWX/aeAN8qFKK+XEsMNWD1Ny03p2JvUKNfFJ+vpl8vcXagoUSxAoQKUk3k8QVv2f9Lvfdp///bXpTVEUkquqcbZDJIoG+X//NExI0RudJYMNYESOfewGj58NwlzwxGGD1Oorty03YcBME2JRLpitOZkYMqG/l4iBgTpADdATubGhKgjwbyCEBREpA20C25RH4vvbC7BlibI02crHSBjKEALvdBrpnC//NExJkOSEpYV08YACRcLRmnqPHv/UeTmhgaFw7ZDdGY//qmjIULNoTS4Cu//nAJxj4XCIkVoLV+ZioXUhChQZuUtTeFGR7FpmSSzoPutxKANrP7rS6berdRuOtbYFCw//NExLIh0lKlnZiAAufI/K1Csvbbh4PNIbdvZFjzRMHi6UXTlqxE9IRzLWAYSpKp3Q+4WkP/7J+i94sThAxInqIpDV7uUyQyw7IY1TPqaaZQzTWN5BDGSrnzTBLhb7kg//NExH0WQMagAdp4AAoW94/IAXiZLweFo43k27jAmbt6nKb/39kfVW9fv6Erq8EcM53BkwS8uz///qWgOxMFtUZ93qJhReHJ5ZK8YeOEtVFRU+cwhxaFLZRN0Di2M7ea//NExHcUYaqxvMvUjFWxWmw7BBCNOEVK3izdC/+v/zer/N6P6v4Unt6U9vX7pdzEPRXe4opA2//bb8k0mRAy1WCIoy7vJJIwgilSD0AuUa5ZA7BwPBK7wDFC2aQAjmva//NExHgV0lqkftIFBHI+q6ThXX/k4G2V2ei9rhBNzlKugYRK19W9RbRgIPtV/p1i7K7nb0fxFvToTkOEJRzHXUzOpf//Wj0ZtD+ttEHOgvAFhAyAn6RFaF/GtQppmXTN//NExHMY4xbKXosKe547R6GQJxkq9abnKjpIYskGhN/PE3Jx2QIot/o3DK/Z1XQEU9XW07muQqP6/XlQdlHyP//iU9J1B3v/5VmS9ocVQGjal1ktgFY2IYXqGgkagQgi//NExGIT0V6pvtJElBACt2KzzOgMFNDY2NQpMuXgwENBwGhcYHSJUNA0Jjx1jVCWo9EQl/hqr+4DKBo0WU8i5P//+vSqBprxgQClJUCGKBHiHiNWLIlviEKYgwABjwNp//NExGUSSKq1vnpGLpWcVBub5crZfrZhSiVRQETmM9H1+j97f6I+1vmMYU+ekVqWGmnV6uz8Ff//9VWACSBQALiBi20VAA1GQAAWYMNjScYaDhBwSEpEyrXIhXOrNK+b//NExG4SCVpMEVoQAMReyLCDCbdFJfzhdK5E2bV8gBUMiNHG9Xb1hy46CoOBZc6Pf9Q6yJjjSlezamr+3atR4qGDE4pdS332/363PmCzdAuG7safq/+/2/uXBcCzQ4aG//NExHgfgypQFZuAAGixfJsn02ggKhZdrG8lotZrLGAIDZcFxzOiMiUe0PVHui52PvZNOJlw65aTXJYepaXi+SRJmZOWVIZ0fgqlFIyZTLUdBnHuSZ0uJk0wdtNE2SNF//NExE0iEtriX49oAiRKnxwFZso3QWZFxBJKpJtNDWXTh5Z9STWMdfXVs6SLqdlpLR50+hV33RNz36BfZWt61U1df5uwEd961aWDUh4aKS3QAq2cBwA4Z4nCYlsgz2BU//NExBcSWh76f8c4Akh9zgSzh4fAJNbOB+W44b8cf19SitSK/USyzPKAsF68/9ff1Y5Tf/+rasROd//cz/x9SmCDHtng6qARZsPwLOhiajmRl11EL6MhDf7TDRjMIgG5//NExCASAVraVmpKxtKCROMFyNoAou/f5fmZdUU5KB8YCF+WrMlBp7/4SUc5VLfA2AfsFZuQJWNoEYgGZbQFRN61Yw7dT1kfVQwY+qgeVkUqLPqQp2QhbzfNN677rYny//NExCsSMU7FtkYUKoTD419Y0HgoVf544sFf061Q67amFXf7KcVUNc0yVowVL/rYnb6Btc1gHxA7q+nQDMZ+IR1G2+phUEKKx7UA6MjfcxX7lR1R/ytro/mfzCvN/9f5//NExDUSGg7iXmJEVr5Vr/VSsQEPLOgqZbDa/zv7cFXVgDlm3lm34CSJmEwwYYhxqs3O0bxyOIFQ/pO0Q3B/+Zypyu75mq19ZEoSao9NupSVdKg0aHtS0FQEF/+oS2PJ//NExD8ScJqpvk5YIKp6guAncOf/R0iVgKtctt1uAB1BHOCzwaQW5VQQca4uJqzA1JwdhWZuNEoU6+pG1cr7q73zrfPVyZbHLLYkChtALJKnXss9eoibs4derSgS8FUE//NExEgRsPq9v1JAAgAQCmhhYuBwrHhUYCBBVKp0j/mYhSe7lBjMqHQkiY6IZgAOumSBaNIEFqLzC5k8Md6oi9WFdPFdtRfoEHsLheZXsyuta7DR5M1SXmcN29dY/z8U//NExFQfQXZcDZx4AJr7zP9eFSv/19fe37Oq1I4QJw1JU1gGRe5KBy1Hm89jAOi6m/q/8q7oAW80zQxcCs2K5E24GIAGFgi4EUehHBtLCGsrrLCGlYxOngR7Osl9Rnqn//NExCocOlawy5pYADkvtkvf7SEzKygYHGU+6HaNZTbnwYlrTGjdxwnuOH5SJ4ijmZyKq4GDZ97//3vfc3VZhGzr1f///2xN3//7zq+n//uR7CkqiARbkTTyACrQ+ZKQ//NExAwRsg7mV8soAwQfW1VuzAQZDOd/CSY75nHEa3kF/Mo4/5SL6lRU9UMV+hnK5H/K53qVtU/sSIh0hxAaLqqAEf7AFIH20BZN4VJI7PcHCyw8UB4LD1XqNm6yiQjD//NExBgR4L7yfkKSMiGxHK1/mq5X8KTkRTRFDfLN1AHmg7vBUzgyIjwTGiiNS9LQ7syIiJhz//y1VsrhWsDk9OaABAwGM4SNuYaSKxRbaDqoJgFfPVGjN/w9el0BE3Ne//NExCMSWNaY9h4GJJBhK6GgqOxL8q4sJQE/LFrCx3EsFXA0BQWfnTx0e4Tf9bv2yS6iNXhgAUjq+qocxhGc5PSaJULrWc73ZpyhArby9m/Zv+qWSqzUqqwCX9V+BRLG//NExCwQmW5cFGZGLI2ux2NfP/1woC3griUh9RtoSyf///1KA9yNxgCD8PN77oRHYhj2/tP9vF/32/76fd/Zq79g6bWIWTqLuHuIzsYQPond/wQiO93dthgWUh73tJAv//NExDwR8gZ0XggMjE4D8E1Vl634neTOLgBJJJJIB2gjIeYTGQBkhP+aG5Py08gxoIGp0vEzECok+SkSewhm3WFST2U2Q+XBBRVCFRBBysP4ggq6jHbLv99h9YgZn7RN//NExEcUmp7AfgBNDphitvHfTwfua7PylVv//////9+mq//7tqTdzCStKZmkYXIIkgeedgEeeiSVZpj3mk9rs+igCigTP5whZKW0l9Nu3+LCpXh1wM17Sg2Z1pjN5C/V//NExEcRoqqYABGHpXAAAPpIiSXRuUIo4GKEnPVWEWXRWU6MlKSEWzop/d8j0qynSzodjNOpwqzE6a6/V9qaNX1//22v/6uYKggQgW8aZqDyxt/CVQm8zNy7e6k/hEij//NExFMR0q7OXggEN+QPWYECwsqSwsCGfLT+xeNese0JlBp8AlBvIPcKxGg81d7LMzays7QngIyBQbP3hkGnE4krBFC9e9Ovfml7bbaWQADesJK7QwPOXrA5sxwAv43N//NExF4R8JLPHADMBPQEsnfSYJBvKKauO1EAtnfONNsQj8NwEioJ26+oCS4KEgPgbRvgdDZACBKTohQqCYbxlVttttHCBrXmnBPaTTkTVDKQL6NSp0rphyWFRw+F41bo//NExGkSIN7uWNZSUyIgkslQf9eiPBJCGDijWwr2dsVzmzsCZMogw/kOnY2ZhMlHd4u3DGPjFcAAgTlmNW/XARLjn9FhZX1tuRYCq6cvtJkNrqJc/ESs09FIzWzWzaP5//NExHMSUNLSUA5eGMpb/IBTz+w8wC9hXYUfCz4uQGfNxZaf7a2r/////MoVgAAUANEwWtqh+C4raYpoKV8KQQAdLvWuNFG4tvnc+zSNwLIiOVCxLopbNZX9jrO41+Vp//NExHwSEaLFjHhHTCyVNrPKUCx7+bVpnRUNf///9YwGQ0RVwIjbdiUldCmzxvGN/kEcFqrjwh/LCuiMUYjTn9dgCOxfI+Hv5ouLpEvOvjyTocrCAkvVl7f+rv/0f17E//NExIYSUQrB/oPOjI4Ct/AKZn08l////dLKwEVqRu7MC8D/i6oyWPQ5BWlgb2eETqsx5rx6hd+gFI6HnLeUnGcf1giBzOX7fI9CeSqysfDL/OH/AwUEQVewse8sWBpL//NExI8SWZLVvlvOXmWWGv87///laomm4zLLuKBi28NYhxlluVUhvHEoC5PxNqo2ETkpwp6PInOzgKj2ftWY2Jg0L0KIf20momYRqDDyhgwROIk2RBrf1u/////5GggC//NExJgTUXbNnnrGlnLbADfaO5yNmeSBh2LsTUHEQxtQAKSiMiMLklo39eWTX2Cbf/9V/s99Tm32KUFDgoCBI4jBMn3UaNuvCGLklzudQgwjJ0gQKgDA2K25znq7dfz1//NExJ0R4RrFvnmGjgfV25t1nyCwcBep//xB/hj+Xyhdb4ELUkjY1+W/XgGbZNJyZkAOAF+EW0E/BiACHYtc9A47c3sOXYgYbqKRvmqsVsN7FUrG4HU2ys6vR0eWst1m//NExKgagbKkXg5SDA0rDf0tbaciCTIXNGJ4qUKYtZkmZrPfHbLuvSksh0LGQ0ksCoPGad+t9Ci//7+l9baayqrdohrY7/wHtjyABomx4HgM3HAWAMVKjA7/pAQlYiAi//NExJEb4bKwXslezNdSYx4hbqM/N8fGWW0Gd+/7qvpqBFKRM76H1AP/xUTO2Gl25SqAhKzd1kuUURLOBcQHzgKaPP6ZlV24kGv/TRLXj2iRt/G0N//rZnwhDEG7z+/+//NExHQRUQcOfloOjlTjDkacg2Lek9trZ6f1xWaj////0YAIpVAUoAu168fWmUJCQMDYylpRu1ETWHZwIDdEQG3Uxd2HFHa4l+gp+QU/VpBpRYBRz40VboPbQ5HR2M/q//NExIEQuQrmXltSKp/7/MvURdTlpvqahQDb/skl8KBYPHXFa0wKBs6ZPUOKPjJ7Yqn0MUOTQmSAlGgqCoFInXhtGVrKwaJJWdz2SeMH4llixVQuDREBGvEr/f//lQV///NExJESYd6xtsiKmPlXMQA7naFLfMBrk6lOSa7ty4NRt9OWInD7smZ/oiFo8Teu7lX/ISHD6Fi5QEAxprD59K1h8MKBN9kpuKBiwhm1S//E/7mijpTcSuWAdySSSSSA//NExJoScGqhvhYSCCctuenAHAfHMyvEtXd8zYJ7VKTkRwTHuYztbfmjHYcGCxzYl8ft0MDA9TIiqfr1ZULEIiRLNSFiF99s/u2Zn8bmNx0Tk+7CyEwifYcYcsFmgAru//NExKMSIOqRvmDEsGj+n5ppXc4Rf/Ev13efOfav92P1/t+cmr6nIEEQ8eqI1bM0skwmE6YJr3fcMZSjyZlVHTy1PNiW9UMfV3jy7EqJ5w20Ed1lcnJmHqRJFuph2c3L//NExK0eGwbFvmDFx660kA0CJGBI0BkmHxtQuU5o+R+AigUbhgZRAcFDILg2ycBQhFTKB5jBjP563Wf+FaL7HNWRXRXP1IyuVFb94QiN/vTncswwGUXAeORQu4wKW5LC//NExIcfKmqYANJE/C7aQ4BtNYjwQIpVKlIo1lLIJ4wX6k10Z8o3ezU5qWMKSWUk9AmZHeeXUvkE5lDHcovaS02svJKUcFdqP//7kGEcpbXVTgAh9cEAG0/IHh9Gse9D//NExF0SOarNtoFHFAxDjIVGsB+GTSmqRia0+NJJmr4KnFdSD+xuHPMWduNMUE1C0yXbsrfR9FICCr2IWlcc+0zVohwt3pzjeFF1fwNBBuHbA3Stcq8Xc+jgQdQCi3KA//NExGcSCObqVlvEdhrPlRixpcAx3cwqHk88UJ1LZqDchS44+L1GkMAWGqneU0fdV8gulX///1IhiBbBKAAm95hZbX3vlFOQALRttHalcKNZq5q33N3P9LIX4bGc443B//NExHESKRLaXkvOSL1k6w4Cn/xOfrl/lhUM38l/nWAbT8jUd9R76lstk4AGLkaUgAByr49ZM6Gp6tHC7yAIfZoiRiWbukCxqKxGiauOVKMUSahNefMWNBURFWJlWlCu//NExHsRgNa6Lg4eEInLyoa/8BaJ4S5KVBVzRKWBqplExReal3AAWZypTvKC8A1XCuxHyljssMgATjLaJDQ97b4J5X1qrzHUNa4eliflnHNwbMigduDbsXp/0IGdwPu///NExIgR+Lq9njYSCgweVfDMm/4aBLnFwAC/O1ow6R8XqXbsNhBwAsHTGg2Lum/wWEIGy+in4AYI4b965EieajAyKLXR8Rfh3KKId7+3o/r7/+rqdAw/y7xAA6fkFUmp//NExJMSAU6dvtPEPFtyBy2ga5/sjkk/KHxTsDIXekUDqKIP1smZgV05SjWBUQRuQIJQt9zhALKJQ4QrZL/73t9vX//RkIIHRv8ggOKGAN2Xf6pZRYDPhb++T//hi3AY//NExJ4SEWKcdtJE5IIHLvUON2eQUZz6OMg0ZL5lRkzE+KBHEUd6AcFAaX6GsMRF/H9QrabjmQ5G5iSpHS2b/////1RXYRMUJDrKl6TREOT4qYV9TDx4j+KqgQBc38cu//NExKgWIerVvsmE4oBT4gI5buzjhkiNZnE2coFoepSBl/Oz6FOAsitFEcjLYsSjozbf7f7fylM9f4Z4UoahzxtQNCQFQl+BQ7///pqqKm21kgAFqqY/iXWLqMUJYUu3//NExKISGZqoIsjK5KZyHKVlCQnxSiscE11Kk2fax9mTTVNqsoUOdVnzaMvSq2q3t/q3qpciwUwFDWs6VCoKuJBzxLrqBgvSUFIThAMV6hAJZ0zRUysgWY0wgGmGdnIH//NExKwRkZrZvnmEirYUwXBGgrEXsS1CAIwTZFng0PBVynoXF7bHfNzmx6VHlhVZLR66Pq6KEBhNsbmr5E4CRC+AagZQeXN7DDjBY4sV+rVTGtTZ5VwVEp4KB0shy1Lv//NExLgSUVaofnpGll023u23enp15HK5qLfxFRrp57rr6/T7agEIIQIBCGCBSS2O21OAETZxnIbMkc6mMuPBKR6kBN8ZA3JgBjDexx+TxUWsql8nw9z8zEGDllsjw/EN//NExMEQ4HJIEM6SMAA1MML/iUgbYDeJssEQAZmJErFwq/yfOEEFICdDpiQYsD5CzZoeGY/5sThPrdzA8gQSQRNA+msn//6H/mBmVycZEvma0/7v7eTBMhWyAkgYDKMl//NExNAQUF48JVgAAJFRqWkEoAn0dKqT1SDUkI+ifMFwnCBLR4aDihQyx/DzHQdZsnhlch4orcMLWt+20ZPBd6gNmnOXWFu2ZswXNRu5aeJEnbHDzQmfcHEK2Y7HPPJm//NExOEhmmJ0+5mAABRIMfGrazE1vFaa+/uPE+dY+aZvv5ximM6xTEO/1jf/xLm1/q//8W7DKv//Mfw4gDIalqnLBiN/85JC5vNxJGItxcY//ta6E5/mMZX+h/QrC08M//NExK0iOkrKX5h4ABA75VDBwZ1UpUOiylKYqI5SzM/Xbardm/+aOgKrBAPgFi01//0YNhE855CsOvSaJ8AE8GtaAc0FRmTOBbIfPJPWpMgHY4t0BRxIYV9JmFHS9SCq//NExHcU+ebeN88QAqX/RK6rQwF8Y9W182oUXiUFQRDVZ26CoLA0PcJfip3Br9///4Knu5UI8QIArbkMpZAIwTgRMMZgszhdlK5TORSZyc5cohOT5n/nVVfnEgpLWONm//NExHYSkSKtljPGLH+fVcpJ88scRgk8FVh3hwjUDWGqzstqHnYiPLcSFUBJn0UBVUTyGCDFoGu2BurK6LqfxrnLXnBiRoKQJDnlXMCSHSMNKKhkyUoZJZJAst1DmLqd//NExH4SAQpoUGZMEKn0PkXVJ+p9HUzd1uq+t1YL0JshiAZFCfxlK6tvn3hQsTwewLyX+vyT2Xx4+lN0dw44YKOOBECPcQJnBBcw5gNIYz+t/3//klOp1Agcieo4AQbD//NExIkReGI4AMZMEG0KGdkjeQOXRtIMACc+v8QO/Eot4X8IDKE8J3iXB9egAWENJNItIIiKQC8S5BCyZnkLzWJpuGQwQQFzQPGNYQecB+feJzRQHz438TvbBzUNBAa+//NExJYPkTpICHhGuBkQF5N6wfKVYprsARRcDHfN256WXMIbDgBRhCQGHITd/+Pl787GTcOxMnt9z73HTaDx7FkJsqd93B5NjMJrg9ZhZe060Ive2HpwhLwsQOLP5ftE//NExKoXmXZsAEjMtAXfv//3+xK+//4LzD88e7wJDhQUXv0mHZhegRZuK4MBFIrTINH39QNMd3lAbp3UUIuZQpOmfBkhfC/mp9zYrGUyMXF9BaAA0DhdHmfp///TZCNp//NExJ4UeZqUAEYMKJtbHBAKA6S9NhvMhrLAF2A7l3Yf9F2FIm1X4kEDf7n9EsYcafVHkMC200LpUvc3tz2MvvSrqb7XBFBQ//1jP/////68FvpVrBVziK10MBGn5gF///NExJ8SOY7JlMIGlLfydpOly5xV0hhyFmt7/pCUgN9L/X8Jjfx/BhxfoYjo2U1dDHkVwYaAguLgiPq9ccaChl/LEUf///1KL0L4UtpADAgDi37NJIvCgm5MshKEhETi//NExKkSUScK/ovWjuRgu9/GDwhsnyKlFsYnsco9EUk4tJYw06JjpoNTIBDQsJygQ+kNMu/////ZpSTYH/EdzBh6AI8HgztrkULaGRDN6qoEIkdM9qlI2Ehb4lVJT/VQ//NExLISKSbuVkPEdqk59IGUIuqowdGBISiIUOg0aOocyTuGIPzyBXhB6HFF////0FvhRZSUtiWr7lYB2SLsnBdxaDgQNntXWsSBVDvsJB1vOqGPpNVWH9VVX9stgtAS//NExLwR6PbaNhsQLBcqVoAQNQVLDniUJLBY89x1pHhzfZpLUryp35b/LfSqDFwJUg84pdQG1l1jGswA4hSXjlLy9HBM+SlaqhRPzTGUrVKZyllUBGLXqWhjcxjNmMbz//NExMcSQPrWNmrGcBv+ht6hTsS/6gZ1P6P+DLlnfWd0ZJMyAgBEIJWlzzXEXBwExsQlZoqJZW5G1DRwn9L47vQGR62KjM+b+hD2BBRQSvWQMBJIqPFWqmgaAD00u/6v//NExNESiQrSNmFGjs7nP6Nu//6lEFE4CZngXtsTpl2ZjpIClQIeHReIr65RrhDH4KAnTGp86tTHqpyOkzPbMz0520bsn9vLMvwm5JCtarOjBtZjryx+c6dmcnv35nNt//NExNkSOZaafnmEaPMG2bgZeXInnI3H1h850dY9P6AAsBi5a6FTGMAwZxiJ0NvmNQ8HCxLRL1VziNIToOTpDBgJaow75u8+/CXmyWCZ3JOf9f+UrnpUpjAQ4eumJcYd//NExOMRINpECMvETGiRxyTras7F0Bp9CWvVW4oqiDfo0p9DIHGG9zm6K9CRfgYKRUMEGgIkO8mEka1X54Fw5ZmGH6maWvT8ub6nulmtV/u8xjFvH53Xax1ft0v1Fz4c//NExPEW8dJQOnmYUAA5lIo4gH6HrGsWF1TknKSBcKvTAai9xM//W+T9Y8LHGhYBoU5JQvXf+SuzMPqwIw7bOmMg4FlUpdYEEhpAo6trHJRXXf+iT/j5TSfMrKoGbr5g//NExOgUiT5YFOMEjIN0CffmZPpWcmBmDpxEsCRgKgxLCJSJkrl8wMExSAggXUkJZFwGi6zcihZz6Gej+pN9I5ohUAwtMYqD8v6f//mN6GnzCA0IJUmoLxsWQ8SyZxQD//NExOgaWUJkAO6EWMH1KqQlFZ4jfff4AqNVY+i93DoHludKb9ZS6hZpPrY1ZbnBjh4SqMxmJfyQNn/tucBb+1DAoQerbt51Ubx4vO/hpoNrO5MCIwGTTd3p02c61r4A//NExNEgCt6IKtxO3H1r5z//Ff8s70CQGrHvyWTya62MCC/vl38Gjq/5/pl/8Q64ZDztPsrJROuWSdO7w7gD/aAHJudfkNuQC7ZpcsUbxcOHe2CGAQVm15SRl6krZgCo//NExKMgwtbyfm4Xa03/lqFtn/xxsTUg5bC6uOvdFlucv9wSbT/zt4wBW4mIF6B1lcPh5jeX0M/Yz/9e9y6EUqUIcVZu+Rn9f//mS9FElDLDVfG1oZvqot62dtgKDKn+//NExHMZmrq+fsPKfLBa4cX7ebZEVSID53pci6r4Uo1mj+tz+DsDw7R7cnwuzOoRkfftGedzNge+7DO2gUSm0rZQETcoEUv//Rr//ylNR7KGDijlAZaLjIs/f/ESm8RJ//NExF8Y+gK+fsMEtDxZ7oiQAIJICEOWs+VOCCQ2MG48N8KTidVTELvDzq0rH5p5oEIigFH47WxWtnqvSs9U/r89iW/1Yh3CRqTW8XDrb01sOPVtpR/tg3qIUsQbkZYn//NExE4ZKVZ1ku6WOC9YmqfVtxE+brXBoDIRnutvuob9jfx1Ya8ZmaNb9/gMM9/dQnqw1sfp04ijbmO3gntLBsMH0MK5lYaqing1f5iZN7gm1cb+reX0TxvBv2E+v//r//NExDwTygrWfsLEsur+jrytO4YYZKM2+Nov1Y5v/86qQSzu3/1v4ACbKlABQLWb5Nk4hAWKDKSN1AjYUiN/zcmFvAod48InhwzNVNQbiuhB/b5d7t1a2T5v//9WVtnr//NExD8R4gbOXoPEP0L97rCsK4S3qjHLGpIAAZAyGwJ4Hbq8p6S5qo6xIKD1dhgm9li0pHuYsL4UmIkHp6UkdzhlYuYeigES56tdlDFDwCFYpFBX3VW3zoroLqBh6RNV//NExEoSSMKcfjZYBjT5KJAyNlAVrgshgLKIOcNciEDMUAasI2s8Sh0CPNIYoEIlsGh+pnq4gD6HPKh+o5UJ3sSv4YIuuOdFZ+8aUd3fD6FAgCCfobViXvwLFjnCGgyC//NExFMR8FJ8KuPWKHk7AMIbz6SBww6iJE/21qf/yaSNZT/E2jvyL2ghgAwCBwCwwJwAYnFCwAAUhEGgLhGjoowxO/0RP//d4/uoUFYKxHUFhou72k/8JUU+Y/8fP/f8//NExF4awsaUANFQmCS7i56Tf1ZYFHOTyhDLdazBJ8F1YIRnOboSRgXVJEGa6//5L6kRrJvzD6ayV3veq55omeHlw2LAPxQAyqTxEAhFAkGI6w9gS6SCJovoomp1naO+//NExEYaolKkAMhWsPuv//3dWqd81JI6qLcgThyIvq55+Lnc1cUb9ryD0EgLBtaH+XWAtO6WRlO8JYlQhd/E0xsycMbm2t89x45xcUCKhACtaEVvlvRi3rKVZ49PgaKk//NExC4R0RLmXE4QKodsSkNPNErxo0mphL8mT/9YugU/lXN//3JVwidaRNhPCze5bRKs8gw1PPFtRQcBNv2uLUOTIPWO06cjvOWHCm3KXb9MrTblrhgxgaHFjfxYPfpZ//NExDkR+UK9tsPESNLE1C1AjPXs//KwOz+RJCAc981utbwtnB8puNkNYRpSuR3CMFivE3vKwj+Pt9U1vsIw83QUPA1RFn2LmM03XR7/9+JHVRBEHbZFR70f1EVWHT06//NExEQSIVrCXHpKkPd///66ZLU3lv92loGt0lTkTtQ/gQbO1Jq3fraNxatKxg4NArrfX6UVreq7RcZzFL5jZUOXvfon/0hApJgv+zyz/+5HuJf/40gtSX0EK6va7AX8//NExE4RqU7qXnsEdq1LRDgE/FhJDEKxkICJEHgBAIinfdoY49BDGa4olysSYzs3V/6b8n0RlbYwMc40HTvod513le9giDv3//xXcBQLQhVMHfP7jgWb2WCMwNmItQ5K//NExFoSUVagfsGEcOlWCHgy9L3cpVAz99/2NNowN/Zr/0nP738/jSzNllknn9v8YGPMg2AZN6tqnBXtf25X////TUuJFQQ5o3bsBYxCmbgYKSHNoJQHOJKH3h8cEV////NExGMSEV6kftDM2OSAgAHF3eHPrlySEm6QWUQMViNFmRHGBXO4lAhkGvilaDDB7ZJ6tSRS1DqP/r/QwAEbubd34FSvb1ddg0Nnyx3ZsPSHB2sxSdbJSoB8/RR9L55N//NExG0SOJ6YfjbQDOZsdgTN8c1ITK/M4YOU+TymoMYY/9UAOifW+oMKl3o/v/oA451RzaJ11bX63GSAJOBWSIct14CjZg5+EVVGRsVBc3UfEpfNjDfYrQAkKn4oKgqx//NExHcTSN61vshYhLepgWx/+vX9CsE1vekAUMM5qRASI0Pgg0UT+Fjpc/zNRI8UAaJdgQ3f/+JjA9n5cYqp3DOIEKJ2EPvU5PBYA7iBorHULFW6m9foVudDNxNEtx7z//NExHwWWVqcANnSjH+DxWa4OPACU0etS6yyZQoDDSekiD+1Ywkx3voIm+00AP//oLPCibPlaoABKvMTEGr0B68JmHnoBXCiltp2TrdZYCBaj3WiaTvnCMjGQvnM5sos//NExHUS0WKsAMlMlM/v0KW04Iwt7hcha3rgIq7/1AhIo+M+jRi0Iipi4YK1o4Mq6hsgI9AKlqn+uQFY3Vl3YATREv2Pah2GSMYutZMKwZTt+pi8eS3BJ/iWkNTITLgQ//NExHwSGSLSfmsEjDQYBw94s5TftyomMBQ2Kud7P/8J0pbQYgk3ttYLzCPGv0yJMaZyK/kaOok6VuNZFWvlBYLB1igoQhFU21tePiAKuBU8sFYqCusiDR7qPLDpGR+z//NExIYSeKbOfsLaaPs4uCwNHi3///24igGMmc5b1T0cDDmEvaQdIaxCNYceZNhp9FN2WKcUzQ07/67/4KEU8guJPyeC6p6k9W/6sZ8c89p7rVS1gxSPtNvDP//zS9P0//NExI8R8I7OXHsEjt8UdQCjpNY0JQBavV64gTHxENXtyx2BlGNET8oixhE9ZLfTJIgxowLIMRjADpt1RDGcraxzRe0NhFjoKVNg6woldn//8ug6QexdptUNtS2z20AU//NExJoSaUqqftJErPKvCxEKYkOdtyHKq0ZhZbVFjO+qlNUrXcxStcY/13R5DCVLF3t/uYWQB3A+jX1Nb12lnioB/yPEQNSqQVdSVrcxMQcgK7RSrNGMMJPZRAyVlrMU//NExKMSELKZvtPSZMYtsqKI0UBMSi29Zdxx//yJNVYYWvhm//////r1NJFha4b2b+eCgVALB6Kmt/+yOrJf5t7EuALq1ZEmbXbbaLdFqxqIw4AFcHwuBPzsF4yGWWwY//NExK0R8Xa5HnlYvg0qwD+ti1lOEEuPGjxowHkwxjzWqRGzPnqyGIXUXi2YYxORk7HnAsAVBpaPxZFcWB4SD8fk5IBTAbE8AQAg4riGF6kJhOv/HSRxeDeW2EYfmFRE//NExLgSkVJcNVpAABJ//9XJzTBoNyT9nkaf///0//zGkY/qVbutuNt0D+0JXhHDwa14aCTR7BLlSYj5YXcZweK2M2HiqqO7oVhCM6lYiUZqHd//3V1IjV5jnVEdXP1y//NExMAg6xbOX49QAyH17n///62gyCC5Aj/+lOWGFSJkkDi1IsjXZHoSTgEUhlYQFiUbEurU40ZnMWpVriZ0KILaEROpC/4LAPMMj81CIvsX8NzZnQ8tgBZym53cEAQ4//NExI8U8hrZt88QAmsPxUQI/rFmg+oS8FRrf/rppLh6J3zUkHx9oRju2sRLcgAGjX2YIsDXvEo3TGf/HkVFP5USwMngYWAJ9UrFwsQmDCnVifyy54uBjQEMmkOM+GzT//NExI4VKV7JtjYGDtHqvHY5hkA+K1f+1aDQIAJAAa+3YqiFtfdQVHoA3ajfBugZUH/7k9YNHmQcLIfVRQISyl8ximskyuhjOzv///oZ2kMJO1PoNwL6vvijGZetYB/n//NExIwTaMLmXjPGGr6To9VNgAHv39wCPoBROKyaAjAFztaeqgiDAaYVsUl9BEEA5yZhquj6+pf2TM5Vcqpsj8xuhSlZ8v///0ysnp9qVb6PVTf////t2Ug/Ay3AbWba//NExJEQqVLmXnmKhrkloDdp7/VvCTJSnV+RBufURvQCIE9qvVAyH8+qD5AomD+LlcWh0FVHu0gCrpGr9M7X4dJHSw6s6RJ6vWJHSGskhuoSqoCVDjSsLQCI3Kuq8FFQ//NExKEScuK6XppKSFNvkWtLw5IH0KgHEfTvaZkqOf7DgJG+XqHEmO8q9LOhp+Rkn7w61O4Jhw64MFSen/6PT4YEf0dv6HLtqqbOkziCfpu4jaC7YEbuzwuQio+sZy4Y//NExKoSCKLFvnpMUsZeNEk/ZV///5oAEfj/k9MACDmINEQ+xnjD01Bgjyi/wwYeCAINAAITn//4fOLT/9n91VUrNOxrsX0xs11AykJLLakYxvjmRciIhP/aiMtOn1iu//NExLQScT6ZPssEVPlXfc+kUaeBQiCgSgEBoH4wUKFQ7BsW4doep2UzxUVcTwY9f/////tXFWXJDX//6S5lsDpkIWW22Jx2Ab9YJWzni4uL3QxIJCZtWNzVj/+/+mr6//NExL0ReXqcAMhMuEPQwGkWfDJuYcy+cQmQt6+Qchgle07mGIG8G3ub/7VMSBQRC9wun//U/RWBGXSeEk6AzDwS+CMCDEwuGvt1vdf9opdMYk7mVSoqEA+MNXoHlpAU//NExMoV6iK0KsCQtC3SVDOJVJPXqDbkuJAH/apDxoKgUAjf/9/PBkDLec0qZL3++tZUslG4wFU4AWeMohBJy8GCJNPNIU2o4PoVBYW2UcLGiJQgZFjJ/aMC+x4zebS+//NExMUSWZL6XjPGQp0pfZakK/yJW1oTBTi///yPpo0ZttZGk5JhO2aR7oTHsmhV+zSoE+KduIQx5Jl9nf/lbuGrtjHV/ecbUCbBRnO7X3bkSIekKGGZG4UQ5T//5/mh//NExM4R2IrdtgpMDs//+oaolQqHU1f/80y7U9cAIxtRSgFvKXUTRWxSckEMcyiFBHQNM0wnGA5jpiugAhjMpC1sf9DNRSuDoJCQ4ggj35vJsJ+lmz/3uwgUYcqMd3u0//NExNkRMILyXjPETlzDX/UsgAvFf/34OzTpxipGKTtqAUBJ4KL0tRiYM89H9vk3DJKGgUJal6+1QKDuujI8eiuE2HQl8l3V5o8fGIwwgKk59yhuDM1KVTypNTgP3NzB//NExOcUOjrmXsBHHqyDBMEFvFANrwod//iFx1Oq5AAbgNub7hVLdPMT4H5NvyqAR9rBCKiUs2oCgG5GwMEk/V1XYa0llN11Pyhof1an5Fb/68jWQ6MiBBsRvBFqPyhU//NExOkUiV61rnsGhHoJoipFrnNvF3f/3rGUyjLQEZGmcDB6TnvKYlgHGN5xMZFqXbwHK1yS8BQAGJWNftUjJmZVZ8YKCNi5rHWH+WcTpa887FvRvL47FSrGW96crGaY//NExOkU8VqkIspG0N7Zn6aOwkGhUkAlLSi/d//y1YOR0Mjl2AR0TLsB0SUdL5IwcUvRLNKnSAgYR2t/6VUibrXOBZcuMUNaZRZD+ND8os7hnsOiuRdadDQdSvF4cXDp//NExOgUcW7KPnsGaGlSKox93f0rEt6Tz2liWSPKK7GgSyX4CTYNLGCgCXJRIWEosajNmPVQGwyl7OkakcFYZ1QMKpft/VFHedk6L6U3ZMFBhVXRXRX+07E3pvhX/Qd5//NExOkVGjK9lmDE3sLy6aN4NN4/7eK/+f+P7it1USlWVciR6UoLccTC6jKVQsqMnGBRLUc7UcS1iSWzn7UiJrhIQmZko0Bo1FmKFkBPQJY5+RDqFlhwdCdyJUNKW6OH//NExOcUWV6hnkvGIGiwVvtbYn+z+ONr/Q4G3J2FQqgxKNdm/USpmcUjyM1pywM9wJsLj6GMOsE8qb/1ODZJNBpJ4BS+8WRi8lndoqKvln+MmI37HrGzvZONnOnie0mZ//NExOgUmQKJnjGGLeoEIg0gV/dX5zITdtWpXGjXesp6Fmv53cT7aYtSxdM5HKBcmkM7wohInSZWlciykOo+pkLWHkcfdJNUnKTnC0qZXPI0mt5tQbHJ6sXpuAGDQDPa//NExOgTwOY4AHmSkEyeIeKkmcMXaYoCA66ptQOdMToC8ou9Y9anCcjq3hI5o5FUOymzdJyzXsPx4z1nQjJ0Trt1tGAeM83UG21TBZ9Kob0owXpfhEX4BfTdZuc2cqKA//NExOwT6KoUAEjGBapV/v4LKUEm+wZLzFTlThw0wzEJ8nwzM4VeL7cY/qxvYMTVGZlRdSpSq1AVVVgZUY+gJU/2ZhVP1Lqlxj6pK6w4e3Sb6v1V+Gqs3xjJijHqRrxt//NExO8UokYQAFhGCbhrG4y+xNzDCsuq8CiqTH1AEhrMjMv/8yL/RURepiggSkduiL3ZFVP1VP//+5TAwZDs+iqi96f/7lMqkdn/3KYKCBByPmKCQSGjQq3VTEFNRTMu//NExO8UeSoQBFBGBzEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExPAV6u4AADBGbTEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExOoPetWQDAgFBDEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVV//2mlTTT//NExKwAAANIAAAAAEnaaaW000tpppNNNNJppppNNNNEymMOMOMTKYw4gWMTKYw4hyIyMjIyIyMjIyIyMjIyIyMjIyEihhxhYgcYYUMOMLEDjDChhxhYgWMMKGHGSLKq//NExKwAAANIAAAAAKolRZZIGBCxzt4DAadn7fvVAoSZ8rF9QIMRsLkZPJAgxdAxD0gYXbQChiyNpBc57CyMVisVo2EBIxiiB02MXFcoLoyM8Rtz1RBbcV9pQUChBFhG//NExKwAAANIAAAAAN0xkIYuFw2jRo0aNvFxWjpjz251bdkYrRoEDEEDiMVt5WUgYtHtz5QEHT/tGj2EGEyd00hQSQUQIEaPVCAky13I96jC4+PVEtCmLIGl4wpW7eok//NExP8XusEEAAhGvQ2Ui3p9RPmrJIdUmB4qL0sqyr1SqPlOAIm4sqGWv2EBBD9TQ5hync00oojZ+owsqsVqFyRwnzSHKNzksUpPSaJ9GHMQZAqNNOaE9K8npThypHmx//NExPMkyxHgAnmSC0ZRy7IG10aJlpj7raDzJAoy0ZOs9FMtNAgimrCGqWWnRBUVopHkmALvVo85rmpuYicfCTdSVEnpHWkirSRhNnhenIVZule0Z129XsVaUvLJ55SL//NExLIgExYAAHmMCWq3XfJzWvPfD0+uITMb6hOnvCnzs6ZXVp1WrGWXtsBPOpvd1ebnubdjFVENfLyHMZ2v0kpJubCe3c7E0XjFr30WuCv0TudKFQIEFIIJAhAAfpMM//NExIQeEx4Rj0swACGdamXxpATeuhFgD51tW8BTJdlr23IObIGtVStFcc+NApE59dDx2CC5JkPJIii36rrTpoMfHIFwDwYOOu2v1p/xW5bGQmhOHBmBm9aaH6/0ENmN//NExF4gIyo9jZOAANjpDxxkUPDlixmBfKjV20Gvbr9/7ZaN0jRRXMCcPoIkTJhl5K/eHvJ9r6PyYo0B96aWB45tGh7r8QEkYIs/8dWP5//pVfj23e3iiyBgMwpI8JAi//NExDASMW7IAZhAALEb93vt3LE4nuCJGjwF6k1PLPecO/8/1GmgFZZZ1qtyAZ9P8NTjW29wj2QZYkKZtSG8b4hqUSigOweQMH+KNQSQRDRqqdni9lsYzb/+7vnSJr5U//NExDoSKQL2d89YAu79BOhfJs//91JH////WmARHJH3ctAVw/JEoamIYESyJ4lD1YCFMzMFASh6gJ0NCI85YKg0RLCVxaHQ0oGnuEoDBUGga/Kvin1dL3rCYzLBQ9////NExEQSgI7aVjpGKi3fKuy0FVdqSicpd5VALfuAd7BfgYFNVxCWDlDBQMUAFHMlv1JZlD0tjkZeX2rt17JVCz/lfaIhUuhg0RIY9ZoQgZOE0YoUJKhZih3LVcFg01JC//NExE0dMjpgRMpE3ISFDlxih1Dkt9sFAnlKxv+yF9DKWXKUrZSsoUSDTf/4az2OCp1x2JYgGDgkHOS9oIJBYYMsTIuTzukJwUasQKHJBM9AYYo51HDNeE1Q4RXZwmyK//NExCsWISY8DNYGTGRE2DZM4Y2VyUjQKc5NcyzIyDjEioGsz1K0SgtYAcMKLQ0xdik/yu/pW/ru/uoRDQdQhhkjJMxZo4UgKqjFuQqcQJo5xhfd+XPdasmAabIrvf3s//NExCURIKZECM6MEJ3RaafxmVUhDXLqODFqHshEeiECSmpU1LHWelNmK/6aiKVawqIAqZTh8vNTikwEAB4Dr2TvMGhFZ8SpJA6DJAvswZN145PT9MIAqE8LrEnRdAz9//NExDMW2TZsAOGGqCFMOLhH5ehTiAAzBOfJpOT72y6z/nDjRULn1irwiPdy9QD/5Sov/KU15Yp4AFATEjOPA4hzlBMcdlBg2nSqDi3PvZ0jwQJKKrULzm9S9uytnGFi//NExCoamgagAMsE3M5zb5R9hu9jCJhY8YON2cudqyWuPLttCQJB5dekPDgkCREVw8kcBEPHK/NJvM0xrkIQhP/t1QnoAOLrDH////KKjBQtttttooFDnSjqSWExHXzI//NExBISMgsGXmsVSne/WTX+e1VGx71n/ZxX2T1iUretWHASRZvZdAza4uM7WsgrBfAoa9f1fo7f//r6D5sXf////6qxNVmh3aKk1o1qsj0YYL62/mxMUt7Vwxj6jf/B//NExBwRkQb6fnnFIvs7G9nkJ4x6zjcAgKpbYIBKV+X83kAXbvgX/nv/lDzWOyv/z2JdnymLhyqAsNuuNOWcASS4+yAiZrOHHzM0b+sj+uv/aFuWAoGK1tkJ5OblK+Qm//NExCgRiVbaXnhHCurALnant+ZR/jgMeCv3HVevscxyCpZ0uQ2WOkEFSNWAIV2xyyUAF8e9IOqFZvymF5qMrM/3B+B22ZgPxvfUkCjfbUWTU1cude0sj8mIlLfWHuXS//NExDQSOVbBvprGfml2phHB3/7o6V1qAwNsO3SgCkyv1IQnUZni3/b4AxU1QfwzeM4LJ7uKgKn54Uy84CI6eiiG8fiyZlKfH9Ct5ehA7N7vgghff6//I1mv87vxQdHK//NExD4SEf7ifmqElhl7pV0NP1eyv/oqYByuv1lttABmRuD2D9tGcJsLUveQES/YZEZFpwHnewwFBSXCu03LyWsgAa+n/VkHld78gJz1LL6KC5cwtYfE6SdUCiBxQnf1//NExEgSaVLWXmoElpRVccnMI/Pu4KBVRZ1FnvN/VKKzQuKCA4HMTVPs2pDrWCoXWqCDnP+jetPXV6tIzc5Agg4GBi0ZFA3BBxc/E84GCH+f/riBTv6FgUgkkbcAQyZh//NExFER4Z6scsDEeNq2b7+mrv///u7/GzHQ9ZznOc/UsZig1CgeHwL2ODot5mCQ2QCQVNtHjWjU2NDVqnqvpYhQTLqU4mAUn+HOtQeAqguqj1AAqj1UR8qbt2oRKT71//NExFwR4bbl/hAQlhXQeEdOnD3KhhSKf/8k5fJvzkhf+ZZbS2RQzTA9sYIOpJdie6yxnU6zIFEQyz9/IDiZmaqnaVgDhVpFiSnJTd33rnyGf3d/qSXlbiBHG3YXPsDy//NExGcQ+Y7DHhAGoAeXYRemo85tDmscKstfSTE4GCx51z3vRujWe0jlnkVLSBK2VLp3bbbRxgAgLJ/BUOb+GHSy3jIJaqmZlucNyCna5HhedKtf8pVOFhJAgJCwkEZM//NExHYR4MK/HAmGACQjqF5SBBntHInIxW9jwYnPdVeHmJd1TAN45RdqgNL5g1RCROTsoouYAEx8pAnBxoYIEoGDJc4ueYibZ5dCGGQgDg9HRQY4vgWS7uo0yIwiBAGm//NExIEP6Nb2WA6SFm17ASsZ5oxcKQlBinFu39I4pYAIAgYtgEk0KgvEOAbhnAsohSK5DAGxD18divi3ugUArd6QCCZtT6MCmt/todRgQ88p8gZc5NeKmXC5Kre3+qKt//NExJQUoM7/EOZexwSJSz/9X3t9Z0wI1aSawk5Y3JrhJuCMOdAYC2fwL0Ta1/5A+IV8exsR9/GRN2besXPtwzT6eBpFoKG81fX7fdDlq/zfMfNc8lqf671fJBoQJDjC//NExJQTEMbF/pvSwH///onhYmqABAF+2peAN5Y/dHXsV/+8TmUIv83QDkXO3r44vuctbmgzWdqCmNB1rsgxxPOg1znSuTXdUf0N7+qP3STCF5N3KqGdqp/XIVXLnb/s//NExJoTWZ7uXlPOeqjEGKFU18QEakbUtgpj9wAplT+w8lvqiMCMte1I9/IodXYWAiXrEjfmao04o4QQ4UbS2eZPAUdStbs7+bURkX9okDCO2QWi5RyYu9TK1iRaYqMx//NExJ8UejbCPsLE7CEhKwZu1KYtCVmhk8DwM/15lbZp6zOPQzL3wzCeumNYMq1IWybJLLR0Q16aK2uZOZeb8pW79W6L/9/9n+vS7G3sQr1sdwhIJchGNEGi7cGTZxMN//NExKASaNrVnlmE4tsjTcdwAL7Ik6q5yQrnAISrjKuZOwxoYIWpwEOstnSMJUhEgIiIuZeKFh5kiejyCMHlQrxGRdRYg2sz/8kjWuFeWT+BSp4NuS2yOJ2AAMDEOT7M//NExKkVOs6MAHsEPMwJaEAZfP2CqzCDNsSLIzMYEBw8sOBsNsYDag2TG7q6i4joTFi3SgiAHZUsMMZE/d+7rlVpUNLKNKos0gZbJ5CbcSASdyQJlDFYFAghl5fY8mTC//NExKcRwKKVvAmGCP2QeoIKj2pH60Z+8RlkwIGKYIZRaxo8H2lHEAufE9anX3aNETvJweb/oRcqEMXeetZr91VS22RuSSTVm3jNjg470YuCqo3CHE5CUmatOZUG2zP0//NExLMSOLKOXgCGAKQDB3WkM9Ffse8+kOP/vEqsmxR+8PxCIkJOnmAkBKG6HlX6QyI/YwIVraeT1Xk9oPyBY/lEU6n+KT6/adU01Sosyp976WMEIQau2dW31RTPCqMq//NExL0SiMqWVgpMCBE4oclZhHhz10B8pqVEMmD0369EIt/RPqt7uG1CuDdVtn8hyCTklrLZsQ6PrvhL/90CTbuWRxzdHjKlJphBps2lwALhWwIUfasWeG0uy0hCgyV5//NExMUW0W7aWNPM04Aliw19V4dJJq5vcmaE/4UiN+bWqY1L7xdChTM8f7dKtSi9oYeKAnKBlqhY2ke7t///////QoEIMABUAqABAj6qkKRe2/iBIklDx4AGc/ml5LYV//NExLwVoT62UNPM7bH1fwSPt/QoIlM/ifT63nsFoOITac0bjEZq8S4dsP1ZQ8om+r5ZTyu0rF7I3VeGgcEOe+Mj5Cbib+yCqHDfgwwqj6ZJbmeL7GZ3xoEV9XbxD4u7//NExLgR6TrJlIvEsG2AAlb9A722Q/na5w/1b//p3V7c3nAVGrb8CtB7///+iIqchFWtXaqsY0923NqBBcKZkDYBPPdeGMYZ6obZQxsmU3uIobusM6AF+/QgZYn+dUIw//NExMMR8N7CXhYeAGknkzBYAypGJtip0QCabXh/bury51CMnh6p3p0B2Q/fCf9EVy6pAFZ/qUYVUSGRoB2hUvoF2Z3linG1HPWo6PAImyOZ5hgiTMbor4Tq3h0ig6Zr//NExM4TqZLNlnrFJuHogq3X2hoWbSkjzrxERbz0Xapxv9g9U8Q/+zcKozybtnNjNOS2Z//2/05Z56v6hp82MFKg4S0RC0gCiLrMKBRrps9qoIYl9Fltw2kut1bDaN5L//NExNIV0OrqXnsejpZdjv05AJYtBT3tipQUF5p4GQw2eRoYlcY/XLniuJd++TOy+S2wodUvXhGgz///slnKaj2E3jJAcIBkC1kIDMpb+6xKRaEXsduFWKtDX1whMGWr//NExM0WOZrC/sPKmMSZItywIxdoG6UoP6NmmFw4wlBd4kHCvUTAxbTP7a7/9W+/OZ+IYjZAX///////dYCeACtIV0wgt85Bnht80iAcI6wq+mj3sL5ZpfT9PTKMFMs9//NExMcV8M66/h4eHNMRk82wlF4+Yso2GSfEIRce/Z2kgMdat58jd9bf9lBzzV3+n/UPS9vqQMe/9ioBoZMNgkEi4V3JbhrqenFT61q67diaiMsInQ6x6FqBIHnsG7Ln//NExMIS6X6+/MPKXOVEINAYXOCYOtWd98iY93PGREHlr9X//yxL6UE4nYANXHsBkuD12tinAkvNNIknIsln0jrPLXNSajWlEgp5r8pS/1GMrOj4ZFSpZlX/tQz5WAjx//NExMkSQMa+PhvYAGpf7QajHjGd8sFVB0jytRQKOoYV5xAXOs5IiLfQC0rBqoMtSomlp7VnXNWwVgVWil09OlhOHkAoHS4J5N7POYmVrvHxLjxISkXoMLKoHB06x2Wt//NExNMReLKxVmJQJhz5EicPZ7UOTW7WW+N/6XeIkFWnWA7w5SZEmtaJtB+ASt5bTxTgJHtx4GAgx0sLhEStHDhFBUs+OqYtqwUrDc8lYtt2BkPnwGoExij50s2xDY8s//NExOASGYqVnmGEevEirwyaYHBZj1sr55xFdRAylMTyAmDY52fB0BSiJjW2SRPZ0k4KUxgiHiKtf/Ifuodg87vC0iy2W20yL8rZvRphwtlrbjHsyBW4so9noqER9hdp//NExOoVeNY0AMaYBMVOgdfzIsYdHQJmykxds66wxGujTs4aOhdPNTkFb5k2RcQisHKXI1KV80QyImGJXIAsfxtzIgFHnxgABHWxHrZi1jRVXjdkF8/KQDzS/DAnbjZS//NExOcT2MIgAHhGQEqudEwSi5xPaG0QJWg1S/u2TkNTKMStCYodim5IhZxSJZBOzVI+OtjvmRvTmbWmp2+1M9IbbZGcMjPMaNax8yM4bOd0Uly6MF6F22xsCUZnOAiM//NExOoTMDIYAkBEAQB7mpOFfQFlpRchuw6ZY1p13o57ofafkDZ2amVGAJsjaQR2rGQeCkQmRrbSaRPmR+NMsrIhTP7LOsFyLjMREZE80jPO6y2JS/sPsNF+2melvkuy//NExPAU8V4UAEBGhTkRytu8CuCnSSoIRo0BtFaOq6psRxUZzdMiOK0NIcQvJskCS5uUmV7czuSpC1j2pPMqzRfppXuRJMrJgoRnFPul25zz9TM0JMijuZVHq5A4Upk4//NExO8VQbIUAkDGAzX/EHweLsLKZTbL0MF56gZ6d6jUi5saFvBo2iI25jEnRDojAxjn9o5VkMyO/vbPyOESvTNmpqV99S6Sl9V6VXD5HzXD6Dbb81/eOhbU00pYd+Jl//NExO0UCwYUAFBG+VMYrZGTbUS/wVVAQME3bgsbnOQ3p716f7JnbmN7lGRnclLTpUbS9QsctMkSqwVlsZnhafKujoalL83hqR9q2cnSsP4W6RevPiob9hKNLNjsY+lm//NExO8V0mYZakBGAWcTZWOqTFhDl9InbDV1R6vhsY+x/wtSKNjVbz/FLK/sDhJqBp+yoVcaGo7zz6fvVPyu8/BMHgCQ6giTJP3O97Hm6FKcuTlmSDKNUfzezSDRg2Fk//NExOoTWd4YAEBGfXDDRjJJa8U6lGDsYyzRjJN3n1B3uOdyb921SmRvZcn0zfrY8//Ow3OKUzrYxM+zv6h780j31yb2yHw+fqDiByxgwCMtpuiSVyoRnhAQIqvMpl3A//NExO8VouIULFhGBbDhhcpVHQgc+Lw/mpe8xCADkCfVFuPuCJxWhOdBGtgt2BroWbBFf0DUwIOVAvgFiggcOQLLJ9AZkmyTjULQhQoCyAtPTW1FHkDaUSPJcmSIDli4//NExOshQxYcAU9YAMzMicf/pMmq6mUTZuQ8n6RgaP/+hsz2bp3Wb1Fw///+J9CVoRUOmKqtEQJlb5KaPDEB7BFVQ29+B4EzESbQLFU9PLQW/aUsPIyuWnjdug+JuRMP//NExLkiImamXZmQAsLUZ/dhqpXwj78YSeUN/TyB4WaL5gdDScn+281p4yqLwVSqKz8bavNSuzVmLMvzwgKQzsCYU81JHLl8E00W8HhdLAKuLFiIdFxIJHfOO5RiVa0i//NExIMgEXawAZnIAJvhbluEuxu0tK0kRDRHv7zuUzow/RzV+VP0y2H7/1YZbgA8CUDwMTpKjsJdNBArHaXDMlyXWZj1KqadknQZmQdBaDMgmgtN2QWplu603MDBBBlq//NExFUhexLmN9hoA39NSkjKgs2UzKdfazulQQQa1UwZPa/9GzqUv/6voOnVUaJrczZMuU0kzE+U002QNKistNQDOSjULo+56kogM2knhmW5R9xRpUC2/5WlzjPxY5TM//NExCIa0xraFsGE80jwh73ucBnEEO/OOz7rEhJifatnMuG2WPSqtS7mCHGOcy0r9KPozGMrd90Ps7FsjVXr//a/9kvvOHMrGI4wSSQO0rqYmzpUcOXqzVa5klqUTClq//NExAkUIabuPnjK9n99JIYYKwUquN5YThj+3zqy7UGvJmYcv19WLsY5/aJUpn/6mvGWpQwZ1V/y+zo5AsynZhNUsmSCYBZQbbF0///JaSb8s5ioyvHIlauRwaiVyGpA//NExAsSkZbJlkjKchgBGWrjCsCZYf4UTxlVVK3lYodZ/RytpQSMrXoY7euyGVqtlaq5jaAMKxKDR0ge9I0NexsVcIf1VZ74LPxL5CoJKIBRvoESywq0hMY8UwDWz26Z//NExBMSMXp9HHpGTBllbc1gqMDddBDMKO1S/1y/OlNmMmZmBlVJbymf5R4zGv6t4U6VAV5YDK+SxFkmL/8QaX/QbrFhSB+gCwfX3+311zH3xvrMRXE2kj6KV0bI2/7c//NExB0SGvp4AEBHVGzr7//////JOck4FxuXy9E8viK5Myyhxw6Ib1zMGOUIOHNKeLbn4cWV4nIVUS/1////+f9vZx1+X//y/9cl//7jLmzszsxS7H85//2bdd4VlJ4Y//NExCcPmxqEABBNHV1Dc5tTgoPB8Ixc0yeq7mTeFH6sY4dVKhAN4mZbf+aBLP/DWofMBlc3JhassoCq6MXo4kiMGNlzPPIyOnCO5iTWQjr7VvuuF/6C0xBwcoPHk/+L//NExDsSKYqifAlGwFCVLBR44c9NVR4aNjyVo3/31wRxsrf71m1YZTSnac4gpqFBldsry0KJkJQkrDj80NHOVf8L7Tiv1f/hHY4hZNGJguv///m+FeS6OmjeMS2+7ted//NExEUSERKMfBAEEf3J8RVy24BAFGzqJhoejUfuxZar66oS0vuWzLyTNjuQzLnaVyU17arYW6lN1Y/zjMz6ZKXz/b7//r3PNmZvptGwxcr+8rxXXdl1iEqDX+hLrGEg//NExE8R2qZkHDgGsW5UbwTNNMQkgciTdzH+TtbZ8UYGTN/QX6E6nPk/+Rs6Mc9kAFFndRGcJqDBoMMOCjvONznxI5Tj+//repqv/poqI04WSwIxCDWCk8BQIQMiYYsE//NExFoR0SZsAMvEUJJBzjF0iZmtlHU9+1+g1Omm6T1pp+7aYYLX04HBILF1hfA+W0gjtLDhQ2vvchHCMc63+c8nVz18oGeZGU+ECIYtE/EDhqPVhZwIBg/IPOfWHxxy//NExGUZMfKMAKMFZNXccqAcHT9z0WDK3aqPwOAVvTtNqVLl3/+uHD+valRX123IzV9zN5121mCb5Y77k2yErjXkURBRhEtzk5XROjIJcToxi/FvDgi2UMBVOA51VCuY//NExFMfYxqUANvKvdserIIiiteY1DQ8WOHKH7IZwpNNvtfmdF//3Rk3RlQiqQ5j//2MgcOMKMqgqW7WxuyWQUMOyT9NjZlXw5kxs5JBq9iemRuffgNoqjx80Y5CBCM3//NExCgXmUreXtPEln68QQdyvowoo3xDVp73ugYy2oCfqj+GM+hAvqKEg0GmbBphvwLPgi3we7/p+jhpR40Rv+cQWdXOuqEC5LZddbII5UnZXVrUMAGBt4OjIZqZ4OmH//NExBwZetaUNtxEtEprWQwZQGI7UKHDNgqSrRNUiI3qcmj/kBKqtibKqXVU4cSmkj8KQxVkFpqXoogUb/yt5hWxTf/zUKaxID2UZ/LzG/+Zd2Cm9JscwDrW3tu2gFXA//NExAkT8kbRvmvOjlWBV6wLIyel1KYsKuIYm6Bg4xDPVx/IoCJYk0wj1ioktkAmS9/POfsb8k78knVvSdaYS85vR/R/+f+6MtGI3EDHV/0+ND5GgATyc1s1tgFJI4j9//NExAwVYV7OXsPKXtIVr9133F1FLiT6wkFQzqjGUDXG7NYMBfQuPdskj/9SQL71Vvv4gbxD5Gbv9/KDC54gG8lU96QDmK3b6zWNBAWUOSW+79ucpunKkaqoQzuXbDBz//NExAkTMUqcVNpQkBqJTzeS/doQQHDwtS34BQQ7eyIBPW/lCpE1F3CQNGJ0JHf9L/7r/v/ot75Fx7ihgoNH0iEg4OEAR0FKF//3f///hko2y/st2ku3oE3UNg3ZyKSC//NExA8RWgbdvlGEUl4AltByB1a+zBCuYwUphVD2QtuZ12/5jGcrMrGSj0qUrG5erQJlRP+/cy8vKJHrcSk//2+ew7Xo9GYAsLVBQAbn/VAZFDUXYkxpP35vj9i3b1Gj//NExBwROG6AVE6eAHN9qVlmNlJY8PESACDDh6PVAjmhQVEjEz5upK2oNOm/HcxyZDRl3/qcgXckkjckjCtRA6JY3oPgvBeN2Y8fsquPBgY+720TRKG2nqf97vd7F5HJ//NExCoYiprFvlGHZ7ewdZMxBO78frmld4B9dzRDh8U930/V2/TwRaNLFDuwMoj/pUpHzmX//c0CpLjfEuWLj3UePMkEVamWWcAFRWcgNA1TkPghgfqsaAkLBJuVQWtS//NExBoXEZKgANIY0CmG2BwRDE+J/hBPLu9vHyWUvG5j89yRn/pgBJrd0vCIT+tHdpmClcOJY6BhYf1px/7sfnAjQZd3fWSc+56v/46lRRWAhO2xxpN5+fFMNf5FJE5v//NExBASOQbmWF4QcprMYlyU5gK19+Y+sBL4dr2aeqya1PaxJXMA4Hh3yi7/A72FDHyXIHhOCYwJHswCD4gkAMJe24zlGszDI04AMWvjhHTjdfbAJU91ubeww0C2vwFK//NExBoSSULJpn4OjDNO/141arWP8PFug+BcjV0DzuPtqg/s6F9lHE9PEQ3eq2v6fsijng+EkidzidykVUIqdqCZIIPwO40Ee8qNIQMyjjUPJgV6LYVMrxd9ZzQEuENd//NExCMSgP7aLgvaGlGlqpNLlJpTI6Rnmnkx/MNWXdL5L+r/+vXk8xT/9A7ZFQ6bMiQTEEBxkJeEKMPXflDHLC1X84iQgSwz0GVCWpwvAmtk0BUfq6kLaIFw5FwNmOeJ//NExCwSEVLO1HrOqIia+Nmd5Qam3lH8sy6l347/tr0v/L6v///2VNoVjMGVZgg3j/jcIcOBDNpM1l9sOShK4neLwtTnog8MzsMybX5FWu5wCZ5wk+iirWMhyre/l9Ha//NExDYR0VLNjnrKrmOLAZjPVo+3d/UOpMt/r//6FcAASDcl/AqomHpgBwEyaELE6sEREFmyHcWsBazhjf9SsxhyqUpRKZVb6K9fu+7NmQz1bN69Ctwv+p9NR6VDX/+L//NExEERcaa5nnpEMGPnW+ytQSrttkkuwADaKuiYBERH8dsUCSWyICxUeW0BsVLbCwjpaWXYqs1XMfpkRhoIQhCFX7evwvNE/OfPkzwl7dRI2s3KGJvRpXke1/4ABhI5//NExE4RcarCXmBHMnsPN8P5eNkKR6MICQCmHOmnOlAaQJ1uQHYEV4Bwu4tNjMukE3PJg4Wm0WxhB7YECCZNlIcigekrJOvue4DAcjgz+mIj+emKXYEIX1HjEB5FZMg+//NExFsbSXKEANGetA+BAQcICdM5JfeLHBR3//+CFSqPZXdYsEMjaFrpYCF1QsFclZIIJGrCsXr2dadJ2UL3/htYImvnMWB9Z+n0P6+LZiQ77tBiObI9yrTlNwmpY0gd//NExEAfuiqcANPK3AwMSJSCLQDfDiLynbFlPqSMcpblkublAZaKh/Aiw7DxzC6CEUFiHLf520/oqDDgQTUPkBAocdSQ/7dT9qOOJ4DB4QBppmR74Eke7WTBINAZX5kH//NExBQSEia8yg4KJpP0+W//7fRDKiKIqrGVHMYw0QOMYUYUQ5g6FjXGs7C6IcYzOSrdv//WlkFVcUDIq1v///pVwESdJZsQImMKC3b/epK6gFi3j50Q+XpmD+x960XA//NExB4SaYrGfsIEcF2arKMKEdSwoJtDOYwj/2TR2XKUTRlej2RlK/U0c2JXCv/7iNQEnmf///yqwLq91RMngDBPTbSNEuBUBRtVdPtPMtLrfyh0GR5alL6lKJr7UFWX//NExCcRiR6tvmFExJjPW1Awq6DQdyQNcyBRKdJHv/jAq4iQqEj9JZ+V/xDVUrAkOk2zuzV+lo29M3QmVf7I1nwkFFa6sVk/lo9SlK1V0MViqCFboblI5dG6gJUTL9Oq//NExDMQ8YpkUsmEZAEOAnWQFJUeeZ8SkWrI9Ph1hq2FCbo0MekSAASjxV0KPWaE2zWIhZr/hMiPi/s171PMvo/9AwNOmIytHkdQoIgySEVpJIKpp5IllrfPEakoqnXK//NExEIQWWIwAHhEnAgkWSgbFhQRCrC06Cro8mKtBNbhyESLKbw1aPIGkta+lBZK4ohJRi3PYCj3DKaKmG87aSkhMs8TyZk8tess91KlEnpqCQCILLp2boM1jJH+Zq/k//NExFMQ0Aoo7CjEAOU7hs+Qw2XvbD+2xjQrV37+H/f/teTaOj9Youf/3m9zF4/WZ62XTa7aTh/gN3f+dodd9f3+ehkqDen/tyX8H8eqwGkUPMqw2aLdAjtEmOn7nls3//NExGIRkAohYkBGAWPdrW8Sn/N/T/97uEOdZ3ldyvmNv4+em63690Ou1dDe2Zlh+P8RLwKLPjVAQg/nuFjjy5Ki8HiXd4bDzKsrdI3m48C83czNWeXXT/N9uXsbYl7t//NExG4RaAocADhGARv9d8++U7+/Ms5cZrup86a1P+38jVLtam/tvfM6XSoNA0eBUFqj0RAU6o8sAgqCq3CVwhBU6GlAqCrsqCriX89lQ1IFgaDpV8RA0p6wVLAq75Yr//NExHsRiAocwjhGAZUFQWfWGup8RA08seqW7LVgR7AZHbCRkf//////ZkZGX///ssssMlDBQwMEHCCzVrLLGVgYIGgYDEqqq6aaRKWmmmiqqociqqqrpppEpaaaVUxB//NExIcQ6AIEABgAAE1FMy4xMDBVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExJYQEhT4NABG3TEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKgAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVTEFNRTMu//NExKwAAANIAAAAADEwMFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVV//NExKwAAANIAAAAAFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVV//NExKwAAANIAAAAAFVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVVV"

Training procedure

This model was trained with SFT.

⚠️ Limitations

Quantization Constraints: The base model is 4-bit quantized. While it is highly efficient, extremely complex logical reasoning might be slightly degraded compared to the FP16 base model.
Language Scope: The model is highly optimized for English/German to Vietnamese explanations. Using it for other language pairs might yield suboptimal results.

Framework versions

PEFT 0.18.1
TRL: 0.29.0
Transformers: 5.2.0
Pytorch: 2.8.0+cu128
Datasets: 4.6.0
Tokenizers: 0.22.2

👨‍💻 Developed by

PHGROUP TECHNOLOGY SOLUTIONS CO., LTD - Building AI-driven educational and omnichannel solutions.

Downloads last month: 7

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for phgrouptechs/Denglish-8B-Instruct

Adapters

1 model