Instructions to use SKT-NRS/NRS_QWEN_MYTHOS_1M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SKT-NRS/NRS_QWEN_MYTHOS_1M with Transformers:

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

pipe = pipeline("text-generation", model="SKT-NRS/NRS_QWEN_MYTHOS_1M")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("SKT-NRS/NRS_QWEN_MYTHOS_1M")
model = AutoModelForMultimodalLM.from_pretrained("SKT-NRS/NRS_QWEN_MYTHOS_1M")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SKT-NRS/NRS_QWEN_MYTHOS_1M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SKT-NRS/NRS_QWEN_MYTHOS_1M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SKT-NRS/NRS_QWEN_MYTHOS_1M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SKT-NRS/NRS_QWEN_MYTHOS_1M

SGLang

How to use SKT-NRS/NRS_QWEN_MYTHOS_1M 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 "SKT-NRS/NRS_QWEN_MYTHOS_1M" \
    --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": "SKT-NRS/NRS_QWEN_MYTHOS_1M",
		"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 "SKT-NRS/NRS_QWEN_MYTHOS_1M" \
        --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": "SKT-NRS/NRS_QWEN_MYTHOS_1M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SKT-NRS/NRS_QWEN_MYTHOS_1M with Docker Model Runner:
```
docker model run hf.co/SKT-NRS/NRS_QWEN_MYTHOS_1M
```

NRS NEURAL REASONING SYSTEM

SKT AI LABS

SKT NRS BOOSTED

1 Million Context • 100x High Reasoning Capacity

Base: Qwen 3.5 9B + Full NRS Neural Reasoning System
Ultra Fast • Deep Reasoning • Exceptional Coherence

SKT NRS AI Representation

🧠 100x REASONING 📜 1M CONTEXT ⚡ BLAZING FAST 💡 10x THINKING

SKT-NRS/NRS_QWEN_MYTHOS_1M

Qwen 3.5 9B + Full Neural Reasoning System

A powerful custom fine-tuned model built on Qwen 3.5 9B with full NRS treatment. Delivers exceptional reasoning depth while maintaining blazing fast speed and a massive 1 Million token context window.

✨ Key Capabilities

100x High Reasoning Capacity — Dramatically improved logical thinking via NRS Boosting.
10x Thinking Enhancement — Advanced step-by-step <think> tags refined by SKT SFT.
1 Million Token Context — Handle huge codebases & documents using YaRN scaling.
Lightning Fast Inference — Optimized for consumer hardware (RTX 3090/4090).
Native Tool Calling — Ready for Python execution & Web Search.

100x HIGH REASONING CAPACITY

Experience next-level reasoning in an efficient 9B package

Open Source • High Performance • Community Driven

REQUEST

REQUEST FROM USER - CLICK TO EXPAND

Show Who Requested to Boost this Model:

Request Evidence

SKT NRS Team is working To Complete On All Request.

🛠️ How to Use & Run

This model is optimized for both Local Execution and Cloud Notebooks (Colab).

1. 🐍 Python (Transformers)

Install the required libraries:

pip install transformers torch accelerate

Basic Inference Code:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "SKT-NRS/NRS_QWEN_MYTHOS_1M" 

# Load Model and Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Prepare Prompt
messages = [
    {"role": "system", "content": "You are NRS, an advanced reasoning assistant."},
    {"role": "user", "content": "Explain quantum entanglement simply."}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate
outputs = model.generate(
    **inputs,
    max_new_tokens=4096,
    temperature=0.6,
    top_p=0.95,
    do_sample=True
)

response = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(response)

2. ☁️ Google Colab Ready

Run this on a free T4 GPU or paid A100/V100 instances.

!pip install transformers accelerate bitsandbytes

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "SKT-NRS/NRS_QWEN_MYTHOS_1M"

# Load in 4-bit for memory efficiency
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    load_in_4bit=True,
    device_map="auto",
    torch_dtype=torch.float16
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

print("Model Loaded Successfully! Ready for Reasoning.")

3. 🖥️ Local Running (Ollama / LM Studio)

For the best local experience, use GGUF quantizations.

Using Ollama:

ollama create nrs-mythos -f Modelfile
ollama run nrs-mythos

Using LM Studio:

Download the .gguf file from the "Files" section.
Drag and drop into LM Studio.
Set Context Length to 8192 or higher.

4. ⚡ High-Performance Serving (vLLM)

For production-grade speed and 1M context support:

pip install vllm

vllm serve SKT-NRS/NRS_QWEN_MYTHOS_1M \
    --max-model-len 1000000 \
    --gpu-memory-utilization 0.9 \
    --dtype bfloat16

🧠 Technical Details & Training

Base Model

Architecture: Qwen 3.5 9B
Context Window: 1,048,576 tokens (via YaRN RoPE Scaling)

NRS Enhancement Process

The model underwent a rigorous Neural Reasoning System (NRS) enhancement pipeline:

Reasoning Boosting Tool: Proprietary NRS tools generated high-quality Chain-of-Thought (CoT) data.
Supervised Fine-Tuning (SFT): Tuned on ~500k high-quality reasoning samples (coding, math, logic).
Tool Calling Optimization: Enhanced native function calling for Python & Web Search.

Sampling Parameters

Temperature: 0.6
Top_P: 0.95
Top_K: 20
Repetition Penalty: 1.05

⚠️ Limitations & Disclaimer

Reasoning Mode: The model outputs <think> blocks. Parse them if needed.
Uncensored Nature: Designed for open research. Use responsibly.
Hallucinations: Always verify critical facts with external sources.

LICENSE AND TERMS

LICENSE

Made with ❤️ by SKT AI Labs

Pushing the boundaries of Open Source Reasoning.

Downloads last month: -

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for SKT-NRS/NRS_QWEN_MYTHOS_1M

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B