Instructions to use Neura-Tech-AI/Neuron-Distill-Qwen2-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Neura-Tech-AI/Neuron-Distill-Qwen2-14B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Neura-Tech-AI/Neuron-Distill-Qwen2-14B",
	filename="Neuron-Distill-Qwen2-14B-Q6_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Neura-Tech-AI/Neuron-Distill-Qwen2-14B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K
# Run inference directly in the terminal:
llama-cli -hf Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K
# Run inference directly in the terminal:
llama-cli -hf Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K

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 Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K

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 Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K

Use Docker

docker model run hf.co/Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K

LM Studio
Jan

vLLM

How to use Neura-Tech-AI/Neuron-Distill-Qwen2-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Neura-Tech-AI/Neuron-Distill-Qwen2-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neura-Tech-AI/Neuron-Distill-Qwen2-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K

Ollama
How to use Neura-Tech-AI/Neuron-Distill-Qwen2-14B with Ollama:
```
ollama run hf.co/Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K
```

Unsloth Studio new

How to use Neura-Tech-AI/Neuron-Distill-Qwen2-14B 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 Neura-Tech-AI/Neuron-Distill-Qwen2-14B 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 Neura-Tech-AI/Neuron-Distill-Qwen2-14B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Neura-Tech-AI/Neuron-Distill-Qwen2-14B to start chatting

Pi new

How to use Neura-Tech-AI/Neuron-Distill-Qwen2-14B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Neura-Tech-AI/Neuron-Distill-Qwen2-14B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K

Run Hermes

hermes

Docker Model Runner
How to use Neura-Tech-AI/Neuron-Distill-Qwen2-14B with Docker Model Runner:
```
docker model run hf.co/Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K
```

Lemonade

How to use Neura-Tech-AI/Neuron-Distill-Qwen2-14B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Neura-Tech-AI/Neuron-Distill-Qwen2-14B:Q6_K

Run and chat with the model

lemonade run user.Neuron-Distill-Qwen2-14B-Q6_K

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🧠 Neuron-14B: The Official Intelligence of Neura Tech

Neuron-14B is a high-performance Large Language Model (LLM) developed by Neura Tech. It serves as the flagship model for advanced reasoning, creative synthesis, and multilingual communication.

🏢 Organization Identity

Company: Neura Tech AI
Project Name: Neuron
Lead Architect: Samarth Anand Pathak

📊 Model Specifications

Architecture: Optimized Transformer (Fine-tuned from Qwen2)
Parameters: ~15 Billion
Precision: BF16 (Bfloat16)
Context Window: 131,072 tokens
License: Apache-2.0 (Open Source)

🎯 Core Capabilities

Advanced Reasoning: Capable of solving complex logical and mathematical queries.
Multilingual Proficiency: Highly optimized for English and Hindi (including Hinglish).
Instruction Following: Specifically tuned to follow complex user prompts with high precision.
Creative Synthesis: Exceptional at generating scripts, stories, and technical documentation.

📜 License & Usage

This model is licensed under the Apache-2.0 License. This means you are free to use, modify, and distribute this model, provided that you credit Neura Tech as the original creator.

🛠️ Quick Start (Python)

To use Neuron-14B, load it via the Hugging Face transformers library:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Anandnrnnffn/Neura-Tech-14B-Weights"

# Load Neuron-14B Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Load Model Weights
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto"
)

Downloads last month: 435

Safetensors

Model size

15B params

Tensor type

F16

Model tree for Neura-Tech-AI/Neuron-Distill-Qwen2-14B

Quantizations

2 models

Neura-Tech-AI
/

Neuron-Distill-Qwen2-14B