Text Generation
Transformers
GGUF
English
continuous-latent-cot
neuro-symbolic
holographic-memory
relational-graph-hrr
reasoning
math
code
agentic
qwen3.8
osakra-research
conversational
Instructions to use Osakra/Project-Norn-V18-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Osakra/Project-Norn-V18-9B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Osakra/Project-Norn-V18-9B")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Osakra/Project-Norn-V18-9B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Osakra/Project-Norn-V18-9B with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Osakra/Project-Norn-V18-9B:Q4_K_M # Run inference directly in the terminal: llama cli -hf Osakra/Project-Norn-V18-9B:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Osakra/Project-Norn-V18-9B:Q4_K_M # Run inference directly in the terminal: llama cli -hf Osakra/Project-Norn-V18-9B: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 Osakra/Project-Norn-V18-9B:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Osakra/Project-Norn-V18-9B: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 Osakra/Project-Norn-V18-9B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Osakra/Project-Norn-V18-9B:Q4_K_M
Use Docker
docker model run hf.co/Osakra/Project-Norn-V18-9B:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Osakra/Project-Norn-V18-9B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Osakra/Project-Norn-V18-9B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Osakra/Project-Norn-V18-9B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Osakra/Project-Norn-V18-9B:Q4_K_M
- SGLang
How to use Osakra/Project-Norn-V18-9B 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 "Osakra/Project-Norn-V18-9B" \ --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": "Osakra/Project-Norn-V18-9B", "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 "Osakra/Project-Norn-V18-9B" \ --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": "Osakra/Project-Norn-V18-9B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use Osakra/Project-Norn-V18-9B with Ollama:
ollama run hf.co/Osakra/Project-Norn-V18-9B:Q4_K_M
- Unsloth Desktop
- Pi
How to use Osakra/Project-Norn-V18-9B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Osakra/Project-Norn-V18-9B:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Osakra/Project-Norn-V18-9B:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Osakra/Project-Norn-V18-9B with Docker Model Runner:
docker model run hf.co/Osakra/Project-Norn-V18-9B:Q4_K_M
- Lemonade
How to use Osakra/Project-Norn-V18-9B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Osakra/Project-Norn-V18-9B:Q4_K_M
Run and chat with the model
lemonade run user.Project-Norn-V18-9B-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Osakra/Project-Norn-V18-9B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Osakra/Project-Norn-V18-9B:Q4_K_M
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 Osakra/Project-Norn-V18-9B:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Osakra/Project-Norn-V18-9B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Osakra/Project-Norn-V18-9B:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "Osakra/Project-Norn-V18-9B:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Release Project Norn V18: 9B Hybrid Linear-Attention GGUF, Cognitive Layer & 1,250-Benchmark Multi-Pillar Suite
046282a verified Download example_inference.py from Osakra/Project-Norn-V18-9B: direct link, hf CLI and curl.
- Browser
- Download file 2.56 kB
-
https://huggingface.co/Osakra/Project-Norn-V18-9B/resolve/main/example_inference.py
- Command line
-
hf download hf://Osakra/Project-Norn-V18-9B/example_inference.py
-
curl -L -o example_inference.py https://huggingface.co/Osakra/Project-Norn-V18-9B/resolve/main/example_inference.py
2.56 kB
| """ | |
| Project Norn V18: Quickstart Inference Demonstration | |
| Osakra Research — 9B Frontier Neuro-Symbolic Intelligence | |
| Powered by Qwen3.8-9B-Distill Backbone | |
| """ | |
| import os | |
| import sys | |
| import json | |
| import time | |
| import urllib.request | |
| OLLAMA_API = "http://localhost:11434/api/generate" | |
| MODEL_NAME = "norn-v18" | |
| def test_inference(query: str, title: str): | |
| print("\n" + "=" * 70) | |
| print(f" {title}") | |
| print("=" * 70) | |
| print(f"[Prompt]: {query}\n") | |
| payload = { | |
| "model": MODEL_NAME, | |
| "prompt": query, | |
| "stream": False, | |
| "options": { | |
| "num_ctx": 8192, | |
| "temperature": 0.2, | |
| "top_p": 0.95, | |
| "repeat_penalty": 1.15 | |
| } | |
| } | |
| t0 = time.time() | |
| req = urllib.request.Request( | |
| OLLAMA_API, | |
| data=json.dumps(payload).encode("utf-8"), | |
| headers={"Content-Type": "application/json"} | |
| ) | |
| with urllib.request.urlopen(req) as res: | |
| data = json.loads(res.read().decode("utf-8")) | |
| dt = time.time() - t0 | |
| resp = data.get("response", "").strip() | |
| print(f"[Norn V18 Response ({dt:.2f}s)]:\n{resp}\n") | |
| def run_demos(): | |
| print("=" * 80) | |
| print(" PROJECT NORN V18: INFERENCE DEMONSTRATION") | |
| print("=" * 80) | |
| # Demo 1: Formal Logic & Self-Awareness | |
| test_inference( | |
| "Introduce yourself, explain your 9B architecture, and describe your 1024-d Relational HRR memory.", | |
| "DEMO 1: Self-Identity & Architecture Verification" | |
| ) | |
| # Demo 2: Mathematical Deduction & Constraint Traps | |
| test_inference( | |
| "Tank A and Tank B start empty. Pump 1 fills Tank A at 4 L/min. Pump 2 fills Tank B at 6 L/min. " | |
| "Tank A has a hole that leaks 1 L/min once it reaches 20 L. Tank B has no leak. At time t = 0, " | |
| "both pumps are turned on. For what positive time t (in minutes, t > 0) is Tank B's volume exactly " | |
| "twice Tank A's volume? Explain clearly.", | |
| "DEMO 2: Mathematical Equation & Constraint Trap" | |
| ) | |
| # Demo 3: Negative Constraints & Discipline | |
| test_inference( | |
| "List exactly 5 European capital cities. Rule 1: Do NOT include any city whose English name " | |
| "contains the letters 'a' or 'e'. Rule 2: Provide the list as a numbered list with country name in parentheses. " | |
| "Rule 3: Output ONLY the list with no preamble or intro.", | |
| "DEMO 3: Strict Negative Constraint Following" | |
| ) | |
| print("=" * 80) | |
| print(" Demonstration completed successfully!") | |
| print("=" * 80) | |
| if __name__ == "__main__": | |
| run_demos() | |