Instructions to use NGARiAI/ngari-ft-distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NGARiAI/ngari-ft-distilled with Transformers:

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

pipe = pipeline("text-generation", model="NGARiAI/ngari-ft-distilled")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NGARiAI/ngari-ft-distilled")
model = AutoModelForCausalLM.from_pretrained("NGARiAI/ngari-ft-distilled", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NGARiAI/ngari-ft-distilled 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 NGARiAI/ngari-ft-distilled:F16
# Run inference directly in the terminal:
llama cli -hf NGARiAI/ngari-ft-distilled:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NGARiAI/ngari-ft-distilled:F16
# Run inference directly in the terminal:
llama cli -hf NGARiAI/ngari-ft-distilled:F16

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 NGARiAI/ngari-ft-distilled:F16
# Run inference directly in the terminal:
./llama-cli -hf NGARiAI/ngari-ft-distilled:F16

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 NGARiAI/ngari-ft-distilled:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NGARiAI/ngari-ft-distilled:F16

Use Docker

docker model run hf.co/NGARiAI/ngari-ft-distilled:F16

LM Studio
Jan

vLLM

How to use NGARiAI/ngari-ft-distilled with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/NGARiAI/ngari-ft-distilled:F16

SGLang

How to use NGARiAI/ngari-ft-distilled 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 "NGARiAI/ngari-ft-distilled" \
    --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": "NGARiAI/ngari-ft-distilled",
		"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 "NGARiAI/ngari-ft-distilled" \
        --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": "NGARiAI/ngari-ft-distilled",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use NGARiAI/ngari-ft-distilled with Ollama:
```
ollama run hf.co/NGARiAI/ngari-ft-distilled:F16
```
Unsloth Desktop

How to use NGARiAI/ngari-ft-distilled with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NGARiAI/ngari-ft-distilled:F16

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": "NGARiAI/ngari-ft-distilled:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use NGARiAI/ngari-ft-distilled with Docker Model Runner:
```
docker model run hf.co/NGARiAI/ngari-ft-distilled:F16
```

Lemonade

How to use NGARiAI/ngari-ft-distilled with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NGARiAI/ngari-ft-distilled:F16

Run and chat with the model

lemonade run user.ngari-ft-distilled-F16

List all available models

lemonade list

Hermes Agent

How to use NGARiAI/ngari-ft-distilled with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NGARiAI/ngari-ft-distilled:F16

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 NGARiAI/ngari-ft-distilled:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use NGARiAI/ngari-ft-distilled with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NGARiAI/ngari-ft-distilled:F16

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 "NGARiAI/ngari-ft-distilled:F16" \
  --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"

NGARi FT Distilled — Sovereign QA 1.5B

A 1.5B distilled QA model fine-tuned on NGARi's sovereign-agent domain data — fast enough to run as a real-time content-safety judge and QA model on aarch64 edge hardware with 8GB RAM, with zero cloud dependency.

This model is the production guardrail judge inside the NGARi Sovereign Business Operating System (NS-BOS): every agent response passes through it before delivery.

Why it exists — the NGARi model pipeline

NGARi's architecture pairs a large teacher model with small, deployable edge models:

Teacher (27B-class, e.g. qwen3.8-27B)
    │  generates reasoning traces, synthetic data, eval judgments
    ▼
Edge models (1.5B–2B: ngari-ft-distilled, ngari-tool)
    │  distilled / fine-tuned on teacher outputs
    ▼
Deployment: air-gapped edge hardware (Jetson AGX Orin, 8GB RAM)

This repo is the distilled student in that pipeline — capabilities that normally need a much larger model, compressed into a 1.5B footprint that runs entirely on owned hardware.

Provenance (verified Aug 3, 2026)

Attribute	Value
Base model	`Qwen/Qwen2.5-1.5B-Instruct` (Apache 2.0) — pinned in `adapter_config.json`
LoRA	rank 32, alpha 64, dropout 0.05, all linear projections
Synthetic data teacher	`qwen3:8b` (v1; 27B-class teacher planned for v2)
License	Apache 2.0 (NGARi-authored artifacts)
Hardware validated	aarch64 / NVIDIA Jetson AGX Orin, 8GB RAM, air-gap verified

Google Gemma models were served only on NGARi hardware and were never used in NGARi training. All training used the Apache-2.0 Qwen2.5 lineage.

Evaluation

Chat quality — `ngari-ft-distilled_chat_eval.json`

{
  "model": "ngari-ft-distilled",
  "num_examples": 200,
  "avg_score": 0.3766,
  "avg_latency_sec": 2.81,
  "tokens_per_sec": 39.78,
  "total_time_sec": 561.98
}

Tool detection (secondary capability) — `ngari-ft-distilled-stable_tool_eval.json`

{
  "model": "ngari-ft-distilled:stable",
  "num_examples": 20,
  "tool_detection_rate": 0.6,
  "tool_name_accuracy": 0.55,
  "params_validity_rate": 0.6,
  "avg_latency_sec": 2.38
}

For high-accuracy tool calling, use NGARiAI/ngari-tool (100% on all three tool metrics). This model's role is QA + safety judging.

Files

File	Purpose
`model-*.safetensors` (+ config)	Merged full model — use with Transformers
`adapter_model.safetensors`	PEFT LoRA adapter — apply on the base
`ngari-ft-distilled-q4_K_M.gguf` / `-f16.gguf`	GGUF — use with Ollama / llama.cpp

Usage

# Ollama (GGUF)
ollama create ngari-ft-distilled -f Modelfile
ollama run ngari-ft-distilled "your prompt"

# Transformers (merged)
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("NGARiAI/ngari-ft-distilled")

# PEFT adapter (apply on the base)
from peft import PeftModel
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
adapter = PeftModel.from_pretrained(base, "NGARiAI/ngari-ft-distilled")

Companion repos

NGARiAI/ngari-tool — tool-calling sibling (100% tool-format eval)
NGARiAI/ngari-datasets — the training data
NGARiAI/ns-bos-kernel — the Apache 2.0 sovereign kernel

Sovereign AI

Trained and verified on user-owned edge hardware with zero cloud dependency. Verified air-gap (monitored via /proc/net/dev). "AI You Own. Completely."

Downloads last month: 470

Safetensors

Model size

2B params

Tensor type

F32

Model tree for NGARiAI/ngari-ft-distilled

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Adapter

(1405)

this model

NGARiAI
/

ngari-ft-distilled

NGARi FT Distilled — Sovereign QA 1.5B

Why it exists — the NGARi model pipeline

Provenance (verified Aug 3, 2026)

Evaluation

Chat quality — `ngari-ft-distilled_chat_eval.json`

Tool detection (secondary capability) — `ngari-ft-distilled-stable_tool_eval.json`

Files

Usage

Companion repos

Sovereign AI

Model tree for NGARiAI/ngari-ft-distilled

Dataset used to train NGARiAI/ngari-ft-distilled

NGARi FT Distilled — Sovereign QA 1.5B

Why it exists — the NGARi model pipeline

Provenance (verified Aug 3, 2026)

Evaluation

Chat quality — ngari-ft-distilled_chat_eval.json

Tool detection (secondary capability) — ngari-ft-distilled-stable_tool_eval.json

Files

Usage

Companion repos

Sovereign AI

Model tree for NGARiAI/ngari-ft-distilled

Dataset used to train NGARiAI/ngari-ft-distilled

Chat quality — `ngari-ft-distilled_chat_eval.json`

Tool detection (secondary capability) — `ngari-ft-distilled-stable_tool_eval.json`