Instructions to use Kami574/Atlas-FirstAid with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Kami574/Atlas-FirstAid 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 Kami574/Atlas-FirstAid:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Kami574/Atlas-FirstAid:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Kami574/Atlas-FirstAid:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Kami574/Atlas-FirstAid: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 Kami574/Atlas-FirstAid:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Kami574/Atlas-FirstAid: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 Kami574/Atlas-FirstAid:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Kami574/Atlas-FirstAid:Q4_K_M

Use Docker

docker model run hf.co/Kami574/Atlas-FirstAid:Q4_K_M

LM Studio
Jan

vLLM

How to use Kami574/Atlas-FirstAid with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kami574/Atlas-FirstAid"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kami574/Atlas-FirstAid",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kami574/Atlas-FirstAid:Q4_K_M

Ollama
How to use Kami574/Atlas-FirstAid with Ollama:
```
ollama run hf.co/Kami574/Atlas-FirstAid:Q4_K_M
```

Unsloth Studio

How to use Kami574/Atlas-FirstAid 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 Kami574/Atlas-FirstAid 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 Kami574/Atlas-FirstAid to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Kami574/Atlas-FirstAid to start chatting

How to use Kami574/Atlas-FirstAid with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kami574/Atlas-FirstAid:Q4_K_M

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": "Kami574/Atlas-FirstAid:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Kami574/Atlas-FirstAid with Docker Model Runner:
```
docker model run hf.co/Kami574/Atlas-FirstAid:Q4_K_M
```

Lemonade

How to use Kami574/Atlas-FirstAid with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Kami574/Atlas-FirstAid:Q4_K_M

Run and chat with the model

lemonade run user.Atlas-FirstAid-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Kami574/Atlas-FirstAid with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kami574/Atlas-FirstAid: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 Kami574/Atlas-FirstAid:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Kami574/Atlas-FirstAid with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kami574/Atlas-FirstAid: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 "Kami574/Atlas-FirstAid: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"

Atlas-FirstAid

File size: 1,925 Bytes

---
license: apache-2.0
base_model: Qwen/Qwen2.5-1.5B-Instruct
datasets:
- i-am-mushfiq/FirstAidQA
language:
- en
pipeline_tag: text-generation
tags:
- first-aid
- emergency
- offline-ai
- gguf
- llama-cpp
- qwen2
- medical-assistance
---

# Atlas-FirstAid (Qwen2.5-1.5B-Instruct Fine-Tune)

**Atlas** is a lightweight, edge-optimized language model fine-tuned specifically for first-aid and emergency guidance in offline, disconnected, or low-resource environments. 

It powers **[Nova F-R (Nova First Response)](https://github.com/Neuille-hush/NovaFR)**—a privacy-first mobile app designed to provide clear, step-by-step medical instructions during disasters, infrastructure outages, or wilderness emergencies when internet access is completely unavailable.

---

## 📌 Model Details

- **Developer:** Ismet Beljulji
- **Base Model:** `Qwen/Qwen2.5-1.5B-Instruct`
- **Fine-Tuning Framework:** Unsloth
- **Dataset:** [FirstAidQA](https://huggingface.co/datasets/i-am-mushfiq/FirstAidQA) (5,500 question-answer pairs derived from the certified *Vital First Aid Book*, presented at the NeurIPS 2025 Workshop on Muslims in ML)
- **Primary Quantization:** GGUF (`Q4_K_M`, ~986 MB)
- **Target Execution Engine:** `llama.cpp` on mobile/edge hardware

---

## ⚙️ Recommended System Prompt

For optimal response structure and safety, pass the following system prompt to the engine:

```text
You are Atlas, an AI emergency first-aid assistant trained to provide immediate, calm, and actionable guidance during health crises. 

Your instructions must be:
1. Clear, numbered, step-by-step, and prioritized by life safety (e.g., checking breathing/airway first).
2. Direct and concise—avoid unnecessary conversational filler in an emergency.
3. Explicit about when to seek immediate emergency services (call 911 / 112) when available.
4. Grounded strictly in standard first-aid protocols. Do not fabricate medical treatments.