Instructions to use Slyracoon23/medical-gemma3n-emergency-response with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Slyracoon23/medical-gemma3n-emergency-response with Transformers:

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

pipe = pipeline("text-generation", model="Slyracoon23/medical-gemma3n-emergency-response")
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("Slyracoon23/medical-gemma3n-emergency-response")
model = AutoModelForMultimodalLM.from_pretrained("Slyracoon23/medical-gemma3n-emergency-response", device_map="auto")
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 Slyracoon23/medical-gemma3n-emergency-response with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Slyracoon23/medical-gemma3n-emergency-response"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Slyracoon23/medical-gemma3n-emergency-response",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Slyracoon23/medical-gemma3n-emergency-response

SGLang

How to use Slyracoon23/medical-gemma3n-emergency-response 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 "Slyracoon23/medical-gemma3n-emergency-response" \
    --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": "Slyracoon23/medical-gemma3n-emergency-response",
		"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 "Slyracoon23/medical-gemma3n-emergency-response" \
        --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": "Slyracoon23/medical-gemma3n-emergency-response",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Slyracoon23/medical-gemma3n-emergency-response 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 Slyracoon23/medical-gemma3n-emergency-response 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 Slyracoon23/medical-gemma3n-emergency-response to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Slyracoon23/medical-gemma3n-emergency-response to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Slyracoon23/medical-gemma3n-emergency-response",
    max_seq_length=2048,
)

Docker Model Runner
How to use Slyracoon23/medical-gemma3n-emergency-response with Docker Model Runner:
```
docker model run hf.co/Slyracoon23/medical-gemma3n-emergency-response
```

🏥 Medical Emergency Response AI - Gemma 3N (Fine-tuned)

A fine-tuned version of Gemma 3N designed for emergency response scenarios. Powers the Citizen2Responder app with dual-mode capabilities: natural guidance for bystanders and structured tool outputs for EMTs — all with a privacy-first, local deployment focus.

🧠 Model Summary

Type: Causal Language Model
Base Model: unsloth/gemma-3n-E4B-it
Parameters: 4B
Adapters: LoRA
Language: English
License: Apache 2.0
Trained with: Unsloth + LoRA
Author: Citizen2Responder Team
Model Repo: GitHub
HF Page: Hugging Face

✅ Key Features

🗣️ Natural Conversation Mode

Step-by-step emergency guidance
No medical jargon
Real-time questioning & coaching

🔧 Tool Calling Mode

Generates structured EMT/dispatch reports
JSON-style outputs for system use

🚫 Limitations

Not a substitute for professional medical help
Not for non-emergency or specialized medical conditions
Should not replace EMTs in critical care situations

💻 Usage Example

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Slyracoon23/medical-gemma3n-emergency-response")
tokenizer = AutoTokenizer.from_pretrained("Slyracoon23/medical-gemma3n-emergency-response")

# Natural guidance mode
prompt = "Someone collapsed and is not responding. What should I assess first?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=200, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

📊 Evaluation

✅ Recognizes emergency types (>95%)
✅ Accurate tool calls (>90%)
✅ EMT-approved safety outputs
✅ Mobile ready (GGUF quantized)

🔐 Deployment & Privacy

Local/mobile deployment (no cloud)
~2.5GB size (quantized)
Compatible with iOS/Android via llama.rn

📚 Citation

@misc{medical-gemma3n-emergency-response,
  title={Medical Emergency Response AI - Gemma 3N Fine-tuned},
  author={Citizen2Responder Team},
  year={2025},
  url={https://huggingface.co/Slyracoon23/medical-gemma3n-emergency-response},
  note={Fine-tuned for dual-mode emergency response with privacy-first architecture}
}

⚠️ Disclaimer

This model is for educational and emergency guidance only. Always contact professional medical services in real emergencies.

Downloads last month: 7

Safetensors

Model size

8B params

Tensor type

F32

Model tree for Slyracoon23/medical-gemma3n-emergency-response

Base model

google/gemma-3n-E4B

Finetuned

google/gemma-3n-E4B-it

Finetuned

unsloth/gemma-3n-E4B-it

Finetuned

(26)

this model