Instructions to use Luigi/edge-fall-vlm-500m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Luigi/edge-fall-vlm-500m with Transformers:

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

pipe = pipeline("image-text-to-text", model="Luigi/edge-fall-vlm-500m")
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("Luigi/edge-fall-vlm-500m")
model = AutoModelForMultimodalLM.from_pretrained("Luigi/edge-fall-vlm-500m", 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]:]))

llama-cpp-python

How to use Luigi/edge-fall-vlm-500m with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Luigi/edge-fall-vlm-500m",
	filename="mmproj-f16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Luigi/edge-fall-vlm-500m 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 Luigi/edge-fall-vlm-500m:F16
# Run inference directly in the terminal:
llama cli -hf Luigi/edge-fall-vlm-500m:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Luigi/edge-fall-vlm-500m:F16
# Run inference directly in the terminal:
llama cli -hf Luigi/edge-fall-vlm-500m: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 Luigi/edge-fall-vlm-500m:F16
# Run inference directly in the terminal:
./llama-cli -hf Luigi/edge-fall-vlm-500m: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 Luigi/edge-fall-vlm-500m:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Luigi/edge-fall-vlm-500m:F16

Use Docker

docker model run hf.co/Luigi/edge-fall-vlm-500m:F16

LM Studio
Jan

vLLM

How to use Luigi/edge-fall-vlm-500m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Luigi/edge-fall-vlm-500m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Luigi/edge-fall-vlm-500m",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Luigi/edge-fall-vlm-500m:F16

SGLang

How to use Luigi/edge-fall-vlm-500m 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 "Luigi/edge-fall-vlm-500m" \
    --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": "Luigi/edge-fall-vlm-500m",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Luigi/edge-fall-vlm-500m" \
        --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": "Luigi/edge-fall-vlm-500m",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use Luigi/edge-fall-vlm-500m with Ollama:
```
ollama run hf.co/Luigi/edge-fall-vlm-500m:F16
```

Unsloth Studio

How to use Luigi/edge-fall-vlm-500m 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 Luigi/edge-fall-vlm-500m 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 Luigi/edge-fall-vlm-500m to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Luigi/edge-fall-vlm-500m to start chatting

Atomic Chat new
Docker Model Runner
How to use Luigi/edge-fall-vlm-500m with Docker Model Runner:
```
docker model run hf.co/Luigi/edge-fall-vlm-500m:F16
```

Lemonade

How to use Luigi/edge-fall-vlm-500m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Luigi/edge-fall-vlm-500m:F16

Run and chat with the model

lemonade run user.edge-fall-vlm-500m-F16

List all available models

lemonade list

edge-fall-vlm-500m — 500M fall / danger detector (size-comparison sibling)

A SmolVLM2-500M-Video-Instruct fine-tune for fall / person-down / distress detection, same recipe as edge-fall-vlm-2.2b but at 500M. Published mainly to show how accuracy scales with VLM size.

Code: https://github.com/vieenrose/edge-fall-vlm · Demo (pick a size): https://huggingface.co/spaces/Luigi/edge-fall-vlm-demo

Accuracy vs size (same recipe, same real test sets)

Model	URFD (easy) recall/spec	OOPS in-the-wild recall
256M	1.0 / 1.0	0.13
500M	1.0 / 1.0	0.31
2.2B (recommended)	0.90 / 1.0	0.83

This 500M model saturates the easy in-distribution test but MISSES most real in-the-wild falls (recall 0.31). Smaller VLMs fit the training distribution but do not generalize to novel real footage. For the actual safety task, use the 2.2B. This model is useful for research / the fastest possible on-device path where recall is not safety-critical.

Files: transformers model.safetensors + model-Q8_0.gguf / mmproj-f16.gguf (llama.cpp). Apache-2.0. Not a medical/safety device.