Instructions to use badluma/lfm2.5-vl-450m-wildfire with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use badluma/lfm2.5-vl-450m-wildfire with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="badluma/lfm2.5-vl-450m-wildfire",
	filename="lfm2.5-vl-450m-wildfire-Q8_0.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

llama.cpp

How to use badluma/lfm2.5-vl-450m-wildfire with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf badluma/lfm2.5-vl-450m-wildfire:Q8_0
# Run inference directly in the terminal:
llama-cli -hf badluma/lfm2.5-vl-450m-wildfire:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf badluma/lfm2.5-vl-450m-wildfire:Q8_0
# Run inference directly in the terminal:
llama-cli -hf badluma/lfm2.5-vl-450m-wildfire:Q8_0

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 badluma/lfm2.5-vl-450m-wildfire:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf badluma/lfm2.5-vl-450m-wildfire:Q8_0

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 badluma/lfm2.5-vl-450m-wildfire:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf badluma/lfm2.5-vl-450m-wildfire:Q8_0

Use Docker

docker model run hf.co/badluma/lfm2.5-vl-450m-wildfire:Q8_0

LM Studio
Jan

vLLM

How to use badluma/lfm2.5-vl-450m-wildfire with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "badluma/lfm2.5-vl-450m-wildfire"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "badluma/lfm2.5-vl-450m-wildfire",
		"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/badluma/lfm2.5-vl-450m-wildfire:Q8_0

Ollama
How to use badluma/lfm2.5-vl-450m-wildfire with Ollama:
```
ollama run hf.co/badluma/lfm2.5-vl-450m-wildfire:Q8_0
```

Unsloth Studio new

How to use badluma/lfm2.5-vl-450m-wildfire 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 badluma/lfm2.5-vl-450m-wildfire 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 badluma/lfm2.5-vl-450m-wildfire to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for badluma/lfm2.5-vl-450m-wildfire to start chatting

Docker Model Runner
How to use badluma/lfm2.5-vl-450m-wildfire with Docker Model Runner:
```
docker model run hf.co/badluma/lfm2.5-vl-450m-wildfire:Q8_0
```

Lemonade

How to use badluma/lfm2.5-vl-450m-wildfire with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull badluma/lfm2.5-vl-450m-wildfire:Q8_0

Run and chat with the model

lemonade run user.lfm2.5-vl-450m-wildfire-Q8_0

List all available models

lemonade list

lfm2.5-vl-450m-wildfire

A wildfire risk classification model finetuned from LiquidAI/LFM2-VL-450M on satellite imagery. Given an RGB satellite image, returns a structured JSON risk assessment.

Model Details


Base model	LiquidAI/LFM2-VL-450M
Architecture	Lfm2VlForConditionalGeneration (hybrid conv/attention + SigLIP2 vision encoder)
Parameters	~450M
Finetuning method	LoRA (r=8, alpha=16) via TRL SFTTrainer
Training compute	Modal H100
Epochs	3
Dataset	Paulescu/wildfire-prevention

Output Format

The model returns a raw JSON object (no markdown, no explanation):

{
  "risk_level": "low | moderate | high | critical",
  "dry_vegetation_present": true,
  "steep_terrain": false,
  "urban_interface": true,
  "water_body_present": false,
  "image_quality_limited": false
}

Usage

With transformers

from transformers import AutoModelForImageTextToText, AutoProcessor
from PIL import Image

model = AutoModelForImageTextToText.from_pretrained("badluma/lfm2.5-vl-450m-wildfire")
processor = AutoProcessor.from_pretrained("badluma/lfm2.5-vl-450m-wildfire")

image = Image.open("satellite.png")

messages = [
    {
        "role": "system",
        "content": "You are a wildfire risk analyst. Examine the satellite image and assess wildfire risk based strictly on what is visible. Respond with ONLY a raw JSON object — no markdown, no explanation, no code fences. Fields: risk_level (string: low/moderate/high/critical), dry_vegetation_present (boolean), steep_terrain (boolean), urban_interface (boolean), water_body_present (boolean), image_quality_limited (boolean)."
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image},
            {"type": "text", "text": "Analyze this satellite image. Return only the JSON."}
        ]
    }
]

inputs = processor.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
output = model.generate(**inputs, max_new_tokens=128, temperature=0.0, do_sample=False)
print(processor.decode(output[0], skip_special_tokens=True))

With llama-server (GGUF)

Download the quantized GGUF files from this repo:

lfm2.5-vl-450m-wildfire-Q8_0.gguf — main model weights (Q8_0)
mmproj-LFM2.5-VL-450m-Q8_0.gguf — multimodal projector

llama-server \
  -m lfm2.5-vl-450m-wildfire-Q8_0.gguf \
  --mmproj mmproj-LFM2.5-VL-450m-Q8_0.gguf \
  --port 8190 --host 127.0.0.1 -c 2048

Then POST to http://127.0.0.1:8190/v1/chat/completions with standard OpenAI-compatible format.

Finetuning Code

The full training pipeline is included in the finetune/ directory of this repo:

finetune/
├── configs/finetune_lfm_450M.yaml   # Training hyperparameters
├── src/wildfire_prevention/          # Training source code
│   ├── fine_tune.py                  # Main training script (Modal)
│   ├── data_preparation.py           # Dataset formatting
│   ├── loaders.py                    # Model + dataset loading
│   └── config.py                     # Config schema
├── scripts/
│   ├── merge_lora.py                 # Merge LoRA adapter into base
│   └── export_gguf.sh                # Convert to GGUF via llama.cpp
├── Makefile                          # make train / make download-checkpoint
└── pyproject.toml                    # Dependencies (uv)

Requirements: Python 3.12+, uv, Modal account, W&B account, HF token.

cd finetune
uv sync
make train          # Runs on Modal H100
make download-checkpoint
bash scripts/export_gguf.sh

Downloads last month: 139

Safetensors

Model size

0.5B params

Tensor type

F16

Model tree for badluma/lfm2.5-vl-450m-wildfire

Base model

LiquidAI/LFM2-VL-450M

Quantized

(15)

this model

badluma
/

lfm2.5-vl-450m-wildfire