Instructions to use bynn-intelligence-com/decisionnode-edge-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bynn-intelligence-com/decisionnode-edge-mini with Transformers:

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

pipe = pipeline("image-text-to-text", model="bynn-intelligence-com/decisionnode-edge-mini")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("bynn-intelligence-com/decisionnode-edge-mini")
model = AutoModelForMultimodalLM.from_pretrained("bynn-intelligence-com/decisionnode-edge-mini", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bynn-intelligence-com/decisionnode-edge-mini 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 bynn-intelligence-com/decisionnode-edge-mini:Q8_0
# Run inference directly in the terminal:
llama cli -hf bynn-intelligence-com/decisionnode-edge-mini:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bynn-intelligence-com/decisionnode-edge-mini:Q8_0
# Run inference directly in the terminal:
llama cli -hf bynn-intelligence-com/decisionnode-edge-mini: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 bynn-intelligence-com/decisionnode-edge-mini:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf bynn-intelligence-com/decisionnode-edge-mini: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 bynn-intelligence-com/decisionnode-edge-mini:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bynn-intelligence-com/decisionnode-edge-mini:Q8_0

Use Docker

docker model run hf.co/bynn-intelligence-com/decisionnode-edge-mini:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use bynn-intelligence-com/decisionnode-edge-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bynn-intelligence-com/decisionnode-edge-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bynn-intelligence-com/decisionnode-edge-mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bynn-intelligence-com/decisionnode-edge-mini:Q8_0

SGLang

How to use bynn-intelligence-com/decisionnode-edge-mini 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 "bynn-intelligence-com/decisionnode-edge-mini" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bynn-intelligence-com/decisionnode-edge-mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "bynn-intelligence-com/decisionnode-edge-mini" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bynn-intelligence-com/decisionnode-edge-mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use bynn-intelligence-com/decisionnode-edge-mini with Ollama:
```
ollama run hf.co/bynn-intelligence-com/decisionnode-edge-mini:Q8_0
```
Unsloth Desktop
Docker Model Runner
How to use bynn-intelligence-com/decisionnode-edge-mini with Docker Model Runner:
```
docker model run hf.co/bynn-intelligence-com/decisionnode-edge-mini:Q8_0
```

Lemonade

How to use bynn-intelligence-com/decisionnode-edge-mini with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bynn-intelligence-com/decisionnode-edge-mini:Q8_0

Run and chat with the model

lemonade run user.decisionnode-edge-mini-Q8_0

List all available models

lemonade list

Atomic Chat

decisionnode-edge-mini / runtime /pyproject.toml

bynn-intelligence

Runtime 0.9.2.1: the MLX backend bounds the memory it keeps between requests

30a6280 verified 3 days ago

Raw History Blame Contribute Delete

1.28 kB

[build-system]
requires = ["setuptools>=77"]  # a PEP 639 license expression
build-backend = "setuptools.build_meta"

[project]
name = "decisionnode-edge"
version = "0.9.2.1"
description = "Run DecisionNode Edge locally: typed, calibrated decisions in the shape of the DecisionNode API."
readme = "README.md"
requires-python = ">=3.10"
license = "AGPL-3.0-only"  # and a commercial license from Bynn Intelligence Inc. (README, License)
license-files = ["LICENSE"]
authors = [{ name = "Bynn Intelligence Inc.", email = "licensing@bynn.com" }]
dependencies = [
    "torch>=2.6",
    "transformers>=5.18",
    "safetensors>=0.4",
]

[project.optional-dependencies]
# pictures: Pillow decodes them, torchvision runs the backbone's fast image processor
images = ["pillow>=10", "torchvision>=0.21"]
# faster backends (src/decisionnode_edge/backends.py), each optional; llama.cpp is a program of its own, not a Python package
vllm = ["vllm>=0.32; sys_platform == 'linux'"]
openvino = ["openvino>=2026.4", "onnx>=1.23", "onnxscript>=0.7"]  # onnx and onnxscript for the build only
mlx = ["mlx>=0.32; sys_platform == 'darwin' and platform_machine == 'arm64'", "mlx-lm>=0.32.2; sys_platform == 'darwin' and platform_machine == 'arm64'"]

[tool.setuptools.packages.find]
where = ["src"]

	[build-system]
	requires = ["setuptools>=77"] # a PEP 639 license expression
	build-backend = "setuptools.build_meta"

	[project]
	name = "decisionnode-edge"
	version = "0.9.2.1"
	description = "Run DecisionNode Edge locally: typed, calibrated decisions in the shape of the DecisionNode API."
	readme = "README.md"
	requires-python = ">=3.10"
	license = "AGPL-3.0-only" # and a commercial license from Bynn Intelligence Inc. (README, License)
	license-files = ["LICENSE"]
	authors = [{ name = "Bynn Intelligence Inc.", email = "licensing@bynn.com" }]
	dependencies = [
	"torch>=2.6",
	"transformers>=5.18",
	"safetensors>=0.4",
	]

	[project.optional-dependencies]
	# pictures: Pillow decodes them, torchvision runs the backbone's fast image processor
	images = ["pillow>=10", "torchvision>=0.21"]
	# faster backends (src/decisionnode_edge/backends.py), each optional; llama.cpp is a program of its own, not a Python package
	vllm = ["vllm>=0.32; sys_platform == 'linux'"]
	openvino = ["openvino>=2026.4", "onnx>=1.23", "onnxscript>=0.7"] # onnx and onnxscript for the build only
	mlx = ["mlx>=0.32; sys_platform == 'darwin' and platform_machine == 'arm64'", "mlx-lm>=0.32.2; sys_platform == 'darwin' and platform_machine == 'arm64'"]

	[tool.setuptools.packages.find]
	where = ["src"]