Instructions to use moondream/moondream3-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moondream/moondream3-preview with Transformers:

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

pipe = pipeline("image-text-to-text", model="moondream/moondream3-preview", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("moondream/moondream3-preview", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use moondream/moondream3-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moondream/moondream3-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moondream/moondream3-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/moondream/moondream3-preview

SGLang

How to use moondream/moondream3-preview 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 "moondream/moondream3-preview" \
    --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": "moondream/moondream3-preview",
		"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 "moondream/moondream3-preview" \
        --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": "moondream/moondream3-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use moondream/moondream3-preview with Docker Model Runner:
```
docker model run hf.co/moondream/moondream3-preview
```

Always output inaccurate results

#34

by Gureumi - opened Mar 13

Discussion

Gureumi

Mar 13

Example code from model card

import torch
from transformers import AutoModelForCausalLM

moondream = AutoModelForCausalLM.from_pretrained(
    "moondream/moondream3-preview",
    trust_remote_code=True,
    dtype=torch.bfloat16,
    device_map={"": "cuda"},
    token="hugging face token"
)

moondream.compile()

image = Image.open("street_scene.jpg")
result = moondream.detect(image, "car")
print(result)

This example code result is

{'objects': [
{'x_min': 0.0033763647079467773, 'y_min': 0.01665535569190979, 'x_max': 0.9966236352920532, 'y_max': 0.9833446443080902},
{'x_min': 0.3129466772079468, 'y_min': 0.01665535569190979, 'x_max': 1.3061939477920532, 'y_max': 0.9833446443080902},
{'x_min': 0.3129466772079468, 'y_min': 0.01665535569190979, 'x_max': 1.3061939477920532, 'y_max': 0.9833446443080902},
{'x_min': 0.0033763647079467773, 'y_min': 0.01665535569190979, 'x_max': 0.9966236352920532, 'y_max': 0.9833446443080902},
{'x_min': 0.0033763647079467773, 'y_min': 0.01665535569190979, 'x_max': 0.9966236352920532, 'y_max': 0.9833446443080902},
{'x_min': 0.0033763647079467773, 'y_min': 0.01665535569190979, 'x_max': 0.9966236352920532, 'y_max': 0.9833446443080902},
{'x_min': 0.0033763647079467773, 'y_min': 0.01665535569190979, 'x_max': 0.9966236352920532, 'y_max': 0.9833446443080902},
{'x_min': 0.0033763647079467773, 'y_min': 0.01665535569190979, 'x_max': 0.9966236352920532, 'y_max': 0.9833446443080902},
{'x_min': 0.0033763647079467773, 'y_min': 0.01665535569190979, 'x_max': 0.9966236352920532, 'y_max': 0.9833446443080902},
{'x_min': 0.0033763647079467773, 'y_min': 0.01665535569190979, 'x_max': 0.9966236352920532, 'y_max': 0.9833446443080902},
{'x_min': 0.0033763647079467773, 'y_min': 0.01665535569190979, 'x_max': 0.9966236352920532, 'y_max': 0.9833446443080902}
]}

This is the same output in the reference of the moondream-station.
The document itself on moondream.ai and the hugging face may be incorrect or outdated.

The only way it's worked out is using https://github.com/m87-labs/kestrel

pazb

Apr 9

Weirdly this happens with transformers>=5, but works well with transformers<5.

err805

moondream org Apr 9

Yep, it has to do with how the new transformers treats buffers. It should work on pre and post 4.51.0 transformers. https://huggingface.co/moondream/moondream3-preview/discussions/37

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment