Instructions to use dill-dev/NanoDream3-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dill-dev/NanoDream3-preview with Transformers:

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

pipe = pipeline("image-text-to-text", model="dill-dev/NanoDream3-preview", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("dill-dev/NanoDream3-preview", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dill-dev/NanoDream3-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dill-dev/NanoDream3-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dill-dev/NanoDream3-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dill-dev/NanoDream3-preview

SGLang

How to use dill-dev/NanoDream3-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 "dill-dev/NanoDream3-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": "dill-dev/NanoDream3-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 "dill-dev/NanoDream3-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": "dill-dev/NanoDream3-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dill-dev/NanoDream3-preview with Docker Model Runner:
```
docker model run hf.co/dill-dev/NanoDream3-preview
```

dill-dev commited on Apr 2

Commit

f55e88e

verified ·

1 Parent(s): e914f21

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -7

README.md CHANGED Viewed

@@ -4,14 +4,8 @@ pipeline_tag: image-text-to-text
 license: other
 ---
-**Moondream 3 (Preview)** is an vision language model with a mixture-of-experts architecture (9B total parameters, 2B active). This model makes no compromises, delivering state-of-the-art visual reasoning while still retaining our efficient and deployment-friendly ethos.
-[✨ Demo](https://moondream.ai/c/playground) &#8201; · &#8201; [☁️ Cloud API](https://moondream.ai/c/docs/quickstart) &#8201; · &#8201; [📝 Release notes](https://moondream.ai/blog/moondream-3-preview)
-![](https://huggingface.co/moondream/moondream3-preview/resolve/main/open_vocab_detect.png)
-![](https://huggingface.co/moondream/moondream3-preview/resolve/main/visual_reasoning.png)
-![](https://huggingface.co/moondream/moondream3-preview/resolve/main/point_count.png)
-![](https://huggingface.co/moondream/moondream3-preview/resolve/main/structured_outputs.png)
 ## Architecture

 license: other
 ---
+**Nanodream 3(Preview)** is an vision language model with a mixture-of-experts architecture (9B total parameters, 2B active). This model makes no compromises, delivering state-of-the-art visual reasoning while still retaining our efficient and deployment-friendly ethos.
 ## Architecture