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

Libraries

How to use moondream/moondream-next with Transformers:

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

pipe = pipeline("text-generation", model="moondream/moondream-next", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("moondream/moondream-next", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moondream/moondream-next with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/moondream/moondream-next

SGLang

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

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

err805 commited on Jun 29

Commit

8c1ddbb

verified ·

1 Parent(s): 2e20db6

Requantize merged MoE experts to FP8

Browse files

Files changed (1) hide show

model.pt +2 -2

model.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b040dfbaf21df7503fb3607c92ea30fa8ab0a3f7738acfb774ac5073e954cc2
-size 18537527199

 version https://git-lfs.github.com/spec/v1
+oid sha256:e1acbd3f5eb8a1e74c7500b8a85051483de0406fa847eae35d53ce4032bb6ac7
+size 10505451019