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

Libraries

How to use vikhyatk/moondream-next with Transformers:

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vikhyatk/moondream-next with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vikhyatk/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": "vikhyatk/moondream-next",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

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

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

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Pre-release version of moondream.

Note that this repository is only used for internal testing. Public releases are uploaded to the vikhyatk/moondream2 repository. But feel free to request access if you want me to send you an email update when we release new versions!

Downloads last month: 2

Safetensors

Model size

9B params

Tensor type

BF16

vikhyatk
/

moondream-next

You need to agree to share your contact information to access this model

Spaces using vikhyatk/moondream-next 7