Instructions to use vikhyatk/moondream2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vikhyatk/moondream2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="vikhyatk/moondream2", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("vikhyatk/moondream2", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use vikhyatk/moondream2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "vikhyatk/moondream2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "vikhyatk/moondream2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/vikhyatk/moondream2
- SGLang
How to use vikhyatk/moondream2 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/moondream2" \ --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/moondream2", "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/moondream2" \ --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/moondream2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use vikhyatk/moondream2 with Docker Model Runner:
docker model run hf.co/vikhyatk/moondream2
Creating a handler.py file to support HF dedicated inference endpoints
Hi all,
Made a quick handler.py file for people to use. It works for me pretty well. Feel free to test it out :)
Here is an example for when making a request to the endpoint:
import requests
import base64
import json
api_url = 'your API URL'
image_path = '' # Replace with the path to your image file
question = 'what is going on in this picture?'
with open(image_path, 'rb') as img:
encoded_image = base64.b64encode(img.read()).decode('utf-8')
payload = {
'inputs': {
'image': encoded_image,
'question': question
}
}
headers = {
"Accept" : "application/json",
"Authorization": "Bearer HUGGINGFACE_TOKEN",
"Content-Type": "application/json"
}
response = requests.post(api_url, headers=headers, data=json.dumps(payload))
print(response.json().get('body', {}))
Thanks! Is this the dedicated endpoints feature? https://huggingface.co/inference-endpoints/dedicated
Looks like it's pointing to your finetune btw
Yes, that's right! It's the dedicated endpoints feature for the HF platform. Also, sorry about that, I'll make sure to remove the fine-tuned model ;)
🫡