Instructions to use Subh775/Perception-moondream2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Subh775/Perception-moondream2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Subh775/Perception-moondream2", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Subh775/Perception-moondream2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Subh775/Perception-moondream2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Subh775/Perception-moondream2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Subh775/Perception-moondream2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Subh775/Perception-moondream2

SGLang

How to use Subh775/Perception-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 "Subh775/Perception-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": "Subh775/Perception-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 "Subh775/Perception-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": "Subh775/Perception-moondream2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Subh775/Perception-moondream2 with Docker Model Runner:
```
docker model run hf.co/Subh775/Perception-moondream2
```

Subh775 commited on 4 days ago

Commit

9635e9c

verified ·

1 Parent(s): 00d746f

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -37,9 +37,7 @@ The training focused on teaching the model to accurately perceive and describe:
 - **Traffic Management:** Generating real-time text logs of intersection activity.
 - **Autonomous Driving Context:** Providing dense contextual descriptions for self-driving datasets.
----
-## Usage and Inference
 Because this model relies on the custom Moondream2 architecture, you will need to use `trust_remote_code=True` when loading it via the `transformers` library.

 - **Traffic Management:** Generating real-time text logs of intersection activity.
 - **Autonomous Driving Context:** Providing dense contextual descriptions for self-driving datasets.
+## Usage
 Because this model relies on the custom Moondream2 architecture, you will need to use `trust_remote_code=True` when loading it via the `transformers` library.