Instructions to use ServiceNow/GroundNext-7B-V0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ServiceNow/GroundNext-7B-V0 with Transformers:

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

pipe = pipeline("image-text-to-text", model="ServiceNow/GroundNext-7B-V0")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ServiceNow/GroundNext-7B-V0")
model = AutoModelForMultimodalLM.from_pretrained("ServiceNow/GroundNext-7B-V0", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ServiceNow/GroundNext-7B-V0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ServiceNow/GroundNext-7B-V0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ServiceNow/GroundNext-7B-V0",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/ServiceNow/GroundNext-7B-V0

SGLang

How to use ServiceNow/GroundNext-7B-V0 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 "ServiceNow/GroundNext-7B-V0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ServiceNow/GroundNext-7B-V0",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "ServiceNow/GroundNext-7B-V0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ServiceNow/GroundNext-7B-V0",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use ServiceNow/GroundNext-7B-V0 with Docker Model Runner:
```
docker model run hf.co/ServiceNow/GroundNext-7B-V0
```

BAJUKA commited on Nov 12, 2025

Commit

dcc653f

verified ·

1 Parent(s): 1d331fe

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -5

README.md CHANGED Viewed

@@ -160,9 +160,8 @@ To achieve optimal grounding performance, we recommend:
    - Maintain original aspect ratios when resizing
 2. **Prompt Engineering**:
-   - Be specific about the target element (e.g., "Click on the blue 'Submit' button in the top-right corner")
    - Include element attributes when available (color, position, text)
-   - Use consistent terminology matching the UI
 3. **Generation Parameters**:
    - Use `temperature=0.0` for deterministic grounding
@@ -177,7 +176,6 @@ To achieve optimal grounding performance, we recommend:
 5. **Post-processing**:
    - Parse `<tool_call>` tags to extract JSON
    - Validate coordinates are within screen bounds
-   - Handle cases where model may describe element instead of providing coordinates
 ## Training
@@ -191,8 +189,8 @@ For detailed training instructions, dataset preparation, and reproduction steps,
 ## Limitations and Future Work
 - **Desktop-focused**: Primarily trained on desktop environments (though shows strong cross-platform generalization)
-- **Action space**: Currently supports mouse and keyboard actions; additional modalities under exploration
-- **Languages**: Optimized for English UI elements; multilingual support in development
 - **Resolution**: Performance may vary with extremely high or low resolution images
 ## Citation

    - Maintain original aspect ratios when resizing
 2. **Prompt Engineering**:
+   - Be specific about the target element (e.g., "Click on the blue 'Submit' button in the top-right corner" or "Click on the following element: Save")
    - Include element attributes when available (color, position, text)
 3. **Generation Parameters**:
    - Use `temperature=0.0` for deterministic grounding
 5. **Post-processing**:
    - Parse `<tool_call>` tags to extract JSON
    - Validate coordinates are within screen bounds
 ## Training
 ## Limitations and Future Work
 - **Desktop-focused**: Primarily trained on desktop environments (though shows strong cross-platform generalization)
+- **Action space**: Currently supports mouse click action only
+- **Languages**: Optimized for English UI elements
 - **Resolution**: Performance may vary with extremely high or low resolution images
 ## Citation