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

Libraries

How to use GroundingPI/GroundAnything-VLM with Transformers:

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

pipe = pipeline("image-text-to-text", model="GroundingPI/GroundAnything-VLM", trust_remote_code=True)
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("GroundingPI/GroundAnything-VLM", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GroundingPI/GroundAnything-VLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GroundingPI/GroundAnything-VLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GroundingPI/GroundAnything-VLM",
		"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/GroundingPI/GroundAnything-VLM

SGLang

How to use GroundingPI/GroundAnything-VLM 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 "GroundingPI/GroundAnything-VLM" \
    --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": "GroundingPI/GroundAnything-VLM",
		"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 "GroundingPI/GroundAnything-VLM" \
        --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": "GroundingPI/GroundAnything-VLM",
		"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 GroundingPI/GroundAnything-VLM with Docker Model Runner:
```
docker model run hf.co/GroundingPI/GroundAnything-VLM
```

GroundAnything-VLM

Commit History

Oct 31 2 days ago

13:23
Update the recommended BibTeX citation (#13)⁠

GroundingPI +1: Skywalker0410

f35603c

Oct 14 19 days ago

10:43
Fix Chinese emphasis rendering in the model overview (#12)⁠

GroundingPI +1: Skywalker0410

0f3cf22
10:25
Harmonize the paper link and live upvote badge (#11)⁠

GroundingPI +1: Skywalker0410

3655bdf
09:37
Update model links, paper badges, and release news (#10)⁠

GroundingPI +1: Skywalker0410

3615354
08:50
Add ModelScope weights and release news (#9)⁠

GroundingPI +1: Skywalker0410

d8273a4

Oct 4 29 days ago

01:37
Add Chinese model card and language navigation (#8)⁠

GroundingPI +1: Skywalker0410

b77314a
00:59
Add October 4 project webpage release to model card (#7)⁠

GroundingPI +1: Skywalker0410

b765d31

Oct 3 30 days ago

02:26
Add October 3 GitHub code release to model card (#6)⁠

GroundingPI +1: Skywalker0410

bb86bbe
01:07
Replace teaser with updated ICLR artwork (#5)⁠

GroundingPI +1: Skywalker0410

1bbc10b
00:56
Update main demo video and prepared cover (#4)⁠

GroundingPI +1: Skywalker0410

8bf4186

Oct 2

05:56
Keep inline title logos compact without image margins (#3)⁠

GroundingPI +1: Skywalker0410

da7d6cd
05:53
Simplify model card layout and evaluation; clarify license scope (#2)⁠

GroundingPI +1: Skywalker0410

40af09a
02:31
Publish model weights, paper figures, and complete model card (#1)⁠

GroundingPI +1: Skywalker0410

d603a32

Sep 30

08:20
initial commit

GroundingPI

Verified signature
0078ab6

Commit History

Oct 31 2 days ago

Update the recommended BibTeX citation (#13)⁠

Oct 14 19 days ago

Fix Chinese emphasis rendering in the model overview (#12)⁠

Harmonize the paper link and live upvote badge (#11)⁠

Update model links, paper badges, and release news (#10)⁠

Add ModelScope weights and release news (#9)⁠

Oct 4 29 days ago

Add Chinese model card and language navigation (#8)⁠

Add October 4 project webpage release to model card (#7)⁠

Oct 3 30 days ago

Add October 3 GitHub code release to model card (#6)⁠

Replace teaser with updated ICLR artwork (#5)⁠

Update main demo video and prepared cover (#4)⁠

Oct 2

Keep inline title logos compact without image margins (#3)⁠

Simplify model card layout and evaluation; clarify license scope (#2)⁠

Publish model weights, paper figures, and complete model card (#1)⁠

Sep 30

initial commit