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

Libraries

How to use GroundingPI/GroundAnything with Transformers:

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GroundingPI/GroundAnything with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GroundingPI/GroundAnything"
# 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",
		"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

SGLang

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

Skywalker0410 commited on 9 days ago

Commit

64aa66c

verified ·

1 Parent(s): eb13709

Fix Chinese emphasis rendering in the model overview

Browse files

Use explicit strong tags in one Chinese overview paragraph so punctuation next to percentages renders correctly on the Hub. Wording, numbers, English content, language links, and release news remain unchanged.

Files changed (2) hide show

README.md +1 -1
checksums.sha256 +1 -1

README.md CHANGED Viewed

@@ -354,7 +354,7 @@ Grounding predictions can miss small or occluded objects, repeat instances, or p
 自回归（AR）视觉定位模型将空间预测串行化，带来顺序生成的延迟，并为输出 token 施加因果顺序。我们将视觉定位视为视觉证据提取：物体、位置和空间关系共同受到图像与查询的约束，但它们之间的依赖关系并不意味着生成过程必须从左到右进行。这一区别使双向扩散成为自然的选择，让空间假设能够并行产生，并通过迭代去噪共同细化。
-我们提出 **GroundAnything**，一个拥有 4B 参数的视觉定位基础模型，通过分块去噪兼顾快速并行解码与精确定位。在 30 个视觉定位基准上，自回归版本 **GroundAnything-VLM** 以 **72.42%** 的综合表现刷新了同等规模模型的最佳水平，并与 GPT-6 Astra（**71.35%**）保持竞争力。采用**熵引导解码**的 GroundAnything 同样超越了这一规模下此前的最佳水平，平均达到 **61.75%**，高于基于 MTP 的快速模型 LocateAnything 的 **53.32%**。
 在论文报告的运行配置下，可选的**自推测模式**相较自回归版本实现了 **4.51× 加速**，同时 **COCO F1mIoU 下降 0.74 个百分点**。基础设施实验表明，逐步优化推理实现能够将并行解码转化为实际加速，为对延迟敏感的实际系统提供高效的视觉定位能力。

 自回归（AR）视觉定位模型将空间预测串行化，带来顺序生成的延迟，并为输出 token 施加因果顺序。我们将视觉定位视为视觉证据提取：物体、位置和空间关系共同受到图像与查询的约束，但它们之间的依赖关系并不意味着生成过程必须从左到右进行。这一区别使双向扩散成为自然的选择，让空间假设能够并行产生，并通过迭代去噪共同细化。
+我们提出 <strong>GroundAnything</strong>，一个拥有 4B 参数的视觉定位基础模型，通过分块去噪兼顾快速并行解码与精确定位。在 30 个视觉定位基准上，自回归版本 <strong>GroundAnything-VLM</strong> 以 <strong>72.42%</strong> 的综合表现刷新了同等规模模型的最佳水平，并与 GPT-6 Astra（<strong>71.35%</strong>）保持竞争力。采用<strong>熵引导解码</strong>的 GroundAnything 同样超越了这一规模下此前的最佳水平，平均达到 <strong>61.75%</strong>，高于基于 MTP 的快速模型 LocateAnything 的 <strong>53.32%</strong>。
 在论文报告的运行配置下，可选的**自推测模式**相较自回归版本实现了 **4.51× 加速**，同时 **COCO F1mIoU 下降 0.74 个百分点**。基础设施实验表明，逐步优化推理实现能够将并行解码转化为实际加速，为对延迟敏感的实际系统提供高效的视觉定位能力。

checksums.sha256 CHANGED Viewed

@@ -24,5 +24,5 @@ cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30  LICENSE-Apache
 cddaec9f528f9ebf5ac627850eefcb3f14ee55e168776a1b650f91353ce8293e  assets/demo.mp4
 3c282238bb1598093c078e57dcc1db4b3ce8fb1f39db6c09ca90e0686f1043a2  assets/demo-poster.jpg
 e0f0bbfa420324807403cfffe5ce664a33675c4e569de71b82cac7fb3b750f3e  assets/fig1-teaser.png
-670e6ba79f9a063968e255c80c58883a9d326259558093252006b00cd11fe5b7  README.md
 5ef0abc7d34eca644c1cdac26dd9a3b9c0204f03137827c6475afa2648420304  assets/modelscope-logo.svg

 cddaec9f528f9ebf5ac627850eefcb3f14ee55e168776a1b650f91353ce8293e  assets/demo.mp4
 3c282238bb1598093c078e57dcc1db4b3ce8fb1f39db6c09ca90e0686f1043a2  assets/demo-poster.jpg
 e0f0bbfa420324807403cfffe5ce664a33675c4e569de71b82cac7fb3b750f3e  assets/fig1-teaser.png
+989680a3f197ead245642d692ec23c86d0fdccff842b1b1f830b3869d05c9f75  README.md
 5ef0abc7d34eca644c1cdac26dd9a3b9c0204f03137827c6475afa2648420304  assets/modelscope-logo.svg