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
```

Fix Chinese emphasis rendering in the model overview

#12

by Skywalker0410 - opened 9 days ago

base: refs/heads/main

←

from: refs/pr/12

Discussion Files changed

-2

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