Image-Text-to-Text
Transformers
Safetensors
English
Chinese
groundinganything
text-generation
visual-grounding
object-detection
referring-expression-comprehension
pointing
ocr
document-layout
custom-code
diffusion-language-model
conversational
custom_code
Instructions to use GroundingPI/GroundAnything with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
Update model links, paper badges, and release news
Browse filesUse the ModelScope logo with the official model links. Add GroundingPI report coverage and its Daily Paper award, and show live paper upvotes for the GroundAnything models. Update both language versions and release news.
- README.md +10 -6
- assets/modelscope-logo.svg +17 -0
- checksums.sha256 +2 -1
README.md
CHANGED
|
@@ -35,12 +35,14 @@ inference: false
|
|
| 35 |
|
| 36 |
## 🔗 Quick Links
|
| 37 |
|
| 38 |
-
- 🤗 **ModelScope:** [GroundAnything](https://www.modelscope.ai/models/GroundingPI/GroundAnything).
|
| 39 |
|
|
|
|
| 40 |
- 🚀 **Online Demo:** The GroundAnything DLM runtime is not supported on ZeroGPU.
|
| 41 |
- 🌐 **Project Page:** [GroundAnything](https://groundingpi.github.io/groundanything/).
|
| 42 |
- 💻 **GitHub Code:** [groundingpi/GroundAnything](https://github.com/groundingpi/GroundAnything).
|
| 43 |
- 📄 **Paper:** [arXiv:2609.39600](https://arxiv.org/abs/2609.39600).
|
|
|
|
|
|
|
| 44 |
|
| 45 |
# Model Overview
|
| 46 |
|
|
@@ -78,8 +80,8 @@ Global.
|
|
| 78 |
|
| 79 |
### Release Date:
|
| 80 |
|
| 81 |
-
- **ModelScope [10/14/2026]:** Model weights are now available on
|
| 82 |
-
|
| 83 |
- **Webpage [10/04/2026]:** Project webpage released: [GroundAnything](https://groundingpi.github.io/groundanything/).
|
| 84 |
- **Code [10/03/2026]:** GitHub code released: [GroundAnything](https://github.com/groundingpi/GroundAnything).
|
| 85 |
- **Paper [09/30/2026]:** [GroundAnything](https://arxiv.org/abs/2609.39600).
|
|
@@ -337,12 +339,14 @@ Grounding predictions can miss small or occluded objects, repeat instances, or p
|
|
| 337 |
|
| 338 |
## 🔗 快速链接
|
| 339 |
|
| 340 |
-
- 🤗 **ModelScope:** [GroundAnything](https://www.modelscope.ai/models/GroundingPI/GroundAnything)。
|
| 341 |
|
|
|
|
| 342 |
- 🚀 **在线演示:** ZeroGPU 不支持 GroundAnything DLM 运行时。
|
| 343 |
- 🌐 **项目主页:** [GroundAnything](https://groundingpi.github.io/groundanything/)。
|
| 344 |
- 💻 **GitHub 代码:** [groundingpi/GroundAnything](https://github.com/groundingpi/GroundAnything)。
|
| 345 |
- 📄 **论文:** [arXiv:2609.39600](https://arxiv.org/abs/2609.39600)。
|
|
|
|
|
|
|
| 346 |
|
| 347 |
# 模型概述
|
| 348 |
|
|
@@ -380,8 +384,8 @@ Grounding predictions can miss small or occluded objects, repeat instances, or p
|
|
| 380 |
|
| 381 |
### 发布日志:
|
| 382 |
|
| 383 |
-
- **ModelScope [10/14/2026]:** 模型权重已在
|
| 384 |
-
|
| 385 |
- **网页 [10/04/2026]:** 项目网页发布:[GroundAnything](https://groundingpi.github.io/groundanything/)。
|
| 386 |
- **代码 [10/03/2026]:** GitHub 代码发布:[GroundAnything](https://github.com/groundingpi/GroundAnything)。
|
| 387 |
- **论文 [09/30/2026]:** [GroundAnything](https://arxiv.org/abs/2609.39600)。
|
|
|
|
| 35 |
|
| 36 |
## 🔗 Quick Links
|
| 37 |
|
|
|
|
| 38 |
|
| 39 |
+
- <img src="https://huggingface.co/GroundingPI/GroundAnything/resolve/main/assets/modelscope-logo.svg" width="22" height="20" style="display: inline-block; vertical-align: middle; margin: 0;" alt="ModelScope" /> **ModelScope:** [GroundAnything (DLM)](https://www.modelscope.ai/models/GroundingPI/GroundAnything) · [GroundAnything-VLM (VLM)](https://www.modelscope.ai/models/GroundingPI/GroundAnything-VLM).
|
| 40 |
- 🚀 **Online Demo:** The GroundAnything DLM runtime is not supported on ZeroGPU.
|
| 41 |
- 🌐 **Project Page:** [GroundAnything](https://groundingpi.github.io/groundanything/).
|
| 42 |
- 💻 **GitHub Code:** [groundingpi/GroundAnything](https://github.com/groundingpi/GroundAnything).
|
| 43 |
- 📄 **Paper:** [arXiv:2609.39600](https://arxiv.org/abs/2609.39600).
|
| 44 |
+
- [](https://huggingface.co/papers/2609.39600)
|
| 45 |
+
|
| 46 |
|
| 47 |
# Model Overview
|
| 48 |
|
|
|
|
| 80 |
|
| 81 |
### Release Date:
|
| 82 |
|
| 83 |
+
- **ModelScope [10/14/2026]:** Model weights are now available on ModelScope: [GroundAnything (DLM)](https://www.modelscope.ai/models/GroundingPI/GroundAnything) · [GroundAnything-VLM (VLM)](https://www.modelscope.ai/models/GroundingPI/GroundAnything-VLM).
|
| 84 |
+
- **HF paper [10/14/2026]:** GroundAnything received strong community recognition on [Hugging Face Papers](https://huggingface.co/papers/2609.39600), reaching **74 upvotes**.
|
| 85 |
- **Webpage [10/04/2026]:** Project webpage released: [GroundAnything](https://groundingpi.github.io/groundanything/).
|
| 86 |
- **Code [10/03/2026]:** GitHub code released: [GroundAnything](https://github.com/groundingpi/GroundAnything).
|
| 87 |
- **Paper [09/30/2026]:** [GroundAnything](https://arxiv.org/abs/2609.39600).
|
|
|
|
| 339 |
|
| 340 |
## 🔗 快速链接
|
| 341 |
|
|
|
|
| 342 |
|
| 343 |
+
- <img src="https://huggingface.co/GroundingPI/GroundAnything/resolve/main/assets/modelscope-logo.svg" width="22" height="20" style="display: inline-block; vertical-align: middle; margin: 0;" alt="ModelScope" /> **ModelScope:** [GroundAnything(DLM)](https://www.modelscope.ai/models/GroundingPI/GroundAnything) · [GroundAnything-VLM(VLM)](https://www.modelscope.ai/models/GroundingPI/GroundAnything-VLM)。
|
| 344 |
- 🚀 **在线演示:** ZeroGPU 不支持 GroundAnything DLM 运行时。
|
| 345 |
- 🌐 **项目主页:** [GroundAnything](https://groundingpi.github.io/groundanything/)。
|
| 346 |
- 💻 **GitHub 代码:** [groundingpi/GroundAnything](https://github.com/groundingpi/GroundAnything)。
|
| 347 |
- 📄 **论文:** [arXiv:2609.39600](https://arxiv.org/abs/2609.39600)。
|
| 348 |
+
- [](https://huggingface.co/papers/2609.39600)
|
| 349 |
+
|
| 350 |
|
| 351 |
# 模型概述
|
| 352 |
|
|
|
|
| 384 |
|
| 385 |
### 发布日志:
|
| 386 |
|
| 387 |
+
- **ModelScope [10/14/2026]:** 模型权重已在 ModelScope 发布:[GroundAnything(DLM)](https://www.modelscope.ai/models/GroundingPI/GroundAnything) · [GroundAnything-VLM(VLM)](https://www.modelscope.ai/models/GroundingPI/GroundAnything-VLM)。
|
| 388 |
+
- **HF paper [10/14/2026]:** GroundAnything 在 [Hugging Face Papers](https://huggingface.co/papers/2609.39600) 获得巨大认可,收获 **74 个 Upvote**。
|
| 389 |
- **网页 [10/04/2026]:** 项目网页发布:[GroundAnything](https://groundingpi.github.io/groundanything/)。
|
| 390 |
- **代码 [10/03/2026]:** GitHub 代码发布:[GroundAnything](https://github.com/groundingpi/GroundAnything)。
|
| 391 |
- **论文 [09/30/2026]:** [GroundAnything](https://arxiv.org/abs/2609.39600)。
|
assets/modelscope-logo.svg
ADDED
|
|
checksums.sha256
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
c419c191a33774f4e1f834b3fb36033dc84e8ba316a3d1935eed1fa529884a74 LICENSE
|
| 2 |
-
5a578e89301793f09e337fc2cab6695ad8c2aebb04e5b18766c2e81082d1fd73 README.md
|
| 3 |
669bb095cca2e86ddc821926f4c3b42dd7389f2ad3ec49c8edca8fe6294aae7f added_tokens.json
|
| 4 |
a0bc6f6fc7a29a80017a433e8f03a1cc1236e838a944a2d034295a60c4f2fddb chat_template.jinja
|
| 5 |
22c369e2bdac19723fe7db7e4c64b224462744b1f1aae7bd5daf05307db3b9fd config.json
|
|
@@ -25,3 +24,5 @@ cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30 LICENSE-Apache
|
|
| 25 |
cddaec9f528f9ebf5ac627850eefcb3f14ee55e168776a1b650f91353ce8293e assets/demo.mp4
|
| 26 |
3c282238bb1598093c078e57dcc1db4b3ce8fb1f39db6c09ca90e0686f1043a2 assets/demo-poster.jpg
|
| 27 |
e0f0bbfa420324807403cfffe5ce664a33675c4e569de71b82cac7fb3b750f3e assets/fig1-teaser.png
|
|
|
|
|
|
|
|
|
| 1 |
c419c191a33774f4e1f834b3fb36033dc84e8ba316a3d1935eed1fa529884a74 LICENSE
|
|
|
|
| 2 |
669bb095cca2e86ddc821926f4c3b42dd7389f2ad3ec49c8edca8fe6294aae7f added_tokens.json
|
| 3 |
a0bc6f6fc7a29a80017a433e8f03a1cc1236e838a944a2d034295a60c4f2fddb chat_template.jinja
|
| 4 |
22c369e2bdac19723fe7db7e4c64b224462744b1f1aae7bd5daf05307db3b9fd config.json
|
|
|
|
| 24 |
cddaec9f528f9ebf5ac627850eefcb3f14ee55e168776a1b650f91353ce8293e assets/demo.mp4
|
| 25 |
3c282238bb1598093c078e57dcc1db4b3ce8fb1f39db6c09ca90e0686f1043a2 assets/demo-poster.jpg
|
| 26 |
e0f0bbfa420324807403cfffe5ce664a33675c4e569de71b82cac7fb3b750f3e assets/fig1-teaser.png
|
| 27 |
+
4de850a509777561891f7ab98ac22a7eeb02250f944c42c8e0c0ee30ebbfe44d README.md
|
| 28 |
+
5ef0abc7d34eca644c1cdac26dd9a3b9c0204f03137827c6475afa2648420304 assets/modelscope-logo.svg
|