Instructions to use OS-Copilot/OS-Atlas-Base-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OS-Copilot/OS-Atlas-Base-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OS-Copilot/OS-Atlas-Base-4B", 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)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("OS-Copilot/OS-Atlas-Base-4B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OS-Copilot/OS-Atlas-Base-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OS-Copilot/OS-Atlas-Base-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OS-Copilot/OS-Atlas-Base-4B",
		"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/OS-Copilot/OS-Atlas-Base-4B

SGLang

How to use OS-Copilot/OS-Atlas-Base-4B 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 "OS-Copilot/OS-Atlas-Base-4B" \
    --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": "OS-Copilot/OS-Atlas-Base-4B",
		"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 "OS-Copilot/OS-Atlas-Base-4B" \
        --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": "OS-Copilot/OS-Atlas-Base-4B",
		"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 OS-Copilot/OS-Atlas-Base-4B with Docker Model Runner:
```
docker model run hf.co/OS-Copilot/OS-Atlas-Base-4B
```

numbmelon commited on Nov 19, 2024

Commit

67bccd1

verified ·

1 Parent(s): ec44dfb

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -3

README.md CHANGED Viewed

@@ -5,16 +5,27 @@ base_model: OpenGVLab/InternVL2-4B
 pipeline_tag: image-text-to-text
 ---
-This repository contains the model of the paper [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://huggingface.co/papers/2410.23218).
 <div align="center">
-[\[🏠Homepage\]](https://osatlas.github.io) [\[💻Code\]](https://github.com/OS-Copilot/OS-Atlas) [\[🚀Quick Start\]](#quick-start) [\[📝Paper\]](https://arxiv.org/abs/2410.23218) [\[🤗Models\]](https://huggingface.co/collections/OS-Copilot/os-atlas-67246e44003a1dfcc5d0d045) [\[🤗ScreenSpot-v2\]](https://huggingface.co/datasets/OS-Copilot/ScreenSpot-v2)
 </div>
 ![os-atlas](https://github.com/user-attachments/assets/cf2ee020-5e15-4087-9a7e-75cc43662494)
 ## Quick Start
 OS-Atlas-Base-4B is a GUI grounding model finetuned from [InternVL2-4B](https://huggingface.co/OpenGVLab/InternVL2-4B).
@@ -27,6 +38,8 @@ pip install transformers
 ```
 For additional dependencies, please refer to the [InternVL2 documentation](https://internvl.readthedocs.io/en/latest/get_started/installation.html)
 Inference code example:
 ```python
 import numpy as np
@@ -119,7 +132,7 @@ model = AutoModel.from_pretrained(
 tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
 # set the max number of tiles in `max_num`
-pixel_values = load_image('https://github.com/OS-Copilot/OS-Atlas/blob/main/exmaples/images/web_dfacd48d-d2c2-492f-b94c-41e6a34ea99f.png', max_num=6).to(torch.bfloat16).cuda()
 generation_config = dict(max_new_tokens=1024, do_sample=True)
 question = "In the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions(with point).\n\"'Champions League' link\""

 pipeline_tag: image-text-to-text
 ---
+# OS-Atlas: A Foundation Action Model For Generalist GUI Agents
 <div align="center">
+[\[🏠Homepage\]](https://osatlas.github.io) [\[💻Code\]](https://github.com/OS-Copilot/OS-Atlas) [\[🚀Quick Start\]](#quick-start) [\[📝Paper\]](https://arxiv.org/abs/2410.23218) [\[🤗Models\]](https://huggingface.co/collections/OS-Copilot/os-atlas-67246e44003a1dfcc5d0d045)[\[🤗Data\]](https://huggingface.co/datasets/OS-Copilot/OS-Atlas-data) [\[🤗ScreenSpot-v2\]](https://huggingface.co/datasets/OS-Copilot/ScreenSpot-v2)
 </div>
+## Overview
 ![os-atlas](https://github.com/user-attachments/assets/cf2ee020-5e15-4087-9a7e-75cc43662494)
+OS-Atlas provides a series of models specifically designed for GUI agents.
+For GUI grounding tasks, you can use:
+- [OS-Atlas-Base-7B](https://huggingface.co/OS-Copilot/OS-Atlas-Base-7B)
+- [OS-Atlas-Base-4B](https://huggingface.co/OS-Copilot/OS-Atlas-Base-4B)
+For generating single-step actions in GUI agent tasks, you can use:
+- [OS-Atlas-Pro-7B](https://huggingface.co/OS-Copilot/OS-Atlas-Pro-7B)
+- [OS-Atlas-Pro-4B](https://huggingface.co/OS-Copilot/OS-Atlas-Pro-4B)
 ## Quick Start
 OS-Atlas-Base-4B is a GUI grounding model finetuned from [InternVL2-4B](https://huggingface.co/OpenGVLab/InternVL2-4B).
 ```
 For additional dependencies, please refer to the [InternVL2 documentation](https://internvl.readthedocs.io/en/latest/get_started/installation.html)
+Then download the [example image](https://github.com/OS-Copilot/OS-Atlas/blob/main/examples/images/web_dfacd48d-d2c2-492f-b94c-41e6a34ea99f.png) and save it to the current directory.
 Inference code example:
 ```python
 import numpy as np
 tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
 # set the max number of tiles in `max_num`
+pixel_values = load_image('./web_dfacd48d-d2c2-492f-b94c-41e6a34ea99f.png', max_num=6).to(torch.bfloat16).cuda()
 generation_config = dict(max_new_tokens=1024, do_sample=True)
 question = "In the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions(with point).\n\"'Champions League' link\""