Instructions to use OS-Copilot/OS-Atlas-Pro-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OS-Copilot/OS-Atlas-Pro-7B 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-Pro-7B")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("OS-Copilot/OS-Atlas-Pro-7B")
model = AutoModelForImageTextToText.from_pretrained("OS-Copilot/OS-Atlas-Pro-7B")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OS-Copilot/OS-Atlas-Pro-7B 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-Pro-7B"
# 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-Pro-7B",
		"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-Pro-7B

SGLang

How to use OS-Copilot/OS-Atlas-Pro-7B 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-Pro-7B" \
    --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-Pro-7B",
		"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-Pro-7B" \
        --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-Pro-7B",
		"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-Pro-7B with Docker Model Runner:
```
docker model run hf.co/OS-Copilot/OS-Atlas-Pro-7B
```

numbmelon commited on Nov 19, 2024

Commit

cd2abba

verified ·

1 Parent(s): 36e4da5

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -5

README.md CHANGED Viewed

@@ -9,7 +9,7 @@ pipeline_tag: image-text-to-text
 <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>
@@ -23,14 +23,16 @@ For GUI grounding tasks, you can use:
 - [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-Action-7B](https://huggingface.co/OS-Copilot/OS-Atlas-Action-7B)
-- [OS-Atlas-Action-4B](https://huggingface.co/OS-Copilot/OS-Atlas-Action-4B)
 ## OS-Atlas-Action-7B
 `OS-Atlas-Action-7B` is a GUI action model finetuned from OS-Atlas-Base-7B. By taking as input a system prompt, basic and custom actions, and a task instruction, the model generates thoughtful reasoning (`thought`) and executes the appropriate next step (`action`).
 ### Installation
 To use `OS-Atlas-Action-7B`, first install the necessary dependencies:
 ```bash
@@ -39,8 +41,9 @@ pip install qwen-vl-utils
 ```
 ### Example Inference Code
-Below is an example of how to perform inference using the model:
 ```python
 from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
 from qwen_vl_utils import process_vision_info
@@ -134,7 +137,7 @@ messages = [
             },
             {
                 "type": "image",
-                "image": "https://github.com/OS-Copilot/OS-Atlas/blob/main/exmaples/images/action_example_1.jpg",
             },
             {"type": "text", "text": "Task instruction: to allow the user to enter their first name\nHistory: null" },
         ],

 <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>
 - [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)
 ## OS-Atlas-Action-7B
 `OS-Atlas-Action-7B` is a GUI action model finetuned from OS-Atlas-Base-7B. By taking as input a system prompt, basic and custom actions, and a task instruction, the model generates thoughtful reasoning (`thought`) and executes the appropriate next step (`action`).
+Note that the released `OS-Atlas-Pro-7B model` is described in the Section 5.4 of the paper. Compared to the OS-Atlas model in Tables 4 and 5, the Pro model demonstrates superior generalizability and performance. Critically, it is not constrained to specific tasks or training datasets merely to satisfy particular experimental conditions like OOD and SFT. Furthermore, this approach prevents us from overdosing HuggingFace by uploading over 20+ distinct model checkpoints.
 ### Installation
 To use `OS-Atlas-Action-7B`, first install the necessary dependencies:
 ```bash
 ```
 ### Example Inference Code
+First download the [example image](https://github.com/OS-Copilot/OS-Atlas/blob/main/examples/images/action_example_1.jpg) and save it to the current directory.
+Below is an example of how to perform inference using the model:
 ```python
 from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
 from qwen_vl_utils import process_vision_info
             },
             {
                 "type": "image",
+                "image": "./action_example_1.jpg",
             },
             {"type": "text", "text": "Task instruction: to allow the user to enter their first name\nHistory: null" },
         ],