Instructions to use OS-Copilot/OS-Genesis-8B-AW with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OS-Copilot/OS-Genesis-8B-AW with Transformers:

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

pipe = pipeline("image-text-to-text", model="OS-Copilot/OS-Genesis-8B-AW", 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-Genesis-8B-AW", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OS-Copilot/OS-Genesis-8B-AW with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OS-Copilot/OS-Genesis-8B-AW"
# 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-Genesis-8B-AW",
		"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-Genesis-8B-AW

SGLang

How to use OS-Copilot/OS-Genesis-8B-AW 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-Genesis-8B-AW" \
    --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-Genesis-8B-AW",
		"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-Genesis-8B-AW" \
        --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-Genesis-8B-AW",
		"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-Genesis-8B-AW with Docker Model Runner:
```
docker model run hf.co/OS-Copilot/OS-Genesis-8B-AW
```

nielsr HF Staff commited on May 1, 2025

Commit

62b8e66

verified ·

1 Parent(s): d0cd248

Add link to project page and correct pipeline tag

Browse files

This PR makes sure the model card is linked to the project page and the pipeline tag is set to any-to-any.

Files changed (1) hide show

README.md +11 -5

README.md CHANGED Viewed

@@ -1,8 +1,8 @@
 ---
-license: apache-2.0
-library_name: transformers
 base_model: OpenGVLab/InternVL2-4B
-pipeline_tag: image-text-to-text
 ---
 # OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
@@ -137,9 +137,15 @@ tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast
 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 = "<image>\nYou are a GUI task expert, I will provide you with a high-level instruction, an action history, a screenshot with its corresponding accessibility tree.\n High-level instruction: {high_level_instruction}\n Action history: {action_history}\n Accessibility tree: {a11y_tree}\n  Please generate the low-level thought and action for the next step."
 response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
 ```

 ---
 base_model: OpenGVLab/InternVL2-4B
+library_name: transformers
+license: apache-2.0
+pipeline_tag: any-to-any
 ---
 # OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
 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 = "<image>
+You are a GUI task expert, I will provide you with a high-level instruction, an action history, a screenshot with its corresponding accessibility tree.
+ High-level instruction: {high_level_instruction}
+ Action history: {action_history}
+ Accessibility tree: {a11y_tree}
+  Please generate the low-level thought and action for the next step."
 response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
+print(f'User: {question}
+Assistant: {response}')
 ```