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

Libraries

How to use OS-Copilot/OS-Atlas-Base-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-Base-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-Base-7B")
model = AutoModelForImageTextToText.from_pretrained("OS-Copilot/OS-Atlas-Base-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-Base-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-Base-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-Base-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-Base-7B

SGLang

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

while deploying the OS-Atlas-Base-7B Getting "ValueError: Unsupported model type qwen2_vl" Error

by Saurabh-hiehq - opened Jan 22, 2025

Discussion

Saurabh-hiehq

Jan 22, 2025

•

edited Jan 22, 2025

import boto3
import sagemaker
from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri

Explicitly set the region

session = boto3.Session(aws_access_key_id="your id",
aws_secret_access_key="your key",
region_name="us-east-1") # Change region as needed
sagemaker_session = sagemaker.Session(boto_session=session)

Check the region explicitly

print(f"Region: {sagemaker_session.boto_session.region_name}")

Use this session in your Hugging Face deployment

role = "your role"
hub = {'HF_MODEL_ID': 'OS-Copilot/OS-Atlas-Base-7B', 'SM_NUM_GPUS': '1', 'TRUST_REMOTE_CODE': 'true'}

huggingface_model = sagemaker.huggingface.HuggingFaceModel(
role=role,
env=hub,
sagemaker_session=sagemaker_session,
image_uri = sagemaker.huggingface.get_huggingface_llm_image_uri(
backend="huggingface",
region="us-east-1", # Explicitly set the region here
version="2.3.1"))

try:
predictor = huggingface_model.deploy(
initial_instance_count=1,
instance_type="ml.g5.4xlarge",
container_startup_health_check_timeout=300,
)
response = predictor.predict({"inputs": "Hi, what can you help me with?"})
print("model_response::::",response)
except Exception as e:
print(f"Deployment failed: {e}")

print(predictor.predict({"inputs": "Hi, what can you help me with?"}))

########
Using above code to create inference endpoint but getting error

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment