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
```

[Error in of repo inference] ValueError: size must contain 'shortest_edge' and 'longest_edge' keys.

by yuriivoievidka - opened Jun 13, 2025

Discussion

yuriivoievidka

Jun 13, 2025

When I run the inference example it fails to load processor it fails with error

ValueError Traceback (most recent call last)
Cell In[4], line 1
----> 1 processor = AutoProcessor.from_pretrained("OS-Copilot/OS-Atlas-Base-7B")

File /venv/main/lib/python3.12/site-packages/transformers/models/auto/processing_auto.py:376, in AutoProcessor.from_pretrained(cls, pretrained_model_name_or_path, **kwargs)
372 return processor_class.from_pretrained(
373 pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
374 )
375 elif processor_class is not None:
--> 376 return processor_class.from_pretrained(
377 pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
378 )
379 # Last try: we use the PROCESSOR_MAPPING.
380 elif type(config) in PROCESSOR_MAPPING:

File /venv/main/lib/python3.12/site-packages/transformers/processing_utils.py:1185, in ProcessorMixin.from_pretrained(cls, pretrained_model_name_or_path, cache_dir, force_download, local_files_only, token, revision, **kwargs)
1182 if token is not None:
1183 kwargs["token"] = token
-> 1185 args = cls._get_arguments_from_pretrained(pretrained_model_name_or_path, **kwargs)
1186 processor_dict, kwargs = cls.get_processor_dict(pretrained_model_name_or_path, **kwargs)
1187 return cls.from_args_and_dict(args, processor_dict, **kwargs)

File /venv/main/lib/python3.12/site-packages/transformers/processing_utils.py:1248, in ProcessorMixin._get_arguments_from_pretrained(cls, pretrained_model_name_or_path, **kwargs)
1245 else:
1246 attribute_class = cls.get_possibly_dynamic_module(class_name)
-> 1248 args.append(attribute_class.from_pretrained(pretrained_model_name_or_path, **kwargs))
1249 return args

File /venv/main/lib/python3.12/site-packages/transformers/models/auto/image_processing_auto.py:564, in AutoImageProcessor.from_pretrained(cls, pretrained_model_name_or_path, *inputs, **kwargs)
562 return image_processor_class.from_dict(config_dict, **kwargs)
563 elif image_processor_class is not None:
--> 564 return image_processor_class.from_dict(config_dict, **kwargs)
565 # Last try: we use the IMAGE_PROCESSOR_MAPPING.
566 elif type(config) in IMAGE_PROCESSOR_MAPPING:

File /venv/main/lib/python3.12/site-packages/transformers/image_processing_base.py:422, in ImageProcessingMixin.from_dict(cls, image_processor_dict, **kwargs)
419 if "crop_size" in kwargs and "crop_size" in image_processor_dict:
420 image_processor_dict["crop_size"] = kwargs.pop("crop_size")
--> 422 image_processor = cls(**image_processor_dict)
424 # Update image_processor with kwargs if needed
425 to_remove = []

File /venv/main/lib/python3.12/site-packages/transformers/models/qwen2_vl/image_processing_qwen2_vl.py:143, in Qwen2VLImageProcessor.init(self, do_resize, size, resample, do_rescale, rescale_factor, do_normalize, image_mean, image_std, do_convert_rgb, min_pixels, max_pixels, patch_size, temporal_patch_size, merge_size, **kwargs)
141 super().init(**kwargs)
142 if size is not None and ("shortest_edge" not in size or "longest_edge" not in size):
--> 143 raise ValueError("size must contain 'shortest_edge' and 'longest_edge' keys.")
144 else:
145 size = {"shortest_edge": 56 * 56, "longest_edge": 28 * 28 * 1280}

ValueError: size must contain 'shortest_edge' and 'longest_edge' keys.

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