Instructions to use xlangai/OpenCUA-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xlangai/OpenCUA-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="xlangai/OpenCUA-7B", 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("xlangai/OpenCUA-7B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xlangai/OpenCUA-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xlangai/OpenCUA-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": "xlangai/OpenCUA-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/xlangai/OpenCUA-7B

SGLang

How to use xlangai/OpenCUA-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 "xlangai/OpenCUA-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": "xlangai/OpenCUA-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 "xlangai/OpenCUA-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": "xlangai/OpenCUA-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 xlangai/OpenCUA-7B with Docker Model Runner:
```
docker model run hf.co/xlangai/OpenCUA-7B
```

xywang626

LutherXD commited on Jan 15

Commit

49c54f8

verified ·

1 Parent(s): 20f7829

add _support_sdpa property to support more transformers version (#7)

Browse files

- add _support_sdpa property to support more transformers version (c366a9cb6e7c970ad5452a9a20a22aef1824bd1c)

Co-authored-by: mqhuang <LutherXD@users.noreply.huggingface.co>

Files changed (1) hide show

modeling_opencua.py +5 -4

modeling_opencua.py CHANGED Viewed

@@ -67,6 +67,10 @@ class OpenCUAPreTrainedModel(PreTrainedModel):
     _skip_keys_device_placement = "past_key_values"
     _supports_flash_attn_2 = True
     def _init_weights(self, module):
         # important: this ported version of Llava isn't meant for training from scratch - only
         # inference and fine-tuning - so the proper init weights code has been removed - the original codebase
@@ -95,11 +99,8 @@ class OpenCUAForConditionalGeneration(OpenCUAPreTrainedModel):
         super().__init__(config)
         self.vision_tower = Qwen2_5_VisionTransformerPretrainedModel(config.vision_config)
         self.language_model = Qwen2ForCausalLM(config.text_config)
         self.post_init()
-    @property
-    def _supports_sdpa(self):
-        return self.language_model._supports_sdpa
     # 使用 property 来创建动态属性
     @property

     _skip_keys_device_placement = "past_key_values"
     _supports_flash_attn_2 = True
+    supports_gradient_checkpointing = True
+    _supports_sdpa = True
     def _init_weights(self, module):
         # important: this ported version of Llava isn't meant for training from scratch - only
         # inference and fine-tuning - so the proper init weights code has been removed - the original codebase
         super().__init__(config)
         self.vision_tower = Qwen2_5_VisionTransformerPretrainedModel(config.vision_config)
         self.language_model = Qwen2ForCausalLM(config.text_config)
+        self._supports_sdpa = True
         self.post_init()
     # 使用 property 来创建动态属性
     @property