Instructions to use Qwen/Qwen2.5-VL-72B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2.5-VL-72B-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="Qwen/Qwen2.5-VL-72B-Instruct")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-72B-Instruct")
model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen2.5-VL-72B-Instruct", device_map="auto")
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen2.5-VL-72B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen2.5-VL-72B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen2.5-VL-72B-Instruct",
		"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/Qwen/Qwen2.5-VL-72B-Instruct

SGLang

How to use Qwen/Qwen2.5-VL-72B-Instruct 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 "Qwen/Qwen2.5-VL-72B-Instruct" \
    --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": "Qwen/Qwen2.5-VL-72B-Instruct",
		"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 "Qwen/Qwen2.5-VL-72B-Instruct" \
        --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": "Qwen/Qwen2.5-VL-72B-Instruct",
		"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 Qwen/Qwen2.5-VL-72B-Instruct with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2.5-VL-72B-Instruct
```

changdazhou commited on 2 days ago

Commit

8b486b8

verified ·

1 Parent(s): 89c8620

Add Real5-OmniDocBench evaluation results for Qwen2.5-VL-72B

Browse files

# Real5-OmniDocBench evaluation results for Qwen2.5-VL-72B

This PR adds the evaluation file for Qwen2.5-VL-72B under the Hugging Face
evaluation-results workflow.

This is based on the new evaluation results feature: https://huggingface.co/docs/hub/eval-results.

## Dataset
- [PaddlePaddle/Real5-OmniDocBench](https://huggingface.co/datasets/PaddlePaddle/Real5-OmniDocBench)

## File
- `.eval_results/real5_omnidocbench.yaml`

## Tasks
- overall
- scanning
- warping
- screen_photography
- illumination
- skew

Files changed (1) hide show

.eval_results/real5_omnidocbench.yaml +54 -0

.eval_results/real5_omnidocbench.yaml ADDED Viewed

	@@ -0,0 +1,54 @@

+- dataset:
+    id: PaddlePaddle/Real5-OmniDocBench
+    task_id: overall
+  value: 86.92
+  source:
+    url: https://paddle-model-ecology.bj.bcebos.com/PPOCRVL/AIStudio/real5_omnidocbench/leaderboard_data.json
+    name: Real5-OmniDocBench leaderboard data
+    user: PaddlePaddle
+  notes: Qwen2.5-VL-72B; official Real5-OmniDocBench result
+- dataset:
+    id: PaddlePaddle/Real5-OmniDocBench
+    task_id: scanning
+  value: 86.19
+  source:
+    url: https://paddle-model-ecology.bj.bcebos.com/PPOCRVL/AIStudio/real5_omnidocbench/leaderboard_data.json
+    name: Real5-OmniDocBench leaderboard data
+    user: PaddlePaddle
+  notes: Qwen2.5-VL-72B; official Real5-OmniDocBench result
+- dataset:
+    id: PaddlePaddle/Real5-OmniDocBench
+    task_id: warping
+  value: 87.77
+  source:
+    url: https://paddle-model-ecology.bj.bcebos.com/PPOCRVL/AIStudio/real5_omnidocbench/leaderboard_data.json
+    name: Real5-OmniDocBench leaderboard data
+    user: PaddlePaddle
+  notes: Qwen2.5-VL-72B; official Real5-OmniDocBench result
+- dataset:
+    id: PaddlePaddle/Real5-OmniDocBench
+    task_id: screen_photography
+  value: 86.48
+  source:
+    url: https://paddle-model-ecology.bj.bcebos.com/PPOCRVL/AIStudio/real5_omnidocbench/leaderboard_data.json
+    name: Real5-OmniDocBench leaderboard data
+    user: PaddlePaddle
+  notes: Qwen2.5-VL-72B; official Real5-OmniDocBench result
+- dataset:
+    id: PaddlePaddle/Real5-OmniDocBench
+    task_id: illumination
+  value: 87.25
+  source:
+    url: https://paddle-model-ecology.bj.bcebos.com/PPOCRVL/AIStudio/real5_omnidocbench/leaderboard_data.json
+    name: Real5-OmniDocBench leaderboard data
+    user: PaddlePaddle
+  notes: Qwen2.5-VL-72B; official Real5-OmniDocBench result
+- dataset:
+    id: PaddlePaddle/Real5-OmniDocBench
+    task_id: skew
+  value: 86.9
+  source:
+    url: https://paddle-model-ecology.bj.bcebos.com/PPOCRVL/AIStudio/real5_omnidocbench/leaderboard_data.json
+    name: Real5-OmniDocBench leaderboard data
+    user: PaddlePaddle
+  notes: Qwen2.5-VL-72B; official Real5-OmniDocBench result