Instructions to use Qwen/QVQ-72B-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/QVQ-72B-Preview with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Qwen/QVQ-72B-Preview") 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("Qwen/QVQ-72B-Preview") model = AutoModelForImageTextToText.from_pretrained("Qwen/QVQ-72B-Preview") 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 Qwen/QVQ-72B-Preview with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/QVQ-72B-Preview" # 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/QVQ-72B-Preview", "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/QVQ-72B-Preview
- SGLang
How to use Qwen/QVQ-72B-Preview 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/QVQ-72B-Preview" \ --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/QVQ-72B-Preview", "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/QVQ-72B-Preview" \ --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/QVQ-72B-Preview", "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/QVQ-72B-Preview with Docker Model Runner:
docker model run hf.co/Qwen/QVQ-72B-Preview
Supports function calls/structured outputs
?
function calls is extremely usefull
I doubt it is gonna be the best in function calling since the authors said it has a tendency to go off track when thinking to itself.
After modify tokenizer.conf to support both image & tool_call , I found the model was not trained to support function tools. What a pity the fling wheel can not be accelerated.
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}\n {%- for tool in tools %}\n {{- "\n" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == "assistant" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\n\n{"name": "' }}\n {{- tool_call.name }}\n {{- '", "arguments": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\n' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == "tool" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\n\n' }}\n {{- message.content }}\n {{- '\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}\n {{- '<|im_end|>\n' }}\n {%- endif %}\n {%- endif %}\n {# 添加对图片和视频的处理 #}\n {%- if message.content is not string and message.content is defined %}\n {%- for content in message.content %}\n {%- if content['type'] == 'image' or 'image' in content or 'image_url' in content %}\n {{- '\n' }}\n {%- if add_vision_id %}\n Picture {{ loop.index }}: \n {%- endif %}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content['type'] == 'video' or 'video' in content %}\n {{- '\n' }}\n {%- if add_vision_id %}\n Video {{ loop.index }}: \n {%- endif %}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content['text'] }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n",
Please I did not know how to use it