Instructions to use yongxianwei/Qwen2.5-VL-32B-VQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yongxianwei/Qwen2.5-VL-32B-VQA with Transformers:

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

pipe = pipeline("image-text-to-text", model="yongxianwei/Qwen2.5-VL-32B-VQA")
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("yongxianwei/Qwen2.5-VL-32B-VQA")
model = AutoModelForMultimodalLM.from_pretrained("yongxianwei/Qwen2.5-VL-32B-VQA", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yongxianwei/Qwen2.5-VL-32B-VQA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yongxianwei/Qwen2.5-VL-32B-VQA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yongxianwei/Qwen2.5-VL-32B-VQA",
		"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/yongxianwei/Qwen2.5-VL-32B-VQA

SGLang

How to use yongxianwei/Qwen2.5-VL-32B-VQA 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 "yongxianwei/Qwen2.5-VL-32B-VQA" \
    --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": "yongxianwei/Qwen2.5-VL-32B-VQA",
		"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 "yongxianwei/Qwen2.5-VL-32B-VQA" \
        --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": "yongxianwei/Qwen2.5-VL-32B-VQA",
		"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 yongxianwei/Qwen2.5-VL-32B-VQA with Docker Model Runner:
```
docker model run hf.co/yongxianwei/Qwen2.5-VL-32B-VQA
```

Qwen2.5-VL-7B-VQA

This is a LoRA adapter for Qwen2.5-VL-7B fine-tuned on Visual Question Answering tasks.

Model Details

Base Model: Qwen/Qwen2.5-VL-7B
Task: Visual Question Answering
Training Method: LoRA (Low-Rank Adaptation)
Framework: Transformers

Usage

from transformers import AutoModelForVision2Seq, AutoProcessor
from peft import PeftModel

# Load base model
base_model = AutoModelForVision2Seq.from_pretrained(
    "Qwen/Qwen2.5-VL-7B",
    trust_remote_code=True
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "yongxianwei/Qwen2.5-VL-7B-VQA")
processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B", trust_remote_code=True)

# Inference
# ... your inference code ...

Training Details

Fine-tuned using LoRA on specific Visual Question Answering datasets.

Citation

@misc{qwen2.5-vl-visual question answering,
  author = {Yongxian Wei},
  title = {Qwen2.5-VL LoRA for Visual Question Answering},
  year = {2024},
  publisher = {Hugging Face},
  url = {https://huggingface.co/yongxianwei/Qwen2.5-VL-7B-VQA}
}

Downloads last month: 24

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for yongxianwei/Qwen2.5-VL-32B-VQA

Adapters

1 model

Collection including yongxianwei/Qwen2.5-VL-32B-VQA

MLLMerging

Collection

23 items • Updated Nov 18, 2025 • 3