Instructions to use aaniri/OPD-V-Qwen3-VL-4B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aaniri/OPD-V-Qwen3-VL-4B-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="aaniri/OPD-V-Qwen3-VL-4B-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("aaniri/OPD-V-Qwen3-VL-4B-Instruct")
model = AutoModelForMultimodalLM.from_pretrained("aaniri/OPD-V-Qwen3-VL-4B-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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aaniri/OPD-V-Qwen3-VL-4B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aaniri/OPD-V-Qwen3-VL-4B-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": "aaniri/OPD-V-Qwen3-VL-4B-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/aaniri/OPD-V-Qwen3-VL-4B-Instruct

SGLang

How to use aaniri/OPD-V-Qwen3-VL-4B-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 "aaniri/OPD-V-Qwen3-VL-4B-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": "aaniri/OPD-V-Qwen3-VL-4B-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 "aaniri/OPD-V-Qwen3-VL-4B-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": "aaniri/OPD-V-Qwen3-VL-4B-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 aaniri/OPD-V-Qwen3-VL-4B-Instruct with Docker Model Runner:
```
docker model run hf.co/aaniri/OPD-V-Qwen3-VL-4B-Instruct
```

OPD-V

This model checkpoint is part of OPD-V, presented in the paper OPD-V: Self-Distillation Improves Visual Detail Perception in Vision-Language Models.

Code & Repository: GitHub - OPD-V
Base Model: Qwen/Qwen3-VL-4B-Instruct
Paper: OPD-V: Self-Distillation Improves Visual Detail Perception in Vision-Language Models

Overview

OPD-V is a visual On-Policy Self-Distillation (OPSD) framework for improving multimodal reasoning under Modality Imbalance. Instead of relying on a single privileged teacher, OPD-V contrasts a Positive Teacher conditioned on a Zoom-In Image with a Negative Teacher conditioned on a Mask Image, and distills only the on-policy tokens selected by the resulting Modality-Balance Trust Region.

This checkpoint corresponds to OPD-V-Qwen3-VL-4B-Instruct trained with teacher-box positive images and random-mask negative images.

Citation

@misc{opdv2026,
  title={OPD-V: Self-Distillation Improves Visual Detail Perception in Vision-Language Models},
  author={},
  year={2026},
  eprint={2608.05131},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

Downloads last month: 6

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for aaniri/OPD-V-Qwen3-VL-4B-Instruct

Base model

Qwen/Qwen3-VL-4B-Instruct

Finetuned

(378)

this model

Paper for aaniri/OPD-V-Qwen3-VL-4B-Instruct

OPD-V: Visual On-Policy Self-Distillation with Modality Balance

Paper • 2608.05131 • Published 8 days ago • 12