Instructions to use CewEhao/OPD-Aha-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CewEhao/OPD-Aha-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="CewEhao/OPD-Aha-4B")
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("CewEhao/OPD-Aha-4B")
model = AutoModelForMultimodalLM.from_pretrained("CewEhao/OPD-Aha-4B", 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 CewEhao/OPD-Aha-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CewEhao/OPD-Aha-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CewEhao/OPD-Aha-4B",
		"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/CewEhao/OPD-Aha-4B

SGLang

How to use CewEhao/OPD-Aha-4B 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 "CewEhao/OPD-Aha-4B" \
    --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": "CewEhao/OPD-Aha-4B",
		"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 "CewEhao/OPD-Aha-4B" \
        --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": "CewEhao/OPD-Aha-4B",
		"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 CewEhao/OPD-Aha-4B with Docker Model Runner:
```
docker model run hf.co/CewEhao/OPD-Aha-4B
```

👁️ OPD-Aha: From Linguistic Momentum to Visual Reflection in Multimodal On-Policy Distillation

🤗 Hugging Face model: CewEhao/OPD-Aha-4B · 💻 Code: Echochef/OPD-Aha

👉 Introduction

This is the official model card for OPD-Aha-4B, built on Qwen/Qwen3.5-4B.

OPD-Aha is an on-policy self-distillation framework for improving fine-grained visual perception and multimodal mathematical reasoning. It trains the model with a frozen visual teacher and a counterfactual visual input so that learning focuses on evidence that changes the teacher distribution.

⚡ Serving

The project provides a vLLM serving entrypoint:

git clone https://github.com/Echochef/OPD-Aha.git
cd OPD-Aha

MODEL_PATH=CewEhao/OPD-Aha-4B \
SERVED_MODEL_NAME=opd-aha-4b \
  bash scripts/serve_model.sh

🏋️ Training and evaluation

Training, checkpoint merging, inference, and evaluation code is available in Echochef/OPD-Aha. The repository includes fine-grained perception evaluation for V*Bench, HR-Bench, MME-RealWorld, and ZoomBench, together with mathematical reasoning evaluation for MathVista, MathVerse, WeMath, MathVision, and DynaMath.

🙏 Acknowledgements

OPD-Aha builds on Qwen, verl, vLLM, and Vision-OPD.

📄 License

This model is released under the Apache-2.0 License. The base model and datasets remain subject to their respective licenses.

Downloads last month: -

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for CewEhao/OPD-Aha-4B

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(631)

this model