Instructions to use glab-caltech/TWIN-Qwen2.5-VL-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use glab-caltech/TWIN-Qwen2.5-VL-3B with Transformers:

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

pipe = pipeline("image-text-to-text", model="glab-caltech/TWIN-Qwen2.5-VL-3B")
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("glab-caltech/TWIN-Qwen2.5-VL-3B")
model = AutoModelForImageTextToText.from_pretrained("glab-caltech/TWIN-Qwen2.5-VL-3B")
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 glab-caltech/TWIN-Qwen2.5-VL-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "glab-caltech/TWIN-Qwen2.5-VL-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "glab-caltech/TWIN-Qwen2.5-VL-3B",
		"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/glab-caltech/TWIN-Qwen2.5-VL-3B

SGLang

How to use glab-caltech/TWIN-Qwen2.5-VL-3B 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 "glab-caltech/TWIN-Qwen2.5-VL-3B" \
    --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": "glab-caltech/TWIN-Qwen2.5-VL-3B",
		"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 "glab-caltech/TWIN-Qwen2.5-VL-3B" \
        --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": "glab-caltech/TWIN-Qwen2.5-VL-3B",
		"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 glab-caltech/TWIN-Qwen2.5-VL-3B with Docker Model Runner:
```
docker model run hf.co/glab-caltech/TWIN-Qwen2.5-VL-3B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for TWIN-Qwen2.5-VL-3B

This is the Qwen2.5-VL-3B-Instruct model post-trained on the TWIN dataset from the paper: Same or Not? Enhancing Visual Perception in Vision-Language Models

For further information please refer to the project webpage, paper, and repository.

Citation

If you use TWIN in your research, please consider citing our work:

BibTeX:

@misc{marsili2025notenhancingvisualperception,
      title={Same or Not? Enhancing Visual Perception in Vision-Language Models}, 
      author={Damiano Marsili and Aditya Mehta and Ryan Y. Lin and Georgia Gkioxari},
      year={2025},
      eprint={2512.23592},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.23592}, 
}

License

The dataset is derived from the UCSD Amazon Reviews’23 dataset. Use is permitted for research and educational purposes only. By using this dataset, you agree to respect the rights of original content owners and comply with applicable terms of service.