Instructions to use kjunh/v1-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kjunh/v1-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="kjunh/v1-7B", trust_remote_code=True)
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 AutoModelForConditionalGeneration
model = AutoModelForConditionalGeneration.from_pretrained("kjunh/v1-7B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kjunh/v1-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kjunh/v1-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kjunh/v1-7B",
		"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/kjunh/v1-7B

SGLang

How to use kjunh/v1-7B 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 "kjunh/v1-7B" \
    --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": "kjunh/v1-7B",
		"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 "kjunh/v1-7B" \
        --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": "kjunh/v1-7B",
		"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 kjunh/v1-7B with Docker Model Runner:
```
docker model run hf.co/kjunh/v1-7B
```

Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation

Jiwan Chung^* Junhyeok Kim^* Siyeol Kim Jaeyoung Lee Minsoo Kim Youngjae Yu

Installation

conda create -n v1 python=3.10 -y
conda activate v1
pip install -r requirements.txt
pip install flash-attn --no-build-isolation

Demo

Gradio Web UI

Highly Recommended as the copy tokens are displayed on image.

python run_gradio.py

Inference

python inference.py

The script uses a default image URL and text prompt. To use your own inputs, you can modify the image variable within the messages list and the text field for the user prompt.

Coming Soon

Inference code
Training data
Evaluation code
Training code

Citation

If you find our work valuable, please cite:

@misc{chung2025dontlookoncemultimodal,
      title={Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation}, 
      author={Jiwan Chung and Junhyeok Kim and Siyeol Kim and Jaeyoung Lee and Min Soo Kim and Youngjae Yu},
      year={2025},
      eprint={2505.18842},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.18842}, 
}

Downloads last month: 712

Safetensors

Model size

8B params

Tensor type

BF16

Paper for kjunh/v1-7B

Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation

Paper • 2505.18842 • Published May 24, 2025 • 36