Instructions to use jihochoi/DR-MV3D-R-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jihochoi/DR-MV3D-R-SFT with Transformers:

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

pipe = pipeline("image-text-to-text", model="jihochoi/DR-MV3D-R-SFT")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("jihochoi/DR-MV3D-R-SFT")
model = AutoModelForMultimodalLM.from_pretrained("jihochoi/DR-MV3D-R-SFT", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jihochoi/DR-MV3D-R-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jihochoi/DR-MV3D-R-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jihochoi/DR-MV3D-R-SFT",
		"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/jihochoi/DR-MV3D-R-SFT

SGLang

How to use jihochoi/DR-MV3D-R-SFT 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 "jihochoi/DR-MV3D-R-SFT" \
    --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": "jihochoi/DR-MV3D-R-SFT",
		"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 "jihochoi/DR-MV3D-R-SFT" \
        --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": "jihochoi/DR-MV3D-R-SFT",
		"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 jihochoi/DR-MV3D-R-SFT with Docker Model Runner:
```
docker model run hf.co/jihochoi/DR-MV3D-R-SFT
```

DR-MV3D-R-SFT / README.md

jihochoi

Create README.md

a204687 verified about 1 month ago

preview code

Raw History Blame Contribute Delete

2.08 kB

metadata

license: apache-2.0
base_model: Qwen/Qwen2.5-VL-3B-Instruct
base_model_relation: finetune
library_name: transformers
pipeline_tag: image-text-to-text
language:
  - en
datasets:
  - MLL-Lab/MindCube
tags:
  - multi-view
  - spatial-reasoning
  - 3d-reasoning
  - visual-question-answering
  - cognitive-map

DR-MV3D (SFT)

Official checkpoint for Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views (ECCV 2026).

Paper · Project page · Code · SFT + GRPO checkpoint

DR-MV3D answers questions about a 3D scene shown from several viewpoints. This is the supervised fine-tuning stage: Qwen2.5-VL-3B-Instruct trained on map-grounded reasoning traces. For general use prefer the final SFT + GRPO checkpoint.

Usage

The model expects the structured task prompt it was trained with, and produces a cognitive map, per-view ego-centric maps, a reasoning chain and the answer. See the GitHub repository for the prompt format, data preparation, inference and evaluation.

python scripts/run_inference.py \
  --model-path jihochoi/DR-MV3D-R-SFT \
  -i data/prompts/MindCube_tinybench_drmv3d.jsonl \
  -o results/tinybench_responses.jsonl \
  --image-root data --batch-size 8

License

The weights are a fine-tune of Qwen2.5-VL-3B-Instruct and are released under Apache-2.0, the base model's license. The code is MIT-licensed.

Citation

@inproceedings{drmv3d2026,
  title={Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views},
  author={Choi, Jiho and Lee, Seonho and Park, Seojeong and Shim, Hyunjung},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  year={2026},
  eprint={2606.23557},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}