Instructions to use xinyili0624/GPD-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xinyili0624/GPD-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="xinyili0624/GPD-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)

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

processor = AutoProcessor.from_pretrained("xinyili0624/GPD-4B")
model = AutoModelForMultimodalLM.from_pretrained("xinyili0624/GPD-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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xinyili0624/GPD-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xinyili0624/GPD-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": "xinyili0624/GPD-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/xinyili0624/GPD-4B

SGLang

How to use xinyili0624/GPD-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 "xinyili0624/GPD-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": "xinyili0624/GPD-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 "xinyili0624/GPD-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": "xinyili0624/GPD-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 xinyili0624/GPD-4B with Docker Model Runner:
```
docker model run hf.co/xinyili0624/GPD-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

GPD-4B

Official checkpoint of GPD (Geometry-Privileged Distillation) from the paper Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models.

Base model: Qwen3-VL-4B-Instruct
Training data: Mixed-15k (VSI 10k + SPAR 4k + MindCube 1k), text_routed variant
Training: GRPO + privileged KL on incorrect trajectories (kl_coef=0.003), 111 steps
Inference: RGB-only, same interface as the base model

Results

Model	VSI-Bench	Avg. (MindCube / SPAR / MMSI / ViewSpatial)
GRPO	56.4	35.7
OPSD (answer privilege)	55.7	31.5
GPD	57.1	37.6

Usage

from transformers import AutoProcessor, Qwen3VLForConditionalGeneration

model_id = "xinyili0624/GPD-4B"
model = Qwen3VLForConditionalGeneration.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained(model_id)

Usage is identical to Qwen3-VL-4B-Instruct; see the base model card for image / video inference examples.

Downloads last month: 31

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for xinyili0624/GPD-4B

Base model

Qwen/Qwen3-VL-4B-Instruct

Finetuned

(472)

this model

Quantizations

1 model

Space using xinyili0624/GPD-4B 1

Paper for xinyili0624/GPD-4B

Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models

Paper • 2610.12355 • Published 5 days ago • 8