Instructions to use P1n3/sdg-detector-grpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use P1n3/sdg-detector-grpo with Transformers:

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

pipe = pipeline("image-text-to-text", model="P1n3/sdg-detector-grpo")
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("P1n3/sdg-detector-grpo")
model = AutoModelForMultimodalLM.from_pretrained("P1n3/sdg-detector-grpo")
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 P1n3/sdg-detector-grpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "P1n3/sdg-detector-grpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "P1n3/sdg-detector-grpo",
		"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/P1n3/sdg-detector-grpo

SGLang

How to use P1n3/sdg-detector-grpo 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 "P1n3/sdg-detector-grpo" \
    --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": "P1n3/sdg-detector-grpo",
		"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 "P1n3/sdg-detector-grpo" \
        --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": "P1n3/sdg-detector-grpo",
		"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 P1n3/sdg-detector-grpo with Docker Model Runner:
```
docker model run hf.co/P1n3/sdg-detector-grpo
```

SDG Detector — GRPO Stage (Merged Checkpoint)

This repository provides the merged full checkpoint of the SDG detector after Stage-2 GRPO. It is already merged with the Stage-1 SFT checkpoint (P1n3/sdg-detector-sft) and can be loaded directly with transformers.

Important: this is not a PEFT/LoRA adapter. Do not load it with PeftModel.from_pretrained, and do not merge it into Qwen/Qwen3-VL-4B-Instruct or P1n3/sdg-detector-sft.

Training Summary

field	value
initialization	`P1n3/sdg-detector-sft`
training stage	GRPO
reward	composite: 0.6×DIoU + 0.25×DescCos + 0.15×ImpAcc
epochs	2
learning rate	5.0e-6
rollouts/prompt	8
precision	bf16
hardware	16 × A100-80G (2 nodes × 8)

Quick Start

from transformers import AutoProcessor, AutoModelForImageTextToText
import torch

ckpt = "P1n3/sdg-detector-grpo"  # merged full checkpoint

processor = AutoProcessor.from_pretrained(ckpt)
model = AutoModelForImageTextToText.from_pretrained(
    ckpt,
    dtype=torch.bfloat16,
    device_map="auto",
)
model.eval()

For SGLang/OpenAI-compatible serving in BoxFlow-GRPO:

python -m sglang.launch_server \
  --model-path P1n3/sdg-detector-grpo \
  --served-model-name sdg-detector \
  --port 17142 --tp 4 --api-key flowgrpo --trust-remote-code

Output Format

The detector predicts structured defect sets:

<think>
... reasoning about image quality and caption alignment ...
</think>
<answer>
[
  {
    "box_2d": [x0, y0, x1, y1],
    "label": "artifact" or "misalignment",
    "description": "...",
    "importance": 1-100
  }
]
</answer>

License

cc-by-nc-4.0. This checkpoint is derived from P1n3/sdg-detector-sft (itself a derivative of Qwen/Qwen3-VL-4B-Instruct, Apache-2.0). Research and non-commercial use only.

Citation

@article{zhang2026and,
  title={Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback},
  author={Zhang, Huaisong and Yu, Hao and Zhang, Yuxuan and Wang, Jiahe and Chen, Xinrui and Cao, Haoxiang and Lu, Feng and Zhang, Wendong and Yu, Changqian and Yuan, Chun},
  journal={arXiv preprint arXiv:2606.06113},
  year={2026}
}