Instructions to use SESPOIR/ReGround-Qwen2.5-VL-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SESPOIR/ReGround-Qwen2.5-VL-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="SESPOIR/ReGround-Qwen2.5-VL-7B")
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("SESPOIR/ReGround-Qwen2.5-VL-7B")
model = AutoModelForMultimodalLM.from_pretrained("SESPOIR/ReGround-Qwen2.5-VL-7B", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SESPOIR/ReGround-Qwen2.5-VL-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SESPOIR/ReGround-Qwen2.5-VL-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": "SESPOIR/ReGround-Qwen2.5-VL-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/SESPOIR/ReGround-Qwen2.5-VL-7B

SGLang

How to use SESPOIR/ReGround-Qwen2.5-VL-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 "SESPOIR/ReGround-Qwen2.5-VL-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": "SESPOIR/ReGround-Qwen2.5-VL-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 "SESPOIR/ReGround-Qwen2.5-VL-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": "SESPOIR/ReGround-Qwen2.5-VL-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 SESPOIR/ReGround-Qwen2.5-VL-7B with Docker Model Runner:
```
docker model run hf.co/SESPOIR/ReGround-Qwen2.5-VL-7B
```

ReGround Qwen2.5-VL-7B

This is the final model checkpoint for ReGround, a visual reasoning method that teaches a vision-language model to request fresh visual evidence through a structured <reground> self-diagnosis.

When <reground> is emitted, the inference controller should re-inject the original image and ask the model to complete its reasoning and final answer. The public repository provides the two-round inference adapter, data construction pipeline, SFT recipe, and Stage-2 GRPO implementation.

The released weights were trained in two stages: full-parameter supervised fine-tuning on structured ReGround trajectories, followed by GRPO policy optimization of the re-examination behavior.

Usage

from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration

model_id = "SESPOIR/ReGround-Qwen2.5-VL-7B"
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    model_id,
    dtype="auto",
    device_map="auto",
)
processor = AutoProcessor.from_pretrained(model_id)

For complete two-round visual inference and evaluation, follow the ReGround repository.

Training

Stage 1 applies full-parameter supervised fine-tuning to Qwen2.5-VL-7B-Instruct using structured visual reasoning trajectories. Stage 2 uses GRPO to optimize self-diagnosis, answer accuracy, and output format. The training format uses <think>, <reground>, and <answer> blocks; portable configurations for both stages are available in the project repository.

Limitations

The model can produce incorrect reasoning or answers and may trigger visual re-examination unnecessarily. It is intended for research use and should not be relied on for high-stakes decisions without independent verification.

Downloads last month: 48

Safetensors

Model size

849k params

Tensor type

BF16

Model tree for SESPOIR/ReGround-Qwen2.5-VL-7B

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Finetuned

(1163)

this model