Instructions to use Sansjudge/eagle360_qwen3vl_grpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sansjudge/eagle360_qwen3vl_grpo with Transformers:

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

pipe = pipeline("image-text-to-text", model="Sansjudge/eagle360_qwen3vl_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("Sansjudge/eagle360_qwen3vl_grpo")
model = AutoModelForMultimodalLM.from_pretrained("Sansjudge/eagle360_qwen3vl_grpo", 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 Sansjudge/eagle360_qwen3vl_grpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sansjudge/eagle360_qwen3vl_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": "Sansjudge/eagle360_qwen3vl_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/Sansjudge/eagle360_qwen3vl_grpo

SGLang

How to use Sansjudge/eagle360_qwen3vl_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 "Sansjudge/eagle360_qwen3vl_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": "Sansjudge/eagle360_qwen3vl_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 "Sansjudge/eagle360_qwen3vl_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": "Sansjudge/eagle360_qwen3vl_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 Sansjudge/eagle360_qwen3vl_grpo with Docker Model Runner:
```
docker model run hf.co/Sansjudge/eagle360_qwen3vl_grpo
```

EAGLE-360 Qwen3-VL GRPO

Project page: EAGLE-360

Paper: arXiv:2607.02479

This repository contains the merged Hugging Face checkpoint used by EAGLE-360 for 360-degree panoramic object localization. Given a panoramic image and a target-object query, the model predicts the object's azimuth and elevation in degrees through multi-turn global-to-local reasoning.

The checkpoint is based on Qwen3-VL and fine-tuned with panoramic multi-turn reasoning and GRPO. It is intended to be used with the EAGLE-360 evaluation code and the panoramic Rolling RoPE patches provided in the project repository.

Data

Public test split: Sansjudge/eagle360_test

Usage

Please install the dependencies and apply the vLLM/Transformers panoramic patches from the EAGLE-360 project repository before running evaluation.

python eval.py \
  --model ./checkpoints/hf_merged \
  --test_file ./eagle360_test/test.json \
  --pano_dir ./eagle360_test/images \
  --n_samples 50

Citation

@misc{xu2026eagle360embodiedactiveglobaltolocal,
      title={EAGLE-360: Embodied Active Global-to-Local Exploration in 360$^\circ$},
      author={Jingtao Xu and Zizhuo Lin and Jianwen Sun and Yi Yang and Yawei Luo},
      year={2026},
      eprint={2607.02479},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2607.02479},
}

Downloads last month: 9

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for Sansjudge/eagle360_qwen3vl_grpo

Base model

Qwen/Qwen3-VL-4B-Instruct

Finetuned

(402)

this model

Paper for Sansjudge/eagle360_qwen3vl_grpo

EAGLE-360: Embodied Active Global-to-Local Exploration in 360^circ

Paper • 2607.02479 • Published Jul 2 • 1