Shuffle-R1-Qwen-3B

Shuffle-R1-Qwen-3B

This is the model checkpoint of Shuffle-R1-Qwen-3B. It is trained based on Qwen2.5-VL-3B

Model Performance

All models are evaluated under CoT prompt.

Inference

Using Transformers

The process is the same as Qwen2.5-VL. Note that it is better to add a "Thinking prompt" at the begining of user query.

from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info

model_path = "path/to/your/checkpoint"

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    device_map="auto",
)

processor = AutoProcessor.from_pretrained(model_path)

system_prompt = """
You FIRST think about the reasoning process as an internal monologue and then provide the final answer. The reasoning process MUST BE enclosed within <think> </think> tags. The final answer MUST BE put in \\boxed{}.
"""

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "path/to/your/image"},
            {"type": "text", "text": system_prompt + "YOUR TEXT QUERY HERE"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to(model.device)

generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

Using vLLM

Our model also supports inference using vLLM.

Please refer to our Official Repo for detailed instructions.

Citation

If you find our work useful for your research, please consider citing:

@misc{zhu2025shuffler1,
      title={Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle}, 
      author={Linghao Zhu, Yiran Guan, Dingkang Liang, Jianzhong Ju, Zhenbo Luo, Bin Qin, Jian Luan, Yuliang Liu, Xiang Bai},
      year={2025},
      eprint={2508.05612},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2508.05612}, 
}