Fancy-MLLM/R1-OneVision-7B

Model Overview

This is a multimodal large language model fine-tuned from Qwen2.5-VL on the R1-OneVision dataset. The model enhances vision-language understanding and reasoning capabilities, making it suitable for various tasks such as visual reasoning, image understanding.

Performance

Usage

You can load the model using the Hugging Face transformers library:

from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "Fancy-MLLM/R1-OneVison/R1-OneVison-7B", torch_dtype="auto", device_map="auto"
)

processor = AutoProcessor.from_pretrained("Fancy-MLLM/R1-OneVison/R1-OneVison-7B")

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "<your image path>"},
            {"type": "text", "text": "Hint: Please answer the question and provide the final answer at the end. Question: Which number do you have to write in the last daisy?"},
        ],
    }
]

# Preparation for inference
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=4096)
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)

Model Contact

• Xiaoxuan He: xiaoxuanhe@zju.edu.cn
• Hongkun Pan: panhongkun@zju.edu.cn