TBAC VLR1 3B Preview

🚀 TBAC-VLR1-3B-preview

TBAC-VLR1-3B-preview 是由腾讯 PCG 基础算法中心微调的多模态语言模型。它基于 Qwen2.5-VL-3B-Instruct，使用 Group Relative Policy Optimization (GRPO) 增强多模态推理能力，在多个多模态推理基准测试中，于同规模模型里取得了最先进的成果。

🚀 快速开始

TBAC-VLR1-3B-preview 是一个经过微调的多模态语言模型，基于 Qwen2.5-VL-3B-Instruct 进一步优化，在多模态推理任务中表现出色。

✨ 主要特性

• 多模态融合：能够处理图像和文本输入，实现跨模态的信息理解和推理。
• 强大推理能力：采用 Group Relative Policy Optimization (GRPO) 方法，在多个多模态推理基准测试中达到同规模模型的领先水平。

📊 性能表现

对比结果来源于 https://opencompass.org.cn。本模型的结果是通过在每个基准测试上进行离线评估得出的。

💻 使用示例

基础用法

from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "TencentBAC/TBAC-VLR1-3B-preview", torch_dtype="auto", device_map="auto"
)

processor = AutoProcessor.from_pretrained("TencentBAC/TBAC-VLR1-3B-preview")

messages = [
    {
        "role": "system",
        "content": "You are a helpful assistant. The user asks a question, and you solve it. You need first think about the reasoning process in the mind and then provides the user with the answer. The answer are enclosed within \\boxed{} tags i.e., reasoning process here \\boxed{ answer here }."
    },
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": image_path,
            },
            {"type": "text", "text": query},
        ],
    }
]

# 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("cuda")

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128, do_sample=False)
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)

📚 详细文档

引用方式

如果您在研究中发现本模型很有用，请考虑给予 ❤️ 并进行引用。谢谢！

@misc{Xu2025tbacvlr1,
  title={TBAC-VLR1-3B-preview}, 
  author={Junzhe Xu and Yuyang yin},
  url={https://huggingface.co/TencentBAC/TBAC-VLR1-3B-preview},
  year={2025},
}

关于

本模型由腾讯 PCG 基础算法中心创建，保留所有权利。

📄 许可证

本项目采用 Apache-2.0 许可证。