Internvit 300M 448px

🚀 InternViT-300M-448px

InternViT-300M-448px主要聚焦於提升視覺基礎模型的效率。該模型通過從強大的視覺基礎模型 InternViT-6B-448px-V1-5 中進行知識蒸餾而開發。它繼承了前者強大的魯棒性、OCR能力和高分辨率處理能力。

[📂 GitHub] [📜 InternVL 1.0] [📜 InternVL 1.5] [📜 Mini-InternVL] [📜 InternVL 2.5]

[🆕 Blog] [🗨️ Chat Demo] [🤗 HF Demo] [🚀 快速開始] [📖 文檔]

🚀 快速開始

⚠️ 重要提示

經測試，InternViT V2.5系列更適合用於構建多模態大語言模型（MLLMs），而非傳統的計算機視覺任務。

import torch
from PIL import Image
from transformers import AutoModel, CLIPImageProcessor

model = AutoModel.from_pretrained(
    'OpenGVLab/InternViT-300M-448px',
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True).cuda().eval()

image = Image.open('./examples/image1.jpg').convert('RGB')

image_processor = CLIPImageProcessor.from_pretrained('OpenGVLab/InternViT-300M-448px')

pixel_values = image_processor(images=image, return_tensors='pt').pixel_values
pixel_values = pixel_values.to(torch.bfloat16).cuda()

outputs = model(pixel_values)

✨ 主要特性

本次更新主要致力於提升視覺基礎模型的效率。通過從強大的視覺基礎模型 InternViT-6B-448px-V1-5 中進行知識蒸餾，開發出了InternViT-300M-448px。和其前身一樣，InternViT-300M-448px具有448×448的動態輸入分辨率，基本圖塊大小為448×448。訓練時允許1到12個圖塊，測試時擴展到1到40個圖塊。此外，它繼承了InternViT-6B-448px-V1-5強大的魯棒性、OCR能力和高分辨率處理能力。

📚 詳細文檔

模型詳情

📄 許可證

本項目採用MIT許可證發佈。

🔖 引用

如果您在研究中發現本項目很有用，請考慮引用以下文獻：

@article{chen2024expanding,
  title={Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling},
  author={Chen, Zhe and Wang, Weiyun and Cao, Yue and Liu, Yangzhou and Gao, Zhangwei and Cui, Erfei and Zhu, Jinguo and Ye, Shenglong and Tian, Hao and Liu, Zhaoyang and others},
  journal={arXiv preprint arXiv:2412.05271},
  year={2024}
}
@article{gao2024mini,
  title={Mini-internvl: A flexible-transfer pocket multimodal model with 5\% parameters and 90\% performance},
  author={Gao, Zhangwei and Chen, Zhe and Cui, Erfei and Ren, Yiming and Wang, Weiyun and Zhu, Jinguo and Tian, Hao and Ye, Shenglong and He, Junjun and Zhu, Xizhou and others},
  journal={arXiv preprint arXiv:2410.16261},
  year={2024}
}
@article{chen2024far,
  title={How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites},
  author={Chen, Zhe and Wang, Weiyun and Tian, Hao and Ye, Shenglong and Gao, Zhangwei and Cui, Erfei and Tong, Wenwen and Hu, Kongzhi and Luo, Jiapeng and Ma, Zheng and others},
  journal={arXiv preprint arXiv:2404.16821},
  year={2024}
}
@inproceedings{chen2024internvl,
  title={Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks},
  author={Chen, Zhe and Wu, Jiannan and Wang, Wenhai and Su, Weijie and Chen, Guo and Xing, Sen and Zhong, Muyan and Zhang, Qinglong and Zhu, Xizhou and Lu, Lewei and others},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={24185--24198},
  year={2024}
}