🚀 InternViT-6B-448px-V1-0
InternViT-6B-448px-V1-0是一款圖像特徵提取模型,集成於InternVL-Chat-V1-1中。本次更新提升了圖像分辨率、OCR能力以及中文對話支持。
[📂 GitHub] [📜 InternVL 1.0] [📜 InternVL 1.5] [📜 Mini-InternVL] [📜 InternVL 2.5]
[🆕 Blog] [🗨️ Chat Demo] [🤗 HF Demo] [🚀 Quick Start] [📖 Documents]
我們發佈了InternViT-6B-448px-V1-0,該模型已集成到InternVL-Chat-V1-1中。在這次更新中,我們嘗試將分辨率提高到448x448,增強了光學字符識別(OCR)能力,並改進了對中文對話的支持。有關增強功能的示例,請參考鏈接。
📚 詳細文檔
模型詳情
屬性 |
詳情 |
模型類型 |
視覺基礎模型,特徵骨幹網絡 |
模型參數(M) |
5903 |
圖像尺寸 |
448 x 448 |
預訓練數據集 |
LAION-en、LAION-COCO、COYO、CC12M、CC3M、SBU、Wukong、LAION-multi、OCR相關數據集 |
⚠️ 重要提示
該模型有48個塊,我們發現使用倒數第四塊後的輸出對多模態大語言模型(MLLM)效果最佳。因此,在使用此模型構建MLLM時,請使用倒數第四層的特徵。
🚀 快速開始
⚠️ 重要提示
根據我們的經驗,InternViT V2.5系列更適合構建多模態大語言模型,而非傳統的計算機視覺任務。
基礎用法
import torch
from PIL import Image
from transformers import AutoModel, CLIPImageProcessor
model = AutoModel.from_pretrained(
'OpenGVLab/InternViT-6B-448px-V1-0',
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-6B-448px-V1-0')
pixel_values = image_processor(images=image, return_tensors='pt').pixel_values
pixel_values = pixel_values.to(torch.bfloat16).cuda()
outputs = model(pixel_values)
📄 許可證
本項目採用MIT許可證。
📖 引用
如果您在研究中發現本項目有用,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}
}