Model Card for InternViT-6B-448px-V1-0

[InternVL 1.5 Technical Report] [Paper] [GitHub] [Chat Demo] [中文解读]

We release InternViT-6B-448px-V1-0, which is integrated into InternVL-Chat-V1-1. In this update, we explored increasing the resolution to 448x448, enhancing Optical Character Recognition (OCR) capabilities, and improving support for Chinese conversations. For examples of the enhanced capabilities, please refer to the LINK.

Model Details

• Model Type: vision foundation model, feature backbone
• Model Stats:
  • Params (M): 5903
  • Image size: 448 x 448
• Pretrain Dataset: LAION-en, LAION-COCO, COYO, CC12M, CC3M, SBU, Wukong, LAION-multi, OCR-related datasets.
• Note: This model has 48 blocks, and we found that using the output after the fourth-to-last block worked best for MLLM. Therefore, when building a MLLM with this model, please use the features from the fourth-to-last layer.

Released Models

Vision Foundation model

Model	Date	Download	Note
InternViT-6B-448px-V1.5	2024.04.20	🤗 HF link	support dynamic resolution, super strong OCR (🔥new)
InternViT-6B-448px-V1.2	2024.02.11	🤗 HF link	448 resolution
InternViT-6B-448px-V1.0	2024.01.30	🤗 HF link	448 resolution
InternViT-6B-224px	2023.12.22	🤗 HF link	vision foundation model
InternVL-14B-224px	2023.12.22	🤗 HF link	vision-language foundation model

Multimodal Large Language Model (MLLM)

Model	Date	Download	Note
InternVL-Chat-V1.5	2024.04.18	🤗 HF link	support 4K image; super strong OCR; Approaching the performance of GPT-4V and Gemini Pro on various benchmarks like MMMU, DocVQA, ChartQA, MathVista, etc. (🔥new)
InternVL-Chat-V1.2-Plus	2024.02.21	🤗 HF link	more SFT data and stronger
InternVL-Chat-V1.2	2024.02.11	🤗 HF link	scaling up LLM to 34B
InternVL-Chat-V1.1	2024.01.24	🤗 HF link	support Chinese and stronger OCR

Model Usage (Image Embeddings)

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)

Citation

If you find this project useful in your research, please consider citing:

@article{chen2023internvl,
  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 Li, Bin and Luo, Ping and Lu, Tong and Qiao, Yu and Dai, Jifeng},
  journal={arXiv preprint arXiv:2312.14238},
  year={2023}
}

Acknowledgement

InternVL is built with reference to the code of the following projects: OpenAI CLIP, Open CLIP, CLIP Benchmark, EVA, InternImage, ViT-Adapter, MMSegmentation, Transformers, DINOv2, BLIP-2, Qwen-VL, and LLaVA-1.5. Thanks for their awesome work!