Mlcd Vit Bigg Patch14 448

🚀 MLCD-ViT-bigG Model Card

MLCD-ViT-bigG is a cutting - edge vision transformer model that leverages 2D Rotary Position Embedding (RoPE2D) to excel in document understanding and visual question - answering tasks.

⚠️ Important Note

LLaVA-NeXT and transformers now supports MLCD-ViT-bigG-14-448px.

💡 Usage Tip

We adopted the official LLaVA-NeXT and the official training dataset LLaVA-NeXT-Data for evaluating the foundational visual models. The language model is Qwen2.5-7B.

MLCD-ViT-bigG is a state-of-the-art vision transformer model enhanced with 2D Rotary Position Embedding (RoPE2D), achieving superior performance on document understanding and visual question answering tasks. Developed by DeepGlint AI, this model demonstrates exceptional capabilities in processing complex visual-language interactions.

Performance Comparison

📦 Installation

pip install torch transformers
git clone https://github.com/deepglint/unicom
cd unicom/mlcd

💻 Usage Examples

Basic Usage

from vit_rope2d_hf import MLCDVisionModel
from transformers import CLIPImageProcessor
from PIL import Image
import requests
import torch

# Load model and processor
model = MLCDVisionModel.from_pretrained("DeepGlint-AI/mlcd-vit-bigG-patch14-448")
processor = CLIPImageProcessor.from_pretrained("DeepGlint-AI/mlcd-vit-bigG-patch14-448")

# Process single image
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(images=image, return_tensors="pt")

# Get visual features
with torch.no_grad():
    outputs = model(**inputs)
features = outputs.last_hidden_state

print(f"Extracted features shape: {features.shape}")

📄 License

This project is licensed under the MIT License.

📚 Citation

@inproceedings{anxiang_2024_mlcd,
  title={Multi-label Cluster Discrimination for Visual Representation Learning},
  author={An, Xiang and Yang, Kaicheng and Dai, Xiangzi and Feng, Ziyong and Deng, Jiankang},
  booktitle={ECCV},
  year={2024}
}