---
title: mlcd-vit-bigG-patch14-224
canonical_url: "https://www.modelscope.cn/models/deepglint/mlcd-vit-bigG-patch14-224"
md_url: "https://www.modelscope.cn/models/deepglint/mlcd-vit-bigG-patch14-224.md"
repository: deepglint/mlcd-vit-bigG-patch14-224
last_updated: 2026-01-19
license: mit
model_type:
  - mlcd
architectures:
  - MLCDVisionModel
parameters: 602.7M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 53
stars: 0
---

# mlcd-vit-bigG-patch14-224

> mlcd-vit-bigG-patch14-224 - deepglint 在 ModelScope 开源的模型。

deepglint/mlcd-vit-bigG-patch14-224 是 ModelScope 魔搭社区上的 602.7M 参数机器学习模型，采用 mit 许可。

- **Repository**: deepglint/mlcd-vit-bigG-patch14-224
- **License**: mit
- **Parameters**: 602.7M
- **Downloads**: 53
- **Stars**: 0
- **Last updated**: 2026-01-19

Source: https://www.modelscope.cn/models/deepglint/mlcd-vit-bigG-patch14-224

---

```shell
git clone https://github.com/deepglint/unicom
cd unicom/mlcd

python
>>> from vit_rope2d_hf import MLCDVisionModel
>>> model = MLCDVisionModel.from_pretrained("DeepGlint-AI/mlcd-vit-bigG-patch14-224")

```



## Citation


```latex
@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}
}
```