README.md

---
base_model:
- facebook/dinov2-large
license: apache-2.0
pipeline_tag: image-feature-extraction
library_name: transformers
---

# Model Card for CoMP-MM-1B

<!-- Provide a quick summary of what the model is/does. -->
This is an VFM that supports <b>native image resolution inputs</b>, continually pre-trained from [DINOv2](https://huggingface.co/facebook/dinov2-large).

## Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/SliMM-X/CoMP-MM
- **Paper:** https://arxiv.org/abs/2503.18931
- **Project Page:** https://slimm-x.github.io/comp

## How to Get Started with the Model

Install the github repo, and use the code below to get started with the model.

```python
import torch
from slimm.model.processor import SliMMQwen2VLProcessor
from slimm.model.utils_vl import process_vision_info
from slimm.model.vision_encoder import CoMPDinov2Model
from PIL import Image

model_path = "SliMM-X/CoMP-DINOv2-Large"

model = CoMPDinov2Model.from_pretrained(
    model_path, torch_dtype="auto", device_map="cuda", w_merger=False
).to(torch.bfloat16)

processor = SliMMQwen2VLProcessor.from_pretrained(model_path)

image_input = Image.open("https://slimm-x.github.io/comp/figs/teaser.png")
inputs = processor(
    images=image_input,
    return_tensors="pt",
)

inputs = inputs.to("cuda")
output_feat = model(inputs.pixel_values.to(torch.bfloat16), inputs.image_grid_thw)
print(output_feat)
```

## Citation

**BibTeX:**

```bibtex
@article{comp2025,
      title={CoMP: Continual Multimodal Pre-training for Vision Foundation Models}, 
      author={Chen, Yitong and Meng, Lingchen and Peng, Wujian and Wu, Zuxuan and Jiang, Yu-Gang},
      year={2025},
      journal={arXiv preprint arXiv:2503.18931}, 
}
```