README.md

---
base_model:
- Qwen/Qwen2.5-1.5B-Instruct
- google/siglip-so400m-patch14-384
datasets:
- weizhiwang/Open-Qwen2VL-Data
- MAmmoTH-VL/MAmmoTH-VL-Instruct-12M
language:
- en
license: cc
pipeline_tag: image-text-to-text
---

# Model Card for Open-Qwen2VL

Open-Qwen2VL is a multimodal model that takes images and text as input and produces text as output.  This model is described in the paper [Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources](https://huggingface.co/papers/2504.00595).  The code is available at [https://github.com/Victorwz/Open-Qwen2VL](https://github.com/Victorwz/Open-Qwen2VL).

## Updates 
- [4/1/2025] The codebase, model, data, and paper are released.

<!-- ## Model Details -->

## How to Use

Please firstly install Open-Qwen2VL via
```
pip install git+https://github.com/Victorwz/Open-Qwen2VL.git#subdirectory=prismatic-vlms
```

You can load the model and perform inference as follows:
```python
import requests
import torch
from PIL import Image
from prismatic import load

device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")

# Load a pretrained VLM (either local path, or ID to auto-download from the HF Hub)
vlm = load("Open-Qwen2VL")
vlm.to(device, dtype=torch.bfloat16)

# Download an image and specify a prompt
image_url = "https://huggingface.co/adept/fuyu-8b/resolve/main/bus.png"
# image = Image.open(requests.get(image_url, stream=True).raw).convert("RGB")
image = [vlm.vision_backbone.image_transform(Image.open(requests.get(image_url, stream=True).raw).convert("RGB")).unsqueeze(0)]
user_prompt = '<image>' + '
' + "Describe the image."

# Generate!
generated_text = vlm.generate_batch(
    image,
    [user_prompt],
    do_sample=False,
    max_new_tokens=512,
    min_length=1,
)
print(generated_text[0])
```
The image caption results look like:
```
The image depicts a blue and orange bus parked on the side of a street. ...
```


## Citation
```bibtex
@article{Open-Qwen2VL,
    title={Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources},
    author={Wang, Weizhi and Tian, Yu and Yang, Linjie and Wang, Heng and Yan, Xifeng},
    journal={arXiv preprint arXiv:2504.00595},
    year={2025}
  }
...