---
license: cc-by-nc-4.0
language:
- en
pipeline_tag: image-text-to-text
---


# Model description

BLIP-3 consists of 3 models: a CLIP-like image encoder, a VL connector, and a large language model.

# Direct Use and Downstream Use


# Bias, Risks, Limitations, and Ethical Considerations

# How to use

> We require use the  development version (`"4.41.0.dev0"`) of the `transformers` library. To get it, as of 05/07/2024, one can use `pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers.`


# License

Our code and weights are released under the Creative Commons Attribution Non Commercial 4.0 [LICENSE](LICENSE.txt).

# Troubleshoot

1. If you missing any packages, please consider the followings

```
pip install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1 --index-url https://download.pytorch.org/whl/cu121
pip install open_clip_torch==2.24.0
pip install einops
pip install einops-exts
```