| # BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models | |
| Session by [johko](https://github.com/johko) | |
| ## Recording 📺 | |
| [YouTube](https://www.youtube.com/watch?v=k0DAtZCCl1w&pp=ygUdaHVnZ2luZyBmYWNlIHN0dWR5IGdyb3VwIHN3aW4%3D) | |
| ## Session Slides 🖥️ | |
| [Google Drive](https://docs.google.com/presentation/d/1Y_8Qu0CMlt7jvCd8Jw0c_ILh8LHB0XgnlrvXObe5FYs/edit?usp=sharing) | |
| ## Original Paper 📄 | |
| [Hugging Face](https://huggingface.co/papers/2301.12597) / | |
| [arxiv](https://arxiv.org/abs/2301.12597) | |
| ## GitHub Repo 🧑🏽💻 | |
| https://github.com/salesforce/lavis | |
| ## Additional Resources 📚 | |
| - [BLIP-2 Demo Space](https://huggingface.co/spaces/hysts/BLIP2-with-transformers) | |
| - [BLIP-2 Transformers Example Notebooks](https://github.com/NielsRogge/Transformers-Tutorials/tree/master/BLIP-2) by Niels Rogge | |
| - [BLIP-2 Transformers Docs](https://huggingface.co/docs/transformers/model_doc/blip-2) | |