Eilev Blip2 Flan T5 Xl

🚀 Model Card for EILEV BLIP-2-Flan-T5-xl

This model is based on Salesforce/blip2-flan-t5-xl and trained using EILeV, enabling in-context learning for videos without large naturalistic video datasets.

🚀 Quick Start

Please check out the official repository: https://github.com/yukw777/EILEV

✨ Features

• In - context Learning: EILEV BLIP-2-Flan-T5-xl can perform in-context learning over videos and texts, which is optimized for egocentric video.
• Multiple Tasks: It can be applied to tasks like video-to-text, video-captioning, image-to-text, image-captioning, and visual-question-answering.

📚 Documentation

Model Details

Model Description

EILEV BLIP-2-Flan-T5-xl is a vision - language model (VLM) optimized for egocentric video. It can perform in-context learning over videos and texts. It was trained on Ego4D.

Model Sources

• Repository: https://github.com/yukw777/EILEV
• Paper: https://arxiv.org/abs/2311.17041
• Demo: https://2e09-141-212-106-177.ngrok-free.app

Bias, Risks, and Limitations

EILEV BLIP-2-OPT-2.7B uses off-the-shelf Flan-T5 as the language model. It inherits the same risks and limitations from Flan-T5:

⚠️ Important Note

Language models, including Flan-T5, can potentially be used for language generation in a harmful way, according to Rae et al. (2021). Flan-T5 should not be used directly in any application, without a prior assessment of safety and fairness concerns specific to the application.

EILEV BLIP-2-OPT-2.7B has not been tested in real world applications. It should not be directly deployed in any applications. Researchers should first carefully assess the safety and fairness of the model in relation to the specific context they’re being deployed within.

📄 License

This project is licensed under the MIT license.